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 08:25:39.280381: step: 4/530, loss: 3.8247714042663574
2023-01-21 08:25:40.402680: step: 8/530, loss: 23.67460060119629
2023-01-21 08:25:41.529597: step: 12/530, loss: 7.792829990386963
2023-01-21 08:25:42.663290: step: 16/530, loss: 4.223147869110107
2023-01-21 08:25:43.754061: step: 20/530, loss: 2.8740739822387695
2023-01-21 08:25:44.846486: step: 24/530, loss: 3.734103202819824
2023-01-21 08:25:45.946954: step: 28/530, loss: 12.453813552856445
2023-01-21 08:25:47.056854: step: 32/530, loss: 14.550145149230957
2023-01-21 08:25:48.161081: step: 36/530, loss: 11.228058815002441
2023-01-21 08:25:49.243366: step: 40/530, loss: 5.496736526489258
2023-01-21 08:25:50.358054: step: 44/530, loss: 4.227232933044434
2023-01-21 08:25:51.486801: step: 48/530, loss: 16.84233283996582
2023-01-21 08:25:52.614766: step: 52/530, loss: 5.055027961730957
2023-01-21 08:25:53.718249: step: 56/530, loss: 3.682136058807373
2023-01-21 08:25:54.853969: step: 60/530, loss: 3.2572784423828125
2023-01-21 08:25:55.975075: step: 64/530, loss: 23.948823928833008
2023-01-21 08:25:57.095110: step: 68/530, loss: 20.843276977539062
2023-01-21 08:25:58.190844: step: 72/530, loss: 4.5136613845825195
2023-01-21 08:25:59.283905: step: 76/530, loss: 2.308722496032715
2023-01-21 08:26:00.390070: step: 80/530, loss: 2.8275487422943115
2023-01-21 08:26:01.519825: step: 84/530, loss: 2.968357563018799
2023-01-21 08:26:02.635709: step: 88/530, loss: 11.509078979492188
2023-01-21 08:26:03.737336: step: 92/530, loss: 3.8847250938415527
2023-01-21 08:26:04.862360: step: 96/530, loss: 9.048340797424316
2023-01-21 08:26:05.950437: step: 100/530, loss: 2.91939640045166
2023-01-21 08:26:07.062842: step: 104/530, loss: 14.225627899169922
2023-01-21 08:26:08.193079: step: 108/530, loss: 14.548890113830566
2023-01-21 08:26:09.296316: step: 112/530, loss: 3.8967552185058594
2023-01-21 08:26:10.398673: step: 116/530, loss: 3.956684112548828
2023-01-21 08:26:11.498816: step: 120/530, loss: 15.386672973632812
2023-01-21 08:26:12.645446: step: 124/530, loss: 2.935511589050293
2023-01-21 08:26:13.737898: step: 128/530, loss: 18.256500244140625
2023-01-21 08:26:14.841113: step: 132/530, loss: 17.10557746887207
2023-01-21 08:26:15.939368: step: 136/530, loss: 15.099573135375977
2023-01-21 08:26:17.056189: step: 140/530, loss: 13.445436477661133
2023-01-21 08:26:18.146669: step: 144/530, loss: 7.539018630981445
2023-01-21 08:26:19.277339: step: 148/530, loss: 4.33933162689209
2023-01-21 08:26:20.399074: step: 152/530, loss: 3.9608230590820312
2023-01-21 08:26:21.521696: step: 156/530, loss: 18.758262634277344
2023-01-21 08:26:22.628608: step: 160/530, loss: 8.985645294189453
2023-01-21 08:26:23.737749: step: 164/530, loss: 2.8852083683013916
2023-01-21 08:26:24.841694: step: 168/530, loss: 11.083765983581543
2023-01-21 08:26:25.956282: step: 172/530, loss: 43.80861282348633
2023-01-21 08:26:27.050205: step: 176/530, loss: 11.351310729980469
2023-01-21 08:26:28.156704: step: 180/530, loss: 4.1110429763793945
2023-01-21 08:26:29.264026: step: 184/530, loss: 32.73598098754883
2023-01-21 08:26:30.385299: step: 188/530, loss: 4.337249279022217
2023-01-21 08:26:31.488568: step: 192/530, loss: 3.4171199798583984
2023-01-21 08:26:32.583180: step: 196/530, loss: 2.5224828720092773
2023-01-21 08:26:33.683466: step: 200/530, loss: 20.38568878173828
2023-01-21 08:26:34.802077: step: 204/530, loss: 26.72294044494629
2023-01-21 08:26:35.920165: step: 208/530, loss: 19.891393661499023
2023-01-21 08:26:37.054311: step: 212/530, loss: 30.0582275390625
2023-01-21 08:26:38.173286: step: 216/530, loss: 19.12263298034668
2023-01-21 08:26:39.295872: step: 220/530, loss: 6.009547710418701
2023-01-21 08:26:40.414375: step: 224/530, loss: 11.162466049194336
2023-01-21 08:26:41.536088: step: 228/530, loss: 4.6891913414001465
2023-01-21 08:26:42.625985: step: 232/530, loss: 2.2201602458953857
2023-01-21 08:26:43.754019: step: 236/530, loss: 7.960633277893066
2023-01-21 08:26:44.838466: step: 240/530, loss: 11.456367492675781
2023-01-21 08:26:45.932106: step: 244/530, loss: 14.501708984375
2023-01-21 08:26:47.055538: step: 248/530, loss: 3.6611335277557373
2023-01-21 08:26:48.124333: step: 252/530, loss: 2.475947380065918
2023-01-21 08:26:49.215466: step: 256/530, loss: 3.2388885021209717
2023-01-21 08:26:50.349068: step: 260/530, loss: 27.763608932495117
2023-01-21 08:26:51.456852: step: 264/530, loss: 18.940582275390625
2023-01-21 08:26:52.566150: step: 268/530, loss: 3.1587743759155273
2023-01-21 08:26:53.706040: step: 272/530, loss: 3.3968143463134766
2023-01-21 08:26:54.810385: step: 276/530, loss: 3.409374713897705
2023-01-21 08:26:55.927136: step: 280/530, loss: 2.417004108428955
2023-01-21 08:26:57.024828: step: 284/530, loss: 16.142274856567383
2023-01-21 08:26:58.127187: step: 288/530, loss: 3.892843246459961
2023-01-21 08:26:59.247813: step: 292/530, loss: 33.742530822753906
2023-01-21 08:27:00.348157: step: 296/530, loss: 2.62148380279541
2023-01-21 08:27:01.462695: step: 300/530, loss: 3.6804006099700928
2023-01-21 08:27:02.564255: step: 304/530, loss: 15.33167839050293
2023-01-21 08:27:03.682212: step: 308/530, loss: 10.790513038635254
2023-01-21 08:27:04.807235: step: 312/530, loss: 26.385334014892578
2023-01-21 08:27:05.922171: step: 316/530, loss: 3.1453404426574707
2023-01-21 08:27:07.038817: step: 320/530, loss: 12.452153205871582
2023-01-21 08:27:08.166110: step: 324/530, loss: 7.401740074157715
2023-01-21 08:27:09.273050: step: 328/530, loss: 3.147793769836426
2023-01-21 08:27:10.387799: step: 332/530, loss: 2.480666399002075
2023-01-21 08:27:11.499513: step: 336/530, loss: 23.008018493652344
2023-01-21 08:27:12.621065: step: 340/530, loss: 3.5525450706481934
2023-01-21 08:27:13.737071: step: 344/530, loss: 7.9330573081970215
2023-01-21 08:27:14.856346: step: 348/530, loss: 16.135713577270508
2023-01-21 08:27:15.983536: step: 352/530, loss: 23.471017837524414
2023-01-21 08:27:17.081954: step: 356/530, loss: 3.0813751220703125
2023-01-21 08:27:18.194110: step: 360/530, loss: 11.863367080688477
2023-01-21 08:27:19.311192: step: 364/530, loss: 10.527448654174805
2023-01-21 08:27:20.443182: step: 368/530, loss: 3.463357925415039
2023-01-21 08:27:21.569192: step: 372/530, loss: 2.7780189514160156
2023-01-21 08:27:22.665484: step: 376/530, loss: 14.865715980529785
2023-01-21 08:27:23.784348: step: 380/530, loss: 10.684891700744629
2023-01-21 08:27:24.870880: step: 384/530, loss: 7.3157548904418945
2023-01-21 08:27:25.960340: step: 388/530, loss: 2.45033597946167
2023-01-21 08:27:27.080467: step: 392/530, loss: 11.809349060058594
2023-01-21 08:27:28.215870: step: 396/530, loss: 42.17725372314453
2023-01-21 08:27:29.366790: step: 400/530, loss: 3.670440912246704
2023-01-21 08:27:30.469198: step: 404/530, loss: 18.743728637695312
2023-01-21 08:27:31.598910: step: 408/530, loss: 10.496770858764648
2023-01-21 08:27:32.712919: step: 412/530, loss: 8.040962219238281
2023-01-21 08:27:33.821643: step: 416/530, loss: 8.307551383972168
2023-01-21 08:27:34.916297: step: 420/530, loss: 2.8908748626708984
2023-01-21 08:27:36.012934: step: 424/530, loss: 2.5674121379852295
2023-01-21 08:27:37.125376: step: 428/530, loss: 6.737289905548096
2023-01-21 08:27:38.234325: step: 432/530, loss: 3.182615280151367
2023-01-21 08:27:39.376835: step: 436/530, loss: 2.5280990600585938
2023-01-21 08:27:40.458870: step: 440/530, loss: 0.8647371530532837
2023-01-21 08:27:41.573148: step: 444/530, loss: 3.473031997680664
2023-01-21 08:27:42.679875: step: 448/530, loss: 19.18760108947754
2023-01-21 08:27:43.834136: step: 452/530, loss: 21.098207473754883
2023-01-21 08:27:44.948644: step: 456/530, loss: 8.163414001464844
2023-01-21 08:27:46.049141: step: 460/530, loss: 2.3193511962890625
2023-01-21 08:27:47.183079: step: 464/530, loss: 13.555221557617188
2023-01-21 08:27:48.281381: step: 468/530, loss: 5.614279747009277
2023-01-21 08:27:49.405847: step: 472/530, loss: 0.9741687774658203
2023-01-21 08:27:50.535142: step: 476/530, loss: 10.289423942565918
2023-01-21 08:27:51.626089: step: 480/530, loss: 2.3159141540527344
2023-01-21 08:27:52.788150: step: 484/530, loss: 22.161727905273438
2023-01-21 08:27:53.877070: step: 488/530, loss: 6.443577289581299
2023-01-21 08:27:54.979196: step: 492/530, loss: 8.419048309326172
2023-01-21 08:27:56.068976: step: 496/530, loss: 14.569345474243164
2023-01-21 08:27:57.172677: step: 500/530, loss: 4.437444686889648
2023-01-21 08:27:58.301145: step: 504/530, loss: 9.023085594177246
2023-01-21 08:27:59.400026: step: 508/530, loss: 1.7570666074752808
2023-01-21 08:28:00.528208: step: 512/530, loss: 1.242442011833191
2023-01-21 08:28:01.632671: step: 516/530, loss: 2.1309428215026855
2023-01-21 08:28:02.804051: step: 520/530, loss: 11.416577339172363
2023-01-21 08:28:03.940814: step: 524/530, loss: 1.3897480964660645
2023-01-21 08:28:05.044037: step: 528/530, loss: 0.7908315658569336
2023-01-21 08:28:06.126825: step: 532/530, loss: 5.504734992980957
2023-01-21 08:28:07.245242: step: 536/530, loss: 7.440115451812744
2023-01-21 08:28:08.329019: step: 540/530, loss: 5.421571731567383
2023-01-21 08:28:09.454975: step: 544/530, loss: 1.9857515096664429
2023-01-21 08:28:10.559612: step: 548/530, loss: 5.138154983520508
2023-01-21 08:28:11.672229: step: 552/530, loss: 7.50291109085083
2023-01-21 08:28:12.793162: step: 556/530, loss: 5.5284423828125
2023-01-21 08:28:13.898335: step: 560/530, loss: 0.5684511661529541
2023-01-21 08:28:15.034827: step: 564/530, loss: 1.676917552947998
2023-01-21 08:28:16.159560: step: 568/530, loss: 3.98514986038208
2023-01-21 08:28:17.254024: step: 572/530, loss: 3.480156183242798
2023-01-21 08:28:18.378159: step: 576/530, loss: 1.4299927949905396
2023-01-21 08:28:19.477671: step: 580/530, loss: 1.1517208814620972
2023-01-21 08:28:20.612141: step: 584/530, loss: 1.609199047088623
2023-01-21 08:28:21.730624: step: 588/530, loss: 4.33005428314209
2023-01-21 08:28:22.785420: step: 592/530, loss: 1.8189414739608765
2023-01-21 08:28:23.902014: step: 596/530, loss: 1.275876760482788
2023-01-21 08:28:25.061961: step: 600/530, loss: 1.5633254051208496
2023-01-21 08:28:26.173470: step: 604/530, loss: 1.5762386322021484
2023-01-21 08:28:27.287541: step: 608/530, loss: 1.553145170211792
2023-01-21 08:28:28.382321: step: 612/530, loss: 0.8412739038467407
2023-01-21 08:28:29.480054: step: 616/530, loss: 12.081649780273438
2023-01-21 08:28:30.581608: step: 620/530, loss: 2.5497283935546875
2023-01-21 08:28:31.685366: step: 624/530, loss: 1.0212419033050537
2023-01-21 08:28:32.795889: step: 628/530, loss: 1.2420941591262817
2023-01-21 08:28:33.941058: step: 632/530, loss: 2.6803927421569824
2023-01-21 08:28:35.044608: step: 636/530, loss: 1.0779914855957031
2023-01-21 08:28:36.125115: step: 640/530, loss: 2.8131189346313477
2023-01-21 08:28:37.246712: step: 644/530, loss: 0.6291118860244751
2023-01-21 08:28:38.341823: step: 648/530, loss: 0.5420863628387451
2023-01-21 08:28:39.454933: step: 652/530, loss: 1.374135136604309
2023-01-21 08:28:40.560244: step: 656/530, loss: 1.1891915798187256
2023-01-21 08:28:41.662689: step: 660/530, loss: 1.52848482131958
2023-01-21 08:28:42.758786: step: 664/530, loss: 0.4244338870048523
2023-01-21 08:28:43.881215: step: 668/530, loss: 2.2306554317474365
2023-01-21 08:28:44.976298: step: 672/530, loss: 1.2155712842941284
2023-01-21 08:28:46.102962: step: 676/530, loss: 5.540233612060547
2023-01-21 08:28:47.204267: step: 680/530, loss: 2.3425376415252686
2023-01-21 08:28:48.323229: step: 684/530, loss: 4.238117218017578
2023-01-21 08:28:49.421769: step: 688/530, loss: 3.1852188110351562
2023-01-21 08:28:50.512987: step: 692/530, loss: 1.182296633720398
2023-01-21 08:28:51.626512: step: 696/530, loss: 0.5667551159858704
2023-01-21 08:28:52.781689: step: 700/530, loss: 0.7019741535186768
2023-01-21 08:28:53.883025: step: 704/530, loss: 2.8834035396575928
2023-01-21 08:28:54.989851: step: 708/530, loss: 0.7900824546813965
2023-01-21 08:28:56.113299: step: 712/530, loss: 0.6206392049789429
2023-01-21 08:28:57.232822: step: 716/530, loss: 0.850639283657074
2023-01-21 08:28:58.339358: step: 720/530, loss: 1.5720481872558594
2023-01-21 08:28:59.440747: step: 724/530, loss: 1.7020812034606934
2023-01-21 08:29:00.552073: step: 728/530, loss: 2.5883989334106445
2023-01-21 08:29:01.652023: step: 732/530, loss: 0.4605291485786438
2023-01-21 08:29:02.777693: step: 736/530, loss: 2.860867500305176
2023-01-21 08:29:03.922685: step: 740/530, loss: 0.6037940979003906
2023-01-21 08:29:05.055156: step: 744/530, loss: 0.5121645331382751
2023-01-21 08:29:06.148974: step: 748/530, loss: 0.8227473497390747
2023-01-21 08:29:07.274105: step: 752/530, loss: 1.8856215476989746
2023-01-21 08:29:08.396562: step: 756/530, loss: 3.2209324836730957
2023-01-21 08:29:09.528120: step: 760/530, loss: 1.5242799520492554
2023-01-21 08:29:10.646618: step: 764/530, loss: 1.6156655550003052
2023-01-21 08:29:11.822052: step: 768/530, loss: 7.142295837402344
2023-01-21 08:29:12.929140: step: 772/530, loss: 2.956252098083496
2023-01-21 08:29:14.015743: step: 776/530, loss: 2.57435941696167
2023-01-21 08:29:15.096598: step: 780/530, loss: 2.185138702392578
2023-01-21 08:29:16.201516: step: 784/530, loss: 1.475036382675171
2023-01-21 08:29:17.305714: step: 788/530, loss: 3.275002956390381
2023-01-21 08:29:18.398445: step: 792/530, loss: 0.53302001953125
2023-01-21 08:29:19.528783: step: 796/530, loss: 1.1679275035858154
2023-01-21 08:29:20.640676: step: 800/530, loss: 1.7728608846664429
2023-01-21 08:29:21.747201: step: 804/530, loss: 1.7904905080795288
2023-01-21 08:29:22.869150: step: 808/530, loss: 0.435213565826416
2023-01-21 08:29:23.990255: step: 812/530, loss: 1.6923174858093262
2023-01-21 08:29:25.097356: step: 816/530, loss: 1.0787800550460815
2023-01-21 08:29:26.205909: step: 820/530, loss: 1.5630905628204346
2023-01-21 08:29:27.299675: step: 824/530, loss: 1.8154237270355225
2023-01-21 08:29:28.415874: step: 828/530, loss: 1.0555299520492554
2023-01-21 08:29:29.523458: step: 832/530, loss: 0.30740228295326233
2023-01-21 08:29:30.677908: step: 836/530, loss: 1.428336501121521
2023-01-21 08:29:31.782121: step: 840/530, loss: 0.840860903263092
2023-01-21 08:29:32.880968: step: 844/530, loss: 1.2396767139434814
2023-01-21 08:29:34.010187: step: 848/530, loss: 3.9791877269744873
2023-01-21 08:29:35.106641: step: 852/530, loss: 0.35215941071510315
2023-01-21 08:29:36.214578: step: 856/530, loss: 0.6679888963699341
2023-01-21 08:29:37.319975: step: 860/530, loss: 0.9668667912483215
2023-01-21 08:29:38.450502: step: 864/530, loss: 1.4698896408081055
2023-01-21 08:29:39.532888: step: 868/530, loss: 0.9979019165039062
2023-01-21 08:29:40.653913: step: 872/530, loss: 1.2002317905426025
2023-01-21 08:29:41.755297: step: 876/530, loss: 1.027078628540039
2023-01-21 08:29:42.903640: step: 880/530, loss: 0.4487758278846741
2023-01-21 08:29:44.040459: step: 884/530, loss: 0.6453434228897095
2023-01-21 08:29:45.167475: step: 888/530, loss: 2.2120256423950195
2023-01-21 08:29:46.261863: step: 892/530, loss: 0.8503849506378174
2023-01-21 08:29:47.355077: step: 896/530, loss: 0.8715493679046631
2023-01-21 08:29:48.455312: step: 900/530, loss: 1.0814640522003174
2023-01-21 08:29:49.602584: step: 904/530, loss: 1.3172224760055542
2023-01-21 08:29:50.700665: step: 908/530, loss: 1.3666542768478394
2023-01-21 08:29:51.800285: step: 912/530, loss: 0.5948504209518433
2023-01-21 08:29:52.922846: step: 916/530, loss: 0.663577675819397
2023-01-21 08:29:54.019721: step: 920/530, loss: 1.9897325038909912
2023-01-21 08:29:55.132871: step: 924/530, loss: 3.843177318572998
2023-01-21 08:29:56.242690: step: 928/530, loss: 0.59805828332901
2023-01-21 08:29:57.350156: step: 932/530, loss: 1.1364173889160156
2023-01-21 08:29:58.473111: step: 936/530, loss: 0.4614202380180359
2023-01-21 08:29:59.584963: step: 940/530, loss: 0.9006638526916504
2023-01-21 08:30:00.678635: step: 944/530, loss: 0.7295122146606445
2023-01-21 08:30:01.771198: step: 948/530, loss: 0.6285088658332825
2023-01-21 08:30:02.884305: step: 952/530, loss: 3.0079128742218018
2023-01-21 08:30:03.989027: step: 956/530, loss: 2.412795305252075
2023-01-21 08:30:05.073084: step: 960/530, loss: 1.062082052230835
2023-01-21 08:30:06.197289: step: 964/530, loss: 7.645524501800537
2023-01-21 08:30:07.285873: step: 968/530, loss: 1.0616767406463623
2023-01-21 08:30:08.420234: step: 972/530, loss: 0.529765248298645
2023-01-21 08:30:09.606729: step: 976/530, loss: 1.302058458328247
2023-01-21 08:30:10.715111: step: 980/530, loss: 0.21375632286071777
2023-01-21 08:30:11.822185: step: 984/530, loss: 0.5772824287414551
2023-01-21 08:30:12.932466: step: 988/530, loss: 1.480478286743164
2023-01-21 08:30:14.062988: step: 992/530, loss: 0.9834421873092651
2023-01-21 08:30:15.165686: step: 996/530, loss: 0.579673707485199
2023-01-21 08:30:16.261280: step: 1000/530, loss: 0.3045511841773987
2023-01-21 08:30:17.375428: step: 1004/530, loss: 0.25266918540000916
2023-01-21 08:30:18.509009: step: 1008/530, loss: 10.320324897766113
2023-01-21 08:30:19.607190: step: 1012/530, loss: 3.3231372833251953
2023-01-21 08:30:20.701694: step: 1016/530, loss: 0.40265029668807983
2023-01-21 08:30:21.787257: step: 1020/530, loss: 2.4831089973449707
2023-01-21 08:30:22.904617: step: 1024/530, loss: 1.7501744031906128
2023-01-21 08:30:23.995584: step: 1028/530, loss: 3.6602187156677246
2023-01-21 08:30:25.115364: step: 1032/530, loss: 0.7583255767822266
2023-01-21 08:30:26.235271: step: 1036/530, loss: 3.5173087120056152
2023-01-21 08:30:27.322274: step: 1040/530, loss: 0.5259652137756348
2023-01-21 08:30:28.413970: step: 1044/530, loss: 0.4828094244003296
2023-01-21 08:30:29.509761: step: 1048/530, loss: 2.1581530570983887
2023-01-21 08:30:30.628400: step: 1052/530, loss: 1.682107925415039
2023-01-21 08:30:31.757746: step: 1056/530, loss: 5.119508266448975
2023-01-21 08:30:32.879113: step: 1060/530, loss: 1.1785764694213867
2023-01-21 08:30:33.982468: step: 1064/530, loss: 3.040731906890869
2023-01-21 08:30:35.094419: step: 1068/530, loss: 1.6753065586090088
2023-01-21 08:30:36.187050: step: 1072/530, loss: 1.3754546642303467
2023-01-21 08:30:37.297253: step: 1076/530, loss: 0.8640093803405762
2023-01-21 08:30:38.465707: step: 1080/530, loss: 2.893430471420288
2023-01-21 08:30:39.560020: step: 1084/530, loss: 0.7830283045768738
2023-01-21 08:30:40.656496: step: 1088/530, loss: 2.3461999893188477
2023-01-21 08:30:41.758518: step: 1092/530, loss: 3.523620128631592
2023-01-21 08:30:42.870368: step: 1096/530, loss: 1.7385973930358887
2023-01-21 08:30:43.994237: step: 1100/530, loss: 1.2825385332107544
2023-01-21 08:30:45.173461: step: 1104/530, loss: 0.9041227698326111
2023-01-21 08:30:46.283902: step: 1108/530, loss: 1.1137878894805908
2023-01-21 08:30:47.410068: step: 1112/530, loss: 1.480239748954773
2023-01-21 08:30:48.507508: step: 1116/530, loss: 2.263979434967041
2023-01-21 08:30:49.582267: step: 1120/530, loss: 0.2563742697238922
2023-01-21 08:30:50.690135: step: 1124/530, loss: 1.25351083278656
2023-01-21 08:30:51.814467: step: 1128/530, loss: 0.672776997089386
2023-01-21 08:30:52.902324: step: 1132/530, loss: 0.7901431322097778
2023-01-21 08:30:54.011207: step: 1136/530, loss: 0.9601890444755554
2023-01-21 08:30:55.117534: step: 1140/530, loss: 0.2271064817905426
2023-01-21 08:30:56.228418: step: 1144/530, loss: 0.5148394107818604
2023-01-21 08:30:57.328364: step: 1148/530, loss: 0.6287330389022827
2023-01-21 08:30:58.455825: step: 1152/530, loss: 0.09950122982263565
2023-01-21 08:30:59.585681: step: 1156/530, loss: 1.6398297548294067
2023-01-21 08:31:00.700950: step: 1160/530, loss: 1.1630470752716064
2023-01-21 08:31:01.821493: step: 1164/530, loss: 2.411144733428955
2023-01-21 08:31:02.933599: step: 1168/530, loss: 0.42353355884552
2023-01-21 08:31:04.054005: step: 1172/530, loss: 0.9469929933547974
2023-01-21 08:31:05.179616: step: 1176/530, loss: 0.553544282913208
2023-01-21 08:31:06.301791: step: 1180/530, loss: 1.738619327545166
2023-01-21 08:31:07.400400: step: 1184/530, loss: 0.6206778883934021
2023-01-21 08:31:08.499106: step: 1188/530, loss: 0.3105440139770508
2023-01-21 08:31:09.634011: step: 1192/530, loss: 2.693908929824829
2023-01-21 08:31:10.717925: step: 1196/530, loss: 1.777593731880188
2023-01-21 08:31:11.804010: step: 1200/530, loss: 0.8583033084869385
2023-01-21 08:31:12.891218: step: 1204/530, loss: 2.3872568607330322
2023-01-21 08:31:13.991467: step: 1208/530, loss: 0.8927949666976929
2023-01-21 08:31:15.107298: step: 1212/530, loss: 3.0335655212402344
2023-01-21 08:31:16.218374: step: 1216/530, loss: 0.5857503414154053
2023-01-21 08:31:17.364315: step: 1220/530, loss: 0.6111335754394531
2023-01-21 08:31:18.435276: step: 1224/530, loss: 1.4603767395019531
2023-01-21 08:31:19.545228: step: 1228/530, loss: 1.1542656421661377
2023-01-21 08:31:20.663380: step: 1232/530, loss: 1.0547513961791992
2023-01-21 08:31:21.798489: step: 1236/530, loss: 0.9050506353378296
2023-01-21 08:31:22.905704: step: 1240/530, loss: 0.29006433486938477
2023-01-21 08:31:24.006376: step: 1244/530, loss: 0.9352859258651733
2023-01-21 08:31:25.134349: step: 1248/530, loss: 3.6817405223846436
2023-01-21 08:31:26.286116: step: 1252/530, loss: 1.9098585844039917
2023-01-21 08:31:27.397079: step: 1256/530, loss: 0.15108633041381836
2023-01-21 08:31:28.541180: step: 1260/530, loss: 0.7575054168701172
2023-01-21 08:31:29.667259: step: 1264/530, loss: 1.0700103044509888
2023-01-21 08:31:30.788947: step: 1268/530, loss: 0.9888304471969604
2023-01-21 08:31:31.919937: step: 1272/530, loss: 1.375380277633667
2023-01-21 08:31:33.027633: step: 1276/530, loss: 0.4859444499015808
2023-01-21 08:31:34.107126: step: 1280/530, loss: 1.3718180656433105
2023-01-21 08:31:35.194015: step: 1284/530, loss: 0.1925945281982422
2023-01-21 08:31:36.304713: step: 1288/530, loss: 3.917142868041992
2023-01-21 08:31:37.408825: step: 1292/530, loss: 1.2278058528900146
2023-01-21 08:31:38.511660: step: 1296/530, loss: 0.9864823222160339
2023-01-21 08:31:39.636423: step: 1300/530, loss: 1.3247333765029907
2023-01-21 08:31:40.731355: step: 1304/530, loss: 8.950865745544434
2023-01-21 08:31:41.841472: step: 1308/530, loss: 2.6282296180725098
2023-01-21 08:31:42.966530: step: 1312/530, loss: 1.0457541942596436
2023-01-21 08:31:44.055810: step: 1316/530, loss: 0.9159600734710693
2023-01-21 08:31:45.149108: step: 1320/530, loss: 0.482572078704834
2023-01-21 08:31:46.261085: step: 1324/530, loss: 0.6768025159835815
2023-01-21 08:31:47.387616: step: 1328/530, loss: 0.4802801012992859
2023-01-21 08:31:48.478531: step: 1332/530, loss: 1.5758532285690308
2023-01-21 08:31:49.580897: step: 1336/530, loss: 1.118682622909546
2023-01-21 08:31:50.667638: step: 1340/530, loss: 0.3925798237323761
2023-01-21 08:31:51.780312: step: 1344/530, loss: 0.8370621800422668
2023-01-21 08:31:52.867810: step: 1348/530, loss: 0.3212825357913971
2023-01-21 08:31:54.007694: step: 1352/530, loss: 1.6958136558532715
2023-01-21 08:31:55.134255: step: 1356/530, loss: 2.019230842590332
2023-01-21 08:31:56.272190: step: 1360/530, loss: 0.8408951163291931
2023-01-21 08:31:57.373097: step: 1364/530, loss: 0.3634986877441406
2023-01-21 08:31:58.485409: step: 1368/530, loss: 0.67097407579422
2023-01-21 08:31:59.589205: step: 1372/530, loss: 1.2005330324172974
2023-01-21 08:32:00.667523: step: 1376/530, loss: 2.2117621898651123
2023-01-21 08:32:01.749997: step: 1380/530, loss: 1.6814545392990112
2023-01-21 08:32:02.882794: step: 1384/530, loss: 1.991078495979309
2023-01-21 08:32:03.977706: step: 1388/530, loss: 0.7127151489257812
2023-01-21 08:32:05.109756: step: 1392/530, loss: 5.336414337158203
2023-01-21 08:32:06.219687: step: 1396/530, loss: 0.8501438498497009
2023-01-21 08:32:07.376260: step: 1400/530, loss: 0.3514707684516907
2023-01-21 08:32:08.519141: step: 1404/530, loss: 3.9994394779205322
2023-01-21 08:32:09.645997: step: 1408/530, loss: 1.231032371520996
2023-01-21 08:32:10.751306: step: 1412/530, loss: 0.8287548422813416
2023-01-21 08:32:11.850391: step: 1416/530, loss: 1.6837100982666016
2023-01-21 08:32:12.962363: step: 1420/530, loss: 0.3052191734313965
2023-01-21 08:32:14.055100: step: 1424/530, loss: 1.0436056852340698
2023-01-21 08:32:15.167722: step: 1428/530, loss: 2.4814023971557617
2023-01-21 08:32:16.280035: step: 1432/530, loss: 0.3525175154209137
2023-01-21 08:32:17.389020: step: 1436/530, loss: 0.3126464784145355
2023-01-21 08:32:18.480765: step: 1440/530, loss: 0.39958441257476807
2023-01-21 08:32:19.597157: step: 1444/530, loss: 1.7367284297943115
2023-01-21 08:32:20.697469: step: 1448/530, loss: 0.5831590890884399
2023-01-21 08:32:21.825933: step: 1452/530, loss: 0.615650475025177
2023-01-21 08:32:22.980584: step: 1456/530, loss: 1.6531391143798828
2023-01-21 08:32:24.093178: step: 1460/530, loss: 0.5343203544616699
2023-01-21 08:32:25.193096: step: 1464/530, loss: 0.47699472308158875
2023-01-21 08:32:26.307589: step: 1468/530, loss: 0.9981957674026489
2023-01-21 08:32:27.395907: step: 1472/530, loss: 1.7923558950424194
2023-01-21 08:32:28.502264: step: 1476/530, loss: 1.1693894863128662
2023-01-21 08:32:29.591453: step: 1480/530, loss: 0.795159101486206
2023-01-21 08:32:30.704256: step: 1484/530, loss: 0.5918500423431396
2023-01-21 08:32:31.784503: step: 1488/530, loss: 2.7539942264556885
2023-01-21 08:32:32.884386: step: 1492/530, loss: 1.7908340692520142
2023-01-21 08:32:34.031972: step: 1496/530, loss: 1.0554401874542236
2023-01-21 08:32:35.135686: step: 1500/530, loss: 0.699389636516571
2023-01-21 08:32:36.253374: step: 1504/530, loss: 0.32550257444381714
2023-01-21 08:32:37.333107: step: 1508/530, loss: 0.28601014614105225
2023-01-21 08:32:38.480153: step: 1512/530, loss: 0.612713634967804
2023-01-21 08:32:39.613690: step: 1516/530, loss: 0.392680287361145
2023-01-21 08:32:40.699081: step: 1520/530, loss: 0.40928196907043457
2023-01-21 08:32:41.795224: step: 1524/530, loss: 0.1674882024526596
2023-01-21 08:32:42.907425: step: 1528/530, loss: 3.099695920944214
2023-01-21 08:32:44.012102: step: 1532/530, loss: 1.3022334575653076
2023-01-21 08:32:45.112304: step: 1536/530, loss: 1.6655919551849365
2023-01-21 08:32:46.230362: step: 1540/530, loss: 0.5938438177108765
2023-01-21 08:32:47.333475: step: 1544/530, loss: 3.4514589309692383
2023-01-21 08:32:48.435112: step: 1548/530, loss: 0.3294870853424072
2023-01-21 08:32:49.553120: step: 1552/530, loss: 1.470881700515747
2023-01-21 08:32:50.641122: step: 1556/530, loss: 0.570382833480835
2023-01-21 08:32:51.758095: step: 1560/530, loss: 0.13573046028614044
2023-01-21 08:32:52.866845: step: 1564/530, loss: 0.5438030958175659
2023-01-21 08:32:53.967288: step: 1568/530, loss: 0.4118262231349945
2023-01-21 08:32:55.075764: step: 1572/530, loss: 0.6908621788024902
2023-01-21 08:32:56.184958: step: 1576/530, loss: 0.889116108417511
2023-01-21 08:32:57.290573: step: 1580/530, loss: 1.42928147315979
2023-01-21 08:32:58.399654: step: 1584/530, loss: 0.3483037054538727
2023-01-21 08:32:59.509342: step: 1588/530, loss: 0.8478102087974548
2023-01-21 08:33:00.627547: step: 1592/530, loss: 2.0233829021453857
2023-01-21 08:33:01.750804: step: 1596/530, loss: 0.46418219804763794
2023-01-21 08:33:02.861483: step: 1600/530, loss: 0.31813845038414
2023-01-21 08:33:03.990754: step: 1604/530, loss: 0.864906370639801
2023-01-21 08:33:05.080354: step: 1608/530, loss: 1.582698941230774
2023-01-21 08:33:06.204189: step: 1612/530, loss: 2.6298794746398926
2023-01-21 08:33:07.327843: step: 1616/530, loss: 0.48941707611083984
2023-01-21 08:33:08.449807: step: 1620/530, loss: 1.6487646102905273
2023-01-21 08:33:09.561035: step: 1624/530, loss: 0.34516072273254395
2023-01-21 08:33:10.651015: step: 1628/530, loss: 0.9980376958847046
2023-01-21 08:33:11.750746: step: 1632/530, loss: 0.4461982846260071
2023-01-21 08:33:12.834741: step: 1636/530, loss: 1.734879970550537
2023-01-21 08:33:13.920998: step: 1640/530, loss: 1.4458205699920654
2023-01-21 08:33:15.037596: step: 1644/530, loss: 0.5368051528930664
2023-01-21 08:33:16.138604: step: 1648/530, loss: 0.6995850801467896
2023-01-21 08:33:17.225514: step: 1652/530, loss: 0.2262871414422989
2023-01-21 08:33:18.337720: step: 1656/530, loss: 1.145828127861023
2023-01-21 08:33:19.428325: step: 1660/530, loss: 0.5478800535202026
2023-01-21 08:33:20.548386: step: 1664/530, loss: 0.4348495602607727
2023-01-21 08:33:21.656140: step: 1668/530, loss: 1.1593722105026245
2023-01-21 08:33:22.766351: step: 1672/530, loss: 0.17307350039482117
2023-01-21 08:33:23.885014: step: 1676/530, loss: 0.41946423053741455
2023-01-21 08:33:25.002177: step: 1680/530, loss: 0.6250231862068176
2023-01-21 08:33:26.083162: step: 1684/530, loss: 1.464827537536621
2023-01-21 08:33:27.194465: step: 1688/530, loss: 0.2861084043979645
2023-01-21 08:33:28.325736: step: 1692/530, loss: 1.3531503677368164
2023-01-21 08:33:29.434055: step: 1696/530, loss: 1.0335527658462524
2023-01-21 08:33:30.507769: step: 1700/530, loss: 0.43667900562286377
2023-01-21 08:33:31.612741: step: 1704/530, loss: 1.32804536819458
2023-01-21 08:33:32.717585: step: 1708/530, loss: 0.5761452913284302
2023-01-21 08:33:33.876869: step: 1712/530, loss: 0.6144669651985168
2023-01-21 08:33:34.995459: step: 1716/530, loss: 0.8968162536621094
2023-01-21 08:33:36.089686: step: 1720/530, loss: 0.7122179865837097
2023-01-21 08:33:37.213031: step: 1724/530, loss: 1.0318787097930908
2023-01-21 08:33:38.315918: step: 1728/530, loss: 2.2600173950195312
2023-01-21 08:33:39.405221: step: 1732/530, loss: 0.864188551902771
2023-01-21 08:33:40.494094: step: 1736/530, loss: 0.36919277906417847
2023-01-21 08:33:41.611307: step: 1740/530, loss: 4.889497756958008
2023-01-21 08:33:42.719705: step: 1744/530, loss: 1.5948606729507446
2023-01-21 08:33:43.826674: step: 1748/530, loss: 0.337212473154068
2023-01-21 08:33:44.943096: step: 1752/530, loss: 0.5207529664039612
2023-01-21 08:33:46.050611: step: 1756/530, loss: 2.303536891937256
2023-01-21 08:33:47.150882: step: 1760/530, loss: 1.9565526247024536
2023-01-21 08:33:48.257676: step: 1764/530, loss: 2.555671453475952
2023-01-21 08:33:49.347462: step: 1768/530, loss: 1.539425015449524
2023-01-21 08:33:50.466983: step: 1772/530, loss: 0.3795326352119446
2023-01-21 08:33:51.559910: step: 1776/530, loss: 1.0622613430023193
2023-01-21 08:33:52.680177: step: 1780/530, loss: 0.19718846678733826
2023-01-21 08:33:53.818662: step: 1784/530, loss: 1.8759675025939941
2023-01-21 08:33:54.917514: step: 1788/530, loss: 0.5692466497421265
2023-01-21 08:33:56.000275: step: 1792/530, loss: 0.5606082081794739
2023-01-21 08:33:57.134878: step: 1796/530, loss: 0.7490469217300415
2023-01-21 08:33:58.230053: step: 1800/530, loss: 0.2673374116420746
2023-01-21 08:33:59.361173: step: 1804/530, loss: 1.0290288925170898
2023-01-21 08:34:00.491764: step: 1808/530, loss: 0.44509202241897583
2023-01-21 08:34:01.617403: step: 1812/530, loss: 0.3291131854057312
2023-01-21 08:34:02.732801: step: 1816/530, loss: 0.6886335015296936
2023-01-21 08:34:03.836835: step: 1820/530, loss: 1.92379629611969
2023-01-21 08:34:04.964760: step: 1824/530, loss: 2.0243961811065674
2023-01-21 08:34:06.076791: step: 1828/530, loss: 0.6118788719177246
2023-01-21 08:34:07.176992: step: 1832/530, loss: 1.6476573944091797
2023-01-21 08:34:08.292612: step: 1836/530, loss: 1.144230604171753
2023-01-21 08:34:09.383356: step: 1840/530, loss: 4.090342044830322
2023-01-21 08:34:10.494278: step: 1844/530, loss: 0.3739830255508423
2023-01-21 08:34:11.588010: step: 1848/530, loss: 0.42024731636047363
2023-01-21 08:34:12.685688: step: 1852/530, loss: 0.6363363265991211
2023-01-21 08:34:13.858158: step: 1856/530, loss: 7.146363258361816
2023-01-21 08:34:15.003769: step: 1860/530, loss: 1.9021787643432617
2023-01-21 08:34:16.117296: step: 1864/530, loss: 0.2815357446670532
2023-01-21 08:34:17.229725: step: 1868/530, loss: 0.3476211428642273
2023-01-21 08:34:18.322545: step: 1872/530, loss: 1.9249788522720337
2023-01-21 08:34:19.416610: step: 1876/530, loss: 2.4019217491149902
2023-01-21 08:34:20.543608: step: 1880/530, loss: 1.1774638891220093
2023-01-21 08:34:21.664547: step: 1884/530, loss: 1.0605806112289429
2023-01-21 08:34:22.799394: step: 1888/530, loss: 1.097830057144165
2023-01-21 08:34:23.915968: step: 1892/530, loss: 0.6262301206588745
2023-01-21 08:34:25.019077: step: 1896/530, loss: 0.3009089231491089
2023-01-21 08:34:26.131507: step: 1900/530, loss: 1.0584033727645874
2023-01-21 08:34:27.281577: step: 1904/530, loss: 2.5493252277374268
2023-01-21 08:34:28.383563: step: 1908/530, loss: 0.9976029992103577
2023-01-21 08:34:29.497094: step: 1912/530, loss: 1.029822587966919
2023-01-21 08:34:30.601106: step: 1916/530, loss: 0.46277350187301636
2023-01-21 08:34:31.711345: step: 1920/530, loss: 0.2852664887905121
2023-01-21 08:34:32.807785: step: 1924/530, loss: 0.7696099281311035
2023-01-21 08:34:33.931045: step: 1928/530, loss: 3.251713514328003
2023-01-21 08:34:35.027276: step: 1932/530, loss: 0.4431355595588684
2023-01-21 08:34:36.128493: step: 1936/530, loss: 1.986539602279663
2023-01-21 08:34:37.262920: step: 1940/530, loss: 0.4960607588291168
2023-01-21 08:34:38.403889: step: 1944/530, loss: 1.300311803817749
2023-01-21 08:34:39.531283: step: 1948/530, loss: 0.26442885398864746
2023-01-21 08:34:40.650186: step: 1952/530, loss: 0.5087611079216003
2023-01-21 08:34:41.761521: step: 1956/530, loss: 1.1133818626403809
2023-01-21 08:34:42.865434: step: 1960/530, loss: 0.18851400911808014
2023-01-21 08:34:43.996234: step: 1964/530, loss: 1.8992023468017578
2023-01-21 08:34:45.081253: step: 1968/530, loss: 0.7801329493522644
2023-01-21 08:34:46.172067: step: 1972/530, loss: 0.614930272102356
2023-01-21 08:34:47.283913: step: 1976/530, loss: 0.27177974581718445
2023-01-21 08:34:48.420418: step: 1980/530, loss: 2.7597458362579346
2023-01-21 08:34:49.554763: step: 1984/530, loss: 0.20599856972694397
2023-01-21 08:34:50.683852: step: 1988/530, loss: 1.3647637367248535
2023-01-21 08:34:51.787972: step: 1992/530, loss: 0.5085301399230957
2023-01-21 08:34:52.918195: step: 1996/530, loss: 1.1464451551437378
2023-01-21 08:34:54.038356: step: 2000/530, loss: 0.3140926957130432
2023-01-21 08:34:55.156670: step: 2004/530, loss: 0.8599792122840881
2023-01-21 08:34:56.256792: step: 2008/530, loss: 0.17204852402210236
2023-01-21 08:34:57.391610: step: 2012/530, loss: 0.24362383782863617
2023-01-21 08:34:58.518142: step: 2016/530, loss: 0.7568389177322388
2023-01-21 08:34:59.626304: step: 2020/530, loss: 1.926169753074646
2023-01-21 08:35:00.733831: step: 2024/530, loss: 0.23006616532802582
2023-01-21 08:35:01.864784: step: 2028/530, loss: 0.782691478729248
2023-01-21 08:35:02.953830: step: 2032/530, loss: 2.08746075630188
2023-01-21 08:35:04.078235: step: 2036/530, loss: 0.6575571298599243
2023-01-21 08:35:05.196896: step: 2040/530, loss: 0.2450738400220871
2023-01-21 08:35:06.336988: step: 2044/530, loss: 0.31441497802734375
2023-01-21 08:35:07.441177: step: 2048/530, loss: 2.1679301261901855
2023-01-21 08:35:08.570910: step: 2052/530, loss: 1.4379644393920898
2023-01-21 08:35:09.694403: step: 2056/530, loss: 0.44014471769332886
2023-01-21 08:35:10.803087: step: 2060/530, loss: 0.10426025092601776
2023-01-21 08:35:11.936701: step: 2064/530, loss: 1.3592344522476196
2023-01-21 08:35:13.050138: step: 2068/530, loss: 0.21736669540405273
2023-01-21 08:35:14.226459: step: 2072/530, loss: 0.11242156475782394
2023-01-21 08:35:15.314325: step: 2076/530, loss: 1.2034382820129395
2023-01-21 08:35:16.409448: step: 2080/530, loss: 0.22735628485679626
2023-01-21 08:35:17.516630: step: 2084/530, loss: 1.4170310497283936
2023-01-21 08:35:18.648136: step: 2088/530, loss: 1.1202428340911865
2023-01-21 08:35:19.755973: step: 2092/530, loss: 0.4065219759941101
2023-01-21 08:35:20.877409: step: 2096/530, loss: 0.8180004358291626
2023-01-21 08:35:22.025356: step: 2100/530, loss: 1.1105661392211914
2023-01-21 08:35:23.118367: step: 2104/530, loss: 1.7270715236663818
2023-01-21 08:35:24.238648: step: 2108/530, loss: 0.36386728286743164
2023-01-21 08:35:25.369073: step: 2112/530, loss: 1.3461484909057617
2023-01-21 08:35:26.467390: step: 2116/530, loss: 1.5666639804840088
2023-01-21 08:35:27.578777: step: 2120/530, loss: 0.3403962552547455
==================================================
Loss: 3.547
--------------------
Dev: {'event': {'p': 0.5575842696629213, 'r': 0.5286284953395473, 'f1': 0.5427204374572795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test: {'event': {'p': 0.47513440860215056, 'r': 0.412004662004662, 'f1': 0.44132334581772786}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Chinese: {'event': {'p': 0.5428571428571428, 'r': 0.35185185185185186, 'f1': 0.42696629213483145}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Korean: {'event': {'p': 0.8571428571428571, 'r': 0.19047619047619047, 'f1': 0.31168831168831174}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Russian: {'event': {'p': 0.875, 'r': 0.19444444444444445, 'f1': 0.3181818181818182}, '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': 0.5575842696629213, 'r': 0.5286284953395473, 'f1': 0.5427204374572795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Chinese: {'event': {'p': 0.47513440860215056, 'r': 0.412004662004662, 'f1': 0.44132334581772786}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Chinese: {'event': {'p': 0.5428571428571428, 'r': 0.35185185185185186, 'f1': 0.42696629213483145}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5575842696629213, 'r': 0.5286284953395473, 'f1': 0.5427204374572795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Korean: {'event': {'p': 0.47513440860215056, 'r': 0.412004662004662, 'f1': 0.44132334581772786}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Korean: {'event': {'p': 0.8571428571428571, 'r': 0.19047619047619047, 'f1': 0.31168831168831174}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5575842696629213, 'r': 0.5286284953395473, 'f1': 0.5427204374572795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Russian: {'event': {'p': 0.47513440860215056, 'r': 0.412004662004662, 'f1': 0.44132334581772786}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Russian: {'event': {'p': 0.875, 'r': 0.19444444444444445, 'f1': 0.3181818181818182}, '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 08:36:22.948630: step: 4/530, loss: 2.200685977935791
2023-01-21 08:36:24.050029: step: 8/530, loss: 1.058659553527832
2023-01-21 08:36:25.135937: step: 12/530, loss: 0.1197165995836258
2023-01-21 08:36:26.237887: step: 16/530, loss: 1.0336403846740723
2023-01-21 08:36:27.359515: step: 20/530, loss: 1.0256123542785645
2023-01-21 08:36:28.471262: step: 24/530, loss: 0.892248272895813
2023-01-21 08:36:29.571176: step: 28/530, loss: 0.22788238525390625
2023-01-21 08:36:30.659499: step: 32/530, loss: 0.28901946544647217
2023-01-21 08:36:31.783755: step: 36/530, loss: 2.5979502201080322
2023-01-21 08:36:32.938896: step: 40/530, loss: 2.4533352851867676
2023-01-21 08:36:34.068385: step: 44/530, loss: 0.34595173597335815
2023-01-21 08:36:35.178362: step: 48/530, loss: 1.4736697673797607
2023-01-21 08:36:36.282780: step: 52/530, loss: 0.563647449016571
2023-01-21 08:36:37.390166: step: 56/530, loss: 0.9589254856109619
2023-01-21 08:36:38.520425: step: 60/530, loss: 0.5077283978462219
2023-01-21 08:36:39.607401: step: 64/530, loss: 0.26661205291748047
2023-01-21 08:36:40.701256: step: 68/530, loss: 0.2586950361728668
2023-01-21 08:36:41.807970: step: 72/530, loss: 1.91961669921875
2023-01-21 08:36:42.883529: step: 76/530, loss: 0.12271666526794434
2023-01-21 08:36:44.005549: step: 80/530, loss: 0.7731084227561951
2023-01-21 08:36:45.139675: step: 84/530, loss: 7.6644368171691895
2023-01-21 08:36:46.278083: step: 88/530, loss: 0.26792946457862854
2023-01-21 08:36:47.447432: step: 92/530, loss: 0.2669130265712738
2023-01-21 08:36:48.558943: step: 96/530, loss: 0.9699838161468506
2023-01-21 08:36:49.682064: step: 100/530, loss: 0.24093469977378845
2023-01-21 08:36:50.825716: step: 104/530, loss: 1.9498194456100464
2023-01-21 08:36:51.959039: step: 108/530, loss: 0.19898051023483276
2023-01-21 08:36:53.144763: step: 112/530, loss: 0.576029896736145
2023-01-21 08:36:54.262424: step: 116/530, loss: 0.27473029494285583
2023-01-21 08:36:55.400646: step: 120/530, loss: 0.3010798990726471
2023-01-21 08:36:56.514290: step: 124/530, loss: 0.8356246948242188
2023-01-21 08:36:57.636960: step: 128/530, loss: 1.5021779537200928
2023-01-21 08:36:58.767655: step: 132/530, loss: 0.6857924461364746
2023-01-21 08:36:59.862547: step: 136/530, loss: 0.324203222990036
2023-01-21 08:37:00.997934: step: 140/530, loss: 0.6615785360336304
2023-01-21 08:37:02.156734: step: 144/530, loss: 0.9998345375061035
2023-01-21 08:37:03.259757: step: 148/530, loss: 1.3763024806976318
2023-01-21 08:37:04.381633: step: 152/530, loss: 1.1671593189239502
2023-01-21 08:37:05.504468: step: 156/530, loss: 0.29817238450050354
2023-01-21 08:37:06.634411: step: 160/530, loss: 0.18124710023403168
2023-01-21 08:37:07.726194: step: 164/530, loss: 1.1664457321166992
2023-01-21 08:37:08.837695: step: 168/530, loss: 3.0986249446868896
2023-01-21 08:37:09.922738: step: 172/530, loss: 0.7280139327049255
2023-01-21 08:37:11.004616: step: 176/530, loss: 0.8106658458709717
2023-01-21 08:37:12.084319: step: 180/530, loss: 0.7450309991836548
2023-01-21 08:37:13.169936: step: 184/530, loss: 0.5360084772109985
2023-01-21 08:37:14.267503: step: 188/530, loss: 2.1084046363830566
2023-01-21 08:37:15.378119: step: 192/530, loss: 1.2971171140670776
2023-01-21 08:37:16.468274: step: 196/530, loss: 0.26097896695137024
2023-01-21 08:37:17.580721: step: 200/530, loss: 0.44702231884002686
2023-01-21 08:37:18.684175: step: 204/530, loss: 0.20342564582824707
2023-01-21 08:37:19.772778: step: 208/530, loss: 0.09978476166725159
2023-01-21 08:37:20.899208: step: 212/530, loss: 0.33453789353370667
2023-01-21 08:37:21.989029: step: 216/530, loss: 1.5588793754577637
2023-01-21 08:37:23.111789: step: 220/530, loss: 0.2923765182495117
2023-01-21 08:37:24.229257: step: 224/530, loss: 1.2631158828735352
2023-01-21 08:37:25.319198: step: 228/530, loss: 0.27993661165237427
2023-01-21 08:37:26.441965: step: 232/530, loss: 0.30080148577690125
2023-01-21 08:37:27.537309: step: 236/530, loss: 1.7464178800582886
2023-01-21 08:37:28.650982: step: 240/530, loss: 0.9044017791748047
2023-01-21 08:37:29.742887: step: 244/530, loss: 0.2250264585018158
2023-01-21 08:37:30.847365: step: 248/530, loss: 0.1649579107761383
2023-01-21 08:37:31.954157: step: 252/530, loss: 1.2601319551467896
2023-01-21 08:37:33.059431: step: 256/530, loss: 0.8354940414428711
2023-01-21 08:37:34.184647: step: 260/530, loss: 1.1860452890396118
2023-01-21 08:37:35.272933: step: 264/530, loss: 0.13848038017749786
2023-01-21 08:37:36.386646: step: 268/530, loss: 0.16463322937488556
2023-01-21 08:37:37.491751: step: 272/530, loss: 6.484447479248047
2023-01-21 08:37:38.568654: step: 276/530, loss: 0.7893614172935486
2023-01-21 08:37:39.635652: step: 280/530, loss: 1.489478349685669
2023-01-21 08:37:40.736917: step: 284/530, loss: 1.029711127281189
2023-01-21 08:37:41.860392: step: 288/530, loss: 0.16102752089500427
2023-01-21 08:37:42.954366: step: 292/530, loss: 1.1562092304229736
2023-01-21 08:37:44.114307: step: 296/530, loss: 0.36202916502952576
2023-01-21 08:37:45.246241: step: 300/530, loss: 0.4381279945373535
2023-01-21 08:37:46.375848: step: 304/530, loss: 0.8384024500846863
2023-01-21 08:37:47.479372: step: 308/530, loss: 0.2489282786846161
2023-01-21 08:37:48.593422: step: 312/530, loss: 0.2302195131778717
2023-01-21 08:37:49.695977: step: 316/530, loss: 0.9098072052001953
2023-01-21 08:37:50.797027: step: 320/530, loss: 0.7628673315048218
2023-01-21 08:37:51.896110: step: 324/530, loss: 0.8541550040245056
2023-01-21 08:37:52.996753: step: 328/530, loss: 10.53091812133789
2023-01-21 08:37:54.116706: step: 332/530, loss: 0.2528610825538635
2023-01-21 08:37:55.233217: step: 336/530, loss: 1.1355164051055908
2023-01-21 08:37:56.377906: step: 340/530, loss: 0.7249311208724976
2023-01-21 08:37:57.481657: step: 344/530, loss: 0.8423562049865723
2023-01-21 08:37:58.592380: step: 348/530, loss: 0.2510421872138977
2023-01-21 08:37:59.722017: step: 352/530, loss: 0.2662091851234436
2023-01-21 08:38:00.841355: step: 356/530, loss: 0.754250168800354
2023-01-21 08:38:01.981380: step: 360/530, loss: 0.9891226291656494
2023-01-21 08:38:03.098657: step: 364/530, loss: 0.43972665071487427
2023-01-21 08:38:04.193547: step: 368/530, loss: 0.6635894775390625
2023-01-21 08:38:05.288770: step: 372/530, loss: 0.795781135559082
2023-01-21 08:38:06.404917: step: 376/530, loss: 0.21503916382789612
2023-01-21 08:38:07.533639: step: 380/530, loss: 0.26122504472732544
2023-01-21 08:38:08.614699: step: 384/530, loss: 0.8479779958724976
2023-01-21 08:38:09.716311: step: 388/530, loss: 0.3621244430541992
2023-01-21 08:38:10.823103: step: 392/530, loss: 0.13838304579257965
2023-01-21 08:38:11.941500: step: 396/530, loss: 0.4224167764186859
2023-01-21 08:38:13.050604: step: 400/530, loss: 1.967092514038086
2023-01-21 08:38:14.133000: step: 404/530, loss: 6.675584316253662
2023-01-21 08:38:15.232965: step: 408/530, loss: 0.2253103405237198
2023-01-21 08:38:16.378702: step: 412/530, loss: 0.5202027559280396
2023-01-21 08:38:17.458426: step: 416/530, loss: 0.37715089321136475
2023-01-21 08:38:18.549720: step: 420/530, loss: 0.4904758334159851
2023-01-21 08:38:19.641966: step: 424/530, loss: 0.22176390886306763
2023-01-21 08:38:20.747441: step: 428/530, loss: 0.20544129610061646
2023-01-21 08:38:21.877597: step: 432/530, loss: 0.6765258312225342
2023-01-21 08:38:23.007201: step: 436/530, loss: 1.2053048610687256
2023-01-21 08:38:24.104351: step: 440/530, loss: 0.4454779624938965
2023-01-21 08:38:25.206512: step: 444/530, loss: 1.6111702919006348
2023-01-21 08:38:26.312241: step: 448/530, loss: 0.06502237170934677
2023-01-21 08:38:27.423744: step: 452/530, loss: 0.22973480820655823
2023-01-21 08:38:28.582849: step: 456/530, loss: 2.492570400238037
2023-01-21 08:38:29.700700: step: 460/530, loss: 0.14618225395679474
2023-01-21 08:38:30.841769: step: 464/530, loss: 2.185479164123535
2023-01-21 08:38:31.947091: step: 468/530, loss: 0.2644267678260803
2023-01-21 08:38:33.062344: step: 472/530, loss: 0.8231765627861023
2023-01-21 08:38:34.189767: step: 476/530, loss: 0.21066045761108398
2023-01-21 08:38:35.290610: step: 480/530, loss: 0.33683720231056213
2023-01-21 08:38:36.394856: step: 484/530, loss: 1.4127780199050903
2023-01-21 08:38:37.475770: step: 488/530, loss: 0.9362136125564575
2023-01-21 08:38:38.574572: step: 492/530, loss: 1.5947743654251099
2023-01-21 08:38:39.710742: step: 496/530, loss: 0.5059801340103149
2023-01-21 08:38:40.832921: step: 500/530, loss: 0.17963333427906036
2023-01-21 08:38:41.960752: step: 504/530, loss: 0.24877767264842987
2023-01-21 08:38:43.044625: step: 508/530, loss: 0.35003119707107544
2023-01-21 08:38:44.162132: step: 512/530, loss: 0.5445950031280518
2023-01-21 08:38:45.284748: step: 516/530, loss: 1.3959622383117676
2023-01-21 08:38:46.398882: step: 520/530, loss: 1.0506694316864014
2023-01-21 08:38:47.495211: step: 524/530, loss: 0.530386745929718
2023-01-21 08:38:48.590919: step: 528/530, loss: 0.1987399160861969
2023-01-21 08:38:49.684668: step: 532/530, loss: 0.3992048501968384
2023-01-21 08:38:50.796343: step: 536/530, loss: 0.39069196581840515
2023-01-21 08:38:51.948052: step: 540/530, loss: 0.16810913383960724
2023-01-21 08:38:53.052528: step: 544/530, loss: 0.24973583221435547
2023-01-21 08:38:54.164428: step: 548/530, loss: 0.24334926903247833
2023-01-21 08:38:55.260455: step: 552/530, loss: 0.8767409324645996
2023-01-21 08:38:56.379804: step: 556/530, loss: 0.761859655380249
2023-01-21 08:38:57.498694: step: 560/530, loss: 3.0349068641662598
2023-01-21 08:38:58.629316: step: 564/530, loss: 0.07478771358728409
2023-01-21 08:38:59.773242: step: 568/530, loss: 0.4298804998397827
2023-01-21 08:39:00.870595: step: 572/530, loss: 0.2968323230743408
2023-01-21 08:39:02.020026: step: 576/530, loss: 1.9561132192611694
2023-01-21 08:39:03.159231: step: 580/530, loss: 0.20468273758888245
2023-01-21 08:39:04.294975: step: 584/530, loss: 0.30116721987724304
2023-01-21 08:39:05.394394: step: 588/530, loss: 3.4594688415527344
2023-01-21 08:39:06.501673: step: 592/530, loss: 0.9758798480033875
2023-01-21 08:39:07.651111: step: 596/530, loss: 0.4043503701686859
2023-01-21 08:39:08.766799: step: 600/530, loss: 0.4305291175842285
2023-01-21 08:39:09.883179: step: 604/530, loss: 1.6910337209701538
2023-01-21 08:39:11.007133: step: 608/530, loss: 0.4943602681159973
2023-01-21 08:39:12.129337: step: 612/530, loss: 0.22036682069301605
2023-01-21 08:39:13.235685: step: 616/530, loss: 1.5216723680496216
2023-01-21 08:39:14.339286: step: 620/530, loss: 0.8112492561340332
2023-01-21 08:39:15.440686: step: 624/530, loss: 0.3797592222690582
2023-01-21 08:39:16.560537: step: 628/530, loss: 0.3138834238052368
2023-01-21 08:39:17.689153: step: 632/530, loss: 0.2239220142364502
2023-01-21 08:39:18.843549: step: 636/530, loss: 0.9719775319099426
2023-01-21 08:39:19.969752: step: 640/530, loss: 0.22301378846168518
2023-01-21 08:39:21.070049: step: 644/530, loss: 0.366659939289093
2023-01-21 08:39:22.161819: step: 648/530, loss: 0.2508353292942047
2023-01-21 08:39:23.285342: step: 652/530, loss: 0.15830039978027344
2023-01-21 08:39:24.388432: step: 656/530, loss: 1.149523377418518
2023-01-21 08:39:25.496330: step: 660/530, loss: 0.10059557110071182
2023-01-21 08:39:26.601100: step: 664/530, loss: 0.946194052696228
2023-01-21 08:39:27.723197: step: 668/530, loss: 0.9798312187194824
2023-01-21 08:39:28.818190: step: 672/530, loss: 0.9051358699798584
2023-01-21 08:39:29.936531: step: 676/530, loss: 0.18281203508377075
2023-01-21 08:39:31.042621: step: 680/530, loss: 0.334725558757782
2023-01-21 08:39:32.143178: step: 684/530, loss: 1.388506531715393
2023-01-21 08:39:33.261470: step: 688/530, loss: 0.34011203050613403
2023-01-21 08:39:34.401881: step: 692/530, loss: 0.28743547201156616
2023-01-21 08:39:35.496225: step: 696/530, loss: 0.19589228928089142
2023-01-21 08:39:36.631996: step: 700/530, loss: 0.5151674151420593
2023-01-21 08:39:37.717328: step: 704/530, loss: 0.22857657074928284
2023-01-21 08:39:38.829312: step: 708/530, loss: 1.3195732831954956
2023-01-21 08:39:39.944359: step: 712/530, loss: 0.34966832399368286
2023-01-21 08:39:41.032871: step: 716/530, loss: 0.255550742149353
2023-01-21 08:39:42.143062: step: 720/530, loss: 0.21411819756031036
2023-01-21 08:39:43.241201: step: 724/530, loss: 0.29211390018463135
2023-01-21 08:39:44.355170: step: 728/530, loss: 1.381205439567566
2023-01-21 08:39:45.487467: step: 732/530, loss: 3.2000765800476074
2023-01-21 08:39:46.581304: step: 736/530, loss: 0.7178811430931091
2023-01-21 08:39:47.718786: step: 740/530, loss: 1.4770170450210571
2023-01-21 08:39:48.809145: step: 744/530, loss: 0.3136110007762909
2023-01-21 08:39:49.903759: step: 748/530, loss: 0.28192827105522156
2023-01-21 08:39:51.002103: step: 752/530, loss: 0.22102923691272736
2023-01-21 08:39:52.118285: step: 756/530, loss: 0.5702583193778992
2023-01-21 08:39:53.209568: step: 760/530, loss: 0.35236233472824097
2023-01-21 08:39:54.333909: step: 764/530, loss: 7.44382381439209
2023-01-21 08:39:55.426610: step: 768/530, loss: 0.8546481132507324
2023-01-21 08:39:56.558400: step: 772/530, loss: 0.9909370541572571
2023-01-21 08:39:57.672258: step: 776/530, loss: 1.0059850215911865
2023-01-21 08:39:58.782673: step: 780/530, loss: 0.5271921753883362
2023-01-21 08:39:59.903181: step: 784/530, loss: 0.17919960618019104
2023-01-21 08:40:00.990515: step: 788/530, loss: 0.5968723297119141
2023-01-21 08:40:02.081933: step: 792/530, loss: 0.5476526618003845
2023-01-21 08:40:03.180081: step: 796/530, loss: 0.32966527342796326
2023-01-21 08:40:04.263637: step: 800/530, loss: 0.9981452226638794
2023-01-21 08:40:05.373905: step: 804/530, loss: 1.527134656906128
2023-01-21 08:40:06.485284: step: 808/530, loss: 0.31798163056373596
2023-01-21 08:40:07.623957: step: 812/530, loss: 0.3976700007915497
2023-01-21 08:40:08.725409: step: 816/530, loss: 1.3337130546569824
2023-01-21 08:40:09.882631: step: 820/530, loss: 0.4176862835884094
2023-01-21 08:40:11.000606: step: 824/530, loss: 1.2289540767669678
2023-01-21 08:40:12.152775: step: 828/530, loss: 0.7914347648620605
2023-01-21 08:40:13.244987: step: 832/530, loss: 2.5298385620117188
2023-01-21 08:40:14.356076: step: 836/530, loss: 0.19650602340698242
2023-01-21 08:40:15.471739: step: 840/530, loss: 0.39637166261672974
2023-01-21 08:40:16.577897: step: 844/530, loss: 0.13046441972255707
2023-01-21 08:40:17.666809: step: 848/530, loss: 0.42809364199638367
2023-01-21 08:40:18.776681: step: 852/530, loss: 0.08593922108411789
2023-01-21 08:40:19.942033: step: 856/530, loss: 0.8894029855728149
2023-01-21 08:40:21.060205: step: 860/530, loss: 0.8561725616455078
2023-01-21 08:40:22.171944: step: 864/530, loss: 0.1408546417951584
2023-01-21 08:40:23.276287: step: 868/530, loss: 0.8385001420974731
2023-01-21 08:40:24.406399: step: 872/530, loss: 0.3299209475517273
2023-01-21 08:40:25.501307: step: 876/530, loss: 0.06449031829833984
2023-01-21 08:40:26.633642: step: 880/530, loss: 0.5882061719894409
2023-01-21 08:40:27.760056: step: 884/530, loss: 1.0153770446777344
2023-01-21 08:40:28.904628: step: 888/530, loss: 0.9610913991928101
2023-01-21 08:40:30.043744: step: 892/530, loss: 0.3587445616722107
2023-01-21 08:40:31.163836: step: 896/530, loss: 0.4174576699733734
2023-01-21 08:40:32.250818: step: 900/530, loss: 6.706972599029541
2023-01-21 08:40:33.372912: step: 904/530, loss: 0.683864951133728
2023-01-21 08:40:34.479573: step: 908/530, loss: 0.4716065227985382
2023-01-21 08:40:35.624754: step: 912/530, loss: 0.254197359085083
2023-01-21 08:40:36.753691: step: 916/530, loss: 0.17095708847045898
2023-01-21 08:40:37.884505: step: 920/530, loss: 0.5439212322235107
2023-01-21 08:40:39.004689: step: 924/530, loss: 0.08776841312646866
2023-01-21 08:40:40.105186: step: 928/530, loss: 0.3539993464946747
2023-01-21 08:40:41.186923: step: 932/530, loss: 0.1430431306362152
2023-01-21 08:40:42.314095: step: 936/530, loss: 0.22902193665504456
2023-01-21 08:40:43.443566: step: 940/530, loss: 0.5222132205963135
2023-01-21 08:40:44.550630: step: 944/530, loss: 0.1301381140947342
2023-01-21 08:40:45.675256: step: 948/530, loss: 1.1966793537139893
2023-01-21 08:40:46.769064: step: 952/530, loss: 0.471148282289505
2023-01-21 08:40:47.838981: step: 956/530, loss: 0.22538577020168304
2023-01-21 08:40:48.963895: step: 960/530, loss: 0.05984830856323242
2023-01-21 08:40:50.077319: step: 964/530, loss: 0.22298157215118408
2023-01-21 08:40:51.206538: step: 968/530, loss: 3.1551895141601562
2023-01-21 08:40:52.331782: step: 972/530, loss: 0.3010341227054596
2023-01-21 08:40:53.429047: step: 976/530, loss: 0.1772564947605133
2023-01-21 08:40:54.547118: step: 980/530, loss: 2.4243040084838867
2023-01-21 08:40:55.675260: step: 984/530, loss: 1.9680969715118408
2023-01-21 08:40:56.766493: step: 988/530, loss: 0.5540863871574402
2023-01-21 08:40:57.888440: step: 992/530, loss: 0.48715218901634216
2023-01-21 08:40:58.993549: step: 996/530, loss: 0.6629146337509155
2023-01-21 08:41:00.092188: step: 1000/530, loss: 0.7571136951446533
2023-01-21 08:41:01.206191: step: 1004/530, loss: 0.20634795725345612
2023-01-21 08:41:02.292254: step: 1008/530, loss: 0.25444328784942627
2023-01-21 08:41:03.400317: step: 1012/530, loss: 0.29206714034080505
2023-01-21 08:41:04.507318: step: 1016/530, loss: 0.13060179352760315
2023-01-21 08:41:05.621908: step: 1020/530, loss: 0.1235198974609375
2023-01-21 08:41:06.755167: step: 1024/530, loss: 1.6179931163787842
2023-01-21 08:41:07.837498: step: 1028/530, loss: 0.3424397110939026
2023-01-21 08:41:08.959295: step: 1032/530, loss: 1.0380901098251343
2023-01-21 08:41:10.062476: step: 1036/530, loss: 1.6306990385055542
2023-01-21 08:41:11.185894: step: 1040/530, loss: 0.3984840214252472
2023-01-21 08:41:12.275906: step: 1044/530, loss: 2.4112985134124756
2023-01-21 08:41:13.387069: step: 1048/530, loss: 0.07761536538600922
2023-01-21 08:41:14.512957: step: 1052/530, loss: 0.23065900802612305
2023-01-21 08:41:15.649784: step: 1056/530, loss: 0.559539794921875
2023-01-21 08:41:16.772041: step: 1060/530, loss: 7.068521976470947
2023-01-21 08:41:17.886966: step: 1064/530, loss: 1.8452435731887817
2023-01-21 08:41:19.002244: step: 1068/530, loss: 0.28903770446777344
2023-01-21 08:41:20.109440: step: 1072/530, loss: 0.4422036409378052
2023-01-21 08:41:21.220410: step: 1076/530, loss: 1.5652391910552979
2023-01-21 08:41:22.366130: step: 1080/530, loss: 0.7198148965835571
2023-01-21 08:41:23.491796: step: 1084/530, loss: 0.543188214302063
2023-01-21 08:41:24.612938: step: 1088/530, loss: 0.17771998047828674
2023-01-21 08:41:25.772845: step: 1092/530, loss: 0.172528937458992
2023-01-21 08:41:26.845189: step: 1096/530, loss: 0.9231682419776917
2023-01-21 08:41:27.918620: step: 1100/530, loss: 0.11629854142665863
2023-01-21 08:41:28.997466: step: 1104/530, loss: 1.3081920146942139
2023-01-21 08:41:30.079963: step: 1108/530, loss: 2.267946243286133
2023-01-21 08:41:31.219689: step: 1112/530, loss: 0.2682268023490906
2023-01-21 08:41:32.313284: step: 1116/530, loss: 0.6809921264648438
2023-01-21 08:41:33.424270: step: 1120/530, loss: 0.25974375009536743
2023-01-21 08:41:34.524118: step: 1124/530, loss: 2.283151149749756
2023-01-21 08:41:35.636841: step: 1128/530, loss: 0.9658295512199402
2023-01-21 08:41:36.761669: step: 1132/530, loss: 1.4376046657562256
2023-01-21 08:41:37.861229: step: 1136/530, loss: 0.1428484469652176
2023-01-21 08:41:38.992589: step: 1140/530, loss: 0.24889430403709412
2023-01-21 08:41:40.114281: step: 1144/530, loss: 0.5231178402900696
2023-01-21 08:41:41.223804: step: 1148/530, loss: 0.7936610579490662
2023-01-21 08:41:42.334804: step: 1152/530, loss: 0.2305418848991394
2023-01-21 08:41:43.441860: step: 1156/530, loss: 0.2333575338125229
2023-01-21 08:41:44.551795: step: 1160/530, loss: 0.589411199092865
2023-01-21 08:41:45.694382: step: 1164/530, loss: 1.415989637374878
2023-01-21 08:41:46.802331: step: 1168/530, loss: 0.8055539727210999
2023-01-21 08:41:47.929022: step: 1172/530, loss: 0.18290147185325623
2023-01-21 08:41:49.031482: step: 1176/530, loss: 0.10870780795812607
2023-01-21 08:41:50.129376: step: 1180/530, loss: 1.1774333715438843
2023-01-21 08:41:51.213616: step: 1184/530, loss: 0.2196376770734787
2023-01-21 08:41:52.326673: step: 1188/530, loss: 0.7387223243713379
2023-01-21 08:41:53.459013: step: 1192/530, loss: 0.24026966094970703
2023-01-21 08:41:54.563237: step: 1196/530, loss: 0.32315802574157715
2023-01-21 08:41:55.661281: step: 1200/530, loss: 0.27900105714797974
2023-01-21 08:41:56.781310: step: 1204/530, loss: 0.3503550887107849
2023-01-21 08:41:57.896602: step: 1208/530, loss: 0.46504974365234375
2023-01-21 08:41:59.018003: step: 1212/530, loss: 0.9156852960586548
2023-01-21 08:42:00.104938: step: 1216/530, loss: 0.28622308373451233
2023-01-21 08:42:01.228660: step: 1220/530, loss: 0.5559775233268738
2023-01-21 08:42:02.350238: step: 1224/530, loss: 0.37156346440315247
2023-01-21 08:42:03.472591: step: 1228/530, loss: 0.2069849967956543
2023-01-21 08:42:04.587436: step: 1232/530, loss: 0.11998063325881958
2023-01-21 08:42:05.759261: step: 1236/530, loss: 0.6977161169052124
2023-01-21 08:42:06.857797: step: 1240/530, loss: 0.15370111167430878
2023-01-21 08:42:07.974102: step: 1244/530, loss: 0.7312580347061157
2023-01-21 08:42:09.110813: step: 1248/530, loss: 0.3679896593093872
2023-01-21 08:42:10.213662: step: 1252/530, loss: 1.4025382995605469
2023-01-21 08:42:11.337183: step: 1256/530, loss: 1.2641417980194092
2023-01-21 08:42:12.438189: step: 1260/530, loss: 0.5815926194190979
2023-01-21 08:42:13.531062: step: 1264/530, loss: 0.5595970153808594
2023-01-21 08:42:14.659547: step: 1268/530, loss: 1.2447837591171265
2023-01-21 08:42:15.776409: step: 1272/530, loss: 0.8371374011039734
2023-01-21 08:42:16.874731: step: 1276/530, loss: 0.3096882700920105
2023-01-21 08:42:17.996412: step: 1280/530, loss: 0.9768273830413818
2023-01-21 08:42:19.122800: step: 1284/530, loss: 0.2760496735572815
2023-01-21 08:42:20.232306: step: 1288/530, loss: 0.6941208243370056
2023-01-21 08:42:21.337597: step: 1292/530, loss: 0.27443069219589233
2023-01-21 08:42:22.424748: step: 1296/530, loss: 0.6266626119613647
2023-01-21 08:42:23.534841: step: 1300/530, loss: 0.1924697458744049
2023-01-21 08:42:24.675533: step: 1304/530, loss: 0.7267837524414062
2023-01-21 08:42:25.794960: step: 1308/530, loss: 0.3956131041049957
2023-01-21 08:42:26.925109: step: 1312/530, loss: 0.8520927429199219
2023-01-21 08:42:28.028575: step: 1316/530, loss: 0.8948471546173096
2023-01-21 08:42:29.157944: step: 1320/530, loss: 1.0180714130401611
2023-01-21 08:42:30.271597: step: 1324/530, loss: 0.3404025137424469
2023-01-21 08:42:31.379307: step: 1328/530, loss: 0.4013948440551758
2023-01-21 08:42:32.497901: step: 1332/530, loss: 0.8326259851455688
2023-01-21 08:42:33.596397: step: 1336/530, loss: 0.5155757665634155
2023-01-21 08:42:34.702358: step: 1340/530, loss: 0.9842905402183533
2023-01-21 08:42:35.811860: step: 1344/530, loss: 1.397153377532959
2023-01-21 08:42:36.912467: step: 1348/530, loss: 1.6116747856140137
2023-01-21 08:42:38.026107: step: 1352/530, loss: 0.9735078811645508
2023-01-21 08:42:39.122171: step: 1356/530, loss: 0.3553386628627777
2023-01-21 08:42:40.233969: step: 1360/530, loss: 0.2220364660024643
2023-01-21 08:42:41.332376: step: 1364/530, loss: 0.37782537937164307
2023-01-21 08:42:42.444463: step: 1368/530, loss: 0.1812712550163269
2023-01-21 08:42:43.541569: step: 1372/530, loss: 0.5432860851287842
2023-01-21 08:42:44.667886: step: 1376/530, loss: 0.25794145464897156
2023-01-21 08:42:45.790994: step: 1380/530, loss: 0.22914743423461914
2023-01-21 08:42:46.906061: step: 1384/530, loss: 0.10989566147327423
2023-01-21 08:42:47.989099: step: 1388/530, loss: 0.3832426965236664
2023-01-21 08:42:49.111451: step: 1392/530, loss: 0.23594056069850922
2023-01-21 08:42:50.209823: step: 1396/530, loss: 6.348154067993164
2023-01-21 08:42:51.306160: step: 1400/530, loss: 0.5787858963012695
2023-01-21 08:42:52.434185: step: 1404/530, loss: 0.6329714059829712
2023-01-21 08:42:53.550523: step: 1408/530, loss: 6.840663909912109
2023-01-21 08:42:54.658092: step: 1412/530, loss: 0.29743510484695435
2023-01-21 08:42:55.771172: step: 1416/530, loss: 0.4690084457397461
2023-01-21 08:42:56.870025: step: 1420/530, loss: 0.3014492988586426
2023-01-21 08:42:57.967944: step: 1424/530, loss: 0.887120246887207
2023-01-21 08:42:59.105601: step: 1428/530, loss: 0.6102879643440247
2023-01-21 08:43:00.206180: step: 1432/530, loss: 0.22859859466552734
2023-01-21 08:43:01.308180: step: 1436/530, loss: 0.18292587995529175
2023-01-21 08:43:02.410845: step: 1440/530, loss: 0.1110515147447586
2023-01-21 08:43:03.537468: step: 1444/530, loss: 0.2376570701599121
2023-01-21 08:43:04.649388: step: 1448/530, loss: 0.800528883934021
2023-01-21 08:43:05.795905: step: 1452/530, loss: 0.6649103760719299
2023-01-21 08:43:06.911601: step: 1456/530, loss: 0.6304930448532104
2023-01-21 08:43:08.056911: step: 1460/530, loss: 1.6297876834869385
2023-01-21 08:43:09.176860: step: 1464/530, loss: 3.6106503009796143
2023-01-21 08:43:10.285632: step: 1468/530, loss: 0.8605820536613464
2023-01-21 08:43:11.403735: step: 1472/530, loss: 0.6748793721199036
2023-01-21 08:43:12.516979: step: 1476/530, loss: 0.967780351638794
2023-01-21 08:43:13.626763: step: 1480/530, loss: 1.4351000785827637
2023-01-21 08:43:14.744569: step: 1484/530, loss: 0.603656530380249
2023-01-21 08:43:15.858109: step: 1488/530, loss: 7.496251583099365
2023-01-21 08:43:16.949619: step: 1492/530, loss: 1.1967928409576416
2023-01-21 08:43:18.068283: step: 1496/530, loss: 0.3948216438293457
2023-01-21 08:43:19.163454: step: 1500/530, loss: 0.34825554490089417
2023-01-21 08:43:20.261473: step: 1504/530, loss: 0.5797415375709534
2023-01-21 08:43:21.366156: step: 1508/530, loss: 0.40484657883644104
2023-01-21 08:43:22.437723: step: 1512/530, loss: 0.18350154161453247
2023-01-21 08:43:23.538201: step: 1516/530, loss: 0.1745496243238449
2023-01-21 08:43:24.700930: step: 1520/530, loss: 2.0335772037506104
2023-01-21 08:43:25.822194: step: 1524/530, loss: 0.583419144153595
2023-01-21 08:43:26.920700: step: 1528/530, loss: 0.5432870984077454
2023-01-21 08:43:28.033222: step: 1532/530, loss: 0.2994877099990845
2023-01-21 08:43:29.131088: step: 1536/530, loss: 1.1855978965759277
2023-01-21 08:43:30.227543: step: 1540/530, loss: 0.017529677599668503
2023-01-21 08:43:31.335732: step: 1544/530, loss: 0.15532922744750977
2023-01-21 08:43:32.470230: step: 1548/530, loss: 0.14575806260108948
2023-01-21 08:43:33.620977: step: 1552/530, loss: 0.6545190811157227
2023-01-21 08:43:34.730113: step: 1556/530, loss: 2.1368188858032227
2023-01-21 08:43:35.852777: step: 1560/530, loss: 0.34058934450149536
2023-01-21 08:43:36.951969: step: 1564/530, loss: 0.2849229574203491
2023-01-21 08:43:38.055538: step: 1568/530, loss: 0.7994819283485413
2023-01-21 08:43:39.179085: step: 1572/530, loss: 0.11903336644172668
2023-01-21 08:43:40.303544: step: 1576/530, loss: 0.2817000448703766
2023-01-21 08:43:41.423734: step: 1580/530, loss: 0.449527770280838
2023-01-21 08:43:42.532422: step: 1584/530, loss: 0.6340710520744324
2023-01-21 08:43:43.641648: step: 1588/530, loss: 2.8808865547180176
2023-01-21 08:43:44.727492: step: 1592/530, loss: 0.2109864056110382
2023-01-21 08:43:45.813024: step: 1596/530, loss: 1.0190500020980835
2023-01-21 08:43:46.918512: step: 1600/530, loss: 0.3280106484889984
2023-01-21 08:43:48.048689: step: 1604/530, loss: 0.5436847805976868
2023-01-21 08:43:49.132363: step: 1608/530, loss: 1.1243443489074707
2023-01-21 08:43:50.232825: step: 1612/530, loss: 2.0383827686309814
2023-01-21 08:43:51.344386: step: 1616/530, loss: 0.33474865555763245
2023-01-21 08:43:52.482630: step: 1620/530, loss: 1.7503913640975952
2023-01-21 08:43:53.627424: step: 1624/530, loss: 0.26492491364479065
2023-01-21 08:43:54.765461: step: 1628/530, loss: 6.1829023361206055
2023-01-21 08:43:55.890998: step: 1632/530, loss: 0.1590873897075653
2023-01-21 08:43:56.985717: step: 1636/530, loss: 0.1909516453742981
2023-01-21 08:43:58.082545: step: 1640/530, loss: 6.731661319732666
2023-01-21 08:43:59.180803: step: 1644/530, loss: 0.19422298669815063
2023-01-21 08:44:00.296969: step: 1648/530, loss: 1.962960124015808
2023-01-21 08:44:01.444726: step: 1652/530, loss: 0.10533075034618378
2023-01-21 08:44:02.538154: step: 1656/530, loss: 0.6906180381774902
2023-01-21 08:44:03.662350: step: 1660/530, loss: 0.8270504474639893
2023-01-21 08:44:04.747561: step: 1664/530, loss: 0.13559304177761078
2023-01-21 08:44:05.855303: step: 1668/530, loss: 0.1347503662109375
2023-01-21 08:44:06.981634: step: 1672/530, loss: 0.575066328048706
2023-01-21 08:44:08.090979: step: 1676/530, loss: 0.14067545533180237
2023-01-21 08:44:09.204406: step: 1680/530, loss: 0.7516908049583435
2023-01-21 08:44:10.297046: step: 1684/530, loss: 6.5101637840271
2023-01-21 08:44:11.402795: step: 1688/530, loss: 1.2372459173202515
2023-01-21 08:44:12.533838: step: 1692/530, loss: 0.3302198350429535
2023-01-21 08:44:13.630314: step: 1696/530, loss: 0.22318939864635468
2023-01-21 08:44:14.740257: step: 1700/530, loss: 0.09426946938037872
2023-01-21 08:44:15.828406: step: 1704/530, loss: 0.27652445435523987
2023-01-21 08:44:16.933872: step: 1708/530, loss: 2.6318087577819824
2023-01-21 08:44:18.023152: step: 1712/530, loss: 0.11620178818702698
2023-01-21 08:44:19.143599: step: 1716/530, loss: 0.1317480206489563
2023-01-21 08:44:20.286518: step: 1720/530, loss: 1.7940690517425537
2023-01-21 08:44:21.384206: step: 1724/530, loss: 1.6589747667312622
2023-01-21 08:44:22.464645: step: 1728/530, loss: 0.8428720235824585
2023-01-21 08:44:23.604601: step: 1732/530, loss: 0.5653031468391418
2023-01-21 08:44:24.732477: step: 1736/530, loss: 0.4600246548652649
2023-01-21 08:44:25.883009: step: 1740/530, loss: 0.794142484664917
2023-01-21 08:44:26.973069: step: 1744/530, loss: 0.1945888102054596
2023-01-21 08:44:28.062300: step: 1748/530, loss: 0.3469984829425812
2023-01-21 08:44:29.162238: step: 1752/530, loss: 0.4326963424682617
2023-01-21 08:44:30.276466: step: 1756/530, loss: 0.4124979078769684
2023-01-21 08:44:31.400572: step: 1760/530, loss: 0.47238463163375854
2023-01-21 08:44:32.505272: step: 1764/530, loss: 0.14860983192920685
2023-01-21 08:44:33.627248: step: 1768/530, loss: 0.09306001663208008
2023-01-21 08:44:34.747186: step: 1772/530, loss: 0.22691026329994202
2023-01-21 08:44:35.856024: step: 1776/530, loss: 0.9747693538665771
2023-01-21 08:44:36.968409: step: 1780/530, loss: 0.20004530251026154
2023-01-21 08:44:38.063649: step: 1784/530, loss: 0.494042307138443
2023-01-21 08:44:39.218995: step: 1788/530, loss: 1.4173266887664795
2023-01-21 08:44:40.335327: step: 1792/530, loss: 0.1959010660648346
2023-01-21 08:44:41.446952: step: 1796/530, loss: 0.04304571449756622
2023-01-21 08:44:42.566984: step: 1800/530, loss: 0.23430344462394714
2023-01-21 08:44:43.651446: step: 1804/530, loss: 0.44915252923965454
2023-01-21 08:44:44.792885: step: 1808/530, loss: 0.4876177906990051
2023-01-21 08:44:45.907194: step: 1812/530, loss: 0.5615189671516418
2023-01-21 08:44:47.037241: step: 1816/530, loss: 0.5588340759277344
2023-01-21 08:44:48.166941: step: 1820/530, loss: 0.8740360140800476
2023-01-21 08:44:49.305040: step: 1824/530, loss: 0.19792518019676208
2023-01-21 08:44:50.441283: step: 1828/530, loss: 0.8894966244697571
2023-01-21 08:44:51.546292: step: 1832/530, loss: 0.7123299241065979
2023-01-21 08:44:52.686789: step: 1836/530, loss: 7.956293106079102
2023-01-21 08:44:53.778273: step: 1840/530, loss: 0.6290836334228516
2023-01-21 08:44:54.858864: step: 1844/530, loss: 0.13174043595790863
2023-01-21 08:44:55.962226: step: 1848/530, loss: 0.05672721937298775
2023-01-21 08:44:57.054154: step: 1852/530, loss: 0.2497064620256424
2023-01-21 08:44:58.178874: step: 1856/530, loss: 1.2424890995025635
2023-01-21 08:44:59.294072: step: 1860/530, loss: 2.1453628540039062
2023-01-21 08:45:00.398401: step: 1864/530, loss: 0.2790115475654602
2023-01-21 08:45:01.546379: step: 1868/530, loss: 1.2661535739898682
2023-01-21 08:45:02.665984: step: 1872/530, loss: 0.19563522934913635
2023-01-21 08:45:03.803039: step: 1876/530, loss: 0.22174735367298126
2023-01-21 08:45:04.933522: step: 1880/530, loss: 0.46822452545166016
2023-01-21 08:45:06.036648: step: 1884/530, loss: 0.29099929332733154
2023-01-21 08:45:07.160939: step: 1888/530, loss: 0.22542151808738708
2023-01-21 08:45:08.280066: step: 1892/530, loss: 0.1695103645324707
2023-01-21 08:45:09.390935: step: 1896/530, loss: 0.9925119876861572
2023-01-21 08:45:10.492310: step: 1900/530, loss: 0.7793893814086914
2023-01-21 08:45:11.613224: step: 1904/530, loss: 0.2987210154533386
2023-01-21 08:45:12.738143: step: 1908/530, loss: 0.19492071866989136
2023-01-21 08:45:13.861313: step: 1912/530, loss: 0.7757922410964966
2023-01-21 08:45:14.971388: step: 1916/530, loss: 0.6475934982299805
2023-01-21 08:45:16.100393: step: 1920/530, loss: 0.14425954222679138
2023-01-21 08:45:17.179841: step: 1924/530, loss: 8.044897079467773
2023-01-21 08:45:18.285747: step: 1928/530, loss: 0.16726180911064148
2023-01-21 08:45:19.395503: step: 1932/530, loss: 3.476111650466919
2023-01-21 08:45:20.529711: step: 1936/530, loss: 0.3560600280761719
2023-01-21 08:45:21.628176: step: 1940/530, loss: 0.385974645614624
2023-01-21 08:45:22.750351: step: 1944/530, loss: 0.18302546441555023
2023-01-21 08:45:23.846637: step: 1948/530, loss: 1.3148813247680664
2023-01-21 08:45:24.966908: step: 1952/530, loss: 1.1450821161270142
2023-01-21 08:45:26.081179: step: 1956/530, loss: 0.276010662317276
2023-01-21 08:45:27.212587: step: 1960/530, loss: 0.46828946471214294
2023-01-21 08:45:28.314375: step: 1964/530, loss: 0.10745782405138016
2023-01-21 08:45:29.416921: step: 1968/530, loss: 0.2576693296432495
2023-01-21 08:45:30.542744: step: 1972/530, loss: 0.27766895294189453
2023-01-21 08:45:31.658682: step: 1976/530, loss: 0.5240230560302734
2023-01-21 08:45:32.748498: step: 1980/530, loss: 0.3402024507522583
2023-01-21 08:45:33.849602: step: 1984/530, loss: 0.24026700854301453
2023-01-21 08:45:34.958297: step: 1988/530, loss: 0.15107068419456482
2023-01-21 08:45:36.094900: step: 1992/530, loss: 0.3911333978176117
2023-01-21 08:45:37.200846: step: 1996/530, loss: 1.0349074602127075
2023-01-21 08:45:38.323266: step: 2000/530, loss: 0.5420598983764648
2023-01-21 08:45:39.412580: step: 2004/530, loss: 0.16595658659934998
2023-01-21 08:45:40.549184: step: 2008/530, loss: 0.30934134125709534
2023-01-21 08:45:41.660939: step: 2012/530, loss: 0.844071090221405
2023-01-21 08:45:42.782040: step: 2016/530, loss: 0.5643080472946167
2023-01-21 08:45:43.911383: step: 2020/530, loss: 0.19648417830467224
2023-01-21 08:45:45.055812: step: 2024/530, loss: 0.8921326398849487
2023-01-21 08:45:46.161462: step: 2028/530, loss: 0.2289905697107315
2023-01-21 08:45:47.287339: step: 2032/530, loss: 0.4843575954437256
2023-01-21 08:45:48.410067: step: 2036/530, loss: 0.09185238182544708
2023-01-21 08:45:49.521490: step: 2040/530, loss: 0.11409693211317062
2023-01-21 08:45:50.678876: step: 2044/530, loss: 1.2405942678451538
2023-01-21 08:45:51.814953: step: 2048/530, loss: 0.7801334261894226
2023-01-21 08:45:52.918371: step: 2052/530, loss: 0.2562309503555298
2023-01-21 08:45:54.032478: step: 2056/530, loss: 0.11504669487476349
2023-01-21 08:45:55.142406: step: 2060/530, loss: 0.12310314178466797
2023-01-21 08:45:56.216658: step: 2064/530, loss: 0.24266549944877625
2023-01-21 08:45:57.317559: step: 2068/530, loss: 0.3099118769168854
2023-01-21 08:45:58.476872: step: 2072/530, loss: 1.113924264907837
2023-01-21 08:45:59.572931: step: 2076/530, loss: 0.1543026864528656
2023-01-21 08:46:00.738989: step: 2080/530, loss: 0.3281656503677368
2023-01-21 08:46:01.853163: step: 2084/530, loss: 0.145040363073349
2023-01-21 08:46:02.987972: step: 2088/530, loss: 0.20680847764015198
2023-01-21 08:46:04.091892: step: 2092/530, loss: 0.41933003067970276
2023-01-21 08:46:05.239380: step: 2096/530, loss: 0.24388772249221802
2023-01-21 08:46:06.354485: step: 2100/530, loss: 0.12686343491077423
2023-01-21 08:46:07.459686: step: 2104/530, loss: 0.1317652463912964
2023-01-21 08:46:08.583428: step: 2108/530, loss: 0.3071400821208954
2023-01-21 08:46:09.697244: step: 2112/530, loss: 0.847781777381897
2023-01-21 08:46:10.821361: step: 2116/530, loss: 0.5406198501586914
2023-01-21 08:46:11.962037: step: 2120/530, loss: 2.2067911624908447
==================================================
Loss: 0.853
--------------------
Dev: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Test: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Chinese: {'event': {'p': 0.5303030303030303, 'r': 0.6481481481481481, 'f1': 0.5833333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Korean: {'event': {'p': 0.6190476190476191, 'r': 0.4126984126984127, 'f1': 0.49523809523809526}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Russian: {'event': {'p': 0.625, 'r': 0.4166666666666667, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Chinese: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Chinese: {'event': {'p': 0.5303030303030303, 'r': 0.6481481481481481, 'f1': 0.5833333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Korean: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'event': {'p': 0.6190476190476191, 'r': 0.4126984126984127, 'f1': 0.49523809523809526}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.625, 'r': 0.4166666666666667, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
Epoch: 2
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 08:47:06.096015: step: 4/530, loss: 0.6198540925979614
2023-01-21 08:47:07.219141: step: 8/530, loss: 1.0048609972000122
2023-01-21 08:47:08.336116: step: 12/530, loss: 0.10401640087366104
2023-01-21 08:47:09.455274: step: 16/530, loss: 0.438334196805954
2023-01-21 08:47:10.528796: step: 20/530, loss: 0.11243266612291336
2023-01-21 08:47:11.632609: step: 24/530, loss: 0.09344482421875
2023-01-21 08:47:12.725194: step: 28/530, loss: 0.0319981575012207
2023-01-21 08:47:13.860433: step: 32/530, loss: 0.8867971301078796
2023-01-21 08:47:14.983388: step: 36/530, loss: 0.07208891212940216
2023-01-21 08:47:16.095714: step: 40/530, loss: 2.2601394653320312
2023-01-21 08:47:17.197459: step: 44/530, loss: 0.2554208040237427
2023-01-21 08:47:18.308068: step: 48/530, loss: 0.5622318983078003
2023-01-21 08:47:19.461681: step: 52/530, loss: 1.9114444255828857
2023-01-21 08:47:20.587661: step: 56/530, loss: 0.22458219528198242
2023-01-21 08:47:21.713031: step: 60/530, loss: 0.376301109790802
2023-01-21 08:47:22.820559: step: 64/530, loss: 0.41722679138183594
2023-01-21 08:47:23.910748: step: 68/530, loss: 0.6288596391677856
2023-01-21 08:47:25.020620: step: 72/530, loss: 0.28783828020095825
2023-01-21 08:47:26.149089: step: 76/530, loss: 0.38284817337989807
2023-01-21 08:47:27.243704: step: 80/530, loss: 1.1731423139572144
2023-01-21 08:47:28.355800: step: 84/530, loss: 0.19999781250953674
2023-01-21 08:47:29.432974: step: 88/530, loss: 0.08881092071533203
2023-01-21 08:47:30.551602: step: 92/530, loss: 0.4845197796821594
2023-01-21 08:47:31.648909: step: 96/530, loss: 0.7929043173789978
2023-01-21 08:47:32.752963: step: 100/530, loss: 0.7115422487258911
2023-01-21 08:47:33.855103: step: 104/530, loss: 0.03243611007928848
2023-01-21 08:47:34.968578: step: 108/530, loss: 0.26674890518188477
2023-01-21 08:47:36.063218: step: 112/530, loss: 1.51459801197052
2023-01-21 08:47:37.174818: step: 116/530, loss: 0.126674085855484
2023-01-21 08:47:38.373457: step: 120/530, loss: 0.30515193939208984
2023-01-21 08:47:39.480416: step: 124/530, loss: 0.8636605143547058
2023-01-21 08:47:40.581792: step: 128/530, loss: 0.3570449650287628
2023-01-21 08:47:41.716283: step: 132/530, loss: 0.19358369708061218
2023-01-21 08:47:42.801997: step: 136/530, loss: 0.8373862504959106
2023-01-21 08:47:43.908547: step: 140/530, loss: 0.6789923906326294
2023-01-21 08:47:45.040531: step: 144/530, loss: 2.21024751663208
2023-01-21 08:47:46.151779: step: 148/530, loss: 0.19918937981128693
2023-01-21 08:47:47.301027: step: 152/530, loss: 0.24911203980445862
2023-01-21 08:47:48.407257: step: 156/530, loss: 0.6159843802452087
2023-01-21 08:47:49.545539: step: 160/530, loss: 0.15210619568824768
2023-01-21 08:47:50.646578: step: 164/530, loss: 1.9229626655578613
2023-01-21 08:47:51.755369: step: 168/530, loss: 0.4069795608520508
2023-01-21 08:47:52.883583: step: 172/530, loss: 0.6554365158081055
2023-01-21 08:47:54.024747: step: 176/530, loss: 1.0374741554260254
2023-01-21 08:47:55.125576: step: 180/530, loss: 0.44456160068511963
2023-01-21 08:47:56.268923: step: 184/530, loss: 0.44057178497314453
2023-01-21 08:47:57.360725: step: 188/530, loss: 0.07241783291101456
2023-01-21 08:47:58.471734: step: 192/530, loss: 0.0739767998456955
2023-01-21 08:47:59.602152: step: 196/530, loss: 0.17059560120105743
2023-01-21 08:48:00.721322: step: 200/530, loss: 0.10765685886144638
2023-01-21 08:48:01.836078: step: 204/530, loss: 0.3262357711791992
2023-01-21 08:48:02.947188: step: 208/530, loss: 0.20020842552185059
2023-01-21 08:48:04.071026: step: 212/530, loss: 0.5621374845504761
2023-01-21 08:48:05.202712: step: 216/530, loss: 0.3833032548427582
2023-01-21 08:48:06.273188: step: 220/530, loss: 0.2669598460197449
2023-01-21 08:48:07.402509: step: 224/530, loss: 0.38778916001319885
2023-01-21 08:48:08.525568: step: 228/530, loss: 0.19167184829711914
2023-01-21 08:48:09.663236: step: 232/530, loss: 0.7273862957954407
2023-01-21 08:48:10.768473: step: 236/530, loss: 0.18002071976661682
2023-01-21 08:48:11.868307: step: 240/530, loss: 0.3420677185058594
2023-01-21 08:48:12.993626: step: 244/530, loss: 0.6326888799667358
2023-01-21 08:48:14.158556: step: 248/530, loss: 0.1943381279706955
2023-01-21 08:48:15.279745: step: 252/530, loss: 0.7952607274055481
2023-01-21 08:48:16.374417: step: 256/530, loss: 0.204506978392601
2023-01-21 08:48:17.509209: step: 260/530, loss: 0.44783174991607666
2023-01-21 08:48:18.615225: step: 264/530, loss: 0.3366151452064514
2023-01-21 08:48:19.754430: step: 268/530, loss: 6.446836948394775
2023-01-21 08:48:20.893658: step: 272/530, loss: 1.0232226848602295
2023-01-21 08:48:22.006161: step: 276/530, loss: 0.7964997291564941
2023-01-21 08:48:23.135897: step: 280/530, loss: 0.5236971974372864
2023-01-21 08:48:24.276048: step: 284/530, loss: 0.3770301938056946
2023-01-21 08:48:25.399039: step: 288/530, loss: 0.404171347618103
2023-01-21 08:48:26.524040: step: 292/530, loss: 0.32622891664505005
2023-01-21 08:48:27.650330: step: 296/530, loss: 1.228914499282837
2023-01-21 08:48:28.764397: step: 300/530, loss: 0.21097077429294586
2023-01-21 08:48:29.888937: step: 304/530, loss: 0.5476157069206238
2023-01-21 08:48:31.009635: step: 308/530, loss: 0.7025691866874695
2023-01-21 08:48:32.113298: step: 312/530, loss: 0.459287166595459
2023-01-21 08:48:33.263009: step: 316/530, loss: 0.1931048035621643
2023-01-21 08:48:34.414017: step: 320/530, loss: 0.1928127259016037
2023-01-21 08:48:35.519194: step: 324/530, loss: 0.41293030977249146
2023-01-21 08:48:36.597781: step: 328/530, loss: 0.7993488311767578
2023-01-21 08:48:37.686538: step: 332/530, loss: 0.219730943441391
2023-01-21 08:48:38.753917: step: 336/530, loss: 0.2729508578777313
2023-01-21 08:48:39.906930: step: 340/530, loss: 0.968357503414154
2023-01-21 08:48:41.018387: step: 344/530, loss: 1.211496353149414
2023-01-21 08:48:42.118374: step: 348/530, loss: 0.1360091269016266
2023-01-21 08:48:43.209099: step: 352/530, loss: 0.1271168738603592
2023-01-21 08:48:44.338125: step: 356/530, loss: 0.21786938607692719
2023-01-21 08:48:45.476929: step: 360/530, loss: 0.758103609085083
2023-01-21 08:48:46.608069: step: 364/530, loss: 0.35645848512649536
2023-01-21 08:48:47.758549: step: 368/530, loss: 0.12861737608909607
2023-01-21 08:48:48.838650: step: 372/530, loss: 0.15587054193019867
2023-01-21 08:48:49.950274: step: 376/530, loss: 0.21404004096984863
2023-01-21 08:48:51.051434: step: 380/530, loss: 0.1603788584470749
2023-01-21 08:48:52.170515: step: 384/530, loss: 0.852162778377533
2023-01-21 08:48:53.318842: step: 388/530, loss: 0.14658966660499573
2023-01-21 08:48:54.439698: step: 392/530, loss: 0.07474938035011292
2023-01-21 08:48:55.561160: step: 396/530, loss: 0.17949095368385315
2023-01-21 08:48:56.668621: step: 400/530, loss: 0.3295811712741852
2023-01-21 08:48:57.770532: step: 404/530, loss: 0.041338253766298294
2023-01-21 08:48:58.871986: step: 408/530, loss: 0.0775061622262001
2023-01-21 08:48:59.974619: step: 412/530, loss: 0.8199677467346191
2023-01-21 08:49:01.081004: step: 416/530, loss: 0.2995205819606781
2023-01-21 08:49:02.177622: step: 420/530, loss: 0.07244706153869629
2023-01-21 08:49:03.279761: step: 424/530, loss: 0.2044380158185959
2023-01-21 08:49:04.399337: step: 428/530, loss: 0.15572519600391388
2023-01-21 08:49:05.511449: step: 432/530, loss: 0.1981772929430008
2023-01-21 08:49:06.632573: step: 436/530, loss: 0.7305552363395691
2023-01-21 08:49:07.782003: step: 440/530, loss: 0.3490244150161743
2023-01-21 08:49:08.888280: step: 444/530, loss: 0.12870512902736664
2023-01-21 08:49:09.989287: step: 448/530, loss: 0.5862518548965454
2023-01-21 08:49:11.139569: step: 452/530, loss: 1.2806965112686157
2023-01-21 08:49:12.261592: step: 456/530, loss: 0.7453708052635193
2023-01-21 08:49:13.380446: step: 460/530, loss: 2.356369972229004
2023-01-21 08:49:14.470060: step: 464/530, loss: 0.37028247117996216
2023-01-21 08:49:15.573249: step: 468/530, loss: 0.1040465384721756
2023-01-21 08:49:16.680426: step: 472/530, loss: 0.2980291247367859
2023-01-21 08:49:17.807747: step: 476/530, loss: 0.4111400842666626
2023-01-21 08:49:18.930331: step: 480/530, loss: 1.046571969985962
2023-01-21 08:49:20.053981: step: 484/530, loss: 0.12694759666919708
2023-01-21 08:49:21.205575: step: 488/530, loss: 0.4188306927680969
2023-01-21 08:49:22.319005: step: 492/530, loss: 0.16274185478687286
2023-01-21 08:49:23.406512: step: 496/530, loss: 1.4421719312667847
2023-01-21 08:49:24.511412: step: 500/530, loss: 0.5529559254646301
2023-01-21 08:49:25.655885: step: 504/530, loss: 1.087599515914917
2023-01-21 08:49:26.748466: step: 508/530, loss: 0.8141428828239441
2023-01-21 08:49:27.874859: step: 512/530, loss: 0.15626506507396698
2023-01-21 08:49:28.969905: step: 516/530, loss: 0.463449090719223
2023-01-21 08:49:30.074507: step: 520/530, loss: 0.17906340956687927
2023-01-21 08:49:31.189767: step: 524/530, loss: 0.18124504387378693
2023-01-21 08:49:32.307015: step: 528/530, loss: 0.8169660568237305
2023-01-21 08:49:33.449064: step: 532/530, loss: 0.08687052875757217
2023-01-21 08:49:34.586050: step: 536/530, loss: 0.34089356660842896
2023-01-21 08:49:35.739433: step: 540/530, loss: 6.535667419433594
2023-01-21 08:49:36.819849: step: 544/530, loss: 0.13303260505199432
2023-01-21 08:49:37.906948: step: 548/530, loss: 0.8227423429489136
2023-01-21 08:49:39.045869: step: 552/530, loss: 2.0486085414886475
2023-01-21 08:49:40.150247: step: 556/530, loss: 1.2675211429595947
2023-01-21 08:49:41.272353: step: 560/530, loss: 0.12148484587669373
2023-01-21 08:49:42.407852: step: 564/530, loss: 0.1736951768398285
2023-01-21 08:49:43.553358: step: 568/530, loss: 0.22327347099781036
2023-01-21 08:49:44.674225: step: 572/530, loss: 0.3861965835094452
2023-01-21 08:49:45.772373: step: 576/530, loss: 0.5449054837226868
2023-01-21 08:49:46.894760: step: 580/530, loss: 0.7828955054283142
2023-01-21 08:49:48.003011: step: 584/530, loss: 0.18622727692127228
2023-01-21 08:49:49.141078: step: 588/530, loss: 0.4909900724887848
2023-01-21 08:49:50.247300: step: 592/530, loss: 0.12133082747459412
2023-01-21 08:49:51.390091: step: 596/530, loss: 0.5887743234634399
2023-01-21 08:49:52.504085: step: 600/530, loss: 0.718548059463501
2023-01-21 08:49:53.596281: step: 604/530, loss: 0.6871337890625
2023-01-21 08:49:54.693660: step: 608/530, loss: 1.932072639465332
2023-01-21 08:49:55.777157: step: 612/530, loss: 0.09411783516407013
2023-01-21 08:49:56.877137: step: 616/530, loss: 6.547301769256592
2023-01-21 08:49:58.019369: step: 620/530, loss: 0.11248989403247833
2023-01-21 08:49:59.114650: step: 624/530, loss: 0.65790855884552
2023-01-21 08:50:00.229962: step: 628/530, loss: 0.42045754194259644
2023-01-21 08:50:01.339311: step: 632/530, loss: 0.235052689909935
2023-01-21 08:50:02.456141: step: 636/530, loss: 1.0346062183380127
2023-01-21 08:50:03.573774: step: 640/530, loss: 0.34569817781448364
2023-01-21 08:50:04.673804: step: 644/530, loss: 0.1865081787109375
2023-01-21 08:50:05.777862: step: 648/530, loss: 1.367523431777954
2023-01-21 08:50:06.914355: step: 652/530, loss: 1.7905677556991577
2023-01-21 08:50:08.025978: step: 656/530, loss: 0.26142510771751404
2023-01-21 08:50:09.158808: step: 660/530, loss: 0.1052650511264801
2023-01-21 08:50:10.252909: step: 664/530, loss: 0.06505956500768661
2023-01-21 08:50:11.380539: step: 668/530, loss: 0.3729133605957031
2023-01-21 08:50:12.492624: step: 672/530, loss: 1.1665695905685425
2023-01-21 08:50:13.595719: step: 676/530, loss: 6.638486862182617
2023-01-21 08:50:14.694128: step: 680/530, loss: 0.2751946449279785
2023-01-21 08:50:15.814756: step: 684/530, loss: 1.2329219579696655
2023-01-21 08:50:16.954117: step: 688/530, loss: 1.2752113342285156
2023-01-21 08:50:18.057615: step: 692/530, loss: 0.14408570528030396
2023-01-21 08:50:19.157908: step: 696/530, loss: 0.1870080530643463
2023-01-21 08:50:20.296353: step: 700/530, loss: 0.10327625274658203
2023-01-21 08:50:21.406221: step: 704/530, loss: 0.08513936400413513
2023-01-21 08:50:22.515307: step: 708/530, loss: 0.13387763500213623
2023-01-21 08:50:23.644380: step: 712/530, loss: 0.20930396020412445
2023-01-21 08:50:24.756823: step: 716/530, loss: 0.0390867218375206
2023-01-21 08:50:25.856436: step: 720/530, loss: 0.1083621084690094
2023-01-21 08:50:26.992366: step: 724/530, loss: 0.21164169907569885
2023-01-21 08:50:28.117614: step: 728/530, loss: 1.0349600315093994
2023-01-21 08:50:29.250010: step: 732/530, loss: 0.7430177330970764
2023-01-21 08:50:30.369289: step: 736/530, loss: 0.9095494747161865
2023-01-21 08:50:31.451020: step: 740/530, loss: 0.17585691809654236
2023-01-21 08:50:32.540777: step: 744/530, loss: 0.1105884537100792
2023-01-21 08:50:33.694438: step: 748/530, loss: 0.3017406165599823
2023-01-21 08:50:34.835326: step: 752/530, loss: 1.8819596767425537
2023-01-21 08:50:35.965922: step: 756/530, loss: 0.08317108452320099
2023-01-21 08:50:37.066846: step: 760/530, loss: 0.11746960133314133
2023-01-21 08:50:38.167536: step: 764/530, loss: 0.3329296112060547
2023-01-21 08:50:39.294434: step: 768/530, loss: 0.7258298993110657
2023-01-21 08:50:40.406245: step: 772/530, loss: 0.6615149974822998
2023-01-21 08:50:41.486646: step: 776/530, loss: 0.42301470041275024
2023-01-21 08:50:42.588564: step: 780/530, loss: 0.7776275873184204
2023-01-21 08:50:43.692986: step: 784/530, loss: 0.277630478143692
2023-01-21 08:50:44.802087: step: 788/530, loss: 0.11778479069471359
2023-01-21 08:50:45.900957: step: 792/530, loss: 0.546926736831665
2023-01-21 08:50:46.996177: step: 796/530, loss: 0.187687486410141
2023-01-21 08:50:48.089695: step: 800/530, loss: 1.0700546503067017
2023-01-21 08:50:49.190376: step: 804/530, loss: 0.16792288422584534
2023-01-21 08:50:50.321497: step: 808/530, loss: 0.4400085508823395
2023-01-21 08:50:51.470085: step: 812/530, loss: 0.4263395369052887
2023-01-21 08:50:52.605031: step: 816/530, loss: 0.8427593111991882
2023-01-21 08:50:53.693571: step: 820/530, loss: 0.18162737786769867
2023-01-21 08:50:54.822053: step: 824/530, loss: 0.17045126855373383
2023-01-21 08:50:55.924118: step: 828/530, loss: 0.21789920330047607
2023-01-21 08:50:57.077997: step: 832/530, loss: 0.33441415429115295
2023-01-21 08:50:58.191423: step: 836/530, loss: 0.4782443046569824
2023-01-21 08:50:59.285171: step: 840/530, loss: 0.2746063768863678
2023-01-21 08:51:00.424285: step: 844/530, loss: 0.10232143849134445
2023-01-21 08:51:01.549221: step: 848/530, loss: 0.3500874638557434
2023-01-21 08:51:02.659616: step: 852/530, loss: 0.46785441040992737
2023-01-21 08:51:03.789163: step: 856/530, loss: 1.894441843032837
2023-01-21 08:51:04.927249: step: 860/530, loss: 1.593152403831482
2023-01-21 08:51:06.047111: step: 864/530, loss: 1.164519190788269
2023-01-21 08:51:07.193574: step: 868/530, loss: 1.2089849710464478
2023-01-21 08:51:08.284192: step: 872/530, loss: 1.041414499282837
2023-01-21 08:51:09.384945: step: 876/530, loss: 0.07045307010412216
2023-01-21 08:51:10.500174: step: 880/530, loss: 0.17739133536815643
2023-01-21 08:51:11.599072: step: 884/530, loss: 0.12095470726490021
2023-01-21 08:51:12.750311: step: 888/530, loss: 0.18453478813171387
2023-01-21 08:51:13.883225: step: 892/530, loss: 0.18750068545341492
2023-01-21 08:51:14.988753: step: 896/530, loss: 0.6000241041183472
2023-01-21 08:51:16.090730: step: 900/530, loss: 0.7636511325836182
2023-01-21 08:51:17.217514: step: 904/530, loss: 0.4843316078186035
2023-01-21 08:51:18.314914: step: 908/530, loss: 2.582265853881836
2023-01-21 08:51:19.434932: step: 912/530, loss: 0.12574473023414612
2023-01-21 08:51:20.562716: step: 916/530, loss: 0.8842158913612366
2023-01-21 08:51:21.686048: step: 920/530, loss: 1.2186427116394043
2023-01-21 08:51:22.781325: step: 924/530, loss: 0.3755435347557068
2023-01-21 08:51:23.919868: step: 928/530, loss: 1.015951156616211
2023-01-21 08:51:25.030729: step: 932/530, loss: 0.3734275698661804
2023-01-21 08:51:26.158464: step: 936/530, loss: 0.12297917157411575
2023-01-21 08:51:27.293165: step: 940/530, loss: 0.3472760319709778
2023-01-21 08:51:28.420980: step: 944/530, loss: 0.11199600994586945
2023-01-21 08:51:29.543738: step: 948/530, loss: 0.27879610657691956
2023-01-21 08:51:30.647304: step: 952/530, loss: 0.4406503438949585
2023-01-21 08:51:31.746909: step: 956/530, loss: 0.6585742831230164
2023-01-21 08:51:32.852471: step: 960/530, loss: 0.34480369091033936
2023-01-21 08:51:33.955491: step: 964/530, loss: 0.23266686499118805
2023-01-21 08:51:35.122970: step: 968/530, loss: 1.4316868782043457
2023-01-21 08:51:36.233771: step: 972/530, loss: 0.6266285181045532
2023-01-21 08:51:37.323483: step: 976/530, loss: 0.6873924732208252
2023-01-21 08:51:38.446784: step: 980/530, loss: 0.1926651895046234
2023-01-21 08:51:39.539129: step: 984/530, loss: 0.36933737993240356
2023-01-21 08:51:40.640137: step: 988/530, loss: 1.355558156967163
2023-01-21 08:51:41.761400: step: 992/530, loss: 0.18986168503761292
2023-01-21 08:51:42.845099: step: 996/530, loss: 0.2724820375442505
2023-01-21 08:51:43.939477: step: 1000/530, loss: 0.7138489484786987
2023-01-21 08:51:45.068177: step: 1004/530, loss: 0.908253014087677
2023-01-21 08:51:46.164585: step: 1008/530, loss: 0.3453788757324219
2023-01-21 08:51:47.266257: step: 1012/530, loss: 0.26265090703964233
2023-01-21 08:51:48.396698: step: 1016/530, loss: 0.36064577102661133
2023-01-21 08:51:49.539432: step: 1020/530, loss: 1.2133195400238037
2023-01-21 08:51:50.640288: step: 1024/530, loss: 0.3026450276374817
2023-01-21 08:51:51.763908: step: 1028/530, loss: 0.5732296109199524
2023-01-21 08:51:52.881605: step: 1032/530, loss: 0.2008655071258545
2023-01-21 08:51:53.992100: step: 1036/530, loss: 0.2666444778442383
2023-01-21 08:51:55.111760: step: 1040/530, loss: 0.18301087617874146
2023-01-21 08:51:56.230971: step: 1044/530, loss: 0.371789813041687
2023-01-21 08:51:57.347483: step: 1048/530, loss: 0.2604500353336334
2023-01-21 08:51:58.442002: step: 1052/530, loss: 1.2724806070327759
2023-01-21 08:51:59.580650: step: 1056/530, loss: 0.2205449640750885
2023-01-21 08:52:00.679696: step: 1060/530, loss: 0.7035865783691406
2023-01-21 08:52:01.791392: step: 1064/530, loss: 0.3009626269340515
2023-01-21 08:52:02.893813: step: 1068/530, loss: 0.12284322082996368
2023-01-21 08:52:04.000217: step: 1072/530, loss: 0.025849152356386185
2023-01-21 08:52:05.148671: step: 1076/530, loss: 0.20307540893554688
2023-01-21 08:52:06.266886: step: 1080/530, loss: 0.15127727389335632
2023-01-21 08:52:07.379114: step: 1084/530, loss: 0.8298312425613403
2023-01-21 08:52:08.509642: step: 1088/530, loss: 0.3243715465068817
2023-01-21 08:52:09.615618: step: 1092/530, loss: 0.13563761115074158
2023-01-21 08:52:10.770900: step: 1096/530, loss: 0.39865627884864807
2023-01-21 08:52:11.896164: step: 1100/530, loss: 2.1657986640930176
2023-01-21 08:52:13.037450: step: 1104/530, loss: 0.6220483779907227
2023-01-21 08:52:14.138345: step: 1108/530, loss: 0.15092018246650696
2023-01-21 08:52:15.267720: step: 1112/530, loss: 0.14293909072875977
2023-01-21 08:52:16.375881: step: 1116/530, loss: 0.08171799778938293
2023-01-21 08:52:17.520843: step: 1120/530, loss: 0.8029688596725464
2023-01-21 08:52:18.643574: step: 1124/530, loss: 0.6350871920585632
2023-01-21 08:52:19.736496: step: 1128/530, loss: 1.74811589717865
2023-01-21 08:52:20.836666: step: 1132/530, loss: 0.8058034777641296
2023-01-21 08:52:21.912628: step: 1136/530, loss: 0.08519790321588516
2023-01-21 08:52:23.024371: step: 1140/530, loss: 0.15289148688316345
2023-01-21 08:52:24.160724: step: 1144/530, loss: 3.25345516204834
2023-01-21 08:52:25.251408: step: 1148/530, loss: 0.06894493103027344
2023-01-21 08:52:26.367652: step: 1152/530, loss: 0.19806723296642303
2023-01-21 08:52:27.491278: step: 1156/530, loss: 0.7688921093940735
2023-01-21 08:52:28.627079: step: 1160/530, loss: 1.1888424158096313
2023-01-21 08:52:29.749904: step: 1164/530, loss: 0.7915208339691162
2023-01-21 08:52:30.829031: step: 1168/530, loss: 0.1744750291109085
2023-01-21 08:52:31.918878: step: 1172/530, loss: 0.31733790040016174
2023-01-21 08:52:33.035597: step: 1176/530, loss: 0.17006739974021912
2023-01-21 08:52:34.158719: step: 1180/530, loss: 0.1752881109714508
2023-01-21 08:52:35.261383: step: 1184/530, loss: 0.10659889876842499
2023-01-21 08:52:36.373202: step: 1188/530, loss: 0.16496124863624573
2023-01-21 08:52:37.487376: step: 1192/530, loss: 0.08374490588903427
2023-01-21 08:52:38.635157: step: 1196/530, loss: 0.48457127809524536
2023-01-21 08:52:39.767548: step: 1200/530, loss: 0.86629718542099
2023-01-21 08:52:40.899286: step: 1204/530, loss: 1.7148301601409912
2023-01-21 08:52:42.003171: step: 1208/530, loss: 0.310912549495697
2023-01-21 08:52:43.131701: step: 1212/530, loss: 1.1179625988006592
2023-01-21 08:52:44.245063: step: 1216/530, loss: 0.2113800048828125
2023-01-21 08:52:45.366036: step: 1220/530, loss: 0.8314051628112793
2023-01-21 08:52:46.531619: step: 1224/530, loss: 1.0424354076385498
2023-01-21 08:52:47.666973: step: 1228/530, loss: 0.26289093494415283
2023-01-21 08:52:48.788760: step: 1232/530, loss: 0.13936421275138855
2023-01-21 08:52:49.875596: step: 1236/530, loss: 0.033315420150756836
2023-01-21 08:52:50.999330: step: 1240/530, loss: 0.191107839345932
2023-01-21 08:52:52.109911: step: 1244/530, loss: 0.13199162483215332
2023-01-21 08:52:53.242117: step: 1248/530, loss: 0.6805388927459717
2023-01-21 08:52:54.357644: step: 1252/530, loss: 0.5157516598701477
2023-01-21 08:52:55.476171: step: 1256/530, loss: 0.05537543445825577
2023-01-21 08:52:56.603129: step: 1260/530, loss: 0.2065807282924652
2023-01-21 08:52:57.746742: step: 1264/530, loss: 0.1371023952960968
2023-01-21 08:52:58.878690: step: 1268/530, loss: 0.20539751648902893
2023-01-21 08:52:59.973031: step: 1272/530, loss: 0.9061517119407654
2023-01-21 08:53:01.092369: step: 1276/530, loss: 0.16917529702186584
2023-01-21 08:53:02.168138: step: 1280/530, loss: 1.4723564386367798
2023-01-21 08:53:03.301292: step: 1284/530, loss: 3.0508389472961426
2023-01-21 08:53:04.443477: step: 1288/530, loss: 0.44625329971313477
2023-01-21 08:53:05.559880: step: 1292/530, loss: 0.799186646938324
2023-01-21 08:53:06.675449: step: 1296/530, loss: 0.31967276334762573
2023-01-21 08:53:07.820062: step: 1300/530, loss: 7.707324028015137
2023-01-21 08:53:08.946496: step: 1304/530, loss: 1.2140929698944092
2023-01-21 08:53:10.082449: step: 1308/530, loss: 0.9212249517440796
2023-01-21 08:53:11.201151: step: 1312/530, loss: 0.13182592391967773
2023-01-21 08:53:12.322563: step: 1316/530, loss: 0.1441677212715149
2023-01-21 08:53:13.425655: step: 1320/530, loss: 0.13301211595535278
2023-01-21 08:53:14.541002: step: 1324/530, loss: 0.7749804854393005
2023-01-21 08:53:15.634926: step: 1328/530, loss: 0.22777405381202698
2023-01-21 08:53:16.756470: step: 1332/530, loss: 0.6694890856742859
2023-01-21 08:53:17.850069: step: 1336/530, loss: 0.7204827666282654
2023-01-21 08:53:18.982320: step: 1340/530, loss: 0.5952070951461792
2023-01-21 08:53:20.071934: step: 1344/530, loss: 1.0272674560546875
2023-01-21 08:53:21.170399: step: 1348/530, loss: 0.13400086760520935
2023-01-21 08:53:22.281501: step: 1352/530, loss: 0.05876760929822922
2023-01-21 08:53:23.420601: step: 1356/530, loss: 0.14156198501586914
2023-01-21 08:53:24.542698: step: 1360/530, loss: 0.27535486221313477
2023-01-21 08:53:25.632170: step: 1364/530, loss: 0.7866953611373901
2023-01-21 08:53:26.743568: step: 1368/530, loss: 0.7986108660697937
2023-01-21 08:53:27.841042: step: 1372/530, loss: 0.12173084914684296
2023-01-21 08:53:28.965678: step: 1376/530, loss: 3.3247289657592773
2023-01-21 08:53:30.120354: step: 1380/530, loss: 0.1582363098859787
2023-01-21 08:53:31.232692: step: 1384/530, loss: 0.32090091705322266
2023-01-21 08:53:32.384366: step: 1388/530, loss: 0.31660154461860657
2023-01-21 08:53:33.486463: step: 1392/530, loss: 0.11389555782079697
2023-01-21 08:53:34.587293: step: 1396/530, loss: 6.792057037353516
2023-01-21 08:53:35.696070: step: 1400/530, loss: 0.3331029415130615
2023-01-21 08:53:36.798474: step: 1404/530, loss: 0.13430070877075195
2023-01-21 08:53:37.935905: step: 1408/530, loss: 0.7255303263664246
2023-01-21 08:53:39.085104: step: 1412/530, loss: 0.17140713334083557
2023-01-21 08:53:40.179118: step: 1416/530, loss: 0.24750347435474396
2023-01-21 08:53:41.284153: step: 1420/530, loss: 0.01286692637950182
2023-01-21 08:53:42.417203: step: 1424/530, loss: 0.2532024383544922
2023-01-21 08:53:43.550080: step: 1428/530, loss: 0.36322012543678284
2023-01-21 08:53:44.675720: step: 1432/530, loss: 0.33569908142089844
2023-01-21 08:53:45.788139: step: 1436/530, loss: 0.47951623797416687
2023-01-21 08:53:46.859690: step: 1440/530, loss: 0.025391483679413795
2023-01-21 08:53:47.985211: step: 1444/530, loss: 0.43312615156173706
2023-01-21 08:53:49.068614: step: 1448/530, loss: 0.4438081979751587
2023-01-21 08:53:50.184558: step: 1452/530, loss: 0.5172765851020813
2023-01-21 08:53:51.281467: step: 1456/530, loss: 0.8032631278038025
2023-01-21 08:53:52.397051: step: 1460/530, loss: 0.18786612153053284
2023-01-21 08:53:53.519057: step: 1464/530, loss: 0.29978665709495544
2023-01-21 08:53:54.650728: step: 1468/530, loss: 0.10103187710046768
2023-01-21 08:53:55.798294: step: 1472/530, loss: 0.5985674858093262
2023-01-21 08:53:56.909106: step: 1476/530, loss: 1.6050618886947632
2023-01-21 08:53:58.016513: step: 1480/530, loss: 0.43668365478515625
2023-01-21 08:53:59.129093: step: 1484/530, loss: 0.3208683133125305
2023-01-21 08:54:00.230230: step: 1488/530, loss: 0.21678543090820312
2023-01-21 08:54:01.350198: step: 1492/530, loss: 0.2097928524017334
2023-01-21 08:54:02.475946: step: 1496/530, loss: 0.09417438507080078
2023-01-21 08:54:03.573990: step: 1500/530, loss: 0.3144418001174927
2023-01-21 08:54:04.682698: step: 1504/530, loss: 0.4504164159297943
2023-01-21 08:54:05.802283: step: 1508/530, loss: 0.1631878912448883
2023-01-21 08:54:06.892523: step: 1512/530, loss: 0.20983830094337463
2023-01-21 08:54:07.992125: step: 1516/530, loss: 0.8044927716255188
2023-01-21 08:54:09.092649: step: 1520/530, loss: 0.8216346502304077
2023-01-21 08:54:10.205635: step: 1524/530, loss: 1.2991403341293335
2023-01-21 08:54:11.356933: step: 1528/530, loss: 0.4122229814529419
2023-01-21 08:54:12.480896: step: 1532/530, loss: 0.12231931835412979
2023-01-21 08:54:13.582941: step: 1536/530, loss: 6.115550518035889
2023-01-21 08:54:14.723811: step: 1540/530, loss: 0.26710453629493713
2023-01-21 08:54:15.843878: step: 1544/530, loss: 0.8378282785415649
2023-01-21 08:54:16.971619: step: 1548/530, loss: 0.5501583814620972
2023-01-21 08:54:18.098529: step: 1552/530, loss: 0.4130508303642273
2023-01-21 08:54:19.203390: step: 1556/530, loss: 0.21987763047218323
2023-01-21 08:54:20.303634: step: 1560/530, loss: 0.11682038754224777
2023-01-21 08:54:21.419153: step: 1564/530, loss: 0.09674187004566193
2023-01-21 08:54:22.522651: step: 1568/530, loss: 1.7349060773849487
2023-01-21 08:54:23.616148: step: 1572/530, loss: 0.3750064969062805
2023-01-21 08:54:24.707570: step: 1576/530, loss: 0.4631040692329407
2023-01-21 08:54:25.832708: step: 1580/530, loss: 0.16033217310905457
2023-01-21 08:54:26.962139: step: 1584/530, loss: 0.8398206830024719
2023-01-21 08:54:28.080312: step: 1588/530, loss: 0.20990324020385742
2023-01-21 08:54:29.208675: step: 1592/530, loss: 0.06987433135509491
2023-01-21 08:54:30.322781: step: 1596/530, loss: 0.09451308846473694
2023-01-21 08:54:31.434681: step: 1600/530, loss: 1.1601035594940186
2023-01-21 08:54:32.523437: step: 1604/530, loss: 0.7201159596443176
2023-01-21 08:54:33.628255: step: 1608/530, loss: 0.22964802384376526
2023-01-21 08:54:34.721144: step: 1612/530, loss: 0.9415991306304932
2023-01-21 08:54:35.848850: step: 1616/530, loss: 0.1375083029270172
2023-01-21 08:54:36.967806: step: 1620/530, loss: 1.0645108222961426
2023-01-21 08:54:38.096346: step: 1624/530, loss: 0.07066698372364044
2023-01-21 08:54:39.218238: step: 1628/530, loss: 0.26522818207740784
2023-01-21 08:54:40.315605: step: 1632/530, loss: 0.15551725029945374
2023-01-21 08:54:41.420985: step: 1636/530, loss: 6.2453484535217285
2023-01-21 08:54:42.531315: step: 1640/530, loss: 1.4349058866500854
2023-01-21 08:54:43.681027: step: 1644/530, loss: 0.38430824875831604
2023-01-21 08:54:44.837633: step: 1648/530, loss: 0.0386800542473793
2023-01-21 08:54:45.941971: step: 1652/530, loss: 0.9878458976745605
2023-01-21 08:54:47.096221: step: 1656/530, loss: 0.4824739396572113
2023-01-21 08:54:48.206795: step: 1660/530, loss: 0.21563193202018738
2023-01-21 08:54:49.334055: step: 1664/530, loss: 0.652431070804596
2023-01-21 08:54:50.432015: step: 1668/530, loss: 0.1932518035173416
2023-01-21 08:54:51.562410: step: 1672/530, loss: 1.0132458209991455
2023-01-21 08:54:52.683632: step: 1676/530, loss: 1.3405945301055908
2023-01-21 08:54:53.796133: step: 1680/530, loss: 1.7321339845657349
2023-01-21 08:54:54.927463: step: 1684/530, loss: 0.21302028000354767
2023-01-21 08:54:56.043766: step: 1688/530, loss: 0.17731493711471558
2023-01-21 08:54:57.169086: step: 1692/530, loss: 0.787173867225647
2023-01-21 08:54:58.278091: step: 1696/530, loss: 0.06732568144798279
2023-01-21 08:54:59.390489: step: 1700/530, loss: 1.5915964841842651
2023-01-21 08:55:00.483087: step: 1704/530, loss: 0.15503031015396118
2023-01-21 08:55:01.562180: step: 1708/530, loss: 0.39534908533096313
2023-01-21 08:55:02.671781: step: 1712/530, loss: 0.7797166705131531
2023-01-21 08:55:03.787049: step: 1716/530, loss: 0.302786648273468
2023-01-21 08:55:04.905712: step: 1720/530, loss: 0.14499126374721527
2023-01-21 08:55:06.032473: step: 1724/530, loss: 0.20327195525169373
2023-01-21 08:55:07.144683: step: 1728/530, loss: 0.19121117889881134
2023-01-21 08:55:08.250750: step: 1732/530, loss: 0.07347283512353897
2023-01-21 08:55:09.392226: step: 1736/530, loss: 0.2325085550546646
2023-01-21 08:55:10.512370: step: 1740/530, loss: 0.33194389939308167
2023-01-21 08:55:11.638839: step: 1744/530, loss: 0.4896666705608368
2023-01-21 08:55:12.796229: step: 1748/530, loss: 2.7166733741760254
2023-01-21 08:55:13.923564: step: 1752/530, loss: 0.2241843342781067
2023-01-21 08:55:15.001085: step: 1756/530, loss: 0.0913543701171875
2023-01-21 08:55:16.127799: step: 1760/530, loss: 0.18727102875709534
2023-01-21 08:55:17.242401: step: 1764/530, loss: 0.12417125701904297
2023-01-21 08:55:18.353349: step: 1768/530, loss: 1.0505057573318481
2023-01-21 08:55:19.477226: step: 1772/530, loss: 0.22307834029197693
2023-01-21 08:55:20.570492: step: 1776/530, loss: 0.7313587665557861
2023-01-21 08:55:21.708763: step: 1780/530, loss: 0.34805068373680115
2023-01-21 08:55:22.822827: step: 1784/530, loss: 0.3424035906791687
2023-01-21 08:55:23.942971: step: 1788/530, loss: 0.2975238859653473
2023-01-21 08:55:25.044281: step: 1792/530, loss: 0.12273558974266052
2023-01-21 08:55:26.144161: step: 1796/530, loss: 0.24811871349811554
2023-01-21 08:55:27.239090: step: 1800/530, loss: 0.1386135071516037
2023-01-21 08:55:28.350570: step: 1804/530, loss: 0.6006054878234863
2023-01-21 08:55:29.499263: step: 1808/530, loss: 1.1441017389297485
2023-01-21 08:55:30.644212: step: 1812/530, loss: 0.364539235830307
2023-01-21 08:55:31.743787: step: 1816/530, loss: 0.11590547859668732
2023-01-21 08:55:32.855301: step: 1820/530, loss: 0.08323030173778534
2023-01-21 08:55:33.946143: step: 1824/530, loss: 0.09578351676464081
2023-01-21 08:55:35.098818: step: 1828/530, loss: 0.3374289572238922
2023-01-21 08:55:36.225071: step: 1832/530, loss: 0.7044450640678406
2023-01-21 08:55:37.377910: step: 1836/530, loss: 0.18089938163757324
2023-01-21 08:55:38.490880: step: 1840/530, loss: 0.1571328192949295
2023-01-21 08:55:39.621486: step: 1844/530, loss: 0.21182399988174438
2023-01-21 08:55:40.739052: step: 1848/530, loss: 6.119668960571289
2023-01-21 08:55:41.833532: step: 1852/530, loss: 1.066497802734375
2023-01-21 08:55:42.968312: step: 1856/530, loss: 0.10223408043384552
2023-01-21 08:55:44.096505: step: 1860/530, loss: 0.8984768390655518
2023-01-21 08:55:45.215542: step: 1864/530, loss: 0.39403578639030457
2023-01-21 08:55:46.381928: step: 1868/530, loss: 1.492438554763794
2023-01-21 08:55:47.492038: step: 1872/530, loss: 0.1259802281856537
2023-01-21 08:55:48.588016: step: 1876/530, loss: 0.792575478553772
2023-01-21 08:55:49.690904: step: 1880/530, loss: 0.123436838388443
2023-01-21 08:55:50.839311: step: 1884/530, loss: 0.9703875780105591
2023-01-21 08:55:51.988838: step: 1888/530, loss: 0.18645372986793518
2023-01-21 08:55:53.099798: step: 1892/530, loss: 0.22802600264549255
2023-01-21 08:55:54.182133: step: 1896/530, loss: 0.3240196406841278
2023-01-21 08:55:55.326494: step: 1900/530, loss: 1.000592827796936
2023-01-21 08:55:56.416165: step: 1904/530, loss: 1.102270483970642
2023-01-21 08:55:57.530060: step: 1908/530, loss: 0.19817887246608734
2023-01-21 08:55:58.646673: step: 1912/530, loss: 0.23716698586940765
2023-01-21 08:55:59.761376: step: 1916/530, loss: 0.3357241749763489
2023-01-21 08:56:00.854686: step: 1920/530, loss: 0.7043208479881287
2023-01-21 08:56:01.981601: step: 1924/530, loss: 1.646287202835083
2023-01-21 08:56:03.087675: step: 1928/530, loss: 0.12129730731248856
2023-01-21 08:56:04.213886: step: 1932/530, loss: 0.46441662311553955
2023-01-21 08:56:05.327992: step: 1936/530, loss: 0.7005584836006165
2023-01-21 08:56:06.434784: step: 1940/530, loss: 0.7100865244865417
2023-01-21 08:56:07.567909: step: 1944/530, loss: 0.9885145425796509
2023-01-21 08:56:08.700237: step: 1948/530, loss: 3.2612500190734863
2023-01-21 08:56:09.802003: step: 1952/530, loss: 0.6922026872634888
2023-01-21 08:56:10.922776: step: 1956/530, loss: 0.49742573499679565
2023-01-21 08:56:12.015459: step: 1960/530, loss: 0.08750258386135101
2023-01-21 08:56:13.120606: step: 1964/530, loss: 0.2963157594203949
2023-01-21 08:56:14.206232: step: 1968/530, loss: 0.1316436231136322
2023-01-21 08:56:15.337217: step: 1972/530, loss: 0.36876344680786133
2023-01-21 08:56:16.450403: step: 1976/530, loss: 0.1679573953151703
2023-01-21 08:56:17.575066: step: 1980/530, loss: 0.12748432159423828
2023-01-21 08:56:18.692343: step: 1984/530, loss: 0.11131172627210617
2023-01-21 08:56:19.780130: step: 1988/530, loss: 0.22851115465164185
2023-01-21 08:56:20.889071: step: 1992/530, loss: 0.24699802696704865
2023-01-21 08:56:21.986218: step: 1996/530, loss: 0.15700551867485046
2023-01-21 08:56:23.106271: step: 2000/530, loss: 0.5740467309951782
2023-01-21 08:56:24.231571: step: 2004/530, loss: 6.835981369018555
2023-01-21 08:56:25.335380: step: 2008/530, loss: 0.3552057147026062
2023-01-21 08:56:26.453250: step: 2012/530, loss: 0.526369571685791
2023-01-21 08:56:27.566767: step: 2016/530, loss: 0.4025844633579254
2023-01-21 08:56:28.686468: step: 2020/530, loss: 0.3946210741996765
2023-01-21 08:56:29.800824: step: 2024/530, loss: 1.455757737159729
2023-01-21 08:56:30.949273: step: 2028/530, loss: 0.4541950225830078
2023-01-21 08:56:32.045825: step: 2032/530, loss: 0.08556075394153595
2023-01-21 08:56:33.178869: step: 2036/530, loss: 0.4059714078903198
2023-01-21 08:56:34.284515: step: 2040/530, loss: 1.0014783143997192
2023-01-21 08:56:35.405350: step: 2044/530, loss: 1.0441620349884033
2023-01-21 08:56:36.520606: step: 2048/530, loss: 0.434211790561676
2023-01-21 08:56:37.618087: step: 2052/530, loss: 0.08645358681678772
2023-01-21 08:56:38.738789: step: 2056/530, loss: 0.4502546489238739
2023-01-21 08:56:39.859173: step: 2060/530, loss: 0.28457754850387573
2023-01-21 08:56:40.979482: step: 2064/530, loss: 0.1551433503627777
2023-01-21 08:56:42.129160: step: 2068/530, loss: 0.12458033859729767
2023-01-21 08:56:43.308156: step: 2072/530, loss: 0.6769781112670898
2023-01-21 08:56:44.437523: step: 2076/530, loss: 0.22615547478199005
2023-01-21 08:56:45.545077: step: 2080/530, loss: 0.14603291451931
2023-01-21 08:56:46.644850: step: 2084/530, loss: 0.43144819140434265
2023-01-21 08:56:47.741079: step: 2088/530, loss: 0.39299678802490234
2023-01-21 08:56:48.855234: step: 2092/530, loss: 1.0879460573196411
2023-01-21 08:56:49.975701: step: 2096/530, loss: 0.3912164866924286
2023-01-21 08:56:51.090629: step: 2100/530, loss: 0.18495550751686096
2023-01-21 08:56:52.226172: step: 2104/530, loss: 1.7121546268463135
2023-01-21 08:56:53.316331: step: 2108/530, loss: 0.03103170543909073
2023-01-21 08:56:54.439205: step: 2112/530, loss: 0.6823851466178894
2023-01-21 08:56:55.542861: step: 2116/530, loss: 0.42215004563331604
2023-01-21 08:56:56.663415: step: 2120/530, loss: 0.8754414916038513
==================================================
Loss: 0.635
--------------------
Dev: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Test: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Chinese: {'event': {'p': 0.5970149253731343, 'r': 0.7407407407407407, 'f1': 0.6611570247933883}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Korean: {'event': {'p': 0.7631578947368421, 'r': 0.4603174603174603, 'f1': 0.5742574257425742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Russian: {'event': {'p': 0.4482758620689655, 'r': 0.3611111111111111, 'f1': 0.39999999999999997}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.5970149253731343, 'r': 0.7407407407407407, 'f1': 0.6611570247933883}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7631578947368421, 'r': 0.4603174603174603, 'f1': 0.5742574257425742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.625, 'r': 0.4166666666666667, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
Epoch: 3
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 08:57:48.996709: step: 4/530, loss: 0.08670216053724289
2023-01-21 08:57:50.108469: step: 8/530, loss: 0.7425211071968079
2023-01-21 08:57:51.262014: step: 12/530, loss: 0.3656993508338928
2023-01-21 08:57:52.387925: step: 16/530, loss: 0.3146924078464508
2023-01-21 08:57:53.490504: step: 20/530, loss: 1.0017139911651611
2023-01-21 08:57:54.630577: step: 24/530, loss: 0.12959051132202148
2023-01-21 08:57:55.732214: step: 28/530, loss: 0.75166916847229
2023-01-21 08:57:56.853316: step: 32/530, loss: 0.21938994526863098
2023-01-21 08:57:57.934036: step: 36/530, loss: 0.6343160271644592
2023-01-21 08:57:59.046661: step: 40/530, loss: 0.8723506927490234
2023-01-21 08:58:00.145707: step: 44/530, loss: 0.44709905982017517
2023-01-21 08:58:01.291616: step: 48/530, loss: 0.31424370408058167
2023-01-21 08:58:02.433273: step: 52/530, loss: 0.1382661908864975
2023-01-21 08:58:03.573727: step: 56/530, loss: 6.676466941833496
2023-01-21 08:58:04.707920: step: 60/530, loss: 0.1759033203125
2023-01-21 08:58:05.816866: step: 64/530, loss: 0.31374847888946533
2023-01-21 08:58:06.928833: step: 68/530, loss: 1.4226709604263306
2023-01-21 08:58:08.046801: step: 72/530, loss: 0.8591247797012329
2023-01-21 08:58:09.180853: step: 76/530, loss: 0.3196790814399719
2023-01-21 08:58:10.303448: step: 80/530, loss: 0.16473107039928436
2023-01-21 08:58:11.457197: step: 84/530, loss: 0.70409095287323
2023-01-21 08:58:12.583717: step: 88/530, loss: 0.14920148253440857
2023-01-21 08:58:13.702754: step: 92/530, loss: 0.20997552573680878
2023-01-21 08:58:14.795808: step: 96/530, loss: 0.272161602973938
2023-01-21 08:58:15.920230: step: 100/530, loss: 0.8385303020477295
2023-01-21 08:58:17.018656: step: 104/530, loss: 6.085962295532227
2023-01-21 08:58:18.142065: step: 108/530, loss: 0.0804353728890419
2023-01-21 08:58:19.238603: step: 112/530, loss: 0.09981179982423782
2023-01-21 08:58:20.333415: step: 116/530, loss: 0.20557069778442383
2023-01-21 08:58:21.468583: step: 120/530, loss: 0.2691030502319336
2023-01-21 08:58:22.600712: step: 124/530, loss: 0.7972768545150757
2023-01-21 08:58:23.724644: step: 128/530, loss: 0.13556356728076935
2023-01-21 08:58:24.865001: step: 132/530, loss: 0.13424137234687805
2023-01-21 08:58:25.964137: step: 136/530, loss: 0.35784590244293213
2023-01-21 08:58:27.083265: step: 140/530, loss: 0.5922499895095825
2023-01-21 08:58:28.220859: step: 144/530, loss: 0.4132048189640045
2023-01-21 08:58:29.357951: step: 148/530, loss: 0.7321273684501648
2023-01-21 08:58:30.464556: step: 152/530, loss: 0.12386198341846466
2023-01-21 08:58:31.591489: step: 156/530, loss: 1.3878066539764404
2023-01-21 08:58:32.695449: step: 160/530, loss: 0.3810931146144867
2023-01-21 08:58:33.801989: step: 164/530, loss: 0.6954941749572754
2023-01-21 08:58:34.911978: step: 168/530, loss: 0.15395422279834747
2023-01-21 08:58:36.025927: step: 172/530, loss: 0.9973186254501343
2023-01-21 08:58:37.127785: step: 176/530, loss: 0.04411964491009712
2023-01-21 08:58:38.233391: step: 180/530, loss: 0.7023789882659912
2023-01-21 08:58:39.377027: step: 184/530, loss: 0.8713164329528809
2023-01-21 08:58:40.486411: step: 188/530, loss: 0.9401844143867493
2023-01-21 08:58:41.608009: step: 192/530, loss: 0.8185009956359863
2023-01-21 08:58:42.701947: step: 196/530, loss: 0.436969518661499
2023-01-21 08:58:43.822299: step: 200/530, loss: 0.7091817855834961
2023-01-21 08:58:44.941122: step: 204/530, loss: 0.1409766674041748
2023-01-21 08:58:46.034656: step: 208/530, loss: 0.1094006597995758
2023-01-21 08:58:47.114795: step: 212/530, loss: 0.12965813279151917
2023-01-21 08:58:48.223758: step: 216/530, loss: 0.9139938354492188
2023-01-21 08:58:49.326009: step: 220/530, loss: 0.09306040406227112
2023-01-21 08:58:50.428468: step: 224/530, loss: 0.15616711974143982
2023-01-21 08:58:51.564539: step: 228/530, loss: 0.021274946630001068
2023-01-21 08:58:52.716741: step: 232/530, loss: 0.18702411651611328
2023-01-21 08:58:53.837510: step: 236/530, loss: 0.17139950394630432
2023-01-21 08:58:54.934001: step: 240/530, loss: 0.10915222018957138
2023-01-21 08:58:56.095232: step: 244/530, loss: 1.5015275478363037
2023-01-21 08:58:57.214733: step: 248/530, loss: 0.9698035717010498
2023-01-21 08:58:58.333406: step: 252/530, loss: 0.35986635088920593
2023-01-21 08:58:59.457961: step: 256/530, loss: 0.510299801826477
2023-01-21 08:59:00.581433: step: 260/530, loss: 0.8220648169517517
2023-01-21 08:59:01.721060: step: 264/530, loss: 0.2708669900894165
2023-01-21 08:59:02.821205: step: 268/530, loss: 0.4881170988082886
2023-01-21 08:59:03.960310: step: 272/530, loss: 0.17152844369411469
2023-01-21 08:59:05.064925: step: 276/530, loss: 0.7094521522521973
2023-01-21 08:59:06.191386: step: 280/530, loss: 0.10604625195264816
2023-01-21 08:59:07.287766: step: 284/530, loss: 0.10316543281078339
2023-01-21 08:59:08.410586: step: 288/530, loss: 0.1440233290195465
2023-01-21 08:59:09.533218: step: 292/530, loss: 0.36348748207092285
2023-01-21 08:59:10.651136: step: 296/530, loss: 0.3383450508117676
2023-01-21 08:59:11.775165: step: 300/530, loss: 0.31017225980758667
2023-01-21 08:59:12.891118: step: 304/530, loss: 1.6978881359100342
2023-01-21 08:59:14.015303: step: 308/530, loss: 0.06570472568273544
2023-01-21 08:59:15.113967: step: 312/530, loss: 0.7695239782333374
2023-01-21 08:59:16.236407: step: 316/530, loss: 0.3221122622489929
2023-01-21 08:59:17.353516: step: 320/530, loss: 0.5657342076301575
2023-01-21 08:59:18.486151: step: 324/530, loss: 0.23307481408119202
2023-01-21 08:59:19.580987: step: 328/530, loss: 0.06699734181165695
2023-01-21 08:59:20.695724: step: 332/530, loss: 0.1255694329738617
2023-01-21 08:59:21.813451: step: 336/530, loss: 0.16757884621620178
2023-01-21 08:59:22.919981: step: 340/530, loss: 0.8738388419151306
2023-01-21 08:59:24.018583: step: 344/530, loss: 2.2099697589874268
2023-01-21 08:59:25.171146: step: 348/530, loss: 0.505162239074707
2023-01-21 08:59:26.302985: step: 352/530, loss: 0.10831813514232635
2023-01-21 08:59:27.426392: step: 356/530, loss: 0.1627213954925537
2023-01-21 08:59:28.538684: step: 360/530, loss: 0.09698152542114258
2023-01-21 08:59:29.691196: step: 364/530, loss: 1.482469081878662
2023-01-21 08:59:30.815979: step: 368/530, loss: 0.1507079005241394
2023-01-21 08:59:31.948261: step: 372/530, loss: 0.7500780820846558
2023-01-21 08:59:33.037977: step: 376/530, loss: 1.529564380645752
2023-01-21 08:59:34.170589: step: 380/530, loss: 0.1849079728126526
2023-01-21 08:59:35.291231: step: 384/530, loss: 1.5442430973052979
2023-01-21 08:59:36.419047: step: 388/530, loss: 0.40095075964927673
2023-01-21 08:59:37.529543: step: 392/530, loss: 0.15654778480529785
2023-01-21 08:59:38.658381: step: 396/530, loss: 0.2123951017856598
2023-01-21 08:59:39.734029: step: 400/530, loss: 0.29726600646972656
2023-01-21 08:59:40.862671: step: 404/530, loss: 0.22025828063488007
2023-01-21 08:59:41.993105: step: 408/530, loss: 0.29780083894729614
2023-01-21 08:59:43.118724: step: 412/530, loss: 0.21444548666477203
2023-01-21 08:59:44.232320: step: 416/530, loss: 0.3012157082557678
2023-01-21 08:59:45.361618: step: 420/530, loss: 2.1054866313934326
2023-01-21 08:59:46.482248: step: 424/530, loss: 0.17260809242725372
2023-01-21 08:59:47.596517: step: 428/530, loss: 0.9646400809288025
2023-01-21 08:59:48.745884: step: 432/530, loss: 0.22282180190086365
2023-01-21 08:59:49.898478: step: 436/530, loss: 0.15118694305419922
2023-01-21 08:59:51.025628: step: 440/530, loss: 0.04808444902300835
2023-01-21 08:59:52.158812: step: 444/530, loss: 0.3841272294521332
2023-01-21 08:59:53.324012: step: 448/530, loss: 0.4097677171230316
2023-01-21 08:59:54.453059: step: 452/530, loss: 0.0768706351518631
2023-01-21 08:59:55.564317: step: 456/530, loss: 0.2223808318376541
2023-01-21 08:59:56.705152: step: 460/530, loss: 0.14105224609375
2023-01-21 08:59:57.828557: step: 464/530, loss: 0.16852979362010956
2023-01-21 08:59:58.938717: step: 468/530, loss: 0.4800230860710144
2023-01-21 09:00:00.056336: step: 472/530, loss: 0.09110622107982635
2023-01-21 09:00:01.190798: step: 476/530, loss: 0.12302207946777344
2023-01-21 09:00:02.297124: step: 480/530, loss: 0.2196028232574463
2023-01-21 09:00:03.415683: step: 484/530, loss: 0.41382282972335815
2023-01-21 09:00:04.554617: step: 488/530, loss: 0.8743951320648193
2023-01-21 09:00:05.654860: step: 492/530, loss: 0.15086722373962402
2023-01-21 09:00:06.768292: step: 496/530, loss: 0.48656120896339417
2023-01-21 09:00:07.912226: step: 500/530, loss: 0.22239823639392853
2023-01-21 09:00:09.009864: step: 504/530, loss: 0.25987881422042847
2023-01-21 09:00:10.133664: step: 508/530, loss: 1.6225955486297607
2023-01-21 09:00:11.262362: step: 512/530, loss: 0.4051980972290039
2023-01-21 09:00:12.361478: step: 516/530, loss: 0.048266030848026276
2023-01-21 09:00:13.491251: step: 520/530, loss: 0.8777795433998108
2023-01-21 09:00:14.601882: step: 524/530, loss: 2.379406690597534
2023-01-21 09:00:15.752917: step: 528/530, loss: 6.20833158493042
2023-01-21 09:00:16.832875: step: 532/530, loss: 0.30463963747024536
2023-01-21 09:00:17.941064: step: 536/530, loss: 0.6157921552658081
2023-01-21 09:00:19.087615: step: 540/530, loss: 0.695269763469696
2023-01-21 09:00:20.190924: step: 544/530, loss: 0.039891719818115234
2023-01-21 09:00:21.309298: step: 548/530, loss: 0.16700954735279083
2023-01-21 09:00:22.433222: step: 552/530, loss: 0.20300647616386414
2023-01-21 09:00:23.549471: step: 556/530, loss: 1.4089555740356445
2023-01-21 09:00:24.646746: step: 560/530, loss: 0.15812574326992035
2023-01-21 09:00:25.741853: step: 564/530, loss: 0.09034595638513565
2023-01-21 09:00:26.885714: step: 568/530, loss: 0.04844699054956436
2023-01-21 09:00:27.983471: step: 572/530, loss: 0.7393420934677124
2023-01-21 09:00:29.108207: step: 576/530, loss: 0.17693018913269043
2023-01-21 09:00:30.222394: step: 580/530, loss: 0.1086801066994667
2023-01-21 09:00:31.317503: step: 584/530, loss: 0.6915250420570374
2023-01-21 09:00:32.423095: step: 588/530, loss: 0.048184920102357864
2023-01-21 09:00:33.534193: step: 592/530, loss: 0.09208717942237854
2023-01-21 09:00:34.636816: step: 596/530, loss: 0.29375720024108887
2023-01-21 09:00:35.758255: step: 600/530, loss: 0.06822118908166885
2023-01-21 09:00:36.901155: step: 604/530, loss: 0.09719639271497726
2023-01-21 09:00:38.016342: step: 608/530, loss: 0.29469040036201477
2023-01-21 09:00:39.132765: step: 612/530, loss: 0.08552694320678711
2023-01-21 09:00:40.249154: step: 616/530, loss: 0.3067701458930969
2023-01-21 09:00:41.341303: step: 620/530, loss: 0.31503018736839294
2023-01-21 09:00:42.465134: step: 624/530, loss: 0.42888134717941284
2023-01-21 09:00:43.579195: step: 628/530, loss: 0.38048458099365234
2023-01-21 09:00:44.705256: step: 632/530, loss: 0.07893228530883789
2023-01-21 09:00:45.777126: step: 636/530, loss: 0.05241525173187256
2023-01-21 09:00:46.914335: step: 640/530, loss: 0.04816789925098419
2023-01-21 09:00:48.014283: step: 644/530, loss: 0.12628765404224396
2023-01-21 09:00:49.131630: step: 648/530, loss: 0.18118058145046234
2023-01-21 09:00:50.279037: step: 652/530, loss: 0.07704129815101624
2023-01-21 09:00:51.370466: step: 656/530, loss: 0.285206139087677
2023-01-21 09:00:52.454630: step: 660/530, loss: 0.26229792833328247
2023-01-21 09:00:53.597685: step: 664/530, loss: 0.32291170954704285
2023-01-21 09:00:54.701882: step: 668/530, loss: 0.7378031611442566
2023-01-21 09:00:55.840018: step: 672/530, loss: 0.2469298392534256
2023-01-21 09:00:56.955613: step: 676/530, loss: 0.1913870871067047
2023-01-21 09:00:58.076254: step: 680/530, loss: 0.08320832252502441
2023-01-21 09:00:59.192031: step: 684/530, loss: 0.12690076231956482
2023-01-21 09:01:00.319084: step: 688/530, loss: 0.05353193357586861
2023-01-21 09:01:01.442421: step: 692/530, loss: 0.16691379249095917
2023-01-21 09:01:02.553631: step: 696/530, loss: 0.4470704197883606
2023-01-21 09:01:03.686260: step: 700/530, loss: 0.05875048413872719
2023-01-21 09:01:04.844012: step: 704/530, loss: 0.39918625354766846
2023-01-21 09:01:05.936393: step: 708/530, loss: 1.0729751586914062
2023-01-21 09:01:07.041511: step: 712/530, loss: 0.1060362383723259
2023-01-21 09:01:08.138807: step: 716/530, loss: 0.33943358063697815
2023-01-21 09:01:09.250133: step: 720/530, loss: 0.13942795991897583
2023-01-21 09:01:10.348594: step: 724/530, loss: 0.12517929077148438
2023-01-21 09:01:11.445363: step: 728/530, loss: 1.0905100107192993
2023-01-21 09:01:12.585711: step: 732/530, loss: 0.15050753951072693
2023-01-21 09:01:13.712613: step: 736/530, loss: 0.7042437791824341
2023-01-21 09:01:14.820693: step: 740/530, loss: 0.06839676201343536
2023-01-21 09:01:15.942604: step: 744/530, loss: 1.2980988025665283
2023-01-21 09:01:17.075048: step: 748/530, loss: 0.25233206152915955
2023-01-21 09:01:18.175432: step: 752/530, loss: 0.27263110876083374
2023-01-21 09:01:19.275083: step: 756/530, loss: 0.8508257269859314
2023-01-21 09:01:20.379849: step: 760/530, loss: 0.4084666669368744
2023-01-21 09:01:21.516034: step: 764/530, loss: 0.3968985676765442
2023-01-21 09:01:22.651434: step: 768/530, loss: 0.15251168608665466
2023-01-21 09:01:23.747878: step: 772/530, loss: 0.43838825821876526
2023-01-21 09:01:24.853576: step: 776/530, loss: 0.031958725303411484
2023-01-21 09:01:25.958132: step: 780/530, loss: 0.7524548768997192
2023-01-21 09:01:27.058021: step: 784/530, loss: 0.6981293559074402
2023-01-21 09:01:28.171710: step: 788/530, loss: 0.4371768534183502
2023-01-21 09:01:29.291241: step: 792/530, loss: 0.11718375980854034
2023-01-21 09:01:30.423168: step: 796/530, loss: 0.10837727040052414
2023-01-21 09:01:31.544654: step: 800/530, loss: 0.17525647580623627
2023-01-21 09:01:32.650964: step: 804/530, loss: 0.09127626568078995
2023-01-21 09:01:33.753601: step: 808/530, loss: 0.6791750192642212
2023-01-21 09:01:34.894581: step: 812/530, loss: 0.207861989736557
2023-01-21 09:01:36.025021: step: 816/530, loss: 0.6816747784614563
2023-01-21 09:01:37.145540: step: 820/530, loss: 0.3126440942287445
2023-01-21 09:01:38.235196: step: 824/530, loss: 0.0521392859518528
2023-01-21 09:01:39.333652: step: 828/530, loss: 0.22106227278709412
2023-01-21 09:01:40.494009: step: 832/530, loss: 1.3859901428222656
2023-01-21 09:01:41.596666: step: 836/530, loss: 0.19412536919116974
2023-01-21 09:01:42.710823: step: 840/530, loss: 0.2482614517211914
2023-01-21 09:01:43.840075: step: 844/530, loss: 0.7644062042236328
2023-01-21 09:01:44.916640: step: 848/530, loss: 0.15085983276367188
2023-01-21 09:01:46.014477: step: 852/530, loss: 0.06524792313575745
2023-01-21 09:01:47.166194: step: 856/530, loss: 0.1701214760541916
2023-01-21 09:01:48.321400: step: 860/530, loss: 0.1320631057024002
2023-01-21 09:01:49.392061: step: 864/530, loss: 0.03023524209856987
2023-01-21 09:01:50.540978: step: 868/530, loss: 0.28986629843711853
2023-01-21 09:01:51.647666: step: 872/530, loss: 0.07692985981702805
2023-01-21 09:01:52.755857: step: 876/530, loss: 0.13957038521766663
2023-01-21 09:01:53.903038: step: 880/530, loss: 0.23064078390598297
2023-01-21 09:01:54.991960: step: 884/530, loss: 0.15076637268066406
2023-01-21 09:01:56.121118: step: 888/530, loss: 0.3444465696811676
2023-01-21 09:01:57.268489: step: 892/530, loss: 0.33475741744041443
2023-01-21 09:01:58.359373: step: 896/530, loss: 6.4810099601745605
2023-01-21 09:01:59.490654: step: 900/530, loss: 0.18743714690208435
2023-01-21 09:02:00.596384: step: 904/530, loss: 0.7146020531654358
2023-01-21 09:02:01.714484: step: 908/530, loss: 0.190684512257576
2023-01-21 09:02:02.832344: step: 912/530, loss: 0.6810562014579773
2023-01-21 09:02:03.945231: step: 916/530, loss: 0.5636365413665771
2023-01-21 09:02:05.034527: step: 920/530, loss: 0.19980698823928833
2023-01-21 09:02:06.164684: step: 924/530, loss: 0.16233186423778534
2023-01-21 09:02:07.268331: step: 928/530, loss: 0.14314156770706177
2023-01-21 09:02:08.372825: step: 932/530, loss: 0.17189884185791016
2023-01-21 09:02:09.496242: step: 936/530, loss: 0.3483818769454956
2023-01-21 09:02:10.615772: step: 940/530, loss: 0.1581161618232727
2023-01-21 09:02:11.731389: step: 944/530, loss: 0.09267788380384445
2023-01-21 09:02:12.820601: step: 948/530, loss: 0.32012274861335754
2023-01-21 09:02:13.927346: step: 952/530, loss: 0.17555943131446838
2023-01-21 09:02:15.010381: step: 956/530, loss: 0.19807392358779907
2023-01-21 09:02:16.125582: step: 960/530, loss: 0.10608863830566406
2023-01-21 09:02:17.272142: step: 964/530, loss: 0.2038031667470932
2023-01-21 09:02:18.393481: step: 968/530, loss: 0.046420954167842865
2023-01-21 09:02:19.497646: step: 972/530, loss: 0.12392480671405792
2023-01-21 09:02:20.618618: step: 976/530, loss: 0.369844913482666
2023-01-21 09:02:21.740349: step: 980/530, loss: 0.5682188868522644
2023-01-21 09:02:22.857205: step: 984/530, loss: 0.14702053368091583
2023-01-21 09:02:23.949275: step: 988/530, loss: 0.5968596935272217
2023-01-21 09:02:25.047733: step: 992/530, loss: 0.050177861005067825
2023-01-21 09:02:26.159499: step: 996/530, loss: 0.15501317381858826
2023-01-21 09:02:27.254674: step: 1000/530, loss: 0.15395088493824005
2023-01-21 09:02:28.345303: step: 1004/530, loss: 0.0687994509935379
2023-01-21 09:02:29.492148: step: 1008/530, loss: 0.24949073791503906
2023-01-21 09:02:30.613060: step: 1012/530, loss: 0.14284944534301758
2023-01-21 09:02:31.774244: step: 1016/530, loss: 0.3091421127319336
2023-01-21 09:02:32.878505: step: 1020/530, loss: 0.7753722071647644
2023-01-21 09:02:33.987524: step: 1024/530, loss: 0.8655267953872681
2023-01-21 09:02:35.119274: step: 1028/530, loss: 0.9411481618881226
2023-01-21 09:02:36.226028: step: 1032/530, loss: 0.11449714004993439
2023-01-21 09:02:37.319586: step: 1036/530, loss: 1.0017517805099487
2023-01-21 09:02:38.435061: step: 1040/530, loss: 0.07056598365306854
2023-01-21 09:02:39.531042: step: 1044/530, loss: 0.11513514816761017
2023-01-21 09:02:40.640213: step: 1048/530, loss: 0.7276437282562256
2023-01-21 09:02:41.735664: step: 1052/530, loss: 0.02608940564095974
2023-01-21 09:02:42.856361: step: 1056/530, loss: 0.24173566699028015
2023-01-21 09:02:43.973022: step: 1060/530, loss: 0.19794926047325134
2023-01-21 09:02:45.077105: step: 1064/530, loss: 0.1670002043247223
2023-01-21 09:02:46.170083: step: 1068/530, loss: 0.029402829706668854
2023-01-21 09:02:47.322239: step: 1072/530, loss: 0.22314368188381195
2023-01-21 09:02:48.434588: step: 1076/530, loss: 0.1544853150844574
2023-01-21 09:02:49.568143: step: 1080/530, loss: 0.10663509368896484
2023-01-21 09:02:50.668639: step: 1084/530, loss: 0.3987272381782532
2023-01-21 09:02:51.793690: step: 1088/530, loss: 0.23635907471179962
2023-01-21 09:02:52.947530: step: 1092/530, loss: 0.4140813946723938
2023-01-21 09:02:54.100738: step: 1096/530, loss: 0.22514677047729492
2023-01-21 09:02:55.201742: step: 1100/530, loss: 0.23145970702171326
2023-01-21 09:02:56.334653: step: 1104/530, loss: 0.2770175039768219
2023-01-21 09:02:57.452221: step: 1108/530, loss: 0.8043496012687683
2023-01-21 09:02:58.542438: step: 1112/530, loss: 0.19974027574062347
2023-01-21 09:02:59.630992: step: 1116/530, loss: 0.7044044137001038
2023-01-21 09:03:00.757448: step: 1120/530, loss: 0.6138517260551453
2023-01-21 09:03:01.855894: step: 1124/530, loss: 0.10854730755090714
2023-01-21 09:03:02.943768: step: 1128/530, loss: 0.24727901816368103
2023-01-21 09:03:04.078376: step: 1132/530, loss: 0.5921028852462769
2023-01-21 09:03:05.180533: step: 1136/530, loss: 0.06702842563390732
2023-01-21 09:03:06.273146: step: 1140/530, loss: 0.8548246622085571
2023-01-21 09:03:07.392452: step: 1144/530, loss: 0.029693983495235443
2023-01-21 09:03:08.517883: step: 1148/530, loss: 0.5369237661361694
2023-01-21 09:03:09.649666: step: 1152/530, loss: 0.368988037109375
2023-01-21 09:03:10.793652: step: 1156/530, loss: 0.8940134048461914
2023-01-21 09:03:11.908987: step: 1160/530, loss: 0.09035807102918625
2023-01-21 09:03:12.999784: step: 1164/530, loss: 0.498096227645874
2023-01-21 09:03:14.086779: step: 1168/530, loss: 0.17247219383716583
2023-01-21 09:03:15.214796: step: 1172/530, loss: 0.3165737986564636
2023-01-21 09:03:16.293945: step: 1176/530, loss: 0.09919185936450958
2023-01-21 09:03:17.415790: step: 1180/530, loss: 0.38924649357795715
2023-01-21 09:03:18.508473: step: 1184/530, loss: 0.08071485161781311
2023-01-21 09:03:19.613362: step: 1188/530, loss: 0.3586675226688385
2023-01-21 09:03:20.731700: step: 1192/530, loss: 0.13473773002624512
2023-01-21 09:03:21.847021: step: 1196/530, loss: 0.18251752853393555
2023-01-21 09:03:22.958119: step: 1200/530, loss: 0.21075686812400818
2023-01-21 09:03:24.049344: step: 1204/530, loss: 0.2585081458091736
2023-01-21 09:03:25.176173: step: 1208/530, loss: 6.483245372772217
2023-01-21 09:03:26.269328: step: 1212/530, loss: 0.09810562431812286
2023-01-21 09:03:27.381771: step: 1216/530, loss: 0.6704650521278381
2023-01-21 09:03:28.500984: step: 1220/530, loss: 0.2988787293434143
2023-01-21 09:03:29.669217: step: 1224/530, loss: 2.280733346939087
2023-01-21 09:03:30.834936: step: 1228/530, loss: 0.7969030141830444
2023-01-21 09:03:31.978947: step: 1232/530, loss: 0.7011225819587708
2023-01-21 09:03:33.109339: step: 1236/530, loss: 0.09697170555591583
2023-01-21 09:03:34.241572: step: 1240/530, loss: 0.17139454185962677
2023-01-21 09:03:35.387096: step: 1244/530, loss: 0.6216720342636108
2023-01-21 09:03:36.498111: step: 1248/530, loss: 0.11119508743286133
2023-01-21 09:03:37.616937: step: 1252/530, loss: 0.7147852182388306
2023-01-21 09:03:38.718951: step: 1256/530, loss: 0.7016855478286743
2023-01-21 09:03:39.854081: step: 1260/530, loss: 0.16261878609657288
2023-01-21 09:03:40.983248: step: 1264/530, loss: 0.3030509948730469
2023-01-21 09:03:42.064479: step: 1268/530, loss: 0.14998197555541992
2023-01-21 09:03:43.159106: step: 1272/530, loss: 0.4762714207172394
2023-01-21 09:03:44.235262: step: 1276/530, loss: 0.05845193937420845
2023-01-21 09:03:45.336234: step: 1280/530, loss: 0.06526260823011398
2023-01-21 09:03:46.410900: step: 1284/530, loss: 0.6663269400596619
2023-01-21 09:03:47.516242: step: 1288/530, loss: 0.11761841922998428
2023-01-21 09:03:48.635572: step: 1292/530, loss: 0.8493305444717407
2023-01-21 09:03:49.770882: step: 1296/530, loss: 0.30929630994796753
2023-01-21 09:03:50.897733: step: 1300/530, loss: 0.16514426469802856
2023-01-21 09:03:52.010293: step: 1304/530, loss: 0.2481299638748169
2023-01-21 09:03:53.142244: step: 1308/530, loss: 0.21487656235694885
2023-01-21 09:03:54.269925: step: 1312/530, loss: 0.15511319041252136
2023-01-21 09:03:55.383664: step: 1316/530, loss: 0.34609389305114746
2023-01-21 09:03:56.482775: step: 1320/530, loss: 0.05653705447912216
2023-01-21 09:03:57.578855: step: 1324/530, loss: 0.16819362342357635
2023-01-21 09:03:58.694246: step: 1328/530, loss: 0.06947198510169983
2023-01-21 09:03:59.814368: step: 1332/530, loss: 0.17193670570850372
2023-01-21 09:04:00.946456: step: 1336/530, loss: 0.6116697788238525
2023-01-21 09:04:02.048348: step: 1340/530, loss: 0.26307305693626404
2023-01-21 09:04:03.165329: step: 1344/530, loss: 0.17689037322998047
2023-01-21 09:04:04.276203: step: 1348/530, loss: 0.06488504260778427
2023-01-21 09:04:05.391580: step: 1352/530, loss: 0.0031575204338878393
2023-01-21 09:04:06.524661: step: 1356/530, loss: 0.14478006958961487
2023-01-21 09:04:07.630142: step: 1360/530, loss: 0.328853040933609
2023-01-21 09:04:08.768006: step: 1364/530, loss: 0.12356052547693253
2023-01-21 09:04:09.887548: step: 1368/530, loss: 0.16449356079101562
2023-01-21 09:04:10.993742: step: 1372/530, loss: 0.13608606159687042
2023-01-21 09:04:12.112882: step: 1376/530, loss: 0.20090952515602112
2023-01-21 09:04:13.269220: step: 1380/530, loss: 0.811094343662262
2023-01-21 09:04:14.383269: step: 1384/530, loss: 0.18214932084083557
2023-01-21 09:04:15.490610: step: 1388/530, loss: 0.20756787061691284
2023-01-21 09:04:16.629415: step: 1392/530, loss: 3.0630927085876465
2023-01-21 09:04:17.741232: step: 1396/530, loss: 0.30200138688087463
2023-01-21 09:04:18.872545: step: 1400/530, loss: 0.36907511949539185
2023-01-21 09:04:19.990405: step: 1404/530, loss: 0.1349874585866928
2023-01-21 09:04:21.094370: step: 1408/530, loss: 0.13987398147583008
2023-01-21 09:04:22.209405: step: 1412/530, loss: 0.6564210653305054
2023-01-21 09:04:23.323271: step: 1416/530, loss: 0.2468002289533615
2023-01-21 09:04:24.420343: step: 1420/530, loss: 0.7673401832580566
2023-01-21 09:04:25.559758: step: 1424/530, loss: 0.16532397270202637
2023-01-21 09:04:26.677103: step: 1428/530, loss: 0.488692969083786
2023-01-21 09:04:27.793742: step: 1432/530, loss: 0.7249547243118286
2023-01-21 09:04:28.934992: step: 1436/530, loss: 0.25163841247558594
2023-01-21 09:04:30.026852: step: 1440/530, loss: 0.14037880301475525
2023-01-21 09:04:31.132899: step: 1444/530, loss: 0.10882120579481125
2023-01-21 09:04:32.226090: step: 1448/530, loss: 0.09499195218086243
2023-01-21 09:04:33.332934: step: 1452/530, loss: 0.47806328535079956
2023-01-21 09:04:34.469154: step: 1456/530, loss: 0.6608163714408875
2023-01-21 09:04:35.600400: step: 1460/530, loss: 1.335606575012207
2023-01-21 09:04:36.710179: step: 1464/530, loss: 0.082666777074337
2023-01-21 09:04:37.824761: step: 1468/530, loss: 0.1971803605556488
2023-01-21 09:04:38.929226: step: 1472/530, loss: 0.42231154441833496
2023-01-21 09:04:40.058358: step: 1476/530, loss: 0.37188807129859924
2023-01-21 09:04:41.165391: step: 1480/530, loss: 0.16070471704006195
2023-01-21 09:04:42.264761: step: 1484/530, loss: 0.3102894723415375
2023-01-21 09:04:43.358922: step: 1488/530, loss: 0.6405572891235352
2023-01-21 09:04:44.457483: step: 1492/530, loss: 0.6251281499862671
2023-01-21 09:04:45.574499: step: 1496/530, loss: 0.10793576389551163
2023-01-21 09:04:46.685093: step: 1500/530, loss: 0.060509875416755676
2023-01-21 09:04:47.838367: step: 1504/530, loss: 0.28500452637672424
2023-01-21 09:04:48.953086: step: 1508/530, loss: 0.14901180565357208
2023-01-21 09:04:50.037277: step: 1512/530, loss: 0.18699979782104492
2023-01-21 09:04:51.134877: step: 1516/530, loss: 0.15403318405151367
2023-01-21 09:04:52.266074: step: 1520/530, loss: 0.2750725746154785
2023-01-21 09:04:53.369888: step: 1524/530, loss: 0.7165981531143188
2023-01-21 09:04:54.503261: step: 1528/530, loss: 0.20892955362796783
2023-01-21 09:04:55.598994: step: 1532/530, loss: 0.794428288936615
2023-01-21 09:04:56.715933: step: 1536/530, loss: 0.7577297687530518
2023-01-21 09:04:57.838119: step: 1540/530, loss: 0.2666401267051697
2023-01-21 09:04:58.934066: step: 1544/530, loss: 0.12612737715244293
2023-01-21 09:05:00.049918: step: 1548/530, loss: 0.11761835217475891
2023-01-21 09:05:01.149121: step: 1552/530, loss: 1.6039170026779175
2023-01-21 09:05:02.248218: step: 1556/530, loss: 0.13649287819862366
2023-01-21 09:05:03.385769: step: 1560/530, loss: 0.2975988984107971
2023-01-21 09:05:04.506459: step: 1564/530, loss: 0.14498673379421234
2023-01-21 09:05:05.619643: step: 1568/530, loss: 0.16661281883716583
2023-01-21 09:05:06.740020: step: 1572/530, loss: 0.20801010727882385
2023-01-21 09:05:07.857875: step: 1576/530, loss: 1.2460899353027344
2023-01-21 09:05:08.985234: step: 1580/530, loss: 0.18675652146339417
2023-01-21 09:05:10.119708: step: 1584/530, loss: 0.8845086693763733
2023-01-21 09:05:11.254751: step: 1588/530, loss: 0.21355904638767242
2023-01-21 09:05:12.359588: step: 1592/530, loss: 0.5205184817314148
2023-01-21 09:05:13.452759: step: 1596/530, loss: 0.33425962924957275
2023-01-21 09:05:14.582568: step: 1600/530, loss: 0.14664211869239807
2023-01-21 09:05:15.697578: step: 1604/530, loss: 0.15042009949684143
2023-01-21 09:05:16.797363: step: 1608/530, loss: 0.25238358974456787
2023-01-21 09:05:17.889049: step: 1612/530, loss: 0.6788644790649414
2023-01-21 09:05:18.999418: step: 1616/530, loss: 0.7578309774398804
2023-01-21 09:05:20.121895: step: 1620/530, loss: 0.3974772095680237
2023-01-21 09:05:21.214560: step: 1624/530, loss: 0.06993112713098526
2023-01-21 09:05:22.332102: step: 1628/530, loss: 0.17946434020996094
2023-01-21 09:05:23.437409: step: 1632/530, loss: 0.7522901892662048
2023-01-21 09:05:24.538716: step: 1636/530, loss: 0.1679244041442871
2023-01-21 09:05:25.686842: step: 1640/530, loss: 0.14097467064857483
2023-01-21 09:05:26.803639: step: 1644/530, loss: 0.35110291838645935
2023-01-21 09:05:27.921003: step: 1648/530, loss: 0.10240183770656586
2023-01-21 09:05:29.038617: step: 1652/530, loss: 0.7020695805549622
2023-01-21 09:05:30.152476: step: 1656/530, loss: 0.7162157297134399
2023-01-21 09:05:31.257641: step: 1660/530, loss: 1.0253666639328003
2023-01-21 09:05:32.397735: step: 1664/530, loss: 0.15080061554908752
2023-01-21 09:05:33.514430: step: 1668/530, loss: 0.11613388359546661
2023-01-21 09:05:34.641252: step: 1672/530, loss: 0.8429597020149231
2023-01-21 09:05:35.760155: step: 1676/530, loss: 0.46606865525245667
2023-01-21 09:05:36.862256: step: 1680/530, loss: 0.16241370141506195
2023-01-21 09:05:37.987184: step: 1684/530, loss: 0.40332090854644775
2023-01-21 09:05:39.078740: step: 1688/530, loss: 0.401131272315979
2023-01-21 09:05:40.200177: step: 1692/530, loss: 0.6422019600868225
2023-01-21 09:05:41.305453: step: 1696/530, loss: 0.20374079048633575
2023-01-21 09:05:42.425033: step: 1700/530, loss: 0.11263875663280487
2023-01-21 09:05:43.543188: step: 1704/530, loss: 0.09507761150598526
2023-01-21 09:05:44.652624: step: 1708/530, loss: 1.0796654224395752
2023-01-21 09:05:45.772848: step: 1712/530, loss: 0.1146307960152626
2023-01-21 09:05:46.852361: step: 1716/530, loss: 0.635841429233551
2023-01-21 09:05:47.955083: step: 1720/530, loss: 0.17098593711853027
2023-01-21 09:05:49.080388: step: 1724/530, loss: 0.26894569396972656
2023-01-21 09:05:50.204207: step: 1728/530, loss: 0.2519933581352234
