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 09:16:56.358065: step: 4/77, loss: 1.0449273586273193
2023-01-22 09:16:57.827825: step: 8/77, loss: 1.0661876201629639
2023-01-22 09:16:59.324630: step: 12/77, loss: 1.0697906017303467
2023-01-22 09:17:00.699488: step: 16/77, loss: 1.0578088760375977
2023-01-22 09:17:02.187594: step: 20/77, loss: 1.0446879863739014
2023-01-22 09:17:03.652851: step: 24/77, loss: 1.0503871440887451
2023-01-22 09:17:05.114233: step: 28/77, loss: 1.04624342918396
2023-01-22 09:17:06.599356: step: 32/77, loss: 1.0361480712890625
2023-01-22 09:17:08.075614: step: 36/77, loss: 1.041550874710083
2023-01-22 09:17:09.568526: step: 40/77, loss: 1.0250319242477417
2023-01-22 09:17:11.019204: step: 44/77, loss: 1.0202736854553223
2023-01-22 09:17:12.507145: step: 48/77, loss: 1.0159680843353271
2023-01-22 09:17:14.090441: step: 52/77, loss: 1.002465844154358
2023-01-22 09:17:15.580382: step: 56/77, loss: 0.977909505367279
2023-01-22 09:17:17.022893: step: 60/77, loss: 0.9835793972015381
2023-01-22 09:17:18.488566: step: 64/77, loss: 0.9763692617416382
2023-01-22 09:17:19.961940: step: 68/77, loss: 0.9826990962028503
2023-01-22 09:17:21.425546: step: 72/77, loss: 0.9448894262313843
2023-01-22 09:17:22.908391: step: 76/77, loss: 0.9651656150817871
2023-01-22 09:17:24.451368: step: 80/77, loss: 0.9191781282424927
2023-01-22 09:17:25.953672: step: 84/77, loss: 0.9262199401855469
2023-01-22 09:17:27.367510: step: 88/77, loss: 0.9188696146011353
2023-01-22 09:17:28.838873: step: 92/77, loss: 0.8682029247283936
2023-01-22 09:17:30.321267: step: 96/77, loss: 0.8716950416564941
2023-01-22 09:17:31.742621: step: 100/77, loss: 0.8641495108604431
2023-01-22 09:17:33.229413: step: 104/77, loss: 0.8422443866729736
2023-01-22 09:17:34.747972: step: 108/77, loss: 0.7932794094085693
2023-01-22 09:17:36.307033: step: 112/77, loss: 0.8285765647888184
2023-01-22 09:17:37.749700: step: 116/77, loss: 0.7687060832977295
2023-01-22 09:17:39.260142: step: 120/77, loss: 0.7670192718505859
2023-01-22 09:17:40.744833: step: 124/77, loss: 0.7816425561904907
2023-01-22 09:17:42.142011: step: 128/77, loss: 0.7292256355285645
2023-01-22 09:17:43.634157: step: 132/77, loss: 0.7331589460372925
2023-01-22 09:17:45.174150: step: 136/77, loss: 0.6675155162811279
2023-01-22 09:17:46.575445: step: 140/77, loss: 0.6493780016899109
2023-01-22 09:17:48.089943: step: 144/77, loss: 0.646944522857666
2023-01-22 09:17:49.591924: step: 148/77, loss: 0.6240701675415039
2023-01-22 09:17:51.172276: step: 152/77, loss: 0.5725189447402954
2023-01-22 09:17:52.690481: step: 156/77, loss: 0.5819498896598816
2023-01-22 09:17:54.174964: step: 160/77, loss: 0.5860099792480469
2023-01-22 09:17:55.688048: step: 164/77, loss: 0.5213608145713806
2023-01-22 09:17:57.209525: step: 168/77, loss: 0.5680379867553711
2023-01-22 09:17:58.686592: step: 172/77, loss: 0.45404040813446045
2023-01-22 09:18:00.140585: step: 176/77, loss: 0.44066500663757324
2023-01-22 09:18:01.626087: step: 180/77, loss: 0.4716237783432007
2023-01-22 09:18:03.090223: step: 184/77, loss: 0.3929561376571655
2023-01-22 09:18:04.621112: step: 188/77, loss: 0.4217242896556854
2023-01-22 09:18:06.057996: step: 192/77, loss: 0.39566516876220703
2023-01-22 09:18:07.523149: step: 196/77, loss: 0.41571173071861267
2023-01-22 09:18:08.982250: step: 200/77, loss: 0.2986573874950409
2023-01-22 09:18:10.428547: step: 204/77, loss: 0.44773268699645996
