Command that produces this log: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-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])
>>> trans_rep.weight: torch.Size([1024, 2048])
>>> trans_rep.bias: torch.Size([1024])
>>> hidden_ffns.Corruplate.layers.0.weight: torch.Size([768, 1024])
>>> hidden_ffns.Corruplate.layers.0.bias: torch.Size([768])
>>> hidden_ffns.Cybercrimeplate.layers.0.weight: torch.Size([768, 1024])
>>> hidden_ffns.Cybercrimeplate.layers.0.bias: torch.Size([768])
>>> hidden_ffns.Disasterplate.layers.0.weight: torch.Size([768, 1024])
>>> hidden_ffns.Disasterplate.layers.0.bias: torch.Size([768])
>>> hidden_ffns.Displacementplate.layers.0.weight: torch.Size([768, 1024])
>>> hidden_ffns.Displacementplate.layers.0.bias: torch.Size([768])
>>> hidden_ffns.Epidemiplate.layers.0.weight: torch.Size([768, 1024])
>>> hidden_ffns.Epidemiplate.layers.0.bias: torch.Size([768])
>>> hidden_ffns.Etiplate.layers.0.weight: torch.Size([768, 1024])
>>> hidden_ffns.Etiplate.layers.0.bias: torch.Size([768])
>>> hidden_ffns.Protestplate.layers.0.weight: torch.Size([768, 1024])
>>> hidden_ffns.Protestplate.layers.0.bias: torch.Size([768])
>>> hidden_ffns.Terrorplate.layers.0.weight: torch.Size([768, 1024])
>>> hidden_ffns.Terrorplate.layers.0.bias: torch.Size([768])
>>> template_classifiers.Corruplate.layers.0.weight: torch.Size([450, 768])
>>> template_classifiers.Corruplate.layers.0.bias: torch.Size([450])
>>> template_classifiers.Corruplate.layers.1.weight: torch.Size([2, 450])
>>> template_classifiers.Corruplate.layers.1.bias: torch.Size([2])
>>> template_classifiers.Cybercrimeplate.layers.0.weight: torch.Size([450, 768])
>>> template_classifiers.Cybercrimeplate.layers.0.bias: torch.Size([450])
>>> template_classifiers.Cybercrimeplate.layers.1.weight: torch.Size([2, 450])
>>> template_classifiers.Cybercrimeplate.layers.1.bias: torch.Size([2])
>>> template_classifiers.Disasterplate.layers.0.weight: torch.Size([450, 768])
>>> template_classifiers.Disasterplate.layers.0.bias: torch.Size([450])
>>> template_classifiers.Disasterplate.layers.1.weight: torch.Size([2, 450])
>>> template_classifiers.Disasterplate.layers.1.bias: torch.Size([2])
>>> template_classifiers.Displacementplate.layers.0.weight: torch.Size([450, 768])
>>> template_classifiers.Displacementplate.layers.0.bias: torch.Size([450])
>>> template_classifiers.Displacementplate.layers.1.weight: torch.Size([2, 450])
>>> template_classifiers.Displacementplate.layers.1.bias: torch.Size([2])
>>> template_classifiers.Epidemiplate.layers.0.weight: torch.Size([450, 768])
>>> template_classifiers.Epidemiplate.layers.0.bias: torch.Size([450])
>>> template_classifiers.Epidemiplate.layers.1.weight: torch.Size([2, 450])
>>> template_classifiers.Epidemiplate.layers.1.bias: torch.Size([2])
>>> template_classifiers.Etiplate.layers.0.weight: torch.Size([450, 768])
>>> template_classifiers.Etiplate.layers.0.bias: torch.Size([450])
>>> template_classifiers.Etiplate.layers.1.weight: torch.Size([2, 450])
>>> template_classifiers.Etiplate.layers.1.bias: torch.Size([2])
>>> template_classifiers.Protestplate.layers.0.weight: torch.Size([450, 768])
>>> template_classifiers.Protestplate.layers.0.bias: torch.Size([450])
>>> template_classifiers.Protestplate.layers.1.weight: torch.Size([2, 450])
>>> template_classifiers.Protestplate.layers.1.bias: torch.Size([2])
>>> template_classifiers.Terrorplate.layers.0.weight: torch.Size([450, 768])
>>> template_classifiers.Terrorplate.layers.0.bias: torch.Size([450])
>>> template_classifiers.Terrorplate.layers.1.weight: torch.Size([2, 450])
>>> template_classifiers.Terrorplate.layers.1.bias: torch.Size([2])
>>> type_classifiers.Corruplate.layers.0.weight: torch.Size([450, 768])
>>> type_classifiers.Corruplate.layers.0.bias: torch.Size([450])
>>> type_classifiers.Corruplate.layers.1.weight: torch.Size([6, 450])
>>> type_classifiers.Corruplate.layers.1.bias: torch.Size([6])
>>> type_classifiers.Cybercrimeplate.layers.0.weight: torch.Size([450, 768])
>>> type_classifiers.Cybercrimeplate.layers.0.bias: torch.Size([450])
>>> type_classifiers.Cybercrimeplate.layers.1.weight: torch.Size([6, 450])
>>> type_classifiers.Cybercrimeplate.layers.1.bias: torch.Size([6])
>>> type_classifiers.Disasterplate.layers.0.weight: torch.Size([450, 768])
>>> type_classifiers.Disasterplate.layers.0.bias: torch.Size([450])
>>> type_classifiers.Disasterplate.layers.1.weight: torch.Size([6, 450])
>>> type_classifiers.Disasterplate.layers.1.bias: torch.Size([6])
>>> type_classifiers.Displacementplate.layers.0.weight: torch.Size([450, 768])
>>> type_classifiers.Displacementplate.layers.0.bias: torch.Size([450])
>>> type_classifiers.Displacementplate.layers.1.weight: torch.Size([6, 450])
>>> type_classifiers.Displacementplate.layers.1.bias: torch.Size([6])
>>> type_classifiers.Epidemiplate.layers.0.weight: torch.Size([450, 768])
>>> type_classifiers.Epidemiplate.layers.0.bias: torch.Size([450])
>>> type_classifiers.Epidemiplate.layers.1.weight: torch.Size([6, 450])
>>> type_classifiers.Epidemiplate.layers.1.bias: torch.Size([6])
>>> type_classifiers.Etiplate.layers.0.weight: torch.Size([450, 768])
>>> type_classifiers.Etiplate.layers.0.bias: torch.Size([450])
>>> type_classifiers.Etiplate.layers.1.weight: torch.Size([6, 450])
>>> type_classifiers.Etiplate.layers.1.bias: torch.Size([6])
>>> type_classifiers.Protestplate.layers.0.weight: torch.Size([450, 768])
>>> type_classifiers.Protestplate.layers.0.bias: torch.Size([450])
>>> type_classifiers.Protestplate.layers.1.weight: torch.Size([6, 450])
>>> type_classifiers.Protestplate.layers.1.bias: torch.Size([6])
>>> type_classifiers.Terrorplate.layers.0.weight: torch.Size([450, 768])
>>> type_classifiers.Terrorplate.layers.0.bias: torch.Size([450])
>>> type_classifiers.Terrorplate.layers.1.weight: torch.Size([6, 450])
>>> type_classifiers.Terrorplate.layers.1.bias: torch.Size([6])
>>> completion_classifiers.Corruplate.layers.0.weight: torch.Size([450, 768])
>>> completion_classifiers.Corruplate.layers.0.bias: torch.Size([450])
>>> completion_classifiers.Corruplate.layers.1.weight: torch.Size([4, 450])
>>> completion_classifiers.Corruplate.layers.1.bias: torch.Size([4])
>>> completion_classifiers.Cybercrimeplate.layers.0.weight: torch.Size([450, 768])
>>> completion_classifiers.Cybercrimeplate.layers.0.bias: torch.Size([450])
>>> completion_classifiers.Cybercrimeplate.layers.1.weight: torch.Size([4, 450])
>>> completion_classifiers.Cybercrimeplate.layers.1.bias: torch.Size([4])
>>> completion_classifiers.Disasterplate.layers.0.weight: torch.Size([450, 768])
>>> completion_classifiers.Disasterplate.layers.0.bias: torch.Size([450])
>>> completion_classifiers.Disasterplate.layers.1.weight: torch.Size([4, 450])
>>> completion_classifiers.Disasterplate.layers.1.bias: torch.Size([4])
>>> completion_classifiers.Displacementplate.layers.0.weight: torch.Size([450, 768])
>>> completion_classifiers.Displacementplate.layers.0.bias: torch.Size([450])
>>> completion_classifiers.Displacementplate.layers.1.weight: torch.Size([4, 450])
>>> completion_classifiers.Displacementplate.layers.1.bias: torch.Size([4])
>>> completion_classifiers.Epidemiplate.layers.0.weight: torch.Size([450, 768])
>>> completion_classifiers.Epidemiplate.layers.0.bias: torch.Size([450])
>>> completion_classifiers.Epidemiplate.layers.1.weight: torch.Size([4, 450])
>>> completion_classifiers.Epidemiplate.layers.1.bias: torch.Size([4])
>>> completion_classifiers.Etiplate.layers.0.weight: torch.Size([450, 768])
>>> completion_classifiers.Etiplate.layers.0.bias: torch.Size([450])
>>> completion_classifiers.Etiplate.layers.1.weight: torch.Size([4, 450])
>>> completion_classifiers.Etiplate.layers.1.bias: torch.Size([4])
>>> completion_classifiers.Protestplate.layers.0.weight: torch.Size([450, 768])
>>> completion_classifiers.Protestplate.layers.0.bias: torch.Size([450])
>>> completion_classifiers.Protestplate.layers.1.weight: torch.Size([4, 450])
>>> completion_classifiers.Protestplate.layers.1.bias: torch.Size([4])
>>> completion_classifiers.Terrorplate.layers.0.weight: torch.Size([450, 768])
>>> completion_classifiers.Terrorplate.layers.0.bias: torch.Size([450])
>>> completion_classifiers.Terrorplate.layers.1.weight: torch.Size([4, 450])
>>> completion_classifiers.Terrorplate.layers.1.bias: torch.Size([4])
>>> overtime_classifiers.Corruplate.layers.0.weight: torch.Size([450, 768])
>>> overtime_classifiers.Corruplate.layers.0.bias: torch.Size([450])
>>> overtime_classifiers.Corruplate.layers.1.weight: torch.Size([2, 450])
>>> overtime_classifiers.Corruplate.layers.1.bias: torch.Size([2])
>>> overtime_classifiers.Cybercrimeplate.layers.0.weight: torch.Size([450, 768])
>>> overtime_classifiers.Cybercrimeplate.layers.0.bias: torch.Size([450])
>>> overtime_classifiers.Cybercrimeplate.layers.1.weight: torch.Size([2, 450])
>>> overtime_classifiers.Cybercrimeplate.layers.1.bias: torch.Size([2])
>>> overtime_classifiers.Disasterplate.layers.0.weight: torch.Size([450, 768])
>>> overtime_classifiers.Disasterplate.layers.0.bias: torch.Size([450])
>>> overtime_classifiers.Disasterplate.layers.1.weight: torch.Size([2, 450])
>>> overtime_classifiers.Disasterplate.layers.1.bias: torch.Size([2])
>>> overtime_classifiers.Displacementplate.layers.0.weight: torch.Size([450, 768])
>>> overtime_classifiers.Displacementplate.layers.0.bias: torch.Size([450])
>>> overtime_classifiers.Displacementplate.layers.1.weight: torch.Size([2, 450])
>>> overtime_classifiers.Displacementplate.layers.1.bias: torch.Size([2])
>>> overtime_classifiers.Epidemiplate.layers.0.weight: torch.Size([450, 768])
>>> overtime_classifiers.Epidemiplate.layers.0.bias: torch.Size([450])
>>> overtime_classifiers.Epidemiplate.layers.1.weight: torch.Size([2, 450])
>>> overtime_classifiers.Epidemiplate.layers.1.bias: torch.Size([2])
>>> overtime_classifiers.Etiplate.layers.0.weight: torch.Size([450, 768])
>>> overtime_classifiers.Etiplate.layers.0.bias: torch.Size([450])
>>> overtime_classifiers.Etiplate.layers.1.weight: torch.Size([2, 450])
>>> overtime_classifiers.Etiplate.layers.1.bias: torch.Size([2])
>>> overtime_classifiers.Protestplate.layers.0.weight: torch.Size([450, 768])
>>> overtime_classifiers.Protestplate.layers.0.bias: torch.Size([450])
>>> overtime_classifiers.Protestplate.layers.1.weight: torch.Size([2, 450])
>>> overtime_classifiers.Protestplate.layers.1.bias: torch.Size([2])
>>> overtime_classifiers.Terrorplate.layers.0.weight: torch.Size([450, 768])
>>> overtime_classifiers.Terrorplate.layers.0.bias: torch.Size([450])
>>> overtime_classifiers.Terrorplate.layers.1.weight: torch.Size([2, 450])
>>> overtime_classifiers.Terrorplate.layers.1.bias: torch.Size([2])
>>> coordinated_classifiers.Corruplate.layers.0.weight: torch.Size([450, 768])
>>> coordinated_classifiers.Corruplate.layers.0.bias: torch.Size([450])
>>> coordinated_classifiers.Corruplate.layers.1.weight: torch.Size([2, 450])
>>> coordinated_classifiers.Corruplate.layers.1.bias: torch.Size([2])
>>> coordinated_classifiers.Cybercrimeplate.layers.0.weight: torch.Size([450, 768])
>>> coordinated_classifiers.Cybercrimeplate.layers.0.bias: torch.Size([450])
>>> coordinated_classifiers.Cybercrimeplate.layers.1.weight: torch.Size([2, 450])
>>> coordinated_classifiers.Cybercrimeplate.layers.1.bias: torch.Size([2])
>>> coordinated_classifiers.Disasterplate.layers.0.weight: torch.Size([450, 768])
>>> coordinated_classifiers.Disasterplate.layers.0.bias: torch.Size([450])
>>> coordinated_classifiers.Disasterplate.layers.1.weight: torch.Size([2, 450])
>>> coordinated_classifiers.Disasterplate.layers.1.bias: torch.Size([2])
>>> coordinated_classifiers.Displacementplate.layers.0.weight: torch.Size([450, 768])
>>> coordinated_classifiers.Displacementplate.layers.0.bias: torch.Size([450])
>>> coordinated_classifiers.Displacementplate.layers.1.weight: torch.Size([2, 450])
>>> coordinated_classifiers.Displacementplate.layers.1.bias: torch.Size([2])
>>> coordinated_classifiers.Epidemiplate.layers.0.weight: torch.Size([450, 768])
>>> coordinated_classifiers.Epidemiplate.layers.0.bias: torch.Size([450])
>>> coordinated_classifiers.Epidemiplate.layers.1.weight: torch.Size([2, 450])
>>> coordinated_classifiers.Epidemiplate.layers.1.bias: torch.Size([2])
>>> coordinated_classifiers.Etiplate.layers.0.weight: torch.Size([450, 768])
>>> coordinated_classifiers.Etiplate.layers.0.bias: torch.Size([450])
>>> coordinated_classifiers.Etiplate.layers.1.weight: torch.Size([2, 450])
>>> coordinated_classifiers.Etiplate.layers.1.bias: torch.Size([2])
>>> coordinated_classifiers.Protestplate.layers.0.weight: torch.Size([450, 768])
>>> coordinated_classifiers.Protestplate.layers.0.bias: torch.Size([450])
>>> coordinated_classifiers.Protestplate.layers.1.weight: torch.Size([2, 450])
>>> coordinated_classifiers.Protestplate.layers.1.bias: torch.Size([2])
>>> coordinated_classifiers.Terrorplate.layers.0.weight: torch.Size([450, 768])
>>> coordinated_classifiers.Terrorplate.layers.0.bias: torch.Size([450])
>>> coordinated_classifiers.Terrorplate.layers.1.weight: torch.Size([2, 450])
>>> coordinated_classifiers.Terrorplate.layers.1.bias: torch.Size([2])
n_trainable_params: 582185936, n_nontrainable_params: 0
----------------------------------------------------------------------------------------------------
******************************
Epoch: 0
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 07:08:52.893130: step: 4/77, loss: 1.0617469549179077
2023-01-22 07:08:54.162231: step: 8/77, loss: 1.071832537651062
2023-01-22 07:08:55.404930: step: 12/77, loss: 1.0500397682189941
2023-01-22 07:08:56.714220: step: 16/77, loss: 1.0569696426391602
2023-01-22 07:08:58.043500: step: 20/77, loss: 1.036795973777771
2023-01-22 07:08:59.403772: step: 24/77, loss: 1.053377628326416
2023-01-22 07:09:00.722331: step: 28/77, loss: 1.0394463539123535
2023-01-22 07:09:02.040397: step: 32/77, loss: 1.0370593070983887
2023-01-22 07:09:03.341771: step: 36/77, loss: 1.0463190078735352
2023-01-22 07:09:04.643713: step: 40/77, loss: 1.0341830253601074
2023-01-22 07:09:05.909549: step: 44/77, loss: 1.01943039894104
2023-01-22 07:09:07.147464: step: 48/77, loss: 1.0161728858947754
2023-01-22 07:09:08.397231: step: 52/77, loss: 0.9935738444328308
2023-01-22 07:09:09.677950: step: 56/77, loss: 0.9947496652603149
2023-01-22 07:09:10.958494: step: 60/77, loss: 0.9947984218597412
2023-01-22 07:09:12.306315: step: 64/77, loss: 0.9740759134292603
2023-01-22 07:09:13.578317: step: 68/77, loss: 0.9578840732574463
2023-01-22 07:09:14.885296: step: 72/77, loss: 0.958991527557373
2023-01-22 07:09:16.190767: step: 76/77, loss: 0.9292556047439575
2023-01-22 07:09:17.533417: step: 80/77, loss: 0.9261636734008789
2023-01-22 07:09:18.815347: step: 84/77, loss: 0.9224743247032166
2023-01-22 07:09:20.142379: step: 88/77, loss: 0.9078954458236694
2023-01-22 07:09:21.493469: step: 92/77, loss: 0.8906626105308533
2023-01-22 07:09:22.779459: step: 96/77, loss: 0.8689224720001221
2023-01-22 07:09:24.090443: step: 100/77, loss: 0.8581384420394897
2023-01-22 07:09:25.414162: step: 104/77, loss: 0.8440836668014526
2023-01-22 07:09:26.738558: step: 108/77, loss: 0.8239055871963501
2023-01-22 07:09:28.028607: step: 112/77, loss: 0.7871434688568115
2023-01-22 07:09:29.310515: step: 116/77, loss: 0.7866687178611755
2023-01-22 07:09:30.616077: step: 120/77, loss: 0.8152998685836792
2023-01-22 07:09:31.920679: step: 124/77, loss: 0.7473165988922119
2023-01-22 07:09:33.274874: step: 128/77, loss: 0.7465535402297974
2023-01-22 07:09:34.553341: step: 132/77, loss: 0.7344512939453125
2023-01-22 07:09:35.866585: step: 136/77, loss: 0.6562771797180176
2023-01-22 07:09:37.188654: step: 140/77, loss: 0.7067196369171143
2023-01-22 07:09:38.532789: step: 144/77, loss: 0.6306025981903076
2023-01-22 07:09:39.835179: step: 148/77, loss: 0.6918684244155884
2023-01-22 07:09:41.215879: step: 152/77, loss: 0.5625179409980774
2023-01-22 07:09:42.562812: step: 156/77, loss: 0.5566755533218384
2023-01-22 07:09:43.880650: step: 160/77, loss: 0.5231382846832275
2023-01-22 07:09:45.237616: step: 164/77, loss: 0.5328485369682312
2023-01-22 07:09:46.497796: step: 168/77, loss: 0.5300477147102356
2023-01-22 07:09:47.794077: step: 172/77, loss: 0.4442155957221985
2023-01-22 07:09:49.082777: step: 176/77, loss: 0.4701414108276367
2023-01-22 07:09:50.368120: step: 180/77, loss: 0.45259642601013184
2023-01-22 07:09:51.639238: step: 184/77, loss: 0.3861841559410095
2023-01-22 07:09:52.917229: step: 188/77, loss: 0.4100555181503296
2023-01-22 07:09:54.220589: step: 192/77, loss: 0.3761431574821472
2023-01-22 07:09:55.548069: step: 196/77, loss: 0.48926883935928345
2023-01-22 07:09:56.879503: step: 200/77, loss: 0.3657160997390747
2023-01-22 07:09:58.214044: step: 204/77, loss: 0.314441055059433
2023-01-22 07:09:59.524866: step: 208/77, loss: 0.2680244743824005
2023-01-22 07:10:00.831989: step: 212/77, loss: 0.2731962502002716
2023-01-22 07:10:02.128947: step: 216/77, loss: 0.22471654415130615
2023-01-22 07:10:03.454176: step: 220/77, loss: 0.26468920707702637
2023-01-22 07:10:04.781479: step: 224/77, loss: 0.20208311080932617
2023-01-22 07:10:06.087821: step: 228/77, loss: 0.24795040488243103
2023-01-22 07:10:07.402426: step: 232/77, loss: 0.23075196146965027
2023-01-22 07:10:08.673249: step: 236/77, loss: 0.20327256619930267
2023-01-22 07:10:09.995248: step: 240/77, loss: 0.17273639142513275
2023-01-22 07:10:11.323577: step: 244/77, loss: 0.1513095498085022
2023-01-22 07:10:12.633779: step: 248/77, loss: 0.17677460610866547
2023-01-22 07:10:13.937355: step: 252/77, loss: 0.10056942701339722
2023-01-22 07:10:15.211168: step: 256/77, loss: 0.09389781951904297
2023-01-22 07:10:16.520970: step: 260/77, loss: 0.11536524444818497
2023-01-22 07:10:17.812066: step: 264/77, loss: 0.17818987369537354
2023-01-22 07:10:19.091578: step: 268/77, loss: 0.23469536006450653
2023-01-22 07:10:20.403383: step: 272/77, loss: 0.16398277878761292
2023-01-22 07:10:21.696174: step: 276/77, loss: 0.27092573046684265
2023-01-22 07:10:22.956012: step: 280/77, loss: 0.15249253809452057
2023-01-22 07:10:24.207220: step: 284/77, loss: 0.14844149351119995
2023-01-22 07:10:25.507519: step: 288/77, loss: 0.034965530037879944
2023-01-22 07:10:26.861519: step: 292/77, loss: 0.19286976754665375
2023-01-22 07:10:28.148278: step: 296/77, loss: 0.13884218037128448
2023-01-22 07:10:29.453245: step: 300/77, loss: 0.05468413233757019
2023-01-22 07:10:30.749059: step: 304/77, loss: 0.2615947425365448
2023-01-22 07:10:32.047828: step: 308/77, loss: 0.06353268027305603
2023-01-22 07:10:33.337525: step: 312/77, loss: 0.3093520402908325
2023-01-22 07:10:34.663847: step: 316/77, loss: 0.13308614492416382
2023-01-22 07:10:35.930327: step: 320/77, loss: 0.0702965259552002
2023-01-22 07:10:37.252929: step: 324/77, loss: 0.09301605820655823
2023-01-22 07:10:38.543066: step: 328/77, loss: 0.0733005702495575
2023-01-22 07:10:39.807030: step: 332/77, loss: 0.10775697976350784
2023-01-22 07:10:41.096357: step: 336/77, loss: 0.08684641122817993
2023-01-22 07:10:42.416227: step: 340/77, loss: 0.07254372537136078
2023-01-22 07:10:43.725912: step: 344/77, loss: 0.11763302981853485
2023-01-22 07:10:44.988089: step: 348/77, loss: 0.16487447917461395
2023-01-22 07:10:46.264963: step: 352/77, loss: 0.08935951441526413
2023-01-22 07:10:47.549792: step: 356/77, loss: 0.08099295198917389
2023-01-22 07:10:48.836034: step: 360/77, loss: 0.07289375364780426
2023-01-22 07:10:50.103969: step: 364/77, loss: 0.07927817851305008
2023-01-22 07:10:51.417887: step: 368/77, loss: 0.06166777387261391
2023-01-22 07:10:52.706395: step: 372/77, loss: 0.1259939819574356
2023-01-22 07:10:54.006446: step: 376/77, loss: 0.36279356479644775
2023-01-22 07:10:55.266712: step: 380/77, loss: 0.035687074065208435
2023-01-22 07:10:56.577458: step: 384/77, loss: 0.11559747159481049
2023-01-22 07:10:57.877237: step: 388/77, loss: 0.12898707389831543
==================================================
Loss: 0.485
--------------------
Dev Chinese: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test Chinese: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Dev Korean: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test Korean: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Dev Russian: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test Russian: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Chinese: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Korean: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Russian: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'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:
--------------------
Dev for Chinese: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Chinese: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test for Korean: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Korean: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test for Russian: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Russian: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
******************************
Epoch: 1
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 07:12:51.304624: step: 4/77, loss: 0.11158759146928787
2023-01-22 07:12:52.572935: step: 8/77, loss: 0.19867026805877686
2023-01-22 07:12:53.851427: step: 12/77, loss: 0.058240726590156555
2023-01-22 07:12:55.164082: step: 16/77, loss: 0.20178799331188202
2023-01-22 07:12:56.463199: step: 20/77, loss: 0.02973691187798977
2023-01-22 07:12:57.759988: step: 24/77, loss: 0.0995328426361084
2023-01-22 07:12:59.069632: step: 28/77, loss: 0.1865939050912857
2023-01-22 07:13:00.378494: step: 32/77, loss: 0.1807020604610443
2023-01-22 07:13:01.666172: step: 36/77, loss: 0.0407174676656723
2023-01-22 07:13:02.963827: step: 40/77, loss: 0.10385138541460037
2023-01-22 07:13:04.232251: step: 44/77, loss: 0.08694268763065338
2023-01-22 07:13:05.510799: step: 48/77, loss: 0.09504902362823486
2023-01-22 07:13:06.789686: step: 52/77, loss: 0.10106496512889862
2023-01-22 07:13:08.068574: step: 56/77, loss: 0.05474689230322838
2023-01-22 07:13:09.344572: step: 60/77, loss: 0.1368316113948822
2023-01-22 07:13:10.639229: step: 64/77, loss: 0.13929077982902527
2023-01-22 07:13:11.965602: step: 68/77, loss: 0.2764717638492584
2023-01-22 07:13:13.234057: step: 72/77, loss: 0.08261242508888245
2023-01-22 07:13:14.478464: step: 76/77, loss: 0.1324632167816162
2023-01-22 07:13:15.783296: step: 80/77, loss: 0.15174496173858643
2023-01-22 07:13:17.098648: step: 84/77, loss: 0.11399096250534058
2023-01-22 07:13:18.347946: step: 88/77, loss: 0.07976777851581573
2023-01-22 07:13:19.649622: step: 92/77, loss: 0.04927085340023041
2023-01-22 07:13:20.911768: step: 96/77, loss: 0.1352429986000061
2023-01-22 07:13:22.187729: step: 100/77, loss: 0.07732612639665604
2023-01-22 07:13:23.557105: step: 104/77, loss: 0.09204569458961487
2023-01-22 07:13:24.845557: step: 108/77, loss: 0.14470499753952026
2023-01-22 07:13:26.134212: step: 112/77, loss: 0.08708120137453079
2023-01-22 07:13:27.438934: step: 116/77, loss: 0.21689417958259583
2023-01-22 07:13:28.747367: step: 120/77, loss: 0.18309366703033447
2023-01-22 07:13:30.040661: step: 124/77, loss: 0.10907326638698578
2023-01-22 07:13:31.321431: step: 128/77, loss: 0.06838659197092056
2023-01-22 07:13:32.581904: step: 132/77, loss: 0.09328626841306686
2023-01-22 07:13:33.849009: step: 136/77, loss: 0.06526198983192444
2023-01-22 07:13:35.128933: step: 140/77, loss: 0.10818645358085632
2023-01-22 07:13:36.412223: step: 144/77, loss: 0.1860373616218567
2023-01-22 07:13:37.673045: step: 148/77, loss: 0.07784507423639297
2023-01-22 07:13:38.964648: step: 152/77, loss: 0.08227992057800293
2023-01-22 07:13:40.224155: step: 156/77, loss: 0.08509774506092072
2023-01-22 07:13:41.495600: step: 160/77, loss: 0.04389530420303345
2023-01-22 07:13:42.779313: step: 164/77, loss: 0.08508370816707611
2023-01-22 07:13:44.096387: step: 168/77, loss: 0.10564348101615906
2023-01-22 07:13:45.403791: step: 172/77, loss: 0.20949102938175201
2023-01-22 07:13:46.701030: step: 176/77, loss: 0.054892972111701965
2023-01-22 07:13:48.024495: step: 180/77, loss: 0.2804702818393707
2023-01-22 07:13:49.236569: step: 184/77, loss: 0.029961321502923965
2023-01-22 07:13:50.576936: step: 188/77, loss: 0.03746054694056511
2023-01-22 07:13:51.869693: step: 192/77, loss: 0.10914406180381775
2023-01-22 07:13:53.177347: step: 196/77, loss: 0.04498276859521866
2023-01-22 07:13:54.437434: step: 200/77, loss: 0.08990252017974854
2023-01-22 07:13:55.700840: step: 204/77, loss: 0.09215635806322098
2023-01-22 07:13:56.988631: step: 208/77, loss: 0.2269093245267868
2023-01-22 07:13:58.287910: step: 212/77, loss: 0.25756344199180603
2023-01-22 07:13:59.591185: step: 216/77, loss: 0.1051335409283638
2023-01-22 07:14:00.910205: step: 220/77, loss: 0.07337190210819244
2023-01-22 07:14:02.150067: step: 224/77, loss: 0.10456050932407379
2023-01-22 07:14:03.460903: step: 228/77, loss: 0.07801325619220734
2023-01-22 07:14:04.784543: step: 232/77, loss: 0.13213995099067688
2023-01-22 07:14:06.072220: step: 236/77, loss: 0.10130394995212555
2023-01-22 07:14:07.387746: step: 240/77, loss: 0.16945858299732208
2023-01-22 07:14:08.656009: step: 244/77, loss: 0.03165304660797119
2023-01-22 07:14:09.889528: step: 248/77, loss: 0.10367722809314728
2023-01-22 07:14:11.121425: step: 252/77, loss: 0.12703952193260193
2023-01-22 07:14:12.426518: step: 256/77, loss: 0.0646631270647049
2023-01-22 07:14:13.731322: step: 260/77, loss: 0.09364254027605057
2023-01-22 07:14:15.007351: step: 264/77, loss: 0.09511947631835938
2023-01-22 07:14:16.287897: step: 268/77, loss: 0.08383557200431824
2023-01-22 07:14:17.585162: step: 272/77, loss: 0.07730644941329956
2023-01-22 07:14:18.886866: step: 276/77, loss: 0.1986403912305832
2023-01-22 07:14:20.216773: step: 280/77, loss: 0.056749798357486725
2023-01-22 07:14:21.538121: step: 284/77, loss: 0.07241851091384888
2023-01-22 07:14:22.853277: step: 288/77, loss: 0.048592459410429
2023-01-22 07:14:24.177886: step: 292/77, loss: 0.1085418313741684
2023-01-22 07:14:25.505806: step: 296/77, loss: 0.06122410297393799
2023-01-22 07:14:26.827861: step: 300/77, loss: 0.07612358033657074
2023-01-22 07:14:28.132983: step: 304/77, loss: 0.047660645097494125
2023-01-22 07:14:29.396388: step: 308/77, loss: 0.08316922932863235
2023-01-22 07:14:30.667191: step: 312/77, loss: 0.11238834261894226
2023-01-22 07:14:31.971750: step: 316/77, loss: 0.1417194902896881
2023-01-22 07:14:33.224471: step: 320/77, loss: 0.12480755150318146
2023-01-22 07:14:34.500577: step: 324/77, loss: 0.05285458266735077
2023-01-22 07:14:35.808600: step: 328/77, loss: 0.16706568002700806
2023-01-22 07:14:37.084689: step: 332/77, loss: 0.13593162596225739
2023-01-22 07:14:38.425276: step: 336/77, loss: 0.07430271804332733
2023-01-22 07:14:39.728013: step: 340/77, loss: 0.05810857564210892
2023-01-22 07:14:41.027047: step: 344/77, loss: 0.1264181137084961
2023-01-22 07:14:42.319525: step: 348/77, loss: 0.05887303501367569
2023-01-22 07:14:43.604132: step: 352/77, loss: 0.1920332908630371
2023-01-22 07:14:44.904111: step: 356/77, loss: 0.03397180885076523
2023-01-22 07:14:46.205197: step: 360/77, loss: 0.061011020094156265
2023-01-22 07:14:47.489247: step: 364/77, loss: 0.06792081892490387
2023-01-22 07:14:48.776268: step: 368/77, loss: 0.10783128440380096
2023-01-22 07:14:50.113828: step: 372/77, loss: 0.05417155474424362
2023-01-22 07:14:51.433025: step: 376/77, loss: 0.0812927782535553
2023-01-22 07:14:52.746640: step: 380/77, loss: 0.06356360018253326
2023-01-22 07:14:54.040895: step: 384/77, loss: 0.07857591658830643
2023-01-22 07:14:55.346960: step: 388/77, loss: 0.05766603723168373
==================================================
Loss: 0.106
--------------------
Dev Chinese: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Test Chinese: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Dev Korean: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Test Korean: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Dev Russian: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Test Russian: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Chinese: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Chinese: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test for Korean: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Korean: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test for Russian: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Russian: {'template': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
******************************
Epoch: 2
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 07:16:31.824762: step: 4/77, loss: 0.11322622001171112
2023-01-22 07:16:33.138290: step: 8/77, loss: 0.10179299116134644
2023-01-22 07:16:34.426109: step: 12/77, loss: 0.06799320876598358
2023-01-22 07:16:35.689018: step: 16/77, loss: 0.15302878618240356
2023-01-22 07:16:36.951790: step: 20/77, loss: 0.11456996202468872
2023-01-22 07:16:38.275036: step: 24/77, loss: 0.06971030682325363
2023-01-22 07:16:39.572398: step: 28/77, loss: 0.09485167264938354
2023-01-22 07:16:40.872259: step: 32/77, loss: 0.09777399897575378
2023-01-22 07:16:42.170731: step: 36/77, loss: 0.04542500525712967
2023-01-22 07:16:43.470850: step: 40/77, loss: 0.10130670666694641
2023-01-22 07:16:44.764773: step: 44/77, loss: 0.04343476518988609
2023-01-22 07:16:46.059922: step: 48/77, loss: 0.2175489366054535
2023-01-22 07:16:47.341241: step: 52/77, loss: 0.04697784036397934
2023-01-22 07:16:48.623007: step: 56/77, loss: 0.11778730154037476
2023-01-22 07:16:49.885134: step: 60/77, loss: 0.056548308581113815
2023-01-22 07:16:51.168955: step: 64/77, loss: 0.01581401564180851
2023-01-22 07:16:52.422405: step: 68/77, loss: 0.05202740058302879
2023-01-22 07:16:53.656251: step: 72/77, loss: 0.06093277037143707
2023-01-22 07:16:54.927276: step: 76/77, loss: 0.02446526102721691
2023-01-22 07:16:56.218287: step: 80/77, loss: 0.06041073054075241
2023-01-22 07:16:57.464448: step: 84/77, loss: 0.04046632722020149
2023-01-22 07:16:58.759467: step: 88/77, loss: 0.07183364033699036
2023-01-22 07:17:00.065777: step: 92/77, loss: 0.10985290259122849
2023-01-22 07:17:01.327008: step: 96/77, loss: 0.06694649904966354
2023-01-22 07:17:02.648753: step: 100/77, loss: 0.04028739407658577
2023-01-22 07:17:03.900229: step: 104/77, loss: 0.07630635052919388
2023-01-22 07:17:05.204201: step: 108/77, loss: 0.03472098335623741
2023-01-22 07:17:06.478627: step: 112/77, loss: 0.12241032719612122
2023-01-22 07:17:07.791635: step: 116/77, loss: 0.02490338310599327
2023-01-22 07:17:09.089799: step: 120/77, loss: 0.1250462681055069
2023-01-22 07:17:10.379363: step: 124/77, loss: 0.05550193041563034
2023-01-22 07:17:11.683331: step: 128/77, loss: 0.01295685488730669
2023-01-22 07:17:12.962672: step: 132/77, loss: 0.03971627354621887
2023-01-22 07:17:14.241807: step: 136/77, loss: 0.10844653099775314
2023-01-22 07:17:15.537563: step: 140/77, loss: 0.0835656076669693
2023-01-22 07:17:16.867004: step: 144/77, loss: 0.04878070205450058
2023-01-22 07:17:18.158366: step: 148/77, loss: 0.0661730170249939
2023-01-22 07:17:19.427284: step: 152/77, loss: 0.07241643965244293
2023-01-22 07:17:20.705577: step: 156/77, loss: 0.01513383537530899
2023-01-22 07:17:22.013018: step: 160/77, loss: 0.021579544991254807
2023-01-22 07:17:23.343926: step: 164/77, loss: 0.04571843147277832
2023-01-22 07:17:24.664532: step: 168/77, loss: 0.05205213278532028
2023-01-22 07:17:25.957647: step: 172/77, loss: 0.07319924980401993
2023-01-22 07:17:27.235476: step: 176/77, loss: 0.0070552583783864975
2023-01-22 07:17:28.519937: step: 180/77, loss: 0.03356878086924553