2023-01-21 09:05:51.311113: step: 1732/530, loss: 0.08846788108348846
2023-01-21 09:05:52.467992: step: 1736/530, loss: 1.0635778903961182
2023-01-21 09:05:53.534306: step: 1740/530, loss: 0.19321660697460175
2023-01-21 09:05:54.620405: step: 1744/530, loss: 1.8589887619018555
2023-01-21 09:05:55.727458: step: 1748/530, loss: 0.28469669818878174
2023-01-21 09:05:56.847795: step: 1752/530, loss: 0.12295150756835938
2023-01-21 09:05:57.946126: step: 1756/530, loss: 0.10439954698085785
2023-01-21 09:05:59.065096: step: 1760/530, loss: 1.2381031513214111
2023-01-21 09:06:00.182763: step: 1764/530, loss: 0.6346668004989624
2023-01-21 09:06:01.302815: step: 1768/530, loss: 0.30067309737205505
2023-01-21 09:06:02.408966: step: 1772/530, loss: 0.7033620476722717
2023-01-21 09:06:03.511917: step: 1776/530, loss: 0.17614135146141052
2023-01-21 09:06:04.615734: step: 1780/530, loss: 0.1508616954088211
2023-01-21 09:06:05.707981: step: 1784/530, loss: 0.1192924976348877
2023-01-21 09:06:06.838261: step: 1788/530, loss: 0.13729210197925568
2023-01-21 09:06:07.940345: step: 1792/530, loss: 0.07399387657642365
2023-01-21 09:06:09.037318: step: 1796/530, loss: 0.16635599732398987
2023-01-21 09:06:10.121436: step: 1800/530, loss: 0.7485564351081848
2023-01-21 09:06:11.228354: step: 1804/530, loss: 0.905587911605835
2023-01-21 09:06:12.370457: step: 1808/530, loss: 0.7672727704048157
2023-01-21 09:06:13.481773: step: 1812/530, loss: 0.6557892560958862
2023-01-21 09:06:14.567849: step: 1816/530, loss: 0.18514873087406158
2023-01-21 09:06:15.692253: step: 1820/530, loss: 0.12211170047521591
2023-01-21 09:06:16.800418: step: 1824/530, loss: 0.21593904495239258
2023-01-21 09:06:17.916987: step: 1828/530, loss: 0.21972951292991638
2023-01-21 09:06:19.014049: step: 1832/530, loss: 0.05491485446691513
2023-01-21 09:06:20.124579: step: 1836/530, loss: 0.4267908036708832
2023-01-21 09:06:21.253409: step: 1840/530, loss: 0.08494883030653
2023-01-21 09:06:22.357203: step: 1844/530, loss: 0.6058789491653442
2023-01-21 09:06:23.459327: step: 1848/530, loss: 0.23098888993263245
2023-01-21 09:06:24.584050: step: 1852/530, loss: 0.09253339469432831
2023-01-21 09:06:25.698943: step: 1856/530, loss: 0.8830114006996155
2023-01-21 09:06:26.805865: step: 1860/530, loss: 0.5928334593772888
2023-01-21 09:06:27.901533: step: 1864/530, loss: 0.3347776532173157
2023-01-21 09:06:29.060489: step: 1868/530, loss: 0.21104544401168823
2023-01-21 09:06:30.130098: step: 1872/530, loss: 0.4050540328025818
2023-01-21 09:06:31.247285: step: 1876/530, loss: 0.3125300407409668
2023-01-21 09:06:32.338012: step: 1880/530, loss: 0.1035439521074295
2023-01-21 09:06:33.428906: step: 1884/530, loss: 0.9132490158081055
2023-01-21 09:06:34.558584: step: 1888/530, loss: 0.9309858083724976
2023-01-21 09:06:35.674753: step: 1892/530, loss: 0.22997914254665375
2023-01-21 09:06:36.841387: step: 1896/530, loss: 0.6879859566688538
2023-01-21 09:06:37.930041: step: 1900/530, loss: 0.0967191755771637
2023-01-21 09:06:39.017193: step: 1904/530, loss: 0.1181757003068924
2023-01-21 09:06:40.150019: step: 1908/530, loss: 0.6646278500556946
2023-01-21 09:06:41.245576: step: 1912/530, loss: 0.2726823687553406
2023-01-21 09:06:42.356434: step: 1916/530, loss: 0.021289754658937454
2023-01-21 09:06:43.454134: step: 1920/530, loss: 0.700293779373169
2023-01-21 09:06:44.527284: step: 1924/530, loss: 0.5711280107498169
2023-01-21 09:06:45.625235: step: 1928/530, loss: 0.054721929132938385
2023-01-21 09:06:46.712232: step: 1932/530, loss: 0.26529660820961
2023-01-21 09:06:47.802734: step: 1936/530, loss: 0.31876295804977417
2023-01-21 09:06:48.937112: step: 1940/530, loss: 0.4228634536266327
2023-01-21 09:06:50.058931: step: 1944/530, loss: 0.48816490173339844
2023-01-21 09:06:51.179734: step: 1948/530, loss: 0.8233122825622559
2023-01-21 09:06:52.273536: step: 1952/530, loss: 0.8538753986358643
2023-01-21 09:06:53.386435: step: 1956/530, loss: 0.2578861117362976
2023-01-21 09:06:54.540096: step: 1960/530, loss: 0.6171329617500305
2023-01-21 09:06:55.626774: step: 1964/530, loss: 0.07076912373304367
2023-01-21 09:06:56.734408: step: 1968/530, loss: 0.14071793854236603
2023-01-21 09:06:57.849139: step: 1972/530, loss: 0.1859898567199707
2023-01-21 09:06:58.953515: step: 1976/530, loss: 0.17195367813110352
2023-01-21 09:07:00.048573: step: 1980/530, loss: 7.5247111320495605
2023-01-21 09:07:01.158468: step: 1984/530, loss: 0.1225653663277626
2023-01-21 09:07:02.302233: step: 1988/530, loss: 0.2066626250743866
2023-01-21 09:07:03.437334: step: 1992/530, loss: 0.18610382080078125
2023-01-21 09:07:04.565849: step: 1996/530, loss: 0.1112181693315506
2023-01-21 09:07:05.700742: step: 2000/530, loss: 0.10484237968921661
2023-01-21 09:07:06.839199: step: 2004/530, loss: 0.09429559856653214
2023-01-21 09:07:07.927294: step: 2008/530, loss: 0.04843835532665253
2023-01-21 09:07:09.026753: step: 2012/530, loss: 0.02923755720257759
2023-01-21 09:07:10.159318: step: 2016/530, loss: 0.27962738275527954
2023-01-21 09:07:11.295453: step: 2020/530, loss: 0.874119758605957
2023-01-21 09:07:12.403854: step: 2024/530, loss: 0.09276409447193146
2023-01-21 09:07:13.508716: step: 2028/530, loss: 0.5249509811401367
2023-01-21 09:07:14.621408: step: 2032/530, loss: 0.17505702376365662
2023-01-21 09:07:15.741889: step: 2036/530, loss: 0.6410484910011292
2023-01-21 09:07:16.847503: step: 2040/530, loss: 0.18552275002002716
2023-01-21 09:07:17.946795: step: 2044/530, loss: 0.599799633026123
2023-01-21 09:07:19.045733: step: 2048/530, loss: 0.10962982475757599
2023-01-21 09:07:20.145878: step: 2052/530, loss: 0.20413756370544434
2023-01-21 09:07:21.239809: step: 2056/530, loss: 0.17080727219581604
2023-01-21 09:07:22.359560: step: 2060/530, loss: 0.3450661599636078
2023-01-21 09:07:23.443011: step: 2064/530, loss: 0.08914312720298767
2023-01-21 09:07:24.563449: step: 2068/530, loss: 0.3270234167575836
2023-01-21 09:07:25.658559: step: 2072/530, loss: 1.773456335067749
2023-01-21 09:07:26.791580: step: 2076/530, loss: 0.45344531536102295
2023-01-21 09:07:27.904676: step: 2080/530, loss: 0.7403789758682251
2023-01-21 09:07:28.995100: step: 2084/530, loss: 0.14244294166564941
2023-01-21 09:07:30.094547: step: 2088/530, loss: 0.08439214527606964
2023-01-21 09:07:31.230360: step: 2092/530, loss: 0.6644097566604614
2023-01-21 09:07:32.334134: step: 2096/530, loss: 0.037229396402835846
2023-01-21 09:07:33.456435: step: 2100/530, loss: 0.16258402168750763
2023-01-21 09:07:34.538165: step: 2104/530, loss: 0.20126695930957794
2023-01-21 09:07:35.646438: step: 2108/530, loss: 0.3019723892211914
2023-01-21 09:07:36.764879: step: 2112/530, loss: 0.13762417435646057
2023-01-21 09:07:37.879534: step: 2116/530, loss: 0.15680614113807678
2023-01-21 09:07:39.004082: step: 2120/530, loss: 0.8581370711326599
==================================================
Loss: 0.457
--------------------
Dev: {'event': {'p': 0.5368007850834151, 'r': 0.7283621837549934, 'f1': 0.6180790960451978}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Test: {'event': {'p': 0.5938209904588824, 'r': 0.7616550116550117, 'f1': 0.6673474597906561}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Chinese: {'event': {'p': 0.5507246376811594, 'r': 0.7037037037037037, 'f1': 0.6178861788617886}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Korean: {'event': {'p': 0.5892857142857143, 'r': 0.5238095238095238, 'f1': 0.5546218487394958}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Russian: {'event': {'p': 0.391304347826087, 'r': 0.5, 'f1': 0.4390243902439025}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.5970149253731343, 'r': 0.7407407407407407, 'f1': 0.6611570247933883}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7631578947368421, 'r': 0.4603174603174603, 'f1': 0.5742574257425742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.625, 'r': 0.4166666666666667, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
Epoch: 4
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 09:08:18.824159: step: 4/530, loss: 0.04388447105884552
2023-01-21 09:08:19.938298: step: 8/530, loss: 0.11198602616786957
2023-01-21 09:08:21.078317: step: 12/530, loss: 0.17019163072109222
2023-01-21 09:08:22.180120: step: 16/530, loss: 0.07312774658203125
2023-01-21 09:08:23.287735: step: 20/530, loss: 0.14284630119800568
2023-01-21 09:08:24.390574: step: 24/530, loss: 6.983399868011475
2023-01-21 09:08:25.517523: step: 28/530, loss: 0.08075971156358719
2023-01-21 09:08:26.629830: step: 32/530, loss: 0.16543205082416534
2023-01-21 09:08:27.771882: step: 36/530, loss: 0.08619938045740128
2023-01-21 09:08:28.924704: step: 40/530, loss: 0.2631988525390625
2023-01-21 09:08:30.035576: step: 44/530, loss: 0.03482332453131676
2023-01-21 09:08:31.171816: step: 48/530, loss: 0.10708332061767578
2023-01-21 09:08:32.280506: step: 52/530, loss: 0.16978469491004944
2023-01-21 09:08:33.408838: step: 56/530, loss: 0.5531366467475891
2023-01-21 09:08:34.495429: step: 60/530, loss: 0.12346000969409943
2023-01-21 09:08:35.623212: step: 64/530, loss: 0.15774431824684143
2023-01-21 09:08:36.727250: step: 68/530, loss: 0.12009501457214355
2023-01-21 09:08:37.831147: step: 72/530, loss: 0.12849397957324982
2023-01-21 09:08:38.930274: step: 76/530, loss: 0.09989356994628906
2023-01-21 09:08:40.045685: step: 80/530, loss: 0.10430637001991272
2023-01-21 09:08:41.162996: step: 84/530, loss: 0.6266195178031921
2023-01-21 09:08:42.278600: step: 88/530, loss: 0.8400307893753052
2023-01-21 09:08:43.400578: step: 92/530, loss: 0.9327991604804993
2023-01-21 09:08:44.511732: step: 96/530, loss: 0.08378791809082031
2023-01-21 09:08:45.624099: step: 100/530, loss: 0.14061537384986877
2023-01-21 09:08:46.727554: step: 104/530, loss: 0.420955091714859
2023-01-21 09:08:47.846017: step: 108/530, loss: 0.10666060447692871
2023-01-21 09:08:48.956676: step: 112/530, loss: 0.7087104916572571
2023-01-21 09:08:50.049927: step: 116/530, loss: 0.04850292205810547
2023-01-21 09:08:51.146859: step: 120/530, loss: 0.324055552482605
2023-01-21 09:08:52.253689: step: 124/530, loss: 0.19033299386501312
2023-01-21 09:08:53.367799: step: 128/530, loss: 6.236368179321289
2023-01-21 09:08:54.446777: step: 132/530, loss: 0.03798713535070419
2023-01-21 09:08:55.546403: step: 136/530, loss: 1.053020715713501
2023-01-21 09:08:56.648191: step: 140/530, loss: 0.0592251755297184
2023-01-21 09:08:57.754947: step: 144/530, loss: 0.042023397982120514
2023-01-21 09:08:58.844440: step: 148/530, loss: 0.21973906457424164
2023-01-21 09:08:59.947062: step: 152/530, loss: 0.8609983325004578
2023-01-21 09:09:01.075698: step: 156/530, loss: 0.3036176860332489
2023-01-21 09:09:02.194409: step: 160/530, loss: 0.085118867456913
2023-01-21 09:09:03.318398: step: 164/530, loss: 0.24596424400806427
2023-01-21 09:09:04.417755: step: 168/530, loss: 0.7658373117446899
2023-01-21 09:09:05.535388: step: 172/530, loss: 0.07617044448852539
2023-01-21 09:09:06.671518: step: 176/530, loss: 0.27061253786087036
2023-01-21 09:09:07.775481: step: 180/530, loss: 0.17514467239379883
2023-01-21 09:09:08.880006: step: 184/530, loss: 0.06347942352294922
2023-01-21 09:09:09.975692: step: 188/530, loss: 0.18137702345848083
2023-01-21 09:09:11.090722: step: 192/530, loss: 0.30927228927612305
2023-01-21 09:09:12.213333: step: 196/530, loss: 0.227268785238266
2023-01-21 09:09:13.317418: step: 200/530, loss: 0.07520995289087296
2023-01-21 09:09:14.421118: step: 204/530, loss: 0.7358288764953613
2023-01-21 09:09:15.536872: step: 208/530, loss: 0.6291963458061218
2023-01-21 09:09:16.687785: step: 212/530, loss: 1.3192707300186157
2023-01-21 09:09:17.795100: step: 216/530, loss: 0.9732673764228821
2023-01-21 09:09:18.923054: step: 220/530, loss: 0.19368776679039001
2023-01-21 09:09:19.999155: step: 224/530, loss: 0.19504660367965698
2023-01-21 09:09:21.094616: step: 228/530, loss: 0.4285208284854889
2023-01-21 09:09:22.189621: step: 232/530, loss: 0.16410227119922638
2023-01-21 09:09:23.298415: step: 236/530, loss: 0.09562702476978302
2023-01-21 09:09:24.422245: step: 240/530, loss: 0.28383591771125793
2023-01-21 09:09:25.533779: step: 244/530, loss: 0.06947479397058487
2023-01-21 09:09:26.678943: step: 248/530, loss: 0.1785689890384674
2023-01-21 09:09:27.790758: step: 252/530, loss: 0.11491565406322479
2023-01-21 09:09:28.889902: step: 256/530, loss: 0.16028264164924622
2023-01-21 09:09:30.005258: step: 260/530, loss: 0.4230189323425293
2023-01-21 09:09:31.077375: step: 264/530, loss: 0.002495241118595004
2023-01-21 09:09:32.181360: step: 268/530, loss: 0.2585994601249695
2023-01-21 09:09:33.316585: step: 272/530, loss: 0.7062785029411316
2023-01-21 09:09:34.443563: step: 276/530, loss: 0.18858233094215393
2023-01-21 09:09:35.564892: step: 280/530, loss: 0.07366481423377991
2023-01-21 09:09:36.667155: step: 284/530, loss: 0.7119276523590088
2023-01-21 09:09:37.783441: step: 288/530, loss: 0.2859219014644623
2023-01-21 09:09:38.887840: step: 292/530, loss: 0.08244998753070831
2023-01-21 09:09:40.026401: step: 296/530, loss: 0.5451288223266602
2023-01-21 09:09:41.131709: step: 300/530, loss: 0.35724082589149475
2023-01-21 09:09:42.243614: step: 304/530, loss: 0.09315011650323868
2023-01-21 09:09:43.333147: step: 308/530, loss: 0.6905643343925476
2023-01-21 09:09:44.423736: step: 312/530, loss: 0.036550235003232956
2023-01-21 09:09:45.598271: step: 316/530, loss: 0.12791705131530762
2023-01-21 09:09:46.702089: step: 320/530, loss: 0.32567092776298523
2023-01-21 09:09:47.810806: step: 324/530, loss: 1.0341269969940186
2023-01-21 09:09:48.968345: step: 328/530, loss: 0.25899046659469604
2023-01-21 09:09:50.067198: step: 332/530, loss: 0.16461749374866486
2023-01-21 09:09:51.185454: step: 336/530, loss: 0.2790655195713043
2023-01-21 09:09:52.333699: step: 340/530, loss: 1.8996248245239258
2023-01-21 09:09:53.469100: step: 344/530, loss: 0.05808250978589058
2023-01-21 09:09:54.590259: step: 348/530, loss: 0.09442539513111115
2023-01-21 09:09:55.735381: step: 352/530, loss: 0.10469003021717072
2023-01-21 09:09:56.852129: step: 356/530, loss: 0.05758700519800186
2023-01-21 09:09:57.977739: step: 360/530, loss: 0.15223579108715057
2023-01-21 09:09:59.086345: step: 364/530, loss: 0.032969094812870026
2023-01-21 09:10:00.214137: step: 368/530, loss: 0.2311607301235199
2023-01-21 09:10:01.316010: step: 372/530, loss: 0.06469903141260147
2023-01-21 09:10:02.415447: step: 376/530, loss: 0.12867331504821777
2023-01-21 09:10:03.527058: step: 380/530, loss: 0.2977760434150696
2023-01-21 09:10:04.620381: step: 384/530, loss: 0.5782980918884277
2023-01-21 09:10:05.720349: step: 388/530, loss: 0.06419911980628967
2023-01-21 09:10:06.808967: step: 392/530, loss: 0.17603835463523865
2023-01-21 09:10:07.903759: step: 396/530, loss: 1.5889110565185547
2023-01-21 09:10:09.036168: step: 400/530, loss: 0.31012162566185
2023-01-21 09:10:10.140373: step: 404/530, loss: 0.6036617159843445
2023-01-21 09:10:11.279027: step: 408/530, loss: 0.04255819320678711
2023-01-21 09:10:12.374797: step: 412/530, loss: 0.07757425308227539
2023-01-21 09:10:13.470892: step: 416/530, loss: 0.1258796751499176
2023-01-21 09:10:14.551518: step: 420/530, loss: 0.17497166991233826
2023-01-21 09:10:15.660699: step: 424/530, loss: 0.2888738811016083
2023-01-21 09:10:16.753591: step: 428/530, loss: 0.6359089016914368
2023-01-21 09:10:17.840757: step: 432/530, loss: 0.04290004074573517
2023-01-21 09:10:18.930837: step: 436/530, loss: 0.8973314762115479
2023-01-21 09:10:20.017603: step: 440/530, loss: 0.6251528263092041
2023-01-21 09:10:21.146369: step: 444/530, loss: 0.10061698406934738
2023-01-21 09:10:22.260951: step: 448/530, loss: 0.6745343804359436
2023-01-21 09:10:23.363760: step: 452/530, loss: 0.22200122475624084
2023-01-21 09:10:24.476585: step: 456/530, loss: 0.1470044106245041
2023-01-21 09:10:25.573453: step: 460/530, loss: 0.22180795669555664
2023-01-21 09:10:26.675621: step: 464/530, loss: 0.11039237678050995
2023-01-21 09:10:27.791955: step: 468/530, loss: 0.3090516924858093
2023-01-21 09:10:28.904129: step: 472/530, loss: 0.8329148292541504
2023-01-21 09:10:29.998720: step: 476/530, loss: 0.2510644495487213
2023-01-21 09:10:31.086467: step: 480/530, loss: 0.11411610245704651
2023-01-21 09:10:32.194790: step: 484/530, loss: 0.1300908625125885
2023-01-21 09:10:33.317928: step: 488/530, loss: 0.2146996557712555
2023-01-21 09:10:34.416650: step: 492/530, loss: 0.41510438919067383
2023-01-21 09:10:35.518263: step: 496/530, loss: 0.6639122366905212
2023-01-21 09:10:36.635706: step: 500/530, loss: 0.2435392439365387
2023-01-21 09:10:37.740616: step: 504/530, loss: 0.2363567352294922
2023-01-21 09:10:38.868394: step: 508/530, loss: 0.7916234731674194
2023-01-21 09:10:39.993945: step: 512/530, loss: 0.08931379020214081
2023-01-21 09:10:41.130704: step: 516/530, loss: 0.14269299805164337
2023-01-21 09:10:42.234427: step: 520/530, loss: 0.6551990509033203
2023-01-21 09:10:43.358166: step: 524/530, loss: 0.10445032268762589
2023-01-21 09:10:44.488519: step: 528/530, loss: 0.1474807858467102
2023-01-21 09:10:45.619426: step: 532/530, loss: 0.13611894845962524
2023-01-21 09:10:46.731076: step: 536/530, loss: 0.13604116439819336
2023-01-21 09:10:47.847395: step: 540/530, loss: 0.18705740571022034
2023-01-21 09:10:48.968896: step: 544/530, loss: 1.0120625495910645
2023-01-21 09:10:50.124824: step: 548/530, loss: 0.05053301155567169
2023-01-21 09:10:51.262367: step: 552/530, loss: 0.2768556773662567
2023-01-21 09:10:52.375238: step: 556/530, loss: 0.3678132891654968
2023-01-21 09:10:53.470398: step: 560/530, loss: 0.0971141904592514
2023-01-21 09:10:54.579535: step: 564/530, loss: 0.16282042860984802
2023-01-21 09:10:55.686168: step: 568/530, loss: 0.13722917437553406
2023-01-21 09:10:56.841498: step: 572/530, loss: 0.14696092903614044
2023-01-21 09:10:58.008236: step: 576/530, loss: 0.6849290728569031
2023-01-21 09:10:59.100194: step: 580/530, loss: 0.4501667022705078
2023-01-21 09:11:00.224563: step: 584/530, loss: 0.06188564747571945
2023-01-21 09:11:01.308795: step: 588/530, loss: 0.1651732474565506
2023-01-21 09:11:02.404540: step: 592/530, loss: 0.5529107451438904
2023-01-21 09:11:03.531961: step: 596/530, loss: 0.07896395027637482
2023-01-21 09:11:04.629720: step: 600/530, loss: 0.7041786909103394
2023-01-21 09:11:05.755944: step: 604/530, loss: 1.0781370401382446
2023-01-21 09:11:06.844227: step: 608/530, loss: 0.07620349526405334
2023-01-21 09:11:07.926988: step: 612/530, loss: 0.11507193744182587
2023-01-21 09:11:09.023925: step: 616/530, loss: 0.12602777779102325
2023-01-21 09:11:10.133804: step: 620/530, loss: 0.7953168153762817
2023-01-21 09:11:11.286533: step: 624/530, loss: 0.095440573990345
2023-01-21 09:11:12.375490: step: 628/530, loss: 1.2022781372070312
2023-01-21 09:11:13.471090: step: 632/530, loss: 0.1201867163181305
2023-01-21 09:11:14.593706: step: 636/530, loss: 0.014252830296754837
2023-01-21 09:11:15.732495: step: 640/530, loss: 0.6441764831542969
2023-01-21 09:11:16.859610: step: 644/530, loss: 0.24249336123466492
2023-01-21 09:11:18.001178: step: 648/530, loss: 1.9413731098175049
2023-01-21 09:11:19.085674: step: 652/530, loss: 0.08212690055370331
2023-01-21 09:11:20.198479: step: 656/530, loss: 0.10359683632850647
2023-01-21 09:11:21.318928: step: 660/530, loss: 0.37283411622047424
2023-01-21 09:11:22.427793: step: 664/530, loss: 0.10111179947853088
2023-01-21 09:11:23.543211: step: 668/530, loss: 0.24938397109508514
2023-01-21 09:11:24.654791: step: 672/530, loss: 0.17855310440063477
2023-01-21 09:11:25.760023: step: 676/530, loss: 0.1608729362487793
2023-01-21 09:11:26.906459: step: 680/530, loss: 0.1649789810180664
2023-01-21 09:11:28.006162: step: 684/530, loss: 0.5319286584854126
2023-01-21 09:11:29.144850: step: 688/530, loss: 0.12849551439285278
2023-01-21 09:11:30.259218: step: 692/530, loss: 0.28484708070755005
2023-01-21 09:11:31.383642: step: 696/530, loss: 0.09623485058546066
2023-01-21 09:11:32.493358: step: 700/530, loss: 0.21513105928897858
2023-01-21 09:11:33.588409: step: 704/530, loss: 0.3709196150302887
2023-01-21 09:11:34.673968: step: 708/530, loss: 0.16567936539649963
2023-01-21 09:11:35.780641: step: 712/530, loss: 0.37518346309661865
2023-01-21 09:11:36.931422: step: 716/530, loss: 0.14251261949539185
2023-01-21 09:11:38.011134: step: 720/530, loss: 0.12498798966407776
2023-01-21 09:11:39.156457: step: 724/530, loss: 0.6333795785903931
2023-01-21 09:11:40.250397: step: 728/530, loss: 0.17226925492286682
2023-01-21 09:11:41.386298: step: 732/530, loss: 0.12304191291332245
2023-01-21 09:11:42.496138: step: 736/530, loss: 0.17060184478759766
2023-01-21 09:11:43.608189: step: 740/530, loss: 0.43817099928855896
2023-01-21 09:11:44.714852: step: 744/530, loss: 0.07978034019470215
2023-01-21 09:11:45.792817: step: 748/530, loss: 0.6017361283302307
2023-01-21 09:11:46.960681: step: 752/530, loss: 0.36384162306785583
2023-01-21 09:11:48.062297: step: 756/530, loss: 1.220491647720337
2023-01-21 09:11:49.174768: step: 760/530, loss: 0.12230122089385986
2023-01-21 09:11:50.280395: step: 764/530, loss: 0.10451364517211914
2023-01-21 09:11:51.412254: step: 768/530, loss: 0.1675034612417221
2023-01-21 09:11:52.533747: step: 772/530, loss: 0.8957836627960205
2023-01-21 09:11:53.671411: step: 776/530, loss: 0.6963475942611694
2023-01-21 09:11:54.745887: step: 780/530, loss: 0.44131603837013245
2023-01-21 09:11:55.850473: step: 784/530, loss: 0.018154477700591087
2023-01-21 09:11:56.964022: step: 788/530, loss: 0.21204958856105804
2023-01-21 09:11:58.081720: step: 792/530, loss: 0.06024010479450226
2023-01-21 09:11:59.226635: step: 796/530, loss: 0.33726751804351807
2023-01-21 09:12:00.304352: step: 800/530, loss: 0.826570987701416
2023-01-21 09:12:01.420626: step: 804/530, loss: 0.26918625831604004
2023-01-21 09:12:02.532459: step: 808/530, loss: 0.2869883179664612
2023-01-21 09:12:03.651532: step: 812/530, loss: 0.013664627447724342
2023-01-21 09:12:04.750921: step: 816/530, loss: 0.0860753059387207
2023-01-21 09:12:05.899040: step: 820/530, loss: 0.15949583053588867
2023-01-21 09:12:07.007250: step: 824/530, loss: 0.6544192433357239
2023-01-21 09:12:08.131346: step: 828/530, loss: 0.1548047959804535
2023-01-21 09:12:09.232249: step: 832/530, loss: 0.1979069709777832
2023-01-21 09:12:10.329387: step: 836/530, loss: 0.07228050380945206
2023-01-21 09:12:11.444799: step: 840/530, loss: 6.875444412231445
2023-01-21 09:12:12.531750: step: 844/530, loss: 0.2356734275817871
2023-01-21 09:12:13.642680: step: 848/530, loss: 0.6459554433822632
2023-01-21 09:12:14.730567: step: 852/530, loss: 0.6395864486694336
2023-01-21 09:12:15.819844: step: 856/530, loss: 0.20317701995372772
2023-01-21 09:12:16.959843: step: 860/530, loss: 0.25498420000076294
2023-01-21 09:12:18.060901: step: 864/530, loss: 0.11433000862598419
2023-01-21 09:12:19.145309: step: 868/530, loss: 0.06698932498693466
2023-01-21 09:12:20.229052: step: 872/530, loss: 0.1255389153957367
2023-01-21 09:12:21.337974: step: 876/530, loss: 0.11043587327003479
2023-01-21 09:12:22.439789: step: 880/530, loss: 0.2697485089302063
2023-01-21 09:12:23.527747: step: 884/530, loss: 0.05824575573205948
2023-01-21 09:12:24.615741: step: 888/530, loss: 0.11491690576076508
2023-01-21 09:12:25.754145: step: 892/530, loss: 0.2918885350227356
2023-01-21 09:12:26.867050: step: 896/530, loss: 0.029052354395389557
2023-01-21 09:12:27.987756: step: 900/530, loss: 0.12050414085388184
2023-01-21 09:12:29.078977: step: 904/530, loss: 0.06294369697570801
2023-01-21 09:12:30.185252: step: 908/530, loss: 0.18864402174949646
2023-01-21 09:12:31.314801: step: 912/530, loss: 0.19394803047180176
2023-01-21 09:12:32.409803: step: 916/530, loss: 0.7425259351730347
2023-01-21 09:12:33.527966: step: 920/530, loss: 0.9460757970809937
2023-01-21 09:12:34.628267: step: 924/530, loss: 0.12582997977733612
2023-01-21 09:12:35.739372: step: 928/530, loss: 1.155656099319458
2023-01-21 09:12:36.848089: step: 932/530, loss: 0.09659481793642044
2023-01-21 09:12:37.989045: step: 936/530, loss: 1.087873935699463
2023-01-21 09:12:39.117717: step: 940/530, loss: 0.23143865168094635
2023-01-21 09:12:40.205094: step: 944/530, loss: 0.0830029547214508
2023-01-21 09:12:41.317145: step: 948/530, loss: 0.33842581510543823
2023-01-21 09:12:42.461774: step: 952/530, loss: 0.1852489411830902
2023-01-21 09:12:43.581901: step: 956/530, loss: 0.28379565477371216
2023-01-21 09:12:44.679082: step: 960/530, loss: 0.2216116040945053
2023-01-21 09:12:45.777625: step: 964/530, loss: 0.04554443061351776
2023-01-21 09:12:46.885544: step: 968/530, loss: 0.15739575028419495
2023-01-21 09:12:47.966349: step: 972/530, loss: 0.3060400187969208
2023-01-21 09:12:49.082615: step: 976/530, loss: 0.040933992713689804
2023-01-21 09:12:50.186409: step: 980/530, loss: 0.1738167107105255
2023-01-21 09:12:51.270492: step: 984/530, loss: 0.5579696297645569
2023-01-21 09:12:52.407724: step: 988/530, loss: 0.8865674734115601
2023-01-21 09:12:53.529047: step: 992/530, loss: 0.0962413102388382
2023-01-21 09:12:54.661462: step: 996/530, loss: 0.6861871480941772
2023-01-21 09:12:55.771668: step: 1000/530, loss: 0.10171470791101456
2023-01-21 09:12:56.897802: step: 1004/530, loss: 0.8661898970603943
2023-01-21 09:12:57.989991: step: 1008/530, loss: 0.5977591872215271
2023-01-21 09:12:59.086222: step: 1012/530, loss: 0.6103788018226624
2023-01-21 09:13:00.202071: step: 1016/530, loss: 0.2674272656440735
2023-01-21 09:13:01.279307: step: 1020/530, loss: 0.41799864172935486
2023-01-21 09:13:02.377231: step: 1024/530, loss: 0.07545948028564453
2023-01-21 09:13:03.482305: step: 1028/530, loss: 0.2168571949005127
2023-01-21 09:13:04.581365: step: 1032/530, loss: 0.06912942230701447
2023-01-21 09:13:05.689386: step: 1036/530, loss: 0.23729991912841797
2023-01-21 09:13:06.821221: step: 1040/530, loss: 0.8589423894882202
2023-01-21 09:13:07.901832: step: 1044/530, loss: 0.8682339787483215
2023-01-21 09:13:08.981232: step: 1048/530, loss: 0.2830013036727905
2023-01-21 09:13:10.081626: step: 1052/530, loss: 0.9885578155517578
2023-01-21 09:13:11.228969: step: 1056/530, loss: 0.08677569031715393
2023-01-21 09:13:12.350481: step: 1060/530, loss: 0.2631365656852722
2023-01-21 09:13:13.443132: step: 1064/530, loss: 0.1325186789035797
2023-01-21 09:13:14.553368: step: 1068/530, loss: 0.22418874502182007
2023-01-21 09:13:15.653905: step: 1072/530, loss: 1.3695142269134521
2023-01-21 09:13:16.757153: step: 1076/530, loss: 0.8808327317237854
2023-01-21 09:13:17.870799: step: 1080/530, loss: 0.04392242804169655
2023-01-21 09:13:18.982930: step: 1084/530, loss: 0.7642565965652466
2023-01-21 09:13:20.074306: step: 1088/530, loss: 0.025134852156043053
2023-01-21 09:13:21.170309: step: 1092/530, loss: 0.10414576530456543
2023-01-21 09:13:22.264704: step: 1096/530, loss: 0.7188560962677002
2023-01-21 09:13:23.372251: step: 1100/530, loss: 0.17085619270801544
2023-01-21 09:13:24.459567: step: 1104/530, loss: 0.20244550704956055
2023-01-21 09:13:25.551029: step: 1108/530, loss: 0.03152339532971382
2023-01-21 09:13:26.657774: step: 1112/530, loss: 0.17336583137512207
2023-01-21 09:13:27.766309: step: 1116/530, loss: 0.7545679211616516
2023-01-21 09:13:28.872534: step: 1120/530, loss: 0.27101603150367737
2023-01-21 09:13:29.964301: step: 1124/530, loss: 0.09907560050487518
2023-01-21 09:13:31.102817: step: 1128/530, loss: 0.1450391709804535
2023-01-21 09:13:32.193933: step: 1132/530, loss: 0.053304340690374374
2023-01-21 09:13:33.334336: step: 1136/530, loss: 1.410706639289856
2023-01-21 09:13:34.442172: step: 1140/530, loss: 0.7419158816337585
2023-01-21 09:13:35.561240: step: 1144/530, loss: 0.21401935815811157
2023-01-21 09:13:36.704360: step: 1148/530, loss: 0.46108514070510864
2023-01-21 09:13:37.838136: step: 1152/530, loss: 0.7044141292572021
2023-01-21 09:13:38.959882: step: 1156/530, loss: 0.06029639393091202
2023-01-21 09:13:40.091279: step: 1160/530, loss: 0.06458232551813126
2023-01-21 09:13:41.192493: step: 1164/530, loss: 0.4040374755859375
2023-01-21 09:13:42.294521: step: 1168/530, loss: 0.09229516983032227
2023-01-21 09:13:43.392286: step: 1172/530, loss: 0.12368221580982208
2023-01-21 09:13:44.464088: step: 1176/530, loss: 0.3297635018825531
2023-01-21 09:13:45.587290: step: 1180/530, loss: 0.1534641683101654
2023-01-21 09:13:46.686598: step: 1184/530, loss: 0.10368862748146057
2023-01-21 09:13:47.799410: step: 1188/530, loss: 0.09948396682739258
2023-01-21 09:13:48.920763: step: 1192/530, loss: 0.6797982454299927
2023-01-21 09:13:50.038741: step: 1196/530, loss: 0.20515289902687073
2023-01-21 09:13:51.214466: step: 1200/530, loss: 0.7703980803489685
2023-01-21 09:13:52.355291: step: 1204/530, loss: 0.16547727584838867
2023-01-21 09:13:53.465293: step: 1208/530, loss: 0.14820536971092224
2023-01-21 09:13:54.577785: step: 1212/530, loss: 0.4443378448486328
2023-01-21 09:13:55.686871: step: 1216/530, loss: 0.12664613127708435
2023-01-21 09:13:56.810283: step: 1220/530, loss: 0.23765869438648224
2023-01-21 09:13:57.924408: step: 1224/530, loss: 0.06319089233875275
2023-01-21 09:13:59.016937: step: 1228/530, loss: 0.08023710548877716
2023-01-21 09:14:00.174762: step: 1232/530, loss: 0.22510838508605957
2023-01-21 09:14:01.266807: step: 1236/530, loss: 0.05953836441040039
2023-01-21 09:14:02.372924: step: 1240/530, loss: 0.09235696494579315
2023-01-21 09:14:03.470246: step: 1244/530, loss: 0.20956096053123474
2023-01-21 09:14:04.599457: step: 1248/530, loss: 0.28998222947120667
2023-01-21 09:14:05.749117: step: 1252/530, loss: 0.2580730617046356
2023-01-21 09:14:06.902005: step: 1256/530, loss: 0.10675134509801865
2023-01-21 09:14:08.023852: step: 1260/530, loss: 0.6177328824996948
2023-01-21 09:14:09.112841: step: 1264/530, loss: 0.7704175710678101
2023-01-21 09:14:10.228981: step: 1268/530, loss: 0.6815082430839539
2023-01-21 09:14:11.307089: step: 1272/530, loss: 0.13198518753051758
2023-01-21 09:14:12.401244: step: 1276/530, loss: 0.13034024834632874
2023-01-21 09:14:13.506944: step: 1280/530, loss: 0.5580323934555054
2023-01-21 09:14:14.666297: step: 1284/530, loss: 0.269948810338974
2023-01-21 09:14:15.791825: step: 1288/530, loss: 0.26116713881492615
2023-01-21 09:14:16.889914: step: 1292/530, loss: 0.3074115812778473
2023-01-21 09:14:17.987133: step: 1296/530, loss: 0.6316810250282288
2023-01-21 09:14:19.060682: step: 1300/530, loss: 0.07565269619226456
2023-01-21 09:14:20.173387: step: 1304/530, loss: 0.05846991389989853
2023-01-21 09:14:21.283675: step: 1308/530, loss: 0.7852305173873901
2023-01-21 09:14:22.395275: step: 1312/530, loss: 2.439734935760498
2023-01-21 09:14:23.514436: step: 1316/530, loss: 0.021925831213593483
2023-01-21 09:14:24.633585: step: 1320/530, loss: 0.3048337996006012
2023-01-21 09:14:25.735545: step: 1324/530, loss: 0.45132145285606384
2023-01-21 09:14:26.818542: step: 1328/530, loss: 0.9666004776954651
2023-01-21 09:14:27.967730: step: 1332/530, loss: 0.10889368504285812
2023-01-21 09:14:29.080049: step: 1336/530, loss: 0.0897543877363205
2023-01-21 09:14:30.217584: step: 1340/530, loss: 0.999549388885498
2023-01-21 09:14:31.329243: step: 1344/530, loss: 0.19912907481193542
2023-01-21 09:14:32.441728: step: 1348/530, loss: 0.1133183017373085
2023-01-21 09:14:33.568700: step: 1352/530, loss: 0.0887356773018837
2023-01-21 09:14:34.662872: step: 1356/530, loss: 0.19019556045532227
2023-01-21 09:14:35.780904: step: 1360/530, loss: 0.2434220314025879
2023-01-21 09:14:36.898014: step: 1364/530, loss: 0.15951910614967346
2023-01-21 09:14:38.009864: step: 1368/530, loss: 0.12713909149169922
2023-01-21 09:14:39.151291: step: 1372/530, loss: 0.16986556351184845
2023-01-21 09:14:40.250539: step: 1376/530, loss: 0.1644512265920639
2023-01-21 09:14:41.355061: step: 1380/530, loss: 0.03011941909790039
2023-01-21 09:14:42.442918: step: 1384/530, loss: 0.05201082304120064
2023-01-21 09:14:43.575431: step: 1388/530, loss: 0.779977560043335
2023-01-21 09:14:44.682590: step: 1392/530, loss: 0.1605144441127777
2023-01-21 09:14:45.812769: step: 1396/530, loss: 0.11674337089061737
2023-01-21 09:14:46.932513: step: 1400/530, loss: 0.4920404553413391
2023-01-21 09:14:48.010643: step: 1404/530, loss: 0.30350393056869507
2023-01-21 09:14:49.090299: step: 1408/530, loss: 0.11145148426294327
2023-01-21 09:14:50.152374: step: 1412/530, loss: 0.1137409657239914
2023-01-21 09:14:51.273664: step: 1416/530, loss: 0.6228853464126587
2023-01-21 09:14:52.391357: step: 1420/530, loss: 0.5316762924194336
2023-01-21 09:14:53.495573: step: 1424/530, loss: 0.0711304172873497
2023-01-21 09:14:54.566480: step: 1428/530, loss: 4.4109673500061035
2023-01-21 09:14:55.667544: step: 1432/530, loss: 0.16078682243824005
2023-01-21 09:14:56.755205: step: 1436/530, loss: 0.044262077659368515
2023-01-21 09:14:57.842315: step: 1440/530, loss: 0.23200149834156036
2023-01-21 09:14:58.966462: step: 1444/530, loss: 0.39855605363845825
2023-01-21 09:15:00.097321: step: 1448/530, loss: 0.3024076521396637
2023-01-21 09:15:01.208558: step: 1452/530, loss: 0.8743209838867188
2023-01-21 09:15:02.326675: step: 1456/530, loss: 0.3770274221897125
2023-01-21 09:15:03.439610: step: 1460/530, loss: 0.21051377058029175
2023-01-21 09:15:04.552622: step: 1464/530, loss: 0.1844814270734787
2023-01-21 09:15:05.704067: step: 1468/530, loss: 0.13277478516101837
2023-01-21 09:15:06.790931: step: 1472/530, loss: 0.3739944100379944
2023-01-21 09:15:07.879219: step: 1476/530, loss: 0.17986154556274414
2023-01-21 09:15:08.958221: step: 1480/530, loss: 0.16679593920707703
2023-01-21 09:15:10.088064: step: 1484/530, loss: 0.04356050491333008
2023-01-21 09:15:11.197391: step: 1488/530, loss: 0.03346309810876846
2023-01-21 09:15:12.294206: step: 1492/530, loss: 0.08938150852918625
2023-01-21 09:15:13.371865: step: 1496/530, loss: 0.3364669680595398
2023-01-21 09:15:14.456720: step: 1500/530, loss: 0.10517878830432892
2023-01-21 09:15:15.571505: step: 1504/530, loss: 0.2583724856376648
2023-01-21 09:15:16.687595: step: 1508/530, loss: 0.15668517351150513
2023-01-21 09:15:17.790905: step: 1512/530, loss: 0.5459786653518677
2023-01-21 09:15:18.900361: step: 1516/530, loss: 0.20449119806289673
2023-01-21 09:15:19.988434: step: 1520/530, loss: 0.20493429899215698
2023-01-21 09:15:21.119672: step: 1524/530, loss: 0.9568063616752625
2023-01-21 09:15:22.233894: step: 1528/530, loss: 0.17917633056640625
2023-01-21 09:15:23.343015: step: 1532/530, loss: 0.0346684455871582
2023-01-21 09:15:24.443920: step: 1536/530, loss: 0.2769407331943512
2023-01-21 09:15:25.550088: step: 1540/530, loss: 0.0798131451010704
2023-01-21 09:15:26.683492: step: 1544/530, loss: 0.48302823305130005
2023-01-21 09:15:27.790794: step: 1548/530, loss: 0.39195314049720764
2023-01-21 09:15:28.886763: step: 1552/530, loss: 0.6648123264312744
2023-01-21 09:15:30.037541: step: 1556/530, loss: 0.1350722461938858
2023-01-21 09:15:31.157943: step: 1560/530, loss: 0.11914177238941193
2023-01-21 09:15:32.261642: step: 1564/530, loss: 0.17729921638965607
2023-01-21 09:15:33.401793: step: 1568/530, loss: 1.0627611875534058
2023-01-21 09:15:34.516728: step: 1572/530, loss: 0.17662353813648224
2023-01-21 09:15:35.611090: step: 1576/530, loss: 0.21470819413661957
2023-01-21 09:15:36.720810: step: 1580/530, loss: 0.12393327057361603
2023-01-21 09:15:37.831635: step: 1584/530, loss: 0.41027840971946716
2023-01-21 09:15:38.935469: step: 1588/530, loss: 0.1743198037147522
2023-01-21 09:15:40.083519: step: 1592/530, loss: 0.08025846630334854
2023-01-21 09:15:41.208640: step: 1596/530, loss: 0.5930920839309692
2023-01-21 09:15:42.347003: step: 1600/530, loss: 0.25289660692214966
2023-01-21 09:15:43.466225: step: 1604/530, loss: 0.3779110014438629
2023-01-21 09:15:44.574912: step: 1608/530, loss: 0.14294977486133575
2023-01-21 09:15:45.724744: step: 1612/530, loss: 0.09378716349601746
2023-01-21 09:15:46.861896: step: 1616/530, loss: 0.3885635435581207
2023-01-21 09:15:47.983245: step: 1620/530, loss: 0.09046244621276855
2023-01-21 09:15:49.091638: step: 1624/530, loss: 0.06720075756311417
2023-01-21 09:15:50.189739: step: 1628/530, loss: 0.20623335242271423
2023-01-21 09:15:51.357709: step: 1632/530, loss: 0.17597731947898865
2023-01-21 09:15:52.465022: step: 1636/530, loss: 0.15388832986354828
2023-01-21 09:15:53.577628: step: 1640/530, loss: 0.03708148002624512
2023-01-21 09:15:54.691152: step: 1644/530, loss: 0.06569299846887589
2023-01-21 09:15:55.775520: step: 1648/530, loss: 0.7898924946784973
2023-01-21 09:15:56.874780: step: 1652/530, loss: 0.4141145646572113
2023-01-21 09:15:58.009871: step: 1656/530, loss: 0.11449708789587021
2023-01-21 09:15:59.119237: step: 1660/530, loss: 0.1139567419886589
2023-01-21 09:16:00.227995: step: 1664/530, loss: 0.4521687626838684
2023-01-21 09:16:01.330674: step: 1668/530, loss: 0.32162562012672424
2023-01-21 09:16:02.441119: step: 1672/530, loss: 0.0649513229727745
2023-01-21 09:16:03.530579: step: 1676/530, loss: 0.13818113505840302
2023-01-21 09:16:04.644997: step: 1680/530, loss: 0.18604105710983276
2023-01-21 09:16:05.792653: step: 1684/530, loss: 0.5167818069458008
2023-01-21 09:16:06.921476: step: 1688/530, loss: 0.09290018677711487
2023-01-21 09:16:08.020705: step: 1692/530, loss: 0.19726505875587463
2023-01-21 09:16:09.118638: step: 1696/530, loss: 0.14751777052879333
2023-01-21 09:16:10.243368: step: 1700/530, loss: 0.12635822594165802
2023-01-21 09:16:11.349845: step: 1704/530, loss: 0.258309543132782
2023-01-21 09:16:12.428420: step: 1708/530, loss: 0.22176837921142578
2023-01-21 09:16:13.514116: step: 1712/530, loss: 0.1805877685546875
2023-01-21 09:16:14.602773: step: 1716/530, loss: 4.1694865226745605
2023-01-21 09:16:15.700677: step: 1720/530, loss: 0.5522695779800415
2023-01-21 09:16:16.791404: step: 1724/530, loss: 0.28466200828552246
2023-01-21 09:16:17.866363: step: 1728/530, loss: 0.6798132658004761
2023-01-21 09:16:18.981711: step: 1732/530, loss: 0.13943806290626526
2023-01-21 09:16:20.102994: step: 1736/530, loss: 0.4698498845100403
2023-01-21 09:16:21.208209: step: 1740/530, loss: 0.06127600744366646
2023-01-21 09:16:22.294576: step: 1744/530, loss: 0.07682600617408752
2023-01-21 09:16:23.401627: step: 1748/530, loss: 0.25692853331565857
2023-01-21 09:16:24.508932: step: 1752/530, loss: 0.013651752844452858
2023-01-21 09:16:25.620886: step: 1756/530, loss: 0.06762795150279999
2023-01-21 09:16:26.751425: step: 1760/530, loss: 0.36070966720581055
2023-01-21 09:16:27.868236: step: 1764/530, loss: 0.5432117581367493
2023-01-21 09:16:28.949834: step: 1768/530, loss: 0.03974132239818573
2023-01-21 09:16:30.060708: step: 1772/530, loss: 0.145559161901474
2023-01-21 09:16:31.179468: step: 1776/530, loss: 0.25911301374435425
2023-01-21 09:16:32.278989: step: 1780/530, loss: 0.14911337196826935
2023-01-21 09:16:33.401970: step: 1784/530, loss: 0.6018800139427185
2023-01-21 09:16:34.503501: step: 1788/530, loss: 0.2114981710910797
2023-01-21 09:16:35.599392: step: 1792/530, loss: 0.06311145424842834
2023-01-21 09:16:36.699741: step: 1796/530, loss: 0.06796560436487198
2023-01-21 09:16:37.804530: step: 1800/530, loss: 0.1299586296081543
2023-01-21 09:16:38.893027: step: 1804/530, loss: 0.30312222242355347
2023-01-21 09:16:39.969249: step: 1808/530, loss: 1.1231557130813599
2023-01-21 09:16:41.071424: step: 1812/530, loss: 0.6786888241767883
2023-01-21 09:16:42.160356: step: 1816/530, loss: 0.6103639602661133
2023-01-21 09:16:43.274095: step: 1820/530, loss: 0.22400322556495667
2023-01-21 09:16:44.380169: step: 1824/530, loss: 0.36156922578811646
2023-01-21 09:16:45.507336: step: 1828/530, loss: 0.8919402360916138
2023-01-21 09:16:46.617255: step: 1832/530, loss: 0.23228321969509125
2023-01-21 09:16:47.724878: step: 1836/530, loss: 0.6111003756523132
2023-01-21 09:16:48.818644: step: 1840/530, loss: 0.12799987196922302
2023-01-21 09:16:49.951483: step: 1844/530, loss: 0.06422419846057892
2023-01-21 09:16:51.060236: step: 1848/530, loss: 0.3487345576286316
2023-01-21 09:16:52.168023: step: 1852/530, loss: 0.4020829200744629
2023-01-21 09:16:53.300398: step: 1856/530, loss: 0.3677646517753601
2023-01-21 09:16:54.385722: step: 1860/530, loss: 0.13299906253814697
2023-01-21 09:16:55.506578: step: 1864/530, loss: 4.291902542114258
2023-01-21 09:16:56.603730: step: 1868/530, loss: 0.12012176960706711
2023-01-21 09:16:57.694577: step: 1872/530, loss: 0.14619025588035583
2023-01-21 09:16:58.807565: step: 1876/530, loss: 0.4764387309551239
2023-01-21 09:16:59.930870: step: 1880/530, loss: 0.9240580797195435
2023-01-21 09:17:01.060014: step: 1884/530, loss: 0.3990843892097473
2023-01-21 09:17:02.169828: step: 1888/530, loss: 0.6117464303970337
2023-01-21 09:17:03.276646: step: 1892/530, loss: 0.20829543471336365
2023-01-21 09:17:04.405548: step: 1896/530, loss: 0.5275556445121765
2023-01-21 09:17:05.535344: step: 1900/530, loss: 0.39034757018089294
2023-01-21 09:17:06.603349: step: 1904/530, loss: 0.7279199361801147
2023-01-21 09:17:07.699070: step: 1908/530, loss: 0.04306039959192276
2023-01-21 09:17:08.833080: step: 1912/530, loss: 0.8557937741279602
2023-01-21 09:17:09.934554: step: 1916/530, loss: 0.6540085673332214
2023-01-21 09:17:11.009123: step: 1920/530, loss: 0.1145077720284462
2023-01-21 09:17:12.112277: step: 1924/530, loss: 0.2529016435146332
2023-01-21 09:17:13.232345: step: 1928/530, loss: 0.14663295447826385
2023-01-21 09:17:14.304218: step: 1932/530, loss: 0.07276878505945206
2023-01-21 09:17:15.407574: step: 1936/530, loss: 0.8042235970497131
2023-01-21 09:17:16.518577: step: 1940/530, loss: 0.11825352162122726
2023-01-21 09:17:17.638179: step: 1944/530, loss: 0.08867798745632172
2023-01-21 09:17:18.753632: step: 1948/530, loss: 0.1077207624912262
2023-01-21 09:17:19.902495: step: 1952/530, loss: 0.3472803235054016
2023-01-21 09:17:21.022864: step: 1956/530, loss: 0.8304993510246277
2023-01-21 09:17:22.107678: step: 1960/530, loss: 0.48092469573020935
2023-01-21 09:17:23.185382: step: 1964/530, loss: 0.15356428921222687
2023-01-21 09:17:24.281274: step: 1968/530, loss: 0.7775717973709106
2023-01-21 09:17:25.370021: step: 1972/530, loss: 0.18315431475639343
2023-01-21 09:17:26.469642: step: 1976/530, loss: 0.36433085799217224
2023-01-21 09:17:27.583223: step: 1980/530, loss: 0.12672452628612518
2023-01-21 09:17:28.700243: step: 1984/530, loss: 0.32066115736961365
2023-01-21 09:17:29.844466: step: 1988/530, loss: 0.15512457489967346
2023-01-21 09:17:30.961589: step: 1992/530, loss: 0.09265957027673721
2023-01-21 09:17:32.069625: step: 1996/530, loss: 0.06471529603004456
2023-01-21 09:17:33.215454: step: 2000/530, loss: 0.20603902637958527
2023-01-21 09:17:34.310773: step: 2004/530, loss: 0.12524700164794922
2023-01-21 09:17:35.438928: step: 2008/530, loss: 0.051560115069150925
2023-01-21 09:17:36.552830: step: 2012/530, loss: 0.0667935386300087
2023-01-21 09:17:37.642275: step: 2016/530, loss: 0.3049278259277344
2023-01-21 09:17:38.744723: step: 2020/530, loss: 0.14669866859912872
2023-01-21 09:17:39.864918: step: 2024/530, loss: 0.13566313683986664
2023-01-21 09:17:40.979612: step: 2028/530, loss: 0.6377245783805847
2023-01-21 09:17:42.062799: step: 2032/530, loss: 0.1285000890493393
2023-01-21 09:17:43.183800: step: 2036/530, loss: 0.10911282896995544
2023-01-21 09:17:44.293209: step: 2040/530, loss: 0.6941738724708557
2023-01-21 09:17:45.411859: step: 2044/530, loss: 0.33101046085357666
2023-01-21 09:17:46.553406: step: 2048/530, loss: 0.6142401099205017
2023-01-21 09:17:47.657252: step: 2052/530, loss: 0.41217711567878723
2023-01-21 09:17:48.770459: step: 2056/530, loss: 0.09512200951576233
2023-01-21 09:17:49.869889: step: 2060/530, loss: 0.11377761512994766
2023-01-21 09:17:50.979947: step: 2064/530, loss: 0.19775763154029846
2023-01-21 09:17:52.090438: step: 2068/530, loss: 0.07653675228357315
2023-01-21 09:17:53.186111: step: 2072/530, loss: 0.32089900970458984
2023-01-21 09:17:54.271139: step: 2076/530, loss: 0.0761415958404541
2023-01-21 09:17:55.391747: step: 2080/530, loss: 0.2697104811668396
2023-01-21 09:17:56.531773: step: 2084/530, loss: 0.05600576475262642
2023-01-21 09:17:57.625594: step: 2088/530, loss: 0.11992950737476349
2023-01-21 09:17:58.719052: step: 2092/530, loss: 0.0929257944226265
2023-01-21 09:17:59.845047: step: 2096/530, loss: 0.27150383591651917
2023-01-21 09:18:00.967484: step: 2100/530, loss: 0.1220850944519043
2023-01-21 09:18:02.079053: step: 2104/530, loss: 1.0428532361984253
2023-01-21 09:18:03.204704: step: 2108/530, loss: 0.15821132063865662
2023-01-21 09:18:04.303298: step: 2112/530, loss: 0.5825380682945251
2023-01-21 09:18:05.416113: step: 2116/530, loss: 0.7651004791259766
2023-01-21 09:18:06.530173: step: 2120/530, loss: 0.7224260568618774
==================================================
Loss: 0.376
--------------------
Dev: {'event': {'p': 0.5357852882703777, 'r': 0.7177097203728362, 'f1': 0.6135458167330677}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Test: {'event': {'p': 0.5814155449413808, 'r': 0.7803030303030303, 'f1': 0.6663349091813884}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Chinese: {'event': {'p': 0.5316455696202531, 'r': 0.7777777777777778, 'f1': 0.6315789473684209}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Korean: {'event': {'p': 0.6037735849056604, 'r': 0.5079365079365079, 'f1': 0.5517241379310345}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Russian: {'event': {'p': 0.391304347826087, 'r': 0.5, 'f1': 0.4390243902439025}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.5970149253731343, 'r': 0.7407407407407407, 'f1': 0.6611570247933883}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7631578947368421, 'r': 0.4603174603174603, 'f1': 0.5742574257425742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.625, 'r': 0.4166666666666667, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
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 09:18:46.201431: step: 4/530, loss: 0.1551334410905838
2023-01-21 09:18:47.328752: step: 8/530, loss: 0.15506239235401154
2023-01-21 09:18:48.434500: step: 12/530, loss: 0.09207554161548615
2023-01-21 09:18:49.527207: step: 16/530, loss: 0.27854424715042114
2023-01-21 09:18:50.627888: step: 20/530, loss: 0.06261630356311798
2023-01-21 09:18:51.744099: step: 24/530, loss: 0.07133197784423828
2023-01-21 09:18:52.841613: step: 28/530, loss: 0.18068867921829224
2023-01-21 09:18:53.980348: step: 32/530, loss: 0.20504236221313477
2023-01-21 09:18:55.073067: step: 36/530, loss: 0.15022096037864685
2023-01-21 09:18:56.188092: step: 40/530, loss: 0.07955169677734375
2023-01-21 09:18:57.301035: step: 44/530, loss: 0.16164475679397583
2023-01-21 09:18:58.396231: step: 48/530, loss: 0.43493157625198364
2023-01-21 09:18:59.509475: step: 52/530, loss: 0.08911388367414474
2023-01-21 09:19:00.616423: step: 56/530, loss: 0.3782656490802765
2023-01-21 09:19:01.729911: step: 60/530, loss: 0.13911986351013184
2023-01-21 09:19:02.837528: step: 64/530, loss: 0.21054372191429138
2023-01-21 09:19:03.947392: step: 68/530, loss: 0.17701081931591034
2023-01-21 09:19:05.058497: step: 72/530, loss: 0.06115255504846573
2023-01-21 09:19:06.172814: step: 76/530, loss: 0.06634383648633957
2023-01-21 09:19:07.246665: step: 80/530, loss: 0.07450045645236969
2023-01-21 09:19:08.357905: step: 84/530, loss: 0.2603018879890442
2023-01-21 09:19:09.467161: step: 88/530, loss: 0.14794005453586578
2023-01-21 09:19:10.570140: step: 92/530, loss: 0.04748525843024254
2023-01-21 09:19:11.658806: step: 96/530, loss: 0.18634852766990662
2023-01-21 09:19:12.769002: step: 100/530, loss: 0.2666800618171692
2023-01-21 09:19:13.875983: step: 104/530, loss: 0.14606314897537231
2023-01-21 09:19:14.982029: step: 108/530, loss: 0.053810931742191315
2023-01-21 09:19:16.083013: step: 112/530, loss: 0.056484125554561615
2023-01-21 09:19:17.209253: step: 116/530, loss: 0.02945990487933159
2023-01-21 09:19:18.301491: step: 120/530, loss: 0.08317270129919052
2023-01-21 09:19:19.380541: step: 124/530, loss: 0.08401679992675781
2023-01-21 09:19:20.508715: step: 128/530, loss: 0.21548672020435333
2023-01-21 09:19:21.602825: step: 132/530, loss: 0.2645147144794464
2023-01-21 09:19:22.681365: step: 136/530, loss: 0.05896034091711044
2023-01-21 09:19:23.780103: step: 140/530, loss: 0.1117984801530838
2023-01-21 09:19:24.883959: step: 144/530, loss: 0.1106325164437294
2023-01-21 09:19:26.022681: step: 148/530, loss: 0.06767185032367706
2023-01-21 09:19:27.121010: step: 152/530, loss: 0.14967116713523865
2023-01-21 09:19:28.230764: step: 156/530, loss: 0.19012156128883362
2023-01-21 09:19:29.351374: step: 160/530, loss: 0.03276777267456055
2023-01-21 09:19:30.447342: step: 164/530, loss: 0.31172531843185425
2023-01-21 09:19:31.539037: step: 168/530, loss: 0.114691823720932
2023-01-21 09:19:32.647271: step: 172/530, loss: 0.18882575631141663
2023-01-21 09:19:33.803562: step: 176/530, loss: 0.11627378314733505
2023-01-21 09:19:34.904604: step: 180/530, loss: 0.10448499023914337
2023-01-21 09:19:36.003202: step: 184/530, loss: 0.14155977964401245
2023-01-21 09:19:37.114950: step: 188/530, loss: 0.8063328266143799
2023-01-21 09:19:38.206494: step: 192/530, loss: 0.0875302329659462
2023-01-21 09:19:39.302154: step: 196/530, loss: 0.5578939318656921
2023-01-21 09:19:40.415583: step: 200/530, loss: 0.10926227271556854
2023-01-21 09:19:41.524904: step: 204/530, loss: 0.7452509999275208
2023-01-21 09:19:42.637181: step: 208/530, loss: 0.03836231306195259
2023-01-21 09:19:43.750608: step: 212/530, loss: 0.09682293236255646
2023-01-21 09:19:44.875135: step: 216/530, loss: 0.15231674909591675
2023-01-21 09:19:45.978180: step: 220/530, loss: 0.117932990193367
2023-01-21 09:19:47.073104: step: 224/530, loss: 0.6837148666381836
2023-01-21 09:19:48.182222: step: 228/530, loss: 0.2826762795448303
2023-01-21 09:19:49.328109: step: 232/530, loss: 0.5543189644813538
2023-01-21 09:19:50.427645: step: 236/530, loss: 0.15985733270645142
2023-01-21 09:19:51.535674: step: 240/530, loss: 0.24577981233596802
2023-01-21 09:19:52.684609: step: 244/530, loss: 0.9133776426315308
2023-01-21 09:19:53.800311: step: 248/530, loss: 0.6930559277534485
2023-01-21 09:19:54.920967: step: 252/530, loss: 0.09299831092357635
2023-01-21 09:19:56.027093: step: 256/530, loss: 0.2885358929634094
2023-01-21 09:19:57.165848: step: 260/530, loss: 0.1749928593635559
2023-01-21 09:19:58.256303: step: 264/530, loss: 0.10827026516199112
2023-01-21 09:19:59.350992: step: 268/530, loss: 0.02184920385479927
2023-01-21 09:20:00.464442: step: 272/530, loss: 0.3510655462741852
2023-01-21 09:20:01.580642: step: 276/530, loss: 0.1348002851009369
2023-01-21 09:20:02.685801: step: 280/530, loss: 0.11623439192771912
2023-01-21 09:20:03.794483: step: 284/530, loss: 0.09722137451171875
2023-01-21 09:20:04.925653: step: 288/530, loss: 0.11461953818798065
2023-01-21 09:20:06.023520: step: 292/530, loss: 0.04510857164859772
2023-01-21 09:20:07.172883: step: 296/530, loss: 0.2510346472263336
2023-01-21 09:20:08.274876: step: 300/530, loss: 0.10553913563489914
2023-01-21 09:20:09.372472: step: 304/530, loss: 0.19953250885009766
2023-01-21 09:20:10.497263: step: 308/530, loss: 0.25582802295684814
2023-01-21 09:20:11.594053: step: 312/530, loss: 0.20102459192276
2023-01-21 09:20:12.698814: step: 316/530, loss: 0.24607200920581818
2023-01-21 09:20:13.806706: step: 320/530, loss: 0.8732153177261353
2023-01-21 09:20:14.922108: step: 324/530, loss: 2.055403709411621
2023-01-21 09:20:16.025064: step: 328/530, loss: 0.03215141221880913
2023-01-21 09:20:17.099371: step: 332/530, loss: 0.32044148445129395
2023-01-21 09:20:18.207784: step: 336/530, loss: 0.34932661056518555
2023-01-21 09:20:19.320680: step: 340/530, loss: 0.12172860652208328
2023-01-21 09:20:20.416266: step: 344/530, loss: 0.24385175108909607
2023-01-21 09:20:21.529649: step: 348/530, loss: 0.4071502685546875
2023-01-21 09:20:22.627303: step: 352/530, loss: 0.683687150478363
2023-01-21 09:20:23.747834: step: 356/530, loss: 0.6186181306838989
2023-01-21 09:20:24.845092: step: 360/530, loss: 0.1526637077331543
2023-01-21 09:20:25.963864: step: 364/530, loss: 0.5194263458251953
2023-01-21 09:20:27.121088: step: 368/530, loss: 0.1720869243144989
2023-01-21 09:20:28.213028: step: 372/530, loss: 0.11544866859912872
2023-01-21 09:20:29.290327: step: 376/530, loss: 0.19601230323314667
2023-01-21 09:20:30.394206: step: 380/530, loss: 0.18928222358226776
2023-01-21 09:20:31.509426: step: 384/530, loss: 0.035704806447029114
2023-01-21 09:20:32.611783: step: 388/530, loss: 0.3087407052516937
2023-01-21 09:20:33.718783: step: 392/530, loss: 0.1764741986989975
2023-01-21 09:20:34.831740: step: 396/530, loss: 0.12920570373535156
2023-01-21 09:20:35.938315: step: 400/530, loss: 0.19927386939525604
2023-01-21 09:20:37.029241: step: 404/530, loss: 0.13349667191505432
2023-01-21 09:20:38.158054: step: 408/530, loss: 0.4260912835597992
2023-01-21 09:20:39.271967: step: 412/530, loss: 0.1230802983045578
2023-01-21 09:20:40.372135: step: 416/530, loss: 0.05097360908985138
2023-01-21 09:20:41.461406: step: 420/530, loss: 0.4008246660232544
2023-01-21 09:20:42.552246: step: 424/530, loss: 0.0753335952758789
2023-01-21 09:20:43.685993: step: 428/530, loss: 0.1770675629377365
2023-01-21 09:20:44.769797: step: 432/530, loss: 0.18485641479492188
2023-01-21 09:20:45.873902: step: 436/530, loss: 0.09987812489271164
2023-01-21 09:20:47.031251: step: 440/530, loss: 0.4275304079055786
2023-01-21 09:20:48.117761: step: 444/530, loss: 0.24299153685569763
2023-01-21 09:20:49.255010: step: 448/530, loss: 0.5446224212646484
2023-01-21 09:20:50.355932: step: 452/530, loss: 0.4821932315826416
2023-01-21 09:20:51.453137: step: 456/530, loss: 0.1085105910897255
2023-01-21 09:20:52.569470: step: 460/530, loss: 0.0808354914188385
2023-01-21 09:20:53.688625: step: 464/530, loss: 0.27912312746047974
2023-01-21 09:20:54.781879: step: 468/530, loss: 0.03377389907836914
2023-01-21 09:20:55.902172: step: 472/530, loss: 0.49941492080688477
2023-01-21 09:20:57.038214: step: 476/530, loss: 0.528192937374115
2023-01-21 09:20:58.127337: step: 480/530, loss: 0.08554622530937195
2023-01-21 09:20:59.278356: step: 484/530, loss: 0.11619433760643005
2023-01-21 09:21:00.401334: step: 488/530, loss: 0.08876297622919083
2023-01-21 09:21:01.536200: step: 492/530, loss: 0.050025273114442825
2023-01-21 09:21:02.637076: step: 496/530, loss: 0.16717156767845154
2023-01-21 09:21:03.764531: step: 500/530, loss: 0.11093826591968536
2023-01-21 09:21:04.901404: step: 504/530, loss: 0.5166789889335632
2023-01-21 09:21:05.989657: step: 508/530, loss: 0.21503543853759766
2023-01-21 09:21:07.081961: step: 512/530, loss: 0.13059958815574646
2023-01-21 09:21:08.227033: step: 516/530, loss: 0.05246753618121147
2023-01-21 09:21:09.311792: step: 520/530, loss: 0.08229523152112961
2023-01-21 09:21:10.434380: step: 524/530, loss: 0.28197503089904785
2023-01-21 09:21:11.571418: step: 528/530, loss: 0.027631474658846855
2023-01-21 09:21:12.658533: step: 532/530, loss: 0.06330624222755432
2023-01-21 09:21:13.749036: step: 536/530, loss: 0.1302996575832367
2023-01-21 09:21:14.879472: step: 540/530, loss: 0.571711540222168
2023-01-21 09:21:15.982279: step: 544/530, loss: 0.6873383522033691
2023-01-21 09:21:17.084181: step: 548/530, loss: 0.0732763335108757
2023-01-21 09:21:18.164330: step: 552/530, loss: 0.507550835609436
2023-01-21 09:21:19.294664: step: 556/530, loss: 0.2017727792263031
2023-01-21 09:21:20.432165: step: 560/530, loss: 0.19548659026622772
2023-01-21 09:21:21.550564: step: 564/530, loss: 0.11503373086452484
2023-01-21 09:21:22.652733: step: 568/530, loss: 0.10834093391895294
2023-01-21 09:21:23.787400: step: 572/530, loss: 0.31352147459983826
2023-01-21 09:21:24.916605: step: 576/530, loss: 0.3023146092891693
2023-01-21 09:21:26.018563: step: 580/530, loss: 0.10832566767930984
2023-01-21 09:21:27.143273: step: 584/530, loss: 0.16336631774902344
2023-01-21 09:21:28.256472: step: 588/530, loss: 0.2481825053691864
2023-01-21 09:21:29.348488: step: 592/530, loss: 0.19358697533607483
2023-01-21 09:21:30.474982: step: 596/530, loss: 0.09596281498670578
2023-01-21 09:21:31.605214: step: 600/530, loss: 0.1801118403673172
2023-01-21 09:21:32.681296: step: 604/530, loss: 0.035079386085271835
2023-01-21 09:21:33.757936: step: 608/530, loss: 0.2649992108345032
2023-01-21 09:21:34.879724: step: 612/530, loss: 0.4586508870124817
2023-01-21 09:21:36.019599: step: 616/530, loss: 0.10550659894943237
2023-01-21 09:21:37.153589: step: 620/530, loss: 0.2990129590034485
2023-01-21 09:21:38.249068: step: 624/530, loss: 0.12080173939466476
2023-01-21 09:21:39.340656: step: 628/530, loss: 0.8232208490371704
2023-01-21 09:21:40.474767: step: 632/530, loss: 0.08620691299438477
2023-01-21 09:21:41.595693: step: 636/530, loss: 0.09553317725658417
2023-01-21 09:21:42.735006: step: 640/530, loss: 0.11280690133571625
2023-01-21 09:21:43.860402: step: 644/530, loss: 0.1648930460214615
2023-01-21 09:21:44.964075: step: 648/530, loss: 0.08147326111793518
2023-01-21 09:21:46.067965: step: 652/530, loss: 0.07111148536205292
2023-01-21 09:21:47.162973: step: 656/530, loss: 0.06882968544960022
2023-01-21 09:21:48.273295: step: 660/530, loss: 0.07458258420228958
2023-01-21 09:21:49.377545: step: 664/530, loss: 0.06435642391443253
2023-01-21 09:21:50.487370: step: 668/530, loss: 0.03547873720526695
2023-01-21 09:21:51.593395: step: 672/530, loss: 0.3290373980998993
2023-01-21 09:21:52.690283: step: 676/530, loss: 0.12128964066505432
2023-01-21 09:21:53.785051: step: 680/530, loss: 0.022686099633574486
2023-01-21 09:21:54.852415: step: 684/530, loss: 0.05937033146619797
2023-01-21 09:21:55.951398: step: 688/530, loss: 0.15541739761829376
2023-01-21 09:21:57.066470: step: 692/530, loss: 0.5816463232040405
2023-01-21 09:21:58.158477: step: 696/530, loss: 0.16766855120658875
2023-01-21 09:21:59.261421: step: 700/530, loss: 0.8123835325241089
2023-01-21 09:22:00.383634: step: 704/530, loss: 0.06023269146680832
2023-01-21 09:22:01.461456: step: 708/530, loss: 0.23824810981750488
2023-01-21 09:22:02.546726: step: 712/530, loss: 0.14797411859035492
2023-01-21 09:22:03.678184: step: 716/530, loss: 0.4418337941169739
2023-01-21 09:22:04.776471: step: 720/530, loss: 0.11328492313623428
2023-01-21 09:22:05.915141: step: 724/530, loss: 0.5148612856864929
2023-01-21 09:22:07.035898: step: 728/530, loss: 0.1719207763671875
2023-01-21 09:22:08.131824: step: 732/530, loss: 0.08941535651683807
2023-01-21 09:22:09.223540: step: 736/530, loss: 0.4617215394973755
2023-01-21 09:22:10.342959: step: 740/530, loss: 0.24298229813575745
2023-01-21 09:22:11.467284: step: 744/530, loss: 0.1684858351945877
2023-01-21 09:22:12.578116: step: 748/530, loss: 0.13890667259693146
2023-01-21 09:22:13.714099: step: 752/530, loss: 0.0818004161119461
2023-01-21 09:22:14.813553: step: 756/530, loss: 0.3300046920776367
2023-01-21 09:22:15.916269: step: 760/530, loss: 0.049156855791807175
2023-01-21 09:22:17.054725: step: 764/530, loss: 0.6946603655815125
2023-01-21 09:22:18.150885: step: 768/530, loss: 0.1192299872636795
2023-01-21 09:22:19.289817: step: 772/530, loss: 0.5141354203224182
2023-01-21 09:22:20.414160: step: 776/530, loss: 0.18026676774024963
2023-01-21 09:22:21.527088: step: 780/530, loss: 0.05397465452551842
2023-01-21 09:22:22.697738: step: 784/530, loss: 0.1251480132341385
2023-01-21 09:22:23.799412: step: 788/530, loss: 0.7057846188545227
2023-01-21 09:22:24.886317: step: 792/530, loss: 0.4519307613372803
2023-01-21 09:22:25.975746: step: 796/530, loss: 0.14722080528736115
2023-01-21 09:22:27.064206: step: 800/530, loss: 0.09747543931007385
2023-01-21 09:22:28.190345: step: 804/530, loss: 0.077850341796875
2023-01-21 09:22:29.278730: step: 808/530, loss: 0.10528307408094406
2023-01-21 09:22:30.397923: step: 812/530, loss: 0.09825949370861053
2023-01-21 09:22:31.505289: step: 816/530, loss: 0.06850776821374893
2023-01-21 09:22:32.616021: step: 820/530, loss: 0.30127421021461487
2023-01-21 09:22:33.746677: step: 824/530, loss: 0.14816370606422424
2023-01-21 09:22:34.890371: step: 828/530, loss: 0.14640340209007263
2023-01-21 09:22:36.022474: step: 832/530, loss: 2.4464852809906006
2023-01-21 09:22:37.148363: step: 836/530, loss: 0.06996269524097443
2023-01-21 09:22:38.281863: step: 840/530, loss: 0.14491620659828186
2023-01-21 09:22:39.378311: step: 844/530, loss: 0.06943173706531525
2023-01-21 09:22:40.489461: step: 848/530, loss: 0.1271343231201172
2023-01-21 09:22:41.618026: step: 852/530, loss: 0.11489133536815643
2023-01-21 09:22:42.765270: step: 856/530, loss: 0.15254774689674377
2023-01-21 09:22:43.869034: step: 860/530, loss: 0.18742027878761292
2023-01-21 09:22:44.970360: step: 864/530, loss: 0.3837968707084656
2023-01-21 09:22:46.092969: step: 868/530, loss: 0.1033800020813942
2023-01-21 09:22:47.228492: step: 872/530, loss: 0.03995781019330025
2023-01-21 09:22:48.363169: step: 876/530, loss: 0.13536810874938965
2023-01-21 09:22:49.477667: step: 880/530, loss: 0.28823918104171753
2023-01-21 09:22:50.565509: step: 884/530, loss: 0.024879170581698418
2023-01-21 09:22:51.696643: step: 888/530, loss: 0.10541597008705139
2023-01-21 09:22:52.845657: step: 892/530, loss: 0.024629544466733932
2023-01-21 09:22:53.948023: step: 896/530, loss: 0.1403234601020813
2023-01-21 09:22:55.077071: step: 900/530, loss: 0.02727055549621582
2023-01-21 09:22:56.202986: step: 904/530, loss: 0.31268197298049927
2023-01-21 09:22:57.357275: step: 908/530, loss: 0.09237900376319885
2023-01-21 09:22:58.456087: step: 912/530, loss: 0.13170138001441956
2023-01-21 09:22:59.574081: step: 916/530, loss: 0.1602492332458496
2023-01-21 09:23:00.699575: step: 920/530, loss: 0.08932428807020187
2023-01-21 09:23:01.805397: step: 924/530, loss: 0.05107317119836807
2023-01-21 09:23:02.924253: step: 928/530, loss: 0.08118797093629837
2023-01-21 09:23:04.021819: step: 932/530, loss: 0.7868897318840027
2023-01-21 09:23:05.135682: step: 936/530, loss: 0.48330992460250854
2023-01-21 09:23:06.235402: step: 940/530, loss: 0.2798249423503876
2023-01-21 09:23:07.342632: step: 944/530, loss: 0.18205463886260986
2023-01-21 09:23:08.427008: step: 948/530, loss: 0.07632866501808167
2023-01-21 09:23:09.543094: step: 952/530, loss: 0.14600276947021484
2023-01-21 09:23:10.644525: step: 956/530, loss: 0.12420116364955902
2023-01-21 09:23:11.759740: step: 960/530, loss: 0.17914581298828125
2023-01-21 09:23:12.858913: step: 964/530, loss: 0.07404899597167969
2023-01-21 09:23:13.994965: step: 968/530, loss: 0.07964115589857101
2023-01-21 09:23:15.087340: step: 972/530, loss: 0.681236743927002
2023-01-21 09:23:16.213034: step: 976/530, loss: 0.07720178365707397
2023-01-21 09:23:17.320374: step: 980/530, loss: 0.0829225480556488
2023-01-21 09:23:18.425529: step: 984/530, loss: 0.3658096492290497
2023-01-21 09:23:19.499756: step: 988/530, loss: 0.06196928024291992
2023-01-21 09:23:20.634748: step: 992/530, loss: 0.10722789913415909
2023-01-21 09:23:21.744442: step: 996/530, loss: 0.4925207495689392
2023-01-21 09:23:22.826901: step: 1000/530, loss: 0.3912269175052643
2023-01-21 09:23:23.929827: step: 1004/530, loss: 0.2373783141374588
2023-01-21 09:23:25.023961: step: 1008/530, loss: 0.1158268004655838
2023-01-21 09:23:26.142723: step: 1012/530, loss: 0.27045750617980957
2023-01-21 09:23:27.231272: step: 1016/530, loss: 0.25494688749313354
2023-01-21 09:23:28.339244: step: 1020/530, loss: 0.08006344735622406
2023-01-21 09:23:29.477220: step: 1024/530, loss: 0.1371137797832489
2023-01-21 09:23:30.581355: step: 1028/530, loss: 0.1419234722852707
2023-01-21 09:23:31.692819: step: 1032/530, loss: 0.5381125211715698
2023-01-21 09:23:32.832701: step: 1036/530, loss: 0.3982507884502411
2023-01-21 09:23:33.957499: step: 1040/530, loss: 0.0492701530456543
2023-01-21 09:23:35.067399: step: 1044/530, loss: 0.9635698795318604
2023-01-21 09:23:36.161400: step: 1048/530, loss: 0.3938000798225403
2023-01-21 09:23:37.271266: step: 1052/530, loss: 0.1287788301706314
2023-01-21 09:23:38.378206: step: 1056/530, loss: 0.17013044655323029
2023-01-21 09:23:39.462520: step: 1060/530, loss: 0.25862035155296326
2023-01-21 09:23:40.608926: step: 1064/530, loss: 0.11327219009399414
2023-01-21 09:23:41.710944: step: 1068/530, loss: 0.1711740493774414
2023-01-21 09:23:42.810121: step: 1072/530, loss: 0.08898964524269104
2023-01-21 09:23:43.939645: step: 1076/530, loss: 0.015608405694365501
2023-01-21 09:23:45.073209: step: 1080/530, loss: 0.1789204627275467
2023-01-21 09:23:46.200036: step: 1084/530, loss: 0.44742846488952637
2023-01-21 09:23:47.340041: step: 1088/530, loss: 0.18467745184898376
2023-01-21 09:23:48.477485: step: 1092/530, loss: 0.570391058921814
2023-01-21 09:23:49.570505: step: 1096/530, loss: 0.046108148992061615
2023-01-21 09:23:50.684687: step: 1100/530, loss: 0.36170142889022827
2023-01-21 09:23:51.807704: step: 1104/530, loss: 0.22364887595176697
2023-01-21 09:23:52.938039: step: 1108/530, loss: 0.1683967560529709
2023-01-21 09:23:54.031259: step: 1112/530, loss: 0.19797784090042114
2023-01-21 09:23:55.138179: step: 1116/530, loss: 0.4206046164035797
2023-01-21 09:23:56.244983: step: 1120/530, loss: 0.14374756813049316
2023-01-21 09:23:57.382576: step: 1124/530, loss: 0.19197100400924683
2023-01-21 09:23:58.470984: step: 1128/530, loss: 0.13220463693141937
2023-01-21 09:23:59.594619: step: 1132/530, loss: 0.13229341804981232
2023-01-21 09:24:00.691875: step: 1136/530, loss: 0.11121062934398651
2023-01-21 09:24:01.802088: step: 1140/530, loss: 0.25190994143486023
2023-01-21 09:24:02.938741: step: 1144/530, loss: 0.1703149825334549
2023-01-21 09:24:04.023351: step: 1148/530, loss: 0.22351226210594177
2023-01-21 09:24:05.094235: step: 1152/530, loss: 0.14180825650691986
2023-01-21 09:24:06.224874: step: 1156/530, loss: 0.30212706327438354
2023-01-21 09:24:07.337395: step: 1160/530, loss: 0.24663162231445312
2023-01-21 09:24:08.440575: step: 1164/530, loss: 0.07623492926359177
2023-01-21 09:24:09.578263: step: 1168/530, loss: 0.16749143600463867
2023-01-21 09:24:10.665114: step: 1172/530, loss: 0.10929059982299805
2023-01-21 09:24:11.797785: step: 1176/530, loss: 0.11108779907226562
2023-01-21 09:24:12.896289: step: 1180/530, loss: 0.23363837599754333
2023-01-21 09:24:14.015036: step: 1184/530, loss: 0.11246080696582794
2023-01-21 09:24:15.121191: step: 1188/530, loss: 0.1567060351371765
2023-01-21 09:24:16.230644: step: 1192/530, loss: 0.316013902425766
2023-01-21 09:24:17.367507: step: 1196/530, loss: 0.2026081085205078
2023-01-21 09:24:18.481543: step: 1200/530, loss: 0.09864607453346252
2023-01-21 09:24:19.587935: step: 1204/530, loss: 0.07972478866577148
2023-01-21 09:24:20.726766: step: 1208/530, loss: 0.3105006217956543
2023-01-21 09:24:21.839327: step: 1212/530, loss: 0.10917239636182785
2023-01-21 09:24:22.944346: step: 1216/530, loss: 0.5183642506599426
2023-01-21 09:24:24.036170: step: 1220/530, loss: 0.04536862298846245
2023-01-21 09:24:25.131339: step: 1224/530, loss: 0.11565761268138885
2023-01-21 09:24:26.250278: step: 1228/530, loss: 0.09205341339111328
2023-01-21 09:24:27.386804: step: 1232/530, loss: 0.06267061084508896
2023-01-21 09:24:28.482382: step: 1236/530, loss: 2.686462879180908
2023-01-21 09:24:29.610416: step: 1240/530, loss: 0.3050172030925751
2023-01-21 09:24:30.727049: step: 1244/530, loss: 0.06304530799388885
2023-01-21 09:24:31.809097: step: 1248/530, loss: 0.1627376675605774
2023-01-21 09:24:32.927116: step: 1252/530, loss: 0.46814003586769104
2023-01-21 09:24:34.012362: step: 1256/530, loss: 0.06027372553944588
2023-01-21 09:24:35.114256: step: 1260/530, loss: 0.2399989515542984
2023-01-21 09:24:36.218736: step: 1264/530, loss: 0.14789867401123047
2023-01-21 09:24:37.329649: step: 1268/530, loss: 0.22475624084472656
2023-01-21 09:24:38.437147: step: 1272/530, loss: 0.7256162762641907
2023-01-21 09:24:39.594905: step: 1276/530, loss: 0.05831442028284073
2023-01-21 09:24:40.681287: step: 1280/530, loss: 0.07535219192504883
2023-01-21 09:24:41.805590: step: 1284/530, loss: 0.21973657608032227
2023-01-21 09:24:42.907242: step: 1288/530, loss: 0.041379548609256744
2023-01-21 09:24:44.007201: step: 1292/530, loss: 0.5651895999908447
2023-01-21 09:24:45.098404: step: 1296/530, loss: 0.22133028507232666
2023-01-21 09:24:46.194485: step: 1300/530, loss: 0.12573829293251038
2023-01-21 09:24:47.303680: step: 1304/530, loss: 0.11169777810573578
2023-01-21 09:24:48.445755: step: 1308/530, loss: 0.1427953690290451
2023-01-21 09:24:49.566165: step: 1312/530, loss: 1.0593838691711426
2023-01-21 09:24:50.704663: step: 1316/530, loss: 0.11087790131568909
2023-01-21 09:24:51.830128: step: 1320/530, loss: 0.17237910628318787
2023-01-21 09:24:52.937818: step: 1324/530, loss: 0.053063295781612396
2023-01-21 09:24:54.060285: step: 1328/530, loss: 0.13668623566627502
2023-01-21 09:24:55.175730: step: 1332/530, loss: 0.18629369139671326
2023-01-21 09:24:56.302195: step: 1336/530, loss: 0.04998207092285156
2023-01-21 09:24:57.398901: step: 1340/530, loss: 0.20288018882274628
2023-01-21 09:24:58.494620: step: 1344/530, loss: 0.42380857467651367
2023-01-21 09:24:59.570765: step: 1348/530, loss: 0.07907561957836151
2023-01-21 09:25:00.684709: step: 1352/530, loss: 0.32152289152145386
2023-01-21 09:25:01.808779: step: 1356/530, loss: 0.28608816862106323
2023-01-21 09:25:02.942514: step: 1360/530, loss: 0.1774696409702301
2023-01-21 09:25:04.085045: step: 1364/530, loss: 0.06905193626880646
2023-01-21 09:25:05.236764: step: 1368/530, loss: 0.08710689097642899
2023-01-21 09:25:06.359142: step: 1372/530, loss: 0.10201006382703781
2023-01-21 09:25:07.475618: step: 1376/530, loss: 0.23266802728176117
2023-01-21 09:25:08.616774: step: 1380/530, loss: 0.1315208375453949
2023-01-21 09:25:09.730403: step: 1384/530, loss: 0.1771114468574524
2023-01-21 09:25:10.847225: step: 1388/530, loss: 0.07756300270557404
2023-01-21 09:25:11.955649: step: 1392/530, loss: 0.12887659668922424
2023-01-21 09:25:13.045404: step: 1396/530, loss: 0.008038520812988281
2023-01-21 09:25:14.162224: step: 1400/530, loss: 0.4961051046848297
2023-01-21 09:25:15.265456: step: 1404/530, loss: 0.03946692869067192
2023-01-21 09:25:16.385421: step: 1408/530, loss: 0.15088291466236115
2023-01-21 09:25:17.505107: step: 1412/530, loss: 0.16244849562644958
2023-01-21 09:25:18.643468: step: 1416/530, loss: 0.2840825915336609
2023-01-21 09:25:19.728844: step: 1420/530, loss: 0.4773137867450714
2023-01-21 09:25:20.822093: step: 1424/530, loss: 0.3524189889431
2023-01-21 09:25:21.944577: step: 1428/530, loss: 0.1570848524570465
2023-01-21 09:25:23.091682: step: 1432/530, loss: 0.21168726682662964
2023-01-21 09:25:24.191483: step: 1436/530, loss: 0.8024312853813171
2023-01-21 09:25:25.273708: step: 1440/530, loss: 0.2134825736284256
2023-01-21 09:25:26.368295: step: 1444/530, loss: 0.36764150857925415
2023-01-21 09:25:27.464075: step: 1448/530, loss: 0.22510509192943573
2023-01-21 09:25:28.584898: step: 1452/530, loss: 0.8723359107971191
2023-01-21 09:25:29.675704: step: 1456/530, loss: 0.133440300822258
2023-01-21 09:25:30.796724: step: 1460/530, loss: 0.05185108631849289
2023-01-21 09:25:31.947559: step: 1464/530, loss: 0.6737065315246582
2023-01-21 09:25:33.065242: step: 1468/530, loss: 0.4873160123825073
2023-01-21 09:25:34.158862: step: 1472/530, loss: 0.11334848403930664
2023-01-21 09:25:35.269485: step: 1476/530, loss: 0.11058960855007172
2023-01-21 09:25:36.382805: step: 1480/530, loss: 0.16094177961349487
2023-01-21 09:25:37.486319: step: 1484/530, loss: 0.5077104568481445
2023-01-21 09:25:38.598855: step: 1488/530, loss: 0.09440350532531738
2023-01-21 09:25:39.663634: step: 1492/530, loss: 0.18258939683437347
2023-01-21 09:25:40.777703: step: 1496/530, loss: 0.7942599058151245
2023-01-21 09:25:41.916129: step: 1500/530, loss: 0.4238957464694977
2023-01-21 09:25:43.016986: step: 1504/530, loss: 0.0418948158621788
2023-01-21 09:25:44.125817: step: 1508/530, loss: 0.27362021803855896
2023-01-21 09:25:45.215230: step: 1512/530, loss: 0.0397065170109272
2023-01-21 09:25:46.334225: step: 1516/530, loss: 0.6666883230209351
2023-01-21 09:25:47.436086: step: 1520/530, loss: 1.1499556303024292
2023-01-21 09:25:48.568766: step: 1524/530, loss: 0.15800829231739044
2023-01-21 09:25:49.688778: step: 1528/530, loss: 0.09731989353895187
2023-01-21 09:25:50.803507: step: 1532/530, loss: 0.10863862186670303
2023-01-21 09:25:51.926828: step: 1536/530, loss: 0.08315277099609375
2023-01-21 09:25:53.060725: step: 1540/530, loss: 0.05565300211310387
2023-01-21 09:25:54.157273: step: 1544/530, loss: 0.03651104122400284
2023-01-21 09:25:55.235046: step: 1548/530, loss: 0.038918305188417435
2023-01-21 09:25:56.356745: step: 1552/530, loss: 0.08883686363697052
2023-01-21 09:25:57.473844: step: 1556/530, loss: 0.7900556325912476
2023-01-21 09:25:58.584200: step: 1560/530, loss: 0.0810883566737175
2023-01-21 09:25:59.698778: step: 1564/530, loss: 0.27109137177467346
2023-01-21 09:26:00.800587: step: 1568/530, loss: 0.22881156206130981
2023-01-21 09:26:01.879745: step: 1572/530, loss: 0.1351308375597
2023-01-21 09:26:02.995394: step: 1576/530, loss: 0.13519592583179474
2023-01-21 09:26:04.097417: step: 1580/530, loss: 0.8639758229255676
2023-01-21 09:26:05.232132: step: 1584/530, loss: 0.22835516929626465
2023-01-21 09:26:06.364464: step: 1588/530, loss: 0.07148914039134979
2023-01-21 09:26:07.455978: step: 1592/530, loss: 0.027689125388860703
2023-01-21 09:26:08.571967: step: 1596/530, loss: 0.04994068294763565
2023-01-21 09:26:09.674249: step: 1600/530, loss: 0.321359246969223
2023-01-21 09:26:10.785461: step: 1604/530, loss: 0.10063913464546204
2023-01-21 09:26:11.913280: step: 1608/530, loss: 0.6468959450721741
2023-01-21 09:26:13.021985: step: 1612/530, loss: 0.1955525279045105
2023-01-21 09:26:14.154529: step: 1616/530, loss: 0.38106268644332886
2023-01-21 09:26:15.269889: step: 1620/530, loss: 0.20295333862304688
2023-01-21 09:26:16.385130: step: 1624/530, loss: 0.4059176445007324
2023-01-21 09:26:17.503855: step: 1628/530, loss: 0.4171333312988281
2023-01-21 09:26:18.610344: step: 1632/530, loss: 0.14496035873889923
2023-01-21 09:26:19.746698: step: 1636/530, loss: 0.30505600571632385
2023-01-21 09:26:20.866471: step: 1640/530, loss: 0.6908669471740723
2023-01-21 09:26:21.966279: step: 1644/530, loss: 0.25509196519851685
2023-01-21 09:26:23.059844: step: 1648/530, loss: 0.17221689224243164
2023-01-21 09:26:24.156334: step: 1652/530, loss: 0.06633615493774414
2023-01-21 09:26:25.257463: step: 1656/530, loss: 0.2502712309360504
2023-01-21 09:26:26.335817: step: 1660/530, loss: 0.8248711824417114
2023-01-21 09:26:27.432846: step: 1664/530, loss: 0.3465215265750885
2023-01-21 09:26:28.543918: step: 1668/530, loss: 0.08193397521972656
2023-01-21 09:26:29.659639: step: 1672/530, loss: 0.12040877342224121
2023-01-21 09:26:30.786040: step: 1676/530, loss: 0.35047677159309387
2023-01-21 09:26:31.910996: step: 1680/530, loss: 0.049019861966371536
2023-01-21 09:26:33.012134: step: 1684/530, loss: 0.05154692009091377
2023-01-21 09:26:34.132427: step: 1688/530, loss: 0.282259464263916
2023-01-21 09:26:35.242695: step: 1692/530, loss: 0.2670758366584778
2023-01-21 09:26:36.341736: step: 1696/530, loss: 0.0017387866973876953
2023-01-21 09:26:37.443672: step: 1700/530, loss: 0.011727381497621536
2023-01-21 09:26:38.556358: step: 1704/530, loss: 0.10878276824951172
2023-01-21 09:26:39.668714: step: 1708/530, loss: 0.2516377568244934
2023-01-21 09:26:40.787707: step: 1712/530, loss: 0.10581941902637482
2023-01-21 09:26:41.920032: step: 1716/530, loss: 0.9195899963378906
2023-01-21 09:26:43.062931: step: 1720/530, loss: 0.16059979796409607
2023-01-21 09:26:44.177116: step: 1724/530, loss: 0.09508000314235687
2023-01-21 09:26:45.291668: step: 1728/530, loss: 0.21087685227394104
2023-01-21 09:26:46.397074: step: 1732/530, loss: 0.055779457092285156
2023-01-21 09:26:47.521650: step: 1736/530, loss: 0.2426820695400238
2023-01-21 09:26:48.707324: step: 1740/530, loss: 0.1860208511352539
2023-01-21 09:26:49.813480: step: 1744/530, loss: 0.05705900490283966
2023-01-21 09:26:50.945610: step: 1748/530, loss: 0.36168450117111206
2023-01-21 09:26:52.067887: step: 1752/530, loss: 0.1211925595998764
2023-01-21 09:26:53.167609: step: 1756/530, loss: 0.03216152265667915
2023-01-21 09:26:54.284301: step: 1760/530, loss: 0.23562975227832794
2023-01-21 09:26:55.358131: step: 1764/530, loss: 1.104426622390747
2023-01-21 09:26:56.474895: step: 1768/530, loss: 0.25021687150001526
2023-01-21 09:26:57.580835: step: 1772/530, loss: 0.058877088129520416
2023-01-21 09:26:58.706288: step: 1776/530, loss: 0.4066980481147766
2023-01-21 09:26:59.776432: step: 1780/530, loss: 0.06185188516974449
2023-01-21 09:27:00.853855: step: 1784/530, loss: 0.08910875022411346
2023-01-21 09:27:01.995167: step: 1788/530, loss: 0.5735712051391602
2023-01-21 09:27:03.108888: step: 1792/530, loss: 0.18641769886016846
2023-01-21 09:27:04.230243: step: 1796/530, loss: 0.15713229775428772
2023-01-21 09:27:05.309539: step: 1800/530, loss: 0.049398139119148254
2023-01-21 09:27:06.424375: step: 1804/530, loss: 0.049103450030088425
2023-01-21 09:27:07.506066: step: 1808/530, loss: 0.15710654854774475
2023-01-21 09:27:08.610616: step: 1812/530, loss: 0.10331745445728302
2023-01-21 09:27:09.697389: step: 1816/530, loss: 0.21179240942001343
2023-01-21 09:27:10.827075: step: 1820/530, loss: 0.09028349071741104
2023-01-21 09:27:11.923759: step: 1824/530, loss: 0.21850453317165375
2023-01-21 09:27:13.058077: step: 1828/530, loss: 0.20966672897338867
2023-01-21 09:27:14.175863: step: 1832/530, loss: 0.7462459802627563
2023-01-21 09:27:15.265586: step: 1836/530, loss: 0.211009219288826
2023-01-21 09:27:16.387954: step: 1840/530, loss: 0.09029360115528107
2023-01-21 09:27:17.512906: step: 1844/530, loss: 0.1499272882938385
2023-01-21 09:27:18.629941: step: 1848/530, loss: 0.4164814054965973
2023-01-21 09:27:19.737654: step: 1852/530, loss: 0.10152693092823029
2023-01-21 09:27:20.842693: step: 1856/530, loss: 0.1695001721382141
2023-01-21 09:27:21.967822: step: 1860/530, loss: 0.1668999195098877
2023-01-21 09:27:23.078750: step: 1864/530, loss: 0.12263212352991104
2023-01-21 09:27:24.195935: step: 1868/530, loss: 0.07730965316295624
2023-01-21 09:27:25.296301: step: 1872/530, loss: 0.12123580276966095
2023-01-21 09:27:26.441820: step: 1876/530, loss: 0.1081201583147049
2023-01-21 09:27:27.565451: step: 1880/530, loss: 0.13940171897411346
2023-01-21 09:27:28.655774: step: 1884/530, loss: 0.4191620647907257
2023-01-21 09:27:29.737027: step: 1888/530, loss: 0.12703362107276917
2023-01-21 09:27:30.872418: step: 1892/530, loss: 0.4371488690376282
2023-01-21 09:27:31.974556: step: 1896/530, loss: 0.4159420132637024
2023-01-21 09:27:33.104069: step: 1900/530, loss: 0.2792503535747528
2023-01-21 09:27:34.220167: step: 1904/530, loss: 0.11866598576307297
2023-01-21 09:27:35.320678: step: 1908/530, loss: 0.19562062621116638
2023-01-21 09:27:36.437056: step: 1912/530, loss: 0.1899430751800537
2023-01-21 09:27:37.580778: step: 1916/530, loss: 0.043691232800483704
2023-01-21 09:27:38.669315: step: 1920/530, loss: 0.6341274976730347
2023-01-21 09:27:39.749444: step: 1924/530, loss: 0.6405299305915833
2023-01-21 09:27:40.851030: step: 1928/530, loss: 0.13126060366630554
2023-01-21 09:27:41.965196: step: 1932/530, loss: 0.19063836336135864
2023-01-21 09:27:43.069124: step: 1936/530, loss: 0.06951484829187393
2023-01-21 09:27:44.191654: step: 1940/530, loss: 0.08657412230968475
2023-01-21 09:27:45.306450: step: 1944/530, loss: 0.30267333984375
2023-01-21 09:27:46.423436: step: 1948/530, loss: 0.24932155013084412
2023-01-21 09:27:47.520960: step: 1952/530, loss: 0.09713473170995712
2023-01-21 09:27:48.633784: step: 1956/530, loss: 0.13251018524169922
2023-01-21 09:27:49.750041: step: 1960/530, loss: 0.13206633925437927
2023-01-21 09:27:50.836091: step: 1964/530, loss: 0.15397652983665466
2023-01-21 09:27:51.989514: step: 1968/530, loss: 0.04049701616168022
2023-01-21 09:27:53.103224: step: 1972/530, loss: 0.19873452186584473
2023-01-21 09:27:54.221632: step: 1976/530, loss: 0.14456096291542053
2023-01-21 09:27:55.292487: step: 1980/530, loss: 0.8957277536392212
2023-01-21 09:27:56.404884: step: 1984/530, loss: 0.06741056591272354
2023-01-21 09:27:57.537838: step: 1988/530, loss: 0.27179330587387085
2023-01-21 09:27:58.648092: step: 1992/530, loss: 0.9821248054504395
2023-01-21 09:27:59.759043: step: 1996/530, loss: 0.1198514923453331
2023-01-21 09:28:00.858918: step: 2000/530, loss: 0.3271741271018982
2023-01-21 09:28:01.981599: step: 2004/530, loss: 0.09060096740722656
2023-01-21 09:28:03.102569: step: 2008/530, loss: 0.08290982246398926
2023-01-21 09:28:04.197893: step: 2012/530, loss: 0.09377145767211914
2023-01-21 09:28:05.289113: step: 2016/530, loss: 0.4499048590660095
2023-01-21 09:28:06.402362: step: 2020/530, loss: 1.5151746273040771
2023-01-21 09:28:07.560314: step: 2024/530, loss: 0.35462790727615356
2023-01-21 09:28:08.669024: step: 2028/530, loss: 0.2617608904838562
2023-01-21 09:28:09.776808: step: 2032/530, loss: 0.1583174765110016
2023-01-21 09:28:10.910445: step: 2036/530, loss: 0.22380900382995605
2023-01-21 09:28:12.057085: step: 2040/530, loss: 0.15170994400978088
2023-01-21 09:28:13.177777: step: 2044/530, loss: 0.432948499917984
2023-01-21 09:28:14.298878: step: 2048/530, loss: 0.11401405930519104
2023-01-21 09:28:15.414903: step: 2052/530, loss: 0.08476801216602325
2023-01-21 09:28:16.517380: step: 2056/530, loss: 0.3172012269496918
2023-01-21 09:28:17.643499: step: 2060/530, loss: 0.11792431771755219
2023-01-21 09:28:18.743026: step: 2064/530, loss: 0.28767237067222595
2023-01-21 09:28:19.855650: step: 2068/530, loss: 0.06708383560180664
2023-01-21 09:28:20.973412: step: 2072/530, loss: 7.337092399597168
2023-01-21 09:28:22.115823: step: 2076/530, loss: 0.1366681158542633
2023-01-21 09:28:23.213840: step: 2080/530, loss: 0.10032234340906143
2023-01-21 09:28:24.367359: step: 2084/530, loss: 0.09884100407361984
2023-01-21 09:28:25.503561: step: 2088/530, loss: 0.1326029747724533
2023-01-21 09:28:26.638368: step: 2092/530, loss: 0.24804915487766266
2023-01-21 09:28:27.778740: step: 2096/530, loss: 0.10813150554895401
2023-01-21 09:28:28.891928: step: 2100/530, loss: 0.13777141273021698
2023-01-21 09:28:30.045612: step: 2104/530, loss: 0.08997378498315811
2023-01-21 09:28:31.157692: step: 2108/530, loss: 0.09419694542884827
2023-01-21 09:28:32.260289: step: 2112/530, loss: 0.5178403258323669
2023-01-21 09:28:33.358804: step: 2116/530, loss: 0.3488030433654785
2023-01-21 09:28:34.439861: step: 2120/530, loss: 0.10376934707164764
==================================================
Loss: 0.253
--------------------
Dev: {'event': {'p': 0.5708622398414271, 'r': 0.7669773635153129, 'f1': 0.6545454545454545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Test: {'event': {'p': 0.6044052863436123, 'r': 0.7995337995337995, 'f1': 0.6884094330155545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Chinese: {'event': {'p': 0.6578947368421053, 'r': 0.9259259259259259, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Korean: {'event': {'p': 0.6470588235294118, 'r': 0.5238095238095238, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Russian: {'event': {'p': 0.391304347826087, 'r': 0.5, 'f1': 0.4390243902439025}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5708622398414271, 'r': 0.7669773635153129, 'f1': 0.6545454545454545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Chinese: {'event': {'p': 0.6044052863436123, 'r': 0.7995337995337995, 'f1': 0.6884094330155545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Chinese: {'event': {'p': 0.6578947368421053, 'r': 0.9259259259259259, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7631578947368421, 'r': 0.4603174603174603, 'f1': 0.5742574257425742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.625, 'r': 0.4166666666666667, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
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 09:29:19.457843: step: 4/530, loss: 0.1412806510925293
2023-01-21 09:29:20.553393: step: 8/530, loss: 0.06201524659991264
2023-01-21 09:29:21.645588: step: 12/530, loss: 0.06677856296300888
2023-01-21 09:29:22.749557: step: 16/530, loss: 0.16642045974731445
2023-01-21 09:29:23.838414: step: 20/530, loss: 0.0463135726749897
2023-01-21 09:29:24.919724: step: 24/530, loss: 0.12257456034421921
2023-01-21 09:29:26.035812: step: 28/530, loss: 0.05361614376306534
2023-01-21 09:29:27.122895: step: 32/530, loss: 0.10993947833776474
2023-01-21 09:29:28.230228: step: 36/530, loss: 0.05338134616613388
2023-01-21 09:29:29.314070: step: 40/530, loss: 0.05153698846697807
2023-01-21 09:29:30.417592: step: 44/530, loss: 0.154712975025177
2023-01-21 09:29:31.507784: step: 48/530, loss: 0.498554527759552
2023-01-21 09:29:32.609889: step: 52/530, loss: 1.0199856758117676
2023-01-21 09:29:33.721573: step: 56/530, loss: 0.0324769988656044
2023-01-21 09:29:34.815973: step: 60/530, loss: 0.0748293399810791
2023-01-21 09:29:35.937053: step: 64/530, loss: 0.21995745599269867
2023-01-21 09:29:37.078563: step: 68/530, loss: 0.1282590925693512
2023-01-21 09:29:38.187097: step: 72/530, loss: 0.10734911262989044
2023-01-21 09:29:39.290972: step: 76/530, loss: 0.22396288812160492
2023-01-21 09:29:40.404477: step: 80/530, loss: 0.07477708160877228
2023-01-21 09:29:41.477415: step: 84/530, loss: 0.03555621951818466
2023-01-21 09:29:42.574493: step: 88/530, loss: 0.23825010657310486
2023-01-21 09:29:43.697160: step: 92/530, loss: 0.30513685941696167
2023-01-21 09:29:44.782272: step: 96/530, loss: 0.051180649548769
2023-01-21 09:29:45.867864: step: 100/530, loss: 0.058794356882572174
2023-01-21 09:29:46.962351: step: 104/530, loss: 0.031160736456513405
2023-01-21 09:29:48.063794: step: 108/530, loss: 0.12346458435058594
2023-01-21 09:29:49.194702: step: 112/530, loss: 0.08231782913208008
2023-01-21 09:29:50.344608: step: 116/530, loss: 0.16058455407619476
2023-01-21 09:29:51.465264: step: 120/530, loss: 0.16344527900218964
2023-01-21 09:29:52.575796: step: 124/530, loss: 0.09799690544605255
2023-01-21 09:29:53.693615: step: 128/530, loss: 0.018441438674926758
2023-01-21 09:29:54.806515: step: 132/530, loss: 0.19248907268047333
2023-01-21 09:29:55.930338: step: 136/530, loss: 0.260833740234375
2023-01-21 09:29:57.028458: step: 140/530, loss: 0.24858427047729492
2023-01-21 09:29:58.115947: step: 144/530, loss: 0.05825462564826012
2023-01-21 09:29:59.204609: step: 148/530, loss: 0.03804969787597656
2023-01-21 09:30:00.304783: step: 152/530, loss: 0.11118941754102707
2023-01-21 09:30:01.400508: step: 156/530, loss: 0.060916900634765625
2023-01-21 09:30:02.478909: step: 160/530, loss: 0.06108136102557182
2023-01-21 09:30:03.596365: step: 164/530, loss: 0.1704285740852356
2023-01-21 09:30:04.669463: step: 168/530, loss: 0.08091020584106445
2023-01-21 09:30:05.781526: step: 172/530, loss: 0.09379314631223679
2023-01-21 09:30:06.939964: step: 176/530, loss: 0.16600283980369568
2023-01-21 09:30:08.035822: step: 180/530, loss: 0.03681764751672745
2023-01-21 09:30:09.171909: step: 184/530, loss: 0.07739467918872833
2023-01-21 09:30:10.286838: step: 188/530, loss: 0.03204236179590225
2023-01-21 09:30:11.399345: step: 192/530, loss: 0.4384584426879883
2023-01-21 09:30:12.513141: step: 196/530, loss: 0.082837775349617
2023-01-21 09:30:13.614320: step: 200/530, loss: 0.16306428611278534
2023-01-21 09:30:14.740812: step: 204/530, loss: 0.12127232551574707
2023-01-21 09:30:15.832026: step: 208/530, loss: 0.050431132316589355
2023-01-21 09:30:16.923199: step: 212/530, loss: 0.2567879855632782
2023-01-21 09:30:18.043838: step: 216/530, loss: 0.16017284989356995
2023-01-21 09:30:19.184473: step: 220/530, loss: 0.16926231980323792
2023-01-21 09:30:20.289016: step: 224/530, loss: 0.08518343418836594
2023-01-21 09:30:21.400905: step: 228/530, loss: 0.12667135894298553
2023-01-21 09:30:22.533064: step: 232/530, loss: 0.13655593991279602
2023-01-21 09:30:23.658649: step: 236/530, loss: 0.39121952652931213
2023-01-21 09:30:24.781190: step: 240/530, loss: 0.4892156720161438
2023-01-21 09:30:25.922914: step: 244/530, loss: 0.19624634087085724
2023-01-21 09:30:27.036493: step: 248/530, loss: 0.04846344143152237
2023-01-21 09:30:28.143984: step: 252/530, loss: 0.1293279528617859
2023-01-21 09:30:29.237494: step: 256/530, loss: 0.023111533373594284
2023-01-21 09:30:30.365829: step: 260/530, loss: 0.2309425324201584
2023-01-21 09:30:31.478931: step: 264/530, loss: 0.39034825563430786
2023-01-21 09:30:32.598843: step: 268/530, loss: 0.040932752192020416
2023-01-21 09:30:33.686242: step: 272/530, loss: 0.10498218238353729
2023-01-21 09:30:34.795807: step: 276/530, loss: 0.04104342311620712
2023-01-21 09:30:35.893177: step: 280/530, loss: 0.13160772621631622
2023-01-21 09:30:37.036918: step: 284/530, loss: 0.04770074039697647
2023-01-21 09:30:38.138153: step: 288/530, loss: 0.05871248245239258
2023-01-21 09:30:39.231528: step: 292/530, loss: 0.08321800827980042
2023-01-21 09:30:40.326058: step: 296/530, loss: 0.3971864581108093
2023-01-21 09:30:41.421144: step: 300/530, loss: 0.15843066573143005
2023-01-21 09:30:42.508931: step: 304/530, loss: 0.05259087309241295
2023-01-21 09:30:43.611419: step: 308/530, loss: 0.11440610885620117
2023-01-21 09:30:44.728958: step: 312/530, loss: 0.0426514632999897
2023-01-21 09:30:45.820470: step: 316/530, loss: 0.07652168720960617
2023-01-21 09:30:46.930773: step: 320/530, loss: 0.04016528278589249
2023-01-21 09:30:48.067287: step: 324/530, loss: 0.06114664301276207
2023-01-21 09:30:49.213381: step: 328/530, loss: 0.059960126876831055
2023-01-21 09:30:50.339430: step: 332/530, loss: 0.06624917685985565
2023-01-21 09:30:51.440332: step: 336/530, loss: 0.07056713104248047
2023-01-21 09:30:52.547710: step: 340/530, loss: 0.20618152618408203
2023-01-21 09:30:53.706827: step: 344/530, loss: 0.28959882259368896
2023-01-21 09:30:54.804092: step: 348/530, loss: 0.13309133052825928
2023-01-21 09:30:55.935547: step: 352/530, loss: 0.03675325959920883
2023-01-21 09:30:57.023902: step: 356/530, loss: 0.10258965194225311
2023-01-21 09:30:58.157472: step: 360/530, loss: 0.17018049955368042
2023-01-21 09:30:59.296309: step: 364/530, loss: 0.1614781618118286
2023-01-21 09:31:00.416023: step: 368/530, loss: 0.49032869935035706
2023-01-21 09:31:01.531574: step: 372/530, loss: 0.06695500016212463
2023-01-21 09:31:02.649120: step: 376/530, loss: 0.37270721793174744
2023-01-21 09:31:03.765675: step: 380/530, loss: 0.05695495754480362
2023-01-21 09:31:04.883487: step: 384/530, loss: 0.11721185594797134
2023-01-21 09:31:05.974344: step: 388/530, loss: 0.06376629322767258
2023-01-21 09:31:07.103332: step: 392/530, loss: 0.10203037410974503
2023-01-21 09:31:08.218709: step: 396/530, loss: 0.14311876893043518
2023-01-21 09:31:09.341656: step: 400/530, loss: 0.14815779030323029
2023-01-21 09:31:10.466095: step: 404/530, loss: 0.8976076245307922
2023-01-21 09:31:11.541571: step: 408/530, loss: 0.049604419618844986
2023-01-21 09:31:12.656932: step: 412/530, loss: 0.05662555992603302
2023-01-21 09:31:13.778953: step: 416/530, loss: 0.07676362991333008
2023-01-21 09:31:14.875899: step: 420/530, loss: 0.05551471561193466
2023-01-21 09:31:15.994923: step: 424/530, loss: 0.1177053451538086
2023-01-21 09:31:17.093224: step: 428/530, loss: 0.14917390048503876
2023-01-21 09:31:18.241747: step: 432/530, loss: 0.07037587463855743
2023-01-21 09:31:19.316496: step: 436/530, loss: 0.2415897399187088
2023-01-21 09:31:20.450781: step: 440/530, loss: 0.7074052691459656
2023-01-21 09:31:21.579096: step: 444/530, loss: 0.1987031102180481
2023-01-21 09:31:22.694225: step: 448/530, loss: 0.13592669367790222
2023-01-21 09:31:23.791338: step: 452/530, loss: 0.07063045352697372
2023-01-21 09:31:24.873549: step: 456/530, loss: 0.05031852796673775
2023-01-21 09:31:26.030420: step: 460/530, loss: 0.13677817583084106
2023-01-21 09:31:27.136629: step: 464/530, loss: 0.2800731658935547
2023-01-21 09:31:28.239074: step: 468/530, loss: 0.11101584136486053
2023-01-21 09:31:29.318455: step: 472/530, loss: 0.2019510269165039
2023-01-21 09:31:30.443511: step: 476/530, loss: 0.1960899829864502
2023-01-21 09:31:31.558503: step: 480/530, loss: 0.040073491632938385
2023-01-21 09:31:32.672160: step: 484/530, loss: 0.2950019836425781
2023-01-21 09:31:33.794585: step: 488/530, loss: 0.10425710678100586
2023-01-21 09:31:34.908732: step: 492/530, loss: 0.21908989548683167
2023-01-21 09:31:36.046273: step: 496/530, loss: 0.07490558922290802
2023-01-21 09:31:37.148157: step: 500/530, loss: 0.22998161613941193
2023-01-21 09:31:38.262773: step: 504/530, loss: 0.004678630735725164
2023-01-21 09:31:39.364469: step: 508/530, loss: 0.19590897858142853
2023-01-21 09:31:40.500628: step: 512/530, loss: 0.0851888656616211
2023-01-21 09:31:41.600412: step: 516/530, loss: 0.0888313353061676
2023-01-21 09:31:42.761276: step: 520/530, loss: 0.12855833768844604
2023-01-21 09:31:43.875151: step: 524/530, loss: 0.3092435896396637
2023-01-21 09:31:44.970253: step: 528/530, loss: 0.08574266731739044
2023-01-21 09:31:46.115288: step: 532/530, loss: 0.08121633529663086
2023-01-21 09:31:47.226592: step: 536/530, loss: 0.0470576286315918
2023-01-21 09:31:48.308716: step: 540/530, loss: 0.05300460010766983
2023-01-21 09:31:49.445369: step: 544/530, loss: 0.05453081056475639
2023-01-21 09:31:50.547081: step: 548/530, loss: 0.08517379313707352
2023-01-21 09:31:51.652484: step: 552/530, loss: 0.07322397083044052
2023-01-21 09:31:52.763005: step: 556/530, loss: 0.04077902063727379
2023-01-21 09:31:53.874933: step: 560/530, loss: 0.019483327865600586
2023-01-21 09:31:54.988485: step: 564/530, loss: 0.4246101379394531
2023-01-21 09:31:56.094132: step: 568/530, loss: 1.004377007484436
2023-01-21 09:31:57.190322: step: 572/530, loss: 0.09844322502613068
2023-01-21 09:31:58.309227: step: 576/530, loss: 0.35216182470321655
2023-01-21 09:31:59.401585: step: 580/530, loss: 0.05642843618988991
2023-01-21 09:32:00.520673: step: 584/530, loss: 0.19548234343528748
2023-01-21 09:32:01.609036: step: 588/530, loss: 0.26619473099708557
2023-01-21 09:32:02.759611: step: 592/530, loss: 0.01701502874493599
2023-01-21 09:32:03.910795: step: 596/530, loss: 0.10624275356531143
2023-01-21 09:32:05.045626: step: 600/530, loss: 0.5641342401504517
2023-01-21 09:32:06.186175: step: 604/530, loss: 0.07854967564344406
2023-01-21 09:32:07.310324: step: 608/530, loss: 0.13105639815330505
2023-01-21 09:32:08.440784: step: 612/530, loss: 0.10545094311237335
2023-01-21 09:32:09.536867: step: 616/530, loss: 0.17296594381332397
2023-01-21 09:32:10.662537: step: 620/530, loss: 4.8435893058776855
2023-01-21 09:32:11.765371: step: 624/530, loss: 0.08275661617517471
2023-01-21 09:32:12.933194: step: 628/530, loss: 0.06939706206321716
2023-01-21 09:32:14.024833: step: 632/530, loss: 0.16816312074661255
2023-01-21 09:32:15.158514: step: 636/530, loss: 0.20705966651439667
2023-01-21 09:32:16.275513: step: 640/530, loss: 0.0594182014465332
2023-01-21 09:32:17.373920: step: 644/530, loss: 0.28857794404029846
2023-01-21 09:32:18.502628: step: 648/530, loss: 0.21053582429885864
2023-01-21 09:32:19.622114: step: 652/530, loss: 0.7438284158706665
2023-01-21 09:32:20.725391: step: 656/530, loss: 0.18033218383789062
2023-01-21 09:32:21.824487: step: 660/530, loss: 0.27255547046661377
2023-01-21 09:32:22.945443: step: 664/530, loss: 0.1447506546974182
2023-01-21 09:32:24.054854: step: 668/530, loss: 0.6236919164657593
2023-01-21 09:32:25.166106: step: 672/530, loss: 0.18955735862255096
2023-01-21 09:32:26.273656: step: 676/530, loss: 0.9992786645889282
2023-01-21 09:32:27.379532: step: 680/530, loss: 0.12059192359447479
2023-01-21 09:32:28.461625: step: 684/530, loss: 0.16654592752456665
2023-01-21 09:32:29.558833: step: 688/530, loss: 0.040083982050418854
2023-01-21 09:32:30.655800: step: 692/530, loss: 0.3588658571243286
2023-01-21 09:32:31.761942: step: 696/530, loss: 0.12521058320999146
2023-01-21 09:32:32.865386: step: 700/530, loss: 0.13614550232887268
2023-01-21 09:32:33.969652: step: 704/530, loss: 0.1731891632080078
2023-01-21 09:32:35.089984: step: 708/530, loss: 0.10172943770885468
2023-01-21 09:32:36.258714: step: 712/530, loss: 0.14219379425048828
2023-01-21 09:32:37.352615: step: 716/530, loss: 0.07694966346025467
2023-01-21 09:32:38.504997: step: 720/530, loss: 1.7732086181640625
2023-01-21 09:32:39.624024: step: 724/530, loss: 0.14430752396583557
2023-01-21 09:32:40.734201: step: 728/530, loss: 0.07118859887123108
2023-01-21 09:32:41.866663: step: 732/530, loss: 0.05580034479498863
2023-01-21 09:32:43.005555: step: 736/530, loss: 0.27044758200645447
2023-01-21 09:32:44.124338: step: 740/530, loss: 0.04577532038092613
2023-01-21 09:32:45.229212: step: 744/530, loss: 0.06258101761341095
2023-01-21 09:32:46.339240: step: 748/530, loss: 0.24775853753089905
2023-01-21 09:32:47.434843: step: 752/530, loss: 0.11392946541309357
2023-01-21 09:32:48.542782: step: 756/530, loss: 0.08901243656873703
2023-01-21 09:32:49.694119: step: 760/530, loss: 0.057595159858465195
2023-01-21 09:32:50.794126: step: 764/530, loss: 0.44379279017448425
2023-01-21 09:32:51.931154: step: 768/530, loss: 0.3000926971435547
2023-01-21 09:32:53.045212: step: 772/530, loss: 0.36787793040275574
2023-01-21 09:32:54.166888: step: 776/530, loss: 0.04904355853796005
2023-01-21 09:32:55.280422: step: 780/530, loss: 0.6074905395507812
2023-01-21 09:32:56.378808: step: 784/530, loss: 0.013667488470673561
2023-01-21 09:32:57.506196: step: 788/530, loss: 0.1963481903076172
2023-01-21 09:32:58.611241: step: 792/530, loss: 0.07738657295703888
2023-01-21 09:32:59.751745: step: 796/530, loss: 0.21989822387695312
2023-01-21 09:33:00.860444: step: 800/530, loss: 0.08679161220788956
2023-01-21 09:33:01.984170: step: 804/530, loss: 0.1227174773812294
2023-01-21 09:33:03.141330: step: 808/530, loss: 0.23414096236228943
2023-01-21 09:33:04.260352: step: 812/530, loss: 0.08174066245555878
2023-01-21 09:33:05.371196: step: 816/530, loss: 0.20460662245750427
2023-01-21 09:33:06.506156: step: 820/530, loss: 0.07549504935741425
2023-01-21 09:33:07.645466: step: 824/530, loss: 0.23754271864891052
2023-01-21 09:33:08.766209: step: 828/530, loss: 0.3883371353149414
2023-01-21 09:33:09.909062: step: 832/530, loss: 0.07773430645465851
2023-01-21 09:33:11.013843: step: 836/530, loss: 0.15171414613723755
2023-01-21 09:33:12.112152: step: 840/530, loss: 0.06627267599105835
2023-01-21 09:33:13.251020: step: 844/530, loss: 0.22590437531471252
2023-01-21 09:33:14.346863: step: 848/530, loss: 0.16169938445091248
2023-01-21 09:33:15.467973: step: 852/530, loss: 2.1008481979370117
2023-01-21 09:33:16.564531: step: 856/530, loss: 0.21117496490478516
2023-01-21 09:33:17.696868: step: 860/530, loss: 0.09196414798498154
2023-01-21 09:33:18.798128: step: 864/530, loss: 0.11832189559936523
2023-01-21 09:33:19.904854: step: 868/530, loss: 0.07642853260040283
2023-01-21 09:33:21.006138: step: 872/530, loss: 2.9095101356506348
2023-01-21 09:33:22.109680: step: 876/530, loss: 0.022319747135043144
2023-01-21 09:33:23.230987: step: 880/530, loss: 0.15028639137744904
2023-01-21 09:33:24.351064: step: 884/530, loss: 0.09087555855512619
2023-01-21 09:33:25.464804: step: 888/530, loss: 1.0790647268295288
2023-01-21 09:33:26.567291: step: 892/530, loss: 1.3735277652740479
2023-01-21 09:33:27.665253: step: 896/530, loss: 0.16378679871559143
2023-01-21 09:33:28.764453: step: 900/530, loss: 0.09727010875940323
2023-01-21 09:33:29.897228: step: 904/530, loss: 0.933566153049469
2023-01-21 09:33:31.016184: step: 908/530, loss: 0.15558242797851562
2023-01-21 09:33:32.102942: step: 912/530, loss: 0.19154386222362518
2023-01-21 09:33:33.227072: step: 916/530, loss: 0.40183225274086
2023-01-21 09:33:34.336996: step: 920/530, loss: 0.07803884893655777
2023-01-21 09:33:35.456525: step: 924/530, loss: 0.17959412932395935
2023-01-21 09:33:36.557722: step: 928/530, loss: 0.11197566986083984
2023-01-21 09:33:37.660173: step: 932/530, loss: 0.29285290837287903
2023-01-21 09:33:38.788937: step: 936/530, loss: 0.07945018261671066
2023-01-21 09:33:39.896151: step: 940/530, loss: 0.07374639809131622
2023-01-21 09:33:41.038495: step: 944/530, loss: 0.2392738312482834
2023-01-21 09:33:42.178117: step: 948/530, loss: 0.13567790389060974
2023-01-21 09:33:43.273264: step: 952/530, loss: 0.08202478289604187
2023-01-21 09:33:44.376450: step: 956/530, loss: 0.31894809007644653
2023-01-21 09:33:45.492598: step: 960/530, loss: 0.1318780928850174
2023-01-21 09:33:46.636391: step: 964/530, loss: 0.06217651441693306
2023-01-21 09:33:47.724718: step: 968/530, loss: 0.01972179487347603
2023-01-21 09:33:48.857596: step: 972/530, loss: 0.08963070064783096
2023-01-21 09:33:49.973834: step: 976/530, loss: 0.12298707664012909
2023-01-21 09:33:51.094388: step: 980/530, loss: 0.10794582217931747
2023-01-21 09:33:52.180268: step: 984/530, loss: 0.03538684919476509
2023-01-21 09:33:53.265180: step: 988/530, loss: 0.09443295001983643
2023-01-21 09:33:54.386626: step: 992/530, loss: 0.11618609726428986
2023-01-21 09:33:55.485714: step: 996/530, loss: 0.08606138825416565
2023-01-21 09:33:56.592892: step: 1000/530, loss: 0.1393057256937027
2023-01-21 09:33:57.727355: step: 1004/530, loss: 0.5516961216926575
2023-01-21 09:33:58.880691: step: 1008/530, loss: 0.06300678104162216
2023-01-21 09:34:00.003822: step: 1012/530, loss: 0.3385885953903198
2023-01-21 09:34:01.175557: step: 1016/530, loss: 0.15946274995803833
2023-01-21 09:34:02.299978: step: 1020/530, loss: 0.8286330103874207
2023-01-21 09:34:03.432627: step: 1024/530, loss: 0.06464748084545135
2023-01-21 09:34:04.558095: step: 1028/530, loss: 0.07358107715845108
2023-01-21 09:34:05.668394: step: 1032/530, loss: 0.5551338195800781
2023-01-21 09:34:06.785919: step: 1036/530, loss: 0.15530119836330414
2023-01-21 09:34:07.909936: step: 1040/530, loss: 0.11508283764123917
2023-01-21 09:34:09.022237: step: 1044/530, loss: 0.10041675716638565
2023-01-21 09:34:10.136304: step: 1048/530, loss: 0.044777631759643555
2023-01-21 09:34:11.279597: step: 1052/530, loss: 0.17852826416492462
2023-01-21 09:34:12.430570: step: 1056/530, loss: 0.07283420860767365
2023-01-21 09:34:13.540231: step: 1060/530, loss: 0.02753610722720623
2023-01-21 09:34:14.648884: step: 1064/530, loss: 0.06696224212646484
2023-01-21 09:34:15.759163: step: 1068/530, loss: 0.17500095069408417
2023-01-21 09:34:16.858420: step: 1072/530, loss: 0.05576524883508682
2023-01-21 09:34:17.925538: step: 1076/530, loss: 0.04979858547449112
2023-01-21 09:34:19.029255: step: 1080/530, loss: 0.017035987228155136
2023-01-21 09:34:20.123484: step: 1084/530, loss: 0.03942747041583061
2023-01-21 09:34:21.211259: step: 1088/530, loss: 0.21578015387058258
2023-01-21 09:34:22.327693: step: 1092/530, loss: 0.13594646751880646
2023-01-21 09:34:23.440172: step: 1096/530, loss: 0.4431777894496918
2023-01-21 09:34:24.543850: step: 1100/530, loss: 0.09824438393115997
2023-01-21 09:34:25.678407: step: 1104/530, loss: 0.43484944105148315
2023-01-21 09:34:26.794100: step: 1108/530, loss: 0.1600465327501297
2023-01-21 09:34:27.896377: step: 1112/530, loss: 0.48954397439956665
2023-01-21 09:34:29.004089: step: 1116/530, loss: 0.12431621551513672
2023-01-21 09:34:30.072810: step: 1120/530, loss: 0.05503235012292862
2023-01-21 09:34:31.184489: step: 1124/530, loss: 0.04081964120268822
2023-01-21 09:34:32.324934: step: 1128/530, loss: 0.008269404992461205
2023-01-21 09:34:33.477123: step: 1132/530, loss: 0.2670232653617859
2023-01-21 09:34:34.590660: step: 1136/530, loss: 0.012583445757627487
2023-01-21 09:34:35.694945: step: 1140/530, loss: 0.03821849822998047
2023-01-21 09:34:36.835778: step: 1144/530, loss: 6.483943462371826
2023-01-21 09:34:37.946037: step: 1148/530, loss: 0.2951178550720215
2023-01-21 09:34:39.048040: step: 1152/530, loss: 0.1675799936056137
2023-01-21 09:34:40.182228: step: 1156/530, loss: 0.061385251581668854
2023-01-21 09:34:41.278392: step: 1160/530, loss: 0.05628480762243271
2023-01-21 09:34:42.430095: step: 1164/530, loss: 0.617857813835144
2023-01-21 09:34:43.533935: step: 1168/530, loss: 0.09353180229663849
2023-01-21 09:34:44.659413: step: 1172/530, loss: 0.1562778353691101
2023-01-21 09:34:45.807269: step: 1176/530, loss: 0.4430685043334961
2023-01-21 09:34:46.935040: step: 1180/530, loss: 0.03023557737469673
2023-01-21 09:34:48.017427: step: 1184/530, loss: 0.15332813560962677
2023-01-21 09:34:49.085109: step: 1188/530, loss: 0.14318440854549408
2023-01-21 09:34:50.171952: step: 1192/530, loss: 0.0890265554189682
2023-01-21 09:34:51.291588: step: 1196/530, loss: 0.02219982072710991
2023-01-21 09:34:52.380160: step: 1200/530, loss: 0.05496816709637642
2023-01-21 09:34:53.461794: step: 1204/530, loss: 0.0460217148065567
2023-01-21 09:34:54.551766: step: 1208/530, loss: 0.06803536415100098
2023-01-21 09:34:55.695309: step: 1212/530, loss: 0.021628262475132942
2023-01-21 09:34:56.801918: step: 1216/530, loss: 0.142535999417305
2023-01-21 09:34:57.903791: step: 1220/530, loss: 0.03314189985394478
2023-01-21 09:34:58.994227: step: 1224/530, loss: 0.04489879682660103
2023-01-21 09:35:00.079220: step: 1228/530, loss: 0.03569202497601509
2023-01-21 09:35:01.185614: step: 1232/530, loss: 0.2565673887729645
2023-01-21 09:35:02.326353: step: 1236/530, loss: 0.19846734404563904
2023-01-21 09:35:03.470258: step: 1240/530, loss: 0.1411205381155014
2023-01-21 09:35:04.576026: step: 1244/530, loss: 0.16838568449020386
2023-01-21 09:35:05.685638: step: 1248/530, loss: 0.1854853630065918
2023-01-21 09:35:06.802178: step: 1252/530, loss: 0.014490032568573952
2023-01-21 09:35:07.912573: step: 1256/530, loss: 0.31826668977737427
2023-01-21 09:35:08.997257: step: 1260/530, loss: 0.007297801785171032
2023-01-21 09:35:10.108779: step: 1264/530, loss: 0.06495866924524307
2023-01-21 09:35:11.216238: step: 1268/530, loss: 0.07826481759548187
2023-01-21 09:35:12.348625: step: 1272/530, loss: 0.12443426251411438
2023-01-21 09:35:13.483065: step: 1276/530, loss: 0.05956573411822319
2023-01-21 09:35:14.561683: step: 1280/530, loss: 0.24829530715942383
2023-01-21 09:35:15.685075: step: 1284/530, loss: 0.17577160894870758
2023-01-21 09:35:16.798894: step: 1288/530, loss: 0.012757587246596813
2023-01-21 09:35:17.895938: step: 1292/530, loss: 0.07738790661096573
2023-01-21 09:35:18.998625: step: 1296/530, loss: 0.058518197387456894
2023-01-21 09:35:20.123605: step: 1300/530, loss: 0.04795525223016739
2023-01-21 09:35:21.239591: step: 1304/530, loss: 0.10983534157276154
2023-01-21 09:35:22.331208: step: 1308/530, loss: 0.22822479903697968
2023-01-21 09:35:23.438246: step: 1312/530, loss: 0.0834013968706131
2023-01-21 09:35:24.542389: step: 1316/530, loss: 0.23015937209129333
2023-01-21 09:35:25.633574: step: 1320/530, loss: 0.35937219858169556
2023-01-21 09:35:26.752473: step: 1324/530, loss: 0.15581531822681427
2023-01-21 09:35:27.854496: step: 1328/530, loss: 0.019521618261933327
2023-01-21 09:35:28.952873: step: 1332/530, loss: 0.10836992412805557
2023-01-21 09:35:30.083692: step: 1336/530, loss: 0.20116910338401794
2023-01-21 09:35:31.152365: step: 1340/530, loss: 0.08201270550489426
2023-01-21 09:35:32.296693: step: 1344/530, loss: 0.6198492050170898
2023-01-21 09:35:33.451479: step: 1348/530, loss: 0.06343241035938263
2023-01-21 09:35:34.564284: step: 1352/530, loss: 0.08712625503540039
2023-01-21 09:35:35.662917: step: 1356/530, loss: 0.08887386322021484
2023-01-21 09:35:36.792729: step: 1360/530, loss: 0.23552294075489044
2023-01-21 09:35:37.904617: step: 1364/530, loss: 0.13663749396800995
2023-01-21 09:35:38.992875: step: 1368/530, loss: 0.11390657722949982
2023-01-21 09:35:40.114652: step: 1372/530, loss: 0.06561855971813202
2023-01-21 09:35:41.223360: step: 1376/530, loss: 0.02843928337097168
2023-01-21 09:35:42.336779: step: 1380/530, loss: 0.18968945741653442
2023-01-21 09:35:43.470704: step: 1384/530, loss: 0.3278907835483551
2023-01-21 09:35:44.600518: step: 1388/530, loss: 0.14762306213378906
2023-01-21 09:35:45.712852: step: 1392/530, loss: 0.03297996520996094
2023-01-21 09:35:46.838305: step: 1396/530, loss: 0.16599509119987488
2023-01-21 09:35:47.965522: step: 1400/530, loss: 0.05211487039923668
2023-01-21 09:35:49.059916: step: 1404/530, loss: 0.03898029401898384
2023-01-21 09:35:50.187781: step: 1408/530, loss: 0.3107908368110657
2023-01-21 09:35:51.323713: step: 1412/530, loss: 0.08039645850658417
2023-01-21 09:35:52.451181: step: 1416/530, loss: 0.24170580506324768
2023-01-21 09:35:53.566743: step: 1420/530, loss: 0.5683291554450989
2023-01-21 09:35:54.672427: step: 1424/530, loss: 0.21980924904346466
2023-01-21 09:35:55.776222: step: 1428/530, loss: 0.2698204815387726
2023-01-21 09:35:56.897929: step: 1432/530, loss: 0.038778066635131836
2023-01-21 09:35:58.025032: step: 1436/530, loss: 0.015592003241181374
2023-01-21 09:35:59.145702: step: 1440/530, loss: 0.07093267142772675
2023-01-21 09:36:00.248390: step: 1444/530, loss: 0.11247185617685318
2023-01-21 09:36:01.344404: step: 1448/530, loss: 0.0854862630367279
2023-01-21 09:36:02.473566: step: 1452/530, loss: 0.19423389434814453
2023-01-21 09:36:03.602243: step: 1456/530, loss: 0.4856361448764801
2023-01-21 09:36:04.738526: step: 1460/530, loss: 0.13886868953704834
2023-01-21 09:36:05.889713: step: 1464/530, loss: 0.022584104910492897
2023-01-21 09:36:06.963394: step: 1468/530, loss: 0.03950967639684677
2023-01-21 09:36:08.087844: step: 1472/530, loss: 0.08375759422779083
2023-01-21 09:36:09.222776: step: 1476/530, loss: 0.1788158416748047
2023-01-21 09:36:10.349300: step: 1480/530, loss: 0.06932497024536133
2023-01-21 09:36:11.465155: step: 1484/530, loss: 0.6988540887832642
2023-01-21 09:36:12.575790: step: 1488/530, loss: 0.09924602508544922
2023-01-21 09:36:13.685378: step: 1492/530, loss: 0.08173694461584091
2023-01-21 09:36:14.772681: step: 1496/530, loss: 0.3696770668029785
2023-01-21 09:36:15.864118: step: 1500/530, loss: 0.09256534278392792
2023-01-21 09:36:17.004066: step: 1504/530, loss: 0.5064190030097961
2023-01-21 09:36:18.095427: step: 1508/530, loss: 0.3354575037956238
2023-01-21 09:36:19.187417: step: 1512/530, loss: 0.07976799458265305
2023-01-21 09:36:20.310706: step: 1516/530, loss: 0.07779359817504883
2023-01-21 09:36:21.396404: step: 1520/530, loss: 0.04734072834253311
2023-01-21 09:36:22.501818: step: 1524/530, loss: 0.13560420274734497
2023-01-21 09:36:23.603448: step: 1528/530, loss: 0.634434700012207
2023-01-21 09:36:24.727840: step: 1532/530, loss: 0.09580822288990021
2023-01-21 09:36:25.842350: step: 1536/530, loss: 0.019923312589526176
2023-01-21 09:36:26.955135: step: 1540/530, loss: 0.17399214208126068
2023-01-21 09:36:28.117575: step: 1544/530, loss: 0.3431612253189087
2023-01-21 09:36:29.242109: step: 1548/530, loss: 0.11711979657411575
2023-01-21 09:36:30.378455: step: 1552/530, loss: 0.4007362425327301
2023-01-21 09:36:31.493213: step: 1556/530, loss: 0.027413655072450638
2023-01-21 09:36:32.622686: step: 1560/530, loss: 0.06437353789806366
2023-01-21 09:36:33.747044: step: 1564/530, loss: 0.12603816390037537
2023-01-21 09:36:34.843062: step: 1568/530, loss: 0.15179356932640076
2023-01-21 09:36:35.921601: step: 1572/530, loss: 0.07432813942432404
2023-01-21 09:36:37.029507: step: 1576/530, loss: 0.0698603168129921
2023-01-21 09:36:38.149247: step: 1580/530, loss: 0.19867831468582153
2023-01-21 09:36:39.234913: step: 1584/530, loss: 0.14878816902637482
2023-01-21 09:36:40.381445: step: 1588/530, loss: 0.07033753395080566
2023-01-21 09:36:41.493664: step: 1592/530, loss: 0.1424090415239334
2023-01-21 09:36:42.614086: step: 1596/530, loss: 0.05425385385751724
2023-01-21 09:36:43.723307: step: 1600/530, loss: 0.17768363654613495
2023-01-21 09:36:44.818336: step: 1604/530, loss: 0.1344536542892456
2023-01-21 09:36:45.935667: step: 1608/530, loss: 0.07669587433338165
2023-01-21 09:36:47.072893: step: 1612/530, loss: 0.19627760350704193
2023-01-21 09:36:48.160992: step: 1616/530, loss: 0.22488613426685333
2023-01-21 09:36:49.256391: step: 1620/530, loss: 0.06286501884460449
2023-01-21 09:36:50.380033: step: 1624/530, loss: 0.032280731946229935
2023-01-21 09:36:51.525783: step: 1628/530, loss: 0.040767598897218704
2023-01-21 09:36:52.638941: step: 1632/530, loss: 0.08839156478643417
2023-01-21 09:36:53.731676: step: 1636/530, loss: 0.09683070331811905
2023-01-21 09:36:54.837101: step: 1640/530, loss: 0.15801803767681122
2023-01-21 09:36:55.954839: step: 1644/530, loss: 0.04566001892089844
2023-01-21 09:36:57.073850: step: 1648/530, loss: 0.03453559800982475
2023-01-21 09:36:58.200682: step: 1652/530, loss: 0.2649565637111664
2023-01-21 09:36:59.299238: step: 1656/530, loss: 0.20853376388549805
2023-01-21 09:37:00.417255: step: 1660/530, loss: 0.03739719092845917
2023-01-21 09:37:01.553554: step: 1664/530, loss: 0.9176833033561707
2023-01-21 09:37:02.691210: step: 1668/530, loss: 0.24372054636478424
2023-01-21 09:37:03.808289: step: 1672/530, loss: 1.1824594736099243
2023-01-21 09:37:04.923191: step: 1676/530, loss: 0.10102196037769318
2023-01-21 09:37:06.060510: step: 1680/530, loss: 0.5427728295326233
2023-01-21 09:37:07.166474: step: 1684/530, loss: 0.7511458992958069
2023-01-21 09:37:08.315676: step: 1688/530, loss: 0.07435502856969833
2023-01-21 09:37:09.424684: step: 1692/530, loss: 0.12371456623077393
2023-01-21 09:37:10.538658: step: 1696/530, loss: 0.013656927272677422
2023-01-21 09:37:11.673684: step: 1700/530, loss: 0.546288013458252
2023-01-21 09:37:12.776950: step: 1704/530, loss: 0.12884268164634705
2023-01-21 09:37:13.870205: step: 1708/530, loss: 0.4251531660556793
2023-01-21 09:37:14.969605: step: 1712/530, loss: 0.11277890205383301
2023-01-21 09:37:16.057017: step: 1716/530, loss: 0.8625238537788391
2023-01-21 09:37:17.187584: step: 1720/530, loss: 0.3238413333892822
2023-01-21 09:37:18.297764: step: 1724/530, loss: 0.13582482933998108
2023-01-21 09:37:19.390917: step: 1728/530, loss: 0.08373288810253143
2023-01-21 09:37:20.528009: step: 1732/530, loss: 0.23664750158786774
2023-01-21 09:37:21.646611: step: 1736/530, loss: 0.10480336844921112
2023-01-21 09:37:22.740914: step: 1740/530, loss: 0.07555494457483292
2023-01-21 09:37:23.855716: step: 1744/530, loss: 0.3895745277404785
2023-01-21 09:37:24.983205: step: 1748/530, loss: 0.0558532252907753
2023-01-21 09:37:26.122074: step: 1752/530, loss: 0.534936249256134
2023-01-21 09:37:27.236213: step: 1756/530, loss: 0.491568386554718
2023-01-21 09:37:28.358125: step: 1760/530, loss: 0.24336567521095276
2023-01-21 09:37:29.455811: step: 1764/530, loss: 0.03911319002509117
2023-01-21 09:37:30.551426: step: 1768/530, loss: 0.1109614446759224
2023-01-21 09:37:31.671160: step: 1772/530, loss: 0.09415673464536667
2023-01-21 09:37:32.772541: step: 1776/530, loss: 0.07102489471435547
2023-01-21 09:37:33.909568: step: 1780/530, loss: 0.21890735626220703
2023-01-21 09:37:35.023580: step: 1784/530, loss: 0.27712059020996094
2023-01-21 09:37:36.138694: step: 1788/530, loss: 0.1479993313550949
2023-01-21 09:37:37.274709: step: 1792/530, loss: 0.05909309536218643
2023-01-21 09:37:38.380066: step: 1796/530, loss: 0.7951620817184448
2023-01-21 09:37:39.500307: step: 1800/530, loss: 0.15672674775123596
2023-01-21 09:37:40.612581: step: 1804/530, loss: 0.17226552963256836
2023-01-21 09:37:41.727182: step: 1808/530, loss: 0.09262494742870331
2023-01-21 09:37:42.843018: step: 1812/530, loss: 0.1969434767961502
2023-01-21 09:37:43.956611: step: 1816/530, loss: 0.08065243065357208
2023-01-21 09:37:45.088413: step: 1820/530, loss: 0.23438984155654907
2023-01-21 09:37:46.215101: step: 1824/530, loss: 0.7949447631835938
2023-01-21 09:37:47.348459: step: 1828/530, loss: 0.3645614683628082
2023-01-21 09:37:48.486398: step: 1832/530, loss: 0.10086217522621155
2023-01-21 09:37:49.575193: step: 1836/530, loss: 0.16418743133544922
2023-01-21 09:37:50.685066: step: 1840/530, loss: 0.03284807130694389
2023-01-21 09:37:51.778863: step: 1844/530, loss: 0.04199647903442383
2023-01-21 09:37:52.908992: step: 1848/530, loss: 0.6918651461601257
2023-01-21 09:37:54.011847: step: 1852/530, loss: 0.03935125097632408
2023-01-21 09:37:55.114503: step: 1856/530, loss: 0.15503883361816406
2023-01-21 09:37:56.229653: step: 1860/530, loss: 0.1573176383972168
2023-01-21 09:37:57.367916: step: 1864/530, loss: 0.18531304597854614
2023-01-21 09:37:58.491959: step: 1868/530, loss: 0.9952538013458252
2023-01-21 09:37:59.587505: step: 1872/530, loss: 0.09039059281349182
2023-01-21 09:38:00.699611: step: 1876/530, loss: 0.09948806464672089
2023-01-21 09:38:01.811756: step: 1880/530, loss: 0.21267862617969513
2023-01-21 09:38:02.987116: step: 1884/530, loss: 0.24610663950443268
2023-01-21 09:38:04.104747: step: 1888/530, loss: 0.379660427570343
2023-01-21 09:38:05.246995: step: 1892/530, loss: 0.24018077552318573
2023-01-21 09:38:06.378999: step: 1896/530, loss: 0.12495160102844238
2023-01-21 09:38:07.507671: step: 1900/530, loss: 0.14095859229564667
2023-01-21 09:38:08.601706: step: 1904/530, loss: 0.09711358696222305
2023-01-21 09:38:09.740554: step: 1908/530, loss: 0.11520948261022568
2023-01-21 09:38:10.835732: step: 1912/530, loss: 0.8499228358268738
2023-01-21 09:38:11.935240: step: 1916/530, loss: 0.10925617814064026
2023-01-21 09:38:13.070689: step: 1920/530, loss: 0.1350785791873932
2023-01-21 09:38:14.156957: step: 1924/530, loss: 0.05995321273803711
2023-01-21 09:38:15.273963: step: 1928/530, loss: 0.03709602355957031
2023-01-21 09:38:16.378184: step: 1932/530, loss: 0.3697931170463562
2023-01-21 09:38:17.490056: step: 1936/530, loss: 0.2087252140045166
2023-01-21 09:38:18.627337: step: 1940/530, loss: 0.25694623589515686
2023-01-21 09:38:19.740295: step: 1944/530, loss: 0.0803590789437294
2023-01-21 09:38:20.853482: step: 1948/530, loss: 0.09548091888427734
2023-01-21 09:38:21.976292: step: 1952/530, loss: 0.06707639992237091
2023-01-21 09:38:23.129357: step: 1956/530, loss: 1.132390022277832
2023-01-21 09:38:24.230650: step: 1960/530, loss: 0.01466674730181694
2023-01-21 09:38:25.313883: step: 1964/530, loss: 0.3246227204799652
2023-01-21 09:38:26.413049: step: 1968/530, loss: 0.30153340101242065
2023-01-21 09:38:27.521383: step: 1972/530, loss: 0.5989601016044617
2023-01-21 09:38:28.626370: step: 1976/530, loss: 0.21505257487297058
2023-01-21 09:38:29.725176: step: 1980/530, loss: 0.38150912523269653
2023-01-21 09:38:30.820543: step: 1984/530, loss: 0.14348506927490234
2023-01-21 09:38:31.948185: step: 1988/530, loss: 0.0634654089808464
2023-01-21 09:38:33.038286: step: 1992/530, loss: 0.02373323403298855
2023-01-21 09:38:34.136735: step: 1996/530, loss: 0.06984737515449524
2023-01-21 09:38:35.272072: step: 2000/530, loss: 0.1760483682155609
2023-01-21 09:38:36.444413: step: 2004/530, loss: 0.07238321751356125
2023-01-21 09:38:37.562747: step: 2008/530, loss: 0.14514485001564026
2023-01-21 09:38:38.639425: step: 2012/530, loss: 0.14287766814231873
2023-01-21 09:38:39.764845: step: 2016/530, loss: 0.17567339539527893
2023-01-21 09:38:40.870131: step: 2020/530, loss: 0.12714596092700958
2023-01-21 09:38:41.982921: step: 2024/530, loss: 0.06722183525562286
2023-01-21 09:38:43.112952: step: 2028/530, loss: 0.11953344941139221
2023-01-21 09:38:44.240256: step: 2032/530, loss: 0.09094009548425674
2023-01-21 09:38:45.382854: step: 2036/530, loss: 0.09003925323486328
2023-01-21 09:38:46.503379: step: 2040/530, loss: 0.16840039193630219
2023-01-21 09:38:47.615427: step: 2044/530, loss: 0.4642484188079834
2023-01-21 09:38:48.748586: step: 2048/530, loss: 0.18713703751564026
2023-01-21 09:38:49.861992: step: 2052/530, loss: 0.21268220245838165
2023-01-21 09:38:50.966431: step: 2056/530, loss: 0.12185921519994736
2023-01-21 09:38:52.078140: step: 2060/530, loss: 0.11772609502077103
2023-01-21 09:38:53.181062: step: 2064/530, loss: 0.0825016051530838
2023-01-21 09:38:54.258711: step: 2068/530, loss: 0.26831990480422974
2023-01-21 09:38:55.385834: step: 2072/530, loss: 0.18535655736923218
2023-01-21 09:38:56.486597: step: 2076/530, loss: 0.32517918944358826
2023-01-21 09:38:57.597586: step: 2080/530, loss: 0.16744498908519745
2023-01-21 09:38:58.728095: step: 2084/530, loss: 3.0062737464904785
2023-01-21 09:38:59.819838: step: 2088/530, loss: 0.07003412395715714
2023-01-21 09:39:00.925668: step: 2092/530, loss: 0.08714008331298828
2023-01-21 09:39:02.027550: step: 2096/530, loss: 0.14412860572338104
2023-01-21 09:39:03.169943: step: 2100/530, loss: 0.02461080625653267
2023-01-21 09:39:04.273788: step: 2104/530, loss: 0.09455351531505585
2023-01-21 09:39:05.375707: step: 2108/530, loss: 0.049488164484500885
2023-01-21 09:39:06.495928: step: 2112/530, loss: 0.21966229379177094
2023-01-21 09:39:07.645977: step: 2116/530, loss: 1.3812816143035889
2023-01-21 09:39:08.753030: step: 2120/530, loss: 0.8254890441894531
==================================================
Loss: 0.224
--------------------
Dev: {'event': {'p': 0.5306691449814126, 'r': 0.7603195739014648, 'f1': 0.6250684181718664}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Test: {'event': {'p': 0.5916594265855778, 'r': 0.7937062937062938, 'f1': 0.6779492284718766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Chinese: {'event': {'p': 0.4943820224719101, 'r': 0.8148148148148148, 'f1': 0.6153846153846153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Korean: {'event': {'p': 0.4666666666666667, 'r': 0.5555555555555556, 'f1': 0.5072463768115943}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Russian: {'event': {'p': 0.3617021276595745, 'r': 0.4722222222222222, 'f1': 0.40963855421686746}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5708622398414271, 'r': 0.7669773635153129, 'f1': 0.6545454545454545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Chinese: {'event': {'p': 0.6044052863436123, 'r': 0.7995337995337995, 'f1': 0.6884094330155545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Chinese: {'event': {'p': 0.6578947368421053, 'r': 0.9259259259259259, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7631578947368421, 'r': 0.4603174603174603, 'f1': 0.5742574257425742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.625, 'r': 0.4166666666666667, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
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 09:39:49.134979: step: 4/530, loss: 0.36224472522735596
2023-01-21 09:39:50.228694: step: 8/530, loss: 0.08169898390769958
2023-01-21 09:39:51.341414: step: 12/530, loss: 0.11723347008228302
2023-01-21 09:39:52.456810: step: 16/530, loss: 0.11726561188697815
2023-01-21 09:39:53.561115: step: 20/530, loss: 0.18027916550636292
2023-01-21 09:39:54.670329: step: 24/530, loss: 0.06626129150390625
2023-01-21 09:39:55.768493: step: 28/530, loss: 0.10006208717823029
2023-01-21 09:39:56.881201: step: 32/530, loss: 0.24529027938842773
2023-01-21 09:39:57.994265: step: 36/530, loss: 0.060425616800785065
2023-01-21 09:39:59.106479: step: 40/530, loss: 0.08134423196315765
2023-01-21 09:40:00.238053: step: 44/530, loss: 0.024162864312529564
2023-01-21 09:40:01.356612: step: 48/530, loss: 0.3644390106201172
2023-01-21 09:40:02.494857: step: 52/530, loss: 0.10955658555030823
2023-01-21 09:40:03.606244: step: 56/530, loss: 0.15728087723255157
2023-01-21 09:40:04.735973: step: 60/530, loss: 0.10733642429113388
2023-01-21 09:40:05.850853: step: 64/530, loss: 0.010541249066591263
2023-01-21 09:40:06.933720: step: 68/530, loss: 0.13670583069324493
2023-01-21 09:40:08.064998: step: 72/530, loss: 0.07948508858680725
2023-01-21 09:40:09.148238: step: 76/530, loss: 0.052745986729860306
2023-01-21 09:40:10.251806: step: 80/530, loss: 0.04770860821008682
2023-01-21 09:40:11.383582: step: 84/530, loss: 0.0271914005279541
2023-01-21 09:40:12.503737: step: 88/530, loss: 0.11575041711330414
2023-01-21 09:40:13.597687: step: 92/530, loss: 0.25489839911460876
2023-01-21 09:40:14.704236: step: 96/530, loss: 0.05923328548669815
2023-01-21 09:40:15.817476: step: 100/530, loss: 0.376596063375473
2023-01-21 09:40:16.934024: step: 104/530, loss: 0.016396379098296165
2023-01-21 09:40:18.060726: step: 108/530, loss: 0.04903850704431534
2023-01-21 09:40:19.177194: step: 112/530, loss: 0.0548674613237381
2023-01-21 09:40:20.249585: step: 116/530, loss: 0.03580117225646973
2023-01-21 09:40:21.391816: step: 120/530, loss: 0.035443879663944244
2023-01-21 09:40:22.504008: step: 124/530, loss: 0.09235982596874237
2023-01-21 09:40:23.645382: step: 128/530, loss: 0.07010116428136826
2023-01-21 09:40:24.759924: step: 132/530, loss: 0.1550171822309494
2023-01-21 09:40:25.888746: step: 136/530, loss: 0.09939423203468323
2023-01-21 09:40:26.991095: step: 140/530, loss: 0.18047255277633667
2023-01-21 09:40:28.109677: step: 144/530, loss: 0.11910267174243927
2023-01-21 09:40:29.213623: step: 148/530, loss: 0.06516984850168228
2023-01-21 09:40:30.299062: step: 152/530, loss: 0.07480421662330627
2023-01-21 09:40:31.421269: step: 156/530, loss: 0.06669798493385315
2023-01-21 09:40:32.539148: step: 160/530, loss: 0.2969152331352234
2023-01-21 09:40:33.685906: step: 164/530, loss: 0.14896050095558167
2023-01-21 09:40:34.783731: step: 168/530, loss: 0.12872613966464996
2023-01-21 09:40:35.884772: step: 172/530, loss: 0.10578031837940216
2023-01-21 09:40:36.992083: step: 176/530, loss: 0.16356438398361206
2023-01-21 09:40:38.120926: step: 180/530, loss: 0.12344856560230255
2023-01-21 09:40:39.271719: step: 184/530, loss: 0.18796882033348083
2023-01-21 09:40:40.391678: step: 188/530, loss: 0.2580105662345886
2023-01-21 09:40:41.487732: step: 192/530, loss: 0.07540258765220642
2023-01-21 09:40:42.589774: step: 196/530, loss: 0.04785637930035591
2023-01-21 09:40:43.709122: step: 200/530, loss: 0.19221201539039612
2023-01-21 09:40:44.826710: step: 204/530, loss: 0.16617251932621002
2023-01-21 09:40:45.938104: step: 208/530, loss: 0.15216389298439026
2023-01-21 09:40:47.058031: step: 212/530, loss: 0.3022747039794922
2023-01-21 09:40:48.198006: step: 216/530, loss: 0.14795561134815216
2023-01-21 09:40:49.328460: step: 220/530, loss: 0.081329345703125
2023-01-21 09:40:50.443998: step: 224/530, loss: 0.07722587883472443
2023-01-21 09:40:51.563878: step: 228/530, loss: 0.1562521904706955
2023-01-21 09:40:52.669497: step: 232/530, loss: 0.020304013043642044
2023-01-21 09:40:53.799325: step: 236/530, loss: 0.16753073036670685
2023-01-21 09:40:54.899944: step: 240/530, loss: 0.04196987301111221
2023-01-21 09:40:56.019083: step: 244/530, loss: 0.06264229118824005
2023-01-21 09:40:57.095237: step: 248/530, loss: 0.23840151727199554
2023-01-21 09:40:58.197704: step: 252/530, loss: 0.04350433498620987
2023-01-21 09:40:59.312665: step: 256/530, loss: 0.05226287990808487
2023-01-21 09:41:00.453766: step: 260/530, loss: 0.25967827439308167
2023-01-21 09:41:01.542057: step: 264/530, loss: 0.20942655205726624
2023-01-21 09:41:02.663296: step: 268/530, loss: 0.026894044131040573
2023-01-21 09:41:03.792352: step: 272/530, loss: 0.09174290299415588
2023-01-21 09:41:04.919018: step: 276/530, loss: 0.12692275643348694
2023-01-21 09:41:06.025578: step: 280/530, loss: 0.06794138252735138
2023-01-21 09:41:07.107600: step: 284/530, loss: 0.21318918466567993
2023-01-21 09:41:08.230699: step: 288/530, loss: 0.08089981228113174
2023-01-21 09:41:09.333848: step: 292/530, loss: 0.1339005082845688
2023-01-21 09:41:10.442890: step: 296/530, loss: 0.17511996626853943
2023-01-21 09:41:11.559679: step: 300/530, loss: 0.02764458768069744
2023-01-21 09:41:12.672553: step: 304/530, loss: 0.033239271491765976
2023-01-21 09:41:13.796542: step: 308/530, loss: 0.06931314617395401
2023-01-21 09:41:14.888583: step: 312/530, loss: 0.08564615249633789
2023-01-21 09:41:16.006509: step: 316/530, loss: 0.30077144503593445
2023-01-21 09:41:17.141794: step: 320/530, loss: 0.195203959941864
2023-01-21 09:41:18.268446: step: 324/530, loss: 0.18814457952976227
2023-01-21 09:41:19.373722: step: 328/530, loss: 0.42802226543426514
2023-01-21 09:41:20.498275: step: 332/530, loss: 0.13078871369361877
2023-01-21 09:41:21.599342: step: 336/530, loss: 0.1847125142812729
2023-01-21 09:41:22.724536: step: 340/530, loss: 0.25691360235214233
2023-01-21 09:41:23.843134: step: 344/530, loss: 0.01910848543047905
2023-01-21 09:41:24.984615: step: 348/530, loss: 0.13002434372901917
2023-01-21 09:41:26.112698: step: 352/530, loss: 0.3374102711677551
2023-01-21 09:41:27.235796: step: 356/530, loss: 0.12634725868701935
2023-01-21 09:41:28.365406: step: 360/530, loss: 0.14684835076332092
2023-01-21 09:41:29.475837: step: 364/530, loss: 0.24435709416866302
2023-01-21 09:41:30.621713: step: 368/530, loss: 0.12131842970848083
2023-01-21 09:41:31.695821: step: 372/530, loss: 0.031496811658144
2023-01-21 09:41:32.817489: step: 376/530, loss: 0.6800879240036011
2023-01-21 09:41:33.931649: step: 380/530, loss: 0.05104236677289009
2023-01-21 09:41:35.026786: step: 384/530, loss: 0.08195820450782776
2023-01-21 09:41:36.116420: step: 388/530, loss: 0.6275573372840881
2023-01-21 09:41:37.245547: step: 392/530, loss: 0.04400348663330078
2023-01-21 09:41:38.353029: step: 396/530, loss: 0.09596381336450577
2023-01-21 09:41:39.446036: step: 400/530, loss: 0.04238080978393555
2023-01-21 09:41:40.575644: step: 404/530, loss: 0.11941839009523392
2023-01-21 09:41:41.687165: step: 408/530, loss: 0.025572681799530983
2023-01-21 09:41:42.858212: step: 412/530, loss: 0.08564386516809464
2023-01-21 09:41:43.997359: step: 416/530, loss: 0.24502038955688477
2023-01-21 09:41:45.114183: step: 420/530, loss: 0.21368902921676636
2023-01-21 09:41:46.262976: step: 424/530, loss: 0.1127803772687912
2023-01-21 09:41:47.372484: step: 428/530, loss: 0.3384517431259155
2023-01-21 09:41:48.480599: step: 432/530, loss: 0.10947570949792862
2023-01-21 09:41:49.614615: step: 436/530, loss: 0.07433748245239258
2023-01-21 09:41:50.747274: step: 440/530, loss: 0.0066460613161325455
2023-01-21 09:41:51.876890: step: 444/530, loss: 0.15554103255271912
2023-01-21 09:41:52.987374: step: 448/530, loss: 0.08113746345043182
2023-01-21 09:41:54.144492: step: 452/530, loss: 0.01602044142782688
2023-01-21 09:41:55.270006: step: 456/530, loss: 0.29054251313209534
2023-01-21 09:41:56.404847: step: 460/530, loss: 0.09272976219654083
2023-01-21 09:41:57.506682: step: 464/530, loss: 0.13529759645462036
2023-01-21 09:41:58.625254: step: 468/530, loss: 0.12897825241088867
2023-01-21 09:41:59.742145: step: 472/530, loss: 0.09445630013942719
2023-01-21 09:42:00.857725: step: 476/530, loss: 0.07652568817138672
2023-01-21 09:42:01.942988: step: 480/530, loss: 0.17240294814109802
2023-01-21 09:42:03.036468: step: 484/530, loss: 0.04783831536769867
2023-01-21 09:42:04.179805: step: 488/530, loss: 0.26537173986434937
2023-01-21 09:42:05.297993: step: 492/530, loss: 0.15151160955429077
2023-01-21 09:42:06.400849: step: 496/530, loss: 0.07788319885730743
2023-01-21 09:42:07.498999: step: 500/530, loss: 0.0807105079293251
2023-01-21 09:42:08.619034: step: 504/530, loss: 0.09307919442653656
2023-01-21 09:42:09.736747: step: 508/530, loss: 0.07221775501966476
2023-01-21 09:42:10.815307: step: 512/530, loss: 0.055219076573848724
2023-01-21 09:42:11.928199: step: 516/530, loss: 0.07111234962940216
2023-01-21 09:42:13.058098: step: 520/530, loss: 0.11655382812023163
2023-01-21 09:42:14.160285: step: 524/530, loss: 0.04891214519739151
2023-01-21 09:42:15.263051: step: 528/530, loss: 0.5244685411453247
2023-01-21 09:42:16.360839: step: 532/530, loss: 0.09860782325267792
2023-01-21 09:42:17.497252: step: 536/530, loss: 0.15768924355506897
2023-01-21 09:42:18.623350: step: 540/530, loss: 0.023074721917510033
2023-01-21 09:42:19.702280: step: 544/530, loss: 0.10996818542480469
2023-01-21 09:42:20.812921: step: 548/530, loss: 0.14653438329696655
2023-01-21 09:42:21.932337: step: 552/530, loss: 0.02022085152566433
2023-01-21 09:42:23.060840: step: 556/530, loss: 0.13782139122486115
2023-01-21 09:42:24.161533: step: 560/530, loss: 0.11602868884801865
2023-01-21 09:42:25.278682: step: 564/530, loss: 0.16662444174289703
2023-01-21 09:42:26.407863: step: 568/530, loss: 0.06321864575147629
2023-01-21 09:42:27.511808: step: 572/530, loss: 0.14570438861846924
2023-01-21 09:42:28.662757: step: 576/530, loss: 0.030066443607211113
2023-01-21 09:42:29.755657: step: 580/530, loss: 0.06422023475170135
2023-01-21 09:42:30.863761: step: 584/530, loss: 0.10024777054786682
2023-01-21 09:42:32.005436: step: 588/530, loss: 0.11624159663915634
2023-01-21 09:42:33.112056: step: 592/530, loss: 0.10526628792285919
2023-01-21 09:42:34.241278: step: 596/530, loss: 0.2598729133605957
2023-01-21 09:42:35.381605: step: 600/530, loss: 0.23966895043849945
2023-01-21 09:42:36.509958: step: 604/530, loss: 0.1576642096042633
2023-01-21 09:42:37.631070: step: 608/530, loss: 0.23652610182762146
2023-01-21 09:42:38.730004: step: 612/530, loss: 0.21020039916038513
2023-01-21 09:42:39.839970: step: 616/530, loss: 0.13178463280200958
2023-01-21 09:42:40.943947: step: 620/530, loss: 0.062041569501161575
2023-01-21 09:42:42.054856: step: 624/530, loss: 0.12152253091335297
2023-01-21 09:42:43.161111: step: 628/530, loss: 0.04203624650835991
2023-01-21 09:42:44.279639: step: 632/530, loss: 0.08141221851110458
2023-01-21 09:42:45.397771: step: 636/530, loss: 0.03884744644165039
2023-01-21 09:42:46.524873: step: 640/530, loss: 0.3405753970146179
2023-01-21 09:42:47.616341: step: 644/530, loss: 0.04978933557868004
2023-01-21 09:42:48.718661: step: 648/530, loss: 0.03873853757977486
2023-01-21 09:42:49.839174: step: 652/530, loss: 0.06918811798095703
2023-01-21 09:42:50.958134: step: 656/530, loss: 0.3046959936618805
2023-01-21 09:42:52.053725: step: 660/530, loss: 0.04819068685173988
2023-01-21 09:42:53.126851: step: 664/530, loss: 0.14781463146209717
2023-01-21 09:42:54.255930: step: 668/530, loss: 0.16608715057373047
2023-01-21 09:42:55.363927: step: 672/530, loss: 1.6966180801391602
2023-01-21 09:42:56.445591: step: 676/530, loss: 0.01608905754983425
2023-01-21 09:42:57.603111: step: 680/530, loss: 0.0703834518790245
2023-01-21 09:42:58.725348: step: 684/530, loss: 0.38224610686302185
2023-01-21 09:42:59.822222: step: 688/530, loss: 0.01757340505719185
2023-01-21 09:43:00.951537: step: 692/530, loss: 0.11459548771381378
2023-01-21 09:43:02.070910: step: 696/530, loss: 0.18223437666893005
2023-01-21 09:43:03.182689: step: 700/530, loss: 0.12882661819458008
2023-01-21 09:43:04.266014: step: 704/530, loss: 0.16912880539894104
2023-01-21 09:43:05.365423: step: 708/530, loss: 0.03116750717163086
2023-01-21 09:43:06.456315: step: 712/530, loss: 0.23051002621650696
2023-01-21 09:43:07.564584: step: 716/530, loss: 0.03588886186480522
2023-01-21 09:43:08.723096: step: 720/530, loss: 0.029929352924227715
2023-01-21 09:43:09.828479: step: 724/530, loss: 0.11127138137817383
2023-01-21 09:43:10.934634: step: 728/530, loss: 0.10038814693689346
2023-01-21 09:43:12.035028: step: 732/530, loss: 0.047283269464969635
2023-01-21 09:43:13.151365: step: 736/530, loss: 0.11007729172706604
2023-01-21 09:43:14.263768: step: 740/530, loss: 0.04739560931921005
2023-01-21 09:43:15.358688: step: 744/530, loss: 0.00405278243124485
2023-01-21 09:43:16.469064: step: 748/530, loss: 0.020952891558408737
2023-01-21 09:43:17.634278: step: 752/530, loss: 0.04703464359045029
2023-01-21 09:43:18.727992: step: 756/530, loss: 0.09642362594604492
2023-01-21 09:43:19.865265: step: 760/530, loss: 0.24380818009376526
2023-01-21 09:43:20.997398: step: 764/530, loss: 0.008885574527084827
2023-01-21 09:43:22.105409: step: 768/530, loss: 0.07128553092479706
2023-01-21 09:43:23.215663: step: 772/530, loss: 0.22350959479808807
2023-01-21 09:43:24.346962: step: 776/530, loss: 0.14705219864845276
2023-01-21 09:43:25.439444: step: 780/530, loss: 0.06413183361291885
2023-01-21 09:43:26.580746: step: 784/530, loss: 0.06745896488428116
2023-01-21 09:43:27.672611: step: 788/530, loss: 0.03466834872961044
2023-01-21 09:43:28.768700: step: 792/530, loss: 0.4959568977355957
2023-01-21 09:43:29.927470: step: 796/530, loss: 0.08434753865003586
2023-01-21 09:43:31.028846: step: 800/530, loss: 0.03377866744995117
2023-01-21 09:43:32.136519: step: 804/530, loss: 0.6991739273071289
2023-01-21 09:43:33.296744: step: 808/530, loss: 0.4068222939968109
2023-01-21 09:43:34.428934: step: 812/530, loss: 0.16741368174552917
2023-01-21 09:43:35.530626: step: 816/530, loss: 0.03897132724523544
2023-01-21 09:43:36.610347: step: 820/530, loss: 0.05940275266766548
2023-01-21 09:43:37.733999: step: 824/530, loss: 0.13710708916187286
2023-01-21 09:43:38.873412: step: 828/530, loss: 0.07942590862512589
2023-01-21 09:43:39.965861: step: 832/530, loss: 0.06220893934369087
2023-01-21 09:43:41.093252: step: 836/530, loss: 0.1766260266304016
2023-01-21 09:43:42.193560: step: 840/530, loss: 0.46785974502563477
2023-01-21 09:43:43.301684: step: 844/530, loss: 0.03129148483276367
2023-01-21 09:43:44.432196: step: 848/530, loss: 0.05395854264497757
2023-01-21 09:43:45.526820: step: 852/530, loss: 0.10576143860816956
2023-01-21 09:43:46.613079: step: 856/530, loss: 0.11757240444421768
2023-01-21 09:43:47.706385: step: 860/530, loss: 0.44978657364845276
2023-01-21 09:43:48.816380: step: 864/530, loss: 0.03127651289105415
2023-01-21 09:43:49.920511: step: 868/530, loss: 0.07244300842285156
2023-01-21 09:43:51.080930: step: 872/530, loss: 0.13387927412986755
2023-01-21 09:43:52.181769: step: 876/530, loss: 0.10329776257276535
2023-01-21 09:43:53.289240: step: 880/530, loss: 0.08379817008972168
2023-01-21 09:43:54.381492: step: 884/530, loss: 0.036215975880622864
2023-01-21 09:43:55.472140: step: 888/530, loss: 1.1378170251846313
2023-01-21 09:43:56.611221: step: 892/530, loss: 0.1116364523768425
2023-01-21 09:43:57.734394: step: 896/530, loss: 0.3022039830684662
2023-01-21 09:43:58.848667: step: 900/530, loss: 0.10958519577980042
2023-01-21 09:43:59.998753: step: 904/530, loss: 0.03434352949261665
2023-01-21 09:44:01.098250: step: 908/530, loss: 0.05333547666668892
2023-01-21 09:44:02.198240: step: 912/530, loss: 0.06869831681251526
2023-01-21 09:44:03.314704: step: 916/530, loss: 0.04169069603085518
2023-01-21 09:44:04.430099: step: 920/530, loss: 0.12139873951673508
2023-01-21 09:44:05.557883: step: 924/530, loss: 0.1329408586025238
2023-01-21 09:44:06.671907: step: 928/530, loss: 0.03367280960083008
2023-01-21 09:44:07.795843: step: 932/530, loss: 0.05431051552295685
2023-01-21 09:44:08.896176: step: 936/530, loss: 0.14356574416160583
2023-01-21 09:44:09.998038: step: 940/530, loss: 0.1011572852730751
2023-01-21 09:44:11.124288: step: 944/530, loss: 0.010050726123154163
2023-01-21 09:44:12.226181: step: 948/530, loss: 0.10786259174346924
2023-01-21 09:44:13.386215: step: 952/530, loss: 0.010282707400619984
2023-01-21 09:44:14.522858: step: 956/530, loss: 0.5963069796562195
2023-01-21 09:44:15.632726: step: 960/530, loss: 0.09364481270313263
2023-01-21 09:44:16.743340: step: 964/530, loss: 0.1207679808139801
2023-01-21 09:44:17.816766: step: 968/530, loss: 0.05529933050274849
2023-01-21 09:44:18.920014: step: 972/530, loss: 0.015235376544296741
2023-01-21 09:44:20.057296: step: 976/530, loss: 0.20274028182029724
2023-01-21 09:44:21.164469: step: 980/530, loss: 0.7186511754989624
2023-01-21 09:44:22.292881: step: 984/530, loss: 0.1629629135131836
2023-01-21 09:44:23.410798: step: 988/530, loss: 0.13507023453712463
2023-01-21 09:44:24.512155: step: 992/530, loss: 0.23437313735485077
2023-01-21 09:44:25.609767: step: 996/530, loss: 0.0550900474190712
2023-01-21 09:44:26.711188: step: 1000/530, loss: 0.019523335620760918
2023-01-21 09:44:27.856677: step: 1004/530, loss: 0.12377357482910156
2023-01-21 09:44:28.969716: step: 1008/530, loss: 0.4395221769809723
2023-01-21 09:44:30.074324: step: 1012/530, loss: 0.043045803904533386
2023-01-21 09:44:31.162541: step: 1016/530, loss: 0.10103683918714523
2023-01-21 09:44:32.303067: step: 1020/530, loss: 0.06155281513929367
2023-01-21 09:44:33.426913: step: 1024/530, loss: 0.07357282936573029
2023-01-21 09:44:34.603801: step: 1028/530, loss: 0.06413498520851135
2023-01-21 09:44:35.730344: step: 1032/530, loss: 0.16371765732765198
2023-01-21 09:44:36.861196: step: 1036/530, loss: 0.11726627498865128
2023-01-21 09:44:37.952280: step: 1040/530, loss: 0.6850401163101196
2023-01-21 09:44:39.065421: step: 1044/530, loss: 0.06839428097009659
2023-01-21 09:44:40.207375: step: 1048/530, loss: 0.033388711512088776
2023-01-21 09:44:41.275624: step: 1052/530, loss: 0.028673553839325905
2023-01-21 09:44:42.407240: step: 1056/530, loss: 0.19330330193042755
2023-01-21 09:44:43.506067: step: 1060/530, loss: 0.2981095612049103
2023-01-21 09:44:44.601800: step: 1064/530, loss: 0.1984301656484604
2023-01-21 09:44:45.700015: step: 1068/530, loss: 0.20417605340480804
2023-01-21 09:44:46.832121: step: 1072/530, loss: 0.11032648384571075
2023-01-21 09:44:47.944675: step: 1076/530, loss: 0.03764014318585396
2023-01-21 09:44:49.063924: step: 1080/530, loss: 0.2675153315067291
2023-01-21 09:44:50.181975: step: 1084/530, loss: 0.6014558672904968
2023-01-21 09:44:51.271526: step: 1088/530, loss: 0.26674529910087585
2023-01-21 09:44:52.387969: step: 1092/530, loss: 0.09670582413673401
2023-01-21 09:44:53.491376: step: 1096/530, loss: 0.05879020690917969
2023-01-21 09:44:54.585757: step: 1100/530, loss: 0.20290032029151917
2023-01-21 09:44:55.710399: step: 1104/530, loss: 1.4648298025131226
2023-01-21 09:44:56.833012: step: 1108/530, loss: 0.4026739299297333
2023-01-21 09:44:57.949447: step: 1112/530, loss: 0.06233644858002663
2023-01-21 09:44:59.054863: step: 1116/530, loss: 0.03955087810754776
2023-01-21 09:45:00.161876: step: 1120/530, loss: 0.2662582993507385
2023-01-21 09:45:01.295990: step: 1124/530, loss: 0.03257620334625244
2023-01-21 09:45:02.419078: step: 1128/530, loss: 0.05949392169713974
2023-01-21 09:45:03.518898: step: 1132/530, loss: 0.19216357171535492
2023-01-21 09:45:04.623181: step: 1136/530, loss: 0.06876587867736816
2023-01-21 09:45:05.740262: step: 1140/530, loss: 0.2931135296821594
2023-01-21 09:45:06.883179: step: 1144/530, loss: 0.3316488265991211
2023-01-21 09:45:07.972502: step: 1148/530, loss: 0.016428422182798386
2023-01-21 09:45:09.134547: step: 1152/530, loss: 0.009912490844726562
2023-01-21 09:45:10.276626: step: 1156/530, loss: 0.04524817690253258
2023-01-21 09:45:11.415598: step: 1160/530, loss: 0.4253700077533722
2023-01-21 09:45:12.533266: step: 1164/530, loss: 0.04487800598144531
2023-01-21 09:45:13.639181: step: 1168/530, loss: 0.13685666024684906
2023-01-21 09:45:14.778003: step: 1172/530, loss: 0.04532451927661896
2023-01-21 09:45:15.888143: step: 1176/530, loss: 0.09571128338575363
2023-01-21 09:45:17.012579: step: 1180/530, loss: 0.16317157447338104
2023-01-21 09:45:18.109005: step: 1184/530, loss: 0.03981933742761612
2023-01-21 09:45:19.270123: step: 1188/530, loss: 0.17559146881103516
2023-01-21 09:45:20.389929: step: 1192/530, loss: 0.076934814453125
2023-01-21 09:45:21.520501: step: 1196/530, loss: 0.6746654510498047
2023-01-21 09:45:22.666641: step: 1200/530, loss: 0.20122194290161133
2023-01-21 09:45:23.784574: step: 1204/530, loss: 0.05625801533460617
2023-01-21 09:45:24.904274: step: 1208/530, loss: 0.1433342695236206
2023-01-21 09:45:26.016708: step: 1212/530, loss: 0.120702363550663
2023-01-21 09:45:27.144703: step: 1216/530, loss: 0.06711377948522568
2023-01-21 09:45:28.233192: step: 1220/530, loss: 0.10089044272899628