2023-01-22 09:18:11.899374: step: 208/77, loss: 0.2613578140735626
2023-01-22 09:18:13.367739: step: 212/77, loss: 0.22704322636127472
2023-01-22 09:18:14.807222: step: 216/77, loss: 0.1780972182750702
2023-01-22 09:18:16.282623: step: 220/77, loss: 0.20675839483737946
2023-01-22 09:18:17.823268: step: 224/77, loss: 0.19478635489940643
2023-01-22 09:18:19.196436: step: 228/77, loss: 0.2304016649723053
2023-01-22 09:18:20.678548: step: 232/77, loss: 0.2229248285293579
2023-01-22 09:18:22.188024: step: 236/77, loss: 0.13515512645244598
2023-01-22 09:18:23.681849: step: 240/77, loss: 0.11883608996868134
2023-01-22 09:18:25.188740: step: 244/77, loss: 0.1275760531425476
2023-01-22 09:18:26.724201: step: 248/77, loss: 0.33747437596321106
2023-01-22 09:18:28.215214: step: 252/77, loss: 0.12381209433078766
2023-01-22 09:18:29.744957: step: 256/77, loss: 0.40654462575912476
2023-01-22 09:18:31.292560: step: 260/77, loss: 0.14962953329086304
2023-01-22 09:18:32.725822: step: 264/77, loss: 0.044936202466487885
2023-01-22 09:18:34.170252: step: 268/77, loss: 0.06391699612140656
2023-01-22 09:18:35.653102: step: 272/77, loss: 0.20007681846618652
2023-01-22 09:18:37.188693: step: 276/77, loss: 0.2122235894203186
2023-01-22 09:18:38.578746: step: 280/77, loss: 0.13911424577236176
2023-01-22 09:18:40.072472: step: 284/77, loss: 0.06268332153558731
2023-01-22 09:18:41.582624: step: 288/77, loss: 0.11234302073717117
2023-01-22 09:18:43.025641: step: 292/77, loss: 0.04873437061905861
2023-01-22 09:18:44.481150: step: 296/77, loss: 0.1151905208826065
2023-01-22 09:18:45.982836: step: 300/77, loss: 0.20775069296360016
2023-01-22 09:18:47.467075: step: 304/77, loss: 0.1022971048951149
2023-01-22 09:18:48.955247: step: 308/77, loss: 0.14672891795635223
2023-01-22 09:18:50.381212: step: 312/77, loss: 0.036175355315208435
2023-01-22 09:18:51.828978: step: 316/77, loss: 0.06932605803012848
2023-01-22 09:18:53.282684: step: 320/77, loss: 0.24824608862400055
2023-01-22 09:18:54.804056: step: 324/77, loss: 0.0985107496380806
2023-01-22 09:18:56.238294: step: 328/77, loss: 0.27712494134902954
2023-01-22 09:18:57.683053: step: 332/77, loss: 0.080054372549057
2023-01-22 09:18:59.085779: step: 336/77, loss: 0.24405285716056824
2023-01-22 09:19:00.549558: step: 340/77, loss: 0.11317433416843414
2023-01-22 09:19:02.044472: step: 344/77, loss: 0.13220016658306122
2023-01-22 09:19:03.484371: step: 348/77, loss: 0.04351910203695297
2023-01-22 09:19:05.005198: step: 352/77, loss: 0.08148898184299469
2023-01-22 09:19:06.447395: step: 356/77, loss: 0.25758957862854004
2023-01-22 09:19:07.942433: step: 360/77, loss: 0.19760257005691528
2023-01-22 09:19:09.448521: step: 364/77, loss: 0.08745350688695908
2023-01-22 09:19:11.015004: step: 368/77, loss: 0.20615199208259583
2023-01-22 09:19:12.517086: step: 372/77, loss: 0.04876667261123657
2023-01-22 09:19:13.968204: step: 376/77, loss: 0.1216202825307846
2023-01-22 09:19:15.377747: step: 380/77, loss: 0.16642817854881287
2023-01-22 09:19:16.884625: step: 384/77, loss: 0.06036415696144104
2023-01-22 09:19:18.340494: step: 388/77, loss: 0.1854311227798462
==================================================
Loss: 0.487
--------------------