2023-01-22 07:17:29.780698: step: 184/77, loss: 0.017069164663553238
2023-01-22 07:17:31.100782: step: 188/77, loss: 0.06316450238227844
2023-01-22 07:17:32.315923: step: 192/77, loss: 0.05764845013618469
2023-01-22 07:17:33.620968: step: 196/77, loss: 0.018638404086232185
2023-01-22 07:17:34.904076: step: 200/77, loss: 0.047206778079271317
2023-01-22 07:17:36.132279: step: 204/77, loss: 0.012387819588184357
2023-01-22 07:17:37.411862: step: 208/77, loss: 0.018886670470237732
2023-01-22 07:17:38.687323: step: 212/77, loss: 0.040599655359983444
2023-01-22 07:17:39.964207: step: 216/77, loss: 0.062156952917575836
2023-01-22 07:17:41.316056: step: 220/77, loss: 0.08114401996135712
2023-01-22 07:17:42.669059: step: 224/77, loss: 0.03974404186010361
2023-01-22 07:17:43.981272: step: 228/77, loss: 0.07013162225484848
2023-01-22 07:17:45.270549: step: 232/77, loss: 0.029353676363825798
2023-01-22 07:17:46.573436: step: 236/77, loss: 0.027635207399725914
2023-01-22 07:17:47.867944: step: 240/77, loss: 0.08846844732761383
2023-01-22 07:17:49.168401: step: 244/77, loss: 0.11539971828460693
2023-01-22 07:17:50.467859: step: 248/77, loss: 0.037433214485645294
2023-01-22 07:17:51.774448: step: 252/77, loss: 0.07446795701980591
2023-01-22 07:17:53.097696: step: 256/77, loss: 0.039659544825553894
2023-01-22 07:17:54.443006: step: 260/77, loss: 0.01527109369635582
2023-01-22 07:17:55.750717: step: 264/77, loss: 0.23154425621032715
2023-01-22 07:17:57.021907: step: 268/77, loss: 0.10503697395324707
2023-01-22 07:17:58.302378: step: 272/77, loss: 0.041720081120729446
2023-01-22 07:17:59.596289: step: 276/77, loss: 0.08117479085922241
2023-01-22 07:18:00.913164: step: 280/77, loss: 0.06630122661590576
2023-01-22 07:18:02.230402: step: 284/77, loss: 0.1733831912279129
2023-01-22 07:18:03.587041: step: 288/77, loss: 0.0781242698431015
2023-01-22 07:18:04.895828: step: 292/77, loss: 0.06188240647315979
2023-01-22 07:18:06.224764: step: 296/77, loss: 0.051947221159935
2023-01-22 07:18:07.512660: step: 300/77, loss: 0.040972497314214706
2023-01-22 07:18:08.847469: step: 304/77, loss: 0.03663957864046097
2023-01-22 07:18:10.177692: step: 308/77, loss: 0.07159535586833954
2023-01-22 07:18:11.526095: step: 312/77, loss: 0.15917694568634033
2023-01-22 07:18:12.871961: step: 316/77, loss: 0.037154968827962875
2023-01-22 07:18:14.115733: step: 320/77, loss: 0.07271397113800049
2023-01-22 07:18:15.400250: step: 324/77, loss: 0.1220267117023468
2023-01-22 07:18:16.691924: step: 328/77, loss: 0.03455435484647751
2023-01-22 07:18:18.018368: step: 332/77, loss: 0.019315311685204506
2023-01-22 07:18:19.306317: step: 336/77, loss: 0.05523783713579178
2023-01-22 07:18:20.680397: step: 340/77, loss: 0.03926079720258713
2023-01-22 07:18:21.992537: step: 344/77, loss: 0.10926296561956406
2023-01-22 07:18:23.301361: step: 348/77, loss: 0.0364389531314373
2023-01-22 07:18:24.578839: step: 352/77, loss: 0.015954257920384407
2023-01-22 07:18:25.886224: step: 356/77, loss: 0.25136813521385193
2023-01-22 07:18:27.238750: step: 360/77, loss: 0.013067019172012806
2023-01-22 07:18:28.562512: step: 364/77, loss: 0.005912239663302898
2023-01-22 07:18:29.908366: step: 368/77, loss: 0.06499234586954117
2023-01-22 07:18:31.157606: step: 372/77, loss: 0.06031108647584915
2023-01-22 07:18:32.449688: step: 376/77, loss: 0.07589991390705109
2023-01-22 07:18:33.762795: step: 380/77, loss: 0.01958923414349556
2023-01-22 07:18:35.062942: step: 384/77, loss: 0.01762222871184349
2023-01-22 07:18:36.394861: step: 388/77, loss: 0.008108420297503471
==================================================
Loss: 0.065
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 2}
Test Chinese: {'template': {'p': 0.958904109589041, 'r': 0.5691056910569106, 'f1': 0.7142857142857142}, 'slot': {'p': 0.5666666666666667, 'r': 0.015454545454545455, 'f1': 0.03008849557522124}, 'combined': 0.021491782553729452, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 2}
Test Korean: {'template': {'p': 0.958904109589041, 'r': 0.5691056910569106, 'f1': 0.7142857142857142}, 'slot': {'p': 0.5666666666666667, 'r': 0.015454545454545455, 'f1': 0.03008849557522124}, 'combined': 0.021491782553729452, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 2}
Test Russian: {'template': {'p': 0.958904109589041, 'r': 0.5691056910569106, 'f1': 0.7142857142857142}, 'slot': {'p': 0.5666666666666667, 'r': 0.015454545454545455, 'f1': 0.03008849557522124}, 'combined': 0.021491782553729452, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 2}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.958904109589041, 'r': 0.5691056910569106, 'f1': 0.7142857142857142}, 'slot': {'p': 0.5666666666666667, 'r': 0.015454545454545455, 'f1': 0.03008849557522124}, 'combined': 0.021491782553729452, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 2}
Test for Korean: {'template': {'p': 0.958904109589041, 'r': 0.5691056910569106, 'f1': 0.7142857142857142}, 'slot': {'p': 0.5666666666666667, 'r': 0.015454545454545455, 'f1': 0.03008849557522124}, 'combined': 0.021491782553729452, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 2}
Test for Russian: {'template': {'p': 0.958904109589041, 'r': 0.5691056910569106, 'f1': 0.7142857142857142}, 'slot': {'p': 0.5666666666666667, 'r': 0.015454545454545455, 'f1': 0.03008849557522124}, 'combined': 0.021491782553729452, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
******************************
Epoch: 3
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 07:20:40.629528: step: 4/77, loss: 0.015968766063451767
2023-01-22 07:20:41.917069: step: 8/77, loss: 0.01351113896816969
2023-01-22 07:20:43.209912: step: 12/77, loss: 0.08549536019563675
2023-01-22 07:20:44.462411: step: 16/77, loss: 0.03732670471072197
2023-01-22 07:20:45.773112: step: 20/77, loss: 0.005760162137448788
2023-01-22 07:20:47.067329: step: 24/77, loss: 0.06140680983662605
2023-01-22 07:20:48.431221: step: 28/77, loss: 0.009903283789753914
2023-01-22 07:20:49.688448: step: 32/77, loss: 0.028609666973352432
2023-01-22 07:20:50.984214: step: 36/77, loss: 0.025533368811011314
2023-01-22 07:20:52.267826: step: 40/77, loss: 0.02272067219018936
2023-01-22 07:20:53.589286: step: 44/77, loss: 0.06468820571899414
2023-01-22 07:20:54.874754: step: 48/77, loss: 0.026076534762978554
2023-01-22 07:20:56.174284: step: 52/77, loss: 0.029940230771899223
2023-01-22 07:20:57.490804: step: 56/77, loss: 0.08760607987642288
2023-01-22 07:20:58.808044: step: 60/77, loss: 0.12449557334184647
2023-01-22 07:21:00.119745: step: 64/77, loss: 0.02922476828098297
2023-01-22 07:21:01.445165: step: 68/77, loss: 0.005582435987889767
2023-01-22 07:21:02.715375: step: 72/77, loss: 0.012879885733127594
2023-01-22 07:21:03.984803: step: 76/77, loss: 0.025143388658761978
2023-01-22 07:21:05.270241: step: 80/77, loss: 0.009446179494261742
2023-01-22 07:21:06.519298: step: 84/77, loss: 0.04552457481622696
2023-01-22 07:21:07.803890: step: 88/77, loss: 0.02507692202925682
2023-01-22 07:21:09.111768: step: 92/77, loss: 0.025074133649468422
2023-01-22 07:21:10.417681: step: 96/77, loss: 0.01472495123744011
2023-01-22 07:21:11.735012: step: 100/77, loss: 0.03009127266705036
2023-01-22 07:21:13.020047: step: 104/77, loss: 0.1456586718559265
2023-01-22 07:21:14.331133: step: 108/77, loss: 0.008024273440241814
2023-01-22 07:21:15.624297: step: 112/77, loss: 0.04816785454750061
2023-01-22 07:21:16.940765: step: 116/77, loss: 0.01610010489821434
2023-01-22 07:21:18.197987: step: 120/77, loss: 0.022976523265242577
2023-01-22 07:21:19.463048: step: 124/77, loss: 0.040475912392139435
2023-01-22 07:21:20.732289: step: 128/77, loss: 0.055941663682460785
2023-01-22 07:21:21.990709: step: 132/77, loss: 0.027231454849243164
2023-01-22 07:21:23.278867: step: 136/77, loss: 0.06407906860113144
2023-01-22 07:21:24.596408: step: 140/77, loss: 0.020403718575835228
2023-01-22 07:21:25.857862: step: 144/77, loss: 0.054121024906635284
2023-01-22 07:21:27.064971: step: 148/77, loss: 0.019535942003130913
2023-01-22 07:21:28.358064: step: 152/77, loss: 0.02978493645787239
2023-01-22 07:21:29.643954: step: 156/77, loss: 0.007111942861229181
2023-01-22 07:21:30.934531: step: 160/77, loss: 0.05967719852924347
2023-01-22 07:21:32.216050: step: 164/77, loss: 0.050702475011348724
2023-01-22 07:21:33.565750: step: 168/77, loss: 0.07628966867923737
2023-01-22 07:21:34.859738: step: 172/77, loss: 0.016380734741687775
2023-01-22 07:21:36.194216: step: 176/77, loss: 0.09666801989078522
2023-01-22 07:21:37.494267: step: 180/77, loss: 0.011515635997056961
2023-01-22 07:21:38.826383: step: 184/77, loss: 0.014797764830291271
2023-01-22 07:21:40.131410: step: 188/77, loss: 0.014288538135588169
2023-01-22 07:21:41.428010: step: 192/77, loss: 0.046548232436180115
2023-01-22 07:21:42.744808: step: 196/77, loss: 0.10158401727676392
2023-01-22 07:21:44.078268: step: 200/77, loss: 0.020895320922136307
2023-01-22 07:21:45.396368: step: 204/77, loss: 0.0929812490940094
2023-01-22 07:21:46.672874: step: 208/77, loss: 0.06224067509174347
2023-01-22 07:21:48.013697: step: 212/77, loss: 0.010834470391273499
2023-01-22 07:21:49.286548: step: 216/77, loss: 0.020457429811358452
2023-01-22 07:21:50.581946: step: 220/77, loss: 0.04090658575296402
2023-01-22 07:21:51.864870: step: 224/77, loss: 0.0852619856595993
2023-01-22 07:21:53.144641: step: 228/77, loss: 0.054530490189790726
2023-01-22 07:21:54.491347: step: 232/77, loss: 0.04404990002512932
2023-01-22 07:21:55.797589: step: 236/77, loss: 0.028828389942646027
2023-01-22 07:21:57.066485: step: 240/77, loss: 0.05302087962627411
2023-01-22 07:21:58.368443: step: 244/77, loss: 0.051580313593149185
2023-01-22 07:21:59.680765: step: 248/77, loss: 0.14568468928337097
2023-01-22 07:22:00.966955: step: 252/77, loss: 0.009636200964450836
2023-01-22 07:22:02.267140: step: 256/77, loss: 0.012510381639003754
2023-01-22 07:22:03.561194: step: 260/77, loss: 0.02064824104309082
2023-01-22 07:22:04.886529: step: 264/77, loss: 0.08655968308448792
2023-01-22 07:22:06.214054: step: 268/77, loss: 0.03449642285704613
2023-01-22 07:22:07.490488: step: 272/77, loss: 0.021431952714920044
2023-01-22 07:22:08.807018: step: 276/77, loss: 0.016396211460232735
2023-01-22 07:22:10.085564: step: 280/77, loss: 0.015242512337863445
2023-01-22 07:22:11.400825: step: 284/77, loss: 0.3615311086177826
2023-01-22 07:22:12.673805: step: 288/77, loss: 0.08149930089712143
2023-01-22 07:22:14.008222: step: 292/77, loss: 0.026354094967246056
2023-01-22 07:22:15.310607: step: 296/77, loss: 0.008077921345829964
2023-01-22 07:22:16.624824: step: 300/77, loss: 0.13474395871162415
2023-01-22 07:22:17.946512: step: 304/77, loss: 0.005618092138320208
2023-01-22 07:22:19.237194: step: 308/77, loss: 0.21946494281291962
2023-01-22 07:22:20.533978: step: 312/77, loss: 0.04267258942127228
2023-01-22 07:22:21.752196: step: 316/77, loss: 0.015815965831279755
2023-01-22 07:22:23.090779: step: 320/77, loss: 0.03485114499926567
2023-01-22 07:22:24.449222: step: 324/77, loss: 0.026810774579644203
2023-01-22 07:22:25.744959: step: 328/77, loss: 0.01187300868332386
2023-01-22 07:22:27.049613: step: 332/77, loss: 0.05864952877163887
2023-01-22 07:22:28.325106: step: 336/77, loss: 0.030480477958917618
2023-01-22 07:22:29.584960: step: 340/77, loss: 0.06372788548469543
2023-01-22 07:22:30.854134: step: 344/77, loss: 0.05656794458627701
2023-01-22 07:22:32.159354: step: 348/77, loss: 0.0045874156057834625
2023-01-22 07:22:33.484614: step: 352/77, loss: 0.05805297940969467
2023-01-22 07:22:34.730961: step: 356/77, loss: 0.044932737946510315
2023-01-22 07:22:36.016318: step: 360/77, loss: 0.01705370470881462
2023-01-22 07:22:37.294174: step: 364/77, loss: 0.15946604311466217
2023-01-22 07:22:38.565880: step: 368/77, loss: 0.006360077764838934
2023-01-22 07:22:39.837731: step: 372/77, loss: 0.04374031722545624
2023-01-22 07:22:41.118232: step: 376/77, loss: 0.006530561950057745
2023-01-22 07:22:42.422119: step: 380/77, loss: 0.0038705565966665745
2023-01-22 07:22:43.705234: step: 384/77, loss: 0.06794550269842148
2023-01-22 07:22:45.014185: step: 388/77, loss: 0.15991713106632233
==================================================
Loss: 0.047
--------------------
Dev Chinese: {'template': {'p': 0.9090909090909091, 'r': 0.5, 'f1': 0.6451612903225806}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.04535404501388967, 'epoch': 3}
Test Chinese: {'template': {'p': 0.9466666666666667, 'r': 0.5772357723577236, 'f1': 0.7171717171717171}, 'slot': {'p': 0.4722222222222222, 'r': 0.015454545454545455, 'f1': 0.029929577464788734}, 'combined': 0.021464646464646464, 'epoch': 3}
Dev Korean: {'template': {'p': 0.90625, 'r': 0.48333333333333334, 'f1': 0.6304347826086957}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.04431878963857263, 'epoch': 3}
Test Korean: {'template': {'p': 0.9466666666666667, 'r': 0.5772357723577236, 'f1': 0.7171717171717171}, 'slot': {'p': 0.4722222222222222, 'r': 0.015454545454545455, 'f1': 0.029929577464788734}, 'combined': 0.021464646464646464, 'epoch': 3}
Dev Russian: {'template': {'p': 0.90625, 'r': 0.48333333333333334, 'f1': 0.6304347826086957}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.04431878963857263, 'epoch': 3}
Test Russian: {'template': {'p': 0.9466666666666667, 'r': 0.5772357723577236, 'f1': 0.7171717171717171}, 'slot': {'p': 0.4722222222222222, 'r': 0.015454545454545455, 'f1': 0.029929577464788734}, 'combined': 0.021464646464646464, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.25, 'f1': 0.4}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.021621621621621623, 'epoch': 3}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Russian: {'template': {'p': 1.0, 'r': 0.25, 'f1': 0.4}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.025806451612903226, 'epoch': 3}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.958904109589041, 'r': 0.5691056910569106, 'f1': 0.7142857142857142}, 'slot': {'p': 0.5666666666666667, 'r': 0.015454545454545455, 'f1': 0.03008849557522124}, 'combined': 0.021491782553729452, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 2}
Test for Korean: {'template': {'p': 0.958904109589041, 'r': 0.5691056910569106, 'f1': 0.7142857142857142}, 'slot': {'p': 0.5666666666666667, 'r': 0.015454545454545455, 'f1': 0.03008849557522124}, 'combined': 0.021491782553729452, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 2}
Test for Russian: {'template': {'p': 0.958904109589041, 'r': 0.5691056910569106, 'f1': 0.7142857142857142}, 'slot': {'p': 0.5666666666666667, 'r': 0.015454545454545455, 'f1': 0.03008849557522124}, 'combined': 0.021491782553729452, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
******************************
Epoch: 4
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 07:24:20.534839: step: 4/77, loss: 0.1591966152191162
2023-01-22 07:24:21.788228: step: 8/77, loss: 0.0036322043742984533
2023-01-22 07:24:23.056355: step: 12/77, loss: 0.0035585726145654917
2023-01-22 07:24:24.284628: step: 16/77, loss: 0.03981819003820419
2023-01-22 07:24:25.587856: step: 20/77, loss: 0.012272844091057777
2023-01-22 07:24:26.888611: step: 24/77, loss: 0.03815988078713417
2023-01-22 07:24:28.187457: step: 28/77, loss: 0.07955527305603027
2023-01-22 07:24:29.532591: step: 32/77, loss: 0.03334498777985573
2023-01-22 07:24:30.854133: step: 36/77, loss: 0.02782886102795601
2023-01-22 07:24:32.116594: step: 40/77, loss: 0.05034760758280754
2023-01-22 07:24:33.442934: step: 44/77, loss: 0.046723365783691406
2023-01-22 07:24:34.683799: step: 48/77, loss: 0.04478670284152031
2023-01-22 07:24:35.960904: step: 52/77, loss: 0.00868067517876625
2023-01-22 07:24:37.192269: step: 56/77, loss: 0.0023823282681405544
2023-01-22 07:24:38.471462: step: 60/77, loss: 0.12383562326431274
2023-01-22 07:24:39.752352: step: 64/77, loss: 0.016625147312879562
2023-01-22 07:24:41.035846: step: 68/77, loss: 0.09449809789657593
2023-01-22 07:24:42.318146: step: 72/77, loss: 0.026286687701940536
2023-01-22 07:24:43.557301: step: 76/77, loss: 0.010752486996352673
2023-01-22 07:24:44.868039: step: 80/77, loss: 0.025785956531763077
2023-01-22 07:24:46.119210: step: 84/77, loss: 0.00048810700536705554
2023-01-22 07:24:47.396784: step: 88/77, loss: 0.03618944063782692
2023-01-22 07:24:48.661484: step: 92/77, loss: 0.010275091975927353
2023-01-22 07:24:49.955103: step: 96/77, loss: 0.019382059574127197
2023-01-22 07:24:51.250733: step: 100/77, loss: 0.022107046097517014
2023-01-22 07:24:52.526220: step: 104/77, loss: 0.03271938115358353
2023-01-22 07:24:53.850188: step: 108/77, loss: 0.02639208734035492
2023-01-22 07:24:55.110411: step: 112/77, loss: 0.07708106935024261
2023-01-22 07:24:56.364082: step: 116/77, loss: 0.01799575239419937
2023-01-22 07:24:57.619258: step: 120/77, loss: 0.035872627049684525
2023-01-22 07:24:58.892683: step: 124/77, loss: 0.005020597018301487
2023-01-22 07:25:00.192560: step: 128/77, loss: 0.048189785331487656
2023-01-22 07:25:01.525789: step: 132/77, loss: 0.012047644704580307
2023-01-22 07:25:02.854661: step: 136/77, loss: 0.06587105244398117
2023-01-22 07:25:04.172920: step: 140/77, loss: 0.17298981547355652
2023-01-22 07:25:05.477652: step: 144/77, loss: 0.03656620532274246
2023-01-22 07:25:06.751406: step: 148/77, loss: 0.03557945042848587
2023-01-22 07:25:08.066896: step: 152/77, loss: 0.0015012272633612156
2023-01-22 07:25:09.348512: step: 156/77, loss: 0.011846780776977539
2023-01-22 07:25:10.626304: step: 160/77, loss: 0.06310739368200302
2023-01-22 07:25:11.901145: step: 164/77, loss: 0.016693251207470894
2023-01-22 07:25:13.206302: step: 168/77, loss: 0.03192953020334244
2023-01-22 07:25:14.484245: step: 172/77, loss: 0.027641138061881065
2023-01-22 07:25:15.798326: step: 176/77, loss: 0.03455713763833046
2023-01-22 07:25:17.103372: step: 180/77, loss: 0.02429923042654991
2023-01-22 07:25:18.408064: step: 184/77, loss: 0.004264523275196552
2023-01-22 07:25:19.721598: step: 188/77, loss: 0.014208164997398853
2023-01-22 07:25:20.997607: step: 192/77, loss: 0.01190916821360588
2023-01-22 07:25:22.275915: step: 196/77, loss: 0.056420039385557175
2023-01-22 07:25:23.584339: step: 200/77, loss: 0.018400974571704865
2023-01-22 07:25:24.911196: step: 204/77, loss: 0.04778168350458145
2023-01-22 07:25:26.179593: step: 208/77, loss: 0.011265124194324017
2023-01-22 07:25:27.452886: step: 212/77, loss: 0.005715106148272753
2023-01-22 07:25:28.727098: step: 216/77, loss: 0.012743368744850159
2023-01-22 07:25:29.985052: step: 220/77, loss: 0.03328631818294525
2023-01-22 07:25:31.243421: step: 224/77, loss: 0.13442906737327576
2023-01-22 07:25:32.532398: step: 228/77, loss: 0.03768271580338478
2023-01-22 07:25:33.850511: step: 232/77, loss: 0.15616267919540405
2023-01-22 07:25:35.152378: step: 236/77, loss: 0.010896775871515274
2023-01-22 07:25:36.413886: step: 240/77, loss: 0.02437608689069748
2023-01-22 07:25:37.719024: step: 244/77, loss: 0.0066629135981202126
2023-01-22 07:25:39.034489: step: 248/77, loss: 0.014826871454715729
2023-01-22 07:25:40.348677: step: 252/77, loss: 0.06286932528018951
2023-01-22 07:25:41.589428: step: 256/77, loss: 0.03753984346985817
2023-01-22 07:25:42.852154: step: 260/77, loss: 0.024473311379551888
2023-01-22 07:25:44.158306: step: 264/77, loss: 0.02880875952541828
2023-01-22 07:25:45.471597: step: 268/77, loss: 0.0316791832447052
2023-01-22 07:25:46.742312: step: 272/77, loss: 0.03705769032239914
2023-01-22 07:25:48.033052: step: 276/77, loss: 0.0716656893491745
2023-01-22 07:25:49.331319: step: 280/77, loss: 0.011389000341296196
2023-01-22 07:25:50.631225: step: 284/77, loss: 0.027336813509464264
2023-01-22 07:25:51.877893: step: 288/77, loss: 0.033267825841903687
2023-01-22 07:25:53.192187: step: 292/77, loss: 0.026131270453333855
2023-01-22 07:25:54.456249: step: 296/77, loss: 0.00949370302259922
2023-01-22 07:25:55.751056: step: 300/77, loss: 0.02307109721004963
2023-01-22 07:25:57.044198: step: 304/77, loss: 0.056111834943294525
2023-01-22 07:25:58.377015: step: 308/77, loss: 0.05641761049628258
2023-01-22 07:25:59.628911: step: 312/77, loss: 0.02172068879008293
2023-01-22 07:26:00.966678: step: 316/77, loss: 0.1652591973543167
2023-01-22 07:26:02.315225: step: 320/77, loss: 0.021472467109560966
2023-01-22 07:26:03.632004: step: 324/77, loss: 0.012137623503804207
2023-01-22 07:26:04.909829: step: 328/77, loss: 0.01814662106335163
2023-01-22 07:26:06.228860: step: 332/77, loss: 0.020530683919787407
2023-01-22 07:26:07.514531: step: 336/77, loss: 0.018007539212703705
2023-01-22 07:26:08.771972: step: 340/77, loss: 0.0415189191699028
2023-01-22 07:26:10.057627: step: 344/77, loss: 0.01093345694243908
2023-01-22 07:26:11.363958: step: 348/77, loss: 0.026807358488440514
2023-01-22 07:26:12.624999: step: 352/77, loss: 0.013095011003315449
2023-01-22 07:26:13.910864: step: 356/77, loss: 0.02017892897129059
2023-01-22 07:26:15.270474: step: 360/77, loss: 0.06183590739965439
2023-01-22 07:26:16.533523: step: 364/77, loss: 0.11347439140081406
2023-01-22 07:26:17.830799: step: 368/77, loss: 0.08657459169626236
2023-01-22 07:26:19.175620: step: 372/77, loss: 0.02488943189382553
2023-01-22 07:26:20.409051: step: 376/77, loss: 0.002923357766121626
2023-01-22 07:26:21.704830: step: 380/77, loss: 0.0434151217341423
2023-01-22 07:26:22.975274: step: 384/77, loss: 0.06214475631713867
2023-01-22 07:26:24.289003: step: 388/77, loss: 0.043125901371240616
==================================================
Loss: 0.038
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.55, 'f1': 0.7096774193548387}, 'slot': {'p': 0.5, 'r': 0.034026465028355386, 'f1': 0.06371681415929203}, 'combined': 0.04521838424207822, 'epoch': 4}
Test Chinese: {'template': {'p': 0.9846153846153847, 'r': 0.5203252032520326, 'f1': 0.6808510638297873}, 'slot': {'p': 0.4838709677419355, 'r': 0.013636363636363636, 'f1': 0.026525198938992044}, 'combined': 0.01805970991590948, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.55, 'f1': 0.7096774193548387}, 'slot': {'p': 0.5, 'r': 0.034026465028355386, 'f1': 0.06371681415929203}, 'combined': 0.04521838424207822, 'epoch': 4}
Test Korean: {'template': {'p': 0.9846153846153847, 'r': 0.5203252032520326, 'f1': 0.6808510638297873}, 'slot': {'p': 0.4838709677419355, 'r': 0.013636363636363636, 'f1': 0.026525198938992044}, 'combined': 0.01805970991590948, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.55, 'f1': 0.7096774193548387}, 'slot': {'p': 0.5, 'r': 0.034026465028355386, 'f1': 0.06371681415929203}, 'combined': 0.04521838424207822, 'epoch': 4}
Test Russian: {'template': {'p': 0.9848484848484849, 'r': 0.5284552845528455, 'f1': 0.6878306878306879}, 'slot': {'p': 0.5151515151515151, 'r': 0.015454545454545455, 'f1': 0.030008826125330977}, 'combined': 0.020640991514777923, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 4}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'template': {'p': 1.0, 'r': 0.25, 'f1': 0.4}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.958904109589041, 'r': 0.5691056910569106, 'f1': 0.7142857142857142}, 'slot': {'p': 0.5666666666666667, 'r': 0.015454545454545455, 'f1': 0.03008849557522124}, 'combined': 0.021491782553729452, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 2}
Test for Korean: {'template': {'p': 0.958904109589041, 'r': 0.5691056910569106, 'f1': 0.7142857142857142}, 'slot': {'p': 0.5666666666666667, 'r': 0.015454545454545455, 'f1': 0.03008849557522124}, 'combined': 0.021491782553729452, 'epoch': 2}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 2}
Test for Russian: {'template': {'p': 0.958904109589041, 'r': 0.5691056910569106, 'f1': 0.7142857142857142}, 'slot': {'p': 0.5666666666666667, 'r': 0.015454545454545455, 'f1': 0.03008849557522124}, 'combined': 0.021491782553729452, 'epoch': 2}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
******************************
Epoch: 5
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 07:28:00.134919: step: 4/77, loss: 0.05281934514641762
2023-01-22 07:28:01.337419: step: 8/77, loss: 0.10034886747598648
2023-01-22 07:28:02.645760: step: 12/77, loss: 0.008094294928014278
2023-01-22 07:28:03.955427: step: 16/77, loss: 0.007729171775281429
2023-01-22 07:28:05.219569: step: 20/77, loss: 0.0249926894903183
2023-01-22 07:28:06.522479: step: 24/77, loss: 0.014677442610263824
2023-01-22 07:28:07.767331: step: 28/77, loss: 0.015226608142256737
2023-01-22 07:28:09.067048: step: 32/77, loss: 0.09592887759208679
2023-01-22 07:28:10.332054: step: 36/77, loss: 0.038398392498493195
2023-01-22 07:28:11.597521: step: 40/77, loss: 0.014437681064009666
2023-01-22 07:28:12.834711: step: 44/77, loss: 0.02251637540757656
2023-01-22 07:28:14.168194: step: 48/77, loss: 0.09548071026802063
2023-01-22 07:28:15.439371: step: 52/77, loss: 0.05408954620361328
2023-01-22 07:28:16.699185: step: 56/77, loss: 0.012811540625989437
2023-01-22 07:28:18.000942: step: 60/77, loss: 0.06582754850387573
2023-01-22 07:28:19.272775: step: 64/77, loss: 0.011044980026781559
2023-01-22 07:28:20.603695: step: 68/77, loss: 0.01578996330499649
2023-01-22 07:28:21.929544: step: 72/77, loss: 0.03434739634394646
2023-01-22 07:28:23.238375: step: 76/77, loss: 0.02023492194712162
2023-01-22 07:28:24.516038: step: 80/77, loss: 0.005539305973798037
2023-01-22 07:28:25.763341: step: 84/77, loss: 0.012604881078004837
2023-01-22 07:28:27.050347: step: 88/77, loss: 0.04681181162595749
2023-01-22 07:28:28.361830: step: 92/77, loss: 0.02078882046043873
2023-01-22 07:28:29.670017: step: 96/77, loss: 0.040004126727581024
2023-01-22 07:28:30.905653: step: 100/77, loss: 0.034155894070863724
2023-01-22 07:28:32.224236: step: 104/77, loss: 0.01139921136200428
2023-01-22 07:28:33.554098: step: 108/77, loss: 0.006441830191761255
2023-01-22 07:28:34.806621: step: 112/77, loss: 0.0597098171710968
2023-01-22 07:28:36.079217: step: 116/77, loss: 0.012973377481102943
2023-01-22 07:28:37.346293: step: 120/77, loss: 0.07683604210615158
2023-01-22 07:28:38.646334: step: 124/77, loss: 0.053127095103263855
2023-01-22 07:28:39.942692: step: 128/77, loss: 0.01308278739452362
2023-01-22 07:28:41.203159: step: 132/77, loss: 0.01676439866423607
2023-01-22 07:28:42.491549: step: 136/77, loss: 0.11097963154315948
2023-01-22 07:28:43.778667: step: 140/77, loss: 0.04553266242146492
2023-01-22 07:28:45.061384: step: 144/77, loss: 0.05289888381958008
2023-01-22 07:28:46.343498: step: 148/77, loss: 0.01658434234559536
2023-01-22 07:28:47.610679: step: 152/77, loss: 0.07442338019609451
2023-01-22 07:28:48.933295: step: 156/77, loss: 0.05406294763088226
2023-01-22 07:28:50.200283: step: 160/77, loss: 0.010441828519105911
2023-01-22 07:28:51.450860: step: 164/77, loss: 0.0038215755484998226
2023-01-22 07:28:52.731269: step: 168/77, loss: 0.0016422360204160213
2023-01-22 07:28:54.039322: step: 172/77, loss: 0.07169732451438904
2023-01-22 07:28:55.355881: step: 176/77, loss: 0.01746036671102047
2023-01-22 07:28:56.671387: step: 180/77, loss: 0.04688744246959686
2023-01-22 07:28:58.026215: step: 184/77, loss: 0.023346032947301865
2023-01-22 07:28:59.308390: step: 188/77, loss: 0.022755956277251244
2023-01-22 07:29:00.591678: step: 192/77, loss: 0.00830506905913353
2023-01-22 07:29:01.861321: step: 196/77, loss: 0.006505207624286413
2023-01-22 07:29:03.186198: step: 200/77, loss: 0.034292690455913544
2023-01-22 07:29:04.544400: step: 204/77, loss: 0.1433955430984497
2023-01-22 07:29:05.784315: step: 208/77, loss: 0.011057563126087189
2023-01-22 07:29:07.077537: step: 212/77, loss: 0.02051542140543461
2023-01-22 07:29:08.326794: step: 216/77, loss: 0.015034375712275505
2023-01-22 07:29:09.615159: step: 220/77, loss: 0.02420666441321373
2023-01-22 07:29:10.953511: step: 224/77, loss: 0.07697256654500961
2023-01-22 07:29:12.217615: step: 228/77, loss: 0.03689153492450714
2023-01-22 07:29:13.503974: step: 232/77, loss: 0.015925971791148186
2023-01-22 07:29:14.773777: step: 236/77, loss: 0.0585017055273056
2023-01-22 07:29:16.103524: step: 240/77, loss: 0.009359755553305149
2023-01-22 07:29:17.350640: step: 244/77, loss: 0.021430548280477524
2023-01-22 07:29:18.668984: step: 248/77, loss: 0.018590224906802177
2023-01-22 07:29:19.974181: step: 252/77, loss: 0.01646292582154274
2023-01-22 07:29:21.303563: step: 256/77, loss: 0.049518853425979614
2023-01-22 07:29:22.619476: step: 260/77, loss: 0.02466382458806038
2023-01-22 07:29:23.974806: step: 264/77, loss: 0.007570900954306126
2023-01-22 07:29:25.309596: step: 268/77, loss: 0.1567116677761078
2023-01-22 07:29:26.653572: step: 272/77, loss: 0.044765837490558624
2023-01-22 07:29:27.945881: step: 276/77, loss: 0.04036088287830353
2023-01-22 07:29:29.268386: step: 280/77, loss: 0.0008329019183292985
2023-01-22 07:29:30.587348: step: 284/77, loss: 0.12199905514717102
2023-01-22 07:29:31.865541: step: 288/77, loss: 0.045698583126068115
2023-01-22 07:29:33.221173: step: 292/77, loss: 0.02223210595548153
2023-01-22 07:29:34.526796: step: 296/77, loss: 0.07185053825378418
2023-01-22 07:29:35.854915: step: 300/77, loss: 0.025253664702177048
2023-01-22 07:29:37.124430: step: 304/77, loss: 0.035008110105991364
2023-01-22 07:29:38.405181: step: 308/77, loss: 0.07302802056074142
2023-01-22 07:29:39.675252: step: 312/77, loss: 0.07924443483352661
2023-01-22 07:29:40.917945: step: 316/77, loss: 0.019673509523272514
2023-01-22 07:29:42.187511: step: 320/77, loss: 0.07078725099563599
2023-01-22 07:29:43.442570: step: 324/77, loss: 0.014910933561623096
2023-01-22 07:29:44.736065: step: 328/77, loss: 0.02365684136748314
2023-01-22 07:29:45.993857: step: 332/77, loss: 0.032946422696113586
2023-01-22 07:29:47.317969: step: 336/77, loss: 0.023019496351480484
2023-01-22 07:29:48.634010: step: 340/77, loss: 0.05330086126923561
2023-01-22 07:29:49.951808: step: 344/77, loss: 0.08135435730218887
2023-01-22 07:29:51.297165: step: 348/77, loss: 0.08608993887901306
2023-01-22 07:29:52.601978: step: 352/77, loss: 0.028688719496130943
2023-01-22 07:29:53.888797: step: 356/77, loss: 0.006268288008868694
2023-01-22 07:29:55.210681: step: 360/77, loss: 0.03752407804131508
2023-01-22 07:29:56.447721: step: 364/77, loss: 0.012255517765879631
2023-01-22 07:29:57.731220: step: 368/77, loss: 0.18901900947093964
2023-01-22 07:29:59.027480: step: 372/77, loss: 0.017559271305799484
2023-01-22 07:30:00.304665: step: 376/77, loss: 0.017930801957845688
2023-01-22 07:30:01.587588: step: 380/77, loss: 0.0486404225230217
2023-01-22 07:30:02.920256: step: 384/77, loss: 0.021391339600086212
2023-01-22 07:30:04.245309: step: 388/77, loss: 0.010606233961880207
==================================================
Loss: 0.039
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 6
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 07:32:07.981745: step: 4/77, loss: 0.014090805314481258
2023-01-22 07:32:09.252200: step: 8/77, loss: 0.037653181701898575
2023-01-22 07:32:10.562065: step: 12/77, loss: 0.012905780225992203
2023-01-22 07:32:11.832518: step: 16/77, loss: 0.12145353853702545
2023-01-22 07:32:13.128756: step: 20/77, loss: 0.004029234871268272
2023-01-22 07:32:14.428653: step: 24/77, loss: 0.0458088181912899
2023-01-22 07:32:15.701896: step: 28/77, loss: 0.013678375631570816
2023-01-22 07:32:16.997473: step: 32/77, loss: 0.016728755086660385
2023-01-22 07:32:18.262397: step: 36/77, loss: 0.00028109041159041226
2023-01-22 07:32:19.569559: step: 40/77, loss: 0.010670517571270466
2023-01-22 07:32:20.829516: step: 44/77, loss: 0.05759980529546738
2023-01-22 07:32:22.081895: step: 48/77, loss: 0.030156835913658142
2023-01-22 07:32:23.323741: step: 52/77, loss: 0.013267605565488338
2023-01-22 07:32:24.619979: step: 56/77, loss: 0.056651029735803604