2023-01-21 09:45:29.344945: step: 1224/530, loss: 0.07660436630249023
2023-01-21 09:45:30.457871: step: 1228/530, loss: 0.10002336651086807
2023-01-21 09:45:31.570808: step: 1232/530, loss: 0.008935785852372646
2023-01-21 09:45:32.664861: step: 1236/530, loss: 0.03334970399737358
2023-01-21 09:45:33.772715: step: 1240/530, loss: 0.22614385187625885
2023-01-21 09:45:34.872731: step: 1244/530, loss: 0.0598149299621582
2023-01-21 09:45:35.984362: step: 1248/530, loss: 0.18491224944591522
2023-01-21 09:45:37.078748: step: 1252/530, loss: 0.12284259498119354
2023-01-21 09:45:38.191306: step: 1256/530, loss: 0.10551224648952484
2023-01-21 09:45:39.276040: step: 1260/530, loss: 0.18351221084594727
2023-01-21 09:45:40.385520: step: 1264/530, loss: 0.17852169275283813
2023-01-21 09:45:41.494071: step: 1268/530, loss: 0.05660710483789444
2023-01-21 09:45:42.623679: step: 1272/530, loss: 0.01652536541223526
2023-01-21 09:45:43.772807: step: 1276/530, loss: 0.056099891662597656
2023-01-21 09:45:44.905065: step: 1280/530, loss: 0.1079021468758583
2023-01-21 09:45:46.030992: step: 1284/530, loss: 0.11702223122119904
2023-01-21 09:45:47.138297: step: 1288/530, loss: 0.12205057591199875
2023-01-21 09:45:48.249424: step: 1292/530, loss: 0.17013882100582123
2023-01-21 09:45:49.367062: step: 1296/530, loss: 0.4505516588687897
2023-01-21 09:45:50.467926: step: 1300/530, loss: 0.04913225397467613
2023-01-21 09:45:51.582751: step: 1304/530, loss: 0.007321691606193781
2023-01-21 09:45:52.723414: step: 1308/530, loss: 0.11692790687084198
2023-01-21 09:45:53.824620: step: 1312/530, loss: 0.1647607386112213
2023-01-21 09:45:54.951128: step: 1316/530, loss: 0.0701846107840538
2023-01-21 09:45:56.062062: step: 1320/530, loss: 0.03838348388671875
2023-01-21 09:45:57.188635: step: 1324/530, loss: 0.0946449339389801
2023-01-21 09:45:58.374254: step: 1328/530, loss: 0.1541803479194641
2023-01-21 09:45:59.470958: step: 1332/530, loss: 0.083636574447155
2023-01-21 09:46:00.588914: step: 1336/530, loss: 0.10761566460132599
2023-01-21 09:46:01.689280: step: 1340/530, loss: 0.01571788638830185
2023-01-21 09:46:02.838683: step: 1344/530, loss: 0.061579324305057526
2023-01-21 09:46:03.959441: step: 1348/530, loss: 0.0747842788696289
2023-01-21 09:46:05.069384: step: 1352/530, loss: 0.2404789924621582
2023-01-21 09:46:06.164083: step: 1356/530, loss: 0.06411950290203094
2023-01-21 09:46:07.251158: step: 1360/530, loss: 0.06407604366540909
2023-01-21 09:46:08.343718: step: 1364/530, loss: 0.2542060613632202
2023-01-21 09:46:09.478511: step: 1368/530, loss: 0.060243330895900726
2023-01-21 09:46:10.602114: step: 1372/530, loss: 0.4493376612663269
2023-01-21 09:46:11.702301: step: 1376/530, loss: 0.6244895458221436
2023-01-21 09:46:12.824422: step: 1380/530, loss: 0.03403501585125923
2023-01-21 09:46:13.942830: step: 1384/530, loss: 0.18758173286914825
2023-01-21 09:46:15.052700: step: 1388/530, loss: 0.024759292602539062
2023-01-21 09:46:16.156297: step: 1392/530, loss: 0.06201000511646271
2023-01-21 09:46:17.265045: step: 1396/530, loss: 0.04967174679040909
2023-01-21 09:46:18.399232: step: 1400/530, loss: 0.14865446090698242
2023-01-21 09:46:19.527437: step: 1404/530, loss: 0.083203986287117
2023-01-21 09:46:20.632028: step: 1408/530, loss: 0.13988637924194336
2023-01-21 09:46:21.760174: step: 1412/530, loss: 0.07094764709472656
2023-01-21 09:46:22.917144: step: 1416/530, loss: 0.15718698501586914
2023-01-21 09:46:24.050506: step: 1420/530, loss: 0.34256047010421753
2023-01-21 09:46:25.146846: step: 1424/530, loss: 0.013786209747195244
2023-01-21 09:46:26.263940: step: 1428/530, loss: 0.04166831821203232
2023-01-21 09:46:27.393955: step: 1432/530, loss: 0.02809758111834526
2023-01-21 09:46:28.511671: step: 1436/530, loss: 0.054114725440740585
2023-01-21 09:46:29.617262: step: 1440/530, loss: 0.1906147599220276
2023-01-21 09:46:30.775595: step: 1444/530, loss: 0.01645221747457981
2023-01-21 09:46:31.885400: step: 1448/530, loss: 0.26801052689552307
2023-01-21 09:46:32.995513: step: 1452/530, loss: 0.1848854124546051
2023-01-21 09:46:34.104905: step: 1456/530, loss: 0.04668988287448883
2023-01-21 09:46:35.204021: step: 1460/530, loss: 0.05898289754986763
2023-01-21 09:46:36.287275: step: 1464/530, loss: 0.03276043012738228
2023-01-21 09:46:37.403034: step: 1468/530, loss: 0.12012281268835068
2023-01-21 09:46:38.509820: step: 1472/530, loss: 0.20264868438243866
2023-01-21 09:46:39.619237: step: 1476/530, loss: 0.08479490131139755
2023-01-21 09:46:40.715209: step: 1480/530, loss: 0.12261982262134552
2023-01-21 09:46:41.804704: step: 1484/530, loss: 0.04406576231122017
2023-01-21 09:46:42.908864: step: 1488/530, loss: 0.18016672134399414
2023-01-21 09:46:44.027969: step: 1492/530, loss: 0.01678161695599556
2023-01-21 09:46:45.152287: step: 1496/530, loss: 0.1961621344089508
2023-01-21 09:46:46.270749: step: 1500/530, loss: 0.03058633953332901
2023-01-21 09:46:47.395409: step: 1504/530, loss: 0.026283692568540573
2023-01-21 09:46:48.511564: step: 1508/530, loss: 1.1503907442092896
2023-01-21 09:46:49.612223: step: 1512/530, loss: 0.13508710265159607
2023-01-21 09:46:50.712299: step: 1516/530, loss: 0.09917883574962616
2023-01-21 09:46:51.858198: step: 1520/530, loss: 0.16245366632938385
2023-01-21 09:46:52.964543: step: 1524/530, loss: 0.33379992842674255
2023-01-21 09:46:54.050644: step: 1528/530, loss: 0.07469645142555237
2023-01-21 09:46:55.183475: step: 1532/530, loss: 0.4811992347240448
2023-01-21 09:46:56.290827: step: 1536/530, loss: 0.6457498669624329
2023-01-21 09:46:57.396963: step: 1540/530, loss: 0.05424566566944122
2023-01-21 09:46:58.514072: step: 1544/530, loss: 0.15637606382369995
2023-01-21 09:46:59.631352: step: 1548/530, loss: 0.1795998215675354
2023-01-21 09:47:00.745006: step: 1552/530, loss: 0.018937159329652786
2023-01-21 09:47:01.859617: step: 1556/530, loss: 0.20717038214206696
2023-01-21 09:47:03.003695: step: 1560/530, loss: 0.2970763146877289
2023-01-21 09:47:04.126916: step: 1564/530, loss: 0.017335079610347748
2023-01-21 09:47:05.239115: step: 1568/530, loss: 0.034961700439453125
2023-01-21 09:47:06.362710: step: 1572/530, loss: 0.1570838987827301
2023-01-21 09:47:07.456891: step: 1576/530, loss: 0.19413965940475464
2023-01-21 09:47:08.580800: step: 1580/530, loss: 0.04839807003736496
2023-01-21 09:47:09.682187: step: 1584/530, loss: 0.015035724267363548
2023-01-21 09:47:10.796807: step: 1588/530, loss: 0.10891500115394592
2023-01-21 09:47:11.950515: step: 1592/530, loss: 0.15524645149707794
2023-01-21 09:47:13.053819: step: 1596/530, loss: 0.13787975907325745
2023-01-21 09:47:14.205102: step: 1600/530, loss: 0.016784286126494408
2023-01-21 09:47:15.325267: step: 1604/530, loss: 0.761996328830719
2023-01-21 09:47:16.444432: step: 1608/530, loss: 0.2046799659729004
2023-01-21 09:47:17.550071: step: 1612/530, loss: 0.08629155158996582
2023-01-21 09:47:18.679540: step: 1616/530, loss: 0.02428760752081871
2023-01-21 09:47:19.781158: step: 1620/530, loss: 0.15176203846931458
2023-01-21 09:47:20.909941: step: 1624/530, loss: 0.08319902420043945
2023-01-21 09:47:22.024598: step: 1628/530, loss: 0.15911245346069336
2023-01-21 09:47:23.131862: step: 1632/530, loss: 0.1149345338344574
2023-01-21 09:47:24.223498: step: 1636/530, loss: 0.10317926853895187
2023-01-21 09:47:25.353079: step: 1640/530, loss: 0.10749483108520508
2023-01-21 09:47:26.516502: step: 1644/530, loss: 0.2425212860107422
2023-01-21 09:47:27.632954: step: 1648/530, loss: 0.13477811217308044
2023-01-21 09:47:28.749615: step: 1652/530, loss: 0.08036184310913086
2023-01-21 09:47:29.873414: step: 1656/530, loss: 0.34441354870796204
2023-01-21 09:47:31.001060: step: 1660/530, loss: 0.05651536211371422
2023-01-21 09:47:32.125088: step: 1664/530, loss: 0.07763798534870148
2023-01-21 09:47:33.270362: step: 1668/530, loss: 0.25647610425949097
2023-01-21 09:47:34.392694: step: 1672/530, loss: 0.792915940284729
2023-01-21 09:47:35.491263: step: 1676/530, loss: 0.01355056744068861
2023-01-21 09:47:36.594570: step: 1680/530, loss: 0.059019140899181366
2023-01-21 09:47:37.722033: step: 1684/530, loss: 0.06971187889575958
2023-01-21 09:47:38.841447: step: 1688/530, loss: 0.042878054082393646
2023-01-21 09:47:39.932201: step: 1692/530, loss: 0.1897238790988922
2023-01-21 09:47:41.070477: step: 1696/530, loss: 0.14532537758350372
2023-01-21 09:47:42.181819: step: 1700/530, loss: 0.05813112482428551
2023-01-21 09:47:43.296073: step: 1704/530, loss: 0.043309591710567474
2023-01-21 09:47:44.421954: step: 1708/530, loss: 0.251463383436203
2023-01-21 09:47:45.520088: step: 1712/530, loss: 0.11341853439807892
2023-01-21 09:47:46.635737: step: 1716/530, loss: 0.3857729732990265
2023-01-21 09:47:47.757095: step: 1720/530, loss: 0.059373639523983
2023-01-21 09:47:48.849383: step: 1724/530, loss: 0.1369960755109787
2023-01-21 09:47:49.947858: step: 1728/530, loss: 0.15533065795898438
2023-01-21 09:47:51.079550: step: 1732/530, loss: 0.10133242607116699
2023-01-21 09:47:52.184680: step: 1736/530, loss: 0.009392976760864258
2023-01-21 09:47:53.312679: step: 1740/530, loss: 0.15127259492874146
2023-01-21 09:47:54.423084: step: 1744/530, loss: 0.40107449889183044
2023-01-21 09:47:55.548880: step: 1748/530, loss: 0.253089964389801
2023-01-21 09:47:56.654868: step: 1752/530, loss: 0.13640379905700684
2023-01-21 09:47:57.742265: step: 1756/530, loss: 0.26185142993927
2023-01-21 09:47:58.864726: step: 1760/530, loss: 0.12110863626003265
2023-01-21 09:47:59.957080: step: 1764/530, loss: 0.14644603431224823
2023-01-21 09:48:01.068818: step: 1768/530, loss: 0.03412375599145889
2023-01-21 09:48:02.188945: step: 1772/530, loss: 0.14674320816993713
2023-01-21 09:48:03.295354: step: 1776/530, loss: 0.03385672718286514
2023-01-21 09:48:04.391441: step: 1780/530, loss: 0.027505040168762207
2023-01-21 09:48:05.474499: step: 1784/530, loss: 1.453717589378357
2023-01-21 09:48:06.583491: step: 1788/530, loss: 0.0479624941945076
2023-01-21 09:48:07.718748: step: 1792/530, loss: 0.08169708400964737
2023-01-21 09:48:08.865337: step: 1796/530, loss: 0.1136348694562912
2023-01-21 09:48:09.969680: step: 1800/530, loss: 0.105889230966568
2023-01-21 09:48:11.082180: step: 1804/530, loss: 0.12311048805713654
2023-01-21 09:48:12.188190: step: 1808/530, loss: 0.3427059054374695
2023-01-21 09:48:13.300125: step: 1812/530, loss: 0.24736528098583221
2023-01-21 09:48:14.396857: step: 1816/530, loss: 0.06742402166128159
2023-01-21 09:48:15.488803: step: 1820/530, loss: 0.19215498864650726
2023-01-21 09:48:16.593934: step: 1824/530, loss: 0.2773607075214386
2023-01-21 09:48:17.700660: step: 1828/530, loss: 0.007732868194580078
2023-01-21 09:48:18.767692: step: 1832/530, loss: 0.05819902569055557
2023-01-21 09:48:19.870788: step: 1836/530, loss: 0.021595144644379616
2023-01-21 09:48:20.989221: step: 1840/530, loss: 0.0987127274274826
2023-01-21 09:48:22.124330: step: 1844/530, loss: 0.03133106231689453
2023-01-21 09:48:23.256408: step: 1848/530, loss: 0.14067693054676056
2023-01-21 09:48:24.357955: step: 1852/530, loss: 0.03854823112487793
2023-01-21 09:48:25.478975: step: 1856/530, loss: 0.46442943811416626
2023-01-21 09:48:26.605480: step: 1860/530, loss: 0.11144295334815979
2023-01-21 09:48:27.701751: step: 1864/530, loss: 0.0530390739440918
2023-01-21 09:48:28.820712: step: 1868/530, loss: 0.25548774003982544
2023-01-21 09:48:29.904946: step: 1872/530, loss: 0.04158220440149307
2023-01-21 09:48:31.011229: step: 1876/530, loss: 0.19178669154644012
2023-01-21 09:48:32.113666: step: 1880/530, loss: 0.08530235290527344
2023-01-21 09:48:33.224936: step: 1884/530, loss: 0.08339400589466095
2023-01-21 09:48:34.339535: step: 1888/530, loss: 0.15072917938232422
2023-01-21 09:48:35.434892: step: 1892/530, loss: 0.1369525045156479
2023-01-21 09:48:36.565546: step: 1896/530, loss: 0.10736475884914398
2023-01-21 09:48:37.652910: step: 1900/530, loss: 1.0873714685440063
2023-01-21 09:48:38.756586: step: 1904/530, loss: 0.21266737580299377
2023-01-21 09:48:39.882261: step: 1908/530, loss: 0.11113186180591583
2023-01-21 09:48:41.003463: step: 1912/530, loss: 0.4375871419906616
2023-01-21 09:48:42.123403: step: 1916/530, loss: 0.06430625915527344
2023-01-21 09:48:43.243688: step: 1920/530, loss: 0.17605695128440857
2023-01-21 09:48:44.392854: step: 1924/530, loss: 0.11253967881202698
2023-01-21 09:48:45.497527: step: 1928/530, loss: 0.4085157811641693
2023-01-21 09:48:46.617959: step: 1932/530, loss: 0.12084998935461044
2023-01-21 09:48:47.733349: step: 1936/530, loss: 0.0790262222290039
2023-01-21 09:48:48.840748: step: 1940/530, loss: 0.12296628952026367
2023-01-21 09:48:49.974100: step: 1944/530, loss: 0.1135474145412445
2023-01-21 09:48:51.064730: step: 1948/530, loss: 0.030989982187747955
2023-01-21 09:48:52.158504: step: 1952/530, loss: 0.08686414361000061
2023-01-21 09:48:53.257798: step: 1956/530, loss: 0.3712020814418793
2023-01-21 09:48:54.410404: step: 1960/530, loss: 0.15691861510276794
2023-01-21 09:48:55.542340: step: 1964/530, loss: 0.0353451743721962
2023-01-21 09:48:56.670750: step: 1968/530, loss: 0.01219949685037136
2023-01-21 09:48:57.800992: step: 1972/530, loss: 0.07300257682800293
2023-01-21 09:48:58.913880: step: 1976/530, loss: 0.7963172793388367
2023-01-21 09:49:00.031424: step: 1980/530, loss: 0.014382028952240944
2023-01-21 09:49:01.151828: step: 1984/530, loss: 0.011725043877959251
2023-01-21 09:49:02.294195: step: 1988/530, loss: 0.9076177477836609
2023-01-21 09:49:03.422535: step: 1992/530, loss: 0.43448925018310547
2023-01-21 09:49:04.589527: step: 1996/530, loss: 0.13645966351032257
2023-01-21 09:49:05.687564: step: 2000/530, loss: 0.1092628538608551
2023-01-21 09:49:06.795474: step: 2004/530, loss: 0.05595436319708824
2023-01-21 09:49:07.890957: step: 2008/530, loss: 0.011530399322509766
2023-01-21 09:49:09.008884: step: 2012/530, loss: 0.38748282194137573
2023-01-21 09:49:10.117387: step: 2016/530, loss: 0.07710695266723633
2023-01-21 09:49:11.246008: step: 2020/530, loss: 0.1639409065246582
2023-01-21 09:49:12.374823: step: 2024/530, loss: 0.06237039342522621
2023-01-21 09:49:13.524425: step: 2028/530, loss: 0.09340152144432068
2023-01-21 09:49:14.685588: step: 2032/530, loss: 0.034457016736269
2023-01-21 09:49:15.806137: step: 2036/530, loss: 0.09790392220020294
2023-01-21 09:49:16.904185: step: 2040/530, loss: 0.32078075408935547
2023-01-21 09:49:18.022334: step: 2044/530, loss: 0.09958477318286896
2023-01-21 09:49:19.146593: step: 2048/530, loss: 0.0667843222618103
2023-01-21 09:49:20.254434: step: 2052/530, loss: 0.13015519082546234
2023-01-21 09:49:21.378427: step: 2056/530, loss: 0.1083078384399414
2023-01-21 09:49:22.496270: step: 2060/530, loss: 0.08503742516040802
2023-01-21 09:49:23.637534: step: 2064/530, loss: 1.3333532810211182
2023-01-21 09:49:24.752976: step: 2068/530, loss: 0.17610615491867065
2023-01-21 09:49:25.882010: step: 2072/530, loss: 0.23218633234500885
2023-01-21 09:49:26.974965: step: 2076/530, loss: 0.04601392522454262
2023-01-21 09:49:28.080172: step: 2080/530, loss: 0.10227089375257492
2023-01-21 09:49:29.171303: step: 2084/530, loss: 0.02254486083984375
2023-01-21 09:49:30.259588: step: 2088/530, loss: 0.06414642184972763
2023-01-21 09:49:31.409768: step: 2092/530, loss: 0.11543788760900497
2023-01-21 09:49:32.493010: step: 2096/530, loss: 0.13644686341285706
2023-01-21 09:49:33.579193: step: 2100/530, loss: 0.022280026227235794
2023-01-21 09:49:34.675364: step: 2104/530, loss: 0.055542588233947754
2023-01-21 09:49:35.783620: step: 2108/530, loss: 0.10805568844079971
2023-01-21 09:49:36.872006: step: 2112/530, loss: 0.17468424141407013
2023-01-21 09:49:37.957663: step: 2116/530, loss: 0.05167236179113388
2023-01-21 09:49:39.055655: step: 2120/530, loss: 0.09521299600601196
==================================================
Loss: 0.157
--------------------
Dev: {'event': {'p': 0.6466512702078522, 'r': 0.7456724367509987, 'f1': 0.6926406926406927}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Test: {'event': {'p': 0.6762148337595908, 'r': 0.7703962703962703, 'f1': 0.7202397166984473}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Chinese: {'event': {'p': 0.5797101449275363, 'r': 0.7407407407407407, 'f1': 0.6504065040650405}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Russian: {'event': {'p': 0.46153846153846156, 'r': 0.5, 'f1': 0.48000000000000004}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5708622398414271, 'r': 0.7669773635153129, 'f1': 0.6545454545454545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Chinese: {'event': {'p': 0.6044052863436123, 'r': 0.7995337995337995, 'f1': 0.6884094330155545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Chinese: {'event': {'p': 0.6578947368421053, 'r': 0.9259259259259259, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6466512702078522, 'r': 0.7456724367509987, 'f1': 0.6926406926406927}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.6762148337595908, 'r': 0.7703962703962703, 'f1': 0.7202397166984473}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6466512702078522, 'r': 0.7456724367509987, 'f1': 0.6926406926406927}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Russian: {'event': {'p': 0.6762148337595908, 'r': 0.7703962703962703, 'f1': 0.7202397166984473}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Russian: {'event': {'p': 0.46153846153846156, 'r': 0.5, 'f1': 0.48000000000000004}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
******************************
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 09:50:27.339383: step: 4/530, loss: 0.11911869049072266
2023-01-21 09:50:28.440047: step: 8/530, loss: 0.05594654381275177
2023-01-21 09:50:29.542952: step: 12/530, loss: 0.06005992740392685
2023-01-21 09:50:30.709232: step: 16/530, loss: 0.10222244262695312
2023-01-21 09:50:31.800962: step: 20/530, loss: 0.03707914426922798
2023-01-21 09:50:32.898825: step: 24/530, loss: 0.3849490284919739
2023-01-21 09:50:34.011785: step: 28/530, loss: 0.0986148864030838
2023-01-21 09:50:35.104990: step: 32/530, loss: 0.017137527465820312
2023-01-21 09:50:36.208601: step: 36/530, loss: 0.04865570366382599
2023-01-21 09:50:37.294197: step: 40/530, loss: 0.06709442287683487
2023-01-21 09:50:38.417945: step: 44/530, loss: 0.029865264892578125
2023-01-21 09:50:39.574650: step: 48/530, loss: 0.03145141527056694
2023-01-21 09:50:40.716929: step: 52/530, loss: 0.06527357548475266
2023-01-21 09:50:41.818683: step: 56/530, loss: 0.007344889920204878
2023-01-21 09:50:42.971413: step: 60/530, loss: 0.08568783104419708
2023-01-21 09:50:44.098066: step: 64/530, loss: 0.06358623504638672
2023-01-21 09:50:45.211216: step: 68/530, loss: 0.010941028594970703
2023-01-21 09:50:46.315119: step: 72/530, loss: 0.10358834266662598
2023-01-21 09:50:47.438182: step: 76/530, loss: 0.03071575053036213
2023-01-21 09:50:48.548244: step: 80/530, loss: 0.06349430233240128
2023-01-21 09:50:49.717696: step: 84/530, loss: 0.049593113362789154
2023-01-21 09:50:50.797733: step: 88/530, loss: 0.13640671968460083
2023-01-21 09:50:51.897367: step: 92/530, loss: 0.09202051162719727
2023-01-21 09:50:53.020751: step: 96/530, loss: 0.11000747978687286
2023-01-21 09:50:54.134579: step: 100/530, loss: 0.0786200538277626
2023-01-21 09:50:55.253704: step: 104/530, loss: 0.21903228759765625
2023-01-21 09:50:56.371687: step: 108/530, loss: 0.08303675800561905
2023-01-21 09:50:57.465221: step: 112/530, loss: 0.07887706905603409
2023-01-21 09:50:58.564913: step: 116/530, loss: 0.06502733379602432
2023-01-21 09:50:59.638043: step: 120/530, loss: 0.021123027428984642
2023-01-21 09:51:00.723804: step: 124/530, loss: 0.013583827763795853
2023-01-21 09:51:01.860700: step: 128/530, loss: 0.08342437446117401
2023-01-21 09:51:02.989954: step: 132/530, loss: 0.19991883635520935
2023-01-21 09:51:04.087433: step: 136/530, loss: 0.010261917486786842
2023-01-21 09:51:05.192476: step: 140/530, loss: 0.17521458864212036
2023-01-21 09:51:06.326679: step: 144/530, loss: 0.5597915649414062
2023-01-21 09:51:07.429652: step: 148/530, loss: 0.22418656945228577
2023-01-21 09:51:08.534403: step: 152/530, loss: 0.027275515720248222
2023-01-21 09:51:09.637341: step: 156/530, loss: 0.03014860302209854
2023-01-21 09:51:10.776949: step: 160/530, loss: 0.0989227294921875
2023-01-21 09:51:11.880120: step: 164/530, loss: 0.24144801497459412
2023-01-21 09:51:13.005409: step: 168/530, loss: 0.6401756405830383
2023-01-21 09:51:14.117080: step: 172/530, loss: 0.15292863547801971
2023-01-21 09:51:15.223591: step: 176/530, loss: 0.05735521391034126
2023-01-21 09:51:16.339524: step: 180/530, loss: 0.11661558598279953
2023-01-21 09:51:17.472611: step: 184/530, loss: 0.102117158472538
2023-01-21 09:51:18.591765: step: 188/530, loss: 0.0296649057418108
2023-01-21 09:51:19.710882: step: 192/530, loss: 0.08524150401353836
2023-01-21 09:51:20.799749: step: 196/530, loss: 0.07382392883300781
2023-01-21 09:51:21.887223: step: 200/530, loss: 0.02957477793097496
2023-01-21 09:51:23.028174: step: 204/530, loss: 0.07235565036535263
2023-01-21 09:51:24.114702: step: 208/530, loss: 0.07224207371473312
2023-01-21 09:51:25.243584: step: 212/530, loss: 0.0077370647341012955
2023-01-21 09:51:26.339439: step: 216/530, loss: 0.05593404918909073
2023-01-21 09:51:27.438567: step: 220/530, loss: 0.3368190824985504
2023-01-21 09:51:28.576544: step: 224/530, loss: 0.054932307451963425
2023-01-21 09:51:29.674637: step: 228/530, loss: 0.05258283391594887
2023-01-21 09:51:30.787311: step: 232/530, loss: 0.8753765821456909
2023-01-21 09:51:31.923622: step: 236/530, loss: 0.2955070734024048
2023-01-21 09:51:33.015279: step: 240/530, loss: 0.024929236620664597
2023-01-21 09:51:34.130745: step: 244/530, loss: 0.027506638318300247
2023-01-21 09:51:35.231585: step: 248/530, loss: 0.2574559152126312
2023-01-21 09:51:36.354397: step: 252/530, loss: 0.07435693591833115
2023-01-21 09:51:37.463073: step: 256/530, loss: 0.14356708526611328
2023-01-21 09:51:38.592854: step: 260/530, loss: 0.024345088750123978
2023-01-21 09:51:39.701566: step: 264/530, loss: 0.08252649754285812
2023-01-21 09:51:40.815191: step: 268/530, loss: 0.05271584540605545
2023-01-21 09:51:41.959498: step: 272/530, loss: 0.05398616939783096
2023-01-21 09:51:43.068189: step: 276/530, loss: 0.03599701076745987
2023-01-21 09:51:44.162701: step: 280/530, loss: 0.30442380905151367
2023-01-21 09:51:45.249379: step: 284/530, loss: 0.012623501010239124
2023-01-21 09:51:46.351472: step: 288/530, loss: 0.04532194137573242
2023-01-21 09:51:47.498457: step: 292/530, loss: 0.13103848695755005
2023-01-21 09:51:48.618407: step: 296/530, loss: 0.13387545943260193
2023-01-21 09:51:49.741638: step: 300/530, loss: 0.13475675880908966
2023-01-21 09:51:50.872801: step: 304/530, loss: 0.13041897118091583
2023-01-21 09:51:51.981942: step: 308/530, loss: 0.024891089648008347
2023-01-21 09:51:53.094654: step: 312/530, loss: 0.06801509857177734
2023-01-21 09:51:54.195822: step: 316/530, loss: 0.06932802498340607
2023-01-21 09:51:55.297160: step: 320/530, loss: 0.13690677285194397
2023-01-21 09:51:56.381465: step: 324/530, loss: 0.055600740015506744
2023-01-21 09:51:57.478564: step: 328/530, loss: 0.11437202244997025
2023-01-21 09:51:58.587329: step: 332/530, loss: 0.02527599409222603
2023-01-21 09:51:59.692273: step: 336/530, loss: 0.1801416277885437
2023-01-21 09:52:00.825421: step: 340/530, loss: 0.1253347396850586
2023-01-21 09:52:01.937132: step: 344/530, loss: 0.14391641318798065
2023-01-21 09:52:03.049062: step: 348/530, loss: 0.4257441461086273
2023-01-21 09:52:04.167768: step: 352/530, loss: 0.02731156349182129
2023-01-21 09:52:05.310198: step: 356/530, loss: 0.09722795337438583
2023-01-21 09:52:06.404393: step: 360/530, loss: 0.08871941268444061
2023-01-21 09:52:07.519430: step: 364/530, loss: 0.0026256563141942024
2023-01-21 09:52:08.638674: step: 368/530, loss: 0.16361045837402344
2023-01-21 09:52:09.743611: step: 372/530, loss: 0.06298217922449112
2023-01-21 09:52:10.877311: step: 376/530, loss: 0.07270222157239914
2023-01-21 09:52:11.975496: step: 380/530, loss: 0.06875000149011612
2023-01-21 09:52:13.072976: step: 384/530, loss: 0.06463241577148438
2023-01-21 09:52:14.173288: step: 388/530, loss: 0.14835090935230255
2023-01-21 09:52:15.266508: step: 392/530, loss: 0.3185749053955078
2023-01-21 09:52:16.375896: step: 396/530, loss: 0.8417788147926331
2023-01-21 09:52:17.524499: step: 400/530, loss: 0.19428329169750214
2023-01-21 09:52:18.635031: step: 404/530, loss: 0.1736827790737152
2023-01-21 09:52:19.736312: step: 408/530, loss: 0.13287745416164398
2023-01-21 09:52:20.859046: step: 412/530, loss: 0.2966168522834778
2023-01-21 09:52:21.983870: step: 416/530, loss: 0.663040280342102
2023-01-21 09:52:23.112359: step: 420/530, loss: 0.08559150993824005
2023-01-21 09:52:24.226482: step: 424/530, loss: 0.43381378054618835
2023-01-21 09:52:25.332676: step: 428/530, loss: 0.10292968899011612
2023-01-21 09:52:26.436124: step: 432/530, loss: 0.04438028484582901
2023-01-21 09:52:27.533559: step: 436/530, loss: 0.11642227321863174
2023-01-21 09:52:28.653774: step: 440/530, loss: 0.054781340062618256
2023-01-21 09:52:29.799934: step: 444/530, loss: 0.05360608547925949
2023-01-21 09:52:30.876206: step: 448/530, loss: 0.027811909094452858
2023-01-21 09:52:31.992587: step: 452/530, loss: 0.08550529181957245
2023-01-21 09:52:33.111577: step: 456/530, loss: 0.06656856834888458
2023-01-21 09:52:34.242713: step: 460/530, loss: 0.04748420789837837
2023-01-21 09:52:35.373926: step: 464/530, loss: 0.07782869040966034
2023-01-21 09:52:36.509362: step: 468/530, loss: 0.056507352739572525
2023-01-21 09:52:37.620165: step: 472/530, loss: 0.15341129899024963
2023-01-21 09:52:38.727595: step: 476/530, loss: 0.029101181775331497
2023-01-21 09:52:39.868795: step: 480/530, loss: 0.2146543562412262
2023-01-21 09:52:41.031431: step: 484/530, loss: 0.06759872287511826
2023-01-21 09:52:42.189425: step: 488/530, loss: 0.18770703673362732
2023-01-21 09:52:43.291446: step: 492/530, loss: 0.09333138912916183
2023-01-21 09:52:44.430055: step: 496/530, loss: 0.07917661964893341
2023-01-21 09:52:45.618636: step: 500/530, loss: 0.06565704196691513
2023-01-21 09:52:46.718077: step: 504/530, loss: 0.6630858778953552
2023-01-21 09:52:47.869545: step: 508/530, loss: 1.6059333086013794
2023-01-21 09:52:48.989493: step: 512/530, loss: 0.18353310227394104
2023-01-21 09:52:50.103718: step: 516/530, loss: 0.2970350980758667
2023-01-21 09:52:51.206670: step: 520/530, loss: 0.09521408379077911
2023-01-21 09:52:52.308861: step: 524/530, loss: 0.03171906620264053
2023-01-21 09:52:53.398267: step: 528/530, loss: 0.0417880043387413
2023-01-21 09:52:54.509482: step: 532/530, loss: 0.09714994579553604
2023-01-21 09:52:55.642073: step: 536/530, loss: 0.08333511650562286
2023-01-21 09:52:56.754274: step: 540/530, loss: 0.10097970813512802
2023-01-21 09:52:57.884142: step: 544/530, loss: 0.08820643275976181
2023-01-21 09:52:58.995499: step: 548/530, loss: 0.21242770552635193
2023-01-21 09:53:00.088368: step: 552/530, loss: 0.03767795488238335
2023-01-21 09:53:01.187337: step: 556/530, loss: 0.0064598084427416325
2023-01-21 09:53:02.254456: step: 560/530, loss: 0.08491519093513489
2023-01-21 09:53:03.378533: step: 564/530, loss: 0.0958637222647667
2023-01-21 09:53:04.517248: step: 568/530, loss: 0.3100414276123047
2023-01-21 09:53:05.592749: step: 572/530, loss: 0.06438927352428436
2023-01-21 09:53:06.708964: step: 576/530, loss: 0.037790488451719284
2023-01-21 09:53:07.800612: step: 580/530, loss: 0.12114611268043518
2023-01-21 09:53:08.904655: step: 584/530, loss: 0.20157796144485474
2023-01-21 09:53:10.007105: step: 588/530, loss: 0.007942711934447289
2023-01-21 09:53:11.115615: step: 592/530, loss: 0.20363445580005646
2023-01-21 09:53:12.243628: step: 596/530, loss: 0.1639750450849533
2023-01-21 09:53:13.399563: step: 600/530, loss: 0.15326690673828125
2023-01-21 09:53:14.489588: step: 604/530, loss: 0.021233271807432175
2023-01-21 09:53:15.598907: step: 608/530, loss: 0.013071263208985329
2023-01-21 09:53:16.703493: step: 612/530, loss: 0.016934489831328392
2023-01-21 09:53:17.821573: step: 616/530, loss: 0.06845493614673615
2023-01-21 09:53:18.940648: step: 620/530, loss: 0.04945418983697891
2023-01-21 09:53:20.049657: step: 624/530, loss: 0.02663288079202175
2023-01-21 09:53:21.179087: step: 628/530, loss: 0.03731508553028107
2023-01-21 09:53:22.262338: step: 632/530, loss: 0.01670842245221138
2023-01-21 09:53:23.397160: step: 636/530, loss: 0.0053452495485544205
2023-01-21 09:53:24.497435: step: 640/530, loss: 0.07053223252296448
2023-01-21 09:53:25.594009: step: 644/530, loss: 0.05582469701766968
2023-01-21 09:53:26.756549: step: 648/530, loss: 0.07306060940027237
2023-01-21 09:53:27.882394: step: 652/530, loss: 0.39343851804733276
2023-01-21 09:53:29.012395: step: 656/530, loss: 0.17465132474899292
2023-01-21 09:53:30.132991: step: 660/530, loss: 0.10805759578943253
2023-01-21 09:53:31.261776: step: 664/530, loss: 0.12455320358276367
2023-01-21 09:53:32.366805: step: 668/530, loss: 0.07217588275671005
2023-01-21 09:53:33.493868: step: 672/530, loss: 0.12222146987915039
2023-01-21 09:53:34.614422: step: 676/530, loss: 0.012021685019135475
2023-01-21 09:53:35.729235: step: 680/530, loss: 0.08690624684095383
2023-01-21 09:53:36.863688: step: 684/530, loss: 0.01951742172241211
2023-01-21 09:53:37.999544: step: 688/530, loss: 0.28196069598197937
2023-01-21 09:53:39.115900: step: 692/530, loss: 0.07948670536279678
2023-01-21 09:53:40.219347: step: 696/530, loss: 0.07117261737585068
2023-01-21 09:53:41.342141: step: 700/530, loss: 0.20772957801818848
2023-01-21 09:53:42.456515: step: 704/530, loss: 0.025627028197050095
2023-01-21 09:53:43.585011: step: 708/530, loss: 0.09152460098266602
2023-01-21 09:53:44.705562: step: 712/530, loss: 0.041408635675907135
2023-01-21 09:53:45.808038: step: 716/530, loss: 0.14207744598388672
2023-01-21 09:53:46.907509: step: 720/530, loss: 0.11624152213335037
2023-01-21 09:53:48.014573: step: 724/530, loss: 0.12275762856006622
2023-01-21 09:53:49.102822: step: 728/530, loss: 0.18236666917800903
2023-01-21 09:53:50.216181: step: 732/530, loss: 0.2133081555366516
2023-01-21 09:53:51.345844: step: 736/530, loss: 0.09168877452611923
2023-01-21 09:53:52.459810: step: 740/530, loss: 0.1224275603890419
2023-01-21 09:53:53.589082: step: 744/530, loss: 0.028417587280273438
2023-01-21 09:53:54.700794: step: 748/530, loss: 0.021269608289003372
2023-01-21 09:53:55.857109: step: 752/530, loss: 0.013565922155976295
2023-01-21 09:53:56.988638: step: 756/530, loss: 0.1359941065311432
2023-01-21 09:53:58.092895: step: 760/530, loss: 0.10326366126537323
2023-01-21 09:53:59.198745: step: 764/530, loss: 0.034735631197690964
2023-01-21 09:54:00.297767: step: 768/530, loss: 0.053417399525642395
2023-01-21 09:54:01.408629: step: 772/530, loss: 0.10511569678783417
2023-01-21 09:54:02.516626: step: 776/530, loss: 0.06361141055822372
2023-01-21 09:54:03.658543: step: 780/530, loss: 0.11846351623535156
2023-01-21 09:54:04.763258: step: 784/530, loss: 0.04683428257703781
2023-01-21 09:54:05.877193: step: 788/530, loss: 0.03210430219769478
2023-01-21 09:54:06.979773: step: 792/530, loss: 0.01716151274740696
2023-01-21 09:54:08.128931: step: 796/530, loss: 0.08280573040246964
2023-01-21 09:54:09.273229: step: 800/530, loss: 0.2534770965576172
2023-01-21 09:54:10.404481: step: 804/530, loss: 0.09977531433105469
2023-01-21 09:54:11.532731: step: 808/530, loss: 0.09530212730169296
2023-01-21 09:54:12.630010: step: 812/530, loss: 0.07445145398378372
2023-01-21 09:54:13.757543: step: 816/530, loss: 0.266034334897995
2023-01-21 09:54:14.858370: step: 820/530, loss: 0.12444248795509338
2023-01-21 09:54:15.973494: step: 824/530, loss: 0.04329118877649307
2023-01-21 09:54:17.066475: step: 828/530, loss: 0.17458286881446838
2023-01-21 09:54:18.198511: step: 832/530, loss: 0.02772388607263565
2023-01-21 09:54:19.311903: step: 836/530, loss: 0.0205248836427927
2023-01-21 09:54:20.440441: step: 840/530, loss: 0.043944455683231354
2023-01-21 09:54:21.534488: step: 844/530, loss: 0.09574851393699646
2023-01-21 09:54:22.660028: step: 848/530, loss: 0.2966393530368805
2023-01-21 09:54:23.754432: step: 852/530, loss: 0.2695699632167816
2023-01-21 09:54:24.883268: step: 856/530, loss: 0.3184199929237366
2023-01-21 09:54:26.021484: step: 860/530, loss: 0.06449492275714874
2023-01-21 09:54:27.126839: step: 864/530, loss: 0.06269311904907227
2023-01-21 09:54:28.235193: step: 868/530, loss: 0.03121483325958252
2023-01-21 09:54:29.370968: step: 872/530, loss: 0.20634803175926208
2023-01-21 09:54:30.463275: step: 876/530, loss: 0.05591907724738121
2023-01-21 09:54:31.560691: step: 880/530, loss: 0.28548121452331543
2023-01-21 09:54:32.667130: step: 884/530, loss: 0.022234417498111725
2023-01-21 09:54:33.765629: step: 888/530, loss: 0.05248622968792915
2023-01-21 09:54:34.883493: step: 892/530, loss: 0.061526820063591
2023-01-21 09:54:35.976429: step: 896/530, loss: 0.0672922134399414
2023-01-21 09:54:37.071752: step: 900/530, loss: 0.141584113240242
2023-01-21 09:54:38.178673: step: 904/530, loss: 0.02793598175048828
2023-01-21 09:54:39.319495: step: 908/530, loss: 0.06663131713867188
2023-01-21 09:54:40.454450: step: 912/530, loss: 0.03127555921673775
2023-01-21 09:54:41.571043: step: 916/530, loss: 0.01583700068295002
2023-01-21 09:54:42.679559: step: 920/530, loss: 0.68163001537323
2023-01-21 09:54:43.760744: step: 924/530, loss: 0.286430686712265
2023-01-21 09:54:44.895102: step: 928/530, loss: 0.06524877995252609
2023-01-21 09:54:46.030601: step: 932/530, loss: 0.7543874979019165
2023-01-21 09:54:47.131155: step: 936/530, loss: 0.1091286689043045
2023-01-21 09:54:48.251091: step: 940/530, loss: 0.3756675720214844
2023-01-21 09:54:49.316673: step: 944/530, loss: 0.29725971817970276
2023-01-21 09:54:50.444625: step: 948/530, loss: 0.15286321938037872
2023-01-21 09:54:51.584732: step: 952/530, loss: 0.30158179998397827
2023-01-21 09:54:52.667761: step: 956/530, loss: 0.08971910178661346
2023-01-21 09:54:53.773758: step: 960/530, loss: 0.11688976734876633
2023-01-21 09:54:54.890030: step: 964/530, loss: 0.09793853759765625
2023-01-21 09:54:56.028555: step: 968/530, loss: 0.08934803307056427
2023-01-21 09:54:57.141657: step: 972/530, loss: 0.030006790533661842
2023-01-21 09:54:58.262221: step: 976/530, loss: 0.10294562578201294
2023-01-21 09:54:59.380801: step: 980/530, loss: 0.20548266172409058
2023-01-21 09:55:00.491661: step: 984/530, loss: 0.10347537696361542
2023-01-21 09:55:01.585809: step: 988/530, loss: 0.017511939629912376
2023-01-21 09:55:02.679401: step: 992/530, loss: 0.06988143920898438
2023-01-21 09:55:03.804273: step: 996/530, loss: 0.1110302284359932
2023-01-21 09:55:04.894514: step: 1000/530, loss: 0.2685500979423523
2023-01-21 09:55:06.014644: step: 1004/530, loss: 0.18499363958835602
2023-01-21 09:55:07.130177: step: 1008/530, loss: 0.14757689833641052
2023-01-21 09:55:08.245054: step: 1012/530, loss: 0.1732262670993805
2023-01-21 09:55:09.364608: step: 1016/530, loss: 0.17172592878341675
2023-01-21 09:55:10.510740: step: 1020/530, loss: 0.2440611720085144
2023-01-21 09:55:11.625598: step: 1024/530, loss: 0.06054963916540146
2023-01-21 09:55:12.750315: step: 1028/530, loss: 0.27140820026397705
2023-01-21 09:55:13.857169: step: 1032/530, loss: 0.030099868774414062
2023-01-21 09:55:14.962358: step: 1036/530, loss: 0.0944155678153038
2023-01-21 09:55:16.056733: step: 1040/530, loss: 0.18252907693386078
2023-01-21 09:55:17.173030: step: 1044/530, loss: 0.03584995120763779
2023-01-21 09:55:18.294366: step: 1048/530, loss: 0.020482826977968216
2023-01-21 09:55:19.416857: step: 1052/530, loss: 0.02874126471579075
2023-01-21 09:55:20.538681: step: 1056/530, loss: 0.23768381774425507
2023-01-21 09:55:21.696200: step: 1060/530, loss: 0.04036913067102432
2023-01-21 09:55:22.825069: step: 1064/530, loss: 0.3108413815498352
2023-01-21 09:55:23.914648: step: 1068/530, loss: 0.18419581651687622
2023-01-21 09:55:25.047346: step: 1072/530, loss: 0.07675810158252716
2023-01-21 09:55:26.190622: step: 1076/530, loss: 0.15113386511802673
2023-01-21 09:55:27.295494: step: 1080/530, loss: 0.13857269287109375
2023-01-21 09:55:28.451264: step: 1084/530, loss: 0.1990751326084137
2023-01-21 09:55:29.570666: step: 1088/530, loss: 0.0037929534446448088
2023-01-21 09:55:30.699209: step: 1092/530, loss: 0.05229482799768448
2023-01-21 09:55:31.823331: step: 1096/530, loss: 0.11247846484184265
2023-01-21 09:55:32.926937: step: 1100/530, loss: 0.4745456278324127
2023-01-21 09:55:34.026111: step: 1104/530, loss: 0.208216592669487
2023-01-21 09:55:35.129555: step: 1108/530, loss: 0.020977400243282318
2023-01-21 09:55:36.253853: step: 1112/530, loss: 0.036166951060295105
2023-01-21 09:55:37.374956: step: 1116/530, loss: 0.11842823028564453
2023-01-21 09:55:38.513669: step: 1120/530, loss: 0.2346639633178711
2023-01-21 09:55:39.621121: step: 1124/530, loss: 0.06267013400793076
2023-01-21 09:55:40.733380: step: 1128/530, loss: 0.15819235146045685
2023-01-21 09:55:41.832653: step: 1132/530, loss: 0.031134678050875664
2023-01-21 09:55:42.942194: step: 1136/530, loss: 0.03771810606122017
2023-01-21 09:55:44.057845: step: 1140/530, loss: 0.04745866358280182
2023-01-21 09:55:45.161326: step: 1144/530, loss: 0.09044208377599716
2023-01-21 09:55:46.293090: step: 1148/530, loss: 0.11263179779052734
2023-01-21 09:55:47.393012: step: 1152/530, loss: 0.07385406643152237
2023-01-21 09:55:48.497422: step: 1156/530, loss: 0.013094283640384674
2023-01-21 09:55:49.593458: step: 1160/530, loss: 0.02526116371154785
2023-01-21 09:55:50.707521: step: 1164/530, loss: 0.09832410514354706
2023-01-21 09:55:51.829742: step: 1168/530, loss: 0.07032763957977295
2023-01-21 09:55:52.942940: step: 1172/530, loss: 0.02007446251809597
2023-01-21 09:55:54.083229: step: 1176/530, loss: 0.0767943412065506
2023-01-21 09:55:55.233015: step: 1180/530, loss: 0.006288337521255016
2023-01-21 09:55:56.384446: step: 1184/530, loss: 0.040837861597537994
2023-01-21 09:55:57.524448: step: 1188/530, loss: 0.03742246702313423
2023-01-21 09:55:58.632621: step: 1192/530, loss: 0.1444648802280426
2023-01-21 09:55:59.718977: step: 1196/530, loss: 0.019832324236631393
2023-01-21 09:56:00.839591: step: 1200/530, loss: 0.016106033697724342
2023-01-21 09:56:01.973819: step: 1204/530, loss: 0.12079861760139465
2023-01-21 09:56:03.092160: step: 1208/530, loss: 0.08075639605522156
2023-01-21 09:56:04.227095: step: 1212/530, loss: 0.09436998516321182
2023-01-21 09:56:05.331900: step: 1216/530, loss: 0.08193521201610565
2023-01-21 09:56:06.425788: step: 1220/530, loss: 0.024799633771181107
2023-01-21 09:56:07.548662: step: 1224/530, loss: 0.33790645003318787
2023-01-21 09:56:08.652084: step: 1228/530, loss: 0.020997188985347748
2023-01-21 09:56:09.775773: step: 1232/530, loss: 0.0569583922624588
2023-01-21 09:56:10.889132: step: 1236/530, loss: 0.14552536606788635
2023-01-21 09:56:12.003738: step: 1240/530, loss: 0.112663134932518
2023-01-21 09:56:13.124068: step: 1244/530, loss: 0.10771408677101135
2023-01-21 09:56:14.202121: step: 1248/530, loss: 0.2917008101940155
2023-01-21 09:56:15.338608: step: 1252/530, loss: 0.024138927459716797
2023-01-21 09:56:16.433423: step: 1256/530, loss: 0.07604708522558212
2023-01-21 09:56:17.528067: step: 1260/530, loss: 0.10218968987464905
2023-01-21 09:56:18.653209: step: 1264/530, loss: 0.1727636605501175
2023-01-21 09:56:19.756397: step: 1268/530, loss: 0.08448926359415054
2023-01-21 09:56:20.873616: step: 1272/530, loss: 0.1318327635526657
2023-01-21 09:56:21.966228: step: 1276/530, loss: 0.001016855239868164
2023-01-21 09:56:23.066281: step: 1280/530, loss: 0.041588593274354935
2023-01-21 09:56:24.153457: step: 1284/530, loss: 0.06368903815746307
2023-01-21 09:56:25.263741: step: 1288/530, loss: 0.02614569664001465
2023-01-21 09:56:26.366703: step: 1292/530, loss: 0.12808971107006073
2023-01-21 09:56:27.481420: step: 1296/530, loss: 0.15766791999340057
2023-01-21 09:56:28.601716: step: 1300/530, loss: 0.3422592282295227
2023-01-21 09:56:29.718764: step: 1304/530, loss: 0.11430913209915161
2023-01-21 09:56:30.811036: step: 1308/530, loss: 0.18840666115283966
2023-01-21 09:56:31.908433: step: 1312/530, loss: 0.017795372754335403
2023-01-21 09:56:33.048538: step: 1316/530, loss: 0.049549005925655365
2023-01-21 09:56:34.171569: step: 1320/530, loss: 0.2594464421272278
2023-01-21 09:56:35.292228: step: 1324/530, loss: 0.3087472915649414
2023-01-21 09:56:36.407496: step: 1328/530, loss: 0.009452497586607933
2023-01-21 09:56:37.536920: step: 1332/530, loss: 0.09292864799499512
2023-01-21 09:56:38.665954: step: 1336/530, loss: 0.1023896262049675
2023-01-21 09:56:39.789938: step: 1340/530, loss: 0.11262637376785278
2023-01-21 09:56:40.893475: step: 1344/530, loss: 0.10290107876062393
2023-01-21 09:56:42.020643: step: 1348/530, loss: 0.019435930997133255
2023-01-21 09:56:43.144746: step: 1352/530, loss: 0.007319331169128418
2023-01-21 09:56:44.275573: step: 1356/530, loss: 0.10708752274513245
2023-01-21 09:56:45.380473: step: 1360/530, loss: 0.13009414076805115
2023-01-21 09:56:46.470337: step: 1364/530, loss: 0.025205519050359726
2023-01-21 09:56:47.609577: step: 1368/530, loss: 0.0754825621843338
2023-01-21 09:56:48.715880: step: 1372/530, loss: 0.11432480812072754
2023-01-21 09:56:49.809716: step: 1376/530, loss: 0.05013017728924751
2023-01-21 09:56:50.926347: step: 1380/530, loss: 0.004275331273674965
2023-01-21 09:56:52.025586: step: 1384/530, loss: 0.7562000155448914
2023-01-21 09:56:53.156577: step: 1388/530, loss: 0.03598523139953613
2023-01-21 09:56:54.265638: step: 1392/530, loss: 0.20649272203445435
2023-01-21 09:56:55.365605: step: 1396/530, loss: 0.25895899534225464
2023-01-21 09:56:56.463756: step: 1400/530, loss: 0.13337011635303497
2023-01-21 09:56:57.588642: step: 1404/530, loss: 0.041832830756902695
2023-01-21 09:56:58.725364: step: 1408/530, loss: 0.05252399295568466
2023-01-21 09:56:59.855090: step: 1412/530, loss: 0.39361023902893066
2023-01-21 09:57:00.968572: step: 1416/530, loss: 0.17604151368141174
2023-01-21 09:57:02.068761: step: 1420/530, loss: 0.015737246721982956
2023-01-21 09:57:03.190841: step: 1424/530, loss: 0.10950168967247009
2023-01-21 09:57:04.320732: step: 1428/530, loss: 0.014858150854706764
2023-01-21 09:57:05.402952: step: 1432/530, loss: 0.02591390535235405
2023-01-21 09:57:06.518189: step: 1436/530, loss: 0.08015008270740509
2023-01-21 09:57:07.631926: step: 1440/530, loss: 0.07703669369220734
2023-01-21 09:57:08.773191: step: 1444/530, loss: 0.048880863934755325
2023-01-21 09:57:09.867776: step: 1448/530, loss: 0.07770642638206482
2023-01-21 09:57:10.985871: step: 1452/530, loss: 0.03424430266022682
2023-01-21 09:57:12.074824: step: 1456/530, loss: 0.013797139748930931
2023-01-21 09:57:13.219390: step: 1460/530, loss: 0.11644693464040756
2023-01-21 09:57:14.326380: step: 1464/530, loss: 0.028011895716190338
2023-01-21 09:57:15.423407: step: 1468/530, loss: 0.04797234386205673
2023-01-21 09:57:16.535967: step: 1472/530, loss: 0.11523942649364471
2023-01-21 09:57:17.685912: step: 1476/530, loss: 0.09139986336231232
2023-01-21 09:57:18.808169: step: 1480/530, loss: 0.20309686660766602
2023-01-21 09:57:19.928413: step: 1484/530, loss: 0.023095274344086647
2023-01-21 09:57:21.019002: step: 1488/530, loss: 0.047832585871219635
2023-01-21 09:57:22.139417: step: 1492/530, loss: 0.12425823509693146
2023-01-21 09:57:23.249747: step: 1496/530, loss: 0.010180855169892311
2023-01-21 09:57:24.353805: step: 1500/530, loss: 0.07949332892894745
2023-01-21 09:57:25.480088: step: 1504/530, loss: 0.04498882219195366
2023-01-21 09:57:26.661583: step: 1508/530, loss: 0.13184386491775513
2023-01-21 09:57:27.777467: step: 1512/530, loss: 0.09427204728126526
2023-01-21 09:57:28.899314: step: 1516/530, loss: 0.25841933488845825
2023-01-21 09:57:30.004423: step: 1520/530, loss: 0.016600705683231354
2023-01-21 09:57:31.158202: step: 1524/530, loss: 0.3405153453350067
2023-01-21 09:57:32.265292: step: 1528/530, loss: 0.06438972055912018
2023-01-21 09:57:33.375137: step: 1532/530, loss: 0.4356212615966797
2023-01-21 09:57:34.466771: step: 1536/530, loss: 0.5848147869110107
2023-01-21 09:57:35.559630: step: 1540/530, loss: 0.05305233225226402
2023-01-21 09:57:36.682757: step: 1544/530, loss: 0.043853759765625
2023-01-21 09:57:37.805772: step: 1548/530, loss: 0.08651427924633026
2023-01-21 09:57:38.894048: step: 1552/530, loss: 0.05195026472210884
2023-01-21 09:57:39.981240: step: 1556/530, loss: 0.3971121907234192
2023-01-21 09:57:41.093433: step: 1560/530, loss: 0.02738790586590767
2023-01-21 09:57:42.185742: step: 1564/530, loss: 0.05520348623394966
2023-01-21 09:57:43.296732: step: 1568/530, loss: 0.03425588458776474
2023-01-21 09:57:44.409346: step: 1572/530, loss: 0.008135700598359108
2023-01-21 09:57:45.504106: step: 1576/530, loss: 0.06154661253094673
2023-01-21 09:57:46.600452: step: 1580/530, loss: 0.09872995316982269
2023-01-21 09:57:47.740387: step: 1584/530, loss: 0.041140079498291016
2023-01-21 09:57:48.841097: step: 1588/530, loss: 0.19032764434814453
2023-01-21 09:57:49.964209: step: 1592/530, loss: 0.19962787628173828
2023-01-21 09:57:51.081099: step: 1596/530, loss: 0.09546937793493271
2023-01-21 09:57:52.218133: step: 1600/530, loss: 0.2381877899169922
2023-01-21 09:57:53.331167: step: 1604/530, loss: 0.04606493562459946
2023-01-21 09:57:54.452920: step: 1608/530, loss: 0.02561226114630699
2023-01-21 09:57:55.589498: step: 1612/530, loss: 0.04352283477783203
2023-01-21 09:57:56.740251: step: 1616/530, loss: 0.04283123090863228
2023-01-21 09:57:57.837223: step: 1620/530, loss: 0.09044961631298065
2023-01-21 09:57:58.940884: step: 1624/530, loss: 0.3653440475463867
2023-01-21 09:58:00.051832: step: 1628/530, loss: 0.06839476525783539
2023-01-21 09:58:01.147375: step: 1632/530, loss: 0.11999340355396271
2023-01-21 09:58:02.260367: step: 1636/530, loss: 0.032875727862119675
2023-01-21 09:58:03.350271: step: 1640/530, loss: 0.003103208728134632
2023-01-21 09:58:04.443152: step: 1644/530, loss: 0.02510986290872097
2023-01-21 09:58:05.567620: step: 1648/530, loss: 0.12627089023590088
2023-01-21 09:58:06.660126: step: 1652/530, loss: 0.11043024063110352
2023-01-21 09:58:07.777505: step: 1656/530, loss: 0.13902896642684937
2023-01-21 09:58:08.896005: step: 1660/530, loss: 0.19835329055786133
2023-01-21 09:58:09.990346: step: 1664/530, loss: 0.03847789764404297
2023-01-21 09:58:11.132990: step: 1668/530, loss: 0.03056039661169052
2023-01-21 09:58:12.256972: step: 1672/530, loss: 0.09128780663013458
2023-01-21 09:58:13.361485: step: 1676/530, loss: 0.0858302116394043
2023-01-21 09:58:14.490767: step: 1680/530, loss: 0.05166025459766388
2023-01-21 09:58:15.581219: step: 1684/530, loss: 0.1438257098197937
2023-01-21 09:58:16.660193: step: 1688/530, loss: 0.08575949817895889
2023-01-21 09:58:17.767511: step: 1692/530, loss: 0.04448442533612251
2023-01-21 09:58:18.917213: step: 1696/530, loss: 0.18154920637607574
2023-01-21 09:58:20.053844: step: 1700/530, loss: 0.0976356565952301
2023-01-21 09:58:21.184933: step: 1704/530, loss: 0.05647869035601616
2023-01-21 09:58:22.310883: step: 1708/530, loss: 0.04309835657477379
2023-01-21 09:58:23.411429: step: 1712/530, loss: 0.05801697075366974
2023-01-21 09:58:24.538235: step: 1716/530, loss: 0.10517054051160812
2023-01-21 09:58:25.660343: step: 1720/530, loss: 0.2723715901374817
2023-01-21 09:58:26.772746: step: 1724/530, loss: 0.09426664561033249
2023-01-21 09:58:27.902538: step: 1728/530, loss: 0.04462461173534393
2023-01-21 09:58:29.039660: step: 1732/530, loss: 0.0062088011763989925
2023-01-21 09:58:30.160498: step: 1736/530, loss: 0.1060112938284874
2023-01-21 09:58:31.259416: step: 1740/530, loss: 0.11627226322889328
2023-01-21 09:58:32.412206: step: 1744/530, loss: 0.09621060639619827
2023-01-21 09:58:33.513876: step: 1748/530, loss: 0.0415617935359478
2023-01-21 09:58:34.633112: step: 1752/530, loss: 0.4230268597602844
2023-01-21 09:58:35.731144: step: 1756/530, loss: 0.10484369099140167
2023-01-21 09:58:36.857723: step: 1760/530, loss: 0.07949161529541016
2023-01-21 09:58:37.984019: step: 1764/530, loss: 0.02367372438311577
2023-01-21 09:58:39.077420: step: 1768/530, loss: 0.26504725217819214
2023-01-21 09:58:40.220363: step: 1772/530, loss: 0.07104086875915527
2023-01-21 09:58:41.335211: step: 1776/530, loss: 0.448211669921875
2023-01-21 09:58:42.441894: step: 1780/530, loss: 0.07855415344238281
2023-01-21 09:58:43.571783: step: 1784/530, loss: 0.02541036531329155
2023-01-21 09:58:44.678972: step: 1788/530, loss: 0.04402752220630646
2023-01-21 09:58:45.815463: step: 1792/530, loss: 0.15280112624168396
2023-01-21 09:58:46.914631: step: 1796/530, loss: 0.08956728130578995
2023-01-21 09:58:48.023605: step: 1800/530, loss: 0.058026693761348724
2023-01-21 09:58:49.133337: step: 1804/530, loss: 0.19854618608951569
2023-01-21 09:58:50.237262: step: 1808/530, loss: 0.09756460785865784
2023-01-21 09:58:51.358223: step: 1812/530, loss: 0.07738981395959854
2023-01-21 09:58:52.449756: step: 1816/530, loss: 0.08537044376134872
2023-01-21 09:58:53.573159: step: 1820/530, loss: 0.043403055518865585
2023-01-21 09:58:54.695819: step: 1824/530, loss: 0.07844428718090057
2023-01-21 09:58:55.801173: step: 1828/530, loss: 0.05578174442052841
2023-01-21 09:58:56.893059: step: 1832/530, loss: 0.04719729721546173
2023-01-21 09:58:58.004085: step: 1836/530, loss: 0.0529266856610775
2023-01-21 09:58:59.117279: step: 1840/530, loss: 0.1260140985250473
2023-01-21 09:59:00.212319: step: 1844/530, loss: 0.8309139609336853
2023-01-21 09:59:01.331913: step: 1848/530, loss: 0.04821648821234703
2023-01-21 09:59:02.434760: step: 1852/530, loss: 0.050139714032411575
2023-01-21 09:59:03.576292: step: 1856/530, loss: 1.1567267179489136
2023-01-21 09:59:04.676844: step: 1860/530, loss: 0.07785234600305557
2023-01-21 09:59:05.788653: step: 1864/530, loss: 0.1178131103515625
2023-01-21 09:59:06.886505: step: 1868/530, loss: 0.12339244037866592
2023-01-21 09:59:08.015593: step: 1872/530, loss: 0.02334156073629856
2023-01-21 09:59:09.111806: step: 1876/530, loss: 0.015031909570097923
2023-01-21 09:59:10.259438: step: 1880/530, loss: 0.08797606825828552
2023-01-21 09:59:11.364206: step: 1884/530, loss: 0.2171286642551422
2023-01-21 09:59:12.481577: step: 1888/530, loss: 0.1767236739397049
2023-01-21 09:59:13.614067: step: 1892/530, loss: 0.0138886459171772
2023-01-21 09:59:14.747500: step: 1896/530, loss: 0.0973726287484169
2023-01-21 09:59:15.854108: step: 1900/530, loss: 0.17795081436634064
2023-01-21 09:59:16.963491: step: 1904/530, loss: 0.05171241983771324
2023-01-21 09:59:18.081324: step: 1908/530, loss: 0.7198076248168945
2023-01-21 09:59:19.196171: step: 1912/530, loss: 0.17739595472812653
2023-01-21 09:59:20.280150: step: 1916/530, loss: 0.02943793497979641
2023-01-21 09:59:21.373934: step: 1920/530, loss: 0.2069990038871765
2023-01-21 09:59:22.495767: step: 1924/530, loss: 0.0882083922624588
2023-01-21 09:59:23.600190: step: 1928/530, loss: 0.08206605166196823
2023-01-21 09:59:24.688785: step: 1932/530, loss: 0.05120064318180084
2023-01-21 09:59:25.810860: step: 1936/530, loss: 0.03551230579614639
2023-01-21 09:59:26.944990: step: 1940/530, loss: 0.056046012789011
2023-01-21 09:59:28.078640: step: 1944/530, loss: 0.05531826242804527
2023-01-21 09:59:29.206651: step: 1948/530, loss: 0.06365184485912323
2023-01-21 09:59:30.323222: step: 1952/530, loss: 0.052738189697265625
2023-01-21 09:59:31.458332: step: 1956/530, loss: 0.10266587883234024
2023-01-21 09:59:32.582918: step: 1960/530, loss: 0.05148601531982422
2023-01-21 09:59:33.740195: step: 1964/530, loss: 0.06124544143676758
2023-01-21 09:59:34.832465: step: 1968/530, loss: 0.08662159740924835
2023-01-21 09:59:35.928728: step: 1972/530, loss: 0.250003457069397
2023-01-21 09:59:37.018013: step: 1976/530, loss: 0.05090451240539551
2023-01-21 09:59:38.128376: step: 1980/530, loss: 0.07934533059597015
2023-01-21 09:59:39.244225: step: 1984/530, loss: 0.03718538209795952
2023-01-21 09:59:40.352808: step: 1988/530, loss: 0.11307653784751892
2023-01-21 09:59:41.469168: step: 1992/530, loss: 0.20911788940429688
2023-01-21 09:59:42.583696: step: 1996/530, loss: 0.10670796036720276
2023-01-21 09:59:43.708294: step: 2000/530, loss: 0.26739901304244995
2023-01-21 09:59:44.805770: step: 2004/530, loss: 0.17810669541358948
2023-01-21 09:59:45.916764: step: 2008/530, loss: 0.10456585884094238
2023-01-21 09:59:47.007224: step: 2012/530, loss: 0.8838997483253479
2023-01-21 09:59:48.146826: step: 2016/530, loss: 0.05686221271753311
2023-01-21 09:59:49.264055: step: 2020/530, loss: 0.0570995919406414
2023-01-21 09:59:50.344797: step: 2024/530, loss: 0.0025862932670861483
2023-01-21 09:59:51.442804: step: 2028/530, loss: 0.10257511585950851
2023-01-21 09:59:52.573000: step: 2032/530, loss: 0.039492033421993256
2023-01-21 09:59:53.667775: step: 2036/530, loss: 0.10757027566432953
2023-01-21 09:59:54.753508: step: 2040/530, loss: 0.05171528086066246
2023-01-21 09:59:55.842083: step: 2044/530, loss: 0.05016450956463814
2023-01-21 09:59:56.965962: step: 2048/530, loss: 0.18939208984375
2023-01-21 09:59:58.102087: step: 2052/530, loss: 0.04572296142578125
2023-01-21 09:59:59.233825: step: 2056/530, loss: 0.14915475249290466
2023-01-21 10:00:00.381303: step: 2060/530, loss: 0.009793151170015335
2023-01-21 10:00:01.515428: step: 2064/530, loss: 0.11170235276222229
2023-01-21 10:00:02.638792: step: 2068/530, loss: 0.15630798041820526
2023-01-21 10:00:03.775566: step: 2072/530, loss: 0.05971813201904297
2023-01-21 10:00:04.871265: step: 2076/530, loss: 0.0030181407928466797
2023-01-21 10:00:05.960151: step: 2080/530, loss: 0.04723968729376793
2023-01-21 10:00:07.064472: step: 2084/530, loss: 0.2330244928598404
2023-01-21 10:00:08.187924: step: 2088/530, loss: 0.019307708367705345
2023-01-21 10:00:09.296526: step: 2092/530, loss: 0.06296195834875107
2023-01-21 10:00:10.419776: step: 2096/530, loss: 0.03877994418144226
2023-01-21 10:00:11.514099: step: 2100/530, loss: 0.011324882507324219
2023-01-21 10:00:12.615485: step: 2104/530, loss: 0.04982485994696617
2023-01-21 10:00:13.731043: step: 2108/530, loss: 0.07450399547815323
2023-01-21 10:00:14.848363: step: 2112/530, loss: 0.2574615478515625
2023-01-21 10:00:15.945756: step: 2116/530, loss: 0.08460921794176102
2023-01-21 10:00:17.078098: step: 2120/530, loss: 0.09280509501695633
==================================================
Loss: 0.124
--------------------
Dev: {'event': {'p': 0.597444089456869, 'r': 0.7470039946737683, 'f1': 0.663905325443787}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Test: {'event': {'p': 0.6259716506630086, 'r': 0.7977855477855478, 'f1': 0.7015116576992056}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Chinese: {'event': {'p': 0.647887323943662, 'r': 0.8518518518518519, 'f1': 0.7360000000000001}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Korean: {'event': {'p': 0.6296296296296297, 'r': 0.5396825396825397, 'f1': 0.5811965811965812}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Russian: {'event': {'p': 0.5405405405405406, 'r': 0.5555555555555556, 'f1': 0.547945205479452}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5708622398414271, 'r': 0.7669773635153129, 'f1': 0.6545454545454545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Chinese: {'event': {'p': 0.6044052863436123, 'r': 0.7995337995337995, 'f1': 0.6884094330155545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Chinese: {'event': {'p': 0.6578947368421053, 'r': 0.9259259259259259, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6466512702078522, 'r': 0.7456724367509987, 'f1': 0.6926406926406927}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.6762148337595908, 'r': 0.7703962703962703, 'f1': 0.7202397166984473}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.597444089456869, 'r': 0.7470039946737683, 'f1': 0.663905325443787}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.6259716506630086, 'r': 0.7977855477855478, 'f1': 0.7015116576992056}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.5405405405405406, 'r': 0.5555555555555556, 'f1': 0.547945205479452}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 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 10:01:02.487811: step: 4/530, loss: 0.059467434883117676
2023-01-21 10:01:03.588852: step: 8/530, loss: 0.06741628795862198
2023-01-21 10:01:04.720188: step: 12/530, loss: 0.0014163493178784847
2023-01-21 10:01:05.838698: step: 16/530, loss: 0.02273840829730034
2023-01-21 10:01:06.938257: step: 20/530, loss: 0.47662153840065
2023-01-21 10:01:08.027297: step: 24/530, loss: 0.3686390817165375
2023-01-21 10:01:09.132733: step: 28/530, loss: 0.013661528006196022
2023-01-21 10:01:10.248225: step: 32/530, loss: 0.10623379051685333
2023-01-21 10:01:11.361187: step: 36/530, loss: 0.039480164647102356
2023-01-21 10:01:12.477862: step: 40/530, loss: 0.055282022804021835
2023-01-21 10:01:13.587875: step: 44/530, loss: 0.04666290432214737
2023-01-21 10:01:14.705634: step: 48/530, loss: 0.09851551055908203
2023-01-21 10:01:15.815717: step: 52/530, loss: 0.0577126070857048
2023-01-21 10:01:16.920526: step: 56/530, loss: 0.043779850006103516
2023-01-21 10:01:18.028150: step: 60/530, loss: 0.03413849323987961
2023-01-21 10:01:19.104927: step: 64/530, loss: 0.00702934293076396
2023-01-21 10:01:20.211114: step: 68/530, loss: 0.22127565741539001
2023-01-21 10:01:21.387347: step: 72/530, loss: 0.1151500791311264
2023-01-21 10:01:22.505398: step: 76/530, loss: 0.07048015296459198
2023-01-21 10:01:23.642297: step: 80/530, loss: 0.316898912191391
2023-01-21 10:01:24.756893: step: 84/530, loss: 0.024481534957885742
2023-01-21 10:01:25.847098: step: 88/530, loss: 0.023911286145448685
2023-01-21 10:01:26.933300: step: 92/530, loss: 0.12105751037597656
2023-01-21 10:01:28.099157: step: 96/530, loss: 0.1114223450422287
2023-01-21 10:01:29.195665: step: 100/530, loss: 0.042087603360414505
2023-01-21 10:01:30.306141: step: 104/530, loss: 0.03492593765258789
2023-01-21 10:01:31.409283: step: 108/530, loss: 0.034452442079782486
2023-01-21 10:01:32.526887: step: 112/530, loss: 0.14111891388893127
2023-01-21 10:01:33.644270: step: 116/530, loss: 0.030294323340058327
2023-01-21 10:01:34.751207: step: 120/530, loss: 0.030425071716308594
2023-01-21 10:01:35.860302: step: 124/530, loss: 0.9508135914802551
2023-01-21 10:01:36.968762: step: 128/530, loss: 0.04664049297571182
2023-01-21 10:01:38.119128: step: 132/530, loss: 0.08364172279834747
2023-01-21 10:01:39.215072: step: 136/530, loss: 0.04367566108703613
2023-01-21 10:01:40.312713: step: 140/530, loss: 0.017160963267087936
2023-01-21 10:01:41.415488: step: 144/530, loss: 0.06891441345214844
2023-01-21 10:01:42.520256: step: 148/530, loss: 0.025079965591430664
2023-01-21 10:01:43.657384: step: 152/530, loss: 0.35502633452415466
2023-01-21 10:01:44.754172: step: 156/530, loss: 0.05305905640125275
2023-01-21 10:01:45.869588: step: 160/530, loss: 0.0020322322379797697
2023-01-21 10:01:46.982988: step: 164/530, loss: 0.16181202232837677
2023-01-21 10:01:48.118222: step: 168/530, loss: 0.11331701278686523
2023-01-21 10:01:49.237740: step: 172/530, loss: 0.06443872302770615
2023-01-21 10:01:50.368420: step: 176/530, loss: 0.053949929773807526
2023-01-21 10:01:51.485008: step: 180/530, loss: 0.06950082629919052
2023-01-21 10:01:52.570031: step: 184/530, loss: 0.07468695938587189
2023-01-21 10:01:53.664242: step: 188/530, loss: 0.01081763580441475
2023-01-21 10:01:54.805941: step: 192/530, loss: 0.02664036676287651
2023-01-21 10:01:55.928148: step: 196/530, loss: 0.1842426359653473
2023-01-21 10:01:57.040342: step: 200/530, loss: 0.0907268300652504
2023-01-21 10:01:58.164083: step: 204/530, loss: 0.07651004940271378
2023-01-21 10:01:59.306136: step: 208/530, loss: 0.09579391777515411
2023-01-21 10:02:00.460549: step: 212/530, loss: 0.12234792858362198
2023-01-21 10:02:01.571777: step: 216/530, loss: 0.47399863600730896
2023-01-21 10:02:02.686207: step: 220/530, loss: 0.10240379720926285
2023-01-21 10:02:03.831410: step: 224/530, loss: 0.14757832884788513
2023-01-21 10:02:04.933651: step: 228/530, loss: 0.02375030517578125
2023-01-21 10:02:06.029382: step: 232/530, loss: 0.06918277591466904
2023-01-21 10:02:07.127046: step: 236/530, loss: 0.12576523423194885
2023-01-21 10:02:08.231144: step: 240/530, loss: 0.03799863159656525
2023-01-21 10:02:09.324781: step: 244/530, loss: 0.044641874730587006
2023-01-21 10:02:10.429505: step: 248/530, loss: 0.12257039546966553
2023-01-21 10:02:11.541800: step: 252/530, loss: 0.10022592544555664
2023-01-21 10:02:12.650271: step: 256/530, loss: 0.0626247376203537
2023-01-21 10:02:13.781883: step: 260/530, loss: 0.0754152312874794
2023-01-21 10:02:14.919712: step: 264/530, loss: 0.0324527733027935
2023-01-21 10:02:16.027792: step: 268/530, loss: 0.07689706981182098
2023-01-21 10:02:17.153299: step: 272/530, loss: 0.2723402976989746
2023-01-21 10:02:18.280850: step: 276/530, loss: 0.03329487144947052
2023-01-21 10:02:19.399733: step: 280/530, loss: 0.10591153800487518
2023-01-21 10:02:20.493591: step: 284/530, loss: 0.1054508239030838
2023-01-21 10:02:21.565216: step: 288/530, loss: 0.09302883595228195
2023-01-21 10:02:22.685803: step: 292/530, loss: 0.4949951171875
2023-01-21 10:02:23.781946: step: 296/530, loss: 0.5504612922668457
2023-01-21 10:02:24.895594: step: 300/530, loss: 0.5561575889587402
2023-01-21 10:02:25.996222: step: 304/530, loss: 0.08872528374195099
2023-01-21 10:02:27.086417: step: 308/530, loss: 0.14894461631774902
2023-01-21 10:02:28.196026: step: 312/530, loss: 0.09469567239284515
2023-01-21 10:02:29.317461: step: 316/530, loss: 0.05680360645055771
2023-01-21 10:02:30.441010: step: 320/530, loss: 0.028053760528564453
2023-01-21 10:02:31.575904: step: 324/530, loss: 0.09207191318273544
2023-01-21 10:02:32.683739: step: 328/530, loss: 0.09661054611206055
2023-01-21 10:02:33.781367: step: 332/530, loss: 0.006581735797226429
2023-01-21 10:02:34.902117: step: 336/530, loss: 0.04672985151410103
2023-01-21 10:02:35.971110: step: 340/530, loss: 0.016573499888181686
2023-01-21 10:02:37.074456: step: 344/530, loss: 0.05010700225830078
2023-01-21 10:02:38.178875: step: 348/530, loss: 0.10732222348451614
2023-01-21 10:02:39.339663: step: 352/530, loss: 0.10449858009815216
2023-01-21 10:02:40.460212: step: 356/530, loss: 0.04569358751177788
2023-01-21 10:02:41.568615: step: 360/530, loss: 0.12227706611156464
2023-01-21 10:02:42.677754: step: 364/530, loss: 0.044361554086208344
2023-01-21 10:02:43.827189: step: 368/530, loss: 0.03411807864904404
2023-01-21 10:02:44.931919: step: 372/530, loss: 0.04581642523407936
2023-01-21 10:02:46.039100: step: 376/530, loss: 0.03163585811853409
2023-01-21 10:02:47.139965: step: 380/530, loss: 0.05841407924890518
2023-01-21 10:02:48.258497: step: 384/530, loss: 0.07240104675292969
2023-01-21 10:02:49.365630: step: 388/530, loss: 0.08861179649829865
2023-01-21 10:02:50.474822: step: 392/530, loss: 0.04914131388068199
2023-01-21 10:02:51.601985: step: 396/530, loss: 0.22335167229175568
2023-01-21 10:02:52.691260: step: 400/530, loss: 0.06992053985595703
2023-01-21 10:02:53.804561: step: 404/530, loss: 0.06421279907226562
2023-01-21 10:02:54.899088: step: 408/530, loss: 0.0355740562081337
2023-01-21 10:02:56.034657: step: 412/530, loss: 0.23547782003879547
2023-01-21 10:02:57.179031: step: 416/530, loss: 0.15474340319633484
2023-01-21 10:02:58.296975: step: 420/530, loss: 0.038662053644657135
2023-01-21 10:02:59.404083: step: 424/530, loss: 0.02536039426922798
2023-01-21 10:03:00.511380: step: 428/530, loss: 0.07532129436731339
2023-01-21 10:03:01.602396: step: 432/530, loss: 0.03606675565242767
2023-01-21 10:03:02.716608: step: 436/530, loss: 0.11642847955226898
2023-01-21 10:03:03.835241: step: 440/530, loss: 0.1911262571811676
2023-01-21 10:03:04.958755: step: 444/530, loss: 0.0046329498291015625
2023-01-21 10:03:06.055372: step: 448/530, loss: 0.051806069910526276
2023-01-21 10:03:07.133362: step: 452/530, loss: 0.011393642984330654
2023-01-21 10:03:08.264948: step: 456/530, loss: 0.05447092279791832
2023-01-21 10:03:09.348975: step: 460/530, loss: 0.03626156225800514
2023-01-21 10:03:10.430798: step: 464/530, loss: 0.28871044516563416
2023-01-21 10:03:11.544023: step: 468/530, loss: 0.1612241268157959
2023-01-21 10:03:12.662390: step: 472/530, loss: 0.03887691721320152
2023-01-21 10:03:13.781004: step: 476/530, loss: 0.03909111022949219
2023-01-21 10:03:14.889812: step: 480/530, loss: 0.020506085827946663
2023-01-21 10:03:16.002171: step: 484/530, loss: 0.1612153947353363
2023-01-21 10:03:17.144359: step: 488/530, loss: 0.5768324732780457
2023-01-21 10:03:18.259028: step: 492/530, loss: 0.04163913428783417
2023-01-21 10:03:19.367515: step: 496/530, loss: 0.05466318503022194
2023-01-21 10:03:20.512851: step: 500/530, loss: 0.01213769894093275
2023-01-21 10:03:21.612623: step: 504/530, loss: 0.03172314167022705
2023-01-21 10:03:22.746494: step: 508/530, loss: 0.14665278792381287
2023-01-21 10:03:23.908830: step: 512/530, loss: 0.18073701858520508
2023-01-21 10:03:25.024088: step: 516/530, loss: 0.03886318579316139
2023-01-21 10:03:26.134817: step: 520/530, loss: 0.10925635695457458
2023-01-21 10:03:27.234503: step: 524/530, loss: 0.5058422088623047
2023-01-21 10:03:28.332804: step: 528/530, loss: 0.04473733901977539
2023-01-21 10:03:29.443150: step: 532/530, loss: 0.07666053622961044
2023-01-21 10:03:30.530372: step: 536/530, loss: 0.05933942645788193
2023-01-21 10:03:31.697853: step: 540/530, loss: 0.073621466755867
2023-01-21 10:03:32.840882: step: 544/530, loss: 0.04668760299682617
2023-01-21 10:03:33.946351: step: 548/530, loss: 0.055408671498298645
2023-01-21 10:03:35.037654: step: 552/530, loss: 0.03224482387304306
2023-01-21 10:03:36.166389: step: 556/530, loss: 0.3635343611240387
2023-01-21 10:03:37.280206: step: 560/530, loss: 0.02834939956665039
2023-01-21 10:03:38.363311: step: 564/530, loss: 0.11555109173059464
2023-01-21 10:03:39.463266: step: 568/530, loss: 0.03168763965368271
2023-01-21 10:03:40.563064: step: 572/530, loss: 0.07923047244548798
2023-01-21 10:03:41.673667: step: 576/530, loss: 0.06916943192481995
2023-01-21 10:03:42.760533: step: 580/530, loss: 0.1113743782043457
2023-01-21 10:03:43.842329: step: 584/530, loss: 0.0602237693965435
2023-01-21 10:03:44.946119: step: 588/530, loss: 0.02346677891910076
2023-01-21 10:03:46.031910: step: 592/530, loss: 0.06817837059497833
2023-01-21 10:03:47.127866: step: 596/530, loss: 0.023755932226777077
2023-01-21 10:03:48.276388: step: 600/530, loss: 0.01371068973094225
2023-01-21 10:03:49.376321: step: 604/530, loss: 0.03939466178417206
2023-01-21 10:03:50.504833: step: 608/530, loss: 0.08455085754394531
2023-01-21 10:03:51.634917: step: 612/530, loss: 0.10320273041725159
2023-01-21 10:03:52.746299: step: 616/530, loss: 0.07854624092578888
2023-01-21 10:03:53.858083: step: 620/530, loss: 0.13549405336380005
2023-01-21 10:03:55.012258: step: 624/530, loss: 0.04325170814990997
2023-01-21 10:03:56.131006: step: 628/530, loss: 0.08605756610631943
2023-01-21 10:03:57.249443: step: 632/530, loss: 0.0449254997074604
2023-01-21 10:03:58.343384: step: 636/530, loss: 0.06233358383178711
2023-01-21 10:03:59.462572: step: 640/530, loss: 0.08319655060768127
2023-01-21 10:04:00.594239: step: 644/530, loss: 0.17743147909641266
2023-01-21 10:04:01.682334: step: 648/530, loss: 0.06862087547779083
2023-01-21 10:04:02.798429: step: 652/530, loss: 0.09276504814624786
2023-01-21 10:04:03.905300: step: 656/530, loss: 0.029688358306884766
2023-01-21 10:04:05.014332: step: 660/530, loss: 0.0371883399784565
2023-01-21 10:04:06.112685: step: 664/530, loss: 0.04769592732191086
2023-01-21 10:04:07.225424: step: 668/530, loss: 0.11620006710290909
2023-01-21 10:04:08.337378: step: 672/530, loss: 0.0788685604929924
2023-01-21 10:04:09.436078: step: 676/530, loss: 0.11887387931346893
2023-01-21 10:04:10.531109: step: 680/530, loss: 0.03980560600757599
2023-01-21 10:04:11.609840: step: 684/530, loss: 0.0112924100831151
2023-01-21 10:04:12.728071: step: 688/530, loss: 0.018542766571044922
2023-01-21 10:04:13.828155: step: 692/530, loss: 0.005323505494743586
2023-01-21 10:04:14.941815: step: 696/530, loss: 0.498462975025177
2023-01-21 10:04:16.038385: step: 700/530, loss: 0.2711736559867859
2023-01-21 10:04:17.145821: step: 704/530, loss: 0.03457784652709961
2023-01-21 10:04:18.248934: step: 708/530, loss: 0.03194618225097656
2023-01-21 10:04:19.344746: step: 712/530, loss: 0.06727543473243713
2023-01-21 10:04:20.453228: step: 716/530, loss: 0.02787027508020401
2023-01-21 10:04:21.565224: step: 720/530, loss: 0.10290078818798065
2023-01-21 10:04:22.664285: step: 724/530, loss: 0.0014772415161132812
2023-01-21 10:04:23.765503: step: 728/530, loss: 0.13221712410449982
2023-01-21 10:04:24.888930: step: 732/530, loss: 1.8202250003814697
2023-01-21 10:04:26.003244: step: 736/530, loss: 0.26255226135253906
2023-01-21 10:04:27.151094: step: 740/530, loss: 0.03638629987835884
2023-01-21 10:04:28.270100: step: 744/530, loss: 0.11133584380149841
2023-01-21 10:04:29.389104: step: 748/530, loss: 0.04976291581988335
2023-01-21 10:04:30.482542: step: 752/530, loss: 0.030758000910282135
2023-01-21 10:04:31.563539: step: 756/530, loss: 0.0846920982003212
2023-01-21 10:04:32.671683: step: 760/530, loss: 0.11802730709314346
2023-01-21 10:04:33.784831: step: 764/530, loss: 0.0611325278878212
2023-01-21 10:04:34.865266: step: 768/530, loss: 0.1037314385175705
2023-01-21 10:04:35.969215: step: 772/530, loss: 0.023491764441132545
2023-01-21 10:04:37.062809: step: 776/530, loss: 0.025437969714403152
2023-01-21 10:04:38.187816: step: 780/530, loss: 0.03173961490392685
2023-01-21 10:04:39.323118: step: 784/530, loss: 0.08323326706886292
2023-01-21 10:04:40.433624: step: 788/530, loss: 0.07005657255649567
2023-01-21 10:04:41.538907: step: 792/530, loss: 0.08603725582361221
2023-01-21 10:04:42.663265: step: 796/530, loss: 0.057090092450380325
2023-01-21 10:04:43.778202: step: 800/530, loss: 0.0837024673819542
2023-01-21 10:04:44.864356: step: 804/530, loss: 0.4514656960964203
2023-01-21 10:04:45.984633: step: 808/530, loss: 0.20156708359718323
2023-01-21 10:04:47.069535: step: 812/530, loss: 0.06731734424829483
2023-01-21 10:04:48.194566: step: 816/530, loss: 0.03028416633605957
2023-01-21 10:04:49.288462: step: 820/530, loss: 0.11520515382289886
2023-01-21 10:04:50.402027: step: 824/530, loss: 0.2195732146501541
2023-01-21 10:04:51.510794: step: 828/530, loss: 0.11928515881299973
2023-01-21 10:04:52.599495: step: 832/530, loss: 0.06800797581672668
2023-01-21 10:04:53.721687: step: 836/530, loss: 0.10840387642383575
2023-01-21 10:04:54.794910: step: 840/530, loss: 0.05319347232580185
2023-01-21 10:04:55.896019: step: 844/530, loss: 0.05626435577869415
2023-01-21 10:04:56.983146: step: 848/530, loss: 0.1913505494594574
2023-01-21 10:04:58.064708: step: 852/530, loss: 0.3311210870742798
2023-01-21 10:04:59.190245: step: 856/530, loss: 0.06856193393468857
2023-01-21 10:05:00.286753: step: 860/530, loss: 0.02766704559326172
2023-01-21 10:05:01.414495: step: 864/530, loss: 0.11915703117847443
2023-01-21 10:05:02.515045: step: 868/530, loss: 0.05146608501672745
2023-01-21 10:05:03.638346: step: 872/530, loss: 0.051688503473997116
2023-01-21 10:05:04.753510: step: 876/530, loss: 0.06542558968067169
2023-01-21 10:05:05.837858: step: 880/530, loss: 0.059754084795713425
2023-01-21 10:05:06.927192: step: 884/530, loss: 0.05255327373743057
2023-01-21 10:05:08.070365: step: 888/530, loss: 0.09187240898609161
2023-01-21 10:05:09.178433: step: 892/530, loss: 0.08481216430664062
2023-01-21 10:05:10.272205: step: 896/530, loss: 0.15302228927612305
2023-01-21 10:05:11.375909: step: 900/530, loss: 0.012938786298036575
2023-01-21 10:05:12.457453: step: 904/530, loss: 0.030353689566254616
2023-01-21 10:05:13.584251: step: 908/530, loss: 0.13592444360256195
2023-01-21 10:05:14.688440: step: 912/530, loss: 0.028123866766691208
2023-01-21 10:05:15.795138: step: 916/530, loss: 0.020467139780521393
2023-01-21 10:05:16.921705: step: 920/530, loss: 0.03194904327392578
2023-01-21 10:05:18.031824: step: 924/530, loss: 0.10587482899427414
2023-01-21 10:05:19.146068: step: 928/530, loss: 0.15732459723949432
2023-01-21 10:05:20.242467: step: 932/530, loss: 0.010158920660614967
2023-01-21 10:05:21.374290: step: 936/530, loss: 0.07161130756139755
2023-01-21 10:05:22.511396: step: 940/530, loss: 0.15675011277198792
2023-01-21 10:05:23.606540: step: 944/530, loss: 0.18385986983776093
2023-01-21 10:05:24.714858: step: 948/530, loss: 0.010151195339858532
2023-01-21 10:05:25.810634: step: 952/530, loss: 0.02192401885986328
2023-01-21 10:05:26.916956: step: 956/530, loss: 0.036783792078495026
2023-01-21 10:05:28.039666: step: 960/530, loss: 0.47565001249313354
2023-01-21 10:05:29.181688: step: 964/530, loss: 0.048403359949588776
2023-01-21 10:05:30.312387: step: 968/530, loss: 0.041521359235048294
2023-01-21 10:05:31.405542: step: 972/530, loss: 0.11711292713880539
2023-01-21 10:05:32.558866: step: 976/530, loss: 0.05844841152429581
2023-01-21 10:05:33.670970: step: 980/530, loss: 0.12454032897949219
2023-01-21 10:05:34.779626: step: 984/530, loss: 0.011598623357713223
2023-01-21 10:05:35.878306: step: 988/530, loss: 0.17863351106643677
2023-01-21 10:05:37.005289: step: 992/530, loss: 0.09128923714160919
2023-01-21 10:05:38.150607: step: 996/530, loss: 0.16409951448440552
2023-01-21 10:05:39.239188: step: 1000/530, loss: 0.11033916473388672
2023-01-21 10:05:40.366157: step: 1004/530, loss: 0.036875154823064804
2023-01-21 10:05:41.496546: step: 1008/530, loss: 0.05740871652960777
2023-01-21 10:05:42.600626: step: 1012/530, loss: 0.06920719146728516
2023-01-21 10:05:43.709512: step: 1016/530, loss: 0.025272943079471588
2023-01-21 10:05:44.828757: step: 1020/530, loss: 0.0780276358127594
2023-01-21 10:05:45.949507: step: 1024/530, loss: 0.04266996309161186
2023-01-21 10:05:47.043016: step: 1028/530, loss: 0.05045013129711151
2023-01-21 10:05:48.154988: step: 1032/530, loss: 0.12587542831897736
2023-01-21 10:05:49.243469: step: 1036/530, loss: 0.047800637781620026
2023-01-21 10:05:50.357274: step: 1040/530, loss: 0.05946522206068039
2023-01-21 10:05:51.483540: step: 1044/530, loss: 0.16668137907981873
2023-01-21 10:05:52.598198: step: 1048/530, loss: 0.06960468739271164
2023-01-21 10:05:53.703352: step: 1052/530, loss: 0.10762587189674377
2023-01-21 10:05:54.811810: step: 1056/530, loss: 0.08002634346485138
2023-01-21 10:05:55.934295: step: 1060/530, loss: 0.18244607746601105
2023-01-21 10:05:57.025373: step: 1064/530, loss: 0.014163590036332607
2023-01-21 10:05:58.154819: step: 1068/530, loss: 0.12196540832519531
2023-01-21 10:05:59.248685: step: 1072/530, loss: 0.33865004777908325
2023-01-21 10:06:00.369642: step: 1076/530, loss: 0.3974939286708832
2023-01-21 10:06:01.447073: step: 1080/530, loss: 0.08966927975416183
2023-01-21 10:06:02.560199: step: 1084/530, loss: 0.03089771419763565
2023-01-21 10:06:03.690105: step: 1088/530, loss: 0.008255625143647194
2023-01-21 10:06:04.798388: step: 1092/530, loss: 0.08978305011987686
2023-01-21 10:06:05.880286: step: 1096/530, loss: 0.06291027367115021
2023-01-21 10:06:06.984312: step: 1100/530, loss: 0.06971579045057297
2023-01-21 10:06:08.086117: step: 1104/530, loss: 0.053247857838869095
2023-01-21 10:06:09.178398: step: 1108/530, loss: 0.02231144905090332
2023-01-21 10:06:10.266600: step: 1112/530, loss: 0.06947823613882065
2023-01-21 10:06:11.393604: step: 1116/530, loss: 0.02197113074362278
2023-01-21 10:06:12.495396: step: 1120/530, loss: 0.08135108649730682
2023-01-21 10:06:13.609449: step: 1124/530, loss: 0.04469728469848633
2023-01-21 10:06:14.750677: step: 1128/530, loss: 0.03761877864599228
2023-01-21 10:06:15.849247: step: 1132/530, loss: 0.24308152496814728
2023-01-21 10:06:16.983817: step: 1136/530, loss: 0.13136939704418182
2023-01-21 10:06:18.089744: step: 1140/530, loss: 0.0869382917881012
2023-01-21 10:06:19.171254: step: 1144/530, loss: 1.1290096044540405
2023-01-21 10:06:20.271154: step: 1148/530, loss: 0.017607593908905983
2023-01-21 10:06:21.377864: step: 1152/530, loss: 0.05117073282599449
2023-01-21 10:06:22.479901: step: 1156/530, loss: 0.11772432178258896
2023-01-21 10:06:23.605618: step: 1160/530, loss: 0.011698246002197266
2023-01-21 10:06:24.726350: step: 1164/530, loss: 0.01843714714050293
2023-01-21 10:06:25.862186: step: 1168/530, loss: 0.02995162084698677
2023-01-21 10:06:26.963575: step: 1172/530, loss: 0.03150139003992081
2023-01-21 10:06:28.095886: step: 1176/530, loss: 0.11452217400074005
2023-01-21 10:06:29.182999: step: 1180/530, loss: 0.08147859573364258
2023-01-21 10:06:30.312646: step: 1184/530, loss: 0.02067422866821289
2023-01-21 10:06:31.436316: step: 1188/530, loss: 0.1286468505859375
2023-01-21 10:06:32.571358: step: 1192/530, loss: 0.1301598995923996
2023-01-21 10:06:33.680075: step: 1196/530, loss: 0.004971504211425781
2023-01-21 10:06:34.788513: step: 1200/530, loss: 0.42529788613319397
2023-01-21 10:06:35.897574: step: 1204/530, loss: 0.12051025778055191
2023-01-21 10:06:37.016839: step: 1208/530, loss: 0.1038203239440918
2023-01-21 10:06:38.147649: step: 1212/530, loss: 0.18087874352931976
2023-01-21 10:06:39.243892: step: 1216/530, loss: 0.04225633293390274
2023-01-21 10:06:40.381177: step: 1220/530, loss: 0.07690220326185226
2023-01-21 10:06:41.490174: step: 1224/530, loss: 0.09403391182422638
2023-01-21 10:06:42.616925: step: 1228/530, loss: 0.6935513019561768
2023-01-21 10:06:43.729568: step: 1232/530, loss: 0.04119567945599556
2023-01-21 10:06:44.813064: step: 1236/530, loss: 0.11418375372886658
2023-01-21 10:06:45.889622: step: 1240/530, loss: 0.031746625900268555
2023-01-21 10:06:46.995723: step: 1244/530, loss: 0.036389730870723724
2023-01-21 10:06:48.113238: step: 1248/530, loss: 0.06745481491088867
2023-01-21 10:06:49.233840: step: 1252/530, loss: 0.04894714429974556
2023-01-21 10:06:50.318758: step: 1256/530, loss: 0.08513341099023819
2023-01-21 10:06:51.429523: step: 1260/530, loss: 0.04502267390489578
2023-01-21 10:06:52.529446: step: 1264/530, loss: 0.1928301751613617
2023-01-21 10:06:53.643648: step: 1268/530, loss: 0.3669787347316742
2023-01-21 10:06:54.736211: step: 1272/530, loss: 0.11448231339454651
2023-01-21 10:06:55.816912: step: 1276/530, loss: 0.04057302325963974
2023-01-21 10:06:56.961529: step: 1280/530, loss: 0.30444374680519104
2023-01-21 10:06:58.069766: step: 1284/530, loss: 0.08582563698291779
2023-01-21 10:06:59.196530: step: 1288/530, loss: 0.13928452134132385
2023-01-21 10:07:00.331712: step: 1292/530, loss: 0.03915577009320259
2023-01-21 10:07:01.424362: step: 1296/530, loss: 0.05849466472864151
2023-01-21 10:07:02.549706: step: 1300/530, loss: 0.05645398795604706
2023-01-21 10:07:03.675915: step: 1304/530, loss: 0.010292625986039639
2023-01-21 10:07:04.755539: step: 1308/530, loss: 0.1323436051607132
2023-01-21 10:07:05.874000: step: 1312/530, loss: 0.07942596822977066
2023-01-21 10:07:06.984954: step: 1316/530, loss: 0.10959644615650177
2023-01-21 10:07:08.079614: step: 1320/530, loss: 0.03783159330487251
2023-01-21 10:07:09.192537: step: 1324/530, loss: 0.016747284680604935
2023-01-21 10:07:10.287220: step: 1328/530, loss: 0.07215280085802078
2023-01-21 10:07:11.409637: step: 1332/530, loss: 0.025126172229647636
2023-01-21 10:07:12.519364: step: 1336/530, loss: 0.0795055404305458
2023-01-21 10:07:13.627741: step: 1340/530, loss: 0.04251251369714737
2023-01-21 10:07:14.723434: step: 1344/530, loss: 0.2454099804162979
2023-01-21 10:07:15.862689: step: 1348/530, loss: 0.09127321094274521
2023-01-21 10:07:16.969256: step: 1352/530, loss: 0.044733621180057526
2023-01-21 10:07:18.084183: step: 1356/530, loss: 0.2725728452205658
2023-01-21 10:07:19.180748: step: 1360/530, loss: 0.10653066635131836
2023-01-21 10:07:20.268847: step: 1364/530, loss: 0.041254233568906784
2023-01-21 10:07:21.419100: step: 1368/530, loss: 0.11273422092199326
2023-01-21 10:07:22.531225: step: 1372/530, loss: 0.03908409923315048
2023-01-21 10:07:23.647733: step: 1376/530, loss: 0.09136947989463806
2023-01-21 10:07:24.750252: step: 1380/530, loss: 0.0916057601571083
2023-01-21 10:07:25.835511: step: 1384/530, loss: 0.022026684135198593
2023-01-21 10:07:26.935854: step: 1388/530, loss: 0.04851255565881729
2023-01-21 10:07:28.058117: step: 1392/530, loss: 0.06088776886463165
2023-01-21 10:07:29.127325: step: 1396/530, loss: 0.02162919007241726
2023-01-21 10:07:30.258710: step: 1400/530, loss: 0.12407321482896805
2023-01-21 10:07:31.378356: step: 1404/530, loss: 0.2935035824775696
2023-01-21 10:07:32.518321: step: 1408/530, loss: 0.016327284276485443
2023-01-21 10:07:33.639503: step: 1412/530, loss: 0.20679211616516113
2023-01-21 10:07:34.725835: step: 1416/530, loss: 0.0630430206656456
2023-01-21 10:07:35.826895: step: 1420/530, loss: 0.043682049959897995
2023-01-21 10:07:36.953673: step: 1424/530, loss: 0.03928108513355255
2023-01-21 10:07:38.069196: step: 1428/530, loss: 0.016768742352724075
2023-01-21 10:07:39.172487: step: 1432/530, loss: 0.07665625214576721
2023-01-21 10:07:40.287718: step: 1436/530, loss: 0.004076576326042414
2023-01-21 10:07:41.397068: step: 1440/530, loss: 0.038597699254751205
2023-01-21 10:07:42.504595: step: 1444/530, loss: 0.01966114155948162
2023-01-21 10:07:43.622638: step: 1448/530, loss: 0.12816362082958221
2023-01-21 10:07:44.757928: step: 1452/530, loss: 0.06268720328807831
2023-01-21 10:07:45.864961: step: 1456/530, loss: 0.0040569305419921875
2023-01-21 10:07:46.982956: step: 1460/530, loss: 0.018898535519838333
2023-01-21 10:07:48.080040: step: 1464/530, loss: 0.7334356904029846
2023-01-21 10:07:49.195625: step: 1468/530, loss: 0.022551918402314186
2023-01-21 10:07:50.288018: step: 1472/530, loss: 0.07510886341333389
2023-01-21 10:07:51.382867: step: 1476/530, loss: 0.05240478366613388
2023-01-21 10:07:52.491976: step: 1480/530, loss: 0.025999926030635834
2023-01-21 10:07:53.587791: step: 1484/530, loss: 0.009007262997329235
2023-01-21 10:07:54.720287: step: 1488/530, loss: 0.07305431365966797
2023-01-21 10:07:55.865190: step: 1492/530, loss: 0.008928585797548294
2023-01-21 10:07:56.973096: step: 1496/530, loss: 0.06958160549402237
2023-01-21 10:07:58.085854: step: 1500/530, loss: 0.04374289512634277
2023-01-21 10:07:59.226567: step: 1504/530, loss: 0.0953243225812912
2023-01-21 10:08:00.327185: step: 1508/530, loss: 0.0019353866809979081
2023-01-21 10:08:01.402854: step: 1512/530, loss: 0.12265358120203018
2023-01-21 10:08:02.486098: step: 1516/530, loss: 0.03210468217730522
2023-01-21 10:08:03.576275: step: 1520/530, loss: 0.021001625806093216
2023-01-21 10:08:04.685523: step: 1524/530, loss: 0.1092386245727539
2023-01-21 10:08:05.795633: step: 1528/530, loss: 0.008463477715849876
2023-01-21 10:08:06.882392: step: 1532/530, loss: 0.045734405517578125
2023-01-21 10:08:07.981604: step: 1536/530, loss: 0.021791458129882812
2023-01-21 10:08:09.094255: step: 1540/530, loss: 0.028057385236024857
2023-01-21 10:08:10.191051: step: 1544/530, loss: 0.07758345454931259
2023-01-21 10:08:11.359567: step: 1548/530, loss: 0.020352650433778763
2023-01-21 10:08:12.462467: step: 1552/530, loss: 0.14214782416820526
2023-01-21 10:08:13.575870: step: 1556/530, loss: 0.041823387145996094
2023-01-21 10:08:14.666038: step: 1560/530, loss: 0.11422014236450195
2023-01-21 10:08:15.758389: step: 1564/530, loss: 0.10865583270788193
2023-01-21 10:08:16.869431: step: 1568/530, loss: 0.09713335335254669
2023-01-21 10:08:17.982839: step: 1572/530, loss: 0.036855410784482956
2023-01-21 10:08:19.069204: step: 1576/530, loss: 0.08533421158790588
2023-01-21 10:08:20.213801: step: 1580/530, loss: 0.13995370268821716
2023-01-21 10:08:21.312854: step: 1584/530, loss: 0.02689371071755886
2023-01-21 10:08:22.413293: step: 1588/530, loss: 0.061470601707696915
2023-01-21 10:08:23.510345: step: 1592/530, loss: 0.37156981229782104
2023-01-21 10:08:24.660220: step: 1596/530, loss: 0.0485624298453331
2023-01-21 10:08:25.798879: step: 1600/530, loss: 0.1754436492919922
2023-01-21 10:08:26.931909: step: 1604/530, loss: 0.19284287095069885
2023-01-21 10:08:28.048183: step: 1608/530, loss: 0.21574535965919495
2023-01-21 10:08:29.165667: step: 1612/530, loss: 0.17788058519363403
2023-01-21 10:08:30.303895: step: 1616/530, loss: 0.017086505889892578
2023-01-21 10:08:31.401804: step: 1620/530, loss: 0.42147207260131836
2023-01-21 10:08:32.493377: step: 1624/530, loss: 0.014336966909468174
2023-01-21 10:08:33.602246: step: 1628/530, loss: 0.029339982196688652
2023-01-21 10:08:34.722088: step: 1632/530, loss: 0.02083911933004856
2023-01-21 10:08:35.841956: step: 1636/530, loss: 0.012180614285171032
2023-01-21 10:08:36.956582: step: 1640/530, loss: 0.048548318445682526
2023-01-21 10:08:38.076447: step: 1644/530, loss: 0.019157838076353073
2023-01-21 10:08:39.187669: step: 1648/530, loss: 0.10239201784133911
2023-01-21 10:08:40.291409: step: 1652/530, loss: 0.016657400876283646
2023-01-21 10:08:41.429405: step: 1656/530, loss: 0.10627421736717224
2023-01-21 10:08:42.549843: step: 1660/530, loss: 0.23718085885047913
2023-01-21 10:08:43.658894: step: 1664/530, loss: 0.03785209730267525
2023-01-21 10:08:44.765477: step: 1668/530, loss: 0.18510520458221436
2023-01-21 10:08:45.869702: step: 1672/530, loss: 0.03379549831151962
2023-01-21 10:08:46.968059: step: 1676/530, loss: 0.04039621353149414
2023-01-21 10:08:48.097102: step: 1680/530, loss: 0.01354975625872612
2023-01-21 10:08:49.209700: step: 1684/530, loss: 0.08295512199401855
2023-01-21 10:08:50.303165: step: 1688/530, loss: 0.5378724336624146
2023-01-21 10:08:51.407267: step: 1692/530, loss: 0.050301551818847656
2023-01-21 10:08:52.535868: step: 1696/530, loss: 0.07720642536878586
2023-01-21 10:08:53.642184: step: 1700/530, loss: 0.01579437218606472
2023-01-21 10:08:54.738970: step: 1704/530, loss: 0.08852110058069229
2023-01-21 10:08:55.835946: step: 1708/530, loss: 0.07513542473316193
2023-01-21 10:08:56.952367: step: 1712/530, loss: 0.18471240997314453
2023-01-21 10:08:58.052167: step: 1716/530, loss: 0.05296935886144638
2023-01-21 10:08:59.168618: step: 1720/530, loss: 0.23193541169166565
2023-01-21 10:09:00.296045: step: 1724/530, loss: 0.19017134606838226
2023-01-21 10:09:01.381029: step: 1728/530, loss: 0.4607086777687073
2023-01-21 10:09:02.486319: step: 1732/530, loss: 1.0089895725250244
2023-01-21 10:09:03.566237: step: 1736/530, loss: 0.05974860116839409
2023-01-21 10:09:04.684809: step: 1740/530, loss: 0.01620645634829998
2023-01-21 10:09:05.800524: step: 1744/530, loss: 0.15811291337013245
2023-01-21 10:09:06.908936: step: 1748/530, loss: 0.04337568208575249
2023-01-21 10:09:08.023907: step: 1752/530, loss: 0.02452678605914116
2023-01-21 10:09:09.141982: step: 1756/530, loss: 0.04370298609137535
2023-01-21 10:09:10.273952: step: 1760/530, loss: 0.02557063102722168
2023-01-21 10:09:11.418468: step: 1764/530, loss: 0.33396807312965393
2023-01-21 10:09:12.510832: step: 1768/530, loss: 0.08546619117259979
2023-01-21 10:09:13.639088: step: 1772/530, loss: 0.009649157524108887
2023-01-21 10:09:14.755416: step: 1776/530, loss: 0.03867368772625923
2023-01-21 10:09:15.856086: step: 1780/530, loss: 0.10215988755226135
2023-01-21 10:09:16.989243: step: 1784/530, loss: 0.07459618896245956
2023-01-21 10:09:18.110994: step: 1788/530, loss: 0.23017263412475586
2023-01-21 10:09:19.204576: step: 1792/530, loss: 0.10287227481603622
2023-01-21 10:09:20.323678: step: 1796/530, loss: 0.07859429717063904
2023-01-21 10:09:21.433415: step: 1800/530, loss: 0.06972646713256836
2023-01-21 10:09:22.543111: step: 1804/530, loss: 0.08223896473646164
2023-01-21 10:09:23.636928: step: 1808/530, loss: 0.007271384820342064
2023-01-21 10:09:24.736361: step: 1812/530, loss: 0.11665526032447815
2023-01-21 10:09:25.893230: step: 1816/530, loss: 0.07261891663074493
2023-01-21 10:09:26.998337: step: 1820/530, loss: 0.013526635244488716
2023-01-21 10:09:28.116645: step: 1824/530, loss: 0.05945263430476189
2023-01-21 10:09:29.208102: step: 1828/530, loss: 0.04386315494775772
2023-01-21 10:09:30.309849: step: 1832/530, loss: 0.01474299468100071
2023-01-21 10:09:31.421381: step: 1836/530, loss: 0.09891348332166672
2023-01-21 10:09:32.511893: step: 1840/530, loss: 0.02595844492316246
2023-01-21 10:09:33.612898: step: 1844/530, loss: 0.04823732376098633
2023-01-21 10:09:34.710268: step: 1848/530, loss: 0.10055723041296005
2023-01-21 10:09:35.818116: step: 1852/530, loss: 0.10621195286512375
2023-01-21 10:09:36.941313: step: 1856/530, loss: 0.006200027652084827
2023-01-21 10:09:38.025447: step: 1860/530, loss: 0.08431287109851837
2023-01-21 10:09:39.117912: step: 1864/530, loss: 0.358629435300827
2023-01-21 10:09:40.261713: step: 1868/530, loss: 0.5737533569335938
2023-01-21 10:09:41.385828: step: 1872/530, loss: 0.11289462447166443
2023-01-21 10:09:42.493504: step: 1876/530, loss: 0.0513484925031662
2023-01-21 10:09:43.637733: step: 1880/530, loss: 0.06045493856072426
2023-01-21 10:09:44.751261: step: 1884/530, loss: 0.0445561446249485
2023-01-21 10:09:45.865577: step: 1888/530, loss: 0.07383691519498825
2023-01-21 10:09:46.967714: step: 1892/530, loss: 0.14242681860923767
2023-01-21 10:09:48.078688: step: 1896/530, loss: 0.27213916182518005
2023-01-21 10:09:49.164379: step: 1900/530, loss: 0.18171927332878113
2023-01-21 10:09:50.268094: step: 1904/530, loss: 0.058362483978271484
2023-01-21 10:09:51.362529: step: 1908/530, loss: 0.13020344078540802
2023-01-21 10:09:52.473326: step: 1912/530, loss: 0.20567511022090912
2023-01-21 10:09:53.571696: step: 1916/530, loss: 0.029943371191620827
2023-01-21 10:09:54.689529: step: 1920/530, loss: 0.06632187217473984
2023-01-21 10:09:55.805511: step: 1924/530, loss: 0.023052597418427467
2023-01-21 10:09:56.919414: step: 1928/530, loss: 0.06741275638341904
2023-01-21 10:09:58.029446: step: 1932/530, loss: 0.05406522750854492
2023-01-21 10:09:59.152704: step: 1936/530, loss: 0.030610274523496628
2023-01-21 10:10:00.277111: step: 1940/530, loss: 0.11733102798461914
2023-01-21 10:10:01.395101: step: 1944/530, loss: 0.09982426464557648
2023-01-21 10:10:02.481569: step: 1948/530, loss: 0.04625272750854492
2023-01-21 10:10:03.608776: step: 1952/530, loss: 0.14949455857276917
2023-01-21 10:10:04.726745: step: 1956/530, loss: 0.04653911665081978
2023-01-21 10:10:05.789948: step: 1960/530, loss: 0.25855380296707153
2023-01-21 10:10:06.885577: step: 1964/530, loss: 0.076437808573246
2023-01-21 10:10:07.994944: step: 1968/530, loss: 0.033800315111875534
2023-01-21 10:10:09.060752: step: 1972/530, loss: 0.5211111307144165
2023-01-21 10:10:10.186161: step: 1976/530, loss: 0.021532397717237473
2023-01-21 10:10:11.331884: step: 1980/530, loss: 0.09326867759227753
2023-01-21 10:10:12.482892: step: 1984/530, loss: 0.013794993981719017
2023-01-21 10:10:13.603879: step: 1988/530, loss: 0.16064491868019104
2023-01-21 10:10:14.779439: step: 1992/530, loss: 0.1874007284641266
2023-01-21 10:10:15.895254: step: 1996/530, loss: 0.08353462815284729
2023-01-21 10:10:16.996900: step: 2000/530, loss: 0.031646180897951126
2023-01-21 10:10:18.097214: step: 2004/530, loss: 0.15700717270374298
2023-01-21 10:10:19.213782: step: 2008/530, loss: 0.06414651870727539
2023-01-21 10:10:20.299521: step: 2012/530, loss: 0.02670001983642578
2023-01-21 10:10:21.406803: step: 2016/530, loss: 0.10737305134534836
2023-01-21 10:10:22.516416: step: 2020/530, loss: 0.05547180026769638
2023-01-21 10:10:23.646004: step: 2024/530, loss: 0.041091155260801315
2023-01-21 10:10:24.740383: step: 2028/530, loss: 0.07718295603990555
2023-01-21 10:10:25.849040: step: 2032/530, loss: 0.01485300064086914
2023-01-21 10:10:26.955386: step: 2036/530, loss: 0.26129063963890076
2023-01-21 10:10:28.093919: step: 2040/530, loss: 0.15680618584156036
2023-01-21 10:10:29.193626: step: 2044/530, loss: 0.02359952963888645
2023-01-21 10:10:30.298194: step: 2048/530, loss: 0.09250812232494354
2023-01-21 10:10:31.396009: step: 2052/530, loss: 0.07625351846218109
2023-01-21 10:10:32.532129: step: 2056/530, loss: 0.03449134901165962
2023-01-21 10:10:33.636362: step: 2060/530, loss: 0.06136827543377876
2023-01-21 10:10:34.742070: step: 2064/530, loss: 0.7650858163833618
2023-01-21 10:10:35.839434: step: 2068/530, loss: 0.03203845024108887
2023-01-21 10:10:36.992224: step: 2072/530, loss: 0.024643398821353912
2023-01-21 10:10:38.102824: step: 2076/530, loss: 0.1855226457118988
2023-01-21 10:10:39.221554: step: 2080/530, loss: 0.014832114800810814
2023-01-21 10:10:40.326149: step: 2084/530, loss: 0.03310804441571236
2023-01-21 10:10:41.466732: step: 2088/530, loss: 0.268356055021286
2023-01-21 10:10:42.662991: step: 2092/530, loss: 0.299412339925766
2023-01-21 10:10:43.770754: step: 2096/530, loss: 0.04766654968261719
2023-01-21 10:10:44.902410: step: 2100/530, loss: 0.07706699520349503
2023-01-21 10:10:45.987009: step: 2104/530, loss: 0.021483946591615677
2023-01-21 10:10:47.090966: step: 2108/530, loss: 0.0529605858027935
2023-01-21 10:10:48.175250: step: 2112/530, loss: 0.06573477387428284
2023-01-21 10:10:49.310740: step: 2116/530, loss: 0.0858016386628151
2023-01-21 10:10:50.397325: step: 2120/530, loss: 0.36201468110084534
==================================================
Loss: 0.109
--------------------
Dev: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Test: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, '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': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5708622398414271, 'r': 0.7669773635153129, 'f1': 0.6545454545454545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Chinese: {'event': {'p': 0.6044052863436123, 'r': 0.7995337995337995, 'f1': 0.6884094330155545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Chinese: {'event': {'p': 0.6578947368421053, 'r': 0.9259259259259259, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6466512702078522, 'r': 0.7456724367509987, 'f1': 0.6926406926406927}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.6762148337595908, 'r': 0.7703962703962703, 'f1': 0.7202397166984473}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 10:11:36.581385: step: 4/530, loss: 0.0834735855460167
2023-01-21 10:11:37.727509: step: 8/530, loss: 0.06531648337841034
2023-01-21 10:11:38.835634: step: 12/530, loss: 0.02104969136416912
2023-01-21 10:11:39.944579: step: 16/530, loss: 1.4563148021697998
2023-01-21 10:11:41.015563: step: 20/530, loss: 0.09583454579114914
2023-01-21 10:11:42.090506: step: 24/530, loss: 0.04431591182947159
2023-01-21 10:11:43.198629: step: 28/530, loss: 0.05222749710083008
2023-01-21 10:11:44.334438: step: 32/530, loss: 0.48342904448509216
2023-01-21 10:11:45.464694: step: 36/530, loss: 0.06960248947143555
2023-01-21 10:11:46.584678: step: 40/530, loss: 0.09375648200511932
2023-01-21 10:11:47.695816: step: 44/530, loss: 0.02256631851196289
2023-01-21 10:11:48.821963: step: 48/530, loss: 0.22881126403808594
2023-01-21 10:11:49.941426: step: 52/530, loss: 0.09813786298036575
2023-01-21 10:11:51.057794: step: 56/530, loss: 0.011032533831894398
2023-01-21 10:11:52.157243: step: 60/530, loss: 0.06088457629084587
2023-01-21 10:11:53.264570: step: 64/530, loss: 0.027191925793886185
2023-01-21 10:11:54.343765: step: 68/530, loss: 0.04366140812635422
2023-01-21 10:11:55.438697: step: 72/530, loss: 0.0096893310546875
2023-01-21 10:11:56.528981: step: 76/530, loss: 0.011082840152084827
2023-01-21 10:11:57.609664: step: 80/530, loss: 0.04648271203041077
2023-01-21 10:11:58.772531: step: 84/530, loss: 0.21836671233177185
2023-01-21 10:11:59.846484: step: 88/530, loss: 0.03273162990808487
2023-01-21 10:12:00.967310: step: 92/530, loss: 0.045271970331668854
2023-01-21 10:12:02.070780: step: 96/530, loss: 0.05436506122350693
2023-01-21 10:12:03.166005: step: 100/530, loss: 0.08144054561853409
2023-01-21 10:12:04.281934: step: 104/530, loss: 0.03153381496667862
2023-01-21 10:12:05.396689: step: 108/530, loss: 0.05513410642743111
2023-01-21 10:12:06.511233: step: 112/530, loss: 0.04428587108850479
2023-01-21 10:12:07.619430: step: 116/530, loss: 0.06590643525123596
2023-01-21 10:12:08.706063: step: 120/530, loss: 0.2835732102394104
2023-01-21 10:12:09.793098: step: 124/530, loss: 0.0005710602272301912
2023-01-21 10:12:10.892863: step: 128/530, loss: 0.0423736572265625
2023-01-21 10:12:11.990156: step: 132/530, loss: 0.1969594955444336
2023-01-21 10:12:13.075931: step: 136/530, loss: 0.046848200261592865
2023-01-21 10:12:14.234166: step: 140/530, loss: 0.11491279304027557
2023-01-21 10:12:15.339047: step: 144/530, loss: 0.08374185860157013
2023-01-21 10:12:16.435342: step: 148/530, loss: 0.3090837299823761
2023-01-21 10:12:17.514092: step: 152/530, loss: 0.1806931048631668
2023-01-21 10:12:18.610764: step: 156/530, loss: 0.07658844441175461
2023-01-21 10:12:19.714616: step: 160/530, loss: 0.0014497756492346525
2023-01-21 10:12:20.784320: step: 164/530, loss: 0.02380204200744629
2023-01-21 10:12:21.881885: step: 168/530, loss: 0.02237396314740181
2023-01-21 10:12:22.974516: step: 172/530, loss: 0.062426187098026276
2023-01-21 10:12:24.091083: step: 176/530, loss: 0.05280666798353195
2023-01-21 10:12:25.209624: step: 180/530, loss: 0.12218570709228516
2023-01-21 10:12:26.308563: step: 184/530, loss: 0.031491946429014206
2023-01-21 10:12:27.411776: step: 188/530, loss: 0.012024307623505592
2023-01-21 10:12:28.530558: step: 192/530, loss: 0.022630594670772552
2023-01-21 10:12:29.648468: step: 196/530, loss: 0.018315697088837624
2023-01-21 10:12:30.765485: step: 200/530, loss: 0.027228165417909622
2023-01-21 10:12:31.874999: step: 204/530, loss: 0.007268715184181929
2023-01-21 10:12:32.994011: step: 208/530, loss: 0.03626976162195206
2023-01-21 10:12:34.118295: step: 212/530, loss: 0.24929890036582947
2023-01-21 10:12:35.232936: step: 216/530, loss: 0.03481864929199219
2023-01-21 10:12:36.328172: step: 220/530, loss: 0.03411092609167099
2023-01-21 10:12:37.426510: step: 224/530, loss: 0.05981817469000816
2023-01-21 10:12:38.532623: step: 228/530, loss: 0.13779029250144958
2023-01-21 10:12:39.629595: step: 232/530, loss: 0.00806660670787096
2023-01-21 10:12:40.732472: step: 236/530, loss: 0.028628967702388763
2023-01-21 10:12:41.862700: step: 240/530, loss: 0.10116253048181534
2023-01-21 10:12:42.970466: step: 244/530, loss: 0.010532760992646217
2023-01-21 10:12:44.050565: step: 248/530, loss: 0.028371762484312057
2023-01-21 10:12:45.188577: step: 252/530, loss: 0.05829181522130966
2023-01-21 10:12:46.268813: step: 256/530, loss: 0.0021398544777184725
2023-01-21 10:12:47.408882: step: 260/530, loss: 0.10395526885986328
2023-01-21 10:12:48.506686: step: 264/530, loss: 0.36564120650291443
2023-01-21 10:12:49.613899: step: 268/530, loss: 0.07277374714612961
2023-01-21 10:12:50.769729: step: 272/530, loss: 0.08302745968103409
2023-01-21 10:12:51.886043: step: 276/530, loss: 0.0510522834956646
2023-01-21 10:12:52.979560: step: 280/530, loss: 0.02546558529138565
2023-01-21 10:12:54.084274: step: 284/530, loss: 0.05524082109332085
2023-01-21 10:12:55.165055: step: 288/530, loss: 0.023154258728027344
2023-01-21 10:12:56.262574: step: 292/530, loss: 0.22347183525562286
2023-01-21 10:12:57.384891: step: 296/530, loss: 0.009690475650131702
2023-01-21 10:12:58.498015: step: 300/530, loss: 0.2514456808567047
2023-01-21 10:12:59.622444: step: 304/530, loss: 0.12265624105930328
2023-01-21 10:13:00.723347: step: 308/530, loss: 0.049795106053352356
2023-01-21 10:13:01.827890: step: 312/530, loss: 0.03181672468781471
2023-01-21 10:13:02.942256: step: 316/530, loss: 0.09142627567052841
2023-01-21 10:13:04.029831: step: 320/530, loss: 0.02604513242840767
2023-01-21 10:13:05.124295: step: 324/530, loss: 0.057601165026426315
2023-01-21 10:13:06.236816: step: 328/530, loss: 0.007393264677375555
2023-01-21 10:13:07.359385: step: 332/530, loss: 0.14607840776443481
2023-01-21 10:13:08.442597: step: 336/530, loss: 0.030007457360625267
2023-01-21 10:13:09.553864: step: 340/530, loss: 0.054877281188964844
2023-01-21 10:13:10.647966: step: 344/530, loss: 0.006588459014892578
2023-01-21 10:13:11.747875: step: 348/530, loss: 0.028640173375606537
2023-01-21 10:13:12.905270: step: 352/530, loss: 0.10570058971643448
2023-01-21 10:13:14.012341: step: 356/530, loss: 0.01734349876642227
2023-01-21 10:13:15.119298: step: 360/530, loss: 0.07597538828849792
2023-01-21 10:13:16.249033: step: 364/530, loss: 0.15829753875732422
2023-01-21 10:13:17.379088: step: 368/530, loss: 0.02716798707842827
2023-01-21 10:13:18.492641: step: 372/530, loss: 0.0546695739030838
2023-01-21 10:13:19.592073: step: 376/530, loss: 0.06157340854406357
2023-01-21 10:13:20.713357: step: 380/530, loss: 0.13005714118480682
2023-01-21 10:13:21.829396: step: 384/530, loss: 0.3410007953643799
2023-01-21 10:13:22.942168: step: 388/530, loss: 0.07926854491233826
2023-01-21 10:13:24.054918: step: 392/530, loss: 0.018945885822176933
2023-01-21 10:13:25.143122: step: 396/530, loss: 0.021465228870511055
2023-01-21 10:13:26.222216: step: 400/530, loss: 0.02206391841173172
2023-01-21 10:13:27.320742: step: 404/530, loss: 0.013283634558320045
2023-01-21 10:13:28.441671: step: 408/530, loss: 0.05972748249769211
2023-01-21 10:13:29.559753: step: 412/530, loss: 0.027878714725375175
2023-01-21 10:13:30.676657: step: 416/530, loss: 0.05552997812628746
2023-01-21 10:13:31.787011: step: 420/530, loss: 0.11758479475975037
2023-01-21 10:13:32.921908: step: 424/530, loss: 0.08100011199712753
2023-01-21 10:13:34.022234: step: 428/530, loss: 0.2722596228122711
2023-01-21 10:13:35.099367: step: 432/530, loss: 0.03753519058227539
2023-01-21 10:13:36.194736: step: 436/530, loss: 0.10826301574707031
2023-01-21 10:13:37.282710: step: 440/530, loss: 0.05514087900519371
2023-01-21 10:13:38.387096: step: 444/530, loss: 0.046673014760017395
2023-01-21 10:13:39.481023: step: 448/530, loss: 0.029434965923428535
2023-01-21 10:13:40.580920: step: 452/530, loss: 0.07514429092407227
2023-01-21 10:13:41.667903: step: 456/530, loss: 0.007110118865966797
2023-01-21 10:13:42.762858: step: 460/530, loss: 0.03357858583331108
2023-01-21 10:13:43.855148: step: 464/530, loss: 0.048253823071718216
2023-01-21 10:13:44.958448: step: 468/530, loss: 0.42511633038520813
2023-01-21 10:13:46.119991: step: 472/530, loss: 0.10517702251672745
2023-01-21 10:13:47.216040: step: 476/530, loss: 0.09064006805419922
2023-01-21 10:13:48.325497: step: 480/530, loss: 0.015919208526611328
2023-01-21 10:13:49.435160: step: 484/530, loss: 0.00928888376802206
2023-01-21 10:13:50.519657: step: 488/530, loss: 0.045835305005311966
2023-01-21 10:13:51.613429: step: 492/530, loss: 0.10745306313037872
2023-01-21 10:13:52.722247: step: 496/530, loss: 0.013304520398378372
2023-01-21 10:13:53.826144: step: 500/530, loss: 0.07792044430971146
2023-01-21 10:13:54.927037: step: 504/530, loss: 0.12546634674072266
2023-01-21 10:13:56.038626: step: 508/530, loss: 0.5122291445732117
2023-01-21 10:13:57.143109: step: 512/530, loss: 0.03413867950439453
2023-01-21 10:13:58.219188: step: 516/530, loss: 0.0019414902199059725
2023-01-21 10:13:59.347460: step: 520/530, loss: 0.0027006627060472965
2023-01-21 10:14:00.450661: step: 524/530, loss: 0.09243831783533096
2023-01-21 10:14:01.570259: step: 528/530, loss: 0.12032070010900497
2023-01-21 10:14:02.702119: step: 532/530, loss: 0.034134864807128906
2023-01-21 10:14:03.797080: step: 536/530, loss: 0.05949496105313301
2023-01-21 10:14:04.896840: step: 540/530, loss: 0.2151658982038498
2023-01-21 10:14:05.986571: step: 544/530, loss: 0.09138303250074387
2023-01-21 10:14:07.087857: step: 548/530, loss: 0.06074059009552002
2023-01-21 10:14:08.177349: step: 552/530, loss: 0.03937659412622452
2023-01-21 10:14:09.308838: step: 556/530, loss: 0.46185609698295593
2023-01-21 10:14:10.472846: step: 560/530, loss: 0.07926788181066513
2023-01-21 10:14:11.584941: step: 564/530, loss: 0.0252514835447073
2023-01-21 10:14:12.681172: step: 568/530, loss: 0.023298712447285652
2023-01-21 10:14:13.768975: step: 572/530, loss: 0.030413247644901276
2023-01-21 10:14:14.859243: step: 576/530, loss: 0.04990358278155327
2023-01-21 10:14:15.958170: step: 580/530, loss: 0.18456298112869263
2023-01-21 10:14:17.069969: step: 584/530, loss: 0.07024664431810379
2023-01-21 10:14:18.185727: step: 588/530, loss: 0.002684021135792136
2023-01-21 10:14:19.296415: step: 592/530, loss: 0.01882925070822239
2023-01-21 10:14:20.424236: step: 596/530, loss: 0.028644084930419922
2023-01-21 10:14:21.523106: step: 600/530, loss: 0.04327097907662392
2023-01-21 10:14:22.648908: step: 604/530, loss: 0.08436079323291779
2023-01-21 10:14:23.757233: step: 608/530, loss: 0.04987182468175888
2023-01-21 10:14:24.842746: step: 612/530, loss: 0.18709707260131836
2023-01-21 10:14:25.952521: step: 616/530, loss: 0.012269115075469017
2023-01-21 10:14:27.072163: step: 620/530, loss: 0.5628917813301086
2023-01-21 10:14:28.167339: step: 624/530, loss: 0.08262629061937332
2023-01-21 10:14:29.257054: step: 628/530, loss: 0.07671672105789185
2023-01-21 10:14:30.393501: step: 632/530, loss: 0.03874702751636505
2023-01-21 10:14:31.515259: step: 636/530, loss: 0.09352779388427734
2023-01-21 10:14:32.629294: step: 640/530, loss: 0.05353522300720215
2023-01-21 10:14:33.749030: step: 644/530, loss: 0.004307246301323175
2023-01-21 10:14:34.814937: step: 648/530, loss: 0.1020701453089714
2023-01-21 10:14:35.914700: step: 652/530, loss: 0.009965991601347923
2023-01-21 10:14:36.989729: step: 656/530, loss: 0.069349005818367
2023-01-21 10:14:38.103910: step: 660/530, loss: 0.038263607770204544
2023-01-21 10:14:39.199086: step: 664/530, loss: 0.013882064260542393
2023-01-21 10:14:40.305375: step: 668/530, loss: 0.021936701610684395
2023-01-21 10:14:41.405077: step: 672/530, loss: 0.04935512691736221
2023-01-21 10:14:42.501029: step: 676/530, loss: 0.0045105936005711555
2023-01-21 10:14:43.626881: step: 680/530, loss: 0.061463452875614166
2023-01-21 10:14:44.743444: step: 684/530, loss: 0.04592590406537056
2023-01-21 10:14:45.834120: step: 688/530, loss: 0.07534332573413849
2023-01-21 10:14:46.987179: step: 692/530, loss: 0.035222575068473816
2023-01-21 10:14:48.074301: step: 696/530, loss: 0.05991983413696289
2023-01-21 10:14:49.185659: step: 700/530, loss: 0.058161258697509766
2023-01-21 10:14:50.296788: step: 704/530, loss: 0.6873898506164551
2023-01-21 10:14:51.386676: step: 708/530, loss: 0.13362407684326172
2023-01-21 10:14:52.495161: step: 712/530, loss: 0.02099323272705078
2023-01-21 10:14:53.608182: step: 716/530, loss: 0.003944134805351496
2023-01-21 10:14:54.697534: step: 720/530, loss: 0.023998450487852097
2023-01-21 10:14:55.787078: step: 724/530, loss: 0.03330354765057564
2023-01-21 10:14:56.880290: step: 728/530, loss: 0.04715704917907715
2023-01-21 10:14:58.001569: step: 732/530, loss: 0.01619720458984375
2023-01-21 10:14:59.119389: step: 736/530, loss: 0.007481765933334827
2023-01-21 10:15:00.264788: step: 740/530, loss: 0.06180219724774361
2023-01-21 10:15:01.371826: step: 744/530, loss: 0.1401459276676178
2023-01-21 10:15:02.492216: step: 748/530, loss: 0.21897634863853455
2023-01-21 10:15:03.607717: step: 752/530, loss: 0.07128188759088516
2023-01-21 10:15:04.729376: step: 756/530, loss: 0.003999615088105202
2023-01-21 10:15:05.858835: step: 760/530, loss: 0.052939701825380325
2023-01-21 10:15:06.956456: step: 764/530, loss: 0.015442252159118652
2023-01-21 10:15:08.066898: step: 768/530, loss: 0.17858104407787323
2023-01-21 10:15:09.178832: step: 772/530, loss: 0.01694483868777752
2023-01-21 10:15:10.283828: step: 776/530, loss: 0.04257345199584961
2023-01-21 10:15:11.380887: step: 780/530, loss: 0.01818552054464817
2023-01-21 10:15:12.494076: step: 784/530, loss: 0.06434686481952667
2023-01-21 10:15:13.586583: step: 788/530, loss: 0.039573170244693756
2023-01-21 10:15:14.709182: step: 792/530, loss: 0.020193099975585938
2023-01-21 10:15:15.838235: step: 796/530, loss: 0.23294369876384735
2023-01-21 10:15:16.951750: step: 800/530, loss: 0.06156263127923012
2023-01-21 10:15:18.056699: step: 804/530, loss: 0.023204898461699486
2023-01-21 10:15:19.154865: step: 808/530, loss: 0.10833749175071716
2023-01-21 10:15:20.248782: step: 812/530, loss: 0.0756952315568924
2023-01-21 10:15:21.347508: step: 816/530, loss: 0.43404093384742737
2023-01-21 10:15:22.442900: step: 820/530, loss: 0.10713472962379456
2023-01-21 10:15:23.527431: step: 824/530, loss: 0.2257017195224762
2023-01-21 10:15:24.623842: step: 828/530, loss: 0.17161358892917633
2023-01-21 10:15:25.722044: step: 832/530, loss: 0.06517940014600754
2023-01-21 10:15:26.832926: step: 836/530, loss: 0.08382339775562286
2023-01-21 10:15:27.938364: step: 840/530, loss: 0.008511734195053577
2023-01-21 10:15:29.051293: step: 844/530, loss: 0.22435151040554047
2023-01-21 10:15:30.141167: step: 848/530, loss: 0.03380937501788139
2023-01-21 10:15:31.239430: step: 852/530, loss: 0.12638626992702484
2023-01-21 10:15:32.346920: step: 856/530, loss: 0.1400773972272873
2023-01-21 10:15:33.429862: step: 860/530, loss: 0.057898808270692825
2023-01-21 10:15:34.519131: step: 864/530, loss: 0.03015538491308689
2023-01-21 10:15:35.649330: step: 868/530, loss: 0.06649813801050186
2023-01-21 10:15:36.763645: step: 872/530, loss: 0.07771673053503036
2023-01-21 10:15:37.869575: step: 876/530, loss: 0.08896628022193909
2023-01-21 10:15:38.978073: step: 880/530, loss: 0.045725442469120026
2023-01-21 10:15:40.081278: step: 884/530, loss: 0.05918693542480469
2023-01-21 10:15:41.171060: step: 888/530, loss: 0.03636446222662926
2023-01-21 10:15:42.314515: step: 892/530, loss: 0.0028726577293127775
2023-01-21 10:15:43.419688: step: 896/530, loss: 0.0045986175537109375
2023-01-21 10:15:44.526526: step: 900/530, loss: 0.12170648574829102
2023-01-21 10:15:45.638261: step: 904/530, loss: 0.14712266623973846
2023-01-21 10:15:46.744122: step: 908/530, loss: 0.10480928421020508
2023-01-21 10:15:47.875680: step: 912/530, loss: 0.013826894573867321
2023-01-21 10:15:48.985749: step: 916/530, loss: 0.003726482391357422
2023-01-21 10:15:50.107761: step: 920/530, loss: 0.03209862485527992
2023-01-21 10:15:51.236980: step: 924/530, loss: 0.028798487037420273
2023-01-21 10:15:52.347831: step: 928/530, loss: 0.04057502746582031
2023-01-21 10:15:53.495839: step: 932/530, loss: 0.812938392162323
2023-01-21 10:15:54.584960: step: 936/530, loss: 0.26519739627838135
2023-01-21 10:15:55.704669: step: 940/530, loss: 0.046123601496219635
2023-01-21 10:15:56.818512: step: 944/530, loss: 0.031608011573553085
2023-01-21 10:15:57.970223: step: 948/530, loss: 0.03800716623663902
2023-01-21 10:15:59.124491: step: 952/530, loss: 0.07375270873308182
2023-01-21 10:16:00.270240: step: 956/530, loss: 0.026720141991972923
2023-01-21 10:16:01.392769: step: 960/530, loss: 0.07317686080932617
2023-01-21 10:16:02.496409: step: 964/530, loss: 0.021296881139278412
2023-01-21 10:16:03.651426: step: 968/530, loss: 0.026706887409090996
2023-01-21 10:16:04.743595: step: 972/530, loss: 0.0815461203455925
2023-01-21 10:16:05.835952: step: 976/530, loss: 0.29885920882225037
2023-01-21 10:16:06.977627: step: 980/530, loss: 0.03130531311035156
2023-01-21 10:16:08.085969: step: 984/530, loss: 0.09579449146986008
2023-01-21 10:16:09.194185: step: 988/530, loss: 0.21842169761657715
2023-01-21 10:16:10.332541: step: 992/530, loss: 0.035544779151678085
2023-01-21 10:16:11.473329: step: 996/530, loss: 0.021796513348817825
2023-01-21 10:16:12.586300: step: 1000/530, loss: 0.04416842758655548
2023-01-21 10:16:13.755657: step: 1004/530, loss: 0.039066411554813385
2023-01-21 10:16:14.928477: step: 1008/530, loss: 0.06291083991527557
2023-01-21 10:16:16.041692: step: 1012/530, loss: 0.09093169867992401
2023-01-21 10:16:17.156471: step: 1016/530, loss: 0.20161285996437073
2023-01-21 10:16:18.303029: step: 1020/530, loss: 0.057431790977716446
2023-01-21 10:16:19.424255: step: 1024/530, loss: 0.07357635349035263
2023-01-21 10:16:20.551764: step: 1028/530, loss: 0.0789494514465332
2023-01-21 10:16:21.670991: step: 1032/530, loss: 0.09398308396339417
2023-01-21 10:16:22.791725: step: 1036/530, loss: 0.03413248062133789
2023-01-21 10:16:23.937066: step: 1040/530, loss: 0.056510262191295624
2023-01-21 10:16:25.037913: step: 1044/530, loss: 0.06041078269481659
2023-01-21 10:16:26.122996: step: 1048/530, loss: 0.07611873000860214
2023-01-21 10:16:27.245886: step: 1052/530, loss: 0.0721227154135704
2023-01-21 10:16:28.342544: step: 1056/530, loss: 0.04976511001586914
2023-01-21 10:16:29.506805: step: 1060/530, loss: 0.08610481768846512
2023-01-21 10:16:30.631899: step: 1064/530, loss: 0.13222475349903107
2023-01-21 10:16:31.757262: step: 1068/530, loss: 0.03965482860803604
2023-01-21 10:16:32.866556: step: 1072/530, loss: 0.14394934475421906
2023-01-21 10:16:33.984541: step: 1076/530, loss: 0.01928567886352539
2023-01-21 10:16:35.072478: step: 1080/530, loss: 0.00718533992767334
2023-01-21 10:16:36.189848: step: 1084/530, loss: 1.941673994064331
2023-01-21 10:16:37.310139: step: 1088/530, loss: 0.2159833014011383
2023-01-21 10:16:38.448283: step: 1092/530, loss: 0.020224381238222122
2023-01-21 10:16:39.532762: step: 1096/530, loss: 0.03317739814519882
2023-01-21 10:16:40.645606: step: 1100/530, loss: 0.046278856694698334
2023-01-21 10:16:41.749452: step: 1104/530, loss: 0.08630237728357315
2023-01-21 10:16:42.844114: step: 1108/530, loss: 0.04170408472418785
2023-01-21 10:16:43.961086: step: 1112/530, loss: 0.03770847246050835
2023-01-21 10:16:45.056891: step: 1116/530, loss: 0.04045286029577255
2023-01-21 10:16:46.170344: step: 1120/530, loss: 0.10530614852905273
2023-01-21 10:16:47.269597: step: 1124/530, loss: 0.013080048374831676
2023-01-21 10:16:48.397606: step: 1128/530, loss: 0.03911328688263893
2023-01-21 10:16:49.540570: step: 1132/530, loss: 0.06311684101819992
2023-01-21 10:16:50.646645: step: 1136/530, loss: 0.3849724531173706
2023-01-21 10:16:51.749907: step: 1140/530, loss: 0.04035468399524689
2023-01-21 10:16:52.866993: step: 1144/530, loss: 0.06432771682739258
2023-01-21 10:16:53.983821: step: 1148/530, loss: 0.0263398177921772
2023-01-21 10:16:55.082940: step: 1152/530, loss: 0.05226574093103409
2023-01-21 10:16:56.204451: step: 1156/530, loss: 0.0528779998421669
2023-01-21 10:16:57.352353: step: 1160/530, loss: 0.035801030695438385
2023-01-21 10:16:58.473252: step: 1164/530, loss: 0.00797119177877903
2023-01-21 10:16:59.571301: step: 1168/530, loss: 0.03395795822143555
2023-01-21 10:17:00.697364: step: 1172/530, loss: 0.11708612740039825
2023-01-21 10:17:01.811344: step: 1176/530, loss: 0.0692654624581337
2023-01-21 10:17:02.934960: step: 1180/530, loss: 0.0196533203125
2023-01-21 10:17:04.030699: step: 1184/530, loss: 0.04314699396491051
2023-01-21 10:17:05.117904: step: 1188/530, loss: 0.03473053127527237
2023-01-21 10:17:06.272092: step: 1192/530, loss: 0.21452751755714417
2023-01-21 10:17:07.425864: step: 1196/530, loss: 0.08094115555286407
2023-01-21 10:17:08.525224: step: 1200/530, loss: 0.002301883650943637
2023-01-21 10:17:09.622434: step: 1204/530, loss: 0.016067886725068092
2023-01-21 10:17:10.717729: step: 1208/530, loss: 0.07824338972568512
2023-01-21 10:17:11.811651: step: 1212/530, loss: 0.060262683779001236
2023-01-21 10:17:12.927677: step: 1216/530, loss: 0.01785602606832981
2023-01-21 10:17:14.020201: step: 1220/530, loss: 0.02940216101706028
2023-01-21 10:17:15.153434: step: 1224/530, loss: 0.04442715644836426
2023-01-21 10:17:16.266538: step: 1228/530, loss: 0.013821602798998356
2023-01-21 10:17:17.342678: step: 1232/530, loss: 0.06709976494312286
2023-01-21 10:17:18.461461: step: 1236/530, loss: 0.22147181630134583
2023-01-21 10:17:19.547714: step: 1240/530, loss: 0.31296637654304504
2023-01-21 10:17:20.644959: step: 1244/530, loss: 0.040456678718328476
2023-01-21 10:17:21.746178: step: 1248/530, loss: 0.004106124397367239
2023-01-21 10:17:22.860472: step: 1252/530, loss: 0.2375870794057846
2023-01-21 10:17:23.988518: step: 1256/530, loss: 0.06646070629358292
2023-01-21 10:17:25.108351: step: 1260/530, loss: 0.10059194266796112
2023-01-21 10:17:26.187346: step: 1264/530, loss: 0.009367180056869984
2023-01-21 10:17:27.312278: step: 1268/530, loss: 0.23852328956127167
2023-01-21 10:17:28.454400: step: 1272/530, loss: 0.06304369121789932
2023-01-21 10:17:29.583264: step: 1276/530, loss: 0.4579445719718933
2023-01-21 10:17:30.675378: step: 1280/530, loss: 0.010230732150375843
2023-01-21 10:17:31.777916: step: 1284/530, loss: 0.06442470848560333
2023-01-21 10:17:32.880882: step: 1288/530, loss: 0.04117155447602272
2023-01-21 10:17:33.995563: step: 1292/530, loss: 0.14889155328273773
2023-01-21 10:17:35.129192: step: 1296/530, loss: 0.038118839263916016
2023-01-21 10:17:36.224339: step: 1300/530, loss: 0.09388618171215057
2023-01-21 10:17:37.366638: step: 1304/530, loss: 0.035646773874759674
2023-01-21 10:17:38.479757: step: 1308/530, loss: 0.36589887738227844
2023-01-21 10:17:39.595380: step: 1312/530, loss: 0.12225160747766495
2023-01-21 10:17:40.719761: step: 1316/530, loss: 0.12188606709241867
2023-01-21 10:17:41.833591: step: 1320/530, loss: 0.0367191806435585
2023-01-21 10:17:42.943372: step: 1324/530, loss: 0.05857901647686958
2023-01-21 10:17:44.048743: step: 1328/530, loss: 0.48173198103904724
2023-01-21 10:17:45.183811: step: 1332/530, loss: 0.0340024009346962
2023-01-21 10:17:46.281655: step: 1336/530, loss: 0.014490509405732155
2023-01-21 10:17:47.378996: step: 1340/530, loss: 0.03950996324419975
2023-01-21 10:17:48.466339: step: 1344/530, loss: 0.02537059783935547
2023-01-21 10:17:49.578998: step: 1348/530, loss: 0.009778786450624466
2023-01-21 10:17:50.676818: step: 1352/530, loss: 0.046988748013973236
2023-01-21 10:17:51.787013: step: 1356/530, loss: 0.04196920618414879
2023-01-21 10:17:52.888536: step: 1360/530, loss: 0.05027418211102486
2023-01-21 10:17:54.029198: step: 1364/530, loss: 0.04635734483599663
2023-01-21 10:17:55.128193: step: 1368/530, loss: 0.10426755249500275
2023-01-21 10:17:56.231848: step: 1372/530, loss: 0.04180192947387695
2023-01-21 10:17:57.344963: step: 1376/530, loss: 0.060674384236335754
2023-01-21 10:17:58.447610: step: 1380/530, loss: 0.04168133810162544
2023-01-21 10:17:59.538375: step: 1384/530, loss: 0.013026809319853783
2023-01-21 10:18:00.681310: step: 1388/530, loss: 0.0715143233537674
2023-01-21 10:18:01.775372: step: 1392/530, loss: 0.06671466678380966
2023-01-21 10:18:02.893979: step: 1396/530, loss: 0.3159492611885071
2023-01-21 10:18:04.032444: step: 1400/530, loss: 0.21715860068798065
2023-01-21 10:18:05.126891: step: 1404/530, loss: 0.11965981125831604
2023-01-21 10:18:06.225629: step: 1408/530, loss: 0.009777355939149857
2023-01-21 10:18:07.329338: step: 1412/530, loss: 0.068603515625
2023-01-21 10:18:08.417201: step: 1416/530, loss: 0.044983960688114166
2023-01-21 10:18:09.557880: step: 1420/530, loss: 0.4129413068294525
2023-01-21 10:18:10.682509: step: 1424/530, loss: 0.08805418014526367
2023-01-21 10:18:11.763972: step: 1428/530, loss: 0.03787889704108238
2023-01-21 10:18:12.848617: step: 1432/530, loss: 0.011502361856400967
2023-01-21 10:18:13.931487: step: 1436/530, loss: 0.16273340582847595
2023-01-21 10:18:15.027995: step: 1440/530, loss: 0.11285905539989471
2023-01-21 10:18:16.120320: step: 1444/530, loss: 0.06554565578699112
2023-01-21 10:18:17.210352: step: 1448/530, loss: 0.013885116204619408
2023-01-21 10:18:18.335893: step: 1452/530, loss: 0.10244350135326385
2023-01-21 10:18:19.427577: step: 1456/530, loss: 0.46494922041893005
2023-01-21 10:18:20.525997: step: 1460/530, loss: 0.1074582114815712
2023-01-21 10:18:21.645864: step: 1464/530, loss: 0.025861645117402077
2023-01-21 10:18:22.750544: step: 1468/530, loss: 0.0388367623090744
2023-01-21 10:18:23.882305: step: 1472/530, loss: 0.05124073103070259
2023-01-21 10:18:24.969367: step: 1476/530, loss: 0.3171003460884094
2023-01-21 10:18:26.078162: step: 1480/530, loss: 0.4540640413761139
2023-01-21 10:18:27.187748: step: 1484/530, loss: 0.40675750374794006
2023-01-21 10:18:28.304454: step: 1488/530, loss: 0.0033395770005881786
2023-01-21 10:18:29.408638: step: 1492/530, loss: 0.3871908187866211
2023-01-21 10:18:30.509313: step: 1496/530, loss: 0.04248657450079918
2023-01-21 10:18:31.634884: step: 1500/530, loss: 0.06422571837902069
2023-01-21 10:18:32.757257: step: 1504/530, loss: 0.12141895294189453
2023-01-21 10:18:33.864791: step: 1508/530, loss: 0.0391656868159771
2023-01-21 10:18:34.941489: step: 1512/530, loss: 0.049579814076423645
2023-01-21 10:18:36.030131: step: 1516/530, loss: 0.07856154441833496
2023-01-21 10:18:37.129782: step: 1520/530, loss: 0.020325278863310814
2023-01-21 10:18:38.229265: step: 1524/530, loss: 0.09964756667613983
2023-01-21 10:18:39.356905: step: 1528/530, loss: 0.18442697823047638
2023-01-21 10:18:40.458870: step: 1532/530, loss: 0.38138407468795776
2023-01-21 10:18:41.595930: step: 1536/530, loss: 0.017789460718631744
2023-01-21 10:18:42.727712: step: 1540/530, loss: 0.12706327438354492
2023-01-21 10:18:43.832952: step: 1544/530, loss: 0.05959014967083931
2023-01-21 10:18:44.949977: step: 1548/530, loss: 0.13648748397827148
2023-01-21 10:18:46.057571: step: 1552/530, loss: 0.020630933344364166
2023-01-21 10:18:47.188628: step: 1556/530, loss: 0.1003485694527626
2023-01-21 10:18:48.338418: step: 1560/530, loss: 0.10602112114429474
2023-01-21 10:18:49.471217: step: 1564/530, loss: 0.0911487564444542
2023-01-21 10:18:50.601680: step: 1568/530, loss: 0.029360296204686165
2023-01-21 10:18:51.732603: step: 1572/530, loss: 0.03755206987261772
2023-01-21 10:18:52.863093: step: 1576/530, loss: 0.09202270209789276
2023-01-21 10:18:53.990691: step: 1580/530, loss: 0.09042072296142578
2023-01-21 10:18:55.120207: step: 1584/530, loss: 0.13148507475852966
2023-01-21 10:18:56.210965: step: 1588/530, loss: 0.019042586907744408
2023-01-21 10:18:57.299948: step: 1592/530, loss: 0.051201630383729935
2023-01-21 10:18:58.441703: step: 1596/530, loss: 0.0725800171494484
2023-01-21 10:18:59.547428: step: 1600/530, loss: 0.024500275030732155
2023-01-21 10:19:00.671015: step: 1604/530, loss: 0.048778679221868515
2023-01-21 10:19:01.783338: step: 1608/530, loss: 0.04110026732087135
2023-01-21 10:19:02.878867: step: 1612/530, loss: 0.14023666083812714
2023-01-21 10:19:04.011077: step: 1616/530, loss: 0.24167995154857635
2023-01-21 10:19:05.142960: step: 1620/530, loss: 0.13343429565429688
2023-01-21 10:19:06.301572: step: 1624/530, loss: 0.3986698091030121
2023-01-21 10:19:07.409466: step: 1628/530, loss: 0.011958790011703968
2023-01-21 10:19:08.551451: step: 1632/530, loss: 0.042142488062381744
2023-01-21 10:19:09.640356: step: 1636/530, loss: 0.0029730796813964844
2023-01-21 10:19:10.745784: step: 1640/530, loss: 0.08714018017053604
2023-01-21 10:19:11.869437: step: 1644/530, loss: 0.08416728675365448
2023-01-21 10:19:12.976756: step: 1648/530, loss: 0.1551641970872879
2023-01-21 10:19:14.065835: step: 1652/530, loss: 0.24525488913059235
2023-01-21 10:19:15.156448: step: 1656/530, loss: 0.624038577079773
2023-01-21 10:19:16.255539: step: 1660/530, loss: 0.04034533351659775
2023-01-21 10:19:17.352942: step: 1664/530, loss: 0.054014015942811966
2023-01-21 10:19:18.470746: step: 1668/530, loss: 0.012287164106965065
2023-01-21 10:19:19.601109: step: 1672/530, loss: 0.4195510745048523
2023-01-21 10:19:20.717539: step: 1676/530, loss: 1.1276097297668457
2023-01-21 10:19:21.819679: step: 1680/530, loss: 0.024541163817048073
2023-01-21 10:19:22.935039: step: 1684/530, loss: 0.05865850672125816
2023-01-21 10:19:24.058676: step: 1688/530, loss: 0.01982259750366211
2023-01-21 10:19:25.220419: step: 1692/530, loss: 0.12230491638183594
2023-01-21 10:19:26.310418: step: 1696/530, loss: 0.03255271911621094
2023-01-21 10:19:27.421951: step: 1700/530, loss: 0.1069973036646843
2023-01-21 10:19:28.527542: step: 1704/530, loss: 0.07531814277172089
2023-01-21 10:19:29.628331: step: 1708/530, loss: 0.016759682446718216
2023-01-21 10:19:30.732912: step: 1712/530, loss: 0.06693068146705627
2023-01-21 10:19:31.870761: step: 1716/530, loss: 0.0857764258980751
2023-01-21 10:19:32.975899: step: 1720/530, loss: 0.018464839085936546
2023-01-21 10:19:34.087793: step: 1724/530, loss: 0.02588810957968235
2023-01-21 10:19:35.179600: step: 1728/530, loss: 0.030108120292425156
2023-01-21 10:19:36.282832: step: 1732/530, loss: 0.03959674760699272
2023-01-21 10:19:37.387585: step: 1736/530, loss: 0.02285795286297798
2023-01-21 10:19:38.484998: step: 1740/530, loss: 0.10198817402124405
2023-01-21 10:19:39.609018: step: 1744/530, loss: 0.08242588490247726
2023-01-21 10:19:40.712177: step: 1748/530, loss: 0.08125295490026474
2023-01-21 10:19:41.809083: step: 1752/530, loss: 0.05591898411512375
2023-01-21 10:19:42.908582: step: 1756/530, loss: 0.04361391067504883
2023-01-21 10:19:44.011575: step: 1760/530, loss: 0.06449469923973083
2023-01-21 10:19:45.144014: step: 1764/530, loss: 0.04774647206068039
2023-01-21 10:19:46.240026: step: 1768/530, loss: 0.10913410782814026
2023-01-21 10:19:47.335549: step: 1772/530, loss: 0.028405381366610527
2023-01-21 10:19:48.423563: step: 1776/530, loss: 0.01448202133178711
2023-01-21 10:19:49.537578: step: 1780/530, loss: 0.5212539434432983
2023-01-21 10:19:50.658706: step: 1784/530, loss: 0.03967972844839096
2023-01-21 10:19:51.765717: step: 1788/530, loss: 0.12832984328269958
2023-01-21 10:19:52.897613: step: 1792/530, loss: 0.05873413011431694
2023-01-21 10:19:54.017291: step: 1796/530, loss: 0.07915592938661575
2023-01-21 10:19:55.160073: step: 1800/530, loss: 0.03998732566833496
2023-01-21 10:19:56.264285: step: 1804/530, loss: 0.0263550765812397
2023-01-21 10:19:57.396138: step: 1808/530, loss: 0.0058193206787109375
2023-01-21 10:19:58.485850: step: 1812/530, loss: 0.012419604696333408
2023-01-21 10:19:59.571859: step: 1816/530, loss: 0.01571207121014595
2023-01-21 10:20:00.674331: step: 1820/530, loss: 0.12479066848754883
2023-01-21 10:20:01.775662: step: 1824/530, loss: 0.023221779614686966
2023-01-21 10:20:02.881144: step: 1828/530, loss: 0.048781681805849075
2023-01-21 10:20:04.012769: step: 1832/530, loss: 0.14184695482254028
2023-01-21 10:20:05.111243: step: 1836/530, loss: 0.056687261909246445
2023-01-21 10:20:06.226633: step: 1840/530, loss: 0.024855613708496094
2023-01-21 10:20:07.316010: step: 1844/530, loss: 0.05488219112157822
2023-01-21 10:20:08.423458: step: 1848/530, loss: 0.009911155328154564
2023-01-21 10:20:09.524643: step: 1852/530, loss: 0.16133423149585724
2023-01-21 10:20:10.623853: step: 1856/530, loss: 0.06242332607507706
2023-01-21 10:20:11.716736: step: 1860/530, loss: 0.29647397994995117
2023-01-21 10:20:12.818342: step: 1864/530, loss: 0.09084615856409073
2023-01-21 10:20:13.914510: step: 1868/530, loss: 0.011372281238436699
2023-01-21 10:20:15.019702: step: 1872/530, loss: 0.055965423583984375
2023-01-21 10:20:16.146516: step: 1876/530, loss: 0.15248116850852966
2023-01-21 10:20:17.243881: step: 1880/530, loss: 0.09900913387537003
2023-01-21 10:20:18.376783: step: 1884/530, loss: 0.005707359407097101
2023-01-21 10:20:19.510788: step: 1888/530, loss: 0.42601072788238525
2023-01-21 10:20:20.622544: step: 1892/530, loss: 0.04569735378026962
2023-01-21 10:20:21.734695: step: 1896/530, loss: 0.036768246442079544
2023-01-21 10:20:22.819094: step: 1900/530, loss: 0.052835848182439804
2023-01-21 10:20:23.933708: step: 1904/530, loss: 0.07460003346204758
2023-01-21 10:20:25.027776: step: 1908/530, loss: 0.0066308025270700455
2023-01-21 10:20:26.141161: step: 1912/530, loss: 0.008951663970947266
2023-01-21 10:20:27.258567: step: 1916/530, loss: 0.0402749702334404
2023-01-21 10:20:28.369972: step: 1920/530, loss: 0.05490460246801376
2023-01-21 10:20:29.463095: step: 1924/530, loss: 0.043356988579034805
2023-01-21 10:20:30.587717: step: 1928/530, loss: 0.08829774707555771
2023-01-21 10:20:31.699186: step: 1932/530, loss: 0.03699655830860138
2023-01-21 10:20:32.801528: step: 1936/530, loss: 0.11772795021533966
2023-01-21 10:20:33.920381: step: 1940/530, loss: 0.12338696420192719
2023-01-21 10:20:35.060664: step: 1944/530, loss: 0.03663668781518936
2023-01-21 10:20:36.142093: step: 1948/530, loss: 0.022455787286162376
2023-01-21 10:20:37.231696: step: 1952/530, loss: 0.03382702171802521
2023-01-21 10:20:38.358363: step: 1956/530, loss: 0.037178803235292435
2023-01-21 10:20:39.458424: step: 1960/530, loss: 0.028437137603759766
2023-01-21 10:20:40.564565: step: 1964/530, loss: 0.12222099304199219
2023-01-21 10:20:41.693739: step: 1968/530, loss: 0.12996742129325867
2023-01-21 10:20:42.793420: step: 1972/530, loss: 0.02355632744729519
2023-01-21 10:20:43.900502: step: 1976/530, loss: 0.013407516293227673
2023-01-21 10:20:45.001136: step: 1980/530, loss: 0.0712771862745285
2023-01-21 10:20:46.137005: step: 1984/530, loss: 0.2157619595527649
2023-01-21 10:20:47.233072: step: 1988/530, loss: 0.011900784447789192
2023-01-21 10:20:48.362271: step: 1992/530, loss: 0.04205045849084854
2023-01-21 10:20:49.462715: step: 1996/530, loss: 0.008880043402314186
2023-01-21 10:20:50.570211: step: 2000/530, loss: 0.09431519359350204
2023-01-21 10:20:51.668362: step: 2004/530, loss: 0.1522396206855774
2023-01-21 10:20:52.812269: step: 2008/530, loss: 0.051564596593379974
2023-01-21 10:20:53.909240: step: 2012/530, loss: 0.07655926048755646
2023-01-21 10:20:55.025557: step: 2016/530, loss: 0.024863576516509056
2023-01-21 10:20:56.130916: step: 2020/530, loss: 0.12144012749195099
2023-01-21 10:20:57.266332: step: 2024/530, loss: 0.0800497978925705
2023-01-21 10:20:58.385796: step: 2028/530, loss: 0.0056365965865552425
2023-01-21 10:20:59.503814: step: 2032/530, loss: 0.005035442300140858
2023-01-21 10:21:00.610580: step: 2036/530, loss: 0.047686293721199036
2023-01-21 10:21:01.757082: step: 2040/530, loss: 0.07552909851074219
2023-01-21 10:21:02.883955: step: 2044/530, loss: 0.04365091398358345
2023-01-21 10:21:04.043718: step: 2048/530, loss: 0.002990531735122204
2023-01-21 10:21:05.196028: step: 2052/530, loss: 0.07317504286766052
2023-01-21 10:21:06.312415: step: 2056/530, loss: 0.13590799272060394
2023-01-21 10:21:07.401053: step: 2060/530, loss: 0.14554038643836975
2023-01-21 10:21:08.522822: step: 2064/530, loss: 0.12408009171485901
2023-01-21 10:21:09.627364: step: 2068/530, loss: 0.0359250083565712
2023-01-21 10:21:10.758117: step: 2072/530, loss: 0.13010473549365997
2023-01-21 10:21:11.840028: step: 2076/530, loss: 0.002796173095703125
2023-01-21 10:21:12.978630: step: 2080/530, loss: 0.07012243568897247
2023-01-21 10:21:14.093160: step: 2084/530, loss: 0.0349484458565712
2023-01-21 10:21:15.191687: step: 2088/530, loss: 0.013703251257538795
2023-01-21 10:21:16.300123: step: 2092/530, loss: 0.025367069989442825
2023-01-21 10:21:17.397106: step: 2096/530, loss: 0.012494039721786976
2023-01-21 10:21:18.476192: step: 2100/530, loss: 0.04867153242230415
2023-01-21 10:21:19.583584: step: 2104/530, loss: 0.07568585127592087
2023-01-21 10:21:20.730001: step: 2108/530, loss: 0.007527160923928022
2023-01-21 10:21:21.823858: step: 2112/530, loss: 0.013137436471879482
2023-01-21 10:21:22.950973: step: 2116/530, loss: 0.012353325262665749
2023-01-21 10:21:24.038901: step: 2120/530, loss: 0.021196747198700905
==================================================
Loss: 0.095
--------------------
Dev: {'event': {'p': 0.6234906695938529, 'r': 0.7563249001331558, 'f1': 0.6835138387484957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Test: {'event': {'p': 0.6422232601588043, 'r': 0.8012820512820513, 'f1': 0.7129893699766658}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Chinese: {'event': {'p': 0.6081081081081081, 'r': 0.8333333333333334, 'f1': 0.7031250000000001}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Korean: {'event': {'p': 0.6, 'r': 0.5714285714285714, 'f1': 0.5853658536585366}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Russian: {'event': {'p': 0.4857142857142857, 'r': 0.4722222222222222, 'f1': 0.47887323943661975}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5708622398414271, 'r': 0.7669773635153129, 'f1': 0.6545454545454545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Chinese: {'event': {'p': 0.6044052863436123, 'r': 0.7995337995337995, 'f1': 0.6884094330155545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Chinese: {'event': {'p': 0.6578947368421053, 'r': 0.9259259259259259, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6466512702078522, 'r': 0.7456724367509987, 'f1': 0.6926406926406927}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.6762148337595908, 'r': 0.7703962703962703, 'f1': 0.7202397166984473}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 10:22:03.766267: step: 4/530, loss: 0.08964863419532776
2023-01-21 10:22:04.854035: step: 8/530, loss: 0.02247953601181507
2023-01-21 10:22:05.978233: step: 12/530, loss: 0.024763204157352448
2023-01-21 10:22:07.104742: step: 16/530, loss: 0.11863622069358826
2023-01-21 10:22:08.237064: step: 20/530, loss: 0.0612177848815918
2023-01-21 10:22:09.359992: step: 24/530, loss: 0.028406143188476562
2023-01-21 10:22:10.469718: step: 28/530, loss: 0.04806508868932724
2023-01-21 10:22:11.599077: step: 32/530, loss: 0.019141722470521927
2023-01-21 10:22:12.700527: step: 36/530, loss: 0.030022049322724342
2023-01-21 10:22:13.840781: step: 40/530, loss: 0.13446128368377686
2023-01-21 10:22:14.968961: step: 44/530, loss: 0.008623600006103516
2023-01-21 10:22:16.079046: step: 48/530, loss: 0.014078712090849876
2023-01-21 10:22:17.197817: step: 52/530, loss: 0.03209686279296875
2023-01-21 10:22:18.303580: step: 56/530, loss: 0.027567386627197266
2023-01-21 10:22:19.423204: step: 60/530, loss: 0.04089780151844025
2023-01-21 10:22:20.531932: step: 64/530, loss: 0.017711259424686432
2023-01-21 10:22:21.662275: step: 68/530, loss: 0.06816921383142471
2023-01-21 10:22:22.757462: step: 72/530, loss: 0.02695159800350666
2023-01-21 10:22:23.903747: step: 76/530, loss: 0.02095775678753853
2023-01-21 10:22:25.012105: step: 80/530, loss: 0.037688061594963074
2023-01-21 10:22:26.107365: step: 84/530, loss: 0.049540139734745026
2023-01-21 10:22:27.220455: step: 88/530, loss: 0.005287385080009699
2023-01-21 10:22:28.350676: step: 92/530, loss: 0.10928115248680115
2023-01-21 10:22:29.461150: step: 96/530, loss: 0.10061845928430557
2023-01-21 10:22:30.550599: step: 100/530, loss: 0.02756796032190323
2023-01-21 10:22:31.661907: step: 104/530, loss: 0.02692422829568386
2023-01-21 10:22:32.750310: step: 108/530, loss: 0.17764797806739807
2023-01-21 10:22:33.901862: step: 112/530, loss: 0.052677348256111145
2023-01-21 10:22:35.015048: step: 116/530, loss: 0.041715528815984726
2023-01-21 10:22:36.127321: step: 120/530, loss: 0.05001135170459747
2023-01-21 10:22:37.231043: step: 124/530, loss: 0.021344946697354317
2023-01-21 10:22:38.347928: step: 128/530, loss: 0.035292696207761765
2023-01-21 10:22:39.450760: step: 132/530, loss: 0.10476885735988617
2023-01-21 10:22:40.563853: step: 136/530, loss: 0.12089284509420395
2023-01-21 10:22:41.702185: step: 140/530, loss: 0.056166935712099075
2023-01-21 10:22:42.830690: step: 144/530, loss: 0.03636594116687775
2023-01-21 10:22:43.932159: step: 148/530, loss: 0.007698822300881147
2023-01-21 10:22:45.052305: step: 152/530, loss: 0.2300596535205841
2023-01-21 10:22:46.182432: step: 156/530, loss: 0.052889633923769
2023-01-21 10:22:47.280118: step: 160/530, loss: 0.07069053500890732
2023-01-21 10:22:48.405899: step: 164/530, loss: 0.044928453862667084
2023-01-21 10:22:49.526343: step: 168/530, loss: 0.00870828703045845
2023-01-21 10:22:50.625023: step: 172/530, loss: 0.03944873809814453
2023-01-21 10:22:51.715868: step: 176/530, loss: 0.004895925521850586
2023-01-21 10:22:52.823589: step: 180/530, loss: 0.3493845462799072
2023-01-21 10:22:53.939811: step: 184/530, loss: 0.03560657799243927
2023-01-21 10:22:55.071419: step: 188/530, loss: 0.0947975218296051
2023-01-21 10:22:56.184414: step: 192/530, loss: 0.13313019275665283
2023-01-21 10:22:57.311897: step: 196/530, loss: 0.0647134780883789
2023-01-21 10:22:58.458289: step: 200/530, loss: 0.04189910739660263
2023-01-21 10:22:59.560733: step: 204/530, loss: 0.46162986755371094
2023-01-21 10:23:00.678131: step: 208/530, loss: 0.053897857666015625
2023-01-21 10:23:01.804507: step: 212/530, loss: 0.0787515640258789
2023-01-21 10:23:02.939548: step: 216/530, loss: 0.05760164558887482
2023-01-21 10:23:04.009576: step: 220/530, loss: 0.060935311019420624
2023-01-21 10:23:05.099913: step: 224/530, loss: 0.19133806228637695
2023-01-21 10:23:06.186293: step: 228/530, loss: 0.01637706719338894
2023-01-21 10:23:07.292395: step: 232/530, loss: 0.0034931180998682976
2023-01-21 10:23:08.375313: step: 236/530, loss: 0.06207694858312607
2023-01-21 10:23:09.500638: step: 240/530, loss: 0.1389867067337036
2023-01-21 10:23:10.608523: step: 244/530, loss: 0.06269846856594086
2023-01-21 10:23:11.709894: step: 248/530, loss: 0.003131961915642023
2023-01-21 10:23:12.822419: step: 252/530, loss: 0.04863929748535156
2023-01-21 10:23:13.948697: step: 256/530, loss: 0.06426163017749786
2023-01-21 10:23:15.058631: step: 260/530, loss: 0.0611545592546463
2023-01-21 10:23:16.167707: step: 264/530, loss: 0.01520681381225586
2023-01-21 10:23:17.300740: step: 268/530, loss: 0.053270816802978516
2023-01-21 10:23:18.405005: step: 272/530, loss: 0.0883183479309082
2023-01-21 10:23:19.522846: step: 276/530, loss: 0.03669586405158043
2023-01-21 10:23:20.640156: step: 280/530, loss: 0.23922061920166016
2023-01-21 10:23:21.764587: step: 284/530, loss: 0.15121793746948242
2023-01-21 10:23:22.866398: step: 288/530, loss: 0.08981809765100479
2023-01-21 10:23:23.984837: step: 292/530, loss: 0.05097770690917969
2023-01-21 10:23:25.101138: step: 296/530, loss: 0.5968635082244873
2023-01-21 10:23:26.198161: step: 300/530, loss: 0.02820425108075142
2023-01-21 10:23:27.307190: step: 304/530, loss: 0.03298044204711914
2023-01-21 10:23:28.432704: step: 308/530, loss: 0.12087040394544601
2023-01-21 10:23:29.527223: step: 312/530, loss: 0.010115813463926315
2023-01-21 10:23:30.624864: step: 316/530, loss: 0.049526214599609375
2023-01-21 10:23:31.747082: step: 320/530, loss: 0.0369388572871685
2023-01-21 10:23:32.826944: step: 324/530, loss: 0.023676013574004173
2023-01-21 10:23:33.962831: step: 328/530, loss: 0.07032632827758789
2023-01-21 10:23:35.092441: step: 332/530, loss: 0.08553314208984375
2023-01-21 10:23:36.186044: step: 336/530, loss: 0.027059080079197884
2023-01-21 10:23:37.314841: step: 340/530, loss: 0.07036428898572922
2023-01-21 10:23:38.434415: step: 344/530, loss: 0.05050468444824219
2023-01-21 10:23:39.550143: step: 348/530, loss: 0.04969625547528267
2023-01-21 10:23:40.675328: step: 352/530, loss: 0.7258001565933228
2023-01-21 10:23:41.774703: step: 356/530, loss: 0.0022842169273644686
2023-01-21 10:23:42.874185: step: 360/530, loss: 0.0031315325759351254
2023-01-21 10:23:43.959460: step: 364/530, loss: 0.07224655151367188
2023-01-21 10:23:45.083710: step: 368/530, loss: 0.056932926177978516
2023-01-21 10:23:46.165993: step: 372/530, loss: 0.03524224832653999
2023-01-21 10:23:47.290875: step: 376/530, loss: 0.09698023647069931
2023-01-21 10:23:48.414156: step: 380/530, loss: 0.07805786281824112
2023-01-21 10:23:49.509009: step: 384/530, loss: 0.0855921283364296
2023-01-21 10:23:50.620178: step: 388/530, loss: 0.10835013538599014
2023-01-21 10:23:51.750519: step: 392/530, loss: 0.021238327026367188
2023-01-21 10:23:52.847638: step: 396/530, loss: 0.0668153315782547
2023-01-21 10:23:53.959166: step: 400/530, loss: 0.05712556838989258
2023-01-21 10:23:55.071588: step: 404/530, loss: 0.05562472343444824
2023-01-21 10:23:56.176500: step: 408/530, loss: 0.13145345449447632
2023-01-21 10:23:57.271226: step: 412/530, loss: 0.16424700617790222
2023-01-21 10:23:58.387843: step: 416/530, loss: 0.01642761379480362
2023-01-21 10:23:59.491481: step: 420/530, loss: 0.04033870995044708
2023-01-21 10:24:00.590128: step: 424/530, loss: 0.006476211827248335
2023-01-21 10:24:01.687707: step: 428/530, loss: 0.003507423447445035
2023-01-21 10:24:02.789050: step: 432/530, loss: 0.008094167336821556
2023-01-21 10:24:03.912826: step: 436/530, loss: 0.27588480710983276
2023-01-21 10:24:05.040119: step: 440/530, loss: 0.17588070034980774
2023-01-21 10:24:06.141512: step: 444/530, loss: 0.08150777965784073
2023-01-21 10:24:07.243737: step: 448/530, loss: 0.06815586239099503
2023-01-21 10:24:08.332237: step: 452/530, loss: 0.006406450178474188
2023-01-21 10:24:09.420708: step: 456/530, loss: 0.047214604914188385
2023-01-21 10:24:10.539582: step: 460/530, loss: 0.03208179771900177
2023-01-21 10:24:11.651596: step: 464/530, loss: 0.03955160453915596
2023-01-21 10:24:12.754702: step: 468/530, loss: 0.056502439081668854
2023-01-21 10:24:13.848900: step: 472/530, loss: 0.05917187035083771
2023-01-21 10:24:14.955261: step: 476/530, loss: 0.033631037920713425
2023-01-21 10:24:16.057525: step: 480/530, loss: 0.040032099932432175
2023-01-21 10:24:17.188138: step: 484/530, loss: 0.18387380242347717
2023-01-21 10:24:18.283519: step: 488/530, loss: 0.003200626466423273
2023-01-21 10:24:19.414309: step: 492/530, loss: 0.18380308151245117
2023-01-21 10:24:20.542277: step: 496/530, loss: 0.0217114444822073
2023-01-21 10:24:21.645142: step: 500/530, loss: 0.021931076422333717
2023-01-21 10:24:22.771437: step: 504/530, loss: 0.13216447830200195
2023-01-21 10:24:23.879204: step: 508/530, loss: 0.04000559076666832
2023-01-21 10:24:25.002745: step: 512/530, loss: 0.02097034454345703
2023-01-21 10:24:26.114345: step: 516/530, loss: 0.015297984704375267
2023-01-21 10:24:27.194750: step: 520/530, loss: 0.03526172786951065
2023-01-21 10:24:28.296809: step: 524/530, loss: 0.46719658374786377
2023-01-21 10:24:29.393743: step: 528/530, loss: 0.036698102951049805
2023-01-21 10:24:30.505758: step: 532/530, loss: 0.2428804486989975
2023-01-21 10:24:31.611934: step: 536/530, loss: 0.052773669362068176
2023-01-21 10:24:32.726193: step: 540/530, loss: 0.0004440784396138042
2023-01-21 10:24:33.848889: step: 544/530, loss: 0.00417327880859375
2023-01-21 10:24:34.965386: step: 548/530, loss: 0.07191815227270126
2023-01-21 10:24:36.077522: step: 552/530, loss: 0.02399730682373047
2023-01-21 10:24:37.223554: step: 556/530, loss: 0.03621072694659233
2023-01-21 10:24:38.337628: step: 560/530, loss: 0.16893033683300018
2023-01-21 10:24:39.427432: step: 564/530, loss: 0.08040142059326172
2023-01-21 10:24:40.541837: step: 568/530, loss: 0.016599148511886597
2023-01-21 10:24:41.703836: step: 572/530, loss: 0.24664005637168884
2023-01-21 10:24:42.819765: step: 576/530, loss: 0.04986991733312607
2023-01-21 10:24:43.917926: step: 580/530, loss: 0.10558776557445526
2023-01-21 10:24:45.063151: step: 584/530, loss: 0.36951446533203125
2023-01-21 10:24:46.193499: step: 588/530, loss: 0.045317839831113815
2023-01-21 10:24:47.314153: step: 592/530, loss: 0.03111591562628746
2023-01-21 10:24:48.426450: step: 596/530, loss: 0.04375341162085533
2023-01-21 10:24:49.546493: step: 600/530, loss: 0.01849212683737278
2023-01-21 10:24:50.642102: step: 604/530, loss: 0.0349031426012516
2023-01-21 10:24:51.727245: step: 608/530, loss: 0.01204538345336914
2023-01-21 10:24:52.819606: step: 612/530, loss: 0.014402390457689762
2023-01-21 10:24:53.937187: step: 616/530, loss: 0.26271793246269226