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': 1.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 1.0, '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': 1.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 1.0, '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': 1.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 1.0, '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': 1.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 1.0, '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': 1.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 1.0, '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': 1.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 1.0, '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 09:21:13.751247: step: 4/77, loss: 0.08808518946170807
2023-01-22 09:21:15.335225: step: 8/77, loss: 0.07598349452018738
2023-01-22 09:21:16.718984: step: 12/77, loss: 0.07537257671356201
2023-01-22 09:21:18.125848: step: 16/77, loss: 0.19350022077560425
2023-01-22 09:21:19.522590: step: 20/77, loss: 0.08845332264900208
2023-01-22 09:21:20.994339: step: 24/77, loss: 0.06127769500017166
2023-01-22 09:21:22.494691: step: 28/77, loss: 0.08885109424591064
2023-01-22 09:21:23.965234: step: 32/77, loss: 0.21233563125133514
2023-01-22 09:21:25.439419: step: 36/77, loss: 0.3040357232093811
2023-01-22 09:21:26.903331: step: 40/77, loss: 0.27482870221138
2023-01-22 09:21:28.425857: step: 44/77, loss: 0.08601843565702438
2023-01-22 09:21:29.869032: step: 48/77, loss: 0.07719548791646957
2023-01-22 09:21:31.343980: step: 52/77, loss: 0.06267912685871124
2023-01-22 09:21:32.809445: step: 56/77, loss: 0.07540792971849442
2023-01-22 09:21:34.248675: step: 60/77, loss: 0.04689452797174454
2023-01-22 09:21:35.712920: step: 64/77, loss: 0.15594510734081268
2023-01-22 09:21:37.232915: step: 68/77, loss: 0.14404773712158203
2023-01-22 09:21:38.711558: step: 72/77, loss: 0.07119323313236237
2023-01-22 09:21:40.214456: step: 76/77, loss: 0.16119280457496643
2023-01-22 09:21:41.674024: step: 80/77, loss: 0.09215322881937027
2023-01-22 09:21:43.234657: step: 84/77, loss: 0.3043191432952881
2023-01-22 09:21:44.708998: step: 88/77, loss: 0.3175913393497467
2023-01-22 09:21:46.174417: step: 92/77, loss: 0.08320172131061554
2023-01-22 09:21:47.649894: step: 96/77, loss: 0.03388125076889992
2023-01-22 09:21:49.048797: step: 100/77, loss: 0.03213505819439888
2023-01-22 09:21:50.522159: step: 104/77, loss: 0.11765853315591812
2023-01-22 09:21:51.961605: step: 108/77, loss: 0.16065680980682373
2023-01-22 09:21:53.445189: step: 112/77, loss: 0.031914323568344116
2023-01-22 09:21:54.858532: step: 116/77, loss: 0.1371314525604248
2023-01-22 09:21:56.368475: step: 120/77, loss: 0.057588137686252594
2023-01-22 09:21:57.806766: step: 124/77, loss: 0.17369845509529114
2023-01-22 09:21:59.245137: step: 128/77, loss: 0.14050480723381042
2023-01-22 09:22:00.746476: step: 132/77, loss: 0.06881752610206604
2023-01-22 09:22:02.173876: step: 136/77, loss: 0.08079089224338531
2023-01-22 09:22:03.591808: step: 140/77, loss: 0.11471383273601532
2023-01-22 09:22:05.034844: step: 144/77, loss: 0.07265495508909225
2023-01-22 09:22:06.488623: step: 148/77, loss: 0.0584573820233345
2023-01-22 09:22:08.043858: step: 152/77, loss: 0.20290088653564453
2023-01-22 09:22:09.500319: step: 156/77, loss: 0.08977239578962326
2023-01-22 09:22:10.974914: step: 160/77, loss: 0.2409203052520752
2023-01-22 09:22:12.422538: step: 164/77, loss: 0.31462815403938293
2023-01-22 09:22:13.874609: step: 168/77, loss: 0.09223669022321701