2023-01-22 07:32:25.918622: step: 60/77, loss: 0.07792923599481583
2023-01-22 07:32:27.200511: step: 64/77, loss: 0.048105549067258835
2023-01-22 07:32:28.492746: step: 68/77, loss: 0.0016152573516592383
2023-01-22 07:32:29.817194: step: 72/77, loss: 0.01203523576259613
2023-01-22 07:32:31.073962: step: 76/77, loss: 0.00038057187339290977
2023-01-22 07:32:32.357816: step: 80/77, loss: 0.00727054663002491
2023-01-22 07:32:33.630776: step: 84/77, loss: 0.008634903468191624
2023-01-22 07:32:34.882829: step: 88/77, loss: 0.05545460432767868
2023-01-22 07:32:36.138351: step: 92/77, loss: 0.08746394515037537
2023-01-22 07:32:37.465630: step: 96/77, loss: 0.0012042783200740814
2023-01-22 07:32:38.754516: step: 100/77, loss: 0.0012032882077619433
2023-01-22 07:32:40.055067: step: 104/77, loss: 0.03924532234668732
2023-01-22 07:32:41.339768: step: 108/77, loss: 0.07420468330383301
2023-01-22 07:32:42.610696: step: 112/77, loss: 0.031061705201864243
2023-01-22 07:32:43.864085: step: 116/77, loss: 0.010193225927650928
2023-01-22 07:32:45.163970: step: 120/77, loss: 0.02527455799281597
2023-01-22 07:32:46.395624: step: 124/77, loss: 0.10996196419000626
2023-01-22 07:32:47.644253: step: 128/77, loss: 0.022913135588169098
2023-01-22 07:32:48.948580: step: 132/77, loss: 0.04355445131659508
2023-01-22 07:32:50.294614: step: 136/77, loss: 0.08999864012002945
2023-01-22 07:32:51.571570: step: 140/77, loss: 0.1155029907822609
2023-01-22 07:32:52.898542: step: 144/77, loss: 0.015417231246829033
2023-01-22 07:32:54.202958: step: 148/77, loss: 0.0026104964781552553
2023-01-22 07:32:55.497720: step: 152/77, loss: 0.015371415764093399
2023-01-22 07:32:56.802314: step: 156/77, loss: 0.028408939018845558
2023-01-22 07:32:58.133472: step: 160/77, loss: 0.013671678490936756
2023-01-22 07:32:59.394432: step: 164/77, loss: 0.0016819187439978123
2023-01-22 07:33:00.708353: step: 168/77, loss: 0.016836147755384445
2023-01-22 07:33:02.011191: step: 172/77, loss: 0.028055887669324875
2023-01-22 07:33:03.318904: step: 176/77, loss: 0.02009519934654236
2023-01-22 07:33:04.614906: step: 180/77, loss: 0.02400626242160797
2023-01-22 07:33:05.908073: step: 184/77, loss: 0.020713580772280693
2023-01-22 07:33:07.212181: step: 188/77, loss: 0.021156713366508484
2023-01-22 07:33:08.533602: step: 192/77, loss: 0.004837479908019304
2023-01-22 07:33:09.831117: step: 196/77, loss: 0.017320267856121063
2023-01-22 07:33:11.119135: step: 200/77, loss: 0.020907748490571976
2023-01-22 07:33:12.442452: step: 204/77, loss: 0.04583645239472389
2023-01-22 07:33:13.737609: step: 208/77, loss: 0.014641058631241322
2023-01-22 07:33:15.014845: step: 212/77, loss: 0.022127849981188774
2023-01-22 07:33:16.338229: step: 216/77, loss: 0.036513473838567734
2023-01-22 07:33:17.675503: step: 220/77, loss: 0.03856131061911583
2023-01-22 07:33:18.991837: step: 224/77, loss: 0.005931971129029989
2023-01-22 07:33:20.296300: step: 228/77, loss: 0.020555173978209496
2023-01-22 07:33:21.552602: step: 232/77, loss: 0.1392797976732254
2023-01-22 07:33:22.857281: step: 236/77, loss: 0.0072579397819936275
2023-01-22 07:33:24.122754: step: 240/77, loss: 0.016458049416542053
2023-01-22 07:33:25.443522: step: 244/77, loss: 0.017515050247311592
2023-01-22 07:33:26.708720: step: 248/77, loss: 0.015963345766067505
2023-01-22 07:33:28.004831: step: 252/77, loss: 0.04388893023133278
2023-01-22 07:33:29.269739: step: 256/77, loss: 0.011263003572821617
2023-01-22 07:33:30.518323: step: 260/77, loss: 0.051796067506074905
2023-01-22 07:33:31.839811: step: 264/77, loss: 0.010814322158694267
2023-01-22 07:33:33.053982: step: 268/77, loss: 0.014244206249713898
2023-01-22 07:33:34.285330: step: 272/77, loss: 0.01440565288066864
2023-01-22 07:33:35.553058: step: 276/77, loss: 0.017506180331110954
2023-01-22 07:33:36.858835: step: 280/77, loss: 0.02340465411543846
2023-01-22 07:33:38.154344: step: 284/77, loss: 0.054062407463788986
2023-01-22 07:33:39.434775: step: 288/77, loss: 0.01714850217103958
2023-01-22 07:33:40.739410: step: 292/77, loss: 0.02229364961385727
2023-01-22 07:33:42.058662: step: 296/77, loss: 0.014405068010091782
2023-01-22 07:33:43.359146: step: 300/77, loss: 0.06514809280633926
2023-01-22 07:33:44.660471: step: 304/77, loss: 0.029408197849988937
2023-01-22 07:33:45.979277: step: 308/77, loss: 0.010319838300347328
2023-01-22 07:33:47.224858: step: 312/77, loss: 0.010362434200942516
2023-01-22 07:33:48.512002: step: 316/77, loss: 0.002917802194133401
2023-01-22 07:33:49.848127: step: 320/77, loss: 0.018622087314724922
2023-01-22 07:33:51.150112: step: 324/77, loss: 0.024601642042398453
2023-01-22 07:33:52.411966: step: 328/77, loss: 0.0031394544057548046
2023-01-22 07:33:53.697040: step: 332/77, loss: 0.00596038531512022
2023-01-22 07:33:55.003910: step: 336/77, loss: 0.02685163915157318
2023-01-22 07:33:56.339599: step: 340/77, loss: 0.019619952887296677
2023-01-22 07:33:57.689168: step: 344/77, loss: 0.003369607264176011
2023-01-22 07:33:59.002302: step: 348/77, loss: 0.03238417208194733
2023-01-22 07:34:00.333673: step: 352/77, loss: 0.03758778050541878
2023-01-22 07:34:01.570874: step: 356/77, loss: 0.006597156636416912
2023-01-22 07:34:02.871489: step: 360/77, loss: 0.007597966585308313
2023-01-22 07:34:04.211102: step: 364/77, loss: 0.024710290133953094
2023-01-22 07:34:05.523048: step: 368/77, loss: 0.0800224095582962
2023-01-22 07:34:06.797999: step: 372/77, loss: 0.11172007769346237
2023-01-22 07:34:08.081970: step: 376/77, loss: 0.029980309307575226
2023-01-22 07:34:09.398194: step: 380/77, loss: 0.03759705647826195
2023-01-22 07:34:10.734802: step: 384/77, loss: 0.012880472466349602
2023-01-22 07:34:12.036696: step: 388/77, loss: 0.006357981823384762
==================================================
Loss: 0.029
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05085442919642522, 'epoch': 6}
Test Chinese: {'template': {'p': 0.9615384615384616, 'r': 0.6097560975609756, 'f1': 0.7462686567164178}, 'slot': {'p': 0.46875, 'r': 0.013636363636363636, 'f1': 0.026501766784452298}, 'combined': 0.019777437898844997, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05085442919642522, 'epoch': 6}
Test Korean: {'template': {'p': 0.9615384615384616, 'r': 0.6097560975609756, 'f1': 0.7462686567164178}, 'slot': {'p': 0.46875, 'r': 0.013636363636363636, 'f1': 0.026501766784452298}, 'combined': 0.019777437898844997, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05085442919642522, 'epoch': 6}
Test Russian: {'template': {'p': 0.974025974025974, 'r': 0.6097560975609756, 'f1': 0.7500000000000001}, 'slot': {'p': 0.5, 'r': 0.013636363636363636, 'f1': 0.026548672566371678}, 'combined': 0.01991150442477876, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 6}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 6}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 7
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 07:35:49.010608: step: 4/77, loss: 0.00365395937114954
2023-01-22 07:35:50.279429: step: 8/77, loss: 0.006277657113969326
2023-01-22 07:35:51.553027: step: 12/77, loss: 0.020647669211030006
2023-01-22 07:35:52.832220: step: 16/77, loss: 0.019607748836278915
2023-01-22 07:35:54.066006: step: 20/77, loss: 0.022213328629732132
2023-01-22 07:35:55.340307: step: 24/77, loss: 0.011937039904296398
2023-01-22 07:35:56.602442: step: 28/77, loss: 0.02456793561577797
2023-01-22 07:35:57.894455: step: 32/77, loss: 0.04214583709836006
2023-01-22 07:35:59.158847: step: 36/77, loss: 0.05198121815919876
2023-01-22 07:36:00.435054: step: 40/77, loss: 0.012112004682421684
2023-01-22 07:36:01.712877: step: 44/77, loss: 0.0383678674697876
2023-01-22 07:36:03.023146: step: 48/77, loss: 0.020618222653865814
2023-01-22 07:36:04.311273: step: 52/77, loss: 0.00845943484455347
2023-01-22 07:36:05.560837: step: 56/77, loss: 0.001100810943171382
2023-01-22 07:36:06.818657: step: 60/77, loss: 0.030928371474146843
2023-01-22 07:36:08.098934: step: 64/77, loss: 0.01059103012084961
2023-01-22 07:36:09.428203: step: 68/77, loss: 0.015934430062770844
2023-01-22 07:36:10.684843: step: 72/77, loss: 0.002905278466641903
2023-01-22 07:36:11.966223: step: 76/77, loss: 0.0014717906014993787
2023-01-22 07:36:13.261153: step: 80/77, loss: 0.014231668785214424
2023-01-22 07:36:14.570499: step: 84/77, loss: 0.01598450541496277
2023-01-22 07:36:15.893001: step: 88/77, loss: 6.96962742949836e-05
2023-01-22 07:36:17.235906: step: 92/77, loss: 0.0290484931319952
2023-01-22 07:36:18.497332: step: 96/77, loss: 0.027346597984433174
2023-01-22 07:36:19.817243: step: 100/77, loss: 0.01010982133448124
2023-01-22 07:36:21.064499: step: 104/77, loss: 0.028047332540154457
2023-01-22 07:36:22.402097: step: 108/77, loss: 0.003457102458924055
2023-01-22 07:36:23.755625: step: 112/77, loss: 0.03708508610725403
2023-01-22 07:36:25.051752: step: 116/77, loss: 0.016202857717871666
2023-01-22 07:36:26.388123: step: 120/77, loss: 0.04042280465364456
2023-01-22 07:36:27.671812: step: 124/77, loss: 0.040032271295785904
2023-01-22 07:36:29.014285: step: 128/77, loss: 0.05625339224934578
2023-01-22 07:36:30.337327: step: 132/77, loss: 0.034802548587322235
2023-01-22 07:36:31.616087: step: 136/77, loss: 0.0036582592874765396
2023-01-22 07:36:32.939396: step: 140/77, loss: 0.00691894581541419
2023-01-22 07:36:34.186647: step: 144/77, loss: 0.013843704015016556
2023-01-22 07:36:35.491272: step: 148/77, loss: 0.005941564217209816
2023-01-22 07:36:36.804938: step: 152/77, loss: 0.06688333302736282
2023-01-22 07:36:38.082842: step: 156/77, loss: 0.01571185328066349
2023-01-22 07:36:39.365809: step: 160/77, loss: 0.0064134192653000355
2023-01-22 07:36:40.690160: step: 164/77, loss: 0.0006494708359241486
2023-01-22 07:36:41.966052: step: 168/77, loss: 0.00016186948050744832
2023-01-22 07:36:43.262153: step: 172/77, loss: 0.03260376676917076
2023-01-22 07:36:44.552632: step: 176/77, loss: 0.016576889902353287
2023-01-22 07:36:45.878618: step: 180/77, loss: 0.08860062062740326
2023-01-22 07:36:47.129017: step: 184/77, loss: 0.004775453824549913
2023-01-22 07:36:48.417204: step: 188/77, loss: 0.10617873817682266
2023-01-22 07:36:49.711127: step: 192/77, loss: 0.014482242986559868
2023-01-22 07:36:51.017728: step: 196/77, loss: 0.037338465452194214
2023-01-22 07:36:52.316784: step: 200/77, loss: 0.011880840174853802
2023-01-22 07:36:53.617654: step: 204/77, loss: 0.02243220992386341
2023-01-22 07:36:54.919375: step: 208/77, loss: 0.006865553557872772
2023-01-22 07:36:56.268950: step: 212/77, loss: 0.023941833525896072
2023-01-22 07:36:57.590132: step: 216/77, loss: 0.048299212008714676
2023-01-22 07:36:58.913540: step: 220/77, loss: 0.04769997298717499
2023-01-22 07:37:00.184105: step: 224/77, loss: 0.0007127886055968702
2023-01-22 07:37:01.493368: step: 228/77, loss: 0.0004685519670601934
2023-01-22 07:37:02.828187: step: 232/77, loss: 0.020813144743442535
2023-01-22 07:37:04.154604: step: 236/77, loss: 0.005600340198725462
2023-01-22 07:37:05.494864: step: 240/77, loss: 0.10227024555206299
2023-01-22 07:37:06.865889: step: 244/77, loss: 0.015351877547800541
2023-01-22 07:37:08.202644: step: 248/77, loss: 0.0005788762355223298
2023-01-22 07:37:09.485223: step: 252/77, loss: 0.003927960526198149
2023-01-22 07:37:10.809264: step: 256/77, loss: 0.02673269994556904
2023-01-22 07:37:12.090438: step: 260/77, loss: 0.039880044758319855
2023-01-22 07:37:13.402468: step: 264/77, loss: 0.03469827026128769
2023-01-22 07:37:14.669701: step: 268/77, loss: 0.011209025979042053
2023-01-22 07:37:15.951740: step: 272/77, loss: 0.013481708243489265
2023-01-22 07:37:17.273324: step: 276/77, loss: 0.02489202469587326
2023-01-22 07:37:18.642960: step: 280/77, loss: 0.018024705350399017
2023-01-22 07:37:19.968215: step: 284/77, loss: 0.006658963393419981
2023-01-22 07:37:21.301948: step: 288/77, loss: 0.032713882625103
2023-01-22 07:37:22.600364: step: 292/77, loss: 0.013792910613119602
2023-01-22 07:37:23.920649: step: 296/77, loss: 0.02276519313454628
2023-01-22 07:37:25.203125: step: 300/77, loss: 0.013171669095754623
2023-01-22 07:37:26.485396: step: 304/77, loss: 0.0017072930932044983
2023-01-22 07:37:27.755714: step: 308/77, loss: 0.00681102741509676
2023-01-22 07:37:29.013853: step: 312/77, loss: 0.019400490447878838
2023-01-22 07:37:30.352331: step: 316/77, loss: 0.029169730842113495
2023-01-22 07:37:31.707058: step: 320/77, loss: 0.0014584583695977926
2023-01-22 07:37:33.031862: step: 324/77, loss: 0.04748348891735077
2023-01-22 07:37:34.370612: step: 328/77, loss: 0.013542639091610909
2023-01-22 07:37:35.624900: step: 332/77, loss: 0.03388283774256706
2023-01-22 07:37:36.989545: step: 336/77, loss: 0.00780377397313714
2023-01-22 07:37:38.289892: step: 340/77, loss: 0.039747536182403564
2023-01-22 07:37:39.626951: step: 344/77, loss: 0.014999479055404663
2023-01-22 07:37:40.925082: step: 348/77, loss: 0.023499522358179092
2023-01-22 07:37:42.242606: step: 352/77, loss: 0.2161271721124649
2023-01-22 07:37:43.585020: step: 356/77, loss: 0.018633641302585602
2023-01-22 07:37:44.888189: step: 360/77, loss: 0.017180128023028374
2023-01-22 07:37:46.222970: step: 364/77, loss: 0.14562822878360748
2023-01-22 07:37:47.537419: step: 368/77, loss: 0.04934248328208923
2023-01-22 07:37:48.835965: step: 372/77, loss: 0.004744932055473328
2023-01-22 07:37:50.132802: step: 376/77, loss: 0.03900888189673424
2023-01-22 07:37:51.464926: step: 380/77, loss: 0.014300035312771797
2023-01-22 07:37:52.777024: step: 384/77, loss: 0.02475110813975334
2023-01-22 07:37:54.111357: step: 388/77, loss: 0.0035867562983185053
==================================================
Loss: 0.025
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 7}
Test Chinese: {'template': {'p': 0.9390243902439024, 'r': 0.6260162601626016, 'f1': 0.751219512195122}, 'slot': {'p': 0.4594594594594595, 'r': 0.015454545454545455, 'f1': 0.029903254177660512}, 'combined': 0.022463908016388874, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 7}
Test Korean: {'template': {'p': 0.9390243902439024, 'r': 0.6260162601626016, 'f1': 0.751219512195122}, 'slot': {'p': 0.4594594594594595, 'r': 0.015454545454545455, 'f1': 0.029903254177660512}, 'combined': 0.022463908016388874, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 7}
Test Russian: {'template': {'p': 0.9390243902439024, 'r': 0.6260162601626016, 'f1': 0.751219512195122}, 'slot': {'p': 0.4594594594594595, 'r': 0.015454545454545455, 'f1': 0.029903254177660512}, 'combined': 0.022463908016388874, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 7}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 7}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 8
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 07:39:32.572099: step: 4/77, loss: 0.010056269355118275
2023-01-22 07:39:33.834538: step: 8/77, loss: 0.018890120089054108
2023-01-22 07:39:35.143073: step: 12/77, loss: 0.017161967232823372
2023-01-22 07:39:36.394790: step: 16/77, loss: 0.02055450901389122
2023-01-22 07:39:37.614189: step: 20/77, loss: 0.024720754474401474
2023-01-22 07:39:38.874501: step: 24/77, loss: 0.010491413995623589
2023-01-22 07:39:40.160996: step: 28/77, loss: 0.0037658684886991978
2023-01-22 07:39:41.477052: step: 32/77, loss: 0.038764867931604385
2023-01-22 07:39:42.793605: step: 36/77, loss: 0.03026004135608673
2023-01-22 07:39:44.036576: step: 40/77, loss: 0.02923579327762127
2023-01-22 07:39:45.380425: step: 44/77, loss: 0.04140114411711693
2023-01-22 07:39:46.633322: step: 48/77, loss: 0.033918458968400955
2023-01-22 07:39:47.923690: step: 52/77, loss: 0.00033601350151002407
2023-01-22 07:39:49.229678: step: 56/77, loss: 0.0021884054876863956
2023-01-22 07:39:50.529597: step: 60/77, loss: 0.005278467666357756
2023-01-22 07:39:51.818210: step: 64/77, loss: 0.07367675006389618
2023-01-22 07:39:53.097805: step: 68/77, loss: 0.05771408602595329
2023-01-22 07:39:54.398775: step: 72/77, loss: 0.08574645966291428
2023-01-22 07:39:55.711179: step: 76/77, loss: 0.013951526023447514
2023-01-22 07:39:56.979021: step: 80/77, loss: 0.016018124297261238
2023-01-22 07:39:58.268877: step: 84/77, loss: 0.00187723059207201
2023-01-22 07:39:59.580844: step: 88/77, loss: 0.002696490380913019
2023-01-22 07:40:00.925248: step: 92/77, loss: 0.013174856081604958
2023-01-22 07:40:02.281240: step: 96/77, loss: 0.005178231745958328
2023-01-22 07:40:03.632501: step: 100/77, loss: 0.019260739907622337
2023-01-22 07:40:04.981579: step: 104/77, loss: 0.05311047285795212
2023-01-22 07:40:06.251168: step: 108/77, loss: 0.01540825143456459
2023-01-22 07:40:07.549203: step: 112/77, loss: 0.006137767806649208
2023-01-22 07:40:08.821219: step: 116/77, loss: 0.01354296412318945
2023-01-22 07:40:10.195561: step: 120/77, loss: 0.016296926885843277
2023-01-22 07:40:11.510778: step: 124/77, loss: 0.0025672190822660923
2023-01-22 07:40:12.811429: step: 128/77, loss: 0.0595506876707077
2023-01-22 07:40:14.119958: step: 132/77, loss: 0.01555662415921688
2023-01-22 07:40:15.413828: step: 136/77, loss: 0.0031445412896573544
2023-01-22 07:40:16.728574: step: 140/77, loss: 0.0343557633459568
2023-01-22 07:40:18.006646: step: 144/77, loss: 0.00534120062366128
2023-01-22 07:40:19.292706: step: 148/77, loss: 0.015882568433880806
2023-01-22 07:40:20.535294: step: 152/77, loss: 0.0034859557636082172
2023-01-22 07:40:21.842243: step: 156/77, loss: 0.0897187888622284
2023-01-22 07:40:23.111300: step: 160/77, loss: 0.03130680322647095
2023-01-22 07:40:24.440251: step: 164/77, loss: 0.005163657478988171
2023-01-22 07:40:25.784146: step: 168/77, loss: 0.014301144517958164
2023-01-22 07:40:27.119128: step: 172/77, loss: 0.002605058718472719
2023-01-22 07:40:28.411281: step: 176/77, loss: 0.004895820282399654
2023-01-22 07:40:29.695836: step: 180/77, loss: 0.0005318675539456308
2023-01-22 07:40:30.991757: step: 184/77, loss: 0.02352241799235344
2023-01-22 07:40:32.289044: step: 188/77, loss: 0.009760452434420586
2023-01-22 07:40:33.632063: step: 192/77, loss: 0.0005129415076225996
2023-01-22 07:40:34.931822: step: 196/77, loss: 0.04506408050656319
2023-01-22 07:40:36.224613: step: 200/77, loss: 0.009796293452382088
2023-01-22 07:40:37.585112: step: 204/77, loss: 0.00035782958730123937
2023-01-22 07:40:38.922610: step: 208/77, loss: 0.031156811863183975
2023-01-22 07:40:40.279799: step: 212/77, loss: 0.038962021470069885
2023-01-22 07:40:41.571408: step: 216/77, loss: 0.003285457845777273
2023-01-22 07:40:42.900138: step: 220/77, loss: 0.030111942440271378
2023-01-22 07:40:44.225620: step: 224/77, loss: 0.0034210169687867165
2023-01-22 07:40:45.458818: step: 228/77, loss: 0.003368095261976123
2023-01-22 07:40:46.782476: step: 232/77, loss: 0.028834929689764977
2023-01-22 07:40:48.118929: step: 236/77, loss: 0.005496030207723379
2023-01-22 07:40:49.399075: step: 240/77, loss: 0.0867997258901596
2023-01-22 07:40:50.705261: step: 244/77, loss: 0.013414930552244186
2023-01-22 07:40:52.022592: step: 248/77, loss: 0.11154910922050476
2023-01-22 07:40:53.361207: step: 252/77, loss: 0.01679971069097519
2023-01-22 07:40:54.697450: step: 256/77, loss: 0.016359906643629074
2023-01-22 07:40:56.011161: step: 260/77, loss: 0.03159204125404358
2023-01-22 07:40:57.333555: step: 264/77, loss: 0.006481696851551533
2023-01-22 07:40:58.671718: step: 268/77, loss: 0.0011871152091771364
2023-01-22 07:40:59.978960: step: 272/77, loss: 0.02756771445274353
2023-01-22 07:41:01.220980: step: 276/77, loss: 0.006530491169542074
2023-01-22 07:41:02.521557: step: 280/77, loss: 0.04043383151292801
2023-01-22 07:41:03.839249: step: 284/77, loss: 0.03230508789420128
2023-01-22 07:41:05.187859: step: 288/77, loss: 0.014443744905292988
2023-01-22 07:41:06.452432: step: 292/77, loss: 0.009209951385855675
2023-01-22 07:41:07.716070: step: 296/77, loss: 0.019323663786053658
2023-01-22 07:41:09.067701: step: 300/77, loss: 0.09706917405128479
2023-01-22 07:41:10.348400: step: 304/77, loss: 0.017132218927145004
2023-01-22 07:41:11.662112: step: 308/77, loss: 0.008376318961381912
2023-01-22 07:41:12.959375: step: 312/77, loss: 0.018071360886096954
2023-01-22 07:41:14.280106: step: 316/77, loss: 0.021176446229219437
2023-01-22 07:41:15.567294: step: 320/77, loss: 0.008609825745224953
2023-01-22 07:41:16.890331: step: 324/77, loss: 0.015605449676513672
2023-01-22 07:41:18.183871: step: 328/77, loss: 0.027690229937434196
2023-01-22 07:41:19.488600: step: 332/77, loss: 0.10342463850975037
2023-01-22 07:41:20.782446: step: 336/77, loss: 0.07532121986150742
2023-01-22 07:41:22.109393: step: 340/77, loss: 0.0045474437065422535
2023-01-22 07:41:23.415536: step: 344/77, loss: 0.014486493542790413
2023-01-22 07:41:24.714523: step: 348/77, loss: 0.015550438314676285
2023-01-22 07:41:26.036348: step: 352/77, loss: 0.0368066281080246
2023-01-22 07:41:27.320233: step: 356/77, loss: 0.007086616940796375
2023-01-22 07:41:28.623680: step: 360/77, loss: 0.017183110117912292
2023-01-22 07:41:29.960048: step: 364/77, loss: 0.011694397777318954
2023-01-22 07:41:31.237513: step: 368/77, loss: 0.011689573526382446
2023-01-22 07:41:32.509865: step: 372/77, loss: 0.08766619861125946
2023-01-22 07:41:33.859223: step: 376/77, loss: 0.0017116167582571507
2023-01-22 07:41:35.133883: step: 380/77, loss: 0.0179583802819252
2023-01-22 07:41:36.414912: step: 384/77, loss: 0.0024103238247334957
2023-01-22 07:41:37.755596: step: 388/77, loss: 0.004919702652841806
==================================================
Loss: 0.023
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 8}
Test Chinese: {'template': {'p': 0.9746835443037974, 'r': 0.6260162601626016, 'f1': 0.7623762376237624}, 'slot': {'p': 0.4146341463414634, 'r': 0.015454545454545455, 'f1': 0.02979842243645925}, 'combined': 0.02271760918423131, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 8}
Test Korean: {'template': {'p': 0.9746835443037974, 'r': 0.6260162601626016, 'f1': 0.7623762376237624}, 'slot': {'p': 0.4146341463414634, 'r': 0.015454545454545455, 'f1': 0.02979842243645925}, 'combined': 0.02271760918423131, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 8}
Test Russian: {'template': {'p': 0.9746835443037974, 'r': 0.6260162601626016, 'f1': 0.7623762376237624}, 'slot': {'p': 0.4146341463414634, 'r': 0.015454545454545455, 'f1': 0.02979842243645925}, 'combined': 0.02271760918423131, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 8}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 8}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 9
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 07:43:16.303224: step: 4/77, loss: 0.009951209649443626
2023-01-22 07:43:17.654690: step: 8/77, loss: 0.01025527622550726
2023-01-22 07:43:18.932759: step: 12/77, loss: 0.010599697008728981
2023-01-22 07:43:20.215956: step: 16/77, loss: 2.8813841709052213e-05
2023-01-22 07:43:21.529569: step: 20/77, loss: 0.015449351631104946
2023-01-22 07:43:22.810644: step: 24/77, loss: 0.013126425445079803
2023-01-22 07:43:24.117672: step: 28/77, loss: 0.024598799645900726
2023-01-22 07:43:25.394495: step: 32/77, loss: 0.015080241486430168
2023-01-22 07:43:26.669282: step: 36/77, loss: 0.04678387939929962
2023-01-22 07:43:27.953064: step: 40/77, loss: 0.012904101982712746
2023-01-22 07:43:29.260919: step: 44/77, loss: 0.015326356515288353
2023-01-22 07:43:30.548624: step: 48/77, loss: 0.021616067737340927
2023-01-22 07:43:31.835951: step: 52/77, loss: 0.016074180603027344
2023-01-22 07:43:33.083702: step: 56/77, loss: 0.013141414150595665
2023-01-22 07:43:34.413347: step: 60/77, loss: 0.05112868547439575
2023-01-22 07:43:35.693371: step: 64/77, loss: 0.0026340484619140625
2023-01-22 07:43:36.965059: step: 68/77, loss: 0.002100118901580572
2023-01-22 07:43:38.261352: step: 72/77, loss: 0.17738491296768188
2023-01-22 07:43:39.558567: step: 76/77, loss: 0.037238575518131256
2023-01-22 07:43:40.831832: step: 80/77, loss: 0.01159091666340828
2023-01-22 07:43:42.132476: step: 84/77, loss: 8.563547453377396e-05
2023-01-22 07:43:43.444509: step: 88/77, loss: 0.0001513077295385301
2023-01-22 07:43:44.744211: step: 92/77, loss: 0.02696680650115013
2023-01-22 07:43:46.013391: step: 96/77, loss: 0.0179781224578619
2023-01-22 07:43:47.294198: step: 100/77, loss: 0.06407640874385834
2023-01-22 07:43:48.632164: step: 104/77, loss: 0.0012260295916348696
2023-01-22 07:43:49.926978: step: 108/77, loss: 0.007572871632874012
2023-01-22 07:43:51.188489: step: 112/77, loss: 0.005561821162700653
2023-01-22 07:43:52.517882: step: 116/77, loss: 0.010646567679941654
2023-01-22 07:43:53.865324: step: 120/77, loss: 0.012919003143906593
2023-01-22 07:43:55.118072: step: 124/77, loss: 0.012604203075170517
2023-01-22 07:43:56.398499: step: 128/77, loss: 0.05541830509901047
2023-01-22 07:43:57.704249: step: 132/77, loss: 0.03553691506385803
2023-01-22 07:43:58.997658: step: 136/77, loss: 0.01568058505654335
2023-01-22 07:44:00.343145: step: 140/77, loss: 0.03287587687373161
2023-01-22 07:44:01.617893: step: 144/77, loss: 0.0027599541936069727
2023-01-22 07:44:02.963452: step: 148/77, loss: 0.01692170463502407
2023-01-22 07:44:04.233807: step: 152/77, loss: 0.08928981423377991
2023-01-22 07:44:05.570079: step: 156/77, loss: 0.04975442215800285
2023-01-22 07:44:06.880405: step: 160/77, loss: 0.02008040063083172
2023-01-22 07:44:08.168179: step: 164/77, loss: 0.0019231241894885898
2023-01-22 07:44:09.491154: step: 168/77, loss: 0.0244793388992548
2023-01-22 07:44:10.765656: step: 172/77, loss: 0.010686839930713177
2023-01-22 07:44:12.044849: step: 176/77, loss: 0.0025486641097813845
2023-01-22 07:44:13.339011: step: 180/77, loss: 0.0068518416956067085
2023-01-22 07:44:14.612731: step: 184/77, loss: 0.014136513695120811
2023-01-22 07:44:15.928586: step: 188/77, loss: 0.03422325477004051
2023-01-22 07:44:17.250235: step: 192/77, loss: 0.0019678741227835417
2023-01-22 07:44:18.567975: step: 196/77, loss: 0.003199803875759244
2023-01-22 07:44:19.818719: step: 200/77, loss: 0.00686542596668005
2023-01-22 07:44:21.124189: step: 204/77, loss: 0.00038556900108233094
2023-01-22 07:44:22.443790: step: 208/77, loss: 0.00295876432210207
2023-01-22 07:44:23.726256: step: 212/77, loss: 8.276679000118747e-05
2023-01-22 07:44:25.030120: step: 216/77, loss: 0.009483201429247856
2023-01-22 07:44:26.306107: step: 220/77, loss: 0.009370522573590279
2023-01-22 07:44:27.582433: step: 224/77, loss: 0.025101710110902786
2023-01-22 07:44:28.921150: step: 228/77, loss: 0.020489763468503952
2023-01-22 07:44:30.213900: step: 232/77, loss: 0.0010126195847988129
2023-01-22 07:44:31.533986: step: 236/77, loss: 0.02698575146496296
2023-01-22 07:44:32.892454: step: 240/77, loss: 0.04893007129430771
2023-01-22 07:44:34.197624: step: 244/77, loss: 0.012933338060975075
2023-01-22 07:44:35.480063: step: 248/77, loss: 0.016066405922174454
2023-01-22 07:44:36.756638: step: 252/77, loss: 0.00607153307646513
2023-01-22 07:44:38.128298: step: 256/77, loss: 0.0004491469881031662
2023-01-22 07:44:39.487939: step: 260/77, loss: 0.14309868216514587
2023-01-22 07:44:40.770998: step: 264/77, loss: 0.01501578837633133
2023-01-22 07:44:42.100566: step: 268/77, loss: 0.006420220248401165
2023-01-22 07:44:43.438264: step: 272/77, loss: 0.028947584331035614
2023-01-22 07:44:44.732785: step: 276/77, loss: 0.03736587241292
2023-01-22 07:44:46.052615: step: 280/77, loss: 0.0055717648938298225
2023-01-22 07:44:47.326951: step: 284/77, loss: 0.017412912100553513
2023-01-22 07:44:48.617611: step: 288/77, loss: 0.01638699881732464
2023-01-22 07:44:49.912089: step: 292/77, loss: 0.003690283978357911
2023-01-22 07:44:51.191527: step: 296/77, loss: 0.0013558377977460623
2023-01-22 07:44:52.492087: step: 300/77, loss: 0.018798088654875755
2023-01-22 07:44:53.801437: step: 304/77, loss: 0.004140047822147608
2023-01-22 07:44:55.079616: step: 308/77, loss: 0.007700146175920963
2023-01-22 07:44:56.348528: step: 312/77, loss: 0.017628833651542664
2023-01-22 07:44:57.621034: step: 316/77, loss: 0.016042888164520264
2023-01-22 07:44:58.918815: step: 320/77, loss: 0.01528505515307188
2023-01-22 07:45:00.250988: step: 324/77, loss: 0.02525682933628559
2023-01-22 07:45:01.599281: step: 328/77, loss: 0.02757682465016842
2023-01-22 07:45:02.896860: step: 332/77, loss: 0.10388769954442978
2023-01-22 07:45:04.272544: step: 336/77, loss: 0.012050546705722809
2023-01-22 07:45:05.611291: step: 340/77, loss: 0.07141268998384476
2023-01-22 07:45:06.901187: step: 344/77, loss: 0.01598818600177765
2023-01-22 07:45:08.221380: step: 348/77, loss: 0.017102017998695374
2023-01-22 07:45:09.491966: step: 352/77, loss: 0.0203529205173254
2023-01-22 07:45:10.724683: step: 356/77, loss: 0.05472177267074585
2023-01-22 07:45:12.024815: step: 360/77, loss: 0.10159629583358765
2023-01-22 07:45:13.332539: step: 364/77, loss: 0.011427942663431168
2023-01-22 07:45:14.595119: step: 368/77, loss: 0.047470469027757645
2023-01-22 07:45:15.940439: step: 372/77, loss: 0.00397944450378418
2023-01-22 07:45:17.242845: step: 376/77, loss: 0.030490266159176826
2023-01-22 07:45:18.559247: step: 380/77, loss: 0.02138015814125538
2023-01-22 07:45:19.876519: step: 384/77, loss: 0.049235884100198746
2023-01-22 07:45:21.187878: step: 388/77, loss: 0.013251261785626411
==================================================
Loss: 0.023
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 9}
Test Chinese: {'template': {'p': 0.9634146341463414, 'r': 0.6422764227642277, 'f1': 0.7707317073170733}, 'slot': {'p': 0.5588235294117647, 'r': 0.017272727272727273, 'f1': 0.03350970017636684}, 'combined': 0.025826988428614448, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05085442919642522, 'epoch': 9}
Test Korean: {'template': {'p': 0.9753086419753086, 'r': 0.6422764227642277, 'f1': 0.7745098039215687}, 'slot': {'p': 0.5757575757575758, 'r': 0.017272727272727273, 'f1': 0.033539276257722864}, 'combined': 0.025976498278040258, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 9}
Test Russian: {'template': {'p': 0.9753086419753086, 'r': 0.6422764227642277, 'f1': 0.7745098039215687}, 'slot': {'p': 0.5757575757575758, 'r': 0.017272727272727273, 'f1': 0.033539276257722864}, 'combined': 0.025976498278040258, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 9}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'template': {'p': 1.0, 'r': 0.25, 'f1': 0.4}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 10
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 07:46:59.412125: step: 4/77, loss: 0.03768238425254822
2023-01-22 07:47:00.738585: step: 8/77, loss: 0.028346769511699677
2023-01-22 07:47:02.025951: step: 12/77, loss: 0.00744956498965621
2023-01-22 07:47:03.338381: step: 16/77, loss: 0.048924703150987625
2023-01-22 07:47:04.669342: step: 20/77, loss: 0.03151417896151543
2023-01-22 07:47:05.966676: step: 24/77, loss: 0.002606735099107027
2023-01-22 07:47:07.226255: step: 28/77, loss: 0.0024922217708081007
2023-01-22 07:47:08.580659: step: 32/77, loss: 0.048660993576049805
2023-01-22 07:47:09.905471: step: 36/77, loss: 0.004283279180526733
2023-01-22 07:47:11.193617: step: 40/77, loss: 0.04208429902791977
2023-01-22 07:47:12.508976: step: 44/77, loss: 0.01696396991610527
2023-01-22 07:47:13.786033: step: 48/77, loss: 0.010859989561140537
2023-01-22 07:47:15.060508: step: 52/77, loss: 0.006402358412742615
2023-01-22 07:47:16.323453: step: 56/77, loss: 0.0019209606107324362
2023-01-22 07:47:17.631640: step: 60/77, loss: 0.0024111694656312466
2023-01-22 07:47:18.951384: step: 64/77, loss: 0.00038403054350055754
2023-01-22 07:47:20.316908: step: 68/77, loss: 0.0019636116921901703
2023-01-22 07:47:21.601026: step: 72/77, loss: 0.015139022842049599
2023-01-22 07:47:22.918204: step: 76/77, loss: 0.018672920763492584
2023-01-22 07:47:24.245622: step: 80/77, loss: 0.0020270387176424265