2023-01-21 10:24:55.041571: step: 620/530, loss: 1.3284703493118286
2023-01-21 10:24:56.150226: step: 624/530, loss: 0.06792745739221573
2023-01-21 10:24:57.288591: step: 628/530, loss: 0.06513457745313644
2023-01-21 10:24:58.402486: step: 632/530, loss: 0.008516788482666016
2023-01-21 10:24:59.496165: step: 636/530, loss: 0.021369457244873047
2023-01-21 10:25:00.569720: step: 640/530, loss: 0.029024600982666016
2023-01-21 10:25:01.655367: step: 644/530, loss: 0.03648862987756729
2023-01-21 10:25:02.784602: step: 648/530, loss: 0.005990028381347656
2023-01-21 10:25:03.902291: step: 652/530, loss: 0.1083964854478836
2023-01-21 10:25:04.988300: step: 656/530, loss: 0.08493395149707794
2023-01-21 10:25:06.114777: step: 660/530, loss: 0.04618282616138458
2023-01-21 10:25:07.220039: step: 664/530, loss: 0.0027610301040112972
2023-01-21 10:25:08.329258: step: 668/530, loss: 0.1387912780046463
2023-01-21 10:25:09.439734: step: 672/530, loss: 0.044145964086055756
2023-01-21 10:25:10.594432: step: 676/530, loss: 0.09207496792078018
2023-01-21 10:25:11.738348: step: 680/530, loss: 0.07142724841833115
2023-01-21 10:25:12.829081: step: 684/530, loss: 0.04970664903521538
2023-01-21 10:25:13.932231: step: 688/530, loss: 0.03837089613080025
2023-01-21 10:25:15.036192: step: 692/530, loss: 0.15382727980613708
2023-01-21 10:25:16.169554: step: 696/530, loss: 0.03988952562212944
2023-01-21 10:25:17.268190: step: 700/530, loss: 0.27731189131736755
2023-01-21 10:25:18.374329: step: 704/530, loss: 0.1183788999915123
2023-01-21 10:25:19.480875: step: 708/530, loss: 0.02717600017786026
2023-01-21 10:25:20.557285: step: 712/530, loss: 0.015778923407197
2023-01-21 10:25:21.649581: step: 716/530, loss: 6.689385414123535
2023-01-21 10:25:22.757925: step: 720/530, loss: 0.10859957337379456
2023-01-21 10:25:23.883409: step: 724/530, loss: 0.16249854862689972
2023-01-21 10:25:24.980513: step: 728/530, loss: 0.004968404769897461
2023-01-21 10:25:26.067915: step: 732/530, loss: 0.07872986793518066
2023-01-21 10:25:27.189635: step: 736/530, loss: 0.09969864040613174
2023-01-21 10:25:28.300943: step: 740/530, loss: 0.05509620159864426
2023-01-21 10:25:29.386445: step: 744/530, loss: 0.022128676995635033
2023-01-21 10:25:30.488668: step: 748/530, loss: 0.0026781796477735043
2023-01-21 10:25:31.583524: step: 752/530, loss: 0.09898748248815536
2023-01-21 10:25:32.676409: step: 756/530, loss: 0.07131247967481613
2023-01-21 10:25:33.782634: step: 760/530, loss: 0.08621535450220108
2023-01-21 10:25:34.901550: step: 764/530, loss: 0.12386369705200195
2023-01-21 10:25:36.022954: step: 768/530, loss: 0.030532479286193848
2023-01-21 10:25:37.142619: step: 772/530, loss: 0.022281788289546967
2023-01-21 10:25:38.285145: step: 776/530, loss: 0.03888406977057457
2023-01-21 10:25:39.447242: step: 780/530, loss: 0.012248135171830654
2023-01-21 10:25:40.606289: step: 784/530, loss: 0.11148204654455185
2023-01-21 10:25:41.721122: step: 788/530, loss: 0.012192582711577415
2023-01-21 10:25:42.843608: step: 792/530, loss: 0.01820354536175728
2023-01-21 10:25:43.960945: step: 796/530, loss: 0.20804691314697266
2023-01-21 10:25:45.073939: step: 800/530, loss: 0.1082301139831543
2023-01-21 10:25:46.193835: step: 804/530, loss: 0.09335007518529892
2023-01-21 10:25:47.290943: step: 808/530, loss: 0.03581352159380913
2023-01-21 10:25:48.384070: step: 812/530, loss: 0.6999807953834534
2023-01-21 10:25:49.452724: step: 816/530, loss: 0.0503966361284256
2023-01-21 10:25:50.558082: step: 820/530, loss: 0.009451841935515404
2023-01-21 10:25:51.690145: step: 824/530, loss: 0.005446339026093483
2023-01-21 10:25:52.804961: step: 828/530, loss: 0.0582975372672081
2023-01-21 10:25:53.915723: step: 832/530, loss: 0.04104194790124893
2023-01-21 10:25:55.031030: step: 836/530, loss: 0.13483142852783203
2023-01-21 10:25:56.148476: step: 840/530, loss: 0.14365415275096893
2023-01-21 10:25:57.264101: step: 844/530, loss: 0.01169199962168932
2023-01-21 10:25:58.344660: step: 848/530, loss: 0.032863810658454895
2023-01-21 10:25:59.440146: step: 852/530, loss: 0.04016037657856941
2023-01-21 10:26:00.568857: step: 856/530, loss: 0.005505370907485485
2023-01-21 10:26:01.667184: step: 860/530, loss: 0.025183584541082382
2023-01-21 10:26:02.757896: step: 864/530, loss: 0.03956041485071182
2023-01-21 10:26:03.871266: step: 868/530, loss: 0.14070911705493927
2023-01-21 10:26:04.973702: step: 872/530, loss: 0.026323700323700905
2023-01-21 10:26:06.093988: step: 876/530, loss: 0.02742145210504532
2023-01-21 10:26:07.227269: step: 880/530, loss: 0.046874236315488815
2023-01-21 10:26:08.343749: step: 884/530, loss: 0.1961050033569336
2023-01-21 10:26:09.464408: step: 888/530, loss: 0.03346848487854004
2023-01-21 10:26:10.565638: step: 892/530, loss: 0.0007472991710528731
2023-01-21 10:26:11.650266: step: 896/530, loss: 0.004427146632224321
2023-01-21 10:26:12.740663: step: 900/530, loss: 0.17340460419654846
2023-01-21 10:26:13.861118: step: 904/530, loss: 0.016116762533783913
2023-01-21 10:26:14.978804: step: 908/530, loss: 0.26669663190841675
2023-01-21 10:26:16.081567: step: 912/530, loss: 0.038085177540779114
2023-01-21 10:26:17.192361: step: 916/530, loss: 0.17962369322776794
2023-01-21 10:26:18.316111: step: 920/530, loss: 0.025181390345096588
2023-01-21 10:26:19.436803: step: 924/530, loss: 0.004583931062370539
2023-01-21 10:26:20.531497: step: 928/530, loss: 0.05066213756799698
2023-01-21 10:26:21.633007: step: 932/530, loss: 0.05351286381483078
2023-01-21 10:26:22.732516: step: 936/530, loss: 0.005134677980095148
2023-01-21 10:26:23.862491: step: 940/530, loss: 0.06675248593091965
2023-01-21 10:26:25.019461: step: 944/530, loss: 0.04150128364562988
2023-01-21 10:26:26.122609: step: 948/530, loss: 0.017281342297792435
2023-01-21 10:26:27.225655: step: 952/530, loss: 0.03934922069311142
2023-01-21 10:26:28.308072: step: 956/530, loss: 0.016982747241854668
2023-01-21 10:26:29.422939: step: 960/530, loss: 0.06882262229919434
2023-01-21 10:26:30.556001: step: 964/530, loss: 0.009514236822724342
2023-01-21 10:26:31.645869: step: 968/530, loss: 0.08088560402393341
2023-01-21 10:26:32.793635: step: 972/530, loss: 0.1286792755126953
2023-01-21 10:26:33.910710: step: 976/530, loss: 0.03190579637885094
2023-01-21 10:26:35.029584: step: 980/530, loss: 0.033347032964229584
2023-01-21 10:26:36.175816: step: 984/530, loss: 0.09323425590991974
2023-01-21 10:26:37.316533: step: 988/530, loss: 0.057544805109500885
2023-01-21 10:26:38.444438: step: 992/530, loss: 0.023393917828798294
2023-01-21 10:26:39.564289: step: 996/530, loss: 0.006495857145637274
2023-01-21 10:26:40.691897: step: 1000/530, loss: 0.05317812040448189
2023-01-21 10:26:41.810776: step: 1004/530, loss: 0.06906137615442276
2023-01-21 10:26:42.934171: step: 1008/530, loss: 0.02431979402899742
2023-01-21 10:26:44.060158: step: 1012/530, loss: 0.05707371234893799
2023-01-21 10:26:45.187123: step: 1016/530, loss: 0.2990041673183441
2023-01-21 10:26:46.315494: step: 1020/530, loss: 0.2590957581996918
2023-01-21 10:26:47.430192: step: 1024/530, loss: 0.04141458123922348
2023-01-21 10:26:48.524936: step: 1028/530, loss: 0.23832359910011292
2023-01-21 10:26:49.652780: step: 1032/530, loss: 0.04406547546386719
2023-01-21 10:26:50.746211: step: 1036/530, loss: 0.03817172348499298
2023-01-21 10:26:51.829484: step: 1040/530, loss: 0.0006984710926190019
2023-01-21 10:26:52.939116: step: 1044/530, loss: 0.09312897175550461
2023-01-21 10:26:54.047225: step: 1048/530, loss: 0.30806446075439453
2023-01-21 10:26:55.193130: step: 1052/530, loss: 0.1998034417629242
2023-01-21 10:26:56.295056: step: 1056/530, loss: 0.0285782590508461
2023-01-21 10:26:57.411380: step: 1060/530, loss: 0.016660405322909355
2023-01-21 10:26:58.536853: step: 1064/530, loss: 0.0252398494631052
2023-01-21 10:26:59.650834: step: 1068/530, loss: 0.11393900215625763
2023-01-21 10:27:00.765265: step: 1072/530, loss: 0.04579200595617294
2023-01-21 10:27:01.837858: step: 1076/530, loss: 0.08616933226585388
2023-01-21 10:27:02.978385: step: 1080/530, loss: 0.012139225378632545
2023-01-21 10:27:04.082443: step: 1084/530, loss: 0.034149982035160065
2023-01-21 10:27:05.191044: step: 1088/530, loss: 0.05119438096880913
2023-01-21 10:27:06.317156: step: 1092/530, loss: 0.04370078817009926
2023-01-21 10:27:07.421979: step: 1096/530, loss: 0.047237493097782135
2023-01-21 10:27:08.527299: step: 1100/530, loss: 0.005970764439553022
2023-01-21 10:27:09.644798: step: 1104/530, loss: 0.038091327995061874
2023-01-21 10:27:10.762931: step: 1108/530, loss: 0.01807422749698162
2023-01-21 10:27:11.850154: step: 1112/530, loss: 0.024179697036743164
2023-01-21 10:27:12.994576: step: 1116/530, loss: 0.26404449343681335
2023-01-21 10:27:14.103570: step: 1120/530, loss: 0.07606907188892365
2023-01-21 10:27:15.230836: step: 1124/530, loss: 0.03739500045776367
2023-01-21 10:27:16.314355: step: 1128/530, loss: 0.0225354190915823
2023-01-21 10:27:17.434155: step: 1132/530, loss: 0.05751834064722061
2023-01-21 10:27:18.548625: step: 1136/530, loss: 0.24944019317626953
2023-01-21 10:27:19.662439: step: 1140/530, loss: 0.009146571159362793
2023-01-21 10:27:20.799508: step: 1144/530, loss: 0.020014572888612747
2023-01-21 10:27:21.894939: step: 1148/530, loss: 0.01992349699139595
2023-01-21 10:27:23.009387: step: 1152/530, loss: 0.09063081443309784
2023-01-21 10:27:24.113138: step: 1156/530, loss: 0.019260788336396217
2023-01-21 10:27:25.210231: step: 1160/530, loss: 0.1189027726650238
2023-01-21 10:27:26.288299: step: 1164/530, loss: 0.008253383450210094
2023-01-21 10:27:27.369942: step: 1168/530, loss: 0.18192434310913086
2023-01-21 10:27:28.463412: step: 1172/530, loss: 0.03202543407678604
2023-01-21 10:27:29.560655: step: 1176/530, loss: 0.006087779998779297
2023-01-21 10:27:30.719127: step: 1180/530, loss: 0.017699718475341797
2023-01-21 10:27:31.867409: step: 1184/530, loss: 0.020438862964510918
2023-01-21 10:27:32.993229: step: 1188/530, loss: 0.18083572387695312
2023-01-21 10:27:34.118883: step: 1192/530, loss: 0.05942139774560928
2023-01-21 10:27:35.214068: step: 1196/530, loss: 0.031481076031923294
2023-01-21 10:27:36.301754: step: 1200/530, loss: 0.10384511947631836
2023-01-21 10:27:37.416519: step: 1204/530, loss: 0.0035838126204907894
2023-01-21 10:27:38.526631: step: 1208/530, loss: 0.03424272686243057
2023-01-21 10:27:39.644755: step: 1212/530, loss: 0.00261936173774302
2023-01-21 10:27:40.765499: step: 1216/530, loss: 0.06642857193946838
2023-01-21 10:27:41.857037: step: 1220/530, loss: 0.05801687389612198
2023-01-21 10:27:42.982384: step: 1224/530, loss: 0.11422616243362427
2023-01-21 10:27:44.109760: step: 1228/530, loss: 0.11314363777637482
2023-01-21 10:27:45.208857: step: 1232/530, loss: 0.006369686219841242
2023-01-21 10:27:46.319858: step: 1236/530, loss: 0.048940468579530716
2023-01-21 10:27:47.407734: step: 1240/530, loss: 0.09101562201976776
2023-01-21 10:27:48.504922: step: 1244/530, loss: 0.025406742468476295
2023-01-21 10:27:49.599881: step: 1248/530, loss: 0.434468537569046
2023-01-21 10:27:50.692532: step: 1252/530, loss: 0.04546623304486275
2023-01-21 10:27:51.805772: step: 1256/530, loss: 0.04888954386115074
2023-01-21 10:27:52.926016: step: 1260/530, loss: 0.025339506566524506
2023-01-21 10:27:54.013979: step: 1264/530, loss: 0.15145409107208252
2023-01-21 10:27:55.120354: step: 1268/530, loss: 0.09872984886169434
2023-01-21 10:27:56.212120: step: 1272/530, loss: 0.07277937233448029
2023-01-21 10:27:57.311291: step: 1276/530, loss: 0.016759490594267845
2023-01-21 10:27:58.408819: step: 1280/530, loss: 0.09770813584327698
2023-01-21 10:27:59.516438: step: 1284/530, loss: 0.015460682101547718
2023-01-21 10:28:00.637723: step: 1288/530, loss: 0.02175579033792019
2023-01-21 10:28:01.745277: step: 1292/530, loss: 0.05364866554737091
2023-01-21 10:28:02.872889: step: 1296/530, loss: 0.012689399532973766
2023-01-21 10:28:03.968407: step: 1300/530, loss: 0.07615194469690323
2023-01-21 10:28:05.054451: step: 1304/530, loss: 0.011107313446700573
2023-01-21 10:28:06.134117: step: 1308/530, loss: 0.026468895375728607
2023-01-21 10:28:07.262683: step: 1312/530, loss: 0.04306092485785484
2023-01-21 10:28:08.387932: step: 1316/530, loss: 0.0030199051834642887
2023-01-21 10:28:09.472176: step: 1320/530, loss: 0.017276287078857422
2023-01-21 10:28:10.608834: step: 1324/530, loss: 0.047972869127988815
2023-01-21 10:28:11.716912: step: 1328/530, loss: 0.03900089114904404
2023-01-21 10:28:12.862806: step: 1332/530, loss: 0.012319850735366344
2023-01-21 10:28:14.023441: step: 1336/530, loss: 0.025771809741854668
2023-01-21 10:28:15.112047: step: 1340/530, loss: 0.0913238525390625
2023-01-21 10:28:16.216098: step: 1344/530, loss: 0.0801122635602951
2023-01-21 10:28:17.328395: step: 1348/530, loss: 0.07319183647632599
2023-01-21 10:28:18.430652: step: 1352/530, loss: 0.025940515100955963
2023-01-21 10:28:19.533270: step: 1356/530, loss: 0.013179494068026543
2023-01-21 10:28:20.653616: step: 1360/530, loss: 0.0041886805556714535
2023-01-21 10:28:21.792001: step: 1364/530, loss: 0.02805519290268421
2023-01-21 10:28:22.922222: step: 1368/530, loss: 0.003676224034279585
2023-01-21 10:28:24.037758: step: 1372/530, loss: 0.010624551214277744
2023-01-21 10:28:25.157122: step: 1376/530, loss: 0.07511921226978302
2023-01-21 10:28:26.282614: step: 1380/530, loss: 0.18047723174095154
2023-01-21 10:28:27.372278: step: 1384/530, loss: 0.014397717081010342
2023-01-21 10:28:28.491590: step: 1388/530, loss: 0.0007568359724245965
2023-01-21 10:28:29.613184: step: 1392/530, loss: 0.05339784920215607
2023-01-21 10:28:30.753381: step: 1396/530, loss: 0.15393885970115662
2023-01-21 10:28:31.838224: step: 1400/530, loss: 0.3205549120903015
2023-01-21 10:28:32.973094: step: 1404/530, loss: 0.14973129332065582
2023-01-21 10:28:34.058319: step: 1408/530, loss: 0.026532746851444244
2023-01-21 10:28:35.180750: step: 1412/530, loss: 0.18216991424560547
2023-01-21 10:28:36.278520: step: 1416/530, loss: 0.0026184082962572575
2023-01-21 10:28:37.381195: step: 1420/530, loss: 0.0292492862790823
2023-01-21 10:28:38.469861: step: 1424/530, loss: 0.007504558656364679
2023-01-21 10:28:39.557908: step: 1428/530, loss: 0.03531865030527115
2023-01-21 10:28:40.665493: step: 1432/530, loss: 0.103765107691288
2023-01-21 10:28:41.821115: step: 1436/530, loss: 0.137089341878891
2023-01-21 10:28:42.925709: step: 1440/530, loss: 0.05499601364135742
2023-01-21 10:28:44.042729: step: 1444/530, loss: 0.04135112836956978
2023-01-21 10:28:45.178832: step: 1448/530, loss: 0.09410267323255539
2023-01-21 10:28:46.298566: step: 1452/530, loss: 0.009761005640029907
2023-01-21 10:28:47.425123: step: 1456/530, loss: 0.007539797108620405
2023-01-21 10:28:48.555055: step: 1460/530, loss: 0.19553260505199432
2023-01-21 10:28:49.664210: step: 1464/530, loss: 0.49554330110549927
2023-01-21 10:28:50.779608: step: 1468/530, loss: 0.22021484375
2023-01-21 10:28:51.863040: step: 1472/530, loss: 0.610744833946228
2023-01-21 10:28:52.960999: step: 1476/530, loss: 0.08355007320642471
2023-01-21 10:28:54.059940: step: 1480/530, loss: 0.029439738020300865
2023-01-21 10:28:55.191835: step: 1484/530, loss: 0.049280356615781784
2023-01-21 10:28:56.289371: step: 1488/530, loss: 0.11735839396715164
2023-01-21 10:28:57.395768: step: 1492/530, loss: 0.002564930822700262
2023-01-21 10:28:58.470429: step: 1496/530, loss: 0.03317832946777344
2023-01-21 10:28:59.608574: step: 1500/530, loss: 0.0918956771492958
2023-01-21 10:29:00.718323: step: 1504/530, loss: 0.022330665960907936
2023-01-21 10:29:01.874459: step: 1508/530, loss: 0.08444252610206604
2023-01-21 10:29:02.994030: step: 1512/530, loss: 0.07895755767822266
2023-01-21 10:29:04.121353: step: 1516/530, loss: 0.00974130630493164
2023-01-21 10:29:05.213091: step: 1520/530, loss: 0.035184480249881744
2023-01-21 10:29:06.325546: step: 1524/530, loss: 0.0067857964895665646
2023-01-21 10:29:07.445029: step: 1528/530, loss: 0.026671219617128372
2023-01-21 10:29:08.536857: step: 1532/530, loss: 0.0470428466796875
2023-01-21 10:29:09.639876: step: 1536/530, loss: 0.021310806274414062
2023-01-21 10:29:10.737806: step: 1540/530, loss: 0.29594412446022034
2023-01-21 10:29:11.862450: step: 1544/530, loss: 0.07302432507276535
2023-01-21 10:29:12.985208: step: 1548/530, loss: 0.03705654293298721
2023-01-21 10:29:14.100194: step: 1552/530, loss: 0.05746441334486008
2023-01-21 10:29:15.225440: step: 1556/530, loss: 0.06561096012592316
2023-01-21 10:29:16.322264: step: 1560/530, loss: 0.049315646290779114
2023-01-21 10:29:17.423936: step: 1564/530, loss: 0.01866288296878338
2023-01-21 10:29:18.515738: step: 1568/530, loss: 0.01026687677949667
2023-01-21 10:29:19.651893: step: 1572/530, loss: 0.3782140612602234
2023-01-21 10:29:20.745740: step: 1576/530, loss: 0.03174915164709091
2023-01-21 10:29:21.869308: step: 1580/530, loss: 0.0519731305539608
2023-01-21 10:29:23.003403: step: 1584/530, loss: 0.06885089725255966
2023-01-21 10:29:24.119374: step: 1588/530, loss: 0.027324486523866653
2023-01-21 10:29:25.232880: step: 1592/530, loss: 0.017322540283203125
2023-01-21 10:29:26.379858: step: 1596/530, loss: 0.06253203749656677
2023-01-21 10:29:27.503387: step: 1600/530, loss: 0.01580047607421875
2023-01-21 10:29:28.608691: step: 1604/530, loss: 0.15220795571804047
2023-01-21 10:29:29.700485: step: 1608/530, loss: 0.03933153301477432
2023-01-21 10:29:30.808803: step: 1612/530, loss: 0.0358029380440712
2023-01-21 10:29:31.897926: step: 1616/530, loss: 0.08002395927906036
2023-01-21 10:29:32.998058: step: 1620/530, loss: 0.010809516534209251
2023-01-21 10:29:34.151061: step: 1624/530, loss: 0.0408916138112545
2023-01-21 10:29:35.254108: step: 1628/530, loss: 0.021119022741913795
2023-01-21 10:29:36.374517: step: 1632/530, loss: 0.06739521026611328
2023-01-21 10:29:37.483539: step: 1636/530, loss: 0.04469342157244682
2023-01-21 10:29:38.575501: step: 1640/530, loss: 0.00572967529296875
2023-01-21 10:29:39.714795: step: 1644/530, loss: 0.010033035650849342
2023-01-21 10:29:40.804487: step: 1648/530, loss: 0.06862048804759979
2023-01-21 10:29:41.905269: step: 1652/530, loss: 0.025652311742305756
2023-01-21 10:29:43.007476: step: 1656/530, loss: 0.017319107428193092
2023-01-21 10:29:44.138718: step: 1660/530, loss: 0.02542905882000923
2023-01-21 10:29:45.273465: step: 1664/530, loss: 0.0934932753443718
2023-01-21 10:29:46.417825: step: 1668/530, loss: 0.04142327606678009
2023-01-21 10:29:47.522255: step: 1672/530, loss: 0.016751479357481003
2023-01-21 10:29:48.648820: step: 1676/530, loss: 0.02858734130859375
2023-01-21 10:29:49.772508: step: 1680/530, loss: 0.04429321363568306
2023-01-21 10:29:50.890867: step: 1684/530, loss: 0.0472647063434124
2023-01-21 10:29:52.002486: step: 1688/530, loss: 0.13532742857933044
2023-01-21 10:29:53.122259: step: 1692/530, loss: 0.07137179374694824
2023-01-21 10:29:54.247235: step: 1696/530, loss: 0.142163947224617
2023-01-21 10:29:55.350815: step: 1700/530, loss: 0.03503751754760742
2023-01-21 10:29:56.441665: step: 1704/530, loss: 0.8746212124824524
2023-01-21 10:29:57.562095: step: 1708/530, loss: 0.03901653364300728
2023-01-21 10:29:58.663126: step: 1712/530, loss: 0.017586277797818184
2023-01-21 10:29:59.788571: step: 1716/530, loss: 0.003415155690163374
2023-01-21 10:30:00.902466: step: 1720/530, loss: 0.36511650681495667
2023-01-21 10:30:02.039499: step: 1724/530, loss: 0.08045588433742523
2023-01-21 10:30:03.162634: step: 1728/530, loss: 0.05283351242542267
2023-01-21 10:30:04.277478: step: 1732/530, loss: 0.08687600493431091
2023-01-21 10:30:05.387702: step: 1736/530, loss: 0.04170827940106392
2023-01-21 10:30:06.487290: step: 1740/530, loss: 0.13895177841186523
2023-01-21 10:30:07.604328: step: 1744/530, loss: 0.017879106104373932
2023-01-21 10:30:08.717374: step: 1748/530, loss: 0.027414703741669655
2023-01-21 10:30:09.822289: step: 1752/530, loss: 0.06810932606458664
2023-01-21 10:30:10.957019: step: 1756/530, loss: 0.019004417583346367
2023-01-21 10:30:12.085784: step: 1760/530, loss: 0.01748180389404297
2023-01-21 10:30:13.182390: step: 1764/530, loss: 0.03506965562701225
2023-01-21 10:30:14.275461: step: 1768/530, loss: 0.07562761008739471
2023-01-21 10:30:15.399040: step: 1772/530, loss: 0.03868556767702103
2023-01-21 10:30:16.525089: step: 1776/530, loss: 0.04110002517700195
2023-01-21 10:30:17.635677: step: 1780/530, loss: 0.0022161006927490234
2023-01-21 10:30:18.752579: step: 1784/530, loss: 0.38225534558296204
2023-01-21 10:30:19.895123: step: 1788/530, loss: 0.04514579847455025
2023-01-21 10:30:21.043123: step: 1792/530, loss: 0.04293088987469673
2023-01-21 10:30:22.161978: step: 1796/530, loss: 0.04873795807361603
2023-01-21 10:30:23.300504: step: 1800/530, loss: 0.068383127450943
2023-01-21 10:30:24.424397: step: 1804/530, loss: 0.03583583980798721
2023-01-21 10:30:25.534292: step: 1808/530, loss: 0.025852110236883163
2023-01-21 10:30:26.670316: step: 1812/530, loss: 0.02477121353149414
2023-01-21 10:30:27.796127: step: 1816/530, loss: 0.17154522240161896
2023-01-21 10:30:28.946706: step: 1820/530, loss: 0.018378447741270065
2023-01-21 10:30:30.043650: step: 1824/530, loss: 0.05001030117273331
2023-01-21 10:30:31.163724: step: 1828/530, loss: 0.04947967454791069
2023-01-21 10:30:32.285085: step: 1832/530, loss: 0.06495733559131622
2023-01-21 10:30:33.447461: step: 1836/530, loss: 0.1112508773803711
2023-01-21 10:30:34.567571: step: 1840/530, loss: 0.03427476808428764
2023-01-21 10:30:35.738004: step: 1844/530, loss: 0.09455899894237518
2023-01-21 10:30:36.860279: step: 1848/530, loss: 0.020157624036073685
2023-01-21 10:30:37.982660: step: 1852/530, loss: 0.08197012543678284
2023-01-21 10:30:39.085883: step: 1856/530, loss: 0.09289780259132385
2023-01-21 10:30:40.212086: step: 1860/530, loss: 0.010397863574326038
2023-01-21 10:30:41.358000: step: 1864/530, loss: 0.05129518732428551
2023-01-21 10:30:42.460215: step: 1868/530, loss: 0.5903326272964478
2023-01-21 10:30:43.545042: step: 1872/530, loss: 0.01797323301434517
2023-01-21 10:30:44.648603: step: 1876/530, loss: 0.07294521480798721
2023-01-21 10:30:45.775887: step: 1880/530, loss: 0.00138940813485533
2023-01-21 10:30:46.909005: step: 1884/530, loss: 0.010287284851074219
2023-01-21 10:30:48.010630: step: 1888/530, loss: 0.02316570281982422
2023-01-21 10:30:49.109150: step: 1892/530, loss: 0.006842136383056641
2023-01-21 10:30:50.210800: step: 1896/530, loss: 0.8414446711540222
2023-01-21 10:30:51.315428: step: 1900/530, loss: 0.018769074231386185
2023-01-21 10:30:52.413203: step: 1904/530, loss: 0.06226663663983345
2023-01-21 10:30:53.540269: step: 1908/530, loss: 0.03171062469482422
2023-01-21 10:30:54.671198: step: 1912/530, loss: 0.028194524347782135
2023-01-21 10:30:55.764022: step: 1916/530, loss: 0.04950986057519913
2023-01-21 10:30:56.875453: step: 1920/530, loss: 0.06573066860437393
2023-01-21 10:30:58.017199: step: 1924/530, loss: 0.03975038602948189
2023-01-21 10:30:59.104056: step: 1928/530, loss: 0.053765106946229935
2023-01-21 10:31:00.207453: step: 1932/530, loss: 0.024614715948700905
2023-01-21 10:31:01.304583: step: 1936/530, loss: 0.003526926040649414
2023-01-21 10:31:02.422048: step: 1940/530, loss: 0.0450170561671257
2023-01-21 10:31:03.550289: step: 1944/530, loss: 0.03073573112487793
2023-01-21 10:31:04.662656: step: 1948/530, loss: 0.054958537220954895
2023-01-21 10:31:05.763957: step: 1952/530, loss: 0.08042354881763458
2023-01-21 10:31:06.850542: step: 1956/530, loss: 0.362433522939682
2023-01-21 10:31:07.987938: step: 1960/530, loss: 0.01531982421875
2023-01-21 10:31:09.119340: step: 1964/530, loss: 0.05685710906982422
2023-01-21 10:31:10.217575: step: 1968/530, loss: 0.10724525153636932
2023-01-21 10:31:11.319094: step: 1972/530, loss: 0.0006605624803341925
2023-01-21 10:31:12.410419: step: 1976/530, loss: 0.023868655785918236
2023-01-21 10:31:13.497854: step: 1980/530, loss: 0.07218912243843079
2023-01-21 10:31:14.613693: step: 1984/530, loss: 0.0767270103096962
2023-01-21 10:31:15.754588: step: 1988/530, loss: 0.034610748291015625
2023-01-21 10:31:16.850396: step: 1992/530, loss: 0.03550998866558075
2023-01-21 10:31:17.943435: step: 1996/530, loss: 0.014169692993164062
2023-01-21 10:31:19.052105: step: 2000/530, loss: 0.10332374274730682
2023-01-21 10:31:20.129849: step: 2004/530, loss: 0.07594108581542969
2023-01-21 10:31:21.240742: step: 2008/530, loss: 0.0193804744631052
2023-01-21 10:31:22.335435: step: 2012/530, loss: 0.027985287830233574
2023-01-21 10:31:23.442009: step: 2016/530, loss: 0.007962321862578392
2023-01-21 10:31:24.583144: step: 2020/530, loss: 0.05670957639813423
2023-01-21 10:31:25.677317: step: 2024/530, loss: 0.010011625476181507
2023-01-21 10:31:26.817671: step: 2028/530, loss: 0.149058535695076
2023-01-21 10:31:27.923038: step: 2032/530, loss: 0.01309061050415039
2023-01-21 10:31:29.037962: step: 2036/530, loss: 0.01413955632597208
2023-01-21 10:31:30.137570: step: 2040/530, loss: 0.18897266685962677
2023-01-21 10:31:31.238157: step: 2044/530, loss: 0.20500129461288452
2023-01-21 10:31:32.346171: step: 2048/530, loss: 0.007315921597182751
2023-01-21 10:31:33.545944: step: 2052/530, loss: 0.10493364185094833
2023-01-21 10:31:34.637666: step: 2056/530, loss: 0.01532754860818386
2023-01-21 10:31:35.748475: step: 2060/530, loss: 0.044478606432676315
2023-01-21 10:31:36.849120: step: 2064/530, loss: 0.17894811928272247
2023-01-21 10:31:37.944490: step: 2068/530, loss: 0.1101846694946289
2023-01-21 10:31:39.069088: step: 2072/530, loss: 0.9316828846931458
2023-01-21 10:31:40.186461: step: 2076/530, loss: 0.004873180761933327
2023-01-21 10:31:41.310965: step: 2080/530, loss: 0.06384678184986115
2023-01-21 10:31:42.429212: step: 2084/530, loss: 0.05898475646972656
2023-01-21 10:31:43.548491: step: 2088/530, loss: 0.014600194059312344
2023-01-21 10:31:44.636208: step: 2092/530, loss: 0.01623525470495224
2023-01-21 10:31:45.726323: step: 2096/530, loss: 0.007298898417502642
2023-01-21 10:31:46.865719: step: 2100/530, loss: 0.03826083987951279
2023-01-21 10:31:47.982292: step: 2104/530, loss: 0.011189555749297142
2023-01-21 10:31:49.092017: step: 2108/530, loss: 0.01828782632946968
2023-01-21 10:31:50.236124: step: 2112/530, loss: 0.021965980529785156
2023-01-21 10:31:51.329995: step: 2116/530, loss: 0.002548742340877652
2023-01-21 10:31:52.462465: step: 2120/530, loss: 0.058190345764160156
==================================================
Loss: 0.092
--------------------
Dev: {'event': {'p': 0.5915201654601862, 'r': 0.7616511318242344, 'f1': 0.6658905704307335}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Test: {'event': {'p': 0.6262898160610139, 'r': 0.8135198135198135, 'f1': 0.7077313054499366}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Chinese: {'event': {'p': 0.5584415584415584, 'r': 0.7962962962962963, 'f1': 0.6564885496183205}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Korean: {'event': {'p': 0.6229508196721312, 'r': 0.6031746031746031, 'f1': 0.6129032258064517}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
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': 11}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5708622398414271, 'r': 0.7669773635153129, 'f1': 0.6545454545454545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Chinese: {'event': {'p': 0.6044052863436123, 'r': 0.7995337995337995, 'f1': 0.6884094330155545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Chinese: {'event': {'p': 0.6578947368421053, 'r': 0.9259259259259259, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6466512702078522, 'r': 0.7456724367509987, 'f1': 0.6926406926406927}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.6762148337595908, 'r': 0.7703962703962703, 'f1': 0.7202397166984473}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 10:32:32.986031: step: 4/530, loss: 0.12217392772436142
2023-01-21 10:32:34.120406: step: 8/530, loss: 0.04355983808636665
2023-01-21 10:32:35.232483: step: 12/530, loss: 0.00415725726634264
2023-01-21 10:32:36.335431: step: 16/530, loss: 0.12369203567504883
2023-01-21 10:32:37.446382: step: 20/530, loss: 0.00567626953125
2023-01-21 10:32:38.523611: step: 24/530, loss: 0.03349151834845543
2023-01-21 10:32:39.637658: step: 28/530, loss: 0.045412540435791016
2023-01-21 10:32:40.772875: step: 32/530, loss: 0.04692840576171875
2023-01-21 10:32:41.879890: step: 36/530, loss: 0.004734134767204523
2023-01-21 10:32:42.972649: step: 40/530, loss: 0.061406850814819336
2023-01-21 10:32:44.066637: step: 44/530, loss: 0.01967925950884819
2023-01-21 10:32:45.173219: step: 48/530, loss: 0.09564915299415588
2023-01-21 10:32:46.262221: step: 52/530, loss: 0.0012290955055505037
2023-01-21 10:32:47.377890: step: 56/530, loss: 0.03349800407886505
2023-01-21 10:32:48.470805: step: 60/530, loss: 0.057605646550655365
2023-01-21 10:32:49.578733: step: 64/530, loss: 0.1997934877872467
2023-01-21 10:32:50.672545: step: 68/530, loss: 0.01654500886797905
2023-01-21 10:32:51.785701: step: 72/530, loss: 0.1611625701189041
2023-01-21 10:32:52.875683: step: 76/530, loss: 0.00711102457717061
2023-01-21 10:32:53.978383: step: 80/530, loss: 0.0069855693727731705
2023-01-21 10:32:55.104323: step: 84/530, loss: 0.06616564095020294
2023-01-21 10:32:56.243438: step: 88/530, loss: 0.5605751872062683
2023-01-21 10:32:57.346977: step: 92/530, loss: 0.07526283711194992
2023-01-21 10:32:58.452410: step: 96/530, loss: 0.3889423608779907
2023-01-21 10:32:59.592062: step: 100/530, loss: 0.002331542782485485
2023-01-21 10:33:00.716249: step: 104/530, loss: 0.05284447595477104
2023-01-21 10:33:01.834640: step: 108/530, loss: 0.028945542871952057
2023-01-21 10:33:02.944927: step: 112/530, loss: 0.007387829013168812
2023-01-21 10:33:04.072346: step: 116/530, loss: 0.0201397892087698
2023-01-21 10:33:05.190061: step: 120/530, loss: 0.011191368103027344
2023-01-21 10:33:06.294168: step: 124/530, loss: 0.03301756829023361
2023-01-21 10:33:07.357615: step: 128/530, loss: 0.0010143041145056486
2023-01-21 10:33:08.449596: step: 132/530, loss: 0.003820768091827631
2023-01-21 10:33:09.585210: step: 136/530, loss: 0.01592733897268772
2023-01-21 10:33:10.736930: step: 140/530, loss: 0.0769595205783844
2023-01-21 10:33:11.868128: step: 144/530, loss: 0.06012621149420738
2023-01-21 10:33:12.966070: step: 148/530, loss: 0.01934204250574112
2023-01-21 10:33:14.064226: step: 152/530, loss: 0.12173499912023544
2023-01-21 10:33:15.185816: step: 156/530, loss: 0.006052779965102673
2023-01-21 10:33:16.279143: step: 160/530, loss: 0.0025989532005041838
2023-01-21 10:33:17.421228: step: 164/530, loss: 0.009674168191850185
2023-01-21 10:33:18.520202: step: 168/530, loss: 0.021408509463071823
2023-01-21 10:33:19.629388: step: 172/530, loss: 0.034229278564453125
2023-01-21 10:33:20.732894: step: 176/530, loss: 0.05949997901916504
2023-01-21 10:33:21.825699: step: 180/530, loss: 0.31714552640914917
2023-01-21 10:33:22.916403: step: 184/530, loss: 0.013253307901322842
2023-01-21 10:33:24.047724: step: 188/530, loss: 0.01837310753762722
2023-01-21 10:33:25.164868: step: 192/530, loss: 0.04658794403076172
2023-01-21 10:33:26.258161: step: 196/530, loss: 0.028780221939086914
2023-01-21 10:33:27.333153: step: 200/530, loss: 0.02681450918316841
2023-01-21 10:33:28.440270: step: 204/530, loss: 0.037584494799375534
2023-01-21 10:33:29.591019: step: 208/530, loss: 0.05729694664478302
2023-01-21 10:33:30.709195: step: 212/530, loss: 0.024480724707245827
2023-01-21 10:33:31.806334: step: 216/530, loss: 0.0057472228072583675
2023-01-21 10:33:32.895857: step: 220/530, loss: 0.1993524432182312
2023-01-21 10:33:34.009752: step: 224/530, loss: 0.04384488984942436
2023-01-21 10:33:35.139138: step: 228/530, loss: 0.08120954036712646
2023-01-21 10:33:36.239162: step: 232/530, loss: 0.08713507652282715
2023-01-21 10:33:37.379357: step: 236/530, loss: 0.04013776779174805
2023-01-21 10:33:38.477759: step: 240/530, loss: 0.026754379272460938
2023-01-21 10:33:39.589175: step: 244/530, loss: 0.012256240472197533
2023-01-21 10:33:40.697181: step: 248/530, loss: 0.021729851141572
2023-01-21 10:33:41.788582: step: 252/530, loss: 0.015575408935546875
2023-01-21 10:33:42.892643: step: 256/530, loss: 0.015318488702178001
2023-01-21 10:33:44.028106: step: 260/530, loss: 0.013233941979706287
2023-01-21 10:33:45.139108: step: 264/530, loss: 0.03330669552087784
2023-01-21 10:33:46.249641: step: 268/530, loss: 0.17449398338794708
2023-01-21 10:33:47.374746: step: 272/530, loss: 0.00700454693287611
2023-01-21 10:33:48.499190: step: 276/530, loss: 0.07040786743164062
2023-01-21 10:33:49.615634: step: 280/530, loss: 0.005203723907470703
2023-01-21 10:33:50.719970: step: 284/530, loss: 0.06285848468542099
2023-01-21 10:33:51.845248: step: 288/530, loss: 0.05106430500745773
2023-01-21 10:33:52.982120: step: 292/530, loss: 0.040328312665224075
2023-01-21 10:33:54.085733: step: 296/530, loss: 0.008420849218964577
2023-01-21 10:33:55.183944: step: 300/530, loss: 0.13301372528076172
2023-01-21 10:33:56.297090: step: 304/530, loss: 0.031146671622991562
2023-01-21 10:33:57.384609: step: 308/530, loss: 0.03583240509033203
2023-01-21 10:33:58.517243: step: 312/530, loss: 0.20479458570480347
2023-01-21 10:33:59.642227: step: 316/530, loss: 0.008874607272446156
2023-01-21 10:34:00.761341: step: 320/530, loss: 0.0280914306640625
2023-01-21 10:34:01.908644: step: 324/530, loss: 0.014903450384736061
2023-01-21 10:34:03.020653: step: 328/530, loss: 0.07563018798828125
2023-01-21 10:34:04.149836: step: 332/530, loss: 0.0005148887867107987
2023-01-21 10:34:05.263812: step: 336/530, loss: 0.06439914554357529
2023-01-21 10:34:06.353179: step: 340/530, loss: 0.03669404983520508
2023-01-21 10:34:07.467711: step: 344/530, loss: 0.04858074337244034
2023-01-21 10:34:08.576344: step: 348/530, loss: 0.15034082531929016
2023-01-21 10:34:09.721548: step: 352/530, loss: 0.04743604734539986
2023-01-21 10:34:10.829632: step: 356/530, loss: 0.004701673984527588
2023-01-21 10:34:11.952415: step: 360/530, loss: 0.03838415443897247
2023-01-21 10:34:13.089046: step: 364/530, loss: 0.016762638464570045
2023-01-21 10:34:14.209627: step: 368/530, loss: 0.0979059487581253
2023-01-21 10:34:15.298841: step: 372/530, loss: 0.0441705696284771
2023-01-21 10:34:16.388462: step: 376/530, loss: 0.0982576310634613
2023-01-21 10:34:17.494439: step: 380/530, loss: 0.16418859362602234
2023-01-21 10:34:18.649095: step: 384/530, loss: 0.007172155659645796
2023-01-21 10:34:19.802100: step: 388/530, loss: 1.0394030809402466
2023-01-21 10:34:20.909765: step: 392/530, loss: 0.008274555206298828
2023-01-21 10:34:22.037456: step: 396/530, loss: 0.050685882568359375
2023-01-21 10:34:23.187360: step: 400/530, loss: 0.035683728754520416
2023-01-21 10:34:24.322885: step: 404/530, loss: 0.03522949293255806
2023-01-21 10:34:25.444507: step: 408/530, loss: 0.03737306594848633
2023-01-21 10:34:26.575324: step: 412/530, loss: 0.010476303286850452
2023-01-21 10:34:27.694879: step: 416/530, loss: 0.027260685339570045
2023-01-21 10:34:28.816132: step: 420/530, loss: 0.0809205025434494
2023-01-21 10:34:29.933813: step: 424/530, loss: 0.07678051292896271
2023-01-21 10:34:31.039801: step: 428/530, loss: 0.014821911230683327
2023-01-21 10:34:32.134353: step: 432/530, loss: 0.006715155206620693
2023-01-21 10:34:33.293540: step: 436/530, loss: 0.006562614813446999
2023-01-21 10:34:34.401476: step: 440/530, loss: 0.02201845683157444
2023-01-21 10:34:35.506213: step: 444/530, loss: 0.04666843265295029
2023-01-21 10:34:36.617781: step: 448/530, loss: 0.03583640977740288
2023-01-21 10:34:37.748436: step: 452/530, loss: 0.2653636932373047
2023-01-21 10:34:38.835473: step: 456/530, loss: 0.01358795166015625
2023-01-21 10:34:39.946737: step: 460/530, loss: 0.023645926266908646
2023-01-21 10:34:41.030246: step: 464/530, loss: 0.0006994247669354081
2023-01-21 10:34:42.117775: step: 468/530, loss: 0.059747982770204544
2023-01-21 10:34:43.230881: step: 472/530, loss: 0.0257110595703125
2023-01-21 10:34:44.366196: step: 476/530, loss: 0.019199514761567116
2023-01-21 10:34:45.492290: step: 480/530, loss: 0.06899251788854599
2023-01-21 10:34:46.613316: step: 484/530, loss: 0.026078414171934128
2023-01-21 10:34:47.707197: step: 488/530, loss: 0.007918357849121094
2023-01-21 10:34:48.807845: step: 492/530, loss: 0.014980316162109375
2023-01-21 10:34:49.929512: step: 496/530, loss: 0.46514204144477844
2023-01-21 10:34:51.021253: step: 500/530, loss: 0.0698794350028038
2023-01-21 10:34:52.142232: step: 504/530, loss: 1.057571291923523
2023-01-21 10:34:53.250325: step: 508/530, loss: 0.006717681884765625
2023-01-21 10:34:54.336380: step: 512/530, loss: 0.11410808563232422
2023-01-21 10:34:55.439706: step: 516/530, loss: 0.023461056873202324
2023-01-21 10:34:56.577260: step: 520/530, loss: 0.019330406561493874
2023-01-21 10:34:57.674907: step: 524/530, loss: 0.017003346234560013
2023-01-21 10:34:58.824123: step: 528/530, loss: 0.02094240114092827
2023-01-21 10:34:59.934380: step: 532/530, loss: 0.03984546661376953
2023-01-21 10:35:01.060003: step: 536/530, loss: 0.19856777787208557
2023-01-21 10:35:02.169212: step: 540/530, loss: 0.1138116866350174
2023-01-21 10:35:03.305076: step: 544/530, loss: 0.013024711981415749
2023-01-21 10:35:04.434164: step: 548/530, loss: 0.0009488106006756425
2023-01-21 10:35:05.564367: step: 552/530, loss: 0.062089256942272186
2023-01-21 10:35:06.672934: step: 556/530, loss: 0.06643286347389221
2023-01-21 10:35:07.802094: step: 560/530, loss: 0.07790813595056534
2023-01-21 10:35:08.896622: step: 564/530, loss: 0.006512498948723078
2023-01-21 10:35:10.025357: step: 568/530, loss: 0.07037000358104706
2023-01-21 10:35:11.135622: step: 572/530, loss: 0.007596397306770086
2023-01-21 10:35:12.229840: step: 576/530, loss: 0.011252403259277344
2023-01-21 10:35:13.355161: step: 580/530, loss: 0.0428893119096756
2023-01-21 10:35:14.451819: step: 584/530, loss: 0.044447995722293854
2023-01-21 10:35:15.577982: step: 588/530, loss: 0.011728476732969284
2023-01-21 10:35:16.662944: step: 592/530, loss: 0.05866604298353195
2023-01-21 10:35:17.767206: step: 596/530, loss: 0.040102627128362656
2023-01-21 10:35:18.877274: step: 600/530, loss: 0.07455454766750336
2023-01-21 10:35:19.971215: step: 604/530, loss: 0.01578970067203045
2023-01-21 10:35:21.086755: step: 608/530, loss: 0.01084680575877428
2023-01-21 10:35:22.183052: step: 612/530, loss: 0.01986847072839737
2023-01-21 10:35:23.304480: step: 616/530, loss: 0.07225351780653
2023-01-21 10:35:24.410271: step: 620/530, loss: 0.012257957831025124
2023-01-21 10:35:25.540459: step: 624/530, loss: 0.011363983154296875
2023-01-21 10:35:26.614139: step: 628/530, loss: 0.01115407980978489
2023-01-21 10:35:27.724922: step: 632/530, loss: 0.049120333045721054
2023-01-21 10:35:28.816236: step: 636/530, loss: 0.04525451362133026
2023-01-21 10:35:29.953846: step: 640/530, loss: 0.22013282775878906
2023-01-21 10:35:31.070555: step: 644/530, loss: 0.037776850163936615
2023-01-21 10:35:32.161852: step: 648/530, loss: 0.0455472469329834
2023-01-21 10:35:33.273012: step: 652/530, loss: 0.12250444293022156
2023-01-21 10:35:34.372726: step: 656/530, loss: 0.07416753470897675
2023-01-21 10:35:35.486851: step: 660/530, loss: 0.2730955183506012
2023-01-21 10:35:36.637568: step: 664/530, loss: 0.11771383136510849
2023-01-21 10:35:37.763153: step: 668/530, loss: 0.023672914132475853
2023-01-21 10:35:38.841348: step: 672/530, loss: 0.05048871040344238
2023-01-21 10:35:39.961349: step: 676/530, loss: 0.028913021087646484
2023-01-21 10:35:41.072536: step: 680/530, loss: 0.05248761549592018
2023-01-21 10:35:42.165635: step: 684/530, loss: 0.13372927904129028
2023-01-21 10:35:43.260733: step: 688/530, loss: 0.031251147389411926
2023-01-21 10:35:44.360696: step: 692/530, loss: 0.1476929783821106
2023-01-21 10:35:45.484656: step: 696/530, loss: 0.0032839300110936165
2023-01-21 10:35:46.614269: step: 700/530, loss: 0.03127546235918999
2023-01-21 10:35:47.713108: step: 704/530, loss: 0.0023738860618323088
2023-01-21 10:35:48.829362: step: 708/530, loss: 0.012925529852509499
2023-01-21 10:35:49.949443: step: 712/530, loss: 0.12085571140050888
2023-01-21 10:35:51.068748: step: 716/530, loss: 0.0068305968306958675
2023-01-21 10:35:52.168918: step: 720/530, loss: 0.008514595218002796
2023-01-21 10:35:53.271262: step: 724/530, loss: 0.019307279959321022
2023-01-21 10:35:54.410777: step: 728/530, loss: 0.023670004680752754
2023-01-21 10:35:55.620658: step: 732/530, loss: 0.026579666882753372
2023-01-21 10:35:56.726256: step: 736/530, loss: 0.041666459292173386
2023-01-21 10:35:57.837731: step: 740/530, loss: 0.01831965520977974
2023-01-21 10:35:58.934108: step: 744/530, loss: 0.026883317157626152
2023-01-21 10:36:00.035479: step: 748/530, loss: 1.3865602016448975
2023-01-21 10:36:01.201469: step: 752/530, loss: 0.018810177221894264
2023-01-21 10:36:02.307790: step: 756/530, loss: 0.03131237253546715
2023-01-21 10:36:03.416826: step: 760/530, loss: 0.060655973851680756
2023-01-21 10:36:04.552175: step: 764/530, loss: 0.09271307289600372
2023-01-21 10:36:05.646596: step: 768/530, loss: 0.017095517367124557
2023-01-21 10:36:06.749169: step: 772/530, loss: 0.0029724121559411287
2023-01-21 10:36:07.879633: step: 776/530, loss: 0.03340339660644531
2023-01-21 10:36:09.005172: step: 780/530, loss: 0.009843254461884499
2023-01-21 10:36:10.121341: step: 784/530, loss: 0.02620868757367134
2023-01-21 10:36:11.235673: step: 788/530, loss: 0.16946296393871307
2023-01-21 10:36:12.321426: step: 792/530, loss: 0.00152845389675349
2023-01-21 10:36:13.434773: step: 796/530, loss: 0.06758613884449005
2023-01-21 10:36:14.542018: step: 800/530, loss: 0.025009775534272194
2023-01-21 10:36:15.650862: step: 804/530, loss: 0.02290639840066433
2023-01-21 10:36:16.766387: step: 808/530, loss: 0.025272177532315254
2023-01-21 10:36:17.875817: step: 812/530, loss: 0.14129333198070526
2023-01-21 10:36:18.990830: step: 816/530, loss: 0.10452881455421448
2023-01-21 10:36:20.088652: step: 820/530, loss: 0.0017179489368572831
2023-01-21 10:36:21.201692: step: 824/530, loss: 0.3946347236633301
2023-01-21 10:36:22.282677: step: 828/530, loss: 0.020306779071688652
2023-01-21 10:36:23.401355: step: 832/530, loss: 0.13113775849342346
2023-01-21 10:36:24.523735: step: 836/530, loss: 0.21663188934326172
2023-01-21 10:36:25.634725: step: 840/530, loss: 0.3175109922885895
2023-01-21 10:36:26.726051: step: 844/530, loss: 0.06110329553484917
2023-01-21 10:36:27.873114: step: 848/530, loss: 0.1135474145412445
2023-01-21 10:36:28.989703: step: 852/530, loss: 0.01379413716495037
2023-01-21 10:36:30.077683: step: 856/530, loss: 0.000433504581451416
2023-01-21 10:36:31.179526: step: 860/530, loss: 0.05575408786535263
2023-01-21 10:36:32.302920: step: 864/530, loss: 0.016370154917240143
2023-01-21 10:36:33.455197: step: 868/530, loss: 0.10320253670215607
2023-01-21 10:36:34.573531: step: 872/530, loss: 0.018551256507635117
2023-01-21 10:36:35.658252: step: 876/530, loss: 0.009125906974077225
2023-01-21 10:36:36.762019: step: 880/530, loss: 0.0428614616394043
2023-01-21 10:36:37.870754: step: 884/530, loss: 0.03135743364691734
2023-01-21 10:36:38.972354: step: 888/530, loss: 0.04365234449505806
2023-01-21 10:36:40.047078: step: 892/530, loss: 0.1356188803911209
2023-01-21 10:36:41.171897: step: 896/530, loss: 0.031800076365470886
2023-01-21 10:36:42.276583: step: 900/530, loss: 0.03432692959904671
2023-01-21 10:36:43.383346: step: 904/530, loss: 0.02647094801068306
2023-01-21 10:36:44.489715: step: 908/530, loss: 0.028005409985780716
2023-01-21 10:36:45.583465: step: 912/530, loss: 0.029528236016631126
2023-01-21 10:36:46.713904: step: 916/530, loss: 0.029340792447328568
2023-01-21 10:36:47.812301: step: 920/530, loss: 0.02888813242316246
2023-01-21 10:36:48.921066: step: 924/530, loss: 0.10296416282653809
2023-01-21 10:36:50.049162: step: 928/530, loss: 0.01380016840994358
2023-01-21 10:36:51.172350: step: 932/530, loss: 0.05210408940911293
2023-01-21 10:36:52.257147: step: 936/530, loss: 0.03244619444012642
2023-01-21 10:36:53.339840: step: 940/530, loss: 0.5938853621482849
2023-01-21 10:36:54.438241: step: 944/530, loss: 0.0017591476207599044
2023-01-21 10:36:55.560875: step: 948/530, loss: 0.08948317170143127
2023-01-21 10:36:56.667423: step: 952/530, loss: 0.025825882330536842
2023-01-21 10:36:57.801360: step: 956/530, loss: 0.05368185415863991
2023-01-21 10:36:58.925743: step: 960/530, loss: 0.009030342102050781
2023-01-21 10:37:00.030755: step: 964/530, loss: 0.02614833600819111
2023-01-21 10:37:01.128547: step: 968/530, loss: 0.11007046699523926
2023-01-21 10:37:02.215062: step: 972/530, loss: 0.03461914137005806
2023-01-21 10:37:03.339941: step: 976/530, loss: 0.08862514793872833
2023-01-21 10:37:04.445601: step: 980/530, loss: 0.009628485888242722
2023-01-21 10:37:05.554709: step: 984/530, loss: 0.28468719124794006
2023-01-21 10:37:06.661118: step: 988/530, loss: 0.03630642965435982
2023-01-21 10:37:07.760268: step: 992/530, loss: 0.007634926121681929
2023-01-21 10:37:08.854941: step: 996/530, loss: 0.008600044064223766
2023-01-21 10:37:09.950188: step: 1000/530, loss: 0.10941076278686523
2023-01-21 10:37:11.087181: step: 1004/530, loss: 0.09134893119335175
2023-01-21 10:37:12.219411: step: 1008/530, loss: 0.10647161304950714
2023-01-21 10:37:13.339878: step: 1012/530, loss: 0.021001815795898438
2023-01-21 10:37:14.464128: step: 1016/530, loss: 0.007102012634277344
2023-01-21 10:37:15.568503: step: 1020/530, loss: 0.03594560548663139
2023-01-21 10:37:16.667617: step: 1024/530, loss: 0.04963388293981552
2023-01-21 10:37:17.781197: step: 1028/530, loss: 0.006227540783584118
2023-01-21 10:37:18.864904: step: 1032/530, loss: 0.057213690131902695
2023-01-21 10:37:19.990669: step: 1036/530, loss: 0.010787582956254482
2023-01-21 10:37:21.083475: step: 1040/530, loss: 0.03327369689941406
2023-01-21 10:37:22.184294: step: 1044/530, loss: 0.02487659454345703
2023-01-21 10:37:23.325374: step: 1048/530, loss: 0.05809640884399414
2023-01-21 10:37:24.410267: step: 1052/530, loss: 0.06843795627355576
2023-01-21 10:37:25.523172: step: 1056/530, loss: 0.08423156291246414
2023-01-21 10:37:26.625015: step: 1060/530, loss: 0.0011695862049236894
2023-01-21 10:37:27.718914: step: 1064/530, loss: 0.019686991348862648
2023-01-21 10:37:28.828381: step: 1068/530, loss: 0.000934600830078125
2023-01-21 10:37:29.923387: step: 1072/530, loss: 0.09884815663099289
2023-01-21 10:37:31.032372: step: 1076/530, loss: 0.03498096764087677
2023-01-21 10:37:32.143631: step: 1080/530, loss: 0.006920528598129749
2023-01-21 10:37:33.276168: step: 1084/530, loss: 0.44732505083084106
2023-01-21 10:37:34.370724: step: 1088/530, loss: 0.028714848682284355
2023-01-21 10:37:35.456510: step: 1092/530, loss: 0.03812284395098686
2023-01-21 10:37:36.541660: step: 1096/530, loss: 0.006140708923339844
2023-01-21 10:37:37.663860: step: 1100/530, loss: 0.045720770955085754
2023-01-21 10:37:38.779900: step: 1104/530, loss: 0.012720775790512562
2023-01-21 10:37:39.897265: step: 1108/530, loss: 0.021930169314146042
2023-01-21 10:37:40.996242: step: 1112/530, loss: 0.016519851982593536
2023-01-21 10:37:42.116178: step: 1116/530, loss: 0.02514674700796604
2023-01-21 10:37:43.250130: step: 1120/530, loss: 0.13176536560058594
2023-01-21 10:37:44.373237: step: 1124/530, loss: 0.047174740582704544
2023-01-21 10:37:45.505268: step: 1128/530, loss: 0.10025063157081604
2023-01-21 10:37:46.599167: step: 1132/530, loss: 0.03635873645544052
2023-01-21 10:37:47.685408: step: 1136/530, loss: 0.07207384705543518
2023-01-21 10:37:48.790118: step: 1140/530, loss: 0.02955608442425728
2023-01-21 10:37:49.891580: step: 1144/530, loss: 0.025429820641875267
2023-01-21 10:37:51.022596: step: 1148/530, loss: 0.08548621833324432
2023-01-21 10:37:52.142156: step: 1152/530, loss: 0.16207322478294373
2023-01-21 10:37:53.218917: step: 1156/530, loss: 0.020700300112366676
2023-01-21 10:37:54.297427: step: 1160/530, loss: 0.002082651946693659
2023-01-21 10:37:55.412500: step: 1164/530, loss: 0.007279396057128906
2023-01-21 10:37:56.499841: step: 1168/530, loss: 0.003183651017025113
2023-01-21 10:37:57.640711: step: 1172/530, loss: 0.018611837178468704
2023-01-21 10:37:58.750329: step: 1176/530, loss: 0.09921710193157196
2023-01-21 10:37:59.860612: step: 1180/530, loss: 0.07083268463611603
2023-01-21 10:38:00.969622: step: 1184/530, loss: 0.025111867114901543
2023-01-21 10:38:02.076428: step: 1188/530, loss: 0.004028988070785999
2023-01-21 10:38:03.165926: step: 1192/530, loss: 0.01356043852865696
2023-01-21 10:38:04.266514: step: 1196/530, loss: 0.0004744529724121094
2023-01-21 10:38:05.380252: step: 1200/530, loss: 0.025488998740911484
2023-01-21 10:38:06.546170: step: 1204/530, loss: 0.009497905150055885
2023-01-21 10:38:07.662471: step: 1208/530, loss: 0.3431139886379242
2023-01-21 10:38:08.769368: step: 1212/530, loss: 0.029784012585878372
2023-01-21 10:38:09.887654: step: 1216/530, loss: 0.017099952325224876
2023-01-21 10:38:10.992743: step: 1220/530, loss: 0.044805239886045456
2023-01-21 10:38:12.090202: step: 1224/530, loss: 0.04540227726101875
2023-01-21 10:38:13.203454: step: 1228/530, loss: 0.021887637674808502
2023-01-21 10:38:14.320266: step: 1232/530, loss: 0.03386092185974121
2023-01-21 10:38:15.429560: step: 1236/530, loss: 0.02501516416668892
2023-01-21 10:38:16.559120: step: 1240/530, loss: 0.02591400034725666
2023-01-21 10:38:17.666012: step: 1244/530, loss: 0.07956273853778839
2023-01-21 10:38:18.773969: step: 1248/530, loss: 0.36626559495925903
2023-01-21 10:38:19.903862: step: 1252/530, loss: 0.01176986750215292
2023-01-21 10:38:21.014898: step: 1256/530, loss: 0.004930878058075905
2023-01-21 10:38:22.149231: step: 1260/530, loss: 0.19106808304786682
2023-01-21 10:38:23.275719: step: 1264/530, loss: 0.03809051588177681
2023-01-21 10:38:24.385613: step: 1268/530, loss: 0.027323437854647636
2023-01-21 10:38:25.482328: step: 1272/530, loss: 0.020868491381406784
2023-01-21 10:38:26.587251: step: 1276/530, loss: 0.025566866621375084
2023-01-21 10:38:27.679948: step: 1280/530, loss: 0.17144207656383514
2023-01-21 10:38:28.776219: step: 1284/530, loss: 0.01393732987344265
2023-01-21 10:38:29.869379: step: 1288/530, loss: 0.021178627386689186
2023-01-21 10:38:30.980070: step: 1292/530, loss: 0.06793908774852753
2023-01-21 10:38:32.089411: step: 1296/530, loss: 0.15275421738624573
2023-01-21 10:38:33.181425: step: 1300/530, loss: 0.09885692596435547
2023-01-21 10:38:34.329412: step: 1304/530, loss: 0.06618261337280273
2023-01-21 10:38:35.410768: step: 1308/530, loss: 0.029015256091952324
2023-01-21 10:38:36.554227: step: 1312/530, loss: 0.037352755665779114
2023-01-21 10:38:37.630451: step: 1316/530, loss: 0.009375429712235928
2023-01-21 10:38:38.788050: step: 1320/530, loss: 0.09770459681749344
2023-01-21 10:38:39.897466: step: 1324/530, loss: 0.03231701999902725
2023-01-21 10:38:41.017949: step: 1328/530, loss: 0.11964817345142365
2023-01-21 10:38:42.174604: step: 1332/530, loss: 0.2794470489025116
2023-01-21 10:38:43.263417: step: 1336/530, loss: 0.014360261149704456
2023-01-21 10:38:44.382659: step: 1340/530, loss: 0.09358978271484375
2023-01-21 10:38:45.478647: step: 1344/530, loss: 0.0189801212400198
2023-01-21 10:38:46.611206: step: 1348/530, loss: 0.05653095245361328
2023-01-21 10:38:47.724702: step: 1352/530, loss: 0.057050321251153946
2023-01-21 10:38:48.816057: step: 1356/530, loss: 0.07047334313392639
2023-01-21 10:38:49.947421: step: 1360/530, loss: 0.04799318313598633
2023-01-21 10:38:51.045013: step: 1364/530, loss: 0.06344003975391388
2023-01-21 10:38:52.139052: step: 1368/530, loss: 0.011250496841967106
2023-01-21 10:38:53.253404: step: 1372/530, loss: 0.18379707634449005
2023-01-21 10:38:54.355121: step: 1376/530, loss: 0.014703750610351562
2023-01-21 10:38:55.443986: step: 1380/530, loss: 0.0005214214324951172
2023-01-21 10:38:56.573577: step: 1384/530, loss: 0.10467061400413513
2023-01-21 10:38:57.674689: step: 1388/530, loss: 0.03388223797082901
2023-01-21 10:38:58.789370: step: 1392/530, loss: 0.28180214762687683
2023-01-21 10:38:59.867547: step: 1396/530, loss: 0.08639049530029297
2023-01-21 10:39:01.032524: step: 1400/530, loss: 0.004028511233627796
2023-01-21 10:39:02.143776: step: 1404/530, loss: 0.05231790617108345
2023-01-21 10:39:03.269338: step: 1408/530, loss: 0.0005071640480309725
2023-01-21 10:39:04.381189: step: 1412/530, loss: 0.023090269416570663
2023-01-21 10:39:05.456045: step: 1416/530, loss: 0.06920156627893448
2023-01-21 10:39:06.614223: step: 1420/530, loss: 0.049269963055849075
2023-01-21 10:39:07.746250: step: 1424/530, loss: 0.03158741071820259
2023-01-21 10:39:08.841405: step: 1428/530, loss: 0.07916012406349182
2023-01-21 10:39:09.967249: step: 1432/530, loss: 0.029845189303159714
2023-01-21 10:39:11.095627: step: 1436/530, loss: 0.0023685453925281763
2023-01-21 10:39:12.231285: step: 1440/530, loss: 0.02087840996682644
2023-01-21 10:39:13.354845: step: 1444/530, loss: 0.010367393493652344
2023-01-21 10:39:14.470686: step: 1448/530, loss: 0.055041778832674026
2023-01-21 10:39:15.587496: step: 1452/530, loss: 0.025073720142245293
2023-01-21 10:39:16.710131: step: 1456/530, loss: 0.014637185260653496
2023-01-21 10:39:17.792142: step: 1460/530, loss: 0.10305138677358627
2023-01-21 10:39:18.892539: step: 1464/530, loss: 0.07657727599143982
2023-01-21 10:39:19.989094: step: 1468/530, loss: 0.00577235221862793
2023-01-21 10:39:21.091715: step: 1472/530, loss: 0.037941742688417435
2023-01-21 10:39:22.216283: step: 1476/530, loss: 0.05729350820183754
2023-01-21 10:39:23.336497: step: 1480/530, loss: 0.04704008251428604
2023-01-21 10:39:24.449272: step: 1484/530, loss: 0.012769078835844994
2023-01-21 10:39:25.554339: step: 1488/530, loss: 0.1735800802707672
2023-01-21 10:39:26.656372: step: 1492/530, loss: 0.03529825434088707
2023-01-21 10:39:27.767482: step: 1496/530, loss: 0.10106156021356583
2023-01-21 10:39:28.874152: step: 1500/530, loss: 0.020718956366181374
2023-01-21 10:39:29.971954: step: 1504/530, loss: 0.016636420041322708
2023-01-21 10:39:31.074776: step: 1508/530, loss: 0.029117537662386894
2023-01-21 10:39:32.208613: step: 1512/530, loss: 0.20411300659179688
2023-01-21 10:39:33.361609: step: 1516/530, loss: 0.09355974197387695
2023-01-21 10:39:34.521425: step: 1520/530, loss: 0.1594589203596115
2023-01-21 10:39:35.614902: step: 1524/530, loss: 0.035562921315431595
2023-01-21 10:39:36.701527: step: 1528/530, loss: 0.030826473608613014
2023-01-21 10:39:37.799458: step: 1532/530, loss: 0.04639816656708717
2023-01-21 10:39:38.899247: step: 1536/530, loss: 0.002740764757618308
2023-01-21 10:39:40.007976: step: 1540/530, loss: 0.01763463020324707
2023-01-21 10:39:41.132990: step: 1544/530, loss: 0.03533878177404404
2023-01-21 10:39:42.219629: step: 1548/530, loss: 0.002085018204525113
2023-01-21 10:39:43.310673: step: 1552/530, loss: 0.038984108716249466
2023-01-21 10:39:44.374146: step: 1556/530, loss: 0.01623830758035183
2023-01-21 10:39:45.495862: step: 1560/530, loss: 0.477698415517807
2023-01-21 10:39:46.608388: step: 1564/530, loss: 0.03649912029504776
2023-01-21 10:39:47.733094: step: 1568/530, loss: 0.05480947718024254
2023-01-21 10:39:48.814763: step: 1572/530, loss: 0.0018564224010333419
2023-01-21 10:39:49.934367: step: 1576/530, loss: 0.08095093071460724
2023-01-21 10:39:51.065458: step: 1580/530, loss: 0.029819583520293236
2023-01-21 10:39:52.151481: step: 1584/530, loss: 0.04954786226153374
2023-01-21 10:39:53.281141: step: 1588/530, loss: 0.04645295441150665
2023-01-21 10:39:54.409294: step: 1592/530, loss: 0.03908901289105415
2023-01-21 10:39:55.486834: step: 1596/530, loss: 0.05355939641594887
2023-01-21 10:39:56.582583: step: 1600/530, loss: 0.05258655548095703
2023-01-21 10:39:57.719971: step: 1604/530, loss: 0.11353526264429092
2023-01-21 10:39:58.820502: step: 1608/530, loss: 0.03134965896606445
2023-01-21 10:39:59.907569: step: 1612/530, loss: 0.03582439571619034
2023-01-21 10:40:01.070795: step: 1616/530, loss: 0.025363540276885033
2023-01-21 10:40:02.199801: step: 1620/530, loss: 0.08655862510204315
2023-01-21 10:40:03.362454: step: 1624/530, loss: 0.001968860626220703
2023-01-21 10:40:04.489490: step: 1628/530, loss: 0.0023981095291674137
2023-01-21 10:40:05.603729: step: 1632/530, loss: 0.0614381805062294
2023-01-21 10:40:06.688641: step: 1636/530, loss: 0.1926080733537674
2023-01-21 10:40:07.795530: step: 1640/530, loss: 0.08081059157848358
2023-01-21 10:40:08.895276: step: 1644/530, loss: 0.1627291738986969
2023-01-21 10:40:10.006318: step: 1648/530, loss: 0.018153857439756393
2023-01-21 10:40:11.119499: step: 1652/530, loss: 0.06737180054187775
2023-01-21 10:40:12.203874: step: 1656/530, loss: 0.42687034606933594
2023-01-21 10:40:13.314373: step: 1660/530, loss: 0.021570205688476562
2023-01-21 10:40:14.414990: step: 1664/530, loss: 0.062410593032836914
2023-01-21 10:40:15.539697: step: 1668/530, loss: 0.15253382921218872
2023-01-21 10:40:16.646034: step: 1672/530, loss: 0.04922495037317276
2023-01-21 10:40:17.769686: step: 1676/530, loss: 0.07331438362598419
2023-01-21 10:40:18.901767: step: 1680/530, loss: 0.012849998660385609
2023-01-21 10:40:20.008762: step: 1684/530, loss: 0.052106477320194244
2023-01-21 10:40:21.124795: step: 1688/530, loss: 0.02233600616455078
2023-01-21 10:40:22.258103: step: 1692/530, loss: 0.06385879218578339
2023-01-21 10:40:23.380080: step: 1696/530, loss: 0.09615517407655716
2023-01-21 10:40:24.475481: step: 1700/530, loss: 0.044299982488155365
2023-01-21 10:40:25.576957: step: 1704/530, loss: 0.024796176701784134
2023-01-21 10:40:26.721390: step: 1708/530, loss: 0.053911250084638596
2023-01-21 10:40:27.819906: step: 1712/530, loss: 0.022984886541962624
2023-01-21 10:40:28.937625: step: 1716/530, loss: 0.1483118087053299
2023-01-21 10:40:30.026088: step: 1720/530, loss: 0.1426558494567871
2023-01-21 10:40:31.133916: step: 1724/530, loss: 0.044199731200933456
2023-01-21 10:40:32.235357: step: 1728/530, loss: 0.0599767230451107
2023-01-21 10:40:33.362587: step: 1732/530, loss: 0.019617414101958275
2023-01-21 10:40:34.486801: step: 1736/530, loss: 0.2137984335422516
2023-01-21 10:40:35.595650: step: 1740/530, loss: 0.012730885297060013
2023-01-21 10:40:36.716146: step: 1744/530, loss: 0.045186806470155716
2023-01-21 10:40:37.818434: step: 1748/530, loss: 0.03270091861486435
2023-01-21 10:40:38.945975: step: 1752/530, loss: 0.05823421850800514
2023-01-21 10:40:40.067286: step: 1756/530, loss: 0.0025764943566173315
2023-01-21 10:40:41.170807: step: 1760/530, loss: 0.02281980589032173
2023-01-21 10:40:42.274767: step: 1764/530, loss: 0.06588523089885712
2023-01-21 10:40:43.366251: step: 1768/530, loss: 0.0008783340454101562
2023-01-21 10:40:44.483780: step: 1772/530, loss: 0.03944587707519531
2023-01-21 10:40:45.591079: step: 1776/530, loss: 0.059264231473207474
2023-01-21 10:40:46.718189: step: 1780/530, loss: 0.0342438705265522
2023-01-21 10:40:47.800718: step: 1784/530, loss: 0.02171487919986248
2023-01-21 10:40:48.943882: step: 1788/530, loss: 0.02807140350341797
2023-01-21 10:40:50.025847: step: 1792/530, loss: 0.012122392654418945
2023-01-21 10:40:51.132087: step: 1796/530, loss: 0.03112201578915119
2023-01-21 10:40:52.223450: step: 1800/530, loss: 0.029650593176484108
2023-01-21 10:40:53.333093: step: 1804/530, loss: 0.0016728402115404606
2023-01-21 10:40:54.443095: step: 1808/530, loss: 0.03131360933184624
2023-01-21 10:40:55.532665: step: 1812/530, loss: 0.041707880795001984
2023-01-21 10:40:56.636310: step: 1816/530, loss: 0.07412929087877274
2023-01-21 10:40:57.781803: step: 1820/530, loss: 0.34434399008750916
2023-01-21 10:40:58.915961: step: 1824/530, loss: 0.12465324252843857
2023-01-21 10:41:00.050514: step: 1828/530, loss: 0.02382803149521351
2023-01-21 10:41:01.176637: step: 1832/530, loss: 6.093580722808838
2023-01-21 10:41:02.297424: step: 1836/530, loss: 0.2687739431858063
2023-01-21 10:41:03.436913: step: 1840/530, loss: 0.10307230800390244
2023-01-21 10:41:04.590836: step: 1844/530, loss: 0.004894256591796875
2023-01-21 10:41:05.693713: step: 1848/530, loss: 0.08389768749475479
2023-01-21 10:41:06.811813: step: 1852/530, loss: 0.02436981163918972
2023-01-21 10:41:07.900398: step: 1856/530, loss: 0.009558772668242455
2023-01-21 10:41:09.006285: step: 1860/530, loss: 0.027902889996767044
2023-01-21 10:41:10.123691: step: 1864/530, loss: 0.016843892633914948
2023-01-21 10:41:11.243947: step: 1868/530, loss: 0.2397083342075348
2023-01-21 10:41:12.331624: step: 1872/530, loss: 0.02057565376162529
2023-01-21 10:41:13.412030: step: 1876/530, loss: 0.05014371871948242
2023-01-21 10:41:14.505770: step: 1880/530, loss: 0.03890800476074219
2023-01-21 10:41:15.650703: step: 1884/530, loss: 0.019967176020145416
2023-01-21 10:41:16.782950: step: 1888/530, loss: 0.040175724774599075
2023-01-21 10:41:17.901105: step: 1892/530, loss: 0.06426181644201279
2023-01-21 10:41:19.024812: step: 1896/530, loss: 0.04157695919275284
2023-01-21 10:41:20.130370: step: 1900/530, loss: 0.02451639249920845
2023-01-21 10:41:21.251250: step: 1904/530, loss: 0.01828775554895401
2023-01-21 10:41:22.343815: step: 1908/530, loss: 0.05919589847326279
2023-01-21 10:41:23.440355: step: 1912/530, loss: 0.059839341789484024
2023-01-21 10:41:24.553582: step: 1916/530, loss: 0.002083253813907504
2023-01-21 10:41:25.644526: step: 1920/530, loss: 0.012130928225815296
2023-01-21 10:41:26.793753: step: 1924/530, loss: 0.0004718780401162803
2023-01-21 10:41:27.952854: step: 1928/530, loss: 0.03372631222009659
2023-01-21 10:41:29.066779: step: 1932/530, loss: 0.20556049048900604
2023-01-21 10:41:30.171348: step: 1936/530, loss: 0.029574299231171608
2023-01-21 10:41:31.276466: step: 1940/530, loss: 0.011908531188964844
2023-01-21 10:41:32.401979: step: 1944/530, loss: 0.019826317206025124
2023-01-21 10:41:33.522464: step: 1948/530, loss: 0.005842399783432484
2023-01-21 10:41:34.651111: step: 1952/530, loss: 0.03626060485839844
2023-01-21 10:41:35.765306: step: 1956/530, loss: 0.010868263430893421
2023-01-21 10:41:36.866782: step: 1960/530, loss: 0.0018940926529467106
2023-01-21 10:41:37.978210: step: 1964/530, loss: 0.0582517646253109
2023-01-21 10:41:39.103874: step: 1968/530, loss: 0.02425565756857395
2023-01-21 10:41:40.238543: step: 1972/530, loss: 0.07246483862400055
2023-01-21 10:41:41.337921: step: 1976/530, loss: 0.00021843911963514984
2023-01-21 10:41:42.479865: step: 1980/530, loss: 0.08026814460754395
2023-01-21 10:41:43.577021: step: 1984/530, loss: 0.029352569952607155
2023-01-21 10:41:44.716267: step: 1988/530, loss: 0.13591709733009338
2023-01-21 10:41:45.825190: step: 1992/530, loss: 0.15342122316360474
2023-01-21 10:41:46.918111: step: 1996/530, loss: 0.005196571350097656
2023-01-21 10:41:48.071083: step: 2000/530, loss: 0.024103974923491478
2023-01-21 10:41:49.192567: step: 2004/530, loss: 0.011603927239775658
2023-01-21 10:41:50.333789: step: 2008/530, loss: 0.05790739133954048
2023-01-21 10:41:51.446357: step: 2012/530, loss: 0.06800079345703125
2023-01-21 10:41:52.561433: step: 2016/530, loss: 0.06087642163038254
2023-01-21 10:41:53.694625: step: 2020/530, loss: 0.014367818832397461
2023-01-21 10:41:54.835536: step: 2024/530, loss: 0.050966836512088776
2023-01-21 10:41:55.933628: step: 2028/530, loss: 0.05780401453375816
2023-01-21 10:41:57.033302: step: 2032/530, loss: 0.008212518878281116
2023-01-21 10:41:58.164695: step: 2036/530, loss: 0.020195960998535156
2023-01-21 10:41:59.284884: step: 2040/530, loss: 0.02652750164270401
2023-01-21 10:42:00.387377: step: 2044/530, loss: 0.0038254738319665194
2023-01-21 10:42:01.503659: step: 2048/530, loss: 0.06252650916576385
2023-01-21 10:42:02.643202: step: 2052/530, loss: 0.1032039150595665
2023-01-21 10:42:03.763209: step: 2056/530, loss: 0.06172027438879013
2023-01-21 10:42:04.871375: step: 2060/530, loss: 0.05524921417236328
2023-01-21 10:42:06.017131: step: 2064/530, loss: 0.01191787701100111
2023-01-21 10:42:07.127519: step: 2068/530, loss: 0.15121574699878693
2023-01-21 10:42:08.237950: step: 2072/530, loss: 0.03222007676959038
2023-01-21 10:42:09.330858: step: 2076/530, loss: 0.0024065019097179174
2023-01-21 10:42:10.431309: step: 2080/530, loss: 0.026377486065030098
2023-01-21 10:42:11.543419: step: 2084/530, loss: 0.01965632662177086
2023-01-21 10:42:12.670557: step: 2088/530, loss: 0.051439620554447174
2023-01-21 10:42:13.804341: step: 2092/530, loss: 0.03644991293549538
2023-01-21 10:42:14.929699: step: 2096/530, loss: 0.06446738541126251
2023-01-21 10:42:16.007446: step: 2100/530, loss: 0.023418238386511803
2023-01-21 10:42:17.106056: step: 2104/530, loss: 0.08159048855304718
2023-01-21 10:42:18.200532: step: 2108/530, loss: 0.10870043188333511
2023-01-21 10:42:19.321817: step: 2112/530, loss: 0.14680452644824982
2023-01-21 10:42:20.425357: step: 2116/530, loss: 0.05283393710851669
2023-01-21 10:42:21.551316: step: 2120/530, loss: 0.015566349029541016
==================================================
Loss: 0.077
--------------------
Dev: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Test: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Russian: {'event': {'p': 0.45714285714285713, 'r': 0.4444444444444444, 'f1': 0.4507042253521127}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 10:43:16.127151: step: 4/530, loss: 0.010338783264160156
2023-01-21 10:43:17.217141: step: 8/530, loss: 0.03937244415283203
2023-01-21 10:43:18.317814: step: 12/530, loss: 0.020406628027558327
2023-01-21 10:43:19.454450: step: 16/530, loss: 0.042916011065244675
2023-01-21 10:43:20.597837: step: 20/530, loss: 0.06998996436595917
2023-01-21 10:43:21.727685: step: 24/530, loss: 0.0072157857939600945
2023-01-21 10:43:22.814057: step: 28/530, loss: 0.025925161316990852
2023-01-21 10:43:23.936838: step: 32/530, loss: 0.00586700439453125
2023-01-21 10:43:25.059900: step: 36/530, loss: 0.05807862430810928
2023-01-21 10:43:26.225611: step: 40/530, loss: 0.016925431787967682
2023-01-21 10:43:27.323104: step: 44/530, loss: 0.013360977172851562
2023-01-21 10:43:28.424971: step: 48/530, loss: 0.03311128541827202
2023-01-21 10:43:29.523822: step: 52/530, loss: 0.03128395229578018
2023-01-21 10:43:30.654075: step: 56/530, loss: 0.0023470879532396793
2023-01-21 10:43:31.772817: step: 60/530, loss: 0.032572176307439804
2023-01-21 10:43:32.870561: step: 64/530, loss: 0.024111270904541016
2023-01-21 10:43:34.016081: step: 68/530, loss: 0.00566492136567831
2023-01-21 10:43:35.112447: step: 72/530, loss: 0.0015707015991210938
2023-01-21 10:43:36.202372: step: 76/530, loss: 0.0338476188480854
2023-01-21 10:43:37.322268: step: 80/530, loss: 0.21581107378005981
2023-01-21 10:43:38.482178: step: 84/530, loss: 0.09263086318969727
2023-01-21 10:43:39.593587: step: 88/530, loss: 0.17962618172168732
2023-01-21 10:43:40.738538: step: 92/530, loss: 0.002164554549381137
2023-01-21 10:43:41.870806: step: 96/530, loss: 0.013078879565000534
2023-01-21 10:43:42.988640: step: 100/530, loss: 0.0051864152774214745
2023-01-21 10:43:44.109572: step: 104/530, loss: 0.012320756912231445
2023-01-21 10:43:45.237428: step: 108/530, loss: 0.06429815292358398
2023-01-21 10:43:46.362606: step: 112/530, loss: 0.06812362372875214
2023-01-21 10:43:47.470982: step: 116/530, loss: 0.009716319851577282
2023-01-21 10:43:48.577937: step: 120/530, loss: 0.024005508050322533
2023-01-21 10:43:49.737056: step: 124/530, loss: 0.1008627861738205
2023-01-21 10:43:50.849586: step: 128/530, loss: 0.007063637487590313
2023-01-21 10:43:51.937514: step: 132/530, loss: 0.03397336229681969
2023-01-21 10:43:53.036513: step: 136/530, loss: 0.047632597386837006
2023-01-21 10:43:54.137902: step: 140/530, loss: 0.0009088516235351562
2023-01-21 10:43:55.233783: step: 144/530, loss: 0.0023310661781579256
2023-01-21 10:43:56.337770: step: 148/530, loss: 0.02565460465848446
2023-01-21 10:43:57.415692: step: 152/530, loss: 0.022119522094726562
2023-01-21 10:43:58.504049: step: 156/530, loss: 0.053354837000370026
2023-01-21 10:43:59.611008: step: 160/530, loss: 0.030416490510106087
2023-01-21 10:44:00.735108: step: 164/530, loss: 0.16296347975730896
2023-01-21 10:44:01.839608: step: 168/530, loss: 0.23141264915466309
2023-01-21 10:44:02.934281: step: 172/530, loss: 0.028998469933867455
2023-01-21 10:44:04.028833: step: 176/530, loss: 0.02377014234662056
2023-01-21 10:44:05.125857: step: 180/530, loss: 0.007561206817626953
2023-01-21 10:44:06.269854: step: 184/530, loss: 0.08007955551147461
2023-01-21 10:44:07.389685: step: 188/530, loss: 0.0014085769653320312
2023-01-21 10:44:08.489213: step: 192/530, loss: 0.009831237606704235
2023-01-21 10:44:09.595481: step: 196/530, loss: 0.04229545593261719
2023-01-21 10:44:10.701699: step: 200/530, loss: 0.018998337909579277
2023-01-21 10:44:11.813096: step: 204/530, loss: 0.032590102404356
2023-01-21 10:44:12.898373: step: 208/530, loss: 0.02253122441470623
2023-01-21 10:44:14.010397: step: 212/530, loss: 0.051273345947265625
2023-01-21 10:44:15.107267: step: 216/530, loss: 0.002879810519516468
2023-01-21 10:44:16.197835: step: 220/530, loss: 0.0307940486818552
2023-01-21 10:44:17.295740: step: 224/530, loss: 0.02374458499252796
2023-01-21 10:44:18.395313: step: 228/530, loss: 0.03650369495153427
2023-01-21 10:44:19.529792: step: 232/530, loss: 0.04383029788732529
2023-01-21 10:44:20.654490: step: 236/530, loss: 0.07303428649902344
2023-01-21 10:44:21.786603: step: 240/530, loss: 0.007997703738510609
2023-01-21 10:44:22.918338: step: 244/530, loss: 0.034932516515254974
2023-01-21 10:44:24.022411: step: 248/530, loss: 0.028576470911502838
2023-01-21 10:44:25.127940: step: 252/530, loss: 0.008052635006606579
2023-01-21 10:44:26.247508: step: 256/530, loss: 0.025313567370176315
2023-01-21 10:44:27.397455: step: 260/530, loss: 0.1439172625541687
2023-01-21 10:44:28.510656: step: 264/530, loss: 0.048309326171875
2023-01-21 10:44:29.633338: step: 268/530, loss: 1.3479048013687134
2023-01-21 10:44:30.764446: step: 272/530, loss: 0.0496278777718544
2023-01-21 10:44:31.867188: step: 276/530, loss: 0.07445869594812393
2023-01-21 10:44:32.996443: step: 280/530, loss: 0.026566125452518463
2023-01-21 10:44:34.121877: step: 284/530, loss: 0.057004641741514206
2023-01-21 10:44:35.241934: step: 288/530, loss: 0.017602598294615746
2023-01-21 10:44:36.361702: step: 292/530, loss: 0.04711494594812393
2023-01-21 10:44:37.475511: step: 296/530, loss: 0.1427549421787262
2023-01-21 10:44:38.603235: step: 300/530, loss: 0.05304918438196182
2023-01-21 10:44:39.753945: step: 304/530, loss: 0.09182686358690262
2023-01-21 10:44:40.877986: step: 308/530, loss: 0.001195764634758234
2023-01-21 10:44:42.009211: step: 312/530, loss: 0.04993772506713867
2023-01-21 10:44:43.084607: step: 316/530, loss: 0.0007867336389608681
2023-01-21 10:44:44.228740: step: 320/530, loss: 0.023862741887569427
2023-01-21 10:44:45.319205: step: 324/530, loss: 0.017171572893857956
2023-01-21 10:44:46.417871: step: 328/530, loss: 0.05512294918298721
2023-01-21 10:44:47.513365: step: 332/530, loss: 0.047381214797496796
2023-01-21 10:44:48.617742: step: 336/530, loss: 0.007836151868104935
2023-01-21 10:44:49.744171: step: 340/530, loss: 0.0010083199013024569
2023-01-21 10:44:50.858078: step: 344/530, loss: 0.052090834826231
2023-01-21 10:44:51.940952: step: 348/530, loss: 0.00030536652775481343
2023-01-21 10:44:53.060511: step: 352/530, loss: 0.0531742125749588
2023-01-21 10:44:54.192687: step: 356/530, loss: 0.07771263271570206
2023-01-21 10:44:55.319702: step: 360/530, loss: 0.02699895203113556
2023-01-21 10:44:56.415807: step: 364/530, loss: 0.08803115040063858
2023-01-21 10:44:57.530263: step: 368/530, loss: 0.03445129096508026
2023-01-21 10:44:58.646774: step: 372/530, loss: 0.3445380926132202
2023-01-21 10:44:59.753638: step: 376/530, loss: 0.005825424566864967
2023-01-21 10:45:00.826800: step: 380/530, loss: 0.050376322120428085
2023-01-21 10:45:01.966690: step: 384/530, loss: 0.016491984948515892
2023-01-21 10:45:03.092107: step: 388/530, loss: 0.009643363766372204
2023-01-21 10:45:04.209877: step: 392/530, loss: 0.006291198544204235
2023-01-21 10:45:05.337949: step: 396/530, loss: 0.053534507751464844
2023-01-21 10:45:06.490954: step: 400/530, loss: 0.06223764643073082
2023-01-21 10:45:07.628172: step: 404/530, loss: 0.14410322904586792
2023-01-21 10:45:08.779963: step: 408/530, loss: 0.015216636471450329
2023-01-21 10:45:09.880006: step: 412/530, loss: 0.0102570541203022
2023-01-21 10:45:10.982181: step: 416/530, loss: 0.017113065347075462
2023-01-21 10:45:12.105638: step: 420/530, loss: 0.04796038195490837
2023-01-21 10:45:13.183558: step: 424/530, loss: 0.0007107734563760459
2023-01-21 10:45:14.303474: step: 428/530, loss: 0.021693039685487747
2023-01-21 10:45:15.419379: step: 432/530, loss: 0.0009634018060751259
2023-01-21 10:45:16.517796: step: 436/530, loss: 0.011694908142089844
2023-01-21 10:45:17.626781: step: 440/530, loss: 0.012576961889863014
2023-01-21 10:45:18.758254: step: 444/530, loss: 0.0637701004743576
2023-01-21 10:45:19.879385: step: 448/530, loss: 0.007513142190873623
2023-01-21 10:45:21.005796: step: 452/530, loss: 0.030734064057469368
2023-01-21 10:45:22.125296: step: 456/530, loss: 0.06175249069929123
2023-01-21 10:45:23.231255: step: 460/530, loss: 0.0865272581577301
2023-01-21 10:45:24.355307: step: 464/530, loss: 0.02545337751507759
2023-01-21 10:45:25.458422: step: 468/530, loss: 0.006183624733239412
2023-01-21 10:45:26.571840: step: 472/530, loss: 0.032352447509765625
2023-01-21 10:45:27.671403: step: 476/530, loss: 0.035086870193481445
2023-01-21 10:45:28.810500: step: 480/530, loss: 0.00989389419555664
2023-01-21 10:45:29.907914: step: 484/530, loss: 0.028569508343935013
2023-01-21 10:45:31.047600: step: 488/530, loss: 0.015160275623202324
2023-01-21 10:45:32.156918: step: 492/530, loss: 0.04662156105041504
2023-01-21 10:45:33.281944: step: 496/530, loss: 0.3977595865726471
2023-01-21 10:45:34.371399: step: 500/530, loss: 0.016504287719726562
2023-01-21 10:45:35.495131: step: 504/530, loss: 0.005976009648293257
2023-01-21 10:45:36.612278: step: 508/530, loss: 0.045073606073856354
2023-01-21 10:45:37.727975: step: 512/530, loss: 0.0394803062081337
2023-01-21 10:45:38.836189: step: 516/530, loss: 0.04611530154943466
2023-01-21 10:45:39.937131: step: 520/530, loss: 0.023482704535126686
2023-01-21 10:45:41.032174: step: 524/530, loss: 0.02788562886416912
2023-01-21 10:45:42.144474: step: 528/530, loss: 0.026611899957060814
2023-01-21 10:45:43.250044: step: 532/530, loss: 0.008923912420868874
2023-01-21 10:45:44.356365: step: 536/530, loss: 0.010407638736069202
2023-01-21 10:45:45.464454: step: 540/530, loss: 0.023578930646181107
2023-01-21 10:45:46.575536: step: 544/530, loss: 0.026604462414979935
2023-01-21 10:45:47.680149: step: 548/530, loss: 0.10553817451000214
2023-01-21 10:45:48.780559: step: 552/530, loss: 0.021996211260557175
2023-01-21 10:45:49.905927: step: 556/530, loss: 0.06420020759105682
2023-01-21 10:45:51.014145: step: 560/530, loss: 0.09322868287563324
2023-01-21 10:45:52.107425: step: 564/530, loss: 0.34221163392066956
2023-01-21 10:45:53.203480: step: 568/530, loss: 0.08991508185863495
2023-01-21 10:45:54.313103: step: 572/530, loss: 0.0015178680187091231
2023-01-21 10:45:55.456309: step: 576/530, loss: 0.014760208316147327
2023-01-21 10:45:56.570918: step: 580/530, loss: 0.10044021904468536
2023-01-21 10:45:57.671002: step: 584/530, loss: 0.06441430747509003
2023-01-21 10:45:58.821197: step: 588/530, loss: 0.006491375155746937
2023-01-21 10:45:59.930203: step: 592/530, loss: 0.05071773752570152
2023-01-21 10:46:01.058745: step: 596/530, loss: 0.14585629105567932
2023-01-21 10:46:02.159325: step: 600/530, loss: 0.043434906750917435
2023-01-21 10:46:03.266544: step: 604/530, loss: 0.007934189401566982
2023-01-21 10:46:04.374967: step: 608/530, loss: 0.05602607876062393
2023-01-21 10:46:05.485180: step: 612/530, loss: 0.003832912538200617
2023-01-21 10:46:06.579040: step: 616/530, loss: 0.024837495759129524
2023-01-21 10:46:07.691324: step: 620/530, loss: 0.0011158466804772615
2023-01-21 10:46:08.825739: step: 624/530, loss: 0.02927389182150364
2023-01-21 10:46:09.942313: step: 628/530, loss: 0.17319431900978088
2023-01-21 10:46:11.070037: step: 632/530, loss: 0.008128928951919079
2023-01-21 10:46:12.180372: step: 636/530, loss: 0.03719482570886612
2023-01-21 10:46:13.269912: step: 640/530, loss: 0.2760624885559082
2023-01-21 10:46:14.388586: step: 644/530, loss: 0.013302231207489967
2023-01-21 10:46:15.529929: step: 648/530, loss: 0.3628973066806793
2023-01-21 10:46:16.636439: step: 652/530, loss: 0.08431144058704376
2023-01-21 10:46:17.799340: step: 656/530, loss: 0.08350582420825958
2023-01-21 10:46:18.895372: step: 660/530, loss: 0.02348480373620987
2023-01-21 10:46:19.975527: step: 664/530, loss: 0.04370307922363281
2023-01-21 10:46:21.082906: step: 668/530, loss: 0.09541530162096024
2023-01-21 10:46:22.193285: step: 672/530, loss: 0.035933684557676315
2023-01-21 10:46:23.306400: step: 676/530, loss: 0.07130423933267593
2023-01-21 10:46:24.419765: step: 680/530, loss: 0.006678295321762562
2023-01-21 10:46:25.524303: step: 684/530, loss: 0.011517524719238281
2023-01-21 10:46:26.625688: step: 688/530, loss: 0.0009331703186035156
2023-01-21 10:46:27.779035: step: 692/530, loss: 0.03302412107586861
2023-01-21 10:46:28.888820: step: 696/530, loss: 0.017586994916200638
2023-01-21 10:46:29.991498: step: 700/530, loss: 0.0015340804820880294
2023-01-21 10:46:31.097381: step: 704/530, loss: 0.2513389587402344
2023-01-21 10:46:32.213583: step: 708/530, loss: 0.03002472035586834
2023-01-21 10:46:33.323712: step: 712/530, loss: 0.0988689437508583
2023-01-21 10:46:34.416847: step: 716/530, loss: 0.003219032194465399
2023-01-21 10:46:35.521938: step: 720/530, loss: 0.10665331035852432
2023-01-21 10:46:36.618061: step: 724/530, loss: 0.046952441334724426
2023-01-21 10:46:37.732878: step: 728/530, loss: 0.015474224463105202
2023-01-21 10:46:38.824902: step: 732/530, loss: 0.011149119585752487
2023-01-21 10:46:39.932780: step: 736/530, loss: 0.0017066956497728825
2023-01-21 10:46:41.044353: step: 740/530, loss: 0.09497762471437454
2023-01-21 10:46:42.213693: step: 744/530, loss: 0.027863884344697
2023-01-21 10:46:43.335705: step: 748/530, loss: 0.03333025053143501
2023-01-21 10:46:44.433136: step: 752/530, loss: 0.06128654628992081
2023-01-21 10:46:45.518455: step: 756/530, loss: 0.047747902572155
2023-01-21 10:46:46.676932: step: 760/530, loss: 0.022834395989775658
2023-01-21 10:46:47.789708: step: 764/530, loss: 0.1315334290266037
2023-01-21 10:46:48.893755: step: 768/530, loss: 0.07128391414880753
2023-01-21 10:46:50.010708: step: 772/530, loss: 0.01073226984590292
2023-01-21 10:46:51.118900: step: 776/530, loss: 0.0070396424271166325
2023-01-21 10:46:52.243029: step: 780/530, loss: 0.020084762945771217
2023-01-21 10:46:53.348977: step: 784/530, loss: 0.08755950629711151
2023-01-21 10:46:54.473018: step: 788/530, loss: 0.048429109156131744
2023-01-21 10:46:55.573086: step: 792/530, loss: 0.07939396053552628
2023-01-21 10:46:56.683922: step: 796/530, loss: 0.024200439453125
2023-01-21 10:46:57.807306: step: 800/530, loss: 0.060389235615730286
2023-01-21 10:46:58.915281: step: 804/530, loss: 0.012849807739257812
2023-01-21 10:47:00.042097: step: 808/530, loss: 0.009954930283129215
2023-01-21 10:47:01.149993: step: 812/530, loss: 0.01673135906457901
2023-01-21 10:47:02.266153: step: 816/530, loss: 0.07015933841466904
2023-01-21 10:47:03.408569: step: 820/530, loss: 0.0017228127690032125
2023-01-21 10:47:04.559202: step: 824/530, loss: 0.008235502988100052
2023-01-21 10:47:05.639736: step: 828/530, loss: 0.03177709877490997
2023-01-21 10:47:06.742164: step: 832/530, loss: 0.023003483191132545
2023-01-21 10:47:07.860288: step: 836/530, loss: 0.050423528999090195
2023-01-21 10:47:08.973719: step: 840/530, loss: 0.05669365078210831
2023-01-21 10:47:10.064347: step: 844/530, loss: 0.031569670885801315
2023-01-21 10:47:11.154470: step: 848/530, loss: 0.02751808427274227
2023-01-21 10:47:12.260329: step: 852/530, loss: 0.0030496600084006786
2023-01-21 10:47:13.370000: step: 856/530, loss: 0.03961982578039169
2023-01-21 10:47:14.470492: step: 860/530, loss: 0.08732762932777405
2023-01-21 10:47:15.573904: step: 864/530, loss: 0.036478426307439804
2023-01-21 10:47:16.649178: step: 868/530, loss: 0.10954676568508148
2023-01-21 10:47:17.762215: step: 872/530, loss: 0.028359128162264824
2023-01-21 10:47:18.920456: step: 876/530, loss: 0.032311439514160156
2023-01-21 10:47:20.033264: step: 880/530, loss: 0.018230844289064407
2023-01-21 10:47:21.117318: step: 884/530, loss: 0.01276321429759264
2023-01-21 10:47:22.228335: step: 888/530, loss: 0.010893153958022594
2023-01-21 10:47:23.345090: step: 892/530, loss: 0.02268095314502716
2023-01-21 10:47:24.465111: step: 896/530, loss: 0.0025853158440440893
2023-01-21 10:47:25.561246: step: 900/530, loss: 0.01673908159136772
2023-01-21 10:47:26.645223: step: 904/530, loss: 0.073175810277462
2023-01-21 10:47:27.767874: step: 908/530, loss: 0.0021816908847540617
2023-01-21 10:47:28.854920: step: 912/530, loss: 0.006593227386474609
2023-01-21 10:47:29.966285: step: 916/530, loss: 0.02126750908792019
2023-01-21 10:47:31.072603: step: 920/530, loss: 0.013964463025331497
2023-01-21 10:47:32.190984: step: 924/530, loss: 0.03364090994000435
2023-01-21 10:47:33.327770: step: 928/530, loss: 0.009216021746397018
2023-01-21 10:47:34.470153: step: 932/530, loss: 0.02861194685101509
2023-01-21 10:47:35.587381: step: 936/530, loss: 0.03366098552942276
2023-01-21 10:47:36.719453: step: 940/530, loss: 0.055822089314460754
2023-01-21 10:47:37.841185: step: 944/530, loss: 0.006997585296630859
2023-01-21 10:47:38.948705: step: 948/530, loss: 0.028049517422914505
2023-01-21 10:47:40.069676: step: 952/530, loss: 0.011530017480254173
2023-01-21 10:47:41.155256: step: 956/530, loss: 0.036008644849061966
2023-01-21 10:47:42.263330: step: 960/530, loss: 0.0007014751899987459
2023-01-21 10:47:43.383305: step: 964/530, loss: 0.040674399584531784
2023-01-21 10:47:44.511058: step: 968/530, loss: 0.0021470070350915194
2023-01-21 10:47:45.633863: step: 972/530, loss: 0.03356514126062393
2023-01-21 10:47:46.789078: step: 976/530, loss: 0.012336350046098232
2023-01-21 10:47:47.885366: step: 980/530, loss: 0.007206535432487726
2023-01-21 10:47:48.993939: step: 984/530, loss: 0.009570646099746227
2023-01-21 10:47:50.087019: step: 988/530, loss: 0.05348358303308487
2023-01-21 10:47:51.182301: step: 992/530, loss: 0.019399693235754967
2023-01-21 10:47:52.280426: step: 996/530, loss: 0.1037638708949089
2023-01-21 10:47:53.398073: step: 1000/530, loss: 0.013699246570467949
2023-01-21 10:47:54.545385: step: 1004/530, loss: 0.06087846681475639
2023-01-21 10:47:55.647214: step: 1008/530, loss: 0.007978105917572975
2023-01-21 10:47:56.735457: step: 1012/530, loss: 0.03927498310804367
2023-01-21 10:47:57.833876: step: 1016/530, loss: 0.017318058758974075
2023-01-21 10:47:58.925313: step: 1020/530, loss: 0.006558513268828392
2023-01-21 10:48:00.009704: step: 1024/530, loss: 0.030318165197968483
2023-01-21 10:48:01.104603: step: 1028/530, loss: 0.06049642711877823
2023-01-21 10:48:02.218212: step: 1032/530, loss: 0.0031309130135923624
2023-01-21 10:48:03.321677: step: 1036/530, loss: 0.0031955719459801912
2023-01-21 10:48:04.437773: step: 1040/530, loss: 0.18545348942279816
2023-01-21 10:48:05.540006: step: 1044/530, loss: 0.01234884187579155
2023-01-21 10:48:06.640592: step: 1048/530, loss: 0.03277568891644478
2023-01-21 10:48:07.761756: step: 1052/530, loss: 0.0341181755065918
2023-01-21 10:48:08.878588: step: 1056/530, loss: 0.03468380123376846
2023-01-21 10:48:10.005445: step: 1060/530, loss: 0.08007068932056427
2023-01-21 10:48:11.081820: step: 1064/530, loss: 0.0023735046852380037
2023-01-21 10:48:12.164336: step: 1068/530, loss: 0.011370993219316006
2023-01-21 10:48:13.265059: step: 1072/530, loss: 0.0012920380104333162
2023-01-21 10:48:14.365538: step: 1076/530, loss: 0.0025459290482103825
2023-01-21 10:48:15.461643: step: 1080/530, loss: 0.029685402289032936
2023-01-21 10:48:16.588987: step: 1084/530, loss: 0.09148693084716797
2023-01-21 10:48:17.766018: step: 1088/530, loss: 0.01048264466226101
2023-01-21 10:48:18.899838: step: 1092/530, loss: 0.013360404409468174
2023-01-21 10:48:20.002790: step: 1096/530, loss: 0.0662989392876625
2023-01-21 10:48:21.137405: step: 1100/530, loss: 0.01094288844615221
2023-01-21 10:48:22.207377: step: 1104/530, loss: 0.006637859158217907
2023-01-21 10:48:23.327150: step: 1108/530, loss: 0.08928364515304565
2023-01-21 10:48:24.439534: step: 1112/530, loss: 0.005601406097412109
2023-01-21 10:48:25.530337: step: 1116/530, loss: 0.003394508268684149
2023-01-21 10:48:26.674335: step: 1120/530, loss: 0.062195394188165665
2023-01-21 10:48:27.778304: step: 1124/530, loss: 0.006798744201660156
2023-01-21 10:48:28.903906: step: 1128/530, loss: 0.06677937507629395
2023-01-21 10:48:30.020316: step: 1132/530, loss: 0.017731856554746628
2023-01-21 10:48:31.143049: step: 1136/530, loss: 0.017788507044315338
2023-01-21 10:48:32.234114: step: 1140/530, loss: 0.1297626495361328
2023-01-21 10:48:33.335527: step: 1144/530, loss: 0.05836191028356552
2023-01-21 10:48:34.464643: step: 1148/530, loss: 0.049906209111213684
2023-01-21 10:48:35.578753: step: 1152/530, loss: 0.05413494259119034
2023-01-21 10:48:36.734187: step: 1156/530, loss: 0.06308393180370331
2023-01-21 10:48:37.844750: step: 1160/530, loss: 0.3992176949977875
2023-01-21 10:48:38.957158: step: 1164/530, loss: 0.05857410654425621
2023-01-21 10:48:40.066277: step: 1168/530, loss: 0.006541872397065163
2023-01-21 10:48:41.217790: step: 1172/530, loss: 0.031515009701251984
2023-01-21 10:48:42.337004: step: 1176/530, loss: 0.026569174602627754
2023-01-21 10:48:43.459770: step: 1180/530, loss: 0.03496980667114258
2023-01-21 10:48:44.573638: step: 1184/530, loss: 0.008834362030029297
2023-01-21 10:48:45.654923: step: 1188/530, loss: 0.0043354216031730175
2023-01-21 10:48:46.778012: step: 1192/530, loss: 0.0486297607421875
2023-01-21 10:48:47.856763: step: 1196/530, loss: 0.006222677417099476
2023-01-21 10:48:48.983340: step: 1200/530, loss: 0.036500170826911926
2023-01-21 10:48:50.110467: step: 1204/530, loss: 0.012458229437470436
2023-01-21 10:48:51.225674: step: 1208/530, loss: 0.05542612075805664
2023-01-21 10:48:52.333546: step: 1212/530, loss: 0.022995758801698685
2023-01-21 10:48:53.431417: step: 1216/530, loss: 0.0016830742824822664
2023-01-21 10:48:54.550602: step: 1220/530, loss: 0.25324830412864685
2023-01-21 10:48:55.676302: step: 1224/530, loss: 0.02370157465338707
2023-01-21 10:48:56.785495: step: 1228/530, loss: 0.0323239341378212
2023-01-21 10:48:57.890513: step: 1232/530, loss: 0.08043403923511505
2023-01-21 10:48:59.026708: step: 1236/530, loss: 0.009507370181381702
2023-01-21 10:49:00.160246: step: 1240/530, loss: 0.0159454345703125
2023-01-21 10:49:01.293805: step: 1244/530, loss: 0.0008348464616574347
2023-01-21 10:49:02.393845: step: 1248/530, loss: 0.02211456373333931
2023-01-21 10:49:03.497053: step: 1252/530, loss: 0.12255540490150452
2023-01-21 10:49:04.600444: step: 1256/530, loss: 0.0025011301040649414
2023-01-21 10:49:05.720314: step: 1260/530, loss: 0.10497932881116867
2023-01-21 10:49:06.817977: step: 1264/530, loss: 0.1726401150226593
2023-01-21 10:49:07.920655: step: 1268/530, loss: 0.029425431042909622
2023-01-21 10:49:09.006288: step: 1272/530, loss: 0.01004643552005291
2023-01-21 10:49:10.126582: step: 1276/530, loss: 0.05260968208312988
2023-01-21 10:49:11.238991: step: 1280/530, loss: 0.2399439811706543
2023-01-21 10:49:12.356244: step: 1284/530, loss: 6.712939262390137
2023-01-21 10:49:13.469165: step: 1288/530, loss: 0.01891613006591797
2023-01-21 10:49:14.585477: step: 1292/530, loss: 0.04805717617273331
2023-01-21 10:49:15.712337: step: 1296/530, loss: 0.02878108061850071
2023-01-21 10:49:16.796021: step: 1300/530, loss: 0.03209738805890083
2023-01-21 10:49:17.895187: step: 1304/530, loss: 0.08726797252893448
2023-01-21 10:49:18.995631: step: 1308/530, loss: 0.0014278412563726306
2023-01-21 10:49:20.094784: step: 1312/530, loss: 0.004249954596161842
2023-01-21 10:49:21.236866: step: 1316/530, loss: 0.02029249630868435
2023-01-21 10:49:22.378099: step: 1320/530, loss: 0.02229156531393528
2023-01-21 10:49:23.481068: step: 1324/530, loss: 0.02374943718314171
2023-01-21 10:49:24.613025: step: 1328/530, loss: 0.03050074726343155
2023-01-21 10:49:25.736696: step: 1332/530, loss: 0.042876724153757095
2023-01-21 10:49:26.884245: step: 1336/530, loss: 0.016658782958984375
2023-01-21 10:49:27.984293: step: 1340/530, loss: 0.02742738649249077
2023-01-21 10:49:29.097417: step: 1344/530, loss: 0.02523946948349476
2023-01-21 10:49:30.212424: step: 1348/530, loss: 0.00893106497824192
2023-01-21 10:49:31.324988: step: 1352/530, loss: 0.03062267228960991
2023-01-21 10:49:32.422994: step: 1356/530, loss: 0.052423857152462006
2023-01-21 10:49:33.528987: step: 1360/530, loss: 0.009342575445771217
2023-01-21 10:49:34.634645: step: 1364/530, loss: 0.00614166259765625
2023-01-21 10:49:35.753309: step: 1368/530, loss: 0.04463396221399307
2023-01-21 10:49:36.869130: step: 1372/530, loss: 0.01674785651266575
2023-01-21 10:49:38.003223: step: 1376/530, loss: 0.0039504049345850945
2023-01-21 10:49:39.116016: step: 1380/530, loss: 1.4564108848571777
2023-01-21 10:49:40.208825: step: 1384/530, loss: 0.047625090926885605
2023-01-21 10:49:41.343596: step: 1388/530, loss: 0.027584457769989967
2023-01-21 10:49:42.435429: step: 1392/530, loss: 0.3598521053791046
2023-01-21 10:49:43.545819: step: 1396/530, loss: 0.004367828369140625
2023-01-21 10:49:44.649752: step: 1400/530, loss: 0.011169862933456898
2023-01-21 10:49:45.763222: step: 1404/530, loss: 0.14048127830028534
2023-01-21 10:49:46.868442: step: 1408/530, loss: 0.03316135331988335
2023-01-21 10:49:47.988411: step: 1412/530, loss: 0.05842571333050728
2023-01-21 10:49:49.146109: step: 1416/530, loss: 0.12167854607105255
2023-01-21 10:49:50.276212: step: 1420/530, loss: 0.0013815403217449784
2023-01-21 10:49:51.392342: step: 1424/530, loss: 0.07725677639245987
2023-01-21 10:49:52.547888: step: 1428/530, loss: 0.03309068828821182
2023-01-21 10:49:53.664736: step: 1432/530, loss: 0.0003942489856854081
2023-01-21 10:49:54.791590: step: 1436/530, loss: 0.06089820712804794
2023-01-21 10:49:55.898129: step: 1440/530, loss: 0.0882258415222168
2023-01-21 10:49:56.992011: step: 1444/530, loss: 0.0553835853934288
2023-01-21 10:49:58.116905: step: 1448/530, loss: 0.07328605651855469
2023-01-21 10:49:59.222343: step: 1452/530, loss: 0.08356419205665588
2023-01-21 10:50:00.307474: step: 1456/530, loss: 0.05502531677484512
2023-01-21 10:50:01.397430: step: 1460/530, loss: 0.00025014879065565765
2023-01-21 10:50:02.531335: step: 1464/530, loss: 0.0031418802682310343
2023-01-21 10:50:03.645927: step: 1468/530, loss: 0.004596996121108532
2023-01-21 10:50:04.764233: step: 1472/530, loss: 0.016309166327118874
2023-01-21 10:50:05.883458: step: 1476/530, loss: 0.05700664594769478
2023-01-21 10:50:06.976674: step: 1480/530, loss: 0.04704780504107475
2023-01-21 10:50:08.098326: step: 1484/530, loss: 0.1345779448747635
2023-01-21 10:50:09.212380: step: 1488/530, loss: 0.04135751724243164
2023-01-21 10:50:10.324171: step: 1492/530, loss: 0.010322571732103825
2023-01-21 10:50:11.481297: step: 1496/530, loss: 0.036879923194646835
2023-01-21 10:50:12.613118: step: 1500/530, loss: 0.0373961441218853
2023-01-21 10:50:13.712465: step: 1504/530, loss: 0.004534626379609108
2023-01-21 10:50:14.843363: step: 1508/530, loss: 0.04933672025799751
2023-01-21 10:50:15.936801: step: 1512/530, loss: 0.01965947076678276
2023-01-21 10:50:17.056299: step: 1516/530, loss: 0.0012077331775799394
2023-01-21 10:50:18.175403: step: 1520/530, loss: 0.032839585095644
2023-01-21 10:50:19.287735: step: 1524/530, loss: 0.029497431591153145
2023-01-21 10:50:20.393927: step: 1528/530, loss: 0.005555152893066406
2023-01-21 10:50:21.513364: step: 1532/530, loss: 0.06750015914440155
2023-01-21 10:50:22.609103: step: 1536/530, loss: 0.005693912506103516
2023-01-21 10:50:23.703600: step: 1540/530, loss: 0.016314124688506126
2023-01-21 10:50:24.840956: step: 1544/530, loss: 0.07892932742834091
2023-01-21 10:50:25.974672: step: 1548/530, loss: 0.07702398300170898
2023-01-21 10:50:27.130753: step: 1552/530, loss: 0.09778318554162979
2023-01-21 10:50:28.244032: step: 1556/530, loss: 0.00705642718821764
2023-01-21 10:50:29.385217: step: 1560/530, loss: 0.09829993546009064
2023-01-21 10:50:30.499403: step: 1564/530, loss: 0.03918581083416939
2023-01-21 10:50:31.616637: step: 1568/530, loss: 0.02735462412238121
2023-01-21 10:50:32.701307: step: 1572/530, loss: 0.01922469213604927
2023-01-21 10:50:33.797172: step: 1576/530, loss: 0.03327655792236328
2023-01-21 10:50:34.963558: step: 1580/530, loss: 0.07415008544921875
2023-01-21 10:50:36.070324: step: 1584/530, loss: 0.10505485534667969
2023-01-21 10:50:37.149042: step: 1588/530, loss: 0.0026955604553222656
2023-01-21 10:50:38.266782: step: 1592/530, loss: 0.016434907913208008
2023-01-21 10:50:39.370255: step: 1596/530, loss: 0.027814485132694244
2023-01-21 10:50:40.490684: step: 1600/530, loss: 0.03342628479003906
2023-01-21 10:50:41.640944: step: 1604/530, loss: 0.03882265090942383
2023-01-21 10:50:42.767542: step: 1608/530, loss: 0.025252485647797585
2023-01-21 10:50:43.849466: step: 1612/530, loss: 0.014138794504106045
2023-01-21 10:50:44.968061: step: 1616/530, loss: 0.018446732312440872
2023-01-21 10:50:46.100828: step: 1620/530, loss: 0.3163818418979645
2023-01-21 10:50:47.214571: step: 1624/530, loss: 0.009291458874940872
2023-01-21 10:50:48.319856: step: 1628/530, loss: 0.11868336796760559
2023-01-21 10:50:49.482441: step: 1632/530, loss: 0.007417869754135609
2023-01-21 10:50:50.591096: step: 1636/530, loss: 0.025185395032167435
2023-01-21 10:50:51.683178: step: 1640/530, loss: 0.0011060715187340975
2023-01-21 10:50:52.812499: step: 1644/530, loss: 0.014728737063705921
2023-01-21 10:50:53.905483: step: 1648/530, loss: 0.0027950764633715153
2023-01-21 10:50:55.018049: step: 1652/530, loss: 0.04572421312332153
2023-01-21 10:50:56.132755: step: 1656/530, loss: 0.020482921972870827
2023-01-21 10:50:57.263945: step: 1660/530, loss: 0.02772236056625843
2023-01-21 10:50:58.354651: step: 1664/530, loss: 0.00012240410433150828
2023-01-21 10:50:59.469824: step: 1668/530, loss: 0.02552185207605362
2023-01-21 10:51:00.578616: step: 1672/530, loss: 0.05476951599121094
2023-01-21 10:51:01.687331: step: 1676/530, loss: 0.002781009767204523
2023-01-21 10:51:02.809726: step: 1680/530, loss: 0.004648399539291859
2023-01-21 10:51:03.925607: step: 1684/530, loss: 0.03226395696401596
2023-01-21 10:51:05.048450: step: 1688/530, loss: 0.04018755257129669
2023-01-21 10:51:06.181856: step: 1692/530, loss: 0.01406173687428236
2023-01-21 10:51:07.304320: step: 1696/530, loss: 0.18474669754505157
2023-01-21 10:51:08.430095: step: 1700/530, loss: 0.00690460205078125
2023-01-21 10:51:09.568455: step: 1704/530, loss: 0.023449230939149857
2023-01-21 10:51:10.667735: step: 1708/530, loss: 0.025321578606963158
2023-01-21 10:51:11.786849: step: 1712/530, loss: 0.013655662536621094
2023-01-21 10:51:12.923731: step: 1716/530, loss: 0.027897071093320847
2023-01-21 10:51:14.032226: step: 1720/530, loss: 0.0948280394077301
2023-01-21 10:51:15.128024: step: 1724/530, loss: 0.03072824515402317
2023-01-21 10:51:16.227541: step: 1728/530, loss: 0.033811189234256744
2023-01-21 10:51:17.346507: step: 1732/530, loss: 0.20510853826999664
2023-01-21 10:51:18.433966: step: 1736/530, loss: 0.05476036295294762
2023-01-21 10:51:19.563668: step: 1740/530, loss: 0.014009762555360794
2023-01-21 10:51:20.653221: step: 1744/530, loss: 0.07911892235279083
2023-01-21 10:51:21.768734: step: 1748/530, loss: 0.011137008666992188
2023-01-21 10:51:22.888910: step: 1752/530, loss: 0.011971366591751575
2023-01-21 10:51:24.007836: step: 1756/530, loss: 0.013309288769960403
2023-01-21 10:51:25.080060: step: 1760/530, loss: 0.002271938370540738
2023-01-21 10:51:26.167118: step: 1764/530, loss: 0.012990761548280716
2023-01-21 10:51:27.307176: step: 1768/530, loss: 0.04801464080810547
2023-01-21 10:51:28.417723: step: 1772/530, loss: 0.02437558025121689
2023-01-21 10:51:29.542329: step: 1776/530, loss: 0.022745704278349876
2023-01-21 10:51:30.646472: step: 1780/530, loss: 0.03569002449512482
2023-01-21 10:51:31.758669: step: 1784/530, loss: 0.014173602685332298
2023-01-21 10:51:32.867506: step: 1788/530, loss: 0.011558150872588158
2023-01-21 10:51:34.002697: step: 1792/530, loss: 0.00604171771556139
2023-01-21 10:51:35.095211: step: 1796/530, loss: 0.005278396420180798
2023-01-21 10:51:36.182851: step: 1800/530, loss: 0.016076279804110527
2023-01-21 10:51:37.305935: step: 1804/530, loss: 0.09397892653942108
2023-01-21 10:51:38.422524: step: 1808/530, loss: 0.009065408259630203
2023-01-21 10:51:39.537843: step: 1812/530, loss: 0.016848040744662285
2023-01-21 10:51:40.632075: step: 1816/530, loss: 0.033849477767944336
2023-01-21 10:51:41.745782: step: 1820/530, loss: 0.008006667718291283
2023-01-21 10:51:42.887564: step: 1824/530, loss: 0.035149671137332916
2023-01-21 10:51:44.008607: step: 1828/530, loss: 0.031958676874637604
2023-01-21 10:51:45.129609: step: 1832/530, loss: 0.016405105590820312
2023-01-21 10:51:46.226401: step: 1836/530, loss: 0.03271064907312393
2023-01-21 10:51:47.390223: step: 1840/530, loss: 0.04124289005994797
2023-01-21 10:51:48.488329: step: 1844/530, loss: 0.002760601229965687
2023-01-21 10:51:49.607184: step: 1848/530, loss: 0.06742048263549805
2023-01-21 10:51:50.704865: step: 1852/530, loss: 0.25570470094680786
2023-01-21 10:51:51.818726: step: 1856/530, loss: 0.023184681311249733
2023-01-21 10:51:52.934299: step: 1860/530, loss: 0.009247493930161
2023-01-21 10:51:54.018754: step: 1864/530, loss: 0.026656342670321465
2023-01-21 10:51:55.129388: step: 1868/530, loss: 0.04822807386517525
2023-01-21 10:51:56.247467: step: 1872/530, loss: 0.062307167798280716
2023-01-21 10:51:57.339885: step: 1876/530, loss: 0.019462300464510918
2023-01-21 10:51:58.449714: step: 1880/530, loss: 0.09912419319152832
2023-01-21 10:51:59.553720: step: 1884/530, loss: 0.05363216623663902
2023-01-21 10:52:00.670740: step: 1888/530, loss: 0.006085253320634365
2023-01-21 10:52:01.766194: step: 1892/530, loss: 0.004158305935561657
2023-01-21 10:52:02.871239: step: 1896/530, loss: 0.051998332142829895
2023-01-21 10:52:04.013360: step: 1900/530, loss: 0.03031158447265625
2023-01-21 10:52:05.135845: step: 1904/530, loss: 0.3368871212005615
2023-01-21 10:52:06.237332: step: 1908/530, loss: 0.2325790375471115
2023-01-21 10:52:07.321396: step: 1912/530, loss: 0.07373352348804474
2023-01-21 10:52:08.418339: step: 1916/530, loss: 0.00828332919627428
2023-01-21 10:52:09.539608: step: 1920/530, loss: 0.04751787334680557
2023-01-21 10:52:10.623492: step: 1924/530, loss: 0.02096271514892578
2023-01-21 10:52:11.718760: step: 1928/530, loss: 0.0014201164012774825
2023-01-21 10:52:12.851243: step: 1932/530, loss: 0.016643429175019264
2023-01-21 10:52:13.984447: step: 1936/530, loss: 0.023142432793974876
2023-01-21 10:52:15.105719: step: 1940/530, loss: 0.001769638154655695
2023-01-21 10:52:16.239284: step: 1944/530, loss: 0.020806312561035156
2023-01-21 10:52:17.356141: step: 1948/530, loss: 0.028652288019657135
2023-01-21 10:52:18.486969: step: 1952/530, loss: 0.032911013811826706
2023-01-21 10:52:19.618716: step: 1956/530, loss: 0.021462060511112213
2023-01-21 10:52:20.718482: step: 1960/530, loss: 0.03213653713464737
2023-01-21 10:52:21.872069: step: 1964/530, loss: 0.09073762595653534
2023-01-21 10:52:23.019706: step: 1968/530, loss: 0.029110753908753395
2023-01-21 10:52:24.125567: step: 1972/530, loss: 0.7114695310592651
2023-01-21 10:52:25.226417: step: 1976/530, loss: 0.029550934210419655
2023-01-21 10:52:26.344970: step: 1980/530, loss: 0.1934029459953308
2023-01-21 10:52:27.463767: step: 1984/530, loss: 0.04341850429773331
2023-01-21 10:52:28.560195: step: 1988/530, loss: 0.06282548606395721
2023-01-21 10:52:29.642632: step: 1992/530, loss: 0.048888206481933594
2023-01-21 10:52:30.730625: step: 1996/530, loss: 0.0530853271484375
2023-01-21 10:52:31.855335: step: 2000/530, loss: 0.015187466517090797
2023-01-21 10:52:32.994084: step: 2004/530, loss: 0.04696941375732422
2023-01-21 10:52:34.077722: step: 2008/530, loss: 0.43210849165916443
2023-01-21 10:52:35.206392: step: 2012/530, loss: 0.014079475775361061
2023-01-21 10:52:36.297311: step: 2016/530, loss: 0.023248672485351562
2023-01-21 10:52:37.416602: step: 2020/530, loss: 0.03494957089424133
2023-01-21 10:52:38.548360: step: 2024/530, loss: 0.19624005258083344
2023-01-21 10:52:39.681876: step: 2028/530, loss: 0.015550232492387295
2023-01-21 10:52:40.792140: step: 2032/530, loss: 0.02035827562212944
2023-01-21 10:52:41.932750: step: 2036/530, loss: 0.08617305755615234
2023-01-21 10:52:43.056477: step: 2040/530, loss: 0.028662491589784622
2023-01-21 10:52:44.162978: step: 2044/530, loss: 0.014487648382782936
2023-01-21 10:52:45.272652: step: 2048/530, loss: 0.8045014142990112
2023-01-21 10:52:46.391892: step: 2052/530, loss: 0.1203043982386589
2023-01-21 10:52:47.535957: step: 2056/530, loss: 0.1416303664445877
2023-01-21 10:52:48.646697: step: 2060/530, loss: 0.005613232031464577
2023-01-21 10:52:49.757103: step: 2064/530, loss: 0.023755835369229317
2023-01-21 10:52:50.888171: step: 2068/530, loss: 0.02379455603659153
2023-01-21 10:52:52.028351: step: 2072/530, loss: 0.02495441399514675
2023-01-21 10:52:53.132629: step: 2076/530, loss: 0.09492950886487961
2023-01-21 10:52:54.239303: step: 2080/530, loss: 0.001062583876773715
2023-01-21 10:52:55.342027: step: 2084/530, loss: 0.05751362070441246
2023-01-21 10:52:56.472900: step: 2088/530, loss: 0.05487098544836044
2023-01-21 10:52:57.572774: step: 2092/530, loss: 0.004440784454345703
2023-01-21 10:52:58.649592: step: 2096/530, loss: 0.0067605976946651936
2023-01-21 10:52:59.745056: step: 2100/530, loss: 0.03372316434979439
2023-01-21 10:53:00.881144: step: 2104/530, loss: 0.17055433988571167
2023-01-21 10:53:01.972227: step: 2108/530, loss: 0.04817914962768555
2023-01-21 10:53:03.093742: step: 2112/530, loss: 0.025104330852627754
2023-01-21 10:53:04.205137: step: 2116/530, loss: 0.14019203186035156
2023-01-21 10:53:05.351572: step: 2120/530, loss: 0.0209871307015419
==================================================
Loss: 0.067
--------------------
Dev: {'event': {'p': 0.5741293532338309, 'r': 0.7683089214380826, 'f1': 0.6571753986332575}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Test: {'event': {'p': 0.6260311640696609, 'r': 0.796037296037296, 'f1': 0.7008722421754746}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
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': 13}
Korean: {'event': {'p': 0.6415094339622641, 'r': 0.5396825396825397, 'f1': 0.5862068965517241}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Russian: {'event': {'p': 0.38636363636363635, 'r': 0.4722222222222222, 'f1': 0.425}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 10:53:45.675003: step: 4/530, loss: 0.04702253267168999
2023-01-21 10:53:46.781755: step: 8/530, loss: 0.053995512425899506
2023-01-21 10:53:47.897735: step: 12/530, loss: 0.06028447300195694
2023-01-21 10:53:49.014269: step: 16/530, loss: 0.061688877642154694
2023-01-21 10:53:50.113318: step: 20/530, loss: 0.019106674939393997
2023-01-21 10:53:51.252498: step: 24/530, loss: 0.05822276696562767
2023-01-21 10:53:52.359592: step: 28/530, loss: 0.010633086785674095
2023-01-21 10:53:53.453282: step: 32/530, loss: 0.0030896186362951994
2023-01-21 10:53:54.564262: step: 36/530, loss: 0.010391426272690296
2023-01-21 10:53:55.654734: step: 40/530, loss: 0.05177793651819229
2023-01-21 10:53:56.783417: step: 44/530, loss: 0.006768893916159868
2023-01-21 10:53:57.896951: step: 48/530, loss: 0.0005341529613360763
2023-01-21 10:53:59.010328: step: 52/530, loss: 0.034753940999507904
2023-01-21 10:54:00.110488: step: 56/530, loss: 0.005556297022849321
2023-01-21 10:54:01.200323: step: 60/530, loss: 0.0033323289826512337
2023-01-21 10:54:02.318744: step: 64/530, loss: 0.018329525366425514
2023-01-21 10:54:03.444948: step: 68/530, loss: 0.022192668169736862
2023-01-21 10:54:04.534901: step: 72/530, loss: 0.011812853626906872
2023-01-21 10:54:05.617578: step: 76/530, loss: 0.00901184044778347
2023-01-21 10:54:06.720672: step: 80/530, loss: 0.011128759942948818
2023-01-21 10:54:07.816887: step: 84/530, loss: 0.014445876702666283
2023-01-21 10:54:08.958852: step: 88/530, loss: 0.0047130584716796875
2023-01-21 10:54:10.093117: step: 92/530, loss: 0.028824998065829277
2023-01-21 10:54:11.196359: step: 96/530, loss: 0.04604749381542206
2023-01-21 10:54:12.329609: step: 100/530, loss: 0.04545726999640465
2023-01-21 10:54:13.432464: step: 104/530, loss: 0.18642081320285797
2023-01-21 10:54:14.527143: step: 108/530, loss: 0.03371763229370117
2023-01-21 10:54:15.665466: step: 112/530, loss: 0.06488686054944992
2023-01-21 10:54:16.794999: step: 116/530, loss: 0.011842155829071999
2023-01-21 10:54:17.898314: step: 120/530, loss: 0.035103797912597656
2023-01-21 10:54:19.031839: step: 124/530, loss: 0.012880897149443626
2023-01-21 10:54:20.147265: step: 128/530, loss: 0.018087053671479225
2023-01-21 10:54:21.222259: step: 132/530, loss: 0.006425953004509211
2023-01-21 10:54:22.424075: step: 136/530, loss: 0.01656184159219265
2023-01-21 10:54:23.536330: step: 140/530, loss: 0.09010204672813416
2023-01-21 10:54:24.663097: step: 144/530, loss: 0.0386720672249794
2023-01-21 10:54:25.796174: step: 148/530, loss: 0.013581561855971813
2023-01-21 10:54:26.880168: step: 152/530, loss: 0.0008546829340048134
2023-01-21 10:54:27.978186: step: 156/530, loss: 0.009652567096054554
2023-01-21 10:54:29.096922: step: 160/530, loss: 0.07323838025331497
2023-01-21 10:54:30.203079: step: 164/530, loss: 0.022803688421845436
2023-01-21 10:54:31.334808: step: 168/530, loss: 0.03015890344977379
2023-01-21 10:54:32.449239: step: 172/530, loss: 0.0009258746867999434
2023-01-21 10:54:33.556971: step: 176/530, loss: 0.023730754852294922
2023-01-21 10:54:34.696003: step: 180/530, loss: 0.0020950317848473787
2023-01-21 10:54:35.780397: step: 184/530, loss: 0.4135301411151886
2023-01-21 10:54:36.900189: step: 188/530, loss: 0.02744932286441326
2023-01-21 10:54:38.020230: step: 192/530, loss: 0.00901031494140625
2023-01-21 10:54:39.147120: step: 196/530, loss: 0.2015785276889801
2023-01-21 10:54:40.257613: step: 200/530, loss: 0.026627065613865852
2023-01-21 10:54:41.373252: step: 204/530, loss: 0.0015189171535894275
2023-01-21 10:54:42.473263: step: 208/530, loss: 0.056769564747810364
2023-01-21 10:54:43.577031: step: 212/530, loss: 0.0029735565185546875
2023-01-21 10:54:44.728052: step: 216/530, loss: 0.027938079088926315
2023-01-21 10:54:45.853249: step: 220/530, loss: 0.14071951806545258
2023-01-21 10:54:46.942376: step: 224/530, loss: 0.03213090822100639
2023-01-21 10:54:48.096391: step: 228/530, loss: 0.1904449462890625
2023-01-21 10:54:49.196402: step: 232/530, loss: 0.0886446014046669
2023-01-21 10:54:50.326995: step: 236/530, loss: 0.02261791191995144
2023-01-21 10:54:51.427361: step: 240/530, loss: 0.04552135244011879
2023-01-21 10:54:52.547403: step: 244/530, loss: 0.0033027648460119963
2023-01-21 10:54:53.640515: step: 248/530, loss: 0.05379519611597061
2023-01-21 10:54:54.732738: step: 252/530, loss: 0.04106717184185982
2023-01-21 10:54:55.863091: step: 256/530, loss: 0.07275620102882385
2023-01-21 10:54:56.981930: step: 260/530, loss: 0.0029544830322265625
2023-01-21 10:54:58.086787: step: 264/530, loss: 0.03281726688146591
2023-01-21 10:54:59.180806: step: 268/530, loss: 0.055399514734745026
2023-01-21 10:55:00.271879: step: 272/530, loss: 0.0007381439208984375
2023-01-21 10:55:01.383852: step: 276/530, loss: 0.03278714418411255
2023-01-21 10:55:02.484622: step: 280/530, loss: 0.0396793857216835
2023-01-21 10:55:03.630087: step: 284/530, loss: 0.026972388848662376
2023-01-21 10:55:04.738063: step: 288/530, loss: 0.14087219536304474
2023-01-21 10:55:05.855533: step: 292/530, loss: 0.06204567104578018
2023-01-21 10:55:06.953386: step: 296/530, loss: 0.023462487384676933
2023-01-21 10:55:08.057991: step: 300/530, loss: 0.020273970440030098
2023-01-21 10:55:09.163019: step: 304/530, loss: 0.35043519735336304
2023-01-21 10:55:10.293368: step: 308/530, loss: 0.09835606068372726
2023-01-21 10:55:11.382982: step: 312/530, loss: 0.03778839111328125
2023-01-21 10:55:12.489064: step: 316/530, loss: 0.011099433526396751
2023-01-21 10:55:13.594086: step: 320/530, loss: 0.024808691814541817
2023-01-21 10:55:14.691780: step: 324/530, loss: 0.0012960435124114156
2023-01-21 10:55:15.787909: step: 328/530, loss: 0.21228285133838654
2023-01-21 10:55:16.881782: step: 332/530, loss: 0.01964855194091797
2023-01-21 10:55:17.983238: step: 336/530, loss: 0.014302825555205345
2023-01-21 10:55:19.099456: step: 340/530, loss: 0.0023017884232103825
2023-01-21 10:55:20.239000: step: 344/530, loss: 0.0010913849109783769
2023-01-21 10:55:21.360411: step: 348/530, loss: 0.007652043830603361
2023-01-21 10:55:22.456001: step: 352/530, loss: 0.009154558181762695
2023-01-21 10:55:23.554520: step: 356/530, loss: 0.03599219396710396
2023-01-21 10:55:24.656145: step: 360/530, loss: 0.011194229125976562
2023-01-21 10:55:25.773863: step: 364/530, loss: 0.005347633734345436
2023-01-21 10:55:26.876828: step: 368/530, loss: 0.0017028808360919356
2023-01-21 10:55:27.967436: step: 372/530, loss: 0.026422597467899323
2023-01-21 10:55:29.049852: step: 376/530, loss: 0.04452910274267197
2023-01-21 10:55:30.141759: step: 380/530, loss: 0.0005995750543661416
2023-01-21 10:55:31.231605: step: 384/530, loss: 0.01575031317770481
2023-01-21 10:55:32.321359: step: 388/530, loss: 0.0006193161243572831
2023-01-21 10:55:33.431573: step: 392/530, loss: 0.0525602325797081
2023-01-21 10:55:34.585780: step: 396/530, loss: 0.03415260463953018
2023-01-21 10:55:35.692803: step: 400/530, loss: 0.026873396709561348
2023-01-21 10:55:36.813511: step: 404/530, loss: 0.0029591561760753393
2023-01-21 10:55:37.906695: step: 408/530, loss: 0.03813915327191353
2023-01-21 10:55:38.992646: step: 412/530, loss: 0.03328828886151314
2023-01-21 10:55:40.087514: step: 416/530, loss: 0.03896684572100639
2023-01-21 10:55:41.198546: step: 420/530, loss: 0.0037037848960608244
2023-01-21 10:55:42.322218: step: 424/530, loss: 0.01860809326171875
2023-01-21 10:55:43.398122: step: 428/530, loss: 0.0035160065162926912
2023-01-21 10:55:44.528047: step: 432/530, loss: 0.01439514197409153
2023-01-21 10:55:45.629599: step: 436/530, loss: 0.0042327879928052425
2023-01-21 10:55:46.745356: step: 440/530, loss: 0.017043257132172585
2023-01-21 10:55:47.843926: step: 444/530, loss: 0.006049538031220436
2023-01-21 10:55:48.941873: step: 448/530, loss: 0.06287059932947159
2023-01-21 10:55:50.065015: step: 452/530, loss: 0.010165786370635033
2023-01-21 10:55:51.162903: step: 456/530, loss: 0.0024124146439135075
2023-01-21 10:55:52.261760: step: 460/530, loss: 0.005789518356323242
2023-01-21 10:55:53.389286: step: 464/530, loss: 0.056801509112119675
2023-01-21 10:55:54.507201: step: 468/530, loss: 0.023688506335020065
2023-01-21 10:55:55.614744: step: 472/530, loss: 0.08715686947107315
2023-01-21 10:55:56.681881: step: 476/530, loss: 0.017769623547792435
2023-01-21 10:55:57.800927: step: 480/530, loss: 0.13071098923683167
2023-01-21 10:55:58.903417: step: 484/530, loss: 0.010578442364931107
2023-01-21 10:56:00.008671: step: 488/530, loss: 0.013220597058534622
2023-01-21 10:56:01.141175: step: 492/530, loss: 0.0063967229798436165
2023-01-21 10:56:02.247243: step: 496/530, loss: 0.03955917805433273
2023-01-21 10:56:03.365803: step: 500/530, loss: 0.013597965240478516
2023-01-21 10:56:04.464087: step: 504/530, loss: 0.04321122169494629
2023-01-21 10:56:05.604805: step: 508/530, loss: 0.005224895663559437
2023-01-21 10:56:06.724252: step: 512/530, loss: 0.026416493579745293
2023-01-21 10:56:07.814700: step: 516/530, loss: 0.0160430446267128
2023-01-21 10:56:08.885774: step: 520/530, loss: 0.033298298716545105
2023-01-21 10:56:10.019416: step: 524/530, loss: 0.033376120030879974
2023-01-21 10:56:11.117308: step: 528/530, loss: 0.00105199811514467
2023-01-21 10:56:12.218459: step: 532/530, loss: 0.06494121253490448
2023-01-21 10:56:13.311770: step: 536/530, loss: 0.06349873542785645
2023-01-21 10:56:14.414517: step: 540/530, loss: 0.03936271741986275
2023-01-21 10:56:15.567155: step: 544/530, loss: 0.0035247982013970613
2023-01-21 10:56:16.679875: step: 548/530, loss: 0.009364891797304153
2023-01-21 10:56:17.807186: step: 552/530, loss: 0.05418434366583824
2023-01-21 10:56:18.959613: step: 556/530, loss: 0.03356046602129936
2023-01-21 10:56:20.073011: step: 560/530, loss: 0.006576729007065296
2023-01-21 10:56:21.202976: step: 564/530, loss: 0.08402281254529953
2023-01-21 10:56:22.316862: step: 568/530, loss: 0.022785712033510208
2023-01-21 10:56:23.419587: step: 572/530, loss: 0.0566926971077919
2023-01-21 10:56:24.538640: step: 576/530, loss: 0.0031988145783543587
2023-01-21 10:56:25.687843: step: 580/530, loss: 0.058861732482910156
2023-01-21 10:56:26.809450: step: 584/530, loss: 0.004862308502197266
2023-01-21 10:56:27.921084: step: 588/530, loss: 0.04411335289478302
2023-01-21 10:56:29.014313: step: 592/530, loss: 0.032705213874578476
2023-01-21 10:56:30.134965: step: 596/530, loss: 0.035577964037656784
2023-01-21 10:56:31.283392: step: 600/530, loss: 0.11690273135900497
2023-01-21 10:56:32.411667: step: 604/530, loss: 0.035485364496707916
2023-01-21 10:56:33.497414: step: 608/530, loss: 0.04994511604309082
2023-01-21 10:56:34.597630: step: 612/530, loss: 0.00014781951904296875
2023-01-21 10:56:35.721348: step: 616/530, loss: 0.02391967922449112
2023-01-21 10:56:36.873319: step: 620/530, loss: 0.03444986045360565
2023-01-21 10:56:38.006266: step: 624/530, loss: 0.024228285998106003
2023-01-21 10:56:39.146516: step: 628/530, loss: 0.02290506474673748
2023-01-21 10:56:40.281776: step: 632/530, loss: 0.06472358852624893
2023-01-21 10:56:41.377345: step: 636/530, loss: 0.00258216867223382
2023-01-21 10:56:42.498635: step: 640/530, loss: 0.07961063832044601
2023-01-21 10:56:43.601192: step: 644/530, loss: 0.013646173290908337
2023-01-21 10:56:44.688619: step: 648/530, loss: 0.01931281015276909
2023-01-21 10:56:45.791514: step: 652/530, loss: 0.04296741262078285
2023-01-21 10:56:46.924560: step: 656/530, loss: 0.02165203168988228
2023-01-21 10:56:48.056698: step: 660/530, loss: 0.012423706240952015
2023-01-21 10:56:49.158628: step: 664/530, loss: 0.0005661010509356856
2023-01-21 10:56:50.253478: step: 668/530, loss: 0.06245794519782066
2023-01-21 10:56:51.344119: step: 672/530, loss: 0.038239289075136185
2023-01-21 10:56:52.456643: step: 676/530, loss: 0.03986511379480362
2023-01-21 10:56:53.566526: step: 680/530, loss: 0.05547704920172691
2023-01-21 10:56:54.669912: step: 684/530, loss: 0.0011751174461096525
2023-01-21 10:56:55.779294: step: 688/530, loss: 0.01283874548971653
2023-01-21 10:56:56.913202: step: 692/530, loss: 0.012485838495194912
2023-01-21 10:56:58.006652: step: 696/530, loss: 0.03501176834106445
2023-01-21 10:56:59.120835: step: 700/530, loss: 0.011805725283920765
2023-01-21 10:57:00.245371: step: 704/530, loss: 0.03932938724756241
2023-01-21 10:57:01.398225: step: 708/530, loss: 0.004594612400978804
2023-01-21 10:57:02.519035: step: 712/530, loss: 0.01157989539206028
2023-01-21 10:57:03.619430: step: 716/530, loss: 0.001975917723029852
2023-01-21 10:57:04.734288: step: 720/530, loss: 0.013444637879729271
2023-01-21 10:57:05.832631: step: 724/530, loss: 0.0134156234562397
2023-01-21 10:57:06.956101: step: 728/530, loss: 0.01780243031680584
2023-01-21 10:57:08.077533: step: 732/530, loss: 0.004899597726762295
2023-01-21 10:57:09.188839: step: 736/530, loss: 0.03235134482383728
2023-01-21 10:57:10.303901: step: 740/530, loss: 0.015716170892119408
2023-01-21 10:57:11.396121: step: 744/530, loss: 0.015531444922089577
2023-01-21 10:57:12.489466: step: 748/530, loss: 0.024732496589422226
2023-01-21 10:57:13.617188: step: 752/530, loss: 0.08232907950878143
2023-01-21 10:57:14.721802: step: 756/530, loss: 0.028269385918974876
2023-01-21 10:57:15.828853: step: 760/530, loss: 0.0457274429500103
2023-01-21 10:57:16.971715: step: 764/530, loss: 0.028673935681581497
2023-01-21 10:57:18.090899: step: 768/530, loss: 0.12333240360021591
2023-01-21 10:57:19.169917: step: 772/530, loss: 0.011832332238554955
2023-01-21 10:57:20.307181: step: 776/530, loss: 0.0030558586586266756
2023-01-21 10:57:21.445303: step: 780/530, loss: 0.12677001953125
2023-01-21 10:57:22.557013: step: 784/530, loss: 0.08717412501573563
2023-01-21 10:57:23.665807: step: 788/530, loss: 0.03781528398394585
2023-01-21 10:57:24.778232: step: 792/530, loss: 0.009796691127121449
2023-01-21 10:57:25.855461: step: 796/530, loss: 0.03370647504925728
2023-01-21 10:57:26.985487: step: 800/530, loss: 0.03340645134449005
2023-01-21 10:57:28.093674: step: 804/530, loss: 0.019536305218935013
2023-01-21 10:57:29.223981: step: 808/530, loss: 0.006667518988251686
2023-01-21 10:57:30.302049: step: 812/530, loss: 0.005557251162827015
2023-01-21 10:57:31.450329: step: 816/530, loss: 0.22441402077674866
2023-01-21 10:57:32.543380: step: 820/530, loss: 0.038706209510564804
2023-01-21 10:57:33.704358: step: 824/530, loss: 0.0004555225314106792
2023-01-21 10:57:34.852811: step: 828/530, loss: 0.05806303024291992
2023-01-21 10:57:35.957294: step: 832/530, loss: 0.00952692050486803
2023-01-21 10:57:37.053634: step: 836/530, loss: 0.06042361259460449
2023-01-21 10:57:38.178676: step: 840/530, loss: 0.11796483397483826
2023-01-21 10:57:39.276768: step: 844/530, loss: 0.005104636773467064
2023-01-21 10:57:40.373207: step: 848/530, loss: 0.009807109832763672
2023-01-21 10:57:41.499943: step: 852/530, loss: 0.019356727600097656
2023-01-21 10:57:42.620149: step: 856/530, loss: 0.049624063074588776
2023-01-21 10:57:43.747857: step: 860/530, loss: 0.04485110938549042
2023-01-21 10:57:44.829273: step: 864/530, loss: 0.000164031982421875
2023-01-21 10:57:45.972177: step: 868/530, loss: 0.0826214849948883
2023-01-21 10:57:47.109713: step: 872/530, loss: 0.06108064949512482
2023-01-21 10:57:48.250745: step: 876/530, loss: 0.03638935089111328
2023-01-21 10:57:49.357691: step: 880/530, loss: 0.02673196792602539
2023-01-21 10:57:50.526696: step: 884/530, loss: 0.032164763659238815
2023-01-21 10:57:51.651951: step: 888/530, loss: 0.0740235298871994
2023-01-21 10:57:52.734566: step: 892/530, loss: 0.01280899066478014
2023-01-21 10:57:53.848392: step: 896/530, loss: 0.12015514075756073
2023-01-21 10:57:54.970453: step: 900/530, loss: 0.013498758897185326
2023-01-21 10:57:56.085195: step: 904/530, loss: 0.05314045026898384
2023-01-21 10:57:57.210975: step: 908/530, loss: 0.031987667083740234
2023-01-21 10:57:58.314964: step: 912/530, loss: 0.00016460419283248484
2023-01-21 10:57:59.431289: step: 916/530, loss: 0.04135780781507492
2023-01-21 10:58:00.523172: step: 920/530, loss: 0.03375639393925667
2023-01-21 10:58:01.634046: step: 924/530, loss: 0.0018406867748126388
2023-01-21 10:58:02.737250: step: 928/530, loss: 0.05179310217499733
2023-01-21 10:58:03.860811: step: 932/530, loss: 0.04589195176959038
2023-01-21 10:58:04.969130: step: 936/530, loss: 0.008453321643173695
2023-01-21 10:58:06.047008: step: 940/530, loss: 0.030608177185058594
2023-01-21 10:58:07.152378: step: 944/530, loss: 0.0008788108825683594
2023-01-21 10:58:08.270465: step: 948/530, loss: 0.012353443540632725
2023-01-21 10:58:09.394208: step: 952/530, loss: 0.03370209038257599
2023-01-21 10:58:10.497936: step: 956/530, loss: 0.026050997897982597
2023-01-21 10:58:11.614367: step: 960/530, loss: 0.01186981238424778
2023-01-21 10:58:12.723834: step: 964/530, loss: 0.03475773334503174
2023-01-21 10:58:13.813866: step: 968/530, loss: 0.049370668828487396
2023-01-21 10:58:14.901777: step: 972/530, loss: 0.04371605068445206
2023-01-21 10:58:16.037296: step: 976/530, loss: 0.0364263541996479
2023-01-21 10:58:17.161763: step: 980/530, loss: 0.06429455429315567
2023-01-21 10:58:18.251748: step: 984/530, loss: 0.010004807263612747
2023-01-21 10:58:19.332665: step: 988/530, loss: 0.043923333287239075
2023-01-21 10:58:20.428480: step: 992/530, loss: 0.0003027915954589844
2023-01-21 10:58:21.552910: step: 996/530, loss: 0.01919269748032093
2023-01-21 10:58:22.622981: step: 1000/530, loss: 0.004035663791000843
2023-01-21 10:58:23.713773: step: 1004/530, loss: 0.014319324865937233
2023-01-21 10:58:24.824774: step: 1008/530, loss: 0.07364041358232498
2023-01-21 10:58:25.950839: step: 1012/530, loss: 0.0019920349586755037
2023-01-21 10:58:27.095113: step: 1016/530, loss: 0.020370198413729668
2023-01-21 10:58:28.206116: step: 1020/530, loss: 0.0007961273076944053
2023-01-21 10:58:29.301716: step: 1024/530, loss: 0.025880910456180573
2023-01-21 10:58:30.426754: step: 1028/530, loss: 0.014011383056640625
2023-01-21 10:58:31.539385: step: 1032/530, loss: 0.004825020208954811
2023-01-21 10:58:32.675702: step: 1036/530, loss: 0.01976175233721733
2023-01-21 10:58:33.800213: step: 1040/530, loss: 0.04754295572638512
2023-01-21 10:58:34.892669: step: 1044/530, loss: 0.018389130011200905
2023-01-21 10:58:36.000304: step: 1048/530, loss: 0.005770969204604626
2023-01-21 10:58:37.147238: step: 1052/530, loss: 0.019846726208925247
2023-01-21 10:58:38.247805: step: 1056/530, loss: 0.0004981040838174522
2023-01-21 10:58:39.357072: step: 1060/530, loss: 0.0172592643648386
2023-01-21 10:58:40.477101: step: 1064/530, loss: 0.08783312141895294
2023-01-21 10:58:41.584759: step: 1068/530, loss: 0.07395347952842712
2023-01-21 10:58:42.682256: step: 1072/530, loss: 0.011962438002228737
2023-01-21 10:58:43.777416: step: 1076/530, loss: 0.05137849226593971
2023-01-21 10:58:44.914790: step: 1080/530, loss: 0.1057291030883789
2023-01-21 10:58:46.016959: step: 1084/530, loss: 0.026575280353426933
2023-01-21 10:58:47.101400: step: 1088/530, loss: 0.11547289043664932
2023-01-21 10:58:48.219805: step: 1092/530, loss: 0.07589836418628693
2023-01-21 10:58:49.331737: step: 1096/530, loss: 0.0512331984937191
2023-01-21 10:58:50.419467: step: 1100/530, loss: 0.0018918991554528475
2023-01-21 10:58:51.523748: step: 1104/530, loss: 0.00016336441331077367
2023-01-21 10:58:52.642226: step: 1108/530, loss: 0.04985189810395241
2023-01-21 10:58:53.738846: step: 1112/530, loss: 0.001569557236507535
2023-01-21 10:58:54.855904: step: 1116/530, loss: 0.07535958290100098
2023-01-21 10:58:55.980716: step: 1120/530, loss: 0.08077564090490341
2023-01-21 10:58:57.105160: step: 1124/530, loss: 0.04405088350176811
2023-01-21 10:58:58.231006: step: 1128/530, loss: 0.026410294696688652
2023-01-21 10:58:59.358098: step: 1132/530, loss: 0.02624998241662979
2023-01-21 10:59:00.474267: step: 1136/530, loss: 0.022647762671113014
2023-01-21 10:59:01.581873: step: 1140/530, loss: 0.07612466812133789
2023-01-21 10:59:02.707505: step: 1144/530, loss: 0.05960845947265625
2023-01-21 10:59:03.805766: step: 1148/530, loss: 0.0007684707525186241
2023-01-21 10:59:04.930615: step: 1152/530, loss: 0.0053043365478515625
2023-01-21 10:59:06.037627: step: 1156/530, loss: 0.005918025970458984
2023-01-21 10:59:07.132628: step: 1160/530, loss: 0.0027459862176328897
2023-01-21 10:59:08.281029: step: 1164/530, loss: 0.021146010607481003
2023-01-21 10:59:09.384836: step: 1168/530, loss: 0.06417503207921982
2023-01-21 10:59:10.484172: step: 1172/530, loss: 0.03320322185754776
2023-01-21 10:59:11.604239: step: 1176/530, loss: 0.028713228181004524
2023-01-21 10:59:12.729747: step: 1180/530, loss: 0.011194038204848766
2023-01-21 10:59:13.849489: step: 1184/530, loss: 0.01003799494355917
2023-01-21 10:59:14.968313: step: 1188/530, loss: 0.11275014281272888
2023-01-21 10:59:16.076247: step: 1192/530, loss: 0.005667686462402344
2023-01-21 10:59:17.181376: step: 1196/530, loss: 0.026314545422792435
2023-01-21 10:59:18.290988: step: 1200/530, loss: 0.037932634353637695
2023-01-21 10:59:19.435336: step: 1204/530, loss: 0.006468009669333696
2023-01-21 10:59:20.536578: step: 1208/530, loss: 0.012236976996064186
2023-01-21 10:59:21.673364: step: 1212/530, loss: 0.043326761573553085
2023-01-21 10:59:22.784476: step: 1216/530, loss: 0.2075360119342804
2023-01-21 10:59:23.883567: step: 1220/530, loss: 0.8059371709823608
2023-01-21 10:59:25.038050: step: 1224/530, loss: 0.01635437086224556
2023-01-21 10:59:26.139651: step: 1228/530, loss: 0.0451078899204731
2023-01-21 10:59:27.257838: step: 1232/530, loss: 0.10109567642211914
2023-01-21 10:59:28.370796: step: 1236/530, loss: 0.004776477813720703
2023-01-21 10:59:29.488494: step: 1240/530, loss: 0.031247520819306374
2023-01-21 10:59:30.598802: step: 1244/530, loss: 0.019735049456357956
2023-01-21 10:59:31.739003: step: 1248/530, loss: 0.0036596297286450863
2023-01-21 10:59:32.870525: step: 1252/530, loss: 0.039902493357658386
2023-01-21 10:59:33.982273: step: 1256/530, loss: 0.007407188415527344
2023-01-21 10:59:35.115293: step: 1260/530, loss: 0.10271687805652618
2023-01-21 10:59:36.268273: step: 1264/530, loss: 0.006028842646628618
2023-01-21 10:59:37.361810: step: 1268/530, loss: 0.0051541803404688835
2023-01-21 10:59:38.440947: step: 1272/530, loss: 0.031397055834531784
2023-01-21 10:59:39.561114: step: 1276/530, loss: 0.020188044756650925
2023-01-21 10:59:40.682488: step: 1280/530, loss: 0.001955747604370117
2023-01-21 10:59:41.801780: step: 1284/530, loss: 0.03940620273351669
2023-01-21 10:59:42.891793: step: 1288/530, loss: 0.02541809156537056
2023-01-21 10:59:43.994478: step: 1292/530, loss: 0.18013162910938263
2023-01-21 10:59:45.117122: step: 1296/530, loss: 0.04410620033740997
2023-01-21 10:59:46.213746: step: 1300/530, loss: 0.026226330548524857
2023-01-21 10:59:47.321351: step: 1304/530, loss: 0.0007550239679403603
2023-01-21 10:59:48.424348: step: 1308/530, loss: 0.033626750111579895
2023-01-21 10:59:49.520188: step: 1312/530, loss: 0.023047257214784622
2023-01-21 10:59:50.613907: step: 1316/530, loss: 0.05268258973956108
2023-01-21 10:59:51.740321: step: 1320/530, loss: 0.01068801898509264
2023-01-21 10:59:52.833941: step: 1324/530, loss: 0.011422348208725452
2023-01-21 10:59:53.969674: step: 1328/530, loss: 0.05138666555285454
2023-01-21 10:59:55.060583: step: 1332/530, loss: 0.3285846710205078
2023-01-21 10:59:56.160846: step: 1336/530, loss: 0.00407142611220479
2023-01-21 10:59:57.263042: step: 1340/530, loss: 0.0057833194732666016
2023-01-21 10:59:58.371909: step: 1344/530, loss: 0.0175718292593956
2023-01-21 10:59:59.516967: step: 1348/530, loss: 0.06573142856359482
2023-01-21 11:00:00.623780: step: 1352/530, loss: 0.04876232147216797
2023-01-21 11:00:01.686193: step: 1356/530, loss: 0.01550216693431139
2023-01-21 11:00:02.767396: step: 1360/530, loss: 0.06156163290143013
2023-01-21 11:00:03.874442: step: 1364/530, loss: 0.0991780236363411
2023-01-21 11:00:04.958077: step: 1368/530, loss: 0.1291217803955078
2023-01-21 11:00:06.060272: step: 1372/530, loss: 0.03913154825568199
2023-01-21 11:00:07.184067: step: 1376/530, loss: 0.018185734748840332
2023-01-21 11:00:08.327291: step: 1380/530, loss: 0.005368709564208984
2023-01-21 11:00:09.478945: step: 1384/530, loss: 0.01321945246309042
2023-01-21 11:00:10.581887: step: 1388/530, loss: 0.012521934695541859
2023-01-21 11:00:11.755103: step: 1392/530, loss: 0.16168007254600525
2023-01-21 11:00:12.870187: step: 1396/530, loss: 0.004801750183105469
2023-01-21 11:00:13.961670: step: 1400/530, loss: 0.044954873621463776
2023-01-21 11:00:15.082858: step: 1404/530, loss: 0.08139253407716751
2023-01-21 11:00:16.216984: step: 1408/530, loss: 0.034287452697753906
2023-01-21 11:00:17.355299: step: 1412/530, loss: 0.023468876257538795
2023-01-21 11:00:18.476536: step: 1416/530, loss: 0.04912176355719566
2023-01-21 11:00:19.550242: step: 1420/530, loss: 0.00845184363424778
2023-01-21 11:00:20.696487: step: 1424/530, loss: 0.04271573945879936
2023-01-21 11:00:21.815209: step: 1428/530, loss: 0.06381885707378387
2023-01-21 11:00:22.920755: step: 1432/530, loss: 0.019021034240722656
2023-01-21 11:00:24.040421: step: 1436/530, loss: 0.07922086864709854
2023-01-21 11:00:25.142843: step: 1440/530, loss: 0.00045027732267044485
2023-01-21 11:00:26.264726: step: 1444/530, loss: 0.015250968746840954
2023-01-21 11:00:27.373604: step: 1448/530, loss: 0.0007928848499432206
2023-01-21 11:00:28.491988: step: 1452/530, loss: 0.08685141056776047
2023-01-21 11:00:29.572333: step: 1456/530, loss: 0.014615059830248356
2023-01-21 11:00:30.671969: step: 1460/530, loss: 0.0018489836947992444
2023-01-21 11:00:31.767547: step: 1464/530, loss: 0.009445381350815296
2023-01-21 11:00:32.919088: step: 1468/530, loss: 0.011879540048539639
2023-01-21 11:00:34.038656: step: 1472/530, loss: 0.1129993349313736
2023-01-21 11:00:35.130647: step: 1476/530, loss: 0.014867305755615234
2023-01-21 11:00:36.252267: step: 1480/530, loss: 0.0007789612282067537
2023-01-21 11:00:37.374332: step: 1484/530, loss: 0.0024732588790357113
2023-01-21 11:00:38.500577: step: 1488/530, loss: 0.06359024345874786
2023-01-21 11:00:39.657235: step: 1492/530, loss: 0.014087867923080921
2023-01-21 11:00:40.772891: step: 1496/530, loss: 0.4675951898097992
2023-01-21 11:00:41.873691: step: 1500/530, loss: 0.15122851729393005
2023-01-21 11:00:42.981106: step: 1504/530, loss: 0.0023272514808923006
2023-01-21 11:00:44.091709: step: 1508/530, loss: 0.0027468204498291016
2023-01-21 11:00:45.209917: step: 1512/530, loss: 0.022343730553984642
2023-01-21 11:00:46.317375: step: 1516/530, loss: 0.0004454970476217568
2023-01-21 11:00:47.402112: step: 1520/530, loss: 0.006854343228042126
2023-01-21 11:00:48.538505: step: 1524/530, loss: 0.014994526281952858
2023-01-21 11:00:49.632842: step: 1528/530, loss: 0.007521724794059992
2023-01-21 11:00:50.725160: step: 1532/530, loss: 0.003412151476368308
2023-01-21 11:00:51.829506: step: 1536/530, loss: 0.02092576026916504
2023-01-21 11:00:52.959048: step: 1540/530, loss: 0.005639362148940563
2023-01-21 11:00:54.087454: step: 1544/530, loss: 0.04359016567468643
2023-01-21 11:00:55.184474: step: 1548/530, loss: 0.08413977921009064
2023-01-21 11:00:56.275004: step: 1552/530, loss: 0.027789782732725143
2023-01-21 11:00:57.406845: step: 1556/530, loss: 0.004153442569077015
2023-01-21 11:00:58.504204: step: 1560/530, loss: 0.03072538413107395
2023-01-21 11:00:59.638533: step: 1564/530, loss: 0.02431678958237171
2023-01-21 11:01:00.777524: step: 1568/530, loss: 0.07511663436889648
2023-01-21 11:01:01.924092: step: 1572/530, loss: 0.042697906494140625
2023-01-21 11:01:03.034814: step: 1576/530, loss: 0.06186962127685547
2023-01-21 11:01:04.152070: step: 1580/530, loss: 0.00678176898509264
2023-01-21 11:01:05.244456: step: 1584/530, loss: 0.03982076793909073
2023-01-21 11:01:06.344172: step: 1588/530, loss: 0.11752519756555557
2023-01-21 11:01:07.497514: step: 1592/530, loss: 0.04287855699658394
2023-01-21 11:01:08.596690: step: 1596/530, loss: 0.004877281375229359
2023-01-21 11:01:09.706277: step: 1600/530, loss: 0.0007444381481036544
2023-01-21 11:01:10.818333: step: 1604/530, loss: 0.02773820050060749
2023-01-21 11:01:11.898855: step: 1608/530, loss: 0.33338847756385803
2023-01-21 11:01:13.007437: step: 1612/530, loss: 0.04131712764501572
2023-01-21 11:01:14.142216: step: 1616/530, loss: 0.11539671570062637
2023-01-21 11:01:15.276930: step: 1620/530, loss: 0.0984533280134201
2023-01-21 11:01:16.410684: step: 1624/530, loss: 0.09835352748632431
2023-01-21 11:01:17.540181: step: 1628/530, loss: 0.0024851798079907894
2023-01-21 11:01:18.693672: step: 1632/530, loss: 0.013050270266830921
2023-01-21 11:01:19.787765: step: 1636/530, loss: 0.14514796435832977
2023-01-21 11:01:20.899201: step: 1640/530, loss: 0.006684637162834406
2023-01-21 11:01:22.038129: step: 1644/530, loss: 0.021122360602021217
2023-01-21 11:01:23.143493: step: 1648/530, loss: 0.08370376378297806
2023-01-21 11:01:24.228562: step: 1652/530, loss: 0.038909342139959335
2023-01-21 11:01:25.342941: step: 1656/530, loss: 0.024690985679626465
2023-01-21 11:01:26.427290: step: 1660/530, loss: 0.0675228163599968
2023-01-21 11:01:27.550860: step: 1664/530, loss: 0.04369344934821129
2023-01-21 11:01:28.627113: step: 1668/530, loss: 0.06066736951470375
2023-01-21 11:01:29.729069: step: 1672/530, loss: 0.10701408982276917
2023-01-21 11:01:30.837888: step: 1676/530, loss: 0.010109711438417435
2023-01-21 11:01:31.921376: step: 1680/530, loss: 0.030431080609560013
2023-01-21 11:01:33.035719: step: 1684/530, loss: 0.016868973150849342
2023-01-21 11:01:34.153807: step: 1688/530, loss: 0.004961490631103516
2023-01-21 11:01:35.286037: step: 1692/530, loss: 0.053442858159542084
2023-01-21 11:01:36.404283: step: 1696/530, loss: 0.002344322158023715
2023-01-21 11:01:37.505173: step: 1700/530, loss: 0.003222990082576871
2023-01-21 11:01:38.604946: step: 1704/530, loss: 0.01374893169850111
2023-01-21 11:01:39.685134: step: 1708/530, loss: 0.001385164214298129
2023-01-21 11:01:40.806772: step: 1712/530, loss: 0.024440240114927292
2023-01-21 11:01:41.901297: step: 1716/530, loss: 0.004100179765373468
2023-01-21 11:01:43.019515: step: 1720/530, loss: 0.009533119387924671
2023-01-21 11:01:44.161426: step: 1724/530, loss: 0.018368912860751152
2023-01-21 11:01:45.249448: step: 1728/530, loss: 0.055997755378484726
2023-01-21 11:01:46.344787: step: 1732/530, loss: 0.009659767150878906
2023-01-21 11:01:47.449737: step: 1736/530, loss: 0.06765079498291016
2023-01-21 11:01:48.558706: step: 1740/530, loss: 0.011044216342270374
2023-01-21 11:01:49.675602: step: 1744/530, loss: 0.012182426638901234
2023-01-21 11:01:50.764502: step: 1748/530, loss: 0.0028264999855309725
2023-01-21 11:01:51.883783: step: 1752/530, loss: 0.027657318860292435
2023-01-21 11:01:53.007878: step: 1756/530, loss: 0.04594878852367401
2023-01-21 11:01:54.079984: step: 1760/530, loss: 0.024839449673891068
2023-01-21 11:01:55.190450: step: 1764/530, loss: 0.029146576300263405
2023-01-21 11:01:56.277543: step: 1768/530, loss: 0.003691005753353238
2023-01-21 11:01:57.378340: step: 1772/530, loss: 0.012962198816239834
2023-01-21 11:01:58.486259: step: 1776/530, loss: 0.0243682861328125
2023-01-21 11:01:59.575934: step: 1780/530, loss: 0.7046001553535461
2023-01-21 11:02:00.687080: step: 1784/530, loss: 0.02164335362613201
2023-01-21 11:02:01.817155: step: 1788/530, loss: 0.020779799669981003
2023-01-21 11:02:02.973904: step: 1792/530, loss: 0.005387115757912397
2023-01-21 11:02:04.100756: step: 1796/530, loss: 0.04198188707232475
2023-01-21 11:02:05.234927: step: 1800/530, loss: 0.005226612091064453
2023-01-21 11:02:06.387159: step: 1804/530, loss: 0.028284218162298203
2023-01-21 11:02:07.517409: step: 1808/530, loss: 0.06694754958152771
2023-01-21 11:02:08.614410: step: 1812/530, loss: 0.03285827487707138
2023-01-21 11:02:09.729628: step: 1816/530, loss: 0.059444572776556015
2023-01-21 11:02:10.874252: step: 1820/530, loss: 0.040041398257017136
2023-01-21 11:02:11.991037: step: 1824/530, loss: 0.18622493743896484
2023-01-21 11:02:13.101139: step: 1828/530, loss: 0.09272956848144531
2023-01-21 11:02:14.193952: step: 1832/530, loss: 0.0005753517034463584
2023-01-21 11:02:15.301838: step: 1836/530, loss: 0.02573680877685547
2023-01-21 11:02:16.415742: step: 1840/530, loss: 0.0005391120794229209
2023-01-21 11:02:17.533916: step: 1844/530, loss: 0.017215155065059662
2023-01-21 11:02:18.683878: step: 1848/530, loss: 0.05284767225384712
2023-01-21 11:02:19.800135: step: 1852/530, loss: 0.002670764923095703
2023-01-21 11:02:20.920500: step: 1856/530, loss: 0.06721992790699005
2023-01-21 11:02:22.014755: step: 1860/530, loss: 0.00736846961081028
2023-01-21 11:02:23.106651: step: 1864/530, loss: 0.025576304644346237
2023-01-21 11:02:24.249047: step: 1868/530, loss: 0.004384136293083429
2023-01-21 11:02:25.358255: step: 1872/530, loss: 0.022989653050899506
2023-01-21 11:02:26.459953: step: 1876/530, loss: 0.0003863335005007684
2023-01-21 11:02:27.586947: step: 1880/530, loss: 0.22870245575904846
2023-01-21 11:02:28.685897: step: 1884/530, loss: 0.042016223073005676
2023-01-21 11:02:29.765665: step: 1888/530, loss: 0.0003993511199951172
2023-01-21 11:02:30.874973: step: 1892/530, loss: 0.031127452850341797
2023-01-21 11:02:31.979232: step: 1896/530, loss: 0.009677315130829811
2023-01-21 11:02:33.077765: step: 1900/530, loss: 0.005593490786850452
2023-01-21 11:02:34.204904: step: 1904/530, loss: 0.03399648889899254
2023-01-21 11:02:35.350340: step: 1908/530, loss: 0.00026960374088957906
2023-01-21 11:02:36.454385: step: 1912/530, loss: 0.10045433044433594
2023-01-21 11:02:37.553086: step: 1916/530, loss: 0.05294227600097656
2023-01-21 11:02:38.638360: step: 1920/530, loss: 0.008403397165238857
2023-01-21 11:02:39.768889: step: 1924/530, loss: 0.014225197024643421
2023-01-21 11:02:40.922045: step: 1928/530, loss: 0.019710540771484375
2023-01-21 11:02:42.021052: step: 1932/530, loss: 0.045116521418094635
2023-01-21 11:02:43.134740: step: 1936/530, loss: 0.028953934088349342
2023-01-21 11:02:44.226494: step: 1940/530, loss: 0.02074890211224556
2023-01-21 11:02:45.345586: step: 1944/530, loss: 0.0022242546547204256
2023-01-21 11:02:46.459867: step: 1948/530, loss: 0.011640453711152077
2023-01-21 11:02:47.558523: step: 1952/530, loss: 0.00682830810546875
2023-01-21 11:02:48.677527: step: 1956/530, loss: 0.08938580006361008
2023-01-21 11:02:49.777232: step: 1960/530, loss: 0.16871434450149536
2023-01-21 11:02:50.875570: step: 1964/530, loss: 0.000920200371183455
2023-01-21 11:02:52.006220: step: 1968/530, loss: 0.0002769470156636089
2023-01-21 11:02:53.117144: step: 1972/530, loss: 0.05166321247816086
2023-01-21 11:02:54.244851: step: 1976/530, loss: 0.046921394765377045
2023-01-21 11:02:55.354399: step: 1980/530, loss: 0.0009542942279949784
2023-01-21 11:02:56.481320: step: 1984/530, loss: 0.03886003792285919
2023-01-21 11:02:57.588352: step: 1988/530, loss: 0.012433338910341263
2023-01-21 11:02:58.685537: step: 1992/530, loss: 0.0513768196105957
2023-01-21 11:02:59.792984: step: 1996/530, loss: 0.0006297111394815147
2023-01-21 11:03:00.897533: step: 2000/530, loss: 0.04782819747924805
2023-01-21 11:03:02.013111: step: 2004/530, loss: 0.036470796912908554
2023-01-21 11:03:03.144355: step: 2008/530, loss: 1.2993037700653076
2023-01-21 11:03:04.223912: step: 2012/530, loss: 0.024122904986143112
2023-01-21 11:03:05.353977: step: 2016/530, loss: 0.07287292927503586
2023-01-21 11:03:06.479531: step: 2020/530, loss: 0.007452202029526234
2023-01-21 11:03:07.603164: step: 2024/530, loss: 0.023409079760313034
2023-01-21 11:03:08.721275: step: 2028/530, loss: 0.028469443321228027
2023-01-21 11:03:09.832209: step: 2032/530, loss: 0.03767271339893341
2023-01-21 11:03:10.950946: step: 2036/530, loss: 0.028090573847293854
2023-01-21 11:03:12.073215: step: 2040/530, loss: 0.0036323547828942537
2023-01-21 11:03:13.198943: step: 2044/530, loss: 0.04720459133386612
2023-01-21 11:03:14.306671: step: 2048/530, loss: 0.04097576066851616
2023-01-21 11:03:15.412455: step: 2052/530, loss: 0.003047657199203968
2023-01-21 11:03:16.507607: step: 2056/530, loss: 0.695419430732727
2023-01-21 11:03:17.602910: step: 2060/530, loss: 0.0984870195388794
2023-01-21 11:03:18.666499: step: 2064/530, loss: 0.05054507404565811
2023-01-21 11:03:19.763179: step: 2068/530, loss: 0.040987778455019
2023-01-21 11:03:20.876364: step: 2072/530, loss: 0.03736119344830513
2023-01-21 11:03:21.993549: step: 2076/530, loss: 0.001831150148063898
2023-01-21 11:03:23.103122: step: 2080/530, loss: 0.05985241010785103
2023-01-21 11:03:24.202254: step: 2084/530, loss: 0.00640482921153307
2023-01-21 11:03:25.303696: step: 2088/530, loss: 0.025707054883241653
2023-01-21 11:03:26.389629: step: 2092/530, loss: 0.09310808032751083
2023-01-21 11:03:27.499430: step: 2096/530, loss: 0.029081057757139206
2023-01-21 11:03:28.640521: step: 2100/530, loss: 0.013036632910370827
2023-01-21 11:03:29.780411: step: 2104/530, loss: 0.031297825276851654
2023-01-21 11:03:30.905181: step: 2108/530, loss: 0.04550447687506676
2023-01-21 11:03:32.034249: step: 2112/530, loss: 0.04033670201897621
2023-01-21 11:03:33.164058: step: 2116/530, loss: 0.05769810825586319
2023-01-21 11:03:34.304706: step: 2120/530, loss: 0.06925149261951447
==================================================
Loss: 0.045
--------------------
Dev: {'event': {'p': 0.5871369294605809, 'r': 0.7536617842876165, 'f1': 0.660058309037901}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Test: {'event': {'p': 0.648320895522388, 'r': 0.8100233100233101, 'f1': 0.7202072538860103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Chinese: {'event': {'p': 0.581081081081081, 'r': 0.7962962962962963, 'f1': 0.6718749999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Korean: {'event': {'p': 0.7115384615384616, 'r': 0.5873015873015873, 'f1': 0.6434782608695652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
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': 14}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 11:04:14.670757: step: 4/530, loss: 0.03840242326259613
2023-01-21 11:04:15.787413: step: 8/530, loss: 0.009069633670151234
2023-01-21 11:04:16.917304: step: 12/530, loss: 0.006418037693947554
2023-01-21 11:04:18.027988: step: 16/530, loss: 0.00023794174194335938
2023-01-21 11:04:19.150488: step: 20/530, loss: 0.024641182273626328
2023-01-21 11:04:20.251180: step: 24/530, loss: 0.0530790314078331
2023-01-21 11:04:21.359478: step: 28/530, loss: 0.007640648167580366
2023-01-21 11:04:22.457030: step: 32/530, loss: 0.011955547146499157
2023-01-21 11:04:23.540546: step: 36/530, loss: 0.040782734751701355
2023-01-21 11:04:24.638378: step: 40/530, loss: 0.000847935676574707
2023-01-21 11:04:25.738347: step: 44/530, loss: 0.034110214561223984
2023-01-21 11:04:26.873228: step: 48/530, loss: 0.007599306292831898
2023-01-21 11:04:27.996701: step: 52/530, loss: 0.002668237779289484
2023-01-21 11:04:29.162115: step: 56/530, loss: 0.02303457260131836
2023-01-21 11:04:30.223401: step: 60/530, loss: 0.008165931329131126
2023-01-21 11:04:31.325625: step: 64/530, loss: 0.0008536339155398309
2023-01-21 11:04:32.418430: step: 68/530, loss: 0.005838251207023859
2023-01-21 11:04:33.525464: step: 72/530, loss: 0.02844543568789959
2023-01-21 11:04:34.623409: step: 76/530, loss: 0.04478492960333824
2023-01-21 11:04:35.769444: step: 80/530, loss: 4.138946678722277e-05
2023-01-21 11:04:36.883292: step: 84/530, loss: 0.0214754119515419
2023-01-21 11:04:37.999889: step: 88/530, loss: 0.005344104953110218
2023-01-21 11:04:39.136860: step: 92/530, loss: 0.037993647158145905
2023-01-21 11:04:40.235302: step: 96/530, loss: 3.0243398214224726e-05
2023-01-21 11:04:41.373322: step: 100/530, loss: 0.0031784535385668278
2023-01-21 11:04:42.468990: step: 104/530, loss: 0.003102970076724887
2023-01-21 11:04:43.576609: step: 108/530, loss: 0.010702324099838734
2023-01-21 11:04:44.689209: step: 112/530, loss: 0.018754959106445312
2023-01-21 11:04:45.791290: step: 116/530, loss: 0.0634412094950676
2023-01-21 11:04:46.901047: step: 120/530, loss: 0.04991002380847931
2023-01-21 11:04:48.021864: step: 124/530, loss: 0.015558863058686256
2023-01-21 11:04:49.129463: step: 128/530, loss: 0.002147102262824774