2023-01-22 09:22:15.392226: step: 172/77, loss: 0.15644097328186035
2023-01-22 09:22:16.873738: step: 176/77, loss: 0.03518672287464142
2023-01-22 09:22:18.366102: step: 180/77, loss: 0.0733434408903122
2023-01-22 09:22:19.871376: step: 184/77, loss: 0.19737818837165833
2023-01-22 09:22:21.332821: step: 188/77, loss: 0.07022371888160706
2023-01-22 09:22:22.834879: step: 192/77, loss: 0.08941012620925903
2023-01-22 09:22:24.313197: step: 196/77, loss: 0.17177169024944305
2023-01-22 09:22:25.768500: step: 200/77, loss: 0.0818762332201004
2023-01-22 09:22:27.255119: step: 204/77, loss: 0.1051383763551712
2023-01-22 09:22:28.623268: step: 208/77, loss: 0.13907712697982788
2023-01-22 09:22:30.048341: step: 212/77, loss: 0.050016190856695175
2023-01-22 09:22:31.477574: step: 216/77, loss: 0.05056443437933922
2023-01-22 09:22:32.937158: step: 220/77, loss: 0.07941845059394836
2023-01-22 09:22:34.412419: step: 224/77, loss: 0.08878391236066818
2023-01-22 09:22:35.914689: step: 228/77, loss: 0.0625339150428772
2023-01-22 09:22:37.298376: step: 232/77, loss: 0.06150152161717415
2023-01-22 09:22:38.765289: step: 236/77, loss: 0.11748947948217392
2023-01-22 09:22:40.263711: step: 240/77, loss: 0.18033303320407867
2023-01-22 09:22:41.759740: step: 244/77, loss: 0.14193198084831238
2023-01-22 09:22:43.279282: step: 248/77, loss: 0.08232773840427399
2023-01-22 09:22:44.743300: step: 252/77, loss: 0.2342931628227234
2023-01-22 09:22:46.198654: step: 256/77, loss: 0.08909574151039124
2023-01-22 09:22:47.679894: step: 260/77, loss: 0.05348915234208107
2023-01-22 09:22:49.126202: step: 264/77, loss: 0.1067211776971817
2023-01-22 09:22:50.556724: step: 268/77, loss: 0.23183506727218628
2023-01-22 09:22:52.030069: step: 272/77, loss: 0.1415650099515915
2023-01-22 09:22:53.509851: step: 276/77, loss: 0.06152913719415665
2023-01-22 09:22:54.956166: step: 280/77, loss: 0.041706740856170654
2023-01-22 09:22:56.445780: step: 284/77, loss: 0.10872595757246017
2023-01-22 09:22:57.946409: step: 288/77, loss: 0.043247997760772705
2023-01-22 09:22:59.409321: step: 292/77, loss: 0.12283715605735779
2023-01-22 09:23:00.872330: step: 296/77, loss: 0.03415264934301376
2023-01-22 09:23:02.308492: step: 300/77, loss: 0.17462123930454254
2023-01-22 09:23:03.790722: step: 304/77, loss: 0.1322343945503235
2023-01-22 09:23:05.317916: step: 308/77, loss: 0.06682181358337402
2023-01-22 09:23:06.866575: step: 312/77, loss: 0.07804687321186066
2023-01-22 09:23:08.285686: step: 316/77, loss: 0.36672520637512207
2023-01-22 09:23:09.726505: step: 320/77, loss: 0.06110672280192375
2023-01-22 09:23:11.201398: step: 324/77, loss: 0.1718875765800476
2023-01-22 09:23:12.714400: step: 328/77, loss: 0.13002590835094452
2023-01-22 09:23:14.166899: step: 332/77, loss: 0.10468481481075287
2023-01-22 09:23:15.662493: step: 336/77, loss: 0.1538790762424469
2023-01-22 09:23:17.050154: step: 340/77, loss: 0.026036838069558144
2023-01-22 09:23:18.552012: step: 344/77, loss: 0.11194135248661041
2023-01-22 09:23:20.054987: step: 348/77, loss: 0.07212279736995697
2023-01-22 09:23:21.572932: step: 352/77, loss: 0.06141982227563858
2023-01-22 09:23:23.073769: step: 356/77, loss: 0.10051367431879044
2023-01-22 09:23:24.592463: step: 360/77, loss: 0.08243393898010254
2023-01-22 09:23:26.041226: step: 364/77, loss: 0.08698487281799316
2023-01-22 09:23:27.518516: step: 368/77, loss: 0.06616237759590149