2023-01-22 07:47:25.483091: step: 84/77, loss: 0.009439261630177498
2023-01-22 07:47:26.776656: step: 88/77, loss: 0.008923723362386227
2023-01-22 07:47:28.012951: step: 92/77, loss: 0.00011983791046077386
2023-01-22 07:47:29.301175: step: 96/77, loss: 0.006050101015716791
2023-01-22 07:47:30.633957: step: 100/77, loss: 0.0179508775472641
2023-01-22 07:47:31.902104: step: 104/77, loss: 0.017849788069725037
2023-01-22 07:47:33.170051: step: 108/77, loss: 0.017486661672592163
2023-01-22 07:47:34.472447: step: 112/77, loss: 0.007766797207295895
2023-01-22 07:47:35.746853: step: 116/77, loss: 0.019981278106570244
2023-01-22 07:47:37.054335: step: 120/77, loss: 0.002379945944994688
2023-01-22 07:47:38.282615: step: 124/77, loss: 0.011582271195948124
2023-01-22 07:47:39.567752: step: 128/77, loss: 0.040890343487262726
2023-01-22 07:47:40.827904: step: 132/77, loss: 0.019269846379756927
2023-01-22 07:47:42.136989: step: 136/77, loss: 0.03777790069580078
2023-01-22 07:47:43.418164: step: 140/77, loss: 0.00588800897821784
2023-01-22 07:47:44.703966: step: 144/77, loss: 0.04820588603615761
2023-01-22 07:47:45.999233: step: 148/77, loss: 0.009185411036014557
2023-01-22 07:47:47.300843: step: 152/77, loss: 0.002547596348449588
2023-01-22 07:47:48.594623: step: 156/77, loss: 0.030245959758758545
2023-01-22 07:47:49.932170: step: 160/77, loss: 0.0031875655986368656
2023-01-22 07:47:51.182307: step: 164/77, loss: 0.053960613906383514
2023-01-22 07:47:52.483721: step: 168/77, loss: 0.009313058108091354
2023-01-22 07:47:53.758495: step: 172/77, loss: 0.03616435080766678
2023-01-22 07:47:55.097454: step: 176/77, loss: 0.006441659759730101
2023-01-22 07:47:56.474770: step: 180/77, loss: 0.012755388393998146
2023-01-22 07:47:57.744182: step: 184/77, loss: 0.01913641393184662
2023-01-22 07:47:59.072172: step: 188/77, loss: 0.011171862483024597
2023-01-22 07:48:00.339415: step: 192/77, loss: 0.05577773600816727
2023-01-22 07:48:01.624310: step: 196/77, loss: 0.014128005132079124
2023-01-22 07:48:02.886410: step: 200/77, loss: 0.0018707435810938478
2023-01-22 07:48:04.155413: step: 204/77, loss: 0.0009870977373793721
2023-01-22 07:48:05.398990: step: 208/77, loss: 0.015966808423399925
2023-01-22 07:48:06.708948: step: 212/77, loss: 0.003523885505273938
2023-01-22 07:48:07.987665: step: 216/77, loss: 0.0007100008078850806
2023-01-22 07:48:09.344595: step: 220/77, loss: 0.009846840053796768
2023-01-22 07:48:10.622712: step: 224/77, loss: 0.003518306650221348
2023-01-22 07:48:11.938654: step: 228/77, loss: 0.013546239584684372
2023-01-22 07:48:13.195765: step: 232/77, loss: 0.008653189055621624
2023-01-22 07:48:14.525511: step: 236/77, loss: 0.0033769761212170124
2023-01-22 07:48:15.821409: step: 240/77, loss: 0.009792322292923927
2023-01-22 07:48:17.094842: step: 244/77, loss: 0.07129838317632675
2023-01-22 07:48:18.395713: step: 248/77, loss: 0.5841067433357239
2023-01-22 07:48:19.672195: step: 252/77, loss: 0.0452253594994545
2023-01-22 07:48:20.954710: step: 256/77, loss: 0.014134548604488373
2023-01-22 07:48:22.273135: step: 260/77, loss: 0.007768142968416214
2023-01-22 07:48:23.530154: step: 264/77, loss: 0.006193614564836025
2023-01-22 07:48:24.880676: step: 268/77, loss: 0.035763513296842575
2023-01-22 07:48:26.155855: step: 272/77, loss: 0.0006083827465772629
2023-01-22 07:48:27.460508: step: 276/77, loss: 0.07475440204143524
2023-01-22 07:48:28.750471: step: 280/77, loss: 0.0016128707211464643
2023-01-22 07:48:30.056842: step: 284/77, loss: 0.0022124836686998606
2023-01-22 07:48:31.342888: step: 288/77, loss: 0.03743232414126396
2023-01-22 07:48:32.691001: step: 292/77, loss: 0.008901816792786121
2023-01-22 07:48:33.940718: step: 296/77, loss: 0.0004599709063768387
2023-01-22 07:48:35.237760: step: 300/77, loss: 0.019326256588101387
2023-01-22 07:48:36.539292: step: 304/77, loss: 0.05005129799246788
2023-01-22 07:48:37.824739: step: 308/77, loss: 0.021847281605005264
2023-01-22 07:48:39.081936: step: 312/77, loss: 0.01302673015743494
2023-01-22 07:48:40.335368: step: 316/77, loss: 0.03336362540721893
2023-01-22 07:48:41.629607: step: 320/77, loss: 0.035148534923791885
2023-01-22 07:48:42.913209: step: 324/77, loss: 0.02668309211730957
2023-01-22 07:48:44.173137: step: 328/77, loss: 0.010160962119698524
2023-01-22 07:48:45.442942: step: 332/77, loss: 0.018455471843481064
2023-01-22 07:48:46.760474: step: 336/77, loss: 0.0010307406773790717
2023-01-22 07:48:48.060617: step: 340/77, loss: 0.0395384207367897
2023-01-22 07:48:49.313450: step: 344/77, loss: 0.031024860218167305
2023-01-22 07:48:50.654751: step: 348/77, loss: 0.007934034802019596
2023-01-22 07:48:51.984641: step: 352/77, loss: 0.020924028009176254
2023-01-22 07:48:53.271384: step: 356/77, loss: 0.007340208627283573
2023-01-22 07:48:54.522681: step: 360/77, loss: 0.026930680498480797
2023-01-22 07:48:55.793950: step: 364/77, loss: 0.017858322709798813
2023-01-22 07:48:57.142973: step: 368/77, loss: 0.018936611711978912
2023-01-22 07:48:58.428800: step: 372/77, loss: 0.0034472201950848103
2023-01-22 07:48:59.780546: step: 376/77, loss: 0.03166472539305687
2023-01-22 07:49:01.092216: step: 380/77, loss: 0.0009081726893782616
2023-01-22 07:49:02.463090: step: 384/77, loss: 0.02587328478693962
2023-01-22 07:49:03.777422: step: 388/77, loss: 0.0031165271066129208
==================================================
Loss: 0.024
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 10}
Test Chinese: {'template': {'p': 0.9594594594594594, 'r': 0.5772357723577236, 'f1': 0.7208121827411168}, 'slot': {'p': 0.5483870967741935, 'r': 0.015454545454545455, 'f1': 0.030061892130857647}, 'combined': 0.021668978084171505, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 10}
Test Korean: {'template': {'p': 0.958904109589041, 'r': 0.5691056910569106, 'f1': 0.7142857142857142}, 'slot': {'p': 0.5161290322580645, 'r': 0.014545454545454545, 'f1': 0.028293545534924847}, 'combined': 0.020209675382089173, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 10}
Test Russian: {'template': {'p': 0.9594594594594594, 'r': 0.5772357723577236, 'f1': 0.7208121827411168}, 'slot': {'p': 0.5151515151515151, 'r': 0.015454545454545455, 'f1': 0.030008826125330977}, 'combined': 0.02163072746089847, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 10}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 10}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 11
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 07:50:39.617775: step: 4/77, loss: 0.00913262739777565
2023-01-22 07:50:40.872672: step: 8/77, loss: 0.023702571168541908
2023-01-22 07:50:42.164863: step: 12/77, loss: 7.023927173577249e-05
2023-01-22 07:50:43.501610: step: 16/77, loss: 0.015598413534462452
2023-01-22 07:50:44.810613: step: 20/77, loss: 0.017305485904216766
2023-01-22 07:50:46.111644: step: 24/77, loss: 0.05371349677443504
2023-01-22 07:50:47.406765: step: 28/77, loss: 0.011336155235767365
2023-01-22 07:50:48.728569: step: 32/77, loss: 0.0017175760585814714
2023-01-22 07:50:49.998234: step: 36/77, loss: 0.00044242324656806886
2023-01-22 07:50:51.321519: step: 40/77, loss: 0.00024273883900605142
2023-01-22 07:50:52.620215: step: 44/77, loss: 0.03868889808654785
2023-01-22 07:50:53.912803: step: 48/77, loss: 0.004320107400417328
2023-01-22 07:50:55.204449: step: 52/77, loss: 0.00013211331679485738
2023-01-22 07:50:56.483464: step: 56/77, loss: 0.014553715474903584
2023-01-22 07:50:57.779454: step: 60/77, loss: 0.0039396206848323345
2023-01-22 07:50:59.092636: step: 64/77, loss: 0.008579259738326073
2023-01-22 07:51:00.405168: step: 68/77, loss: 0.02406681329011917
2023-01-22 07:51:01.726653: step: 72/77, loss: 0.026409517973661423
2023-01-22 07:51:03.013165: step: 76/77, loss: 0.02277933806180954
2023-01-22 07:51:04.330127: step: 80/77, loss: 0.014436050318181515
2023-01-22 07:51:05.642828: step: 84/77, loss: 0.012562789022922516
2023-01-22 07:51:06.949529: step: 88/77, loss: 0.00025714567163959146
2023-01-22 07:51:08.198802: step: 92/77, loss: 0.0011654815170913935
2023-01-22 07:51:09.494397: step: 96/77, loss: 7.128174183890224e-05
2023-01-22 07:51:10.771659: step: 100/77, loss: 0.0016908040270209312
2023-01-22 07:51:12.081223: step: 104/77, loss: 0.05296008661389351
2023-01-22 07:51:13.350834: step: 108/77, loss: 0.0006149305845610797
2023-01-22 07:51:14.585659: step: 112/77, loss: 0.07239086925983429
2023-01-22 07:51:15.884175: step: 116/77, loss: 0.005651980172842741
2023-01-22 07:51:17.111498: step: 120/77, loss: 0.025895126163959503
2023-01-22 07:51:18.403763: step: 124/77, loss: 0.03647073358297348
2023-01-22 07:51:19.683002: step: 128/77, loss: 3.863106030621566e-05
2023-01-22 07:51:20.987547: step: 132/77, loss: 0.009307922795414925
2023-01-22 07:51:22.254434: step: 136/77, loss: 0.0012862995499745011
2023-01-22 07:51:23.559212: step: 140/77, loss: 0.011451378464698792
2023-01-22 07:51:24.816510: step: 144/77, loss: 0.0032769562676548958
2023-01-22 07:51:26.127722: step: 148/77, loss: 0.005432584322988987
2023-01-22 07:51:27.393079: step: 152/77, loss: 0.024685127660632133
2023-01-22 07:51:28.712214: step: 156/77, loss: 0.013838456943631172
2023-01-22 07:51:29.993199: step: 160/77, loss: 0.0025978866033256054
2023-01-22 07:51:31.281186: step: 164/77, loss: 0.008826863020658493
2023-01-22 07:51:32.592219: step: 168/77, loss: 0.005616775713860989
2023-01-22 07:51:33.893678: step: 172/77, loss: 0.008297703228890896
2023-01-22 07:51:35.195808: step: 176/77, loss: 0.009488863870501518
2023-01-22 07:51:36.480811: step: 180/77, loss: 0.0032529172021895647
2023-01-22 07:51:37.762931: step: 184/77, loss: 0.0705006793141365
2023-01-22 07:51:39.050941: step: 188/77, loss: 0.008520006202161312
2023-01-22 07:51:40.341140: step: 192/77, loss: 0.0003739010135177523
2023-01-22 07:51:41.616386: step: 196/77, loss: 0.009315535426139832
2023-01-22 07:51:42.878674: step: 200/77, loss: 0.004182401578873396
2023-01-22 07:51:44.157941: step: 204/77, loss: 0.0474054291844368
2023-01-22 07:51:45.424990: step: 208/77, loss: 0.05022357776761055
2023-01-22 07:51:46.657083: step: 212/77, loss: 0.011805780231952667
2023-01-22 07:51:47.900541: step: 216/77, loss: 0.062389228492975235
2023-01-22 07:51:49.206144: step: 220/77, loss: 0.06036899983882904
2023-01-22 07:51:50.496087: step: 224/77, loss: 0.0013627760345116258
2023-01-22 07:51:51.821224: step: 228/77, loss: 0.04754606634378433
2023-01-22 07:51:53.127457: step: 232/77, loss: 0.004517616704106331
2023-01-22 07:51:54.428054: step: 236/77, loss: 6.662487430730835e-05
2023-01-22 07:51:55.797228: step: 240/77, loss: 0.01598535105586052
2023-01-22 07:51:57.149996: step: 244/77, loss: 0.024257568642497063
2023-01-22 07:51:58.460477: step: 248/77, loss: 0.024137431755661964
2023-01-22 07:51:59.715248: step: 252/77, loss: 0.024435149505734444
2023-01-22 07:52:01.014062: step: 256/77, loss: 0.007032178808003664
2023-01-22 07:52:02.320437: step: 260/77, loss: 0.005066059995442629
2023-01-22 07:52:03.646048: step: 264/77, loss: 0.0007375497953034937
2023-01-22 07:52:04.964793: step: 268/77, loss: 0.0025754738599061966
2023-01-22 07:52:06.242063: step: 272/77, loss: 0.012038455344736576
2023-01-22 07:52:07.533079: step: 276/77, loss: 0.03843052312731743
2023-01-22 07:52:08.822970: step: 280/77, loss: 0.01894669234752655
2023-01-22 07:52:10.116339: step: 284/77, loss: 0.015208638273179531
2023-01-22 07:52:11.458056: step: 288/77, loss: 0.006000806577503681
2023-01-22 07:52:12.782182: step: 292/77, loss: 0.0017294568242505193
2023-01-22 07:52:14.076788: step: 296/77, loss: 0.0027547322679311037
2023-01-22 07:52:15.332220: step: 300/77, loss: 0.002827903488650918
2023-01-22 07:52:16.614064: step: 304/77, loss: 0.024109508842229843
2023-01-22 07:52:17.897491: step: 308/77, loss: 0.03593812137842178
2023-01-22 07:52:19.131994: step: 312/77, loss: 0.003940297290682793
2023-01-22 07:52:20.408572: step: 316/77, loss: 0.04253112152218819
2023-01-22 07:52:21.693729: step: 320/77, loss: 0.056184787303209305
2023-01-22 07:52:23.003139: step: 324/77, loss: 0.0005866457941010594
2023-01-22 07:52:24.287281: step: 328/77, loss: 0.0031070266850292683
2023-01-22 07:52:25.538844: step: 332/77, loss: 0.004228291101753712
2023-01-22 07:52:26.748483: step: 336/77, loss: 0.013488009572029114
2023-01-22 07:52:28.035312: step: 340/77, loss: 0.00031433472759090364
2023-01-22 07:52:29.344881: step: 344/77, loss: 0.01137051172554493
2023-01-22 07:52:30.662501: step: 348/77, loss: 0.02159648761153221
2023-01-22 07:52:31.933281: step: 352/77, loss: 0.0018602788913995028
2023-01-22 07:52:33.259215: step: 356/77, loss: 8.241426985478029e-05
2023-01-22 07:52:34.624251: step: 360/77, loss: 0.008178231306374073
2023-01-22 07:52:35.960922: step: 364/77, loss: 0.053727056831121445
2023-01-22 07:52:37.225022: step: 368/77, loss: 0.08346982300281525
2023-01-22 07:52:38.558944: step: 372/77, loss: 0.008330187760293484
2023-01-22 07:52:39.843766: step: 376/77, loss: 0.10757150501012802
2023-01-22 07:52:41.125247: step: 380/77, loss: 0.07443412393331528
2023-01-22 07:52:42.417908: step: 384/77, loss: 0.0016130568692460656
2023-01-22 07:52:43.742741: step: 388/77, loss: 0.03187939152121544
==================================================
Loss: 0.018
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 11}
Test Chinese: {'template': {'p': 0.9397590361445783, 'r': 0.6341463414634146, 'f1': 0.7572815533980584}, 'slot': {'p': 0.47619047619047616, 'r': 0.01818181818181818, 'f1': 0.0350262697022767}, 'combined': 0.026524747929879446, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 11}
Test Korean: {'template': {'p': 0.9397590361445783, 'r': 0.6341463414634146, 'f1': 0.7572815533980584}, 'slot': {'p': 0.46511627906976744, 'r': 0.01818181818181818, 'f1': 0.034995625546806644}, 'combined': 0.026501541676222512, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 11}
Test Russian: {'template': {'p': 0.9397590361445783, 'r': 0.6341463414634146, 'f1': 0.7572815533980584}, 'slot': {'p': 0.46511627906976744, 'r': 0.01818181818181818, 'f1': 0.034995625546806644}, 'combined': 0.026501541676222512, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 11}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 11}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 12
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 07:54:20.471143: step: 4/77, loss: 0.026703253388404846
2023-01-22 07:54:21.723545: step: 8/77, loss: 6.608450348721817e-05
2023-01-22 07:54:22.954591: step: 12/77, loss: 0.0021594602148979902
2023-01-22 07:54:24.211045: step: 16/77, loss: 0.0006289744051173329
2023-01-22 07:54:25.494158: step: 20/77, loss: 0.018942205235362053
2023-01-22 07:54:26.798079: step: 24/77, loss: 0.013272013515233994
2023-01-22 07:54:28.062541: step: 28/77, loss: 0.01688517816364765
2023-01-22 07:54:29.332871: step: 32/77, loss: 0.01106287818402052
2023-01-22 07:54:30.609218: step: 36/77, loss: 0.032344695180654526
2023-01-22 07:54:31.907546: step: 40/77, loss: 0.0002201721363235265
2023-01-22 07:54:33.218992: step: 44/77, loss: 0.0014146651374176145
2023-01-22 07:54:34.489961: step: 48/77, loss: 0.011268083937466145
2023-01-22 07:54:35.826796: step: 52/77, loss: 0.01278699655085802
2023-01-22 07:54:37.152212: step: 56/77, loss: 0.012389368377625942
2023-01-22 07:54:38.383697: step: 60/77, loss: 0.02331053465604782
2023-01-22 07:54:39.623921: step: 64/77, loss: 0.01478915847837925
2023-01-22 07:54:40.929350: step: 68/77, loss: 0.006758468225598335
2023-01-22 07:54:42.234586: step: 72/77, loss: 0.00636525172740221
2023-01-22 07:54:43.538540: step: 76/77, loss: 0.0365261435508728
2023-01-22 07:54:44.836792: step: 80/77, loss: 0.007071449421346188
2023-01-22 07:54:46.084212: step: 84/77, loss: 0.0159720741212368
2023-01-22 07:54:47.409637: step: 88/77, loss: 3.108736564172432e-05
2023-01-22 07:54:48.684724: step: 92/77, loss: 0.002529098652303219
2023-01-22 07:54:49.967389: step: 96/77, loss: 0.01439334824681282
2023-01-22 07:54:51.205136: step: 100/77, loss: 0.01917685568332672
2023-01-22 07:54:52.498936: step: 104/77, loss: 0.004402280319482088
2023-01-22 07:54:53.749800: step: 108/77, loss: 0.004489831626415253
2023-01-22 07:54:55.053111: step: 112/77, loss: 0.04092923924326897
2023-01-22 07:54:56.318985: step: 116/77, loss: 0.039381761103868484
2023-01-22 07:54:57.549879: step: 120/77, loss: 0.013376251794397831
2023-01-22 07:54:58.843513: step: 124/77, loss: 0.0016149815637618303
2023-01-22 07:55:00.121646: step: 128/77, loss: 0.00484588835388422
2023-01-22 07:55:01.397158: step: 132/77, loss: 0.03189440071582794
2023-01-22 07:55:02.696065: step: 136/77, loss: 0.00017303042113780975
2023-01-22 07:55:04.027266: step: 140/77, loss: 0.00938489194959402
2023-01-22 07:55:05.322841: step: 144/77, loss: 0.01806403324007988
2023-01-22 07:55:06.613945: step: 148/77, loss: 1.3843055057805032e-06
2023-01-22 07:55:07.917615: step: 152/77, loss: 0.0012917781714349985
2023-01-22 07:55:09.191520: step: 156/77, loss: 0.00010156808275496587
2023-01-22 07:55:10.515475: step: 160/77, loss: 5.2645496907643974e-05
2023-01-22 07:55:11.800431: step: 164/77, loss: 0.018050380051136017
2023-01-22 07:55:13.128830: step: 168/77, loss: 0.0017785239033401012
2023-01-22 07:55:14.418329: step: 172/77, loss: 0.004214688669890165
2023-01-22 07:55:15.675811: step: 176/77, loss: 0.004522663075476885
2023-01-22 07:55:16.998330: step: 180/77, loss: 0.004108669701963663
2023-01-22 07:55:18.264993: step: 184/77, loss: 0.005246539134532213
2023-01-22 07:55:19.548121: step: 188/77, loss: 0.03378375247120857
2023-01-22 07:55:20.832073: step: 192/77, loss: 0.01473064161837101
2023-01-22 07:55:22.104619: step: 196/77, loss: 0.12296944111585617
2023-01-22 07:55:23.392488: step: 200/77, loss: 0.038474295288324356
2023-01-22 07:55:24.704305: step: 204/77, loss: 0.027129890397191048
2023-01-22 07:55:26.039810: step: 208/77, loss: 2.7496336770127527e-05
2023-01-22 07:55:27.348897: step: 212/77, loss: 0.0018721886444836855
2023-01-22 07:55:28.642853: step: 216/77, loss: 7.349484076257795e-05
2023-01-22 07:55:29.957326: step: 220/77, loss: 0.028560999780893326
2023-01-22 07:55:31.236238: step: 224/77, loss: 0.00273231347091496
2023-01-22 07:55:32.524388: step: 228/77, loss: 0.017860732972621918
2023-01-22 07:55:33.797813: step: 232/77, loss: 0.0005846356507390738
2023-01-22 07:55:35.119935: step: 236/77, loss: 0.016033103689551353
2023-01-22 07:55:36.424200: step: 240/77, loss: 5.783687447546981e-05
2023-01-22 07:55:37.761284: step: 244/77, loss: 0.012645246461033821
2023-01-22 07:55:39.039933: step: 248/77, loss: 0.01751253381371498
2023-01-22 07:55:40.324765: step: 252/77, loss: 0.0007793352706357837
2023-01-22 07:55:41.679042: step: 256/77, loss: 0.034364163875579834
2023-01-22 07:55:42.924576: step: 260/77, loss: 0.010526706464588642
2023-01-22 07:55:44.218949: step: 264/77, loss: 0.008218883536756039
2023-01-22 07:55:45.470625: step: 268/77, loss: 0.023118719458580017
2023-01-22 07:55:46.770138: step: 272/77, loss: 0.0068781073205173016
2023-01-22 07:55:48.100277: step: 276/77, loss: 0.004687698557972908
2023-01-22 07:55:49.419855: step: 280/77, loss: 0.052164994180202484
2023-01-22 07:55:50.698974: step: 284/77, loss: 0.0036531335208564997
2023-01-22 07:55:52.025979: step: 288/77, loss: 0.019436553120613098
2023-01-22 07:55:53.287736: step: 292/77, loss: 0.00011274051939835772
2023-01-22 07:55:54.598845: step: 296/77, loss: 0.01647758297622204
2023-01-22 07:55:55.883150: step: 300/77, loss: 0.009985197335481644
2023-01-22 07:55:57.236016: step: 304/77, loss: 0.0005102159921079874
2023-01-22 07:55:58.559784: step: 308/77, loss: 0.007778570055961609
2023-01-22 07:55:59.839180: step: 312/77, loss: 6.139573088148609e-05
2023-01-22 07:56:01.134340: step: 316/77, loss: 7.233645737869665e-05
2023-01-22 07:56:02.445672: step: 320/77, loss: 0.0017407573759555817
2023-01-22 07:56:03.802437: step: 324/77, loss: 0.011609593406319618
2023-01-22 07:56:05.095926: step: 328/77, loss: 0.00018634925072547048
2023-01-22 07:56:06.382348: step: 332/77, loss: 0.003662088653072715
2023-01-22 07:56:07.698242: step: 336/77, loss: 0.00013480721099767834
2023-01-22 07:56:09.028255: step: 340/77, loss: 0.02257470041513443
2023-01-22 07:56:10.365192: step: 344/77, loss: 0.04621454328298569
2023-01-22 07:56:11.689106: step: 348/77, loss: 0.0009833829244598746
2023-01-22 07:56:12.994512: step: 352/77, loss: 0.0029590395279228687
2023-01-22 07:56:14.287210: step: 356/77, loss: 0.02674620971083641
2023-01-22 07:56:15.616000: step: 360/77, loss: 0.019447756931185722
2023-01-22 07:56:16.883207: step: 364/77, loss: 0.0001418082683812827
2023-01-22 07:56:18.202328: step: 368/77, loss: 0.014620725065469742
2023-01-22 07:56:19.480826: step: 372/77, loss: 0.026280973106622696
2023-01-22 07:56:20.763424: step: 376/77, loss: 0.00032260813168250024
2023-01-22 07:56:22.020991: step: 380/77, loss: 0.0002889384631998837
2023-01-22 07:56:23.319654: step: 384/77, loss: 0.009093235246837139
2023-01-22 07:56:24.600936: step: 388/77, loss: 0.0010739528806880116
==================================================
Loss: 0.013
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 12}
Test Chinese: {'template': {'p': 0.9863013698630136, 'r': 0.5853658536585366, 'f1': 0.7346938775510202}, 'slot': {'p': 0.4878048780487805, 'r': 0.01818181818181818, 'f1': 0.035056967572304996}, 'combined': 0.025756139440877134, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 12}
Test Korean: {'template': {'p': 0.9863013698630136, 'r': 0.5853658536585366, 'f1': 0.7346938775510202}, 'slot': {'p': 0.5, 'r': 0.019090909090909092, 'f1': 0.03677758318739055}, 'combined': 0.027020265198899173, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 12}
Test Russian: {'template': {'p': 0.9863013698630136, 'r': 0.5853658536585366, 'f1': 0.7346938775510202}, 'slot': {'p': 0.47619047619047616, 'r': 0.01818181818181818, 'f1': 0.0350262697022767}, 'combined': 0.02573358590371349, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 12}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 12}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 13
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 07:58:01.585767: step: 4/77, loss: 2.2610862288274802e-05
2023-01-22 07:58:02.859992: step: 8/77, loss: 0.005637861788272858
2023-01-22 07:58:04.155058: step: 12/77, loss: 0.003688807599246502
2023-01-22 07:58:05.448095: step: 16/77, loss: 0.02665168233215809
2023-01-22 07:58:06.726301: step: 20/77, loss: 0.016970016062259674
2023-01-22 07:58:08.048800: step: 24/77, loss: 1.4817988812865224e-05
2023-01-22 07:58:09.365424: step: 28/77, loss: 6.925305933691561e-05
2023-01-22 07:58:10.662509: step: 32/77, loss: 0.015504427254199982
2023-01-22 07:58:11.900188: step: 36/77, loss: 5.249499008641578e-05
2023-01-22 07:58:13.158570: step: 40/77, loss: 0.008829350583255291
2023-01-22 07:58:14.361642: step: 44/77, loss: 2.025206595135387e-05
2023-01-22 07:58:15.645557: step: 48/77, loss: 4.0971288399305195e-05
2023-01-22 07:58:16.991867: step: 52/77, loss: 0.021271025761961937
2023-01-22 07:58:18.303781: step: 56/77, loss: 0.0010673669166862965
2023-01-22 07:58:19.604202: step: 60/77, loss: 0.0002164973266189918
2023-01-22 07:58:20.872003: step: 64/77, loss: 0.06440609693527222
2023-01-22 07:58:22.171529: step: 68/77, loss: 0.03388819843530655
2023-01-22 07:58:23.445093: step: 72/77, loss: 0.014041759073734283
2023-01-22 07:58:24.746026: step: 76/77, loss: 0.023477237671613693
2023-01-22 07:58:26.017280: step: 80/77, loss: 0.0043355543166399
2023-01-22 07:58:27.257916: step: 84/77, loss: 0.007156530395150185
2023-01-22 07:58:28.518958: step: 88/77, loss: 0.00291500985622406
2023-01-22 07:58:29.819664: step: 92/77, loss: 0.007723457179963589
2023-01-22 07:58:31.067293: step: 96/77, loss: 0.00468220841139555
2023-01-22 07:58:32.336939: step: 100/77, loss: 5.247871013125405e-05
2023-01-22 07:58:33.624908: step: 104/77, loss: 4.394134066387778e-06
2023-01-22 07:58:34.931226: step: 108/77, loss: 6.272006430663168e-05
2023-01-22 07:58:36.205084: step: 112/77, loss: 0.00835472159087658
2023-01-22 07:58:37.442659: step: 116/77, loss: 0.05480552464723587
2023-01-22 07:58:38.756661: step: 120/77, loss: 0.022276371717453003
2023-01-22 07:58:40.121105: step: 124/77, loss: 0.002669721841812134
2023-01-22 07:58:41.420132: step: 128/77, loss: 0.09122525900602341
2023-01-22 07:58:42.749486: step: 132/77, loss: 0.010938310995697975
2023-01-22 07:58:44.052499: step: 136/77, loss: 4.7641540732001886e-05
2023-01-22 07:58:45.400755: step: 140/77, loss: 8.525445446139202e-05
2023-01-22 07:58:46.691465: step: 144/77, loss: 0.008205310441553593
2023-01-22 07:58:48.007922: step: 148/77, loss: 0.02473701536655426
2023-01-22 07:58:49.295176: step: 152/77, loss: 0.025928953662514687
2023-01-22 07:58:50.567428: step: 156/77, loss: 0.0324617400765419
2023-01-22 07:58:51.859262: step: 160/77, loss: 0.0030810926109552383
2023-01-22 07:58:53.211051: step: 164/77, loss: 0.022286182269454002
2023-01-22 07:58:54.514026: step: 168/77, loss: 0.021500881761312485
2023-01-22 07:58:55.837995: step: 172/77, loss: 0.009073024615645409
2023-01-22 07:58:57.105823: step: 176/77, loss: 0.0035487054847180843
2023-01-22 07:58:58.403962: step: 180/77, loss: 0.002166708232834935
2023-01-22 07:58:59.706028: step: 184/77, loss: 0.01816055364906788
2023-01-22 07:59:01.020754: step: 188/77, loss: 0.05229934677481651
2023-01-22 07:59:02.329783: step: 192/77, loss: 0.004905913025140762
2023-01-22 07:59:03.593649: step: 196/77, loss: 0.04279464855790138
2023-01-22 07:59:04.884848: step: 200/77, loss: 1.9669514017550682e-07
2023-01-22 07:59:06.194643: step: 204/77, loss: 0.025499440729618073
2023-01-22 07:59:07.486359: step: 208/77, loss: 0.009133759886026382
2023-01-22 07:59:08.830497: step: 212/77, loss: 0.011703042313456535
2023-01-22 07:59:10.139731: step: 216/77, loss: 0.0017015681369230151
2023-01-22 07:59:11.452853: step: 220/77, loss: 0.03688368201255798
2023-01-22 07:59:12.743385: step: 224/77, loss: 0.03645056113600731
2023-01-22 07:59:14.034375: step: 228/77, loss: 0.022262584418058395
2023-01-22 07:59:15.340423: step: 232/77, loss: 0.00811818242073059
2023-01-22 07:59:16.676925: step: 236/77, loss: 0.05509474128484726
2023-01-22 07:59:17.951559: step: 240/77, loss: 0.08739019930362701
2023-01-22 07:59:19.246078: step: 244/77, loss: 0.03550776094198227
2023-01-22 07:59:20.552648: step: 248/77, loss: 0.0076720230281353
2023-01-22 07:59:21.846539: step: 252/77, loss: 0.03817453980445862
2023-01-22 07:59:23.159261: step: 256/77, loss: 0.00017829393618740141
2023-01-22 07:59:24.477645: step: 260/77, loss: 1.9056222299695946e-05
2023-01-22 07:59:25.759703: step: 264/77, loss: 0.040975864976644516
2023-01-22 07:59:27.075459: step: 268/77, loss: 0.0011579713318496943
2023-01-22 07:59:28.335031: step: 272/77, loss: 0.025947313755750656
2023-01-22 07:59:29.592314: step: 276/77, loss: 0.0001307231286773458
2023-01-22 07:59:30.855108: step: 280/77, loss: 0.03271069750189781
2023-01-22 07:59:32.143582: step: 284/77, loss: 0.015176949091255665
2023-01-22 07:59:33.442208: step: 288/77, loss: 0.0007837112061679363
2023-01-22 07:59:34.771997: step: 292/77, loss: 0.05998732149600983
2023-01-22 07:59:36.099503: step: 296/77, loss: 0.022658394649624825
2023-01-22 07:59:37.347543: step: 300/77, loss: 0.007944842800498009
2023-01-22 07:59:38.647686: step: 304/77, loss: 0.03138115629553795
2023-01-22 07:59:39.958765: step: 308/77, loss: 0.003645453369244933
2023-01-22 07:59:41.239294: step: 312/77, loss: 0.0005130755598656833
2023-01-22 07:59:42.537654: step: 316/77, loss: 0.008485173806548119
2023-01-22 07:59:43.813394: step: 320/77, loss: 8.350548159796745e-05
2023-01-22 07:59:45.103970: step: 324/77, loss: 0.014045147225260735
2023-01-22 07:59:46.386387: step: 328/77, loss: 0.002589387120679021
2023-01-22 07:59:47.693181: step: 332/77, loss: 1.4230943634174764e-05
2023-01-22 07:59:49.037400: step: 336/77, loss: 0.00667186314240098
2023-01-22 07:59:50.330671: step: 340/77, loss: 0.01891062594950199
2023-01-22 07:59:51.661023: step: 344/77, loss: 0.04488614574074745
2023-01-22 07:59:52.962345: step: 348/77, loss: 0.019665377214550972
2023-01-22 07:59:54.308867: step: 352/77, loss: 0.007895408198237419
2023-01-22 07:59:55.656439: step: 356/77, loss: 0.001936072949320078
2023-01-22 07:59:56.974576: step: 360/77, loss: 0.036314986646175385
2023-01-22 07:59:58.240554: step: 364/77, loss: 0.002707503968849778
2023-01-22 07:59:59.518990: step: 368/77, loss: 0.006123952567577362
2023-01-22 08:00:00.833362: step: 372/77, loss: 0.05331498384475708
2023-01-22 08:00:02.159613: step: 376/77, loss: 0.009307156316936016
2023-01-22 08:00:03.429294: step: 380/77, loss: 0.00793666671961546
2023-01-22 08:00:04.715751: step: 384/77, loss: 0.07914161682128906
2023-01-22 08:00:06.050179: step: 388/77, loss: 0.04725559428334236
==================================================
Loss: 0.018
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 13}
Test Chinese: {'template': {'p': 0.95, 'r': 0.6178861788617886, 'f1': 0.748768472906404}, 'slot': {'p': 0.5, 'r': 0.025454545454545455, 'f1': 0.04844290657439446}, 'combined': 0.036272521178856945, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 13}
Test Korean: {'template': {'p': 0.95, 'r': 0.6178861788617886, 'f1': 0.748768472906404}, 'slot': {'p': 0.49122807017543857, 'r': 0.025454545454545455, 'f1': 0.0484010371650821}, 'combined': 0.036241170685184634, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 13}
Test Russian: {'template': {'p': 0.95, 'r': 0.6178861788617886, 'f1': 0.748768472906404}, 'slot': {'p': 0.5087719298245614, 'r': 0.026363636363636363, 'f1': 0.05012964563526361}, 'combined': 0.037535498209655516, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 13}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 13}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 14
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 08:01:42.972240: step: 4/77, loss: 0.004430257249623537
2023-01-22 08:01:44.279941: step: 8/77, loss: 0.0018078071298077703
2023-01-22 08:01:45.535686: step: 12/77, loss: 0.0023698084987699986
2023-01-22 08:01:46.815426: step: 16/77, loss: 0.015932057052850723
2023-01-22 08:01:48.136363: step: 20/77, loss: 0.00013169035082682967
2023-01-22 08:01:49.377977: step: 24/77, loss: 0.0037448059301823378
2023-01-22 08:01:50.693850: step: 28/77, loss: 0.03657084330916405
2023-01-22 08:01:51.943316: step: 32/77, loss: 0.04973209649324417
2023-01-22 08:01:53.246833: step: 36/77, loss: 0.026404602453112602
2023-01-22 08:01:54.551206: step: 40/77, loss: 0.00232500908896327
2023-01-22 08:01:55.839728: step: 44/77, loss: 0.01054262463003397
2023-01-22 08:01:57.086465: step: 48/77, loss: 0.008980286307632923
2023-01-22 08:01:58.362970: step: 52/77, loss: 0.01709909178316593
2023-01-22 08:01:59.638362: step: 56/77, loss: 0.0010604806011542678
2023-01-22 08:02:00.956351: step: 60/77, loss: 0.0008716561715118587
2023-01-22 08:02:02.199014: step: 64/77, loss: 0.0012432102812454104
2023-01-22 08:02:03.548317: step: 68/77, loss: 0.05664519965648651
2023-01-22 08:02:04.853240: step: 72/77, loss: 0.06241287291049957
2023-01-22 08:02:06.143074: step: 76/77, loss: 0.00022028060629963875
2023-01-22 08:02:07.434299: step: 80/77, loss: 0.08272923529148102
2023-01-22 08:02:08.764465: step: 84/77, loss: 0.010699925944209099
2023-01-22 08:02:10.027393: step: 88/77, loss: 0.05161707103252411
2023-01-22 08:02:11.339264: step: 92/77, loss: 0.005692289210855961
2023-01-22 08:02:12.687436: step: 96/77, loss: 0.0022551261354237795
2023-01-22 08:02:13.966806: step: 100/77, loss: 0.0010835323482751846
2023-01-22 08:02:15.253163: step: 104/77, loss: 0.00023391967988573015
2023-01-22 08:02:16.550594: step: 108/77, loss: 0.04434645548462868