2023-01-21 11:04:50.269437: step: 132/530, loss: 0.00147247314453125
2023-01-21 11:04:51.378362: step: 136/530, loss: 0.028916455805301666
2023-01-21 11:04:52.486158: step: 140/530, loss: 0.004498386289924383
2023-01-21 11:04:53.583290: step: 144/530, loss: 0.0010434150462970138
2023-01-21 11:04:54.674839: step: 148/530, loss: 0.04522104188799858
2023-01-21 11:04:55.777486: step: 152/530, loss: 0.011435126885771751
2023-01-21 11:04:56.881037: step: 156/530, loss: 6.771087646484375e-05
2023-01-21 11:04:57.985252: step: 160/530, loss: 0.03163528069853783
2023-01-21 11:04:59.066279: step: 164/530, loss: 0.008217906579375267
2023-01-21 11:05:00.165025: step: 168/530, loss: 0.003614234970882535
2023-01-21 11:05:01.300296: step: 172/530, loss: 0.044017985463142395
2023-01-21 11:05:02.446891: step: 176/530, loss: 0.0057722097262740135
2023-01-21 11:05:03.553343: step: 180/530, loss: 0.0001218795805471018
2023-01-21 11:05:04.666541: step: 184/530, loss: 0.00022239684767555445
2023-01-21 11:05:05.789964: step: 188/530, loss: 0.04460444673895836
2023-01-21 11:05:06.874385: step: 192/530, loss: 0.01856975629925728
2023-01-21 11:05:07.988369: step: 196/530, loss: 0.012131595984101295
2023-01-21 11:05:09.093656: step: 200/530, loss: 0.003978061955422163
2023-01-21 11:05:10.192245: step: 204/530, loss: 0.007702064234763384
2023-01-21 11:05:11.298690: step: 208/530, loss: 0.014125823974609375
2023-01-21 11:05:12.421738: step: 212/530, loss: 0.015476226806640625
2023-01-21 11:05:13.538859: step: 216/530, loss: 0.0036568641662597656
2023-01-21 11:05:14.681902: step: 220/530, loss: 0.025734614580869675
2023-01-21 11:05:15.817495: step: 224/530, loss: 0.018188001587986946
2023-01-21 11:05:16.921471: step: 228/530, loss: 0.022769736126065254
2023-01-21 11:05:18.048285: step: 232/530, loss: 0.027862204238772392
2023-01-21 11:05:19.132702: step: 236/530, loss: 0.05745887756347656
2023-01-21 11:05:20.225650: step: 240/530, loss: 0.025739002972841263
2023-01-21 11:05:21.323308: step: 244/530, loss: 1.544952465337701e-05
2023-01-21 11:05:22.445550: step: 248/530, loss: 0.04292182996869087
2023-01-21 11:05:23.550181: step: 252/530, loss: 0.026149630546569824
2023-01-21 11:05:24.679796: step: 256/530, loss: 0.005676746368408203
2023-01-21 11:05:25.779682: step: 260/530, loss: 0.003265380859375
2023-01-21 11:05:26.884979: step: 264/530, loss: 0.065595343708992
2023-01-21 11:05:27.991622: step: 268/530, loss: 0.005357789807021618
2023-01-21 11:05:29.103114: step: 272/530, loss: 0.018476469442248344
2023-01-21 11:05:30.181232: step: 276/530, loss: 0.008679008111357689
2023-01-21 11:05:31.291818: step: 280/530, loss: 0.0465240515768528
2023-01-21 11:05:32.392624: step: 284/530, loss: 0.05339546501636505
2023-01-21 11:05:33.518051: step: 288/530, loss: 0.016270209103822708
2023-01-21 11:05:34.616840: step: 292/530, loss: 0.016114234924316406
2023-01-21 11:05:35.724376: step: 296/530, loss: 0.02471294440329075
2023-01-21 11:05:36.806426: step: 300/530, loss: 0.0001739501894917339
2023-01-21 11:05:37.903707: step: 304/530, loss: 0.0020293237175792456
2023-01-21 11:05:39.031664: step: 308/530, loss: 0.09704923629760742
2023-01-21 11:05:40.119375: step: 312/530, loss: 0.019133806228637695
2023-01-21 11:05:41.230230: step: 316/530, loss: 0.01810932159423828
2023-01-21 11:05:42.335686: step: 320/530, loss: 0.003530168440192938
2023-01-21 11:05:43.463045: step: 324/530, loss: 0.0002617835998535156
2023-01-21 11:05:44.585236: step: 328/530, loss: 0.013393307104706764
2023-01-21 11:05:45.680969: step: 332/530, loss: 0.03494396060705185
2023-01-21 11:05:46.834838: step: 336/530, loss: 0.0034837722778320312
2023-01-21 11:05:47.922109: step: 340/530, loss: 0.02880272828042507
2023-01-21 11:05:49.044922: step: 344/530, loss: 0.003423309186473489
2023-01-21 11:05:50.147566: step: 348/530, loss: 0.017697572708129883
2023-01-21 11:05:51.279549: step: 352/530, loss: 0.007029914762824774
2023-01-21 11:05:52.383167: step: 356/530, loss: 0.0052734375931322575
2023-01-21 11:05:53.473135: step: 360/530, loss: 0.015992354601621628
2023-01-21 11:05:54.594674: step: 364/530, loss: 0.0542660728096962
2023-01-21 11:05:55.717541: step: 368/530, loss: 0.004149436950683594
2023-01-21 11:05:56.819943: step: 372/530, loss: 0.010693073272705078
2023-01-21 11:05:57.949185: step: 376/530, loss: 0.010441207326948643
2023-01-21 11:05:59.068904: step: 380/530, loss: 0.005313968751579523
2023-01-21 11:06:00.178608: step: 384/530, loss: 0.04609241336584091
2023-01-21 11:06:01.303475: step: 388/530, loss: 0.022980879992246628
2023-01-21 11:06:02.447736: step: 392/530, loss: 0.0005656242719851434
2023-01-21 11:06:03.564866: step: 396/530, loss: 0.02291107177734375
2023-01-21 11:06:04.679318: step: 400/530, loss: 0.04540662840008736
2023-01-21 11:06:05.777770: step: 404/530, loss: 0.05089666694402695
2023-01-21 11:06:06.896144: step: 408/530, loss: 0.0479000099003315
2023-01-21 11:06:07.972479: step: 412/530, loss: 0.03380577638745308
2023-01-21 11:06:09.102108: step: 416/530, loss: 0.052324485033750534
2023-01-21 11:06:10.222421: step: 420/530, loss: 0.014741898514330387
2023-01-21 11:06:11.335831: step: 424/530, loss: 0.05988769605755806
2023-01-21 11:06:12.433535: step: 428/530, loss: 0.025874996557831764
2023-01-21 11:06:13.534841: step: 432/530, loss: 0.0030241012573242188
2023-01-21 11:06:14.625261: step: 436/530, loss: 0.012413645163178444
2023-01-21 11:06:15.739886: step: 440/530, loss: 0.023438835516572
2023-01-21 11:06:16.844522: step: 444/530, loss: 0.0017874717013910413
2023-01-21 11:06:17.928251: step: 448/530, loss: 0.007959174923598766
2023-01-21 11:06:19.054065: step: 452/530, loss: 0.012431908398866653
2023-01-21 11:06:20.147627: step: 456/530, loss: 0.005193615332245827
2023-01-21 11:06:21.262158: step: 460/530, loss: 0.07342529296875
2023-01-21 11:06:22.366328: step: 464/530, loss: 0.01830902136862278
2023-01-21 11:06:23.469682: step: 468/530, loss: 0.12217597663402557
2023-01-21 11:06:24.581423: step: 472/530, loss: 0.012664414942264557
2023-01-21 11:06:25.695624: step: 476/530, loss: 0.010254954919219017
2023-01-21 11:06:26.812965: step: 480/530, loss: 0.00870370864868164
2023-01-21 11:06:27.940623: step: 484/530, loss: 0.03427162021398544
2023-01-21 11:06:29.037076: step: 488/530, loss: 0.03593731299042702
2023-01-21 11:06:30.146783: step: 492/530, loss: 0.016793059185147285
2023-01-21 11:06:31.302173: step: 496/530, loss: 0.01389703806489706
2023-01-21 11:06:32.427074: step: 500/530, loss: 0.0063329702243208885
2023-01-21 11:06:33.553475: step: 504/530, loss: 0.612633228302002
2023-01-21 11:06:34.662098: step: 508/530, loss: 0.03549759462475777
2023-01-21 11:06:35.792448: step: 512/530, loss: 0.15078334510326385
2023-01-21 11:06:36.872753: step: 516/530, loss: 0.002058267593383789
2023-01-21 11:06:37.996553: step: 520/530, loss: 0.004456329625099897
2023-01-21 11:06:39.095389: step: 524/530, loss: 0.001306819962337613
2023-01-21 11:06:40.180446: step: 528/530, loss: 0.0025599480140954256
2023-01-21 11:06:41.294168: step: 532/530, loss: 0.03457145765423775
2023-01-21 11:06:42.403324: step: 536/530, loss: 0.08291168510913849
2023-01-21 11:06:43.520401: step: 540/530, loss: 0.09893875569105148
2023-01-21 11:06:44.624636: step: 544/530, loss: 0.05193014442920685
2023-01-21 11:06:45.757881: step: 548/530, loss: 0.026662444695830345
2023-01-21 11:06:46.899671: step: 552/530, loss: 0.0039231302216649055
2023-01-21 11:06:48.009172: step: 556/530, loss: 0.0011560439597815275
2023-01-21 11:06:49.095593: step: 560/530, loss: 0.02017073705792427
2023-01-21 11:06:50.191190: step: 564/530, loss: 0.017523575574159622
2023-01-21 11:06:51.311990: step: 568/530, loss: 0.05107874795794487
2023-01-21 11:06:52.405959: step: 572/530, loss: 0.03371162340044975
2023-01-21 11:06:53.535112: step: 576/530, loss: 0.015005683526396751
2023-01-21 11:06:54.643127: step: 580/530, loss: 0.0010227203601971269
2023-01-21 11:06:55.761516: step: 584/530, loss: 0.0069373128935694695
2023-01-21 11:06:56.871940: step: 588/530, loss: 0.0036689757835119963
2023-01-21 11:06:57.956019: step: 592/530, loss: 0.01164999045431614
2023-01-21 11:06:59.072423: step: 596/530, loss: 0.0009566307417117059
2023-01-21 11:07:00.215836: step: 600/530, loss: 0.10820828378200531
2023-01-21 11:07:01.303504: step: 604/530, loss: 0.02452840842306614
2023-01-21 11:07:02.402679: step: 608/530, loss: 0.032178595662117004
2023-01-21 11:07:03.516071: step: 612/530, loss: 0.03753180801868439
2023-01-21 11:07:04.643644: step: 616/530, loss: 0.008643722161650658
2023-01-21 11:07:05.759198: step: 620/530, loss: 0.00036826133145950735
2023-01-21 11:07:06.868918: step: 624/530, loss: 0.0019894361030310392
2023-01-21 11:07:07.977796: step: 628/530, loss: 0.012667560949921608
2023-01-21 11:07:09.113952: step: 632/530, loss: 0.0326550267636776
2023-01-21 11:07:10.253148: step: 636/530, loss: 0.02403888665139675
2023-01-21 11:07:11.395022: step: 640/530, loss: 0.00953369215130806
2023-01-21 11:07:12.477192: step: 644/530, loss: 0.021070100367069244
2023-01-21 11:07:13.609940: step: 648/530, loss: 0.0033937455154955387
2023-01-21 11:07:14.729506: step: 652/530, loss: 0.031713105738162994
2023-01-21 11:07:15.812691: step: 656/530, loss: 0.012997722253203392
2023-01-21 11:07:16.895719: step: 660/530, loss: 0.004050063900649548
2023-01-21 11:07:18.012091: step: 664/530, loss: 0.045154571533203125
2023-01-21 11:07:19.166244: step: 668/530, loss: 0.008099079132080078
2023-01-21 11:07:20.277457: step: 672/530, loss: 0.005531025119125843
2023-01-21 11:07:21.392287: step: 676/530, loss: 0.01414504088461399
2023-01-21 11:07:22.491184: step: 680/530, loss: 0.0023255348205566406
2023-01-21 11:07:23.637515: step: 684/530, loss: 0.05395030975341797
2023-01-21 11:07:24.752544: step: 688/530, loss: 0.00413126964122057
2023-01-21 11:07:25.884259: step: 692/530, loss: 0.020533179864287376
2023-01-21 11:07:26.971931: step: 696/530, loss: 0.008992671966552734
2023-01-21 11:07:28.063598: step: 700/530, loss: 0.005629253573715687
2023-01-21 11:07:29.165821: step: 704/530, loss: 0.036220453679561615
2023-01-21 11:07:30.267069: step: 708/530, loss: 0.015161609277129173
2023-01-21 11:07:31.425274: step: 712/530, loss: 0.34428828954696655
2023-01-21 11:07:32.531953: step: 716/530, loss: 0.05602912977337837
2023-01-21 11:07:33.658390: step: 720/530, loss: 0.0003578186151571572
2023-01-21 11:07:34.780595: step: 724/530, loss: 0.008083343505859375
2023-01-21 11:07:35.919486: step: 728/530, loss: 0.003274965099990368
2023-01-21 11:07:37.019114: step: 732/530, loss: 0.059556201100349426
2023-01-21 11:07:38.135702: step: 736/530, loss: 0.014365101233124733
2023-01-21 11:07:39.249698: step: 740/530, loss: 0.0006901741144247353
2023-01-21 11:07:40.363341: step: 744/530, loss: 0.019325971603393555
2023-01-21 11:07:41.474301: step: 748/530, loss: 0.05002956464886665
2023-01-21 11:07:42.611710: step: 752/530, loss: 0.015990352258086205
2023-01-21 11:07:43.725941: step: 756/530, loss: 0.00857400894165039
2023-01-21 11:07:44.867087: step: 760/530, loss: 0.0022113800514489412
2023-01-21 11:07:45.966484: step: 764/530, loss: 0.00019302369037177414
2023-01-21 11:07:47.089039: step: 768/530, loss: 0.08483857661485672
2023-01-21 11:07:48.189673: step: 772/530, loss: 0.014361190609633923
2023-01-21 11:07:49.297418: step: 776/530, loss: 0.13020524382591248
2023-01-21 11:07:50.406483: step: 780/530, loss: 0.5335664749145508
2023-01-21 11:07:51.522567: step: 784/530, loss: 0.033621788024902344
2023-01-21 11:07:52.627564: step: 788/530, loss: 0.007825278677046299
2023-01-21 11:07:53.746029: step: 792/530, loss: 0.02518320083618164
2023-01-21 11:07:54.827579: step: 796/530, loss: 0.12295150756835938
2023-01-21 11:07:55.918733: step: 800/530, loss: 0.03141040727496147
2023-01-21 11:07:57.028741: step: 804/530, loss: 0.004620742984116077
2023-01-21 11:07:58.120030: step: 808/530, loss: 0.010891055688261986
2023-01-21 11:07:59.249869: step: 812/530, loss: 0.03944864124059677
2023-01-21 11:08:00.341204: step: 816/530, loss: 0.045034077018499374
2023-01-21 11:08:01.450141: step: 820/530, loss: 0.0368741974234581
2023-01-21 11:08:02.581837: step: 824/530, loss: 0.00417981157079339
2023-01-21 11:08:03.666582: step: 828/530, loss: 0.019805049523711205
2023-01-21 11:08:04.767151: step: 832/530, loss: 0.02046079747378826
2023-01-21 11:08:05.887326: step: 836/530, loss: 0.03033618815243244
2023-01-21 11:08:06.994686: step: 840/530, loss: 0.07592006027698517
2023-01-21 11:08:08.102069: step: 844/530, loss: 0.002530002733692527
2023-01-21 11:08:09.253074: step: 848/530, loss: 0.009886790066957474
2023-01-21 11:08:10.350505: step: 852/530, loss: 0.06473427265882492
2023-01-21 11:08:11.469759: step: 856/530, loss: 0.0004981040838174522
2023-01-21 11:08:12.599657: step: 860/530, loss: 0.0020929337479174137
2023-01-21 11:08:13.744467: step: 864/530, loss: 0.002754306886345148
2023-01-21 11:08:14.900275: step: 868/530, loss: 0.01937265321612358
2023-01-21 11:08:15.989207: step: 872/530, loss: 0.003805398941040039
2023-01-21 11:08:17.126339: step: 876/530, loss: 0.0018307685386389494
2023-01-21 11:08:18.227882: step: 880/530, loss: 0.03172473981976509
2023-01-21 11:08:19.371939: step: 884/530, loss: 0.01272659283131361
2023-01-21 11:08:20.476038: step: 888/530, loss: 0.0021369934547692537
2023-01-21 11:08:21.573897: step: 892/530, loss: 0.0118598947301507
2023-01-21 11:08:22.686776: step: 896/530, loss: 0.027636097744107246
2023-01-21 11:08:23.832275: step: 900/530, loss: 0.004925918765366077
2023-01-21 11:08:24.965922: step: 904/530, loss: 0.0002288818359375
2023-01-21 11:08:26.064188: step: 908/530, loss: 0.02348318137228489
2023-01-21 11:08:27.158699: step: 912/530, loss: 7.82012939453125e-05
2023-01-21 11:08:28.269082: step: 916/530, loss: 0.007669543847441673
2023-01-21 11:08:29.360966: step: 920/530, loss: 2.47955322265625e-05
2023-01-21 11:08:30.439296: step: 924/530, loss: 0.15422238409519196
2023-01-21 11:08:31.586285: step: 928/530, loss: 0.03189344331622124
2023-01-21 11:08:32.716891: step: 932/530, loss: 0.009030628018081188
2023-01-21 11:08:33.832962: step: 936/530, loss: 0.028885841369628906
2023-01-21 11:08:34.987260: step: 940/530, loss: 0.01490101870149374
2023-01-21 11:08:36.117675: step: 944/530, loss: 0.02431516721844673
2023-01-21 11:08:37.226440: step: 948/530, loss: 0.07218370586633682
2023-01-21 11:08:38.357187: step: 952/530, loss: 0.05511894449591637
2023-01-21 11:08:39.467362: step: 956/530, loss: 0.026274681091308594
2023-01-21 11:08:40.583885: step: 960/530, loss: 0.009793853387236595
2023-01-21 11:08:41.677948: step: 964/530, loss: 0.01799640618264675
2023-01-21 11:08:42.818869: step: 968/530, loss: 0.03685379400849342
2023-01-21 11:08:43.960912: step: 972/530, loss: 0.04366359859704971
2023-01-21 11:08:45.078451: step: 976/530, loss: 0.0006680488586425781
2023-01-21 11:08:46.177698: step: 980/530, loss: 0.03017336316406727
2023-01-21 11:08:47.285757: step: 984/530, loss: 0.05321183428168297
2023-01-21 11:08:48.385095: step: 988/530, loss: 0.0317266471683979
2023-01-21 11:08:49.514259: step: 992/530, loss: 0.05910377576947212
2023-01-21 11:08:50.626340: step: 996/530, loss: 0.06197796016931534
2023-01-21 11:08:51.756192: step: 1000/530, loss: 0.00122489919885993
2023-01-21 11:08:52.871214: step: 1004/530, loss: 0.009475327096879482
2023-01-21 11:08:53.977669: step: 1008/530, loss: 0.005061936564743519
2023-01-21 11:08:55.073951: step: 1012/530, loss: 0.06972198188304901
2023-01-21 11:08:56.182309: step: 1016/530, loss: 0.0006240844959393144
2023-01-21 11:08:57.283559: step: 1020/530, loss: 0.04617580398917198
2023-01-21 11:08:58.375109: step: 1024/530, loss: 0.006876469124108553
2023-01-21 11:08:59.521071: step: 1028/530, loss: 0.0519350990653038
2023-01-21 11:09:00.636114: step: 1032/530, loss: 0.011633205227553844
2023-01-21 11:09:01.783953: step: 1036/530, loss: 0.017735058441758156
2023-01-21 11:09:02.896531: step: 1040/530, loss: 0.04231987148523331
2023-01-21 11:09:04.030961: step: 1044/530, loss: 0.014898204244673252
2023-01-21 11:09:05.144321: step: 1048/530, loss: 0.022055961191654205
2023-01-21 11:09:06.261827: step: 1052/530, loss: 0.0467718169093132
2023-01-21 11:09:07.338533: step: 1056/530, loss: 0.009108162485063076
2023-01-21 11:09:08.427345: step: 1060/530, loss: 0.018407821655273438
2023-01-21 11:09:09.522752: step: 1064/530, loss: 0.023163510486483574
2023-01-21 11:09:10.636760: step: 1068/530, loss: 0.015588188543915749
2023-01-21 11:09:11.762353: step: 1072/530, loss: 0.01715545728802681
2023-01-21 11:09:12.846318: step: 1076/530, loss: 0.004157352726906538
2023-01-21 11:09:13.991426: step: 1080/530, loss: 0.10756760090589523
2023-01-21 11:09:15.086540: step: 1084/530, loss: 0.007722282316535711
2023-01-21 11:09:16.195519: step: 1088/530, loss: 0.25852030515670776
2023-01-21 11:09:17.354877: step: 1092/530, loss: 0.0028404234908521175
2023-01-21 11:09:18.451702: step: 1096/530, loss: 0.02288227155804634
2023-01-21 11:09:19.551227: step: 1100/530, loss: 0.03561963886022568
2023-01-21 11:09:20.645854: step: 1104/530, loss: 0.02105865441262722
2023-01-21 11:09:21.757845: step: 1108/530, loss: 0.02662849612534046
2023-01-21 11:09:22.897676: step: 1112/530, loss: 0.06679821014404297
2023-01-21 11:09:24.015800: step: 1116/530, loss: 0.02941122092306614
2023-01-21 11:09:25.130336: step: 1120/530, loss: 0.0052242279052734375
2023-01-21 11:09:26.275967: step: 1124/530, loss: 0.000965118408203125
2023-01-21 11:09:27.380022: step: 1128/530, loss: 0.003691721009090543
2023-01-21 11:09:28.467091: step: 1132/530, loss: 0.054492950439453125
2023-01-21 11:09:29.595745: step: 1136/530, loss: 0.015259837731719017
2023-01-21 11:09:30.686081: step: 1140/530, loss: 0.0229174941778183
2023-01-21 11:09:31.789609: step: 1144/530, loss: 0.0075460439547896385
2023-01-21 11:09:32.936614: step: 1148/530, loss: 0.022366667166352272
2023-01-21 11:09:34.022093: step: 1152/530, loss: 0.013931477442383766
2023-01-21 11:09:35.135751: step: 1156/530, loss: 0.0032839300110936165
2023-01-21 11:09:36.234346: step: 1160/530, loss: 0.02798900566995144
2023-01-21 11:09:37.330380: step: 1164/530, loss: 0.022859765216708183
2023-01-21 11:09:38.422023: step: 1168/530, loss: 0.0017206191550940275
2023-01-21 11:09:39.544762: step: 1172/530, loss: 0.008795070461928844
2023-01-21 11:09:40.662940: step: 1176/530, loss: 0.21655330061912537
2023-01-21 11:09:41.771716: step: 1180/530, loss: 0.02131366729736328
2023-01-21 11:09:42.905893: step: 1184/530, loss: 0.06843052059412003
2023-01-21 11:09:44.026286: step: 1188/530, loss: 0.05016050487756729
2023-01-21 11:09:45.132368: step: 1192/530, loss: 0.05927343666553497
2023-01-21 11:09:46.244780: step: 1196/530, loss: 0.0058654784224927425
2023-01-21 11:09:47.333333: step: 1200/530, loss: 0.1620623618364334
2023-01-21 11:09:48.447546: step: 1204/530, loss: 0.0029786110389977694
2023-01-21 11:09:49.570715: step: 1208/530, loss: 0.00979471206665039
2023-01-21 11:09:50.690148: step: 1212/530, loss: 0.009833144955337048
2023-01-21 11:09:51.827283: step: 1216/530, loss: 0.03238401189446449
2023-01-21 11:09:52.935862: step: 1220/530, loss: 0.05477018281817436
2023-01-21 11:09:54.053977: step: 1224/530, loss: 0.015384006313979626
2023-01-21 11:09:55.178479: step: 1228/530, loss: 0.05691862106323242
2023-01-21 11:09:56.295113: step: 1232/530, loss: 0.02624073065817356
2023-01-21 11:09:57.455900: step: 1236/530, loss: 0.024321652948856354
2023-01-21 11:09:58.576220: step: 1240/530, loss: 0.0011670112144201994
2023-01-21 11:09:59.710207: step: 1244/530, loss: 0.13921470940113068
2023-01-21 11:10:00.805574: step: 1248/530, loss: 0.0004746437189169228
2023-01-21 11:10:01.935454: step: 1252/530, loss: 0.08361601829528809
2023-01-21 11:10:03.090703: step: 1256/530, loss: 0.03683442994952202
2023-01-21 11:10:04.183060: step: 1260/530, loss: 0.01796703413128853
2023-01-21 11:10:05.260367: step: 1264/530, loss: 0.0005685806390829384
2023-01-21 11:10:06.393736: step: 1268/530, loss: 0.012295866385102272
2023-01-21 11:10:07.528896: step: 1272/530, loss: 0.024425983428955078
2023-01-21 11:10:08.642754: step: 1276/530, loss: 0.0015705585246905684
2023-01-21 11:10:09.787660: step: 1280/530, loss: 0.013979816809296608
2023-01-21 11:10:10.892988: step: 1284/530, loss: 0.01157372072339058
2023-01-21 11:10:12.007239: step: 1288/530, loss: 0.2807699143886566
2023-01-21 11:10:13.149932: step: 1292/530, loss: 0.005910873878747225
2023-01-21 11:10:14.278489: step: 1296/530, loss: 0.003741645719856024
2023-01-21 11:10:15.406150: step: 1300/530, loss: 0.21141962707042694
2023-01-21 11:10:16.539468: step: 1304/530, loss: 0.042479708790779114
2023-01-21 11:10:17.662102: step: 1308/530, loss: 0.1723569929599762
2023-01-21 11:10:18.775933: step: 1312/530, loss: 0.09767894446849823
2023-01-21 11:10:19.912793: step: 1316/530, loss: 0.039337158203125
2023-01-21 11:10:21.034431: step: 1320/530, loss: 0.0754978209733963
2023-01-21 11:10:22.104479: step: 1324/530, loss: 0.004464626312255859
2023-01-21 11:10:23.228452: step: 1328/530, loss: 0.04487276077270508
2023-01-21 11:10:24.356542: step: 1332/530, loss: 0.009469224140048027
2023-01-21 11:10:25.461458: step: 1336/530, loss: 0.01969289779663086
2023-01-21 11:10:26.600414: step: 1340/530, loss: 0.07884535938501358
2023-01-21 11:10:27.691733: step: 1344/530, loss: 0.05041675642132759
2023-01-21 11:10:28.795035: step: 1348/530, loss: 0.023331500589847565
2023-01-21 11:10:29.904544: step: 1352/530, loss: 0.06804981827735901
2023-01-21 11:10:30.994999: step: 1356/530, loss: 0.006998634431511164
2023-01-21 11:10:32.114390: step: 1360/530, loss: 0.037338923662900925
2023-01-21 11:10:33.263716: step: 1364/530, loss: 0.04044532775878906
2023-01-21 11:10:34.372810: step: 1368/530, loss: 0.04161481931805611
2023-01-21 11:10:35.460722: step: 1372/530, loss: 0.6274380683898926
2023-01-21 11:10:36.560799: step: 1376/530, loss: 0.06226787716150284
2023-01-21 11:10:37.659528: step: 1380/530, loss: 0.0027858258690685034
2023-01-21 11:10:38.802111: step: 1384/530, loss: 0.009277534671127796
2023-01-21 11:10:39.926997: step: 1388/530, loss: 0.023471739143133163
2023-01-21 11:10:41.031827: step: 1392/530, loss: 0.010932731442153454
2023-01-21 11:10:42.121782: step: 1396/530, loss: 0.033903125673532486
2023-01-21 11:10:43.216903: step: 1400/530, loss: 0.004085254389792681
2023-01-21 11:10:44.327037: step: 1404/530, loss: 0.012323570437729359
2023-01-21 11:10:45.421516: step: 1408/530, loss: 0.0011724949581548572
2023-01-21 11:10:46.537498: step: 1412/530, loss: 0.044562362134456635
2023-01-21 11:10:47.642034: step: 1416/530, loss: 0.0334782600402832
2023-01-21 11:10:48.743135: step: 1420/530, loss: 0.0332433246076107
2023-01-21 11:10:49.865625: step: 1424/530, loss: 0.03523731231689453
2023-01-21 11:10:50.983787: step: 1428/530, loss: 0.004351711366325617
2023-01-21 11:10:52.126326: step: 1432/530, loss: 0.008992379531264305
2023-01-21 11:10:53.256404: step: 1436/530, loss: 0.03551445156335831
2023-01-21 11:10:54.379760: step: 1440/530, loss: 0.008700896054506302
2023-01-21 11:10:55.506658: step: 1444/530, loss: 0.03925041854381561
2023-01-21 11:10:56.625060: step: 1448/530, loss: 0.002571630524471402
2023-01-21 11:10:57.742080: step: 1452/530, loss: 0.01748218573629856
2023-01-21 11:10:58.901215: step: 1456/530, loss: 0.00038423537625931203
2023-01-21 11:11:00.007213: step: 1460/530, loss: 0.11973171681165695
2023-01-21 11:11:01.123504: step: 1464/530, loss: 0.02832183800637722
2023-01-21 11:11:02.210748: step: 1468/530, loss: 0.03799581527709961
2023-01-21 11:11:03.334695: step: 1472/530, loss: 0.07473854720592499
2023-01-21 11:11:04.428504: step: 1476/530, loss: 0.005482101812958717
2023-01-21 11:11:05.540136: step: 1480/530, loss: 0.00017824172391556203
2023-01-21 11:11:06.641328: step: 1484/530, loss: 0.0015570640098303556
2023-01-21 11:11:07.742248: step: 1488/530, loss: 0.003506946610286832
2023-01-21 11:11:08.820523: step: 1492/530, loss: 0.09422293305397034
2023-01-21 11:11:09.949837: step: 1496/530, loss: 0.007080745883285999
2023-01-21 11:11:11.081753: step: 1500/530, loss: 0.0014700889587402344
2023-01-21 11:11:12.190272: step: 1504/530, loss: 0.031247805804014206
2023-01-21 11:11:13.299512: step: 1508/530, loss: 0.09658461064100266
2023-01-21 11:11:14.382717: step: 1512/530, loss: 0.044455386698246
2023-01-21 11:11:15.500037: step: 1516/530, loss: 0.03336143493652344
2023-01-21 11:11:16.617375: step: 1520/530, loss: 0.012038039974868298
2023-01-21 11:11:17.704455: step: 1524/530, loss: 0.4502524435520172
2023-01-21 11:11:18.792088: step: 1528/530, loss: 0.025072479620575905
2023-01-21 11:11:19.898129: step: 1532/530, loss: 0.007258415222167969
2023-01-21 11:11:21.011815: step: 1536/530, loss: 0.004117202945053577
2023-01-21 11:11:22.145602: step: 1540/530, loss: 0.001439905259758234
2023-01-21 11:11:23.298123: step: 1544/530, loss: 0.009568024426698685
2023-01-21 11:11:24.407855: step: 1548/530, loss: 0.0367489829659462
2023-01-21 11:11:25.513356: step: 1552/530, loss: 0.003459978150203824
2023-01-21 11:11:26.636665: step: 1556/530, loss: 0.014469528570771217
2023-01-21 11:11:27.747991: step: 1560/530, loss: 0.026285268366336823
2023-01-21 11:11:28.863181: step: 1564/530, loss: 0.010631131939589977
2023-01-21 11:11:29.970347: step: 1568/530, loss: 0.06253137439489365
2023-01-21 11:11:31.096715: step: 1572/530, loss: 0.0058743953704833984
2023-01-21 11:11:32.196137: step: 1576/530, loss: 0.0008081435807980597
2023-01-21 11:11:33.314954: step: 1580/530, loss: 0.014841699972748756
2023-01-21 11:11:34.433774: step: 1584/530, loss: 0.0303923599421978
2023-01-21 11:11:35.544404: step: 1588/530, loss: 0.020233154296875
2023-01-21 11:11:36.657067: step: 1592/530, loss: 0.00054340367205441
2023-01-21 11:11:37.770542: step: 1596/530, loss: 0.0015866756439208984
2023-01-21 11:11:38.892993: step: 1600/530, loss: 0.023419713601469994
2023-01-21 11:11:40.000916: step: 1604/530, loss: 0.0007610321044921875
2023-01-21 11:11:41.114873: step: 1608/530, loss: 0.008882475085556507
2023-01-21 11:11:42.256188: step: 1612/530, loss: 0.025136185809969902
2023-01-21 11:11:43.371383: step: 1616/530, loss: 0.0573999397456646
2023-01-21 11:11:44.513499: step: 1620/530, loss: 0.06960811465978622
2023-01-21 11:11:45.653773: step: 1624/530, loss: 0.013595867902040482
2023-01-21 11:11:46.748490: step: 1628/530, loss: 0.0018093109829351306
2023-01-21 11:11:47.873727: step: 1632/530, loss: 0.008505702018737793
2023-01-21 11:11:48.998642: step: 1636/530, loss: 0.00020599365234375
2023-01-21 11:11:50.128131: step: 1640/530, loss: 0.04881725460290909
2023-01-21 11:11:51.271496: step: 1644/530, loss: 0.05637397989630699
2023-01-21 11:11:52.397797: step: 1648/530, loss: 0.026079177856445312
2023-01-21 11:11:53.510157: step: 1652/530, loss: 0.0010074615711346269
2023-01-21 11:11:54.702824: step: 1656/530, loss: 0.01110844686627388
2023-01-21 11:11:55.823128: step: 1660/530, loss: 0.028516102582216263
2023-01-21 11:11:56.907358: step: 1664/530, loss: 0.03979663923382759
2023-01-21 11:11:58.022586: step: 1668/530, loss: 1.2816070318222046
2023-01-21 11:11:59.121961: step: 1672/530, loss: 0.02012329176068306
2023-01-21 11:12:00.214258: step: 1676/530, loss: 0.007733821868896484
2023-01-21 11:12:01.336531: step: 1680/530, loss: 0.007509517949074507
2023-01-21 11:12:02.444037: step: 1684/530, loss: 0.0038934231270104647
2023-01-21 11:12:03.530756: step: 1688/530, loss: 0.02810950204730034
2023-01-21 11:12:04.614795: step: 1692/530, loss: 0.044361017644405365
2023-01-21 11:12:05.715919: step: 1696/530, loss: 0.11027304828166962
2023-01-21 11:12:06.842434: step: 1700/530, loss: 5.426407005870715e-05
2023-01-21 11:12:07.955289: step: 1704/530, loss: 0.036669157445430756
2023-01-21 11:12:09.076704: step: 1708/530, loss: 0.043581772595644
2023-01-21 11:12:10.197270: step: 1712/530, loss: 0.023237133398652077
2023-01-21 11:12:11.302371: step: 1716/530, loss: 0.0337887741625309
2023-01-21 11:12:12.389878: step: 1720/530, loss: 0.017784500494599342
2023-01-21 11:12:13.503306: step: 1724/530, loss: 0.0017353057628497481
2023-01-21 11:12:14.596135: step: 1728/530, loss: 0.03257398679852486
2023-01-21 11:12:15.702774: step: 1732/530, loss: 0.002972411923110485
2023-01-21 11:12:16.783450: step: 1736/530, loss: 0.017431069165468216
2023-01-21 11:12:17.944378: step: 1740/530, loss: 0.007779788691550493
2023-01-21 11:12:19.030434: step: 1744/530, loss: 0.06137056648731232
2023-01-21 11:12:20.142983: step: 1748/530, loss: 0.021506119519472122
2023-01-21 11:12:21.252692: step: 1752/530, loss: 0.023546982556581497
2023-01-21 11:12:22.351782: step: 1756/530, loss: 0.004004573915153742
2023-01-21 11:12:23.441761: step: 1760/530, loss: 0.0021692276932299137
2023-01-21 11:12:24.555008: step: 1764/530, loss: 0.0023047446738928556
2023-01-21 11:12:25.703093: step: 1768/530, loss: 0.09165382385253906
2023-01-21 11:12:26.788180: step: 1772/530, loss: 0.07605700939893723
2023-01-21 11:12:27.891794: step: 1776/530, loss: 0.00102910993155092
2023-01-21 11:12:28.993080: step: 1780/530, loss: 0.029495811089873314
2023-01-21 11:12:30.105250: step: 1784/530, loss: 0.012430811300873756
2023-01-21 11:12:31.209716: step: 1788/530, loss: 0.03245430067181587
2023-01-21 11:12:32.320200: step: 1792/530, loss: 0.006335926242172718
2023-01-21 11:12:33.422527: step: 1796/530, loss: 0.0017846107948571444
2023-01-21 11:12:34.548156: step: 1800/530, loss: 0.0445735938847065
2023-01-21 11:12:35.640351: step: 1804/530, loss: 0.011932088062167168
2023-01-21 11:12:36.769138: step: 1808/530, loss: 0.03533673286437988
2023-01-21 11:12:37.864456: step: 1812/530, loss: 0.019838904961943626
2023-01-21 11:12:38.963598: step: 1816/530, loss: 0.022262001410126686
2023-01-21 11:12:40.069590: step: 1820/530, loss: 0.024143362417817116
2023-01-21 11:12:41.171261: step: 1824/530, loss: 0.031217576935887337
2023-01-21 11:12:42.292714: step: 1828/530, loss: 0.0005869388696737587
2023-01-21 11:12:43.400308: step: 1832/530, loss: 0.038331225514411926
2023-01-21 11:12:44.501803: step: 1836/530, loss: 0.03635158762335777
2023-01-21 11:12:45.651749: step: 1840/530, loss: 0.0013438225723803043
2023-01-21 11:12:46.794123: step: 1844/530, loss: 0.5774036645889282
2023-01-21 11:12:47.946631: step: 1848/530, loss: 0.01458129845559597
2023-01-21 11:12:49.068228: step: 1852/530, loss: 0.07336712628602982
2023-01-21 11:12:50.202143: step: 1856/530, loss: 0.0931333601474762
2023-01-21 11:12:51.299574: step: 1860/530, loss: 0.007402515504509211
2023-01-21 11:12:52.397693: step: 1864/530, loss: 0.004745769780129194
2023-01-21 11:12:53.523743: step: 1868/530, loss: 0.016877364367246628
2023-01-21 11:12:54.631199: step: 1872/530, loss: 0.009440422058105469
2023-01-21 11:12:55.747515: step: 1876/530, loss: 0.010044110007584095
2023-01-21 11:12:56.871413: step: 1880/530, loss: 0.011895943433046341
2023-01-21 11:12:57.985924: step: 1884/530, loss: 1.2731469869613647
2023-01-21 11:12:59.070763: step: 1888/530, loss: 0.00010795593698276207
2023-01-21 11:13:00.195276: step: 1892/530, loss: 0.03233356773853302
2023-01-21 11:13:01.320362: step: 1896/530, loss: 0.021082306280732155
2023-01-21 11:13:02.419652: step: 1900/530, loss: 0.0005115509266033769
2023-01-21 11:13:03.535480: step: 1904/530, loss: 0.0410245917737484
2023-01-21 11:13:04.627646: step: 1908/530, loss: 0.014094257727265358
2023-01-21 11:13:05.791150: step: 1912/530, loss: 0.011416626162827015
2023-01-21 11:13:06.904840: step: 1916/530, loss: 0.005322170443832874
2023-01-21 11:13:08.030338: step: 1920/530, loss: 0.03090343438088894
2023-01-21 11:13:09.154361: step: 1924/530, loss: 0.008490943349897861
2023-01-21 11:13:10.270908: step: 1928/530, loss: 0.004160786047577858
2023-01-21 11:13:11.440213: step: 1932/530, loss: 0.021747207269072533
2023-01-21 11:13:12.547945: step: 1936/530, loss: 0.01864147186279297
2023-01-21 11:13:13.637327: step: 1940/530, loss: 0.036138057708740234
2023-01-21 11:13:14.784845: step: 1944/530, loss: 0.007146930787712336
2023-01-21 11:13:15.890470: step: 1948/530, loss: 1.71661376953125e-05
2023-01-21 11:13:16.989365: step: 1952/530, loss: 0.0022264481522142887
2023-01-21 11:13:18.089184: step: 1956/530, loss: 0.019896602258086205
2023-01-21 11:13:19.198195: step: 1960/530, loss: 0.010755825787782669
2023-01-21 11:13:20.306141: step: 1964/530, loss: 0.008393336087465286
2023-01-21 11:13:21.423135: step: 1968/530, loss: 0.01708192750811577
2023-01-21 11:13:22.535786: step: 1972/530, loss: 0.01895160786807537
2023-01-21 11:13:23.659402: step: 1976/530, loss: 0.007607078179717064
2023-01-21 11:13:24.777426: step: 1980/530, loss: 0.0017756461165845394
2023-01-21 11:13:25.902752: step: 1984/530, loss: 0.03867168352007866
2023-01-21 11:13:27.011724: step: 1988/530, loss: 0.012145495042204857
2023-01-21 11:13:28.128962: step: 1992/530, loss: 0.014162588864564896
2023-01-21 11:13:29.230020: step: 1996/530, loss: 0.018490267917513847
2023-01-21 11:13:30.391850: step: 2000/530, loss: 0.12102717906236649
2023-01-21 11:13:31.485941: step: 2004/530, loss: 0.0005085945595055819
2023-01-21 11:13:32.572257: step: 2008/530, loss: 8.344650268554688e-05
2023-01-21 11:13:33.682747: step: 2012/530, loss: 0.026729583740234375
2023-01-21 11:13:34.783748: step: 2016/530, loss: 0.06280127167701721
2023-01-21 11:13:35.912694: step: 2020/530, loss: 0.00139532086905092
2023-01-21 11:13:37.011028: step: 2024/530, loss: 0.0075057027861475945
2023-01-21 11:13:38.114199: step: 2028/530, loss: 0.029274560511112213
2023-01-21 11:13:39.204949: step: 2032/530, loss: 0.02344655990600586
2023-01-21 11:13:40.319122: step: 2036/530, loss: 0.05932817608118057
2023-01-21 11:13:41.412445: step: 2040/530, loss: 0.035944364964962006
2023-01-21 11:13:42.516266: step: 2044/530, loss: 0.02032174915075302
2023-01-21 11:13:43.638341: step: 2048/530, loss: 0.053028397262096405
2023-01-21 11:13:44.751897: step: 2052/530, loss: 0.0640474334359169
2023-01-21 11:13:45.846648: step: 2056/530, loss: 0.051745299249887466
2023-01-21 11:13:46.955998: step: 2060/530, loss: 0.0018241762882098556
2023-01-21 11:13:48.079280: step: 2064/530, loss: 0.0402621254324913
2023-01-21 11:13:49.195996: step: 2068/530, loss: 0.01775200292468071
2023-01-21 11:13:50.307616: step: 2072/530, loss: 0.00011148452904308215
2023-01-21 11:13:51.427359: step: 2076/530, loss: 0.012066412717103958
2023-01-21 11:13:52.517357: step: 2080/530, loss: 0.06936779618263245
2023-01-21 11:13:53.622728: step: 2084/530, loss: 0.04780597612261772
2023-01-21 11:13:54.728112: step: 2088/530, loss: 0.019060945138335228
2023-01-21 11:13:55.840042: step: 2092/530, loss: 0.0015701055526733398
2023-01-21 11:13:56.948762: step: 2096/530, loss: 0.0025784492027014494
2023-01-21 11:13:58.068780: step: 2100/530, loss: 0.0008533477666787803
2023-01-21 11:13:59.202259: step: 2104/530, loss: 0.007522392552345991
2023-01-21 11:14:00.325486: step: 2108/530, loss: 0.051296330988407135
2023-01-21 11:14:01.446052: step: 2112/530, loss: 0.02603931352496147
2023-01-21 11:14:02.551219: step: 2116/530, loss: 0.002379989717155695
2023-01-21 11:14:03.692660: step: 2120/530, loss: 0.01710519939661026
==================================================
Loss: 0.037
--------------------
Dev: {'event': {'p': 0.586171310629515, 'r': 0.7563249001331558, 'f1': 0.6604651162790698}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Test: {'event': {'p': 0.650093808630394, 'r': 0.8076923076923077, 'f1': 0.7203742203742204}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Chinese: {'event': {'p': 0.5945945945945946, 'r': 0.8148148148148148, 'f1': 0.6875}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Korean: {'event': {'p': 0.6491228070175439, 'r': 0.5873015873015873, 'f1': 0.6166666666666668}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Russian: {'event': {'p': 0.5277777777777778, 'r': 0.5277777777777778, 'f1': 0.5277777777777778}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 11:14:44.299235: step: 4/530, loss: 0.0026096345391124487
2023-01-21 11:14:45.406162: step: 8/530, loss: 0.008737373165786266
2023-01-21 11:14:46.487535: step: 12/530, loss: 0.05006594583392143
2023-01-21 11:14:47.580118: step: 16/530, loss: 0.0007851123809814453
2023-01-21 11:14:48.728817: step: 20/530, loss: 0.006977224722504616
2023-01-21 11:14:49.832330: step: 24/530, loss: 0.0014032365288585424
2023-01-21 11:14:50.962554: step: 28/530, loss: 0.0013179780216887593
2023-01-21 11:14:52.046168: step: 32/530, loss: 0.003001833101734519
2023-01-21 11:14:53.142411: step: 36/530, loss: 0.006005573086440563
2023-01-21 11:14:54.228990: step: 40/530, loss: 0.07602062821388245
2023-01-21 11:14:55.349485: step: 44/530, loss: 0.009712410159409046
2023-01-21 11:14:56.460615: step: 48/530, loss: 0.014066696166992188
2023-01-21 11:14:57.557558: step: 52/530, loss: 0.00030856134253554046
2023-01-21 11:14:58.649811: step: 56/530, loss: 0.09133699536323547
2023-01-21 11:14:59.800639: step: 60/530, loss: 0.01047430094331503
2023-01-21 11:15:00.876009: step: 64/530, loss: 0.004975557327270508
2023-01-21 11:15:01.985264: step: 68/530, loss: 0.03455772250890732
2023-01-21 11:15:03.081206: step: 72/530, loss: 0.005787086207419634
2023-01-21 11:15:04.246859: step: 76/530, loss: 0.026619913056492805
2023-01-21 11:15:05.378518: step: 80/530, loss: 0.0002605438348837197
2023-01-21 11:15:06.473497: step: 84/530, loss: 0.005034064874053001
2023-01-21 11:15:07.605068: step: 88/530, loss: 0.008485604077577591
2023-01-21 11:15:08.732287: step: 92/530, loss: 0.025510119274258614
2023-01-21 11:15:09.830240: step: 96/530, loss: 0.003732109209522605
2023-01-21 11:15:10.929810: step: 100/530, loss: 0.0235642921179533
2023-01-21 11:15:12.035045: step: 104/530, loss: 0.008184242062270641
2023-01-21 11:15:13.151821: step: 108/530, loss: 0.00490150460973382
2023-01-21 11:15:14.270115: step: 112/530, loss: 0.03522300720214844
2023-01-21 11:15:15.346002: step: 116/530, loss: 0.005222320556640625
2023-01-21 11:15:16.460070: step: 120/530, loss: 0.01125946082174778
2023-01-21 11:15:17.553148: step: 124/530, loss: 0.010607719421386719
2023-01-21 11:15:18.663525: step: 128/530, loss: 0.03161945194005966
2023-01-21 11:15:19.758510: step: 132/530, loss: 0.0026453970931470394
2023-01-21 11:15:20.871349: step: 136/530, loss: 0.0019149781437590718
2023-01-21 11:15:22.004581: step: 140/530, loss: 0.005530357360839844
2023-01-21 11:15:23.073484: step: 144/530, loss: 0.472377210855484
2023-01-21 11:15:24.210891: step: 148/530, loss: 0.0025650025345385075
2023-01-21 11:15:25.324021: step: 152/530, loss: 0.0034577371552586555
2023-01-21 11:15:26.461565: step: 156/530, loss: 0.003615093184635043
2023-01-21 11:15:27.580542: step: 160/530, loss: 0.17555637657642365
2023-01-21 11:15:28.691358: step: 164/530, loss: 0.002581977751106024
2023-01-21 11:15:29.791798: step: 168/530, loss: 0.026271535083651543
2023-01-21 11:15:30.919275: step: 172/530, loss: 0.019331859424710274
2023-01-21 11:15:32.026233: step: 176/530, loss: 0.0004039764462504536
2023-01-21 11:15:33.170876: step: 180/530, loss: 0.012410067953169346
2023-01-21 11:15:34.285778: step: 184/530, loss: 0.05592861399054527
2023-01-21 11:15:35.400298: step: 188/530, loss: 0.04153309017419815
2023-01-21 11:15:36.500095: step: 192/530, loss: 0.009405993856489658
2023-01-21 11:15:37.618572: step: 196/530, loss: 0.01063756924122572
2023-01-21 11:15:38.705186: step: 200/530, loss: 0.030408715829253197
2023-01-21 11:15:39.817586: step: 204/530, loss: 1.430511474609375e-05
2023-01-21 11:15:40.937788: step: 208/530, loss: 0.08489446341991425
2023-01-21 11:15:42.051068: step: 212/530, loss: 0.0008311271667480469
2023-01-21 11:15:43.170066: step: 216/530, loss: 0.0012578964233398438
2023-01-21 11:15:44.304006: step: 220/530, loss: 0.001083803130313754
2023-01-21 11:15:45.384214: step: 224/530, loss: 0.00426530884578824
2023-01-21 11:15:46.480771: step: 228/530, loss: 0.0009167671087197959
2023-01-21 11:15:47.614977: step: 232/530, loss: 0.044957924634218216
2023-01-21 11:15:48.705577: step: 236/530, loss: 0.006188249681144953
2023-01-21 11:15:49.834182: step: 240/530, loss: 0.004193687345832586
2023-01-21 11:15:50.916520: step: 244/530, loss: 0.041961051523685455
2023-01-21 11:15:52.034689: step: 248/530, loss: 0.016870975494384766
2023-01-21 11:15:53.139981: step: 252/530, loss: 0.07717037200927734
2023-01-21 11:15:54.260124: step: 256/530, loss: 0.030640553683042526
2023-01-21 11:15:55.367280: step: 260/530, loss: 0.001344871474429965
2023-01-21 11:15:56.485470: step: 264/530, loss: 0.008956718258559704
2023-01-21 11:15:57.584746: step: 268/530, loss: 0.0279680248349905
2023-01-21 11:15:58.676442: step: 272/530, loss: 0.011220455169677734
2023-01-21 11:15:59.764189: step: 276/530, loss: 0.0028352737426757812
2023-01-21 11:16:00.860340: step: 280/530, loss: 0.03299360349774361
2023-01-21 11:16:01.965505: step: 284/530, loss: 0.0014082908164709806
2023-01-21 11:16:03.081803: step: 288/530, loss: 0.0166015625
2023-01-21 11:16:04.179660: step: 292/530, loss: 0.02297210693359375
2023-01-21 11:16:05.279377: step: 296/530, loss: 0.0012806892627850175
2023-01-21 11:16:06.431113: step: 300/530, loss: 0.0901295617222786
2023-01-21 11:16:07.551693: step: 304/530, loss: 0.476127028465271
2023-01-21 11:16:08.633918: step: 308/530, loss: 0.006267356686294079
2023-01-21 11:16:09.746328: step: 312/530, loss: 0.022666500881314278
2023-01-21 11:16:10.863468: step: 316/530, loss: 0.014592742547392845
2023-01-21 11:16:11.985450: step: 320/530, loss: 0.0005290984991006553
2023-01-21 11:16:13.115491: step: 324/530, loss: 0.011837197467684746
2023-01-21 11:16:14.219493: step: 328/530, loss: 0.008163833059370518
2023-01-21 11:16:15.353890: step: 332/530, loss: 0.03495226055383682
2023-01-21 11:16:16.444692: step: 336/530, loss: 0.0020742416381835938
2023-01-21 11:16:17.571281: step: 340/530, loss: 0.012751484289765358
2023-01-21 11:16:18.656889: step: 344/530, loss: 0.023176193237304688
2023-01-21 11:16:19.785365: step: 348/530, loss: 0.00091724400408566
2023-01-21 11:16:20.890375: step: 352/530, loss: 0.0646636039018631
2023-01-21 11:16:22.034182: step: 356/530, loss: 0.006764411926269531
2023-01-21 11:16:23.132029: step: 360/530, loss: 0.0021659613121300936
2023-01-21 11:16:24.242427: step: 364/530, loss: 0.016031693667173386
2023-01-21 11:16:25.348132: step: 368/530, loss: 0.2545141279697418
2023-01-21 11:16:26.450206: step: 372/530, loss: 0.029867172241210938
2023-01-21 11:16:27.582586: step: 376/530, loss: 0.019176291301846504
2023-01-21 11:16:28.676393: step: 380/530, loss: 0.005105781834572554
2023-01-21 11:16:29.752229: step: 384/530, loss: 0.0037616731133311987
2023-01-21 11:16:30.867979: step: 388/530, loss: 0.0009654999012127519
2023-01-21 11:16:31.966196: step: 392/530, loss: 0.004054916091263294
2023-01-21 11:16:33.103313: step: 396/530, loss: 0.024544525891542435
2023-01-21 11:16:34.194202: step: 400/530, loss: 0.0023601532448083162
2023-01-21 11:16:35.265747: step: 404/530, loss: 0.020042039453983307
2023-01-21 11:16:36.358251: step: 408/530, loss: 0.007198929786682129
2023-01-21 11:16:37.457614: step: 412/530, loss: 0.02568025514483452
2023-01-21 11:16:38.566462: step: 416/530, loss: 0.027436351403594017
2023-01-21 11:16:39.667835: step: 420/530, loss: 0.0005029678577557206
2023-01-21 11:16:40.756804: step: 424/530, loss: 0.051404621452093124
2023-01-21 11:16:41.856855: step: 428/530, loss: 0.0075965882278978825
2023-01-21 11:16:42.963185: step: 432/530, loss: 0.0012785912258550525
2023-01-21 11:16:44.066378: step: 436/530, loss: 0.0546293780207634
2023-01-21 11:16:45.197637: step: 440/530, loss: 0.030843354761600494
2023-01-21 11:16:46.299564: step: 444/530, loss: 0.02581319771707058
2023-01-21 11:16:47.430589: step: 448/530, loss: 0.006031990051269531
2023-01-21 11:16:48.574508: step: 452/530, loss: 0.03751411288976669
2023-01-21 11:16:49.674763: step: 456/530, loss: 0.01381225697696209
2023-01-21 11:16:50.786697: step: 460/530, loss: 0.14594613015651703
2023-01-21 11:16:51.878953: step: 464/530, loss: 0.009919356554746628
2023-01-21 11:16:52.967067: step: 468/530, loss: 0.04968976974487305
2023-01-21 11:16:54.083191: step: 472/530, loss: 0.0009607315296307206
2023-01-21 11:16:55.188438: step: 476/530, loss: 0.021875428035855293
2023-01-21 11:16:56.307952: step: 480/530, loss: 0.0008830070728436112
2023-01-21 11:16:57.440322: step: 484/530, loss: 0.10106706619262695
2023-01-21 11:16:58.569539: step: 488/530, loss: 0.03615245968103409
2023-01-21 11:16:59.672539: step: 492/530, loss: 0.0011098862159997225
2023-01-21 11:17:00.780249: step: 496/530, loss: 0.037485696375370026
2023-01-21 11:17:01.908632: step: 500/530, loss: 0.008068657480180264
2023-01-21 11:17:03.037252: step: 504/530, loss: 0.0007484436500817537
2023-01-21 11:17:04.142544: step: 508/530, loss: 0.0028930664993822575
2023-01-21 11:17:05.256589: step: 512/530, loss: 0.06997394561767578
2023-01-21 11:17:06.362501: step: 516/530, loss: 0.0004976272466592491
2023-01-21 11:17:07.499439: step: 520/530, loss: 0.009317588992416859
2023-01-21 11:17:08.589941: step: 524/530, loss: 0.040335655212402344
2023-01-21 11:17:09.672819: step: 528/530, loss: 0.009569501504302025
2023-01-21 11:17:10.773372: step: 532/530, loss: 0.01207876205444336
2023-01-21 11:17:11.883749: step: 536/530, loss: 0.00047512055607512593
2023-01-21 11:17:13.023539: step: 540/530, loss: 0.061328887939453125
2023-01-21 11:17:14.145818: step: 544/530, loss: 0.02001495473086834
2023-01-21 11:17:15.246225: step: 548/530, loss: 0.00834197923541069
2023-01-21 11:17:16.348132: step: 552/530, loss: 0.14684951305389404
2023-01-21 11:17:17.452179: step: 556/530, loss: 0.13284379243850708
2023-01-21 11:17:18.561117: step: 560/530, loss: 0.07882557064294815
2023-01-21 11:17:19.706481: step: 564/530, loss: 0.014153195545077324
2023-01-21 11:17:20.803375: step: 568/530, loss: 0.0015981197357177734
2023-01-21 11:17:21.913525: step: 572/530, loss: 0.00620117224752903
2023-01-21 11:17:23.036498: step: 576/530, loss: 0.02842097170650959
2023-01-21 11:17:24.151501: step: 580/530, loss: 0.0009136199951171875
2023-01-21 11:17:25.289589: step: 584/530, loss: 0.018334578722715378
2023-01-21 11:17:26.374700: step: 588/530, loss: 0.0417022667825222
2023-01-21 11:17:27.484236: step: 592/530, loss: 0.0021401403937488794
2023-01-21 11:17:28.655509: step: 596/530, loss: 0.027335835620760918
2023-01-21 11:17:29.788999: step: 600/530, loss: 0.00942163448780775
2023-01-21 11:17:30.893743: step: 604/530, loss: 0.0005393982282839715
2023-01-21 11:17:32.012430: step: 608/530, loss: 0.004176282789558172
2023-01-21 11:17:33.150422: step: 612/530, loss: 0.004477500915527344
2023-01-21 11:17:34.266807: step: 616/530, loss: 0.02010359801352024
2023-01-21 11:17:35.350292: step: 620/530, loss: 0.003826999804005027
2023-01-21 11:17:36.471467: step: 624/530, loss: 0.010530472733080387
2023-01-21 11:17:37.570070: step: 628/530, loss: 0.48352622985839844
2023-01-21 11:17:38.699309: step: 632/530, loss: 0.004313468933105469
2023-01-21 11:17:39.792797: step: 636/530, loss: 0.029853105545043945
2023-01-21 11:17:40.874669: step: 640/530, loss: 0.0017503738636150956
2023-01-21 11:17:42.033248: step: 644/530, loss: 0.09529876708984375
2023-01-21 11:17:43.173659: step: 648/530, loss: 0.009164620190858841
2023-01-21 11:17:44.275558: step: 652/530, loss: 0.001909398939460516
2023-01-21 11:17:45.428501: step: 656/530, loss: 0.015333461575210094
2023-01-21 11:17:46.528196: step: 660/530, loss: 0.012388992123305798
2023-01-21 11:17:47.640387: step: 664/530, loss: 0.027003003284335136
2023-01-21 11:17:48.742052: step: 668/530, loss: 0.022673320025205612
2023-01-21 11:17:49.875314: step: 672/530, loss: 0.05640869215130806
2023-01-21 11:17:50.961786: step: 676/530, loss: 0.18259334564208984
2023-01-21 11:17:52.075065: step: 680/530, loss: 0.05725069344043732
2023-01-21 11:17:53.181614: step: 684/530, loss: 0.016090011224150658
2023-01-21 11:17:54.287565: step: 688/530, loss: 0.00819478090852499
2023-01-21 11:17:55.387668: step: 692/530, loss: 0.004620933905243874
2023-01-21 11:17:56.488635: step: 696/530, loss: 0.03376026079058647
2023-01-21 11:17:57.584909: step: 700/530, loss: 0.000614166259765625
2023-01-21 11:17:58.703088: step: 704/530, loss: 0.005454635713249445
2023-01-21 11:17:59.798697: step: 708/530, loss: 0.011223411187529564
2023-01-21 11:18:00.896483: step: 712/530, loss: 0.03956909477710724
2023-01-21 11:18:02.024636: step: 716/530, loss: 0.00919080339372158
2023-01-21 11:18:03.153869: step: 720/530, loss: 0.09515400230884552
2023-01-21 11:18:04.271839: step: 724/530, loss: 0.006445407867431641
2023-01-21 11:18:05.370316: step: 728/530, loss: 0.0006406783941201866
2023-01-21 11:18:06.450500: step: 732/530, loss: 0.008631658740341663
2023-01-21 11:18:07.553622: step: 736/530, loss: 0.01547927875071764
2023-01-21 11:18:08.669831: step: 740/530, loss: 0.013899898156523705
2023-01-21 11:18:09.768234: step: 744/530, loss: 0.007287025451660156
2023-01-21 11:18:10.874095: step: 748/530, loss: 0.060418032109737396
2023-01-21 11:18:11.985640: step: 752/530, loss: 0.013784694485366344
2023-01-21 11:18:13.097486: step: 756/530, loss: 0.004078865051269531
2023-01-21 11:18:14.183744: step: 760/530, loss: 0.005148029420524836
2023-01-21 11:18:15.288709: step: 764/530, loss: 0.002786636585369706
2023-01-21 11:18:16.413562: step: 768/530, loss: 0.009826707653701305
2023-01-21 11:18:17.505220: step: 772/530, loss: 0.0002690315304789692
2023-01-21 11:18:18.639870: step: 776/530, loss: 0.0018097878200933337
2023-01-21 11:18:19.745623: step: 780/530, loss: 0.00013165474229026586
2023-01-21 11:18:20.849328: step: 784/530, loss: 0.051764775067567825
2023-01-21 11:18:21.980833: step: 788/530, loss: 0.010389518924057484
2023-01-21 11:18:23.101355: step: 792/530, loss: 0.0006260871887207031
2023-01-21 11:18:24.247881: step: 796/530, loss: 0.012496472336351871
2023-01-21 11:18:25.354637: step: 800/530, loss: 0.08666171878576279
2023-01-21 11:18:26.463273: step: 804/530, loss: 0.011906290426850319
2023-01-21 11:18:27.569805: step: 808/530, loss: 0.012635231018066406
2023-01-21 11:18:28.715883: step: 812/530, loss: 0.012938880361616611
2023-01-21 11:18:29.817545: step: 816/530, loss: 0.028399372473359108
2023-01-21 11:18:30.930547: step: 820/530, loss: 0.09615077823400497
2023-01-21 11:18:32.003435: step: 824/530, loss: 0.0004273414670024067
2023-01-21 11:18:33.113932: step: 828/530, loss: 0.02262573316693306
2023-01-21 11:18:34.251617: step: 832/530, loss: 0.02915208414196968
2023-01-21 11:18:35.387368: step: 836/530, loss: 0.0334194153547287
2023-01-21 11:18:36.502763: step: 840/530, loss: 0.00044498444185592234
2023-01-21 11:18:37.632843: step: 844/530, loss: 0.1068183034658432
2023-01-21 11:18:38.755740: step: 848/530, loss: 0.02968454547226429
2023-01-21 11:18:39.867230: step: 852/530, loss: 0.09853249043226242
2023-01-21 11:18:40.986772: step: 856/530, loss: 0.0004447936953511089
2023-01-21 11:18:42.108990: step: 860/530, loss: 0.031416039913892746
2023-01-21 11:18:43.211757: step: 864/530, loss: 0.2399987280368805
2023-01-21 11:18:44.321945: step: 868/530, loss: 0.11753010749816895
2023-01-21 11:18:45.455947: step: 872/530, loss: 0.04470062255859375
2023-01-21 11:18:46.579786: step: 876/530, loss: 0.018079757690429688
2023-01-21 11:18:47.690149: step: 880/530, loss: 0.021625136956572533
2023-01-21 11:18:48.781889: step: 884/530, loss: 0.004472064785659313
2023-01-21 11:18:49.908416: step: 888/530, loss: 0.02916712872684002
2023-01-21 11:18:51.032717: step: 892/530, loss: 0.000257641077041626
2023-01-21 11:18:52.154775: step: 896/530, loss: 0.001990032382309437
2023-01-21 11:18:53.270377: step: 900/530, loss: 0.0047844890505075455
2023-01-21 11:18:54.418407: step: 904/530, loss: 0.013147926889359951
2023-01-21 11:18:55.512857: step: 908/530, loss: 0.016425324603915215
2023-01-21 11:18:56.613151: step: 912/530, loss: 0.01337738148868084
2023-01-21 11:18:57.718502: step: 916/530, loss: 0.0005602836608886719
2023-01-21 11:18:58.821377: step: 920/530, loss: 0.025411320850253105
2023-01-21 11:18:59.968897: step: 924/530, loss: 0.03919658809900284
2023-01-21 11:19:01.079306: step: 928/530, loss: 0.009774064645171165
2023-01-21 11:19:02.169852: step: 932/530, loss: 0.0007413864368572831
2023-01-21 11:19:03.275494: step: 936/530, loss: 0.010137938894331455
2023-01-21 11:19:04.361178: step: 940/530, loss: 0.05636034160852432
2023-01-21 11:19:05.485744: step: 944/530, loss: 0.006942367646843195
2023-01-21 11:19:06.594888: step: 948/530, loss: 0.08903008699417114
2023-01-21 11:19:07.730798: step: 952/530, loss: 0.0013545036781579256
2023-01-21 11:19:08.855068: step: 956/530, loss: 0.0007080078357830644
2023-01-21 11:19:09.943637: step: 960/530, loss: 0.05321807786822319
2023-01-21 11:19:11.055876: step: 964/530, loss: 0.03147897496819496
2023-01-21 11:19:12.163119: step: 968/530, loss: 0.019057273864746094
2023-01-21 11:19:13.288837: step: 972/530, loss: 0.03451404720544815
2023-01-21 11:19:14.422375: step: 976/530, loss: 0.00665626535192132
2023-01-21 11:19:15.533456: step: 980/530, loss: 0.00017919539823196828
2023-01-21 11:19:16.630229: step: 984/530, loss: 0.01682901382446289
2023-01-21 11:19:17.742077: step: 988/530, loss: 0.0006068229558877647
2023-01-21 11:19:18.868153: step: 992/530, loss: 0.041375160217285156
2023-01-21 11:19:19.969669: step: 996/530, loss: 0.008054685778915882
2023-01-21 11:19:21.077889: step: 1000/530, loss: 0.0034139633644372225
2023-01-21 11:19:22.187142: step: 1004/530, loss: 0.09210024029016495
2023-01-21 11:19:23.310889: step: 1008/530, loss: 0.06712131202220917
2023-01-21 11:19:24.416974: step: 1012/530, loss: 0.027309799566864967
2023-01-21 11:19:25.527158: step: 1016/530, loss: 0.002092075301334262
2023-01-21 11:19:26.645996: step: 1020/530, loss: 0.017806099727749825
2023-01-21 11:19:27.767341: step: 1024/530, loss: 0.15123941004276276
2023-01-21 11:19:28.893382: step: 1028/530, loss: 0.0025316239334642887
2023-01-21 11:19:30.010323: step: 1032/530, loss: 0.020592212677001953
2023-01-21 11:19:31.127819: step: 1036/530, loss: 0.0052585601806640625
2023-01-21 11:19:32.239791: step: 1040/530, loss: 0.022068405523896217
2023-01-21 11:19:33.373811: step: 1044/530, loss: 0.026339245960116386
2023-01-21 11:19:34.479465: step: 1048/530, loss: 0.01343383826315403
2023-01-21 11:19:35.588196: step: 1052/530, loss: 0.0006569862016476691
2023-01-21 11:19:36.681822: step: 1056/530, loss: 0.024186039343476295
2023-01-21 11:19:37.800074: step: 1060/530, loss: 0.009835625067353249
2023-01-21 11:19:38.931592: step: 1064/530, loss: 0.00011072159395553172
2023-01-21 11:19:40.045404: step: 1068/530, loss: 0.085893914103508
2023-01-21 11:19:41.147154: step: 1072/530, loss: 0.02461276203393936
2023-01-21 11:19:42.318813: step: 1076/530, loss: 0.02232734113931656
2023-01-21 11:19:43.433019: step: 1080/530, loss: 0.01565737836062908
2023-01-21 11:19:44.564434: step: 1084/530, loss: 0.02214031293988228
2023-01-21 11:19:45.674153: step: 1088/530, loss: 0.00012235641770530492
2023-01-21 11:19:46.792866: step: 1092/530, loss: 0.0033653259743005037
2023-01-21 11:19:47.895989: step: 1096/530, loss: 0.5417042374610901
2023-01-21 11:19:49.021500: step: 1100/530, loss: 0.0035800933837890625
2023-01-21 11:19:50.145979: step: 1104/530, loss: 0.02330474741756916
2023-01-21 11:19:51.250600: step: 1108/530, loss: 0.001342868898063898
2023-01-21 11:19:52.325459: step: 1112/530, loss: -1.144409225162235e-06
2023-01-21 11:19:53.444235: step: 1116/530, loss: 0.0027744295075535774
2023-01-21 11:19:54.573966: step: 1120/530, loss: 0.0069938660599291325
2023-01-21 11:19:55.684128: step: 1124/530, loss: 0.10436997562646866
2023-01-21 11:19:56.812976: step: 1128/530, loss: 0.020429611206054688
2023-01-21 11:19:57.936395: step: 1132/530, loss: 0.00021419525728560984
2023-01-21 11:19:59.063718: step: 1136/530, loss: 0.0010223388671875
2023-01-21 11:20:00.165222: step: 1140/530, loss: 0.00876159593462944
2023-01-21 11:20:01.307802: step: 1144/530, loss: 0.005516433622688055
2023-01-21 11:20:02.397165: step: 1148/530, loss: 0.004676151089370251
2023-01-21 11:20:03.536067: step: 1152/530, loss: 0.01613597944378853
2023-01-21 11:20:04.656620: step: 1156/530, loss: 0.006712150759994984
2023-01-21 11:20:05.781731: step: 1160/530, loss: 0.08199349045753479
2023-01-21 11:20:06.876143: step: 1164/530, loss: 0.002145290607586503
2023-01-21 11:20:07.990931: step: 1168/530, loss: 0.02720623090863228
2023-01-21 11:20:09.127516: step: 1172/530, loss: 0.0070053101517260075
2023-01-21 11:20:10.230836: step: 1176/530, loss: 0.0006077289581298828
2023-01-21 11:20:11.345455: step: 1180/530, loss: 0.006890153978019953
2023-01-21 11:20:12.453286: step: 1184/530, loss: 0.0015504838665947318
2023-01-21 11:20:13.565422: step: 1188/530, loss: 0.0063339234329760075
2023-01-21 11:20:14.655394: step: 1192/530, loss: 0.09852425754070282
2023-01-21 11:20:15.741756: step: 1196/530, loss: 0.04136495664715767
2023-01-21 11:20:16.863152: step: 1200/530, loss: 0.0794849544763565
2023-01-21 11:20:17.972789: step: 1204/530, loss: 0.03389853239059448
2023-01-21 11:20:19.094831: step: 1208/530, loss: 0.00020675659470725805
2023-01-21 11:20:20.231880: step: 1212/530, loss: 0.015740204602479935
2023-01-21 11:20:21.330259: step: 1216/530, loss: 0.014971543103456497
2023-01-21 11:20:22.441798: step: 1220/530, loss: 0.0011601329315453768
2023-01-21 11:20:23.560225: step: 1224/530, loss: 0.04130592569708824
2023-01-21 11:20:24.700265: step: 1228/530, loss: 0.0010036468738690019
2023-01-21 11:20:25.826387: step: 1232/530, loss: 0.0008438110235147178
2023-01-21 11:20:26.923675: step: 1236/530, loss: 0.026101304218173027
2023-01-21 11:20:28.007958: step: 1240/530, loss: 0.03869905322790146
2023-01-21 11:20:29.105029: step: 1244/530, loss: 0.014095974154770374
2023-01-21 11:20:30.226814: step: 1248/530, loss: 0.0408666618168354
2023-01-21 11:20:31.382702: step: 1252/530, loss: 0.04023304209113121
2023-01-21 11:20:32.518120: step: 1256/530, loss: 0.04168128967285156
2023-01-21 11:20:33.638320: step: 1260/530, loss: 0.0017606735927984118
2023-01-21 11:20:34.773049: step: 1264/530, loss: 0.08702965080738068
2023-01-21 11:20:35.904998: step: 1268/530, loss: 0.006293678190559149
2023-01-21 11:20:37.008125: step: 1272/530, loss: 0.018437767401337624
2023-01-21 11:20:38.090434: step: 1276/530, loss: 0.00019989015709143132
2023-01-21 11:20:39.213077: step: 1280/530, loss: 0.03458233177661896
2023-01-21 11:20:40.326809: step: 1284/530, loss: 0.04725909233093262
2023-01-21 11:20:41.439942: step: 1288/530, loss: 0.004369544796645641
2023-01-21 11:20:42.559879: step: 1292/530, loss: 0.14484548568725586
2023-01-21 11:20:43.655951: step: 1296/530, loss: 0.04737739637494087
2023-01-21 11:20:44.770750: step: 1300/530, loss: 0.017830276861786842
2023-01-21 11:20:45.898987: step: 1304/530, loss: 0.05960889160633087
2023-01-21 11:20:46.989680: step: 1308/530, loss: 0.013987923040986061
2023-01-21 11:20:48.083019: step: 1312/530, loss: 0.059500597417354584
2023-01-21 11:20:49.237784: step: 1316/530, loss: 0.004475403111428022
2023-01-21 11:20:50.340068: step: 1320/530, loss: 0.036643028259277344
2023-01-21 11:20:51.439773: step: 1324/530, loss: 0.003297424176707864
2023-01-21 11:20:52.559993: step: 1328/530, loss: 0.09255476295948029
2023-01-21 11:20:53.701743: step: 1332/530, loss: 0.07465648651123047
2023-01-21 11:20:54.810267: step: 1336/530, loss: 0.016371821984648705
2023-01-21 11:20:55.915352: step: 1340/530, loss: 0.008239460177719593
2023-01-21 11:20:57.046371: step: 1344/530, loss: 0.0009898185962811112
2023-01-21 11:20:58.181415: step: 1348/530, loss: 0.0026920319069176912
2023-01-21 11:20:59.293732: step: 1352/530, loss: 0.006384659092873335
2023-01-21 11:21:00.390507: step: 1356/530, loss: 0.0018002509605139494
2023-01-21 11:21:01.532045: step: 1360/530, loss: 0.010363388806581497
2023-01-21 11:21:02.664785: step: 1364/530, loss: 0.03910541534423828
2023-01-21 11:21:03.782623: step: 1368/530, loss: 0.08220481872558594
2023-01-21 11:21:04.887820: step: 1372/530, loss: 0.051215123385190964
2023-01-21 11:21:05.972013: step: 1376/530, loss: 0.02475719526410103
2023-01-21 11:21:07.090951: step: 1380/530, loss: 0.00834035873413086
2023-01-21 11:21:08.192594: step: 1384/530, loss: 0.012173652648925781
2023-01-21 11:21:09.319699: step: 1388/530, loss: 0.01556462049484253
2023-01-21 11:21:10.413330: step: 1392/530, loss: 0.0032630921341478825
2023-01-21 11:21:11.524494: step: 1396/530, loss: 0.022950172424316406
2023-01-21 11:21:12.635130: step: 1400/530, loss: 0.017870904877781868
2023-01-21 11:21:13.768615: step: 1404/530, loss: 0.018709564581513405
2023-01-21 11:21:14.880704: step: 1408/530, loss: 0.0019338608253747225
2023-01-21 11:21:16.013934: step: 1412/530, loss: 0.0017212391830980778
2023-01-21 11:21:17.160572: step: 1416/530, loss: 0.03352975845336914
2023-01-21 11:21:18.261387: step: 1420/530, loss: 0.01043720357120037
2023-01-21 11:21:19.389825: step: 1424/530, loss: 0.0127401826903224
2023-01-21 11:21:20.505537: step: 1428/530, loss: 0.023438643664121628
2023-01-21 11:21:21.628220: step: 1432/530, loss: 0.0009836197132244706
2023-01-21 11:21:22.735074: step: 1436/530, loss: 0.0030391693580895662
2023-01-21 11:21:23.859887: step: 1440/530, loss: 0.0015737534267827868
2023-01-21 11:21:24.975738: step: 1444/530, loss: 0.00190143589861691
2023-01-21 11:21:26.072422: step: 1448/530, loss: 0.008566570468246937
2023-01-21 11:21:27.169130: step: 1452/530, loss: 8.57353225001134e-05
2023-01-21 11:21:28.260681: step: 1456/530, loss: 0.06895885616540909
2023-01-21 11:21:29.375470: step: 1460/530, loss: 0.0032720565795898438
2023-01-21 11:21:30.462014: step: 1464/530, loss: 0.0038191794883459806
2023-01-21 11:21:31.556473: step: 1468/530, loss: 0.00015020370483398438
2023-01-21 11:21:32.658074: step: 1472/530, loss: 0.007961606606841087
2023-01-21 11:21:33.773338: step: 1476/530, loss: 0.0033529282081872225
2023-01-21 11:21:34.902754: step: 1480/530, loss: 0.00021104812913108617
2023-01-21 11:21:35.988374: step: 1484/530, loss: 0.0024018287658691406
2023-01-21 11:21:37.099598: step: 1488/530, loss: 0.011574173346161842
2023-01-21 11:21:38.252355: step: 1492/530, loss: 0.0013336181873455644
2023-01-21 11:21:39.340489: step: 1496/530, loss: 0.0016519785858690739
2023-01-21 11:21:40.431522: step: 1500/530, loss: 0.008941650390625
2023-01-21 11:21:41.539932: step: 1504/530, loss: 0.01779651641845703
2023-01-21 11:21:42.639080: step: 1508/530, loss: 0.039354514330625534
2023-01-21 11:21:43.738753: step: 1512/530, loss: 0.05947704240679741
2023-01-21 11:21:44.852909: step: 1516/530, loss: 0.047955796122550964
2023-01-21 11:21:46.009189: step: 1520/530, loss: 0.011865329928696156
2023-01-21 11:21:47.125520: step: 1524/530, loss: 0.006604385562241077
2023-01-21 11:21:48.249388: step: 1528/530, loss: 0.004587078001350164
2023-01-21 11:21:49.385290: step: 1532/530, loss: 0.004681682679802179
2023-01-21 11:21:50.513236: step: 1536/530, loss: 0.055883027613162994
2023-01-21 11:21:51.627557: step: 1540/530, loss: 0.004079401958733797
2023-01-21 11:21:52.747433: step: 1544/530, loss: 0.03232517093420029
2023-01-21 11:21:53.899067: step: 1548/530, loss: 0.011879158206284046
2023-01-21 11:21:55.006284: step: 1552/530, loss: 0.015729952603578568
2023-01-21 11:21:56.101281: step: 1556/530, loss: 0.008579254150390625
2023-01-21 11:21:57.205547: step: 1560/530, loss: 0.0006083488697186112
2023-01-21 11:21:58.343264: step: 1564/530, loss: 0.03473472595214844
2023-01-21 11:21:59.460777: step: 1568/530, loss: 0.0174452792853117
2023-01-21 11:22:00.557453: step: 1572/530, loss: 0.007180976681411266
2023-01-21 11:22:01.676716: step: 1576/530, loss: 0.0038840770721435547
2023-01-21 11:22:02.786018: step: 1580/530, loss: 0.32468509674072266
2023-01-21 11:22:03.935503: step: 1584/530, loss: 0.0002134323149221018
2023-01-21 11:22:05.046370: step: 1588/530, loss: 0.0013719559647142887
2023-01-21 11:22:06.145830: step: 1592/530, loss: 0.029858112335205078
2023-01-21 11:22:07.263152: step: 1596/530, loss: 0.0034971237182617188
2023-01-21 11:22:08.377466: step: 1600/530, loss: 0.005486297886818647
2023-01-21 11:22:09.533893: step: 1604/530, loss: 0.02865924872457981
2023-01-21 11:22:10.643766: step: 1608/530, loss: 0.024501444771885872
2023-01-21 11:22:11.768088: step: 1612/530, loss: 0.08277097344398499
2023-01-21 11:22:12.878713: step: 1616/530, loss: 0.04843711853027344
2023-01-21 11:22:13.977270: step: 1620/530, loss: 0.019440174102783203
2023-01-21 11:22:15.080011: step: 1624/530, loss: 0.003404855728149414
2023-01-21 11:22:16.243652: step: 1628/530, loss: 0.012141036801040173
2023-01-21 11:22:17.382725: step: 1632/530, loss: 0.02066192589700222
2023-01-21 11:22:18.527819: step: 1636/530, loss: 0.032501984387636185
2023-01-21 11:22:19.633527: step: 1640/530, loss: 0.0032460689544677734
2023-01-21 11:22:20.758216: step: 1644/530, loss: 0.0456174835562706
2023-01-21 11:22:21.863135: step: 1648/530, loss: 0.0013841629261150956
2023-01-21 11:22:22.992608: step: 1652/530, loss: 0.02473926544189453
2023-01-21 11:22:24.130884: step: 1656/530, loss: 0.02271904982626438
2023-01-21 11:22:25.266005: step: 1660/530, loss: 0.00816803053021431
2023-01-21 11:22:26.372079: step: 1664/530, loss: 0.002902221865952015
2023-01-21 11:22:27.492682: step: 1668/530, loss: 0.031546879559755325
2023-01-21 11:22:28.610303: step: 1672/530, loss: 0.005530166905373335
2023-01-21 11:22:29.707698: step: 1676/530, loss: 0.017757035791873932
2023-01-21 11:22:30.791521: step: 1680/530, loss: 0.0009286880376748741
2023-01-21 11:22:31.877995: step: 1684/530, loss: 0.009922122582793236
2023-01-21 11:22:32.994324: step: 1688/530, loss: 0.014352631755173206
2023-01-21 11:22:34.083290: step: 1692/530, loss: 0.016274547204375267
2023-01-21 11:22:35.172214: step: 1696/530, loss: 0.012370157055556774
2023-01-21 11:22:36.276357: step: 1700/530, loss: 0.00052642822265625
2023-01-21 11:22:37.401497: step: 1704/530, loss: 0.06131858751177788
2023-01-21 11:22:38.503836: step: 1708/530, loss: 0.030119895935058594
2023-01-21 11:22:39.596873: step: 1712/530, loss: 0.011890602298080921
2023-01-21 11:22:40.692526: step: 1716/530, loss: 0.019771575927734375
2023-01-21 11:22:41.795761: step: 1720/530, loss: 0.08073930442333221
2023-01-21 11:22:42.927270: step: 1724/530, loss: 0.0028011694084852934
2023-01-21 11:22:44.031750: step: 1728/530, loss: 0.07083974033594131
2023-01-21 11:22:45.151240: step: 1732/530, loss: 0.027170753106474876
2023-01-21 11:22:46.272818: step: 1736/530, loss: 0.03600182756781578
2023-01-21 11:22:47.377296: step: 1740/530, loss: 1.2782566547393799
2023-01-21 11:22:48.482311: step: 1744/530, loss: 0.02714400365948677
2023-01-21 11:22:49.593906: step: 1748/530, loss: 0.007042550947517157
2023-01-21 11:22:50.717670: step: 1752/530, loss: 0.0006359577528201044
2023-01-21 11:22:51.802997: step: 1756/530, loss: 0.00020213128300383687
2023-01-21 11:22:52.939686: step: 1760/530, loss: 0.010347938165068626
2023-01-21 11:22:54.012976: step: 1764/530, loss: 0.02387523651123047
2023-01-21 11:22:55.119147: step: 1768/530, loss: 0.01089630089700222
2023-01-21 11:22:56.231960: step: 1772/530, loss: 0.07758770138025284
2023-01-21 11:22:57.411777: step: 1776/530, loss: 0.02532673068344593
2023-01-21 11:22:58.514452: step: 1780/530, loss: 0.002962446305900812
2023-01-21 11:22:59.587428: step: 1784/530, loss: 0.6591671705245972
2023-01-21 11:23:00.722512: step: 1788/530, loss: 0.034917399287223816
2023-01-21 11:23:01.871439: step: 1792/530, loss: 0.0007560729864053428
2023-01-21 11:23:02.989433: step: 1796/530, loss: 0.12798985838890076
2023-01-21 11:23:04.091269: step: 1800/530, loss: 0.006716489791870117
2023-01-21 11:23:05.186097: step: 1804/530, loss: 0.05302458256483078
2023-01-21 11:23:06.314499: step: 1808/530, loss: 0.005708026699721813
2023-01-21 11:23:07.419565: step: 1812/530, loss: 0.014288521371781826
2023-01-21 11:23:08.515522: step: 1816/530, loss: 0.001903533935546875
2023-01-21 11:23:09.618622: step: 1820/530, loss: 0.36050042510032654
2023-01-21 11:23:10.702776: step: 1824/530, loss: 0.005066824145615101
2023-01-21 11:23:11.806931: step: 1828/530, loss: 0.10884599387645721
2023-01-21 11:23:12.929093: step: 1832/530, loss: 0.0005013465997762978
2023-01-21 11:23:14.050778: step: 1836/530, loss: 0.04595642164349556
2023-01-21 11:23:15.204839: step: 1840/530, loss: 0.049460601061582565
2023-01-21 11:23:16.322088: step: 1844/530, loss: 0.02969665639102459
2023-01-21 11:23:17.511002: step: 1848/530, loss: 0.049024634063243866
2023-01-21 11:23:18.630689: step: 1852/530, loss: 0.04389185085892677
2023-01-21 11:23:19.751010: step: 1856/530, loss: 0.0017632603412494063
2023-01-21 11:23:20.861607: step: 1860/530, loss: 0.011154556646943092
2023-01-21 11:23:21.964726: step: 1864/530, loss: 0.054690077900886536
2023-01-21 11:23:23.076949: step: 1868/530, loss: 0.0006351470947265625
2023-01-21 11:23:24.186196: step: 1872/530, loss: 0.02438100054860115
2023-01-21 11:23:25.321611: step: 1876/530, loss: 0.00036525726318359375
2023-01-21 11:23:26.481083: step: 1880/530, loss: 0.047116659581661224
2023-01-21 11:23:27.591109: step: 1884/530, loss: 0.017323588952422142
2023-01-21 11:23:28.754060: step: 1888/530, loss: 0.005760383792221546
2023-01-21 11:23:29.858453: step: 1892/530, loss: 0.006068515591323376
2023-01-21 11:23:30.959750: step: 1896/530, loss: 0.012779808603227139
2023-01-21 11:23:32.046905: step: 1900/530, loss: 0.028653431683778763
2023-01-21 11:23:33.156404: step: 1904/530, loss: 0.025748729705810547
2023-01-21 11:23:34.245628: step: 1908/530, loss: 0.001165974186733365
2023-01-21 11:23:35.334901: step: 1912/530, loss: 0.09264449775218964
2023-01-21 11:23:36.456150: step: 1916/530, loss: 0.030138254165649414
2023-01-21 11:23:37.571809: step: 1920/530, loss: 0.08005218952894211
2023-01-21 11:23:38.642890: step: 1924/530, loss: 0.0014788627158850431
2023-01-21 11:23:39.755482: step: 1928/530, loss: 0.03776111826300621
2023-01-21 11:23:40.866603: step: 1932/530, loss: 0.0024306774139404297
2023-01-21 11:23:41.998234: step: 1936/530, loss: 0.0034062385093420744
2023-01-21 11:23:43.083505: step: 1940/530, loss: 0.04630127176642418
2023-01-21 11:23:44.218926: step: 1944/530, loss: 0.00444340705871582
2023-01-21 11:23:45.336744: step: 1948/530, loss: 0.016202669590711594
2023-01-21 11:23:46.453235: step: 1952/530, loss: 0.044142868369817734
2023-01-21 11:23:47.579400: step: 1956/530, loss: 0.032686758786439896
2023-01-21 11:23:48.691249: step: 1960/530, loss: 0.005498790647834539
2023-01-21 11:23:49.794667: step: 1964/530, loss: 0.0027975437697023153
2023-01-21 11:23:50.920156: step: 1968/530, loss: 0.009188652038574219
2023-01-21 11:23:52.014693: step: 1972/530, loss: 0.011859416961669922
2023-01-21 11:23:53.141075: step: 1976/530, loss: 0.20896291732788086
2023-01-21 11:23:54.279870: step: 1980/530, loss: 0.030010033398866653
2023-01-21 11:23:55.388822: step: 1984/530, loss: 0.07112963497638702
2023-01-21 11:23:56.485911: step: 1988/530, loss: 0.06819553673267365
2023-01-21 11:23:57.589099: step: 1992/530, loss: 0.0008634566911496222
2023-01-21 11:23:58.724413: step: 1996/530, loss: 0.027050208300352097
2023-01-21 11:23:59.832015: step: 2000/530, loss: 0.009219515137374401
2023-01-21 11:24:00.938218: step: 2004/530, loss: 4.3201445805607364e-05
2023-01-21 11:24:02.096086: step: 2008/530, loss: 0.03811082988977432
2023-01-21 11:24:03.213310: step: 2012/530, loss: 0.030016329139471054
2023-01-21 11:24:04.347473: step: 2016/530, loss: 0.0031457901932299137
2023-01-21 11:24:05.457086: step: 2020/530, loss: 0.0024652481079101562
2023-01-21 11:24:06.553618: step: 2024/530, loss: 0.03889341279864311
2023-01-21 11:24:07.683362: step: 2028/530, loss: 0.0028830289375036955
2023-01-21 11:24:08.800858: step: 2032/530, loss: 0.005615234375
2023-01-21 11:24:09.911140: step: 2036/530, loss: 0.0007209301693364978
2023-01-21 11:24:11.042150: step: 2040/530, loss: 0.03858451917767525
2023-01-21 11:24:12.142664: step: 2044/530, loss: 0.0026111602783203125
2023-01-21 11:24:13.261687: step: 2048/530, loss: 0.03425021097064018
2023-01-21 11:24:14.383689: step: 2052/530, loss: 0.03392324596643448
2023-01-21 11:24:15.473081: step: 2056/530, loss: 0.026357173919677734
2023-01-21 11:24:16.600825: step: 2060/530, loss: 0.0012678145430982113
2023-01-21 11:24:17.693566: step: 2064/530, loss: 0.003803253173828125
2023-01-21 11:24:18.805126: step: 2068/530, loss: 0.06784587353467941
2023-01-21 11:24:19.900699: step: 2072/530, loss: 0.0005203246837481856
2023-01-21 11:24:21.021293: step: 2076/530, loss: 0.0056588174775242805
2023-01-21 11:24:22.133638: step: 2080/530, loss: 0.05423889309167862
2023-01-21 11:24:23.264495: step: 2084/530, loss: 0.01734619215130806
2023-01-21 11:24:24.351577: step: 2088/530, loss: 0.0034699440002441406
2023-01-21 11:24:25.458034: step: 2092/530, loss: 0.09937791526317596
2023-01-21 11:24:26.592665: step: 2096/530, loss: 0.004464149475097656
2023-01-21 11:24:27.697606: step: 2100/530, loss: 0.008090019226074219
2023-01-21 11:24:28.792449: step: 2104/530, loss: 0.004296112339943647
2023-01-21 11:24:29.936224: step: 2108/530, loss: 0.007798671722412109
2023-01-21 11:24:31.025508: step: 2112/530, loss: 0.004139900207519531
2023-01-21 11:24:32.138410: step: 2116/530, loss: 0.027470208704471588
2023-01-21 11:24:33.246978: step: 2120/530, loss: 0.002394723938778043
==================================================
Loss: 0.032
--------------------
Dev: {'event': {'p': 0.6097297297297297, 'r': 0.7509986684420772, 'f1': 0.6730310262529833}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Test: {'event': {'p': 0.6394052044609665, 'r': 0.8018648018648019, 'f1': 0.7114788004136504}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Chinese: {'event': {'p': 0.6428571428571429, 'r': 0.8333333333333334, 'f1': 0.7258064516129034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Korean: {'event': {'p': 0.6792452830188679, 'r': 0.5714285714285714, 'f1': 0.6206896551724137}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Russian: {'event': {'p': 0.4166666666666667, 'r': 0.4166666666666667, 'f1': 0.4166666666666667}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 11:25:14.907492: step: 4/530, loss: 0.0014448165893554688
2023-01-21 11:25:16.021975: step: 8/530, loss: 0.010218429379165173
2023-01-21 11:25:17.160247: step: 12/530, loss: 0.07780561596155167
2023-01-21 11:25:18.322611: step: 16/530, loss: 0.7697376012802124
2023-01-21 11:25:19.431622: step: 20/530, loss: 0.026992131024599075
2023-01-21 11:25:20.554018: step: 24/530, loss: 0.005077171139419079
2023-01-21 11:25:21.657721: step: 28/530, loss: 0.0009737968211993575
2023-01-21 11:25:22.763600: step: 32/530, loss: 0.003857135772705078
2023-01-21 11:25:23.859101: step: 36/530, loss: 0.00013504027447197586
2023-01-21 11:25:24.965702: step: 40/530, loss: 0.005188846495002508
2023-01-21 11:25:26.101628: step: 44/530, loss: 0.0016004563076421618
2023-01-21 11:25:27.190453: step: 48/530, loss: 0.0042930603958666325
2023-01-21 11:25:28.289246: step: 52/530, loss: 0.010409165173768997
2023-01-21 11:25:29.410662: step: 56/530, loss: 0.057645462453365326
2023-01-21 11:25:30.515336: step: 60/530, loss: 0.02639141120016575
2023-01-21 11:25:31.657326: step: 64/530, loss: 0.000263023393927142
2023-01-21 11:25:32.769674: step: 68/530, loss: 0.002488470170646906
2023-01-21 11:25:33.900694: step: 72/530, loss: 0.004537153523415327
2023-01-21 11:25:35.002244: step: 76/530, loss: 0.0009065628401003778
2023-01-21 11:25:36.111181: step: 80/530, loss: 0.001922607421875
2023-01-21 11:25:37.217042: step: 84/530, loss: 0.0006616592290811241
2023-01-21 11:25:38.321409: step: 88/530, loss: 0.0059552667662501335
2023-01-21 11:25:39.438638: step: 92/530, loss: 0.0014220238663256168
2023-01-21 11:25:40.566104: step: 96/530, loss: 0.003830528352409601
2023-01-21 11:25:41.658870: step: 100/530, loss: 0.006626129150390625
2023-01-21 11:25:42.789255: step: 104/530, loss: 0.0006578445318154991
2023-01-21 11:25:43.877666: step: 108/530, loss: 0.6272986531257629
2023-01-21 11:25:44.968470: step: 112/530, loss: 0.0014255524147301912
2023-01-21 11:25:46.081877: step: 116/530, loss: 0.010433768853545189
2023-01-21 11:25:47.179482: step: 120/530, loss: 0.02750416100025177
2023-01-21 11:25:48.280069: step: 124/530, loss: 0.018428804352879524
2023-01-21 11:25:49.399279: step: 128/530, loss: 0.1627538651227951
2023-01-21 11:25:50.512090: step: 132/530, loss: 0.0002609252987895161
2023-01-21 11:25:51.620715: step: 136/530, loss: 0.049125757068395615
2023-01-21 11:25:52.692266: step: 140/530, loss: 0.0004446029488462955
2023-01-21 11:25:53.832371: step: 144/530, loss: 0.19546298682689667
2023-01-21 11:25:54.946014: step: 148/530, loss: 0.025575732812285423
2023-01-21 11:25:56.063120: step: 152/530, loss: 0.0008000374073162675
2023-01-21 11:25:57.221992: step: 156/530, loss: 0.012858295813202858
2023-01-21 11:25:58.316233: step: 160/530, loss: 0.015578222461044788
2023-01-21 11:25:59.414792: step: 164/530, loss: 0.05391797795891762
2023-01-21 11:26:00.524043: step: 168/530, loss: 0.0004455566231627017
2023-01-21 11:26:01.624267: step: 172/530, loss: 0.01202402077615261
2023-01-21 11:26:02.745309: step: 176/530, loss: 0.001851940294727683
2023-01-21 11:26:03.859902: step: 180/530, loss: 0.040908049792051315
2023-01-21 11:26:04.981054: step: 184/530, loss: 0.003222560975700617
2023-01-21 11:26:06.088909: step: 188/530, loss: 0.007326317019760609
2023-01-21 11:26:07.200013: step: 192/530, loss: 0.016690731048583984
2023-01-21 11:26:08.305924: step: 196/530, loss: 0.01824788935482502
2023-01-21 11:26:09.460365: step: 200/530, loss: 0.003951549530029297
2023-01-21 11:26:10.558664: step: 204/530, loss: 0.10313473641872406
2023-01-21 11:26:11.628347: step: 208/530, loss: 0.0009653091547079384
2023-01-21 11:26:12.734036: step: 212/530, loss: 0.004527473356574774
2023-01-21 11:26:13.810612: step: 216/530, loss: 0.006493187043815851
2023-01-21 11:26:14.893475: step: 220/530, loss: 0.005120372865349054
2023-01-21 11:26:16.024954: step: 224/530, loss: 0.009389781393110752
2023-01-21 11:26:17.157129: step: 228/530, loss: 0.11678294837474823
2023-01-21 11:26:18.256982: step: 232/530, loss: 0.01537313498556614
2023-01-21 11:26:19.410076: step: 236/530, loss: 0.001144027803093195
2023-01-21 11:26:20.528792: step: 240/530, loss: 0.006143069360405207
2023-01-21 11:26:21.630056: step: 244/530, loss: 0.0010856628650799394
2023-01-21 11:26:22.816108: step: 248/530, loss: 0.07156830281019211
2023-01-21 11:26:23.884949: step: 252/530, loss: 0.002552032470703125
2023-01-21 11:26:24.991495: step: 256/530, loss: 0.49163171648979187
2023-01-21 11:26:26.104657: step: 260/530, loss: 0.002796077635139227
2023-01-21 11:26:27.211334: step: 264/530, loss: 0.06929449737071991
2023-01-21 11:26:28.304370: step: 268/530, loss: 0.014154244214296341
2023-01-21 11:26:29.404884: step: 272/530, loss: 0.0005712032434530556
2023-01-21 11:26:30.507591: step: 276/530, loss: 0.018225956708192825
2023-01-21 11:26:31.633012: step: 280/530, loss: 0.08001823723316193
2023-01-21 11:26:32.723356: step: 284/530, loss: 0.007810402195900679
2023-01-21 11:26:33.868707: step: 288/530, loss: 0.033522892743349075
2023-01-21 11:26:34.979015: step: 292/530, loss: 0.0025755881797522306
2023-01-21 11:26:36.083679: step: 296/530, loss: 0.032387733459472656
2023-01-21 11:26:37.242094: step: 300/530, loss: 0.04019508138298988
2023-01-21 11:26:38.337749: step: 304/530, loss: 6.67572021484375e-05
2023-01-21 11:26:39.435475: step: 308/530, loss: 0.00018591881962493062
2023-01-21 11:26:40.532897: step: 312/530, loss: 0.0056649683974683285
2023-01-21 11:26:41.694196: step: 316/530, loss: 0.000644302403088659
2023-01-21 11:26:42.817055: step: 320/530, loss: 0.060369398444890976
2023-01-21 11:26:43.933133: step: 324/530, loss: 0.02066974714398384
2023-01-21 11:26:45.034102: step: 328/530, loss: 0.029868222773075104
2023-01-21 11:26:46.141177: step: 332/530, loss: 0.010073757730424404
2023-01-21 11:26:47.264028: step: 336/530, loss: 0.015745854005217552
2023-01-21 11:26:48.355967: step: 340/530, loss: 0.05678978189826012
2023-01-21 11:26:49.476984: step: 344/530, loss: 0.04481000825762749
2023-01-21 11:26:50.599307: step: 348/530, loss: 0.0015425682067871094
2023-01-21 11:26:51.716195: step: 352/530, loss: 0.0005639076698571444
2023-01-21 11:26:52.814370: step: 356/530, loss: 0.0049591064453125
2023-01-21 11:26:53.960463: step: 360/530, loss: 0.002276897430419922
2023-01-21 11:26:55.073523: step: 364/530, loss: 0.009274577721953392
2023-01-21 11:26:56.180759: step: 368/530, loss: 0.014779853634536266
2023-01-21 11:26:57.294968: step: 372/530, loss: 0.013894558884203434
2023-01-21 11:26:58.441271: step: 376/530, loss: 0.0003088951052632183
2023-01-21 11:26:59.573727: step: 380/530, loss: 0.034830473363399506
2023-01-21 11:27:00.654271: step: 384/530, loss: 0.0005460739484988153
2023-01-21 11:27:01.758637: step: 388/530, loss: 0.025982379913330078
2023-01-21 11:27:02.843797: step: 392/530, loss: 0.005467033479362726
2023-01-21 11:27:03.940212: step: 396/530, loss: 0.003776168916374445
2023-01-21 11:27:05.065474: step: 400/530, loss: 0.045676421374082565
2023-01-21 11:27:06.163619: step: 404/530, loss: 0.0002334117889404297
2023-01-21 11:27:07.285472: step: 408/530, loss: 0.031914424151182175
2023-01-21 11:27:08.412045: step: 412/530, loss: 0.04085502773523331
2023-01-21 11:27:09.531094: step: 416/530, loss: 0.0005533219082280993
2023-01-21 11:27:10.655679: step: 420/530, loss: 0.0004146576102357358
2023-01-21 11:27:11.765243: step: 424/530, loss: 0.015208244323730469
2023-01-21 11:27:12.868300: step: 428/530, loss: 0.06183815374970436
2023-01-21 11:27:13.963441: step: 432/530, loss: 0.005413723178207874
2023-01-21 11:27:15.085008: step: 436/530, loss: 0.0002808094141073525
2023-01-21 11:27:16.184308: step: 440/530, loss: 0.001342392060905695
2023-01-21 11:27:17.313310: step: 444/530, loss: 0.0001523971586721018
2023-01-21 11:27:18.423496: step: 448/530, loss: 0.12129536271095276
2023-01-21 11:27:19.512954: step: 452/530, loss: 0.02196807973086834
2023-01-21 11:27:20.613178: step: 456/530, loss: 0.002911186311393976
2023-01-21 11:27:21.733900: step: 460/530, loss: 0.019698239862918854
2023-01-21 11:27:22.848427: step: 464/530, loss: 0.0006911277887411416
2023-01-21 11:27:23.955598: step: 468/530, loss: 0.0035709382500499487
2023-01-21 11:27:25.042642: step: 472/530, loss: 0.022966384887695312
2023-01-21 11:27:26.153671: step: 476/530, loss: 0.007455635350197554
2023-01-21 11:27:27.287574: step: 480/530, loss: 0.00420646695420146
2023-01-21 11:27:28.390924: step: 484/530, loss: 0.029030703008174896
2023-01-21 11:27:29.506440: step: 488/530, loss: 0.008334135636687279
2023-01-21 11:27:30.611559: step: 492/530, loss: 0.058210086077451706
2023-01-21 11:27:31.765235: step: 496/530, loss: 0.01308908499777317
2023-01-21 11:27:32.842135: step: 500/530, loss: 0.013102435506880283
2023-01-21 11:27:33.935597: step: 504/530, loss: 0.018065262585878372
2023-01-21 11:27:35.038115: step: 508/530, loss: 0.020305633544921875
2023-01-21 11:27:36.156528: step: 512/530, loss: 0.03859882056713104
2023-01-21 11:27:37.280748: step: 516/530, loss: 0.012969780713319778
2023-01-21 11:27:38.399888: step: 520/530, loss: 0.004222106654196978
2023-01-21 11:27:39.478791: step: 524/530, loss: 0.0008533478248864412
2023-01-21 11:27:40.560154: step: 528/530, loss: 0.00029535291832871735
2023-01-21 11:27:41.694982: step: 532/530, loss: 0.02418975904583931
2023-01-21 11:27:42.794419: step: 536/530, loss: 0.0007802486652508378
2023-01-21 11:27:43.896808: step: 540/530, loss: 0.07002153992652893
2023-01-21 11:27:45.029301: step: 544/530, loss: 0.00782232265919447
2023-01-21 11:27:46.121214: step: 548/530, loss: 0.026316644623875618
2023-01-21 11:27:47.231495: step: 552/530, loss: 0.08285784721374512
2023-01-21 11:27:48.339619: step: 556/530, loss: 0.13837261497974396
2023-01-21 11:27:49.444184: step: 560/530, loss: 0.0020817758049815893
2023-01-21 11:27:50.571278: step: 564/530, loss: 0.00945348758250475
2023-01-21 11:27:51.704863: step: 568/530, loss: 0.0014045715797692537
2023-01-21 11:27:52.795662: step: 572/530, loss: 0.049512770026922226
2023-01-21 11:27:53.895620: step: 576/530, loss: 0.016512585803866386
2023-01-21 11:27:55.028112: step: 580/530, loss: 0.0007040023920126259
2023-01-21 11:27:56.178454: step: 584/530, loss: 0.014866066165268421
2023-01-21 11:27:57.302791: step: 588/530, loss: 0.015486050397157669
2023-01-21 11:27:58.375470: step: 592/530, loss: 0.026675604283809662
2023-01-21 11:27:59.446952: step: 596/530, loss: 0.4199257791042328
2023-01-21 11:28:00.542169: step: 600/530, loss: 0.005817413330078125
2023-01-21 11:28:01.625744: step: 604/530, loss: 0.00019946099200751632
2023-01-21 11:28:02.723242: step: 608/530, loss: 0.04819921776652336
2023-01-21 11:28:03.843405: step: 612/530, loss: 0.04078993573784828
2023-01-21 11:28:04.961119: step: 616/530, loss: 0.07472534477710724
2023-01-21 11:28:06.093400: step: 620/530, loss: 5.755424717790447e-05
2023-01-21 11:28:07.194812: step: 624/530, loss: 0.01546626165509224
2023-01-21 11:28:08.304969: step: 628/530, loss: 0.021909713745117188
2023-01-21 11:28:09.437338: step: 632/530, loss: 0.0010271072387695312
2023-01-21 11:28:10.533076: step: 636/530, loss: 0.004310893826186657
2023-01-21 11:28:11.639150: step: 640/530, loss: 0.0010842562187463045
2023-01-21 11:28:12.733798: step: 644/530, loss: 0.00028781889704987407
2023-01-21 11:28:13.837834: step: 648/530, loss: 0.00011148452904308215
2023-01-21 11:28:14.960149: step: 652/530, loss: 0.00046243667020462453
2023-01-21 11:28:16.092244: step: 656/530, loss: 0.011238956823945045
2023-01-21 11:28:17.174213: step: 660/530, loss: 0.003329467959702015
2023-01-21 11:28:18.309336: step: 664/530, loss: 0.0005368232959881425
2023-01-21 11:28:19.400472: step: 668/530, loss: 0.011597633361816406
2023-01-21 11:28:20.483573: step: 672/530, loss: 0.0012506007915362716
2023-01-21 11:28:21.607603: step: 676/530, loss: 0.06612415611743927
2023-01-21 11:28:22.700878: step: 680/530, loss: 0.05307193100452423
2023-01-21 11:28:23.799469: step: 684/530, loss: 0.04668540880084038
2023-01-21 11:28:24.910210: step: 688/530, loss: 0.04380912706255913
2023-01-21 11:28:26.015945: step: 692/530, loss: 0.017929984256625175
2023-01-21 11:28:27.127606: step: 696/530, loss: 0.006539058871567249
2023-01-21 11:28:28.235328: step: 700/530, loss: 0.0019691467750817537
2023-01-21 11:28:29.368530: step: 704/530, loss: 0.0007365703349933028
2023-01-21 11:28:30.485748: step: 708/530, loss: 0.010886765085160732
2023-01-21 11:28:31.577535: step: 712/530, loss: 0.03156595304608345
2023-01-21 11:28:32.681417: step: 716/530, loss: 0.029905986040830612
2023-01-21 11:28:33.774610: step: 720/530, loss: 0.002662849612534046
2023-01-21 11:28:34.912401: step: 724/530, loss: 0.024061013013124466
2023-01-21 11:28:36.029871: step: 728/530, loss: 0.004641151521354914
2023-01-21 11:28:37.118175: step: 732/530, loss: 0.006412720773369074
2023-01-21 11:28:38.212736: step: 736/530, loss: 0.06767654418945312
2023-01-21 11:28:39.291255: step: 740/530, loss: 0.019868278875947
2023-01-21 11:28:40.386843: step: 744/530, loss: 0.01916370540857315
2023-01-21 11:28:41.487955: step: 748/530, loss: 0.07350406795740128
2023-01-21 11:28:42.575415: step: 752/530, loss: 0.0066051483154296875
2023-01-21 11:28:43.679630: step: 756/530, loss: 0.1249973326921463
2023-01-21 11:28:44.777725: step: 760/530, loss: 0.03013324737548828
2023-01-21 11:28:45.890568: step: 764/530, loss: 0.00017642974853515625
2023-01-21 11:28:47.005860: step: 768/530, loss: 0.00016336441331077367
2023-01-21 11:28:48.120385: step: 772/530, loss: 0.01298151072114706
2023-01-21 11:28:49.206169: step: 776/530, loss: 0.024737929925322533
2023-01-21 11:28:50.330830: step: 780/530, loss: 0.00292549142614007
2023-01-21 11:28:51.450849: step: 784/530, loss: 7.390975952148438e-05
2023-01-21 11:28:52.553961: step: 788/530, loss: 0.0022426603827625513
2023-01-21 11:28:53.646918: step: 792/530, loss: 0.07834243774414062
2023-01-21 11:28:54.764987: step: 796/530, loss: 0.005349159240722656
2023-01-21 11:28:55.863684: step: 800/530, loss: 0.022838031873106956
2023-01-21 11:28:56.983090: step: 804/530, loss: 0.045226193964481354
2023-01-21 11:28:58.099465: step: 808/530, loss: 0.00441131554543972
2023-01-21 11:28:59.194923: step: 812/530, loss: 0.4004550874233246
2023-01-21 11:29:00.326937: step: 816/530, loss: 0.048462674021720886
2023-01-21 11:29:01.434475: step: 820/530, loss: 0.0003896713024005294
2023-01-21 11:29:02.555241: step: 824/530, loss: 0.002521391026675701
2023-01-21 11:29:03.686295: step: 828/530, loss: 0.04993181303143501
2023-01-21 11:29:04.806403: step: 832/530, loss: 0.006475258152931929
2023-01-21 11:29:05.913038: step: 836/530, loss: 0.0036249160766601562
2023-01-21 11:29:06.999755: step: 840/530, loss: 0.001237201620824635
2023-01-21 11:29:08.110218: step: 844/530, loss: 0.012454223819077015
2023-01-21 11:29:09.208698: step: 848/530, loss: 0.04208245128393173
2023-01-21 11:29:10.316346: step: 852/530, loss: 0.04520421102643013
2023-01-21 11:29:11.397569: step: 856/530, loss: 0.025693703442811966
2023-01-21 11:29:12.520402: step: 860/530, loss: 0.00781869888305664
2023-01-21 11:29:13.602440: step: 864/530, loss: 0.018005656078457832
2023-01-21 11:29:14.728452: step: 868/530, loss: 0.007506656926125288
2023-01-21 11:29:15.841638: step: 872/530, loss: 0.0045302389189600945
2023-01-21 11:29:16.969687: step: 876/530, loss: 0.006920624058693647
2023-01-21 11:29:18.083522: step: 880/530, loss: 0.0008099555852822959
2023-01-21 11:29:19.201943: step: 884/530, loss: 0.006557369604706764
2023-01-21 11:29:20.326364: step: 888/530, loss: 0.03865756839513779
2023-01-21 11:29:21.416716: step: 892/530, loss: 0.03716907650232315
2023-01-21 11:29:22.511802: step: 896/530, loss: 0.012309838086366653
2023-01-21 11:29:23.621277: step: 900/530, loss: 0.09240760654211044
2023-01-21 11:29:24.698000: step: 904/530, loss: 0.0033102035522460938
2023-01-21 11:29:25.786960: step: 908/530, loss: 0.0028446197975426912
2023-01-21 11:29:26.894909: step: 912/530, loss: 0.006618213839828968
2023-01-21 11:29:27.996060: step: 916/530, loss: 0.00742950476706028
2023-01-21 11:29:29.112593: step: 920/530, loss: 0.0037856101989746094
2023-01-21 11:29:30.211128: step: 924/530, loss: 0.33206939697265625
2023-01-21 11:29:31.345592: step: 928/530, loss: 0.01862478442490101
2023-01-21 11:29:32.477194: step: 932/530, loss: 0.018245648592710495
2023-01-21 11:29:33.550797: step: 936/530, loss: 0.005423545837402344
2023-01-21 11:29:34.631953: step: 940/530, loss: 0.0021450042258948088
2023-01-21 11:29:35.727577: step: 944/530, loss: 0.01322860736399889
2023-01-21 11:29:36.842596: step: 948/530, loss: 0.0042719366028904915
2023-01-21 11:29:37.938340: step: 952/530, loss: 0.008036327548325062
2023-01-21 11:29:39.037210: step: 956/530, loss: 0.001439094659872353
2023-01-21 11:29:40.146529: step: 960/530, loss: 0.004388093948364258
2023-01-21 11:29:41.271479: step: 964/530, loss: 0.002310418989509344
2023-01-21 11:29:42.369824: step: 968/530, loss: 0.05793743208050728
2023-01-21 11:29:43.503578: step: 972/530, loss: 0.016104554757475853
2023-01-21 11:29:44.595265: step: 976/530, loss: 0.0019298553233966231
2023-01-21 11:29:45.684486: step: 980/530, loss: 0.0005709647666662931
2023-01-21 11:29:46.765186: step: 984/530, loss: 0.013628673739731312
2023-01-21 11:29:47.874728: step: 988/530, loss: 0.0021984102204442024
2023-01-21 11:29:49.018798: step: 992/530, loss: 0.0018981933826580644
2023-01-21 11:29:50.168045: step: 996/530, loss: 0.0006200313218869269
2023-01-21 11:29:51.265876: step: 1000/530, loss: 0.0013141632080078125
2023-01-21 11:29:52.365650: step: 1004/530, loss: 0.0003028392675332725
2023-01-21 11:29:53.478697: step: 1008/530, loss: 0.0624542236328125
2023-01-21 11:29:54.609141: step: 1012/530, loss: 0.010038947686553001
2023-01-21 11:29:55.726043: step: 1016/530, loss: 0.00207347865216434
2023-01-21 11:29:56.831374: step: 1020/530, loss: 0.0008069038158282638
2023-01-21 11:29:57.980665: step: 1024/530, loss: 0.022597646340727806
2023-01-21 11:29:59.084117: step: 1028/530, loss: 0.01680469512939453
2023-01-21 11:30:00.195991: step: 1032/530, loss: 0.0006066322675906122
2023-01-21 11:30:01.332743: step: 1036/530, loss: 0.030229568481445312
2023-01-21 11:30:02.455159: step: 1040/530, loss: 0.006845283322036266
2023-01-21 11:30:03.564025: step: 1044/530, loss: 0.010268783196806908
2023-01-21 11:30:04.677383: step: 1048/530, loss: 0.06993541866540909
2023-01-21 11:30:05.777509: step: 1052/530, loss: 0.005876445677131414
2023-01-21 11:30:06.910103: step: 1056/530, loss: 0.010522461496293545
2023-01-21 11:30:08.031405: step: 1060/530, loss: 0.06326141208410263
2023-01-21 11:30:09.170250: step: 1064/530, loss: 0.00012912749662064016
2023-01-21 11:30:10.271646: step: 1068/530, loss: 0.00051965715829283
2023-01-21 11:30:11.373120: step: 1072/530, loss: 0.00010814666165970266
2023-01-21 11:30:12.466874: step: 1076/530, loss: 0.047141075134277344
2023-01-21 11:30:13.583106: step: 1080/530, loss: 0.015032959170639515
2023-01-21 11:30:14.688901: step: 1084/530, loss: 0.004160690121352673
2023-01-21 11:30:15.809733: step: 1088/530, loss: 0.015010643750429153
2023-01-21 11:30:16.922296: step: 1092/530, loss: 0.003953408915549517
2023-01-21 11:30:18.039637: step: 1096/530, loss: 0.007323170080780983
2023-01-21 11:30:19.154562: step: 1100/530, loss: 0.04953975975513458
2023-01-21 11:30:20.280178: step: 1104/530, loss: 0.008510207757353783
2023-01-21 11:30:21.385817: step: 1108/530, loss: 0.006116438191384077
2023-01-21 11:30:22.528957: step: 1112/530, loss: 0.05720578506588936
2023-01-21 11:30:23.629717: step: 1116/530, loss: 0.0023756027221679688
2023-01-21 11:30:24.770665: step: 1120/530, loss: 0.03934650495648384
2023-01-21 11:30:25.867155: step: 1124/530, loss: 0.052307795733213425
2023-01-21 11:30:27.002827: step: 1128/530, loss: 0.0009531974792480469
2023-01-21 11:30:28.116579: step: 1132/530, loss: 0.08214350044727325
2023-01-21 11:30:29.225657: step: 1136/530, loss: 0.012887381948530674
2023-01-21 11:30:30.328308: step: 1140/530, loss: 0.025521278381347656
2023-01-21 11:30:31.433699: step: 1144/530, loss: 0.013566065579652786
2023-01-21 11:30:32.553812: step: 1148/530, loss: 0.0010683536529541016
2023-01-21 11:30:33.687741: step: 1152/530, loss: 0.13899211585521698
2023-01-21 11:30:34.779757: step: 1156/530, loss: 0.018077468499541283
2023-01-21 11:30:35.904208: step: 1160/530, loss: 0.263627827167511
2023-01-21 11:30:37.011201: step: 1164/530, loss: 4.711151268566027e-05
2023-01-21 11:30:38.105312: step: 1168/530, loss: 0.0001961708185262978
2023-01-21 11:30:39.205657: step: 1172/530, loss: 0.0324854850769043
2023-01-21 11:30:40.328699: step: 1176/530, loss: 0.44663000106811523
2023-01-21 11:30:41.420071: step: 1180/530, loss: 0.00045080186100676656
2023-01-21 11:30:42.560752: step: 1184/530, loss: 0.015191745944321156
2023-01-21 11:30:43.674223: step: 1188/530, loss: 0.004278946202248335
2023-01-21 11:30:44.798278: step: 1192/530, loss: 0.001898098038509488
2023-01-21 11:30:45.911755: step: 1196/530, loss: 0.1506543606519699
2023-01-21 11:30:46.990070: step: 1200/530, loss: 0.002842593239620328
2023-01-21 11:30:48.091555: step: 1204/530, loss: 0.0010952949523925781
2023-01-21 11:30:49.213509: step: 1208/530, loss: 0.0014229774242267013
2023-01-21 11:30:50.323217: step: 1212/530, loss: 0.002802085829898715
2023-01-21 11:30:51.434111: step: 1216/530, loss: 0.001006698701530695
2023-01-21 11:30:52.528211: step: 1220/530, loss: 0.002110767411068082
2023-01-21 11:30:53.634797: step: 1224/530, loss: 0.00084686279296875
2023-01-21 11:30:54.757137: step: 1228/530, loss: 0.046021416783332825
2023-01-21 11:30:55.888803: step: 1232/530, loss: 0.011029434390366077
2023-01-21 11:30:56.992889: step: 1236/530, loss: 0.009351730346679688
2023-01-21 11:30:58.115738: step: 1240/530, loss: 0.09081153571605682
2023-01-21 11:30:59.207454: step: 1244/530, loss: 0.0023753151763230562
2023-01-21 11:31:00.302838: step: 1248/530, loss: 0.005281639285385609
2023-01-21 11:31:01.408648: step: 1252/530, loss: 0.03441214561462402
2023-01-21 11:31:02.515964: step: 1256/530, loss: 0.018236350268125534
2023-01-21 11:31:03.651926: step: 1260/530, loss: 0.016182422637939453
2023-01-21 11:31:04.767678: step: 1264/530, loss: 0.03475761413574219
2023-01-21 11:31:05.813720: step: 1268/530, loss: 0.015668869018554688
2023-01-21 11:31:06.887431: step: 1272/530, loss: 0.0037629129365086555
2023-01-21 11:31:08.007180: step: 1276/530, loss: 0.013821984641253948
2023-01-21 11:31:09.136567: step: 1280/530, loss: 0.008289003744721413
2023-01-21 11:31:10.234643: step: 1284/530, loss: 0.010158920660614967
2023-01-21 11:31:11.395876: step: 1288/530, loss: 0.06707501411437988
2023-01-21 11:31:12.513339: step: 1292/530, loss: 0.016602326184511185
2023-01-21 11:31:13.587696: step: 1296/530, loss: 0.0032186508178710938
2023-01-21 11:31:14.711015: step: 1300/530, loss: 0.0208711139857769
2023-01-21 11:31:15.837279: step: 1304/530, loss: 0.0171751007437706
2023-01-21 11:31:16.937765: step: 1308/530, loss: 0.0004302978632040322
2023-01-21 11:31:18.064896: step: 1312/530, loss: 0.007154989521950483
2023-01-21 11:31:19.153102: step: 1316/530, loss: 0.0006483078468590975
2023-01-21 11:31:20.274530: step: 1320/530, loss: 0.0193968303501606
2023-01-21 11:31:21.365627: step: 1324/530, loss: 0.002743244171142578
2023-01-21 11:31:22.505898: step: 1328/530, loss: 0.055486202239990234
2023-01-21 11:31:23.638450: step: 1332/530, loss: 3.814696901827119e-05
2023-01-21 11:31:24.767492: step: 1336/530, loss: 0.002487754914909601
2023-01-21 11:31:25.860956: step: 1340/530, loss: 0.06938514858484268
2023-01-21 11:31:26.950696: step: 1344/530, loss: 0.006404876708984375
2023-01-21 11:31:28.066337: step: 1348/530, loss: 0.0020507811568677425
2023-01-21 11:31:29.165539: step: 1352/530, loss: 6.337166269076988e-05
2023-01-21 11:31:30.273979: step: 1356/530, loss: 0.011004543863236904
2023-01-21 11:31:31.402774: step: 1360/530, loss: 0.011021668091416359
2023-01-21 11:31:32.568685: step: 1364/530, loss: 0.00020847321138717234
2023-01-21 11:31:33.699115: step: 1368/530, loss: 0.01799039915204048
2023-01-21 11:31:34.807847: step: 1372/530, loss: 0.009519101120531559
2023-01-21 11:31:35.902831: step: 1376/530, loss: 0.0018707275157794356
2023-01-21 11:31:37.037941: step: 1380/530, loss: 0.004285669419914484
2023-01-21 11:31:38.144639: step: 1384/530, loss: 0.01641540601849556
2023-01-21 11:31:39.264904: step: 1388/530, loss: 0.02902202680706978
2023-01-21 11:31:40.365461: step: 1392/530, loss: 0.06374301761388779
2023-01-21 11:31:41.466896: step: 1396/530, loss: 0.02755141258239746
2023-01-21 11:31:42.576188: step: 1400/530, loss: 0.04143853113055229
2023-01-21 11:31:43.730277: step: 1404/530, loss: 0.008482742123305798
2023-01-21 11:31:44.845712: step: 1408/530, loss: 0.01750326156616211
2023-01-21 11:31:46.016210: step: 1412/530, loss: 0.005590343382209539
2023-01-21 11:31:47.138576: step: 1416/530, loss: 0.01011571940034628
2023-01-21 11:31:48.293376: step: 1420/530, loss: 0.04805183783173561
2023-01-21 11:31:49.447945: step: 1424/530, loss: 0.03670348972082138
2023-01-21 11:31:50.556914: step: 1428/530, loss: 0.0006895065307617188
2023-01-21 11:31:51.683389: step: 1432/530, loss: 0.009813213720917702
2023-01-21 11:31:52.793968: step: 1436/530, loss: 0.09463150799274445
2023-01-21 11:31:53.917717: step: 1440/530, loss: 0.0005071639898233116
2023-01-21 11:31:55.013969: step: 1444/530, loss: 0.012918567284941673
2023-01-21 11:31:56.113712: step: 1448/530, loss: 0.0014408588176593184
2023-01-21 11:31:57.236519: step: 1452/530, loss: 0.05398865044116974
2023-01-21 11:31:58.361942: step: 1456/530, loss: 0.0016940117347985506
2023-01-21 11:31:59.462900: step: 1460/530, loss: 0.00015649796114303172
2023-01-21 11:32:00.546936: step: 1464/530, loss: 0.04098358377814293
2023-01-21 11:32:01.666497: step: 1468/530, loss: 0.08411483466625214
2023-01-21 11:32:02.770610: step: 1472/530, loss: 0.01969590224325657
2023-01-21 11:32:03.880377: step: 1476/530, loss: 0.023730851709842682
2023-01-21 11:32:04.985945: step: 1480/530, loss: 1.133135437965393
2023-01-21 11:32:06.097842: step: 1484/530, loss: 0.005062961485236883
2023-01-21 11:32:07.229687: step: 1488/530, loss: 0.03160534054040909
2023-01-21 11:32:08.346157: step: 1492/530, loss: 0.0005936622619628906
2023-01-21 11:32:09.443063: step: 1496/530, loss: 0.0010514259338378906
2023-01-21 11:32:10.557770: step: 1500/530, loss: 0.019589615985751152
2023-01-21 11:32:11.641715: step: 1504/530, loss: 0.03720245137810707
2023-01-21 11:32:12.741520: step: 1508/530, loss: 0.004843330476433039
2023-01-21 11:32:13.883222: step: 1512/530, loss: 0.010355734266340733
2023-01-21 11:32:14.988471: step: 1516/530, loss: 0.003432035678997636
2023-01-21 11:32:16.108666: step: 1520/530, loss: 0.0013755798572674394
2023-01-21 11:32:17.204286: step: 1524/530, loss: 0.0015692710876464844
2023-01-21 11:32:18.309384: step: 1528/530, loss: 0.0005036354414187372
2023-01-21 11:32:19.417229: step: 1532/530, loss: 0.009550381451845169
2023-01-21 11:32:20.515467: step: 1536/530, loss: 0.02171912230551243
2023-01-21 11:32:21.659134: step: 1540/530, loss: 0.008292770013213158
2023-01-21 11:32:22.787836: step: 1544/530, loss: 0.0006641388172283769
2023-01-21 11:32:23.859813: step: 1548/530, loss: 0.004772603511810303
2023-01-21 11:32:24.975644: step: 1552/530, loss: 0.06319675594568253
2023-01-21 11:32:26.072956: step: 1556/530, loss: 0.01020803488790989
2023-01-21 11:32:27.182784: step: 1560/530, loss: 0.03091888502240181
2023-01-21 11:32:28.285531: step: 1564/530, loss: 0.1375046670436859
2023-01-21 11:32:29.397864: step: 1568/530, loss: 0.1253339797258377
2023-01-21 11:32:30.520282: step: 1572/530, loss: 0.6169979572296143
2023-01-21 11:32:31.643923: step: 1576/530, loss: 0.00706715602427721
2023-01-21 11:32:32.751738: step: 1580/530, loss: 0.02337600104510784
2023-01-21 11:32:33.870545: step: 1584/530, loss: 0.0005942345014773309
2023-01-21 11:32:34.973545: step: 1588/530, loss: 0.0015623093349859118
2023-01-21 11:32:36.090045: step: 1592/530, loss: 0.004889869596809149
2023-01-21 11:32:37.197594: step: 1596/530, loss: 0.0002951383648905903
2023-01-21 11:32:38.318209: step: 1600/530, loss: 0.023521041497588158
2023-01-21 11:32:39.420785: step: 1604/530, loss: 0.002965402789413929
2023-01-21 11:32:40.509766: step: 1608/530, loss: 0.02208738401532173
2023-01-21 11:32:41.657195: step: 1612/530, loss: 0.0007821082836017013
2023-01-21 11:32:42.792905: step: 1616/530, loss: 0.026735972613096237
2023-01-21 11:32:43.922850: step: 1620/530, loss: 0.04595356062054634
2023-01-21 11:32:45.011762: step: 1624/530, loss: 0.01731548272073269
2023-01-21 11:32:46.140675: step: 1628/530, loss: 7.343292963923886e-06
2023-01-21 11:32:47.325029: step: 1632/530, loss: 0.05352676659822464
2023-01-21 11:32:48.472451: step: 1636/530, loss: 0.03643341362476349
2023-01-21 11:32:49.559255: step: 1640/530, loss: 0.0003656387561932206
2023-01-21 11:32:50.698381: step: 1644/530, loss: 0.0871182456612587
2023-01-21 11:32:51.813172: step: 1648/530, loss: 0.021767806261777878
2023-01-21 11:32:52.941818: step: 1652/530, loss: 0.1720612645149231
2023-01-21 11:32:54.061643: step: 1656/530, loss: 0.06254511326551437
2023-01-21 11:32:55.169295: step: 1660/530, loss: 0.01138153113424778
2023-01-21 11:32:56.279539: step: 1664/530, loss: 0.03359236940741539
2023-01-21 11:32:57.385633: step: 1668/530, loss: 0.001922559691593051
2023-01-21 11:32:58.470113: step: 1672/530, loss: 0.19638358056545258
2023-01-21 11:32:59.590213: step: 1676/530, loss: 0.0018589973915368319
2023-01-21 11:33:00.689512: step: 1680/530, loss: 0.007766914553940296
2023-01-21 11:33:01.812699: step: 1684/530, loss: 0.003131961915642023
2023-01-21 11:33:02.932893: step: 1688/530, loss: 0.001168537070043385
2023-01-21 11:33:04.029594: step: 1692/530, loss: 0.0058494568802416325
2023-01-21 11:33:05.153692: step: 1696/530, loss: 0.01965651474893093
2023-01-21 11:33:06.252937: step: 1700/530, loss: 0.0018943786853924394
2023-01-21 11:33:07.358914: step: 1704/530, loss: 0.12588845193386078
2023-01-21 11:33:08.487671: step: 1708/530, loss: 0.042249299585819244
2023-01-21 11:33:09.573240: step: 1712/530, loss: 0.003041601274162531
2023-01-21 11:33:10.696330: step: 1716/530, loss: 0.004197502508759499
2023-01-21 11:33:11.838360: step: 1720/530, loss: 0.12388534843921661
2023-01-21 11:33:12.921226: step: 1724/530, loss: 0.01287984848022461
2023-01-21 11:33:14.053343: step: 1728/530, loss: 0.04360847547650337
2023-01-21 11:33:15.194349: step: 1732/530, loss: 0.04967312887310982
2023-01-21 11:33:16.302069: step: 1736/530, loss: 0.0017263413174077868
2023-01-21 11:33:17.405588: step: 1740/530, loss: 0.0005640029557980597
2023-01-21 11:33:18.540562: step: 1744/530, loss: 0.05066833272576332
2023-01-21 11:33:19.695624: step: 1748/530, loss: 0.012136077508330345
2023-01-21 11:33:20.792563: step: 1752/530, loss: 0.007398128975182772
2023-01-21 11:33:21.905562: step: 1756/530, loss: 0.06604347378015518
2023-01-21 11:33:23.086346: step: 1760/530, loss: 0.07191848754882812
2023-01-21 11:33:24.199830: step: 1764/530, loss: 0.0009829520713537931
2023-01-21 11:33:25.304610: step: 1768/530, loss: 0.0003837585391011089
2023-01-21 11:33:26.412396: step: 1772/530, loss: 0.07267170399427414
2023-01-21 11:33:27.498458: step: 1776/530, loss: 0.04729194566607475
2023-01-21 11:33:28.577672: step: 1780/530, loss: 0.0005975246313028038
2023-01-21 11:33:29.686836: step: 1784/530, loss: 0.0007963180541992188
2023-01-21 11:33:30.800989: step: 1788/530, loss: 0.003995037171989679
2023-01-21 11:33:31.886972: step: 1792/530, loss: 0.0062049152329564095
2023-01-21 11:33:32.995248: step: 1796/530, loss: 0.0180877223610878
2023-01-21 11:33:34.094768: step: 1800/530, loss: 0.03542742878198624
2023-01-21 11:33:35.199736: step: 1804/530, loss: 0.007823467254638672
2023-01-21 11:33:36.329572: step: 1808/530, loss: 0.03264360502362251
2023-01-21 11:33:37.458172: step: 1812/530, loss: 0.032199956476688385
2023-01-21 11:33:38.564692: step: 1816/530, loss: 0.00252113351598382
2023-01-21 11:33:39.704439: step: 1820/530, loss: 0.010976314544677734
2023-01-21 11:33:40.773503: step: 1824/530, loss: 0.022455643862485886
2023-01-21 11:33:41.870505: step: 1828/530, loss: 0.0027786255814135075
2023-01-21 11:33:42.994443: step: 1832/530, loss: 0.14431552588939667
2023-01-21 11:33:44.095842: step: 1836/530, loss: 0.014445018954575062
2023-01-21 11:33:45.191832: step: 1840/530, loss: 0.04419555887579918
2023-01-21 11:33:46.324007: step: 1844/530, loss: 0.00693435687571764
2023-01-21 11:33:47.438910: step: 1848/530, loss: 0.008030891418457031
2023-01-21 11:33:48.528331: step: 1852/530, loss: 0.004249763675034046
2023-01-21 11:33:49.647495: step: 1856/530, loss: 0.05397143214941025
2023-01-21 11:33:50.749020: step: 1860/530, loss: 0.050740115344524384
2023-01-21 11:33:51.869190: step: 1864/530, loss: 0.008066559210419655
2023-01-21 11:33:52.960630: step: 1868/530, loss: 0.007135581690818071
2023-01-21 11:33:54.043018: step: 1872/530, loss: 0.01119381282478571
2023-01-21 11:33:55.163613: step: 1876/530, loss: 0.01633424684405327
2023-01-21 11:33:56.289301: step: 1880/530, loss: 0.001943397568538785
2023-01-21 11:33:57.397123: step: 1884/530, loss: 0.02282531186938286
2023-01-21 11:33:58.541642: step: 1888/530, loss: 0.002081585116684437
2023-01-21 11:33:59.670638: step: 1892/530, loss: 0.0017817497719079256
2023-01-21 11:34:00.749196: step: 1896/530, loss: 0.0016619681846350431
2023-01-21 11:34:01.832415: step: 1900/530, loss: 0.0036008835304528475
2023-01-21 11:34:02.980194: step: 1904/530, loss: 0.004469871520996094
2023-01-21 11:34:04.046981: step: 1908/530, loss: 0.0018893718952313066
2023-01-21 11:34:05.149940: step: 1912/530, loss: 0.00920410268008709
2023-01-21 11:34:06.269150: step: 1916/530, loss: 0.025570059195160866
2023-01-21 11:34:07.382186: step: 1920/530, loss: 0.022469710558652878
2023-01-21 11:34:08.507825: step: 1924/530, loss: 0.0013681412674486637
2023-01-21 11:34:09.657602: step: 1928/530, loss: 0.0003390312194824219
2023-01-21 11:34:10.747884: step: 1932/530, loss: 0.006837748922407627
2023-01-21 11:34:11.855641: step: 1936/530, loss: 0.01760253868997097
2023-01-21 11:34:12.979653: step: 1940/530, loss: 0.02842344157397747
2023-01-21 11:34:14.063258: step: 1944/530, loss: 0.004081821534782648
2023-01-21 11:34:15.184996: step: 1948/530, loss: 0.024408437311649323
2023-01-21 11:34:16.272615: step: 1952/530, loss: 0.0008460045210085809
2023-01-21 11:34:17.376883: step: 1956/530, loss: 0.0230820644646883
2023-01-21 11:34:18.501691: step: 1960/530, loss: 0.004494190216064453
2023-01-21 11:34:19.622529: step: 1964/530, loss: 0.01319127157330513
2023-01-21 11:34:20.739980: step: 1968/530, loss: 0.0295123104006052
2023-01-21 11:34:21.879927: step: 1972/530, loss: 0.03885011747479439
2023-01-21 11:34:23.015820: step: 1976/530, loss: 0.011473655700683594
2023-01-21 11:34:24.112722: step: 1980/530, loss: 0.013992500491440296
2023-01-21 11:34:25.233684: step: 1984/530, loss: 0.034926414489746094
2023-01-21 11:34:26.345378: step: 1988/530, loss: 0.006973314099013805
2023-01-21 11:34:27.419486: step: 1992/530, loss: 0.014472723007202148
2023-01-21 11:34:28.527043: step: 1996/530, loss: 0.04264340549707413
2023-01-21 11:34:29.630492: step: 2000/530, loss: 0.012286758050322533
2023-01-21 11:34:30.733909: step: 2004/530, loss: 0.011006737127900124
2023-01-21 11:34:31.844818: step: 2008/530, loss: 0.006806612014770508
2023-01-21 11:34:32.983704: step: 2012/530, loss: 0.0011075973743572831
2023-01-21 11:34:34.100332: step: 2016/530, loss: 0.00903930701315403
2023-01-21 11:34:35.219691: step: 2020/530, loss: 0.030427835881710052
2023-01-21 11:34:36.318147: step: 2024/530, loss: 0.016294801607728004
2023-01-21 11:34:37.448783: step: 2028/530, loss: 0.048102568835020065
2023-01-21 11:34:38.548958: step: 2032/530, loss: 0.026589298620820045
2023-01-21 11:34:39.663951: step: 2036/530, loss: 0.030198097229003906
2023-01-21 11:34:40.782192: step: 2040/530, loss: 0.0032948972657322884
2023-01-21 11:34:41.911622: step: 2044/530, loss: 0.005795955657958984
2023-01-21 11:34:43.006070: step: 2048/530, loss: 0.04451313242316246
2023-01-21 11:34:44.077296: step: 2052/530, loss: 0.024013806134462357
2023-01-21 11:34:45.185958: step: 2056/530, loss: 0.003892520209774375
2023-01-21 11:34:46.272611: step: 2060/530, loss: 0.015264512039721012
2023-01-21 11:34:47.398862: step: 2064/530, loss: 0.0035377503372728825
2023-01-21 11:34:48.540413: step: 2068/530, loss: 0.004120826721191406
2023-01-21 11:34:49.661067: step: 2072/530, loss: 0.03057260625064373
2023-01-21 11:34:50.779163: step: 2076/530, loss: 0.013895321637392044
2023-01-21 11:34:51.903535: step: 2080/530, loss: 0.03908119350671768
2023-01-21 11:34:52.998720: step: 2084/530, loss: 0.006292152684181929
2023-01-21 11:34:54.125268: step: 2088/530, loss: 0.030089663341641426
2023-01-21 11:34:55.260645: step: 2092/530, loss: 0.07492685317993164
2023-01-21 11:34:56.337128: step: 2096/530, loss: 0.08126763999462128
2023-01-21 11:34:57.450497: step: 2100/530, loss: 0.08265075832605362
2023-01-21 11:34:58.593616: step: 2104/530, loss: 0.03354005888104439
2023-01-21 11:34:59.690275: step: 2108/530, loss: 6.65664701955393e-05
2023-01-21 11:35:00.804548: step: 2112/530, loss: 0.014124584384262562
2023-01-21 11:35:01.931875: step: 2116/530, loss: 0.02004718966782093
2023-01-21 11:35:03.046936: step: 2120/530, loss: 0.0010485649108886719
==================================================
Loss: 0.031
--------------------
Dev: {'event': {'p': 0.6169527896995708, 'r': 0.7656458055925432, 'f1': 0.683303624480095}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Test: {'event': {'p': 0.6591454632741238, 'r': 0.8001165501165501, 'f1': 0.7228217952092656}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Chinese: {'event': {'p': 0.6493506493506493, 'r': 0.9259259259259259, 'f1': 0.7633587786259541}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
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': 17}
Russian: {'event': {'p': 0.47368421052631576, 'r': 0.5, 'f1': 0.4864864864864865}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 11:35:44.527462: step: 4/530, loss: 0.015538406558334827
2023-01-21 11:35:45.624212: step: 8/530, loss: 0.00010309219942428172
2023-01-21 11:35:46.721711: step: 12/530, loss: 0.004303836729377508
2023-01-21 11:35:47.854253: step: 16/530, loss: 0.016955042257905006
2023-01-21 11:35:48.984205: step: 20/530, loss: 0.00020675659470725805
2023-01-21 11:35:50.082025: step: 24/530, loss: 0.027109241113066673
2023-01-21 11:35:51.200827: step: 28/530, loss: 0.03707714006304741
2023-01-21 11:35:52.298774: step: 32/530, loss: 0.0035808563698083162
2023-01-21 11:35:53.396758: step: 36/530, loss: 0.010753536596894264
2023-01-21 11:35:54.544343: step: 40/530, loss: 0.0924493744969368
2023-01-21 11:35:55.649962: step: 44/530, loss: 0.05271138995885849
2023-01-21 11:35:56.753399: step: 48/530, loss: 0.018538713455200195
2023-01-21 11:35:57.861606: step: 52/530, loss: 0.0024030685890465975
2023-01-21 11:35:58.980693: step: 56/530, loss: 0.004207992926239967
2023-01-21 11:36:00.083672: step: 60/530, loss: 0.027288056910037994
2023-01-21 11:36:01.195259: step: 64/530, loss: 0.0019202232360839844
2023-01-21 11:36:02.285737: step: 68/530, loss: 0.007225990295410156
2023-01-21 11:36:03.403387: step: 72/530, loss: 0.005442047491669655
2023-01-21 11:36:04.525363: step: 76/530, loss: 0.0031801224686205387
2023-01-21 11:36:05.615476: step: 80/530, loss: 0.018955161795020103
2023-01-21 11:36:06.730279: step: 84/530, loss: 0.03357210010290146
2023-01-21 11:36:07.835246: step: 88/530, loss: 0.04536399990320206
2023-01-21 11:36:08.932603: step: 92/530, loss: 0.014856052584946156
2023-01-21 11:36:10.032589: step: 96/530, loss: 0.014833355322480202
2023-01-21 11:36:11.148492: step: 100/530, loss: 0.48924142122268677
2023-01-21 11:36:12.249509: step: 104/530, loss: 0.022322725504636765
2023-01-21 11:36:13.389156: step: 108/530, loss: 0.0014595985412597656
2023-01-21 11:36:14.523385: step: 112/530, loss: 0.030552484095096588
2023-01-21 11:36:15.626228: step: 116/530, loss: 0.23088565468788147
2023-01-21 11:36:16.739081: step: 120/530, loss: 0.003956031985580921
2023-01-21 11:36:17.846043: step: 124/530, loss: 0.002081298967823386
2023-01-21 11:36:18.953303: step: 128/530, loss: 0.0001837253657868132
2023-01-21 11:36:20.091580: step: 132/530, loss: 0.02134404331445694
2023-01-21 11:36:21.204057: step: 136/530, loss: 0.0015944242477416992
2023-01-21 11:36:22.310816: step: 140/530, loss: 0.00046958925668150187
2023-01-21 11:36:23.451939: step: 144/530, loss: 0.05222949758172035
2023-01-21 11:36:24.576910: step: 148/530, loss: 0.14044417440891266
2023-01-21 11:36:25.684515: step: 152/530, loss: 0.010602761059999466
2023-01-21 11:36:26.776161: step: 156/530, loss: 0.006151819601655006
2023-01-21 11:36:27.877621: step: 160/530, loss: 0.501025915145874
2023-01-21 11:36:28.995904: step: 164/530, loss: 0.02580413781106472
2023-01-21 11:36:30.106765: step: 168/530, loss: 0.019426966086030006
2023-01-21 11:36:31.211415: step: 172/530, loss: 0.015244388952851295
2023-01-21 11:36:32.375061: step: 176/530, loss: 0.05114803463220596
2023-01-21 11:36:33.504856: step: 180/530, loss: 0.008577799424529076
2023-01-21 11:36:34.609828: step: 184/530, loss: 0.019380569458007812
2023-01-21 11:36:35.712664: step: 188/530, loss: 0.0034818649291992188
2023-01-21 11:36:36.847197: step: 192/530, loss: 0.003602647688239813
2023-01-21 11:36:37.966155: step: 196/530, loss: 0.03370017930865288
2023-01-21 11:36:39.073922: step: 200/530, loss: 0.04303693771362305
2023-01-21 11:36:40.161656: step: 204/530, loss: 0.017069054767489433
2023-01-21 11:36:41.312096: step: 208/530, loss: 0.000293731689453125
2023-01-21 11:36:42.436953: step: 212/530, loss: 0.0003974914725404233
2023-01-21 11:36:43.515857: step: 216/530, loss: 0.0039803506806492805
2023-01-21 11:36:44.651299: step: 220/530, loss: 0.001768350601196289
2023-01-21 11:36:45.729446: step: 224/530, loss: 0.01432584598660469
2023-01-21 11:36:46.817496: step: 228/530, loss: 0.01977372169494629
2023-01-21 11:36:47.938271: step: 232/530, loss: 0.0009492874378338456
2023-01-21 11:36:49.039650: step: 236/530, loss: 0.0005287170642986894
2023-01-21 11:36:50.218297: step: 240/530, loss: 0.021034814417362213
2023-01-21 11:36:51.324829: step: 244/530, loss: 0.018206119537353516
2023-01-21 11:36:52.454288: step: 248/530, loss: 0.001902771065942943
2023-01-21 11:36:53.574064: step: 252/530, loss: 0.007700443267822266
2023-01-21 11:36:54.670097: step: 256/530, loss: 7.534027099609375e-05
2023-01-21 11:36:55.792602: step: 260/530, loss: 0.0032901763916015625
2023-01-21 11:36:56.928806: step: 264/530, loss: 0.00017814636521507055
2023-01-21 11:36:58.012789: step: 268/530, loss: 0.0002706051163841039
2023-01-21 11:36:59.134611: step: 272/530, loss: 0.02653331682085991
2023-01-21 11:37:00.249027: step: 276/530, loss: 0.004841804504394531
2023-01-21 11:37:01.369255: step: 280/530, loss: 0.0033611299004405737
2023-01-21 11:37:02.483167: step: 284/530, loss: 0.07295341789722443
2023-01-21 11:37:03.592021: step: 288/530, loss: 0.0005941391573287547
2023-01-21 11:37:04.727666: step: 292/530, loss: 0.010306740179657936
2023-01-21 11:37:05.818058: step: 296/530, loss: 0.0021865845192223787
2023-01-21 11:37:06.930457: step: 300/530, loss: 0.0004426002560649067
2023-01-21 11:37:08.025232: step: 304/530, loss: 0.04763620346784592
2023-01-21 11:37:09.104457: step: 308/530, loss: 0.013392258435487747
2023-01-21 11:37:10.241198: step: 312/530, loss: 0.008871651254594326
2023-01-21 11:37:11.376787: step: 316/530, loss: 0.005811118986457586
2023-01-21 11:37:12.514067: step: 320/530, loss: 0.022293759509921074
2023-01-21 11:37:13.613737: step: 324/530, loss: 0.0020002364180982113
2023-01-21 11:37:14.717463: step: 328/530, loss: 0.0330398827791214
2023-01-21 11:37:15.830808: step: 332/530, loss: 0.00025930406991392374
2023-01-21 11:37:16.951936: step: 336/530, loss: 0.03254289552569389
2023-01-21 11:37:18.077508: step: 340/530, loss: 0.00011692046246025711
2023-01-21 11:37:19.185504: step: 344/530, loss: 0.0008636474376544356
2023-01-21 11:37:20.282795: step: 348/530, loss: 0.004574966616928577
2023-01-21 11:37:21.404276: step: 352/530, loss: 0.004576397128403187
2023-01-21 11:37:22.506519: step: 356/530, loss: 0.0005890846368856728
2023-01-21 11:37:23.618025: step: 360/530, loss: -1.1444089977885596e-06
2023-01-21 11:37:24.696827: step: 364/530, loss: 0.000111627574369777
2023-01-21 11:37:25.835568: step: 368/530, loss: 0.003235054202377796
2023-01-21 11:37:26.945635: step: 372/530, loss: 0.011699390597641468
2023-01-21 11:37:28.066990: step: 376/530, loss: 0.004066848661750555
2023-01-21 11:37:29.210829: step: 380/530, loss: 0.0002948761102743447
2023-01-21 11:37:30.336641: step: 384/530, loss: 0.0039044858422130346
2023-01-21 11:37:31.449198: step: 388/530, loss: 0.019080735743045807
2023-01-21 11:37:32.551501: step: 392/530, loss: 0.00011539459956111386
2023-01-21 11:37:33.684432: step: 396/530, loss: 0.0013751983642578125
2023-01-21 11:37:34.798964: step: 400/530, loss: 0.031068991869688034
2023-01-21 11:37:35.928690: step: 404/530, loss: 0.016893481835722923
2023-01-21 11:37:37.084031: step: 408/530, loss: 0.0004928589332848787
2023-01-21 11:37:38.198548: step: 412/530, loss: 0.03213987499475479
2023-01-21 11:37:39.327689: step: 416/530, loss: 0.012542724609375
2023-01-21 11:37:40.383150: step: 420/530, loss: 0.42835816740989685
2023-01-21 11:37:41.487665: step: 424/530, loss: 0.0012778282398357987
2023-01-21 11:37:42.579477: step: 428/530, loss: 0.00319499964825809
2023-01-21 11:37:43.732475: step: 432/530, loss: 0.023506546393036842
2023-01-21 11:37:44.884773: step: 436/530, loss: 0.0023518563248217106
2023-01-21 11:37:46.001524: step: 440/530, loss: 0.04606781154870987
2023-01-21 11:37:47.162590: step: 444/530, loss: 0.01867084577679634
2023-01-21 11:37:48.272254: step: 448/530, loss: 0.004562568850815296
2023-01-21 11:37:49.418925: step: 452/530, loss: 0.02485079877078533
2023-01-21 11:37:50.527153: step: 456/530, loss: 0.005431652069091797
2023-01-21 11:37:51.628479: step: 460/530, loss: 0.048281479626894
2023-01-21 11:37:52.726817: step: 464/530, loss: 0.020136166363954544
2023-01-21 11:37:53.848774: step: 468/530, loss: 0.0009610175620764494
2023-01-21 11:37:54.939433: step: 472/530, loss: 0.11516576260328293
2023-01-21 11:37:56.041353: step: 476/530, loss: 0.016741467639803886
2023-01-21 11:37:57.154516: step: 480/530, loss: 0.000522232090588659
2023-01-21 11:37:58.310603: step: 484/530, loss: 0.022007465362548828
2023-01-21 11:37:59.411288: step: 488/530, loss: 0.021456528455018997
2023-01-21 11:38:00.497354: step: 492/530, loss: 0.018104268237948418
2023-01-21 11:38:01.629165: step: 496/530, loss: 0.015808487311005592
2023-01-21 11:38:02.731658: step: 500/530, loss: 0.029055356979370117
2023-01-21 11:38:03.828840: step: 504/530, loss: 0.0161114688962698
2023-01-21 11:38:04.917239: step: 508/530, loss: 0.00018653868755791336
2023-01-21 11:38:06.032485: step: 512/530, loss: 0.007222556974738836
2023-01-21 11:38:07.139115: step: 516/530, loss: 0.010155295953154564
2023-01-21 11:38:08.246728: step: 520/530, loss: 0.02970104105770588
2023-01-21 11:38:09.343410: step: 524/530, loss: 0.0001541137753520161
2023-01-21 11:38:10.458927: step: 528/530, loss: 0.0009910583030432463
2023-01-21 11:38:11.568655: step: 532/530, loss: 0.006185054779052734
2023-01-21 11:38:12.664995: step: 536/530, loss: 0.003994321916252375
2023-01-21 11:38:13.772242: step: 540/530, loss: 0.014900398440659046
2023-01-21 11:38:14.882506: step: 544/530, loss: 0.0010254860389977694
2023-01-21 11:38:15.984430: step: 548/530, loss: 0.00048160552978515625
2023-01-21 11:38:17.085972: step: 552/530, loss: 0.18701010942459106
2023-01-21 11:38:18.178250: step: 556/530, loss: 0.0036806107964366674
2023-01-21 11:38:19.294171: step: 560/530, loss: 0.005240059457719326
2023-01-21 11:38:20.383570: step: 564/530, loss: 0.010839272290468216
2023-01-21 11:38:21.510815: step: 568/530, loss: 0.011540602892637253
2023-01-21 11:38:22.601872: step: 572/530, loss: 0.00151996617205441
2023-01-21 11:38:23.731519: step: 576/530, loss: 0.0014375686878338456
2023-01-21 11:38:24.854472: step: 580/530, loss: 0.10259618610143661
2023-01-21 11:38:25.959215: step: 584/530, loss: 0.00822744332253933
2023-01-21 11:38:27.032190: step: 588/530, loss: 0.019188832491636276
2023-01-21 11:38:28.134428: step: 592/530, loss: 0.013908673077821732
2023-01-21 11:38:29.261128: step: 596/530, loss: 0.034647177904844284
2023-01-21 11:38:30.363961: step: 600/530, loss: 0.021599579602479935
2023-01-21 11:38:31.464212: step: 604/530, loss: 0.0003159523184876889
2023-01-21 11:38:32.562056: step: 608/530, loss: 0.0006524086347781122
2023-01-21 11:38:33.705909: step: 612/530, loss: 0.009001636877655983
2023-01-21 11:38:34.827305: step: 616/530, loss: 0.013050413690507412
2023-01-21 11:38:35.965140: step: 620/530, loss: 0.0023550032638013363
2023-01-21 11:38:37.083907: step: 624/530, loss: 0.039183422923088074
2023-01-21 11:38:38.204656: step: 628/530, loss: 0.022510241717100143
2023-01-21 11:38:39.303716: step: 632/530, loss: 0.05098772048950195
2023-01-21 11:38:40.413105: step: 636/530, loss: 0.010355758480727673
2023-01-21 11:38:41.533329: step: 640/530, loss: 0.02342822775244713
2023-01-21 11:38:42.644251: step: 644/530, loss: 0.018220901489257812
2023-01-21 11:38:43.772026: step: 648/530, loss: -3.0851362680550665e-05
2023-01-21 11:38:44.897828: step: 652/530, loss: 0.012862730771303177
2023-01-21 11:38:45.991626: step: 656/530, loss: 0.12144008278846741
2023-01-21 11:38:47.112275: step: 660/530, loss: 7.724761962890625e-05
2023-01-21 11:38:48.277202: step: 664/530, loss: 0.024877214804291725
2023-01-21 11:38:49.412766: step: 668/530, loss: 0.024576187133789062
2023-01-21 11:38:50.514533: step: 672/530, loss: 0.001784896943718195
2023-01-21 11:38:51.631976: step: 676/530, loss: 0.009118652902543545
2023-01-21 11:38:52.717510: step: 680/530, loss: 0.00015435219393111765
2023-01-21 11:38:53.819202: step: 684/530, loss: 0.00161066057626158
2023-01-21 11:38:54.912599: step: 688/530, loss: 0.00672836322337389
2023-01-21 11:38:55.999701: step: 692/530, loss: 0.7931879758834839
2023-01-21 11:38:57.118947: step: 696/530, loss: 0.005603981204330921
2023-01-21 11:38:58.239729: step: 700/530, loss: 0.009859275072813034
2023-01-21 11:38:59.378085: step: 704/530, loss: 0.24037614464759827
2023-01-21 11:39:00.483689: step: 708/530, loss: 7.867813110351562e-05
2023-01-21 11:39:01.608728: step: 712/530, loss: 0.18329600989818573
2023-01-21 11:39:02.685915: step: 716/530, loss: 0.00334587087854743
2023-01-21 11:39:03.786263: step: 720/530, loss: 0.08267302811145782
2023-01-21 11:39:04.890380: step: 724/530, loss: 0.0005297660827636719
2023-01-21 11:39:05.992223: step: 728/530, loss: 0.005096435546875
2023-01-21 11:39:07.096591: step: 732/530, loss: 0.0003702164103742689
2023-01-21 11:39:08.195008: step: 736/530, loss: 0.0314258337020874
2023-01-21 11:39:09.289541: step: 740/530, loss: 0.0048768045380711555
2023-01-21 11:39:10.416653: step: 744/530, loss: 0.010059737600386143
2023-01-21 11:39:11.497795: step: 748/530, loss: 0.05085020139813423
2023-01-21 11:39:12.630779: step: 752/530, loss: 0.03216400370001793
2023-01-21 11:39:13.744332: step: 756/530, loss: 0.0208601001650095
2023-01-21 11:39:14.848714: step: 760/530, loss: 0.029767656698822975
2023-01-21 11:39:15.992207: step: 764/530, loss: 5.3119660151423886e-05
2023-01-21 11:39:17.128615: step: 768/530, loss: 0.0013719559647142887
2023-01-21 11:39:18.222619: step: 772/530, loss: 0.02174057997763157
2023-01-21 11:39:19.341998: step: 776/530, loss: 0.001155853271484375
2023-01-21 11:39:20.434544: step: 780/530, loss: 0.14572611451148987
2023-01-21 11:39:21.546638: step: 784/530, loss: 0.0017318249447271228
2023-01-21 11:39:22.660735: step: 788/530, loss: 0.06550540775060654
2023-01-21 11:39:23.779046: step: 792/530, loss: 0.016634799540042877
2023-01-21 11:39:24.915622: step: 796/530, loss: 0.015673398971557617
2023-01-21 11:39:26.018870: step: 800/530, loss: 0.002036619232967496
2023-01-21 11:39:27.116914: step: 804/530, loss: 0.00023374558077193797
2023-01-21 11:39:28.242671: step: 808/530, loss: 0.0007801055908203125
2023-01-21 11:39:29.333366: step: 812/530, loss: 0.00719795236364007
2023-01-21 11:39:30.434716: step: 816/530, loss: 0.0022953986190259457
2023-01-21 11:39:31.549018: step: 820/530, loss: 0.0043548583053052425
2023-01-21 11:39:32.650068: step: 824/530, loss: 0.021163560450077057
2023-01-21 11:39:33.768374: step: 828/530, loss: 0.017868518829345703
2023-01-21 11:39:34.899076: step: 832/530, loss: 0.10996018350124359
2023-01-21 11:39:36.046690: step: 836/530, loss: 0.004439258482307196
2023-01-21 11:39:37.158221: step: 840/530, loss: 0.020337535068392754
2023-01-21 11:39:38.243376: step: 844/530, loss: 0.0018639564514160156
2023-01-21 11:39:39.356727: step: 848/530, loss: 0.016733933240175247
2023-01-21 11:39:40.465022: step: 852/530, loss: 0.008910560980439186
2023-01-21 11:39:41.564993: step: 856/530, loss: 0.018204832449555397
2023-01-21 11:39:42.659960: step: 860/530, loss: 0.006949901580810547
2023-01-21 11:39:43.777328: step: 864/530, loss: 0.006422758102416992
2023-01-21 11:39:44.903297: step: 868/530, loss: 0.0007054328452795744
2023-01-21 11:39:46.020112: step: 872/530, loss: 0.043793678283691406
2023-01-21 11:39:47.117843: step: 876/530, loss: 0.0029680251609534025
2023-01-21 11:39:48.219307: step: 880/530, loss: 0.022115685045719147
2023-01-21 11:39:49.354279: step: 884/530, loss: 0.012332010082900524
2023-01-21 11:39:50.463385: step: 888/530, loss: 0.0007526398403570056
2023-01-21 11:39:51.581484: step: 892/530, loss: 0.006965446751564741
2023-01-21 11:39:52.697096: step: 896/530, loss: 0.0022890090476721525
2023-01-21 11:39:53.806225: step: 900/530, loss: 0.09139204770326614
2023-01-21 11:39:54.935239: step: 904/530, loss: 0.022707652300596237
2023-01-21 11:39:56.037199: step: 908/530, loss: 0.04201870039105415
2023-01-21 11:39:57.116529: step: 912/530, loss: 0.037773940712213516
2023-01-21 11:39:58.206512: step: 916/530, loss: 0.01642465591430664
2023-01-21 11:39:59.326462: step: 920/530, loss: 0.027944182977080345
2023-01-21 11:40:00.437512: step: 924/530, loss: 0.0032597542740404606
2023-01-21 11:40:01.523011: step: 928/530, loss: 0.0019674301147460938
2023-01-21 11:40:02.630750: step: 932/530, loss: 0.03970353677868843
2023-01-21 11:40:03.772446: step: 936/530, loss: 0.023433685302734375
2023-01-21 11:40:04.857507: step: 940/530, loss: 0.025008391588926315
2023-01-21 11:40:05.969557: step: 944/530, loss: 0.004248475655913353
2023-01-21 11:40:07.077217: step: 948/530, loss: 0.0020300389733165503
2023-01-21 11:40:08.200881: step: 952/530, loss: 0.0002847671858035028
2023-01-21 11:40:09.298414: step: 956/530, loss: 0.02259097620844841
2023-01-21 11:40:10.403327: step: 960/530, loss: 0.0003372192441020161
2023-01-21 11:40:11.524144: step: 964/530, loss: 0.0007192611810751259
2023-01-21 11:40:12.664776: step: 968/530, loss: 5.1021575927734375e-05
2023-01-21 11:40:13.796469: step: 972/530, loss: 0.058175280690193176
2023-01-21 11:40:14.901464: step: 976/530, loss: 0.007278156001120806
2023-01-21 11:40:15.987648: step: 980/530, loss: 0.00102405552752316
2023-01-21 11:40:17.129480: step: 984/530, loss: 0.00042400360689498484
2023-01-21 11:40:18.244516: step: 988/530, loss: 0.012501525692641735
2023-01-21 11:40:19.376382: step: 992/530, loss: 0.005577182397246361
2023-01-21 11:40:20.463105: step: 996/530, loss: 0.01881866529583931
2023-01-21 11:40:21.573240: step: 1000/530, loss: 0.00030345917912200093
2023-01-21 11:40:22.746026: step: 1004/530, loss: 0.01647014729678631
2023-01-21 11:40:23.870972: step: 1008/530, loss: 0.04443302005529404
2023-01-21 11:40:24.982906: step: 1012/530, loss: 0.023709489032626152
2023-01-21 11:40:26.090894: step: 1016/530, loss: 0.0029163360595703125
2023-01-21 11:40:27.228972: step: 1020/530, loss: 0.03952503204345703
2023-01-21 11:40:28.329209: step: 1024/530, loss: 0.07119293510913849
2023-01-21 11:40:29.452241: step: 1028/530, loss: 0.05188923329114914
2023-01-21 11:40:30.577669: step: 1032/530, loss: 0.09085045009851456
2023-01-21 11:40:31.692662: step: 1036/530, loss: 0.02921009249985218
2023-01-21 11:40:32.808848: step: 1040/530, loss: 0.05702047049999237
2023-01-21 11:40:33.921571: step: 1044/530, loss: 0.0001164436325780116
2023-01-21 11:40:35.042465: step: 1048/530, loss: 0.004671192262321711
2023-01-21 11:40:36.149724: step: 1052/530, loss: 0.17353801429271698
2023-01-21 11:40:37.235333: step: 1056/530, loss: 8.840561349643394e-05
2023-01-21 11:40:38.345452: step: 1060/530, loss: 0.01607656478881836
2023-01-21 11:40:39.467901: step: 1064/530, loss: 0.00016078949556685984
2023-01-21 11:40:40.597726: step: 1068/530, loss: 0.026284312829375267
2023-01-21 11:40:41.727962: step: 1072/530, loss: 0.0002891063631977886
2023-01-21 11:40:42.841458: step: 1076/530, loss: 0.0008088588947430253
2023-01-21 11:40:43.924228: step: 1080/530, loss: 0.003712570760399103
2023-01-21 11:40:45.016885: step: 1084/530, loss: 0.0003281593380961567
2023-01-21 11:40:46.130492: step: 1088/530, loss: 0.002109432127326727
2023-01-21 11:40:47.259162: step: 1092/530, loss: 0.008589553646743298
2023-01-21 11:40:48.363859: step: 1096/530, loss: 0.004763794131577015
2023-01-21 11:40:49.489002: step: 1100/530, loss: 0.017424870282411575
2023-01-21 11:40:50.596653: step: 1104/530, loss: 0.18673038482666016
2023-01-21 11:40:51.750274: step: 1108/530, loss: 0.07209110260009766
2023-01-21 11:40:52.847555: step: 1112/530, loss: 0.04773082584142685
2023-01-21 11:40:53.940990: step: 1116/530, loss: 0.004270744509994984
2023-01-21 11:40:55.049215: step: 1120/530, loss: 0.002678489778190851
2023-01-21 11:40:56.171896: step: 1124/530, loss: 0.0006042004097253084
2023-01-21 11:40:57.280630: step: 1128/530, loss: 0.0003546714724507183
2023-01-21 11:40:58.428080: step: 1132/530, loss: 0.0033932209480553865
2023-01-21 11:40:59.531705: step: 1136/530, loss: 0.027182389050722122
2023-01-21 11:41:00.661376: step: 1140/530, loss: 0.025155067443847656
2023-01-21 11:41:01.767689: step: 1144/530, loss: -5.0067901611328125e-06
2023-01-21 11:41:02.870786: step: 1148/530, loss: 0.005621051881462336
2023-01-21 11:41:03.964887: step: 1152/530, loss: 0.005864906124770641
2023-01-21 11:41:05.038896: step: 1156/530, loss: 0.0001346349745290354
2023-01-21 11:41:06.144097: step: 1160/530, loss: 0.06018419191241264
2023-01-21 11:41:07.244443: step: 1164/530, loss: 0.0012487411731854081
2023-01-21 11:41:08.357088: step: 1168/530, loss: 0.028756260871887207
2023-01-21 11:41:09.472237: step: 1172/530, loss: 0.005887698847800493
2023-01-21 11:41:10.537873: step: 1176/530, loss: 0.005175781436264515
2023-01-21 11:41:11.648092: step: 1180/530, loss: 4.7206878662109375e-05
2023-01-21 11:41:12.783638: step: 1184/530, loss: 0.05222377926111221
2023-01-21 11:41:13.879999: step: 1188/530, loss: 0.06117239221930504
2023-01-21 11:41:14.975304: step: 1192/530, loss: 0.011347579769790173
2023-01-21 11:41:16.100699: step: 1196/530, loss: 0.0015993118286132812
2023-01-21 11:41:17.193362: step: 1200/530, loss: 0.0009314537164755166
2023-01-21 11:41:18.321949: step: 1204/530, loss: 0.013143539428710938
2023-01-21 11:41:19.451582: step: 1208/530, loss: 0.007003211881965399
2023-01-21 11:41:20.580817: step: 1212/530, loss: 0.323643296957016
2023-01-21 11:41:21.680162: step: 1216/530, loss: 0.11925859749317169
2023-01-21 11:41:22.810008: step: 1220/530, loss: 0.01886158064007759
2023-01-21 11:41:23.901226: step: 1224/530, loss: 0.005920982453972101
2023-01-21 11:41:25.017215: step: 1228/530, loss: 0.1177511215209961
2023-01-21 11:41:26.154448: step: 1232/530, loss: 0.22948989272117615
2023-01-21 11:41:27.262793: step: 1236/530, loss: 0.0021741867531090975
2023-01-21 11:41:28.360757: step: 1240/530, loss: 0.0008554458618164062
2023-01-21 11:41:29.453832: step: 1244/530, loss: 5.073547436040826e-05
2023-01-21 11:41:30.545502: step: 1248/530, loss: 0.0016447067027911544
2023-01-21 11:41:31.621023: step: 1252/530, loss: 0.0376313216984272
2023-01-21 11:41:32.753743: step: 1256/530, loss: 0.0007063865195959806
2023-01-21 11:41:33.848038: step: 1260/530, loss: 0.024647142738103867
2023-01-21 11:41:34.931637: step: 1264/530, loss: 0.021284889429807663
2023-01-21 11:41:36.042716: step: 1268/530, loss: 0.09582366794347763
2023-01-21 11:41:37.164224: step: 1272/530, loss: 0.0066734314896166325
2023-01-21 11:41:38.276231: step: 1276/530, loss: 0.034357450902462006
2023-01-21 11:41:39.370536: step: 1280/530, loss: 0.037011146545410156
2023-01-21 11:41:40.475090: step: 1284/530, loss: 0.01544332504272461
2023-01-21 11:41:41.606486: step: 1288/530, loss: 0.05303249508142471
2023-01-21 11:41:42.726577: step: 1292/530, loss: 0.0011049271561205387
2023-01-21 11:41:43.828324: step: 1296/530, loss: 0.010771751403808594
2023-01-21 11:41:44.955763: step: 1300/530, loss: 0.011503983289003372
2023-01-21 11:41:46.064136: step: 1304/530, loss: 0.014945602975785732
2023-01-21 11:41:47.173157: step: 1308/530, loss: 0.0007500648498535156
2023-01-21 11:41:48.279341: step: 1312/530, loss: 0.013756513595581055
2023-01-21 11:41:49.384899: step: 1316/530, loss: 0.00014634132094215602
2023-01-21 11:41:50.511072: step: 1320/530, loss: 0.0002094268857035786
2023-01-21 11:41:51.637130: step: 1324/530, loss: 0.06457634270191193
2023-01-21 11:41:52.761621: step: 1328/530, loss: 0.03155803680419922
2023-01-21 11:41:53.874996: step: 1332/530, loss: 0.0036422729026526213
2023-01-21 11:41:54.974722: step: 1336/530, loss: 0.13641805946826935
2023-01-21 11:41:56.108471: step: 1340/530, loss: 0.02289733849465847
2023-01-21 11:41:57.180035: step: 1344/530, loss: 0.00011153220839332789
2023-01-21 11:41:58.300513: step: 1348/530, loss: 0.00653152447193861
2023-01-21 11:41:59.398039: step: 1352/530, loss: 3.533363633323461e-05
2023-01-21 11:42:00.536635: step: 1356/530, loss: 0.01332855224609375
2023-01-21 11:42:01.639252: step: 1360/530, loss: 0.0009347915765829384
2023-01-21 11:42:02.780527: step: 1364/530, loss: 0.006294441409409046
2023-01-21 11:42:03.882944: step: 1368/530, loss: 0.0006768703460693359
2023-01-21 11:42:04.988893: step: 1372/530, loss: 0.02087097242474556
2023-01-21 11:42:06.086953: step: 1376/530, loss: 0.0005721867200918496
2023-01-21 11:42:07.236899: step: 1380/530, loss: 0.020159531384706497
2023-01-21 11:42:08.369974: step: 1384/530, loss: 0.05679168924689293
2023-01-21 11:42:09.487898: step: 1388/530, loss: 0.04632997885346413
2023-01-21 11:42:10.579417: step: 1392/530, loss: 0.007859897799789906
2023-01-21 11:42:11.686713: step: 1396/530, loss: 0.004583167843520641
2023-01-21 11:42:12.783899: step: 1400/530, loss: 0.03721633180975914
2023-01-21 11:42:13.893929: step: 1404/530, loss: 0.05515632778406143
2023-01-21 11:42:14.993167: step: 1408/530, loss: 0.04446087032556534
2023-01-21 11:42:16.120093: step: 1412/530, loss: 0.03361453860998154
2023-01-21 11:42:17.225062: step: 1416/530, loss: 0.00042362214298918843
2023-01-21 11:42:18.297160: step: 1420/530, loss: 5.545616295421496e-05
2023-01-21 11:42:19.398464: step: 1424/530, loss: 0.06790123134851456
2023-01-21 11:42:20.498399: step: 1428/530, loss: 0.014075184240937233
2023-01-21 11:42:21.622889: step: 1432/530, loss: 0.01500854454934597
2023-01-21 11:42:22.738240: step: 1436/530, loss: 0.007605075836181641
2023-01-21 11:42:23.829000: step: 1440/530, loss: 0.007139969151467085
2023-01-21 11:42:25.002853: step: 1444/530, loss: 0.00014781951904296875
2023-01-21 11:42:26.093700: step: 1448/530, loss: 0.023858357220888138
2023-01-21 11:42:27.219414: step: 1452/530, loss: 0.00028104783268645406
2023-01-21 11:42:28.327827: step: 1456/530, loss: 0.025980280712246895
2023-01-21 11:42:29.402843: step: 1460/530, loss: 0.016693973913788795
2023-01-21 11:42:30.494667: step: 1464/530, loss: 0.008809184655547142
2023-01-21 11:42:31.599469: step: 1468/530, loss: 0.0070022582076489925
2023-01-21 11:42:32.709392: step: 1472/530, loss: 0.0016303539741784334
2023-01-21 11:42:33.826369: step: 1476/530, loss: 0.06903534382581711
2023-01-21 11:42:34.991546: step: 1480/530, loss: 0.0017650604713708162
2023-01-21 11:42:36.071624: step: 1484/530, loss: 0.0031463622581213713
2023-01-21 11:42:37.172651: step: 1488/530, loss: 0.07946892082691193
2023-01-21 11:42:38.315981: step: 1492/530, loss: 0.01411895826458931
2023-01-21 11:42:39.405612: step: 1496/530, loss: 0.04037361219525337
2023-01-21 11:42:40.485368: step: 1500/530, loss: 9.250640869140625e-05
2023-01-21 11:42:41.604412: step: 1504/530, loss: 0.012080097571015358
2023-01-21 11:42:42.742859: step: 1508/530, loss: 0.0013203620910644531
2023-01-21 11:42:43.862369: step: 1512/530, loss: 0.008947658352553844
2023-01-21 11:42:44.968073: step: 1516/530, loss: 0.023270893841981888
2023-01-21 11:42:46.089129: step: 1520/530, loss: 0.015252781100571156
2023-01-21 11:42:47.226731: step: 1524/530, loss: 0.0014043807750567794
2023-01-21 11:42:48.355328: step: 1528/530, loss: 0.004772949498146772
2023-01-21 11:42:49.443952: step: 1532/530, loss: 0.003431701799854636
2023-01-21 11:42:50.586430: step: 1536/530, loss: 0.025314711034297943
2023-01-21 11:42:51.685535: step: 1540/530, loss: 0.010156822390854359
2023-01-21 11:42:52.796340: step: 1544/530, loss: 0.0037425996270030737
2023-01-21 11:42:53.914052: step: 1548/530, loss: 0.0001510620058979839
2023-01-21 11:42:55.002319: step: 1552/530, loss: 0.0036911964416503906
2023-01-21 11:42:56.112411: step: 1556/530, loss: 0.00013236999802757055
2023-01-21 11:42:57.221720: step: 1560/530, loss: 0.0006529808160848916
2023-01-21 11:42:58.345374: step: 1564/530, loss: 0.10707416385412216
2023-01-21 11:42:59.442195: step: 1568/530, loss: 0.05747414007782936
2023-01-21 11:43:00.548812: step: 1572/530, loss: 0.0020286559592932463
2023-01-21 11:43:01.660343: step: 1576/530, loss: 0.006119442172348499
2023-01-21 11:43:02.780455: step: 1580/530, loss: 0.00829172134399414
2023-01-21 11:43:03.896905: step: 1584/530, loss: 0.03436412662267685
2023-01-21 11:43:04.990985: step: 1588/530, loss: 0.000941848789807409
2023-01-21 11:43:06.105257: step: 1592/530, loss: 0.05208345502614975
2023-01-21 11:43:07.219423: step: 1596/530, loss: 0.06081562116742134
2023-01-21 11:43:08.300704: step: 1600/530, loss: 0.00010342597670387477
2023-01-21 11:43:09.377592: step: 1604/530, loss: 3.967285010730848e-05
2023-01-21 11:43:10.496426: step: 1608/530, loss: 0.004682731814682484
2023-01-21 11:43:11.589531: step: 1612/530, loss: 0.7012049555778503
2023-01-21 11:43:12.693613: step: 1616/530, loss: 0.005007839296013117
2023-01-21 11:43:13.779931: step: 1620/530, loss: 0.029549788683652878
2023-01-21 11:43:14.897977: step: 1624/530, loss: 0.04130697250366211
2023-01-21 11:43:16.005445: step: 1628/530, loss: 0.005343914031982422
2023-01-21 11:43:17.151913: step: 1632/530, loss: 0.1487049013376236
2023-01-21 11:43:18.270811: step: 1636/530, loss: 0.00945434533059597
2023-01-21 11:43:19.374730: step: 1640/530, loss: 0.022394943982362747
2023-01-21 11:43:20.477957: step: 1644/530, loss: 0.06925764679908752
2023-01-21 11:43:21.576609: step: 1648/530, loss: 0.02374572865664959
2023-01-21 11:43:22.718855: step: 1652/530, loss: 0.0027790190652012825
2023-01-21 11:43:23.817339: step: 1656/530, loss: 0.015136432833969593
2023-01-21 11:43:24.932016: step: 1660/530, loss: 0.044382572174072266
2023-01-21 11:43:26.059460: step: 1664/530, loss: 0.0006704330444335938
2023-01-21 11:43:27.160608: step: 1668/530, loss: 0.003330803010612726
2023-01-21 11:43:28.251584: step: 1672/530, loss: 0.015287494286894798
2023-01-21 11:43:29.340538: step: 1676/530, loss: 0.0016093254089355469
2023-01-21 11:43:30.460369: step: 1680/530, loss: 0.049257468432188034
2023-01-21 11:43:31.604920: step: 1684/530, loss: 0.01935148425400257
2023-01-21 11:43:32.691224: step: 1688/530, loss: 0.0006874084938317537
2023-01-21 11:43:33.790531: step: 1692/530, loss: 0.020571382716298103
2023-01-21 11:43:34.900975: step: 1696/530, loss: 0.3436241149902344
2023-01-21 11:43:36.034513: step: 1700/530, loss: 0.0077949524857103825
2023-01-21 11:43:37.140654: step: 1704/530, loss: 0.014030742458999157
2023-01-21 11:43:38.217405: step: 1708/530, loss: 0.003091955091804266
2023-01-21 11:43:39.300982: step: 1712/530, loss: 0.0004459381161723286
2023-01-21 11:43:40.421018: step: 1716/530, loss: 0.09762582182884216
2023-01-21 11:43:41.551428: step: 1720/530, loss: 0.006093787960708141
2023-01-21 11:43:42.667072: step: 1724/530, loss: 0.02343130111694336
2023-01-21 11:43:43.762121: step: 1728/530, loss: 0.0009000301361083984
2023-01-21 11:43:44.892771: step: 1732/530, loss: 0.0010390281677246094
2023-01-21 11:43:46.021757: step: 1736/530, loss: 0.0038806914817541838
2023-01-21 11:43:47.132066: step: 1740/530, loss: 1.487731969973538e-05
2023-01-21 11:43:48.247852: step: 1744/530, loss: 0.0025426866486668587
2023-01-21 11:43:49.338434: step: 1748/530, loss: 0.01592388190329075
2023-01-21 11:43:50.467379: step: 1752/530, loss: 0.0025650025345385075
2023-01-21 11:43:51.595138: step: 1756/530, loss: 0.00018539429584052414
2023-01-21 11:43:52.676322: step: 1760/530, loss: 0.004696178715676069
2023-01-21 11:43:53.788623: step: 1764/530, loss: 0.00021696090698242188