2023-01-22 08:02:17.876519: step: 112/77, loss: 0.013929794542491436
2023-01-22 08:02:19.203028: step: 116/77, loss: 0.012213967740535736
2023-01-22 08:02:20.527728: step: 120/77, loss: 0.04906335845589638
2023-01-22 08:02:21.874073: step: 124/77, loss: 0.004624365828931332
2023-01-22 08:02:23.163971: step: 128/77, loss: 0.0008969166083261371
2023-01-22 08:02:24.502929: step: 132/77, loss: 0.041873492300510406
2023-01-22 08:02:25.794309: step: 136/77, loss: 0.0015139449387788773
2023-01-22 08:02:27.015425: step: 140/77, loss: 0.008322593756020069
2023-01-22 08:02:28.320653: step: 144/77, loss: 0.03902991861104965
2023-01-22 08:02:29.640699: step: 148/77, loss: 0.016263600438833237
2023-01-22 08:02:30.963410: step: 152/77, loss: 0.009588202461600304
2023-01-22 08:02:32.241751: step: 156/77, loss: 0.00011158635606989264
2023-01-22 08:02:33.519501: step: 160/77, loss: 0.020438387989997864
2023-01-22 08:02:34.811168: step: 164/77, loss: 0.04943925142288208
2023-01-22 08:02:36.108694: step: 168/77, loss: 0.008242144249379635
2023-01-22 08:02:37.408522: step: 172/77, loss: 0.008970575407147408
2023-01-22 08:02:38.675369: step: 176/77, loss: 3.817386459559202e-05
2023-01-22 08:02:39.982081: step: 180/77, loss: 0.04439555108547211
2023-01-22 08:02:41.313263: step: 184/77, loss: 0.007772160694003105
2023-01-22 08:02:42.602051: step: 188/77, loss: 0.0020781750790774822
2023-01-22 08:02:43.958042: step: 192/77, loss: 1.6847297956701368e-05
2023-01-22 08:02:45.241099: step: 196/77, loss: 0.021913882344961166
2023-01-22 08:02:46.593101: step: 200/77, loss: 0.0016695652157068253
2023-01-22 08:02:47.918608: step: 204/77, loss: 0.007512289099395275
2023-01-22 08:02:49.233334: step: 208/77, loss: 0.0001379475143039599
2023-01-22 08:02:50.520227: step: 212/77, loss: 0.012302246876060963
2023-01-22 08:02:51.789366: step: 216/77, loss: 0.0013374080881476402
2023-01-22 08:02:53.063756: step: 220/77, loss: 0.0029978842940181494
2023-01-22 08:02:54.323700: step: 224/77, loss: 0.012731088325381279
2023-01-22 08:02:55.630604: step: 228/77, loss: 0.0037896474823355675
2023-01-22 08:02:56.952012: step: 232/77, loss: 0.007226157002151012
2023-01-22 08:02:58.240854: step: 236/77, loss: 0.010333065874874592
2023-01-22 08:02:59.513714: step: 240/77, loss: 0.025543566793203354
2023-01-22 08:03:00.767298: step: 244/77, loss: 0.003890481311827898
2023-01-22 08:03:02.100713: step: 248/77, loss: 0.0061135608702898026
2023-01-22 08:03:03.353036: step: 252/77, loss: 0.0002315741148777306
2023-01-22 08:03:04.627725: step: 256/77, loss: 0.022473495453596115
2023-01-22 08:03:05.935296: step: 260/77, loss: 0.0070287445560097694
2023-01-22 08:03:07.217083: step: 264/77, loss: 0.0042348294518888
2023-01-22 08:03:08.497318: step: 268/77, loss: 0.008537882007658482
2023-01-22 08:03:09.818279: step: 272/77, loss: 0.00023712392430752516
2023-01-22 08:03:11.112401: step: 276/77, loss: 0.016111375764012337
2023-01-22 08:03:12.437267: step: 280/77, loss: 0.023547686636447906
2023-01-22 08:03:13.781196: step: 284/77, loss: 0.09503351151943207
2023-01-22 08:03:15.059125: step: 288/77, loss: 7.513206946896389e-05
2023-01-22 08:03:16.377317: step: 292/77, loss: 0.004765697754919529
2023-01-22 08:03:17.686004: step: 296/77, loss: 0.003875546855852008
2023-01-22 08:03:18.985044: step: 300/77, loss: 0.0038535785861313343
2023-01-22 08:03:20.284639: step: 304/77, loss: 0.003971458412706852
2023-01-22 08:03:21.627483: step: 308/77, loss: 0.020400844514369965
2023-01-22 08:03:22.919210: step: 312/77, loss: 0.00289251864887774
2023-01-22 08:03:24.281891: step: 316/77, loss: 0.0013335293624550104
2023-01-22 08:03:25.598557: step: 320/77, loss: 6.220525392564014e-06
2023-01-22 08:03:26.907332: step: 324/77, loss: 0.00018553411064203829
2023-01-22 08:03:28.255621: step: 328/77, loss: 0.02815510518848896
2023-01-22 08:03:29.533062: step: 332/77, loss: 1.5467263665414066e-06
2023-01-22 08:03:30.807954: step: 336/77, loss: 0.022374749183654785
2023-01-22 08:03:32.094729: step: 340/77, loss: 6.251667946344241e-05
2023-01-22 08:03:33.392494: step: 344/77, loss: 0.0003971634723711759
2023-01-22 08:03:34.701476: step: 348/77, loss: 0.048008985817432404
2023-01-22 08:03:36.033866: step: 352/77, loss: 0.06184585392475128
2023-01-22 08:03:37.335862: step: 356/77, loss: 0.000282044435152784
2023-01-22 08:03:38.651251: step: 360/77, loss: 0.000977915246039629
2023-01-22 08:03:39.914979: step: 364/77, loss: 0.055823519825935364
2023-01-22 08:03:41.256015: step: 368/77, loss: 0.0415327325463295
2023-01-22 08:03:42.570813: step: 372/77, loss: 0.08297859877347946
2023-01-22 08:03:43.893931: step: 376/77, loss: 0.016023965552449226
2023-01-22 08:03:45.146870: step: 380/77, loss: 0.01686960645020008
2023-01-22 08:03:46.485587: step: 384/77, loss: 0.0008093234500847757
2023-01-22 08:03:47.771408: step: 388/77, loss: 0.04213680326938629
==================================================
Loss: 0.016
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.55, 'f1': 0.7096774193548387}, 'slot': {'p': 0.5, 'r': 0.034026465028355386, 'f1': 0.06371681415929203}, 'combined': 0.04521838424207822, 'epoch': 14}
Test Chinese: {'template': {'p': 0.9240506329113924, 'r': 0.5934959349593496, 'f1': 0.7227722772277229}, 'slot': {'p': 0.43636363636363634, 'r': 0.02181818181818182, 'f1': 0.041558441558441565}, 'combined': 0.030037289443230045, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.55, 'f1': 0.7096774193548387}, 'slot': {'p': 0.5, 'r': 0.034026465028355386, 'f1': 0.06371681415929203}, 'combined': 0.04521838424207822, 'epoch': 14}
Test Korean: {'template': {'p': 0.925, 'r': 0.6016260162601627, 'f1': 0.7290640394088671}, 'slot': {'p': 0.43636363636363634, 'r': 0.02181818181818182, 'f1': 0.041558441558441565}, 'combined': 0.03029876527413474, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.55, 'f1': 0.7096774193548387}, 'slot': {'p': 0.5, 'r': 0.034026465028355386, 'f1': 0.06371681415929203}, 'combined': 0.04521838424207822, 'epoch': 14}
Test Russian: {'template': {'p': 0.925, 'r': 0.6016260162601627, 'f1': 0.7290640394088671}, 'slot': {'p': 0.43636363636363634, 'r': 0.02181818181818182, 'f1': 0.041558441558441565}, 'combined': 0.03029876527413474, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 14}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Sample Russian: {'template': {'p': 1.0, 'r': 0.25, 'f1': 0.4}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 15
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 08:05:24.268982: step: 4/77, loss: 0.0011530212359502912
2023-01-22 08:05:25.556670: step: 8/77, loss: 0.006455153692513704
2023-01-22 08:05:26.826725: step: 12/77, loss: 0.03983420133590698
2023-01-22 08:05:28.136676: step: 16/77, loss: 0.011238010600209236
2023-01-22 08:05:29.414213: step: 20/77, loss: 0.0026525515131652355
2023-01-22 08:05:30.720367: step: 24/77, loss: 0.012394571676850319
2023-01-22 08:05:32.040995: step: 28/77, loss: 0.01089528203010559
2023-01-22 08:05:33.330335: step: 32/77, loss: 0.002410109620541334
2023-01-22 08:05:34.629859: step: 36/77, loss: 0.07191843539476395
2023-01-22 08:05:35.915309: step: 40/77, loss: 0.04111922159790993
2023-01-22 08:05:37.148326: step: 44/77, loss: 0.006325423717498779
2023-01-22 08:05:38.423070: step: 48/77, loss: 0.0018762395484372973
2023-01-22 08:05:39.745867: step: 52/77, loss: 0.016316326335072517
2023-01-22 08:05:41.047681: step: 56/77, loss: 0.021863887086510658
2023-01-22 08:05:42.348857: step: 60/77, loss: 0.004629537463188171
2023-01-22 08:05:43.647501: step: 64/77, loss: 0.05812714248895645
2023-01-22 08:05:44.984995: step: 68/77, loss: 0.0006646717665717006
2023-01-22 08:05:46.271549: step: 72/77, loss: 0.025584321469068527
2023-01-22 08:05:47.542167: step: 76/77, loss: 0.005306669045239687
2023-01-22 08:05:48.812272: step: 80/77, loss: 0.00021504539472516626
2023-01-22 08:05:50.104286: step: 84/77, loss: 0.03863883763551712
2023-01-22 08:05:51.361343: step: 88/77, loss: 0.013125048018991947
2023-01-22 08:05:52.696161: step: 92/77, loss: 0.0073471637442708015
2023-01-22 08:05:54.004793: step: 96/77, loss: 0.0024326976854354143
2023-01-22 08:05:55.336160: step: 100/77, loss: 0.014627272263169289
2023-01-22 08:05:56.610462: step: 104/77, loss: 0.03934137895703316
2023-01-22 08:05:57.932595: step: 108/77, loss: 0.0004098295175936073
2023-01-22 08:05:59.211985: step: 112/77, loss: 0.0012081761378794909
2023-01-22 08:06:00.488734: step: 116/77, loss: 0.008219428360462189
2023-01-22 08:06:01.775687: step: 120/77, loss: 0.0010092520387843251
2023-01-22 08:06:03.013655: step: 124/77, loss: 0.02881784364581108
2023-01-22 08:06:04.272815: step: 128/77, loss: 0.00022574173635803163
2023-01-22 08:06:05.577152: step: 132/77, loss: 0.014033297076821327
2023-01-22 08:06:06.844179: step: 136/77, loss: 0.00023875743499957025
2023-01-22 08:06:08.135715: step: 140/77, loss: 0.012619758024811745
2023-01-22 08:06:09.430344: step: 144/77, loss: 0.007678681518882513
2023-01-22 08:06:10.679286: step: 148/77, loss: 0.0004265752504579723
2023-01-22 08:06:11.969926: step: 152/77, loss: 0.047454044222831726
2023-01-22 08:06:13.239688: step: 156/77, loss: 0.0020707775838673115
2023-01-22 08:06:14.539024: step: 160/77, loss: 3.5891003790311515e-05
2023-01-22 08:06:15.902399: step: 164/77, loss: 0.014533540233969688
2023-01-22 08:06:17.140735: step: 168/77, loss: 0.0010304294992238283
2023-01-22 08:06:18.408055: step: 172/77, loss: 0.0004204391734674573
2023-01-22 08:06:19.693650: step: 176/77, loss: 0.0028548361733555794
2023-01-22 08:06:20.988733: step: 180/77, loss: 0.0018736727070063353
2023-01-22 08:06:22.290274: step: 184/77, loss: 5.218083970248699e-06
2023-01-22 08:06:23.582507: step: 188/77, loss: 0.012196572497487068
2023-01-22 08:06:24.835362: step: 192/77, loss: 0.03711218386888504
2023-01-22 08:06:26.165599: step: 196/77, loss: 0.019275743514299393
2023-01-22 08:06:27.485206: step: 200/77, loss: 0.001391243189573288
2023-01-22 08:06:28.795371: step: 204/77, loss: 0.004645006265491247
2023-01-22 08:06:30.086169: step: 208/77, loss: 0.00014529861800838262
2023-01-22 08:06:31.375423: step: 212/77, loss: 0.0007189132156781852
2023-01-22 08:06:32.675442: step: 216/77, loss: 0.0036826361902058125
2023-01-22 08:06:34.008890: step: 220/77, loss: 0.016211818903684616
2023-01-22 08:06:35.330058: step: 224/77, loss: 0.008424910716712475
2023-01-22 08:06:36.602479: step: 228/77, loss: 0.005087016150355339
2023-01-22 08:06:37.904397: step: 232/77, loss: 0.0021495078690350056
2023-01-22 08:06:39.173753: step: 236/77, loss: 0.016692375764250755
2023-01-22 08:06:40.465024: step: 240/77, loss: 0.0010836259461939335
2023-01-22 08:06:41.764153: step: 244/77, loss: 8.891993638826534e-05
2023-01-22 08:06:43.044031: step: 248/77, loss: 0.0019844304770231247
2023-01-22 08:06:44.350112: step: 252/77, loss: 0.008615804836153984
2023-01-22 08:06:45.631312: step: 256/77, loss: 0.00010830286919372156
2023-01-22 08:06:46.902399: step: 260/77, loss: 0.009233257733285427
2023-01-22 08:06:48.258407: step: 264/77, loss: 0.01212453655898571
2023-01-22 08:06:49.547943: step: 268/77, loss: 0.0026560192927718163
2023-01-22 08:06:50.823298: step: 272/77, loss: 0.006347885821014643
2023-01-22 08:06:52.104766: step: 276/77, loss: 0.0009034523391164839
2023-01-22 08:06:53.437624: step: 280/77, loss: 0.003021764103323221
2023-01-22 08:06:54.766311: step: 284/77, loss: 0.006079188548028469
2023-01-22 08:06:56.059027: step: 288/77, loss: 0.038373105227947235
2023-01-22 08:06:57.345718: step: 292/77, loss: 0.0031433424446731806
2023-01-22 08:06:58.651099: step: 296/77, loss: 0.02784053236246109
2023-01-22 08:06:59.956246: step: 300/77, loss: 0.0005230466485954821
2023-01-22 08:07:01.276511: step: 304/77, loss: 0.00455853994935751
2023-01-22 08:07:02.544727: step: 308/77, loss: 0.0012094294652342796
2023-01-22 08:07:03.889297: step: 312/77, loss: 0.0003353256033733487
2023-01-22 08:07:05.180887: step: 316/77, loss: 0.00011404056567698717
2023-01-22 08:07:06.485019: step: 320/77, loss: 0.1456245481967926
2023-01-22 08:07:07.785984: step: 324/77, loss: 0.0008838959038257599
2023-01-22 08:07:09.081483: step: 328/77, loss: 0.04460209980607033
2023-01-22 08:07:10.371605: step: 332/77, loss: 0.0077811977826058865
2023-01-22 08:07:11.656877: step: 336/77, loss: 0.000999920885078609
2023-01-22 08:07:12.940255: step: 340/77, loss: 0.0008804184617474675
2023-01-22 08:07:14.225682: step: 344/77, loss: 0.03426405042409897
2023-01-22 08:07:15.538700: step: 348/77, loss: 0.00249478523619473
2023-01-22 08:07:16.871401: step: 352/77, loss: 0.028345339000225067
2023-01-22 08:07:18.160216: step: 356/77, loss: 1.6141852029250003e-05
2023-01-22 08:07:19.473891: step: 360/77, loss: 0.004599923733621836
2023-01-22 08:07:20.720451: step: 364/77, loss: 0.0015322489198297262
2023-01-22 08:07:22.045852: step: 368/77, loss: 0.029466429725289345
2023-01-22 08:07:23.405906: step: 372/77, loss: 0.0002610405208542943
2023-01-22 08:07:24.703690: step: 376/77, loss: 0.00028324045706540346
2023-01-22 08:07:25.969261: step: 380/77, loss: 0.00011046537838410586
2023-01-22 08:07:27.285210: step: 384/77, loss: 0.01054134126752615
2023-01-22 08:07:28.615346: step: 388/77, loss: 0.0020199620630592108
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 15}
Test Chinese: {'template': {'p': 0.8974358974358975, 'r': 0.5691056910569106, 'f1': 0.6965174129353233}, 'slot': {'p': 0.4583333333333333, 'r': 0.02, 'f1': 0.03832752613240418}, 'combined': 0.026695789345953156, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 15}
Test Korean: {'template': {'p': 0.8974358974358975, 'r': 0.5691056910569106, 'f1': 0.6965174129353233}, 'slot': {'p': 0.45652173913043476, 'r': 0.019090909090909092, 'f1': 0.03664921465968587}, 'combined': 0.025526816180875725, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 15}
Test Russian: {'template': {'p': 0.8961038961038961, 'r': 0.5609756097560976, 'f1': 0.69}, 'slot': {'p': 0.46808510638297873, 'r': 0.02, 'f1': 0.03836094158674804}, 'combined': 0.026469049694856146, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 15}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 15}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 16
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 08:09:05.525025: step: 4/77, loss: 0.006552703212946653
2023-01-22 08:09:06.849060: step: 8/77, loss: 0.0009742131805978715
2023-01-22 08:09:08.148064: step: 12/77, loss: 0.0017733649583533406
2023-01-22 08:09:09.488100: step: 16/77, loss: 0.03460262715816498
2023-01-22 08:09:10.809333: step: 20/77, loss: 0.013664139434695244
2023-01-22 08:09:12.124795: step: 24/77, loss: 6.580878107342869e-05
2023-01-22 08:09:13.403592: step: 28/77, loss: 0.011652027256786823
2023-01-22 08:09:14.671286: step: 32/77, loss: 0.02981100231409073
2023-01-22 08:09:15.954305: step: 36/77, loss: 0.018231457099318504
2023-01-22 08:09:17.228395: step: 40/77, loss: 0.009962860494852066
2023-01-22 08:09:18.451424: step: 44/77, loss: 0.01126846019178629
2023-01-22 08:09:19.696281: step: 48/77, loss: 1.236806383531075e-05
2023-01-22 08:09:20.975592: step: 52/77, loss: 0.0025686314329504967
2023-01-22 08:09:22.244689: step: 56/77, loss: 0.022444654256105423
2023-01-22 08:09:23.528000: step: 60/77, loss: 8.586797775933519e-06
2023-01-22 08:09:24.801821: step: 64/77, loss: 6.882055458845571e-06
2023-01-22 08:09:26.112974: step: 68/77, loss: 0.004656787030398846
2023-01-22 08:09:27.369997: step: 72/77, loss: 0.005976193118840456
2023-01-22 08:09:28.628631: step: 76/77, loss: 0.003050893312320113
2023-01-22 08:09:29.925445: step: 80/77, loss: 0.11868611723184586
2023-01-22 08:09:31.210895: step: 84/77, loss: 0.022080106660723686
2023-01-22 08:09:32.450157: step: 88/77, loss: 0.005611381493508816
2023-01-22 08:09:33.748779: step: 92/77, loss: 0.0006953682750463486
2023-01-22 08:09:35.086916: step: 96/77, loss: 0.003470786614343524
2023-01-22 08:09:36.414785: step: 100/77, loss: 0.00038696586852893233
2023-01-22 08:09:37.629595: step: 104/77, loss: 0.04702460765838623
2023-01-22 08:09:38.891722: step: 108/77, loss: 0.00037538877222687006
2023-01-22 08:09:40.223809: step: 112/77, loss: 0.0009814082877710462
2023-01-22 08:09:41.503953: step: 116/77, loss: 0.00010789869702421129
2023-01-22 08:09:42.826469: step: 120/77, loss: 0.02089921198785305
2023-01-22 08:09:44.151306: step: 124/77, loss: 0.014739819802343845
2023-01-22 08:09:45.420125: step: 128/77, loss: 0.001180226681753993
2023-01-22 08:09:46.731797: step: 132/77, loss: 0.04211696237325668
2023-01-22 08:09:48.006478: step: 136/77, loss: 3.5734439734369516e-05
2023-01-22 08:09:49.324340: step: 140/77, loss: 0.04853532090783119
2023-01-22 08:09:50.579704: step: 144/77, loss: 0.004052129108458757
2023-01-22 08:09:51.870954: step: 148/77, loss: 0.0004372121475171298
2023-01-22 08:09:53.152300: step: 152/77, loss: 0.04190046712756157
2023-01-22 08:09:54.455200: step: 156/77, loss: 0.0018922454910352826
2023-01-22 08:09:55.745641: step: 160/77, loss: 0.009773260913789272
2023-01-22 08:09:57.045035: step: 164/77, loss: 0.001528030028566718
2023-01-22 08:09:58.348950: step: 168/77, loss: 0.02765164151787758
2023-01-22 08:09:59.692183: step: 172/77, loss: 0.0005780403153039515
2023-01-22 08:10:01.017222: step: 176/77, loss: 0.0038615819066762924
2023-01-22 08:10:02.286569: step: 180/77, loss: 0.014504548162221909
2023-01-22 08:10:03.611962: step: 184/77, loss: 0.007875760085880756
2023-01-22 08:10:04.907776: step: 188/77, loss: 0.0010432120179757476
2023-01-22 08:10:06.173363: step: 192/77, loss: 1.9311471533001168e-06
2023-01-22 08:10:07.490255: step: 196/77, loss: 0.008792483247816563
2023-01-22 08:10:08.778913: step: 200/77, loss: 0.033647846430540085
2023-01-22 08:10:10.097313: step: 204/77, loss: 8.60294239828363e-05
2023-01-22 08:10:11.419116: step: 208/77, loss: 0.0026480434462428093
2023-01-22 08:10:12.704259: step: 212/77, loss: 0.0073967669159173965
2023-01-22 08:10:14.002429: step: 216/77, loss: 0.027375243604183197
2023-01-22 08:10:15.265171: step: 220/77, loss: 0.0054856291972100735
2023-01-22 08:10:16.519894: step: 224/77, loss: 0.024888327345252037
2023-01-22 08:10:17.795445: step: 228/77, loss: 0.0061912983655929565
2023-01-22 08:10:19.136608: step: 232/77, loss: 0.004951823502779007
2023-01-22 08:10:20.480869: step: 236/77, loss: 0.002676447154954076
2023-01-22 08:10:21.814223: step: 240/77, loss: 4.45177975052502e-05
2023-01-22 08:10:23.065784: step: 244/77, loss: 0.010543622076511383
2023-01-22 08:10:24.365904: step: 248/77, loss: 0.02687632292509079
2023-01-22 08:10:25.644517: step: 252/77, loss: 0.0023010619916021824
2023-01-22 08:10:26.935346: step: 256/77, loss: 0.07297077775001526
2023-01-22 08:10:28.253172: step: 260/77, loss: 0.0007688794867135584
2023-01-22 08:10:29.543868: step: 264/77, loss: 7.96151434769854e-05
2023-01-22 08:10:30.884642: step: 268/77, loss: 0.00010676166857592762
2023-01-22 08:10:32.191735: step: 272/77, loss: 0.011700259521603584
2023-01-22 08:10:33.508567: step: 276/77, loss: 0.010706624016165733
2023-01-22 08:10:34.822260: step: 280/77, loss: 0.00010317780106561258
2023-01-22 08:10:36.099118: step: 284/77, loss: 0.027786539867520332
2023-01-22 08:10:37.413325: step: 288/77, loss: 0.001600670162588358
2023-01-22 08:10:38.719368: step: 292/77, loss: 0.0003801693383138627
2023-01-22 08:10:39.995912: step: 296/77, loss: 0.0010835555149242282
2023-01-22 08:10:41.292658: step: 300/77, loss: 0.0013048271648585796
2023-01-22 08:10:42.537332: step: 304/77, loss: 0.00392378494143486
2023-01-22 08:10:43.801686: step: 308/77, loss: 2.722800854826346e-05
2023-01-22 08:10:45.078109: step: 312/77, loss: 0.01019936054944992
2023-01-22 08:10:46.382346: step: 316/77, loss: 0.04807935282588005
2023-01-22 08:10:47.656633: step: 320/77, loss: 3.8343645428540185e-05
2023-01-22 08:10:48.970186: step: 324/77, loss: 0.00013135296467225999
2023-01-22 08:10:50.286106: step: 328/77, loss: 0.012444362044334412
2023-01-22 08:10:51.563327: step: 332/77, loss: 0.0005562487640418112
2023-01-22 08:10:52.830183: step: 336/77, loss: 0.0027817520312964916
2023-01-22 08:10:54.173231: step: 340/77, loss: 0.04739411547780037
2023-01-22 08:10:55.456317: step: 344/77, loss: 0.015705594792962074
2023-01-22 08:10:56.745570: step: 348/77, loss: 0.014253773726522923
2023-01-22 08:10:58.054575: step: 352/77, loss: 0.0039000764954835176
2023-01-22 08:10:59.368566: step: 356/77, loss: 0.04627962410449982
2023-01-22 08:11:00.628510: step: 360/77, loss: 0.033766452223062515
2023-01-22 08:11:01.871261: step: 364/77, loss: 0.0040741246193647385
2023-01-22 08:11:03.215849: step: 368/77, loss: 0.002382186008617282
2023-01-22 08:11:04.467194: step: 372/77, loss: 0.0462690070271492
2023-01-22 08:11:05.729243: step: 376/77, loss: 0.000892925076186657
2023-01-22 08:11:07.019846: step: 380/77, loss: 0.01855640299618244
2023-01-22 08:11:08.301258: step: 384/77, loss: 0.0007892133435234427
2023-01-22 08:11:09.602964: step: 388/77, loss: 0.05648082494735718
==================================================
Loss: 0.013
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 16}
Test Chinese: {'template': {'p': 0.961038961038961, 'r': 0.6016260162601627, 'f1': 0.74}, 'slot': {'p': 0.4722222222222222, 'r': 0.015454545454545455, 'f1': 0.029929577464788734}, 'combined': 0.02214788732394366, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 16}
Test Korean: {'template': {'p': 0.9615384615384616, 'r': 0.6097560975609756, 'f1': 0.7462686567164178}, 'slot': {'p': 0.4722222222222222, 'r': 0.015454545454545455, 'f1': 0.029929577464788734}, 'combined': 0.02233550557073786, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 16}
Test Russian: {'template': {'p': 0.961038961038961, 'r': 0.6016260162601627, 'f1': 0.74}, 'slot': {'p': 0.4594594594594595, 'r': 0.015454545454545455, 'f1': 0.029903254177660512}, 'combined': 0.02212840809146878, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 16}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Sample Russian: {'template': {'p': 1.0, 'r': 0.25, 'f1': 0.4}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 17
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 08:12:46.254830: step: 4/77, loss: 0.0003037060087081045
2023-01-22 08:12:47.561304: step: 8/77, loss: 0.00038242657319642603
2023-01-22 08:12:48.894444: step: 12/77, loss: 0.0013528617564588785
2023-01-22 08:12:50.203786: step: 16/77, loss: 0.00010484598897164688
2023-01-22 08:12:51.479891: step: 20/77, loss: 0.004785007331520319
2023-01-22 08:12:52.808345: step: 24/77, loss: 0.00010676060628611594
2023-01-22 08:12:54.047753: step: 28/77, loss: 0.00020604948804248124
2023-01-22 08:12:55.354573: step: 32/77, loss: 0.0016604478005319834
2023-01-22 08:12:56.635888: step: 36/77, loss: 0.0016582023818045855
2023-01-22 08:12:57.938866: step: 40/77, loss: 0.0004796137218363583
2023-01-22 08:12:59.206680: step: 44/77, loss: 0.008982490748167038
2023-01-22 08:13:00.421731: step: 48/77, loss: 0.005666470155119896
2023-01-22 08:13:01.705815: step: 52/77, loss: 0.013005124405026436
2023-01-22 08:13:03.015171: step: 56/77, loss: 0.00043898681178689003
2023-01-22 08:13:04.279135: step: 60/77, loss: 0.010772701352834702
2023-01-22 08:13:05.544737: step: 64/77, loss: 0.014273944310843945
2023-01-22 08:13:06.794042: step: 68/77, loss: 0.009036684408783913
2023-01-22 08:13:08.099376: step: 72/77, loss: 0.0006658356287516654
2023-01-22 08:13:09.402041: step: 76/77, loss: 1.80274473677855e-05
2023-01-22 08:13:10.656535: step: 80/77, loss: 0.00024116590793710202
2023-01-22 08:13:11.948532: step: 84/77, loss: 0.014361845329403877
2023-01-22 08:13:13.232437: step: 88/77, loss: 0.02260422147810459
2023-01-22 08:13:14.497725: step: 92/77, loss: 0.0029067930299788713
2023-01-22 08:13:15.782850: step: 96/77, loss: 0.0024856228847056627
2023-01-22 08:13:17.094527: step: 100/77, loss: 1.2357354535197373e-05
2023-01-22 08:13:18.408485: step: 104/77, loss: 0.0018393194768577814
2023-01-22 08:13:19.710568: step: 108/77, loss: 4.3470787204569206e-05
2023-01-22 08:13:20.989463: step: 112/77, loss: 0.012341336347162724
2023-01-22 08:13:22.288581: step: 116/77, loss: 0.004242464900016785
2023-01-22 08:13:23.599688: step: 120/77, loss: 0.0019005483482033014
2023-01-22 08:13:24.885713: step: 124/77, loss: 8.54067548061721e-06
2023-01-22 08:13:26.155206: step: 128/77, loss: 0.00011833629105240107
2023-01-22 08:13:27.485459: step: 132/77, loss: 0.04586326330900192
2023-01-22 08:13:28.710961: step: 136/77, loss: 0.012901647947728634
2023-01-22 08:13:29.981866: step: 140/77, loss: 0.0001440030027879402
2023-01-22 08:13:31.266249: step: 144/77, loss: 0.00040081614861264825
2023-01-22 08:13:32.614947: step: 148/77, loss: 0.02381657063961029
2023-01-22 08:13:33.916858: step: 152/77, loss: 0.0023007721174508333
2023-01-22 08:13:35.236398: step: 156/77, loss: 0.0388503298163414
2023-01-22 08:13:36.539534: step: 160/77, loss: 0.0034463191404938698
2023-01-22 08:13:37.876971: step: 164/77, loss: 0.0004672359791584313
2023-01-22 08:13:39.189878: step: 168/77, loss: 0.0018541706958785653
2023-01-22 08:13:40.483062: step: 172/77, loss: 0.0327320471405983
2023-01-22 08:13:41.757737: step: 176/77, loss: 0.0024690069258213043
2023-01-22 08:13:43.065240: step: 180/77, loss: 0.0010510309366509318
2023-01-22 08:13:44.346902: step: 184/77, loss: 0.0008923964924179018
2023-01-22 08:13:45.641235: step: 188/77, loss: 0.00029543269192799926
2023-01-22 08:13:46.933616: step: 192/77, loss: 0.0028764773160219193
2023-01-22 08:13:48.235869: step: 196/77, loss: 1.1312491551507264e-05
2023-01-22 08:13:49.587440: step: 200/77, loss: 0.009550292044878006
2023-01-22 08:13:50.901351: step: 204/77, loss: 0.0052166227251291275
2023-01-22 08:13:52.205648: step: 208/77, loss: 0.0008433779585175216
2023-01-22 08:13:53.497519: step: 212/77, loss: 2.461548319843132e-06
2023-01-22 08:13:54.813561: step: 216/77, loss: 0.0022772536613047123
2023-01-22 08:13:56.100547: step: 220/77, loss: 0.0036285670939832926
2023-01-22 08:13:57.357040: step: 224/77, loss: 0.032222650945186615
2023-01-22 08:13:58.603930: step: 228/77, loss: 6.528257654281333e-05
2023-01-22 08:13:59.923318: step: 232/77, loss: 0.010111379437148571
2023-01-22 08:14:01.222666: step: 236/77, loss: 0.003799677127972245
2023-01-22 08:14:02.535589: step: 240/77, loss: 0.026927510276436806
2023-01-22 08:14:03.907478: step: 244/77, loss: 0.009405246004462242
2023-01-22 08:14:05.243106: step: 248/77, loss: 0.032634347677230835
2023-01-22 08:14:06.548058: step: 252/77, loss: 0.0018777992809191346
2023-01-22 08:14:07.839408: step: 256/77, loss: 0.06961376965045929
2023-01-22 08:14:09.137864: step: 260/77, loss: 0.015779821202158928
2023-01-22 08:14:10.456265: step: 264/77, loss: 0.0018593231216073036
2023-01-22 08:14:11.748533: step: 268/77, loss: 3.989012475358322e-05
2023-01-22 08:14:13.063700: step: 272/77, loss: 2.904075699916575e-05
2023-01-22 08:14:14.367495: step: 276/77, loss: 1.4655574887001421e-05
2023-01-22 08:14:15.658314: step: 280/77, loss: 0.006797629874199629
2023-01-22 08:14:16.952896: step: 284/77, loss: 0.0001961684611160308
2023-01-22 08:14:18.250767: step: 288/77, loss: 0.04722617566585541
2023-01-22 08:14:19.612511: step: 292/77, loss: 0.0010816743597388268
2023-01-22 08:14:20.928998: step: 296/77, loss: 1.5971452739904635e-05
2023-01-22 08:14:22.203534: step: 300/77, loss: 0.03634996712207794
2023-01-22 08:14:23.504458: step: 304/77, loss: 0.004210877697914839
2023-01-22 08:14:24.890950: step: 308/77, loss: 0.0038256642874330282
2023-01-22 08:14:26.147946: step: 312/77, loss: 0.0038271218072623014
2023-01-22 08:14:27.456330: step: 316/77, loss: 0.052637092769145966
2023-01-22 08:14:28.817692: step: 320/77, loss: 0.0030049553606659174
2023-01-22 08:14:30.176313: step: 324/77, loss: 0.0036819763481616974
2023-01-22 08:14:31.432434: step: 328/77, loss: 0.007940493524074554
2023-01-22 08:14:32.767216: step: 332/77, loss: 0.014108079485595226
2023-01-22 08:14:34.132685: step: 336/77, loss: 0.00021898458362556994
2023-01-22 08:14:35.448158: step: 340/77, loss: 7.66866924095666e-06
2023-01-22 08:14:36.679105: step: 344/77, loss: 0.035794321447610855
2023-01-22 08:14:38.018035: step: 348/77, loss: 0.0010580236557871103
2023-01-22 08:14:39.316191: step: 352/77, loss: 0.0006705737905576825
2023-01-22 08:14:40.601293: step: 356/77, loss: 8.463625272270292e-05
2023-01-22 08:14:41.868066: step: 360/77, loss: 0.03241058066487312
2023-01-22 08:14:43.139502: step: 364/77, loss: 0.0008318339241668582
2023-01-22 08:14:44.365591: step: 368/77, loss: 0.008623465895652771
2023-01-22 08:14:45.689455: step: 372/77, loss: 0.0006912436801940203
2023-01-22 08:14:47.008442: step: 376/77, loss: 0.007522268686443567
2023-01-22 08:14:48.336906: step: 380/77, loss: 0.010126580484211445
2023-01-22 08:14:49.653076: step: 384/77, loss: 0.00013385726197157055
2023-01-22 08:14:50.956467: step: 388/77, loss: 0.0001453287695767358
==================================================
Loss: 0.008
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 17}
Test Chinese: {'template': {'p': 0.9512195121951219, 'r': 0.6341463414634146, 'f1': 0.7609756097560976}, 'slot': {'p': 0.5555555555555556, 'r': 0.022727272727272728, 'f1': 0.04366812227074236}, 'combined': 0.03323037597188199, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 17}
Test Korean: {'template': {'p': 0.9512195121951219, 'r': 0.6341463414634146, 'f1': 0.7609756097560976}, 'slot': {'p': 0.5555555555555556, 'r': 0.022727272727272728, 'f1': 0.04366812227074236}, 'combined': 0.03323037597188199, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 17}
Test Russian: {'template': {'p': 0.9506172839506173, 'r': 0.6260162601626016, 'f1': 0.7549019607843136}, 'slot': {'p': 0.5681818181818182, 'r': 0.022727272727272728, 'f1': 0.04370629370629371}, 'combined': 0.03299396681749623, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 17}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 17}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 18
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 08:16:29.934324: step: 4/77, loss: 0.001075280481018126
2023-01-22 08:16:31.202593: step: 8/77, loss: 0.0016390618402510881
2023-01-22 08:16:32.486331: step: 12/77, loss: 2.4888377083698288e-05
2023-01-22 08:16:33.800438: step: 16/77, loss: 0.00032724355696700513
2023-01-22 08:16:35.063751: step: 20/77, loss: 3.541986006894149e-05
2023-01-22 08:16:36.373238: step: 24/77, loss: 0.012699036858975887
2023-01-22 08:16:37.673548: step: 28/77, loss: 3.851627843687311e-05
2023-01-22 08:16:38.970975: step: 32/77, loss: 0.0511711984872818
2023-01-22 08:16:40.301741: step: 36/77, loss: 0.001221914542838931
2023-01-22 08:16:41.604099: step: 40/77, loss: 0.019967470318078995
2023-01-22 08:16:42.870021: step: 44/77, loss: 0.00016486311506014317
2023-01-22 08:16:44.157197: step: 48/77, loss: 6.0238003243284766e-06
2023-01-22 08:16:45.436291: step: 52/77, loss: 0.003115791827440262
2023-01-22 08:16:46.737602: step: 56/77, loss: 0.0009298291988670826
2023-01-22 08:16:48.049410: step: 60/77, loss: 2.789767131616827e-05
2023-01-22 08:16:49.315693: step: 64/77, loss: 0.025554176419973373
2023-01-22 08:16:50.615647: step: 68/77, loss: 0.056334611028432846
2023-01-22 08:16:51.915882: step: 72/77, loss: 0.0028062222991138697
2023-01-22 08:16:53.279048: step: 76/77, loss: 0.10629882663488388
2023-01-22 08:16:54.605427: step: 80/77, loss: 0.05901770293712616
2023-01-22 08:16:55.887809: step: 84/77, loss: 1.7697377188596874e-05
2023-01-22 08:16:57.204361: step: 88/77, loss: 0.010094331577420235
2023-01-22 08:16:58.479810: step: 92/77, loss: 0.0006838410045020282
2023-01-22 08:16:59.792574: step: 96/77, loss: 3.121390182059258e-05
2023-01-22 08:17:01.085433: step: 100/77, loss: 0.00021746208949480206
2023-01-22 08:17:02.396277: step: 104/77, loss: 0.00015648044063709676
2023-01-22 08:17:03.681688: step: 108/77, loss: 0.007220795378088951
2023-01-22 08:17:04.977694: step: 112/77, loss: 0.006847000680863857
2023-01-22 08:17:06.281525: step: 116/77, loss: 1.8800854377332143e-05
2023-01-22 08:17:07.588201: step: 120/77, loss: 0.000735764333512634
2023-01-22 08:17:08.855165: step: 124/77, loss: 0.0020050792954862118
2023-01-22 08:17:10.194103: step: 128/77, loss: 6.402538929251023e-06
2023-01-22 08:17:11.497056: step: 132/77, loss: 0.01608336716890335
2023-01-22 08:17:12.804849: step: 136/77, loss: 6.378698162734509e-05
2023-01-22 08:17:14.148975: step: 140/77, loss: 0.0006921316962689161
2023-01-22 08:17:15.412571: step: 144/77, loss: 3.956109139835462e-06
2023-01-22 08:17:16.737440: step: 148/77, loss: 0.008236408233642578
2023-01-22 08:17:18.047451: step: 152/77, loss: 0.003246211213991046
2023-01-22 08:17:19.384623: step: 156/77, loss: 0.04419539496302605
2023-01-22 08:17:20.700750: step: 160/77, loss: 0.0031513397116214037
2023-01-22 08:17:21.996526: step: 164/77, loss: 0.0011053562629967928
2023-01-22 08:17:23.335261: step: 168/77, loss: 0.0018971740501001477
2023-01-22 08:17:24.665708: step: 172/77, loss: 1.8000569980358705e-05
2023-01-22 08:17:25.972046: step: 176/77, loss: 0.0016024464275687933
2023-01-22 08:17:27.233125: step: 180/77, loss: 0.00030853645876049995
2023-01-22 08:17:28.585163: step: 184/77, loss: 0.010142313316464424
2023-01-22 08:17:29.854715: step: 188/77, loss: 0.01915617100894451
2023-01-22 08:17:31.122374: step: 192/77, loss: 0.004522524308413267
2023-01-22 08:17:32.402985: step: 196/77, loss: 0.006432425230741501
2023-01-22 08:17:33.656153: step: 200/77, loss: 0.01698668859899044
2023-01-22 08:17:34.974409: step: 204/77, loss: 0.0007753705722279847
2023-01-22 08:17:36.303615: step: 208/77, loss: 0.003447559429332614
2023-01-22 08:17:37.620448: step: 212/77, loss: 0.07996546477079391
2023-01-22 08:17:38.880472: step: 216/77, loss: 0.0007899499032646418
2023-01-22 08:17:40.179031: step: 220/77, loss: 0.00014828376879449934
2023-01-22 08:17:41.519320: step: 224/77, loss: 0.0031378234270960093
2023-01-22 08:17:42.835174: step: 228/77, loss: 0.0024087419733405113
2023-01-22 08:17:44.160004: step: 232/77, loss: 0.022225063294172287
2023-01-22 08:17:45.472923: step: 236/77, loss: 0.013735632412135601
2023-01-22 08:17:46.759111: step: 240/77, loss: 0.024480065330863
2023-01-22 08:17:48.007596: step: 244/77, loss: 0.0015148434322327375
2023-01-22 08:17:49.299073: step: 248/77, loss: 0.047594137489795685
2023-01-22 08:17:50.624274: step: 252/77, loss: 1.2218940526054212e-07
2023-01-22 08:17:52.009868: step: 256/77, loss: 0.00227353535592556
2023-01-22 08:17:53.305523: step: 260/77, loss: 0.013032825663685799
2023-01-22 08:17:54.592545: step: 264/77, loss: 0.0023532661143690348
2023-01-22 08:17:55.898757: step: 268/77, loss: 1.5874851669650525e-05
2023-01-22 08:17:57.207684: step: 272/77, loss: 3.869067586492747e-05
2023-01-22 08:17:58.523801: step: 276/77, loss: 0.007464665919542313
2023-01-22 08:17:59.820959: step: 280/77, loss: 7.692573490203358e-06
2023-01-22 08:18:01.113608: step: 284/77, loss: 0.0008798784692771733
2023-01-22 08:18:02.399833: step: 288/77, loss: 0.0005066373851150274
2023-01-22 08:18:03.670086: step: 292/77, loss: 0.0033748496789485216
2023-01-22 08:18:04.962256: step: 296/77, loss: 0.03423455357551575
2023-01-22 08:18:06.259567: step: 300/77, loss: 0.0004929510178044438
2023-01-22 08:18:07.605620: step: 304/77, loss: 0.30837780237197876
2023-01-22 08:18:08.935388: step: 308/77, loss: 7.889981498010457e-05
2023-01-22 08:18:10.262130: step: 312/77, loss: 0.05586982145905495
2023-01-22 08:18:11.589991: step: 316/77, loss: 0.007840905338525772
2023-01-22 08:18:12.878717: step: 320/77, loss: 0.0010584781412035227
2023-01-22 08:18:14.170146: step: 324/77, loss: 0.0004989710869267583
2023-01-22 08:18:15.467296: step: 328/77, loss: 0.00011972568609053269
2023-01-22 08:18:16.755428: step: 332/77, loss: 0.0002813867758959532
2023-01-22 08:18:18.074463: step: 336/77, loss: 0.008618929423391819
2023-01-22 08:18:19.443242: step: 340/77, loss: 1.6787849745014682e-05
2023-01-22 08:18:20.741598: step: 344/77, loss: 0.0036653918214142323
2023-01-22 08:18:22.094514: step: 348/77, loss: 0.0006011840887367725
2023-01-22 08:18:23.420978: step: 352/77, loss: 7.024506885500159e-06
2023-01-22 08:18:24.731323: step: 356/77, loss: 9.986665827454999e-05
2023-01-22 08:18:26.032302: step: 360/77, loss: 4.4611333578359336e-06
2023-01-22 08:18:27.370752: step: 364/77, loss: 0.001176069607026875
2023-01-22 08:18:28.659737: step: 368/77, loss: 3.282143370597623e-05
2023-01-22 08:18:29.941161: step: 372/77, loss: 0.002442543162032962
2023-01-22 08:18:31.260189: step: 376/77, loss: 0.04803265258669853
2023-01-22 08:18:32.571047: step: 380/77, loss: 0.0002765162498690188
2023-01-22 08:18:33.852035: step: 384/77, loss: 0.007188045885413885
2023-01-22 08:18:35.140198: step: 388/77, loss: 0.02457827515900135
==================================================
Loss: 0.013
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 18}
Test Chinese: {'template': {'p': 0.9625, 'r': 0.6260162601626016, 'f1': 0.7586206896551725}, 'slot': {'p': 0.49056603773584906, 'r': 0.023636363636363636, 'f1': 0.0450997398091934}, 'combined': 0.034213595717319134, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 18}
Test Korean: {'template': {'p': 0.9625, 'r': 0.6260162601626016, 'f1': 0.7586206896551725}, 'slot': {'p': 0.48148148148148145, 'r': 0.023636363636363636, 'f1': 0.045060658578856154}, 'combined': 0.03418394788740812, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 18}
Test Russian: {'template': {'p': 0.9629629629629629, 'r': 0.6341463414634146, 'f1': 0.7647058823529412}, 'slot': {'p': 0.48148148148148145, 'r': 0.023636363636363636, 'f1': 0.045060658578856154}, 'combined': 0.03445815067794883, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 18}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Sample Russian: {'template': {'p': 1.0, 'r': 0.25, 'f1': 0.4}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 19
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 08:20:14.454646: step: 4/77, loss: 0.002298800041899085
2023-01-22 08:20:15.725508: step: 8/77, loss: 0.0049286182038486
2023-01-22 08:20:17.053111: step: 12/77, loss: 0.0019144328543916345
2023-01-22 08:20:18.337715: step: 16/77, loss: 0.00031539713381789625
2023-01-22 08:20:19.649183: step: 20/77, loss: 0.0002348479174543172
2023-01-22 08:20:20.950921: step: 24/77, loss: 0.00013729455531574786
2023-01-22 08:20:22.262986: step: 28/77, loss: 6.911471427883953e-05
2023-01-22 08:20:23.554297: step: 32/77, loss: 0.02153841033577919
2023-01-22 08:20:24.848205: step: 36/77, loss: 9.762252739164978e-05
2023-01-22 08:20:26.142947: step: 40/77, loss: 0.003212488256394863
2023-01-22 08:20:27.469872: step: 44/77, loss: 0.003010992892086506
2023-01-22 08:20:28.825752: step: 48/77, loss: 0.0010896417079493403
2023-01-22 08:20:30.128342: step: 52/77, loss: 0.028930403292179108
2023-01-22 08:20:31.483398: step: 56/77, loss: 4.31520129495766e-06
2023-01-22 08:20:32.773170: step: 60/77, loss: 0.012675435282289982
2023-01-22 08:20:34.087651: step: 64/77, loss: 0.0007141504902392626
2023-01-22 08:20:35.384136: step: 68/77, loss: 0.0005412647151388228
2023-01-22 08:20:36.670521: step: 72/77, loss: 4.95978338221903e-06
2023-01-22 08:20:37.932826: step: 76/77, loss: 0.0003975495637860149
2023-01-22 08:20:39.250222: step: 80/77, loss: 0.0002749481936916709
2023-01-22 08:20:40.470143: step: 84/77, loss: 0.016873259097337723
2023-01-22 08:20:41.742179: step: 88/77, loss: 0.030899502336978912
2023-01-22 08:20:43.099276: step: 92/77, loss: 0.003275349037721753
2023-01-22 08:20:44.435945: step: 96/77, loss: 0.047433532774448395
2023-01-22 08:20:45.736303: step: 100/77, loss: 0.0008755750604905188
2023-01-22 08:20:47.053213: step: 104/77, loss: 6.030965960235335e-05
2023-01-22 08:20:48.295816: step: 108/77, loss: 0.043235622346401215
2023-01-22 08:20:49.565332: step: 112/77, loss: 0.01793503761291504
2023-01-22 08:20:50.823897: step: 116/77, loss: 0.0010350135853514075
2023-01-22 08:20:52.114651: step: 120/77, loss: 2.9047590942354873e-05
2023-01-22 08:20:53.415439: step: 124/77, loss: 5.7926597946789116e-05
2023-01-22 08:20:54.660246: step: 128/77, loss: 9.975417924579233e-05
2023-01-22 08:20:55.940014: step: 132/77, loss: 0.016122905537486076
2023-01-22 08:20:57.229370: step: 136/77, loss: 0.012848117388784885
2023-01-22 08:20:58.531096: step: 140/77, loss: 0.00012284377589821815
2023-01-22 08:20:59.795246: step: 144/77, loss: 0.00014236402057576925
2023-01-22 08:21:01.057293: step: 148/77, loss: 0.03676806390285492
2023-01-22 08:21:02.359109: step: 152/77, loss: 0.03311936557292938
2023-01-22 08:21:03.678269: step: 156/77, loss: 3.850349457934499e-05
2023-01-22 08:21:04.975562: step: 160/77, loss: 0.0006413233932107687
2023-01-22 08:21:06.288786: step: 164/77, loss: 0.0027559632435441017
2023-01-22 08:21:07.558274: step: 168/77, loss: 0.0016262399731203914
2023-01-22 08:21:08.856067: step: 172/77, loss: 0.0035593020729720592
2023-01-22 08:21:10.135669: step: 176/77, loss: 0.00036346568958833814
2023-01-22 08:21:11.434916: step: 180/77, loss: 0.0005653153057210147
2023-01-22 08:21:12.734945: step: 184/77, loss: 2.0861619987044833e-08
2023-01-22 08:21:14.055971: step: 188/77, loss: 0.00012467730266507715
2023-01-22 08:21:15.356135: step: 192/77, loss: 0.001481741899624467
2023-01-22 08:21:16.713580: step: 196/77, loss: 6.3034076447365806e-06
2023-01-22 08:21:17.999709: step: 200/77, loss: 0.00010196158837061375
2023-01-22 08:21:19.301815: step: 204/77, loss: 0.0004513350431807339
2023-01-22 08:21:20.624422: step: 208/77, loss: 0.005133800208568573
2023-01-22 08:21:21.934853: step: 212/77, loss: 0.00018107425421476364
2023-01-22 08:21:23.259400: step: 216/77, loss: 2.1516948436328676e-06
2023-01-22 08:21:24.507527: step: 220/77, loss: 0.009150481782853603
2023-01-22 08:21:25.801389: step: 224/77, loss: 0.000125797902001068
2023-01-22 08:21:27.129244: step: 228/77, loss: 0.0288016926497221
2023-01-22 08:21:28.419002: step: 232/77, loss: 7.740493310848251e-05
2023-01-22 08:21:29.668701: step: 236/77, loss: 0.012049062177538872
2023-01-22 08:21:30.947916: step: 240/77, loss: 0.0032380330376327038
2023-01-22 08:21:32.248485: step: 244/77, loss: 6.329387815640075e-06
2023-01-22 08:21:33.584234: step: 248/77, loss: 0.018659718334674835
2023-01-22 08:21:34.881736: step: 252/77, loss: 0.00016582694661337882
2023-01-22 08:21:36.181681: step: 256/77, loss: 1.3560040201809898e-07
2023-01-22 08:21:37.500975: step: 260/77, loss: 0.04998790845274925
2023-01-22 08:21:38.838137: step: 264/77, loss: 5.789184069726616e-05
2023-01-22 08:21:40.123808: step: 268/77, loss: 9.110860992223024e-05
2023-01-22 08:21:41.400442: step: 272/77, loss: 0.01263953372836113
2023-01-22 08:21:42.630637: step: 276/77, loss: 0.0018562874756753445
2023-01-22 08:21:43.975567: step: 280/77, loss: 7.022190402494743e-05
2023-01-22 08:21:45.203082: step: 284/77, loss: 0.026238013058900833
2023-01-22 08:21:46.513371: step: 288/77, loss: 0.009614682756364346
2023-01-22 08:21:47.811761: step: 292/77, loss: 1.8372948034084402e-06
2023-01-22 08:21:49.121094: step: 296/77, loss: 0.01663910411298275
2023-01-22 08:21:50.465678: step: 300/77, loss: 0.02676456980407238
2023-01-22 08:21:51.755611: step: 304/77, loss: 2.913009438998415e-06
2023-01-22 08:21:53.016195: step: 308/77, loss: 0.0046882545575499535
2023-01-22 08:21:54.318077: step: 312/77, loss: 6.624018715228885e-05
2023-01-22 08:21:55.612527: step: 316/77, loss: 1.5274457837222144e-05
2023-01-22 08:21:56.954024: step: 320/77, loss: 0.03436944633722305
2023-01-22 08:21:58.210053: step: 324/77, loss: 0.00013097852934151888
2023-01-22 08:21:59.545889: step: 328/77, loss: 0.0005952545907348394
2023-01-22 08:22:00.894788: step: 332/77, loss: 0.05988472327589989
2023-01-22 08:22:02.206664: step: 336/77, loss: 0.00022210535826161504
2023-01-22 08:22:03.542346: step: 340/77, loss: 4.118560354982037e-06
2023-01-22 08:22:04.834665: step: 344/77, loss: 0.021829169243574142
2023-01-22 08:22:06.171823: step: 348/77, loss: 9.185371163766831e-05
2023-01-22 08:22:07.510120: step: 352/77, loss: 9.739038068801165e-05
2023-01-22 08:22:08.823461: step: 356/77, loss: 0.005260576028376818
2023-01-22 08:22:10.125248: step: 360/77, loss: 0.003987782634794712
2023-01-22 08:22:11.445481: step: 364/77, loss: 0.00033517484553158283
2023-01-22 08:22:12.740157: step: 368/77, loss: 7.898044714238495e-05
2023-01-22 08:22:14.111103: step: 372/77, loss: 0.05937068909406662
2023-01-22 08:22:15.420859: step: 376/77, loss: 0.015781676396727562
2023-01-22 08:22:16.666378: step: 380/77, loss: 0.00015802726557012647
2023-01-22 08:22:17.978450: step: 384/77, loss: 0.021459216251969337
2023-01-22 08:22:19.275339: step: 388/77, loss: 0.0018189732218161225
==================================================
Loss: 0.008
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4878048780487805, 'r': 0.03780718336483932, 'f1': 0.07017543859649122}, 'combined': 0.051708217913204055, 'epoch': 19}
Test Chinese: {'template': {'p': 0.9594594594594594, 'r': 0.5772357723577236, 'f1': 0.7208121827411168}, 'slot': {'p': 0.48, 'r': 0.02181818181818182, 'f1': 0.041739130434782605}, 'combined': 0.03008607371441183, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4878048780487805, 'r': 0.03780718336483932, 'f1': 0.07017543859649122}, 'combined': 0.051708217913204055, 'epoch': 19}
Test Korean: {'template': {'p': 0.96, 'r': 0.5853658536585366, 'f1': 0.7272727272727272}, 'slot': {'p': 0.48, 'r': 0.02181818181818182, 'f1': 0.041739130434782605}, 'combined': 0.030355731225296435, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.4878048780487805, 'r': 0.03780718336483932, 'f1': 0.07017543859649122}, 'combined': 0.051708217913204055, 'epoch': 19}
Test Russian: {'template': {'p': 0.96, 'r': 0.5853658536585366, 'f1': 0.7272727272727272}, 'slot': {'p': 0.48, 'r': 0.02181818181818182, 'f1': 0.041739130434782605}, 'combined': 0.030355731225296435, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 19}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Sample Russian: {'template': {'p': 1.0, 'r': 0.25, 'f1': 0.4}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 20
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 08:23:58.160784: step: 4/77, loss: 0.00020769896218553185
2023-01-22 08:23:59.500618: step: 8/77, loss: 7.160383393056691e-05
2023-01-22 08:24:00.810239: step: 12/77, loss: 3.1052193207870005e-06
2023-01-22 08:24:02.076596: step: 16/77, loss: 0.0009628063999116421
2023-01-22 08:24:03.398336: step: 20/77, loss: 0.0011009183945134282
2023-01-22 08:24:04.709593: step: 24/77, loss: 0.0008464275742881
2023-01-22 08:24:06.023258: step: 28/77, loss: 0.00027758374926634133
2023-01-22 08:24:07.295335: step: 32/77, loss: 0.007552329450845718
2023-01-22 08:24:08.562839: step: 36/77, loss: 2.311597745574545e-05
2023-01-22 08:24:09.838146: step: 40/77, loss: 0.00032255385303869843
2023-01-22 08:24:11.116389: step: 44/77, loss: 0.00015895852993708104
2023-01-22 08:24:12.429090: step: 48/77, loss: 0.01976187527179718
2023-01-22 08:24:13.708446: step: 52/77, loss: 0.0017516795778647065
2023-01-22 08:24:15.017282: step: 56/77, loss: 2.9258440918056294e-05
2023-01-22 08:24:16.320836: step: 60/77, loss: 5.6702177971601486e-05
2023-01-22 08:24:17.643136: step: 64/77, loss: 0.004498021677136421
2023-01-22 08:24:18.887231: step: 68/77, loss: 3.304888014099561e-05
2023-01-22 08:24:20.179939: step: 72/77, loss: 0.00022221094695851207
2023-01-22 08:24:21.505307: step: 76/77, loss: 0.00012549127859529108
2023-01-22 08:24:22.805256: step: 80/77, loss: 9.402490945831232e-07
2023-01-22 08:24:24.103233: step: 84/77, loss: 0.0007180677494034171
2023-01-22 08:24:25.326304: step: 88/77, loss: 0.00019054979202337563
2023-01-22 08:24:26.588407: step: 92/77, loss: 0.0010646095033735037
2023-01-22 08:24:27.865359: step: 96/77, loss: 0.0002717445604503155
2023-01-22 08:24:29.118621: step: 100/77, loss: 0.004205161239951849
2023-01-22 08:24:30.419211: step: 104/77, loss: 0.0046676695346832275
2023-01-22 08:24:31.700059: step: 108/77, loss: 0.00028675587964244187
2023-01-22 08:24:33.063073: step: 112/77, loss: 0.0002091683418257162
2023-01-22 08:24:34.363156: step: 116/77, loss: 0.0005976128159090877
2023-01-22 08:24:35.661830: step: 120/77, loss: 0.04944419860839844
2023-01-22 08:24:36.950619: step: 124/77, loss: 7.888769687269814e-06
2023-01-22 08:24:38.240494: step: 128/77, loss: 2.536001557018608e-05
2023-01-22 08:24:39.496747: step: 132/77, loss: 1.2457341654226184e-05
2023-01-22 08:24:40.830754: step: 136/77, loss: 4.223461291985586e-05
2023-01-22 08:24:42.164073: step: 140/77, loss: 0.0043779960833489895
2023-01-22 08:24:43.470117: step: 144/77, loss: 0.00011629718210315332
2023-01-22 08:24:44.802329: step: 148/77, loss: 0.011396033689379692
2023-01-22 08:24:46.115757: step: 152/77, loss: 0.0025481493212282658
2023-01-22 08:24:47.410180: step: 156/77, loss: 0.013005420565605164
2023-01-22 08:24:48.660608: step: 160/77, loss: 0.07505260407924652
2023-01-22 08:24:49.974515: step: 164/77, loss: 0.00014636758714914322
2023-01-22 08:24:51.295775: step: 168/77, loss: 0.0018843450816348195
2023-01-22 08:24:52.592080: step: 172/77, loss: 0.007612647954374552
2023-01-22 08:24:53.895081: step: 176/77, loss: 0.0030222514178603888
2023-01-22 08:24:55.212886: step: 180/77, loss: 9.826284076552838e-05
2023-01-22 08:24:56.544102: step: 184/77, loss: 0.0009221957880072296
2023-01-22 08:24:57.836469: step: 188/77, loss: 0.007369095925241709
2023-01-22 08:24:59.100860: step: 192/77, loss: 5.647513603435073e-07
2023-01-22 08:25:00.401479: step: 196/77, loss: 0.003735194681212306
2023-01-22 08:25:01.686308: step: 200/77, loss: 0.0003531751863192767
2023-01-22 08:25:03.024225: step: 204/77, loss: 0.00419339956715703
2023-01-22 08:25:04.324372: step: 208/77, loss: 9.134208085015416e-05
2023-01-22 08:25:05.695232: step: 212/77, loss: 7.7279910328798e-05
2023-01-22 08:25:07.006995: step: 216/77, loss: 1.5623803847120143e-05
2023-01-22 08:25:08.307644: step: 220/77, loss: 0.002031370997428894
2023-01-22 08:25:09.585500: step: 224/77, loss: 0.03100615181028843
2023-01-22 08:25:10.869472: step: 228/77, loss: 0.0006410797941498458
2023-01-22 08:25:12.202949: step: 232/77, loss: 3.231957407479058e-06
2023-01-22 08:25:13.511646: step: 236/77, loss: 4.3285936044412665e-06
2023-01-22 08:25:14.835215: step: 240/77, loss: 0.010497227311134338
2023-01-22 08:25:16.206679: step: 244/77, loss: 0.00025311787612736225
2023-01-22 08:25:17.571314: step: 248/77, loss: 0.01094940584152937
2023-01-22 08:25:18.871976: step: 252/77, loss: 0.005903997924178839
2023-01-22 08:25:20.191281: step: 256/77, loss: 0.0039853062480688095
2023-01-22 08:25:21.509613: step: 260/77, loss: 0.008176511153578758
2023-01-22 08:25:22.809669: step: 264/77, loss: 0.009724855422973633
2023-01-22 08:25:24.108379: step: 268/77, loss: 0.005896150600165129
2023-01-22 08:25:25.430776: step: 272/77, loss: 0.025987211614847183
2023-01-22 08:25:26.737277: step: 276/77, loss: 1.1424914191593416e-05
2023-01-22 08:25:28.045921: step: 280/77, loss: 0.00039195033605210483
2023-01-22 08:25:29.348077: step: 284/77, loss: 0.0040579866617918015
2023-01-22 08:25:30.649165: step: 288/77, loss: 4.544458988675615e-06
2023-01-22 08:25:31.928666: step: 292/77, loss: 9.509296796750277e-05
2023-01-22 08:25:33.223806: step: 296/77, loss: 0.08171162754297256
2023-01-22 08:25:34.505256: step: 300/77, loss: 2.0242150640115142e-05
2023-01-22 08:25:35.767048: step: 304/77, loss: 0.0001572638429934159
2023-01-22 08:25:37.067174: step: 308/77, loss: 0.002182783093303442
2023-01-22 08:25:38.376852: step: 312/77, loss: 0.00037773323128931224
2023-01-22 08:25:39.715062: step: 316/77, loss: 0.0036809672601521015
2023-01-22 08:25:40.987872: step: 320/77, loss: 0.002347944537177682
2023-01-22 08:25:42.338216: step: 324/77, loss: 0.05394945666193962
2023-01-22 08:25:43.648059: step: 328/77, loss: 0.0023451726883649826
2023-01-22 08:25:44.958990: step: 332/77, loss: 0.01851961389183998
2023-01-22 08:25:46.268867: step: 336/77, loss: 4.4434455048758537e-05
2023-01-22 08:25:47.632901: step: 340/77, loss: 0.006946150679141283
2023-01-22 08:25:48.951685: step: 344/77, loss: 0.01549392007291317
2023-01-22 08:25:50.288041: step: 348/77, loss: 4.792132676811889e-05
2023-01-22 08:25:51.580796: step: 352/77, loss: 4.237364009895828e-06
2023-01-22 08:25:52.886607: step: 356/77, loss: 1.0000697329815011e-05
2023-01-22 08:25:54.190362: step: 360/77, loss: 0.00021215454034972936
2023-01-22 08:25:55.490091: step: 364/77, loss: 0.029700905084609985
2023-01-22 08:25:56.787236: step: 368/77, loss: 6.0535454394994304e-05
2023-01-22 08:25:58.107031: step: 372/77, loss: 0.000546629133168608
2023-01-22 08:25:59.406640: step: 376/77, loss: 0.0011142148869112134
2023-01-22 08:26:00.691524: step: 380/77, loss: 0.003580347867682576
2023-01-22 08:26:01.967098: step: 384/77, loss: 0.0002462729753460735
2023-01-22 08:26:03.268830: step: 388/77, loss: 4.011456621810794e-05
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 20}
Test Chinese: {'template': {'p': 0.9487179487179487, 'r': 0.6016260162601627, 'f1': 0.736318407960199}, 'slot': {'p': 0.4375, 'r': 0.019090909090909092, 'f1': 0.036585365853658534}, 'combined': 0.026938478340007278, 'epoch': 20}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 20}
Test Korean: {'template': {'p': 0.9487179487179487, 'r': 0.6016260162601627, 'f1': 0.736318407960199}, 'slot': {'p': 0.4583333333333333, 'r': 0.02, 'f1': 0.03832752613240418}, 'combined': 0.02822126302286477, 'epoch': 20}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 20}
Test Russian: {'template': {'p': 0.9487179487179487, 'r': 0.6016260162601627, 'f1': 0.736318407960199}, 'slot': {'p': 0.4666666666666667, 'r': 0.019090909090909092, 'f1': 0.036681222707423584}, 'combined': 0.027009059505963634, 'epoch': 20}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 20}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Sample Russian: {'template': {'p': 1.0, 'r': 0.25, 'f1': 0.4}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 21
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 08:27:41.820174: step: 4/77, loss: 0.03239181637763977
2023-01-22 08:27:43.090179: step: 8/77, loss: 0.017717987298965454
2023-01-22 08:27:44.428521: step: 12/77, loss: 6.446881343435962e-06
2023-01-22 08:27:45.713198: step: 16/77, loss: 0.008411260321736336
2023-01-22 08:27:46.976505: step: 20/77, loss: 3.678425491671078e-05
2023-01-22 08:27:48.300571: step: 24/77, loss: 7.518615802837303e-06
2023-01-22 08:27:49.604251: step: 28/77, loss: 8.049477764870971e-05
2023-01-22 08:27:50.913986: step: 32/77, loss: 0.00012354887439869344
2023-01-22 08:27:52.174996: step: 36/77, loss: 1.3187103604650474e-06
2023-01-22 08:27:53.458230: step: 40/77, loss: 8.020484528969973e-05
2023-01-22 08:27:54.749707: step: 44/77, loss: 0.0003721020766533911
2023-01-22 08:27:56.105427: step: 48/77, loss: 4.947678462485783e-05
2023-01-22 08:27:57.408802: step: 52/77, loss: 0.006109760142862797
2023-01-22 08:27:58.720056: step: 56/77, loss: 0.03650211915373802
2023-01-22 08:28:00.002687: step: 60/77, loss: 1.3884582585887983e-05
2023-01-22 08:28:01.262780: step: 64/77, loss: 2.6498164515942335e-05
2023-01-22 08:28:02.505471: step: 68/77, loss: 0.0009089701343327761
2023-01-22 08:28:03.811059: step: 72/77, loss: 0.000358206540113315
2023-01-22 08:28:05.107746: step: 76/77, loss: 0.028453640639781952
2023-01-22 08:28:06.430718: step: 80/77, loss: 0.0003351859631948173
2023-01-22 08:28:07.713773: step: 84/77, loss: 4.7906294639687985e-05
2023-01-22 08:28:09.035625: step: 88/77, loss: 0.00013332579692360014
2023-01-22 08:28:10.364934: step: 92/77, loss: 0.0007689341437071562
2023-01-22 08:28:11.645218: step: 96/77, loss: 0.0031823881436139345
2023-01-22 08:28:12.991356: step: 100/77, loss: 0.00011390875442884862
2023-01-22 08:28:14.319595: step: 104/77, loss: 0.0002913151402026415
2023-01-22 08:28:15.555332: step: 108/77, loss: 8.261164111900143e-06
2023-01-22 08:28:16.856679: step: 112/77, loss: 5.380424227041658e-06
2023-01-22 08:28:18.170756: step: 116/77, loss: 0.005360376555472612
2023-01-22 08:28:19.502018: step: 120/77, loss: 2.903307176893577e-05
2023-01-22 08:28:20.820768: step: 124/77, loss: 2.8209698939463124e-05
2023-01-22 08:28:22.132699: step: 128/77, loss: 4.687665568781085e-05
2023-01-22 08:28:23.446997: step: 132/77, loss: 0.0002770746359601617
2023-01-22 08:28:24.731661: step: 136/77, loss: 0.00012425713066477329
2023-01-22 08:28:26.024359: step: 140/77, loss: 0.00012386722664814442
2023-01-22 08:28:27.281016: step: 144/77, loss: 0.04620302841067314
2023-01-22 08:28:28.570198: step: 148/77, loss: 0.023962827399373055
2023-01-22 08:28:29.910714: step: 152/77, loss: 1.7255728380405344e-05
2023-01-22 08:28:31.203390: step: 156/77, loss: 0.0002274275029776618
2023-01-22 08:28:32.461908: step: 160/77, loss: 1.3703098375117406e-05
2023-01-22 08:28:33.803981: step: 164/77, loss: 4.8758891352918e-05
2023-01-22 08:28:35.117221: step: 168/77, loss: 0.009159489534795284
2023-01-22 08:28:36.395814: step: 172/77, loss: 0.0037564877420663834
2023-01-22 08:28:37.704520: step: 176/77, loss: 0.0002380924706812948
2023-01-22 08:28:38.956850: step: 180/77, loss: 5.755915935878875e-06
2023-01-22 08:28:40.255779: step: 184/77, loss: 5.0621150876395404e-05
2023-01-22 08:28:41.545691: step: 188/77, loss: 2.6403948140796274e-05
2023-01-22 08:28:42.825608: step: 192/77, loss: 0.00014365346578415483
2023-01-22 08:28:44.130365: step: 196/77, loss: 0.002432482549920678
2023-01-22 08:28:45.408770: step: 200/77, loss: 4.91056744067464e-05
2023-01-22 08:28:46.714271: step: 204/77, loss: 0.0019472897984087467
2023-01-22 08:28:48.023030: step: 208/77, loss: 0.049116019159555435
2023-01-22 08:28:49.309740: step: 212/77, loss: 0.00023824565869290382
2023-01-22 08:28:50.570456: step: 216/77, loss: 0.0004655311640817672
2023-01-22 08:28:51.863355: step: 220/77, loss: 5.9485246310941875e-05
2023-01-22 08:28:53.156814: step: 224/77, loss: 0.003002239391207695
2023-01-22 08:28:54.453681: step: 228/77, loss: 0.0006095260032452643
2023-01-22 08:28:55.728052: step: 232/77, loss: 0.027523092925548553
2023-01-22 08:28:57.035858: step: 236/77, loss: 0.13839784264564514
2023-01-22 08:28:58.353238: step: 240/77, loss: 0.0003813329676631838
2023-01-22 08:28:59.668927: step: 244/77, loss: 0.0010819652816280723
2023-01-22 08:29:01.013130: step: 248/77, loss: 0.0006821186398155987
2023-01-22 08:29:02.251518: step: 252/77, loss: 1.6465527323816787e-06
2023-01-22 08:29:03.556245: step: 256/77, loss: 6.989516805333551e-06
2023-01-22 08:29:04.858456: step: 260/77, loss: 0.0004569220182020217
2023-01-22 08:29:06.140343: step: 264/77, loss: 2.5564697352820076e-05
2023-01-22 08:29:07.423081: step: 268/77, loss: 0.0005146386101841927
2023-01-22 08:29:08.717176: step: 272/77, loss: 0.00024345022393390536
2023-01-22 08:29:10.017379: step: 276/77, loss: 2.1641742932843044e-05
2023-01-22 08:29:11.303105: step: 280/77, loss: 5.6872628192650154e-05
2023-01-22 08:29:12.630105: step: 284/77, loss: 0.004902479238808155
2023-01-22 08:29:13.932466: step: 288/77, loss: 8.766914834268391e-05
2023-01-22 08:29:15.202647: step: 292/77, loss: 2.6567552140477346e-06
2023-01-22 08:29:16.507659: step: 296/77, loss: 0.026077698916196823
2023-01-22 08:29:17.794849: step: 300/77, loss: 0.0014514094218611717
2023-01-22 08:29:19.087643: step: 304/77, loss: 4.962047341905418e-07
2023-01-22 08:29:20.425948: step: 308/77, loss: 4.67259633296635e-06
2023-01-22 08:29:21.696480: step: 312/77, loss: 0.026495279744267464
2023-01-22 08:29:23.024662: step: 316/77, loss: 0.0038940461818128824
2023-01-22 08:29:24.295320: step: 320/77, loss: 0.029748141765594482
2023-01-22 08:29:25.610390: step: 324/77, loss: 0.00021692071459256113
2023-01-22 08:29:26.920358: step: 328/77, loss: 0.004932933486998081
2023-01-22 08:29:28.173246: step: 332/77, loss: 0.00018782397091854364
2023-01-22 08:29:29.453971: step: 336/77, loss: 0.0314268097281456
2023-01-22 08:29:30.785275: step: 340/77, loss: 9.739911183714867e-05
2023-01-22 08:29:32.076320: step: 344/77, loss: 0.0005904044955968857
2023-01-22 08:29:33.367962: step: 348/77, loss: 0.005018756724894047
2023-01-22 08:29:34.719829: step: 352/77, loss: 0.0028589535504579544
2023-01-22 08:29:36.022894: step: 356/77, loss: 0.13345322012901306
2023-01-22 08:29:37.343376: step: 360/77, loss: 0.005826289765536785
2023-01-22 08:29:38.626486: step: 364/77, loss: 0.000740259129088372
2023-01-22 08:29:39.870253: step: 368/77, loss: 0.010807367041707039
2023-01-22 08:29:41.159450: step: 372/77, loss: 0.049246374517679214
2023-01-22 08:29:42.444308: step: 376/77, loss: 2.707458406803198e-06
2023-01-22 08:29:43.788834: step: 380/77, loss: 0.0026401567738503218
2023-01-22 08:29:45.093592: step: 384/77, loss: 0.01615547016263008
2023-01-22 08:29:46.438618: step: 388/77, loss: 3.602041761041619e-05
==================================================
Loss: 0.008
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 21}
Test Chinese: {'template': {'p': 0.9342105263157895, 'r': 0.5772357723577236, 'f1': 0.71356783919598}, 'slot': {'p': 0.44, 'r': 0.02, 'f1': 0.03826086956521739}, 'combined': 0.027301726021411406, 'epoch': 21}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 21}
Test Korean: {'template': {'p': 0.9342105263157895, 'r': 0.5772357723577236, 'f1': 0.71356783919598}, 'slot': {'p': 0.44, 'r': 0.02, 'f1': 0.03826086956521739}, 'combined': 0.027301726021411406, 'epoch': 21}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 21}
Test Russian: {'template': {'p': 0.9342105263157895, 'r': 0.5772357723577236, 'f1': 0.71356783919598}, 'slot': {'p': 0.4489795918367347, 'r': 0.02, 'f1': 0.038294168842471714}, 'combined': 0.02732548731472856, 'epoch': 21}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 21}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Sample Russian: {'template': {'p': 1.0, 'r': 0.25, 'f1': 0.4}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 22
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 08:31:24.789539: step: 4/77, loss: 0.0007809511735104024
2023-01-22 08:31:26.098953: step: 8/77, loss: 0.001551383757032454
2023-01-22 08:31:27.385089: step: 12/77, loss: 0.007308583240956068
2023-01-22 08:31:28.660519: step: 16/77, loss: 2.1040819774498232e-05
2023-01-22 08:31:29.925877: step: 20/77, loss: 0.0037530087865889072
2023-01-22 08:31:31.246946: step: 24/77, loss: 0.0008601925801485777
2023-01-22 08:31:32.540521: step: 28/77, loss: 9.703524119686335e-05
2023-01-22 08:31:33.843172: step: 32/77, loss: 0.00015865601017139852
2023-01-22 08:31:35.128032: step: 36/77, loss: 0.00012202590005472302
2023-01-22 08:31:36.423188: step: 40/77, loss: 0.011112484149634838
2023-01-22 08:31:37.695266: step: 44/77, loss: 0.000339729362167418
2023-01-22 08:31:38.935714: step: 48/77, loss: 0.0005652804975397885
2023-01-22 08:31:40.216519: step: 52/77, loss: 0.003238065168261528
2023-01-22 08:31:41.503813: step: 56/77, loss: 4.828845339943655e-05
2023-01-22 08:31:42.762974: step: 60/77, loss: 0.003508348250761628
2023-01-22 08:31:44.107915: step: 64/77, loss: 8.385243745578919e-06
2023-01-22 08:31:45.438837: step: 68/77, loss: 0.035650648176670074
2023-01-22 08:31:46.722671: step: 72/77, loss: 0.037739142775535583
2023-01-22 08:31:48.036559: step: 76/77, loss: 0.0001413650024915114
2023-01-22 08:31:49.313400: step: 80/77, loss: 0.0006701253587380052
2023-01-22 08:31:50.586069: step: 84/77, loss: 0.0020222077146172523