2023-01-21 11:43:54.913782: step: 1768/530, loss: 0.009579754434525967
2023-01-21 11:43:56.054412: step: 1772/530, loss: 0.24316748976707458
2023-01-21 11:43:57.183804: step: 1776/530, loss: 0.03547258675098419
2023-01-21 11:43:58.288759: step: 1780/530, loss: 0.09324925392866135
2023-01-21 11:43:59.413127: step: 1784/530, loss: 0.005812454503029585
2023-01-21 11:44:00.541937: step: 1788/530, loss: 0.0005620956653729081
2023-01-21 11:44:01.646883: step: 1792/530, loss: 0.025864887982606888
2023-01-21 11:44:02.746675: step: 1796/530, loss: 0.002695178845897317
2023-01-21 11:44:03.827695: step: 1800/530, loss: 0.011013984680175781
2023-01-21 11:44:04.934547: step: 1804/530, loss: 0.00029315947904251516
2023-01-21 11:44:06.072444: step: 1808/530, loss: 0.022449970245361328
2023-01-21 11:44:07.172601: step: 1812/530, loss: 0.00017137527174782008
2023-01-21 11:44:08.310359: step: 1816/530, loss: 0.06276092678308487
2023-01-21 11:44:09.411519: step: 1820/530, loss: 0.0011528015602380037
2023-01-21 11:44:10.496145: step: 1824/530, loss: 0.00099859235342592
2023-01-21 11:44:11.614390: step: 1828/530, loss: 0.0012840271228924394
2023-01-21 11:44:12.755012: step: 1832/530, loss: 0.0395539291203022
2023-01-21 11:44:13.874888: step: 1836/530, loss: 0.03256263956427574
2023-01-21 11:44:14.993228: step: 1840/530, loss: 0.006854057312011719
2023-01-21 11:44:16.127702: step: 1844/530, loss: 0.026057148352265358
2023-01-21 11:44:17.244929: step: 1848/530, loss: 0.05324840545654297
2023-01-21 11:44:18.356515: step: 1852/530, loss: 0.0158431064337492
2023-01-21 11:44:19.475962: step: 1856/530, loss: 0.04741191864013672
2023-01-21 11:44:20.585239: step: 1860/530, loss: 0.007835007272660732
2023-01-21 11:44:21.732621: step: 1864/530, loss: 0.036286354064941406
2023-01-21 11:44:22.828918: step: 1868/530, loss: 0.0020513059571385384
2023-01-21 11:44:23.924453: step: 1872/530, loss: 0.0014045715797692537
2023-01-21 11:44:25.002643: step: 1876/530, loss: 0.004722500219941139
2023-01-21 11:44:26.094031: step: 1880/530, loss: 0.05336952209472656
2023-01-21 11:44:27.200334: step: 1884/530, loss: 0.002191829727962613
2023-01-21 11:44:28.325206: step: 1888/530, loss: 0.00035943987313658
2023-01-21 11:44:29.463493: step: 1892/530, loss: 0.0009249686845578253
2023-01-21 11:44:30.588863: step: 1896/530, loss: 0.003943490795791149
2023-01-21 11:44:31.662014: step: 1900/530, loss: 0.00026044846163131297
2023-01-21 11:44:32.759338: step: 1904/530, loss: 0.010267066769301891
2023-01-21 11:44:33.877357: step: 1908/530, loss: 0.015498924069106579
2023-01-21 11:44:34.992531: step: 1912/530, loss: 0.005458545871078968
2023-01-21 11:44:36.107399: step: 1916/530, loss: 0.0021534920670092106
2023-01-21 11:44:37.233054: step: 1920/530, loss: 0.010009193792939186
2023-01-21 11:44:38.346875: step: 1924/530, loss: 0.00035324099007993937
2023-01-21 11:44:39.473677: step: 1928/530, loss: 0.11067288368940353
2023-01-21 11:44:40.572780: step: 1932/530, loss: 0.0017961800331249833
2023-01-21 11:44:41.668852: step: 1936/530, loss: 0.0023491859901696444
2023-01-21 11:44:42.785868: step: 1940/530, loss: 0.018761729821562767
2023-01-21 11:44:43.873384: step: 1944/530, loss: 0.0020810128189623356
2023-01-21 11:44:44.990140: step: 1948/530, loss: 0.29024773836135864
2023-01-21 11:44:46.130477: step: 1952/530, loss: 0.003209781600162387
2023-01-21 11:44:47.232680: step: 1956/530, loss: 0.0015465737087652087
2023-01-21 11:44:48.349723: step: 1960/530, loss: 0.012009143829345703
2023-01-21 11:44:49.463402: step: 1964/530, loss: 0.01633596420288086
2023-01-21 11:44:50.595190: step: 1968/530, loss: 0.00499801617115736
2023-01-21 11:44:51.710232: step: 1972/530, loss: 1.3351441339182202e-06
2023-01-21 11:44:52.833421: step: 1976/530, loss: 0.06334781646728516
2023-01-21 11:44:53.953104: step: 1980/530, loss: 0.04197588190436363
2023-01-21 11:44:55.070893: step: 1984/530, loss: 0.27490195631980896
2023-01-21 11:44:56.203835: step: 1988/530, loss: 0.0019353866809979081
2023-01-21 11:44:57.310848: step: 1992/530, loss: 0.00024890899658203125
2023-01-21 11:44:58.403794: step: 1996/530, loss: 2.9304625059012324e-05
2023-01-21 11:44:59.507255: step: 2000/530, loss: 0.0029045583214610815
2023-01-21 11:45:00.610272: step: 2004/530, loss: 0.005679797846823931
2023-01-21 11:45:01.725856: step: 2008/530, loss: 0.028824234381318092
2023-01-21 11:45:02.835439: step: 2012/530, loss: 0.00569419888779521
2023-01-21 11:45:03.948224: step: 2016/530, loss: 0.03195934370160103
2023-01-21 11:45:05.036612: step: 2020/530, loss: 0.012851143255829811
2023-01-21 11:45:06.117924: step: 2024/530, loss: 0.05117626488208771
2023-01-21 11:45:07.229693: step: 2028/530, loss: -1.468658410885837e-05
2023-01-21 11:45:08.364799: step: 2032/530, loss: 0.0016850472893565893
2023-01-21 11:45:09.450326: step: 2036/530, loss: 0.0027854086365550756
2023-01-21 11:45:10.565982: step: 2040/530, loss: 0.03502919524908066
2023-01-21 11:45:11.677427: step: 2044/530, loss: 0.0008890152676030993
2023-01-21 11:45:12.791561: step: 2048/530, loss: 0.012233376502990723
2023-01-21 11:45:13.895418: step: 2052/530, loss: 0.0004127502324990928
2023-01-21 11:45:15.019930: step: 2056/530, loss: 0.005877113435417414
2023-01-21 11:45:16.131873: step: 2060/530, loss: 0.00423431396484375
2023-01-21 11:45:17.255636: step: 2064/530, loss: 0.0005033016204833984
2023-01-21 11:45:18.381921: step: 2068/530, loss: 0.02495880238711834
2023-01-21 11:45:19.496206: step: 2072/530, loss: 0.0012793303467333317
2023-01-21 11:45:20.585807: step: 2076/530, loss: 0.021669864654541016
2023-01-21 11:45:21.706153: step: 2080/530, loss: 0.4046580195426941
2023-01-21 11:45:22.862220: step: 2084/530, loss: 0.0008994102827273309
2023-01-21 11:45:23.974360: step: 2088/530, loss: 0.12079425156116486
2023-01-21 11:45:25.073150: step: 2092/530, loss: 0.01052160281687975
2023-01-21 11:45:26.195327: step: 2096/530, loss: 0.022985078394412994
2023-01-21 11:45:27.319399: step: 2100/530, loss: 3.4809112548828125e-05
2023-01-21 11:45:28.398161: step: 2104/530, loss: 0.02949695661664009
2023-01-21 11:45:29.526556: step: 2108/530, loss: 0.0043350220657885075
2023-01-21 11:45:30.631528: step: 2112/530, loss: 0.0072761536575853825
2023-01-21 11:45:31.716406: step: 2116/530, loss: 0.3526698052883148
2023-01-21 11:45:32.854807: step: 2120/530, loss: 0.006498909089714289
==================================================
Loss: 0.030
--------------------
Dev: {'event': {'p': 0.5793650793650794, 'r': 0.7776298268974701, 'f1': 0.6640136441159751}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Test: {'event': {'p': 0.6375286041189931, 'r': 0.8117715617715617, 'f1': 0.7141758523455524}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
Korean: {'event': {'p': 0.6724137931034483, 'r': 0.6190476190476191, 'f1': 0.6446280991735537}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 11:46:15.013100: step: 4/530, loss: 0.0034091949928551912
2023-01-21 11:46:16.103592: step: 8/530, loss: 0.0019034385913982987
2023-01-21 11:46:17.249845: step: 12/530, loss: 0.031867220997810364
2023-01-21 11:46:18.339987: step: 16/530, loss: 0.0018473626114428043
2023-01-21 11:46:19.448776: step: 20/530, loss: 0.0009202957153320312
2023-01-21 11:46:20.530870: step: 24/530, loss: 0.010785293765366077
2023-01-21 11:46:21.628493: step: 28/530, loss: 0.044645603746175766
2023-01-21 11:46:22.704422: step: 32/530, loss: 0.0032550811301916838
2023-01-21 11:46:23.820838: step: 36/530, loss: 0.024207307025790215
2023-01-21 11:46:24.935379: step: 40/530, loss: 0.005213928408920765
2023-01-21 11:46:26.035437: step: 44/530, loss: 0.6288784146308899
2023-01-21 11:46:27.121962: step: 48/530, loss: 0.00022392271785065532
2023-01-21 11:46:28.249433: step: 52/530, loss: 0.15328730642795563
2023-01-21 11:46:29.382024: step: 56/530, loss: 0.018764590844511986
2023-01-21 11:46:30.502678: step: 60/530, loss: 4.0721897676121444e-05
2023-01-21 11:46:31.607389: step: 64/530, loss: 0.00045776370097883046
2023-01-21 11:46:32.687292: step: 68/530, loss: 0.00021629333787132055
2023-01-21 11:46:33.849431: step: 72/530, loss: 0.026780128479003906
2023-01-21 11:46:34.957308: step: 76/530, loss: 0.02058105543255806
2023-01-21 11:46:36.060209: step: 80/530, loss: 0.0008292198181152344
2023-01-21 11:46:37.162863: step: 84/530, loss: 0.003988075535744429
2023-01-21 11:46:38.294724: step: 88/530, loss: 0.04498253017663956
2023-01-21 11:46:39.424034: step: 92/530, loss: 0.002807998564094305
2023-01-21 11:46:40.601754: step: 96/530, loss: 0.04000682756304741
2023-01-21 11:46:41.706471: step: 100/530, loss: 0.002509593963623047
2023-01-21 11:46:42.828677: step: 104/530, loss: 0.007209682371467352
2023-01-21 11:46:43.958776: step: 108/530, loss: 0.0013561248779296875
2023-01-21 11:46:45.027080: step: 112/530, loss: 0.02415313757956028
2023-01-21 11:46:46.153289: step: 116/530, loss: 0.002601051237434149
2023-01-21 11:46:47.253865: step: 120/530, loss: 0.002884387969970703
2023-01-21 11:46:48.351400: step: 124/530, loss: 8.18252592580393e-05
2023-01-21 11:46:49.439692: step: 128/530, loss: 0.0002881288528442383
2023-01-21 11:46:50.554226: step: 132/530, loss: 0.022058868780732155
2023-01-21 11:46:51.644589: step: 136/530, loss: 0.01372599508613348
2023-01-21 11:46:52.758952: step: 140/530, loss: 0.004072952084243298
2023-01-21 11:46:53.860055: step: 144/530, loss: 0.02881307527422905
2023-01-21 11:46:54.956373: step: 148/530, loss: 0.005015516187995672
2023-01-21 11:46:56.043187: step: 152/530, loss: 0.013761281967163086
2023-01-21 11:46:57.176846: step: 156/530, loss: 0.005974388215690851
2023-01-21 11:46:58.302076: step: 160/530, loss: 0.00023908614821266383
2023-01-21 11:46:59.393042: step: 164/530, loss: 0.03368755429983139
2023-01-21 11:47:00.487161: step: 168/530, loss: 0.0037100552581250668
2023-01-21 11:47:01.600067: step: 172/530, loss: 0.016433047130703926
2023-01-21 11:47:02.753362: step: 176/530, loss: 0.004917907994240522
2023-01-21 11:47:03.859954: step: 180/530, loss: 0.04632911458611488
2023-01-21 11:47:04.948239: step: 184/530, loss: 0.003569984342902899
2023-01-21 11:47:06.027605: step: 188/530, loss: 0.02788066864013672
2023-01-21 11:47:07.136974: step: 192/530, loss: 0.01816578023135662
2023-01-21 11:47:08.227202: step: 196/530, loss: 0.0038685323670506477
2023-01-21 11:47:09.347711: step: 200/530, loss: 0.00527148274704814
2023-01-21 11:47:10.484761: step: 204/530, loss: 0.0329379066824913
2023-01-21 11:47:11.580491: step: 208/530, loss: 3.948211815441027e-05
2023-01-21 11:47:12.721657: step: 212/530, loss: 0.01047058217227459
2023-01-21 11:47:13.836417: step: 216/530, loss: 0.013763809576630592
2023-01-21 11:47:14.960260: step: 220/530, loss: 0.0038690567016601562
2023-01-21 11:47:16.063863: step: 224/530, loss: 0.0023657798301428556
2023-01-21 11:47:17.162884: step: 228/530, loss: 0.014734364114701748
2023-01-21 11:47:18.292016: step: 232/530, loss: 0.0008111476781778038
2023-01-21 11:47:19.404265: step: 236/530, loss: 0.14696788787841797
2023-01-21 11:47:20.523009: step: 240/530, loss: 0.0006644249078817666
2023-01-21 11:47:21.633704: step: 244/530, loss: 0.012244701385498047
2023-01-21 11:47:22.706802: step: 248/530, loss: 0.009781074710190296
2023-01-21 11:47:23.805014: step: 252/530, loss: 0.007044220343232155
2023-01-21 11:47:24.907525: step: 256/530, loss: 0.012603282928466797
2023-01-21 11:47:26.027771: step: 260/530, loss: 0.012927437201142311
2023-01-21 11:47:27.129837: step: 264/530, loss: 0.0013759852154180408
2023-01-21 11:47:28.217114: step: 268/530, loss: 0.00262794503942132
2023-01-21 11:47:29.318603: step: 272/530, loss: 0.00012855530076194555
2023-01-21 11:47:30.419298: step: 276/530, loss: 0.012608624063432217
2023-01-21 11:47:31.548047: step: 280/530, loss: 0.0007369041559286416
2023-01-21 11:47:32.641689: step: 284/530, loss: 0.0003531932889018208
2023-01-21 11:47:33.772755: step: 288/530, loss: 0.0015770912868902087
2023-01-21 11:47:34.883186: step: 292/530, loss: 0.00454025249928236
2023-01-21 11:47:36.012436: step: 296/530, loss: 0.03350086137652397
2023-01-21 11:47:37.134085: step: 300/530, loss: 0.09072523564100266
2023-01-21 11:47:38.223388: step: 304/530, loss: 0.045365143567323685
2023-01-21 11:47:39.331981: step: 308/530, loss: 0.0015707970596849918
2023-01-21 11:47:40.437032: step: 312/530, loss: 0.018577218055725098
2023-01-21 11:47:41.564288: step: 316/530, loss: 0.006319618318229914
2023-01-21 11:47:42.699780: step: 320/530, loss: 0.005485344212502241
2023-01-21 11:47:43.775936: step: 324/530, loss: 0.010674476623535156
2023-01-21 11:47:44.897568: step: 328/530, loss: 0.17406940460205078
2023-01-21 11:47:46.004909: step: 332/530, loss: 0.0005251884576864541
2023-01-21 11:47:47.120954: step: 336/530, loss: 0.023634053766727448
2023-01-21 11:47:48.241182: step: 340/530, loss: 0.03794508054852486
2023-01-21 11:47:49.347668: step: 344/530, loss: 3.700256274896674e-05
2023-01-21 11:47:50.449040: step: 348/530, loss: 0.0004760742303915322
2023-01-21 11:47:51.587995: step: 352/530, loss: 0.0010686874156817794
2023-01-21 11:47:52.697129: step: 356/530, loss: 0.0005650520324707031
2023-01-21 11:47:53.803024: step: 360/530, loss: 0.0023110390175133944
2023-01-21 11:47:54.928299: step: 364/530, loss: 0.27877846360206604
2023-01-21 11:47:56.022350: step: 368/530, loss: 0.00013256072998046875
2023-01-21 11:47:57.140953: step: 372/530, loss: 0.06950131058692932
2023-01-21 11:47:58.230066: step: 376/530, loss: 0.000293540972052142
2023-01-21 11:47:59.342233: step: 380/530, loss: 0.03360772505402565
2023-01-21 11:48:00.462176: step: 384/530, loss: 2.4127959477482364e-05
2023-01-21 11:48:01.559404: step: 388/530, loss: 0.0009849548805505037
2023-01-21 11:48:02.663887: step: 392/530, loss: 0.0013438225723803043
2023-01-21 11:48:03.786844: step: 396/530, loss: 0.007925224490463734
2023-01-21 11:48:04.864843: step: 400/530, loss: 0.005747795104980469
2023-01-21 11:48:05.950863: step: 404/530, loss: 0.12380104511976242
2023-01-21 11:48:07.034724: step: 408/530, loss: 0.00047712327796034515
2023-01-21 11:48:08.135662: step: 412/530, loss: 0.005205434747040272
2023-01-21 11:48:09.225210: step: 416/530, loss: 0.0001520156947663054
2023-01-21 11:48:10.340217: step: 420/530, loss: 0.002767849015071988
2023-01-21 11:48:11.456838: step: 424/530, loss: 0.028301334008574486
2023-01-21 11:48:12.541645: step: 428/530, loss: 0.0032245637848973274
2023-01-21 11:48:13.662285: step: 432/530, loss: 0.004717600531876087
2023-01-21 11:48:14.795028: step: 436/530, loss: 0.0007719040149822831
2023-01-21 11:48:15.911223: step: 440/530, loss: 0.003094196319580078
2023-01-21 11:48:17.012750: step: 444/530, loss: 0.08459696918725967
2023-01-21 11:48:18.126190: step: 448/530, loss: 0.004091834649443626
2023-01-21 11:48:19.258828: step: 452/530, loss: 0.0009126663208007812
2023-01-21 11:48:20.385801: step: 456/530, loss: 0.028426742181181908
2023-01-21 11:48:21.503355: step: 460/530, loss: 2.3841855636419496e-06
2023-01-21 11:48:22.602478: step: 464/530, loss: 0.00263385777361691
2023-01-21 11:48:23.729565: step: 468/530, loss: 0.02220935933291912
2023-01-21 11:48:24.813210: step: 472/530, loss: 0.03517866134643555
2023-01-21 11:48:25.912954: step: 476/530, loss: 0.01036615390330553
2023-01-21 11:48:27.035009: step: 480/530, loss: 0.11877574771642685
2023-01-21 11:48:28.144257: step: 484/530, loss: 0.0001546859712107107
2023-01-21 11:48:29.262865: step: 488/530, loss: 0.00022540093050338328
2023-01-21 11:48:30.421503: step: 492/530, loss: 0.010837174020707607
2023-01-21 11:48:31.534651: step: 496/530, loss: 0.011769247241318226
2023-01-21 11:48:32.643158: step: 500/530, loss: 0.006908082868903875
2023-01-21 11:48:33.769473: step: 504/530, loss: 0.02253875695168972
2023-01-21 11:48:34.844878: step: 508/530, loss: 3.0231476557673886e-05
2023-01-21 11:48:35.929108: step: 512/530, loss: 0.0017405509715899825
2023-01-21 11:48:37.042646: step: 516/530, loss: 0.026087380945682526
2023-01-21 11:48:38.163824: step: 520/530, loss: 0.06235980987548828
2023-01-21 11:48:39.295730: step: 524/530, loss: 0.01061716116964817
2023-01-21 11:48:40.404264: step: 528/530, loss: 0.015833426266908646
2023-01-21 11:48:41.535290: step: 532/530, loss: 0.006182003300637007
2023-01-21 11:48:42.672681: step: 536/530, loss: 0.01676889695227146
2023-01-21 11:48:43.843269: step: 540/530, loss: 0.0006196975591592491
2023-01-21 11:48:44.971750: step: 544/530, loss: 0.001897621201351285
2023-01-21 11:48:46.081408: step: 548/530, loss: 0.0015483855968341231
2023-01-21 11:48:47.187088: step: 552/530, loss: 0.01638955995440483
2023-01-21 11:48:48.285637: step: 556/530, loss: 0.034158192574977875
2023-01-21 11:48:49.390772: step: 560/530, loss: 0.00027751922607421875
2023-01-21 11:48:50.481659: step: 564/530, loss: 0.0030271292198449373
2023-01-21 11:48:51.575019: step: 568/530, loss: 0.0021017075050622225
2023-01-21 11:48:52.674226: step: 572/530, loss: 0.012898731976747513
2023-01-21 11:48:53.781614: step: 576/530, loss: 0.04820384830236435
2023-01-21 11:48:54.938180: step: 580/530, loss: 0.001486110733821988
2023-01-21 11:48:56.109404: step: 584/530, loss: 0.03345317766070366
2023-01-21 11:48:57.236470: step: 588/530, loss: 0.00045843125553801656
2023-01-21 11:48:58.349585: step: 592/530, loss: 0.012680530548095703
2023-01-21 11:48:59.448276: step: 596/530, loss: 0.37928637862205505
2023-01-21 11:49:00.557890: step: 600/530, loss: 0.015897369012236595
2023-01-21 11:49:01.683679: step: 604/530, loss: 0.005233574192970991
2023-01-21 11:49:02.797395: step: 608/530, loss: 6.2041015625
2023-01-21 11:49:03.952697: step: 612/530, loss: 0.0319274440407753
2023-01-21 11:49:05.044047: step: 616/530, loss: 0.06821155548095703
2023-01-21 11:49:06.154664: step: 620/530, loss: 0.023381341248750687
2023-01-21 11:49:07.261960: step: 624/530, loss: 0.009149646386504173
2023-01-21 11:49:08.361282: step: 628/530, loss: 0.0005740165943279862
2023-01-21 11:49:09.466777: step: 632/530, loss: 0.0010797500144690275
2023-01-21 11:49:10.549253: step: 636/530, loss: 0.005460548214614391
2023-01-21 11:49:11.628575: step: 640/530, loss: 0.0027456283569335938
2023-01-21 11:49:12.745837: step: 644/530, loss: 1.888275073724799e-05
2023-01-21 11:49:13.855178: step: 648/530, loss: 0.003803444094955921
2023-01-21 11:49:14.971015: step: 652/530, loss: 0.002662467770278454
2023-01-21 11:49:16.095169: step: 656/530, loss: 0.4119015634059906
2023-01-21 11:49:17.225134: step: 660/530, loss: 0.033118247985839844
2023-01-21 11:49:18.347216: step: 664/530, loss: 0.0003365039883647114
2023-01-21 11:49:19.467563: step: 668/530, loss: 0.022732913494110107
2023-01-21 11:49:20.580068: step: 672/530, loss: 0.11164913326501846
2023-01-21 11:49:21.678800: step: 676/530, loss: 0.006422615144401789
2023-01-21 11:49:22.760501: step: 680/530, loss: 0.0001486778346588835
2023-01-21 11:49:23.887947: step: 684/530, loss: 0.0013898849720135331
2023-01-21 11:49:25.022325: step: 688/530, loss: 0.004419135861098766
2023-01-21 11:49:26.125208: step: 692/530, loss: 0.06912650913000107
2023-01-21 11:49:27.225669: step: 696/530, loss: 0.003159713465720415
2023-01-21 11:49:28.326038: step: 700/530, loss: 0.030974864959716797
2023-01-21 11:49:29.438699: step: 704/530, loss: 0.0015718459617346525
2023-01-21 11:49:30.583233: step: 708/530, loss: 0.05807838216423988
2023-01-21 11:49:31.666511: step: 712/530, loss: 0.002372622722759843
2023-01-21 11:49:32.784163: step: 716/530, loss: 0.005496427416801453
2023-01-21 11:49:33.915835: step: 720/530, loss: 0.00978460256010294
2023-01-21 11:49:35.043122: step: 724/530, loss: 0.0036508559715002775
2023-01-21 11:49:36.134500: step: 728/530, loss: 0.04507208243012428
2023-01-21 11:49:37.251284: step: 732/530, loss: 0.06725358963012695
2023-01-21 11:49:38.387242: step: 736/530, loss: 2.517700158932712e-05
2023-01-21 11:49:39.499586: step: 740/530, loss: 0.06271419674158096
2023-01-21 11:49:40.585868: step: 744/530, loss: 0.03714122995734215
2023-01-21 11:49:41.680586: step: 748/530, loss: 0.012750553898513317
2023-01-21 11:49:42.764075: step: 752/530, loss: 0.033313848078250885
2023-01-21 11:49:43.851873: step: 756/530, loss: 0.00023412704467773438
2023-01-21 11:49:44.936205: step: 760/530, loss: 0.0010076522594317794
2023-01-21 11:49:46.008347: step: 764/530, loss: 0.01904602162539959
2023-01-21 11:49:47.080309: step: 768/530, loss: 0.03557164594531059
2023-01-21 11:49:48.189286: step: 772/530, loss: 0.06672267615795135
2023-01-21 11:49:49.314639: step: 776/530, loss: 0.0001180648832814768
2023-01-21 11:49:50.406045: step: 780/530, loss: 1.0299683708581142e-05
2023-01-21 11:49:51.516400: step: 784/530, loss: 0.042052604258060455
2023-01-21 11:49:52.642330: step: 788/530, loss: 1.0829336643218994
2023-01-21 11:49:53.746862: step: 792/530, loss: 0.007277870550751686
2023-01-21 11:49:54.858223: step: 796/530, loss: 0.0016148567665368319
2023-01-21 11:49:55.972051: step: 800/530, loss: 0.004467988386750221
2023-01-21 11:49:57.086952: step: 804/530, loss: 0.3038408160209656
2023-01-21 11:49:58.195445: step: 808/530, loss: 0.004821968264877796
2023-01-21 11:49:59.319090: step: 812/530, loss: 0.019588088616728783
2023-01-21 11:50:00.416827: step: 816/530, loss: 0.008867979049682617
2023-01-21 11:50:01.580783: step: 820/530, loss: 0.4668981432914734
2023-01-21 11:50:02.689822: step: 824/530, loss: 0.0013471603160724044
2023-01-21 11:50:03.791269: step: 828/530, loss: 0.02161569520831108
2023-01-21 11:50:04.921888: step: 832/530, loss: 0.007617759983986616
2023-01-21 11:50:06.044541: step: 836/530, loss: 0.006304549984633923
2023-01-21 11:50:07.118204: step: 840/530, loss: 4.138946678722277e-05
2023-01-21 11:50:08.222262: step: 844/530, loss: 0.0031252861954271793
2023-01-21 11:50:09.337861: step: 848/530, loss: 0.0004732370434794575
2023-01-21 11:50:10.436875: step: 852/530, loss: 0.012659072875976562
2023-01-21 11:50:11.557210: step: 856/530, loss: 0.03408327326178551
2023-01-21 11:50:12.646528: step: 860/530, loss: 0.44312822818756104
2023-01-21 11:50:13.723219: step: 864/530, loss: 0.005470371339470148
2023-01-21 11:50:14.860728: step: 868/530, loss: 0.0005792618030682206
2023-01-21 11:50:15.970345: step: 872/530, loss: 0.010272979736328125
2023-01-21 11:50:17.075845: step: 876/530, loss: 0.0034227371215820312
2023-01-21 11:50:18.180797: step: 880/530, loss: 0.030771778896450996
2023-01-21 11:50:19.275123: step: 884/530, loss: 0.6555532217025757
2023-01-21 11:50:20.368057: step: 888/530, loss: 2.498626781743951e-05
2023-01-21 11:50:21.475622: step: 892/530, loss: 2.8908289095852524e-07
2023-01-21 11:50:22.575301: step: 896/530, loss: 0.0002452850458212197
2023-01-21 11:50:23.686359: step: 900/530, loss: 0.009789371863007545
2023-01-21 11:50:24.827746: step: 904/530, loss: 0.7422406077384949
2023-01-21 11:50:25.898603: step: 908/530, loss: 0.06669817864894867
2023-01-21 11:50:27.046522: step: 912/530, loss: 0.0007894918671809137
2023-01-21 11:50:28.181868: step: 916/530, loss: 0.015140151605010033
2023-01-21 11:50:29.280080: step: 920/530, loss: 0.0004150390450377017
2023-01-21 11:50:30.389657: step: 924/530, loss: 0.00042724609375
2023-01-21 11:50:31.512117: step: 928/530, loss: 9.1552734375e-05
2023-01-21 11:50:32.626933: step: 932/530, loss: 0.004136275965720415
2023-01-21 11:50:33.765848: step: 936/530, loss: 0.004865026567131281
2023-01-21 11:50:34.878497: step: 940/530, loss: 0.01209402084350586
2023-01-21 11:50:35.981972: step: 944/530, loss: 0.9639291763305664
2023-01-21 11:50:37.102335: step: 948/530, loss: 0.001890468643978238
2023-01-21 11:50:38.258238: step: 952/530, loss: 0.04224586859345436
2023-01-21 11:50:39.346404: step: 956/530, loss: 0.021381568163633347
2023-01-21 11:50:40.478992: step: 960/530, loss: 0.006392288487404585
2023-01-21 11:50:41.607632: step: 964/530, loss: 0.025151537731289864
2023-01-21 11:50:42.705041: step: 968/530, loss: 0.068425752222538
2023-01-21 11:50:43.793437: step: 972/530, loss: 0.0042781829833984375
2023-01-21 11:50:44.874612: step: 976/530, loss: 0.0666540116071701
2023-01-21 11:50:45.967436: step: 980/530, loss: 0.012535477057099342
2023-01-21 11:50:47.101684: step: 984/530, loss: 0.005095815751701593
2023-01-21 11:50:48.218951: step: 988/530, loss: 0.007094860076904297
2023-01-21 11:50:49.312742: step: 992/530, loss: 0.0004225731245242059
2023-01-21 11:50:50.434100: step: 996/530, loss: 0.03543434292078018
2023-01-21 11:50:51.543506: step: 1000/530, loss: 0.013332461938261986
2023-01-21 11:50:52.659469: step: 1004/530, loss: 0.027044106274843216
2023-01-21 11:50:53.807877: step: 1008/530, loss: 0.04256897047162056
2023-01-21 11:50:54.920530: step: 1012/530, loss: 0.010259628295898438
2023-01-21 11:50:56.030007: step: 1016/530, loss: 0.02849479950964451
2023-01-21 11:50:57.121264: step: 1020/530, loss: 0.00013093948655296117
2023-01-21 11:50:58.216210: step: 1024/530, loss: 0.0160504337400198
2023-01-21 11:50:59.315530: step: 1028/530, loss: 0.0008813858148641884
2023-01-21 11:51:00.429952: step: 1032/530, loss: 0.009639930911362171
2023-01-21 11:51:01.523947: step: 1036/530, loss: 0.01188507117331028
2023-01-21 11:51:02.649228: step: 1040/530, loss: 0.16213148832321167
2023-01-21 11:51:03.747122: step: 1044/530, loss: 0.0029811635613441467
2023-01-21 11:51:04.862522: step: 1048/530, loss: 0.024472856894135475
2023-01-21 11:51:05.967196: step: 1052/530, loss: 0.0312594436109066
2023-01-21 11:51:07.043531: step: 1056/530, loss: 0.05646343529224396
2023-01-21 11:51:08.163146: step: 1060/530, loss: 0.001609897706657648
2023-01-21 11:51:09.267799: step: 1064/530, loss: 0.017012977972626686
2023-01-21 11:51:10.357266: step: 1068/530, loss: 8.544922457076609e-05
2023-01-21 11:51:11.494345: step: 1072/530, loss: 0.09310703724622726
2023-01-21 11:51:12.589327: step: 1076/530, loss: 0.0007383346674032509
2023-01-21 11:51:13.699111: step: 1080/530, loss: 0.036528777331113815
2023-01-21 11:51:14.811151: step: 1084/530, loss: 0.08380565792322159
2023-01-21 11:51:15.955227: step: 1088/530, loss: 0.004727697465568781
2023-01-21 11:51:17.041576: step: 1092/530, loss: 0.005180931184440851
2023-01-21 11:51:18.161771: step: 1096/530, loss: 0.02166728861629963
2023-01-21 11:51:19.271213: step: 1100/530, loss: 0.002404499100521207
2023-01-21 11:51:20.376357: step: 1104/530, loss: 0.0031962874345481396
2023-01-21 11:51:21.557710: step: 1108/530, loss: 0.020989038050174713
2023-01-21 11:51:22.696058: step: 1112/530, loss: 0.006503391079604626
2023-01-21 11:51:23.803259: step: 1116/530, loss: 0.019374562427401543
2023-01-21 11:51:24.933650: step: 1120/530, loss: 0.00011310577974654734
2023-01-21 11:51:26.029525: step: 1124/530, loss: 4.048794289701618e-05
2023-01-21 11:51:27.149004: step: 1128/530, loss: 0.0201478973031044
2023-01-21 11:51:28.257672: step: 1132/530, loss: 0.00022983551025390625
2023-01-21 11:51:29.343592: step: 1136/530, loss: 0.009818077087402344
2023-01-21 11:51:30.435985: step: 1140/530, loss: 0.00019598007202148438
2023-01-21 11:51:31.576630: step: 1144/530, loss: 0.009396982379257679
2023-01-21 11:51:32.669104: step: 1148/530, loss: 0.034554291516542435
2023-01-21 11:51:33.774646: step: 1152/530, loss: 0.00870513916015625
2023-01-21 11:51:34.871612: step: 1156/530, loss: 0.002601146697998047
2023-01-21 11:51:35.975850: step: 1160/530, loss: -9.5367431640625e-07
2023-01-21 11:51:37.095152: step: 1164/530, loss: 0.0006130218971520662
2023-01-21 11:51:38.209775: step: 1168/530, loss: 0.01850605010986328
2023-01-21 11:51:39.329059: step: 1172/530, loss: 0.006359672639518976
2023-01-21 11:51:40.482799: step: 1176/530, loss: 0.008261299692094326
2023-01-21 11:51:41.604178: step: 1180/530, loss: 0.0049537657760083675
2023-01-21 11:51:42.747965: step: 1184/530, loss: 0.014668751507997513
2023-01-21 11:51:43.852413: step: 1188/530, loss: 0.0007142424583435059
2023-01-21 11:51:44.975603: step: 1192/530, loss: 0.014633560553193092
2023-01-21 11:51:46.087107: step: 1196/530, loss: 0.00015501974849030375
2023-01-21 11:51:47.189385: step: 1200/530, loss: 0.009972954168915749
2023-01-21 11:51:48.292398: step: 1204/530, loss: 0.1317215859889984
2023-01-21 11:51:49.384609: step: 1208/530, loss: 0.002022361848503351
2023-01-21 11:51:50.457400: step: 1212/530, loss: 0.00047302249004133046
2023-01-21 11:51:51.581650: step: 1216/530, loss: 0.0024082183372229338
2023-01-21 11:51:52.685936: step: 1220/530, loss: 0.17281703650951385
2023-01-21 11:51:53.781281: step: 1224/530, loss: 0.03386878967285156
2023-01-21 11:51:54.890459: step: 1228/530, loss: 0.02229137346148491
2023-01-21 11:51:55.988631: step: 1232/530, loss: 4.1961669921875e-05
2023-01-21 11:51:57.084682: step: 1236/530, loss: 0.001348781632259488
2023-01-21 11:51:58.180591: step: 1240/530, loss: 1.7070771718863398e-05
2023-01-21 11:51:59.289060: step: 1244/530, loss: 0.036410141736269
2023-01-21 11:52:00.398393: step: 1248/530, loss: 0.0038714411202818155
2023-01-21 11:52:01.520389: step: 1252/530, loss: 0.07400169968605042
2023-01-21 11:52:02.664348: step: 1256/530, loss: 0.00035009384737350047
2023-01-21 11:52:03.795825: step: 1260/530, loss: 0.007288026623427868
2023-01-21 11:52:04.904397: step: 1264/530, loss: 0.0009682655218057334
2023-01-21 11:52:06.008868: step: 1268/530, loss: 8.00132766016759e-05
2023-01-21 11:52:07.097444: step: 1272/530, loss: 0.00016698837862350047
2023-01-21 11:52:08.200717: step: 1276/530, loss: 0.01668071746826172
2023-01-21 11:52:09.295829: step: 1280/530, loss: 0.045046236366033554
2023-01-21 11:52:10.396178: step: 1284/530, loss: 0.007641696836799383
2023-01-21 11:52:11.540475: step: 1288/530, loss: 0.0012553215492516756
2023-01-21 11:52:12.637495: step: 1292/530, loss: 0.007515001576393843
2023-01-21 11:52:13.769468: step: 1296/530, loss: 0.013015221804380417
2023-01-21 11:52:14.887445: step: 1300/530, loss: 0.08292216807603836
2023-01-21 11:52:15.976053: step: 1304/530, loss: 0.004078865051269531
2023-01-21 11:52:17.082886: step: 1308/530, loss: 0.04541473463177681
2023-01-21 11:52:18.189340: step: 1312/530, loss: 0.0204180721193552
2023-01-21 11:52:19.299133: step: 1316/530, loss: 0.008442306891083717
2023-01-21 11:52:20.417233: step: 1320/530, loss: 0.02502145804464817
2023-01-21 11:52:21.511330: step: 1324/530, loss: 0.005723190493881702
2023-01-21 11:52:22.607860: step: 1328/530, loss: 0.0024667263496667147
2023-01-21 11:52:23.716760: step: 1332/530, loss: 0.044756900519132614
2023-01-21 11:52:24.854453: step: 1336/530, loss: 0.03814239427447319
2023-01-21 11:52:25.951217: step: 1340/530, loss: 0.009924125857651234
2023-01-21 11:52:27.041911: step: 1344/530, loss: 0.06864146888256073
2023-01-21 11:52:28.171563: step: 1348/530, loss: 0.029261494055390358
2023-01-21 11:52:29.261976: step: 1352/530, loss: 0.013843536376953125
2023-01-21 11:52:30.346590: step: 1356/530, loss: 0.019724274054169655
2023-01-21 11:52:31.445610: step: 1360/530, loss: 0.002116656396538019
2023-01-21 11:52:32.553322: step: 1364/530, loss: 8.77380352903856e-06
2023-01-21 11:52:33.674980: step: 1368/530, loss: 0.0008076310041360557
2023-01-21 11:52:34.782060: step: 1372/530, loss: 0.004234886262565851
2023-01-21 11:52:35.923045: step: 1376/530, loss: 0.0653219223022461
2023-01-21 11:52:37.013748: step: 1380/530, loss: 0.00426483154296875
2023-01-21 11:52:38.109752: step: 1384/530, loss: 0.004421901423484087
2023-01-21 11:52:39.238856: step: 1388/530, loss: 0.03896503522992134
2023-01-21 11:52:40.324938: step: 1392/530, loss: 1.52587890625e-05
2023-01-21 11:52:41.454998: step: 1396/530, loss: 1.621246337890625e-05
2023-01-21 11:52:42.568523: step: 1400/530, loss: 0.010278606787323952
2023-01-21 11:52:43.687218: step: 1404/530, loss: 0.020675277337431908
2023-01-21 11:52:44.808757: step: 1408/530, loss: 0.00064172747079283
2023-01-21 11:52:45.908584: step: 1412/530, loss: 0.013917803764343262
2023-01-21 11:52:47.025975: step: 1416/530, loss: 4.9400332500226796e-05
2023-01-21 11:52:48.139961: step: 1420/530, loss: 0.0021236420143395662
2023-01-21 11:52:49.230114: step: 1424/530, loss: 0.0009799957042559981
2023-01-21 11:52:50.352270: step: 1428/530, loss: 0.04166078940033913
2023-01-21 11:52:51.473759: step: 1432/530, loss: 0.001198721001856029
2023-01-21 11:52:52.622983: step: 1436/530, loss: 9.279251389671117e-05
2023-01-21 11:52:53.753756: step: 1440/530, loss: 0.1728280633687973
2023-01-21 11:52:54.880742: step: 1444/530, loss: 7.343292236328125e-05
2023-01-21 11:52:55.980814: step: 1448/530, loss: 0.03286729007959366
2023-01-21 11:52:57.108487: step: 1452/530, loss: 0.06603384017944336
2023-01-21 11:52:58.202054: step: 1456/530, loss: 0.00038566591683775187
2023-01-21 11:52:59.303264: step: 1460/530, loss: 0.0004103660467080772
2023-01-21 11:53:00.390537: step: 1464/530, loss: 0.022350406274199486
2023-01-21 11:53:01.514599: step: 1468/530, loss: 8.578300185035914e-05
2023-01-21 11:53:02.612773: step: 1472/530, loss: 0.0057597397826612
2023-01-21 11:53:03.718400: step: 1476/530, loss: 1.468658410885837e-05
2023-01-21 11:53:04.830869: step: 1480/530, loss: 0.035652924329042435
2023-01-21 11:53:05.952959: step: 1484/530, loss: 0.02006225660443306
2023-01-21 11:53:07.039048: step: 1488/530, loss: 0.004315400030463934
2023-01-21 11:53:08.179271: step: 1492/530, loss: 0.0440157875418663
2023-01-21 11:53:09.317141: step: 1496/530, loss: 0.0006309509044513106
2023-01-21 11:53:10.406002: step: 1500/530, loss: 0.01628723181784153
2023-01-21 11:53:11.496988: step: 1504/530, loss: 0.0033539533615112305
2023-01-21 11:53:12.609158: step: 1508/530, loss: 0.0008552551153115928
2023-01-21 11:53:13.787214: step: 1512/530, loss: 0.0022017478477209806
2023-01-21 11:53:14.897309: step: 1516/530, loss: 0.07858486473560333
2023-01-21 11:53:16.009672: step: 1520/530, loss: 0.156391441822052
2023-01-21 11:53:17.117954: step: 1524/530, loss: 0.003317594761028886
2023-01-21 11:53:18.229149: step: 1528/530, loss: 0.0031710625626146793
2023-01-21 11:53:19.332608: step: 1532/530, loss: 0.03515835106372833
2023-01-21 11:53:20.465878: step: 1536/530, loss: 0.0077110291458666325
2023-01-21 11:53:21.595460: step: 1540/530, loss: 0.003881359240040183
2023-01-21 11:53:22.687068: step: 1544/530, loss: 0.019438840448856354
2023-01-21 11:53:23.783746: step: 1548/530, loss: 0.0017639161087572575
2023-01-21 11:53:24.919854: step: 1552/530, loss: 0.09869042038917542
2023-01-21 11:53:26.006368: step: 1556/530, loss: 0.026928137987852097
2023-01-21 11:53:27.101394: step: 1560/530, loss: 0.00115118024405092
2023-01-21 11:53:28.188775: step: 1564/530, loss: 0.0004074096796102822
2023-01-21 11:53:29.322842: step: 1568/530, loss: 0.05402183532714844
2023-01-21 11:53:30.445874: step: 1572/530, loss: 0.007879257202148438
2023-01-21 11:53:31.525943: step: 1576/530, loss: 0.016720199957489967
2023-01-21 11:53:32.666862: step: 1580/530, loss: 0.03910808637738228
2023-01-21 11:53:33.791612: step: 1584/530, loss: 0.01147689949721098
2023-01-21 11:53:34.909881: step: 1588/530, loss: 0.010814475826919079
2023-01-21 11:53:36.018714: step: 1592/530, loss: 7.90119229350239e-05
2023-01-21 11:53:37.119795: step: 1596/530, loss: 0.0009774684440344572
2023-01-21 11:53:38.252607: step: 1600/530, loss: 6.017685154802166e-05
2023-01-21 11:53:39.348202: step: 1604/530, loss: 0.00023078919912222773
2023-01-21 11:53:40.458621: step: 1608/530, loss: 0.012811469845473766
2023-01-21 11:53:41.558345: step: 1612/530, loss: 0.012253952212631702
2023-01-21 11:53:42.641791: step: 1616/530, loss: 3.2424929941043956e-06
2023-01-21 11:53:43.730091: step: 1620/530, loss: 0.0021566867362707853
2023-01-21 11:53:44.848440: step: 1624/530, loss: 0.0004830360412597656
2023-01-21 11:53:45.984988: step: 1628/530, loss: 0.027592848986387253
2023-01-21 11:53:47.083837: step: 1632/530, loss: 0.05040645971894264
2023-01-21 11:53:48.173549: step: 1636/530, loss: 0.0016323089366778731
2023-01-21 11:53:49.295437: step: 1640/530, loss: 0.014081288129091263
2023-01-21 11:53:50.432206: step: 1644/530, loss: 0.015056419186294079
2023-01-21 11:53:51.552845: step: 1648/530, loss: 0.0013641358818858862
2023-01-21 11:53:52.668966: step: 1652/530, loss: 7.83920258982107e-05
2023-01-21 11:53:53.806389: step: 1656/530, loss: 0.0814613327383995
2023-01-21 11:53:54.942578: step: 1660/530, loss: 0.02677326276898384
2023-01-21 11:53:56.079814: step: 1664/530, loss: 0.0051132203079760075
2023-01-21 11:53:57.195363: step: 1668/530, loss: 0.0009502411121502519
2023-01-21 11:53:58.344845: step: 1672/530, loss: 0.033921051770448685
2023-01-21 11:53:59.448717: step: 1676/530, loss: 0.004532623570412397
2023-01-21 11:54:00.546692: step: 1680/530, loss: 0.011680603958666325
2023-01-21 11:54:01.629062: step: 1684/530, loss: 0.06151679903268814
2023-01-21 11:54:02.738805: step: 1688/530, loss: 0.03455018997192383
2023-01-21 11:54:03.876094: step: 1692/530, loss: 0.004935741424560547
2023-01-21 11:54:04.976187: step: 1696/530, loss: 0.00011367797560524195
2023-01-21 11:54:06.087543: step: 1700/530, loss: 0.02002906985580921
2023-01-21 11:54:07.220001: step: 1704/530, loss: 0.01657142862677574
2023-01-21 11:54:08.326268: step: 1708/530, loss: 0.04720735922455788
2023-01-21 11:54:09.416296: step: 1712/530, loss: 0.00019030571274925023
2023-01-21 11:54:10.542663: step: 1716/530, loss: 0.0916501060128212
2023-01-21 11:54:11.651674: step: 1720/530, loss: 0.0005937576061114669
2023-01-21 11:54:12.791547: step: 1724/530, loss: 0.0009849548805505037
2023-01-21 11:54:13.896233: step: 1728/530, loss: 0.42615824937820435
2023-01-21 11:54:15.057591: step: 1732/530, loss: 0.014369201846420765
2023-01-21 11:54:16.166294: step: 1736/530, loss: 0.007511854637414217
2023-01-21 11:54:17.263646: step: 1740/530, loss: 0.0006941318861208856
2023-01-21 11:54:18.375977: step: 1744/530, loss: 0.01081695593893528
2023-01-21 11:54:19.480689: step: 1748/530, loss: 0.009366368874907494
2023-01-21 11:54:20.585350: step: 1752/530, loss: 0.002460479736328125
2023-01-21 11:54:21.692545: step: 1756/530, loss: 0.07039991766214371
2023-01-21 11:54:22.828903: step: 1760/530, loss: 0.006768703460693359
2023-01-21 11:54:23.945269: step: 1764/530, loss: 0.10855960845947266
2023-01-21 11:54:25.078779: step: 1768/530, loss: 0.04037828743457794
2023-01-21 11:54:26.182839: step: 1772/530, loss: 0.0015172958374023438
2023-01-21 11:54:27.294754: step: 1776/530, loss: 1.7505884898127988e-05
2023-01-21 11:54:28.424073: step: 1780/530, loss: 0.008764267899096012
2023-01-21 11:54:29.533787: step: 1784/530, loss: 0.004359626676887274
2023-01-21 11:54:30.631563: step: 1788/530, loss: 0.008399391546845436
2023-01-21 11:54:31.779157: step: 1792/530, loss: 0.024730682373046875
2023-01-21 11:54:32.885407: step: 1796/530, loss: 0.03802294656634331
2023-01-21 11:54:34.035899: step: 1800/530, loss: 0.047095589339733124
2023-01-21 11:54:35.145405: step: 1804/530, loss: 0.005465054884552956
2023-01-21 11:54:36.235465: step: 1808/530, loss: 0.00023422240337822586
2023-01-21 11:54:37.359245: step: 1812/530, loss: 0.05126752704381943
2023-01-21 11:54:38.474242: step: 1816/530, loss: 0.03438548743724823
2023-01-21 11:54:39.591923: step: 1820/530, loss: 0.04506521299481392
2023-01-21 11:54:40.692410: step: 1824/530, loss: 0.020792581140995026
2023-01-21 11:54:41.782065: step: 1828/530, loss: 0.00799856148660183
2023-01-21 11:54:42.887501: step: 1832/530, loss: 0.011962890625
2023-01-21 11:54:44.015824: step: 1836/530, loss: 0.031734466552734375
2023-01-21 11:54:45.136473: step: 1840/530, loss: 0.0014396667247638106
2023-01-21 11:54:46.249592: step: 1844/530, loss: 0.10179100185632706
2023-01-21 11:54:47.340604: step: 1848/530, loss: 0.012831592932343483
2023-01-21 11:54:48.440064: step: 1852/530, loss: 0.004360771272331476
2023-01-21 11:54:49.565249: step: 1856/530, loss: 0.0007726669427938759
2023-01-21 11:54:50.672246: step: 1860/530, loss: 0.0006330490577965975
2023-01-21 11:54:51.789300: step: 1864/530, loss: 0.005430984776467085
2023-01-21 11:54:52.905789: step: 1868/530, loss: 0.0020674229599535465
2023-01-21 11:54:54.001300: step: 1872/530, loss: 0.006577706430107355
2023-01-21 11:54:55.085730: step: 1876/530, loss: 0.00012111663818359375
2023-01-21 11:54:56.178311: step: 1880/530, loss: 0.00033164024353027344
2023-01-21 11:54:57.275986: step: 1884/530, loss: 0.03621979057788849
2023-01-21 11:54:58.383828: step: 1888/530, loss: 0.023960687220096588
2023-01-21 11:54:59.483454: step: 1892/530, loss: 0.003901863005012274
2023-01-21 11:55:00.616052: step: 1896/530, loss: 0.020878203213214874
2023-01-21 11:55:01.723438: step: 1900/530, loss: 0.0003599167102947831
2023-01-21 11:55:02.816414: step: 1904/530, loss: 0.003304100129753351
2023-01-21 11:55:03.927951: step: 1908/530, loss: 6.389618647517636e-05
2023-01-21 11:55:05.050963: step: 1912/530, loss: 0.008986282162368298
2023-01-21 11:55:06.140493: step: 1916/530, loss: 0.002562618348747492
2023-01-21 11:55:07.239413: step: 1920/530, loss: 7.114410982467234e-05
2023-01-21 11:55:08.346735: step: 1924/530, loss: 0.0005035400390625
2023-01-21 11:55:09.451798: step: 1928/530, loss: 0.00018787384033203125
2023-01-21 11:55:10.567137: step: 1932/530, loss: 0.009007548913359642
2023-01-21 11:55:11.683833: step: 1936/530, loss: 0.004380607977509499
2023-01-21 11:55:12.782416: step: 1940/530, loss: -4.00543194700731e-06
2023-01-21 11:55:13.891630: step: 1944/530, loss: 0.030496977269649506
2023-01-21 11:55:15.038885: step: 1948/530, loss: 0.018125154078006744
2023-01-21 11:55:16.150403: step: 1952/530, loss: 0.08990593254566193
2023-01-21 11:55:17.249308: step: 1956/530, loss: 0.0001548767031636089
2023-01-21 11:55:18.366637: step: 1960/530, loss: 0.14841556549072266
2023-01-21 11:55:19.478950: step: 1964/530, loss: 0.014743233099579811
2023-01-21 11:55:20.616960: step: 1968/530, loss: 0.0007826805231161416
2023-01-21 11:55:21.712765: step: 1972/530, loss: 0.0006612777942791581
2023-01-21 11:55:22.824329: step: 1976/530, loss: 0.008655548095703125
2023-01-21 11:55:23.953238: step: 1980/530, loss: 0.02308177947998047
2023-01-21 11:55:25.058574: step: 1984/530, loss: 0.001957798143848777
2023-01-21 11:55:26.162176: step: 1988/530, loss: 0.030045509338378906
2023-01-21 11:55:27.250895: step: 1992/530, loss: 0.0010838508605957031
2023-01-21 11:55:28.330937: step: 1996/530, loss: 0.0029673578683286905
2023-01-21 11:55:29.447003: step: 2000/530, loss: 0.0028097154572606087
2023-01-21 11:55:30.544431: step: 2004/530, loss: 0.0008169173961505294
2023-01-21 11:55:31.626966: step: 2008/530, loss: 0.010988712310791016
2023-01-21 11:55:32.722742: step: 2012/530, loss: 0.004591751378029585
2023-01-21 11:55:33.821999: step: 2016/530, loss: 0.00115966796875
2023-01-21 11:55:34.943422: step: 2020/530, loss: 0.022836877033114433
2023-01-21 11:55:36.030037: step: 2024/530, loss: 0.014849472790956497
2023-01-21 11:55:37.150226: step: 2028/530, loss: 0.000903701817151159
2023-01-21 11:55:38.255878: step: 2032/530, loss: 0.0006887436029501259
2023-01-21 11:55:39.382690: step: 2036/530, loss: 0.015825653448700905
2023-01-21 11:55:40.483104: step: 2040/530, loss: 0.0892999917268753
2023-01-21 11:55:41.588653: step: 2044/530, loss: 0.02092280425131321
2023-01-21 11:55:42.714500: step: 2048/530, loss: 0.007922648452222347
2023-01-21 11:55:43.796129: step: 2052/530, loss: 0.008164215832948685
2023-01-21 11:55:44.891364: step: 2056/530, loss: 0.005188322626054287
2023-01-21 11:55:46.000337: step: 2060/530, loss: 0.000285911577520892
2023-01-21 11:55:47.106808: step: 2064/530, loss: 0.0011363982921466231
2023-01-21 11:55:48.204877: step: 2068/530, loss: 0.00215568533167243
2023-01-21 11:55:49.372246: step: 2072/530, loss: 0.006918382365256548
2023-01-21 11:55:50.486123: step: 2076/530, loss: 0.025876808911561966
2023-01-21 11:55:51.606204: step: 2080/530, loss: 0.008435249328613281
2023-01-21 11:55:52.703933: step: 2084/530, loss: 0.0009778976673260331
2023-01-21 11:55:53.793624: step: 2088/530, loss: 0.0005497932434082031
2023-01-21 11:55:54.886366: step: 2092/530, loss: 0.02659912221133709
2023-01-21 11:55:56.003132: step: 2096/530, loss: 0.0002971649228129536
2023-01-21 11:55:57.081796: step: 2100/530, loss: 0.00221424107439816
2023-01-21 11:55:58.176824: step: 2104/530, loss: 0.01221923902630806
2023-01-21 11:55:59.258242: step: 2108/530, loss: 0.0394987128674984
2023-01-21 11:56:00.384596: step: 2112/530, loss: 0.012666893191635609
2023-01-21 11:56:01.498682: step: 2116/530, loss: 0.011446761898696423
2023-01-21 11:56:02.588465: step: 2120/530, loss: 0.0004986763233318925
==================================================
Loss: 0.042
--------------------
Dev: {'event': {'p': 0.5771144278606966, 'r': 0.7723035952063915, 'f1': 0.6605922551252847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Test: {'event': {'p': 0.6271949572264746, 'r': 0.8117715617715617, 'f1': 0.7076454152908306}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Korean: {'event': {'p': 0.6296296296296297, 'r': 0.5396825396825397, 'f1': 0.5811965811965812}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Russian: {'event': {'p': 0.5, 'r': 0.6111111111111112, 'f1': 0.55}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 11:56:42.221512: step: 4/530, loss: 0.013702202588319778
2023-01-21 11:56:43.333559: step: 8/530, loss: 0.0011085510486736894
2023-01-21 11:56:44.456108: step: 12/530, loss: 0.0001623153657419607
2023-01-21 11:56:45.601893: step: 16/530, loss: 0.001183366752229631
2023-01-21 11:56:46.689786: step: 20/530, loss: 0.000568008457776159
2023-01-21 11:56:47.761950: step: 24/530, loss: 0.0005524635780602694
2023-01-21 11:56:48.879500: step: 28/530, loss: 0.009451866149902344
2023-01-21 11:56:49.983490: step: 32/530, loss: 0.06998118758201599
2023-01-21 11:56:51.112027: step: 36/530, loss: 0.04846648871898651
2023-01-21 11:56:52.231593: step: 40/530, loss: 0.007088661193847656
2023-01-21 11:56:53.305574: step: 44/530, loss: 0.019867420196533203
2023-01-21 11:56:54.442604: step: 48/530, loss: 0.0013003349304199219
2023-01-21 11:56:55.539781: step: 52/530, loss: 0.01750764809548855
2023-01-21 11:56:56.639646: step: 56/530, loss: 0.011864567175507545
2023-01-21 11:56:57.733338: step: 60/530, loss: 0.00046215057955123484
2023-01-21 11:56:58.817793: step: 64/530, loss: 0.0007159233209677041
2023-01-21 11:56:59.912109: step: 68/530, loss: 0.007852363400161266
2023-01-21 11:57:00.998190: step: 72/530, loss: 0.00015840530977584422
2023-01-21 11:57:02.088271: step: 76/530, loss: 0.007292747963219881
2023-01-21 11:57:03.184590: step: 80/530, loss: 0.00016679764667060226
2023-01-21 11:57:04.292205: step: 84/530, loss: 0.015070153400301933
2023-01-21 11:57:05.364161: step: 88/530, loss: 0.0012836456298828125
2023-01-21 11:57:06.455611: step: 92/530, loss: 0.0015808106400072575
2023-01-21 11:57:07.564785: step: 96/530, loss: 0.0002468109014444053
2023-01-21 11:57:08.660486: step: 100/530, loss: 0.002647066256031394
2023-01-21 11:57:09.751987: step: 104/530, loss: 0.02456836774945259
2023-01-21 11:57:10.869473: step: 108/530, loss: 0.06033115088939667
2023-01-21 11:57:11.967781: step: 112/530, loss: 1.819133831304498e-05
2023-01-21 11:57:13.057053: step: 116/530, loss: 0.016558362171053886
2023-01-21 11:57:14.139459: step: 120/530, loss: 0.029140951111912727
2023-01-21 11:57:15.239638: step: 124/530, loss: 0.04360942915081978
2023-01-21 11:57:16.367376: step: 128/530, loss: 0.047702886164188385
2023-01-21 11:57:17.471169: step: 132/530, loss: 0.00558738736435771
2023-01-21 11:57:18.578949: step: 136/530, loss: 0.004562950227409601
2023-01-21 11:57:19.688699: step: 140/530, loss: 0.0001352310209767893
2023-01-21 11:57:20.818757: step: 144/530, loss: 0.0012454986572265625
2023-01-21 11:57:21.919767: step: 148/530, loss: 0.03179344907402992
2023-01-21 11:57:23.018936: step: 152/530, loss: 0.8701611161231995
2023-01-21 11:57:24.107135: step: 156/530, loss: 0.0002997875271830708
2023-01-21 11:57:25.222892: step: 160/530, loss: 0.000621795654296875
2023-01-21 11:57:26.327339: step: 164/530, loss: 0.02601451799273491
2023-01-21 11:57:27.476958: step: 168/530, loss: 0.018696118146181107
2023-01-21 11:57:28.586198: step: 172/530, loss: 0.0031511306297034025
2023-01-21 11:57:29.694059: step: 176/530, loss: 0.0005868911975994706
2023-01-21 11:57:30.796213: step: 180/530, loss: 0.00574684189632535
2023-01-21 11:57:31.896390: step: 184/530, loss: 0.03121156617999077
2023-01-21 11:57:32.997096: step: 188/530, loss: 0.0011748314136639237
2023-01-21 11:57:34.122576: step: 192/530, loss: 0.01318140048533678
2023-01-21 11:57:35.222341: step: 196/530, loss: 0.02394542656838894
2023-01-21 11:57:36.347322: step: 200/530, loss: 0.007840156555175781
2023-01-21 11:57:37.438103: step: 204/530, loss: 0.04470319673418999
2023-01-21 11:57:38.535497: step: 208/530, loss: 0.0007863998762331903
2023-01-21 11:57:39.651047: step: 212/530, loss: 0.0051017762161791325
2023-01-21 11:57:40.771850: step: 216/530, loss: 0.012769317254424095
2023-01-21 11:57:41.864017: step: 220/530, loss: 0.0030887604225426912
2023-01-21 11:57:42.941004: step: 224/530, loss: 0.009069729596376419
2023-01-21 11:57:44.061416: step: 228/530, loss: 0.014878702349960804
2023-01-21 11:57:45.151146: step: 232/530, loss: 0.007018184754997492
2023-01-21 11:57:46.218753: step: 236/530, loss: 0.015143834054470062
2023-01-21 11:57:47.353776: step: 240/530, loss: 0.07363662868738174
2023-01-21 11:57:48.463086: step: 244/530, loss: 0.06507330387830734
2023-01-21 11:57:49.577635: step: 248/530, loss: 0.0012275695335119963
2023-01-21 11:57:50.684339: step: 252/530, loss: 0.009775925427675247
2023-01-21 11:57:51.820294: step: 256/530, loss: 0.003391456790268421
2023-01-21 11:57:52.997434: step: 260/530, loss: 0.02909889444708824
2023-01-21 11:57:54.081860: step: 264/530, loss: 1.9550323031580774e-06
2023-01-21 11:57:55.197444: step: 268/530, loss: 0.012193870730698109
2023-01-21 11:57:56.342925: step: 272/530, loss: 0.0007455825689248741
2023-01-21 11:57:57.440528: step: 276/530, loss: 9.193420555675402e-05
2023-01-21 11:57:58.548429: step: 280/530, loss: 0.008006667718291283
2023-01-21 11:57:59.679758: step: 284/530, loss: 0.00024709702120162547
2023-01-21 11:58:00.769872: step: 288/530, loss: 0.0006490707746706903
2023-01-21 11:58:01.861071: step: 292/530, loss: 0.03775904327630997
2023-01-21 11:58:03.019368: step: 296/530, loss: 0.06860389560461044
2023-01-21 11:58:04.120322: step: 300/530, loss: 0.025400161743164062
2023-01-21 11:58:05.246214: step: 304/530, loss: 0.11770230531692505
2023-01-21 11:58:06.360269: step: 308/530, loss: 0.004616546910256147
2023-01-21 11:58:07.476286: step: 312/530, loss: 0.0016580582596361637
2023-01-21 11:58:08.558563: step: 316/530, loss: 0.037839125841856
2023-01-21 11:58:09.634952: step: 320/530, loss: 0.006119346711784601
2023-01-21 11:58:10.746098: step: 324/530, loss: 0.0006593704456463456
2023-01-21 11:58:11.844938: step: 328/530, loss: 0.0012426853645592928
2023-01-21 11:58:12.936514: step: 332/530, loss: 0.008990669623017311
2023-01-21 11:58:14.042184: step: 336/530, loss: 0.0012235641479492188
2023-01-21 11:58:15.138982: step: 340/530, loss: 0.05049324035644531
2023-01-21 11:58:16.264495: step: 344/530, loss: 5.760193016612902e-05
2023-01-21 11:58:17.368842: step: 348/530, loss: 0.0004986763233318925
2023-01-21 11:58:18.476534: step: 352/530, loss: 0.0029499055817723274
2023-01-21 11:58:19.578087: step: 356/530, loss: 0.004632187075912952
2023-01-21 11:58:20.675792: step: 360/530, loss: 0.019753742963075638
2023-01-21 11:58:21.783891: step: 364/530, loss: -4.8220157623291016e-05
2023-01-21 11:58:22.903070: step: 368/530, loss: 0.0250410083681345
2023-01-21 11:58:24.026920: step: 372/530, loss: 0.06525502353906631
2023-01-21 11:58:25.134620: step: 376/530, loss: 0.002073430921882391
2023-01-21 11:58:26.224965: step: 380/530, loss: 0.022220993414521217
2023-01-21 11:58:27.322456: step: 384/530, loss: 0.0005358696216717362
2023-01-21 11:58:28.414896: step: 388/530, loss: 0.00350189208984375
2023-01-21 11:58:29.495849: step: 392/530, loss: 0.003215694334357977
2023-01-21 11:58:30.594379: step: 396/530, loss: 0.0018817901145666838
2023-01-21 11:58:31.672251: step: 400/530, loss: 0.0002195358247263357
2023-01-21 11:58:32.773508: step: 404/530, loss: 0.011682892218232155
2023-01-21 11:58:33.889687: step: 408/530, loss: 0.0019309043418616056
2023-01-21 11:58:34.994449: step: 412/530, loss: 0.035097602754831314
2023-01-21 11:58:36.104872: step: 416/530, loss: 0.038558389991521835
2023-01-21 11:58:37.201592: step: 420/530, loss: 0.009222984313964844
2023-01-21 11:58:38.260925: step: 424/530, loss: 0.004097986500710249
2023-01-21 11:58:39.364975: step: 428/530, loss: 0.0017765045631676912
2023-01-21 11:58:40.487762: step: 432/530, loss: 0.015746690332889557
2023-01-21 11:58:41.593468: step: 436/530, loss: 0.0035184859298169613
2023-01-21 11:58:42.683254: step: 440/530, loss: 0.004490661434829235
2023-01-21 11:58:43.801307: step: 444/530, loss: 6.985665095271543e-05
2023-01-21 11:58:44.903584: step: 448/530, loss: 0.0006153106805868447
2023-01-21 11:58:45.998215: step: 452/530, loss: 0.0016108513809740543
2023-01-21 11:58:47.089532: step: 456/530, loss: 0.0014966963790357113
2023-01-21 11:58:48.224305: step: 460/530, loss: 0.010564805008471012
2023-01-21 11:58:49.306595: step: 464/530, loss: 0.005067062564194202
2023-01-21 11:58:50.471665: step: 468/530, loss: 0.022270966321229935
2023-01-21 11:58:51.586054: step: 472/530, loss: 0.00055017473641783
2023-01-21 11:58:52.702171: step: 476/530, loss: 0.0006603241199627519
2023-01-21 11:58:53.799610: step: 480/530, loss: 0.021640967577695847
2023-01-21 11:58:54.954346: step: 484/530, loss: 0.0022422790061682463
2023-01-21 11:58:56.071067: step: 488/530, loss: 0.0013174057239666581
2023-01-21 11:58:57.165872: step: 492/530, loss: 0.004908084869384766
2023-01-21 11:58:58.259029: step: 496/530, loss: 0.01400079671293497
2023-01-21 11:58:59.353639: step: 500/530, loss: 0.0022152424789965153
2023-01-21 11:59:00.460351: step: 504/530, loss: 0.0030012130737304688
2023-01-21 11:59:01.564781: step: 508/530, loss: 0.001694679376669228
2023-01-21 11:59:02.639508: step: 512/530, loss: 0.0004158973752055317
2023-01-21 11:59:03.755270: step: 516/530, loss: 0.06253807246685028
2023-01-21 11:59:04.843592: step: 520/530, loss: 0.01295175589621067
2023-01-21 11:59:05.953714: step: 524/530, loss: 0.05713405832648277
2023-01-21 11:59:07.061561: step: 528/530, loss: 0.21823176741600037
2023-01-21 11:59:08.160171: step: 532/530, loss: 0.0009615898597985506
2023-01-21 11:59:09.254876: step: 536/530, loss: 1.9073486328125e-06
2023-01-21 11:59:10.357119: step: 540/530, loss: 0.011937523260712624
2023-01-21 11:59:11.446506: step: 544/530, loss: 0.0006996155134402215
2023-01-21 11:59:12.546908: step: 548/530, loss: 0.03397512435913086
2023-01-21 11:59:13.693772: step: 552/530, loss: 0.02670135535299778
2023-01-21 11:59:14.799306: step: 556/530, loss: 0.047303106635808945
2023-01-21 11:59:15.859758: step: 560/530, loss: 1.730919029796496e-05
2023-01-21 11:59:16.999622: step: 564/530, loss: 0.0040111541748046875
2023-01-21 11:59:18.121292: step: 568/530, loss: 0.0013871192932128906
2023-01-21 11:59:19.250752: step: 572/530, loss: 0.004490089137107134
2023-01-21 11:59:20.364138: step: 576/530, loss: 0.004046845715492964
2023-01-21 11:59:21.474310: step: 580/530, loss: 0.02622690238058567
2023-01-21 11:59:22.574842: step: 584/530, loss: 0.00133848178666085
2023-01-21 11:59:23.666127: step: 588/530, loss: 0.0017461776733398438
2023-01-21 11:59:24.824253: step: 592/530, loss: 0.019324207678437233
2023-01-21 11:59:25.939241: step: 596/530, loss: 0.003932380583137274
2023-01-21 11:59:27.037752: step: 600/530, loss: 0.0020681379828602076
2023-01-21 11:59:28.142019: step: 604/530, loss: 0.007012557704001665
2023-01-21 11:59:29.231945: step: 608/530, loss: 0.008876514621078968
2023-01-21 11:59:30.356368: step: 612/530, loss: 0.0004070281866006553
2023-01-21 11:59:31.436473: step: 616/530, loss: 0.03316166624426842
2023-01-21 11:59:32.542597: step: 620/530, loss: 0.007374954409897327
2023-01-21 11:59:33.660023: step: 624/530, loss: 0.005403781309723854
2023-01-21 11:59:34.794260: step: 628/530, loss: 0.013536644168198109
2023-01-21 11:59:35.879022: step: 632/530, loss: 9.51766996877268e-05
2023-01-21 11:59:36.988682: step: 636/530, loss: 6.29425048828125e-05
2023-01-21 11:59:38.076303: step: 640/530, loss: 0.004754448309540749
2023-01-21 11:59:39.166120: step: 644/530, loss: 0.0035243036691099405
2023-01-21 11:59:40.280334: step: 648/530, loss: 0.003586387727409601
2023-01-21 11:59:41.411702: step: 652/530, loss: 0.01120004616677761
2023-01-21 11:59:42.493411: step: 656/530, loss: 0.01255579013377428
2023-01-21 11:59:43.602558: step: 660/530, loss: 0.03167724609375
2023-01-21 11:59:44.696265: step: 664/530, loss: 0.004136466886848211
2023-01-21 11:59:45.780884: step: 668/530, loss: 0.0165910255163908
2023-01-21 11:59:46.863984: step: 672/530, loss: 0.00047321320744231343
2023-01-21 11:59:47.992339: step: 676/530, loss: 0.08018293976783752
2023-01-21 11:59:49.102813: step: 680/530, loss: 0.0019296646350994706
2023-01-21 11:59:50.230975: step: 684/530, loss: 3.7765505112474784e-05
2023-01-21 11:59:51.342308: step: 688/530, loss: -4.673004241340095e-06
2023-01-21 11:59:52.426888: step: 692/530, loss: 0.007663154974579811
2023-01-21 11:59:53.531507: step: 696/530, loss: 0.024094389751553535
2023-01-21 11:59:54.711948: step: 700/530, loss: 0.09568710625171661
2023-01-21 11:59:55.842965: step: 704/530, loss: 0.0001312255917582661
2023-01-21 11:59:56.954890: step: 708/530, loss: 0.0025327682960778475
2023-01-21 11:59:58.087099: step: 712/530, loss: 0.011421775445342064
2023-01-21 11:59:59.204592: step: 716/530, loss: 0.0010828018421307206
2023-01-21 12:00:00.343715: step: 720/530, loss: 0.007840251550078392
2023-01-21 12:00:01.454393: step: 724/530, loss: 0.00012283325486350805
2023-01-21 12:00:02.578050: step: 728/530, loss: 0.12658576667308807
2023-01-21 12:00:03.649214: step: 732/530, loss: 0.0002840518718585372
2023-01-21 12:00:04.767680: step: 736/530, loss: 0.001406002091243863
2023-01-21 12:00:05.863835: step: 740/530, loss: 0.0004659653059206903
2023-01-21 12:00:06.969698: step: 744/530, loss: 1.8501283193472773e-05
2023-01-21 12:00:08.088332: step: 748/530, loss: 0.03036480024456978
2023-01-21 12:00:09.203865: step: 752/530, loss: 0.146479994058609
2023-01-21 12:00:10.301770: step: 756/530, loss: 3.280639793956652e-05
2023-01-21 12:00:11.419248: step: 760/530, loss: 0.0037858011201024055
2023-01-21 12:00:12.528963: step: 764/530, loss: 0.0036580085288733244
2023-01-21 12:00:13.662292: step: 768/530, loss: 0.0005910873296670616
2023-01-21 12:00:14.770233: step: 772/530, loss: 0.0027942657470703125
2023-01-21 12:00:15.833208: step: 776/530, loss: 0.004878806881606579
2023-01-21 12:00:16.958833: step: 780/530, loss: 0.030193326994776726
2023-01-21 12:00:18.051561: step: 784/530, loss: 0.003887701081112027
2023-01-21 12:00:19.189091: step: 788/530, loss: 0.07249746471643448
2023-01-21 12:00:20.300609: step: 792/530, loss: 0.00020618439884856343
2023-01-21 12:00:21.411239: step: 796/530, loss: 0.004320526495575905
2023-01-21 12:00:22.514573: step: 800/530, loss: -5.817413239128655e-06
2023-01-21 12:00:23.605676: step: 804/530, loss: 0.0012645244132727385
2023-01-21 12:00:24.706873: step: 808/530, loss: 0.10172891616821289
2023-01-21 12:00:25.822078: step: 812/530, loss: 0.027861882001161575
2023-01-21 12:00:26.942955: step: 816/530, loss: 9.536744300930877e-07
2023-01-21 12:00:28.035628: step: 820/530, loss: 0.015621853061020374
2023-01-21 12:00:29.109843: step: 824/530, loss: 0.00679359445348382
2023-01-21 12:00:30.201226: step: 828/530, loss: 0.006345176603645086
2023-01-21 12:00:31.334316: step: 832/530, loss: 0.0034237862564623356
2023-01-21 12:00:32.425237: step: 836/530, loss: 0.013395404443144798
2023-01-21 12:00:33.517406: step: 840/530, loss: 0.0001733779936330393
2023-01-21 12:00:34.619282: step: 844/530, loss: 0.00018520356388762593
2023-01-21 12:00:35.717278: step: 848/530, loss: 0.02094755321741104
2023-01-21 12:00:36.838678: step: 852/530, loss: 0.07129726558923721
2023-01-21 12:00:37.921434: step: 856/530, loss: 0.003086281009018421
2023-01-21 12:00:39.017698: step: 860/530, loss: 0.00028972624568268657
2023-01-21 12:00:40.115344: step: 864/530, loss: 0.020303726196289062
2023-01-21 12:00:41.230958: step: 868/530, loss: 0.028679655864834785
2023-01-21 12:00:42.340510: step: 872/530, loss: 0.05021009221673012
2023-01-21 12:00:43.427716: step: 876/530, loss: 0.015396595932543278
2023-01-21 12:00:44.530902: step: 880/530, loss: 0.005320835392922163
2023-01-21 12:00:45.631094: step: 884/530, loss: 0.006844186689704657
2023-01-21 12:00:46.781463: step: 888/530, loss: 0.0005314826848916709
2023-01-21 12:00:47.877335: step: 892/530, loss: 0.015700342133641243
2023-01-21 12:00:48.974336: step: 896/530, loss: 2.3365020751953125e-05
2023-01-21 12:00:50.100310: step: 900/530, loss: 0.0110359201207757
2023-01-21 12:00:51.216122: step: 904/530, loss: 0.008791351690888405
2023-01-21 12:00:52.331526: step: 908/530, loss: 0.0004482269287109375
2023-01-21 12:00:53.429041: step: 912/530, loss: 4.4441225327318534e-05
2023-01-21 12:00:54.546610: step: 916/530, loss: 0.021976852789521217
2023-01-21 12:00:55.662271: step: 920/530, loss: 0.008385514840483665
2023-01-21 12:00:56.802504: step: 924/530, loss: 0.007043648045510054
2023-01-21 12:00:57.891994: step: 928/530, loss: 0.004284095950424671
2023-01-21 12:00:59.006304: step: 932/530, loss: 0.0027051924262195826
2023-01-21 12:01:00.110361: step: 936/530, loss: 0.012682247906923294
2023-01-21 12:01:01.212648: step: 940/530, loss: 0.05198821797966957
2023-01-21 12:01:02.317727: step: 944/530, loss: 0.08935842663049698
2023-01-21 12:01:03.425197: step: 948/530, loss: 1.7833710444392636e-05
2023-01-21 12:01:04.528816: step: 952/530, loss: 0.006075191777199507
2023-01-21 12:01:05.632740: step: 956/530, loss: 0.14893826842308044
2023-01-21 12:01:06.768994: step: 960/530, loss: 0.0017613411182537675
2023-01-21 12:01:07.881013: step: 964/530, loss: 0.009627008810639381
2023-01-21 12:01:09.005253: step: 968/530, loss: 0.020511675626039505
2023-01-21 12:01:10.143631: step: 972/530, loss: 0.020804787054657936
2023-01-21 12:01:11.274036: step: 976/530, loss: 0.0073333741165697575
2023-01-21 12:01:12.399641: step: 980/530, loss: 0.0011839866638183594
2023-01-21 12:01:13.492105: step: 984/530, loss: 9.016990952659398e-05
2023-01-21 12:01:14.581533: step: 988/530, loss: 0.005725824739784002
2023-01-21 12:01:15.697022: step: 992/530, loss: 0.0002807617129292339
2023-01-21 12:01:16.821861: step: 996/530, loss: 0.0009922027820721269
2023-01-21 12:01:17.920344: step: 1000/530, loss: 0.0020875930786132812
2023-01-21 12:01:19.009675: step: 1004/530, loss: 0.0006810188642702997
2023-01-21 12:01:20.102763: step: 1008/530, loss: 6.794929504394531e-05
2023-01-21 12:01:21.207056: step: 1012/530, loss: 0.007236385717988014
2023-01-21 12:01:22.326368: step: 1016/530, loss: 0.003933525178581476
2023-01-21 12:01:23.432500: step: 1020/530, loss: 0.0019006729125976562
2023-01-21 12:01:24.518185: step: 1024/530, loss: 0.00023651123046875
2023-01-21 12:01:25.648922: step: 1028/530, loss: 0.04137764126062393
2023-01-21 12:01:26.747081: step: 1032/530, loss: -2.8610227218450746e-06
2023-01-21 12:01:27.847712: step: 1036/530, loss: 0.06641516089439392
2023-01-21 12:01:28.938570: step: 1040/530, loss: 0.0001000881238724105
2023-01-21 12:01:30.025807: step: 1044/530, loss: 0.011546516790986061
2023-01-21 12:01:31.119252: step: 1048/530, loss: 0.00047621727571822703
2023-01-21 12:01:32.229929: step: 1052/530, loss: 0.025702668353915215
2023-01-21 12:01:33.300313: step: 1056/530, loss: 0.00927886925637722
2023-01-21 12:01:34.396056: step: 1060/530, loss: 0.0007946968544274569
2023-01-21 12:01:35.498837: step: 1064/530, loss: 0.003356552217155695
2023-01-21 12:01:36.627541: step: 1068/530, loss: 0.10069771111011505
2023-01-21 12:01:37.717792: step: 1072/530, loss: 0.023482704535126686
2023-01-21 12:01:38.821281: step: 1076/530, loss: -2.346038854739163e-05
2023-01-21 12:01:39.924183: step: 1080/530, loss: 0.003303623292595148
2023-01-21 12:01:40.993643: step: 1084/530, loss: 0.0033012391068041325
2023-01-21 12:01:42.108636: step: 1088/530, loss: 0.0002801895316224545
2023-01-21 12:01:43.225960: step: 1092/530, loss: 0.0003284454287495464
2023-01-21 12:01:44.343242: step: 1096/530, loss: 0.002607154892757535
2023-01-21 12:01:45.440847: step: 1100/530, loss: 0.003906536381691694
2023-01-21 12:01:46.521573: step: 1104/530, loss: 0.0004486083926167339
2023-01-21 12:01:47.613479: step: 1108/530, loss: 0.0004220008850097656
2023-01-21 12:01:48.724386: step: 1112/530, loss: 0.002198886824771762
2023-01-21 12:01:49.842940: step: 1116/530, loss: 0.036374930292367935
2023-01-21 12:01:50.959462: step: 1120/530, loss: 0.06577225029468536
2023-01-21 12:01:52.085151: step: 1124/530, loss: 0.03767261654138565
2023-01-21 12:01:53.226563: step: 1128/530, loss: 3.633499363786541e-05
2023-01-21 12:01:54.308466: step: 1132/530, loss: 0.007889151573181152
2023-01-21 12:01:55.389443: step: 1136/530, loss: 0.0010631084442138672
2023-01-21 12:01:56.498320: step: 1140/530, loss: 0.022317886352539062
2023-01-21 12:01:57.607929: step: 1144/530, loss: 0.01177682913839817
2023-01-21 12:01:58.694805: step: 1148/530, loss: 0.000872707343660295
2023-01-21 12:01:59.778173: step: 1152/530, loss: 0.007864522747695446
2023-01-21 12:02:00.898852: step: 1156/530, loss: 0.004351616371423006
2023-01-21 12:02:02.028749: step: 1160/530, loss: 0.007796669378876686
2023-01-21 12:02:03.138682: step: 1164/530, loss: 0.002498817630112171
2023-01-21 12:02:04.286892: step: 1168/530, loss: 0.00023498536029364914
2023-01-21 12:02:05.411395: step: 1172/530, loss: 0.006945705506950617
2023-01-21 12:02:06.487061: step: 1176/530, loss: 0.014984702691435814
2023-01-21 12:02:07.563112: step: 1180/530, loss: 0.007767581846565008
2023-01-21 12:02:08.655570: step: 1184/530, loss: 0.10443844646215439
2023-01-21 12:02:09.756394: step: 1188/530, loss: 0.008370781317353249
2023-01-21 12:02:10.861181: step: 1192/530, loss: 0.00087823870126158
2023-01-21 12:02:11.952047: step: 1196/530, loss: 0.013243675231933594
2023-01-21 12:02:13.030198: step: 1200/530, loss: 0.010766602121293545
2023-01-21 12:02:14.124991: step: 1204/530, loss: 0.0030880451668053865
2023-01-21 12:02:15.269293: step: 1208/530, loss: 0.0040108682587742805
2023-01-21 12:02:16.362665: step: 1212/530, loss: 0.0008795738685876131
2023-01-21 12:02:17.458183: step: 1216/530, loss: 0.00023183823213912547
2023-01-21 12:02:18.551169: step: 1220/530, loss: 0.01147537212818861
2023-01-21 12:02:19.682791: step: 1224/530, loss: 0.0035400390625
2023-01-21 12:02:20.817586: step: 1228/530, loss: 0.004630470648407936
2023-01-21 12:02:21.927762: step: 1232/530, loss: 0.0013826369540765882
2023-01-21 12:02:23.022455: step: 1236/530, loss: 0.0034570693969726562
2023-01-21 12:02:24.134024: step: 1240/530, loss: 0.029636478051543236
2023-01-21 12:02:25.222002: step: 1244/530, loss: 0.003082466311752796
2023-01-21 12:02:26.356850: step: 1248/530, loss: 5.6076052715070546e-05
2023-01-21 12:02:27.450640: step: 1252/530, loss: 0.004104518797248602
2023-01-21 12:02:28.548717: step: 1256/530, loss: 0.005885315127670765
2023-01-21 12:02:29.674681: step: 1260/530, loss: 0.00041828156099654734
2023-01-21 12:02:30.767608: step: 1264/530, loss: 0.006185627076774836
2023-01-21 12:02:31.874280: step: 1268/530, loss: 0.0018439292907714844
2023-01-21 12:02:32.986627: step: 1272/530, loss: 0.043486595153808594
2023-01-21 12:02:34.082801: step: 1276/530, loss: 0.0005762100336141884
2023-01-21 12:02:35.200870: step: 1280/530, loss: 0.04392519220709801
2023-01-21 12:02:36.326701: step: 1284/530, loss: 0.020858382806181908
2023-01-21 12:02:37.458425: step: 1288/530, loss: 0.0015802383422851562
2023-01-21 12:02:38.573824: step: 1292/530, loss: 0.001987361814826727
2023-01-21 12:02:39.701165: step: 1296/530, loss: 2.520737886428833
2023-01-21 12:02:40.810973: step: 1300/530, loss: 0.0012183666694909334
2023-01-21 12:02:41.916320: step: 1304/530, loss: 0.00046410562936216593
2023-01-21 12:02:42.999040: step: 1308/530, loss: 0.004085922613739967
2023-01-21 12:02:44.093951: step: 1312/530, loss: 0.0003492355172056705
2023-01-21 12:02:45.187439: step: 1316/530, loss: 0.1049533411860466
2023-01-21 12:02:46.289234: step: 1320/530, loss: 0.002922534942626953
2023-01-21 12:02:47.418573: step: 1324/530, loss: 0.011168098077178001
2023-01-21 12:02:48.566856: step: 1328/530, loss: 0.03147849813103676
2023-01-21 12:02:49.675670: step: 1332/530, loss: 0.016718769446015358
2023-01-21 12:02:50.809920: step: 1336/530, loss: 0.003756809514015913
2023-01-21 12:02:51.920195: step: 1340/530, loss: 0.00523719796910882
2023-01-21 12:02:53.029932: step: 1344/530, loss: 2.593994213384576e-05
2023-01-21 12:02:54.132601: step: 1348/530, loss: 0.013735294342041016
2023-01-21 12:02:55.249452: step: 1352/530, loss: 0.022109031677246094
2023-01-21 12:02:56.378049: step: 1356/530, loss: 3.452301098150201e-05
2023-01-21 12:02:57.490739: step: 1360/530, loss: 0.016129398718476295
2023-01-21 12:02:58.585780: step: 1364/530, loss: 9.5367431640625e-06
2023-01-21 12:02:59.672631: step: 1368/530, loss: 0.0016930580604821444
2023-01-21 12:03:00.781636: step: 1372/530, loss: 0.0326780304312706
2023-01-21 12:03:01.911678: step: 1376/530, loss: 0.068964384496212
2023-01-21 12:03:03.021845: step: 1380/530, loss: 0.005650997161865234
2023-01-21 12:03:04.145304: step: 1384/530, loss: 0.0001960754452738911
2023-01-21 12:03:05.248323: step: 1388/530, loss: 0.01739673502743244
2023-01-21 12:03:06.314334: step: 1392/530, loss: 0.00039539337740279734
2023-01-21 12:03:07.396889: step: 1396/530, loss: 0.0188217181712389
2023-01-21 12:03:08.499473: step: 1400/530, loss: 0.0019685744773596525
2023-01-21 12:03:09.607021: step: 1404/530, loss: 0.06984911113977432
2023-01-21 12:03:10.709369: step: 1408/530, loss: 0.0022966384422034025
2023-01-21 12:03:11.829454: step: 1412/530, loss: 0.0014090538024902344
2023-01-21 12:03:12.921371: step: 1416/530, loss: 0.036104965955019
2023-01-21 12:03:14.036339: step: 1420/530, loss: 0.008893776684999466
2023-01-21 12:03:15.153202: step: 1424/530, loss: 0.0008678436279296875
2023-01-21 12:03:16.270428: step: 1428/530, loss: 0.09487000107765198
2023-01-21 12:03:17.380515: step: 1432/530, loss: 0.005013275425881147
2023-01-21 12:03:18.486077: step: 1436/530, loss: 0.00045433046761900187
2023-01-21 12:03:19.595380: step: 1440/530, loss: 0.0005047321319580078
2023-01-21 12:03:20.726560: step: 1444/530, loss: 0.002739048097282648
2023-01-21 12:03:21.818321: step: 1448/530, loss: 0.008296584710478783
2023-01-21 12:03:22.949918: step: 1452/530, loss: 0.000815963838249445
2023-01-21 12:03:24.071828: step: 1456/530, loss: 0.017080115154385567
2023-01-21 12:03:25.186799: step: 1460/530, loss: 0.6368786692619324
2023-01-21 12:03:26.302412: step: 1464/530, loss: 5.892513751983643
2023-01-21 12:03:27.409276: step: 1468/530, loss: 0.034474946558475494
2023-01-21 12:03:28.523896: step: 1472/530, loss: 0.001537752104923129
2023-01-21 12:03:29.631036: step: 1476/530, loss: 0.027782535180449486
2023-01-21 12:03:30.738797: step: 1480/530, loss: 0.03053741529583931
2023-01-21 12:03:31.841472: step: 1484/530, loss: 0.011218547821044922
2023-01-21 12:03:32.978923: step: 1488/530, loss: 0.00045604706974700093
2023-01-21 12:03:34.078979: step: 1492/530, loss: 0.07214794307947159
2023-01-21 12:03:35.164858: step: 1496/530, loss: 0.05027732998132706
2023-01-21 12:03:36.269123: step: 1500/530, loss: 0.0002788543642964214
2023-01-21 12:03:37.362397: step: 1504/530, loss: 0.0003163337823934853
2023-01-21 12:03:38.474912: step: 1508/530, loss: 0.007839154452085495
2023-01-21 12:03:39.575839: step: 1512/530, loss: 0.05560602620244026
2023-01-21 12:03:40.665770: step: 1516/530, loss: 0.0016209125751629472
2023-01-21 12:03:41.785819: step: 1520/530, loss: 0.006072712130844593
2023-01-21 12:03:42.882169: step: 1524/530, loss: 0.07927601784467697
2023-01-21 12:03:43.963674: step: 1528/530, loss: 0.05301971361041069
2023-01-21 12:03:45.035081: step: 1532/530, loss: 0.014274120330810547
2023-01-21 12:03:46.182161: step: 1536/530, loss: 0.00013399124145507812
2023-01-21 12:03:47.305040: step: 1540/530, loss: 0.2528859078884125
2023-01-21 12:03:48.415929: step: 1544/530, loss: 0.015109063126146793
2023-01-21 12:03:49.513414: step: 1548/530, loss: 0.006765175145119429
2023-01-21 12:03:50.627767: step: 1552/530, loss: 0.005243110936135054
2023-01-21 12:03:51.752592: step: 1556/530, loss: 2.86102294921875e-05
2023-01-21 12:03:52.879886: step: 1560/530, loss: 0.011653185822069645
2023-01-21 12:03:53.970453: step: 1564/530, loss: 0.03421726077795029
2023-01-21 12:03:55.089538: step: 1568/530, loss: 0.03194742277264595
2023-01-21 12:03:56.163268: step: 1572/530, loss: 0.002777958055958152
2023-01-21 12:03:57.244269: step: 1576/530, loss: 9.393692380399443e-06
2023-01-21 12:03:58.313956: step: 1580/530, loss: 0.0002262592315673828
2023-01-21 12:03:59.414053: step: 1584/530, loss: 0.0006759644020348787
2023-01-21 12:04:00.521103: step: 1588/530, loss: 0.006273651495575905
2023-01-21 12:04:01.608177: step: 1592/530, loss: 0.001735258148983121
2023-01-21 12:04:02.740797: step: 1596/530, loss: 0.04846210405230522
2023-01-21 12:04:03.839845: step: 1600/530, loss: 0.0015045165782794356
2023-01-21 12:04:04.926837: step: 1604/530, loss: 0.004803276155143976
2023-01-21 12:04:06.043154: step: 1608/530, loss: 5.836486889165826e-05
2023-01-21 12:04:07.180802: step: 1612/530, loss: 0.021181296557188034
2023-01-21 12:04:08.281450: step: 1616/530, loss: 0.0016685485607013106
2023-01-21 12:04:09.381880: step: 1620/530, loss: 0.010678291320800781
2023-01-21 12:04:10.476829: step: 1624/530, loss: 0.0006398201221600175
2023-01-21 12:04:11.597957: step: 1628/530, loss: 0.02193737030029297
2023-01-21 12:04:12.671217: step: 1632/530, loss: 0.017219066619873047
2023-01-21 12:04:13.774903: step: 1636/530, loss: 0.005360889248549938
2023-01-21 12:04:14.910405: step: 1640/530, loss: 0.0017593384254723787
2023-01-21 12:04:16.014867: step: 1644/530, loss: 0.001151275704614818
2023-01-21 12:04:17.117328: step: 1648/530, loss: 0.037880513817071915
2023-01-21 12:04:18.224525: step: 1652/530, loss: 0.03352966159582138
2023-01-21 12:04:19.358293: step: 1656/530, loss: 0.00021305083646439016
2023-01-21 12:04:20.460005: step: 1660/530, loss: 0.004274225328117609
2023-01-21 12:04:21.582864: step: 1664/530, loss: 0.5841953158378601
2023-01-21 12:04:22.674489: step: 1668/530, loss: 0.004036832135170698
2023-01-21 12:04:23.772475: step: 1672/530, loss: 0.02430119551718235
2023-01-21 12:04:24.848298: step: 1676/530, loss: 0.010055947117507458
2023-01-21 12:04:25.948109: step: 1680/530, loss: 0.0040635112673044205
2023-01-21 12:04:27.054984: step: 1684/530, loss: 0.01917877234518528
2023-01-21 12:04:28.156404: step: 1688/530, loss: 0.0027620315086096525
2023-01-21 12:04:29.263477: step: 1692/530, loss: 0.0018906593322753906
2023-01-21 12:04:30.377414: step: 1696/530, loss: 0.045891571789979935
2023-01-21 12:04:31.473240: step: 1700/530, loss: 0.029369354248046875
2023-01-21 12:04:32.577777: step: 1704/530, loss: 2.0694733393611386e-05
2023-01-21 12:04:33.702808: step: 1708/530, loss: 0.004292869474738836
2023-01-21 12:04:34.812427: step: 1712/530, loss: 0.0661342591047287
2023-01-21 12:04:35.930736: step: 1716/530, loss: 0.0003841400321107358
2023-01-21 12:04:37.049611: step: 1720/530, loss: 0.014523698017001152
2023-01-21 12:04:38.169041: step: 1724/530, loss: 0.0015240192878991365
2023-01-21 12:04:39.305725: step: 1728/530, loss: 8.869171324477065e-06
2023-01-21 12:04:40.398739: step: 1732/530, loss: 0.0001852035493357107
2023-01-21 12:04:41.496236: step: 1736/530, loss: 0.0012662888038903475
2023-01-21 12:04:42.605967: step: 1740/530, loss: 0.0020177841652184725
2023-01-21 12:04:43.737423: step: 1744/530, loss: 0.07132712006568909
2023-01-21 12:04:44.828488: step: 1748/530, loss: 0.0010319710709154606
2023-01-21 12:04:45.919710: step: 1752/530, loss: 3.070831371587701e-05
2023-01-21 12:04:47.036546: step: 1756/530, loss: 0.0236361026763916
2023-01-21 12:04:48.128491: step: 1760/530, loss: 0.01700725592672825
2023-01-21 12:04:49.240732: step: 1764/530, loss: 0.016237638890743256
2023-01-21 12:04:50.334047: step: 1768/530, loss: 0.0021445690654218197
2023-01-21 12:04:51.447741: step: 1772/530, loss: 0.04841356351971626
2023-01-21 12:04:52.560372: step: 1776/530, loss: 8.487701961712446e-06
2023-01-21 12:04:53.645508: step: 1780/530, loss: 0.0085296630859375
2023-01-21 12:04:54.759114: step: 1784/530, loss: 0.0010553359752520919
2023-01-21 12:04:55.885781: step: 1788/530, loss: 0.055750466883182526
2023-01-21 12:04:57.013691: step: 1792/530, loss: 0.0027425766456872225
2023-01-21 12:04:58.123321: step: 1796/530, loss: 0.04624443128705025
2023-01-21 12:04:59.208889: step: 1800/530, loss: 0.005002832505851984
2023-01-21 12:05:00.306139: step: 1804/530, loss: 0.0008607864729128778
2023-01-21 12:05:01.406676: step: 1808/530, loss: 0.021225357428193092
2023-01-21 12:05:02.503443: step: 1812/530, loss: 0.00011014939082087949
2023-01-21 12:05:03.628233: step: 1816/530, loss: 8.77380352903856e-06
2023-01-21 12:05:04.778979: step: 1820/530, loss: 0.01788168027997017
2023-01-21 12:05:05.880118: step: 1824/530, loss: 0.05901694670319557
2023-01-21 12:05:07.018755: step: 1828/530, loss: 0.0024751664604991674
2023-01-21 12:05:08.154221: step: 1832/530, loss: 0.049889758229255676
2023-01-21 12:05:09.265439: step: 1836/530, loss: 0.0010969162685796618
2023-01-21 12:05:10.358597: step: 1840/530, loss: 0.0012890816433355212
2023-01-21 12:05:11.466136: step: 1844/530, loss: 8.087158494163305e-05
2023-01-21 12:05:12.569506: step: 1848/530, loss: 0.0037783621810376644
2023-01-21 12:05:13.688386: step: 1852/530, loss: 5.197524842515122e-06
2023-01-21 12:05:14.809647: step: 1856/530, loss: 0.020339393988251686
2023-01-21 12:05:15.907392: step: 1860/530, loss: 0.00945138931274414
2023-01-21 12:05:17.046714: step: 1864/530, loss: 0.02587261237204075
2023-01-21 12:05:18.153141: step: 1868/530, loss: 4.625320343620842e-06
2023-01-21 12:05:19.245755: step: 1872/530, loss: 0.0034822942689061165
2023-01-21 12:05:20.358947: step: 1876/530, loss: 0.0008013725164346397
2023-01-21 12:05:21.462557: step: 1880/530, loss: 0.016428470611572266
2023-01-21 12:05:22.510659: step: 1884/530, loss: 0.0006886482588015497
2023-01-21 12:05:23.648443: step: 1888/530, loss: 0.008295392617583275
2023-01-21 12:05:24.755560: step: 1892/530, loss: 0.028010845184326172
2023-01-21 12:05:25.847495: step: 1896/530, loss: 0.05603837966918945
2023-01-21 12:05:26.931093: step: 1900/530, loss: 0.035078953951597214
2023-01-21 12:05:28.035162: step: 1904/530, loss: 0.0004676342068705708
2023-01-21 12:05:29.165716: step: 1908/530, loss: 0.004656520672142506
2023-01-21 12:05:30.271555: step: 1912/530, loss: 5.617141869151965e-05
2023-01-21 12:05:31.404993: step: 1916/530, loss: 0.06429300457239151
2023-01-21 12:05:32.472180: step: 1920/530, loss: 0.006229258142411709
2023-01-21 12:05:33.576505: step: 1924/530, loss: 0.015364741906523705
2023-01-21 12:05:34.709254: step: 1928/530, loss: 0.09784059971570969
2023-01-21 12:05:35.792841: step: 1932/530, loss: 0.003754520323127508
2023-01-21 12:05:36.882125: step: 1936/530, loss: 0.0009252548334188759
2023-01-21 12:05:37.969335: step: 1940/530, loss: 0.021436309441924095
2023-01-21 12:05:39.108127: step: 1944/530, loss: 0.010712528601288795
2023-01-21 12:05:40.220216: step: 1948/530, loss: 0.0016798734432086349
2023-01-21 12:05:41.300484: step: 1952/530, loss: 0.000510787998791784
2023-01-21 12:05:42.382891: step: 1956/530, loss: 0.0033443449065089226
2023-01-21 12:05:43.493904: step: 1960/530, loss: 0.0024662972427904606
2023-01-21 12:05:44.590825: step: 1964/530, loss: 0.00020227434288244694
2023-01-21 12:05:45.686477: step: 1968/530, loss: 0.03358955681324005
2023-01-21 12:05:46.779393: step: 1972/530, loss: 0.06409893184900284
2023-01-21 12:05:47.888253: step: 1976/530, loss: 0.0022865296341478825
2023-01-21 12:05:48.970808: step: 1980/530, loss: 0.0816129520535469
2023-01-21 12:05:50.080103: step: 1984/530, loss: 0.024106215685606003
2023-01-21 12:05:51.200537: step: 1988/530, loss: 0.00022811889357399195
2023-01-21 12:05:52.301260: step: 1992/530, loss: 0.0008514404762536287
2023-01-21 12:05:53.404228: step: 1996/530, loss: 0.05869140848517418
2023-01-21 12:05:54.504696: step: 2000/530, loss: 0.006288766860961914
2023-01-21 12:05:55.636500: step: 2004/530, loss: 0.004698467440903187
2023-01-21 12:05:56.769344: step: 2008/530, loss: 6.0749054682673886e-05
2023-01-21 12:05:57.883909: step: 2012/530, loss: 0.37041524052619934
2023-01-21 12:05:58.983923: step: 2016/530, loss: 0.029657555744051933
2023-01-21 12:06:00.119482: step: 2020/530, loss: 3.604888843256049e-05
2023-01-21 12:06:01.273689: step: 2024/530, loss: 0.04117755964398384
2023-01-21 12:06:02.399328: step: 2028/530, loss: 0.016595078632235527
2023-01-21 12:06:03.504368: step: 2032/530, loss: 0.0004937172052450478
2023-01-21 12:06:04.579221: step: 2036/530, loss: 0.00011639595322776586
2023-01-21 12:06:05.688906: step: 2040/530, loss: 0.00011329651169944555
2023-01-21 12:06:06.795024: step: 2044/530, loss: 0.026999760419130325
2023-01-21 12:06:07.933444: step: 2048/530, loss: 0.0006911277887411416
2023-01-21 12:06:09.041990: step: 2052/530, loss: 0.00013442040653899312
2023-01-21 12:06:10.160796: step: 2056/530, loss: 0.0051156519912183285
2023-01-21 12:06:11.264113: step: 2060/530, loss: 0.10337970405817032
2023-01-21 12:06:12.358745: step: 2064/530, loss: 0.0008745193481445312
2023-01-21 12:06:13.455699: step: 2068/530, loss: 0.007480621337890625
2023-01-21 12:06:14.581063: step: 2072/530, loss: 0.0010400294559076428
2023-01-21 12:06:15.664517: step: 2076/530, loss: 0.000244140625
2023-01-21 12:06:16.762241: step: 2080/530, loss: 0.00175733573269099
2023-01-21 12:06:17.892671: step: 2084/530, loss: 0.00104265206027776
2023-01-21 12:06:19.033248: step: 2088/530, loss: 0.014296531677246094
2023-01-21 12:06:20.126154: step: 2092/530, loss: 0.10305872559547424
2023-01-21 12:06:21.246277: step: 2096/530, loss: 0.011514091864228249
2023-01-21 12:06:22.339282: step: 2100/530, loss: 0.0003814697265625
2023-01-21 12:06:23.442308: step: 2104/530, loss: 0.042704202234745026
2023-01-21 12:06:24.542686: step: 2108/530, loss: 0.0033733367454260588
2023-01-21 12:06:25.648040: step: 2112/530, loss: 0.0008620262378826737
2023-01-21 12:06:26.744121: step: 2116/530, loss: 0.0004953384632244706
2023-01-21 12:06:27.856636: step: 2120/530, loss: 0.09318371117115021
==================================================
Loss: 0.036
--------------------
Dev: {'event': {'p': 0.59958071278826, 'r': 0.7616511318242344, 'f1': 0.6709677419354839}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Test: {'event': {'p': 0.6527255639097744, 'r': 0.8094405594405595, 'f1': 0.722684703433923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Chinese: {'event': {'p': 0.6351351351351351, 'r': 0.8703703703703703, 'f1': 0.734375}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Korean: {'event': {'p': 0.7045454545454546, 'r': 0.49206349206349204, 'f1': 0.5794392523364486}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Russian: {'event': {'p': 0.4864864864864865, 'r': 0.5, 'f1': 0.4931506849315069}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 12:07:07.208988: step: 4/530, loss: 0.005220795050263405
2023-01-21 12:07:08.313905: step: 8/530, loss: 0.0014435768825933337
2023-01-21 12:07:09.391300: step: 12/530, loss: 0.010496092028915882
2023-01-21 12:07:10.525362: step: 16/530, loss: 0.022896479815244675
2023-01-21 12:07:11.643747: step: 20/530, loss: 0.0010209083557128906
2023-01-21 12:07:12.777323: step: 24/530, loss: 0.0005056381342001259
2023-01-21 12:07:13.905620: step: 28/530, loss: 0.04812159761786461
2023-01-21 12:07:15.007670: step: 32/530, loss: 0.0010648727184161544
2023-01-21 12:07:16.091920: step: 36/530, loss: 0.008623314090073109
2023-01-21 12:07:17.208291: step: 40/530, loss: 0.002969122026115656
2023-01-21 12:07:18.334244: step: 44/530, loss: 0.009552001953125
2023-01-21 12:07:19.431094: step: 48/530, loss: 0.01859302446246147
2023-01-21 12:07:20.566806: step: 52/530, loss: 0.009499549865722656
2023-01-21 12:07:21.704811: step: 56/530, loss: 0.031667519360780716
2023-01-21 12:07:22.804134: step: 60/530, loss: 2.975463939947076e-05
2023-01-21 12:07:23.919191: step: 64/530, loss: 0.021511554718017578
2023-01-21 12:07:25.036937: step: 68/530, loss: 0.28213050961494446
2023-01-21 12:07:26.163931: step: 72/530, loss: 0.0024738311767578125
2023-01-21 12:07:27.295352: step: 76/530, loss: 0.05939216911792755
2023-01-21 12:07:28.388438: step: 80/530, loss: 0.04792824015021324
2023-01-21 12:07:29.500600: step: 84/530, loss: 0.0018741608364507556
2023-01-21 12:07:30.594812: step: 88/530, loss: 0.002627086825668812
2023-01-21 12:07:31.695521: step: 92/530, loss: 0.032552435994148254
2023-01-21 12:07:32.787817: step: 96/530, loss: 0.00012044906907249242
2023-01-21 12:07:33.941173: step: 100/530, loss: 0.013947868719696999
2023-01-21 12:07:35.071299: step: 104/530, loss: 0.0003714561462402344
2023-01-21 12:07:36.170097: step: 108/530, loss: 0.026905346661806107
2023-01-21 12:07:37.320531: step: 112/530, loss: 0.0006355285877361894
2023-01-21 12:07:38.413483: step: 116/530, loss: 0.00066547398455441
2023-01-21 12:07:39.500023: step: 120/530, loss: 0.00015764236741233617
2023-01-21 12:07:40.586987: step: 124/530, loss: 0.000476646440802142
2023-01-21 12:07:41.687596: step: 128/530, loss: 0.0022202550899237394
2023-01-21 12:07:42.788244: step: 132/530, loss: 6.599425978492945e-05
2023-01-21 12:07:43.900825: step: 136/530, loss: 0.09879417717456818
2023-01-21 12:07:45.005260: step: 140/530, loss: 0.00018053053645417094
2023-01-21 12:07:46.104997: step: 144/530, loss: 0.006721877958625555
2023-01-21 12:07:47.219437: step: 148/530, loss: 0.022664451971650124
2023-01-21 12:07:48.326623: step: 152/530, loss: 0.0009610176202841103
2023-01-21 12:07:49.428258: step: 156/530, loss: 0.005118560511618853
2023-01-21 12:07:50.582820: step: 160/530, loss: 0.0034122467041015625
2023-01-21 12:07:51.707149: step: 164/530, loss: 0.00017228125943802297
2023-01-21 12:07:52.796304: step: 168/530, loss: 0.0029002188239246607
2023-01-21 12:07:53.887322: step: 172/530, loss: 0.018877696245908737
2023-01-21 12:07:55.017301: step: 176/530, loss: 0.006978893186897039
2023-01-21 12:07:56.110860: step: 180/530, loss: 2.7751922971219756e-05
2023-01-21 12:07:57.206510: step: 184/530, loss: 0.01998930051922798
2023-01-21 12:07:58.314361: step: 188/530, loss: 0.007425894029438496
2023-01-21 12:07:59.424991: step: 192/530, loss: 0.0015660285716876388
2023-01-21 12:08:00.518406: step: 196/530, loss: 0.25065168738365173
2023-01-21 12:08:01.608948: step: 200/530, loss: 0.008869933895766735
2023-01-21 12:08:02.709838: step: 204/530, loss: 0.11607913672924042
2023-01-21 12:08:03.844809: step: 208/530, loss: 0.01905803754925728
2023-01-21 12:08:04.943775: step: 212/530, loss: 0.0019712448120117188
2023-01-21 12:08:06.051213: step: 216/530, loss: 0.0059667592868208885
2023-01-21 12:08:07.166506: step: 220/530, loss: 0.040360454469919205
2023-01-21 12:08:08.267515: step: 224/530, loss: 0.6400712728500366
2023-01-21 12:08:09.392506: step: 228/530, loss: 0.0016618729569017887
2023-01-21 12:08:10.504314: step: 232/530, loss: 0.03634977340698242
2023-01-21 12:08:11.607331: step: 236/530, loss: 0.01165542658418417
2023-01-21 12:08:12.672915: step: 240/530, loss: 0.00030431748018600047
2023-01-21 12:08:13.829758: step: 244/530, loss: 0.000702381192240864
2023-01-21 12:08:14.937823: step: 248/530, loss: 0.01600813865661621
2023-01-21 12:08:16.034846: step: 252/530, loss: 0.012385440059006214
2023-01-21 12:08:17.160005: step: 256/530, loss: 0.0031621933449059725
2023-01-21 12:08:18.263649: step: 260/530, loss: 0.00155887589789927
2023-01-21 12:08:19.377427: step: 264/530, loss: 0.015993738546967506
2023-01-21 12:08:20.478776: step: 268/530, loss: 0.008565139956772327
2023-01-21 12:08:21.580110: step: 272/530, loss: 0.0017847062554210424
2023-01-21 12:08:22.696460: step: 276/530, loss: 0.0001866340753622353
2023-01-21 12:08:23.817063: step: 280/530, loss: 0.003197956131771207
2023-01-21 12:08:24.905659: step: 284/530, loss: 0.01449365634471178
2023-01-21 12:08:26.043747: step: 288/530, loss: 0.00026226043701171875
2023-01-21 12:08:27.137781: step: 292/530, loss: 0.013360501267015934
2023-01-21 12:08:28.265740: step: 296/530, loss: 0.0008565902826376259
2023-01-21 12:08:29.388140: step: 300/530, loss: 0.003094291780143976
2023-01-21 12:08:30.490045: step: 304/530, loss: 0.00167503347620368
2023-01-21 12:08:31.600042: step: 308/530, loss: 0.09138841927051544
2023-01-21 12:08:32.699134: step: 312/530, loss: 0.04195060953497887
2023-01-21 12:08:33.806350: step: 316/530, loss: 0.0033664703369140625
2023-01-21 12:08:34.923035: step: 320/530, loss: 8.678436643094756e-06
2023-01-21 12:08:36.033811: step: 324/530, loss: 0.03383312374353409
2023-01-21 12:08:37.156868: step: 328/530, loss: 0.0005852699396200478
2023-01-21 12:08:38.261028: step: 332/530, loss: 0.0005355834728106856
2023-01-21 12:08:39.344792: step: 336/530, loss: 0.004864883609116077
2023-01-21 12:08:40.430229: step: 340/530, loss: 9.450913057662547e-05
2023-01-21 12:08:41.525312: step: 344/530, loss: 0.005634212400764227
2023-01-21 12:08:42.640097: step: 348/530, loss: 0.0009313583141192794
2023-01-21 12:08:43.738077: step: 352/530, loss: 0.002052498050034046
2023-01-21 12:08:44.829373: step: 356/530, loss: 0.0025899887550622225
2023-01-21 12:08:45.923423: step: 360/530, loss: 0.06435515731573105
2023-01-21 12:08:47.022736: step: 364/530, loss: 0.0010286332108080387
2023-01-21 12:08:48.143423: step: 368/530, loss: 1.76429750808893e-06
2023-01-21 12:08:49.227199: step: 372/530, loss: 0.012348556891083717
2023-01-21 12:08:50.349080: step: 376/530, loss: 2.6035308110294864e-05
2023-01-21 12:08:51.452573: step: 380/530, loss: 0.04826488718390465
2023-01-21 12:08:52.559940: step: 384/530, loss: 0.014689350500702858
2023-01-21 12:08:53.655633: step: 388/530, loss: 5.187988426769152e-05
2023-01-21 12:08:54.763196: step: 392/530, loss: 0.009760474786162376
2023-01-21 12:08:55.853077: step: 396/530, loss: 0.004920005798339844
2023-01-21 12:08:56.960618: step: 400/530, loss: 0.0144538888707757
2023-01-21 12:08:58.064020: step: 404/530, loss: 7.62939453125e-06
2023-01-21 12:08:59.184807: step: 408/530, loss: 2.6607514882925898e-05
2023-01-21 12:09:00.307272: step: 412/530, loss: 0.013176250271499157
2023-01-21 12:09:01.413517: step: 416/530, loss: 4.0531158447265625e-06
2023-01-21 12:09:02.501768: step: 420/530, loss: 0.0016982138622552156
2023-01-21 12:09:03.609179: step: 424/530, loss: 0.006275653839111328
2023-01-21 12:09:04.706160: step: 428/530, loss: 0.00026187897310592234
2023-01-21 12:09:05.827144: step: 432/530, loss: 0.011815833859145641
2023-01-21 12:09:06.947806: step: 436/530, loss: 0.0057960511185228825
2023-01-21 12:09:08.050486: step: 440/530, loss: 0.00037450791569426656
2023-01-21 12:09:09.179143: step: 444/530, loss: 0.00012493133544921875
2023-01-21 12:09:10.337464: step: 448/530, loss: 0.00014171600923873484
2023-01-21 12:09:11.461076: step: 452/530, loss: 0.005940246395766735
2023-01-21 12:09:12.603402: step: 456/530, loss: -5.722045557376987e-07
2023-01-21 12:09:13.712824: step: 460/530, loss: 0.053108785301446915
2023-01-21 12:09:14.810525: step: 464/530, loss: 0.005061912816017866
2023-01-21 12:09:15.923106: step: 468/530, loss: 0.1517396867275238
2023-01-21 12:09:17.057364: step: 472/530, loss: 0.13978537917137146
2023-01-21 12:09:18.164196: step: 476/530, loss: 0.00673522986471653
2023-01-21 12:09:19.289644: step: 480/530, loss: 0.014184570871293545
2023-01-21 12:09:20.382476: step: 484/530, loss: 0.00040225981501862407
2023-01-21 12:09:21.510933: step: 488/530, loss: 0.0009510517120361328
2023-01-21 12:09:22.602612: step: 492/530, loss: 0.005855655297636986
2023-01-21 12:09:23.712623: step: 496/530, loss: 0.04139576107263565
2023-01-21 12:09:24.825793: step: 500/530, loss: 0.00010526627011131495
2023-01-21 12:09:25.950208: step: 504/530, loss: 0.21094922721385956
2023-01-21 12:09:27.017003: step: 508/530, loss: 0.0017601967556402087
2023-01-21 12:09:28.116848: step: 512/530, loss: 0.0002006530703511089
2023-01-21 12:09:29.230995: step: 516/530, loss: 0.008532715030014515
2023-01-21 12:09:30.330629: step: 520/530, loss: 0.0022155761253088713
2023-01-21 12:09:31.429762: step: 524/530, loss: 0.003313255263492465
2023-01-21 12:09:32.521581: step: 528/530, loss: 0.04838543012738228
2023-01-21 12:09:33.648215: step: 532/530, loss: 0.0440642386674881
2023-01-21 12:09:34.756729: step: 536/530, loss: 0.015325736254453659
2023-01-21 12:09:35.851897: step: 540/530, loss: 0.016004370525479317
2023-01-21 12:09:36.957064: step: 544/530, loss: 0.0019083976512774825
2023-01-21 12:09:38.052590: step: 548/530, loss: 1.4209747860149946e-05
2023-01-21 12:09:39.193136: step: 552/530, loss: 0.011877727694809437
2023-01-21 12:09:40.309394: step: 556/530, loss: 5.113704681396484
2023-01-21 12:09:41.386837: step: 560/530, loss: 0.060760498046875
2023-01-21 12:09:42.491323: step: 564/530, loss: 0.0001332283136434853
2023-01-21 12:09:43.624478: step: 568/530, loss: 0.01604766771197319
2023-01-21 12:09:44.686269: step: 572/530, loss: 3.709793236339465e-05
2023-01-21 12:09:45.776590: step: 576/530, loss: 0.0377134345471859
2023-01-21 12:09:46.887861: step: 580/530, loss: 0.0007618427625857294
2023-01-21 12:09:47.993804: step: 584/530, loss: 0.0034811736550182104
2023-01-21 12:09:49.092361: step: 588/530, loss: 0.0023624419700354338
2023-01-21 12:09:50.183454: step: 592/530, loss: 0.0011046171421185136
2023-01-21 12:09:51.276375: step: 596/530, loss: 0.011535263620316982
2023-01-21 12:09:52.406604: step: 600/530, loss: 0.02174224890768528
2023-01-21 12:09:53.537621: step: 604/530, loss: 0.00499992398545146
2023-01-21 12:09:54.642784: step: 608/530, loss: 0.004269504453986883
2023-01-21 12:09:55.757726: step: 612/530, loss: 0.027096843346953392
2023-01-21 12:09:56.867287: step: 616/530, loss: 0.12083053588867188
2023-01-21 12:09:57.953262: step: 620/530, loss: 0.0006939053419046104
2023-01-21 12:09:59.043905: step: 624/530, loss: 0.003638315247371793
2023-01-21 12:10:00.151961: step: 628/530, loss: 0.00696067837998271
2023-01-21 12:10:01.260191: step: 632/530, loss: 9.12666364456527e-05
2023-01-21 12:10:02.395507: step: 636/530, loss: 0.016834449023008347
2023-01-21 12:10:03.556178: step: 640/530, loss: 0.012977124191820621
2023-01-21 12:10:04.660098: step: 644/530, loss: 5.092620995128527e-05
2023-01-21 12:10:05.768101: step: 648/530, loss: 0.0681210532784462
2023-01-21 12:10:06.877971: step: 652/530, loss: 7.41958647267893e-05
2023-01-21 12:10:07.949065: step: 656/530, loss: 0.003253936767578125
2023-01-21 12:10:09.071749: step: 660/530, loss: 0.9449615478515625
2023-01-21 12:10:10.180022: step: 664/530, loss: 0.0018711090087890625
2023-01-21 12:10:11.312061: step: 668/530, loss: 0.0023601532448083162
2023-01-21 12:10:12.408594: step: 672/530, loss: 0.0005748749244958162
2023-01-21 12:10:13.522796: step: 676/530, loss: 4.1580202378099784e-05
2023-01-21 12:10:14.647344: step: 680/530, loss: 0.001959228655323386
2023-01-21 12:10:15.739507: step: 684/530, loss: 0.0007136345375329256
2023-01-21 12:10:16.847097: step: 688/530, loss: 0.012615394778549671
2023-01-21 12:10:17.988994: step: 692/530, loss: 0.06530018150806427
2023-01-21 12:10:19.107703: step: 696/530, loss: 0.03249035030603409
2023-01-21 12:10:20.200916: step: 700/530, loss: 9.641647193348035e-05
2023-01-21 12:10:21.396986: step: 704/530, loss: 0.01230621337890625
2023-01-21 12:10:22.510890: step: 708/530, loss: 0.004474544897675514
2023-01-21 12:10:23.635363: step: 712/530, loss: 0.003972435370087624
2023-01-21 12:10:24.747023: step: 716/530, loss: 1.392364538332913e-05
2023-01-21 12:10:25.856508: step: 720/530, loss: 0.020096970722079277
2023-01-21 12:10:26.942575: step: 724/530, loss: 0.002680015517398715
2023-01-21 12:10:28.056505: step: 728/530, loss: 4.816055661649443e-05
2023-01-21 12:10:29.154298: step: 732/530, loss: 0.00805683247745037
2023-01-21 12:10:30.283093: step: 736/530, loss: 0.04042300954461098
2023-01-21 12:10:31.389396: step: 740/530, loss: 0.0035667421761900187
2023-01-21 12:10:32.503571: step: 744/530, loss: 0.026675034314393997
2023-01-21 12:10:33.608242: step: 748/530, loss: 0.00019130707369185984
2023-01-21 12:10:34.692620: step: 752/530, loss: 0.1128196269273758
2023-01-21 12:10:35.803771: step: 756/530, loss: 0.002897071884945035
2023-01-21 12:10:36.900962: step: 760/530, loss: 0.021552467718720436
2023-01-21 12:10:37.983124: step: 764/530, loss: 0.0003197670157533139
2023-01-21 12:10:39.055844: step: 768/530, loss: 0.003800678299739957
2023-01-21 12:10:40.159838: step: 772/530, loss: 8.430481102550402e-05
2023-01-21 12:10:41.273428: step: 776/530, loss: 0.047208309173583984
2023-01-21 12:10:42.388744: step: 780/530, loss: 0.4871490001678467
2023-01-21 12:10:43.501026: step: 784/530, loss: 0.026512717828154564
2023-01-21 12:10:44.605996: step: 788/530, loss: 0.0709049254655838
2023-01-21 12:10:45.719282: step: 792/530, loss: 0.025051211938261986
2023-01-21 12:10:46.833897: step: 796/530, loss: 0.009515953250229359
2023-01-21 12:10:47.944627: step: 800/530, loss: 0.006145763676613569
2023-01-21 12:10:49.098004: step: 804/530, loss: 0.022965049371123314
2023-01-21 12:10:50.200897: step: 808/530, loss: 0.01587848737835884
2023-01-21 12:10:51.332188: step: 812/530, loss: 0.0017555237282067537
2023-01-21 12:10:52.442929: step: 816/530, loss: 0.010108566842973232
2023-01-21 12:10:53.537102: step: 820/530, loss: 0.00017671583918854594
2023-01-21 12:10:54.650222: step: 824/530, loss: 0.1538395881652832
2023-01-21 12:10:55.729594: step: 828/530, loss: 0.02229447476565838
2023-01-21 12:10:56.856471: step: 832/530, loss: 0.004184722900390625
2023-01-21 12:10:57.972609: step: 836/530, loss: 0.04305100440979004
2023-01-21 12:10:59.075833: step: 840/530, loss: 0.0006993293645791709
2023-01-21 12:11:00.204291: step: 844/530, loss: 0.007149124518036842
2023-01-21 12:11:01.319943: step: 848/530, loss: 2.021789623540826e-05
2023-01-21 12:11:02.436508: step: 852/530, loss: 2.3937225705594756e-05
2023-01-21 12:11:03.576018: step: 856/530, loss: 0.0026364328805357218
2023-01-21 12:11:04.683821: step: 860/530, loss: 0.019340135157108307
2023-01-21 12:11:05.805240: step: 864/530, loss: 0.03844489902257919
2023-01-21 12:11:06.906454: step: 868/530, loss: 0.000363254570402205
2023-01-21 12:11:08.064534: step: 872/530, loss: 0.0005132198566570878
2023-01-21 12:11:09.190323: step: 876/530, loss: 0.000294590019620955
2023-01-21 12:11:10.306204: step: 880/530, loss: 4.873275611316785e-05
2023-01-21 12:11:11.405984: step: 884/530, loss: 0.004424953367561102
2023-01-21 12:11:12.508467: step: 888/530, loss: 0.00740509107708931
2023-01-21 12:11:13.609221: step: 892/530, loss: 0.04560208320617676
2023-01-21 12:11:14.714655: step: 896/530, loss: 0.5973265171051025
2023-01-21 12:11:15.824593: step: 900/530, loss: 0.0002993583620991558
2023-01-21 12:11:16.962635: step: 904/530, loss: 0.0004534721374511719
2023-01-21 12:11:18.083443: step: 908/530, loss: 0.0058956146240234375
2023-01-21 12:11:19.175524: step: 912/530, loss: 0.003862094832584262
2023-01-21 12:11:20.299129: step: 916/530, loss: 1.364870548248291
2023-01-21 12:11:21.404122: step: 920/530, loss: 8.811950829112902e-05
2023-01-21 12:11:22.535317: step: 924/530, loss: 0.0002382278471486643
2023-01-21 12:11:23.629363: step: 928/530, loss: 0.04688673093914986
2023-01-21 12:11:24.721362: step: 932/530, loss: 0.030300522223114967
2023-01-21 12:11:25.825564: step: 936/530, loss: 0.00010261536226607859
2023-01-21 12:11:26.921896: step: 940/530, loss: 0.03785572201013565
2023-01-21 12:11:28.036796: step: 944/530, loss: 0.012190056033432484
2023-01-21 12:11:29.143751: step: 948/530, loss: 0.059978339821100235
2023-01-21 12:11:30.239884: step: 952/530, loss: 0.03271036222577095
2023-01-21 12:11:31.346253: step: 956/530, loss: 0.005850410554558039
2023-01-21 12:11:32.443604: step: 960/530, loss: 0.0003733634948730469
2023-01-21 12:11:33.560274: step: 964/530, loss: 0.006627464666962624
2023-01-21 12:11:34.674994: step: 968/530, loss: 0.0023478984367102385
2023-01-21 12:11:35.786431: step: 972/530, loss: 0.0005533219082280993
2023-01-21 12:11:36.891369: step: 976/530, loss: 0.00254478445276618
2023-01-21 12:11:37.959884: step: 980/530, loss: 5.559921555686742e-05
2023-01-21 12:11:39.040246: step: 984/530, loss: 0.004350090399384499
2023-01-21 12:11:40.132003: step: 988/530, loss: 0.01745014265179634
2023-01-21 12:11:41.240175: step: 992/530, loss: 0.00801706314086914
2023-01-21 12:11:42.351602: step: 996/530, loss: 0.0001888275146484375
2023-01-21 12:11:43.480461: step: 1000/530, loss: 0.011542893014848232
2023-01-21 12:11:44.564668: step: 1004/530, loss: 9.15527380129788e-06
2023-01-21 12:11:45.673284: step: 1008/530, loss: 0.4879912734031677
2023-01-21 12:11:46.803354: step: 1012/530, loss: 0.00011711120896507055
2023-01-21 12:11:47.908446: step: 1016/530, loss: 0.0652977004647255
2023-01-21 12:11:48.993661: step: 1020/530, loss: 0.00016574861365370452
2023-01-21 12:11:50.105859: step: 1024/530, loss: 0.0002658844168763608
2023-01-21 12:11:51.233339: step: 1028/530, loss: 0.002760982606559992
2023-01-21 12:11:52.333709: step: 1032/530, loss: 0.004348087590187788
2023-01-21 12:11:53.426502: step: 1036/530, loss: 0.00039949416532181203
2023-01-21 12:11:54.549126: step: 1040/530, loss: 0.024202918633818626
2023-01-21 12:11:55.660988: step: 1044/530, loss: 0.00033216478186659515
2023-01-21 12:11:56.774790: step: 1048/530, loss: 1.4066695257497486e-05
2023-01-21 12:11:57.868407: step: 1052/530, loss: 0.17680606245994568
2023-01-21 12:11:58.956621: step: 1056/530, loss: 0.0007547378772869706
2023-01-21 12:12:00.062633: step: 1060/530, loss: 0.02746753767132759
2023-01-21 12:12:01.160417: step: 1064/530, loss: 0.0013050079578533769
2023-01-21 12:12:02.252490: step: 1068/530, loss: 0.00905618630349636
2023-01-21 12:12:03.356960: step: 1072/530, loss: 0.003548908280208707
2023-01-21 12:12:04.474636: step: 1076/530, loss: 0.00011405945406295359
2023-01-21 12:12:05.560960: step: 1080/530, loss: 0.00024857520475052297
2023-01-21 12:12:06.634335: step: 1084/530, loss: 2.784729076665826e-05
2023-01-21 12:12:07.746674: step: 1088/530, loss: 7.25746140233241e-05
2023-01-21 12:12:08.834414: step: 1092/530, loss: 0.002909755567088723
2023-01-21 12:12:09.972133: step: 1096/530, loss: 0.00884027499705553
2023-01-21 12:12:11.078055: step: 1100/530, loss: 0.008242321200668812
2023-01-21 12:12:12.191612: step: 1104/530, loss: 0.0010475158924236894
2023-01-21 12:12:13.294318: step: 1108/530, loss: 0.0036596297286450863
2023-01-21 12:12:14.389486: step: 1112/530, loss: 0.02861328050494194
2023-01-21 12:12:15.472479: step: 1116/530, loss: 0.046180155128240585
2023-01-21 12:12:16.571584: step: 1120/530, loss: 0.015436363406479359
2023-01-21 12:12:17.672613: step: 1124/530, loss: 6.017685154802166e-05
2023-01-21 12:12:18.744632: step: 1128/530, loss: 0.0001220703125
2023-01-21 12:12:19.850309: step: 1132/530, loss: 0.0005414009792730212
2023-01-21 12:12:20.942047: step: 1136/530, loss: 0.0029452324379235506
2023-01-21 12:12:22.041677: step: 1140/530, loss: 0.00018806457228492945
2023-01-21 12:12:23.147511: step: 1144/530, loss: 7.572174217784777e-05
2023-01-21 12:12:24.254886: step: 1148/530, loss: 0.010421943850815296
2023-01-21 12:12:25.374500: step: 1152/530, loss: 2.689361645025201e-05
2023-01-21 12:12:26.487305: step: 1156/530, loss: 0.011257171630859375
2023-01-21 12:12:27.588252: step: 1160/530, loss: 0.0001506805419921875
2023-01-21 12:12:28.683283: step: 1164/530, loss: 0.00923233013600111
2023-01-21 12:12:29.763483: step: 1168/530, loss: 0.01772146299481392
2023-01-21 12:12:30.835074: step: 1172/530, loss: 0.00010910034325206652
2023-01-21 12:12:31.925577: step: 1176/530, loss: 5.626678466796875e-05
2023-01-21 12:12:33.020933: step: 1180/530, loss: 0.0054565430618822575
2023-01-21 12:12:34.132830: step: 1184/530, loss: 4.57763671875e-05
2023-01-21 12:12:35.226898: step: 1188/530, loss: 9.121894981944934e-05
2023-01-21 12:12:36.311186: step: 1192/530, loss: -1.5258785879268544e-06
2023-01-21 12:12:37.426852: step: 1196/530, loss: 0.0007101059309206903
2023-01-21 12:12:38.513290: step: 1200/530, loss: 0.004572677426040173
2023-01-21 12:12:39.647121: step: 1204/530, loss: 0.0070664407685399055
2023-01-21 12:12:40.749516: step: 1208/530, loss: 0.013383341021835804
2023-01-21 12:12:41.842451: step: 1212/530, loss: 0.0008581161382608116
2023-01-21 12:12:42.922950: step: 1216/530, loss: 0.00032415392342954874
2023-01-21 12:12:44.033274: step: 1220/530, loss: 0.08208665996789932
2023-01-21 12:12:45.140963: step: 1224/530, loss: 0.0001976490020751953
2023-01-21 12:12:46.242242: step: 1228/530, loss: 0.00046663283137604594
2023-01-21 12:12:47.357945: step: 1232/530, loss: 0.01401443500071764
2023-01-21 12:12:48.460828: step: 1236/530, loss: 5.1212315156590194e-05
2023-01-21 12:12:49.577605: step: 1240/530, loss: 0.051000308245420456
2023-01-21 12:12:50.694864: step: 1244/530, loss: 0.018848992884159088
2023-01-21 12:12:51.773618: step: 1248/530, loss: 4.839897155761719e-05
2023-01-21 12:12:52.875182: step: 1252/530, loss: 0.5384510159492493
2023-01-21 12:12:53.961703: step: 1256/530, loss: 1.9073486612342094e-07
2023-01-21 12:12:55.063603: step: 1260/530, loss: 0.00114526750985533
2023-01-21 12:12:56.173970: step: 1264/530, loss: 0.028896141797304153
2023-01-21 12:12:57.265803: step: 1268/530, loss: 0.046811964362859726
2023-01-21 12:12:58.377876: step: 1272/530, loss: 0.06894226372241974
2023-01-21 12:12:59.467647: step: 1276/530, loss: 0.006539058405905962
2023-01-21 12:13:00.554797: step: 1280/530, loss: 0.0001682281435932964
2023-01-21 12:13:01.660014: step: 1284/530, loss: 0.012586211785674095
2023-01-21 12:13:02.747713: step: 1288/530, loss: 0.09386825561523438
2023-01-21 12:13:03.856201: step: 1292/530, loss: 0.0007105827680788934
2023-01-21 12:13:04.973598: step: 1296/530, loss: 0.028109168633818626
2023-01-21 12:13:06.112295: step: 1300/530, loss: 0.002482795622199774
2023-01-21 12:13:07.215562: step: 1304/530, loss: 0.00031070708064362407
2023-01-21 12:13:08.306392: step: 1308/530, loss: 0.01983346976339817
2023-01-21 12:13:09.403826: step: 1312/530, loss: 0.0002649307425599545
2023-01-21 12:13:10.510373: step: 1316/530, loss: 0.0022909166291356087
2023-01-21 12:13:11.622567: step: 1320/530, loss: 0.0003948688681703061
2023-01-21 12:13:12.712230: step: 1324/530, loss: 0.0005290985573083162
2023-01-21 12:13:13.808405: step: 1328/530, loss: 0.0003675461048260331
2023-01-21 12:13:14.933911: step: 1332/530, loss: 0.037842560559511185
2023-01-21 12:13:16.014957: step: 1336/530, loss: 0.023119354620575905
2023-01-21 12:13:17.136251: step: 1340/530, loss: 0.00843734759837389
2023-01-21 12:13:18.241345: step: 1344/530, loss: 0.0018355369102209806
2023-01-21 12:13:19.354475: step: 1348/530, loss: 0.0003505706845317036
2023-01-21 12:13:20.435557: step: 1352/530, loss: 0.0495484359562397
2023-01-21 12:13:21.526354: step: 1356/530, loss: 0.018940448760986328
2023-01-21 12:13:22.641150: step: 1360/530, loss: 0.0015443802112713456
2023-01-21 12:13:23.726424: step: 1364/530, loss: 0.000851058925036341
2023-01-21 12:13:24.829896: step: 1368/530, loss: 0.0019054414005950093
2023-01-21 12:13:25.914834: step: 1372/530, loss: 0.09177283942699432
2023-01-21 12:13:27.030574: step: 1376/530, loss: 0.047292523086071014
2023-01-21 12:13:28.126754: step: 1380/530, loss: 0.0025266646407544613
2023-01-21 12:13:29.228719: step: 1384/530, loss: 0.0012206077808514237
2023-01-21 12:13:30.333448: step: 1388/530, loss: 0.021045496687293053
2023-01-21 12:13:31.420327: step: 1392/530, loss: 0.0014844894176349044
2023-01-21 12:13:32.524182: step: 1396/530, loss: 0.027077436447143555
2023-01-21 12:13:33.680023: step: 1400/530, loss: 0.016130639240145683
2023-01-21 12:13:34.786938: step: 1404/530, loss: 0.0004931449657306075
2023-01-21 12:13:35.927064: step: 1408/530, loss: 3.166198803228326e-05
2023-01-21 12:13:37.026441: step: 1412/530, loss: 0.014764023013412952
2023-01-21 12:13:38.121429: step: 1416/530, loss: 0.00995016098022461
2023-01-21 12:13:39.213496: step: 1420/530, loss: 0.0008300780900754035
2023-01-21 12:13:40.299289: step: 1424/530, loss: 0.005065536592155695
2023-01-21 12:13:41.429088: step: 1428/530, loss: 0.00044145583524368703
2023-01-21 12:13:42.526202: step: 1432/530, loss: 0.009423637762665749
2023-01-21 12:13:43.653040: step: 1436/530, loss: 0.0014270782703533769
2023-01-21 12:13:44.759568: step: 1440/530, loss: 0.0047393799759447575
2023-01-21 12:13:45.904566: step: 1444/530, loss: 0.006506109610199928
2023-01-21 12:13:46.994941: step: 1448/530, loss: 0.00292377476580441
2023-01-21 12:13:48.103951: step: 1452/530, loss: 0.10083892941474915
2023-01-21 12:13:49.204402: step: 1456/530, loss: 0.001064205076545477
2023-01-21 12:13:50.301513: step: 1460/530, loss: 0.0017686843639239669
2023-01-21 12:13:51.421677: step: 1464/530, loss: 0.0010738372802734375
2023-01-21 12:13:52.508932: step: 1468/530, loss: 0.012791706249117851
2023-01-21 12:13:53.593824: step: 1472/530, loss: 0.00105543143581599
2023-01-21 12:13:54.691312: step: 1476/530, loss: 0.0002208113728556782
2023-01-21 12:13:55.809093: step: 1480/530, loss: 0.012577056884765625
2023-01-21 12:13:56.949571: step: 1484/530, loss: 1.1444091796875e-05
2023-01-21 12:13:58.051756: step: 1488/530, loss: 0.00029892922611907125
2023-01-21 12:13:59.176466: step: 1492/530, loss: 3.471374657237902e-05
2023-01-21 12:14:00.301889: step: 1496/530, loss: 0.0011487007141113281
2023-01-21 12:14:01.426683: step: 1500/530, loss: 0.009208393283188343
2023-01-21 12:14:02.527306: step: 1504/530, loss: 0.002470684237778187
2023-01-21 12:14:03.683913: step: 1508/530, loss: 0.0017355919117107987
2023-01-21 12:14:04.794095: step: 1512/530, loss: 0.004153442569077015
2023-01-21 12:14:05.883239: step: 1516/530, loss: 0.01511373557150364
2023-01-21 12:14:06.985848: step: 1520/530, loss: 0.025942228734493256
2023-01-21 12:14:08.068311: step: 1524/530, loss: 0.016079138964414597
2023-01-21 12:14:09.185410: step: 1528/530, loss: 0.01818518526852131
2023-01-21 12:14:10.297347: step: 1532/530, loss: 0.04637184366583824
2023-01-21 12:14:11.373034: step: 1536/530, loss: 0.000736236572265625
2023-01-21 12:14:12.473604: step: 1540/530, loss: 0.005008840933442116
2023-01-21 12:14:13.556248: step: 1544/530, loss: 0.035138990730047226
2023-01-21 12:14:14.667713: step: 1548/530, loss: 0.0015506267081946135
2023-01-21 12:14:15.777946: step: 1552/530, loss: 0.031310271471738815
2023-01-21 12:14:16.885037: step: 1556/530, loss: 0.15729141235351562
2023-01-21 12:14:18.026925: step: 1560/530, loss: 0.001617860863916576
2023-01-21 12:14:19.145327: step: 1564/530, loss: 0.031832315027713776
2023-01-21 12:14:20.234092: step: 1568/530, loss: 0.005492973141372204
2023-01-21 12:14:21.329783: step: 1572/530, loss: 0.0015227317344397306
2023-01-21 12:14:22.448308: step: 1576/530, loss: 0.002660751575604081
2023-01-21 12:14:23.532965: step: 1580/530, loss: 2.613067590573337e-05
2023-01-21 12:14:24.642586: step: 1584/530, loss: 0.000690078770276159
2023-01-21 12:14:25.743434: step: 1588/530, loss: 0.002153110457584262
2023-01-21 12:14:26.856750: step: 1592/530, loss: 0.00014038085646461695
2023-01-21 12:14:27.954905: step: 1596/530, loss: 0.003947925288230181
2023-01-21 12:14:29.066461: step: 1600/530, loss: 0.02417907677590847
2023-01-21 12:14:30.165766: step: 1604/530, loss: 0.008671760559082031
2023-01-21 12:14:31.266633: step: 1608/530, loss: 0.006177139468491077
2023-01-21 12:14:32.369813: step: 1612/530, loss: 0.0005815505865029991
2023-01-21 12:14:33.470103: step: 1616/530, loss: 0.016411496326327324
2023-01-21 12:14:34.609779: step: 1620/530, loss: 0.0018385887378826737
2023-01-21 12:14:35.709433: step: 1624/530, loss: 0.0010951042640954256
2023-01-21 12:14:36.803058: step: 1628/530, loss: -1.373290979245212e-05
2023-01-21 12:14:37.908588: step: 1632/530, loss: 0.0010644913418218493
2023-01-21 12:14:39.009237: step: 1636/530, loss: 0.0031946422532200813
2023-01-21 12:14:40.108695: step: 1640/530, loss: 0.03508109971880913
2023-01-21 12:14:41.218020: step: 1644/530, loss: 0.0035972597543150187
2023-01-21 12:14:42.338505: step: 1648/530, loss: 0.060037851333618164
2023-01-21 12:14:43.428466: step: 1652/530, loss: 0.00016860962205100805
2023-01-21 12:14:44.529620: step: 1656/530, loss: 2.5272369384765625e-05
2023-01-21 12:14:45.626152: step: 1660/530, loss: 0.023647308349609375
2023-01-21 12:14:46.739498: step: 1664/530, loss: 0.018071748316287994
2023-01-21 12:14:47.824184: step: 1668/530, loss: 0.0003309726598672569
2023-01-21 12:14:48.925745: step: 1672/530, loss: 0.02766113355755806
2023-01-21 12:14:50.038430: step: 1676/530, loss: 0.0031376839615404606
2023-01-21 12:14:51.165891: step: 1680/530, loss: 0.000985479331575334
2023-01-21 12:14:52.248383: step: 1684/530, loss: 0.005018997006118298
2023-01-21 12:14:53.320673: step: 1688/530, loss: 0.7209326028823853
2023-01-21 12:14:54.437523: step: 1692/530, loss: 0.006072712130844593
2023-01-21 12:14:55.540848: step: 1696/530, loss: 0.0005210876697674394
2023-01-21 12:14:56.641840: step: 1700/530, loss: 0.0035539628006517887
2023-01-21 12:14:57.739357: step: 1704/530, loss: 0.25266438722610474
2023-01-21 12:14:58.853054: step: 1708/530, loss: 0.005540752317756414
2023-01-21 12:14:59.981821: step: 1712/530, loss: 0.05774059146642685
2023-01-21 12:15:01.095370: step: 1716/530, loss: 0.0017560005653649569
2023-01-21 12:15:02.216095: step: 1720/530, loss: 0.005229854490607977
2023-01-21 12:15:03.314073: step: 1724/530, loss: 0.017778875306248665
2023-01-21 12:15:04.432791: step: 1728/530, loss: 0.00939102191478014
2023-01-21 12:15:05.540260: step: 1732/530, loss: 0.010485458187758923
2023-01-21 12:15:06.654492: step: 1736/530, loss: 0.007012749090790749
2023-01-21 12:15:07.737302: step: 1740/530, loss: 0.005204105284065008
2023-01-21 12:15:08.828941: step: 1744/530, loss: 0.02857828326523304
2023-01-21 12:15:09.922300: step: 1748/530, loss: 0.003041219897568226
2023-01-21 12:15:11.012313: step: 1752/530, loss: 0.014059782959520817
2023-01-21 12:15:12.120445: step: 1756/530, loss: 0.002980137011036277
2023-01-21 12:15:13.238281: step: 1760/530, loss: 0.023015404120087624
2023-01-21 12:15:14.343188: step: 1764/530, loss: 0.0009369373437948525
2023-01-21 12:15:15.452717: step: 1768/530, loss: 0.21640634536743164
2023-01-21 12:15:16.550494: step: 1772/530, loss: 0.008955764584243298
2023-01-21 12:15:17.647544: step: 1776/530, loss: 0.00010452271089889109
2023-01-21 12:15:18.736040: step: 1780/530, loss: 0.005344581790268421
2023-01-21 12:15:19.819915: step: 1784/530, loss: 0.036281779408454895
2023-01-21 12:15:20.937617: step: 1788/530, loss: 0.009711075574159622
2023-01-21 12:15:22.050629: step: 1792/530, loss: 0.006456566043198109
2023-01-21 12:15:23.149676: step: 1796/530, loss: 0.1239846721291542
2023-01-21 12:15:24.234245: step: 1800/530, loss: 0.01740856096148491
2023-01-21 12:15:25.335000: step: 1804/530, loss: 0.022455215454101562
2023-01-21 12:15:26.456930: step: 1808/530, loss: 0.002722358563914895
2023-01-21 12:15:27.550089: step: 1812/530, loss: 0.004055118653923273
2023-01-21 12:15:28.707253: step: 1816/530, loss: 3.542900230968371e-05
2023-01-21 12:15:29.803924: step: 1820/530, loss: 0.000489354133605957
2023-01-21 12:15:30.944079: step: 1824/530, loss: 0.0008420467493124306
2023-01-21 12:15:32.061706: step: 1828/530, loss: 0.12214889377355576
2023-01-21 12:15:33.176972: step: 1832/530, loss: 0.03563747555017471
2023-01-21 12:15:34.297250: step: 1836/530, loss: 0.00022373200044967234
2023-01-21 12:15:35.391855: step: 1840/530, loss: 2.4890900022001006e-05
2023-01-21 12:15:36.497808: step: 1844/530, loss: 0.01895151101052761
2023-01-21 12:15:37.602305: step: 1848/530, loss: 0.11069031059741974
2023-01-21 12:15:38.701690: step: 1852/530, loss: 0.001604270888492465
2023-01-21 12:15:39.787499: step: 1856/530, loss: 0.00043888093205168843
2023-01-21 12:15:40.849661: step: 1860/530, loss: 0.0004282951704226434
2023-01-21 12:15:41.926868: step: 1864/530, loss: 0.005627441219985485
2023-01-21 12:15:43.028038: step: 1868/530, loss: 0.007857704535126686
2023-01-21 12:15:44.124062: step: 1872/530, loss: 6.437301635742188e-05
2023-01-21 12:15:45.277018: step: 1876/530, loss: 0.0009330749744549394
2023-01-21 12:15:46.384142: step: 1880/530, loss: 0.033197786659002304
2023-01-21 12:15:47.481686: step: 1884/530, loss: 0.007854461669921875
2023-01-21 12:15:48.600792: step: 1888/530, loss: 0.000150775900692679
2023-01-21 12:15:49.690153: step: 1892/530, loss: 0.009442711248993874
2023-01-21 12:15:50.781142: step: 1896/530, loss: 0.0042969705536961555
2023-01-21 12:15:51.912755: step: 1900/530, loss: 0.0037317276000976562
2023-01-21 12:15:53.015002: step: 1904/530, loss: 0.00022001266188453883
2023-01-21 12:15:54.098326: step: 1908/530, loss: 0.012866782955825329
2023-01-21 12:15:55.194465: step: 1912/530, loss: 0.0015930176014080644
2023-01-21 12:15:56.293826: step: 1916/530, loss: 0.006220245733857155
2023-01-21 12:15:57.376001: step: 1920/530, loss: 0.012356949038803577
2023-01-21 12:15:58.497831: step: 1924/530, loss: 0.001119327498599887
2023-01-21 12:15:59.623670: step: 1928/530, loss: 0.00033969880314543843
2023-01-21 12:16:00.744284: step: 1932/530, loss: 0.005018997471779585
2023-01-21 12:16:01.830589: step: 1936/530, loss: 0.00010938644845737144
2023-01-21 12:16:02.941303: step: 1940/530, loss: 0.0006373882060870528
2023-01-21 12:16:04.013099: step: 1944/530, loss: 0.0007758140563964844
2023-01-21 12:16:05.130882: step: 1948/530, loss: 0.001622962998226285
2023-01-21 12:16:06.277252: step: 1952/530, loss: 0.007097435183823109
2023-01-21 12:16:07.390120: step: 1956/530, loss: 0.01904139667749405
2023-01-21 12:16:08.500821: step: 1960/530, loss: 0.0015006065368652344
2023-01-21 12:16:09.616786: step: 1964/530, loss: 0.004491615574806929
2023-01-21 12:16:10.718790: step: 1968/530, loss: 0.00012521744065452367
2023-01-21 12:16:11.817010: step: 1972/530, loss: 0.00010499954805709422
2023-01-21 12:16:12.905717: step: 1976/530, loss: 0.01228790357708931
2023-01-21 12:16:14.025410: step: 1980/530, loss: 0.04665551334619522
2023-01-21 12:16:15.131501: step: 1984/530, loss: 0.02315979078412056
2023-01-21 12:16:16.238001: step: 1988/530, loss: 0.001349210855551064
2023-01-21 12:16:17.327942: step: 1992/530, loss: 0.0018367768498137593
2023-01-21 12:16:18.413582: step: 1996/530, loss: 0.011182880960404873
2023-01-21 12:16:19.500501: step: 2000/530, loss: 0.0030622482299804688
2023-01-21 12:16:20.623871: step: 2004/530, loss: 0.018260573968291283
2023-01-21 12:16:21.761073: step: 2008/530, loss: 0.06368732452392578
2023-01-21 12:16:22.869124: step: 2012/530, loss: 0.039682384580373764
2023-01-21 12:16:23.980997: step: 2016/530, loss: 0.00018529893714003265
2023-01-21 12:16:25.098164: step: 2020/530, loss: 0.016443347558379173
2023-01-21 12:16:26.211589: step: 2024/530, loss: 0.00123090751003474
2023-01-21 12:16:27.352313: step: 2028/530, loss: 0.002041387604549527
2023-01-21 12:16:28.490927: step: 2032/530, loss: 0.012533235363662243
2023-01-21 12:16:29.590157: step: 2036/530, loss: 0.01345901470631361
2023-01-21 12:16:30.685352: step: 2040/530, loss: 0.04271411895751953
2023-01-21 12:16:31.792587: step: 2044/530, loss: 9.765625145519152e-05
2023-01-21 12:16:32.942264: step: 2048/530, loss: 0.002914142794907093
2023-01-21 12:16:34.068252: step: 2052/530, loss: 0.15699510276317596
2023-01-21 12:16:35.150580: step: 2056/530, loss: 0.0002851486497092992
2023-01-21 12:16:36.277379: step: 2060/530, loss: 0.0015765189891681075
2023-01-21 12:16:37.420121: step: 2064/530, loss: 0.0018166541121900082
2023-01-21 12:16:38.523627: step: 2068/530, loss: 0.00585250835865736
2023-01-21 12:16:39.593446: step: 2072/530, loss: 0.0664762482047081
2023-01-21 12:16:40.698799: step: 2076/530, loss: 0.017146587371826172
2023-01-21 12:16:41.792962: step: 2080/530, loss: 0.033246710896492004
2023-01-21 12:16:42.936025: step: 2084/530, loss: 0.00276527414098382
2023-01-21 12:16:44.040918: step: 2088/530, loss: 0.010992812924087048
2023-01-21 12:16:45.129804: step: 2092/530, loss: 0.04770393297076225
2023-01-21 12:16:46.203023: step: 2096/530, loss: 0.00011959076073253527
2023-01-21 12:16:47.346803: step: 2100/530, loss: 0.026585737243294716
2023-01-21 12:16:48.436611: step: 2104/530, loss: 0.005973625462502241
2023-01-21 12:16:49.573671: step: 2108/530, loss: 0.010623455047607422
2023-01-21 12:16:50.713332: step: 2112/530, loss: 0.0046437024138867855
2023-01-21 12:16:51.864767: step: 2116/530, loss: 0.0008586883777752519
2023-01-21 12:16:52.956821: step: 2120/530, loss: 0.0050712586380541325
==================================================
Loss: 0.037
--------------------
Dev: {'event': {'p': 0.6002143622722401, 'r': 0.7456724367509987, 'f1': 0.665083135391924}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Test: {'event': {'p': 0.6443711728685821, 'r': 0.7972027972027972, 'f1': 0.7126855952070851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Chinese: {'event': {'p': 0.6714285714285714, 'r': 0.8703703703703703, 'f1': 0.7580645161290323}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Korean: {'event': {'p': 0.7317073170731707, 'r': 0.47619047619047616, 'f1': 0.576923076923077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Russian: {'event': {'p': 0.4444444444444444, 'r': 0.4444444444444444, 'f1': 0.4444444444444444}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 12:17:32.106699: step: 4/530, loss: 0.0003976345178671181
2023-01-21 12:17:33.234030: step: 8/530, loss: 0.0723840594291687
2023-01-21 12:17:34.365833: step: 12/530, loss: 9.5367431640625e-05
2023-01-21 12:17:35.496440: step: 16/530, loss: 0.00391731271520257
2023-01-21 12:17:36.587476: step: 20/530, loss: 0.00043735504732467234
2023-01-21 12:17:37.686502: step: 24/530, loss: 0.0018428802723065019
2023-01-21 12:17:38.779332: step: 28/530, loss: 0.0005863189580850303
2023-01-21 12:17:39.888801: step: 32/530, loss: 0.00014181136793922633
2023-01-21 12:17:41.032334: step: 36/530, loss: 0.0005159378051757812
2023-01-21 12:17:42.133209: step: 40/530, loss: 0.03040151484310627
2023-01-21 12:17:43.252126: step: 44/530, loss: 0.007854843512177467
2023-01-21 12:17:44.357829: step: 48/530, loss: 0.013159465976059437
2023-01-21 12:17:45.484879: step: 52/530, loss: 0.006870078854262829
2023-01-21 12:17:46.587595: step: 56/530, loss: 0.006834126077592373
2023-01-21 12:17:47.693072: step: 60/530, loss: 1.959800829354208e-05
2023-01-21 12:17:48.799327: step: 64/530, loss: 0.0008382797241210938
2023-01-21 12:17:49.882710: step: 68/530, loss: 0.0019088268745690584
2023-01-21 12:17:50.973991: step: 72/530, loss: 0.004424715414643288
2023-01-21 12:17:52.071426: step: 76/530, loss: 0.0006326198927126825
2023-01-21 12:17:53.215377: step: 80/530, loss: 0.08639007061719894
2023-01-21 12:17:54.299744: step: 84/530, loss: 1.029968279908644e-05
2023-01-21 12:17:55.404790: step: 88/530, loss: 0.019137192517518997
2023-01-21 12:17:56.504417: step: 92/530, loss: 0.00012807846360374242
2023-01-21 12:17:57.598749: step: 96/530, loss: 8.921623521018773e-05
2023-01-21 12:17:58.700929: step: 100/530, loss: 0.0021835328079760075
2023-01-21 12:17:59.793948: step: 104/530, loss: 0.0018634796142578125
2023-01-21 12:18:00.886957: step: 108/530, loss: 0.002501869108527899
2023-01-21 12:18:01.958483: step: 112/530, loss: 0.03804483264684677
2023-01-21 12:18:03.064972: step: 116/530, loss: 0.0011772155994549394
2023-01-21 12:18:04.143782: step: 120/530, loss: 1.3303757441462949e-05
2023-01-21 12:18:05.226925: step: 124/530, loss: 0.009917545132339
2023-01-21 12:18:06.307047: step: 128/530, loss: 0.007371139712631702
2023-01-21 12:18:07.424270: step: 132/530, loss: 0.04135332256555557
2023-01-21 12:18:08.508716: step: 136/530, loss: 0.00012865067401435226
2023-01-21 12:18:09.580160: step: 140/530, loss: 0.05237245559692383
2023-01-21 12:18:10.682663: step: 144/530, loss: 0.00015254021855071187
2023-01-21 12:18:11.798133: step: 148/530, loss: 0.28070932626724243
2023-01-21 12:18:12.904371: step: 152/530, loss: 0.005045128054916859
2023-01-21 12:18:14.010557: step: 156/530, loss: 0.002064323518425226
2023-01-21 12:18:15.127757: step: 160/530, loss: 0.0004643440479412675
2023-01-21 12:18:16.241589: step: 164/530, loss: 0.0088355066254735
2023-01-21 12:18:17.335841: step: 168/530, loss: 0.0002476692316122353
2023-01-21 12:18:18.440283: step: 172/530, loss: 0.18677674233913422
2023-01-21 12:18:19.530198: step: 176/530, loss: 0.02877178229391575
2023-01-21 12:18:20.646453: step: 180/530, loss: 0.016104411333799362
2023-01-21 12:18:21.776544: step: 184/530, loss: 0.03168316185474396
2023-01-21 12:18:22.884177: step: 188/530, loss: 7.364750490523875e-05
2023-01-21 12:18:23.993897: step: 192/530, loss: 0.005032348912209272
2023-01-21 12:18:25.096569: step: 196/530, loss: 0.0005095482338219881
2023-01-21 12:18:26.225970: step: 200/530, loss: 4.0340422856388614e-05
2023-01-21 12:18:27.316771: step: 204/530, loss: 0.0012983321212232113
2023-01-21 12:18:28.409529: step: 208/530, loss: 0.011368894949555397
2023-01-21 12:18:29.498183: step: 212/530, loss: 3.528594970703125e-05
2023-01-21 12:18:30.626226: step: 216/530, loss: 0.0027915954124182463
2023-01-21 12:18:31.720187: step: 220/530, loss: 0.0021087646018713713
2023-01-21 12:18:32.856593: step: 224/530, loss: 0.0012569427490234375
2023-01-21 12:18:33.946092: step: 228/530, loss: 3.066063072765246e-05
2023-01-21 12:18:35.042612: step: 232/530, loss: 0.000271701836027205
2023-01-21 12:18:36.150350: step: 236/530, loss: 0.00025196076603606343
2023-01-21 12:18:37.272623: step: 240/530, loss: 0.000667572021484375
2023-01-21 12:18:38.385481: step: 244/530, loss: 0.021225357428193092
2023-01-21 12:18:39.521527: step: 248/530, loss: 0.000194549560546875
2023-01-21 12:18:40.627883: step: 252/530, loss: 9.059906915354077e-06
2023-01-21 12:18:41.739840: step: 256/530, loss: 5.34057608092553e-06
2023-01-21 12:18:42.843369: step: 260/530, loss: 0.0009078502771444619
2023-01-21 12:18:43.933577: step: 264/530, loss: 0.0025032043922692537
2023-01-21 12:18:45.051967: step: 268/530, loss: 0.0019360543228685856
2023-01-21 12:18:46.161950: step: 272/530, loss: 0.0733974426984787
2023-01-21 12:18:47.273014: step: 276/530, loss: 0.000774383544921875
2023-01-21 12:18:48.374725: step: 280/530, loss: 0.02871309034526348
2023-01-21 12:18:49.493025: step: 284/530, loss: 0.015671921893954277
2023-01-21 12:18:50.624088: step: 288/530, loss: 0.0007848739624023438
2023-01-21 12:18:51.739477: step: 292/530, loss: 0.014094734564423561
2023-01-21 12:18:52.847528: step: 296/530, loss: 0.0025188445579260588
2023-01-21 12:18:53.993615: step: 300/530, loss: 0.0035118102096021175
2023-01-21 12:18:55.072401: step: 304/530, loss: 0.0019347190391272306
2023-01-21 12:18:56.172117: step: 308/530, loss: 0.0015083312755450606
2023-01-21 12:18:57.298612: step: 312/530, loss: 0.008204078301787376
2023-01-21 12:18:58.377275: step: 316/530, loss: 0.0050065042451024055
2023-01-21 12:18:59.466219: step: 320/530, loss: 0.0004498481866903603
2023-01-21 12:19:00.554378: step: 324/530, loss: 0.0012167930835857987
2023-01-21 12:19:01.631887: step: 328/530, loss: 0.008488655090332031
2023-01-21 12:19:02.743574: step: 332/530, loss: 0.02094249613583088
2023-01-21 12:19:03.882116: step: 336/530, loss: 0.0036266804672777653
2023-01-21 12:19:04.961618: step: 340/530, loss: 0.0006717205396853387
2023-01-21 12:19:06.089983: step: 344/530, loss: 0.003299427218735218
2023-01-21 12:19:07.191500: step: 348/530, loss: 0.0003722667752299458
2023-01-21 12:19:08.311814: step: 352/530, loss: 0.0003857612609863281
2023-01-21 12:19:09.452566: step: 356/530, loss: 0.012955093756318092
2023-01-21 12:19:10.559961: step: 360/530, loss: 5.327165126800537e-05
2023-01-21 12:19:11.653681: step: 364/530, loss: 0.0012156486045569181
2023-01-21 12:19:12.759598: step: 368/530, loss: 5.52177443751134e-05
2023-01-21 12:19:13.854496: step: 372/530, loss: 0.0017345428932458162
2023-01-21 12:19:14.970015: step: 376/530, loss: 1.8215177988167852e-05
2023-01-21 12:19:16.098304: step: 380/530, loss: 0.0064684865064918995
2023-01-21 12:19:17.211196: step: 384/530, loss: 0.0003680229128804058
2023-01-21 12:19:18.313765: step: 388/530, loss: 0.03520164638757706
2023-01-21 12:19:19.425509: step: 392/530, loss: 0.04322004318237305
2023-01-21 12:19:20.508975: step: 396/530, loss: 0.021910380572080612
2023-01-21 12:19:21.612120: step: 400/530, loss: 0.0017875672783702612
2023-01-21 12:19:22.719431: step: 404/530, loss: 0.00012631416029762477
2023-01-21 12:19:23.801455: step: 408/530, loss: 0.0010340691078454256
2023-01-21 12:19:24.910592: step: 412/530, loss: 0.0024124146439135075
2023-01-21 12:19:26.003523: step: 416/530, loss: 0.00013246535672806203
2023-01-21 12:19:27.103064: step: 420/530, loss: 0.011876678094267845
2023-01-21 12:19:28.189512: step: 424/530, loss: 0.001030922052450478
2023-01-21 12:19:29.282560: step: 428/530, loss: 0.0006758690578863025
2023-01-21 12:19:30.377733: step: 432/530, loss: 0.00838174857199192
2023-01-21 12:19:31.474643: step: 436/530, loss: 0.0007442474598065019
2023-01-21 12:19:32.564157: step: 440/530, loss: 0.00013618469529319555
2023-01-21 12:19:33.693614: step: 444/530, loss: 0.032279398292303085
2023-01-21 12:19:34.784981: step: 448/530, loss: 0.0067418101243674755
2023-01-21 12:19:35.861196: step: 452/530, loss: 0.0001356124848825857
2023-01-21 12:19:36.967235: step: 456/530, loss: 0.004150962922722101
2023-01-21 12:19:38.051097: step: 460/530, loss: 0.02308959886431694
2023-01-21 12:19:39.169150: step: 464/530, loss: 2.7084352041129023e-05
2023-01-21 12:19:40.285800: step: 468/530, loss: 7.905960228526965e-05
2023-01-21 12:19:41.410248: step: 472/530, loss: 0.0030261040665209293
2023-01-21 12:19:42.539572: step: 476/530, loss: 0.010237502865493298
2023-01-21 12:19:43.644564: step: 480/530, loss: 0.00848464947193861
2023-01-21 12:19:44.755113: step: 484/530, loss: 0.04960937798023224
2023-01-21 12:19:45.886095: step: 488/530, loss: 0.0007406234508380294
2023-01-21 12:19:46.968580: step: 492/530, loss: 0.05589485168457031
2023-01-21 12:19:48.046993: step: 496/530, loss: 0.00010499954805709422
2023-01-21 12:19:49.149857: step: 500/530, loss: 0.008489036001265049
2023-01-21 12:19:50.244505: step: 504/530, loss: 0.0075667379423975945
2023-01-21 12:19:51.378500: step: 508/530, loss: 0.036260221153497696
2023-01-21 12:19:52.492300: step: 512/530, loss: 0.8706932067871094
2023-01-21 12:19:53.598323: step: 516/530, loss: 0.004640483763068914
2023-01-21 12:19:54.699322: step: 520/530, loss: 0.000419425981817767
2023-01-21 12:19:55.766224: step: 524/530, loss: 0.0025835991837084293
2023-01-21 12:19:56.897218: step: 528/530, loss: 0.002392769092693925
2023-01-21 12:19:58.005182: step: 532/530, loss: 0.0637846291065216
2023-01-21 12:19:59.112225: step: 536/530, loss: 0.004237628076225519
2023-01-21 12:20:00.192116: step: 540/530, loss: 0.01355358399450779
2023-01-21 12:20:01.305420: step: 544/530, loss: 0.004283618647605181
2023-01-21 12:20:02.404213: step: 548/530, loss: 0.013311577029526234
2023-01-21 12:20:03.545577: step: 552/530, loss: 0.0060933115892112255
2023-01-21 12:20:04.618772: step: 556/530, loss: 0.04587965086102486
2023-01-21 12:20:05.715776: step: 560/530, loss: 0.0002696514129638672
2023-01-21 12:20:06.816443: step: 564/530, loss: 0.002296066377311945
2023-01-21 12:20:07.924074: step: 568/530, loss: 0.0070247650146484375
2023-01-21 12:20:09.063406: step: 572/530, loss: 0.029396986588835716
2023-01-21 12:20:10.162675: step: 576/530, loss: 4.0185448597185314e-05
2023-01-21 12:20:11.234900: step: 580/530, loss: 0.0011550902854651213
2023-01-21 12:20:12.352440: step: 584/530, loss: 0.0033814432099461555
2023-01-21 12:20:13.457850: step: 588/530, loss: 0.016238784417510033
2023-01-21 12:20:14.571868: step: 592/530, loss: 0.14269722998142242
2023-01-21 12:20:15.680835: step: 596/530, loss: 0.03598785772919655
2023-01-21 12:20:16.780554: step: 600/530, loss: 0.008385753259062767
2023-01-21 12:20:17.873318: step: 604/530, loss: 0.00024166106595657766
2023-01-21 12:20:18.999835: step: 608/530, loss: 0.0035868645645678043
2023-01-21 12:20:20.098341: step: 612/530, loss: 0.0011723518837243319
2023-01-21 12:20:21.245183: step: 616/530, loss: 0.001582336495630443
2023-01-21 12:20:22.386507: step: 620/530, loss: 0.024824142456054688
2023-01-21 12:20:23.453881: step: 624/530, loss: 0.0008823394891805947
2023-01-21 12:20:24.586355: step: 628/530, loss: 0.002735233400017023
2023-01-21 12:20:25.678118: step: 632/530, loss: 0.000911331211682409
2023-01-21 12:20:26.767672: step: 636/530, loss: 0.0002845764101948589
2023-01-21 12:20:27.917160: step: 640/530, loss: 0.015321922488510609
2023-01-21 12:20:29.004579: step: 644/530, loss: 0.006480979733169079
2023-01-21 12:20:30.128319: step: 648/530, loss: 0.005180645268410444
2023-01-21 12:20:31.230554: step: 652/530, loss: 0.008174420334398746
2023-01-21 12:20:32.319380: step: 656/530, loss: 0.026570606976747513
2023-01-21 12:20:33.423280: step: 660/530, loss: 0.014085614122450352
2023-01-21 12:20:34.527194: step: 664/530, loss: 0.003076934954151511
2023-01-21 12:20:35.686715: step: 668/530, loss: 0.00023622512526344508
2023-01-21 12:20:36.789330: step: 672/530, loss: 0.004090643022209406
2023-01-21 12:20:37.905566: step: 676/530, loss: 0.0003572463756427169
2023-01-21 12:20:39.008936: step: 680/530, loss: 0.018599510192871094
2023-01-21 12:20:40.108936: step: 684/530, loss: 0.0008249282836914062
2023-01-21 12:20:41.247428: step: 688/530, loss: 0.00023307801166083664
2023-01-21 12:20:42.363859: step: 692/530, loss: 8.277892629848793e-05
2023-01-21 12:20:43.435691: step: 696/530, loss: -3.814697606685513e-07
2023-01-21 12:20:44.545315: step: 700/530, loss: 0.00012264252291060984
2023-01-21 12:20:45.657703: step: 704/530, loss: 0.0019449234241619706
2023-01-21 12:20:46.755770: step: 708/530, loss: 0.00043258670484647155
2023-01-21 12:20:47.920358: step: 712/530, loss: 0.06276588141918182
2023-01-21 12:20:49.037740: step: 716/530, loss: 0.008349991403520107
2023-01-21 12:20:50.130717: step: 720/530, loss: 0.0009480953449383378
2023-01-21 12:20:51.227758: step: 724/530, loss: 0.0006827354081906378
2023-01-21 12:20:52.315572: step: 728/530, loss: 3.223419116693549e-05
2023-01-21 12:20:53.382765: step: 732/530, loss: 0.001206684042699635
2023-01-21 12:20:54.506279: step: 736/530, loss: 0.00024499892606399953
2023-01-21 12:20:55.596249: step: 740/530, loss: 0.008846950717270374
2023-01-21 12:20:56.724512: step: 744/530, loss: 0.02328777313232422
2023-01-21 12:20:57.821090: step: 748/530, loss: 0.04045991972088814
2023-01-21 12:20:58.934823: step: 752/530, loss: 0.002870941301807761
2023-01-21 12:21:00.039289: step: 756/530, loss: 0.01673445664346218
2023-01-21 12:21:01.103891: step: 760/530, loss: 0.004992750473320484
2023-01-21 12:21:02.172789: step: 764/530, loss: 0.014320469461381435
2023-01-21 12:21:03.287283: step: 768/530, loss: 0.04595832899212837
2023-01-21 12:21:04.388670: step: 772/530, loss: 0.0014236450660973787
2023-01-21 12:21:05.477352: step: 776/530, loss: 0.016146229580044746
2023-01-21 12:21:06.576351: step: 780/530, loss: 0.005085754673928022
2023-01-21 12:21:07.699370: step: 784/530, loss: 0.025014806538820267
2023-01-21 12:21:08.792249: step: 788/530, loss: 0.00013332365779206157
2023-01-21 12:21:09.897716: step: 792/530, loss: -7.82012921263231e-06
2023-01-21 12:21:10.987180: step: 796/530, loss: 0.025908375158905983
2023-01-21 12:21:12.090772: step: 800/530, loss: 0.00031108857365325093
2023-01-21 12:21:13.193613: step: 804/530, loss: 0.04907989501953125
2023-01-21 12:21:14.307946: step: 808/530, loss: 0.006317520514130592
2023-01-21 12:21:15.415461: step: 812/530, loss: 3.814698175119702e-06
2023-01-21 12:21:16.502883: step: 816/530, loss: 0.010487556457519531
2023-01-21 12:21:17.594099: step: 820/530, loss: 0.009267854504287243
2023-01-21 12:21:18.676188: step: 824/530, loss: 0.0009135246509686112
2023-01-21 12:21:19.775553: step: 828/530, loss: 1.9454957509879023e-05
2023-01-21 12:21:20.896371: step: 832/530, loss: 0.00038547517033293843
2023-01-21 12:21:21.989916: step: 836/530, loss: 0.003556156298145652
2023-01-21 12:21:23.104262: step: 840/530, loss: 0.002094459719955921
2023-01-21 12:21:24.202918: step: 844/530, loss: 0.005781507585197687
2023-01-21 12:21:25.295228: step: 848/530, loss: 0.0008722305065020919
2023-01-21 12:21:26.387606: step: 852/530, loss: 0.0002157211274607107
2023-01-21 12:21:27.490303: step: 856/530, loss: 0.022112656384706497
2023-01-21 12:21:28.604405: step: 860/530, loss: 0.0009470939403399825
2023-01-21 12:21:29.701622: step: 864/530, loss: 0.00062646868173033
2023-01-21 12:21:30.802476: step: 868/530, loss: 0.01717204973101616
2023-01-21 12:21:31.906391: step: 872/530, loss: 0.04960909113287926
2023-01-21 12:21:33.022604: step: 876/530, loss: 0.3084259033203125
2023-01-21 12:21:34.103068: step: 880/530, loss: 0.0038666725158691406
2023-01-21 12:21:35.206076: step: 884/530, loss: 1.33514404296875e-05
2023-01-21 12:21:36.289198: step: 888/530, loss: 0.00017509459576103836
2023-01-21 12:21:37.367212: step: 892/530, loss: 5.9819223679369316e-05
2023-01-21 12:21:38.474622: step: 896/530, loss: 0.057565879076719284
2023-01-21 12:21:39.582882: step: 900/530, loss: 0.0015078544383868575
2023-01-21 12:21:40.713305: step: 904/530, loss: 0.012163257226347923
2023-01-21 12:21:41.821194: step: 908/530, loss: 0.0001146316499216482
2023-01-21 12:21:42.924471: step: 912/530, loss: 1.8501283193472773e-05
2023-01-21 12:21:44.008324: step: 916/530, loss: 4.272460864740424e-05
2023-01-21 12:21:45.125298: step: 920/530, loss: 0.0014146805042400956
2023-01-21 12:21:46.238721: step: 924/530, loss: 0.07103166729211807
2023-01-21 12:21:47.322719: step: 928/530, loss: 0.00173273088876158
2023-01-21 12:21:48.400810: step: 932/530, loss: 0.0008845329284667969
2023-01-21 12:21:49.489056: step: 936/530, loss: 0.0010318756103515625
2023-01-21 12:21:50.583060: step: 940/530, loss: 0.0018466949695721269
2023-01-21 12:21:51.700410: step: 944/530, loss: 0.0009229898569174111
2023-01-21 12:21:52.814439: step: 948/530, loss: 0.013654994778335094
2023-01-21 12:21:53.965827: step: 952/530, loss: 0.0005373954772949219
2023-01-21 12:21:55.076985: step: 956/530, loss: 0.006377506535500288
2023-01-21 12:21:56.177789: step: 960/530, loss: 4.305839684093371e-05
2023-01-21 12:21:57.284331: step: 964/530, loss: 0.020833779126405716
2023-01-21 12:21:58.423263: step: 968/530, loss: 0.0005011558532714844
2023-01-21 12:21:59.530585: step: 972/530, loss: 0.020433997735381126
2023-01-21 12:22:00.629500: step: 976/530, loss: 6.198883056640625e-05
2023-01-21 12:22:01.776555: step: 980/530, loss: 0.00235919957049191
2023-01-21 12:22:02.858256: step: 984/530, loss: 2.403259350103326e-05
2023-01-21 12:22:03.986881: step: 988/530, loss: 0.0014646530617028475
2023-01-21 12:22:05.106160: step: 992/530, loss: 0.0170409195125103
2023-01-21 12:22:06.210558: step: 996/530, loss: 0.00012083053297828883
2023-01-21 12:22:07.303284: step: 1000/530, loss: 5.91278057981981e-06
2023-01-21 12:22:08.440419: step: 1004/530, loss: 9.784699068404734e-05
2023-01-21 12:22:09.549426: step: 1008/530, loss: 0.04106420278549194
2023-01-21 12:22:10.681002: step: 1012/530, loss: 0.00188703543972224
2023-01-21 12:22:11.795629: step: 1016/530, loss: 0.052794601768255234
2023-01-21 12:22:12.926413: step: 1020/530, loss: 0.0004684448358602822
2023-01-21 12:22:14.015462: step: 1024/530, loss: 0.0006625175592489541
2023-01-21 12:22:15.122965: step: 1028/530, loss: 0.0030277250334620476
2023-01-21 12:22:16.256104: step: 1032/530, loss: 0.00536193884909153
2023-01-21 12:22:17.361493: step: 1036/530, loss: 0.00016222000704146922
2023-01-21 12:22:18.512878: step: 1040/530, loss: 0.0004039764462504536
2023-01-21 12:22:19.648891: step: 1044/530, loss: 3.705024573719129e-05
2023-01-21 12:22:20.775149: step: 1048/530, loss: 1.3446808225126006e-05
2023-01-21 12:22:21.897952: step: 1052/530, loss: 0.0007089137798175216
2023-01-21 12:22:22.991645: step: 1056/530, loss: 0.001898956368677318
2023-01-21 12:22:24.106240: step: 1060/530, loss: 0.08673210442066193
2023-01-21 12:22:25.223617: step: 1064/530, loss: 0.024607278406620026
2023-01-21 12:22:26.349872: step: 1068/530, loss: 0.003500127699226141
2023-01-21 12:22:27.467795: step: 1072/530, loss: 0.00025043488130904734
2023-01-21 12:22:28.584570: step: 1076/530, loss: 0.03418693691492081
2023-01-21 12:22:29.700762: step: 1080/530, loss: 0.0018697292543947697
2023-01-21 12:22:30.817753: step: 1084/530, loss: 0.002153778215870261
2023-01-21 12:22:31.941623: step: 1088/530, loss: 0.0015455245738849044
2023-01-21 12:22:33.055449: step: 1092/530, loss: 0.0006849289056845009
2023-01-21 12:22:34.186138: step: 1096/530, loss: 0.00514488248154521
2023-01-21 12:22:35.293791: step: 1100/530, loss: 0.0028198242653161287
2023-01-21 12:22:36.376383: step: 1104/530, loss: 0.033954717218875885
2023-01-21 12:22:37.474317: step: 1108/530, loss: 6.742477853549644e-05
2023-01-21 12:22:38.574874: step: 1112/530, loss: 0.0024618147872388363
2023-01-21 12:22:39.676462: step: 1116/530, loss: 0.0015536308055743575
2023-01-21 12:22:40.792702: step: 1120/530, loss: 0.012928854674100876
2023-01-21 12:22:41.905015: step: 1124/530, loss: 0.0012012481456622481
2023-01-21 12:22:42.985003: step: 1128/530, loss: 0.00042724609375
2023-01-21 12:22:44.076323: step: 1132/530, loss: 0.0010509490966796875
2023-01-21 12:22:45.178910: step: 1136/530, loss: 0.0011124759912490845
2023-01-21 12:22:46.269702: step: 1140/530, loss: 0.0035295486450195312
2023-01-21 12:22:47.383696: step: 1144/530, loss: 0.004352736286818981
2023-01-21 12:22:48.474116: step: 1148/530, loss: 0.004186725709587336
2023-01-21 12:22:49.555547: step: 1152/530, loss: 0.0003269195731263608
2023-01-21 12:22:50.650579: step: 1156/530, loss: 0.003506183624267578
2023-01-21 12:22:51.743122: step: 1160/530, loss: 0.0007779121515341103
2023-01-21 12:22:52.823175: step: 1164/530, loss: 0.0012259007198736072
2023-01-21 12:22:53.918613: step: 1168/530, loss: 0.00035476687480695546
2023-01-21 12:22:55.024449: step: 1172/530, loss: 0.3261560797691345
2023-01-21 12:22:56.137046: step: 1176/530, loss: 0.002636814257130027
2023-01-21 12:22:57.260754: step: 1180/530, loss: 0.00030994415283203125
2023-01-21 12:22:58.362571: step: 1184/530, loss: 0.00011863708641612902
2023-01-21 12:22:59.493387: step: 1188/530, loss: 0.017110252752900124
2023-01-21 12:23:00.604561: step: 1192/530, loss: 2.8324127924861386e-05
2023-01-21 12:23:01.690479: step: 1196/530, loss: 0.005969715304672718
2023-01-21 12:23:02.770555: step: 1200/530, loss: 0.5043748617172241
2023-01-21 12:23:03.890564: step: 1204/530, loss: 0.005442619323730469
2023-01-21 12:23:04.997021: step: 1208/530, loss: 0.008517075330018997
2023-01-21 12:23:06.083985: step: 1212/530, loss: 0.10449686646461487
2023-01-21 12:23:07.194170: step: 1216/530, loss: 0.00749282818287611
2023-01-21 12:23:08.303038: step: 1220/530, loss: 0.00422515906393528
2023-01-21 12:23:09.424410: step: 1224/530, loss: 1.2816870212554932
2023-01-21 12:23:10.493625: step: 1228/530, loss: -1.0013580322265625e-05
2023-01-21 12:23:11.596578: step: 1232/530, loss: 0.005074501037597656
2023-01-21 12:23:12.688397: step: 1236/530, loss: 0.04412341117858887
2023-01-21 12:23:13.803633: step: 1240/530, loss: 0.010665512643754482
2023-01-21 12:23:14.931341: step: 1244/530, loss: 0.0008766174432821572
2023-01-21 12:23:16.021752: step: 1248/530, loss: 0.0002544403250794858
2023-01-21 12:23:17.138281: step: 1252/530, loss: 0.08309125900268555
2023-01-21 12:23:18.243648: step: 1256/530, loss: 0.03335275501012802
2023-01-21 12:23:19.329962: step: 1260/530, loss: 0.0006405829917639494
2023-01-21 12:23:20.425274: step: 1264/530, loss: 0.009982299990952015
2023-01-21 12:23:21.519584: step: 1268/530, loss: 5.14984130859375e-05
2023-01-21 12:23:22.591089: step: 1272/530, loss: 0.014845085330307484
2023-01-21 12:23:23.701586: step: 1276/530, loss: 0.0006991386180743575
2023-01-21 12:23:24.804622: step: 1280/530, loss: 0.01333694439381361
2023-01-21 12:23:25.890767: step: 1284/530, loss: 0.0013908863766118884
2023-01-21 12:23:26.992051: step: 1288/530, loss: 0.0005038261879235506
2023-01-21 12:23:28.090827: step: 1292/530, loss: 0.0001253128139069304
2023-01-21 12:23:29.199748: step: 1296/530, loss: 0.04228544235229492
2023-01-21 12:23:30.309249: step: 1300/530, loss: 2.1457672119140625e-05
2023-01-21 12:23:31.441689: step: 1304/530, loss: 0.013326907530426979
2023-01-21 12:23:32.525384: step: 1308/530, loss: 0.0006330490577965975
2023-01-21 12:23:33.633730: step: 1312/530, loss: 0.08600423485040665
2023-01-21 12:23:34.731994: step: 1316/530, loss: 7.266998727573082e-05
2023-01-21 12:23:35.830878: step: 1320/530, loss: 0.00010452271089889109
2023-01-21 12:23:36.922780: step: 1324/530, loss: 0.03246946632862091
2023-01-21 12:23:38.018213: step: 1328/530, loss: 0.0005215167766436934
2023-01-21 12:23:39.133940: step: 1332/530, loss: 0.0013937473995611072
2023-01-21 12:23:40.248387: step: 1336/530, loss: 0.004111194983124733
2023-01-21 12:23:41.362259: step: 1340/530, loss: 0.04070339351892471
2023-01-21 12:23:42.472737: step: 1344/530, loss: 0.043186187744140625
2023-01-21 12:23:43.569447: step: 1348/530, loss: 0.006456160452216864
2023-01-21 12:23:44.662154: step: 1352/530, loss: 0.008366155438125134
2023-01-21 12:23:45.801453: step: 1356/530, loss: 0.008889198303222656
2023-01-21 12:23:46.894957: step: 1360/530, loss: 0.0006443500169552863
2023-01-21 12:23:47.975865: step: 1364/530, loss: 0.0143890380859375
2023-01-21 12:23:49.068538: step: 1368/530, loss: 0.00018167495727539062
2023-01-21 12:23:50.146986: step: 1372/530, loss: 1.792907642084174e-05
2023-01-21 12:23:51.276644: step: 1376/530, loss: 0.0018383980495855212
2023-01-21 12:23:52.398185: step: 1380/530, loss: 0.01601867564022541
2023-01-21 12:23:53.505581: step: 1384/530, loss: 0.044692136347293854
2023-01-21 12:23:54.655951: step: 1388/530, loss: 0.057747840881347656
2023-01-21 12:23:55.747568: step: 1392/530, loss: 0.0002559661807026714
2023-01-21 12:23:56.843323: step: 1396/530, loss: 0.00120887765660882
2023-01-21 12:23:57.943807: step: 1400/530, loss: 0.0016321182483807206
2023-01-21 12:23:59.051194: step: 1404/530, loss: 0.010409926995635033
2023-01-21 12:24:00.193751: step: 1408/530, loss: 0.009701347909867764
2023-01-21 12:24:01.328615: step: 1412/530, loss: 0.003151798387989402
2023-01-21 12:24:02.439382: step: 1416/530, loss: 0.0027456283569335938
2023-01-21 12:24:03.547481: step: 1420/530, loss: 0.02613067626953125
2023-01-21 12:24:04.665523: step: 1424/530, loss: 0.07314015179872513
2023-01-21 12:24:05.767535: step: 1428/530, loss: 0.5101076364517212
2023-01-21 12:24:06.879279: step: 1432/530, loss: 0.016321564093232155
2023-01-21 12:24:07.982520: step: 1436/530, loss: 0.00026526450528763235
2023-01-21 12:24:09.095376: step: 1440/530, loss: 0.018955565989017487
2023-01-21 12:24:10.201122: step: 1444/530, loss: 0.004082346335053444
2023-01-21 12:24:11.328791: step: 1448/530, loss: 0.02451639249920845
2023-01-21 12:24:12.418444: step: 1452/530, loss: 0.0017275810241699219
2023-01-21 12:24:13.532271: step: 1456/530, loss: 0.05800151824951172
2023-01-21 12:24:14.620782: step: 1460/530, loss: 0.003689384553581476
2023-01-21 12:24:15.747188: step: 1464/530, loss: 0.061934471130371094
2023-01-21 12:24:16.874723: step: 1468/530, loss: 0.0007879257318563759
2023-01-21 12:24:17.990810: step: 1472/530, loss: 0.02274627611041069
2023-01-21 12:24:19.064491: step: 1476/530, loss: 0.006922912783920765
2023-01-21 12:24:20.169844: step: 1480/530, loss: 0.022803355008363724
2023-01-21 12:24:21.265524: step: 1484/530, loss: 2.4223329091910273e-05
2023-01-21 12:24:22.355005: step: 1488/530, loss: 0.09159398823976517
2023-01-21 12:24:23.470505: step: 1492/530, loss: 0.001693677855655551
2023-01-21 12:24:24.572757: step: 1496/530, loss: 0.027047349140048027
2023-01-21 12:24:25.707669: step: 1500/530, loss: 0.025938892737030983
2023-01-21 12:24:26.830224: step: 1504/530, loss: 0.006134796421974897
2023-01-21 12:24:27.926373: step: 1508/530, loss: 0.010800862684845924
2023-01-21 12:24:29.001566: step: 1512/530, loss: 0.0016693114303052425
2023-01-21 12:24:30.096309: step: 1516/530, loss: 0.0024861812125891447
2023-01-21 12:24:31.197031: step: 1520/530, loss: 0.0006982803461141884
2023-01-21 12:24:32.319982: step: 1524/530, loss: 0.005189323332160711
2023-01-21 12:24:33.445965: step: 1528/530, loss: 0.048064421862363815
2023-01-21 12:24:34.560250: step: 1532/530, loss: 0.0012525558704510331
2023-01-21 12:24:35.647938: step: 1536/530, loss: 0.0011914253700524569
2023-01-21 12:24:36.742791: step: 1540/530, loss: 0.05544796213507652
2023-01-21 12:24:37.832916: step: 1544/530, loss: 0.03422355651855469
2023-01-21 12:24:38.925972: step: 1548/530, loss: 0.026355935260653496
2023-01-21 12:24:40.041742: step: 1552/530, loss: 0.002795839449390769
2023-01-21 12:24:41.192341: step: 1556/530, loss: 0.027133941650390625
2023-01-21 12:24:42.309091: step: 1560/530, loss: 0.01924610137939453
2023-01-21 12:24:43.410260: step: 1564/530, loss: 9.851455979514867e-05
2023-01-21 12:24:44.521275: step: 1568/530, loss: 0.003003883408382535
2023-01-21 12:24:45.618174: step: 1572/530, loss: 0.000716781651135534
2023-01-21 12:24:46.701077: step: 1576/530, loss: 0.006088065914809704
2023-01-21 12:24:47.782249: step: 1580/530, loss: 0.00209465017542243
2023-01-21 12:24:48.883755: step: 1584/530, loss: 0.026086904108524323
2023-01-21 12:24:49.993350: step: 1588/530, loss: 0.0016064643859863281
2023-01-21 12:24:51.081486: step: 1592/530, loss: 0.005140113644301891
2023-01-21 12:24:52.176076: step: 1596/530, loss: 0.0002264022914459929
2023-01-21 12:24:53.266477: step: 1600/530, loss: 0.007840538397431374
2023-01-21 12:24:54.347269: step: 1604/530, loss: 0.00015954970149323344
2023-01-21 12:24:55.433916: step: 1608/530, loss: 0.025756072252988815
2023-01-21 12:24:56.557693: step: 1612/530, loss: 1.9550323486328125e-05
2023-01-21 12:24:57.668910: step: 1616/530, loss: 0.00357818603515625
2023-01-21 12:24:58.772337: step: 1620/530, loss: 0.0004165649588685483
2023-01-21 12:24:59.880817: step: 1624/530, loss: 0.018174361437559128
2023-01-21 12:25:01.014134: step: 1628/530, loss: 0.0745948776602745
2023-01-21 12:25:02.107581: step: 1632/530, loss: 0.00011482238915050402
2023-01-21 12:25:03.212230: step: 1636/530, loss: 0.01668567769229412
2023-01-21 12:25:04.314702: step: 1640/530, loss: 0.007037449162453413
2023-01-21 12:25:05.419842: step: 1644/530, loss: 0.00028247834416106343
2023-01-21 12:25:06.508285: step: 1648/530, loss: 0.00013208389282226562
2023-01-21 12:25:07.598907: step: 1652/530, loss: 5.6743621826171875e-05
2023-01-21 12:25:08.697781: step: 1656/530, loss: 0.0015368461608886719
2023-01-21 12:25:09.807917: step: 1660/530, loss: 0.0030134201515465975
2023-01-21 12:25:10.941623: step: 1664/530, loss: 0.0008429527515545487
2023-01-21 12:25:12.057672: step: 1668/530, loss: 0.1338164359331131
2023-01-21 12:25:13.179071: step: 1672/530, loss: 0.001293182373046875
2023-01-21 12:25:14.272342: step: 1676/530, loss: 0.004181480500847101
2023-01-21 12:25:15.386181: step: 1680/530, loss: 0.021399687975645065
2023-01-21 12:25:16.495633: step: 1684/530, loss: 0.0029786110389977694
2023-01-21 12:25:17.562642: step: 1688/530, loss: 0.009052181616425514
2023-01-21 12:25:18.674653: step: 1692/530, loss: 0.00313396449200809
2023-01-21 12:25:19.792589: step: 1696/530, loss: 0.0006866455078125
2023-01-21 12:25:20.898099: step: 1700/530, loss: 0.0005804062238894403
2023-01-21 12:25:22.029442: step: 1704/530, loss: 0.015380478464066982
2023-01-21 12:25:23.151795: step: 1708/530, loss: 0.0005458832019940019
2023-01-21 12:25:24.256888: step: 1712/530, loss: 0.09722118079662323
2023-01-21 12:25:25.398347: step: 1716/530, loss: 0.0046180724166333675
2023-01-21 12:25:26.518656: step: 1720/530, loss: 0.014525937847793102
2023-01-21 12:25:27.592516: step: 1724/530, loss: 1.9836426872643642e-05
2023-01-21 12:25:28.639598: step: 1728/530, loss: 0.035836268216371536
2023-01-21 12:25:29.727348: step: 1732/530, loss: 2.2315980459097773e-05
2023-01-21 12:25:30.847566: step: 1736/530, loss: 0.0034383772872388363
2023-01-21 12:25:31.968156: step: 1740/530, loss: -6.294250852079131e-06
2023-01-21 12:25:33.091911: step: 1744/530, loss: 0.0009846687316894531
2023-01-21 12:25:34.201383: step: 1748/530, loss: 0.004477024078369141
2023-01-21 12:25:35.280748: step: 1752/530, loss: 0.0009902954334393144
2023-01-21 12:25:36.406937: step: 1756/530, loss: 1.8596649169921875e-05
2023-01-21 12:25:37.531075: step: 1760/530, loss: 0.0003364563162904233
2023-01-21 12:25:38.636952: step: 1764/530, loss: 0.03831992298364639
2023-01-21 12:25:39.742437: step: 1768/530, loss: 0.00010576248314464465
2023-01-21 12:25:40.852211: step: 1772/530, loss: 0.003054332686588168
2023-01-21 12:25:41.947990: step: 1776/530, loss: 4.601478394761216e-06
2023-01-21 12:25:43.030707: step: 1780/530, loss: 0.0038658143021166325
2023-01-21 12:25:44.140062: step: 1784/530, loss: 0.0040381429716944695
2023-01-21 12:25:45.231253: step: 1788/530, loss: 0.0007472038851119578
2023-01-21 12:25:46.330999: step: 1792/530, loss: 0.0008172988891601562
2023-01-21 12:25:47.446042: step: 1796/530, loss: 5.559921555686742e-05
2023-01-21 12:25:48.529301: step: 1800/530, loss: 1.583099401614163e-05
2023-01-21 12:25:49.651096: step: 1804/530, loss: 0.00021667481632903218
2023-01-21 12:25:50.753526: step: 1808/530, loss: 0.00011234283010708168
2023-01-21 12:25:51.888988: step: 1812/530, loss: 0.012704659253358841
2023-01-21 12:25:53.021076: step: 1816/530, loss: 0.004326343536376953
2023-01-21 12:25:54.120298: step: 1820/530, loss: 7.934570021461695e-05
2023-01-21 12:25:55.237287: step: 1824/530, loss: 0.003646564669907093
2023-01-21 12:25:56.313204: step: 1828/530, loss: 0.0010173798073083162
2023-01-21 12:25:57.387800: step: 1832/530, loss: 0.014623928815126419
2023-01-21 12:25:58.484597: step: 1836/530, loss: 0.0008357047918252647
2023-01-21 12:25:59.584878: step: 1840/530, loss: 2.0122528439969756e-05
2023-01-21 12:26:00.692670: step: 1844/530, loss: 0.021237945184111595
2023-01-21 12:26:01.793538: step: 1848/530, loss: 0.00845479965209961
2023-01-21 12:26:02.891653: step: 1852/530, loss: 0.0033786774147301912
2023-01-21 12:26:04.006157: step: 1856/530, loss: 1.258850079466356e-05
2023-01-21 12:26:05.131930: step: 1860/530, loss: 0.01694471947848797
2023-01-21 12:26:06.276004: step: 1864/530, loss: 0.018485261127352715
2023-01-21 12:26:07.396108: step: 1868/530, loss: 0.004404640290886164
2023-01-21 12:26:08.502938: step: 1872/530, loss: 3.1280520488508046e-05
2023-01-21 12:26:09.611683: step: 1876/530, loss: 0.013298416510224342
2023-01-21 12:26:10.749346: step: 1880/530, loss: 0.047537706792354584
2023-01-21 12:26:11.860205: step: 1884/530, loss: 0.00022721290588378906
2023-01-21 12:26:12.989832: step: 1888/530, loss: 0.0003864288446493447
2023-01-21 12:26:14.099654: step: 1892/530, loss: 0.0007467747200280428
2023-01-21 12:26:15.225240: step: 1896/530, loss: 0.0008653640979900956
2023-01-21 12:26:16.346912: step: 1900/530, loss: 0.0008832932217046618
2023-01-21 12:26:17.465434: step: 1904/530, loss: 5.416870044427924e-05
2023-01-21 12:26:18.608887: step: 1908/530, loss: 8.22067231638357e-05
2023-01-21 12:26:19.725362: step: 1912/530, loss: 0.00596466101706028
2023-01-21 12:26:20.820949: step: 1916/530, loss: 0.0001983642578125
2023-01-21 12:26:21.925235: step: 1920/530, loss: 0.0003845214960165322
2023-01-21 12:26:23.033664: step: 1924/530, loss: 7.79151960159652e-05
2023-01-21 12:26:24.129849: step: 1928/530, loss: 0.024324703961610794
2023-01-21 12:26:25.203751: step: 1932/530, loss: 0.001174163888208568
2023-01-21 12:26:26.293272: step: 1936/530, loss: 0.0005849838489666581
2023-01-21 12:26:27.406125: step: 1940/530, loss: 0.00019521712965797633
2023-01-21 12:26:28.502781: step: 1944/530, loss: 0.025488663464784622
2023-01-21 12:26:29.608804: step: 1948/530, loss: 0.0009419441339559853
2023-01-21 12:26:30.711205: step: 1952/530, loss: 0.04294757917523384
2023-01-21 12:26:31.813513: step: 1956/530, loss: 6.980896432651207e-05
2023-01-21 12:26:32.942582: step: 1960/530, loss: 0.03148479387164116
2023-01-21 12:26:34.047779: step: 1964/530, loss: 0.019302941858768463
2023-01-21 12:26:35.177257: step: 1968/530, loss: 0.008126449771225452
2023-01-21 12:26:36.292411: step: 1972/530, loss: 0.0011161804432049394
2023-01-21 12:26:37.398032: step: 1976/530, loss: 0.010176753625273705
2023-01-21 12:26:38.498663: step: 1980/530, loss: 0.00593180675059557
2023-01-21 12:26:39.592468: step: 1984/530, loss: 0.01613016054034233
2023-01-21 12:26:40.681355: step: 1988/530, loss: 0.0032448293641209602
2023-01-21 12:26:41.784837: step: 1992/530, loss: 0.005726432893425226
2023-01-21 12:26:42.883628: step: 1996/530, loss: 0.00026531220646575093
2023-01-21 12:26:44.002940: step: 2000/530, loss: 4.405975414556451e-05
2023-01-21 12:26:45.127101: step: 2004/530, loss: 0.0003266334533691406
2023-01-21 12:26:46.211915: step: 2008/530, loss: 0.016266725957393646
2023-01-21 12:26:47.334489: step: 2012/530, loss: 0.0010808944934979081
2023-01-21 12:26:48.509132: step: 2016/530, loss: 0.0034533501602709293
2023-01-21 12:26:49.612770: step: 2020/530, loss: 0.008124828338623047
2023-01-21 12:26:50.707839: step: 2024/530, loss: 7.705688767600805e-05
2023-01-21 12:26:51.818214: step: 2028/530, loss: 0.00010957718041026965
2023-01-21 12:26:52.939931: step: 2032/530, loss: 0.019656755030155182
2023-01-21 12:26:54.045591: step: 2036/530, loss: 0.021117210388183594
2023-01-21 12:26:55.197201: step: 2040/530, loss: 0.0003597259637899697
2023-01-21 12:26:56.342163: step: 2044/530, loss: 0.0007114410400390625
2023-01-21 12:26:57.441813: step: 2048/530, loss: 0.02782921865582466
2023-01-21 12:26:58.547738: step: 2052/530, loss: 0.02720027044415474
2023-01-21 12:26:59.669366: step: 2056/530, loss: 0.0007640838739462197
2023-01-21 12:27:00.788245: step: 2060/530, loss: 0.0013050080742686987
2023-01-21 12:27:01.894068: step: 2064/530, loss: 0.02047717012465
2023-01-21 12:27:03.029927: step: 2068/530, loss: 0.015955066308379173
2023-01-21 12:27:04.137294: step: 2072/530, loss: 0.00010824203491210938
2023-01-21 12:27:05.221752: step: 2076/530, loss: 0.0002804756222758442
2023-01-21 12:27:06.324584: step: 2080/530, loss: 0.002164554549381137
2023-01-21 12:27:07.413278: step: 2084/530, loss: 0.02267751842737198
2023-01-21 12:27:08.536521: step: 2088/530, loss: 4.2629242670955136e-05
2023-01-21 12:27:09.639107: step: 2092/530, loss: 0.002406788058578968
2023-01-21 12:27:10.754243: step: 2096/530, loss: 0.0003466606140136719
2023-01-21 12:27:11.867512: step: 2100/530, loss: 0.0883968323469162
2023-01-21 12:27:12.960399: step: 2104/530, loss: 2.3460386728402227e-05
2023-01-21 12:27:14.059547: step: 2108/530, loss: 0.004645824432373047
2023-01-21 12:27:15.179313: step: 2112/530, loss: 0.011185836978256702
2023-01-21 12:27:16.276159: step: 2116/530, loss: 0.016965484246611595
2023-01-21 12:27:17.394451: step: 2120/530, loss: 0.047889139503240585
==================================================
Loss: 0.019
--------------------
Dev: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Test: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Chinese: {'event': {'p': 0.5789473684210527, 'r': 0.8148148148148148, 'f1': 0.6769230769230768}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Russian: {'event': {'p': 0.39473684210526316, 'r': 0.4166666666666667, 'f1': 0.40540540540540543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Korean: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 12:28:01.381271: step: 4/530, loss: 0.001223230268806219
2023-01-21 12:28:02.477413: step: 8/530, loss: 0.0003259658988099545
2023-01-21 12:28:03.590936: step: 12/530, loss: 0.1738794893026352
2023-01-21 12:28:04.688695: step: 16/530, loss: 0.0008614063845016062
2023-01-21 12:28:05.780765: step: 20/530, loss: 0.004119491670280695
2023-01-21 12:28:06.871951: step: 24/530, loss: 0.010311508551239967
2023-01-21 12:28:07.976436: step: 28/530, loss: 0.0067477719858288765
2023-01-21 12:28:09.065543: step: 32/530, loss: 0.030724050477147102
2023-01-21 12:28:10.175896: step: 36/530, loss: 1.277923547604587e-05
2023-01-21 12:28:11.269829: step: 40/530, loss: 0.0001356124848825857
2023-01-21 12:28:12.379702: step: 44/530, loss: 6.675720101156912e-07
2023-01-21 12:28:13.496587: step: 48/530, loss: 0.000358772260369733
2023-01-21 12:28:14.629912: step: 52/530, loss: 0.0010837555164471269
2023-01-21 12:28:15.785414: step: 56/530, loss: 0.002117633819580078
2023-01-21 12:28:16.900345: step: 60/530, loss: 0.03319740295410156
2023-01-21 12:28:18.068822: step: 64/530, loss: 0.0018774033524096012
2023-01-21 12:28:19.189334: step: 68/530, loss: 0.0018703460227698088
2023-01-21 12:28:20.293555: step: 72/530, loss: 0.006689739413559437
2023-01-21 12:28:21.401423: step: 76/530, loss: 0.655320405960083
2023-01-21 12:28:22.510166: step: 80/530, loss: 0.006328773684799671
2023-01-21 12:28:23.633102: step: 84/530, loss: 1.430511474609375e-05
2023-01-21 12:28:24.720510: step: 88/530, loss: 0.005216026678681374
2023-01-21 12:28:25.805880: step: 92/530, loss: 0.0012471199734136462
2023-01-21 12:28:26.920841: step: 96/530, loss: 0.0008646965143270791
2023-01-21 12:28:28.019597: step: 100/530, loss: 5.922317723161541e-05
2023-01-21 12:28:29.152392: step: 104/530, loss: 0.06308680027723312
2023-01-21 12:28:30.245050: step: 108/530, loss: 0.006271076388657093
2023-01-21 12:28:31.309982: step: 112/530, loss: 0.00993957556784153
2023-01-21 12:28:32.443556: step: 116/530, loss: 0.03684253618121147
2023-01-21 12:28:33.559974: step: 120/530, loss: 0.00023345947556663305
2023-01-21 12:28:34.646933: step: 124/530, loss: 0.005297183990478516
2023-01-21 12:28:35.758369: step: 128/530, loss: 0.0022068978287279606
2023-01-21 12:28:36.866737: step: 132/530, loss: 0.06721878051757812
2023-01-21 12:28:37.964326: step: 136/530, loss: 3.62396240234375e-05
2023-01-21 12:28:39.058423: step: 140/530, loss: 0.0019158362410962582
2023-01-21 12:28:40.171235: step: 144/530, loss: 0.007707977667450905
2023-01-21 12:28:41.281296: step: 148/530, loss: 0.00526771554723382
2023-01-21 12:28:42.376111: step: 152/530, loss: 0.019206427037715912
2023-01-21 12:28:43.493021: step: 156/530, loss: 0.024002360180020332
2023-01-21 12:28:44.586815: step: 160/530, loss: 0.0004898071638308465
2023-01-21 12:28:45.686925: step: 164/530, loss: 0.0011127472389489412
2023-01-21 12:28:46.809205: step: 168/530, loss: 0.005709266755729914
2023-01-21 12:28:47.908713: step: 172/530, loss: 0.008604193106293678
2023-01-21 12:28:49.032262: step: 176/530, loss: -1.430511474609375e-06
2023-01-21 12:28:50.151111: step: 180/530, loss: 0.0034673691261559725
2023-01-21 12:28:51.288869: step: 184/530, loss: 0.0011022567050531507
2023-01-21 12:28:52.396642: step: 188/530, loss: 0.00027079583378508687
2023-01-21 12:28:53.484986: step: 192/530, loss: 0.02292327769100666
2023-01-21 12:28:54.592945: step: 196/530, loss: 0.0003555298026185483
2023-01-21 12:28:55.690081: step: 200/530, loss: 0.010971642099320889
2023-01-21 12:28:56.838034: step: 204/530, loss: 0.013446426950395107
2023-01-21 12:28:57.932465: step: 208/530, loss: 6.69479341013357e-05
2023-01-21 12:28:59.015201: step: 212/530, loss: 7.181167893577367e-05
2023-01-21 12:29:00.168011: step: 216/530, loss: 7.500648644054309e-05
2023-01-21 12:29:01.250712: step: 220/530, loss: 0.0002321243373444304
2023-01-21 12:29:02.404051: step: 224/530, loss: 0.040443990379571915
2023-01-21 12:29:03.515014: step: 228/530, loss: 0.00324935931712389
2023-01-21 12:29:04.605477: step: 232/530, loss: 0.009080648422241211
2023-01-21 12:29:05.715126: step: 236/530, loss: 0.0015554428100585938
2023-01-21 12:29:06.815974: step: 240/530, loss: 0.0017174005042761564
2023-01-21 12:29:07.917458: step: 244/530, loss: 0.002349853515625
2023-01-21 12:29:09.023469: step: 248/530, loss: 0.0004907607799395919
2023-01-21 12:29:10.126429: step: 252/530, loss: 0.011743927374482155
2023-01-21 12:29:11.237824: step: 256/530, loss: 0.0059282779693603516
2023-01-21 12:29:12.366096: step: 260/530, loss: 2.2792815798311494e-05
2023-01-21 12:29:13.479211: step: 264/530, loss: 0.003955650143325329
2023-01-21 12:29:14.575090: step: 268/530, loss: 0.026785852387547493
2023-01-21 12:29:15.692105: step: 272/530, loss: 4.425048973644152e-05
2023-01-21 12:29:16.798305: step: 276/530, loss: 0.003799057099968195
2023-01-21 12:29:17.895265: step: 280/530, loss: 0.0005006790161132812
2023-01-21 12:29:19.006738: step: 284/530, loss: 0.04760046303272247
2023-01-21 12:29:20.124336: step: 288/530, loss: 0.007458948064595461
2023-01-21 12:29:21.265906: step: 292/530, loss: 0.0013801574241369963
2023-01-21 12:29:22.399482: step: 296/530, loss: 1.5719053745269775
2023-01-21 12:29:23.489972: step: 300/530, loss: 0.04180707782506943
2023-01-21 12:29:24.592904: step: 304/530, loss: 0.0007768630748614669
2023-01-21 12:29:25.725571: step: 308/530, loss: 5.6838991440599784e-05
2023-01-21 12:29:26.833866: step: 312/530, loss: 0.0017410278087481856
2023-01-21 12:29:27.941908: step: 316/530, loss: 0.022579574957489967
2023-01-21 12:29:29.039040: step: 320/530, loss: 0.0325225368142128
2023-01-21 12:29:30.152785: step: 324/530, loss: 0.0003025055048055947
2023-01-21 12:29:31.259100: step: 328/530, loss: 9.479522850597277e-05
2023-01-21 12:29:32.357299: step: 332/530, loss: 0.006933259777724743
2023-01-21 12:29:33.449891: step: 336/530, loss: 0.013144874945282936
2023-01-21 12:29:34.564626: step: 340/530, loss: 0.020781993865966797
2023-01-21 12:29:35.691865: step: 344/530, loss: 0.2155187726020813
2023-01-21 12:29:36.808313: step: 348/530, loss: 0.006764793302863836
2023-01-21 12:29:37.922159: step: 352/530, loss: 0.03321046754717827
2023-01-21 12:29:39.008449: step: 356/530, loss: 0.00022153854661155492
2023-01-21 12:29:40.123875: step: 360/530, loss: 0.0005739211919717491
2023-01-21 12:29:41.257663: step: 364/530, loss: 0.007083797827363014
2023-01-21 12:29:42.356394: step: 368/530, loss: -6.103515261202119e-06
2023-01-21 12:29:43.459942: step: 372/530, loss: 0.0037605285178869963
2023-01-21 12:29:44.561326: step: 376/530, loss: 0.00016059876361396164
2023-01-21 12:29:45.677391: step: 380/530, loss: 0.017607450485229492
2023-01-21 12:29:46.805071: step: 384/530, loss: 0.03431444242596626
2023-01-21 12:29:47.911197: step: 388/530, loss: 0.0032397271133959293
2023-01-21 12:29:49.022583: step: 392/530, loss: 0.0005640983581542969
2023-01-21 12:29:50.155798: step: 396/530, loss: 0.0010150909656658769
2023-01-21 12:29:51.285623: step: 400/530, loss: 0.0014982223510742188
2023-01-21 12:29:52.373532: step: 404/530, loss: 0.019080162048339844
2023-01-21 12:29:53.484945: step: 408/530, loss: 0.022403717041015625
2023-01-21 12:29:54.595457: step: 412/530, loss: 0.0003603935183491558
2023-01-21 12:29:55.686250: step: 416/530, loss: 0.009385108947753906
2023-01-21 12:29:56.802979: step: 420/530, loss: 0.0025144575629383326
2023-01-21 12:29:57.875368: step: 424/530, loss: 5.435944331111386e-06
2023-01-21 12:29:58.971512: step: 428/530, loss: 0.0005411148304119706
2023-01-21 12:30:00.075556: step: 432/530, loss: 0.000263214111328125
2023-01-21 12:30:01.197859: step: 436/530, loss: 0.002623271895572543
2023-01-21 12:30:02.280045: step: 440/530, loss: 0.00019550323486328125
2023-01-21 12:30:03.391428: step: 444/530, loss: 0.0003775119548663497
2023-01-21 12:30:04.506600: step: 448/530, loss: 0.0038082122337073088
2023-01-21 12:30:05.599383: step: 452/530, loss: 3.900528099620715e-05
2023-01-21 12:30:06.682713: step: 456/530, loss: 0.029935408383607864
2023-01-21 12:30:07.815936: step: 460/530, loss: 0.0007833242416381836
2023-01-21 12:30:08.951918: step: 464/530, loss: 3.833770824712701e-05
2023-01-21 12:30:10.074449: step: 468/530, loss: 0.025014305487275124
2023-01-21 12:30:11.176589: step: 472/530, loss: 0.010751771740615368
2023-01-21 12:30:12.277795: step: 476/530, loss: 0.048979952931404114
2023-01-21 12:30:13.375354: step: 480/530, loss: 0.04413461685180664
2023-01-21 12:30:14.479264: step: 484/530, loss: 0.00740890484303236
2023-01-21 12:30:15.580600: step: 488/530, loss: 0.0014662742614746094
2023-01-21 12:30:16.681278: step: 492/530, loss: 0.0017795562744140625
2023-01-21 12:30:17.786506: step: 496/530, loss: 0.00013723372831009328
2023-01-21 12:30:18.907177: step: 500/530, loss: 0.09296799451112747
2023-01-21 12:30:20.030026: step: 504/530, loss: 0.09633350372314453
2023-01-21 12:30:21.131323: step: 508/530, loss: 0.0009740829700604081
2023-01-21 12:30:22.238459: step: 512/530, loss: 0.001823043916374445
2023-01-21 12:30:23.361138: step: 516/530, loss: 0.00019025802612304688
2023-01-21 12:30:24.469109: step: 520/530, loss: 6.771087555534905e-06
2023-01-21 12:30:25.589850: step: 524/530, loss: 0.0031440737657248974
2023-01-21 12:30:26.688513: step: 528/530, loss: 0.0050182342529296875
2023-01-21 12:30:27.815005: step: 532/530, loss: 0.04634227976202965
2023-01-21 12:30:28.936254: step: 536/530, loss: 7.362366159213707e-05
2023-01-21 12:30:30.057743: step: 540/530, loss: 0.014524650759994984
2023-01-21 12:30:31.139436: step: 544/530, loss: 0.0012355804210528731
2023-01-21 12:30:32.258353: step: 548/530, loss: 0.0051246643997728825
2023-01-21 12:30:33.358115: step: 552/530, loss: 0.00019512177095748484
2023-01-21 12:30:34.484877: step: 556/530, loss: 0.0004864693037234247
2023-01-21 12:30:35.576360: step: 560/530, loss: 0.045590780675411224
2023-01-21 12:30:36.677531: step: 564/530, loss: 0.5763065218925476
2023-01-21 12:30:37.795850: step: 568/530, loss: 0.0009144783252850175
2023-01-21 12:30:38.887480: step: 572/530, loss: 0.04613819345831871
2023-01-21 12:30:39.991290: step: 576/530, loss: 0.00035260917502455413
2023-01-21 12:30:41.088017: step: 580/530, loss: 0.00043716432992368937
2023-01-21 12:30:42.185594: step: 584/530, loss: 0.04950008541345596
2023-01-21 12:30:43.311062: step: 588/530, loss: 0.0010515213944017887
2023-01-21 12:30:44.451309: step: 592/530, loss: 7.295608156709932e-06
2023-01-21 12:30:45.550478: step: 596/530, loss: 0.0004485130193643272
2023-01-21 12:30:46.656764: step: 600/530, loss: 0.05837049335241318
2023-01-21 12:30:47.766839: step: 604/530, loss: 0.020619869232177734
2023-01-21 12:30:48.873106: step: 608/530, loss: 0.007382392883300781
2023-01-21 12:30:49.943783: step: 612/530, loss: 0.00658416748046875
2023-01-21 12:30:51.049989: step: 616/530, loss: 0.00838317908346653
2023-01-21 12:30:52.140425: step: 620/530, loss: 0.01456451416015625
2023-01-21 12:30:53.247585: step: 624/530, loss: 0.007539558224380016
2023-01-21 12:30:54.355567: step: 628/530, loss: 0.005856609903275967
2023-01-21 12:30:55.449440: step: 632/530, loss: 0.0017355919117107987
2023-01-21 12:30:56.563059: step: 636/530, loss: 0.0003650665457826108
2023-01-21 12:30:57.686336: step: 640/530, loss: 0.042017269879579544
2023-01-21 12:30:58.759051: step: 644/530, loss: 0.0003281593380961567
2023-01-21 12:30:59.863687: step: 648/530, loss: 0.010825205594301224
2023-01-21 12:31:00.965556: step: 652/530, loss: 0.03243480250239372
2023-01-21 12:31:02.041261: step: 656/530, loss: 0.0012981414329260588
2023-01-21 12:31:03.180521: step: 660/530, loss: 0.000619268452282995
2023-01-21 12:31:04.254968: step: 664/530, loss: 0.00185737619176507
2023-01-21 12:31:05.340153: step: 668/530, loss: 0.0005755424499511719
2023-01-21 12:31:06.449250: step: 672/530, loss: 0.011188507080078125
2023-01-21 12:31:07.548908: step: 676/530, loss: 0.006601238157600164
2023-01-21 12:31:08.637033: step: 680/530, loss: 0.0029247284401208162
2023-01-21 12:31:09.729572: step: 684/530, loss: 0.009040451608598232
2023-01-21 12:31:10.873852: step: 688/530, loss: 8.964539119915571e-06
2023-01-21 12:31:11.958101: step: 692/530, loss: 0.0006734848138876259
2023-01-21 12:31:13.041188: step: 696/530, loss: 0.000293731689453125
2023-01-21 12:31:14.163421: step: 700/530, loss: 0.4883761405944824
2023-01-21 12:31:15.257974: step: 704/530, loss: 0.00230236048810184
2023-01-21 12:31:16.372212: step: 708/530, loss: 0.008263016119599342
2023-01-21 12:31:17.482899: step: 712/530, loss: 0.00038132668123580515
2023-01-21 12:31:18.579355: step: 716/530, loss: 0.00845184363424778
2023-01-21 12:31:19.698156: step: 720/530, loss: 0.02366333082318306
2023-01-21 12:31:20.797861: step: 724/530, loss: 0.0014160156715661287
2023-01-21 12:31:21.922792: step: 728/530, loss: 4.4345855712890625e-05
2023-01-21 12:31:23.058784: step: 732/530, loss: 0.00022201538376975805
2023-01-21 12:31:24.178591: step: 736/530, loss: 0.0008140563732013106
2023-01-21 12:31:25.285145: step: 740/530, loss: 0.007577800657600164
2023-01-21 12:31:26.396753: step: 744/530, loss: 0.0001604080171091482
2023-01-21 12:31:27.518700: step: 748/530, loss: 0.029819585382938385
2023-01-21 12:31:28.617000: step: 752/530, loss: 6.828308687545359e-05
2023-01-21 12:31:29.730914: step: 756/530, loss: 0.0733589231967926
2023-01-21 12:31:30.830792: step: 760/530, loss: 0.016954900696873665
2023-01-21 12:31:31.944260: step: 764/530, loss: 0.00044803618220612407
2023-01-21 12:31:33.057982: step: 768/530, loss: 0.00041484832763671875
2023-01-21 12:31:34.180870: step: 772/530, loss: 0.0025035827420651913
2023-01-21 12:31:35.301666: step: 776/530, loss: 0.0026735307183116674
2023-01-21 12:31:36.372483: step: 780/530, loss: 2.2506712411995977e-05
2023-01-21 12:31:37.470566: step: 784/530, loss: 0.0019132614834234118
2023-01-21 12:31:38.606936: step: 788/530, loss: 0.002827930264174938
2023-01-21 12:31:39.721890: step: 792/530, loss: 0.022905398160219193
2023-01-21 12:31:40.844105: step: 796/530, loss: 0.03483419120311737
2023-01-21 12:31:41.964963: step: 800/530, loss: 0.0018978118896484375
2023-01-21 12:31:43.057741: step: 804/530, loss: 0.004006767179816961
2023-01-21 12:31:44.142769: step: 808/530, loss: 0.02750072441995144
2023-01-21 12:31:45.291378: step: 812/530, loss: 0.054307177662849426
2023-01-21 12:31:46.381766: step: 816/530, loss: 0.00027027129544876516
2023-01-21 12:31:47.476366: step: 820/530, loss: 0.0004173278866801411
2023-01-21 12:31:48.585596: step: 824/530, loss: 0.0001218795805471018
2023-01-21 12:31:49.733893: step: 828/530, loss: 0.060800742357969284
2023-01-21 12:31:50.848638: step: 832/530, loss: 0.00015048982459120452
2023-01-21 12:31:51.938318: step: 836/530, loss: 0.017201997339725494
2023-01-21 12:31:53.038644: step: 840/530, loss: 0.00020256043353583664
2023-01-21 12:31:54.132353: step: 844/530, loss: 0.00136737828142941
2023-01-21 12:31:55.278525: step: 848/530, loss: 4.749298022943549e-05
2023-01-21 12:31:56.396869: step: 852/530, loss: 0.018430422991514206
2023-01-21 12:31:57.502778: step: 856/530, loss: 0.002789330668747425
2023-01-21 12:31:58.636119: step: 860/530, loss: 0.01636352576315403
2023-01-21 12:31:59.730612: step: 864/530, loss: 0.002908372785896063
2023-01-21 12:32:00.812618: step: 868/530, loss: 0.009708167053759098
2023-01-21 12:32:01.922007: step: 872/530, loss: 0.004147339146584272
2023-01-21 12:32:03.014247: step: 876/530, loss: 6.895065598655492e-05
2023-01-21 12:32:04.112194: step: 880/530, loss: 0.019960401579737663
2023-01-21 12:32:05.242844: step: 884/530, loss: 0.011982726864516735
2023-01-21 12:32:06.333187: step: 888/530, loss: 0.0012177468743175268
2023-01-21 12:32:07.466253: step: 892/530, loss: 0.031755831092596054
2023-01-21 12:32:08.559456: step: 896/530, loss: 0.0010133743053302169
2023-01-21 12:32:09.698084: step: 900/530, loss: 0.0001554012269480154
2023-01-21 12:32:10.811694: step: 904/530, loss: 0.06439266353845596
2023-01-21 12:32:11.954667: step: 908/530, loss: 0.006093025207519531
2023-01-21 12:32:13.069881: step: 912/530, loss: 0.002510452177375555
2023-01-21 12:32:14.164158: step: 916/530, loss: 0.001956939697265625
2023-01-21 12:32:15.285171: step: 920/530, loss: 0.008199977688491344
2023-01-21 12:32:16.369784: step: 924/530, loss: 0.00013809204392600805
2023-01-21 12:32:17.475233: step: 928/530, loss: 0.00019268988398835063
2023-01-21 12:32:18.581046: step: 932/530, loss: 0.01661110110580921
2023-01-21 12:32:19.673151: step: 936/530, loss: 0.003295993898063898
2023-01-21 12:32:20.781919: step: 940/530, loss: 0.005607128143310547
2023-01-21 12:32:21.891909: step: 944/530, loss: 0.05993795394897461
2023-01-21 12:32:22.985484: step: 948/530, loss: 0.0001770019589457661
2023-01-21 12:32:24.068330: step: 952/530, loss: 0.00013265610323287547
2023-01-21 12:32:25.162586: step: 956/530, loss: 0.03682594373822212
2023-01-21 12:32:26.281665: step: 960/530, loss: 0.007557678502053022
2023-01-21 12:32:27.375297: step: 964/530, loss: 0.004063415341079235
2023-01-21 12:32:28.470903: step: 968/530, loss: 0.0008279799949377775
2023-01-21 12:32:29.576275: step: 972/530, loss: -1.1873245966853574e-05
2023-01-21 12:32:30.669385: step: 976/530, loss: 0.009339523501694202
2023-01-21 12:32:31.760863: step: 980/530, loss: 2.7465821403893642e-05
2023-01-21 12:32:32.878201: step: 984/530, loss: 0.04427976906299591
2023-01-21 12:32:33.962097: step: 988/530, loss: 0.00028553008451126516
2023-01-21 12:32:35.090324: step: 992/530, loss: 0.013398361392319202
2023-01-21 12:32:36.208376: step: 996/530, loss: 0.013470841571688652
2023-01-21 12:32:37.318285: step: 1000/530, loss: 0.0009891510708257556
2023-01-21 12:32:38.409384: step: 1004/530, loss: 0.020771121606230736
2023-01-21 12:32:39.536057: step: 1008/530, loss: 0.0033872604835778475
2023-01-21 12:32:40.627611: step: 1012/530, loss: 0.00011854172043967992
2023-01-21 12:32:41.721358: step: 1016/530, loss: 4.320144944358617e-05
2023-01-21 12:32:42.857856: step: 1020/530, loss: 0.002172183943912387
2023-01-21 12:32:43.980878: step: 1024/530, loss: 0.01824493333697319
2023-01-21 12:32:45.066562: step: 1028/530, loss: -1.5258789289873675e-06
2023-01-21 12:32:46.161144: step: 1032/530, loss: 0.0057586668990552425
2023-01-21 12:32:47.321249: step: 1036/530, loss: 0.00696220388635993
2023-01-21 12:32:48.425823: step: 1040/530, loss: -8.96453821042087e-06
2023-01-21 12:32:49.548176: step: 1044/530, loss: 0.0012565612560138106
2023-01-21 12:32:50.672169: step: 1048/530, loss: 0.005820846650749445
2023-01-21 12:32:51.758311: step: 1052/530, loss: 0.008389520458877087
2023-01-21 12:32:52.871000: step: 1056/530, loss: 0.0006235122564248741
2023-01-21 12:32:53.966663: step: 1060/530, loss: 0.01103820838034153
2023-01-21 12:32:55.078790: step: 1064/530, loss: 0.00092740060063079
2023-01-21 12:32:56.200134: step: 1068/530, loss: 0.0005703926435671747
2023-01-21 12:32:57.298878: step: 1072/530, loss: 0.04490146413445473
2023-01-21 12:32:58.450468: step: 1076/530, loss: 0.0005027771112509072
2023-01-21 12:32:59.597739: step: 1080/530, loss: 0.024184800684452057
2023-01-21 12:33:00.719583: step: 1084/530, loss: 0.005805111024528742
2023-01-21 12:33:01.809462: step: 1088/530, loss: 0.043514348566532135
2023-01-21 12:33:02.930559: step: 1092/530, loss: 0.0004415511793922633
2023-01-21 12:33:04.027389: step: 1096/530, loss: 0.001503944513387978
2023-01-21 12:33:05.123786: step: 1100/530, loss: 0.007948732003569603
2023-01-21 12:33:06.238272: step: 1104/530, loss: 0.00040602684020996094
2023-01-21 12:33:07.379041: step: 1108/530, loss: 0.007936859503388405
2023-01-21 12:33:08.464030: step: 1112/530, loss: 0.009998702444136143
2023-01-21 12:33:09.593072: step: 1116/530, loss: 0.0008195877308025956
2023-01-21 12:33:10.720727: step: 1120/530, loss: 0.026778889819979668
2023-01-21 12:33:11.832288: step: 1124/530, loss: 0.02886371687054634
2023-01-21 12:33:12.942178: step: 1128/530, loss: 0.0005548477056436241
2023-01-21 12:33:14.045904: step: 1132/530, loss: 0.0006591796991415322
2023-01-21 12:33:15.190794: step: 1136/530, loss: 0.014800643548369408
2023-01-21 12:33:16.345307: step: 1140/530, loss: 0.7176936268806458
2023-01-21 12:33:17.465698: step: 1144/530, loss: 0.0008934020879678428
2023-01-21 12:33:18.596199: step: 1148/530, loss: 7.200241088867188e-05
2023-01-21 12:33:19.695233: step: 1152/530, loss: 0.012579060159623623
2023-01-21 12:33:20.795104: step: 1156/530, loss: 5.722046125811175e-07
2023-01-21 12:33:21.900680: step: 1160/530, loss: 0.00027236941969022155
2023-01-21 12:33:22.985159: step: 1164/530, loss: 0.00017967224994208664
2023-01-21 12:33:24.095155: step: 1168/530, loss: 8.773804438533261e-06
2023-01-21 12:33:25.229030: step: 1172/530, loss: 0.015769243240356445
2023-01-21 12:33:26.329511: step: 1176/530, loss: 0.00031766892061568797
2023-01-21 12:33:27.426700: step: 1180/530, loss: 0.0007321357843466103
2023-01-21 12:33:28.534876: step: 1184/530, loss: 0.0004665374872274697
2023-01-21 12:33:29.612995: step: 1188/530, loss: 0.000419425981817767
2023-01-21 12:33:30.711720: step: 1192/530, loss: 0.00047931671724654734
2023-01-21 12:33:31.810755: step: 1196/530, loss: 0.0027671335265040398
2023-01-21 12:33:32.928361: step: 1200/530, loss: 0.012008501216769218
2023-01-21 12:33:34.000852: step: 1204/530, loss: 4.215240551275201e-05
2023-01-21 12:33:35.094524: step: 1208/530, loss: 0.0010000228649005294
2023-01-21 12:33:36.197477: step: 1212/530, loss: 0.0024730681907385588
2023-01-21 12:33:37.317540: step: 1216/530, loss: 9.880066500045359e-05
2023-01-21 12:33:38.429259: step: 1220/530, loss: 0.001472854521125555
2023-01-21 12:33:39.570775: step: 1224/530, loss: 0.005084419623017311
2023-01-21 12:33:40.655738: step: 1228/530, loss: 3.938675217796117e-05
2023-01-21 12:33:41.752694: step: 1232/530, loss: 4.4488908315543085e-05
2023-01-21 12:33:42.851025: step: 1236/530, loss: 0.0020829676650464535
2023-01-21 12:33:43.931616: step: 1240/530, loss: 0.00021967888460494578
2023-01-21 12:33:45.022336: step: 1244/530, loss: 0.0005834579933434725
2023-01-21 12:33:46.139222: step: 1248/530, loss: 1.850128137448337e-05
2023-01-21 12:33:47.284162: step: 1252/530, loss: 0.03547334671020508
2023-01-21 12:33:48.393966: step: 1256/530, loss: 0.02529440075159073
2023-01-21 12:33:49.498393: step: 1260/530, loss: 0.00463447580114007
2023-01-21 12:33:50.606471: step: 1264/530, loss: 0.10710448771715164
2023-01-21 12:33:51.683882: step: 1268/530, loss: 0.0029116631485521793
2023-01-21 12:33:52.813074: step: 1272/530, loss: 0.002628421876579523
2023-01-21 12:33:53.918503: step: 1276/530, loss: 0.006462669465690851
2023-01-21 12:33:55.011098: step: 1280/530, loss: 0.001979351043701172
2023-01-21 12:33:56.094984: step: 1284/530, loss: 0.0221710205078125
2023-01-21 12:33:57.202252: step: 1288/530, loss: 0.0002401351957814768
2023-01-21 12:33:58.299961: step: 1292/530, loss: 0.002731370972469449
2023-01-21 12:33:59.372247: step: 1296/530, loss: 0.004636764992028475
2023-01-21 12:34:00.466337: step: 1300/530, loss: 0.33591651916503906
2023-01-21 12:34:01.572078: step: 1304/530, loss: 0.004771137144416571
2023-01-21 12:34:02.668747: step: 1308/530, loss: 0.00010414123971713707
2023-01-21 12:34:03.772538: step: 1312/530, loss: 0.0019754411187022924
2023-01-21 12:34:04.872998: step: 1316/530, loss: 0.00037937163142487407
2023-01-21 12:34:05.955612: step: 1320/530, loss: 0.017027854919433594
2023-01-21 12:34:07.108529: step: 1324/530, loss: 0.0301939956843853
2023-01-21 12:34:08.201278: step: 1328/530, loss: 0.1273849457502365
2023-01-21 12:34:09.318181: step: 1332/530, loss: 0.005249977111816406
2023-01-21 12:34:10.434362: step: 1336/530, loss: 0.01485443115234375
2023-01-21 12:34:11.604358: step: 1340/530, loss: 0.04502906650304794
2023-01-21 12:34:12.713771: step: 1344/530, loss: 0.01974649354815483
2023-01-21 12:34:13.792209: step: 1348/530, loss: 0.0020643712487071753
2023-01-21 12:34:14.903931: step: 1352/530, loss: 0.0002511978382244706
2023-01-21 12:34:16.039691: step: 1356/530, loss: 0.03373584523797035
2023-01-21 12:34:17.130377: step: 1360/530, loss: 0.0005797863123007119
2023-01-21 12:34:18.224501: step: 1364/530, loss: 0.016827011480927467
2023-01-21 12:34:19.310408: step: 1368/530, loss: -6.48498553346144e-06
2023-01-21 12:34:20.438773: step: 1372/530, loss: 8.96453821042087e-06
2023-01-21 12:34:21.536372: step: 1376/530, loss: 6.732940528308973e-05
2023-01-21 12:34:22.644961: step: 1380/530, loss: 0.0025796890258789062
2023-01-21 12:34:23.741750: step: 1384/530, loss: 0.0007453918224200606
2023-01-21 12:34:24.859239: step: 1388/530, loss: 0.01558532752096653
2023-01-21 12:34:25.989269: step: 1392/530, loss: 0.014037705026566982
2023-01-21 12:34:27.102791: step: 1396/530, loss: 0.0004398345772642642
2023-01-21 12:34:28.188629: step: 1400/530, loss: 0.0005353927845135331
2023-01-21 12:34:29.289360: step: 1404/530, loss: 0.003597831819206476
2023-01-21 12:34:30.380527: step: 1408/530, loss: 0.026904871687293053
2023-01-21 12:34:31.464929: step: 1412/530, loss: 4.425048973644152e-05
2023-01-21 12:34:32.577649: step: 1416/530, loss: 0.002578639890998602
2023-01-21 12:34:33.713726: step: 1420/530, loss: 0.04206442832946777
2023-01-21 12:34:34.827990: step: 1424/530, loss: 0.0002612113894429058
2023-01-21 12:34:35.905888: step: 1428/530, loss: 0.0006733656045980752
2023-01-21 12:34:37.022059: step: 1432/530, loss: 0.0008470535976812243
2023-01-21 12:34:38.127773: step: 1436/530, loss: 0.023834897205233574
2023-01-21 12:34:39.195465: step: 1440/530, loss: -6.198883056640625e-06
2023-01-21 12:34:40.281934: step: 1444/530, loss: 0.0002265930233988911
2023-01-21 12:34:41.341084: step: 1448/530, loss: 0.005977678578346968
2023-01-21 12:34:42.445723: step: 1452/530, loss: 0.0013768196804448962
2023-01-21 12:34:43.533642: step: 1456/530, loss: 0.596026599407196
2023-01-21 12:34:44.611698: step: 1460/530, loss: 0.007172965910285711
2023-01-21 12:34:45.743151: step: 1464/530, loss: 0.005070686340332031
2023-01-21 12:34:46.843432: step: 1468/530, loss: 0.04132404178380966
2023-01-21 12:34:47.944574: step: 1472/530, loss: 0.0007271766662597656
2023-01-21 12:34:49.057109: step: 1476/530, loss: 0.003949403762817383
2023-01-21 12:34:50.156905: step: 1480/530, loss: 5.726814561057836e-05
2023-01-21 12:34:51.243683: step: 1484/530, loss: 1.430511474609375e-06
2023-01-21 12:34:52.329401: step: 1488/530, loss: 0.008794165216386318
2023-01-21 12:34:53.453425: step: 1492/530, loss: 0.02519082836806774
2023-01-21 12:34:54.529098: step: 1496/530, loss: 1.869201696536038e-05
2023-01-21 12:34:55.631740: step: 1500/530, loss: 0.018928242847323418
2023-01-21 12:34:56.749528: step: 1504/530, loss: 0.0009658813942223787
2023-01-21 12:34:57.834104: step: 1508/530, loss: 0.03637199476361275
2023-01-21 12:34:58.933280: step: 1512/530, loss: 0.001326751778833568
2023-01-21 12:35:00.037794: step: 1516/530, loss: -4.9591067181609105e-06
2023-01-21 12:35:01.110652: step: 1520/530, loss: 0.000580838299356401
2023-01-21 12:35:02.201859: step: 1524/530, loss: 0.004694509785622358
2023-01-21 12:35:03.323326: step: 1528/530, loss: 0.0007190704345703125
2023-01-21 12:35:04.465244: step: 1532/530, loss: 0.041944313794374466
2023-01-21 12:35:05.613577: step: 1536/530, loss: 0.0783195048570633
2023-01-21 12:35:06.718294: step: 1540/530, loss: 0.0011120795970782638
2023-01-21 12:35:07.840429: step: 1544/530, loss: 0.03445339575409889
2023-01-21 12:35:08.936942: step: 1548/530, loss: 2.3937223886605352e-05
2023-01-21 12:35:10.050712: step: 1552/530, loss: 0.00269393902271986
2023-01-21 12:35:11.130099: step: 1556/530, loss: 3.0994415283203125e-06
2023-01-21 12:35:12.252210: step: 1560/530, loss: 0.0025085448287427425
2023-01-21 12:35:13.348153: step: 1564/530, loss: 0.0025135038886219263
2023-01-21 12:35:14.452627: step: 1568/530, loss: 0.03264026716351509
2023-01-21 12:35:15.531389: step: 1572/530, loss: 0.022303033620119095
2023-01-21 12:35:16.650585: step: 1576/530, loss: 0.0024772644974291325
2023-01-21 12:35:17.752105: step: 1580/530, loss: 0.0011322021018713713
2023-01-21 12:35:18.875886: step: 1584/530, loss: 8.306503877975047e-05
2023-01-21 12:35:19.994476: step: 1588/530, loss: 0.04471893608570099
2023-01-21 12:35:21.095337: step: 1592/530, loss: 1.4114380974206142e-05
2023-01-21 12:35:22.193674: step: 1596/530, loss: 0.006565404124557972
2023-01-21 12:35:23.298398: step: 1600/530, loss: 2.822876012942288e-05
2023-01-21 12:35:24.407682: step: 1604/530, loss: 0.0061675552278757095
2023-01-21 12:35:25.533817: step: 1608/530, loss: 0.0013930320274084806
2023-01-21 12:35:26.636242: step: 1612/530, loss: 0.0004811763938050717
2023-01-21 12:35:27.724276: step: 1616/530, loss: 0.002718257950618863
2023-01-21 12:35:28.868218: step: 1620/530, loss: 0.0006052970420569181
2023-01-21 12:35:29.964727: step: 1624/530, loss: 0.017832566052675247
2023-01-21 12:35:31.051524: step: 1628/530, loss: 0.00026798248291015625
2023-01-21 12:35:32.136012: step: 1632/530, loss: 5.674362455465598e-06
2023-01-21 12:35:33.214774: step: 1636/530, loss: 0.0008571147918701172
2023-01-21 12:35:34.302940: step: 1640/530, loss: 6.3419347497983836e-06
2023-01-21 12:35:35.381380: step: 1644/530, loss: 3.180504063493572e-05
2023-01-21 12:35:36.484971: step: 1648/530, loss: 5.826950291520916e-05
2023-01-21 12:35:37.575086: step: 1652/530, loss: 0.005058264825493097
2023-01-21 12:35:38.694051: step: 1656/530, loss: 0.012596678920090199
2023-01-21 12:35:39.776399: step: 1660/530, loss: 0.0012564659118652344
2023-01-21 12:35:40.888168: step: 1664/530, loss: 0.07707862555980682
2023-01-21 12:35:41.991209: step: 1668/530, loss: 0.04216022416949272
2023-01-21 12:35:43.076422: step: 1672/530, loss: 0.002632999327033758
2023-01-21 12:35:44.177381: step: 1676/530, loss: 0.02209930494427681
2023-01-21 12:35:45.340894: step: 1680/530, loss: 0.03626756742596626
2023-01-21 12:35:46.464170: step: 1684/530, loss: 0.012114906683564186
2023-01-21 12:35:47.557317: step: 1688/530, loss: 0.01845397986471653
2023-01-21 12:35:48.672683: step: 1692/530, loss: 0.005199146457016468
2023-01-21 12:35:49.781032: step: 1696/530, loss: 0.0005088805919513106
2023-01-21 12:35:50.908979: step: 1700/530, loss: 0.006882953457534313
2023-01-21 12:35:52.003101: step: 1704/530, loss: 0.029113102704286575
2023-01-21 12:35:53.155987: step: 1708/530, loss: 0.038135334849357605
2023-01-21 12:35:54.249216: step: 1712/530, loss: 2.784729076665826e-05
2023-01-21 12:35:55.390129: step: 1716/530, loss: 0.04022855684161186
2023-01-21 12:35:56.487001: step: 1720/530, loss: 0.016542483121156693
2023-01-21 12:35:57.594785: step: 1724/530, loss: 0.09811268746852875
2023-01-21 12:35:58.714766: step: 1728/530, loss: 0.003682136768475175
2023-01-21 12:35:59.837568: step: 1732/530, loss: 8.60214204294607e-05
2023-01-21 12:36:00.944449: step: 1736/530, loss: 0.009171867743134499
2023-01-21 12:36:02.054917: step: 1740/530, loss: 0.0441431999206543
2023-01-21 12:36:03.174117: step: 1744/530, loss: 0.007792663760483265
2023-01-21 12:36:04.304588: step: 1748/530, loss: 0.04929351806640625
2023-01-21 12:36:05.415057: step: 1752/530, loss: 0.0033597948495298624
2023-01-21 12:36:06.527569: step: 1756/530, loss: 0.022371673956513405
2023-01-21 12:36:07.684216: step: 1760/530, loss: 0.03011927753686905
2023-01-21 12:36:08.809134: step: 1764/530, loss: 0.005393600556999445
2023-01-21 12:36:09.939785: step: 1768/530, loss: 0.006622409913688898
2023-01-21 12:36:11.015883: step: 1772/530, loss: 3.24249276673072e-06
2023-01-21 12:36:12.116614: step: 1776/530, loss: 0.0022425891365855932
2023-01-21 12:36:13.226126: step: 1780/530, loss: 0.002239704132080078
2023-01-21 12:36:14.342699: step: 1784/530, loss: 0.008510970510542393
2023-01-21 12:36:15.446297: step: 1788/530, loss: -3.814697265625e-06
2023-01-21 12:36:16.540467: step: 1792/530, loss: 9.498596773482859e-05
2023-01-21 12:36:17.642607: step: 1796/530, loss: 0.0006328582530841231
2023-01-21 12:36:18.770588: step: 1800/530, loss: 0.017905235290527344
2023-01-21 12:36:19.906032: step: 1804/530, loss: 0.24385519325733185
2023-01-21 12:36:21.001587: step: 1808/530, loss: 0.0002732276916503906
2023-01-21 12:36:22.096557: step: 1812/530, loss: 2.269744800287299e-05
2023-01-21 12:36:23.188179: step: 1816/530, loss: 0.007462859153747559
2023-01-21 12:36:24.283498: step: 1820/530, loss: 0.011810302734375
2023-01-21 12:36:25.416527: step: 1824/530, loss: 0.00024137497530318797
2023-01-21 12:36:26.517902: step: 1828/530, loss: 0.035941507667303085
2023-01-21 12:36:27.632577: step: 1832/530, loss: 0.00824284553527832
2023-01-21 12:36:28.720325: step: 1836/530, loss: 0.0012829303741455078
2023-01-21 12:36:29.800481: step: 1840/530, loss: 4.9781796406023204e-05
2023-01-21 12:36:30.916598: step: 1844/530, loss: 0.000579833984375
2023-01-21 12:36:32.011035: step: 1848/530, loss: 1.049041748046875e-05
2023-01-21 12:36:33.090906: step: 1852/530, loss: 0.018314171582460403
2023-01-21 12:36:34.228721: step: 1856/530, loss: 0.00010013580322265625
2023-01-21 12:36:35.317175: step: 1860/530, loss: 0.0001957416534423828
2023-01-21 12:36:36.455503: step: 1864/530, loss: 0.012576103210449219
2023-01-21 12:36:37.532629: step: 1868/530, loss: 0.007226563058793545
2023-01-21 12:36:38.632543: step: 1872/530, loss: 0.0015048980712890625
2023-01-21 12:36:39.735526: step: 1876/530, loss: 0.0006517410511150956
2023-01-21 12:36:40.847844: step: 1880/530, loss: 0.0016218186356127262
2023-01-21 12:36:41.927987: step: 1884/530, loss: 0.0010039329063147306
2023-01-21 12:36:43.005514: step: 1888/530, loss: 0.0004635810910258442
2023-01-21 12:36:44.098685: step: 1892/530, loss: 0.005362033843994141
2023-01-21 12:36:45.192521: step: 1896/530, loss: 0.00110712053719908
2023-01-21 12:36:46.298296: step: 1900/530, loss: 0.00048441888066008687
2023-01-21 12:36:47.393627: step: 1904/530, loss: 0.006543636322021484
2023-01-21 12:36:48.475043: step: 1908/530, loss: -1.8119812921213452e-06
2023-01-21 12:36:49.565456: step: 1912/530, loss: 0.007022667210549116
2023-01-21 12:36:50.725642: step: 1916/530, loss: -3.42369094141759e-05
2023-01-21 12:36:51.842879: step: 1920/530, loss: 0.03026561811566353
2023-01-21 12:36:52.951869: step: 1924/530, loss: 0.010492324829101562
2023-01-21 12:36:54.065266: step: 1928/530, loss: 6.008148193359375e-05
2023-01-21 12:36:55.148657: step: 1932/530, loss: 1.4019012269272935e-05
2023-01-21 12:36:56.273853: step: 1936/530, loss: 0.0004623412969522178
2023-01-21 12:36:57.376056: step: 1940/530, loss: 0.0041217803955078125
2023-01-21 12:36:58.458756: step: 1944/530, loss: 2.7179719381820178e-06
2023-01-21 12:36:59.536066: step: 1948/530, loss: 0.000177288064151071
2023-01-21 12:37:00.639371: step: 1952/530, loss: 0.013975572772324085
2023-01-21 12:37:01.758222: step: 1956/530, loss: 0.0005696773296222091
2023-01-21 12:37:02.862707: step: 1960/530, loss: 2.9373170036706142e-05
2023-01-21 12:37:03.967312: step: 1964/530, loss: 0.010573388077318668
2023-01-21 12:37:05.129127: step: 1968/530, loss: 0.005488968454301357
2023-01-21 12:37:06.242651: step: 1972/530, loss: 0.03534388542175293
2023-01-21 12:37:07.341265: step: 1976/530, loss: 0.0025485993828624487
2023-01-21 12:37:08.461516: step: 1980/530, loss: 0.0005553722730837762
2023-01-21 12:37:09.549461: step: 1984/530, loss: 0.0002442359982524067
2023-01-21 12:37:10.646487: step: 1988/530, loss: 0.0011517524253576994
2023-01-21 12:37:11.751259: step: 1992/530, loss: 5.064010838395916e-05
2023-01-21 12:37:12.851821: step: 1996/530, loss: 0.003597450442612171
2023-01-21 12:37:13.947691: step: 2000/530, loss: 0.009614372625946999
2023-01-21 12:37:15.039202: step: 2004/530, loss: 0.003248119493946433
2023-01-21 12:37:16.098513: step: 2008/530, loss: 0.0001390457182424143
2023-01-21 12:37:17.229380: step: 2012/530, loss: 3.0469893317786045e-05
2023-01-21 12:37:18.317121: step: 2016/530, loss: 0.00018959045701194555
2023-01-21 12:37:19.437787: step: 2020/530, loss: 0.014476108364760876
2023-01-21 12:37:20.525565: step: 2024/530, loss: 0.00046114923316054046
2023-01-21 12:37:21.625571: step: 2028/530, loss: 0.030524635687470436
2023-01-21 12:37:22.734556: step: 2032/530, loss: 0.011456107720732689
2023-01-21 12:37:23.868696: step: 2036/530, loss: 0.020128441974520683
2023-01-21 12:37:24.980953: step: 2040/530, loss: 0.07104626297950745
2023-01-21 12:37:26.074310: step: 2044/530, loss: 0.0013711928622797132
2023-01-21 12:37:27.196265: step: 2048/530, loss: 0.028418540954589844
2023-01-21 12:37:28.297305: step: 2052/530, loss: 0.0042282105423510075
2023-01-21 12:37:29.401815: step: 2056/530, loss: 6.0558319091796875e-05
2023-01-21 12:37:30.472153: step: 2060/530, loss: 0.0007425308576785028
2023-01-21 12:37:31.572679: step: 2064/530, loss: 0.017597580328583717
2023-01-21 12:37:32.701289: step: 2068/530, loss: 0.02717743068933487
2023-01-21 12:37:33.819622: step: 2072/530, loss: 0.0004070282157044858
2023-01-21 12:37:34.922805: step: 2076/530, loss: 0.023640252649784088
2023-01-21 12:37:36.024916: step: 2080/530, loss: 0.005477047525346279
2023-01-21 12:37:37.145229: step: 2084/530, loss: 0.009013175964355469
2023-01-21 12:37:38.284193: step: 2088/530, loss: 0.040326882153749466
2023-01-21 12:37:39.387566: step: 2092/530, loss: 0.0025306702591478825
2023-01-21 12:37:40.493329: step: 2096/530, loss: 1.7833710444392636e-05
2023-01-21 12:37:41.614757: step: 2100/530, loss: 0.0012613296275958419
2023-01-21 12:37:42.731091: step: 2104/530, loss: 0.031528472900390625
2023-01-21 12:37:43.848135: step: 2108/530, loss: 6.103515261202119e-05
2023-01-21 12:37:44.942370: step: 2112/530, loss: 0.005725097376853228
2023-01-21 12:37:46.067871: step: 2116/530, loss: 0.004639053251594305
2023-01-21 12:37:47.149452: step: 2120/530, loss: 5.931854320806451e-05
==================================================
Loss: 0.021
--------------------
Dev: {'event': {'p': 0.5826612903225806, 'r': 0.7696404793608522, 'f1': 0.6632243258749283}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Test: {'event': {'p': 0.6385321100917432, 'r': 0.8111888111888111, 'f1': 0.7145790554414785}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Chinese: {'event': {'p': 0.6571428571428571, 'r': 0.8518518518518519, 'f1': 0.7419354838709677}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Korean: {'event': {'p': 0.6551724137931034, 'r': 0.6031746031746031, 'f1': 0.628099173553719}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Russian: {'event': {'p': 0.5, 'r': 0.5555555555555556, 'f1': 0.5263157894736842}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Korean: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 12:38:26.659686: step: 4/530, loss: 0.0001181602492579259
2023-01-21 12:38:27.762927: step: 8/530, loss: 4.315376281738281e-05
2023-01-21 12:38:28.889708: step: 12/530, loss: 0.007059860043227673
2023-01-21 12:38:29.982219: step: 16/530, loss: 0.00021152498084120452
2023-01-21 12:38:31.116272: step: 20/530, loss: 0.005780410952866077
2023-01-21 12:38:32.217246: step: 24/530, loss: 0.0024755478370934725
2023-01-21 12:38:33.326425: step: 28/530, loss: 0.0013053894508630037
2023-01-21 12:38:34.410825: step: 32/530, loss: 0.0005859375814907253
2023-01-21 12:38:35.495451: step: 36/530, loss: 0.000217437744140625
2023-01-21 12:38:36.629643: step: 40/530, loss: 0.0004322052118368447
2023-01-21 12:38:37.706995: step: 44/530, loss: 0.0024472237564623356
2023-01-21 12:38:38.816533: step: 48/530, loss: 0.0023786069359630346
2023-01-21 12:38:39.983934: step: 52/530, loss: 0.01628742180764675
2023-01-21 12:38:41.096355: step: 56/530, loss: 0.0023448944557458162
2023-01-21 12:38:42.202322: step: 60/530, loss: 0.00939102191478014
2023-01-21 12:38:43.351530: step: 64/530, loss: 0.022030210122466087
2023-01-21 12:38:44.436563: step: 68/530, loss: 0.00042819976806640625
2023-01-21 12:38:45.551480: step: 72/530, loss: 0.004167079925537109
2023-01-21 12:38:46.641077: step: 76/530, loss: 3.5095217754133046e-05
2023-01-21 12:38:47.758111: step: 80/530, loss: 0.023180866613984108
2023-01-21 12:38:48.840483: step: 84/530, loss: 0.001747608301229775
2023-01-21 12:38:49.938606: step: 88/530, loss: 0.0008821488008834422
2023-01-21 12:38:51.042678: step: 92/530, loss: 0.0002480506955180317
2023-01-21 12:38:52.151164: step: 96/530, loss: 0.006002617534250021
2023-01-21 12:38:53.243942: step: 100/530, loss: 1.3828278497385327e-05
2023-01-21 12:38:54.348562: step: 104/530, loss: 0.0005464553833007812
2023-01-21 12:38:55.469940: step: 108/530, loss: 3.051757857974735e-06
2023-01-21 12:38:56.583605: step: 112/530, loss: 0.03663787990808487
2023-01-21 12:38:57.693225: step: 116/530, loss: 0.01664094813168049
2023-01-21 12:38:58.793369: step: 120/530, loss: 0.008404731750488281
2023-01-21 12:38:59.872579: step: 124/530, loss: 0.00017223358736373484
2023-01-21 12:39:01.003532: step: 128/530, loss: 0.01043481845408678
2023-01-21 12:39:02.104981: step: 132/530, loss: 1.3542176020564511e-05
2023-01-21 12:39:03.223754: step: 136/530, loss: 0.004161739256232977
2023-01-21 12:39:04.334528: step: 140/530, loss: 0.0005633354303427041
2023-01-21 12:39:05.445449: step: 144/530, loss: 3.337860107421875e-06
2023-01-21 12:39:06.563139: step: 148/530, loss: 0.00010557174391578883
2023-01-21 12:39:07.669490: step: 152/530, loss: 0.0018682479858398438
2023-01-21 12:39:08.771175: step: 156/530, loss: 0.03556881099939346
2023-01-21 12:39:09.871430: step: 160/530, loss: 0.00486183213070035
2023-01-21 12:39:11.005187: step: 164/530, loss: 0.0003407478507142514
2023-01-21 12:39:12.111898: step: 168/530, loss: 0.0029088975861668587
2023-01-21 12:39:13.214499: step: 172/530, loss: 0.00019893646822310984
2023-01-21 12:39:14.317342: step: 176/530, loss: 0.03455962985754013
2023-01-21 12:39:15.404589: step: 180/530, loss: 0.0019924165681004524
2023-01-21 12:39:16.499794: step: 184/530, loss: 0.05401868745684624
2023-01-21 12:39:17.602494: step: 188/530, loss: 0.0007426262018270791
2023-01-21 12:39:18.691037: step: 192/530, loss: 0.043405912816524506
2023-01-21 12:39:19.826277: step: 196/530, loss: 0.00483021792024374
2023-01-21 12:39:20.924626: step: 200/530, loss: 0.005067634396255016
2023-01-21 12:39:22.032459: step: 204/530, loss: 0.049700167030096054
2023-01-21 12:39:23.177407: step: 208/530, loss: 0.0004032135184388608
2023-01-21 12:39:24.277790: step: 212/530, loss: 0.0001678466796875
2023-01-21 12:39:25.377449: step: 216/530, loss: 0.00030078887357376516
2023-01-21 12:39:26.477722: step: 220/530, loss: 9.450912330066785e-05
2023-01-21 12:39:27.587334: step: 224/530, loss: 0.0022581100929528475
2023-01-21 12:39:28.720572: step: 228/530, loss: 0.0008321762434206903
2023-01-21 12:39:29.816388: step: 232/530, loss: 0.0009102821350097656
2023-01-21 12:39:30.910452: step: 236/530, loss: 0.0002178192080464214
2023-01-21 12:39:32.006661: step: 240/530, loss: 0.3204216957092285
2023-01-21 12:39:33.115016: step: 244/530, loss: 0.01825866848230362
2023-01-21 12:39:34.185052: step: 248/530, loss: 0.0003409385681152344
2023-01-21 12:39:35.309400: step: 252/530, loss: 0.07293710857629776
2023-01-21 12:39:36.409417: step: 256/530, loss: 0.0006601333734579384
2023-01-21 12:39:37.556092: step: 260/530, loss: 4.081726001459174e-05
2023-01-21 12:39:38.659283: step: 264/530, loss: 0.009628105908632278
2023-01-21 12:39:39.765108: step: 268/530, loss: 0.003125953720882535
2023-01-21 12:39:40.881526: step: 272/530, loss: 0.18219681084156036
2023-01-21 12:39:41.961784: step: 276/530, loss: 0.0006276131025515497
2023-01-21 12:39:43.062893: step: 280/530, loss: 0.0007067203987389803
2023-01-21 12:39:44.171406: step: 284/530, loss: 1.945495569088962e-05
2023-01-21 12:39:45.252074: step: 288/530, loss: 0.004003429319709539
2023-01-21 12:39:46.339756: step: 292/530, loss: 0.0003593921719584614
2023-01-21 12:39:47.418805: step: 296/530, loss: 4.358291334938258e-05
2023-01-21 12:39:48.504059: step: 300/530, loss: 0.01516122929751873
2023-01-21 12:39:49.604754: step: 304/530, loss: 0.009535026736557484
2023-01-21 12:39:50.690015: step: 308/530, loss: 0.00018405914306640625
2023-01-21 12:39:51.786631: step: 312/530, loss: 0.018927576020359993
2023-01-21 12:39:52.901097: step: 316/530, loss: 0.00014610291691496968
2023-01-21 12:39:54.013556: step: 320/530, loss: 0.0006084442138671875
2023-01-21 12:39:55.122588: step: 324/530, loss: 0.005340385250747204
2023-01-21 12:39:56.204525: step: 328/530, loss: 0.01884470134973526
2023-01-21 12:39:57.292089: step: 332/530, loss: 6.904602196300402e-05
2023-01-21 12:39:58.394433: step: 336/530, loss: 0.00077991490252316
2023-01-21 12:39:59.511041: step: 340/530, loss: 3.52859501617786e-06
2023-01-21 12:40:00.619748: step: 344/530, loss: 0.00022039414034225047
2023-01-21 12:40:01.702392: step: 348/530, loss: 0.00018386841111350805
2023-01-21 12:40:02.834488: step: 352/530, loss: 0.00035858154296875
2023-01-21 12:40:03.943309: step: 356/530, loss: 0.00054254534188658
2023-01-21 12:40:05.034040: step: 360/530, loss: 0.00017185212345793843
2023-01-21 12:40:06.147820: step: 364/530, loss: 0.0002635955752339214
2023-01-21 12:40:07.284097: step: 368/530, loss: 0.0005266189691610634
2023-01-21 12:40:08.374763: step: 372/530, loss: 0.045053862035274506
2023-01-21 12:40:09.500221: step: 376/530, loss: 0.003920555114746094
2023-01-21 12:40:10.606696: step: 380/530, loss: 0.04845566675066948
2023-01-21 12:40:11.705979: step: 384/530, loss: 6.499290611827746e-05
2023-01-21 12:40:12.796093: step: 388/530, loss: -3.0517576306010596e-06
2023-01-21 12:40:13.911598: step: 392/530, loss: 0.008835315704345703
2023-01-21 12:40:15.010655: step: 396/530, loss: 0.043308451771736145
2023-01-21 12:40:16.109132: step: 400/530, loss: 0.002752399304881692
2023-01-21 12:40:17.229167: step: 404/530, loss: 0.00021276474581100047
2023-01-21 12:40:18.346471: step: 408/530, loss: 0.0014449120499193668
2023-01-21 12:40:19.418510: step: 412/530, loss: 0.00418777484446764
2023-01-21 12:40:20.517568: step: 416/530, loss: 1.6021729607018642e-05
2023-01-21 12:40:21.618946: step: 420/530, loss: 0.002090645022690296
2023-01-21 12:40:22.723633: step: 424/530, loss: 0.014922904781997204
2023-01-21 12:40:23.806264: step: 428/530, loss: 0.006016826257109642
2023-01-21 12:40:24.928280: step: 432/530, loss: 0.0005315780872479081
2023-01-21 12:40:26.018274: step: 436/530, loss: 0.0015379905235022306
2023-01-21 12:40:27.130499: step: 440/530, loss: 0.01862926408648491
2023-01-21 12:40:28.201294: step: 444/530, loss: 0.0006584167713299394
2023-01-21 12:40:29.290726: step: 448/530, loss: 0.00014543533325195312
2023-01-21 12:40:30.389191: step: 452/530, loss: 0.0004741668817587197
2023-01-21 12:40:31.473199: step: 456/530, loss: 0.0010362624889239669
2023-01-21 12:40:32.540918: step: 460/530, loss: 0.0006955146673135459
2023-01-21 12:40:33.675309: step: 464/530, loss: 0.014077950268983841
2023-01-21 12:40:34.753668: step: 468/530, loss: 3.337860107421875e-05
2023-01-21 12:40:35.857601: step: 472/530, loss: 0.00022811889357399195
2023-01-21 12:40:36.942137: step: 476/530, loss: 0.0010173798073083162
2023-01-21 12:40:38.022412: step: 480/530, loss: -1.4781952586417901e-06
2023-01-21 12:40:39.140214: step: 484/530, loss: 0.017048073932528496
2023-01-21 12:40:40.251330: step: 488/530, loss: 0.020419597625732422
2023-01-21 12:40:41.365655: step: 492/530, loss: 0.004304313566535711
2023-01-21 12:40:42.482079: step: 496/530, loss: 0.0002826690615620464
2023-01-21 12:40:43.585079: step: 500/530, loss: 0.00017146169557236135
2023-01-21 12:40:44.704183: step: 504/530, loss: 0.00031719208345748484
2023-01-21 12:40:45.812558: step: 508/530, loss: 8.840560622047633e-05
2023-01-21 12:40:46.913687: step: 512/530, loss: 8.0108642578125e-05
2023-01-21 12:40:48.029951: step: 516/530, loss: 0.008255290798842907
2023-01-21 12:40:49.113125: step: 520/530, loss: 0.005081653594970703
2023-01-21 12:40:50.266334: step: 524/530, loss: 0.0005936622619628906
2023-01-21 12:40:51.357283: step: 528/530, loss: 0.004739189054816961
2023-01-21 12:40:52.448675: step: 532/530, loss: 0.00023932458134368062
2023-01-21 12:40:53.586451: step: 536/530, loss: -2.7179717108083423e-06
2023-01-21 12:40:54.701525: step: 540/530, loss: 0.0025644302368164062
2023-01-21 12:40:55.806163: step: 544/530, loss: 0.002995395800098777
2023-01-21 12:40:56.929450: step: 548/530, loss: 4.673004150390625e-05
2023-01-21 12:40:58.039245: step: 552/530, loss: 0.004652452189475298
2023-01-21 12:40:59.130015: step: 556/530, loss: 0.007967948913574219
2023-01-21 12:41:00.227346: step: 560/530, loss: 2.2411346435546875e-05
2023-01-21 12:41:01.334480: step: 564/530, loss: 0.0012355804210528731
2023-01-21 12:41:02.442833: step: 568/530, loss: 0.020633887499570847
2023-01-21 12:41:03.575137: step: 572/530, loss: 6.961823601159267e-06
2023-01-21 12:41:04.688042: step: 576/530, loss: 0.0017211914528161287
2023-01-21 12:41:05.778181: step: 580/530, loss: 0.06138734892010689
2023-01-21 12:41:06.877554: step: 584/530, loss: 0.0018898011185228825
2023-01-21 12:41:07.971463: step: 588/530, loss: 0.0027740478981286287
2023-01-21 12:41:09.068583: step: 592/530, loss: 0.004668331239372492
2023-01-21 12:41:10.163073: step: 596/530, loss: 7.581711543025449e-06
2023-01-21 12:41:11.245687: step: 600/530, loss: 0.0035331726539880037
2023-01-21 12:41:12.359096: step: 604/530, loss: 0.00034437180147506297
2023-01-21 12:41:13.441914: step: 608/530, loss: 0.0010023117065429688
2023-01-21 12:41:14.538308: step: 612/530, loss: 0.055156707763671875
2023-01-21 12:41:15.642736: step: 616/530, loss: 0.037053827196359634
2023-01-21 12:41:16.740300: step: 620/530, loss: 0.4583573341369629
2023-01-21 12:41:17.865080: step: 624/530, loss: 0.0027387558948248625
2023-01-21 12:41:18.974059: step: 628/530, loss: 0.0004874229780398309
2023-01-21 12:41:20.049825: step: 632/530, loss: 0.0010898590553551912
2023-01-21 12:41:21.157418: step: 636/530, loss: 0.0673213005065918
2023-01-21 12:41:22.267250: step: 640/530, loss: 0.002672863192856312
2023-01-21 12:41:23.356026: step: 644/530, loss: 0.0008506775484420359
2023-01-21 12:41:24.476583: step: 648/530, loss: 0.011867523193359375
2023-01-21 12:41:25.572013: step: 652/530, loss: 0.0004531860467977822
2023-01-21 12:41:26.687423: step: 656/530, loss: 0.004370689857751131
2023-01-21 12:41:27.775327: step: 660/530, loss: 0.024695873260498047
2023-01-21 12:41:28.894954: step: 664/530, loss: 0.009311104193329811
2023-01-21 12:41:29.989337: step: 668/530, loss: 0.0002847671858035028
2023-01-21 12:41:31.084953: step: 672/530, loss: 0.00011577605619095266
2023-01-21 12:41:32.256870: step: 676/530, loss: 0.3177453875541687
2023-01-21 12:41:33.357545: step: 680/530, loss: 0.00013065338134765625
2023-01-21 12:41:34.459112: step: 684/530, loss: 0.0005950927734375
2023-01-21 12:41:35.569211: step: 688/530, loss: 0.03645019605755806
2023-01-21 12:41:36.685732: step: 692/530, loss: 0.00023641585721634328
2023-01-21 12:41:37.797831: step: 696/530, loss: 0.49969181418418884
2023-01-21 12:41:38.904078: step: 700/530, loss: 0.0001312255917582661
2023-01-21 12:41:40.057922: step: 704/530, loss: 0.02437572553753853
2023-01-21 12:41:41.183607: step: 708/530, loss: 4.9591064453125e-05
2023-01-21 12:41:42.286395: step: 712/530, loss: 0.005005550570785999
2023-01-21 12:41:43.413242: step: 716/530, loss: 0.020033836364746094
2023-01-21 12:41:44.522059: step: 720/530, loss: 0.00111817114520818
2023-01-21 12:41:45.629109: step: 724/530, loss: 5.550384594243951e-05
2023-01-21 12:41:46.745196: step: 728/530, loss: 0.024981975555419922
2023-01-21 12:41:47.813024: step: 732/530, loss: 8.893013000488281e-05
2023-01-21 12:41:48.916353: step: 736/530, loss: 0.00029754638671875
2023-01-21 12:41:50.030666: step: 740/530, loss: 0.0016672135097905993
2023-01-21 12:41:51.103020: step: 744/530, loss: 0.031229306012392044
2023-01-21 12:41:52.198354: step: 748/530, loss: 0.009283638559281826
2023-01-21 12:41:53.314382: step: 752/530, loss: 0.03994441032409668
2023-01-21 12:41:54.458989: step: 756/530, loss: 0.00011520386033225805
2023-01-21 12:41:55.601593: step: 760/530, loss: 0.0028385163750499487
2023-01-21 12:41:56.697565: step: 764/530, loss: 0.002548408694565296
2023-01-21 12:41:57.826052: step: 768/530, loss: 0.005142879206687212
2023-01-21 12:41:58.951105: step: 772/530, loss: 0.03744678199291229
2023-01-21 12:42:00.028452: step: 776/530, loss: 0.0002884865098167211
2023-01-21 12:42:01.099564: step: 780/530, loss: 3.738403393072076e-05
2023-01-21 12:42:02.226581: step: 784/530, loss: 6.961822509765625e-05
2023-01-21 12:42:03.351346: step: 788/530, loss: 0.01434869784861803
2023-01-21 12:42:04.470036: step: 792/530, loss: 0.0008829116704873741
2023-01-21 12:42:05.553204: step: 796/530, loss: 6.48498553346144e-06
2023-01-21 12:42:06.702491: step: 800/530, loss: 0.025713825598359108
2023-01-21 12:42:07.810049: step: 804/530, loss: 1.3399124327406753e-05
2023-01-21 12:42:08.895734: step: 808/530, loss: 7.486344111384824e-05
2023-01-21 12:42:09.992412: step: 812/530, loss: 0.018118999898433685
2023-01-21 12:42:11.118704: step: 816/530, loss: 0.03981170803308487
2023-01-21 12:42:12.218639: step: 820/530, loss: 0.07109756767749786
2023-01-21 12:42:13.350053: step: 824/530, loss: 0.00024690627469681203
2023-01-21 12:42:14.443512: step: 828/530, loss: 0.0032117129303514957
2023-01-21 12:42:15.532044: step: 832/530, loss: 2.079009937006049e-05
2023-01-21 12:42:16.622173: step: 836/530, loss: 2.8896331059513614e-05
2023-01-21 12:42:17.755706: step: 840/530, loss: 0.0009204864618368447
2023-01-21 12:42:18.864279: step: 844/530, loss: 0.001543235732242465
2023-01-21 12:42:19.931928: step: 848/530, loss: 5.9604644775390625e-06
2023-01-21 12:42:21.041435: step: 852/530, loss: 0.00014705659123137593
2023-01-21 12:42:22.154914: step: 856/530, loss: 0.10301666706800461
2023-01-21 12:42:23.275163: step: 860/530, loss: 0.0002754211309365928
2023-01-21 12:42:24.354493: step: 864/530, loss: 0.012121295556426048
2023-01-21 12:42:25.433068: step: 868/530, loss: 1.602172778802924e-05
2023-01-21 12:42:26.535568: step: 872/530, loss: 0.0038080215454101562
2023-01-21 12:42:27.618299: step: 876/530, loss: 3.376007225597277e-05
2023-01-21 12:42:28.723325: step: 880/530, loss: 0.0038259506691247225
2023-01-21 12:42:29.865199: step: 884/530, loss: 0.0013064384693279862
2023-01-21 12:42:30.967758: step: 888/530, loss: 0.0045497422106564045
2023-01-21 12:42:32.137165: step: 892/530, loss: 0.009140742011368275
2023-01-21 12:42:33.247570: step: 896/530, loss: 7.400512549793348e-05
2023-01-21 12:42:34.343041: step: 900/530, loss: 0.00025081634521484375
2023-01-21 12:42:35.449247: step: 904/530, loss: 0.0005198478465899825
2023-01-21 12:42:36.575091: step: 908/530, loss: 0.02880859375
2023-01-21 12:42:37.667361: step: 912/530, loss: 0.0015477180713787675
2023-01-21 12:42:38.751468: step: 916/530, loss: 0.5670353174209595
2023-01-21 12:42:39.855946: step: 920/530, loss: 4.301071021473035e-05
2023-01-21 12:42:40.982246: step: 924/530, loss: 0.00040435791015625
2023-01-21 12:42:42.113645: step: 928/530, loss: 0.029523467645049095
2023-01-21 12:42:43.248955: step: 932/530, loss: 0.0002792835293803364
2023-01-21 12:42:44.411986: step: 936/530, loss: 0.0011518478859215975
2023-01-21 12:42:45.534347: step: 940/530, loss: 0.016272639855742455
2023-01-21 12:42:46.659464: step: 944/530, loss: 0.01273798942565918
2023-01-21 12:42:47.783941: step: 948/530, loss: 0.038091469556093216
2023-01-21 12:42:48.924210: step: 952/530, loss: 0.01286239642649889
2023-01-21 12:42:50.016363: step: 956/530, loss: 0.0037246705032885075
2023-01-21 12:42:51.130525: step: 960/530, loss: 0.0008117675897665322
2023-01-21 12:42:52.264631: step: 964/530, loss: 0.0012517928844317794
2023-01-21 12:42:53.400898: step: 968/530, loss: 0.00197181710973382
2023-01-21 12:42:54.521517: step: 972/530, loss: 0.0002876281796488911
2023-01-21 12:42:55.632090: step: 976/530, loss: 2.498626781743951e-05
2023-01-21 12:42:56.771506: step: 980/530, loss: 0.008121490478515625
2023-01-21 12:42:57.907709: step: 984/530, loss: 0.02439708635210991
2023-01-21 12:42:59.024480: step: 988/530, loss: 1.8119826563633978e-06
2023-01-21 12:43:00.109695: step: 992/530, loss: 0.0011347770923748612
2023-01-21 12:43:01.217333: step: 996/530, loss: 6.046295311534777e-05
2023-01-21 12:43:02.322233: step: 1000/530, loss: 0.0009944438934326172
2023-01-21 12:43:03.435016: step: 1004/530, loss: 0.00013828277587890625
2023-01-21 12:43:04.552386: step: 1008/530, loss: 8.258819434558973e-05
2023-01-21 12:43:05.685950: step: 1012/530, loss: 0.028845978900790215
2023-01-21 12:43:06.785029: step: 1016/530, loss: 0.0033416748046875
2023-01-21 12:43:07.914010: step: 1020/530, loss: 0.01681804656982422
2023-01-21 12:43:09.007359: step: 1024/530, loss: 0.04450998455286026
2023-01-21 12:43:10.119735: step: 1028/530, loss: 0.09645596146583557
2023-01-21 12:43:11.230644: step: 1032/530, loss: 0.010912513360381126
2023-01-21 12:43:12.326249: step: 1036/530, loss: 0.0013650894397869706
2023-01-21 12:43:13.428846: step: 1040/530, loss: 6.532669067382812e-05
2023-01-21 12:43:14.552222: step: 1044/530, loss: 0.01375570334494114
2023-01-21 12:43:15.685491: step: 1048/530, loss: 0.0018524170154705644
2023-01-21 12:43:16.823725: step: 1052/530, loss: 0.00483627337962389
2023-01-21 12:43:17.935278: step: 1056/530, loss: 0.0001780033198883757
2023-01-21 12:43:19.021084: step: 1060/530, loss: 0.0001085281401174143
2023-01-21 12:43:20.149574: step: 1064/530, loss: 5.908012462896295e-05
2023-01-21 12:43:21.264452: step: 1068/530, loss: 0.026308298110961914
2023-01-21 12:43:22.369736: step: 1072/530, loss: 0.0011111260391771793
2023-01-21 12:43:23.469278: step: 1076/530, loss: 0.0002441972610540688
2023-01-21 12:43:24.553080: step: 1080/530, loss: 3.814697606685513e-07
2023-01-21 12:43:25.665623: step: 1084/530, loss: 0.0008270263788290322
2023-01-21 12:43:26.787752: step: 1088/530, loss: 0.001354217529296875
2023-01-21 12:43:27.947272: step: 1092/530, loss: 0.0005074500804767013
2023-01-21 12:43:29.030725: step: 1096/530, loss: 0.003538703778758645
2023-01-21 12:43:30.157174: step: 1100/530, loss: 0.014377403073012829
2023-01-21 12:43:31.270723: step: 1104/530, loss: 2.746581958490424e-05
2023-01-21 12:43:32.368475: step: 1108/530, loss: 0.007102012634277344
2023-01-21 12:43:33.520326: step: 1112/530, loss: 0.02230844646692276
2023-01-21 12:43:34.617699: step: 1116/530, loss: 2.1457672119140625e-05
2023-01-21 12:43:35.706699: step: 1120/530, loss: 0.0001049041748046875
2023-01-21 12:43:36.829418: step: 1124/530, loss: 1.9550323486328125e-05
2023-01-21 12:43:37.963988: step: 1128/530, loss: 0.09099344909191132
2023-01-21 12:43:39.070396: step: 1132/530, loss: 0.005656624212861061
2023-01-21 12:43:40.179048: step: 1136/530, loss: 0.004279041197150946
2023-01-21 12:43:41.335750: step: 1140/530, loss: 0.0001928329438669607
2023-01-21 12:43:42.442569: step: 1144/530, loss: 0.015855886042118073
2023-01-21 12:43:43.558609: step: 1148/530, loss: 0.00024585722712799907
2023-01-21 12:43:44.674735: step: 1152/530, loss: 5.6934361055027694e-05
2023-01-21 12:43:45.779517: step: 1156/530, loss: 0.0002584934118203819
2023-01-21 12:43:46.879965: step: 1160/530, loss: 1.9645693100756034e-05
2023-01-21 12:43:48.001239: step: 1164/530, loss: 0.00010290146747138351
2023-01-21 12:43:49.101894: step: 1168/530, loss: 0.09521675109863281
2023-01-21 12:43:50.226485: step: 1172/530, loss: 0.0002265930233988911
2023-01-21 12:43:51.385626: step: 1176/530, loss: 0.0049988748505711555
2023-01-21 12:43:52.514302: step: 1180/530, loss: 0.019220924004912376
2023-01-21 12:43:53.659836: step: 1184/530, loss: 0.000446319580078125
2023-01-21 12:43:54.784380: step: 1188/530, loss: 0.001766967703588307
2023-01-21 12:43:55.951652: step: 1192/530, loss: 0.008145619183778763
2023-01-21 12:43:57.038005: step: 1196/530, loss: 0.0037691115867346525
2023-01-21 12:43:58.128583: step: 1200/530, loss: 0.00022182465181685984
2023-01-21 12:43:59.221326: step: 1204/530, loss: 0.0003319740353617817
2023-01-21 12:44:00.353126: step: 1208/530, loss: 0.0008969306945800781
2023-01-21 12:44:01.490634: step: 1212/530, loss: 3.185272362316027e-05
2023-01-21 12:44:02.583109: step: 1216/530, loss: 0.0006044387700967491
2023-01-21 12:44:03.715299: step: 1220/530, loss: 0.005807018373161554
2023-01-21 12:44:04.818719: step: 1224/530, loss: 0.002032899996265769
2023-01-21 12:44:05.947612: step: 1228/530, loss: 0.003013229463249445
2023-01-21 12:44:07.094613: step: 1232/530, loss: 0.0010243416763842106
2023-01-21 12:44:08.215766: step: 1236/530, loss: 0.0004020213964395225
2023-01-21 12:44:09.334726: step: 1240/530, loss: 0.00019035338482353836
2023-01-21 12:44:10.461671: step: 1244/530, loss: 7.667541649425402e-05
2023-01-21 12:44:11.568259: step: 1248/530, loss: 5.340576535672881e-06
2023-01-21 12:44:12.667007: step: 1252/530, loss: 0.38790231943130493
2023-01-21 12:44:13.783640: step: 1256/530, loss: 0.050110626965761185
2023-01-21 12:44:14.906740: step: 1260/530, loss: 0.023627936840057373
2023-01-21 12:44:16.038777: step: 1264/530, loss: 0.7670993804931641
2023-01-21 12:44:17.190191: step: 1268/530, loss: 0.004557418636977673
2023-01-21 12:44:18.288783: step: 1272/530, loss: 0.0012234688038006425
2023-01-21 12:44:19.404200: step: 1276/530, loss: 0.022089004516601562
2023-01-21 12:44:20.514185: step: 1280/530, loss: 0.003429317381232977
2023-01-21 12:44:21.606201: step: 1284/530, loss: 0.0007022857898846269
2023-01-21 12:44:22.756089: step: 1288/530, loss: 0.009295462630689144
2023-01-21 12:44:23.865096: step: 1292/530, loss: 1.859665098891128e-05
2023-01-21 12:44:24.993068: step: 1296/530, loss: 0.016332531347870827
2023-01-21 12:44:26.110230: step: 1300/530, loss: -1.287460349885805e-06
2023-01-21 12:44:27.242620: step: 1304/530, loss: 0.002175808185711503
2023-01-21 12:44:28.363224: step: 1308/530, loss: 0.0217437744140625
2023-01-21 12:44:29.480026: step: 1312/530, loss: 0.02145233191549778
2023-01-21 12:44:30.578775: step: 1316/530, loss: 0.005115890875458717
2023-01-21 12:44:31.710742: step: 1320/530, loss: 1.220703143189894e-05
2023-01-21 12:44:32.804168: step: 1324/530, loss: 0.00405197124928236
2023-01-21 12:44:33.926267: step: 1328/530, loss: 0.0015566349029541016
2023-01-21 12:44:35.050103: step: 1332/530, loss: 0.0002992630179505795
2023-01-21 12:44:36.182047: step: 1336/530, loss: 0.05089912563562393
2023-01-21 12:44:37.318196: step: 1340/530, loss: 0.0034837722778320312
2023-01-21 12:44:38.463851: step: 1344/530, loss: 0.09760265797376633
2023-01-21 12:44:39.577901: step: 1348/530, loss: 0.0007250786293298006
2023-01-21 12:44:40.681215: step: 1352/530, loss: 0.052616216242313385
2023-01-21 12:44:41.800009: step: 1356/530, loss: 0.015094185248017311
2023-01-21 12:44:42.908636: step: 1360/530, loss: 8.144378807628527e-05
2023-01-21 12:44:44.006945: step: 1364/530, loss: 8.392333984375e-05
2023-01-21 12:44:45.100597: step: 1368/530, loss: 0.22115115821361542
2023-01-21 12:44:46.208794: step: 1372/530, loss: 0.025307562202215195
2023-01-21 12:44:47.312111: step: 1376/530, loss: 0.024248123168945312
2023-01-21 12:44:48.412457: step: 1380/530, loss: 0.02683706395328045
2023-01-21 12:44:49.561414: step: 1384/530, loss: 0.014273738488554955
2023-01-21 12:44:50.660561: step: 1388/530, loss: 0.015970801934599876
2023-01-21 12:44:51.764407: step: 1392/530, loss: 0.021416664123535156
2023-01-21 12:44:52.873159: step: 1396/530, loss: 0.03747883066534996
2023-01-21 12:44:53.999892: step: 1400/530, loss: 2.403259350103326e-05
2023-01-21 12:44:55.096242: step: 1404/530, loss: 0.069361113011837
2023-01-21 12:44:56.173045: step: 1408/530, loss: 0.0010403634514659643
2023-01-21 12:44:57.286303: step: 1412/530, loss: 0.0036463739816099405
2023-01-21 12:44:58.386036: step: 1416/530, loss: 0.00032005307730287313
2023-01-21 12:44:59.490118: step: 1420/530, loss: 0.016077041625976562
2023-01-21 12:45:00.617695: step: 1424/530, loss: 0.06343209743499756
2023-01-21 12:45:01.724675: step: 1428/530, loss: 0.02687687799334526
2023-01-21 12:45:02.815453: step: 1432/530, loss: 0.0008306503877975047
2023-01-21 12:45:03.940864: step: 1436/530, loss: 0.00041537283686921
2023-01-21 12:45:05.088388: step: 1440/530, loss: 0.0008162021404132247
2023-01-21 12:45:06.216544: step: 1444/530, loss: 5.8460234868107364e-05
2023-01-21 12:45:07.310181: step: 1448/530, loss: 0.001305532525293529
2023-01-21 12:45:08.405963: step: 1452/530, loss: 0.008279371075332165
2023-01-21 12:45:09.500659: step: 1456/530, loss: 0.0005608558421954513
2023-01-21 12:45:10.573840: step: 1460/530, loss: 0.0015186310047283769
2023-01-21 12:45:11.662490: step: 1464/530, loss: 0.002937126439064741
2023-01-21 12:45:12.763073: step: 1468/530, loss: 0.008966874331235886
2023-01-21 12:45:13.869221: step: 1472/530, loss: 0.0007056236499920487
2023-01-21 12:45:14.989386: step: 1476/530, loss: 0.03482925891876221
2023-01-21 12:45:16.076463: step: 1480/530, loss: 0.03040785901248455
2023-01-21 12:45:17.176756: step: 1484/530, loss: 0.0003125190851278603
2023-01-21 12:45:18.303884: step: 1488/530, loss: 0.13238820433616638
2023-01-21 12:45:19.417940: step: 1492/530, loss: 0.0005943774594925344
2023-01-21 12:45:20.543622: step: 1496/530, loss: 0.20336304605007172
2023-01-21 12:45:21.682517: step: 1500/530, loss: 0.010007238015532494
2023-01-21 12:45:22.766921: step: 1504/530, loss: 0.0001773834228515625
2023-01-21 12:45:23.887248: step: 1508/530, loss: 0.00023865699768066406
2023-01-21 12:45:25.042483: step: 1512/530, loss: 0.0029567719902843237
2023-01-21 12:45:26.148636: step: 1516/530, loss: 0.2214791178703308
2023-01-21 12:45:27.251934: step: 1520/530, loss: 0.016840552911162376
2023-01-21 12:45:28.350943: step: 1524/530, loss: 0.0015007973415777087
2023-01-21 12:45:29.453462: step: 1528/530, loss: 3.490447852527723e-05
2023-01-21 12:45:30.547021: step: 1532/530, loss: 0.0037677527870982885
2023-01-21 12:45:31.642519: step: 1536/530, loss: 0.005546760745346546
2023-01-21 12:45:32.726387: step: 1540/530, loss: 0.0004440307675395161
2023-01-21 12:45:33.816213: step: 1544/530, loss: 0.0040573119185864925
2023-01-21 12:45:34.926129: step: 1548/530, loss: 0.00013656617375090718
2023-01-21 12:45:36.034443: step: 1552/530, loss: 0.03892365097999573
2023-01-21 12:45:37.172557: step: 1556/530, loss: 3.452301098150201e-05
2023-01-21 12:45:38.251275: step: 1560/530, loss: 9.608268737792969e-05
2023-01-21 12:45:39.370376: step: 1564/530, loss: 0.0007122039678506553
2023-01-21 12:45:40.469366: step: 1568/530, loss: 0.004614353179931641
2023-01-21 12:45:41.596991: step: 1572/530, loss: 0.004091453738510609
2023-01-21 12:45:42.739607: step: 1576/530, loss: 0.003056049346923828
2023-01-21 12:45:43.929861: step: 1580/530, loss: 6.103515261202119e-06
2023-01-21 12:45:45.052546: step: 1584/530, loss: 2.1743775505456142e-05
2023-01-21 12:45:46.147338: step: 1588/530, loss: 0.012013768777251244
2023-01-21 12:45:47.275924: step: 1592/530, loss: 0.0006466865306720138
2023-01-21 12:45:48.370173: step: 1596/530, loss: 0.0014451980823650956
2023-01-21 12:45:49.491819: step: 1600/530, loss: 0.1019367203116417
2023-01-21 12:45:50.654987: step: 1604/530, loss: 0.10819997638463974
2023-01-21 12:45:51.756401: step: 1608/530, loss: 0.00867385882884264
2023-01-21 12:45:52.868619: step: 1612/530, loss: 0.004678917117416859
2023-01-21 12:45:53.941497: step: 1616/530, loss: 1.888275073724799e-05
2023-01-21 12:45:55.070154: step: 1620/530, loss: 0.013427353464066982
2023-01-21 12:45:56.180397: step: 1624/530, loss: 0.010287332348525524
2023-01-21 12:45:57.269820: step: 1628/530, loss: 0.13267642259597778
2023-01-21 12:45:58.393836: step: 1632/530, loss: 0.027617646381258965
2023-01-21 12:45:59.490430: step: 1636/530, loss: 0.00013790131197310984
2023-01-21 12:46:00.604155: step: 1640/530, loss: 0.0011988639598712325
2023-01-21 12:46:01.692814: step: 1644/530, loss: 0.018183326348662376
2023-01-21 12:46:02.808141: step: 1648/530, loss: 0.048110101372003555
2023-01-21 12:46:03.908627: step: 1652/530, loss: 0.000493896019179374
2023-01-21 12:46:05.014758: step: 1656/530, loss: 2.7179718017578125e-05
2023-01-21 12:46:06.134620: step: 1660/530, loss: 2.765655608527595e-06
2023-01-21 12:46:07.227859: step: 1664/530, loss: 5.798339770990424e-05
2023-01-21 12:46:08.304983: step: 1668/530, loss: 0.00041427614632993937
2023-01-21 12:46:09.388724: step: 1672/530, loss: 0.005241870880126953
2023-01-21 12:46:10.476975: step: 1676/530, loss: 0.003254890674725175
2023-01-21 12:46:11.612611: step: 1680/530, loss: 0.006860780529677868
2023-01-21 12:46:12.721367: step: 1684/530, loss: 0.0004207611200399697
2023-01-21 12:46:13.817304: step: 1688/530, loss: 5.440712266135961e-05
2023-01-21 12:46:14.939118: step: 1692/530, loss: 0.0016813278198242188
2023-01-21 12:46:16.002470: step: 1696/530, loss: 0.00386390695348382
2023-01-21 12:46:17.083284: step: 1700/530, loss: 0.0019323349697515368
2023-01-21 12:46:18.194325: step: 1704/530, loss: 0.0003498554287943989
2023-01-21 12:46:19.308773: step: 1708/530, loss: 0.003450918011367321
2023-01-21 12:46:20.404461: step: 1712/530, loss: 0.0006682396051473916
2023-01-21 12:46:21.479253: step: 1716/530, loss: 0.0030312538146972656
2023-01-21 12:46:22.575798: step: 1720/530, loss: 0.004015827085822821
2023-01-21 12:46:23.700452: step: 1724/530, loss: 0.00018043517775367945
2023-01-21 12:46:24.792869: step: 1728/530, loss: 0.0027051924262195826
2023-01-21 12:46:25.891352: step: 1732/530, loss: 0.019979191944003105
2023-01-21 12:46:27.022872: step: 1736/530, loss: 0.0014423370594158769
2023-01-21 12:46:28.161370: step: 1740/530, loss: 0.013526344671845436
2023-01-21 12:46:29.267269: step: 1744/530, loss: 0.020875215530395508
2023-01-21 12:46:30.368345: step: 1748/530, loss: 0.009434891864657402
2023-01-21 12:46:31.479219: step: 1752/530, loss: 0.008918190374970436
2023-01-21 12:46:32.585473: step: 1756/530, loss: 0.0020404814276844263
2023-01-21 12:46:33.684049: step: 1760/530, loss: 0.00026407241239212453
2023-01-21 12:46:34.775797: step: 1764/530, loss: -1.1539459592313506e-05
2023-01-21 12:46:35.850924: step: 1768/530, loss: 0.0017778397304937243
2023-01-21 12:46:36.941013: step: 1772/530, loss: 0.0024145126808434725
2023-01-21 12:46:38.062885: step: 1776/530, loss: 0.017945481464266777
2023-01-21 12:46:39.163004: step: 1780/530, loss: 0.001502609346061945
2023-01-21 12:46:40.262543: step: 1784/530, loss: 0.02790260501205921
2023-01-21 12:46:41.363333: step: 1788/530, loss: 0.00025262832059524953
2023-01-21 12:46:42.457821: step: 1792/530, loss: 0.014989947900176048
2023-01-21 12:46:43.545193: step: 1796/530, loss: 0.0025745390448719263
2023-01-21 12:46:44.647409: step: 1800/530, loss: 0.020673513412475586
2023-01-21 12:46:45.763802: step: 1804/530, loss: -3.862381163344253e-06
2023-01-21 12:46:46.910033: step: 1808/530, loss: 0.010018253698945045
2023-01-21 12:46:48.022994: step: 1812/530, loss: 0.30904483795166016
2023-01-21 12:46:49.121074: step: 1816/530, loss: 0.002582025481387973
2023-01-21 12:46:50.216951: step: 1820/530, loss: 5.896091170143336e-05
2023-01-21 12:46:51.304043: step: 1824/530, loss: 0.007372856140136719
2023-01-21 12:46:52.405449: step: 1828/530, loss: 0.015140152536332607
2023-01-21 12:46:53.502756: step: 1832/530, loss: 0.00011768341209972277
2023-01-21 12:46:54.598084: step: 1836/530, loss: 0.0006092071416787803
2023-01-21 12:46:55.697463: step: 1840/530, loss: 0.003922748379409313
2023-01-21 12:46:56.841026: step: 1844/530, loss: 0.003601646516472101
2023-01-21 12:46:57.920280: step: 1848/530, loss: 0.0008712768321856856
2023-01-21 12:46:59.033416: step: 1852/530, loss: 0.022364426404237747
2023-01-21 12:47:00.153958: step: 1856/530, loss: 0.011196423321962357
2023-01-21 12:47:01.234707: step: 1860/530, loss: 0.005649459548294544
2023-01-21 12:47:02.335738: step: 1864/530, loss: 0.0013299465645104647
2023-01-21 12:47:03.421420: step: 1868/530, loss: 0.008362484164536
2023-01-21 12:47:04.520612: step: 1872/530, loss: 3.24249267578125e-05
2023-01-21 12:47:05.623061: step: 1876/530, loss: 0.0039099217392504215
2023-01-21 12:47:06.730496: step: 1880/530, loss: 0.0012866973411291838
2023-01-21 12:47:07.832283: step: 1884/530, loss: 0.016264427453279495
2023-01-21 12:47:08.935571: step: 1888/530, loss: 0.0229464303702116
2023-01-21 12:47:10.030306: step: 1892/530, loss: 0.005539989564567804
2023-01-21 12:47:11.129445: step: 1896/530, loss: 0.0005311965942382812
2023-01-21 12:47:12.217861: step: 1900/530, loss: 0.02552509307861328
2023-01-21 12:47:13.316156: step: 1904/530, loss: 1.7070769899873994e-05
2023-01-21 12:47:14.441629: step: 1908/530, loss: 6.923676119185984e-05
2023-01-21 12:47:15.520601: step: 1912/530, loss: 0.0014566421741619706
2023-01-21 12:47:16.608128: step: 1916/530, loss: 0.01744053326547146
2023-01-21 12:47:17.700580: step: 1920/530, loss: 0.00016689300537109375
2023-01-21 12:47:18.827262: step: 1924/530, loss: 0.0012124062050133944
2023-01-21 12:47:19.932683: step: 1928/530, loss: -2.1457671550706436e-07
2023-01-21 12:47:21.005258: step: 1932/530, loss: 5.14984139954322e-06
2023-01-21 12:47:22.102421: step: 1936/530, loss: 0.0009291649330407381
2023-01-21 12:47:23.222647: step: 1940/530, loss: 8.559226989746094e-05
2023-01-21 12:47:24.341323: step: 1944/530, loss: 0.010659217834472656
2023-01-21 12:47:25.442956: step: 1948/530, loss: 0.02501850016415119
2023-01-21 12:47:26.524202: step: 1952/530, loss: 0.07284589111804962
2023-01-21 12:47:27.644299: step: 1956/530, loss: 0.04702110216021538
2023-01-21 12:47:28.776771: step: 1960/530, loss: 0.0007806778303347528
2023-01-21 12:47:29.872072: step: 1964/530, loss: 0.0013385772472247481
2023-01-21 12:47:30.991621: step: 1968/530, loss: 0.04651908949017525
2023-01-21 12:47:32.100140: step: 1972/530, loss: 0.017020607367157936
2023-01-21 12:47:33.199656: step: 1976/530, loss: 0.00768203753978014
2023-01-21 12:47:34.293526: step: 1980/530, loss: 1.316070574830519e-05
2023-01-21 12:47:35.399680: step: 1984/530, loss: 0.056861210614442825
2023-01-21 12:47:36.510930: step: 1988/530, loss: 0.012256050482392311
2023-01-21 12:47:37.585914: step: 1992/530, loss: 0.005224514286965132
2023-01-21 12:47:38.709366: step: 1996/530, loss: 4.425048973644152e-05
2023-01-21 12:47:39.841520: step: 2000/530, loss: 0.0013729095226153731
2023-01-21 12:47:40.962400: step: 2004/530, loss: 0.07634048163890839
2023-01-21 12:47:42.097586: step: 2008/530, loss: 0.004924201872199774
2023-01-21 12:47:43.249453: step: 2012/530, loss: 0.001954364823177457
2023-01-21 12:47:44.338796: step: 2016/530, loss: 0.032430462539196014
2023-01-21 12:47:45.445323: step: 2020/530, loss: 0.014415168203413486
2023-01-21 12:47:46.561097: step: 2024/530, loss: 0.00013661386037711054
2023-01-21 12:47:47.655379: step: 2028/530, loss: 0.007250738330185413
2023-01-21 12:47:48.762277: step: 2032/530, loss: 0.007100057788193226
2023-01-21 12:47:49.880721: step: 2036/530, loss: 0.001987457275390625
2023-01-21 12:47:50.968210: step: 2040/530, loss: 0.010371637530624866
2023-01-21 12:47:52.069034: step: 2044/530, loss: 0.0006251335144042969
2023-01-21 12:47:53.195820: step: 2048/530, loss: 0.0031387328635901213
2023-01-21 12:47:54.322786: step: 2052/530, loss: 0.002663898514583707
2023-01-21 12:47:55.415131: step: 2056/530, loss: 0.00012474060349632055
2023-01-21 12:47:56.528764: step: 2060/530, loss: 1.8167496818932705e-05
2023-01-21 12:47:57.642094: step: 2064/530, loss: 0.062425803393125534
2023-01-21 12:47:58.744089: step: 2068/530, loss: 0.0004299640713725239
2023-01-21 12:47:59.882352: step: 2072/530, loss: 0.0001733779936330393
2023-01-21 12:48:00.981294: step: 2076/530, loss: 0.20610304176807404
2023-01-21 12:48:02.051929: step: 2080/530, loss: 0.00035429003764875233
2023-01-21 12:48:03.165868: step: 2084/530, loss: 0.00011205673217773438
2023-01-21 12:48:04.259274: step: 2088/530, loss: 4.38690176451928e-06
2023-01-21 12:48:05.390949: step: 2092/530, loss: 0.006417274475097656
2023-01-21 12:48:06.502107: step: 2096/530, loss: 7.858276512706652e-05
2023-01-21 12:48:07.604678: step: 2100/530, loss: 6.570815457962453e-05
2023-01-21 12:48:08.703048: step: 2104/530, loss: 0.06294260174036026
2023-01-21 12:48:09.788979: step: 2108/530, loss: 0.0017305852379649878
2023-01-21 12:48:10.902547: step: 2112/530, loss: 2.19345088225964e-06
2023-01-21 12:48:12.017493: step: 2116/530, loss: 0.00017070770263671875
2023-01-21 12:48:13.099444: step: 2120/530, loss: 0.0006749153253622353
==================================================
Loss: 0.018
--------------------
Dev: {'event': {'p': 0.5895061728395061, 'r': 0.762982689747004, 'f1': 0.665118978525827}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Test: {'event': {'p': 0.6339779005524862, 'r': 0.8024475524475524, 'f1': 0.7083333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Chinese: {'event': {'p': 0.5866666666666667, 'r': 0.8148148148148148, 'f1': 0.6821705426356589}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Korean: {'event': {'p': 0.6724137931034483, 'r': 0.6190476190476191, 'f1': 0.6446280991735537}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Russian: {'event': {'p': 0.48717948717948717, 'r': 0.5277777777777778, 'f1': 0.5066666666666667}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Korean: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 12:48:52.507630: step: 4/530, loss: 0.04722995683550835
2023-01-21 12:48:53.608247: step: 8/530, loss: 0.006507301237434149
2023-01-21 12:48:54.705367: step: 12/530, loss: 0.005153465084731579
2023-01-21 12:48:55.799599: step: 16/530, loss: 7.3432925091765355e-06
2023-01-21 12:48:56.874638: step: 20/530, loss: 0.002524948213249445
2023-01-21 12:48:57.998338: step: 24/530, loss: 0.002706432482227683
2023-01-21 12:48:59.130651: step: 28/530, loss: -1.9073486328125e-06
2023-01-21 12:49:00.229850: step: 32/530, loss: 0.000759983086027205
2023-01-21 12:49:01.364593: step: 36/530, loss: 0.011025046929717064
2023-01-21 12:49:02.521654: step: 40/530, loss: 0.007126999087631702
2023-01-21 12:49:03.590848: step: 44/530, loss: 0.025605248287320137
2023-01-21 12:49:04.684710: step: 48/530, loss: 2.956390380859375e-05
2023-01-21 12:49:05.808129: step: 52/530, loss: 0.00011057854135287926
2023-01-21 12:49:06.921939: step: 56/530, loss: 0.0008554935920983553
2023-01-21 12:49:08.027695: step: 60/530, loss: 0.0004230499325785786
2023-01-21 12:49:09.143725: step: 64/530, loss: 2.4509430659236386e-05
2023-01-21 12:49:10.223344: step: 68/530, loss: 1.9550323486328125e-05
2023-01-21 12:49:11.333488: step: 72/530, loss: 0.0012712478637695312
2023-01-21 12:49:12.426697: step: 76/530, loss: 0.03780489042401314
2023-01-21 12:49:13.533410: step: 80/530, loss: 5.2642819355241954e-05
2023-01-21 12:49:14.631047: step: 84/530, loss: 0.00014801025099586695
2023-01-21 12:49:15.811887: step: 88/530, loss: 1.4686585927847773e-05
2023-01-21 12:49:16.891937: step: 92/530, loss: 0.0014385223621502519
2023-01-21 12:49:18.028516: step: 96/530, loss: 0.1341615617275238
2023-01-21 12:49:19.121866: step: 100/530, loss: 0.004081153776496649
2023-01-21 12:49:20.250683: step: 104/530, loss: 8.831024024402723e-05
2023-01-21 12:49:21.341098: step: 108/530, loss: 1.5544892448815517e-05
2023-01-21 12:49:22.451422: step: 112/530, loss: 0.004470634739845991
2023-01-21 12:49:23.536671: step: 116/530, loss: 4.911422365694307e-06
2023-01-21 12:49:24.635274: step: 120/530, loss: 0.000492095947265625
2023-01-21 12:49:25.747883: step: 124/530, loss: 0.0008932590717449784
2023-01-21 12:49:26.841618: step: 128/530, loss: 0.0006298065418377519
2023-01-21 12:49:27.932884: step: 132/530, loss: 1.0824203855008818e-05
2023-01-21 12:49:29.032022: step: 136/530, loss: 0.00033168791560456157
2023-01-21 12:49:30.123320: step: 140/530, loss: 0.0001293182431254536
2023-01-21 12:49:31.222960: step: 144/530, loss: 0.00031270983163267374
2023-01-21 12:49:32.334401: step: 148/530, loss: 0.0004245758173055947
2023-01-21 12:49:33.458657: step: 152/530, loss: 5.207061622058973e-05
2023-01-21 12:49:34.554458: step: 156/530, loss: 0.004668140783905983
2023-01-21 12:49:35.648148: step: 160/530, loss: 0.0001549005537526682
2023-01-21 12:49:36.746368: step: 164/530, loss: 0.026813507080078125
2023-01-21 12:49:37.876591: step: 168/530, loss: 5.817413330078125e-05
2023-01-21 12:49:38.993853: step: 172/530, loss: 0.004975604824721813
2023-01-21 12:49:40.105633: step: 176/530, loss: 0.010276603512465954
2023-01-21 12:49:41.211371: step: 180/530, loss: 0.0337039977312088
2023-01-21 12:49:42.293375: step: 184/530, loss: 0.007909965701401234
2023-01-21 12:49:43.383176: step: 188/530, loss: 0.013691998086869717
2023-01-21 12:49:44.481337: step: 192/530, loss: 0.046692658215761185
2023-01-21 12:49:45.588855: step: 196/530, loss: 4.39643845311366e-05
2023-01-21 12:49:46.675654: step: 200/530, loss: 0.0009597778553143144
2023-01-21 12:49:47.786367: step: 204/530, loss: 0.08455977588891983
2023-01-21 12:49:48.863448: step: 208/530, loss: 0.007660388946533203
2023-01-21 12:49:49.962841: step: 212/530, loss: 0.0005658150184899569
2023-01-21 12:49:51.042812: step: 216/530, loss: 0.0011463165283203125
2023-01-21 12:49:52.145116: step: 220/530, loss: 0.02997284010052681
2023-01-21 12:49:53.243013: step: 224/530, loss: 7.772445314913057e-06
2023-01-21 12:49:54.355238: step: 228/530, loss: 0.023921657353639603
2023-01-21 12:49:55.481454: step: 232/530, loss: 0.0005196809652261436
2023-01-21 12:49:56.568951: step: 236/530, loss: 0.0006315231439657509
2023-01-21 12:49:57.657970: step: 240/530, loss: 0.016075754538178444
2023-01-21 12:49:58.745360: step: 244/530, loss: 0.0009379386901855469
2023-01-21 12:49:59.815302: step: 248/530, loss: 0.008540726266801357
2023-01-21 12:50:00.919162: step: 252/530, loss: 0.00045261383638717234
2023-01-21 12:50:02.038826: step: 256/530, loss: 0.01786184310913086
2023-01-21 12:50:03.149357: step: 260/530, loss: 0.003457355545833707
2023-01-21 12:50:04.234793: step: 264/530, loss: 0.00020170211791992188
2023-01-21 12:50:05.307830: step: 268/530, loss: 0.0003158569452352822
2023-01-21 12:50:06.422459: step: 272/530, loss: 0.006680727005004883
2023-01-21 12:50:07.533071: step: 276/530, loss: 0.0005456925136968493
2023-01-21 12:50:08.640512: step: 280/530, loss: 0.00037136077298782766
2023-01-21 12:50:09.771873: step: 284/530, loss: 0.01712055318057537
2023-01-21 12:50:10.860063: step: 288/530, loss: 0.0004516601620707661
2023-01-21 12:50:11.941246: step: 292/530, loss: 0.0009038925636559725
2023-01-21 12:50:13.039436: step: 296/530, loss: 0.018912507221102715
2023-01-21 12:50:14.135925: step: 300/530, loss: 0.001996851060539484
2023-01-21 12:50:15.260135: step: 304/530, loss: 0.0004201889387331903
2023-01-21 12:50:16.352588: step: 308/530, loss: 0.00010566711716819555
2023-01-21 12:50:17.464376: step: 312/530, loss: 2.0503997802734375e-05
2023-01-21 12:50:18.590558: step: 316/530, loss: 0.0006224632379598916
2023-01-21 12:50:19.745303: step: 320/530, loss: 0.00022068023099564016
2023-01-21 12:50:20.843061: step: 324/530, loss: 0.07869367301464081
2023-01-21 12:50:21.945924: step: 328/530, loss: 0.004807138349860907
2023-01-21 12:50:23.020628: step: 332/530, loss: 0.0005497932434082031
2023-01-21 12:50:24.120667: step: 336/530, loss: 0.0018842697609215975
2023-01-21 12:50:25.222933: step: 340/530, loss: 0.0012351989280432463
2023-01-21 12:50:26.345000: step: 344/530, loss: 0.01212768629193306
2023-01-21 12:50:27.475635: step: 348/530, loss: 0.00291271205060184
2023-01-21 12:50:28.587301: step: 352/530, loss: 0.0009590148692950606
2023-01-21 12:50:29.707776: step: 356/530, loss: 0.0005356550100259483
2023-01-21 12:50:30.822916: step: 360/530, loss: 0.00011124611046398059
2023-01-21 12:50:31.909538: step: 364/530, loss: 0.0003190040588378906
2023-01-21 12:50:33.024435: step: 368/530, loss: 0.0028252601623535156
2023-01-21 12:50:34.153902: step: 372/530, loss: 7.576942152809352e-05
2023-01-21 12:50:35.277936: step: 376/530, loss: 0.0014024734264239669
2023-01-21 12:50:36.398352: step: 380/530, loss: 0.0031455992721021175
2023-01-21 12:50:37.490214: step: 384/530, loss: 0.00014061927504371852
2023-01-21 12:50:38.596329: step: 388/530, loss: 0.013525962829589844
2023-01-21 12:50:39.703205: step: 392/530, loss: -1.0490416570974048e-06
2023-01-21 12:50:40.802602: step: 396/530, loss: 0.554465115070343
2023-01-21 12:50:41.908024: step: 400/530, loss: 0.0021772384643554688
2023-01-21 12:50:43.056498: step: 404/530, loss: 5.807876732433215e-05
2023-01-21 12:50:44.167830: step: 408/530, loss: 0.0012197494506835938
2023-01-21 12:50:45.261754: step: 412/530, loss: 0.003692054655402899
2023-01-21 12:50:46.356063: step: 416/530, loss: -1.9073468138230965e-07
2023-01-21 12:50:47.430579: step: 420/530, loss: 0.01598997227847576
2023-01-21 12:50:48.518303: step: 424/530, loss: 0.0017528533935546875
2023-01-21 12:50:49.627911: step: 428/530, loss: 0.004490375518798828
2023-01-21 12:50:50.733804: step: 432/530, loss: 0.005492687691003084
2023-01-21 12:50:51.843842: step: 436/530, loss: 0.05463390424847603
2023-01-21 12:50:52.944788: step: 440/530, loss: 0.0016963958041742444
2023-01-21 12:50:54.026144: step: 444/530, loss: 0.0006232261657714844
2023-01-21 12:50:55.135946: step: 448/530, loss: 0.0022510529961436987
2023-01-21 12:50:56.230337: step: 452/530, loss: 0.025351429358124733
2023-01-21 12:50:57.309051: step: 456/530, loss: 0.00013446807861328125
2023-01-21 12:50:58.455629: step: 460/530, loss: 0.013764476403594017
2023-01-21 12:50:59.546768: step: 464/530, loss: 0.00011339187767589465
2023-01-21 12:51:00.655380: step: 468/530, loss: 0.0009132385021075606
2023-01-21 12:51:01.761757: step: 472/530, loss: 0.00017576217942405492
2023-01-21 12:51:02.872859: step: 476/530, loss: 0.04987630620598793
2023-01-21 12:51:03.958868: step: 480/530, loss: 0.02460164949297905
2023-01-21 12:51:05.029749: step: 484/530, loss: 1.6355514162569307e-05
2023-01-21 12:51:06.130383: step: 488/530, loss: 0.02014312706887722
2023-01-21 12:51:07.242752: step: 492/530, loss: 0.0007257461547851562
2023-01-21 12:51:08.357715: step: 496/530, loss: 0.00020144581503700465
2023-01-21 12:51:09.470023: step: 500/530, loss: 0.0008329391130246222
2023-01-21 12:51:10.523039: step: 504/530, loss: 0.00021848677715752274
2023-01-21 12:51:11.644286: step: 508/530, loss: 0.0016999244689941406
2023-01-21 12:51:12.741193: step: 512/530, loss: 0.0022586823906749487
2023-01-21 12:51:13.820906: step: 516/530, loss: 2.8038026357535273e-05
2023-01-21 12:51:14.907726: step: 520/530, loss: 5.998611595714465e-05
2023-01-21 12:51:16.013171: step: 524/530, loss: 0.0001143455519923009
2023-01-21 12:51:17.158937: step: 528/530, loss: 0.004932880867272615
2023-01-21 12:51:18.306402: step: 532/530, loss: 0.020798780024051666
2023-01-21 12:51:19.426067: step: 536/530, loss: 0.009405707940459251
2023-01-21 12:51:20.527582: step: 540/530, loss: 0.010867644101381302
2023-01-21 12:51:21.655978: step: 544/530, loss: 0.007351684849709272
2023-01-21 12:51:22.783221: step: 548/530, loss: 0.0003692626778502017
2023-01-21 12:51:23.943584: step: 552/530, loss: 0.014289951883256435
2023-01-21 12:51:25.036730: step: 556/530, loss: 0.0012221335200592875
2023-01-21 12:51:26.150816: step: 560/530, loss: 0.004057884216308594
2023-01-21 12:51:27.274999: step: 564/530, loss: 0.02413156069815159
2023-01-21 12:51:28.388765: step: 568/530, loss: 0.0004905700916424394
2023-01-21 12:51:29.478166: step: 572/530, loss: 0.0001739501894917339
2023-01-21 12:51:30.564492: step: 576/530, loss: 0.002389621688053012
2023-01-21 12:51:31.646600: step: 580/530, loss: 0.0016176224453374743
2023-01-21 12:51:32.742111: step: 584/530, loss: 0.03457632288336754
2023-01-21 12:51:33.863286: step: 588/530, loss: 0.0020925523713231087
2023-01-21 12:51:34.939301: step: 592/530, loss: 3.337860107421875e-06
2023-01-21 12:51:36.041164: step: 596/530, loss: 7.638931856490672e-05
2023-01-21 12:51:37.140152: step: 600/530, loss: 0.037329718470573425
2023-01-21 12:51:38.251241: step: 604/530, loss: 0.0004299640713725239
2023-01-21 12:51:39.372014: step: 608/530, loss: 0.0006592273712158203
2023-01-21 12:51:40.487331: step: 612/530, loss: 0.0005601883167400956
2023-01-21 12:51:41.577844: step: 616/530, loss: 0.035027313977479935
2023-01-21 12:51:42.740179: step: 620/530, loss: 0.0012137056328356266
2023-01-21 12:51:43.850426: step: 624/530, loss: 2.880096508306451e-05
2023-01-21 12:51:44.947197: step: 628/530, loss: 8.668899681651965e-05
2023-01-21 12:51:46.061722: step: 632/530, loss: 0.027423381805419922
2023-01-21 12:51:47.181505: step: 636/530, loss: 0.0077041625045239925
2023-01-21 12:51:48.277323: step: 640/530, loss: 8.535385859431699e-06
2023-01-21 12:51:49.382435: step: 644/530, loss: 0.0006603241199627519
2023-01-21 12:51:50.471709: step: 648/530, loss: 0.009639739990234375
2023-01-21 12:51:51.586506: step: 652/530, loss: 0.0016557216877117753
2023-01-21 12:51:52.663134: step: 656/530, loss: 0.02028980292379856
2023-01-21 12:51:53.743006: step: 660/530, loss: 0.0034016608260571957
2023-01-21 12:51:54.824812: step: 664/530, loss: 0.003178215119987726
2023-01-21 12:51:55.939253: step: 668/530, loss: 0.02085561864078045
2023-01-21 12:51:57.038793: step: 672/530, loss: 0.00034213069011457264
2023-01-21 12:51:58.141944: step: 676/530, loss: 0.0011877060169354081
2023-01-21 12:51:59.216747: step: 680/530, loss: 2.0408631826285273e-05
2023-01-21 12:52:00.322832: step: 684/530, loss: 0.00039143560570664704
2023-01-21 12:52:01.454800: step: 688/530, loss: 0.0184478759765625
2023-01-21 12:52:02.552738: step: 692/530, loss: 0.0019886016380041838
2023-01-21 12:52:03.674494: step: 696/530, loss: 0.002204513642936945
2023-01-21 12:52:04.787211: step: 700/530, loss: 0.02226715162396431
2023-01-21 12:52:05.906502: step: 704/530, loss: 0.0016760826110839844
2023-01-21 12:52:07.035128: step: 708/530, loss: 0.0001087188720703125
2023-01-21 12:52:08.161728: step: 712/530, loss: 0.007320213597267866
2023-01-21 12:52:09.248386: step: 716/530, loss: 0.0002645254135131836
2023-01-21 12:52:10.338542: step: 720/530, loss: 2.86102294921875e-06
2023-01-21 12:52:11.411675: step: 724/530, loss: 0.000305366498650983
2023-01-21 12:52:12.517087: step: 728/530, loss: 0.0002894401550292969
2023-01-21 12:52:13.592277: step: 732/530, loss: 0.0028312685899436474
2023-01-21 12:52:14.673998: step: 736/530, loss: 0.009303283877670765
2023-01-21 12:52:15.767541: step: 740/530, loss: 0.0020860673394054174
2023-01-21 12:52:16.874324: step: 744/530, loss: 0.004052543547004461
2023-01-21 12:52:17.987694: step: 748/530, loss: 0.09322519600391388
2023-01-21 12:52:19.076472: step: 752/530, loss: 0.0005322456709109247
2023-01-21 12:52:20.202968: step: 756/530, loss: 0.015447044745087624
2023-01-21 12:52:21.280749: step: 760/530, loss: 0.00033173561678268015
2023-01-21 12:52:22.431189: step: 764/530, loss: 0.06259326636791229
2023-01-21 12:52:23.530660: step: 768/530, loss: 0.011116600595414639
2023-01-21 12:52:24.630605: step: 772/530, loss: 0.041582491248846054
2023-01-21 12:52:25.713617: step: 776/530, loss: 0.4507943391799927
2023-01-21 12:52:26.825830: step: 780/530, loss: 0.0004926681285724044
2023-01-21 12:52:27.928734: step: 784/530, loss: 5.4359438763640355e-06
2023-01-21 12:52:29.040789: step: 788/530, loss: 0.014278173446655273
2023-01-21 12:52:30.174691: step: 792/530, loss: 0.004047298338264227
2023-01-21 12:52:31.285054: step: 796/530, loss: 0.0006560325855389237
2023-01-21 12:52:32.395505: step: 800/530, loss: 0.005858230870217085
2023-01-21 12:52:33.502653: step: 804/530, loss: 0.0016461373306810856
2023-01-21 12:52:34.598499: step: 808/530, loss: 0.025136232376098633
2023-01-21 12:52:35.725517: step: 812/530, loss: 2.6035308110294864e-05
2023-01-21 12:52:36.829573: step: 816/530, loss: 0.007239818572998047
2023-01-21 12:52:37.965632: step: 820/530, loss: 0.0034332750365138054
2023-01-21 12:52:39.100619: step: 824/530, loss: 2.727508581301663e-05
2023-01-21 12:52:40.179031: step: 828/530, loss: 4.8923491704044864e-05
2023-01-21 12:52:41.276842: step: 832/530, loss: 0.0041336058638989925
2023-01-21 12:52:42.387601: step: 836/530, loss: 0.027501869946718216
2023-01-21 12:52:43.504073: step: 840/530, loss: 0.06568918377161026
2023-01-21 12:52:44.599360: step: 844/530, loss: 0.014821053482592106
2023-01-21 12:52:45.715656: step: 848/530, loss: 0.019756508991122246
2023-01-21 12:52:46.834606: step: 852/530, loss: 1.220703143189894e-05
2023-01-21 12:52:47.939167: step: 856/530, loss: 0.0004754066758323461
2023-01-21 12:52:49.048354: step: 860/530, loss: 0.0005312919383868575
2023-01-21 12:52:50.166099: step: 864/530, loss: 1.888275073724799e-05
2023-01-21 12:52:51.267058: step: 868/530, loss: 3.99589553126134e-05
2023-01-21 12:52:52.387969: step: 872/530, loss: 0.0025051117409020662
2023-01-21 12:52:53.471568: step: 876/530, loss: 0.0011125088203698397
2023-01-21 12:52:54.581678: step: 880/530, loss: 0.016980934888124466
2023-01-21 12:52:55.719053: step: 884/530, loss: 0.030041933059692383
2023-01-21 12:52:56.783271: step: 888/530, loss: 0.0027034759987145662
2023-01-21 12:52:57.881515: step: 892/530, loss: 0.0003354072687216103
2023-01-21 12:52:58.967126: step: 896/530, loss: 0.003802680876106024
2023-01-21 12:53:00.070507: step: 900/530, loss: 0.0007093430031090975
2023-01-21 12:53:01.194557: step: 904/530, loss: 0.0005811214214190841
2023-01-21 12:53:02.298312: step: 908/530, loss: 8.449554297840223e-05
2023-01-21 12:53:03.461109: step: 912/530, loss: 0.001377964043058455
2023-01-21 12:53:04.545956: step: 916/530, loss: 0.04289431497454643
2023-01-21 12:53:05.638358: step: 920/530, loss: 4.0817263652570546e-05
2023-01-21 12:53:06.767402: step: 924/530, loss: 0.040535736829042435
2023-01-21 12:53:07.876938: step: 928/530, loss: 0.008727455511689186
2023-01-21 12:53:08.958226: step: 932/530, loss: 0.003745126770809293
2023-01-21 12:53:10.079523: step: 936/530, loss: -2.956390289909905e-06
2023-01-21 12:53:11.165555: step: 940/530, loss: 0.0005401611560955644
2023-01-21 12:53:12.248766: step: 944/530, loss: 0.0032356262672692537
2023-01-21 12:53:13.342105: step: 948/530, loss: 0.00028362273587845266
2023-01-21 12:53:14.435084: step: 952/530, loss: 0.0003520965401548892
2023-01-21 12:53:15.504035: step: 956/530, loss: 0.036427877843379974
2023-01-21 12:53:16.592065: step: 960/530, loss: 3.075599670410156e-05
2023-01-21 12:53:17.688000: step: 964/530, loss: 0.03636689484119415
2023-01-21 12:53:18.764006: step: 968/530, loss: 0.0015252113807946444
2023-01-21 12:53:19.825595: step: 972/530, loss: 0.0008503437275066972
2023-01-21 12:53:20.926299: step: 976/530, loss: 0.026938581839203835
2023-01-21 12:53:22.050220: step: 980/530, loss: 0.05759334936738014
2023-01-21 12:53:23.147269: step: 984/530, loss: 0.0029325485229492188
2023-01-21 12:53:24.247651: step: 988/530, loss: 0.004162514582276344
2023-01-21 12:53:25.310809: step: 992/530, loss: 0.0004974007606506348
2023-01-21 12:53:26.419654: step: 996/530, loss: 0.0006010055658407509
2023-01-21 12:53:27.528655: step: 1000/530, loss: 0.0006549835088662803
2023-01-21 12:53:28.643783: step: 1004/530, loss: 0.04351158067584038
2023-01-21 12:53:29.766056: step: 1008/530, loss: 0.00028524399385787547
2023-01-21 12:53:30.864627: step: 1012/530, loss: 0.010936069302260876
2023-01-21 12:53:31.966491: step: 1016/530, loss: 0.003226327942684293
2023-01-21 12:53:33.054873: step: 1020/530, loss: 0.00013589859008789062
2023-01-21 12:53:34.175384: step: 1024/530, loss: 0.004448986146599054
2023-01-21 12:53:35.288589: step: 1028/530, loss: 0.0035955430939793587
2023-01-21 12:53:36.401314: step: 1032/530, loss: 4.854202416026965e-05
2023-01-21 12:53:37.490601: step: 1036/530, loss: 0.00025935174198821187
2023-01-21 12:53:38.591879: step: 1040/530, loss: 0.0266131404787302
2023-01-21 12:53:39.710193: step: 1044/530, loss: 3.0851362680550665e-05
2023-01-21 12:53:40.831573: step: 1048/530, loss: 5.092620995128527e-05
2023-01-21 12:53:41.915421: step: 1052/530, loss: 0.0040611266158521175
2023-01-21 12:53:43.034244: step: 1056/530, loss: 1.354217511106981e-05
2023-01-21 12:53:44.138563: step: 1060/530, loss: 3.981590270996094e-05
2023-01-21 12:53:45.260466: step: 1064/530, loss: 0.20756812393665314
2023-01-21 12:53:46.385680: step: 1068/530, loss: 0.0017080307006835938
2023-01-21 12:53:47.482020: step: 1072/530, loss: 0.0060065267607569695
2023-01-21 12:53:48.597451: step: 1076/530, loss: 3.471374657237902e-05
2023-01-21 12:53:49.716185: step: 1080/530, loss: 7.629394076502649e-07
2023-01-21 12:53:50.823687: step: 1084/530, loss: 0.062209080904722214
2023-01-21 12:53:51.957958: step: 1088/530, loss: 0.07628345489501953
2023-01-21 12:53:53.060581: step: 1092/530, loss: 9.231567673850805e-05
2023-01-21 12:53:54.144284: step: 1096/530, loss: 0.004822445102035999
2023-01-21 12:53:55.258152: step: 1100/530, loss: 0.0013984680408611894
2023-01-21 12:53:56.392237: step: 1104/530, loss: 0.0018266676925122738
2023-01-21 12:53:57.484482: step: 1108/530, loss: 4.882812572759576e-05
2023-01-21 12:53:58.608804: step: 1112/530, loss: 0.004096985328942537
2023-01-21 12:53:59.686719: step: 1116/530, loss: 0.006518650334328413
2023-01-21 12:54:00.803025: step: 1120/530, loss: 0.0011026383144780993
2023-01-21 12:54:01.931768: step: 1124/530, loss: 8.440018427791074e-05
2023-01-21 12:54:03.038452: step: 1128/530, loss: 8.283853821922094e-05
2023-01-21 12:54:04.174227: step: 1132/530, loss: 4.343986802268773e-05
2023-01-21 12:54:05.278800: step: 1136/530, loss: 0.0021999359596520662
2023-01-21 12:54:06.386258: step: 1140/530, loss: 0.019924068823456764
2023-01-21 12:54:07.463783: step: 1144/530, loss: 0.042476460337638855
2023-01-21 12:54:08.568995: step: 1148/530, loss: 0.00019769668870139867
2023-01-21 12:54:09.660615: step: 1152/530, loss: 0.0004432678106240928
2023-01-21 12:54:10.779924: step: 1156/530, loss: 0.062159352004528046
2023-01-21 12:54:11.894070: step: 1160/530, loss: 0.011827182956039906
2023-01-21 12:54:12.993783: step: 1164/530, loss: 0.0022527696564793587
2023-01-21 12:54:14.118622: step: 1168/530, loss: 1.9073486612342094e-07
2023-01-21 12:54:15.221418: step: 1172/530, loss: 0.0011508942116051912
2023-01-21 12:54:16.342234: step: 1176/530, loss: 0.003374099964275956
2023-01-21 12:54:17.423124: step: 1180/530, loss: 9.117126319324598e-05
2023-01-21 12:54:18.509765: step: 1184/530, loss: 0.6503921151161194
2023-01-21 12:54:19.626941: step: 1188/530, loss: 0.0009100913885049522
2023-01-21 12:54:20.707396: step: 1192/530, loss: 0.0002119064301950857
2023-01-21 12:54:21.801497: step: 1196/530, loss: 0.008825588971376419
2023-01-21 12:54:22.910024: step: 1200/530, loss: 0.08517579734325409
2023-01-21 12:54:24.021304: step: 1204/530, loss: 6.4373016357421875e-06
2023-01-21 12:54:25.117507: step: 1208/530, loss: 0.0017513275379315019
2023-01-21 12:54:26.204588: step: 1212/530, loss: 0.5070964694023132
2023-01-21 12:54:27.298953: step: 1216/530, loss: 0.0010450363624840975
2023-01-21 12:54:28.381093: step: 1220/530, loss: 0.0002019882231252268
2023-01-21 12:54:29.502497: step: 1224/530, loss: 0.0003076791763305664
2023-01-21 12:54:30.602256: step: 1228/530, loss: 0.002882242202758789
2023-01-21 12:54:31.707304: step: 1232/530, loss: 2.250671423098538e-05
2023-01-21 12:54:32.797942: step: 1236/530, loss: 3.9577484130859375e-05
2023-01-21 12:54:33.959496: step: 1240/530, loss: 0.00012664795212913305
2023-01-21 12:54:35.065730: step: 1244/530, loss: 0.002530813217163086
2023-01-21 12:54:36.155809: step: 1248/530, loss: 0.0033914565574377775
2023-01-21 12:54:37.269050: step: 1252/530, loss: 0.020035266876220703
2023-01-21 12:54:38.372212: step: 1256/530, loss: 1.5354156857938506e-05
2023-01-21 12:54:39.512254: step: 1260/530, loss: 3.814697322468419e-07
2023-01-21 12:54:40.638617: step: 1264/530, loss: 0.0004520416259765625
2023-01-21 12:54:41.766112: step: 1268/530, loss: 0.030242253094911575
2023-01-21 12:54:42.877228: step: 1272/530, loss: 0.0007990360027179122
2023-01-21 12:54:43.991036: step: 1276/530, loss: 0.00014200209989212453
2023-01-21 12:54:45.115211: step: 1280/530, loss: 0.006500435061752796
2023-01-21 12:54:46.211129: step: 1284/530, loss: 0.0013354301918298006
2023-01-21 12:54:47.301142: step: 1288/530, loss: 0.00023145676823332906
2023-01-21 12:54:48.393938: step: 1292/530, loss: 0.0027272223960608244
2023-01-21 12:54:49.475332: step: 1296/530, loss: 0.0027792933396995068
2023-01-21 12:54:50.565769: step: 1300/530, loss: 0.0002803802490234375
2023-01-21 12:54:51.683782: step: 1304/530, loss: 0.00017542838759254664
2023-01-21 12:54:52.790755: step: 1308/530, loss: 0.011533738113939762
2023-01-21 12:54:53.920892: step: 1312/530, loss: 3.5048744678497314
2023-01-21 12:54:55.047393: step: 1316/530, loss: 0.0529085174202919
2023-01-21 12:54:56.184811: step: 1320/530, loss: 0.0029927254654467106
2023-01-21 12:54:57.329140: step: 1324/530, loss: 0.0325622595846653
2023-01-21 12:54:58.452182: step: 1328/530, loss: 0.015258599072694778
2023-01-21 12:54:59.573756: step: 1332/530, loss: 0.01711559295654297
2023-01-21 12:55:00.696748: step: 1336/530, loss: 0.0004385948122944683
2023-01-21 12:55:01.810471: step: 1340/530, loss: 0.39757195115089417
2023-01-21 12:55:02.936814: step: 1344/530, loss: 0.001965141389518976
2023-01-21 12:55:04.029252: step: 1348/530, loss: 0.0014477253425866365
2023-01-21 12:55:05.153841: step: 1352/530, loss: 0.0031809809152036905
2023-01-21 12:55:06.259907: step: 1356/530, loss: 0.0006017684936523438
2023-01-21 12:55:07.404250: step: 1360/530, loss: 0.0034381865989416838
2023-01-21 12:55:08.514295: step: 1364/530, loss: 2.441406286379788e-05
2023-01-21 12:55:09.624150: step: 1368/530, loss: 0.007786208298057318
2023-01-21 12:55:10.745410: step: 1372/530, loss: 0.00016717911057639867
2023-01-21 12:55:11.855955: step: 1376/530, loss: 0.0016846656799316406
2023-01-21 12:55:12.961437: step: 1380/530, loss: 0.004592704586684704
2023-01-21 12:55:14.077724: step: 1384/530, loss: 0.0014440537197515368
2023-01-21 12:55:15.206231: step: 1388/530, loss: 0.0017663001781329513
2023-01-21 12:55:16.294212: step: 1392/530, loss: 0.00453681917861104
2023-01-21 12:55:17.410589: step: 1396/530, loss: 0.0002994537353515625
2023-01-21 12:55:18.502957: step: 1400/530, loss: 0.000209808349609375
2023-01-21 12:55:19.585228: step: 1404/530, loss: 0.0002300739288330078
2023-01-21 12:55:20.708801: step: 1408/530, loss: 0.09959588199853897
2023-01-21 12:55:21.813713: step: 1412/530, loss: 0.005264949519187212
2023-01-21 12:55:22.966737: step: 1416/530, loss: 0.002631664276123047
2023-01-21 12:55:24.116460: step: 1420/530, loss: 0.02011279948055744
2023-01-21 12:55:25.211193: step: 1424/530, loss: 0.0006235599867068231
2023-01-21 12:55:26.305813: step: 1428/530, loss: 0.00156660086940974
2023-01-21 12:55:27.414036: step: 1432/530, loss: 0.018874311819672585
2023-01-21 12:55:28.539811: step: 1436/530, loss: 1.5544890629826114e-05
2023-01-21 12:55:29.676016: step: 1440/530, loss: 0.0019668578170239925
2023-01-21 12:55:30.809018: step: 1444/530, loss: 0.0003955840948037803
2023-01-21 12:55:31.912599: step: 1448/530, loss: 0.0004201889387331903
2023-01-21 12:55:33.025574: step: 1452/530, loss: 0.022609233856201172
2023-01-21 12:55:34.110327: step: 1456/530, loss: 0.019643783569335938
2023-01-21 12:55:35.211828: step: 1460/530, loss: 0.015396405011415482
2023-01-21 12:55:36.344254: step: 1464/530, loss: 0.004237174987792969
2023-01-21 12:55:37.456594: step: 1468/530, loss: 2.899169885495212e-05
2023-01-21 12:55:38.547272: step: 1472/530, loss: 0.08381299674510956
2023-01-21 12:55:39.708002: step: 1476/530, loss: 0.041929055005311966
2023-01-21 12:55:40.835068: step: 1480/530, loss: 0.061078548431396484
2023-01-21 12:55:41.937635: step: 1484/530, loss: 0.009345054626464844
2023-01-21 12:55:43.032647: step: 1488/530, loss: 0.030644893646240234
2023-01-21 12:55:44.132636: step: 1492/530, loss: 0.004668998531997204
2023-01-21 12:55:45.254137: step: 1496/530, loss: 0.0002442359982524067
2023-01-21 12:55:46.338570: step: 1500/530, loss: 0.0003310203901492059
2023-01-21 12:55:47.447613: step: 1504/530, loss: 0.0008363723754882812
2023-01-21 12:55:48.538160: step: 1508/530, loss: 0.029625702649354935
2023-01-21 12:55:49.619107: step: 1512/530, loss: 0.0017625123728066683
2023-01-21 12:55:50.719037: step: 1516/530, loss: 0.005372428800910711
2023-01-21 12:55:51.838700: step: 1520/530, loss: 0.3130576014518738
2023-01-21 12:55:52.938240: step: 1524/530, loss: 0.00015444755263160914
2023-01-21 12:55:54.052991: step: 1528/530, loss: 0.024785803630948067
2023-01-21 12:55:55.178422: step: 1532/530, loss: 0.0010930061107501388
2023-01-21 12:55:56.255926: step: 1536/530, loss: 0.002026176545768976
2023-01-21 12:55:57.368720: step: 1540/530, loss: 0.001341152237728238
2023-01-21 12:55:58.463866: step: 1544/530, loss: 0.0007477760664187372
2023-01-21 12:55:59.578409: step: 1548/530, loss: 0.0006202697986736894
2023-01-21 12:56:00.688941: step: 1552/530, loss: 0.0037949562538415194
2023-01-21 12:56:01.795401: step: 1556/530, loss: 0.01739645004272461
2023-01-21 12:56:02.947054: step: 1560/530, loss: 0.0024330138694494963
2023-01-21 12:56:04.033102: step: 1564/530, loss: 0.00013990403385832906
2023-01-21 12:56:05.157087: step: 1568/530, loss: 0.0007499695057049394
2023-01-21 12:56:06.262347: step: 1572/530, loss: 0.03244819492101669
2023-01-21 12:56:07.391244: step: 1576/530, loss: 0.00025138852652162313
2023-01-21 12:56:08.480563: step: 1580/530, loss: -7.152561920520384e-08
2023-01-21 12:56:09.592833: step: 1584/530, loss: 0.0012388229370117188
2023-01-21 12:56:10.718711: step: 1588/530, loss: 0.031202031299471855
2023-01-21 12:56:11.812016: step: 1592/530, loss: 0.0011800766224041581
2023-01-21 12:56:12.933239: step: 1596/530, loss: 0.0004047393740620464
2023-01-21 12:56:14.023677: step: 1600/530, loss: 0.011413288302719593
2023-01-21 12:56:15.121414: step: 1604/530, loss: 0.0024421692360192537
2023-01-21 12:56:16.236650: step: 1608/530, loss: 0.00242195138707757
2023-01-21 12:56:17.337390: step: 1612/530, loss: 0.0018444061279296875
2023-01-21 12:56:18.451142: step: 1616/530, loss: 1.621246337890625e-05
2023-01-21 12:56:19.535255: step: 1620/530, loss: 0.024398326873779297
2023-01-21 12:56:20.637191: step: 1624/530, loss: 0.00043334963265806437
2023-01-21 12:56:21.728329: step: 1628/530, loss: 0.00022420883760787547
2023-01-21 12:56:22.859524: step: 1632/530, loss: 0.00014038085646461695
2023-01-21 12:56:23.972354: step: 1636/530, loss: 0.016608715057373047
2023-01-21 12:56:25.102738: step: 1640/530, loss: 0.012693596072494984
2023-01-21 12:56:26.190182: step: 1644/530, loss: 0.00014200209989212453
2023-01-21 12:56:27.275897: step: 1648/530, loss: 0.0008685112115927041
2023-01-21 12:56:28.351625: step: 1652/530, loss: 0.012342739850282669
2023-01-21 12:56:29.469663: step: 1656/530, loss: 0.011956882663071156
2023-01-21 12:56:30.590032: step: 1660/530, loss: 0.004529762081801891
2023-01-21 12:56:31.703235: step: 1664/530, loss: 0.005699109751731157
2023-01-21 12:56:32.795867: step: 1668/530, loss: 0.0001790046808309853
2023-01-21 12:56:33.908357: step: 1672/530, loss: 0.06953687220811844
2023-01-21 12:56:34.998424: step: 1676/530, loss: 0.0008713722345419228
2023-01-21 12:56:36.095142: step: 1680/530, loss: 0.031763460487127304
2023-01-21 12:56:37.228115: step: 1684/530, loss: 8.0108642578125e-05
2023-01-21 12:56:38.329657: step: 1688/530, loss: 0.004968118853867054
2023-01-21 12:56:39.417202: step: 1692/530, loss: 0.00033550261287018657
2023-01-21 12:56:40.520376: step: 1696/530, loss: 3.566742088878527e-05
2023-01-21 12:56:41.617178: step: 1700/530, loss: 0.003076171735301614
2023-01-21 12:56:42.702916: step: 1704/530, loss: 0.0001276016264455393
2023-01-21 12:56:43.818707: step: 1708/530, loss: 9.880065772449598e-05
2023-01-21 12:56:44.926173: step: 1712/530, loss: 0.00235672015696764
2023-01-21 12:56:46.038291: step: 1716/530, loss: 0.0002490997430868447
2023-01-21 12:56:47.175215: step: 1720/530, loss: 6.103516170696821e-06
2023-01-21 12:56:48.272060: step: 1724/530, loss: 2.613067590573337e-05
2023-01-21 12:56:49.373339: step: 1728/530, loss: 0.0014015198685228825
2023-01-21 12:56:50.520413: step: 1732/530, loss: 4.928111957269721e-05
2023-01-21 12:56:51.613064: step: 1736/530, loss: 0.055178169161081314
2023-01-21 12:56:52.744474: step: 1740/530, loss: 2.2792817617300898e-05
2023-01-21 12:56:53.830377: step: 1744/530, loss: 0.000164031982421875
2023-01-21 12:56:54.952689: step: 1748/530, loss: 0.0009350776672363281
2023-01-21 12:56:56.044887: step: 1752/530, loss: 0.00012502670870162547
2023-01-21 12:56:57.138746: step: 1756/530, loss: 0.00087738037109375
2023-01-21 12:56:58.237987: step: 1760/530, loss: 0.0022929192055016756
2023-01-21 12:56:59.337899: step: 1764/530, loss: 0.016465187072753906
2023-01-21 12:57:00.463111: step: 1768/530, loss: 0.0002925872977357358
2023-01-21 12:57:01.607814: step: 1772/530, loss: 0.03180332109332085
2023-01-21 12:57:02.694899: step: 1776/530, loss: 1.7309188478975557e-05
2023-01-21 12:57:03.821939: step: 1780/530, loss: 0.00043048858060501516
2023-01-21 12:57:04.909346: step: 1784/530, loss: 0.014838123694062233
2023-01-21 12:57:05.998108: step: 1788/530, loss: 5.73158249608241e-05
2023-01-21 12:57:07.073219: step: 1792/530, loss: 0.00015754700871184468
2023-01-21 12:57:08.192425: step: 1796/530, loss: 0.02205810695886612
2023-01-21 12:57:09.310327: step: 1800/530, loss: 0.002079200930893421
2023-01-21 12:57:10.419141: step: 1804/530, loss: 0.04273023456335068
2023-01-21 12:57:11.503212: step: 1808/530, loss: 0.0004676103708334267
2023-01-21 12:57:12.627479: step: 1812/530, loss: 0.006861209869384766
2023-01-21 12:57:13.727819: step: 1816/530, loss: 8.516311936546117e-05
2023-01-21 12:57:14.825056: step: 1820/530, loss: 0.0067656515166163445
2023-01-21 12:57:15.948965: step: 1824/530, loss: 0.028238391503691673
2023-01-21 12:57:17.078352: step: 1828/530, loss: 0.11601724475622177
2023-01-21 12:57:18.192853: step: 1832/530, loss: 0.0003273964102845639
2023-01-21 12:57:19.298652: step: 1836/530, loss: 0.018491197377443314
2023-01-21 12:57:20.417201: step: 1840/530, loss: 5.6838991440599784e-05
2023-01-21 12:57:21.502121: step: 1844/530, loss: 0.0017460347153246403
2023-01-21 12:57:22.610464: step: 1848/530, loss: 0.009456252679228783
2023-01-21 12:57:23.755152: step: 1852/530, loss: 1.980755090713501
2023-01-21 12:57:24.892787: step: 1856/530, loss: 0.00031957626924850047
2023-01-21 12:57:25.994388: step: 1860/530, loss: 3.223419116693549e-05
2023-01-21 12:57:27.110481: step: 1864/530, loss: 0.01775188557803631
2023-01-21 12:57:28.239899: step: 1868/530, loss: 0.0002731323183979839
2023-01-21 12:57:29.369636: step: 1872/530, loss: 0.029294587671756744
2023-01-21 12:57:30.476568: step: 1876/530, loss: 0.0009731292957440019
2023-01-21 12:57:31.646458: step: 1880/530, loss: 0.0014904976123943925
2023-01-21 12:57:32.755040: step: 1884/530, loss: 0.0049987793900072575
2023-01-21 12:57:33.875299: step: 1888/530, loss: 0.0008016586070880294
2023-01-21 12:57:34.966879: step: 1892/530, loss: 0.00014181138249114156
2023-01-21 12:57:36.074438: step: 1896/530, loss: 0.005658340640366077
2023-01-21 12:57:37.183860: step: 1900/530, loss: 9.5367431640625e-06
2023-01-21 12:57:38.311372: step: 1904/530, loss: 0.0009243011591024697
2023-01-21 12:57:39.433047: step: 1908/530, loss: 0.004503107164055109
2023-01-21 12:57:40.559852: step: 1912/530, loss: 0.017327118664979935
2023-01-21 12:57:41.666262: step: 1916/530, loss: 4.4155120122013614e-05
2023-01-21 12:57:42.752477: step: 1920/530, loss: 0.0004862785281147808
2023-01-21 12:57:43.844477: step: 1924/530, loss: 0.0007985115516930819
2023-01-21 12:57:44.938485: step: 1928/530, loss: 0.0027611732948571444
2023-01-21 12:57:46.055281: step: 1932/530, loss: 0.013783550821244717
2023-01-21 12:57:47.128661: step: 1936/530, loss: 0.0010929107666015625
2023-01-21 12:57:48.234945: step: 1940/530, loss: 0.052123069763183594
2023-01-21 12:57:49.319631: step: 1944/530, loss: 0.011940956115722656
2023-01-21 12:57:50.424450: step: 1948/530, loss: 0.000888824462890625
2023-01-21 12:57:51.534846: step: 1952/530, loss: 0.03435344994068146
2023-01-21 12:57:52.674960: step: 1956/530, loss: 0.025199031457304955
2023-01-21 12:57:53.787985: step: 1960/530, loss: 7.972717139637098e-05
2023-01-21 12:57:54.886759: step: 1964/530, loss: 3.4904482163256034e-05
2023-01-21 12:57:55.960539: step: 1968/530, loss: 0.0027645111549645662
2023-01-21 12:57:57.074637: step: 1972/530, loss: 0.0034851073287427425
2023-01-21 12:57:58.190646: step: 1976/530, loss: 0.0005037784576416016
2023-01-21 12:57:59.320146: step: 1980/530, loss: 9.13620024221018e-05
2023-01-21 12:58:00.449840: step: 1984/530, loss: 0.04556474834680557
2023-01-21 12:58:01.564663: step: 1988/530, loss: 7.667540921829641e-05
2023-01-21 12:58:02.727277: step: 1992/530, loss: 0.0006044387700967491
2023-01-21 12:58:03.843052: step: 1996/530, loss: 0.006947183515876532
2023-01-21 12:58:04.911651: step: 2000/530, loss: 0.0038581849075853825
2023-01-21 12:58:06.017405: step: 2004/530, loss: 1.106262243411038e-05
2023-01-21 12:58:07.116318: step: 2008/530, loss: 0.12032680958509445
2023-01-21 12:58:08.233238: step: 2012/530, loss: 5.731582859880291e-05
2023-01-21 12:58:09.341083: step: 2016/530, loss: 2.0027162008773303e-06
2023-01-21 12:58:10.433357: step: 2020/530, loss: 0.24131107330322266
2023-01-21 12:58:11.548211: step: 2024/530, loss: 0.030902672559022903
2023-01-21 12:58:12.643853: step: 2028/530, loss: 0.009600449353456497
2023-01-21 12:58:13.764797: step: 2032/530, loss: 0.0019876479636877775
2023-01-21 12:58:14.859819: step: 2036/530, loss: 0.03327293321490288
2023-01-21 12:58:15.974455: step: 2040/530, loss: 0.0004704475577455014
2023-01-21 12:58:17.064898: step: 2044/530, loss: 0.05720863491296768
2023-01-21 12:58:18.150674: step: 2048/530, loss: 6.628036499023438e-05
2023-01-21 12:58:19.231717: step: 2052/530, loss: 0.011372094973921776
2023-01-21 12:58:20.355201: step: 2056/530, loss: 0.02214241214096546
2023-01-21 12:58:21.431981: step: 2060/530, loss: 0.006056881044059992
2023-01-21 12:58:22.558902: step: 2064/530, loss: 0.0035987854935228825
2023-01-21 12:58:23.673824: step: 2068/530, loss: 6.542205665027723e-05
2023-01-21 12:58:24.773828: step: 2072/530, loss: 2.689361645025201e-05
2023-01-21 12:58:25.914659: step: 2076/530, loss: 3.156661841785535e-05
2023-01-21 12:58:27.053364: step: 2080/530, loss: 0.0016698838444426656
2023-01-21 12:58:28.147393: step: 2084/530, loss: 0.0003034591500181705
2023-01-21 12:58:29.263990: step: 2088/530, loss: 0.06633710861206055
2023-01-21 12:58:30.365405: step: 2092/530, loss: 0.02072906494140625
2023-01-21 12:58:31.468440: step: 2096/530, loss: 0.005288505461066961
2023-01-21 12:58:32.571731: step: 2100/530, loss: 0.000419425981817767
2023-01-21 12:58:33.664967: step: 2104/530, loss: 0.007842540740966797
2023-01-21 12:58:34.760110: step: 2108/530, loss: 0.0012838364345952868
2023-01-21 12:58:35.840736: step: 2112/530, loss: 4.9209596909349784e-05
2023-01-21 12:58:36.950628: step: 2116/530, loss: 0.021673966199159622
2023-01-21 12:58:38.082328: step: 2120/530, loss: 0.0042476654052734375
==================================================
Loss: 0.026
--------------------
Dev: {'event': {'p': 0.593167701863354, 'r': 0.762982689747004, 'f1': 0.6674432149097262}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Test: {'event': {'p': 0.6428241808952468, 'r': 0.8117715617715617, 'f1': 0.7174864795261395}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Chinese: {'event': {'p': 0.581081081081081, 'r': 0.7962962962962963, 'f1': 0.6718749999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Korean: {'event': {'p': 0.5740740740740741, 'r': 0.49206349206349204, 'f1': 0.5299145299145299}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Russian: {'event': {'p': 0.4864864864864865, 'r': 0.5, 'f1': 0.4931506849315069}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Korean: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 12:59:17.556907: step: 4/530, loss: 1.1157990229548886e-05
2023-01-21 12:59:18.709435: step: 8/530, loss: 9.860992577159777e-05
2023-01-21 12:59:19.819816: step: 12/530, loss: 0.029435252770781517
2023-01-21 12:59:20.931517: step: 16/530, loss: 0.0015669644344598055
2023-01-21 12:59:22.045186: step: 20/530, loss: 0.0034360885620117188
2023-01-21 12:59:23.162892: step: 24/530, loss: 0.005712271202355623
2023-01-21 12:59:24.272148: step: 28/530, loss: 0.04923725500702858
2023-01-21 12:59:25.393754: step: 32/530, loss: 3.280639793956652e-05
2023-01-21 12:59:26.507324: step: 36/530, loss: 0.001529693603515625
2023-01-21 12:59:27.585782: step: 40/530, loss: 0.0001638412504689768
2023-01-21 12:59:28.663505: step: 44/530, loss: 0.0005210876697674394
2023-01-21 12:59:29.745742: step: 48/530, loss: 0.0004524230898823589
2023-01-21 12:59:30.850626: step: 52/530, loss: 0.00015468598576262593
2023-01-21 12:59:31.946931: step: 56/530, loss: 0.0006010055658407509
2023-01-21 12:59:33.074371: step: 60/530, loss: 7.724761962890625e-05
2023-01-21 12:59:34.172175: step: 64/530, loss: 0.0005258560413494706
2023-01-21 12:59:35.240532: step: 68/530, loss: 0.03582150861620903
2023-01-21 12:59:36.350527: step: 72/530, loss: 0.00010957718041026965
2023-01-21 12:59:37.462164: step: 76/530, loss: 0.002403736114501953
2023-01-21 12:59:38.591616: step: 80/530, loss: 7.724762326688506e-06
2023-01-21 12:59:39.687874: step: 84/530, loss: 0.00015163421630859375
2023-01-21 12:59:40.774003: step: 88/530, loss: 0.00011005401756847277
2023-01-21 12:59:41.877038: step: 92/530, loss: 0.010606384836137295
2023-01-21 12:59:42.974774: step: 96/530, loss: 0.0002722263161558658
2023-01-21 12:59:44.080700: step: 100/530, loss: 0.0005909919855184853
2023-01-21 12:59:45.200846: step: 104/530, loss: 0.02245931699872017
2023-01-21 12:59:46.293145: step: 108/530, loss: 0.001161321997642517
2023-01-21 12:59:47.403910: step: 112/530, loss: 0.012830877676606178
2023-01-21 12:59:48.503641: step: 116/530, loss: 0.0008175074472092092
2023-01-21 12:59:49.593045: step: 120/530, loss: 4.1484832763671875e-05
2023-01-21 12:59:50.706714: step: 124/530, loss: 0.0493658073246479
2023-01-21 12:59:51.819804: step: 128/530, loss: 0.013104820623993874
2023-01-21 12:59:52.902695: step: 132/530, loss: 8.096695091808215e-05
2023-01-21 12:59:54.018519: step: 136/530, loss: 0.00013017654418945312
2023-01-21 12:59:55.124578: step: 140/530, loss: 0.00047397613525390625
2023-01-21 12:59:56.222499: step: 144/530, loss: 6.8664553509734105e-06
2023-01-21 12:59:57.316430: step: 148/530, loss: 0.00032329559326171875
2023-01-21 12:59:58.428787: step: 152/530, loss: 0.00010070800635730848
2023-01-21 12:59:59.539662: step: 156/530, loss: 0.0018201827770099044
2023-01-21 13:00:00.657619: step: 160/530, loss: 0.046710968017578125
2023-01-21 13:00:01.746752: step: 164/530, loss: 0.0021920683793723583
2023-01-21 13:00:02.836992: step: 168/530, loss: 0.019598007202148438
2023-01-21 13:00:03.953843: step: 172/530, loss: 0.004548835568130016
2023-01-21 13:00:05.047799: step: 176/530, loss: 0.001579380128532648
2023-01-21 13:00:06.139575: step: 180/530, loss: 0.002179431961849332
2023-01-21 13:00:07.310322: step: 184/530, loss: 0.000134265428641811
2023-01-21 13:00:08.429150: step: 188/530, loss: 2.307891918462701e-05
2023-01-21 13:00:09.513531: step: 192/530, loss: -2.098083541568485e-06
2023-01-21 13:00:10.661606: step: 196/530, loss: 0.0005447388393804431
2023-01-21 13:00:11.753571: step: 200/530, loss: 0.17504529654979706
2023-01-21 13:00:12.864562: step: 204/530, loss: 0.009723090566694736
2023-01-21 13:00:13.931326: step: 208/530, loss: 0.005770397372543812
2023-01-21 13:00:15.051589: step: 212/530, loss: 4.138946678722277e-05
2023-01-21 13:00:16.135483: step: 216/530, loss: 0.01642761379480362
2023-01-21 13:00:17.256389: step: 220/530, loss: 0.0005374908214434981
2023-01-21 13:00:18.377911: step: 224/530, loss: 0.03251204267144203
2023-01-21 13:00:19.507358: step: 228/530, loss: 0.0005940437549725175
2023-01-21 13:00:20.613115: step: 232/530, loss: 4.863739013671875e-05
2023-01-21 13:00:21.743178: step: 236/530, loss: 0.017530251294374466
2023-01-21 13:00:22.837946: step: 240/530, loss: 0.00012540817260742188
2023-01-21 13:00:23.951722: step: 244/530, loss: 0.1345689743757248
2023-01-21 13:00:25.045603: step: 248/530, loss: 2.651214526849799e-05
2023-01-21 13:00:26.166642: step: 252/530, loss: 0.0005752563592977822
2023-01-21 13:00:27.277164: step: 256/530, loss: 0.003058910369873047
2023-01-21 13:00:28.355152: step: 260/530, loss: 0.02488093450665474
2023-01-21 13:00:29.512828: step: 264/530, loss: 0.0002075195370707661
2023-01-21 13:00:30.610064: step: 268/530, loss: 1.6403197150793858e-05
2023-01-21 13:00:31.709577: step: 272/530, loss: 0.004748344421386719
2023-01-21 13:00:32.804491: step: 276/530, loss: 0.0008715391159057617
2023-01-21 13:00:33.916591: step: 280/530, loss: 8.621215965831652e-05
2023-01-21 13:00:35.021213: step: 284/530, loss: 0.003278541611507535
2023-01-21 13:00:36.110691: step: 288/530, loss: 0.0012996196746826172
2023-01-21 13:00:37.197426: step: 292/530, loss: 0.004025363828986883
2023-01-21 13:00:38.312326: step: 296/530, loss: 0.0002639770682435483
2023-01-21 13:00:39.424128: step: 300/530, loss: 0.06756363064050674
2023-01-21 13:00:40.526903: step: 304/530, loss: 0.00033130645169876516
2023-01-21 13:00:41.628349: step: 308/530, loss: 1.8119812921213452e-06
2023-01-21 13:00:42.723271: step: 312/530, loss: 0.005310869310051203
2023-01-21 13:00:43.850738: step: 316/530, loss: 0.00027751922607421875
2023-01-21 13:00:44.956071: step: 320/530, loss: 4.549026198219508e-05
2023-01-21 13:00:46.072648: step: 324/530, loss: 0.0003276825009379536
2023-01-21 13:00:47.177537: step: 328/530, loss: 0.0001377105654682964
2023-01-21 13:00:48.299568: step: 332/530, loss: 0.034422874450683594
2023-01-21 13:00:49.395476: step: 336/530, loss: 0.004054450895637274
2023-01-21 13:00:50.499490: step: 340/530, loss: 0.04195096716284752
2023-01-21 13:00:51.595119: step: 344/530, loss: 0.01164169330149889
2023-01-21 13:00:52.741321: step: 348/530, loss: 6.008148375258315e-06
2023-01-21 13:00:53.841063: step: 352/530, loss: 0.003418350126594305
2023-01-21 13:00:54.954714: step: 356/530, loss: -3.957748049288057e-06
2023-01-21 13:00:56.060707: step: 360/530, loss: 0.0015730857849121094
2023-01-21 13:00:57.165282: step: 364/530, loss: 0.0019794225227087736
2023-01-21 13:00:58.265832: step: 368/530, loss: 5.474090721691027e-05
2023-01-21 13:00:59.338216: step: 372/530, loss: 0.000142955788760446
2023-01-21 13:01:00.431486: step: 376/530, loss: 0.014256859198212624
2023-01-21 13:01:01.537098: step: 380/530, loss: 0.013043498620390892
2023-01-21 13:01:02.638777: step: 384/530, loss: 0.015285111032426357
2023-01-21 13:01:03.747141: step: 388/530, loss: 0.00013070108252577484
2023-01-21 13:01:04.853421: step: 392/530, loss: 0.01378779485821724
2023-01-21 13:01:05.954753: step: 396/530, loss: 0.006086444947868586
2023-01-21 13:01:07.070976: step: 400/530, loss: 0.004956245422363281
2023-01-21 13:01:08.159472: step: 404/530, loss: 0.0001424789516022429
2023-01-21 13:01:09.287430: step: 408/530, loss: 0.00032224657479673624
2023-01-21 13:01:10.448168: step: 412/530, loss: 0.0006439209100790322
2023-01-21 13:01:11.536895: step: 416/530, loss: 0.006103229243308306
2023-01-21 13:01:12.647387: step: 420/530, loss: 0.00018939973961096257
2023-01-21 13:01:13.778019: step: 424/530, loss: 0.018399430438876152
2023-01-21 13:01:14.854768: step: 428/530, loss: 0.00026426315889693797
2023-01-21 13:01:15.936103: step: 432/530, loss: 0.034485433250665665
2023-01-21 13:01:17.063499: step: 436/530, loss: 0.00123853690456599
2023-01-21 13:01:18.186369: step: 440/530, loss: 0.0002925872977357358
2023-01-21 13:01:19.324259: step: 444/530, loss: 0.0002666473446879536
2023-01-21 13:01:20.419435: step: 448/530, loss: 0.0008953094366006553
2023-01-21 13:01:21.538437: step: 452/530, loss: 0.00030794143094681203
2023-01-21 13:01:22.646144: step: 456/530, loss: 6.532669431180693e-06
2023-01-21 13:01:23.746910: step: 460/530, loss: -1.0824202036019415e-05
2023-01-21 13:01:24.838873: step: 464/530, loss: 8.583068620282575e-07
2023-01-21 13:01:25.947721: step: 468/530, loss: 0.03253975138068199
2023-01-21 13:01:27.030915: step: 472/530, loss: 2.136230432370212e-05
2023-01-21 13:01:28.127117: step: 476/530, loss: 8.306503150379285e-05
2023-01-21 13:01:29.216809: step: 480/530, loss: 2.2506712411995977e-05
2023-01-21 13:01:30.296895: step: 484/530, loss: 0.012070560827851295
2023-01-21 13:01:31.400558: step: 488/530, loss: 0.00019397735013626516
2023-01-21 13:01:32.514315: step: 492/530, loss: 0.12563222646713257
2023-01-21 13:01:33.613254: step: 496/530, loss: 0.000109624867036473
2023-01-21 13:01:34.696667: step: 500/530, loss: -9.536688594380394e-08
2023-01-21 13:01:35.826817: step: 504/530, loss: 0.01101923082023859
2023-01-21 13:01:36.927334: step: 508/530, loss: 0.0004941940424032509
2023-01-21 13:01:38.035870: step: 512/530, loss: 0.00046367646427825093
2023-01-21 13:01:39.134632: step: 516/530, loss: 0.0035005570389330387
2023-01-21 13:01:40.227251: step: 520/530, loss: 0.06160468980669975
2023-01-21 13:01:41.346358: step: 524/530, loss: 0.08625183254480362
2023-01-21 13:01:42.448521: step: 528/530, loss: 0.006708526983857155
2023-01-21 13:01:43.590910: step: 532/530, loss: 0.008047866635024548
2023-01-21 13:01:44.730901: step: 536/530, loss: 0.0011442184913903475
2023-01-21 13:01:45.823242: step: 540/530, loss: 0.001378822373226285
2023-01-21 13:01:46.902904: step: 544/530, loss: 0.005866670981049538
2023-01-21 13:01:48.000278: step: 548/530, loss: 0.017339278012514114
2023-01-21 13:01:49.102435: step: 552/530, loss: 0.0013941765064373612
2023-01-21 13:01:50.191813: step: 556/530, loss: 0.04866056516766548
2023-01-21 13:01:51.284496: step: 560/530, loss: 0.12443151324987411
2023-01-21 13:01:52.422013: step: 564/530, loss: 0.0091705322265625
2023-01-21 13:01:53.559035: step: 568/530, loss: 0.015758037567138672
2023-01-21 13:01:54.664312: step: 572/530, loss: 0.004190015606582165
2023-01-21 13:01:55.760529: step: 576/530, loss: 0.0022509575355798006
2023-01-21 13:01:56.847511: step: 580/530, loss: 0.00527381943538785
2023-01-21 13:01:57.940859: step: 584/530, loss: 6.437301635742188e-05
2023-01-21 13:01:59.042873: step: 588/530, loss: 0.015719985589385033
2023-01-21 13:02:00.147111: step: 592/530, loss: 0.0040496825240552425
2023-01-21 13:02:01.261148: step: 596/530, loss: 0.00021363497944548726
2023-01-21 13:02:02.388042: step: 600/530, loss: 0.003868484403938055
2023-01-21 13:02:03.469148: step: 604/530, loss: 3.223419116693549e-05
2023-01-21 13:02:04.587634: step: 608/530, loss: 0.008206367492675781
2023-01-21 13:02:05.680487: step: 612/530, loss: 0.00392074603587389
2023-01-21 13:02:06.811275: step: 616/530, loss: 0.0008504867437295616
2023-01-21 13:02:07.909754: step: 620/530, loss: 6.809234764659777e-05
2023-01-21 13:02:09.001092: step: 624/530, loss: 0.0011110305786132812
2023-01-21 13:02:10.075926: step: 628/530, loss: -3.14712519866589e-06
2023-01-21 13:02:11.170326: step: 632/530, loss: 0.011076497845351696
2023-01-21 13:02:12.280789: step: 636/530, loss: 8.635521226096898e-05