2023-01-22 08:31:51.916511: step: 88/77, loss: 0.0008589206263422966
2023-01-22 08:31:53.206854: step: 92/77, loss: 0.0011655199341475964
2023-01-22 08:31:54.473672: step: 96/77, loss: 0.0014887371798977256
2023-01-22 08:31:55.748921: step: 100/77, loss: 0.001581578399054706
2023-01-22 08:31:57.020972: step: 104/77, loss: 0.00011187476047780365
2023-01-22 08:31:58.314904: step: 108/77, loss: 0.00048642870387993753
2023-01-22 08:31:59.578525: step: 112/77, loss: 0.000898391823284328
2023-01-22 08:32:00.903233: step: 116/77, loss: 8.436571988568176e-06
2023-01-22 08:32:02.196282: step: 120/77, loss: 0.02246893011033535
2023-01-22 08:32:03.509959: step: 124/77, loss: 0.001038522575981915
2023-01-22 08:32:04.779547: step: 128/77, loss: 3.281307726865634e-05
2023-01-22 08:32:06.054512: step: 132/77, loss: 0.003178850281983614
2023-01-22 08:32:07.351254: step: 136/77, loss: 1.7324404325336218e-05
2023-01-22 08:32:08.666770: step: 140/77, loss: 0.0005918988026678562
2023-01-22 08:32:09.945460: step: 144/77, loss: 2.3243248506332748e-05
2023-01-22 08:32:11.200660: step: 148/77, loss: 0.0066335974261164665
2023-01-22 08:32:12.491718: step: 152/77, loss: 0.00011396820627851412
2023-01-22 08:32:13.763013: step: 156/77, loss: 0.03955855965614319
2023-01-22 08:32:15.076613: step: 160/77, loss: 9.686138218967244e-05
2023-01-22 08:32:16.388720: step: 164/77, loss: 0.021154014393687248
2023-01-22 08:32:17.697153: step: 168/77, loss: 0.00011484503920655698
2023-01-22 08:32:19.044723: step: 172/77, loss: 0.0008551405044272542
2023-01-22 08:32:20.400660: step: 176/77, loss: 0.02964947558939457
2023-01-22 08:32:21.717300: step: 180/77, loss: 0.0017165419412776828
2023-01-22 08:32:23.053873: step: 184/77, loss: 0.004964523948729038
2023-01-22 08:32:24.371061: step: 188/77, loss: 0.002340970328077674
2023-01-22 08:32:25.714520: step: 192/77, loss: 0.0009994141291826963
2023-01-22 08:32:27.027842: step: 196/77, loss: 0.005752595141530037
2023-01-22 08:32:28.261394: step: 200/77, loss: 4.916898251394741e-05
2023-01-22 08:32:29.562547: step: 204/77, loss: 0.0013054257724434137
2023-01-22 08:32:30.849049: step: 208/77, loss: 5.486142617883161e-05
2023-01-22 08:32:32.139313: step: 212/77, loss: 0.00024407217279076576
2023-01-22 08:32:33.474177: step: 216/77, loss: 1.1915855793631636e-05
2023-01-22 08:32:34.800315: step: 220/77, loss: 0.0007540610968135297
2023-01-22 08:32:36.118424: step: 224/77, loss: 0.00014220400771591812
2023-01-22 08:32:37.410500: step: 228/77, loss: 0.07779377698898315
2023-01-22 08:32:38.688892: step: 232/77, loss: 0.032325536012649536
2023-01-22 08:32:39.945136: step: 236/77, loss: 5.522904302779352e-06
2023-01-22 08:32:41.198513: step: 240/77, loss: 0.0035868207924067974
2023-01-22 08:32:42.524049: step: 244/77, loss: 0.004020586609840393
2023-01-22 08:32:43.805016: step: 248/77, loss: 0.0007980067748576403
2023-01-22 08:32:45.137485: step: 252/77, loss: 1.5416650057886727e-05
2023-01-22 08:32:46.413066: step: 256/77, loss: 1.2635971415875247e-06
2023-01-22 08:32:47.737128: step: 260/77, loss: 0.0012691058218479156
2023-01-22 08:32:48.990130: step: 264/77, loss: 0.016745002940297127
2023-01-22 08:32:50.292266: step: 268/77, loss: 0.0318622961640358
2023-01-22 08:32:51.618404: step: 272/77, loss: 8.759008051129058e-05
2023-01-22 08:32:52.909945: step: 276/77, loss: 0.0004965168191120028
2023-01-22 08:32:54.182852: step: 280/77, loss: 1.5795176011579315e-07
2023-01-22 08:32:55.433874: step: 284/77, loss: 2.293473153258674e-05
2023-01-22 08:32:56.754493: step: 288/77, loss: 3.388850382179953e-05
2023-01-22 08:32:58.035112: step: 292/77, loss: 0.009840208105742931
2023-01-22 08:32:59.323782: step: 296/77, loss: 0.0010038908803835511
2023-01-22 08:33:00.640582: step: 300/77, loss: 4.372560579213314e-05
2023-01-22 08:33:01.901902: step: 304/77, loss: 0.0003445250040385872
2023-01-22 08:33:03.216858: step: 308/77, loss: 0.00039814409683458507
2023-01-22 08:33:04.509902: step: 312/77, loss: 0.0046538361348211765
2023-01-22 08:33:05.804147: step: 316/77, loss: 0.022742586210370064
2023-01-22 08:33:07.128954: step: 320/77, loss: 0.01748577691614628
2023-01-22 08:33:08.401142: step: 324/77, loss: 0.00017750824918039143
2023-01-22 08:33:09.674258: step: 328/77, loss: 3.159026960020128e-07
2023-01-22 08:33:10.938271: step: 332/77, loss: 0.00035073619801551104
2023-01-22 08:33:12.233105: step: 336/77, loss: 4.3746422306867316e-05
2023-01-22 08:33:13.537145: step: 340/77, loss: 0.045224498957395554
2023-01-22 08:33:14.875144: step: 344/77, loss: 0.03973131626844406
2023-01-22 08:33:16.126413: step: 348/77, loss: 0.0003504282212816179
2023-01-22 08:33:17.416488: step: 352/77, loss: 7.479263877030462e-05
2023-01-22 08:33:18.717224: step: 356/77, loss: 0.00043065831414423883
2023-01-22 08:33:20.004482: step: 360/77, loss: 0.0263584665954113
2023-01-22 08:33:21.292226: step: 364/77, loss: 7.684577576583251e-05
2023-01-22 08:33:22.581641: step: 368/77, loss: 7.579052908113226e-05
2023-01-22 08:33:23.882341: step: 372/77, loss: 0.005002635531127453
2023-01-22 08:33:25.159686: step: 376/77, loss: 0.047192104160785675
2023-01-22 08:33:26.421782: step: 380/77, loss: 0.0021299412474036217
2023-01-22 08:33:27.647392: step: 384/77, loss: 0.0011768265394493937
2023-01-22 08:33:28.916288: step: 388/77, loss: 0.02807861752808094
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 22}
Test Chinese: {'template': {'p': 0.974025974025974, 'r': 0.6097560975609756, 'f1': 0.7500000000000001}, 'slot': {'p': 0.5, 'r': 0.02, 'f1': 0.038461538461538464}, 'combined': 0.02884615384615385, 'epoch': 22}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 22}
Test Korean: {'template': {'p': 0.974025974025974, 'r': 0.6097560975609756, 'f1': 0.7500000000000001}, 'slot': {'p': 0.5, 'r': 0.019090909090909092, 'f1': 0.03677758318739055}, 'combined': 0.027583187390542916, 'epoch': 22}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 22}
Test Russian: {'template': {'p': 0.974025974025974, 'r': 0.6097560975609756, 'f1': 0.7500000000000001}, 'slot': {'p': 0.5116279069767442, 'r': 0.02, 'f1': 0.03849518810148731}, 'combined': 0.02887139107611549, 'epoch': 22}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 22}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 22}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 23
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 08:35:04.550529: step: 4/77, loss: 0.000223344934056513
2023-01-22 08:35:05.817055: step: 8/77, loss: 0.0002499055990483612
2023-01-22 08:35:07.130214: step: 12/77, loss: 0.003980610053986311
2023-01-22 08:35:08.425983: step: 16/77, loss: 0.0001560335367685184
2023-01-22 08:35:09.662525: step: 20/77, loss: 0.009259466081857681
2023-01-22 08:35:10.951815: step: 24/77, loss: 0.005971284583210945
2023-01-22 08:35:12.261686: step: 28/77, loss: 0.0023534297943115234
2023-01-22 08:35:13.517184: step: 32/77, loss: 0.0012932337122038007
2023-01-22 08:35:14.774423: step: 36/77, loss: 0.06185340881347656
2023-01-22 08:35:16.066187: step: 40/77, loss: 0.027082540094852448
2023-01-22 08:35:17.332958: step: 44/77, loss: 5.294245056575164e-05
2023-01-22 08:35:18.633555: step: 48/77, loss: 1.238259415003995e-06
2023-01-22 08:35:19.901409: step: 52/77, loss: 2.2649683728559467e-07
2023-01-22 08:35:21.173506: step: 56/77, loss: 0.0020577346440404654
2023-01-22 08:35:22.460355: step: 60/77, loss: 0.0
2023-01-22 08:35:23.732907: step: 64/77, loss: 4.52091044280678e-05
2023-01-22 08:35:25.052400: step: 68/77, loss: 1.0430811769879256e-08
2023-01-22 08:35:26.362647: step: 72/77, loss: 0.0011307750828564167
2023-01-22 08:35:27.635088: step: 76/77, loss: 5.794014214188792e-05
2023-01-22 08:35:28.895379: step: 80/77, loss: 1.281494945715167e-07
2023-01-22 08:35:30.146375: step: 84/77, loss: 0.000748545688111335
2023-01-22 08:35:31.397789: step: 88/77, loss: 3.0113683351373766e-06
2023-01-22 08:35:32.709516: step: 92/77, loss: 0.003903226926922798
2023-01-22 08:35:34.049925: step: 96/77, loss: 0.031046070158481598
2023-01-22 08:35:35.335342: step: 100/77, loss: 9.00256636668928e-05
2023-01-22 08:35:36.598607: step: 104/77, loss: 8.201535092666745e-05
2023-01-22 08:35:37.911529: step: 108/77, loss: 1.2367941337743105e-07
2023-01-22 08:35:39.188585: step: 112/77, loss: 0.0028015454299747944
2023-01-22 08:35:40.521074: step: 116/77, loss: 1.5853851209612912e-06
2023-01-22 08:35:41.819096: step: 120/77, loss: 1.0672863936633803e-05
2023-01-22 08:35:43.120597: step: 124/77, loss: 6.288173040047695e-07
2023-01-22 08:35:44.443865: step: 128/77, loss: 0.002125179162248969
2023-01-22 08:35:45.713574: step: 132/77, loss: 0.0003999666660092771
2023-01-22 08:35:46.968240: step: 136/77, loss: 0.06220989674329758
2023-01-22 08:35:48.239717: step: 140/77, loss: 0.00030411180341616273
2023-01-22 08:35:49.482620: step: 144/77, loss: 0.00021978866425342858
2023-01-22 08:35:50.803289: step: 148/77, loss: 0.0013275524834170938
2023-01-22 08:35:52.120869: step: 152/77, loss: 0.0007778856670483947
2023-01-22 08:35:53.447132: step: 156/77, loss: 0.03293122723698616
2023-01-22 08:35:54.708358: step: 160/77, loss: 1.7612574083614163e-06
2023-01-22 08:35:55.996977: step: 164/77, loss: 0.043627262115478516
2023-01-22 08:35:57.265003: step: 168/77, loss: 0.001226570806466043
2023-01-22 08:35:58.517952: step: 172/77, loss: 0.00017758070316631347
2023-01-22 08:35:59.832808: step: 176/77, loss: 3.354599903104827e-05
2023-01-22 08:36:01.123938: step: 180/77, loss: 0.03583592548966408
2023-01-22 08:36:02.383855: step: 184/77, loss: 5.370784492697567e-05
2023-01-22 08:36:03.691709: step: 188/77, loss: 0.0017548176692798734
2023-01-22 08:36:04.975638: step: 192/77, loss: 0.02631654031574726
2023-01-22 08:36:06.239982: step: 196/77, loss: 9.08508081920445e-06
2023-01-22 08:36:07.497855: step: 200/77, loss: 0.0017153595108538866
2023-01-22 08:36:08.870361: step: 204/77, loss: 0.00011920402175746858
2023-01-22 08:36:10.159484: step: 208/77, loss: 0.03767101839184761
2023-01-22 08:36:11.442740: step: 212/77, loss: 2.3928218070068397e-05
2023-01-22 08:36:12.765952: step: 216/77, loss: 3.788954472838668e-06
2023-01-22 08:36:14.023848: step: 220/77, loss: 0.0002056130178971216
2023-01-22 08:36:15.314578: step: 224/77, loss: 0.000769798643887043
2023-01-22 08:36:16.597123: step: 228/77, loss: 0.00010402412590337917
2023-01-22 08:36:17.886841: step: 232/77, loss: 0.00010068294795928523
2023-01-22 08:36:19.158569: step: 236/77, loss: 0.002481456147506833
2023-01-22 08:36:20.452161: step: 240/77, loss: 5.516312376130372e-05
2023-01-22 08:36:21.781995: step: 244/77, loss: 3.2243500754702836e-05
2023-01-22 08:36:23.082225: step: 248/77, loss: 0.0004081795923411846
2023-01-22 08:36:24.379633: step: 252/77, loss: 8.850173799146432e-06
2023-01-22 08:36:25.624685: step: 256/77, loss: 0.0003328286111354828
2023-01-22 08:36:26.923097: step: 260/77, loss: 0.0030909974593669176
2023-01-22 08:36:28.190904: step: 264/77, loss: 4.4013545448251534e-06
2023-01-22 08:36:29.489208: step: 268/77, loss: 0.012226199731230736
2023-01-22 08:36:30.819441: step: 272/77, loss: 0.0010382995242252946
2023-01-22 08:36:32.108565: step: 276/77, loss: 0.00013937246694695204
2023-01-22 08:36:33.426997: step: 280/77, loss: 0.021476108580827713
2023-01-22 08:36:34.735604: step: 284/77, loss: 0.009720050729811192
2023-01-22 08:36:36.060112: step: 288/77, loss: 0.005399320740252733
2023-01-22 08:36:37.360837: step: 292/77, loss: 4.12450208386872e-06
2023-01-22 08:36:38.588928: step: 296/77, loss: 0.0008546271128579974
2023-01-22 08:36:39.893498: step: 300/77, loss: 0.0015399702824652195
2023-01-22 08:36:41.181704: step: 304/77, loss: 0.0012370938202366233
2023-01-22 08:36:42.475891: step: 308/77, loss: 0.024090373888611794
2023-01-22 08:36:43.737108: step: 312/77, loss: 6.0301408666418865e-06
2023-01-22 08:36:45.036784: step: 316/77, loss: 1.606405567144975e-05
2023-01-22 08:36:46.322876: step: 320/77, loss: 0.0001153816920123063
2023-01-22 08:36:47.577252: step: 324/77, loss: 0.0015452578663825989
2023-01-22 08:36:48.868006: step: 328/77, loss: 0.0007853202987462282
2023-01-22 08:36:50.149053: step: 332/77, loss: 4.006969174952246e-05
2023-01-22 08:36:51.448644: step: 336/77, loss: 4.237548182572937e-06
2023-01-22 08:36:52.751816: step: 340/77, loss: 5.247162334853783e-05
2023-01-22 08:36:54.059704: step: 344/77, loss: 4.022320354124531e-05
2023-01-22 08:36:55.341919: step: 348/77, loss: 0.004062959458678961
2023-01-22 08:36:56.633675: step: 352/77, loss: 5.144433816894889e-05
2023-01-22 08:36:57.925392: step: 356/77, loss: 0.04348785802721977
2023-01-22 08:36:59.176867: step: 360/77, loss: 2.714705260586925e-05
2023-01-22 08:37:00.493920: step: 364/77, loss: 7.023421494523063e-05
2023-01-22 08:37:01.786956: step: 368/77, loss: 0.003611247520893812
2023-01-22 08:37:03.092189: step: 372/77, loss: 6.616061227759928e-07
2023-01-22 08:37:04.442766: step: 376/77, loss: 0.0027029793709516525
2023-01-22 08:37:05.744954: step: 380/77, loss: 3.5358483728487045e-05
2023-01-22 08:37:07.061168: step: 384/77, loss: 5.154731115908362e-05
2023-01-22 08:37:08.344471: step: 388/77, loss: 0.0008300709305331111
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 23}
Test Chinese: {'template': {'p': 0.9620253164556962, 'r': 0.6178861788617886, 'f1': 0.7524752475247525}, 'slot': {'p': 0.5106382978723404, 'r': 0.02181818181818182, 'f1': 0.041848299912816043}, 'combined': 0.03148980983538633, 'epoch': 23}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 23}
Test Korean: {'template': {'p': 0.9615384615384616, 'r': 0.6097560975609756, 'f1': 0.7462686567164178}, 'slot': {'p': 0.5111111111111111, 'r': 0.02090909090909091, 'f1': 0.04017467248908297}, 'combined': 0.029981098872449975, 'epoch': 23}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 23}
Test Russian: {'template': {'p': 0.9615384615384616, 'r': 0.6097560975609756, 'f1': 0.7462686567164178}, 'slot': {'p': 0.5217391304347826, 'r': 0.02181818181818182, 'f1': 0.041884816753926704}, 'combined': 0.031257325935766196, 'epoch': 23}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 23}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Russian: {'template': {'p': 1.0, 'r': 0.25, 'f1': 0.4}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 24
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 08:38:44.046383: step: 4/77, loss: 0.000768980011343956
2023-01-22 08:38:45.320085: step: 8/77, loss: 0.0007521238876506686
2023-01-22 08:38:46.618926: step: 12/77, loss: 0.0003945432836189866
2023-01-22 08:38:47.891944: step: 16/77, loss: 2.3855304789321963e-06
2023-01-22 08:38:49.154871: step: 20/77, loss: 0.0001138556472142227
2023-01-22 08:38:50.417714: step: 24/77, loss: 1.5491634258069098e-05
2023-01-22 08:38:51.716339: step: 28/77, loss: 3.6268065741751343e-06
2023-01-22 08:38:52.980242: step: 32/77, loss: 0.01696803607046604
2023-01-22 08:38:54.260937: step: 36/77, loss: 1.2886805961898062e-05
2023-01-22 08:38:55.502923: step: 40/77, loss: 0.05772382393479347
2023-01-22 08:38:56.771084: step: 44/77, loss: 8.849301957525313e-05
2023-01-22 08:38:58.076290: step: 48/77, loss: 3.100880803685868e-06
2023-01-22 08:38:59.331332: step: 52/77, loss: 0.021691516041755676
2023-01-22 08:39:00.580772: step: 56/77, loss: 0.00035898658097721636
2023-01-22 08:39:01.913161: step: 60/77, loss: 7.435634188368567e-07
2023-01-22 08:39:03.250587: step: 64/77, loss: 0.0022912865970283747
2023-01-22 08:39:04.597791: step: 68/77, loss: 1.6972255707514705e-06
2023-01-22 08:39:05.836954: step: 72/77, loss: 0.0005609336076304317
2023-01-22 08:39:07.138726: step: 76/77, loss: 9.501824933977332e-06
2023-01-22 08:39:08.442974: step: 80/77, loss: 0.0011109262704849243
2023-01-22 08:39:09.724449: step: 84/77, loss: 0.0012305447598919272
2023-01-22 08:39:11.012272: step: 88/77, loss: 0.0032722926698625088
2023-01-22 08:39:12.277506: step: 92/77, loss: 0.0003757534723263234
2023-01-22 08:39:13.600609: step: 96/77, loss: 0.0036070612259209156
2023-01-22 08:39:14.873257: step: 100/77, loss: 0.0010984732070937753
2023-01-22 08:39:16.164338: step: 104/77, loss: 0.011957976035773754
2023-01-22 08:39:17.451738: step: 108/77, loss: 0.00025756648392416537
2023-01-22 08:39:18.687939: step: 112/77, loss: 0.0005127987242303789
2023-01-22 08:39:19.993542: step: 116/77, loss: 3.300553362350911e-05
2023-01-22 08:39:21.326492: step: 120/77, loss: 0.0017934296047315001
2023-01-22 08:39:22.635476: step: 124/77, loss: 0.0026127288583666086
2023-01-22 08:39:23.960521: step: 128/77, loss: 0.0007074242457747459
2023-01-22 08:39:25.260369: step: 132/77, loss: 1.341101665275346e-07
2023-01-22 08:39:26.538675: step: 136/77, loss: 0.03210016340017319
2023-01-22 08:39:27.784814: step: 140/77, loss: 0.0003734312776941806
2023-01-22 08:39:29.093662: step: 144/77, loss: 4.366786015452817e-05
2023-01-22 08:39:30.404238: step: 148/77, loss: 2.6971114493790083e-05
2023-01-22 08:39:31.696591: step: 152/77, loss: 0.08323478698730469
2023-01-22 08:39:32.969140: step: 156/77, loss: 0.000449273589765653
2023-01-22 08:39:34.212482: step: 160/77, loss: 4.991859441361157e-07
2023-01-22 08:39:35.504671: step: 164/77, loss: 0.00018791876209434122
2023-01-22 08:39:36.767763: step: 168/77, loss: 0.0005903139826841652
2023-01-22 08:39:38.066184: step: 172/77, loss: 0.047918688505887985
2023-01-22 08:39:39.344689: step: 176/77, loss: 1.1026830293303647e-07
2023-01-22 08:39:40.619924: step: 180/77, loss: 1.6316491837642388e-06
2023-01-22 08:39:41.903881: step: 184/77, loss: 0.008988398127257824
2023-01-22 08:39:43.169771: step: 188/77, loss: 3.704776463564485e-05
2023-01-22 08:39:44.497613: step: 192/77, loss: 0.00014370733697433025
2023-01-22 08:39:45.754520: step: 196/77, loss: 2.8802598990296246e-06
2023-01-22 08:39:47.062571: step: 200/77, loss: 5.006774586036045e-07
2023-01-22 08:39:48.363486: step: 204/77, loss: 0.00034350191708654165
2023-01-22 08:39:49.655286: step: 208/77, loss: 0.03332750126719475
2023-01-22 08:39:50.958875: step: 212/77, loss: 1.9984458049293607e-05
2023-01-22 08:39:52.224721: step: 216/77, loss: 0.01212351955473423
2023-01-22 08:39:53.507475: step: 220/77, loss: 5.1427905418677256e-05
2023-01-22 08:39:54.755113: step: 224/77, loss: 0.02780834026634693
2023-01-22 08:39:55.992363: step: 228/77, loss: 0.00018175665172748268
2023-01-22 08:39:57.243163: step: 232/77, loss: 0.015692438930273056
2023-01-22 08:39:58.538171: step: 236/77, loss: 0.023305445909500122
2023-01-22 08:39:59.820213: step: 240/77, loss: 7.883200851210859e-06
2023-01-22 08:40:01.098457: step: 244/77, loss: 0.00015500333392992616
2023-01-22 08:40:02.326800: step: 248/77, loss: 0.0010909754782915115
2023-01-22 08:40:03.632226: step: 252/77, loss: 0.00029513833578675985
2023-01-22 08:40:04.952706: step: 256/77, loss: 2.437727061987971e-06
2023-01-22 08:40:06.252746: step: 260/77, loss: 4.5102613512426615e-05
2023-01-22 08:40:07.533049: step: 264/77, loss: 0.00025953652220778167
2023-01-22 08:40:08.813058: step: 268/77, loss: 6.334707450150745e-06
2023-01-22 08:40:10.112807: step: 272/77, loss: 0.02517692744731903
2023-01-22 08:40:11.389772: step: 276/77, loss: 0.00019247032469138503
2023-01-22 08:40:12.720743: step: 280/77, loss: 2.308360672031995e-05
2023-01-22 08:40:13.970151: step: 284/77, loss: 0.02027995139360428
2023-01-22 08:40:15.169969: step: 288/77, loss: 0.0476166270673275
2023-01-22 08:40:16.448815: step: 292/77, loss: 3.230684524169192e-05
2023-01-22 08:40:17.738036: step: 296/77, loss: 1.7493573523097439e-06
2023-01-22 08:40:19.053444: step: 300/77, loss: 8.653674740344286e-06
2023-01-22 08:40:20.297221: step: 304/77, loss: 3.8240621506702155e-05
2023-01-22 08:40:21.574243: step: 308/77, loss: 6.724038030370139e-06
2023-01-22 08:40:22.796557: step: 312/77, loss: 0.0011275878641754389
2023-01-22 08:40:24.061384: step: 316/77, loss: 1.1667386843328131e-06
2023-01-22 08:40:25.346221: step: 320/77, loss: 0.030673200264573097
2023-01-22 08:40:26.606316: step: 324/77, loss: 0.0004541727830655873
2023-01-22 08:40:27.869602: step: 328/77, loss: 0.0002860415552277118
2023-01-22 08:40:29.134224: step: 332/77, loss: 0.00033971594530157745
2023-01-22 08:40:30.427183: step: 336/77, loss: 0.000280650652712211
2023-01-22 08:40:31.745197: step: 340/77, loss: 0.0005106690223328769
2023-01-22 08:40:33.048198: step: 344/77, loss: 3.868105068249861e-06
2023-01-22 08:40:34.352684: step: 348/77, loss: 4.0064624045044184e-05
2023-01-22 08:40:35.655732: step: 352/77, loss: 7.297834963537753e-05
2023-01-22 08:40:36.957855: step: 356/77, loss: 0.0032857412006706
2023-01-22 08:40:38.275127: step: 360/77, loss: 1.8298316035725293e-06
2023-01-22 08:40:39.544741: step: 364/77, loss: 0.000829779717605561
2023-01-22 08:40:40.841762: step: 368/77, loss: 3.9558733988087624e-05
2023-01-22 08:40:42.163231: step: 372/77, loss: 2.1275000108289532e-05
2023-01-22 08:40:43.489439: step: 376/77, loss: 2.1526575437746942e-05
2023-01-22 08:40:44.755945: step: 380/77, loss: 0.00012161017366452143
2023-01-22 08:40:46.076065: step: 384/77, loss: 0.0010571739403530955
2023-01-22 08:40:47.314929: step: 388/77, loss: 0.0003159367188345641
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 24}
Test Chinese: {'template': {'p': 0.961038961038961, 'r': 0.6016260162601627, 'f1': 0.74}, 'slot': {'p': 0.45098039215686275, 'r': 0.02090909090909091, 'f1': 0.03996524761077324}, 'combined': 0.029574283231972198, 'epoch': 24}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 24}
Test Korean: {'template': {'p': 0.9615384615384616, 'r': 0.6097560975609756, 'f1': 0.7462686567164178}, 'slot': {'p': 0.46, 'r': 0.02090909090909091, 'f1': 0.04}, 'combined': 0.029850746268656716, 'epoch': 24}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 24}
Test Russian: {'template': {'p': 0.9615384615384616, 'r': 0.6097560975609756, 'f1': 0.7462686567164178}, 'slot': {'p': 0.46, 'r': 0.02090909090909091, 'f1': 0.04}, 'combined': 0.029850746268656716, 'epoch': 24}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 24}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Sample Russian: {'template': {'p': 1.0, 'r': 0.25, 'f1': 0.4}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 25
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 08:42:22.686772: step: 4/77, loss: 0.005719621200114489
2023-01-22 08:42:23.977937: step: 8/77, loss: 0.008860756643116474
2023-01-22 08:42:25.291153: step: 12/77, loss: 0.0028032902628183365
2023-01-22 08:42:26.577586: step: 16/77, loss: 6.109435730650148e-07
2023-01-22 08:42:27.883127: step: 20/77, loss: 2.298797517141793e-05
2023-01-22 08:42:29.168162: step: 24/77, loss: 6.934415523573989e-06
2023-01-22 08:42:30.435144: step: 28/77, loss: 0.00017443645629100502
2023-01-22 08:42:31.738022: step: 32/77, loss: 3.634882523328997e-05
2023-01-22 08:42:33.011578: step: 36/77, loss: 7.09361211193027e-06
2023-01-22 08:42:34.310423: step: 40/77, loss: 0.016919534653425217
2023-01-22 08:42:35.590022: step: 44/77, loss: 8.22349829832092e-06
2023-01-22 08:42:36.817262: step: 48/77, loss: 0.0002756982285063714
2023-01-22 08:42:38.086384: step: 52/77, loss: 5.055268957221415e-06
2023-01-22 08:42:39.346733: step: 56/77, loss: 0.0003850968205370009
2023-01-22 08:42:40.652495: step: 60/77, loss: 0.0004995691706426442
2023-01-22 08:42:41.932483: step: 64/77, loss: 0.001346847042441368
2023-01-22 08:42:43.189483: step: 68/77, loss: 0.0004229228070471436
2023-01-22 08:42:44.405717: step: 72/77, loss: 0.03281763941049576
2023-01-22 08:42:45.658816: step: 76/77, loss: 0.038519665598869324
2023-01-22 08:42:46.949622: step: 80/77, loss: 0.009992430917918682
2023-01-22 08:42:48.218483: step: 84/77, loss: 0.002286661881953478
2023-01-22 08:42:49.458950: step: 88/77, loss: 0.0002374086616327986
2023-01-22 08:42:50.753262: step: 92/77, loss: 8.106205496005714e-05
2023-01-22 08:42:52.007325: step: 96/77, loss: 0.0010453971335664392
2023-01-22 08:42:53.331912: step: 100/77, loss: 0.0001758149592205882
2023-01-22 08:42:54.619930: step: 104/77, loss: 0.009996388107538223
2023-01-22 08:42:55.932431: step: 108/77, loss: 0.0004022825451102108
2023-01-22 08:42:57.179840: step: 112/77, loss: 0.004816494882106781
2023-01-22 08:42:58.446808: step: 116/77, loss: 0.005425009410828352
2023-01-22 08:42:59.715900: step: 120/77, loss: 2.0414493917542131e-07
2023-01-22 08:43:01.003714: step: 124/77, loss: 9.027479973156005e-05
2023-01-22 08:43:02.240733: step: 128/77, loss: 0.06450998783111572
2023-01-22 08:43:03.539803: step: 132/77, loss: 9.049760410562158e-05
2023-01-22 08:43:04.791225: step: 136/77, loss: 5.903685814701021e-05
2023-01-22 08:43:06.044023: step: 140/77, loss: 4.318053015595069e-06
2023-01-22 08:43:07.313686: step: 144/77, loss: 2.9786574486934114e-06
2023-01-22 08:43:08.625234: step: 148/77, loss: 3.1425793167727534e-06
2023-01-22 08:43:09.904414: step: 152/77, loss: 9.415208478458226e-05
2023-01-22 08:43:11.204943: step: 156/77, loss: 5.3753981774207205e-05
2023-01-22 08:43:12.492293: step: 160/77, loss: 0.0004957958590239286
2023-01-22 08:43:13.768681: step: 164/77, loss: 0.0008796628098934889
2023-01-22 08:43:15.056151: step: 168/77, loss: 0.002826994052156806
2023-01-22 08:43:16.324978: step: 172/77, loss: 0.00016862266056705266
2023-01-22 08:43:17.561491: step: 176/77, loss: 3.725287101019603e-08
2023-01-22 08:43:18.823521: step: 180/77, loss: 0.00611914461478591
2023-01-22 08:43:20.113361: step: 184/77, loss: 0.0009060569573193789
2023-01-22 08:43:21.467624: step: 188/77, loss: 8.879319648258388e-05
2023-01-22 08:43:22.699211: step: 192/77, loss: 0.00410617096349597
2023-01-22 08:43:23.995744: step: 196/77, loss: 0.001179800252430141
2023-01-22 08:43:25.261597: step: 200/77, loss: 1.5466710010514362e-06
2023-01-22 08:43:26.476724: step: 204/77, loss: 0.00045527133625000715
2023-01-22 08:43:27.753538: step: 208/77, loss: 0.006096724420785904
2023-01-22 08:43:29.094607: step: 212/77, loss: 0.05618688464164734
2023-01-22 08:43:30.392295: step: 216/77, loss: 0.0006208279519341886
2023-01-22 08:43:31.702924: step: 220/77, loss: 1.430508973498945e-07
2023-01-22 08:43:33.048783: step: 224/77, loss: 4.76835111840046e-07
2023-01-22 08:43:34.360290: step: 228/77, loss: 0.0012825513258576393
2023-01-22 08:43:35.652059: step: 232/77, loss: 0.00010251560888718814
2023-01-22 08:43:36.920799: step: 236/77, loss: 0.00014983654546085745
2023-01-22 08:43:38.190877: step: 240/77, loss: 0.0007250534254126251
2023-01-22 08:43:39.488202: step: 244/77, loss: 3.565517909009941e-05
2023-01-22 08:43:40.772028: step: 248/77, loss: 3.2824344089021906e-05
2023-01-22 08:43:42.042324: step: 252/77, loss: 0.0004473893204703927
2023-01-22 08:43:43.337439: step: 256/77, loss: 0.0002924882574006915
2023-01-22 08:43:44.579068: step: 260/77, loss: 0.0029194727540016174
2023-01-22 08:43:45.858295: step: 264/77, loss: 0.00955183431506157
2023-01-22 08:43:47.147546: step: 268/77, loss: 0.027585407719016075
2023-01-22 08:43:48.416657: step: 272/77, loss: 1.8800383259076625e-05
2023-01-22 08:43:49.698427: step: 276/77, loss: 0.0003292300389148295
2023-01-22 08:43:50.961727: step: 280/77, loss: 6.807313184253871e-05
2023-01-22 08:43:52.268529: step: 284/77, loss: 0.001798221142962575
2023-01-22 08:43:53.595141: step: 288/77, loss: 0.0032155895605683327
2023-01-22 08:43:54.878085: step: 292/77, loss: 1.2091225471522193e-05
2023-01-22 08:43:56.190413: step: 296/77, loss: 0.00014940323308110237
2023-01-22 08:43:57.464521: step: 300/77, loss: 0.018790228292346
2023-01-22 08:43:58.779740: step: 304/77, loss: 4.5596917175316776e-07
2023-01-22 08:44:00.093341: step: 308/77, loss: 5.038719609729014e-05
2023-01-22 08:44:01.424885: step: 312/77, loss: 0.00027558201691135764
2023-01-22 08:44:02.760302: step: 316/77, loss: 0.0001998369989451021
2023-01-22 08:44:04.051428: step: 320/77, loss: 0.00041272686212323606
2023-01-22 08:44:05.335614: step: 324/77, loss: 6.429352652048692e-06
2023-01-22 08:44:06.631295: step: 328/77, loss: 1.4448265574174002e-05
2023-01-22 08:44:07.928833: step: 332/77, loss: 0.0008989330381155014
2023-01-22 08:44:09.249221: step: 336/77, loss: 0.009158177301287651
2023-01-22 08:44:10.524273: step: 340/77, loss: 9.308809239882976e-06
2023-01-22 08:44:11.823462: step: 344/77, loss: 0.0002032999909715727
2023-01-22 08:44:13.113450: step: 348/77, loss: 8.418882089245017e-07
2023-01-22 08:44:14.433935: step: 352/77, loss: 9.536737621829161e-08
2023-01-22 08:44:15.689074: step: 356/77, loss: 0.0013869872782379389
2023-01-22 08:44:16.974520: step: 360/77, loss: 0.00016957623302005231
2023-01-22 08:44:18.284574: step: 364/77, loss: 0.0033187230583280325
2023-01-22 08:44:19.582231: step: 368/77, loss: 0.00044626800809055567
2023-01-22 08:44:20.864478: step: 372/77, loss: 0.0005619988078251481
2023-01-22 08:44:22.142827: step: 376/77, loss: 4.350573817646364e-06
2023-01-22 08:44:23.407601: step: 380/77, loss: 0.002264243783429265
2023-01-22 08:44:24.668365: step: 384/77, loss: 1.1637284842436202e-06
2023-01-22 08:44:25.982792: step: 388/77, loss: 0.026438845321536064
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.46511627906976744, 'r': 0.03780718336483932, 'f1': 0.06993006993006994}, 'combined': 0.05152741994847258, 'epoch': 25}
Test Chinese: {'template': {'p': 0.9487179487179487, 'r': 0.6016260162601627, 'f1': 0.736318407960199}, 'slot': {'p': 0.5, 'r': 0.02, 'f1': 0.038461538461538464}, 'combined': 0.028319938767699962, 'epoch': 25}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.46511627906976744, 'r': 0.03780718336483932, 'f1': 0.06993006993006994}, 'combined': 0.05152741994847258, 'epoch': 25}
Test Korean: {'template': {'p': 0.9493670886075949, 'r': 0.6097560975609756, 'f1': 0.7425742574257426}, 'slot': {'p': 0.5116279069767442, 'r': 0.02, 'f1': 0.03849518810148731}, 'combined': 0.02858553571892622, 'epoch': 25}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.46511627906976744, 'r': 0.03780718336483932, 'f1': 0.06993006993006994}, 'combined': 0.05152741994847258, 'epoch': 25}
Test Russian: {'template': {'p': 0.9487179487179487, 'r': 0.6016260162601627, 'f1': 0.736318407960199}, 'slot': {'p': 0.4888888888888889, 'r': 0.02, 'f1': 0.03842794759825328}, 'combined': 0.028295205196723804, 'epoch': 25}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 25}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 25}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 26
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 08:46:01.789369: step: 4/77, loss: 7.405794235637586e-07
2023-01-22 08:46:03.060253: step: 8/77, loss: 4.420810910232831e-06
2023-01-22 08:46:04.390209: step: 12/77, loss: 0.009897311218082905
2023-01-22 08:46:05.637682: step: 16/77, loss: 6.879275588289602e-06
2023-01-22 08:46:06.960144: step: 20/77, loss: 0.001125571085140109
2023-01-22 08:46:08.224507: step: 24/77, loss: 5.025583959650248e-05
2023-01-22 08:46:09.554546: step: 28/77, loss: 0.03362608328461647
2023-01-22 08:46:10.835043: step: 32/77, loss: 0.00027511155349202454
2023-01-22 08:46:12.131517: step: 36/77, loss: 0.012906921096146107
2023-01-22 08:46:13.425513: step: 40/77, loss: 6.1619521147804335e-06
2023-01-22 08:46:14.623999: step: 44/77, loss: 1.0552851563261356e-05
2023-01-22 08:46:15.877364: step: 48/77, loss: 0.0006020730943419039
2023-01-22 08:46:17.156901: step: 52/77, loss: 0.005116917658597231
2023-01-22 08:46:18.454779: step: 56/77, loss: 1.1251551768509671e-05
2023-01-22 08:46:19.753779: step: 60/77, loss: 0.024727124720811844
2023-01-22 08:46:21.056560: step: 64/77, loss: 8.761744538787752e-07
2023-01-22 08:46:22.354002: step: 68/77, loss: 0.006382717750966549
2023-01-22 08:46:23.595633: step: 72/77, loss: 0.0001176731166196987
2023-01-22 08:46:24.874577: step: 76/77, loss: 8.199903095373884e-05
2023-01-22 08:46:26.184012: step: 80/77, loss: 0.007674494292587042