2023-01-21 13:02:13.388130: step: 640/530, loss: 0.00038051605224609375
2023-01-21 13:02:14.501340: step: 644/530, loss: 0.0009580135811120272
2023-01-21 13:02:15.592954: step: 648/530, loss: 0.000466763973236084
2023-01-21 13:02:16.684399: step: 652/530, loss: 0.014777708798646927
2023-01-21 13:02:17.806526: step: 656/530, loss: 0.003245115280151367
2023-01-21 13:02:18.896084: step: 660/530, loss: 2.0885467165498994e-05
2023-01-21 13:02:19.997774: step: 664/530, loss: 3.8695336115779355e-05
2023-01-21 13:02:21.140187: step: 668/530, loss: 0.007199478335678577
2023-01-21 13:02:22.234780: step: 672/530, loss: 0.0011286735534667969
2023-01-21 13:02:23.335146: step: 676/530, loss: 0.00013570785813499242
2023-01-21 13:02:24.448961: step: 680/530, loss: 0.02729034423828125
2023-01-21 13:02:25.557943: step: 684/530, loss: 0.0005313873407430947
2023-01-21 13:02:26.660579: step: 688/530, loss: 0.004558372311294079
2023-01-21 13:02:27.766621: step: 692/530, loss: 0.0023105619475245476
2023-01-21 13:02:28.885545: step: 696/530, loss: 0.0005208969232626259
2023-01-21 13:02:29.976076: step: 700/530, loss: 0.007081508636474609
2023-01-21 13:02:31.059470: step: 704/530, loss: 6.923676119185984e-05
2023-01-21 13:02:32.164612: step: 708/530, loss: 0.0021877288818359375
2023-01-21 13:02:33.289529: step: 712/530, loss: 5.14984139954322e-06
2023-01-21 13:02:34.394730: step: 716/530, loss: 0.06427783519029617
2023-01-21 13:02:35.502156: step: 720/530, loss: 0.006396484561264515
2023-01-21 13:02:36.606811: step: 724/530, loss: 0.0006708145374432206
2023-01-21 13:02:37.717440: step: 728/530, loss: 0.0008666992071084678
2023-01-21 13:02:38.809992: step: 732/530, loss: 0.00407829275354743
2023-01-21 13:02:39.919913: step: 736/530, loss: 0.0016889572143554688
2023-01-21 13:02:41.002500: step: 740/530, loss: 6.0653688706224784e-05
2023-01-21 13:02:42.082120: step: 744/530, loss: 0.0006469726795330644
2023-01-21 13:02:43.185193: step: 748/530, loss: 5.507469177246094e-05
2023-01-21 13:02:44.281917: step: 752/530, loss: 0.025494765490293503
2023-01-21 13:02:45.386882: step: 756/530, loss: 0.0001260757417185232
2023-01-21 13:02:46.482733: step: 760/530, loss: 0.0004618644597940147
2023-01-21 13:02:47.583713: step: 764/530, loss: 4.38690176451928e-06
2023-01-21 13:02:48.706072: step: 768/530, loss: 0.037951089441776276
2023-01-21 13:02:49.829727: step: 772/530, loss: 0.011043357662856579
2023-01-21 13:02:50.988573: step: 776/530, loss: 0.002699947450309992
2023-01-21 13:02:52.139863: step: 780/530, loss: 0.0010293960804119706
2023-01-21 13:02:53.246338: step: 784/530, loss: 0.03637123107910156
2023-01-21 13:02:54.366803: step: 788/530, loss: 0.000865936279296875
2023-01-21 13:02:55.482886: step: 792/530, loss: 0.0012589097023010254
2023-01-21 13:02:56.590628: step: 796/530, loss: 9.331703040516004e-05
2023-01-21 13:02:57.715680: step: 800/530, loss: 0.01222838182002306
2023-01-21 13:02:58.797413: step: 804/530, loss: 0.0003603935183491558
2023-01-21 13:02:59.922793: step: 808/530, loss: 0.0033665657974779606
2023-01-21 13:03:01.029686: step: 812/530, loss: 0.04898262023925781
2023-01-21 13:03:02.109049: step: 816/530, loss: 0.0007745742332190275
2023-01-21 13:03:03.232103: step: 820/530, loss: 0.0017484665149822831
2023-01-21 13:03:04.303941: step: 824/530, loss: 1.5594067008350976e-05
2023-01-21 13:03:05.423929: step: 828/530, loss: 0.011928940191864967
2023-01-21 13:03:06.499765: step: 832/530, loss: 0.0004944801330566406
2023-01-21 13:03:07.594149: step: 836/530, loss: 0.08316879719495773
2023-01-21 13:03:08.690649: step: 840/530, loss: 0.00011520386033225805
2023-01-21 13:03:09.781902: step: 844/530, loss: 0.0023003576789051294
2023-01-21 13:03:10.923238: step: 848/530, loss: 0.0009042262681759894
2023-01-21 13:03:12.028470: step: 852/530, loss: 0.02319011092185974
2023-01-21 13:03:13.115309: step: 856/530, loss: 2.307891918462701e-05
2023-01-21 13:03:14.209300: step: 860/530, loss: 0.009898853488266468
2023-01-21 13:03:15.315183: step: 864/530, loss: 0.007693099789321423
2023-01-21 13:03:16.397016: step: 868/530, loss: 0.08891773223876953
2023-01-21 13:03:17.516799: step: 872/530, loss: 0.0014736176235601306
2023-01-21 13:03:18.622304: step: 876/530, loss: 0.0031101228669285774
2023-01-21 13:03:19.715864: step: 880/530, loss: 0.06769299507141113
2023-01-21 13:03:20.810107: step: 884/530, loss: 0.00031795501126907766
2023-01-21 13:03:21.920505: step: 888/530, loss: 1.144409225162235e-06
2023-01-21 13:03:23.003177: step: 892/530, loss: 0.0024682998191565275
2023-01-21 13:03:24.132520: step: 896/530, loss: 0.005889797117561102
2023-01-21 13:03:25.274062: step: 900/530, loss: 0.00019111634173896164
2023-01-21 13:03:26.387459: step: 904/530, loss: 2.19345088225964e-06
2023-01-21 13:03:27.489991: step: 908/530, loss: 9.51766996877268e-05
2023-01-21 13:03:28.589798: step: 912/530, loss: 0.0017923356499522924
2023-01-21 13:03:29.686582: step: 916/530, loss: 0.00038485525874421
2023-01-21 13:03:30.817405: step: 920/530, loss: 0.007113933563232422
2023-01-21 13:03:31.897832: step: 924/530, loss: 0.00019497872563079
2023-01-21 13:03:33.003534: step: 928/530, loss: -2.6702882678364404e-06
2023-01-21 13:03:34.132486: step: 932/530, loss: 0.008819389156997204
2023-01-21 13:03:35.239451: step: 936/530, loss: 8.907318260753527e-05
2023-01-21 13:03:36.319975: step: 940/530, loss: 0.0006539822206832469
2023-01-21 13:03:37.415106: step: 944/530, loss: 0.017255211248993874
2023-01-21 13:03:38.526332: step: 948/530, loss: 0.0143890380859375
2023-01-21 13:03:39.614448: step: 952/530, loss: 0.008497429080307484
2023-01-21 13:03:40.700046: step: 956/530, loss: 0.01560201682150364
2023-01-21 13:03:41.785548: step: 960/530, loss: 0.00018668174743652344
2023-01-21 13:03:42.872795: step: 964/530, loss: 0.0010456085437908769
2023-01-21 13:03:43.972174: step: 968/530, loss: 1.5258789289873675e-06
2023-01-21 13:03:45.076740: step: 972/530, loss: 0.00011358261690475047
2023-01-21 13:03:46.160379: step: 976/530, loss: 0.0005155563121661544
2023-01-21 13:03:47.227840: step: 980/530, loss: 0.0016478538746014237
2023-01-21 13:03:48.329092: step: 984/530, loss: 0.001124572823755443
2023-01-21 13:03:49.481287: step: 988/530, loss: 0.03444557264447212
2023-01-21 13:03:50.574753: step: 992/530, loss: 0.0025963785592466593
2023-01-21 13:03:51.694891: step: 996/530, loss: 0.0007981777307577431
2023-01-21 13:03:52.817946: step: 1000/530, loss: 2.28881845032447e-06
2023-01-21 13:03:53.942845: step: 1004/530, loss: 0.00042552949162200093
2023-01-21 13:03:55.039241: step: 1008/530, loss: 0.0015125274658203125
2023-01-21 13:03:56.150726: step: 1012/530, loss: 3.256797936046496e-05
2023-01-21 13:03:57.267736: step: 1016/530, loss: 0.0007802963373251259
2023-01-21 13:03:58.353088: step: 1020/530, loss: 0.037128545343875885
2023-01-21 13:03:59.467176: step: 1024/530, loss: 0.00014419556828215718
2023-01-21 13:04:00.558918: step: 1028/530, loss: 0.0001985549897653982
2023-01-21 13:04:01.670365: step: 1032/530, loss: 0.018280314281582832
2023-01-21 13:04:02.773862: step: 1036/530, loss: 0.005886650178581476
2023-01-21 13:04:03.878274: step: 1040/530, loss: 0.037924766540527344
2023-01-21 13:04:04.965938: step: 1044/530, loss: 1.1444091796875e-05
2023-01-21 13:04:06.072845: step: 1048/530, loss: 0.020010853186249733
2023-01-21 13:04:07.161542: step: 1052/530, loss: 0.0058193206787109375
2023-01-21 13:04:08.255716: step: 1056/530, loss: 0.018397904932498932
2023-01-21 13:04:09.442842: step: 1060/530, loss: 0.0002628326474223286
2023-01-21 13:04:10.554555: step: 1064/530, loss: 0.0003414154052734375
2023-01-21 13:04:11.655084: step: 1068/530, loss: 0.002363014267757535
2023-01-21 13:04:12.753191: step: 1072/530, loss: 6.923675391590223e-05
2023-01-21 13:04:13.854734: step: 1076/530, loss: 3.070831371587701e-05
2023-01-21 13:04:14.942351: step: 1080/530, loss: 0.0001294136163778603
2023-01-21 13:04:16.046359: step: 1084/530, loss: 3.3903121220646426e-05
2023-01-21 13:04:17.133884: step: 1088/530, loss: 0.0008142471197061241
2023-01-21 13:04:18.226121: step: 1092/530, loss: 0.0005998611450195312
2023-01-21 13:04:19.323630: step: 1096/530, loss: -1.6689301673977752e-07
2023-01-21 13:04:20.424604: step: 1100/530, loss: 0.02089834213256836
2023-01-21 13:04:21.540244: step: 1104/530, loss: 0.0013528346316888928
2023-01-21 13:04:22.640060: step: 1108/530, loss: 0.013146591372787952
2023-01-21 13:04:23.761448: step: 1112/530, loss: 0.014933396130800247
2023-01-21 13:04:24.877967: step: 1116/530, loss: 0.004085540771484375
2023-01-21 13:04:25.965626: step: 1120/530, loss: 0.00102148053701967
2023-01-21 13:04:27.076150: step: 1124/530, loss: 4.625320343620842e-06
2023-01-21 13:04:28.197490: step: 1128/530, loss: 1.544952465337701e-05
2023-01-21 13:04:29.292483: step: 1132/530, loss: 0.013423156924545765
2023-01-21 13:04:30.417166: step: 1136/530, loss: 0.02184591442346573
2023-01-21 13:04:31.513587: step: 1140/530, loss: 0.03049163706600666
2023-01-21 13:04:32.628228: step: 1144/530, loss: 0.0017245293129235506
2023-01-21 13:04:33.760609: step: 1148/530, loss: 0.019046783447265625
2023-01-21 13:04:34.895667: step: 1152/530, loss: 0.013104438781738281
2023-01-21 13:04:36.003876: step: 1156/530, loss: 1.7166138377433526e-06
2023-01-21 13:04:37.123870: step: 1160/530, loss: 0.07359505444765091
2023-01-21 13:04:38.263783: step: 1164/530, loss: 0.002857208251953125
2023-01-21 13:04:39.357070: step: 1168/530, loss: 0.01428766269236803
2023-01-21 13:04:40.478185: step: 1172/530, loss: 0.0001465797540731728
2023-01-21 13:04:41.631192: step: 1176/530, loss: 0.0024166107177734375
2023-01-21 13:04:42.737749: step: 1180/530, loss: 2.422332727292087e-05
2023-01-21 13:04:43.850582: step: 1184/530, loss: 0.0417386032640934
2023-01-21 13:04:44.968272: step: 1188/530, loss: 0.002197265625
2023-01-21 13:04:46.077031: step: 1192/530, loss: 0.006925869267433882
2023-01-21 13:04:47.181753: step: 1196/530, loss: 0.0008164405589923263
2023-01-21 13:04:48.307781: step: 1200/530, loss: 3.814697265625e-06
2023-01-21 13:04:49.458360: step: 1204/530, loss: 0.12293558567762375
2023-01-21 13:04:50.583016: step: 1208/530, loss: 0.021139884367585182
2023-01-21 13:04:51.704630: step: 1212/530, loss: 0.00037450791569426656
2023-01-21 13:04:52.795364: step: 1216/530, loss: 0.0002123355952790007
2023-01-21 13:04:53.877596: step: 1220/530, loss: 0.0006303787231445312
2023-01-21 13:04:54.986325: step: 1224/530, loss: 9.460449655307457e-05
2023-01-21 13:04:56.083034: step: 1228/530, loss: 0.005875611677765846
2023-01-21 13:04:57.172832: step: 1232/530, loss: 0.0003562927304301411
2023-01-21 13:04:58.306921: step: 1236/530, loss: 0.0016563415993005037
2023-01-21 13:04:59.426945: step: 1240/530, loss: 0.0020252226386219263
2023-01-21 13:05:00.552053: step: 1244/530, loss: 0.003129387041553855
2023-01-21 13:05:01.660947: step: 1248/530, loss: 2.6607514882925898e-05
2023-01-21 13:05:02.753903: step: 1252/530, loss: 8.678436279296875e-05
2023-01-21 13:05:03.852925: step: 1256/530, loss: 4.08649466407951e-05
2023-01-21 13:05:04.938735: step: 1260/530, loss: 0.00042705534724518657
2023-01-21 13:05:06.039481: step: 1264/530, loss: 0.00036196707515046
2023-01-21 13:05:07.171472: step: 1268/530, loss: 0.002379512647166848
2023-01-21 13:05:08.261122: step: 1272/530, loss: 0.00021018982806708664
2023-01-21 13:05:09.360730: step: 1276/530, loss: 0.00013656615919899195
2023-01-21 13:05:10.490827: step: 1280/530, loss: 0.08921489864587784
2023-01-21 13:05:11.573263: step: 1284/530, loss: 0.5422126650810242
2023-01-21 13:05:12.674993: step: 1288/530, loss: 0.002125644823536277
2023-01-21 13:05:13.779821: step: 1292/530, loss: 0.0005640030140057206
2023-01-21 13:05:14.874913: step: 1296/530, loss: 5.7888031733455136e-05
2023-01-21 13:05:16.009076: step: 1300/530, loss: 0.0030906680040061474
2023-01-21 13:05:17.087301: step: 1304/530, loss: 0.0002229690580861643
2023-01-21 13:05:18.157114: step: 1308/530, loss: 0.022458650171756744
2023-01-21 13:05:19.280329: step: 1312/530, loss: 0.07224559783935547
2023-01-21 13:05:20.393588: step: 1316/530, loss: 0.002983188722282648
2023-01-21 13:05:21.499652: step: 1320/530, loss: 0.0032672882080078125
2023-01-21 13:05:22.605855: step: 1324/530, loss: 7.42912307032384e-05
2023-01-21 13:05:23.718300: step: 1328/530, loss: -1.277923547604587e-05
2023-01-21 13:05:24.815700: step: 1332/530, loss: 9.250640869140625e-05
2023-01-21 13:05:25.924088: step: 1336/530, loss: 0.0002472877677064389
2023-01-21 13:05:27.042605: step: 1340/530, loss: 0.0001846313534770161
2023-01-21 13:05:28.149668: step: 1344/530, loss: 0.0018259048229083419
2023-01-21 13:05:29.258371: step: 1348/530, loss: 0.015125465579330921
2023-01-21 13:05:30.381089: step: 1352/530, loss: 0.00010552406456554309
2023-01-21 13:05:31.471701: step: 1356/530, loss: 0.029802896082401276
2023-01-21 13:05:32.570813: step: 1360/530, loss: 0.009287071414291859
2023-01-21 13:05:33.720997: step: 1364/530, loss: 0.0016962051158770919
2023-01-21 13:05:34.851748: step: 1368/530, loss: 0.05070772022008896
2023-01-21 13:05:35.982508: step: 1372/530, loss: 0.0001220703125
2023-01-21 13:05:37.118155: step: 1376/530, loss: 0.0008016586070880294
2023-01-21 13:05:38.258432: step: 1380/530, loss: 0.12225323170423508
2023-01-21 13:05:39.376078: step: 1384/530, loss: 0.0001961708185262978
2023-01-21 13:05:40.486467: step: 1388/530, loss: 0.0018245697719976306
2023-01-21 13:05:41.595705: step: 1392/530, loss: 5.493163916980848e-05
2023-01-21 13:05:42.710177: step: 1396/530, loss: 3.62396240234375e-05
2023-01-21 13:05:43.815184: step: 1400/530, loss: 0.0017461300594732165
2023-01-21 13:05:44.920282: step: 1404/530, loss: 0.001063442206941545
2023-01-21 13:05:46.005895: step: 1408/530, loss: -2.6702882678364404e-06
2023-01-21 13:05:47.119740: step: 1412/530, loss: 2.2315980459097773e-05
2023-01-21 13:05:48.261889: step: 1416/530, loss: 0.15167808532714844
2023-01-21 13:05:49.378528: step: 1420/530, loss: 0.011538887396454811
2023-01-21 13:05:50.461108: step: 1424/530, loss: 0.02946019172668457
2023-01-21 13:05:51.616988: step: 1428/530, loss: 0.0005007744184695184
2023-01-21 13:05:52.748612: step: 1432/530, loss: 8.74519391800277e-05
2023-01-21 13:05:53.863470: step: 1436/530, loss: 0.007039070129394531
2023-01-21 13:05:54.973865: step: 1440/530, loss: 0.002211666200309992
2023-01-21 13:05:56.098432: step: 1444/530, loss: 0.002252769423648715
2023-01-21 13:05:57.218711: step: 1448/530, loss: 0.017626095563173294
2023-01-21 13:05:58.334133: step: 1452/530, loss: 0.04771079868078232
2023-01-21 13:05:59.435833: step: 1456/530, loss: 0.00021529197692871094
2023-01-21 13:06:00.516184: step: 1460/530, loss: 0.021303797140717506
2023-01-21 13:06:01.634808: step: 1464/530, loss: 0.021502112969756126
2023-01-21 13:06:02.735238: step: 1468/530, loss: 0.00021286010451149195
2023-01-21 13:06:03.820075: step: 1472/530, loss: 0.026974869892001152
2023-01-21 13:06:04.892189: step: 1476/530, loss: 0.03495273366570473
2023-01-21 13:06:06.013914: step: 1480/530, loss: 0.0011823654640465975
2023-01-21 13:06:07.131617: step: 1484/530, loss: 0.004939174745231867
2023-01-21 13:06:08.267134: step: 1488/530, loss: 0.035330772399902344
2023-01-21 13:06:09.358007: step: 1492/530, loss: 3.0231476557673886e-05
2023-01-21 13:06:10.483266: step: 1496/530, loss: 0.00087060930673033
2023-01-21 13:06:11.651085: step: 1500/530, loss: 0.001101589179597795
2023-01-21 13:06:12.810283: step: 1504/530, loss: 0.029007529839873314
2023-01-21 13:06:13.934243: step: 1508/530, loss: 4.138946678722277e-05
2023-01-21 13:06:15.040798: step: 1512/530, loss: 3.252029637224041e-05
2023-01-21 13:06:16.128276: step: 1516/530, loss: 0.005960798356682062
2023-01-21 13:06:17.246738: step: 1520/530, loss: 0.0016349792713299394
2023-01-21 13:06:18.371323: step: 1524/530, loss: 0.0010149001609534025
2023-01-21 13:06:19.458010: step: 1528/530, loss: 0.014621496200561523
2023-01-21 13:06:20.597080: step: 1532/530, loss: 6.217956251930445e-05
2023-01-21 13:06:21.696817: step: 1536/530, loss: 0.023708727210760117
2023-01-21 13:06:22.840351: step: 1540/530, loss: 0.009775924496352673
2023-01-21 13:06:23.958458: step: 1544/530, loss: 0.05845604091882706
2023-01-21 13:06:25.079109: step: 1548/530, loss: 0.0002932548522949219
2023-01-21 13:06:26.227012: step: 1552/530, loss: 0.0006668090936727822
2023-01-21 13:06:27.297759: step: 1556/530, loss: 0.004498577211052179
2023-01-21 13:06:28.418936: step: 1560/530, loss: 0.0006767273298464715
2023-01-21 13:06:29.547872: step: 1564/530, loss: 0.0002667427179403603
2023-01-21 13:06:30.653586: step: 1568/530, loss: 0.07163677364587784
2023-01-21 13:06:31.775960: step: 1572/530, loss: 0.0012791634071618319
2023-01-21 13:06:32.886227: step: 1576/530, loss: 0.01545562781393528
2023-01-21 13:06:33.998577: step: 1580/530, loss: 0.052401352673769
2023-01-21 13:06:35.098218: step: 1584/530, loss: 0.0019769668579101562
2023-01-21 13:06:36.209812: step: 1588/530, loss: 8.58306884765625e-06
2023-01-21 13:06:37.291360: step: 1592/530, loss: 0.07593629509210587
2023-01-21 13:06:38.397757: step: 1596/530, loss: 0.0024896622635424137
2023-01-21 13:06:39.520977: step: 1600/530, loss: 0.02565021626651287
2023-01-21 13:06:40.645468: step: 1604/530, loss: 0.04879875108599663
2023-01-21 13:06:41.734133: step: 1608/530, loss: 0.02191152609884739
2023-01-21 13:06:42.835851: step: 1612/530, loss: 0.0007493972661904991
2023-01-21 13:06:43.912481: step: 1616/530, loss: 6.86645489622606e-06
2023-01-21 13:06:45.013322: step: 1620/530, loss: 1.4066696166992188e-05
2023-01-21 13:06:46.134330: step: 1624/530, loss: 0.001956462860107422
2023-01-21 13:06:47.288483: step: 1628/530, loss: 0.0011052131885662675
2023-01-21 13:06:48.413258: step: 1632/530, loss: 3.008842577401083e-05
2023-01-21 13:06:49.543446: step: 1636/530, loss: 0.06111621856689453
2023-01-21 13:06:50.671055: step: 1640/530, loss: 0.0961918830871582
2023-01-21 13:06:51.751706: step: 1644/530, loss: 0.0366147980093956
2023-01-21 13:06:52.873558: step: 1648/530, loss: 0.00013875961303710938
2023-01-21 13:06:53.970769: step: 1652/530, loss: 0.00020456314086914062
2023-01-21 13:06:55.048743: step: 1656/530, loss: 0.00014743805513717234
2023-01-21 13:06:56.186646: step: 1660/530, loss: 0.026435280218720436
2023-01-21 13:06:57.311163: step: 1664/530, loss: 0.013074684888124466
2023-01-21 13:06:58.445935: step: 1668/530, loss: 0.0015708922874182463
2023-01-21 13:06:59.518729: step: 1672/530, loss: 7.028579420875758e-05
2023-01-21 13:07:00.624729: step: 1676/530, loss: 0.02171039581298828
2023-01-21 13:07:01.733278: step: 1680/530, loss: 0.00040426256600767374
2023-01-21 13:07:02.833150: step: 1684/530, loss: 0.0002588272327557206
2023-01-21 13:07:03.949543: step: 1688/530, loss: 0.016860390082001686
2023-01-21 13:07:05.076448: step: 1692/530, loss: 0.000698089599609375
2023-01-21 13:07:06.161780: step: 1696/530, loss: 0.00045871734619140625
2023-01-21 13:07:07.245691: step: 1700/530, loss: 0.010169411078095436
2023-01-21 13:07:08.370014: step: 1704/530, loss: 0.0022070587147027254
2023-01-21 13:07:09.457342: step: 1708/530, loss: 3.0040741876291577e-06
2023-01-21 13:07:10.565053: step: 1712/530, loss: 0.003843927290290594
2023-01-21 13:07:11.700303: step: 1716/530, loss: 0.027553748339414597
2023-01-21 13:07:12.806046: step: 1720/530, loss: 0.00010032654245151207
2023-01-21 13:07:13.908025: step: 1724/530, loss: 6.471872620750219e-05
2023-01-21 13:07:15.022502: step: 1728/530, loss: 0.012194443494081497
2023-01-21 13:07:16.138216: step: 1732/530, loss: 0.0004935264587402344
2023-01-21 13:07:17.239765: step: 1736/530, loss: 0.0001237869291799143
2023-01-21 13:07:18.326824: step: 1740/530, loss: 0.0044682505540549755
2023-01-21 13:07:19.439456: step: 1744/530, loss: 0.009037971496582031
2023-01-21 13:07:20.541569: step: 1748/530, loss: 0.0004528045537881553
2023-01-21 13:07:21.646723: step: 1752/530, loss: 0.008081579580903053
2023-01-21 13:07:22.740525: step: 1756/530, loss: 0.09083328396081924
2023-01-21 13:07:23.890458: step: 1760/530, loss: 9.212493750965223e-05
2023-01-21 13:07:24.989339: step: 1764/530, loss: 0.019496917724609375
2023-01-21 13:07:26.072480: step: 1768/530, loss: 0.06898327171802521
2023-01-21 13:07:27.187070: step: 1772/530, loss: 0.00013227462477516383
2023-01-21 13:07:28.296948: step: 1776/530, loss: 0.0004791736719198525
2023-01-21 13:07:29.405261: step: 1780/530, loss: 0.0001474380405852571
2023-01-21 13:07:30.501800: step: 1784/530, loss: 2.0122528439969756e-05
2023-01-21 13:07:31.600844: step: 1788/530, loss: 2.2888182229507947e-06
2023-01-21 13:07:32.721037: step: 1792/530, loss: 0.0007535934564657509
2023-01-21 13:07:33.820386: step: 1796/530, loss: 0.0009433747036382556
2023-01-21 13:07:34.942193: step: 1800/530, loss: 0.0003368377801962197
2023-01-21 13:07:36.066271: step: 1804/530, loss: 0.0006818771944381297
2023-01-21 13:07:37.154861: step: 1808/530, loss: 0.014892674051225185
2023-01-21 13:07:38.260951: step: 1812/530, loss: 1.8644332158146426e-05
2023-01-21 13:07:39.386503: step: 1816/530, loss: 0.01797199249267578
2023-01-21 13:07:40.520778: step: 1820/530, loss: 0.007116890046745539
2023-01-21 13:07:41.598174: step: 1824/530, loss: 0.00049591064453125
2023-01-21 13:07:42.732490: step: 1828/530, loss: 0.01926250569522381
2023-01-21 13:07:43.819226: step: 1832/530, loss: 0.002722835401073098
2023-01-21 13:07:44.927389: step: 1836/530, loss: 0.00034370424691587687
2023-01-21 13:07:46.016946: step: 1840/530, loss: 0.0001274108944926411
2023-01-21 13:07:47.148868: step: 1844/530, loss: 2.307891918462701e-05
2023-01-21 13:07:48.258231: step: 1848/530, loss: -5.722044988942798e-07
2023-01-21 13:07:49.366543: step: 1852/530, loss: 0.0025342940352857113
2023-01-21 13:07:50.449947: step: 1856/530, loss: 4.8446658183820546e-05
2023-01-21 13:07:51.556308: step: 1860/530, loss: 8.716583397472277e-05
2023-01-21 13:07:52.659883: step: 1864/530, loss: 0.018255997449159622
2023-01-21 13:07:53.757340: step: 1868/530, loss: 0.024232864379882812
2023-01-21 13:07:54.895305: step: 1872/530, loss: 0.0029203416779637337
2023-01-21 13:07:56.009679: step: 1876/530, loss: 8.077621896518394e-05
2023-01-21 13:07:57.135880: step: 1880/530, loss: 0.0002073288051178679
2023-01-21 13:07:58.232443: step: 1884/530, loss: 0.003910255618393421
2023-01-21 13:07:59.366892: step: 1888/530, loss: 0.00177345285192132
2023-01-21 13:08:00.489893: step: 1892/530, loss: 0.023700904101133347
2023-01-21 13:08:01.606002: step: 1896/530, loss: 0.008883285336196423
2023-01-21 13:08:02.730662: step: 1900/530, loss: 1.6689300537109375e-05
2023-01-21 13:08:03.843272: step: 1904/530, loss: 0.0009330749744549394
2023-01-21 13:08:04.952337: step: 1908/530, loss: 0.0004020690976176411
2023-01-21 13:08:06.084744: step: 1912/530, loss: 0.00103168492205441
2023-01-21 13:08:07.185451: step: 1916/530, loss: 2.288818359375e-05
2023-01-21 13:08:08.309573: step: 1920/530, loss: 0.0003933906555175781
2023-01-21 13:08:09.456959: step: 1924/530, loss: 0.008941269479691982
2023-01-21 13:08:10.568184: step: 1928/530, loss: 0.0024581910111010075
2023-01-21 13:08:11.655694: step: 1932/530, loss: 2.4890900022001006e-05
2023-01-21 13:08:12.772484: step: 1936/530, loss: 0.004462289623916149
2023-01-21 13:08:13.891478: step: 1940/530, loss: 0.01343617495149374
2023-01-21 13:08:14.985934: step: 1944/530, loss: 0.005720329470932484
2023-01-21 13:08:16.069800: step: 1948/530, loss: 2.19345088225964e-06
2023-01-21 13:08:17.169386: step: 1952/530, loss: 0.006926346104592085
2023-01-21 13:08:18.298125: step: 1956/530, loss: 0.049279119819402695
2023-01-21 13:08:19.429627: step: 1960/530, loss: 5.493163916980848e-05
2023-01-21 13:08:20.525982: step: 1964/530, loss: 0.0014108658069744706
2023-01-21 13:08:21.638253: step: 1968/530, loss: 0.012261772528290749
2023-01-21 13:08:22.770908: step: 1972/530, loss: 0.08735714107751846
2023-01-21 13:08:23.881328: step: 1976/530, loss: 0.0006707191932946444
2023-01-21 13:08:24.973255: step: 1980/530, loss: 0.00034465789212845266
2023-01-21 13:08:26.060773: step: 1984/530, loss: 0.00010528564598644152
2023-01-21 13:08:27.163575: step: 1988/530, loss: 0.007911848835647106
2023-01-21 13:08:28.249889: step: 1992/530, loss: 0.0011487960582599044
2023-01-21 13:08:29.348222: step: 1996/530, loss: 0.00415878277271986
2023-01-21 13:08:30.451535: step: 2000/530, loss: 0.000102996826171875
2023-01-21 13:08:31.552833: step: 2004/530, loss: 0.010316086001694202
2023-01-21 13:08:32.693612: step: 2008/530, loss: 0.0009088516235351562
2023-01-21 13:08:33.807351: step: 2012/530, loss: 0.03199787437915802
2023-01-21 13:08:34.931370: step: 2016/530, loss: 0.008266925811767578
2023-01-21 13:08:36.053579: step: 2020/530, loss: 0.0008687973022460938
2023-01-21 13:08:37.139428: step: 2024/530, loss: 0.007015037350356579
2023-01-21 13:08:38.250003: step: 2028/530, loss: 1.9073468138230965e-07
2023-01-21 13:08:39.378530: step: 2032/530, loss: 0.0005262374761514366
2023-01-21 13:08:40.506838: step: 2036/530, loss: 0.0008533478248864412
2023-01-21 13:08:41.620376: step: 2040/530, loss: 3.719329833984375e-05
2023-01-21 13:08:42.733243: step: 2044/530, loss: 0.020283222198486328
2023-01-21 13:08:43.848361: step: 2048/530, loss: 0.05246772617101669
2023-01-21 13:08:44.955230: step: 2052/530, loss: 9.72747784544481e-06
2023-01-21 13:08:46.070663: step: 2056/530, loss: 0.002403640653938055
2023-01-21 13:08:47.165779: step: 2060/530, loss: 0.007567406166344881
2023-01-21 13:08:48.271645: step: 2064/530, loss: 0.09182777255773544
2023-01-21 13:08:49.399935: step: 2068/530, loss: 4.158019874012098e-05
2023-01-21 13:08:50.511581: step: 2072/530, loss: 0.0003243446408305317
2023-01-21 13:08:51.626778: step: 2076/530, loss: 0.035164546221494675
2023-01-21 13:08:52.727113: step: 2080/530, loss: 0.001502227853052318
2023-01-21 13:08:53.847721: step: 2084/530, loss: 0.02115955390036106
2023-01-21 13:08:54.968932: step: 2088/530, loss: 1.144409225162235e-06
2023-01-21 13:08:56.081718: step: 2092/530, loss: 0.0027053833473473787
2023-01-21 13:08:57.209993: step: 2096/530, loss: 0.0006269455188885331
2023-01-21 13:08:58.299926: step: 2100/530, loss: 0.0007406235090456903
2023-01-21 13:08:59.411290: step: 2104/530, loss: 0.004179859068244696
2023-01-21 13:09:00.529383: step: 2108/530, loss: 0.012934589758515358
2023-01-21 13:09:01.648300: step: 2112/530, loss: 0.14338044822216034
2023-01-21 13:09:02.743820: step: 2116/530, loss: 9.632110959501006e-06
2023-01-21 13:09:03.885282: step: 2120/530, loss: 3.032684253412299e-05
==================================================
Loss: 0.012
--------------------
Dev: {'event': {'p': 0.5743639921722113, 'r': 0.7816245006657789, 'f1': 0.6621545403271291}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Test: {'event': {'p': 0.6367774237596723, 'r': 0.8152680652680653, 'f1': 0.7150523894709941}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Chinese: {'event': {'p': 0.5974025974025974, 'r': 0.8518518518518519, 'f1': 0.7022900763358778}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Korean: {'event': {'p': 0.6101694915254238, 'r': 0.5714285714285714, 'f1': 0.5901639344262296}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
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': 26}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Korean: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 13:09:43.458783: step: 4/530, loss: 0.0010096549522131681
2023-01-21 13:09:44.587781: step: 8/530, loss: 0.00012464524479582906
2023-01-21 13:09:45.678428: step: 12/530, loss: 0.0027126313652843237
2023-01-21 13:09:46.795765: step: 16/530, loss: 0.0016362189780920744
2023-01-21 13:09:47.897486: step: 20/530, loss: 0.0075286864303052425
2023-01-21 13:09:48.998177: step: 24/530, loss: 0.002128791995346546
2023-01-21 13:09:50.133364: step: 28/530, loss: 0.021907806396484375
2023-01-21 13:09:51.235834: step: 32/530, loss: 2.870559910661541e-05
2023-01-21 13:09:52.341901: step: 36/530, loss: 0.0001319885195698589
2023-01-21 13:09:53.424438: step: 40/530, loss: 0.035663798451423645
2023-01-21 13:09:54.538166: step: 44/530, loss: 0.0008243561023846269
2023-01-21 13:09:55.667810: step: 48/530, loss: 1.220703143189894e-05
2023-01-21 13:09:56.759574: step: 52/530, loss: 6.389617919921875e-05
2023-01-21 13:09:57.861101: step: 56/530, loss: 0.0003759383980650455
2023-01-21 13:09:58.967230: step: 60/530, loss: 0.004250288475304842
2023-01-21 13:10:00.082749: step: 64/530, loss: 0.0003361701965332031
2023-01-21 13:10:01.205833: step: 68/530, loss: 8.487702143611386e-05
2023-01-21 13:10:02.318544: step: 72/530, loss: 0.00279064173810184
2023-01-21 13:10:03.446494: step: 76/530, loss: 2.212524486822076e-05
2023-01-21 13:10:04.601198: step: 80/530, loss: 0.00035953521728515625
2023-01-21 13:10:05.700209: step: 84/530, loss: 0.00030746462289243937
2023-01-21 13:10:06.794650: step: 88/530, loss: 7.82012921263231e-06
2023-01-21 13:10:07.881081: step: 92/530, loss: 0.0002442359982524067
2023-01-21 13:10:08.991278: step: 96/530, loss: -1.5258790426742053e-06
2023-01-21 13:10:10.091706: step: 100/530, loss: 0.0008955001831054688
2023-01-21 13:10:11.187651: step: 104/530, loss: 0.0049835206009447575
2023-01-21 13:10:12.288753: step: 108/530, loss: 0.003570556640625
2023-01-21 13:10:13.388620: step: 112/530, loss: 5.435943421616685e-06
2023-01-21 13:10:14.533855: step: 116/530, loss: 0.005488777533173561
2023-01-21 13:10:15.675965: step: 120/530, loss: 0.7814303040504456
2023-01-21 13:10:16.787381: step: 124/530, loss: 0.012199878692626953
2023-01-21 13:10:17.853328: step: 128/530, loss: 0.0003070831298828125
2023-01-21 13:10:18.963430: step: 132/530, loss: 0.0020907402504235506
2023-01-21 13:10:20.091489: step: 136/530, loss: 0.008513259701430798
2023-01-21 13:10:21.198036: step: 140/530, loss: 0.00013484954251907766
2023-01-21 13:10:22.287158: step: 144/530, loss: 5.340576535672881e-05
2023-01-21 13:10:23.387901: step: 148/530, loss: 0.00028133392333984375
2023-01-21 13:10:24.482561: step: 152/530, loss: 0.0003326416190247983
2023-01-21 13:10:25.608592: step: 156/530, loss: 0.0008787155384197831
2023-01-21 13:10:26.759472: step: 160/530, loss: 2.4175644284696318e-05
2023-01-21 13:10:27.887893: step: 164/530, loss: 0.0069141392596066
2023-01-21 13:10:29.001026: step: 168/530, loss: 0.0025159837678074837
2023-01-21 13:10:30.106026: step: 172/530, loss: 1.564025842526462e-05
2023-01-21 13:10:31.240251: step: 176/530, loss: 2.8610230629055877e-07
2023-01-21 13:10:32.414125: step: 180/530, loss: 7.896422903286293e-05
2023-01-21 13:10:33.558212: step: 184/530, loss: 3.051757857974735e-06
2023-01-21 13:10:34.676391: step: 188/530, loss: 5.7983401347883046e-05
2023-01-21 13:10:35.795307: step: 192/530, loss: 0.0006700515514239669
2023-01-21 13:10:36.912045: step: 196/530, loss: -6.3896181927702855e-06
2023-01-21 13:10:38.049289: step: 200/530, loss: 3.280639793956652e-05
2023-01-21 13:10:39.189508: step: 204/530, loss: 1.1444094525359105e-06
2023-01-21 13:10:40.279700: step: 208/530, loss: 0.018450547009706497
2023-01-21 13:10:41.388656: step: 212/530, loss: 0.004146575927734375
2023-01-21 13:10:42.497113: step: 216/530, loss: 1.049041748046875e-05
2023-01-21 13:10:43.599430: step: 220/530, loss: 0.0004729270876850933
2023-01-21 13:10:44.712921: step: 224/530, loss: 0.02790956385433674
2023-01-21 13:10:45.812417: step: 228/530, loss: 0.07359971106052399
2023-01-21 13:10:46.889759: step: 232/530, loss: 0.008219147101044655
2023-01-21 13:10:47.988552: step: 236/530, loss: 9.632110959501006e-06
2023-01-21 13:10:49.115499: step: 240/530, loss: 0.0003383636649232358
2023-01-21 13:10:50.242944: step: 244/530, loss: 0.00019979476928710938
2023-01-21 13:10:51.358177: step: 248/530, loss: 0.000308799761114642
2023-01-21 13:10:52.496925: step: 252/530, loss: 0.0016082765068858862
2023-01-21 13:10:53.576633: step: 256/530, loss: 0.05128088220953941
2023-01-21 13:10:54.697441: step: 260/530, loss: 0.004553794860839844
2023-01-21 13:10:55.830398: step: 264/530, loss: 0.003433799836784601
2023-01-21 13:10:56.939745: step: 268/530, loss: 1.4209746950655244e-05
2023-01-21 13:10:58.022544: step: 272/530, loss: 0.00014991761418059468
2023-01-21 13:10:59.133753: step: 276/530, loss: 0.022023772820830345
2023-01-21 13:11:00.265292: step: 280/530, loss: 0.0008543014409951866
2023-01-21 13:11:01.382813: step: 284/530, loss: 0.007998799905180931
2023-01-21 13:11:02.487654: step: 288/530, loss: 1.3256072634248994e-05
2023-01-21 13:11:03.590012: step: 292/530, loss: 0.01682457886636257
2023-01-21 13:11:04.720311: step: 296/530, loss: 0.019149303436279297
2023-01-21 13:11:05.828664: step: 300/530, loss: 0.00010976791236316785
2023-01-21 13:11:06.923597: step: 304/530, loss: 0.0038158418610692024
2023-01-21 13:11:08.078804: step: 308/530, loss: 0.0002145290345652029
2023-01-21 13:11:09.212604: step: 312/530, loss: 0.00022230147442314774
2023-01-21 13:11:10.311496: step: 316/530, loss: 0.015474510379135609
2023-01-21 13:11:11.408565: step: 320/530, loss: 0.0010788918007165194
2023-01-21 13:11:12.507667: step: 324/530, loss: 0.00108509068377316
2023-01-21 13:11:13.654478: step: 328/530, loss: 0.015140295028686523
2023-01-21 13:11:14.788675: step: 332/530, loss: 0.001922607421875
2023-01-21 13:11:15.916177: step: 336/530, loss: 0.0005485534784384072
2023-01-21 13:11:17.067241: step: 340/530, loss: 0.0006781578413210809
2023-01-21 13:11:18.162302: step: 344/530, loss: -1.1157990229548886e-05
2023-01-21 13:11:19.254574: step: 348/530, loss: 0.0023775100708007812
2023-01-21 13:11:20.373226: step: 352/530, loss: 0.03296509012579918
2023-01-21 13:11:21.444256: step: 356/530, loss: 0.021395349875092506
2023-01-21 13:11:22.545306: step: 360/530, loss: 2.6798248654813506e-05
2023-01-21 13:11:23.636654: step: 364/530, loss: 0.005473041906952858
2023-01-21 13:11:24.731111: step: 368/530, loss: 0.002603721572086215
2023-01-21 13:11:25.863679: step: 372/530, loss: 0.005002403166145086
2023-01-21 13:11:26.951832: step: 376/530, loss: 0.00012664793757721782
2023-01-21 13:11:28.033422: step: 380/530, loss: 2.0408631826285273e-05
2023-01-21 13:11:29.132570: step: 384/530, loss: 3.051757857974735e-06
2023-01-21 13:11:30.235282: step: 388/530, loss: 0.0010314941173419356
2023-01-21 13:11:31.431342: step: 392/530, loss: 0.007472324185073376
2023-01-21 13:11:32.553041: step: 396/530, loss: 0.00023345947556663305
2023-01-21 13:11:33.665778: step: 400/530, loss: 0.008788490667939186
2023-01-21 13:11:34.773118: step: 404/530, loss: 1.9073486328125e-06
2023-01-21 13:11:35.906843: step: 408/530, loss: 0.012767791748046875
2023-01-21 13:11:37.023273: step: 412/530, loss: 0.0020271302200853825
2023-01-21 13:11:38.106914: step: 416/530, loss: 5.073547436040826e-05
2023-01-21 13:11:39.204797: step: 420/530, loss: 0.0002856254577636719
2023-01-21 13:11:40.300351: step: 424/530, loss: 0.016585826873779297
2023-01-21 13:11:41.421015: step: 428/530, loss: 0.06579236686229706
2023-01-21 13:11:42.556136: step: 432/530, loss: 0.00033884047297760844
2023-01-21 13:11:43.658702: step: 436/530, loss: 5.3882598876953125e-05
2023-01-21 13:11:44.762664: step: 440/530, loss: 5.340576535672881e-06
2023-01-21 13:11:45.866693: step: 444/530, loss: 0.01808910444378853
2023-01-21 13:11:46.981641: step: 448/530, loss: 0.0004714965762104839
2023-01-21 13:11:48.073358: step: 452/530, loss: 3.566742088878527e-05
2023-01-21 13:11:49.184240: step: 456/530, loss: 0.000152587890625
2023-01-21 13:11:50.271600: step: 460/530, loss: 0.0021878243423998356
2023-01-21 13:11:51.389823: step: 464/530, loss: 9.5367431640625e-05
2023-01-21 13:11:52.505910: step: 468/530, loss: 6.446838960982859e-05
2023-01-21 13:11:53.616772: step: 472/530, loss: 0.011886215768754482
2023-01-21 13:11:54.694973: step: 476/530, loss: 9.579658217262477e-05
2023-01-21 13:11:55.818017: step: 480/530, loss: 0.0019781114533543587
2023-01-21 13:11:56.936421: step: 484/530, loss: 2.6512147087487392e-05
2023-01-21 13:11:58.033656: step: 488/530, loss: 0.00591201800853014
2023-01-21 13:11:59.172775: step: 492/530, loss: 0.0002845764101948589
2023-01-21 13:12:00.262261: step: 496/530, loss: -2.6702878130890895e-06
2023-01-21 13:12:01.398942: step: 500/530, loss: 6.580352783203125e-05
2023-01-21 13:12:02.534077: step: 504/530, loss: 3.271103196311742e-05
2023-01-21 13:12:03.647453: step: 508/530, loss: 0.000152587890625
2023-01-21 13:12:04.748601: step: 512/530, loss: 0.002174949739128351
2023-01-21 13:12:05.853464: step: 516/530, loss: 0.2822275161743164
2023-01-21 13:12:06.986366: step: 520/530, loss: 0.0025876997970044613
2023-01-21 13:12:08.067321: step: 524/530, loss: 0.0001642227143747732
2023-01-21 13:12:09.169093: step: 528/530, loss: 0.023834228515625
2023-01-21 13:12:10.281542: step: 532/530, loss: 0.003063678741455078
2023-01-21 13:12:11.393978: step: 536/530, loss: 0.008183956146240234
2023-01-21 13:12:12.531136: step: 540/530, loss: 5.912781489314511e-06
2023-01-21 13:12:13.617293: step: 544/530, loss: 0.0005004882696084678
2023-01-21 13:12:14.727856: step: 548/530, loss: 1.029968279908644e-05
2023-01-21 13:12:15.823159: step: 552/530, loss: 0.007947539910674095
2023-01-21 13:12:16.941637: step: 556/530, loss: 0.0004594803031068295
2023-01-21 13:12:18.026611: step: 560/530, loss: 5.722044988942798e-07
2023-01-21 13:12:19.140481: step: 564/530, loss: 7.915496826171875e-05
2023-01-21 13:12:20.192651: step: 568/530, loss: 0.004147338680922985
2023-01-21 13:12:21.320519: step: 572/530, loss: 0.00020313262939453125
2023-01-21 13:12:22.413128: step: 576/530, loss: 0.0012911796802654862
2023-01-21 13:12:23.512009: step: 580/530, loss: 0.03221764788031578
2023-01-21 13:12:24.625357: step: 584/530, loss: 0.0023469924926757812
2023-01-21 13:12:25.703208: step: 588/530, loss: 0.0006121456390246749
2023-01-21 13:12:26.858236: step: 592/530, loss: -9.632110959501006e-06
2023-01-21 13:12:27.966098: step: 596/530, loss: 1.926422191900201e-05
2023-01-21 13:12:29.070729: step: 600/530, loss: 2.1362306142691523e-05
2023-01-21 13:12:30.147549: step: 604/530, loss: 0.000508213066495955
2023-01-21 13:12:31.294939: step: 608/530, loss: 8.96453857421875e-05
2023-01-21 13:12:32.390130: step: 612/530, loss: 5.292892637953628e-06
2023-01-21 13:12:33.502712: step: 616/530, loss: 0.003673267550766468
2023-01-21 13:12:34.613156: step: 620/530, loss: 0.01336822472512722
2023-01-21 13:12:35.731198: step: 624/530, loss: 0.0013370513916015625
2023-01-21 13:12:36.875087: step: 628/530, loss: 0.0011447906726971269
2023-01-21 13:12:38.014578: step: 632/530, loss: 5.14984139954322e-06
2023-01-21 13:12:39.158738: step: 636/530, loss: 0.00775146484375
2023-01-21 13:12:40.258755: step: 640/530, loss: 0.00015583037748001516
2023-01-21 13:12:41.384840: step: 644/530, loss: 0.0515630729496479
2023-01-21 13:12:42.491836: step: 648/530, loss: 0.00110034947283566
2023-01-21 13:12:43.600663: step: 652/530, loss: 0.0018465042812749743
2023-01-21 13:12:44.705003: step: 656/530, loss: 0.00016059876361396164
2023-01-21 13:12:45.807805: step: 660/530, loss: 0.007879448123276234
2023-01-21 13:12:46.934631: step: 664/530, loss: 9.965896606445312e-05
2023-01-21 13:12:48.039408: step: 668/530, loss: 3.4046173823298886e-05
2023-01-21 13:12:49.121492: step: 672/530, loss: 0.0016366958152502775
2023-01-21 13:12:50.227125: step: 676/530, loss: 1.0490417707842425e-06
2023-01-21 13:12:51.356163: step: 680/530, loss: 4.8351288569392636e-05
2023-01-21 13:12:52.447783: step: 684/530, loss: 2.4366378056583926e-05
2023-01-21 13:12:53.555403: step: 688/530, loss: 2.0122528439969756e-05
2023-01-21 13:12:54.658547: step: 692/530, loss: 0.02140960842370987
2023-01-21 13:12:55.774252: step: 696/530, loss: 1.9550323486328125e-05
2023-01-21 13:12:56.872878: step: 700/530, loss: 2.2411346435546875e-05
2023-01-21 13:12:57.956697: step: 704/530, loss: 0.004517364781349897
2023-01-21 13:12:59.046228: step: 708/530, loss: 0.004183006472885609
2023-01-21 13:13:00.127163: step: 712/530, loss: 0.00036644935607910156
2023-01-21 13:13:01.232329: step: 716/530, loss: 0.00021810532780364156
2023-01-21 13:13:02.339987: step: 720/530, loss: 3.643035961431451e-05
2023-01-21 13:13:03.457509: step: 724/530, loss: 0.00020451545424293727
2023-01-21 13:13:04.592074: step: 728/530, loss: 0.022845841944217682
2023-01-21 13:13:05.711176: step: 732/530, loss: 7.963180905790068e-06
2023-01-21 13:13:06.825562: step: 736/530, loss: 0.1205991730093956
2023-01-21 13:13:07.919642: step: 740/530, loss: 0.0001256942778127268
2023-01-21 13:13:09.035368: step: 744/530, loss: 0.0001307010679738596
2023-01-21 13:13:10.134112: step: 748/530, loss: 7.534027099609375e-05
2023-01-21 13:13:11.259771: step: 752/530, loss: 2.2888179955771193e-06
2023-01-21 13:13:12.363309: step: 756/530, loss: 0.0009071350214071572
2023-01-21 13:13:13.471405: step: 760/530, loss: 3.728866431629285e-05
2023-01-21 13:13:14.585896: step: 764/530, loss: 2.346038854739163e-05
2023-01-21 13:13:15.697049: step: 768/530, loss: 5.416870044427924e-05
2023-01-21 13:13:16.803505: step: 772/530, loss: 0.0007337570423260331
2023-01-21 13:13:17.893475: step: 776/530, loss: 0.0025575635954737663
2023-01-21 13:13:19.018878: step: 780/530, loss: 0.00017578601546119899
2023-01-21 13:13:20.111821: step: 784/530, loss: 0.0004924774402752519
2023-01-21 13:13:21.207958: step: 788/530, loss: 0.0032939910888671875
2023-01-21 13:13:22.323636: step: 792/530, loss: 0.0022895813453942537
2023-01-21 13:13:23.418021: step: 796/530, loss: 0.0001958847133209929
2023-01-21 13:13:24.525684: step: 800/530, loss: 4.10556785936933e-05
2023-01-21 13:13:25.656877: step: 804/530, loss: 0.019309282302856445
2023-01-21 13:13:26.775198: step: 808/530, loss: 0.03515605628490448
2023-01-21 13:13:27.892605: step: 812/530, loss: 0.0006406784523278475
2023-01-21 13:13:29.003119: step: 816/530, loss: 0.0013569355942308903
2023-01-21 13:13:30.150653: step: 820/530, loss: 0.019174957647919655
2023-01-21 13:13:31.253597: step: 824/530, loss: 9.5367431640625e-07
2023-01-21 13:13:32.358730: step: 828/530, loss: 0.0001541137753520161
2023-01-21 13:13:33.491026: step: 832/530, loss: 0.0008588791242800653
2023-01-21 13:13:34.595188: step: 836/530, loss: 0.00534133892506361
2023-01-21 13:13:35.693733: step: 840/530, loss: 0.0001928329438669607
2023-01-21 13:13:36.776209: step: 844/530, loss: 0.00010194779315497726
2023-01-21 13:13:37.925526: step: 848/530, loss: 2.57015235547442e-05
2023-01-21 13:13:39.058545: step: 852/530, loss: 0.0002609252987895161
2023-01-21 13:13:40.145704: step: 856/530, loss: 3.42369094141759e-05
2023-01-21 13:13:41.244875: step: 860/530, loss: 4.100799560546875e-05
2023-01-21 13:13:42.367176: step: 864/530, loss: 0.0002229690580861643
2023-01-21 13:13:43.490831: step: 868/530, loss: 0.001729011652059853
2023-01-21 13:13:44.607459: step: 872/530, loss: 0.0005086899036541581
2023-01-21 13:13:45.714508: step: 876/530, loss: 7.62939453125e-06
2023-01-21 13:13:46.811684: step: 880/530, loss: 0.00961842481046915
2023-01-21 13:13:47.924995: step: 884/530, loss: 0.00019292833167128265
2023-01-21 13:13:49.029887: step: 888/530, loss: 0.0027963637840002775
2023-01-21 13:13:50.128698: step: 892/530, loss: 0.0016664504073560238
2023-01-21 13:13:51.246568: step: 896/530, loss: 0.18164244294166565
2023-01-21 13:13:52.378414: step: 900/530, loss: 9.784698340808973e-05
2023-01-21 13:13:53.467195: step: 904/530, loss: 0.009173869155347347
2023-01-21 13:13:54.571592: step: 908/530, loss: 0.0009234428871423006
2023-01-21 13:13:55.703134: step: 912/530, loss: 0.0015529155498370528
2023-01-21 13:13:56.802379: step: 916/530, loss: 0.0032547474838793278
2023-01-21 13:13:57.926772: step: 920/530, loss: 0.004950427915900946
2023-01-21 13:13:59.022657: step: 924/530, loss: 0.00021562576876021922
2023-01-21 13:14:00.144460: step: 928/530, loss: 1.678466833254788e-05
2023-01-21 13:14:01.224044: step: 932/530, loss: 0.008465195074677467
2023-01-21 13:14:02.371706: step: 936/530, loss: 1.506805438111769e-05
2023-01-21 13:14:03.488708: step: 940/530, loss: 0.04710598289966583
2023-01-21 13:14:04.613128: step: 944/530, loss: 0.01031026802957058
2023-01-21 13:14:05.715460: step: 948/530, loss: 0.00243034353479743
2023-01-21 13:14:06.812871: step: 952/530, loss: 8.106232598947827e-06
2023-01-21 13:14:07.957682: step: 956/530, loss: 0.000247955322265625
2023-01-21 13:14:09.069117: step: 960/530, loss: 0.003259849501773715
2023-01-21 13:14:10.177354: step: 964/530, loss: 0.00048675539437681437
2023-01-21 13:14:11.275748: step: 968/530, loss: 9.422301809536293e-05
2023-01-21 13:14:12.364063: step: 972/530, loss: 3.814697265625e-05
2023-01-21 13:14:13.492456: step: 976/530, loss: 1.7452241081628017e-05
2023-01-21 13:14:14.607531: step: 980/530, loss: 0.02725839801132679
2023-01-21 13:14:15.728205: step: 984/530, loss: 0.0006204128148965538
2023-01-21 13:14:16.830555: step: 988/530, loss: 0.0010396003490313888
2023-01-21 13:14:17.948667: step: 992/530, loss: 0.0016298294067382812
2023-01-21 13:14:19.042256: step: 996/530, loss: 0.00018310546875
2023-01-21 13:14:20.184166: step: 1000/530, loss: 0.0004096984921488911
2023-01-21 13:14:21.309998: step: 1004/530, loss: 0.007838249206542969
2023-01-21 13:14:22.423580: step: 1008/530, loss: 9.059906005859375e-05
2023-01-21 13:14:23.529449: step: 1012/530, loss: 6.31332368357107e-05
2023-01-21 13:14:24.627153: step: 1016/530, loss: 0.004192305263131857
2023-01-21 13:14:25.731931: step: 1020/530, loss: 0.0005960464477539062
2023-01-21 13:14:26.866441: step: 1024/530, loss: 0.003124237060546875
2023-01-21 13:14:27.976210: step: 1028/530, loss: 0.035961344838142395
2023-01-21 13:14:29.088392: step: 1032/530, loss: 0.04003048315644264
2023-01-21 13:14:30.178969: step: 1036/530, loss: 0.01762714423239231
2023-01-21 13:14:31.286511: step: 1040/530, loss: 0.00048313141451217234
2023-01-21 13:14:32.403244: step: 1044/530, loss: 0.40052005648612976
2023-01-21 13:14:33.530581: step: 1048/530, loss: 0.0035814286675304174
2023-01-21 13:14:34.668736: step: 1052/530, loss: 0.09833412617444992
2023-01-21 13:14:35.772582: step: 1056/530, loss: 0.12969213724136353
2023-01-21 13:14:36.888143: step: 1060/530, loss: 0.00010242462303722277
2023-01-21 13:14:37.996129: step: 1064/530, loss: 4.944801185047254e-05
2023-01-21 13:14:39.115183: step: 1068/530, loss: 9.117127046920359e-05
2023-01-21 13:14:40.227201: step: 1072/530, loss: 0.0005752563010901213
2023-01-21 13:14:41.371240: step: 1076/530, loss: 0.00030269622220657766
2023-01-21 13:14:42.465664: step: 1080/530, loss: 4.100799560546875e-05
2023-01-21 13:14:43.574418: step: 1084/530, loss: 0.00019750595674850047
2023-01-21 13:14:44.694226: step: 1088/530, loss: 0.0004329681396484375
2023-01-21 13:14:45.806866: step: 1092/530, loss: 0.0002244949428131804
2023-01-21 13:14:46.914387: step: 1096/530, loss: 0.006389522459357977
2023-01-21 13:14:48.067738: step: 1100/530, loss: 0.06389942765235901
2023-01-21 13:14:49.178891: step: 1104/530, loss: 7.367134094238281e-05
2023-01-21 13:14:50.328511: step: 1108/530, loss: 5.836487252963707e-05
2023-01-21 13:14:51.429697: step: 1112/530, loss: 0.0010914802551269531
2023-01-21 13:14:52.514482: step: 1116/530, loss: 0.0007221222040243447
2023-01-21 13:14:53.625053: step: 1120/530, loss: 0.0002206802455475554
2023-01-21 13:14:54.727717: step: 1124/530, loss: 4.825591895496473e-05
2023-01-21 13:14:55.834173: step: 1128/530, loss: 0.004268741700798273
2023-01-21 13:14:56.908787: step: 1132/530, loss: 4.6253204345703125e-05
2023-01-21 13:14:58.003378: step: 1136/530, loss: 0.5552914142608643
2023-01-21 13:14:59.166339: step: 1140/530, loss: 0.0036377906799316406
2023-01-21 13:15:00.269619: step: 1144/530, loss: 5.0163271225756034e-05
2023-01-21 13:15:01.405569: step: 1148/530, loss: 0.0003183365042787045
2023-01-21 13:15:02.508095: step: 1152/530, loss: 0.0018349647289142013
2023-01-21 13:15:03.649849: step: 1156/530, loss: 2.9087066195643274e-06
2023-01-21 13:15:04.756940: step: 1160/530, loss: 0.009746838361024857
2023-01-21 13:15:05.868285: step: 1164/530, loss: 5.14984130859375e-05
2023-01-21 13:15:06.977119: step: 1168/530, loss: 0.0021588325034826994
2023-01-21 13:15:08.076568: step: 1172/530, loss: 0.018843458965420723
2023-01-21 13:15:09.168037: step: 1176/530, loss: 0.0001731872616801411
2023-01-21 13:15:10.319218: step: 1180/530, loss: 0.03321237489581108
2023-01-21 13:15:11.430253: step: 1184/530, loss: 3.3736228942871094e-05
2023-01-21 13:15:12.559256: step: 1188/530, loss: 0.06683731079101562
2023-01-21 13:15:13.661729: step: 1192/530, loss: 1.6498564946232364e-05
2023-01-21 13:15:14.773905: step: 1196/530, loss: 0.002348232315853238
2023-01-21 13:15:15.856575: step: 1200/530, loss: 0.003155350685119629
2023-01-21 13:15:16.961081: step: 1204/530, loss: 0.00011310577974654734
2023-01-21 13:15:18.051833: step: 1208/530, loss: 0.011898803524672985
2023-01-21 13:15:19.178721: step: 1212/530, loss: 0.00017099380784202367
2023-01-21 13:15:20.295394: step: 1216/530, loss: 9.078979201149195e-05
2023-01-21 13:15:21.401863: step: 1220/530, loss: 0.012598324567079544
2023-01-21 13:15:22.516689: step: 1224/530, loss: 4.272460864740424e-05
2023-01-21 13:15:23.619741: step: 1228/530, loss: 0.008247184567153454
2023-01-21 13:15:24.708020: step: 1232/530, loss: 2.3937225705594756e-05
2023-01-21 13:15:25.804285: step: 1236/530, loss: 8.344650268554688e-06
2023-01-21 13:15:26.895559: step: 1240/530, loss: 0.05277138203382492
2023-01-21 13:15:27.990561: step: 1244/530, loss: 0.024059487506747246
2023-01-21 13:15:29.072944: step: 1248/530, loss: 2.57492069977161e-06
2023-01-21 13:15:30.172425: step: 1252/530, loss: 0.03417501226067543
2023-01-21 13:15:31.263609: step: 1256/530, loss: 0.00791635550558567
2023-01-21 13:15:32.397681: step: 1260/530, loss: 0.0004467964172363281
2023-01-21 13:15:33.536846: step: 1264/530, loss: 0.00011672973778331652
2023-01-21 13:15:34.603217: step: 1268/530, loss: -1.754760705807712e-05
2023-01-21 13:15:35.693245: step: 1272/530, loss: 0.027198314666748047
2023-01-21 13:15:36.827777: step: 1276/530, loss: -3.986358569818549e-05
2023-01-21 13:15:37.930980: step: 1280/530, loss: 0.0018262863159179688
2023-01-21 13:15:39.056257: step: 1284/530, loss: 0.01218109205365181
2023-01-21 13:15:40.198707: step: 1288/530, loss: 0.015147591009736061
2023-01-21 13:15:41.306731: step: 1292/530, loss: 0.0001583099365234375
2023-01-21 13:15:42.394480: step: 1296/530, loss: 0.008032942190766335
2023-01-21 13:15:43.480071: step: 1300/530, loss: 0.03481235355138779
2023-01-21 13:15:44.560828: step: 1304/530, loss: 1.8787384760798886e-05
2023-01-21 13:15:45.682014: step: 1308/530, loss: 0.028191566467285156
2023-01-21 13:15:46.796359: step: 1312/530, loss: 3.4952165151480585e-05
2023-01-21 13:15:47.920669: step: 1316/530, loss: 0.002737045520916581
2023-01-21 13:15:49.024981: step: 1320/530, loss: 0.002050376031547785
2023-01-21 13:15:50.138606: step: 1324/530, loss: 0.04877433925867081
2023-01-21 13:15:51.214003: step: 1328/530, loss: 0.0007799148443154991
2023-01-21 13:15:52.346978: step: 1332/530, loss: 7.009506134636467e-06
2023-01-21 13:15:53.509881: step: 1336/530, loss: 0.007594585418701172
2023-01-21 13:15:54.615856: step: 1340/530, loss: 0.012871837243437767
2023-01-21 13:15:55.718430: step: 1344/530, loss: 0.0014665602939203382
2023-01-21 13:15:56.836515: step: 1348/530, loss: 0.0005381584051065147
2023-01-21 13:15:57.944385: step: 1352/530, loss: 0.000457763671875
2023-01-21 13:15:59.049848: step: 1356/530, loss: 0.0007632255437783897
2023-01-21 13:16:00.133366: step: 1360/530, loss: 0.0016248227329924703
2023-01-21 13:16:01.226180: step: 1364/530, loss: 0.024770306423306465
2023-01-21 13:16:02.332070: step: 1368/530, loss: 0.0315372459590435
2023-01-21 13:16:03.437911: step: 1372/530, loss: 0.01925830915570259
2023-01-21 13:16:04.544731: step: 1376/530, loss: 0.0003323554992675781
2023-01-21 13:16:05.643045: step: 1380/530, loss: 0.0029994964133948088
2023-01-21 13:16:06.771184: step: 1384/530, loss: 0.0006886005285196006
2023-01-21 13:16:07.896735: step: 1388/530, loss: 0.005381774622946978
2023-01-21 13:16:09.017727: step: 1392/530, loss: 0.004721260163933039
2023-01-21 13:16:10.120108: step: 1396/530, loss: 0.009737777523696423
2023-01-21 13:16:11.218211: step: 1400/530, loss: 0.0003829956112895161
2023-01-21 13:16:12.311075: step: 1404/530, loss: 0.00012092590623069555
2023-01-21 13:16:13.391061: step: 1408/530, loss: 1.602172778802924e-05
2023-01-21 13:16:14.502432: step: 1412/530, loss: 0.008525085635483265
2023-01-21 13:16:15.654295: step: 1416/530, loss: 0.0013958930503576994
2023-01-21 13:16:16.758825: step: 1420/530, loss: 0.014683819375932217
2023-01-21 13:16:17.846128: step: 1424/530, loss: 2.956390289909905e-06
2023-01-21 13:16:18.928315: step: 1428/530, loss: -2.86102294921875e-06
2023-01-21 13:16:20.011859: step: 1432/530, loss: 0.00031223296537064016
2023-01-21 13:16:21.111200: step: 1436/530, loss: 0.0008543968433514237
2023-01-21 13:16:22.214869: step: 1440/530, loss: 6.246566772460938e-05
2023-01-21 13:16:23.338906: step: 1444/530, loss: 2.467632293701172e-05
2023-01-21 13:16:24.465361: step: 1448/530, loss: 0.0001371383696096018
2023-01-21 13:16:25.557147: step: 1452/530, loss: 1.4305115314527939e-07
2023-01-21 13:16:26.659599: step: 1456/530, loss: 0.005004500970244408
2023-01-21 13:16:27.794007: step: 1460/530, loss: 2.470016261213459e-05
2023-01-21 13:16:28.914441: step: 1464/530, loss: 0.002196884248405695
2023-01-21 13:16:29.996683: step: 1468/530, loss: 0.00021629333787132055
2023-01-21 13:16:31.098098: step: 1472/530, loss: 6.713867333019152e-05
2023-01-21 13:16:32.192464: step: 1476/530, loss: 4.992485264665447e-05
2023-01-21 13:16:33.327640: step: 1480/530, loss: 1.4257431757869199e-05
2023-01-21 13:16:34.442343: step: 1484/530, loss: 5.5313107623078395e-06
2023-01-21 13:16:35.551303: step: 1488/530, loss: 0.005343055818229914
2023-01-21 13:16:36.657004: step: 1492/530, loss: 3.597736213123426e-05
2023-01-21 13:16:37.784760: step: 1496/530, loss: 0.023518182337284088
2023-01-21 13:16:38.866418: step: 1500/530, loss: 0.00028247834416106343
2023-01-21 13:16:39.983463: step: 1504/530, loss: 0.0004214286745991558
2023-01-21 13:16:41.091335: step: 1508/530, loss: 0.0031370639335364103
2023-01-21 13:16:42.207801: step: 1512/530, loss: 0.004721451085060835
2023-01-21 13:16:43.318838: step: 1516/530, loss: 0.0005359649658203125
2023-01-21 13:16:44.445247: step: 1520/530, loss: 0.004294776823371649
2023-01-21 13:16:45.544604: step: 1524/530, loss: 0.004687500651925802
2023-01-21 13:16:46.648096: step: 1528/530, loss: 0.00979461707174778
2023-01-21 13:16:47.782121: step: 1532/530, loss: 2.2411346435546875e-05
2023-01-21 13:16:48.868836: step: 1536/530, loss: 4.0531158447265625e-05
2023-01-21 13:16:50.016801: step: 1540/530, loss: 0.034278105944395065
2023-01-21 13:16:51.132779: step: 1544/530, loss: 0.06323222815990448
2023-01-21 13:16:52.285373: step: 1548/530, loss: 0.002895546145737171
2023-01-21 13:16:53.419408: step: 1552/530, loss: 0.0006244659307412803
2023-01-21 13:16:54.511355: step: 1556/530, loss: 0.005742931272834539
2023-01-21 13:16:55.648471: step: 1560/530, loss: 0.06888294219970703
2023-01-21 13:16:56.762377: step: 1564/530, loss: 0.0837133377790451
2023-01-21 13:16:57.880677: step: 1568/530, loss: 0.0010878562461584806
2023-01-21 13:16:59.010713: step: 1572/530, loss: 0.015175819396972656
2023-01-21 13:17:00.146219: step: 1576/530, loss: 0.0026901247911155224
2023-01-21 13:17:01.268880: step: 1580/530, loss: 2.6893614631262608e-05
2023-01-21 13:17:02.376117: step: 1584/530, loss: 0.010282636620104313
2023-01-21 13:17:03.522516: step: 1588/530, loss: 0.0028836249839514494
2023-01-21 13:17:04.620992: step: 1592/530, loss: 0.0038822172209620476
2023-01-21 13:17:05.721878: step: 1596/530, loss: 3.638267298811115e-05
2023-01-21 13:17:06.829438: step: 1600/530, loss: 0.0006497383001260459
2023-01-21 13:17:07.946156: step: 1604/530, loss: 0.0014176368713378906
2023-01-21 13:17:09.085442: step: 1608/530, loss: 0.013205445371568203
2023-01-21 13:17:10.190373: step: 1612/530, loss: 4.76837158203125e-06
2023-01-21 13:17:11.274963: step: 1616/530, loss: 0.00020632744417525828
2023-01-21 13:17:12.359739: step: 1620/530, loss: 0.00438957242295146
2023-01-21 13:17:13.455296: step: 1624/530, loss: 3.900527735822834e-05
2023-01-21 13:17:14.553170: step: 1628/530, loss: 0.008436108008027077
2023-01-21 13:17:15.671400: step: 1632/530, loss: 0.004226303193718195
2023-01-21 13:17:16.774622: step: 1636/530, loss: 0.001207637833431363
2023-01-21 13:17:17.925784: step: 1640/530, loss: 5.741119457525201e-05
2023-01-21 13:17:19.032222: step: 1644/530, loss: 0.0001947641430888325
2023-01-21 13:17:20.123389: step: 1648/530, loss: 0.0005242347833700478
2023-01-21 13:17:21.205352: step: 1652/530, loss: 8.106231689453125e-06
2023-01-21 13:17:22.336606: step: 1656/530, loss: 0.25929784774780273
2023-01-21 13:17:23.441426: step: 1660/530, loss: 0.0014763831859454513
2023-01-21 13:17:24.534864: step: 1664/530, loss: 0.010774183087050915
2023-01-21 13:17:25.638401: step: 1668/530, loss: 0.0017530441982671618
2023-01-21 13:17:26.771406: step: 1672/530, loss: 0.0024311065208166838
2023-01-21 13:17:27.903669: step: 1676/530, loss: 0.003326416015625
2023-01-21 13:17:28.991426: step: 1680/530, loss: 0.0018481732113286853
2023-01-21 13:17:30.085852: step: 1684/530, loss: 1.3542176020564511e-05
2023-01-21 13:17:31.171916: step: 1688/530, loss: 0.0009551048860885203
2023-01-21 13:17:32.273082: step: 1692/530, loss: 0.006049538031220436
2023-01-21 13:17:33.402356: step: 1696/530, loss: 2.212524486822076e-05
2023-01-21 13:17:34.521860: step: 1700/530, loss: 0.0004325866757426411
2023-01-21 13:17:35.621644: step: 1704/530, loss: 0.009316349402070045
2023-01-21 13:17:36.783492: step: 1708/530, loss: 0.039919376373291016
2023-01-21 13:17:37.878122: step: 1712/530, loss: 0.0015592575073242188
2023-01-21 13:17:38.999085: step: 1716/530, loss: 0.0003067016659770161
2023-01-21 13:17:40.101325: step: 1720/530, loss: 1.0776520866784267e-05
2023-01-21 13:17:41.222889: step: 1724/530, loss: 0.0004425048828125
2023-01-21 13:17:42.322505: step: 1728/530, loss: 0.00282115931622684
2023-01-21 13:17:43.428588: step: 1732/530, loss: 0.0003891944943461567
2023-01-21 13:17:44.565195: step: 1736/530, loss: 0.00961227435618639
2023-01-21 13:17:45.700594: step: 1740/530, loss: 0.0005256652948446572
2023-01-21 13:17:46.828911: step: 1744/530, loss: 0.0030451775528490543
2023-01-21 13:17:47.939111: step: 1748/530, loss: 0.0014260768657550216
2023-01-21 13:17:49.056263: step: 1752/530, loss: 8.821487426757812e-05
2023-01-21 13:17:50.180927: step: 1756/530, loss: 0.005660820286720991
2023-01-21 13:17:51.311710: step: 1760/530, loss: 0.0007322311867028475
2023-01-21 13:17:52.415633: step: 1764/530, loss: 0.030092239379882812
2023-01-21 13:17:53.526372: step: 1768/530, loss: 0.04018134996294975
2023-01-21 13:17:54.644628: step: 1772/530, loss: 0.0006579876062460244
2023-01-21 13:17:55.762147: step: 1776/530, loss: 2.1839141481905244e-05
2023-01-21 13:17:56.893023: step: 1780/530, loss: 1.6117095583467744e-05
2023-01-21 13:17:57.984265: step: 1784/530, loss: 0.0028345107566565275
2023-01-21 13:17:59.064466: step: 1788/530, loss: 0.0024671554565429688
2023-01-21 13:18:00.137853: step: 1792/530, loss: 0.00020122528076171875
2023-01-21 13:18:01.239081: step: 1796/530, loss: 0.0018091201782226562
2023-01-21 13:18:02.321593: step: 1800/530, loss: 0.004432964604347944
2023-01-21 13:18:03.450230: step: 1804/530, loss: 0.0003448486386332661
2023-01-21 13:18:04.579968: step: 1808/530, loss: 7.400513277389109e-05
2023-01-21 13:18:05.717369: step: 1812/530, loss: 0.011529112234711647
2023-01-21 13:18:06.804252: step: 1816/530, loss: 0.00010013580322265625
2023-01-21 13:18:07.911983: step: 1820/530, loss: 0.0007772445678710938
2023-01-21 13:18:09.032245: step: 1824/530, loss: 0.00011100769188487902
2023-01-21 13:18:10.158466: step: 1828/530, loss: 0.010199164971709251
2023-01-21 13:18:11.274848: step: 1832/530, loss: 0.0003094673447776586
2023-01-21 13:18:12.377469: step: 1836/530, loss: 0.016125153750181198
2023-01-21 13:18:13.500624: step: 1840/530, loss: 9.727478754939511e-06
2023-01-21 13:18:14.598317: step: 1844/530, loss: 3.280639793956652e-05
2023-01-21 13:18:15.751441: step: 1848/530, loss: 0.014998816885054111
2023-01-21 13:18:16.877136: step: 1852/530, loss: 0.02959260903298855
2023-01-21 13:18:18.027484: step: 1856/530, loss: 0.04317960888147354
2023-01-21 13:18:19.137496: step: 1860/530, loss: 2.422332727292087e-05
2023-01-21 13:18:20.251273: step: 1864/530, loss: 5.826950291520916e-05
2023-01-21 13:18:21.349837: step: 1868/530, loss: 0.02931070514023304
2023-01-21 13:18:22.438997: step: 1872/530, loss: 6.27517729299143e-05
2023-01-21 13:18:23.564919: step: 1876/530, loss: 5.841255187988281e-05
2023-01-21 13:18:24.682101: step: 1880/530, loss: 0.0016360284062102437
2023-01-21 13:18:25.804679: step: 1884/530, loss: 0.07107105106115341
2023-01-21 13:18:26.917470: step: 1888/530, loss: 0.007952404208481312
2023-01-21 13:18:28.013610: step: 1892/530, loss: 6.489753286587074e-05
2023-01-21 13:18:29.108802: step: 1896/530, loss: 9.722710092319176e-05
2023-01-21 13:18:30.199030: step: 1900/530, loss: 0.017777537927031517
2023-01-21 13:18:31.262231: step: 1904/530, loss: 0.00012693405733443797
2023-01-21 13:18:32.343047: step: 1908/530, loss: 0.00017786027456168085
2023-01-21 13:18:33.440211: step: 1912/530, loss: 0.0009184837690554559
2023-01-21 13:18:34.529579: step: 1916/530, loss: 0.0005043029668740928
2023-01-21 13:18:35.622424: step: 1920/530, loss: 0.0010626792209222913
2023-01-21 13:18:36.686092: step: 1924/530, loss: 0.0005792140727862716
2023-01-21 13:18:37.772538: step: 1928/530, loss: 0.0005459785461425781
2023-01-21 13:18:38.885020: step: 1932/530, loss: 0.00039095879765227437
2023-01-21 13:18:39.982134: step: 1936/530, loss: 6.718635268043727e-05
2023-01-21 13:18:41.077212: step: 1940/530, loss: 0.0009237289777956903
2023-01-21 13:18:42.200981: step: 1944/530, loss: 0.002246761228889227
2023-01-21 13:18:43.336985: step: 1948/530, loss: 0.0007325172773562372
2023-01-21 13:18:44.463685: step: 1952/530, loss: 0.051781561225652695
2023-01-21 13:18:45.538962: step: 1956/530, loss: 7.905960228526965e-05
2023-01-21 13:18:46.679709: step: 1960/530, loss: 0.08850985020399094
2023-01-21 13:18:47.812171: step: 1964/530, loss: 0.016207123175263405
2023-01-21 13:18:48.936638: step: 1968/530, loss: 0.0004255295207258314
2023-01-21 13:18:50.049421: step: 1972/530, loss: 3.719329833984375e-05
2023-01-21 13:18:51.117674: step: 1976/530, loss: 0.0003643989621195942
2023-01-21 13:18:52.234403: step: 1980/530, loss: 0.00019464493379928172
2023-01-21 13:18:53.356277: step: 1984/530, loss: 9.93728608591482e-05
2023-01-21 13:18:54.485416: step: 1988/530, loss: 0.027887536212801933
2023-01-21 13:18:55.610303: step: 1992/530, loss: 3.709793236339465e-05
2023-01-21 13:18:56.728455: step: 1996/530, loss: 0.2826540768146515
2023-01-21 13:18:57.821986: step: 2000/530, loss: 0.013715744018554688
2023-01-21 13:18:58.935317: step: 2004/530, loss: 0.0035851476714015007
2023-01-21 13:19:00.035563: step: 2008/530, loss: 0.03893556445837021
2023-01-21 13:19:01.127272: step: 2012/530, loss: 0.010373878292739391
2023-01-21 13:19:02.225495: step: 2016/530, loss: 0.3003626763820648
2023-01-21 13:19:03.329676: step: 2020/530, loss: 0.03634843975305557
2023-01-21 13:19:04.434000: step: 2024/530, loss: 0.00016622543625999242
2023-01-21 13:19:05.512756: step: 2028/530, loss: 0.0023660659790039062
2023-01-21 13:19:06.621277: step: 2032/530, loss: 8.945464651333168e-05
2023-01-21 13:19:07.730933: step: 2036/530, loss: 0.09421481937170029
2023-01-21 13:19:08.838796: step: 2040/530, loss: 0.006899738218635321
2023-01-21 13:19:09.974024: step: 2044/530, loss: 9.841918654274195e-05
2023-01-21 13:19:11.136200: step: 2048/530, loss: 0.00013942719670012593
2023-01-21 13:19:12.226060: step: 2052/530, loss: 0.020216751843690872
2023-01-21 13:19:13.314732: step: 2056/530, loss: 3.681182715808973e-05
2023-01-21 13:19:14.441354: step: 2060/530, loss: 0.03598308563232422
2023-01-21 13:19:15.564763: step: 2064/530, loss: 0.04095497354865074
2023-01-21 13:19:16.664597: step: 2068/530, loss: 2.593994213384576e-05
2023-01-21 13:19:17.784449: step: 2072/530, loss: 0.0004803657648153603
2023-01-21 13:19:18.906025: step: 2076/530, loss: 0.00043506623478606343
2023-01-21 13:19:19.986389: step: 2080/530, loss: 1.62124638336536e-06
2023-01-21 13:19:21.081124: step: 2084/530, loss: 0.0028630257584154606
2023-01-21 13:19:22.208605: step: 2088/530, loss: 0.007358551025390625
2023-01-21 13:19:23.331878: step: 2092/530, loss: 0.00019612311734817922
2023-01-21 13:19:24.438613: step: 2096/530, loss: 0.0027858735993504524
2023-01-21 13:19:25.565624: step: 2100/530, loss: 0.059932902455329895
2023-01-21 13:19:26.673292: step: 2104/530, loss: 0.016859544441103935
2023-01-21 13:19:27.809270: step: 2108/530, loss: 8.659363084007055e-05
2023-01-21 13:19:28.946860: step: 2112/530, loss: 3.728866431629285e-05
2023-01-21 13:19:30.060844: step: 2116/530, loss: 0.0197543166577816
2023-01-21 13:19:31.144616: step: 2120/530, loss: 0.0003839731216430664
==================================================
Loss: 0.013
--------------------
Dev: {'event': {'p': 0.5972369819341127, 'r': 0.748335552596538, 'f1': 0.6643026004728132}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Test: {'event': {'p': 0.6417633410672854, 'r': 0.8059440559440559, 'f1': 0.7145440454662877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Chinese: {'event': {'p': 0.5694444444444444, 'r': 0.7592592592592593, 'f1': 0.6507936507936508}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Korean: {'event': {'p': 0.8, 'r': 0.5079365079365079, 'f1': 0.6213592233009708}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Russian: {'event': {'p': 0.4146341463414634, 'r': 0.4722222222222222, 'f1': 0.4415584415584415}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Korean: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 13:20:10.646007: step: 4/530, loss: 0.0009229659917764366
2023-01-21 13:20:11.741478: step: 8/530, loss: 2.098083541568485e-06
2023-01-21 13:20:12.847527: step: 12/530, loss: 0.03904075548052788
2023-01-21 13:20:13.967277: step: 16/530, loss: 5.054474058852065e-06
2023-01-21 13:20:15.091231: step: 20/530, loss: 0.0012743950355798006
2023-01-21 13:20:16.211676: step: 24/530, loss: 0.0008071899646893144
2023-01-21 13:20:17.336952: step: 28/530, loss: 0.06114683300256729
2023-01-21 13:20:18.430404: step: 32/530, loss: 0.003858423326164484
2023-01-21 13:20:19.530095: step: 36/530, loss: 5.24044044141192e-05
2023-01-21 13:20:20.668454: step: 40/530, loss: 2.6702882678364404e-06
2023-01-21 13:20:21.785333: step: 44/530, loss: 0.0011781692737713456
2023-01-21 13:20:22.900390: step: 48/530, loss: 0.012569714337587357
2023-01-21 13:20:24.002667: step: 52/530, loss: 2.1743775505456142e-05
2023-01-21 13:20:25.089606: step: 56/530, loss: 0.0006578445318154991
2023-01-21 13:20:26.215756: step: 60/530, loss: 9.424686868442222e-05
2023-01-21 13:20:27.304617: step: 64/530, loss: 0.016581345349550247
2023-01-21 13:20:28.407362: step: 68/530, loss: 0.0005012512556277215
2023-01-21 13:20:29.517032: step: 72/530, loss: 0.004143428988754749
2023-01-21 13:20:30.614481: step: 76/530, loss: 0.003126526018604636
2023-01-21 13:20:31.719176: step: 80/530, loss: 0.0007184982532635331
2023-01-21 13:20:32.837309: step: 84/530, loss: 0.02431163750588894
2023-01-21 13:20:33.938125: step: 88/530, loss: 4.768372036778601e-06
2023-01-21 13:20:35.037639: step: 92/530, loss: 0.00013790131197310984
2023-01-21 13:20:36.186406: step: 96/530, loss: 4.47750098828692e-05
2023-01-21 13:20:37.299133: step: 100/530, loss: 0.0005819320795126259
2023-01-21 13:20:38.417715: step: 104/530, loss: 1.9359587895451114e-05
2023-01-21 13:20:39.543883: step: 108/530, loss: 0.002309608506038785
2023-01-21 13:20:40.650620: step: 112/530, loss: 0.0016008376842364669
2023-01-21 13:20:41.783055: step: 116/530, loss: 7.724761417193804e-06
2023-01-21 13:20:42.889199: step: 120/530, loss: 1.2302398317842744e-05
2023-01-21 13:20:44.019026: step: 124/530, loss: 0.006310272496193647
2023-01-21 13:20:45.128657: step: 128/530, loss: 6.237030174816027e-05
2023-01-21 13:20:46.223374: step: 132/530, loss: 0.03372449800372124
2023-01-21 13:20:47.344879: step: 136/530, loss: 0.027324484661221504
2023-01-21 13:20:48.442130: step: 140/530, loss: 0.000988864921964705
2023-01-21 13:20:49.566445: step: 144/530, loss: 0.01523289643228054
2023-01-21 13:20:50.689628: step: 148/530, loss: 0.04396963119506836
2023-01-21 13:20:51.760880: step: 152/530, loss: 0.00046916009159758687
2023-01-21 13:20:52.882027: step: 156/530, loss: 0.0020969391334801912
2023-01-21 13:20:53.949299: step: 160/530, loss: 0.00043907167855650187
2023-01-21 13:20:55.046727: step: 164/530, loss: 0.015908576548099518
2023-01-21 13:20:56.174322: step: 168/530, loss: 0.00022373201500158757
2023-01-21 13:20:57.250796: step: 172/530, loss: 1.4019013178767636e-05
2023-01-21 13:20:58.381548: step: 176/530, loss: 0.05156669765710831
2023-01-21 13:20:59.464168: step: 180/530, loss: 0.0002509593905415386
2023-01-21 13:21:00.568658: step: 184/530, loss: 0.0355280376970768
2023-01-21 13:21:01.685681: step: 188/530, loss: 2.517700158932712e-05
2023-01-21 13:21:02.837595: step: 192/530, loss: 0.006950664333999157
2023-01-21 13:21:03.951215: step: 196/530, loss: 0.0006632328731939197
2023-01-21 13:21:05.060316: step: 200/530, loss: 0.0006520271417684853
2023-01-21 13:21:06.154074: step: 204/530, loss: 0.0001260757417185232
2023-01-21 13:21:07.265285: step: 208/530, loss: 0.0016664505237713456
2023-01-21 13:21:08.371203: step: 212/530, loss: 0.0012594223953783512
2023-01-21 13:21:09.514109: step: 216/530, loss: 0.00030007361783646047
2023-01-21 13:21:10.611523: step: 220/530, loss: 0.02172260358929634
2023-01-21 13:21:11.717380: step: 224/530, loss: 0.00016040803166106343
2023-01-21 13:21:12.823221: step: 228/530, loss: 0.06179637834429741
2023-01-21 13:21:13.899113: step: 232/530, loss: 0.00010242462303722277
2023-01-21 13:21:14.995450: step: 236/530, loss: 3.3950807846849784e-05
2023-01-21 13:21:16.084740: step: 240/530, loss: 3.070831371587701e-05
2023-01-21 13:21:17.168623: step: 244/530, loss: 0.0029663562308996916
2023-01-21 13:21:18.271382: step: 248/530, loss: 0.005881762597709894
2023-01-21 13:21:19.372656: step: 252/530, loss: 0.006851959507912397
2023-01-21 13:21:20.476008: step: 256/530, loss: 0.001330566476099193
2023-01-21 13:21:21.565375: step: 260/530, loss: 0.00039005279541015625
2023-01-21 13:21:22.681834: step: 264/530, loss: 5.283355858409777e-05
2023-01-21 13:21:23.784249: step: 268/530, loss: 0.0006299972883425653
2023-01-21 13:21:24.872510: step: 272/530, loss: 9.918213436321821e-06
2023-01-21 13:21:25.980744: step: 276/530, loss: 0.017178155481815338
2023-01-21 13:21:27.093471: step: 280/530, loss: 0.00013809204392600805
2023-01-21 13:21:28.227739: step: 284/530, loss: 0.03849988058209419
2023-01-21 13:21:29.363298: step: 288/530, loss: 0.0422937385737896
2023-01-21 13:21:30.500137: step: 292/530, loss: 0.0005568981287069619
2023-01-21 13:21:31.640221: step: 296/530, loss: 0.000295531761366874
2023-01-21 13:21:32.775285: step: 300/530, loss: 0.002651310060173273
2023-01-21 13:21:33.854342: step: 304/530, loss: 0.0001181602492579259
2023-01-21 13:21:34.956583: step: 308/530, loss: 0.005441808607429266
2023-01-21 13:21:36.077609: step: 312/530, loss: 0.061397455632686615
2023-01-21 13:21:37.183327: step: 316/530, loss: 2.193450927734375e-05
2023-01-21 13:21:38.284070: step: 320/530, loss: 2.9563905172835803e-06
2023-01-21 13:21:39.396942: step: 324/530, loss: 1.1444091796875e-05
2023-01-21 13:21:40.503010: step: 328/530, loss: 0.0008769988780841231
2023-01-21 13:21:41.623633: step: 332/530, loss: 0.011965751647949219
2023-01-21 13:21:42.726405: step: 336/530, loss: 0.0050147054716944695
2023-01-21 13:21:43.829475: step: 340/530, loss: 0.001248478889465332
2023-01-21 13:21:44.941094: step: 344/530, loss: 2.937316821771674e-05
2023-01-21 13:21:46.058467: step: 348/530, loss: 0.23125873506069183
2023-01-21 13:21:47.181973: step: 352/530, loss: 0.0008073807111941278
2023-01-21 13:21:48.262169: step: 356/530, loss: 5.569458153331652e-05
2023-01-21 13:21:49.395212: step: 360/530, loss: 0.00013837814913131297
2023-01-21 13:21:50.512723: step: 364/530, loss: 6.341934295051033e-06
2023-01-21 13:21:51.608497: step: 368/530, loss: 0.005256843753159046
2023-01-21 13:21:52.692544: step: 372/530, loss: 3.1757354008732364e-05
2023-01-21 13:21:53.838569: step: 376/530, loss: 0.10189895331859589
2023-01-21 13:21:54.937786: step: 380/530, loss: 0.0039685252122581005
2023-01-21 13:21:56.041367: step: 384/530, loss: 0.03534860908985138
2023-01-21 13:21:57.124806: step: 388/530, loss: 0.0003299713134765625
2023-01-21 13:21:58.212776: step: 392/530, loss: 0.018732406198978424
2023-01-21 13:21:59.324802: step: 396/530, loss: 0.017844010144472122
2023-01-21 13:22:00.445815: step: 400/530, loss: 0.0007582188118249178
2023-01-21 13:22:01.550632: step: 404/530, loss: 4.1770937968976796e-05
2023-01-21 13:22:02.672342: step: 408/530, loss: 0.00011596680269576609
2023-01-21 13:22:03.790460: step: 412/530, loss: 0.006153678987175226
2023-01-21 13:22:04.881702: step: 416/530, loss: 0.00026865003746934235
2023-01-21 13:22:06.020771: step: 420/530, loss: 0.0002304077206645161
2023-01-21 13:22:07.093142: step: 424/530, loss: 5.435943421616685e-06
2023-01-21 13:22:08.165330: step: 428/530, loss: 3.0422212148550898e-05
2023-01-21 13:22:09.286220: step: 432/530, loss: 2.050399962172378e-05
2023-01-21 13:22:10.369538: step: 436/530, loss: 0.0001386642543366179
2023-01-21 13:22:11.506496: step: 440/530, loss: 1.7833710444392636e-05
2023-01-21 13:22:12.619274: step: 444/530, loss: 0.0001127243012888357
2023-01-21 13:22:13.715863: step: 448/530, loss: 0.0015014648670330644
2023-01-21 13:22:14.832174: step: 452/530, loss: 0.0003955840948037803
2023-01-21 13:22:15.931210: step: 456/530, loss: 0.04159178584814072
2023-01-21 13:22:17.056836: step: 460/530, loss: 0.0026561259292066097
2023-01-21 13:22:18.202626: step: 464/530, loss: 4.6253204345703125e-05
2023-01-21 13:22:19.310206: step: 468/530, loss: 0.01020207442343235
2023-01-21 13:22:20.388631: step: 472/530, loss: 0.0003520488680806011
2023-01-21 13:22:21.522298: step: 476/530, loss: 0.03383493423461914
2023-01-21 13:22:22.612642: step: 480/530, loss: 4.5108794438419864e-05
2023-01-21 13:22:23.728879: step: 484/530, loss: 0.007518577855080366
2023-01-21 13:22:24.838663: step: 488/530, loss: 7.553101022494957e-05
2023-01-21 13:22:25.926013: step: 492/530, loss: 1.5163422176556196e-05
2023-01-21 13:22:27.038379: step: 496/530, loss: 1.5258788153005298e-06
2023-01-21 13:22:28.202545: step: 500/530, loss: 0.00019874573627021164
2023-01-21 13:22:29.312921: step: 504/530, loss: 0.0003895759582519531
2023-01-21 13:22:30.433767: step: 508/530, loss: 0.00015597343735862523
2023-01-21 13:22:31.521186: step: 512/530, loss: -1.296997106692288e-05
2023-01-21 13:22:32.635489: step: 516/530, loss: 4.510879807639867e-05
2023-01-21 13:22:33.735458: step: 520/530, loss: 0.0001903533993754536
2023-01-21 13:22:34.848850: step: 524/530, loss: 0.00045723916264250875
2023-01-21 13:22:35.925278: step: 528/530, loss: 9.140968177234754e-05
2023-01-21 13:22:37.055139: step: 532/530, loss: 0.0018447876209393144
2023-01-21 13:22:38.178230: step: 536/530, loss: 0.0031841278541833162
2023-01-21 13:22:39.279340: step: 540/530, loss: 0.0012926101917400956
2023-01-21 13:22:40.391454: step: 544/530, loss: 1.239776611328125e-05
2023-01-21 13:22:41.488758: step: 548/530, loss: 0.0030548095237463713
2023-01-21 13:22:42.567930: step: 552/530, loss: 0.013393307104706764
2023-01-21 13:22:43.642670: step: 556/530, loss: 6.28471389063634e-05
2023-01-21 13:22:44.740923: step: 560/530, loss: 0.00019445418729446828
2023-01-21 13:22:45.845889: step: 564/530, loss: 4.510879807639867e-05
2023-01-21 13:22:46.997462: step: 568/530, loss: 0.0006181717035360634
2023-01-21 13:22:48.106271: step: 572/530, loss: 0.056319236755371094
2023-01-21 13:22:49.231342: step: 576/530, loss: 4.382133556646295e-05
2023-01-21 13:22:50.321333: step: 580/530, loss: 5.2165985835017636e-05
2023-01-21 13:22:51.425574: step: 584/530, loss: 0.008712291717529297
2023-01-21 13:22:52.538355: step: 588/530, loss: 8.325577073264867e-05
2023-01-21 13:22:53.652479: step: 592/530, loss: 4.110336521989666e-05
2023-01-21 13:22:54.795889: step: 596/530, loss: 0.0010107040870934725
2023-01-21 13:22:55.892383: step: 600/530, loss: 0.0013206482399255037
2023-01-21 13:22:57.002542: step: 604/530, loss: 1.888275073724799e-05
2023-01-21 13:22:58.097668: step: 608/530, loss: 0.04675489291548729
2023-01-21 13:22:59.194144: step: 612/530, loss: 0.00010929107520496473
2023-01-21 13:23:00.295533: step: 616/530, loss: 0.00014934541832190007
2023-01-21 13:23:01.395785: step: 620/530, loss: 2.0313262211857364e-05
2023-01-21 13:23:02.512637: step: 624/530, loss: 0.00318737025372684
2023-01-21 13:23:03.596376: step: 628/530, loss: 8.39233416627394e-06
2023-01-21 13:23:04.688733: step: 632/530, loss: 0.00022768972849007696
2023-01-21 13:23:05.806962: step: 636/530, loss: 0.005745220463722944
2023-01-21 13:23:06.893700: step: 640/530, loss: 0.025087738409638405
2023-01-21 13:23:08.000683: step: 644/530, loss: 4.792213439941406e-05
2023-01-21 13:23:09.106712: step: 648/530, loss: 0.0017478943336755037
2023-01-21 13:23:10.242849: step: 652/530, loss: 0.03402920067310333
2023-01-21 13:23:11.326670: step: 656/530, loss: 0.0003834724484477192
2023-01-21 13:23:12.491289: step: 660/530, loss: 0.0030072215013206005
2023-01-21 13:23:13.612215: step: 664/530, loss: 0.003998184110969305
2023-01-21 13:23:14.724223: step: 668/530, loss: 0.0004158973752055317
2023-01-21 13:23:15.830100: step: 672/530, loss: 9.536779543850571e-08
2023-01-21 13:23:16.964021: step: 676/530, loss: 0.035379983484745026
2023-01-21 13:23:18.062821: step: 680/530, loss: 9.393692016601562e-05
2023-01-21 13:23:19.193731: step: 684/530, loss: 0.000135326394229196
2023-01-21 13:23:20.339771: step: 688/530, loss: 0.0006980896578170359
2023-01-21 13:23:21.427499: step: 692/530, loss: -5.292892183206277e-06
2023-01-21 13:23:22.536496: step: 696/530, loss: 2.341270555916708e-05
2023-01-21 13:23:23.665272: step: 700/530, loss: 0.07872925698757172
2023-01-21 13:23:24.782985: step: 704/530, loss: 4.615783836925402e-05
2023-01-21 13:23:25.905082: step: 708/530, loss: 0.0009909630753099918
2023-01-21 13:23:27.029889: step: 712/530, loss: 0.0011909485328942537
2023-01-21 13:23:28.132790: step: 716/530, loss: 0.00013618468074128032
2023-01-21 13:23:29.304320: step: 720/530, loss: 0.008033180609345436
2023-01-21 13:23:30.395235: step: 724/530, loss: 0.0009420395363122225
2023-01-21 13:23:31.497257: step: 728/530, loss: 0.0007971763843670487
2023-01-21 13:23:32.589953: step: 732/530, loss: 0.00034179689828306437
2023-01-21 13:23:33.702445: step: 736/530, loss: 0.0026996613014489412
2023-01-21 13:23:34.791457: step: 740/530, loss: 9.212494478560984e-05
2023-01-21 13:23:35.908802: step: 744/530, loss: 5.2738188969669864e-05
2023-01-21 13:23:37.044274: step: 748/530, loss: 0.017889022827148438
2023-01-21 13:23:38.170788: step: 752/530, loss: 0.004961967468261719
2023-01-21 13:23:39.266395: step: 756/530, loss: 0.05314483866095543
2023-01-21 13:23:40.332359: step: 760/530, loss: 2.574920654296875e-05
2023-01-21 13:23:41.436753: step: 764/530, loss: -3.2424923119833693e-06
2023-01-21 13:23:42.541996: step: 768/530, loss: 1.1730194273695815e-05
2023-01-21 13:23:43.639166: step: 772/530, loss: 5.8364865253679454e-05
2023-01-21 13:23:44.770740: step: 776/530, loss: 0.0005382538074627519
2023-01-21 13:23:45.875515: step: 780/530, loss: 0.005088138394057751
2023-01-21 13:23:46.956859: step: 784/530, loss: 0.0001968383730854839
2023-01-21 13:23:48.056679: step: 788/530, loss: 2.8944017685716972e-05
2023-01-21 13:23:49.134109: step: 792/530, loss: 0.004815292544662952
2023-01-21 13:23:50.217014: step: 796/530, loss: 0.015410042367875576
2023-01-21 13:23:51.335380: step: 800/530, loss: 0.026335623115301132
2023-01-21 13:23:52.463261: step: 804/530, loss: 0.017641641199588776
2023-01-21 13:23:53.573857: step: 808/530, loss: 0.041811753064394
2023-01-21 13:23:54.694439: step: 812/530, loss: 0.000521755195222795
2023-01-21 13:23:55.812118: step: 816/530, loss: 4.167556471657008e-05
2023-01-21 13:23:56.936803: step: 820/530, loss: 2.7084352041129023e-05
2023-01-21 13:23:58.082804: step: 824/530, loss: 7.133484905352816e-05
2023-01-21 13:23:59.193674: step: 828/530, loss: 0.15551558136940002
2023-01-21 13:24:00.296456: step: 832/530, loss: 0.0006693362956866622
2023-01-21 13:24:01.421684: step: 836/530, loss: 0.0013718605041503906
2023-01-21 13:24:02.567735: step: 840/530, loss: 0.026207733899354935
2023-01-21 13:24:03.671797: step: 844/530, loss: 0.00010585785639705136
2023-01-21 13:24:04.756374: step: 848/530, loss: 0.0015985966892912984
2023-01-21 13:24:05.857772: step: 852/530, loss: 4.95910626341356e-06
2023-01-21 13:24:07.009290: step: 856/530, loss: 1.9073486328125e-06
2023-01-21 13:24:08.107020: step: 860/530, loss: 0.047466181218624115
2023-01-21 13:24:09.201891: step: 864/530, loss: 0.006888008210808039
2023-01-21 13:24:10.297672: step: 868/530, loss: 0.00038075449992902577
2023-01-21 13:24:11.403221: step: 872/530, loss: 0.015539360232651234
2023-01-21 13:24:12.520771: step: 876/530, loss: 3.585815284168348e-05
2023-01-21 13:24:13.608486: step: 880/530, loss: 0.00989522971212864
2023-01-21 13:24:14.735416: step: 884/530, loss: 0.03495483472943306
2023-01-21 13:24:15.821872: step: 888/530, loss: 0.0013396263821050525
2023-01-21 13:24:16.923636: step: 892/530, loss: 0.0007195472717285156
2023-01-21 13:24:18.050296: step: 896/530, loss: 0.0053039551712572575
2023-01-21 13:24:19.138037: step: 900/530, loss: 4.4631960918195546e-05
2023-01-21 13:24:20.245571: step: 904/530, loss: 0.005351925268769264
2023-01-21 13:24:21.340457: step: 908/530, loss: 0.00018386841111350805
2023-01-21 13:24:22.490676: step: 912/530, loss: 0.003766822861507535
2023-01-21 13:24:23.587033: step: 916/530, loss: 0.0004925489192828536
2023-01-21 13:24:24.712586: step: 920/530, loss: 5.5789947509765625e-05
2023-01-21 13:24:25.862284: step: 924/530, loss: -1.0204315003647935e-05
2023-01-21 13:24:26.940418: step: 928/530, loss: 0.00013952255540061742
2023-01-21 13:24:28.086563: step: 932/530, loss: 2.708435022213962e-05
2023-01-21 13:24:29.190511: step: 936/530, loss: 0.0013339996803551912
2023-01-21 13:24:30.282508: step: 940/530, loss: 0.0017431259620934725
2023-01-21 13:24:31.381499: step: 944/530, loss: 0.00021848679170943797
2023-01-21 13:24:32.491531: step: 948/530, loss: 0.005098819732666016
2023-01-21 13:24:33.578665: step: 952/530, loss: 0.006736421957612038
2023-01-21 13:24:34.671341: step: 956/530, loss: 0.0012333870399743319
2023-01-21 13:24:35.816873: step: 960/530, loss: 0.0004223823780193925
2023-01-21 13:24:36.923341: step: 964/530, loss: 0.10441255569458008
2023-01-21 13:24:38.019377: step: 968/530, loss: 0.028757857158780098
2023-01-21 13:24:39.150741: step: 972/530, loss: 9.202957880916074e-05
2023-01-21 13:24:40.283360: step: 976/530, loss: 0.00014858247595839202
2023-01-21 13:24:41.409398: step: 980/530, loss: 0.002829647157341242
2023-01-21 13:24:42.521603: step: 984/530, loss: 0.0016164302360266447
2023-01-21 13:24:43.615732: step: 988/530, loss: 0.009170341305434704
2023-01-21 13:24:44.737952: step: 992/530, loss: 0.006107521243393421
2023-01-21 13:24:45.862260: step: 996/530, loss: 0.0030161382164806128
2023-01-21 13:24:46.942730: step: 1000/530, loss: 2.1696090698242188e-05
2023-01-21 13:24:48.034509: step: 1004/530, loss: 0.0031592370942234993
2023-01-21 13:24:49.124483: step: 1008/530, loss: 0.00019578934006858617
2023-01-21 13:24:50.234104: step: 1012/530, loss: 0.021430397406220436
2023-01-21 13:24:51.359134: step: 1016/530, loss: 0.00037174223689362407
2023-01-21 13:24:52.455516: step: 1020/530, loss: 0.00047388076200149953
2023-01-21 13:24:53.530109: step: 1024/530, loss: 0.0002367019624216482
2023-01-21 13:24:54.631763: step: 1028/530, loss: 1.1062621524615679e-05
2023-01-21 13:24:55.729231: step: 1032/530, loss: 0.025748252868652344
2023-01-21 13:24:56.836720: step: 1036/530, loss: 1.6355514162569307e-05
2023-01-21 13:24:57.939138: step: 1040/530, loss: 0.0006443976890295744
2023-01-21 13:24:59.074998: step: 1044/530, loss: 0.006474304012954235
2023-01-21 13:25:00.171284: step: 1048/530, loss: 0.00276012415997684
2023-01-21 13:25:01.271477: step: 1052/530, loss: 4.200935291009955e-05
2023-01-21 13:25:02.394780: step: 1056/530, loss: 0.5726009607315063
2023-01-21 13:25:03.488166: step: 1060/530, loss: 2.4366378056583926e-05
2023-01-21 13:25:04.593213: step: 1064/530, loss: 2.975463939947076e-05
2023-01-21 13:25:05.717722: step: 1068/530, loss: 0.04387016221880913
2023-01-21 13:25:06.830874: step: 1072/530, loss: 0.008613396435976028
2023-01-21 13:25:07.940045: step: 1076/530, loss: 0.001984023954719305
2023-01-21 13:25:09.066787: step: 1080/530, loss: 0.0034473419655114412
2023-01-21 13:25:10.166999: step: 1084/530, loss: 1.2969970157428179e-05
2023-01-21 13:25:11.263677: step: 1088/530, loss: 4.0626528061693534e-05
2023-01-21 13:25:12.368459: step: 1092/530, loss: 3.604888843256049e-05
2023-01-21 13:25:13.473163: step: 1096/530, loss: 0.0010149956215173006
2023-01-21 13:25:14.578120: step: 1100/530, loss: 0.0002774238819256425
2023-01-21 13:25:15.685859: step: 1104/530, loss: 9.346007573185489e-06
2023-01-21 13:25:16.802790: step: 1108/530, loss: 0.00012211799912620336
2023-01-21 13:25:17.928893: step: 1112/530, loss: 0.004173374269157648
2023-01-21 13:25:19.062101: step: 1116/530, loss: 0.0025569917634129524
2023-01-21 13:25:20.176284: step: 1120/530, loss: 0.008492469787597656
2023-01-21 13:25:21.247176: step: 1124/530, loss: 0.0019285203889012337
2023-01-21 13:25:22.346453: step: 1128/530, loss: 0.0002206802455475554
2023-01-21 13:25:23.456286: step: 1132/530, loss: 0.0005338669288903475
2023-01-21 13:25:24.552505: step: 1136/530, loss: 6.065368506824598e-05
2023-01-21 13:25:25.674866: step: 1140/530, loss: 5.1784514653263614e-05
2023-01-21 13:25:26.761077: step: 1144/530, loss: 0.00017032623873092234
2023-01-21 13:25:27.862124: step: 1148/530, loss: -1.1444091796875e-05
2023-01-21 13:25:28.977650: step: 1152/530, loss: 0.0009275436750613153
2023-01-21 13:25:30.096619: step: 1156/530, loss: 9.15527380129788e-06
2023-01-21 13:25:31.198344: step: 1160/530, loss: 5.6743621826171875e-05
2023-01-21 13:25:32.319237: step: 1164/530, loss: 0.08822441101074219
2023-01-21 13:25:33.445563: step: 1168/530, loss: 0.0014806747203692794
2023-01-21 13:25:34.571904: step: 1172/530, loss: -4.1770188545342535e-05
2023-01-21 13:25:35.711799: step: 1176/530, loss: 5.455017162603326e-05
2023-01-21 13:25:36.827514: step: 1180/530, loss: 0.005130958743393421
2023-01-21 13:25:37.901892: step: 1184/530, loss: 0.0002884388086386025
2023-01-21 13:25:38.984496: step: 1188/530, loss: 0.0047550201416015625
2023-01-21 13:25:40.094495: step: 1192/530, loss: 0.03452110290527344
2023-01-21 13:25:41.203213: step: 1196/530, loss: 0.008860398083925247
2023-01-21 13:25:42.298220: step: 1200/530, loss: 7.090569124557078e-05
2023-01-21 13:25:43.390349: step: 1204/530, loss: 1.0585785275907256e-05
2023-01-21 13:25:44.511475: step: 1208/530, loss: 0.0445004478096962
2023-01-21 13:25:45.607049: step: 1212/530, loss: 2.6226043701171875e-06
2023-01-21 13:25:46.787853: step: 1216/530, loss: 0.002046013018116355
2023-01-21 13:25:47.897410: step: 1220/530, loss: 0.01266031339764595
2023-01-21 13:25:48.978007: step: 1224/530, loss: 6.246566954359878e-06
2023-01-21 13:25:50.093237: step: 1228/530, loss: 0.00030889513436704874
2023-01-21 13:25:51.176681: step: 1232/530, loss: 3.967285010730848e-05
2023-01-21 13:25:52.263713: step: 1236/530, loss: 0.0002111435023834929
2023-01-21 13:25:53.387394: step: 1240/530, loss: 0.000312614458380267
2023-01-21 13:25:54.496444: step: 1244/530, loss: 0.0019449711544439197
2023-01-21 13:25:55.607229: step: 1248/530, loss: 0.005079841706901789
2023-01-21 13:25:56.704120: step: 1252/530, loss: 0.00550689734518528
2023-01-21 13:25:57.797668: step: 1256/530, loss: 0.001361846923828125
2023-01-21 13:25:58.916243: step: 1260/530, loss: 0.0181577205657959
2023-01-21 13:26:00.022330: step: 1264/530, loss: 0.0506596565246582
2023-01-21 13:26:01.081649: step: 1268/530, loss: 2.3365021206700476e-06
2023-01-21 13:26:02.194219: step: 1272/530, loss: 4.19616708313697e-06
2023-01-21 13:26:03.308634: step: 1276/530, loss: 0.4252834618091583
2023-01-21 13:26:04.376195: step: 1280/530, loss: 9.870529902400449e-05
2023-01-21 13:26:05.467693: step: 1284/530, loss: 0.0007711410289630294
2023-01-21 13:26:06.562141: step: 1288/530, loss: 7.772445678710938e-05
2023-01-21 13:26:07.666404: step: 1292/530, loss: 0.006256484892219305
2023-01-21 13:26:08.793828: step: 1296/530, loss: 0.00016078949556685984
2023-01-21 13:26:09.903031: step: 1300/530, loss: 2.307891918462701e-05
2023-01-21 13:26:10.992718: step: 1304/530, loss: 0.00018558502779342234
2023-01-21 13:26:12.068402: step: 1308/530, loss: 0.0006884575122967362
2023-01-21 13:26:13.166780: step: 1312/530, loss: -7.4386593951203395e-06
2023-01-21 13:26:14.268874: step: 1316/530, loss: 0.0002462386910337955
2023-01-21 13:26:15.382736: step: 1320/530, loss: 0.006736373994499445
2023-01-21 13:26:16.500771: step: 1324/530, loss: 2.555847095209174e-05
2023-01-21 13:26:17.598364: step: 1328/530, loss: 0.0010400773026049137
2023-01-21 13:26:18.732663: step: 1332/530, loss: 0.0006032944074831903
2023-01-21 13:26:19.860442: step: 1336/530, loss: 0.001121139619499445
2023-01-21 13:26:20.966650: step: 1340/530, loss: 2.822876012942288e-05
2023-01-21 13:26:22.055278: step: 1344/530, loss: 8.087158494163305e-05
2023-01-21 13:26:23.172916: step: 1348/530, loss: -1.8215179807157256e-05
2023-01-21 13:26:24.267134: step: 1352/530, loss: 0.00023841859365347773
2023-01-21 13:26:25.371177: step: 1356/530, loss: -4.863738467975054e-06
2023-01-21 13:26:26.484991: step: 1360/530, loss: 0.011794280260801315
2023-01-21 13:26:27.632210: step: 1364/530, loss: 0.0020538331009447575
2023-01-21 13:26:28.744833: step: 1368/530, loss: 0.00014352798461914062
2023-01-21 13:26:29.882200: step: 1372/530, loss: 0.0250486359000206
2023-01-21 13:26:30.984941: step: 1376/530, loss: 0.010883426293730736
2023-01-21 13:26:32.110479: step: 1380/530, loss: 0.016922378912568092
2023-01-21 13:26:33.246184: step: 1384/530, loss: 0.0009827613830566406
2023-01-21 13:26:34.364629: step: 1388/530, loss: 0.017726421356201172
2023-01-21 13:26:35.462201: step: 1392/530, loss: 0.0227032657712698
2023-01-21 13:26:36.582454: step: 1396/530, loss: 1.773834264895413e-05
2023-01-21 13:26:37.665857: step: 1400/530, loss: 0.004320716951042414
2023-01-21 13:26:38.779268: step: 1404/530, loss: 0.052590563893318176
2023-01-21 13:26:39.908589: step: 1408/530, loss: 0.00010766983177745715
2023-01-21 13:26:40.991837: step: 1412/530, loss: 0.02021484635770321
2023-01-21 13:26:42.091908: step: 1416/530, loss: 1.201629675051663e-05
2023-01-21 13:26:43.181097: step: 1420/530, loss: 0.00013103484525345266
2023-01-21 13:26:44.280172: step: 1424/530, loss: 0.0021976472344249487
2023-01-21 13:26:45.397465: step: 1428/530, loss: 0.0019039154285565019
2023-01-21 13:26:46.518018: step: 1432/530, loss: 0.0010318756103515625
2023-01-21 13:26:47.621406: step: 1436/530, loss: -3.910064606316155e-06
2023-01-21 13:26:48.721372: step: 1440/530, loss: 4.94956984766759e-05
2023-01-21 13:26:49.844106: step: 1444/530, loss: 7.867813110351562e-06
2023-01-21 13:26:50.913619: step: 1448/530, loss: 3.0183793569449335e-05
2023-01-21 13:26:52.029488: step: 1452/530, loss: 0.012162781320512295
2023-01-21 13:26:53.133801: step: 1456/530, loss: -1.5258789289873675e-06
2023-01-21 13:26:54.218008: step: 1460/530, loss: 0.0005529403570108116
2023-01-21 13:26:55.327572: step: 1464/530, loss: 0.01263351459056139
2023-01-21 13:26:56.403128: step: 1468/530, loss: 0.04742584377527237
2023-01-21 13:26:57.536446: step: 1472/530, loss: 0.00010356903658248484
2023-01-21 13:26:58.633184: step: 1476/530, loss: 0.010910892859101295
2023-01-21 13:26:59.763123: step: 1480/530, loss: 0.0010728836059570312
2023-01-21 13:27:00.861725: step: 1484/530, loss: 2.28881845032447e-06
2023-01-21 13:27:01.947888: step: 1488/530, loss: 0.02781372144818306
2023-01-21 13:27:03.033582: step: 1492/530, loss: -1.3351440202313825e-06
2023-01-21 13:27:04.152070: step: 1496/530, loss: 3.619194103521295e-05
2023-01-21 13:27:05.240658: step: 1500/530, loss: 0.00023479462834075093
2023-01-21 13:27:06.357815: step: 1504/530, loss: 0.0010267258621752262
2023-01-21 13:27:07.494200: step: 1508/530, loss: 4.95910626341356e-06
2023-01-21 13:27:08.592391: step: 1512/530, loss: 5.464554124046117e-05
2023-01-21 13:27:09.699281: step: 1516/530, loss: 5.53131103515625e-05
2023-01-21 13:27:10.788010: step: 1520/530, loss: 0.0007488250848837197
2023-01-21 13:27:11.878514: step: 1524/530, loss: 0.010063553228974342
2023-01-21 13:27:13.000711: step: 1528/530, loss: 5.035400317865424e-05
2023-01-21 13:27:14.115473: step: 1532/530, loss: 0.001187992049381137
2023-01-21 13:27:15.230602: step: 1536/530, loss: 7.343292054429185e-06
2023-01-21 13:27:16.327471: step: 1540/530, loss: 0.0012093543773517013
2023-01-21 13:27:17.439844: step: 1544/530, loss: 1.869201696536038e-05
2023-01-21 13:27:18.559339: step: 1548/530, loss: 0.00020904542179778218
2023-01-21 13:27:19.661799: step: 1552/530, loss: 0.0028181076049804688
2023-01-21 13:27:20.804029: step: 1556/530, loss: 0.0262451171875
2023-01-21 13:27:21.906412: step: 1560/530, loss: 0.03380327299237251
2023-01-21 13:27:23.014045: step: 1564/530, loss: 0.12318307161331177
2023-01-21 13:27:24.113845: step: 1568/530, loss: 0.24842096865177155
2023-01-21 13:27:25.214293: step: 1572/530, loss: 0.0003291606844868511
2023-01-21 13:27:26.353606: step: 1576/530, loss: 0.0035772323608398438
2023-01-21 13:27:27.458163: step: 1580/530, loss: -1.3351436791708693e-06
2023-01-21 13:27:28.566955: step: 1584/530, loss: 2.1266938347253017e-05
2023-01-21 13:27:29.651476: step: 1588/530, loss: 1.0776519957289565e-05
2023-01-21 13:27:30.741541: step: 1592/530, loss: 0.00022430421086028218
2023-01-21 13:27:31.822858: step: 1596/530, loss: 6.675720669591101e-07
2023-01-21 13:27:32.951130: step: 1600/530, loss: 1.7833710444392636e-05
2023-01-21 13:27:34.118808: step: 1604/530, loss: 0.00043020248995162547
2023-01-21 13:27:35.251292: step: 1608/530, loss: 0.0005462646367959678
2023-01-21 13:27:36.417624: step: 1612/530, loss: 0.0023721696343272924
2023-01-21 13:27:37.540675: step: 1616/530, loss: 8.106231689453125e-06
2023-01-21 13:27:38.646450: step: 1620/530, loss: 0.009445000439882278
2023-01-21 13:27:39.753977: step: 1624/530, loss: 0.00015916823758743703
2023-01-21 13:27:40.858676: step: 1628/530, loss: 0.002831840654835105
2023-01-21 13:27:41.931957: step: 1632/530, loss: 2.19345088225964e-06
2023-01-21 13:27:43.047162: step: 1636/530, loss: 2.632141149661038e-05
2023-01-21 13:27:44.143997: step: 1640/530, loss: 2.918243444582913e-05
2023-01-21 13:27:45.247964: step: 1644/530, loss: 0.0029728414956480265
2023-01-21 13:27:46.374341: step: 1648/530, loss: 0.00014982224092818797
2023-01-21 13:27:47.463369: step: 1652/530, loss: 0.0015291214222088456
2023-01-21 13:27:48.554493: step: 1656/530, loss: 0.004897594451904297
2023-01-21 13:27:49.664266: step: 1660/530, loss: 2.784729076665826e-05
2023-01-21 13:27:50.786611: step: 1664/530, loss: 0.1471010148525238
2023-01-21 13:27:51.862973: step: 1668/530, loss: 1.0395049685030244e-05
2023-01-21 13:27:52.975132: step: 1672/530, loss: 0.0003562927304301411
2023-01-21 13:27:54.087094: step: 1676/530, loss: 5.4931642807787284e-05
2023-01-21 13:27:55.202870: step: 1680/530, loss: 0.0004313468816690147
2023-01-21 13:27:56.336239: step: 1684/530, loss: 0.023760128766298294
2023-01-21 13:27:57.461750: step: 1688/530, loss: 0.0010833740234375
2023-01-21 13:27:58.567652: step: 1692/530, loss: 5.111694190418348e-05
2023-01-21 13:27:59.700809: step: 1696/530, loss: 4.305839684093371e-05
2023-01-21 13:28:00.817562: step: 1700/530, loss: 2.5749204723979346e-06
2023-01-21 13:28:01.911157: step: 1704/530, loss: 4.301071021473035e-05
2023-01-21 13:28:03.047532: step: 1708/530, loss: 9.5367431640625e-06
2023-01-21 13:28:04.162233: step: 1712/530, loss: 0.00021529197692871094
2023-01-21 13:28:05.300138: step: 1716/530, loss: 0.0006444930913858116
2023-01-21 13:28:06.427613: step: 1720/530, loss: 6.65664701955393e-05
2023-01-21 13:28:07.502385: step: 1724/530, loss: 0.0013866424560546875
2023-01-21 13:28:08.631087: step: 1728/530, loss: 0.030509136617183685
2023-01-21 13:28:09.732686: step: 1732/530, loss: 0.00017833711171988398
2023-01-21 13:28:10.809049: step: 1736/530, loss: 0.00022220611572265625
2023-01-21 13:28:11.902116: step: 1740/530, loss: 1.6117095583467744e-05
2023-01-21 13:28:13.030419: step: 1744/530, loss: 4.305839684093371e-05
2023-01-21 13:28:14.139873: step: 1748/530, loss: 0.010710716247558594
2023-01-21 13:28:15.251660: step: 1752/530, loss: 0.00498700188472867
2023-01-21 13:28:16.364800: step: 1756/530, loss: 0.0033548830542713404
2023-01-21 13:28:17.474893: step: 1760/530, loss: 0.004049873445183039
2023-01-21 13:28:18.567684: step: 1764/530, loss: 0.013058949261903763
2023-01-21 13:28:19.677252: step: 1768/530, loss: 0.0026417733170092106
2023-01-21 13:28:20.793945: step: 1772/530, loss: 2.1934511096333154e-05
2023-01-21 13:28:21.943319: step: 1776/530, loss: 0.0008058547973632812
2023-01-21 13:28:23.044974: step: 1780/530, loss: 0.0002092361537506804
2023-01-21 13:28:24.156133: step: 1784/530, loss: 0.11256122589111328
2023-01-21 13:28:25.255786: step: 1788/530, loss: 0.004712057299911976
2023-01-21 13:28:26.387649: step: 1792/530, loss: 0.03334465250372887
2023-01-21 13:28:27.496243: step: 1796/530, loss: 0.0004414081631693989
2023-01-21 13:28:28.596860: step: 1800/530, loss: 1.506805438111769e-05
2023-01-21 13:28:29.708330: step: 1804/530, loss: 0.06063595041632652
2023-01-21 13:28:30.820023: step: 1808/530, loss: 0.0013854980934411287
2023-01-21 13:28:31.938775: step: 1812/530, loss: 9.622574725653976e-05
2023-01-21 13:28:33.075556: step: 1816/530, loss: 0.023438835516572
2023-01-21 13:28:34.174131: step: 1820/530, loss: 0.004013252444565296
2023-01-21 13:28:35.279092: step: 1824/530, loss: 0.0030981062445789576
2023-01-21 13:28:36.373763: step: 1828/530, loss: 0.12134285271167755
2023-01-21 13:28:37.473162: step: 1832/530, loss: 0.00010433197167003527
2023-01-21 13:28:38.610712: step: 1836/530, loss: 0.00027232171851210296
2023-01-21 13:28:39.706912: step: 1840/530, loss: 0.004335212986916304
2023-01-21 13:28:40.770792: step: 1844/530, loss: 0.000164031982421875
2023-01-21 13:28:41.903545: step: 1848/530, loss: 0.035561371594667435
2023-01-21 13:28:43.021472: step: 1852/530, loss: 0.14002734422683716
2023-01-21 13:28:44.143469: step: 1856/530, loss: 1.8787384760798886e-05
2023-01-21 13:28:45.272899: step: 1860/530, loss: 0.01986560970544815
2023-01-21 13:28:46.373599: step: 1864/530, loss: 0.002645397325977683
2023-01-21 13:28:47.481247: step: 1868/530, loss: 0.0004326820489950478
2023-01-21 13:28:48.606146: step: 1872/530, loss: 0.07766446471214294
2023-01-21 13:28:49.746478: step: 1876/530, loss: 0.00013055800809524953
2023-01-21 13:28:50.835821: step: 1880/530, loss: 3.5858156479662284e-05
2023-01-21 13:28:51.948946: step: 1884/530, loss: 0.04719515144824982
2023-01-21 13:28:53.102856: step: 1888/530, loss: 3.1948089599609375e-05
2023-01-21 13:28:54.209053: step: 1892/530, loss: 0.0010848998790606856
2023-01-21 13:28:55.324953: step: 1896/530, loss: 0.00013999939255882055
2023-01-21 13:28:56.441656: step: 1900/530, loss: 0.05254707485437393
2023-01-21 13:28:57.570607: step: 1904/530, loss: 0.00010523795936023816
2023-01-21 13:28:58.694150: step: 1908/530, loss: 2.2554397219209932e-05
2023-01-21 13:28:59.802405: step: 1912/530, loss: 6.8664553509734105e-06
2023-01-21 13:29:00.897538: step: 1916/530, loss: 0.00041790009709075093
2023-01-21 13:29:01.986884: step: 1920/530, loss: 0.0242767333984375
2023-01-21 13:29:03.133935: step: 1924/530, loss: 0.008136939257383347
2023-01-21 13:29:04.231928: step: 1928/530, loss: 0.0008774757734499872
2023-01-21 13:29:05.306664: step: 1932/530, loss: 2.9277802241267636e-05
2023-01-21 13:29:06.404188: step: 1936/530, loss: -4.196166628389619e-06
2023-01-21 13:29:07.502199: step: 1940/530, loss: 0.005142879206687212
2023-01-21 13:29:08.610823: step: 1944/530, loss: 0.0016587257850915194
2023-01-21 13:29:09.713144: step: 1948/530, loss: 0.019158076494932175
2023-01-21 13:29:10.812862: step: 1952/530, loss: 0.005306816194206476
2023-01-21 13:29:11.936390: step: 1956/530, loss: 0.001859426498413086
2023-01-21 13:29:13.046255: step: 1960/530, loss: 4.501342846197076e-05
2023-01-21 13:29:14.139581: step: 1964/530, loss: 0.0017673493130132556
2023-01-21 13:29:15.248901: step: 1968/530, loss: 0.021413613110780716
2023-01-21 13:29:16.367695: step: 1972/530, loss: 0.011100483126938343
2023-01-21 13:29:17.474681: step: 1976/530, loss: 0.03028392791748047
2023-01-21 13:29:18.557770: step: 1980/530, loss: 0.0007142543909139931
2023-01-21 13:29:19.711282: step: 1984/530, loss: 0.00026192667428404093
2023-01-21 13:29:20.863491: step: 1988/530, loss: 3.452301098150201e-05
2023-01-21 13:29:21.950432: step: 1992/530, loss: 0.0020510198082774878
2023-01-21 13:29:23.097668: step: 1996/530, loss: 0.0008483887067995965
2023-01-21 13:29:24.180725: step: 2000/530, loss: 0.0001583099365234375
2023-01-21 13:29:25.267803: step: 2004/530, loss: 0.00597991980612278
2023-01-21 13:29:26.366116: step: 2008/530, loss: 0.0006293297046795487
2023-01-21 13:29:27.516184: step: 2012/530, loss: 0.0004289627249818295
2023-01-21 13:29:28.653290: step: 2016/530, loss: -1.1920928955078125e-06
2023-01-21 13:29:29.750685: step: 2020/530, loss: 0.028151322156190872
2023-01-21 13:29:30.870116: step: 2024/530, loss: 4.749298022943549e-05
2023-01-21 13:29:31.971742: step: 2028/530, loss: 0.0016389847733080387
2023-01-21 13:29:33.062355: step: 2032/530, loss: 0.0014969349140301347
2023-01-21 13:29:34.124653: step: 2036/530, loss: 0.0001476764737162739
2023-01-21 13:29:35.232498: step: 2040/530, loss: 0.008602429181337357
2023-01-21 13:29:36.340541: step: 2044/530, loss: 0.004796028137207031
2023-01-21 13:29:37.441209: step: 2048/530, loss: 0.08157216012477875
2023-01-21 13:29:38.565261: step: 2052/530, loss: 0.00031261442927643657
2023-01-21 13:29:39.655242: step: 2056/530, loss: 3.814697322468419e-07
2023-01-21 13:29:40.782013: step: 2060/530, loss: 0.002353382296860218
2023-01-21 13:29:41.865738: step: 2064/530, loss: 9.34600848268019e-06
2023-01-21 13:29:42.982211: step: 2068/530, loss: 2.6226043701171875e-05
2023-01-21 13:29:44.104383: step: 2072/530, loss: 0.00015964507474564016
2023-01-21 13:29:45.221275: step: 2076/530, loss: 0.009865951724350452
2023-01-21 13:29:46.332866: step: 2080/530, loss: 1.0277678966522217
2023-01-21 13:29:47.468901: step: 2084/530, loss: 0.007714462466537952
2023-01-21 13:29:48.582715: step: 2088/530, loss: 0.0003246307314839214
2023-01-21 13:29:49.715020: step: 2092/530, loss: 0.0042854310013353825
2023-01-21 13:29:50.815733: step: 2096/530, loss: 0.0031880377791821957
2023-01-21 13:29:51.963630: step: 2100/530, loss: 0.0009963989723473787
2023-01-21 13:29:53.103191: step: 2104/530, loss: 0.002493238542228937
2023-01-21 13:29:54.201354: step: 2108/530, loss: 0.004219150636345148
2023-01-21 13:29:55.298928: step: 2112/530, loss: 0.005974722094833851
2023-01-21 13:29:56.395455: step: 2116/530, loss: 0.00011444091796875
2023-01-21 13:29:57.516950: step: 2120/530, loss: 0.03793644905090332
==================================================
Loss: 0.013
--------------------
Dev: {'event': {'p': 0.6045548654244306, 'r': 0.7776298268974701, 'f1': 0.6802562609202096}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Test: {'event': {'p': 0.6389016018306636, 'r': 0.8135198135198135, 'f1': 0.7157139195078185}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Chinese: {'event': {'p': 0.6164383561643836, 'r': 0.8333333333333334, 'f1': 0.7086614173228347}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Korean: {'event': {'p': 0.7619047619047619, 'r': 0.5079365079365079, 'f1': 0.6095238095238095}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Russian: {'event': {'p': 0.46153846153846156, 'r': 0.5, 'f1': 0.48000000000000004}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Korean: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 13:30:37.075864: step: 4/530, loss: 3.890991138177924e-05
2023-01-21 13:30:38.164192: step: 8/530, loss: 6.198883511387976e-06
2023-01-21 13:30:39.265703: step: 12/530, loss: 0.000780296279117465
2023-01-21 13:30:40.375172: step: 16/530, loss: 1.8978118532686494e-05
2023-01-21 13:30:41.496652: step: 20/530, loss: 0.005344391334801912
2023-01-21 13:30:42.601061: step: 24/530, loss: 0.0016595841152593493
2023-01-21 13:30:43.705002: step: 28/530, loss: 0.0007118225912563503
2023-01-21 13:30:44.859915: step: 32/530, loss: 0.00027694704476743937
2023-01-21 13:30:45.975811: step: 36/530, loss: 0.03676815330982208
2023-01-21 13:30:47.064228: step: 40/530, loss: 3.347396705066785e-05
2023-01-21 13:30:48.161154: step: 44/530, loss: 0.0037827491760253906
2023-01-21 13:30:49.271165: step: 48/530, loss: 0.011240005493164062
2023-01-21 13:30:50.381689: step: 52/530, loss: 0.017479324713349342
2023-01-21 13:30:51.480658: step: 56/530, loss: 4.9591067181609105e-06
2023-01-21 13:30:52.589268: step: 60/530, loss: 0.010850906372070312
2023-01-21 13:30:53.674963: step: 64/530, loss: 3.633499363786541e-05
2023-01-21 13:30:54.770001: step: 68/530, loss: 0.006569766905158758
2023-01-21 13:30:55.854474: step: 72/530, loss: 0.020728018134832382
2023-01-21 13:30:56.924786: step: 76/530, loss: 7.152557373046875e-05
2023-01-21 13:30:58.008437: step: 80/530, loss: 0.0005804061656817794
2023-01-21 13:30:59.110584: step: 84/530, loss: 0.014216899871826172
2023-01-21 13:31:00.242409: step: 88/530, loss: 0.0013484955998137593
2023-01-21 13:31:01.359334: step: 92/530, loss: 0.0015741349197924137
2023-01-21 13:31:02.479621: step: 96/530, loss: -1.392364538332913e-05
2023-01-21 13:31:03.565172: step: 100/530, loss: 9.193419828079641e-05
2023-01-21 13:31:04.675351: step: 104/530, loss: 0.0001548767031636089
2023-01-21 13:31:05.761016: step: 108/530, loss: -1.8215179807157256e-05
2023-01-21 13:31:06.832139: step: 112/530, loss: 1.583099401614163e-05
2023-01-21 13:31:07.907858: step: 116/530, loss: 4.272460864740424e-05
2023-01-21 13:31:09.030926: step: 120/530, loss: 0.0004975319025106728
2023-01-21 13:31:10.158512: step: 124/530, loss: 1.449584942747606e-05
2023-01-21 13:31:11.254297: step: 128/530, loss: -1.1205673217773438e-05
2023-01-21 13:31:12.362966: step: 132/530, loss: 2.09808349609375e-05
2023-01-21 13:31:13.455912: step: 136/530, loss: 0.010014343075454235
2023-01-21 13:31:14.562934: step: 140/530, loss: 6.370544724632055e-05
2023-01-21 13:31:15.687661: step: 144/530, loss: 0.00011339187767589465
2023-01-21 13:31:16.813267: step: 148/530, loss: 0.00023927689471747726
2023-01-21 13:31:17.907182: step: 152/530, loss: 0.00033359526423737407
2023-01-21 13:31:18.990941: step: 156/530, loss: 2.708435022213962e-05
2023-01-21 13:31:20.082801: step: 160/530, loss: 0.0004328727663960308
2023-01-21 13:31:21.177602: step: 164/530, loss: 0.0005460739484988153
2023-01-21 13:31:22.300030: step: 168/530, loss: 0.00011358260962879285
2023-01-21 13:31:23.424721: step: 172/530, loss: 0.00025196076603606343
2023-01-21 13:31:24.546139: step: 176/530, loss: 7.05719003235572e-06
2023-01-21 13:31:25.628764: step: 180/530, loss: 0.0013875007862225175
2023-01-21 13:31:26.743853: step: 184/530, loss: 0.00039091112557798624
2023-01-21 13:31:27.847729: step: 188/530, loss: 0.01099462527781725
2023-01-21 13:31:28.933230: step: 192/530, loss: 0.0025278092361986637
2023-01-21 13:31:30.025616: step: 196/530, loss: 1.907349087559851e-07
2023-01-21 13:31:31.117310: step: 200/530, loss: -1.0490417707842425e-06
2023-01-21 13:31:32.222686: step: 204/530, loss: 0.0064601898193359375
2023-01-21 13:31:33.334528: step: 208/530, loss: 3.0183793569449335e-05
2023-01-21 13:31:34.479253: step: 212/530, loss: 0.00010929107520496473
2023-01-21 13:31:35.605837: step: 216/530, loss: 1.3494491213350557e-05
2023-01-21 13:31:36.709403: step: 220/530, loss: 0.005573845002800226
2023-01-21 13:31:37.829615: step: 224/530, loss: 0.00548477191478014
2023-01-21 13:31:38.907549: step: 228/530, loss: 0.00038375856820493937
2023-01-21 13:31:40.022491: step: 232/530, loss: 4.6443939936580136e-05
2023-01-21 13:31:41.136599: step: 236/530, loss: 8.0108642578125e-05
2023-01-21 13:31:42.225886: step: 240/530, loss: 0.008176421746611595
2023-01-21 13:31:43.352160: step: 244/530, loss: 0.034354403614997864
2023-01-21 13:31:44.432034: step: 248/530, loss: 1.0961294719891157e-05
2023-01-21 13:31:45.563981: step: 252/530, loss: 0.011131287552416325
2023-01-21 13:31:46.665127: step: 256/530, loss: 0.00012502670870162547
2023-01-21 13:31:47.822636: step: 260/530, loss: 7.02858014847152e-05
2023-01-21 13:31:48.934299: step: 264/530, loss: 2.28881845032447e-06
2023-01-21 13:31:50.042530: step: 268/530, loss: 0.012936783023178577
2023-01-21 13:31:51.124553: step: 272/530, loss: 5.5265431001316756e-05
2023-01-21 13:31:52.222455: step: 276/530, loss: 2.8610247682081535e-07
2023-01-21 13:31:53.327665: step: 280/530, loss: 0.00015001297288108617
2023-01-21 13:31:54.409436: step: 284/530, loss: 1.9168854123563506e-05
2023-01-21 13:31:55.550647: step: 288/530, loss: 0.0020424844697117805
2023-01-21 13:31:56.707077: step: 292/530, loss: 2.5844574338407256e-05
2023-01-21 13:31:57.826593: step: 296/530, loss: 0.0004562377871479839
2023-01-21 13:31:58.950595: step: 300/530, loss: 0.03921656310558319
2023-01-21 13:32:00.086360: step: 304/530, loss: 0.029955388978123665
2023-01-21 13:32:01.216427: step: 308/530, loss: 0.0005227088695392013
2023-01-21 13:32:02.315281: step: 312/530, loss: 1.716613724056515e-06
2023-01-21 13:32:03.444434: step: 316/530, loss: 1.239776611328125e-05
2023-01-21 13:32:04.520971: step: 320/530, loss: 0.003644275479018688
2023-01-21 13:32:05.639640: step: 324/530, loss: 0.00013256072998046875
2023-01-21 13:32:06.718679: step: 328/530, loss: 4.94956984766759e-05
2023-01-21 13:32:07.792045: step: 332/530, loss: 0.0006685256958007812
2023-01-21 13:32:08.894922: step: 336/530, loss: 0.00012159347534179688
2023-01-21 13:32:09.996172: step: 340/530, loss: 0.01426792237907648
2023-01-21 13:32:11.072393: step: 344/530, loss: 0.0007764339097775519
2023-01-21 13:32:12.198005: step: 348/530, loss: 1.6498566765221767e-05
2023-01-21 13:32:13.303491: step: 352/530, loss: 8.0108642578125e-05
2023-01-21 13:32:14.384261: step: 356/530, loss: 0.01762542687356472
2023-01-21 13:32:15.496688: step: 360/530, loss: 0.008090591058135033
2023-01-21 13:32:16.581161: step: 364/530, loss: 0.00021429063053801656
2023-01-21 13:32:17.682423: step: 368/530, loss: 0.0017854692414402962
2023-01-21 13:32:18.781061: step: 372/530, loss: 0.0031813145615160465
2023-01-21 13:32:19.865009: step: 376/530, loss: 8.822679956210777e-05
2023-01-21 13:32:20.948045: step: 380/530, loss: 5.222559047979303e-05
2023-01-21 13:32:22.056191: step: 384/530, loss: 0.0020753622520715
2023-01-21 13:32:23.140109: step: 388/530, loss: 0.00017557146202307194
2023-01-21 13:32:24.238275: step: 392/530, loss: 0.0038789750542491674
2023-01-21 13:32:25.364146: step: 396/530, loss: 0.0021792410407215357
2023-01-21 13:32:26.469416: step: 400/530, loss: 0.03272876888513565
2023-01-21 13:32:27.567414: step: 404/530, loss: 5.0926206313306466e-05
2023-01-21 13:32:28.664547: step: 408/530, loss: 1.182556115963962e-05
2023-01-21 13:32:29.756165: step: 412/530, loss: 0.0017423630924895406
2023-01-21 13:32:30.858603: step: 416/530, loss: 0.00044622423592954874
2023-01-21 13:32:31.974365: step: 420/530, loss: -1.1420250302762724e-05
2023-01-21 13:32:33.097032: step: 424/530, loss: 0.0032587051391601562
2023-01-21 13:32:34.187229: step: 428/530, loss: -1.8119811784345075e-06
2023-01-21 13:32:35.307396: step: 432/530, loss: 0.010600185953080654
2023-01-21 13:32:36.416136: step: 436/530, loss: 0.00033550261287018657
2023-01-21 13:32:37.527387: step: 440/530, loss: 0.5257606506347656
2023-01-21 13:32:38.631947: step: 444/530, loss: 0.0025041578337550163
2023-01-21 13:32:39.753844: step: 448/530, loss: 0.03446917608380318
2023-01-21 13:32:40.851269: step: 452/530, loss: 0.03645334392786026
2023-01-21 13:32:41.977671: step: 456/530, loss: 0.0035427093971520662
2023-01-21 13:32:43.078417: step: 460/530, loss: 2.307891918462701e-05
2023-01-21 13:32:44.216015: step: 464/530, loss: 1.9073486328125e-06
2023-01-21 13:32:45.303005: step: 468/530, loss: 7.24792471373803e-06
2023-01-21 13:32:46.445059: step: 472/530, loss: 7.057190487103071e-06
2023-01-21 13:32:47.543392: step: 476/530, loss: 0.0004782676696777344
2023-01-21 13:32:48.659157: step: 480/530, loss: 0.0024044038727879524
2023-01-21 13:32:49.760017: step: 484/530, loss: 5.884170241188258e-05
2023-01-21 13:32:50.871764: step: 488/530, loss: 0.0033718112390488386
2023-01-21 13:32:51.979091: step: 492/530, loss: 0.02174835279583931
2023-01-21 13:32:53.085571: step: 496/530, loss: 0.0005529403570108116
2023-01-21 13:32:54.178917: step: 500/530, loss: 0.00074005126953125
2023-01-21 13:32:55.329059: step: 504/530, loss: 0.001361084054224193
2023-01-21 13:32:56.448041: step: 508/530, loss: 0.05779757350683212
2023-01-21 13:32:57.548450: step: 512/530, loss: 0.00034122465876862407
2023-01-21 13:32:58.648325: step: 516/530, loss: 0.015423583798110485
2023-01-21 13:32:59.754528: step: 520/530, loss: 0.01027526892721653
2023-01-21 13:33:00.849708: step: 524/530, loss: 0.008314036764204502
2023-01-21 13:33:01.970969: step: 528/530, loss: 0.003544759703800082
2023-01-21 13:33:03.052125: step: 532/530, loss: 0.0021855831146240234
2023-01-21 13:33:04.181725: step: 536/530, loss: -4.539489600574598e-05
2023-01-21 13:33:05.244885: step: 540/530, loss: 0.0004616737423930317
2023-01-21 13:33:06.384582: step: 544/530, loss: 0.044037818908691406
2023-01-21 13:33:07.456827: step: 548/530, loss: 5.3215029765851796e-05
2023-01-21 13:33:08.523313: step: 552/530, loss: 0.0035499571822583675
2023-01-21 13:33:09.628613: step: 556/530, loss: 0.001546621322631836
2023-01-21 13:33:10.748116: step: 560/530, loss: 1.411438006471144e-05
2023-01-21 13:33:11.853375: step: 564/530, loss: 8.487701052217744e-06
2023-01-21 13:33:12.924193: step: 568/530, loss: 1.8024444216280244e-05
2023-01-21 13:33:14.032141: step: 572/530, loss: -5.722046125811175e-07
2023-01-21 13:33:15.160660: step: 576/530, loss: 0.31961217522621155
2023-01-21 13:33:16.248446: step: 580/530, loss: 0.04861736297607422
2023-01-21 13:33:17.358372: step: 584/530, loss: 1.3351441339182202e-06
2023-01-21 13:33:18.470078: step: 588/530, loss: 9.212493750965223e-05
2023-01-21 13:33:19.619950: step: 592/530, loss: 3.337860107421875e-05
2023-01-21 13:33:20.703401: step: 596/530, loss: 0.011237908154726028
2023-01-21 13:33:21.820348: step: 600/530, loss: 0.0005907058366574347
2023-01-21 13:33:22.959241: step: 604/530, loss: 0.04331379383802414
2023-01-21 13:33:24.047284: step: 608/530, loss: 6.146430678199977e-05
2023-01-21 13:33:25.149123: step: 612/530, loss: 0.008853530511260033
2023-01-21 13:33:26.275866: step: 616/530, loss: 7.305145845748484e-05
2023-01-21 13:33:27.388683: step: 620/530, loss: 4.501342846197076e-05
2023-01-21 13:33:28.528601: step: 624/530, loss: 3.137588646495715e-05
2023-01-21 13:33:29.614036: step: 628/530, loss: 7.467270188499242e-05
2023-01-21 13:33:30.713866: step: 632/530, loss: 3.719329924933845e-06
2023-01-21 13:33:31.828003: step: 636/530, loss: 0.0016036510933190584
2023-01-21 13:33:32.974110: step: 640/530, loss: 6.103515625e-05
2023-01-21 13:33:34.083466: step: 644/530, loss: 0.0002863883855752647
2023-01-21 13:33:35.198335: step: 648/530, loss: 0.04936389997601509
2023-01-21 13:33:36.332876: step: 652/530, loss: 0.0014019012451171875
2023-01-21 13:33:37.441972: step: 656/530, loss: 0.011093712411820889
2023-01-21 13:33:38.546217: step: 660/530, loss: 1.430511474609375e-06
2023-01-21 13:33:39.629986: step: 664/530, loss: 9.34600848268019e-06
2023-01-21 13:33:40.723982: step: 668/530, loss: 2.2125243049231358e-05
2023-01-21 13:33:41.845260: step: 672/530, loss: 0.04928307607769966
2023-01-21 13:33:42.971001: step: 676/530, loss: 0.00010032653517555445
2023-01-21 13:33:44.069458: step: 680/530, loss: 0.043377067893743515
2023-01-21 13:33:45.184417: step: 684/530, loss: 0.0004592895566020161
2023-01-21 13:33:46.275146: step: 688/530, loss: 0.0006210327264852822
2023-01-21 13:33:47.401096: step: 692/530, loss: 4.0531158447265625e-05
2023-01-21 13:33:48.496652: step: 696/530, loss: 0.019286155700683594
2023-01-21 13:33:49.572786: step: 700/530, loss: 0.0013612746261060238
2023-01-21 13:33:50.686302: step: 704/530, loss: 0.00032186511089093983
2023-01-21 13:33:51.795866: step: 708/530, loss: 5.7744979130802676e-05
2023-01-21 13:33:52.869174: step: 712/530, loss: 0.0013157606590539217
2023-01-21 13:33:53.955985: step: 716/530, loss: 6.341934204101562e-05
2023-01-21 13:33:55.058503: step: 720/530, loss: 4.615783836925402e-05
2023-01-21 13:33:56.191191: step: 724/530, loss: 1.7976761228055693e-05
2023-01-21 13:33:57.303380: step: 728/530, loss: 2.231597864010837e-05
2023-01-21 13:33:58.403382: step: 732/530, loss: 0.017851924523711205
2023-01-21 13:33:59.537313: step: 736/530, loss: 0.00011787414405262098
2023-01-21 13:34:00.685933: step: 740/530, loss: 0.006387901492416859
2023-01-21 13:34:01.788185: step: 744/530, loss: 0.0002860069216694683
2023-01-21 13:34:02.973161: step: 748/530, loss: 0.00010623932030284777
2023-01-21 13:34:04.078516: step: 752/530, loss: 0.006388283334672451
2023-01-21 13:34:05.192862: step: 756/530, loss: 0.00021567344083450735
2023-01-21 13:34:06.275175: step: 760/530, loss: 0.00027551653329283
2023-01-21 13:34:07.387172: step: 764/530, loss: 2.3746490114717744e-05
2023-01-21 13:34:08.510820: step: 768/530, loss: -5.507469268195564e-06
2023-01-21 13:34:09.636193: step: 772/530, loss: 0.0010121345985680819
2023-01-21 13:34:10.738323: step: 776/530, loss: 1.6021729607018642e-05
2023-01-21 13:34:11.842120: step: 780/530, loss: 8.39233416627394e-06
2023-01-21 13:34:12.968440: step: 784/530, loss: 0.0015523910988122225
2023-01-21 13:34:14.095043: step: 788/530, loss: 0.020052339881658554
2023-01-21 13:34:15.223320: step: 792/530, loss: 0.02536621317267418
2023-01-21 13:34:16.326189: step: 796/530, loss: 0.0010267257457599044
2023-01-21 13:34:17.417736: step: 800/530, loss: 6.866455805720761e-05
2023-01-21 13:34:18.555388: step: 804/530, loss: 0.10678310692310333
2023-01-21 13:34:19.643602: step: 808/530, loss: 0.0006478309514932334
2023-01-21 13:34:20.737732: step: 812/530, loss: 0.00012464524479582906
2023-01-21 13:34:21.860048: step: 816/530, loss: 0.0003482818719930947
2023-01-21 13:34:22.978195: step: 820/530, loss: 0.005203056614845991
2023-01-21 13:34:24.086597: step: 824/530, loss: 0.00028162001399323344
2023-01-21 13:34:25.201640: step: 828/530, loss: 0.004108619876205921
2023-01-21 13:34:26.327087: step: 832/530, loss: 0.0001050949067575857
2023-01-21 13:34:27.459413: step: 836/530, loss: 0.03114309348165989
2023-01-21 13:34:28.573817: step: 840/530, loss: 0.0004096984921488911
2023-01-21 13:34:29.706578: step: 844/530, loss: -2.86102294921875e-06
2023-01-21 13:34:30.785935: step: 848/530, loss: 0.00025815964909270406
2023-01-21 13:34:31.905571: step: 852/530, loss: 0.00041675567626953125
2023-01-21 13:34:33.016437: step: 856/530, loss: 0.0006967544904910028
2023-01-21 13:34:34.131588: step: 860/530, loss: 1.5354156857938506e-05
2023-01-21 13:34:35.222258: step: 864/530, loss: 0.002492713974788785
2023-01-21 13:34:36.314140: step: 868/530, loss: 0.0003426551993470639
2023-01-21 13:34:37.412184: step: 872/530, loss: 5.7220458984375e-06
2023-01-21 13:34:38.527522: step: 876/530, loss: 0.011728096753358841
2023-01-21 13:34:39.635115: step: 880/530, loss: 0.0033672333229333162
2023-01-21 13:34:40.744050: step: 884/530, loss: 1.4162063962430693e-05
2023-01-21 13:34:41.840399: step: 888/530, loss: 0.0014015198685228825
2023-01-21 13:34:42.946187: step: 892/530, loss: 0.003694724990054965
2023-01-21 13:34:44.087883: step: 896/530, loss: 0.0001392364501953125
2023-01-21 13:34:45.168619: step: 900/530, loss: 1.8501283193472773e-05
2023-01-21 13:34:46.294216: step: 904/530, loss: 0.02150108851492405
2023-01-21 13:34:47.411020: step: 908/530, loss: 0.003271674970164895
2023-01-21 13:34:48.517296: step: 912/530, loss: 8.821487426757812e-05
2023-01-21 13:34:49.656713: step: 916/530, loss: 0.00021638871112372726
2023-01-21 13:34:50.757971: step: 920/530, loss: 0.00019130708824377507
2023-01-21 13:34:51.858508: step: 924/530, loss: 0.0004391670227050781
2023-01-21 13:34:52.953228: step: 928/530, loss: 0.001921844552271068
2023-01-21 13:34:54.022221: step: 932/530, loss: 3.643035961431451e-05
2023-01-21 13:34:55.096620: step: 936/530, loss: 0.01632533222436905
2023-01-21 13:34:56.194859: step: 940/530, loss: 8.850097947288305e-05
2023-01-21 13:34:57.273670: step: 944/530, loss: 3.24249276673072e-06
2023-01-21 13:34:58.399677: step: 948/530, loss: 0.007223653607070446
2023-01-21 13:34:59.486198: step: 952/530, loss: 0.013106775470077991
2023-01-21 13:35:00.575925: step: 956/530, loss: 0.0002998829004354775
2023-01-21 13:35:01.695685: step: 960/530, loss: 0.00030956268892623484
2023-01-21 13:35:02.797322: step: 964/530, loss: 0.04158134385943413
2023-01-21 13:35:03.931506: step: 968/530, loss: 0.00016536712064407766
2023-01-21 13:35:05.029777: step: 972/530, loss: 0.01878223568201065
2023-01-21 13:35:06.135704: step: 976/530, loss: 2.9325485229492188e-05
2023-01-21 13:35:07.234157: step: 980/530, loss: 0.004874419886618853
2023-01-21 13:35:08.337269: step: 984/530, loss: 0.00011215209815418348
2023-01-21 13:35:09.464975: step: 988/530, loss: 0.008832740597426891
2023-01-21 13:35:10.551163: step: 992/530, loss: 0.00017585755267646164
2023-01-21 13:35:11.696401: step: 996/530, loss: 0.00022811890812590718
2023-01-21 13:35:12.800841: step: 1000/530, loss: 0.053105734288692474
2023-01-21 13:35:13.932226: step: 1004/530, loss: 0.00018310546875
2023-01-21 13:35:15.045724: step: 1008/530, loss: 2.2029877072782256e-05
2023-01-21 13:35:16.127459: step: 1012/530, loss: 0.0010477066971361637
2023-01-21 13:35:17.272684: step: 1016/530, loss: 0.017580414190888405
2023-01-21 13:35:18.366688: step: 1020/530, loss: 4.434585662238533e-06
2023-01-21 13:35:19.458714: step: 1024/530, loss: 0.014266586862504482
2023-01-21 13:35:20.633829: step: 1028/530, loss: 0.0001199722319142893
2023-01-21 13:35:21.737524: step: 1032/530, loss: 3.6811830796068534e-05
2023-01-21 13:35:22.835161: step: 1036/530, loss: 0.000347375898854807
2023-01-21 13:35:23.940438: step: 1040/530, loss: 0.000927352870348841
2023-01-21 13:35:25.088070: step: 1044/530, loss: 0.0008510589832440019
2023-01-21 13:35:26.232355: step: 1048/530, loss: 0.0007715702522546053
2023-01-21 13:35:27.355241: step: 1052/530, loss: 0.0011595726246014237
2023-01-21 13:35:28.513757: step: 1056/530, loss: 0.0020853043533861637
2023-01-21 13:35:29.629597: step: 1060/530, loss: 1.8024444216280244e-05
2023-01-21 13:35:30.742202: step: 1064/530, loss: 0.0004734992980957031
2023-01-21 13:35:31.888479: step: 1068/530, loss: 0.00264568324200809
2023-01-21 13:35:33.019512: step: 1072/530, loss: 0.0012210846180096269
2023-01-21 13:35:34.121747: step: 1076/530, loss: -4.76837158203125e-06
2023-01-21 13:35:35.243212: step: 1080/530, loss: 0.0407983772456646
2023-01-21 13:35:36.365569: step: 1084/530, loss: 0.13124600052833557
2023-01-21 13:35:37.458931: step: 1088/530, loss: -1.907349087559851e-07
2023-01-21 13:35:38.572713: step: 1092/530, loss: 0.04686775431036949
2023-01-21 13:35:39.670687: step: 1096/530, loss: 5.35011276951991e-05
2023-01-21 13:35:40.783642: step: 1100/530, loss: -4.95910626341356e-06
2023-01-21 13:35:41.871592: step: 1104/530, loss: 0.00028285980806685984
2023-01-21 13:35:42.984025: step: 1108/530, loss: -1.5258790426742053e-06
2023-01-21 13:35:44.085667: step: 1112/530, loss: -1.2777745723724365e-05
2023-01-21 13:35:45.182601: step: 1116/530, loss: 0.0007844925276003778
2023-01-21 13:35:46.286607: step: 1120/530, loss: 2.47955313170678e-06
2023-01-21 13:35:47.402377: step: 1124/530, loss: 4.181861731922254e-05
2023-01-21 13:35:48.523933: step: 1128/530, loss: 5.493163916980848e-05
2023-01-21 13:35:49.636614: step: 1132/530, loss: 0.0004955291515216231
2023-01-21 13:35:50.764461: step: 1136/530, loss: 0.0035698891151696444
2023-01-21 13:35:51.891106: step: 1140/530, loss: 0.0011486053699627519
2023-01-21 13:35:52.992088: step: 1144/530, loss: 0.05339193716645241
2023-01-21 13:35:54.106032: step: 1148/530, loss: 2.098083541568485e-06
2023-01-21 13:35:55.231404: step: 1152/530, loss: -5.34057608092553e-06
2023-01-21 13:35:56.328287: step: 1156/530, loss: 0.00012464523024391383
2023-01-21 13:35:57.470348: step: 1160/530, loss: -1.2302398317842744e-05
2023-01-21 13:35:58.552709: step: 1164/530, loss: 7.247925168485381e-06
2023-01-21 13:35:59.658630: step: 1168/530, loss: 0.000994873116724193
2023-01-21 13:36:00.754557: step: 1172/530, loss: 1.716613724056515e-06
2023-01-21 13:36:01.841948: step: 1176/530, loss: 0.0005027770530432463
2023-01-21 13:36:02.995854: step: 1180/530, loss: 5.0067901611328125e-05
2023-01-21 13:36:04.121414: step: 1184/530, loss: 5.817413693876006e-06
2023-01-21 13:36:05.204544: step: 1188/530, loss: 0.0020944594871252775
2023-01-21 13:36:06.305852: step: 1192/530, loss: 0.00014090538024902344
2023-01-21 13:36:07.436661: step: 1196/530, loss: 0.0024373054038733244
2023-01-21 13:36:08.536432: step: 1200/530, loss: 0.008447266183793545
2023-01-21 13:36:09.661463: step: 1204/530, loss: 0.03229274973273277
2023-01-21 13:36:10.745580: step: 1208/530, loss: 1.5354156857938506e-05
2023-01-21 13:36:11.844252: step: 1212/530, loss: 0.002697324613109231
2023-01-21 13:36:12.943129: step: 1216/530, loss: 0.0002155303955078125
2023-01-21 13:36:14.045796: step: 1220/530, loss: 0.013344001956284046
2023-01-21 13:36:15.154654: step: 1224/530, loss: 0.000156402587890625
2023-01-21 13:36:16.275870: step: 1228/530, loss: 0.00023918152146507055
2023-01-21 13:36:17.401883: step: 1232/530, loss: 0.017763758078217506
2023-01-21 13:36:18.507911: step: 1236/530, loss: 0.0007492065196856856
2023-01-21 13:36:19.631262: step: 1240/530, loss: 0.030246257781982422
2023-01-21 13:36:20.744171: step: 1244/530, loss: 0.007139683235436678
2023-01-21 13:36:21.855762: step: 1248/530, loss: 0.0008123397710733116
2023-01-21 13:36:22.951143: step: 1252/530, loss: 0.0007519721984863281
2023-01-21 13:36:24.078690: step: 1256/530, loss: 0.04609966278076172
2023-01-21 13:36:25.156515: step: 1260/530, loss: 0.002103185746818781
2023-01-21 13:36:26.309657: step: 1264/530, loss: 5.416870044427924e-05
2023-01-21 13:36:27.438541: step: 1268/530, loss: 0.003810882568359375
2023-01-21 13:36:28.539548: step: 1272/530, loss: 0.007046985439956188
2023-01-21 13:36:29.715807: step: 1276/530, loss: 2.6130677724722773e-05
2023-01-21 13:36:30.853502: step: 1280/530, loss: 0.0003641128714662045
2023-01-21 13:36:31.938035: step: 1284/530, loss: 0.004894828889518976
2023-01-21 13:36:33.017104: step: 1288/530, loss: 0.08625183254480362
2023-01-21 13:36:34.134047: step: 1292/530, loss: 6.284713163040578e-05
2023-01-21 13:36:35.232477: step: 1296/530, loss: 0.03153266757726669
2023-01-21 13:36:36.323724: step: 1300/530, loss: 0.0030193328857421875
2023-01-21 13:36:37.416179: step: 1304/530, loss: 2.002716064453125e-05
2023-01-21 13:36:38.551336: step: 1308/530, loss: 0.016692256554961205
2023-01-21 13:36:39.638240: step: 1312/530, loss: 0.0019135475158691406
2023-01-21 13:36:40.752102: step: 1316/530, loss: 0.0013895034790039062
2023-01-21 13:36:41.904553: step: 1320/530, loss: 0.02096405066549778
2023-01-21 13:36:43.010190: step: 1324/530, loss: 0.001596736954525113
2023-01-21 13:36:44.113262: step: 1328/530, loss: 0.0001398086460540071
2023-01-21 13:36:45.234234: step: 1332/530, loss: 4.978180004400201e-05
2023-01-21 13:36:46.331223: step: 1336/530, loss: 0.00035411419230513275
2023-01-21 13:36:47.432746: step: 1340/530, loss: 7.052422006381676e-05
2023-01-21 13:36:48.556161: step: 1344/530, loss: 7.719993300270289e-05
2023-01-21 13:36:49.642550: step: 1348/530, loss: 0.05265455320477486
2023-01-21 13:36:50.743788: step: 1352/530, loss: 1.1539459592313506e-05
2023-01-21 13:36:51.851360: step: 1356/530, loss: 0.00043845176696777344
2023-01-21 13:36:52.973039: step: 1360/530, loss: 0.0018323898548260331
2023-01-21 13:36:54.076422: step: 1364/530, loss: 7.05719003235572e-06
2023-01-21 13:36:55.185859: step: 1368/530, loss: 0.00014791489229537547
2023-01-21 13:36:56.280041: step: 1372/530, loss: 0.00033206940861418843
2023-01-21 13:36:57.402911: step: 1376/530, loss: 0.0012651443248614669
2023-01-21 13:36:58.486037: step: 1380/530, loss: 0.006691169925034046
2023-01-21 13:36:59.607618: step: 1384/530, loss: 0.00017976760864257812
2023-01-21 13:37:00.685319: step: 1388/530, loss: 0.0006376266246661544
2023-01-21 13:37:01.810813: step: 1392/530, loss: 3.43322744811303e-06
2023-01-21 13:37:02.931198: step: 1396/530, loss: 0.0034801482688635588
2023-01-21 13:37:04.003526: step: 1400/530, loss: 0.00205574044957757
2023-01-21 13:37:05.115684: step: 1404/530, loss: 4.57763671875e-05
2023-01-21 13:37:06.201093: step: 1408/530, loss: 0.03355369344353676
2023-01-21 13:37:07.321621: step: 1412/530, loss: 5.7697296142578125e-05
2023-01-21 13:37:08.432264: step: 1416/530, loss: 0.0007795334095135331
2023-01-21 13:37:09.528828: step: 1420/530, loss: 3.814697265625e-06
2023-01-21 13:37:10.654047: step: 1424/530, loss: -6.389617738022935e-06
2023-01-21 13:37:11.756079: step: 1428/530, loss: 0.00022048951359465718
2023-01-21 13:37:12.842730: step: 1432/530, loss: 0.0369873046875
2023-01-21 13:37:13.937238: step: 1436/530, loss: 0.0006166458479128778
2023-01-21 13:37:15.039265: step: 1440/530, loss: 0.0008240699535235763
2023-01-21 13:37:16.169479: step: 1444/530, loss: 0.02875046618282795
2023-01-21 13:37:17.260437: step: 1448/530, loss: 9.012222108140122e-06
2023-01-21 13:37:18.364081: step: 1452/530, loss: 0.00011897087097167969
2023-01-21 13:37:19.470695: step: 1456/530, loss: 6.198883056640625e-06
2023-01-21 13:37:20.563992: step: 1460/530, loss: 0.0026089190505445004
2023-01-21 13:37:21.667065: step: 1464/530, loss: 0.0026412964798510075
2023-01-21 13:37:22.807539: step: 1468/530, loss: 0.013840675354003906
2023-01-21 13:37:23.924077: step: 1472/530, loss: 0.01151733472943306
2023-01-21 13:37:25.020802: step: 1476/530, loss: 4.00543194700731e-06
2023-01-21 13:37:26.133493: step: 1480/530, loss: 0.0010827063815668225
2023-01-21 13:37:27.256266: step: 1484/530, loss: 6.427765038097277e-05
2023-01-21 13:37:28.375956: step: 1488/530, loss: 3.776550147449598e-05
2023-01-21 13:37:29.443803: step: 1492/530, loss: 0.0004416942538227886
2023-01-21 13:37:30.568242: step: 1496/530, loss: -2.269744800287299e-05
2023-01-21 13:37:31.665522: step: 1500/530, loss: 1.029968279908644e-05
2023-01-21 13:37:32.797363: step: 1504/530, loss: 8.106231689453125e-05
2023-01-21 13:37:33.924939: step: 1508/530, loss: 0.0003513336123432964
2023-01-21 13:37:35.024969: step: 1512/530, loss: 3.385544005141128e-06
2023-01-21 13:37:36.144053: step: 1516/530, loss: 0.0001958847133209929
2023-01-21 13:37:37.259059: step: 1520/530, loss: 6.322861008811742e-05
2023-01-21 13:37:38.349946: step: 1524/530, loss: 3.5762786865234375e-05
2023-01-21 13:37:39.448248: step: 1528/530, loss: 0.0002197265566792339
2023-01-21 13:37:40.577165: step: 1532/530, loss: 0.023019982501864433
2023-01-21 13:37:41.680174: step: 1536/530, loss: 3.7765505112474784e-05
2023-01-21 13:37:42.802929: step: 1540/530, loss: 0.002713489579036832
2023-01-21 13:37:43.910125: step: 1544/530, loss: 8.878708467818797e-05
2023-01-21 13:37:45.019308: step: 1548/530, loss: 0.0007563590770587325
2023-01-21 13:37:46.153598: step: 1552/530, loss: 2.689361645025201e-05
2023-01-21 13:37:47.260937: step: 1556/530, loss: 0.004341316409409046
2023-01-21 13:37:48.378257: step: 1560/530, loss: -7.43865984986769e-06
2023-01-21 13:37:49.531188: step: 1564/530, loss: 0.000636196113191545
2023-01-21 13:37:50.648516: step: 1568/530, loss: 0.0011468887096270919
2023-01-21 13:37:51.776410: step: 1572/530, loss: 0.024539949372410774
2023-01-21 13:37:52.888397: step: 1576/530, loss: 0.003494834993034601
2023-01-21 13:37:54.023292: step: 1580/530, loss: 0.0003715515194926411
2023-01-21 13:37:55.148649: step: 1584/530, loss: 7.085800461936742e-05
2023-01-21 13:37:56.274287: step: 1588/530, loss: 9.52720656641759e-05
2023-01-21 13:37:57.377789: step: 1592/530, loss: 0.1194818913936615
2023-01-21 13:37:58.478251: step: 1596/530, loss: 0.006272125523537397
2023-01-21 13:37:59.622075: step: 1600/530, loss: 0.007403469178825617
2023-01-21 13:38:00.752410: step: 1604/530, loss: 0.0004604339774232358
2023-01-21 13:38:01.851360: step: 1608/530, loss: 0.6316318511962891
2023-01-21 13:38:02.988668: step: 1612/530, loss: 0.0007030487176962197
2023-01-21 13:38:04.114664: step: 1616/530, loss: 7.553100294899195e-05
2023-01-21 13:38:05.217464: step: 1620/530, loss: 0.00012130737013649195
2023-01-21 13:38:06.293443: step: 1624/530, loss: 4.310607982915826e-05
2023-01-21 13:38:07.394601: step: 1628/530, loss: 1.5783309208927676e-05
2023-01-21 13:38:08.489715: step: 1632/530, loss: 0.051241107285022736
2023-01-21 13:38:09.620510: step: 1636/530, loss: 2.155303991457913e-05
2023-01-21 13:38:10.730369: step: 1640/530, loss: 0.0011890887981280684
2023-01-21 13:38:11.848323: step: 1644/530, loss: 0.0010676385136321187
2023-01-21 13:38:12.973085: step: 1648/530, loss: 0.007977867498993874
2023-01-21 13:38:14.067387: step: 1652/530, loss: 0.0008755684248171747
2023-01-21 13:38:15.150043: step: 1656/530, loss: 0.02317504957318306
2023-01-21 13:38:16.265624: step: 1660/530, loss: 0.006262397859245539
2023-01-21 13:38:17.364891: step: 1664/530, loss: 0.0007551193120889366
2023-01-21 13:38:18.448473: step: 1668/530, loss: 4.425048973644152e-05
2023-01-21 13:38:19.542959: step: 1672/530, loss: 0.001087188720703125
2023-01-21 13:38:20.654403: step: 1676/530, loss: -1.411438006471144e-05
2023-01-21 13:38:21.761751: step: 1680/530, loss: 0.0006421089055947959
2023-01-21 13:38:22.894984: step: 1684/530, loss: 5.0354006816633046e-05
2023-01-21 13:38:23.997522: step: 1688/530, loss: 0.017382431775331497
2023-01-21 13:38:25.087846: step: 1692/530, loss: 3.814698175119702e-06
2023-01-21 13:38:26.197150: step: 1696/530, loss: 0.009712029248476028
2023-01-21 13:38:27.274534: step: 1700/530, loss: 0.0010938644409179688
2023-01-21 13:38:28.369583: step: 1704/530, loss: 3.1757354008732364e-05
2023-01-21 13:38:29.458450: step: 1708/530, loss: 0.0444524809718132
2023-01-21 13:38:30.561036: step: 1712/530, loss: 0.0024413110222667456
2023-01-21 13:38:31.673249: step: 1716/530, loss: 0.0006350517505779862
2023-01-21 13:38:32.779878: step: 1720/530, loss: 0.01232757605612278
2023-01-21 13:38:33.943136: step: 1724/530, loss: 0.03368110954761505
2023-01-21 13:38:35.056424: step: 1728/530, loss: 0.00010776519775390625
2023-01-21 13:38:36.172437: step: 1732/530, loss: 0.00019168853759765625
2023-01-21 13:38:37.290493: step: 1736/530, loss: 0.01845264434814453
2023-01-21 13:38:38.411165: step: 1740/530, loss: -2.6893614631262608e-05
2023-01-21 13:38:39.481527: step: 1744/530, loss: 1.9454957509879023e-05
2023-01-21 13:38:40.600412: step: 1748/530, loss: 0.0001947402924997732
2023-01-21 13:38:41.704591: step: 1752/530, loss: 0.08016948401927948
2023-01-21 13:38:42.794224: step: 1756/530, loss: 0.029342079535126686
2023-01-21 13:38:43.888529: step: 1760/530, loss: 0.07217636704444885
2023-01-21 13:38:45.008720: step: 1764/530, loss: 8.010864803509321e-06
2023-01-21 13:38:46.147448: step: 1768/530, loss: 7.410049147438258e-05
2023-01-21 13:38:47.248488: step: 1772/530, loss: 0.04358520731329918
2023-01-21 13:38:48.358939: step: 1776/530, loss: 0.02006387710571289
2023-01-21 13:38:49.455338: step: 1780/530, loss: 7.710456702625379e-05
2023-01-21 13:38:50.559332: step: 1784/530, loss: 0.0009565353393554688
2023-01-21 13:38:51.679208: step: 1788/530, loss: 0.0006052971002645791
2023-01-21 13:38:52.801250: step: 1792/530, loss: 9.059906005859375e-05
2023-01-21 13:38:53.889274: step: 1796/530, loss: 0.02305593527853489
2023-01-21 13:38:55.010271: step: 1800/530, loss: 7.104873657226562e-05
2023-01-21 13:38:56.108426: step: 1804/530, loss: 0.02657165564596653
2023-01-21 13:38:57.224952: step: 1808/530, loss: 0.04848675802350044
2023-01-21 13:38:58.358558: step: 1812/530, loss: 0.0006486892816610634
2023-01-21 13:38:59.471629: step: 1816/530, loss: 1.5163422176556196e-05
2023-01-21 13:39:00.572025: step: 1820/530, loss: 3.0934810638427734e-05
2023-01-21 13:39:01.713338: step: 1824/530, loss: 0.002617454621940851
2023-01-21 13:39:02.818176: step: 1828/530, loss: 0.0002020835963776335
2023-01-21 13:39:03.921466: step: 1832/530, loss: 0.00014572143845725805
2023-01-21 13:39:05.037246: step: 1836/530, loss: 3.070831371587701e-05
2023-01-21 13:39:06.136586: step: 1840/530, loss: 0.006595039740204811
2023-01-21 13:39:07.232881: step: 1844/530, loss: 3.24249276673072e-06
2023-01-21 13:39:08.324392: step: 1848/530, loss: 0.38332873582839966
2023-01-21 13:39:09.454292: step: 1852/530, loss: 8.754729788051918e-05
2023-01-21 13:39:10.543249: step: 1856/530, loss: 0.0014815331669524312
2023-01-21 13:39:11.618555: step: 1860/530, loss: 5.91278076171875e-05
2023-01-21 13:39:12.720275: step: 1864/530, loss: 1.220703143189894e-05
2023-01-21 13:39:13.805656: step: 1868/530, loss: 0.0001296043483307585
2023-01-21 13:39:14.915855: step: 1872/530, loss: 0.002555465791374445
2023-01-21 13:39:16.027873: step: 1876/530, loss: 0.12273406982421875
2023-01-21 13:39:17.151792: step: 1880/530, loss: 0.0011685371864587069
2023-01-21 13:39:18.279597: step: 1884/530, loss: 0.000613355659879744
2023-01-21 13:39:19.400738: step: 1888/530, loss: 1.2969970157428179e-05
2023-01-21 13:39:20.486082: step: 1892/530, loss: 2.6035308110294864e-05
2023-01-21 13:39:21.602334: step: 1896/530, loss: 0.00016312600928358734
2023-01-21 13:39:22.710159: step: 1900/530, loss: 0.0007160186651162803
2023-01-21 13:39:23.802696: step: 1904/530, loss: 0.000484657270135358
2023-01-21 13:39:24.921871: step: 1908/530, loss: 3.108978125965223e-05
2023-01-21 13:39:26.008104: step: 1912/530, loss: 0.0006547927623614669
2023-01-21 13:39:27.117827: step: 1916/530, loss: 0.0013147353893145919
2023-01-21 13:39:28.218444: step: 1920/530, loss: 0.00020065308490302414
2023-01-21 13:39:29.322294: step: 1924/530, loss: 0.0026014328468590975
2023-01-21 13:39:30.458251: step: 1928/530, loss: 0.0006048202631063759
2023-01-21 13:39:31.551076: step: 1932/530, loss: 0.0004174232599325478
2023-01-21 13:39:32.672337: step: 1936/530, loss: 0.009001731872558594
2023-01-21 13:39:33.779199: step: 1940/530, loss: 8.096695091808215e-05
2023-01-21 13:39:34.874087: step: 1944/530, loss: -2.002716064453125e-05
2023-01-21 13:39:35.963812: step: 1948/530, loss: 4.00543194700731e-06
2023-01-21 13:39:37.067019: step: 1952/530, loss: 3.948211815441027e-05
2023-01-21 13:39:38.157191: step: 1956/530, loss: 0.0002763748343568295
2023-01-21 13:39:39.271884: step: 1960/530, loss: 0.0001084327741409652
2023-01-21 13:39:40.373747: step: 1964/530, loss: 2.174377368646674e-05
2023-01-21 13:39:41.477967: step: 1968/530, loss: 4.76837158203125e-06
2023-01-21 13:39:42.571452: step: 1972/530, loss: 0.02414684370160103
2023-01-21 13:39:43.696544: step: 1976/530, loss: 0.00010356903658248484
2023-01-21 13:39:44.851054: step: 1980/530, loss: 4.711151268566027e-05
2023-01-21 13:39:45.981906: step: 1984/530, loss: 0.0009056091657839715
2023-01-21 13:39:47.123011: step: 1988/530, loss: -4.196166628389619e-06
2023-01-21 13:39:48.254445: step: 1992/530, loss: 0.0012894630199298263
2023-01-21 13:39:49.356403: step: 1996/530, loss: 0.00011959076800849289
2023-01-21 13:39:50.457026: step: 2000/530, loss: 0.004378605168312788
2023-01-21 13:39:51.556310: step: 2004/530, loss: 0.03665943443775177
2023-01-21 13:39:52.677190: step: 2008/530, loss: -8.01086389401462e-06
2023-01-21 13:39:53.789454: step: 2012/530, loss: -1.087188684323337e-05
2023-01-21 13:39:54.902260: step: 2016/530, loss: 0.02641754224896431
2023-01-21 13:39:56.015703: step: 2020/530, loss: 0.000179290771484375
2023-01-21 13:39:57.111820: step: 2024/530, loss: 0.00010614395432639867
2023-01-21 13:39:58.235214: step: 2028/530, loss: 1.00374218163779e-05
2023-01-21 13:39:59.352312: step: 2032/530, loss: 0.0001964569091796875
2023-01-21 13:40:00.503736: step: 2036/530, loss: 0.0001243591250386089
2023-01-21 13:40:01.605835: step: 2040/530, loss: 0.009293843060731888
2023-01-21 13:40:02.725163: step: 2044/530, loss: 0.0001361370086669922
2023-01-21 13:40:03.853460: step: 2048/530, loss: 0.0009220839128829539
2023-01-21 13:40:04.951426: step: 2052/530, loss: 6.0367583500919864e-05
2023-01-21 13:40:06.059914: step: 2056/530, loss: 0.03232908248901367
2023-01-21 13:40:07.159950: step: 2060/530, loss: 0.0002918243408203125
2023-01-21 13:40:08.300418: step: 2064/530, loss: 0.00020189284987282008
2023-01-21 13:40:09.426653: step: 2068/530, loss: 0.001088047050870955
2023-01-21 13:40:10.538923: step: 2072/530, loss: 0.0007814407581463456
2023-01-21 13:40:11.662909: step: 2076/530, loss: 0.003830432891845703
2023-01-21 13:40:12.766961: step: 2080/530, loss: 0.014248276129364967
2023-01-21 13:40:13.853205: step: 2084/530, loss: 0.0001605033758096397
2023-01-21 13:40:14.965610: step: 2088/530, loss: 0.0002109050692524761
2023-01-21 13:40:16.069385: step: 2092/530, loss: 0.002663230989128351
2023-01-21 13:40:17.252424: step: 2096/530, loss: 0.00017042159743141383
2023-01-21 13:40:18.358836: step: 2100/530, loss: 0.019017985090613365
2023-01-21 13:40:19.456213: step: 2104/530, loss: 0.057625580579042435
2023-01-21 13:40:20.586143: step: 2108/530, loss: 0.00010948180715786293
2023-01-21 13:40:21.706084: step: 2112/530, loss: 4.768372718899627e-08
2023-01-21 13:40:22.804198: step: 2116/530, loss: 0.00043277739314362407
2023-01-21 13:40:23.932985: step: 2120/530, loss: 3.4141543437726796e-05
==================================================
Loss: 0.010
--------------------
Dev: {'event': {'p': 0.6085594989561587, 'r': 0.7762982689747004, 'f1': 0.6822703335283792}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Test: {'event': {'p': 0.6420269642026964, 'r': 0.8047785547785548, 'f1': 0.7142487716576158}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Chinese: {'event': {'p': 0.5769230769230769, 'r': 0.8333333333333334, 'f1': 0.6818181818181818}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Korean: {'event': {'p': 0.6111111111111112, 'r': 0.5238095238095238, 'f1': 0.5641025641025642}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Russian: {'event': {'p': 0.475, 'r': 0.5277777777777778, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Korean: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}