2023-01-22 08:46:27.488069: step: 84/77, loss: 0.08472293615341187
2023-01-22 08:46:28.801989: step: 88/77, loss: 1.7702009245113004e-06
2023-01-22 08:46:30.063353: step: 92/77, loss: 0.0014696570578962564
2023-01-22 08:46:31.377484: step: 96/77, loss: 4.095823442185065e-06
2023-01-22 08:46:32.649838: step: 100/77, loss: 5.805840191897005e-05
2023-01-22 08:46:33.908305: step: 104/77, loss: 0.003786920104175806
2023-01-22 08:46:35.173393: step: 108/77, loss: 0.012779447250068188
2023-01-22 08:46:36.444376: step: 112/77, loss: 1.1473886019075508e-07
2023-01-22 08:46:37.718939: step: 116/77, loss: 4.9697860958985984e-05
2023-01-22 08:46:39.035739: step: 120/77, loss: 3.697064676089212e-05
2023-01-22 08:46:40.267339: step: 124/77, loss: 0.0015872609801590443
2023-01-22 08:46:41.530983: step: 128/77, loss: 0.006903848610818386
2023-01-22 08:46:42.806492: step: 132/77, loss: 0.005575467366725206
2023-01-22 08:46:44.097725: step: 136/77, loss: 0.005671120248734951
2023-01-22 08:46:45.398765: step: 140/77, loss: 4.039318810100667e-05
2023-01-22 08:46:46.679688: step: 144/77, loss: 0.00020730840333271772
2023-01-22 08:46:47.968983: step: 148/77, loss: 9.252969903172925e-06
2023-01-22 08:46:49.283876: step: 152/77, loss: 0.0001278579729842022
2023-01-22 08:46:50.609441: step: 156/77, loss: 0.027770182117819786
2023-01-22 08:46:51.888948: step: 160/77, loss: 4.7683688109145805e-08
2023-01-22 08:46:53.173209: step: 164/77, loss: 0.00022923552023712546
2023-01-22 08:46:54.475281: step: 168/77, loss: 2.0663854229496792e-05
2023-01-22 08:46:55.798652: step: 172/77, loss: 4.5862248953199014e-05
2023-01-22 08:46:57.092565: step: 176/77, loss: 0.0016720297280699015
2023-01-22 08:46:58.355111: step: 180/77, loss: 0.00010752508387668058
2023-01-22 08:46:59.693878: step: 184/77, loss: 0.0006299956585280597
2023-01-22 08:47:00.981782: step: 188/77, loss: 0.011298703029751778
2023-01-22 08:47:02.267033: step: 192/77, loss: 6.590948032680899e-05
2023-01-22 08:47:03.539975: step: 196/77, loss: 5.185305781196803e-06
2023-01-22 08:47:04.826975: step: 200/77, loss: 2.2649717834610783e-07
2023-01-22 08:47:06.130317: step: 204/77, loss: 0.0001983733382076025
2023-01-22 08:47:07.441152: step: 208/77, loss: 3.112400372629054e-05
2023-01-22 08:47:08.711082: step: 212/77, loss: 2.7714126190403476e-05
2023-01-22 08:47:10.083914: step: 216/77, loss: 0.00013845518697053194
2023-01-22 08:47:11.410263: step: 220/77, loss: 3.977232699980959e-05
2023-01-22 08:47:12.714311: step: 224/77, loss: 0.000929908303078264
2023-01-22 08:47:14.020387: step: 228/77, loss: 1.7579246559762396e-05
2023-01-22 08:47:15.318024: step: 232/77, loss: 0.0007625438156537712
2023-01-22 08:47:16.626862: step: 236/77, loss: 4.9652739107841626e-05
2023-01-22 08:47:17.938443: step: 240/77, loss: 1.2576102790262667e-06
2023-01-22 08:47:19.248316: step: 244/77, loss: 8.551467908546329e-05
2023-01-22 08:47:20.513457: step: 248/77, loss: 0.000155415793415159
2023-01-22 08:47:21.828629: step: 252/77, loss: 7.673896789128776e-07
2023-01-22 08:47:23.103339: step: 256/77, loss: 1.6112244338728487e-05
2023-01-22 08:47:24.427170: step: 260/77, loss: 0.020630180835723877
2023-01-22 08:47:25.698616: step: 264/77, loss: 0.0011570448987185955
2023-01-22 08:47:26.944183: step: 268/77, loss: 6.015104190737475e-06
2023-01-22 08:47:28.226889: step: 272/77, loss: 3.4272662929879516e-08
2023-01-22 08:47:29.524162: step: 276/77, loss: 0.018049897626042366
2023-01-22 08:47:30.849676: step: 280/77, loss: 0.00012221011274959892
2023-01-22 08:47:32.134601: step: 284/77, loss: 0.009114380925893784
2023-01-22 08:47:33.374058: step: 288/77, loss: 0.0005977398250252008
2023-01-22 08:47:34.665143: step: 292/77, loss: 0.002121040364727378
2023-01-22 08:47:35.916367: step: 296/77, loss: 1.7078427845262922e-05
2023-01-22 08:47:37.219232: step: 300/77, loss: 1.7234993720194325e-05
2023-01-22 08:47:38.561114: step: 304/77, loss: 2.008646333706565e-06
2023-01-22 08:47:39.907921: step: 308/77, loss: 1.3609464986075182e-05
2023-01-22 08:47:41.236781: step: 312/77, loss: 1.9376695490791462e-05
2023-01-22 08:47:42.506718: step: 316/77, loss: 0.0002871832111850381
2023-01-22 08:47:43.790223: step: 320/77, loss: 8.973329386208206e-06
2023-01-22 08:47:45.100467: step: 324/77, loss: 0.0001281930017285049
2023-01-22 08:47:46.392584: step: 328/77, loss: 0.006611789111047983
2023-01-22 08:47:47.664572: step: 332/77, loss: 6.0470832977443933e-05
2023-01-22 08:47:48.987977: step: 336/77, loss: 0.00381635595113039
2023-01-22 08:47:50.311990: step: 340/77, loss: 1.8114980775862932e-05
2023-01-22 08:47:51.610067: step: 344/77, loss: 0.0001864713995018974
2023-01-22 08:47:52.887634: step: 348/77, loss: 0.017800893634557724
2023-01-22 08:47:54.217602: step: 352/77, loss: 0.008395765908062458
2023-01-22 08:47:55.484497: step: 356/77, loss: 1.6391246049352048e-07
2023-01-22 08:47:56.761328: step: 360/77, loss: 0.0011608715867623687
2023-01-22 08:47:58.083785: step: 364/77, loss: 2.5806618850765517e-06
2023-01-22 08:47:59.382069: step: 368/77, loss: 0.00028230599127709866
2023-01-22 08:48:00.690967: step: 372/77, loss: 6.524189757328713e-06
2023-01-22 08:48:01.964173: step: 376/77, loss: 5.015195711166598e-06
2023-01-22 08:48:03.229803: step: 380/77, loss: 0.00017462043615523726
2023-01-22 08:48:04.531220: step: 384/77, loss: 2.010021489695646e-06
2023-01-22 08:48:05.835408: step: 388/77, loss: 9.521669562673196e-05
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 26}
Test Chinese: {'template': {'p': 0.9487179487179487, 'r': 0.6016260162601627, 'f1': 0.736318407960199}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.02955553819037448, 'epoch': 26}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 26}
Test Korean: {'template': {'p': 0.9493670886075949, 'r': 0.6097560975609756, 'f1': 0.7425742574257426}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.02978065897261042, 'epoch': 26}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 26}
Test Russian: {'template': {'p': 0.9487179487179487, 'r': 0.6016260162601627, 'f1': 0.736318407960199}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.02952977050232707, 'epoch': 26}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 26}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Sample Russian: {'template': {'p': 1.0, 'r': 0.25, 'f1': 0.4}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 27
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 08:49:42.204409: step: 4/77, loss: 4.3786039896076545e-05
2023-01-22 08:49:43.514557: step: 8/77, loss: 1.3262005893466267e-07
2023-01-22 08:49:44.825300: step: 12/77, loss: 0.004400265868753195
2023-01-22 08:49:46.043937: step: 16/77, loss: 1.0698581718315836e-06
2023-01-22 08:49:47.350285: step: 20/77, loss: 0.023978853598237038
2023-01-22 08:49:48.616657: step: 24/77, loss: 4.8583251555101015e-06
2023-01-22 08:49:49.878423: step: 28/77, loss: 0.03092852607369423
2023-01-22 08:49:51.153380: step: 32/77, loss: 0.0003409860364627093
2023-01-22 08:49:52.454080: step: 36/77, loss: 6.979777390370145e-05
2023-01-22 08:49:53.712970: step: 40/77, loss: 0.0005804693792015314
2023-01-22 08:49:55.036055: step: 44/77, loss: 0.011256477795541286
2023-01-22 08:49:56.291214: step: 48/77, loss: 1.1070699656556826e-05
2023-01-22 08:49:57.589635: step: 52/77, loss: 3.316633183203521e-06
2023-01-22 08:49:58.852743: step: 56/77, loss: 3.561252924555447e-06
2023-01-22 08:50:00.084386: step: 60/77, loss: 9.22357571653265e-07
2023-01-22 08:50:01.380555: step: 64/77, loss: 1.6862717529875226e-05
2023-01-22 08:50:02.661693: step: 68/77, loss: 0.00019232039630878717
2023-01-22 08:50:03.936329: step: 72/77, loss: 0.016592321917414665
2023-01-22 08:50:05.203767: step: 76/77, loss: 1.5529300071648322e-05
2023-01-22 08:50:06.525728: step: 80/77, loss: 1.6067247997852974e-05
2023-01-22 08:50:07.774602: step: 84/77, loss: 8.976113167591393e-05
2023-01-22 08:50:09.071093: step: 88/77, loss: 0.04106712341308594
2023-01-22 08:50:10.355501: step: 92/77, loss: 1.9371507065102378e-08
2023-01-22 08:50:11.691857: step: 96/77, loss: 2.0861591565335402e-07
2023-01-22 08:50:12.946040: step: 100/77, loss: 2.2351732908987287e-08
2023-01-22 08:50:14.241921: step: 104/77, loss: 0.0007628971361555159
2023-01-22 08:50:15.485762: step: 108/77, loss: 2.9802318390892424e-09
2023-01-22 08:50:16.808003: step: 112/77, loss: 2.0861618210687993e-08
2023-01-22 08:50:18.107019: step: 116/77, loss: 0.0005382683593779802
2023-01-22 08:50:19.418066: step: 120/77, loss: 2.1457547916270414e-07
2023-01-22 08:50:20.723590: step: 124/77, loss: 3.502124309306964e-05
2023-01-22 08:50:22.076117: step: 128/77, loss: 3.145249866065569e-05
2023-01-22 08:50:23.315951: step: 132/77, loss: 0.00019145975238643587
2023-01-22 08:50:24.610622: step: 136/77, loss: 0.0002411496825516224
2023-01-22 08:50:25.901420: step: 140/77, loss: 0.0012163245119154453
2023-01-22 08:50:27.156201: step: 144/77, loss: 0.00010317091800970957
2023-01-22 08:50:28.468066: step: 148/77, loss: 4.620007985067787e-06
2023-01-22 08:50:29.756163: step: 152/77, loss: 8.60757427290082e-05
2023-01-22 08:50:31.020817: step: 156/77, loss: 6.705515431804088e-08
2023-01-22 08:50:32.301495: step: 160/77, loss: 0.00013355020200833678
2023-01-22 08:50:33.618890: step: 164/77, loss: 0.005990986712276936
2023-01-22 08:50:34.893352: step: 168/77, loss: 0.00027787365252152085
2023-01-22 08:50:36.124132: step: 172/77, loss: 0.04725373163819313
2023-01-22 08:50:37.400863: step: 176/77, loss: 7.853271381463856e-05
2023-01-22 08:50:38.708780: step: 180/77, loss: 0.00018676927720662206
2023-01-22 08:50:39.930412: step: 184/77, loss: 0.006754858419299126
2023-01-22 08:50:41.242366: step: 188/77, loss: 8.532601350452751e-05
2023-01-22 08:50:42.517720: step: 192/77, loss: 0.0007004007347859442
2023-01-22 08:50:43.806485: step: 196/77, loss: 0.0011839126236736774
2023-01-22 08:50:45.070401: step: 200/77, loss: 0.0004985693376511335
2023-01-22 08:50:46.334920: step: 204/77, loss: 1.244201371264353e-06
2023-01-22 08:50:47.609360: step: 208/77, loss: 0.08877816051244736
2023-01-22 08:50:48.845635: step: 212/77, loss: 1.2874467074652785e-06
2023-01-22 08:50:50.168457: step: 216/77, loss: 6.705516852889559e-08
2023-01-22 08:50:51.437744: step: 220/77, loss: 1.627982419449836e-05
2023-01-22 08:50:52.735358: step: 224/77, loss: 6.169013317958161e-07
2023-01-22 08:50:54.018813: step: 228/77, loss: 5.7242756156483665e-05
2023-01-22 08:50:55.286662: step: 232/77, loss: 0.00034215141204185784
2023-01-22 08:50:56.546358: step: 236/77, loss: 0.0015011318027973175
2023-01-22 08:50:57.870410: step: 240/77, loss: 0.0012336316285654902
2023-01-22 08:50:59.154473: step: 244/77, loss: 0.00022003508638590574
2023-01-22 08:51:00.405855: step: 248/77, loss: 0.01599096693098545
2023-01-22 08:51:01.680428: step: 252/77, loss: 9.920450247591361e-05
2023-01-22 08:51:02.968380: step: 256/77, loss: 0.00031245272839441895
2023-01-22 08:51:04.265470: step: 260/77, loss: 1.2031691767333541e-05
2023-01-22 08:51:05.549489: step: 264/77, loss: 9.238696208058172e-08
2023-01-22 08:51:06.839393: step: 268/77, loss: 6.817108805989847e-05
2023-01-22 08:51:08.148512: step: 272/77, loss: 9.894110917230137e-07
2023-01-22 08:51:09.475172: step: 276/77, loss: 0.0005339889321476221
2023-01-22 08:51:10.717444: step: 280/77, loss: 0.00012003527081105858
2023-01-22 08:51:11.987275: step: 284/77, loss: 1.629951293580234e-05
2023-01-22 08:51:13.300460: step: 288/77, loss: 7.010930858086795e-05
2023-01-22 08:51:14.639858: step: 292/77, loss: 1.5854463981668232e-06
2023-01-22 08:51:15.912409: step: 296/77, loss: 1.568728475831449e-05
2023-01-22 08:51:17.245670: step: 300/77, loss: 0.003171185264363885
2023-01-22 08:51:18.604417: step: 304/77, loss: 4.264489234628854e-06
2023-01-22 08:51:19.870486: step: 308/77, loss: 0.007752659730613232
2023-01-22 08:51:21.182725: step: 312/77, loss: 4.3374842789489776e-05
2023-01-22 08:51:22.481863: step: 316/77, loss: 0.00010408271919004619
2023-01-22 08:51:23.805695: step: 320/77, loss: 0.0005090486956760287
2023-01-22 08:51:25.058679: step: 324/77, loss: 9.227226109942421e-05
2023-01-22 08:51:26.293743: step: 328/77, loss: 0.003174896351993084
2023-01-22 08:51:27.564767: step: 332/77, loss: 0.0017001423984766006
2023-01-22 08:51:28.833021: step: 336/77, loss: 0.00042848309385590255
2023-01-22 08:51:30.150559: step: 340/77, loss: 0.0005391308222897351
2023-01-22 08:51:31.419992: step: 344/77, loss: 0.0006425658357329667
2023-01-22 08:51:32.768944: step: 348/77, loss: 1.4663381080026738e-05
2023-01-22 08:51:34.065453: step: 352/77, loss: 5.437660729512572e-05
2023-01-22 08:51:35.404663: step: 356/77, loss: 0.14871054887771606
2023-01-22 08:51:36.710997: step: 360/77, loss: 2.2351734685344127e-08
2023-01-22 08:51:37.992204: step: 364/77, loss: 0.0003183669177815318
2023-01-22 08:51:39.365182: step: 368/77, loss: 2.8474557893787278e-06
2023-01-22 08:51:40.647338: step: 372/77, loss: 8.405734115513042e-05
2023-01-22 08:51:41.972802: step: 376/77, loss: 3.2782395464892033e-07
2023-01-22 08:51:43.261133: step: 380/77, loss: 3.4272460425199824e-07
2023-01-22 08:51:44.592602: step: 384/77, loss: 4.10609118262073e-06
2023-01-22 08:51:45.900529: step: 388/77, loss: 0.018402086570858955
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 27}
Test Chinese: {'template': {'p': 0.9518072289156626, 'r': 0.6422764227642277, 'f1': 0.7669902912621358}, 'slot': {'p': 0.5, 'r': 0.022727272727272728, 'f1': 0.04347826086956522}, 'combined': 0.03334740396791895, 'epoch': 27}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.48717948717948717, 'r': 0.035916824196597356, 'f1': 0.06690140845070423}, 'combined': 0.04929577464788733, 'epoch': 27}
Test Korean: {'template': {'p': 0.9634146341463414, 'r': 0.6422764227642277, 'f1': 0.7707317073170733}, 'slot': {'p': 0.5102040816326531, 'r': 0.022727272727272728, 'f1': 0.043516100957354226}, 'combined': 0.03353923878664375, 'epoch': 27}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 27}
Test Russian: {'template': {'p': 0.9634146341463414, 'r': 0.6422764227642277, 'f1': 0.7707317073170733}, 'slot': {'p': 0.5102040816326531, 'r': 0.022727272727272728, 'f1': 0.043516100957354226}, 'combined': 0.03353923878664375, 'epoch': 27}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 27}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Sample Russian: {'template': {'p': 1.0, 'r': 0.25, 'f1': 0.4}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 28
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 08:53:26.457994: step: 4/77, loss: 1.582411414347007e-06
2023-01-22 08:53:27.747116: step: 8/77, loss: 0.00010717161057982594
2023-01-22 08:53:29.018612: step: 12/77, loss: 1.4007048321218463e-07
2023-01-22 08:53:30.336842: step: 16/77, loss: 8.115675154840574e-05
2023-01-22 08:53:31.637443: step: 20/77, loss: 0.03191979229450226
2023-01-22 08:53:32.964779: step: 24/77, loss: 1.1622893225649022e-07
2023-01-22 08:53:34.337035: step: 28/77, loss: 3.9084603486116976e-05
2023-01-22 08:53:35.609557: step: 32/77, loss: 0.002637272235006094
2023-01-22 08:53:36.886311: step: 36/77, loss: 0.05554957687854767
2023-01-22 08:53:38.190111: step: 40/77, loss: 3.560824188753031e-05
2023-01-22 08:53:39.452662: step: 44/77, loss: 1.0132781369520671e-07
2023-01-22 08:53:40.745190: step: 48/77, loss: 0.000232343387324363
2023-01-22 08:53:41.989383: step: 52/77, loss: 1.0445479574627825e-06
2023-01-22 08:53:43.256753: step: 56/77, loss: 1.3514809324988164e-06
2023-01-22 08:53:44.535079: step: 60/77, loss: 1.9591614545788616e-05
2023-01-22 08:53:45.835840: step: 64/77, loss: 0.04506542533636093
2023-01-22 08:53:47.185540: step: 68/77, loss: 4.386712680570781e-05
2023-01-22 08:53:48.465556: step: 72/77, loss: 7.815002390998416e-06
2023-01-22 08:53:49.794323: step: 76/77, loss: 3.305016434751451e-05
2023-01-22 08:53:51.081381: step: 80/77, loss: 0.0001534569018986076
2023-01-22 08:53:52.415492: step: 84/77, loss: 0.0012685380643233657
2023-01-22 08:53:53.680794: step: 88/77, loss: 7.361089160440315e-07
2023-01-22 08:53:54.996876: step: 92/77, loss: 2.9308637294889195e-06
2023-01-22 08:53:56.313193: step: 96/77, loss: 0.0008253856794908643
2023-01-22 08:53:57.570142: step: 100/77, loss: 0.00027290164143778384
2023-01-22 08:53:58.840351: step: 104/77, loss: 0.0004043147200718522
2023-01-22 08:54:00.143504: step: 108/77, loss: 0.00016128386778291315
2023-01-22 08:54:01.433743: step: 112/77, loss: 0.005868277978152037
2023-01-22 08:54:02.733202: step: 116/77, loss: 1.4603088516196294e-07
2023-01-22 08:54:04.018145: step: 120/77, loss: 0.0019091747235506773
2023-01-22 08:54:05.333408: step: 124/77, loss: 0.011760505847632885
2023-01-22 08:54:06.661415: step: 128/77, loss: 0.00010481792560312897
2023-01-22 08:54:07.969672: step: 132/77, loss: 1.921913462865632e-05
2023-01-22 08:54:09.271435: step: 136/77, loss: 2.227662662335206e-06
2023-01-22 08:54:10.573811: step: 140/77, loss: 5.334582056093495e-07
2023-01-22 08:54:11.929592: step: 144/77, loss: 3.588026402212563e-06
2023-01-22 08:54:13.240868: step: 148/77, loss: 0.00016857915034051985
2023-01-22 08:54:14.538831: step: 152/77, loss: 0.031219307333230972
2023-01-22 08:54:15.868136: step: 156/77, loss: 0.0020155508536845446
2023-01-22 08:54:17.146287: step: 160/77, loss: 1.321755553362891e-05
2023-01-22 08:54:18.399619: step: 164/77, loss: 0.018532564863562584
2023-01-22 08:54:19.712076: step: 168/77, loss: 1.5903380699455738e-05
2023-01-22 08:54:21.033446: step: 172/77, loss: 0.024859033524990082
2023-01-22 08:54:22.328128: step: 176/77, loss: 2.0681964087998495e-06
2023-01-22 08:54:23.575537: step: 180/77, loss: 2.6700056423578644e-06
2023-01-22 08:54:24.870709: step: 184/77, loss: 1.8923403786175186e-06
2023-01-22 08:54:26.152295: step: 188/77, loss: 1.3589453828899423e-06
2023-01-22 08:54:27.386309: step: 192/77, loss: 0.04262559115886688
2023-01-22 08:54:28.720428: step: 196/77, loss: 8.77968250279082e-06
2023-01-22 08:54:29.987568: step: 200/77, loss: 0.0001077373162843287
2023-01-22 08:54:31.308588: step: 204/77, loss: 0.00020571955246850848
2023-01-22 08:54:32.620863: step: 208/77, loss: 0.0005280431942082942
2023-01-22 08:54:33.944431: step: 212/77, loss: 1.048697049554903e-05
2023-01-22 08:54:35.238460: step: 216/77, loss: 4.216946035739966e-05
2023-01-22 08:54:36.483759: step: 220/77, loss: 4.079658083355753e-06
2023-01-22 08:54:37.754166: step: 224/77, loss: 0.0004498214984778315
2023-01-22 08:54:39.054122: step: 228/77, loss: 0.0011945064179599285
2023-01-22 08:54:40.325417: step: 232/77, loss: 8.898941814550199e-06
2023-01-22 08:54:41.603818: step: 236/77, loss: 4.5448163632499927e-07
2023-01-22 08:54:42.873506: step: 240/77, loss: 7.256832645907707e-07
2023-01-22 08:54:44.161338: step: 244/77, loss: 0.009154018014669418
2023-01-22 08:54:45.456414: step: 248/77, loss: 9.619673801353201e-05
2023-01-22 08:54:46.753069: step: 252/77, loss: 0.00031977289472706616
2023-01-22 08:54:48.068062: step: 256/77, loss: 0.050523921847343445
2023-01-22 08:54:49.378862: step: 260/77, loss: 1.8461626041244017e-06
2023-01-22 08:54:50.668886: step: 264/77, loss: 9.738103835843503e-05
2023-01-22 08:54:51.933319: step: 268/77, loss: 1.4901155864777138e-08
2023-01-22 08:54:53.234945: step: 272/77, loss: 1.162021635536803e-05
2023-01-22 08:54:54.510439: step: 276/77, loss: 0.0044382489286363125
2023-01-22 08:54:55.757847: step: 280/77, loss: 2.4317955649166834e-06
2023-01-22 08:54:57.072121: step: 284/77, loss: 1.6182344779736013e-06
2023-01-22 08:54:58.397780: step: 288/77, loss: 3.710630699060857e-05
2023-01-22 08:54:59.729024: step: 292/77, loss: 2.1636074052366894e-06
2023-01-22 08:55:01.039177: step: 296/77, loss: 0.004715841729193926
2023-01-22 08:55:02.322871: step: 300/77, loss: 9.745041325004422e-07
2023-01-22 08:55:03.569063: step: 304/77, loss: 0.00031040236353874207
2023-01-22 08:55:04.842372: step: 308/77, loss: 2.852852048818022e-05
2023-01-22 08:55:06.081976: step: 312/77, loss: 0.0031233031768351793
2023-01-22 08:55:07.339446: step: 316/77, loss: 0.0001433442666893825
2023-01-22 08:55:08.653140: step: 320/77, loss: 0.006575982552021742
2023-01-22 08:55:09.957717: step: 324/77, loss: 7.856477168388665e-06
2023-01-22 08:55:11.242991: step: 328/77, loss: 0.00030488992342725396
2023-01-22 08:55:12.512899: step: 332/77, loss: 2.0770582978002494e-06
2023-01-22 08:55:13.757581: step: 336/77, loss: 1.2665948645462777e-07
2023-01-22 08:55:15.048561: step: 340/77, loss: 3.27336965710856e-06
2023-01-22 08:55:16.294042: step: 344/77, loss: 4.828689634450711e-05
2023-01-22 08:55:17.577532: step: 348/77, loss: 0.037822216749191284
2023-01-22 08:55:18.815654: step: 352/77, loss: 7.748373172944412e-05
2023-01-22 08:55:20.074072: step: 356/77, loss: 1.3292006769916043e-05
2023-01-22 08:55:21.393362: step: 360/77, loss: 0.00017053502961061895
2023-01-22 08:55:22.668052: step: 364/77, loss: 1.1916748917428777e-05
2023-01-22 08:55:23.978220: step: 368/77, loss: 0.019462842494249344
2023-01-22 08:55:25.272977: step: 372/77, loss: 4.768004146171734e-06
2023-01-22 08:55:26.545184: step: 376/77, loss: 1.578027513460256e-05
2023-01-22 08:55:27.825812: step: 380/77, loss: 0.011081244796514511
2023-01-22 08:55:29.124304: step: 384/77, loss: 0.052583497017621994
2023-01-22 08:55:30.414640: step: 388/77, loss: 3.352726878347312e-07
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 28}
Test Chinese: {'template': {'p': 0.9743589743589743, 'r': 0.6178861788617886, 'f1': 0.7562189054726368}, 'slot': {'p': 0.5609756097560976, 'r': 0.02090909090909091, 'f1': 0.040315512708150744}, 'combined': 0.030487352893725936, 'epoch': 28}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.48717948717948717, 'r': 0.035916824196597356, 'f1': 0.06690140845070423}, 'combined': 0.04839676356008391, 'epoch': 28}
Test Korean: {'template': {'p': 0.9743589743589743, 'r': 0.6178861788617886, 'f1': 0.7562189054726368}, 'slot': {'p': 0.5609756097560976, 'r': 0.02090909090909091, 'f1': 0.040315512708150744}, 'combined': 0.030487352893725936, 'epoch': 28}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.48717948717948717, 'r': 0.035916824196597356, 'f1': 0.06690140845070423}, 'combined': 0.04839676356008391, 'epoch': 28}
Test Russian: {'template': {'p': 0.9743589743589743, 'r': 0.6178861788617886, 'f1': 0.7562189054726368}, 'slot': {'p': 0.5609756097560976, 'r': 0.02090909090909091, 'f1': 0.040315512708150744}, 'combined': 0.030487352893725936, 'epoch': 28}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 28}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Sample Russian: {'template': {'p': 1.0, 'r': 0.25, 'f1': 0.4}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}
******************************
Epoch: 29
command: python train.py --model_name template --xlmr_model_name xlm-roberta-large --batch_size 10 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 2e-4
2023-01-22 08:57:08.570007: step: 4/77, loss: 3.144855872960761e-05
2023-01-22 08:57:09.845615: step: 8/77, loss: 5.751747949034325e-07
2023-01-22 08:57:11.123139: step: 12/77, loss: 8.017163054319099e-05
2023-01-22 08:57:12.402249: step: 16/77, loss: 0.022102270275354385
2023-01-22 08:57:13.659973: step: 20/77, loss: 2.7567057259147987e-07
2023-01-22 08:57:14.928175: step: 24/77, loss: 4.811163307749666e-06
2023-01-22 08:57:16.179808: step: 28/77, loss: 8.746854973651352e-07
2023-01-22 08:57:17.492487: step: 32/77, loss: 6.541539505633409e-07
2023-01-22 08:57:18.796564: step: 36/77, loss: 7.522347732447088e-05
2023-01-22 08:57:20.065519: step: 40/77, loss: 0.0008213004330173135
2023-01-22 08:57:21.333708: step: 44/77, loss: 2.7119872925140953e-07
2023-01-22 08:57:22.630808: step: 48/77, loss: 3.8976580981398e-05
2023-01-22 08:57:23.867477: step: 52/77, loss: 0.024472558870911598
2023-01-22 08:57:25.143472: step: 56/77, loss: 0.002236069878563285
2023-01-22 08:57:26.455565: step: 60/77, loss: 0.0008119684061966836
2023-01-22 08:57:27.730387: step: 64/77, loss: 0.00016473043069709092
2023-01-22 08:57:29.036513: step: 68/77, loss: 1.0659737199603114e-05
2023-01-22 08:57:30.308768: step: 72/77, loss: 6.331157783279195e-05
2023-01-22 08:57:31.650761: step: 76/77, loss: 8.398948921239935e-06
2023-01-22 08:57:32.961883: step: 80/77, loss: 1.9222457581236085e-07
2023-01-22 08:57:34.232432: step: 84/77, loss: 0.00012843337026424706
2023-01-22 08:57:35.563091: step: 88/77, loss: 2.4824919819366187e-05
2023-01-22 08:57:36.885953: step: 92/77, loss: 7.043376172077842e-06
2023-01-22 08:57:38.250172: step: 96/77, loss: 0.002021679887548089
2023-01-22 08:57:39.564795: step: 100/77, loss: 4.277397238183767e-06
2023-01-22 08:57:40.838448: step: 104/77, loss: 0.01951354369521141
2023-01-22 08:57:42.137515: step: 108/77, loss: 0.0237126424908638
2023-01-22 08:57:43.396720: step: 112/77, loss: 2.9460461519192904e-05
2023-01-22 08:57:44.707864: step: 116/77, loss: 4.008111318398733e-06
2023-01-22 08:57:46.044425: step: 120/77, loss: 0.00021640595514327288
2023-01-22 08:57:47.374526: step: 124/77, loss: 0.013219022192060947
2023-01-22 08:57:48.685543: step: 128/77, loss: 1.1595335308811627e-05
2023-01-22 08:57:49.979990: step: 132/77, loss: 0.00018398706743028015
2023-01-22 08:57:51.322424: step: 136/77, loss: 4.208624886814505e-05
2023-01-22 08:57:52.681441: step: 140/77, loss: 7.261715381901013e-06
2023-01-22 08:57:54.038523: step: 144/77, loss: 0.02468251623213291
2023-01-22 08:57:55.334149: step: 148/77, loss: 4.6508765080943704e-05
2023-01-22 08:57:56.617106: step: 152/77, loss: 1.3247890819911845e-05
2023-01-22 08:57:57.904955: step: 156/77, loss: 2.968638546008151e-05
2023-01-22 08:57:59.199415: step: 160/77, loss: 0.0024238319601863623
2023-01-22 08:58:00.483720: step: 164/77, loss: 8.205627636925783e-06
2023-01-22 08:58:01.764687: step: 168/77, loss: 0.0014939033426344395
2023-01-22 08:58:03.051005: step: 172/77, loss: 9.685743407317204e-08
2023-01-22 08:58:04.352245: step: 176/77, loss: 1.5675155964345322e-06
2023-01-22 08:58:05.635184: step: 180/77, loss: 2.3959746613400057e-06
2023-01-22 08:58:06.878798: step: 184/77, loss: 0.00026503464323468506
2023-01-22 08:58:08.180933: step: 188/77, loss: 0.00022445156355388463
2023-01-22 08:58:09.516821: step: 192/77, loss: 7.375857649094542e-07
2023-01-22 08:58:10.827129: step: 196/77, loss: 2.0861621763401672e-08
2023-01-22 08:58:12.115694: step: 200/77, loss: 0.0003767440211959183
2023-01-22 08:58:13.338135: step: 204/77, loss: 7.617295341333374e-05
2023-01-22 08:58:14.666906: step: 208/77, loss: 0.00012021034490317106
2023-01-22 08:58:15.977528: step: 212/77, loss: 0.005869630724191666
2023-01-22 08:58:17.254250: step: 216/77, loss: 0.00020114541985094547
2023-01-22 08:58:18.546139: step: 220/77, loss: 0.004399897996336222
2023-01-22 08:58:19.847035: step: 224/77, loss: 0.0016715697711333632
2023-01-22 08:58:21.146112: step: 228/77, loss: 0.00018241455836687237
2023-01-22 08:58:22.410040: step: 232/77, loss: 0.0009146218653768301
2023-01-22 08:58:23.710162: step: 236/77, loss: 0.0018498735735192895
2023-01-22 08:58:24.917572: step: 240/77, loss: 0.00022577299387194216
2023-01-22 08:58:26.239081: step: 244/77, loss: 0.05294421315193176
2023-01-22 08:58:27.580575: step: 248/77, loss: 0.0485006682574749
2023-01-22 08:58:28.848035: step: 252/77, loss: 5.894068635825533e-06
2023-01-22 08:58:30.094808: step: 256/77, loss: 1.2963988638148294e-07
2023-01-22 08:58:31.414051: step: 260/77, loss: 5.3644139796915624e-08
2023-01-22 08:58:32.642233: step: 264/77, loss: 0.002035744721069932
2023-01-22 08:58:33.940568: step: 268/77, loss: 0.017132868990302086
2023-01-22 08:58:35.209421: step: 272/77, loss: 3.955773718189448e-05
2023-01-22 08:58:36.488845: step: 276/77, loss: 3.992898200522177e-06
2023-01-22 08:58:37.761690: step: 280/77, loss: 0.0005716330488212407
2023-01-22 08:58:39.019771: step: 284/77, loss: 4.1489121940685436e-05
2023-01-22 08:58:40.308083: step: 288/77, loss: 5.015826172893867e-05
2023-01-22 08:58:41.643766: step: 292/77, loss: 9.168793621938676e-05
2023-01-22 08:58:42.933809: step: 296/77, loss: 1.1026848767414776e-07
2023-01-22 08:58:44.245177: step: 300/77, loss: 0.002865537302568555
2023-01-22 08:58:45.490568: step: 304/77, loss: 0.0002901027328334749
2023-01-22 08:58:46.752038: step: 308/77, loss: 0.0021394614595919847
2023-01-22 08:58:48.044567: step: 312/77, loss: 4.060235369252041e-06
2023-01-22 08:58:49.380721: step: 316/77, loss: 0.0009134943829849362
2023-01-22 08:58:50.695270: step: 320/77, loss: 1.3618976026918972e-06
2023-01-22 08:58:51.998339: step: 324/77, loss: 0.00023269267694558948
2023-01-22 08:58:53.287694: step: 328/77, loss: 9.249313734471798e-05
2023-01-22 08:58:54.597454: step: 332/77, loss: 7.471351273125038e-05
2023-01-22 08:58:55.892156: step: 336/77, loss: 0.00022001775505486876
2023-01-22 08:58:57.164240: step: 340/77, loss: 0.00011256830475758761
2023-01-22 08:58:58.449742: step: 344/77, loss: 4.7683684556432127e-08
2023-01-22 08:58:59.712790: step: 348/77, loss: 9.553597010381054e-06
2023-01-22 08:59:01.009333: step: 352/77, loss: 0.002149000996723771
2023-01-22 08:59:02.342711: step: 356/77, loss: 0.00040330199408344924
2023-01-22 08:59:03.648237: step: 360/77, loss: 4.79812626963394e-07
2023-01-22 08:59:04.990332: step: 364/77, loss: 1.3858060299298813e-07
2023-01-22 08:59:06.291528: step: 368/77, loss: 0.023484427481889725
2023-01-22 08:59:07.582394: step: 372/77, loss: 0.02371416613459587
2023-01-22 08:59:08.892694: step: 376/77, loss: 9.029912462210632e-07
2023-01-22 08:59:10.189678: step: 380/77, loss: 1.163185606856132e-05
2023-01-22 08:59:11.461104: step: 384/77, loss: 6.451639819715638e-06
2023-01-22 08:59:12.739359: step: 388/77, loss: 5.81145016553819e-08
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.55, 'f1': 0.7096774193548387}, 'slot': {'p': 0.5, 'r': 0.034026465028355386, 'f1': 0.06371681415929203}, 'combined': 0.04521838424207822, 'epoch': 29}
Test Chinese: {'template': {'p': 0.9605263157894737, 'r': 0.5934959349593496, 'f1': 0.7336683417085428}, 'slot': {'p': 0.575, 'r': 0.02090909090909091, 'f1': 0.04035087719298246}, 'combined': 0.029604161156660497, 'epoch': 29}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 29}
Test Korean: {'template': {'p': 0.961038961038961, 'r': 0.6016260162601627, 'f1': 0.74}, 'slot': {'p': 0.5641025641025641, 'r': 0.02, 'f1': 0.038630377524143986}, 'combined': 0.028586479367866548, 'epoch': 29}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5666666666666667, 'f1': 0.7234042553191489}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.048482119404105226, 'epoch': 29}
Test Russian: {'template': {'p': 0.961038961038961, 'r': 0.6016260162601627, 'f1': 0.74}, 'slot': {'p': 0.575, 'r': 0.02090909090909091, 'f1': 0.04035087719298246}, 'combined': 0.029859649122807017, 'epoch': 29}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 29}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Sample Russian: {'template': {'p': 1.0, 'r': 0.25, 'f1': 0.4}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Chinese: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.5, 'r': 0.02090909090909091, 'f1': 0.04013961605584642}, 'combined': 0.031113003832761343, 'epoch': 5}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.02857142857142857, 'f1': 0.05405405405405405}, 'combined': 0.03603603603603603, 'epoch': 5}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Korean: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05179909351586346, 'epoch': 5}
Test for Russian: {'template': {'p': 0.9418604651162791, 'r': 0.6585365853658537, 'f1': 0.7751196172248804}, 'slot': {'p': 0.48936170212765956, 'r': 0.02090909090909091, 'f1': 0.040104620749782036}, 'combined': 0.031085878284520047, 'epoch': 5}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 5}