2023-01-22 09:23:29.007801: step: 372/77, loss: 0.08207230269908905
2023-01-22 09:23:30.513073: step: 376/77, loss: 0.13694001734256744
2023-01-22 09:23:31.942351: step: 380/77, loss: 0.06030358374118805
2023-01-22 09:23:33.452444: step: 384/77, loss: 0.07378076016902924
2023-01-22 09:23:34.930755: step: 388/77, loss: 0.0624019056558609
==================================================
Loss: 0.115
--------------------
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': 1.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 1.0, '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': 1.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 1.0, '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': 1.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 1.0, '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': 1.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 1.0, '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': 1.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 1.0, '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': 1.0, 'r': 0.0, 'f1': 0.0}, 'slot': {'p': 1.0, '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 09:25:12.086793: step: 4/77, loss: 0.13258124887943268
2023-01-22 09:25:13.552149: step: 8/77, loss: 0.06252895295619965
2023-01-22 09:25:14.977051: step: 12/77, loss: 0.10674737393856049
2023-01-22 09:25:16.496701: step: 16/77, loss: 0.09641920775175095
2023-01-22 09:25:17.950756: step: 20/77, loss: 0.11784550547599792
2023-01-22 09:25:19.413090: step: 24/77, loss: 0.05828585475683212
2023-01-22 09:25:20.916118: step: 28/77, loss: 0.058067552745342255
2023-01-22 09:25:22.448289: step: 32/77, loss: 0.09018880873918533
2023-01-22 09:25:23.861144: step: 36/77, loss: 0.22561988234519958
2023-01-22 09:25:25.282741: step: 40/77, loss: 0.14366985857486725
2023-01-22 09:25:26.785761: step: 44/77, loss: 0.08453567326068878
2023-01-22 09:25:28.184787: step: 48/77, loss: 0.03233639895915985
2023-01-22 09:25:29.627863: step: 52/77, loss: 0.07216435670852661
2023-01-22 09:25:31.049688: step: 56/77, loss: 0.24645262956619263
2023-01-22 09:25:32.571934: step: 60/77, loss: 0.050122007727622986
2023-01-22 09:25:34.043053: step: 64/77, loss: 0.12721282243728638
2023-01-22 09:25:35.427719: step: 68/77, loss: 0.05591835081577301
2023-01-22 09:25:36.934350: step: 72/77, loss: 0.06773615628480911
2023-01-22 09:25:38.341711: step: 76/77, loss: 0.14394433796405792
2023-01-22 09:25:39.747372: step: 80/77, loss: 0.0904054343700409
2023-01-22 09:25:41.264409: step: 84/77, loss: 0.23689547181129456
2023-01-22 09:25:42.778573: step: 88/77, loss: 0.1101958304643631
2023-01-22 09:25:44.238477: step: 92/77, loss: 0.08307532966136932
2023-01-22 09:25:45.711351: step: 96/77, loss: 0.15602004528045654
2023-01-22 09:25:47.159056: step: 100/77, loss: 0.04147651046514511
2023-01-22 09:25:48.660307: step: 104/77, loss: 0.15626007318496704
2023-01-22 09:25:50.212289: step: 108/77, loss: 0.08543263375759125
2023-01-22 09:25:51.608057: step: 112/77, loss: 0.05249679833650589
2023-01-22 09:25:53.157450: step: 116/77, loss: 0.13839921355247498
2023-01-22 09:25:54.635012: step: 120/77, loss: 0.1184510886669159
2023-01-22 09:25:56.092777: step: 124/77, loss: 0.12318076193332672
2023-01-22 09:25:57.571807: step: 128/77, loss: 0.06913600862026215
2023-01-22 09:25:59.029294: step: 132/77, loss: 0.07552852481603622
2023-01-22 09:26:00.517843: step: 136/77, loss: 0.1511237621307373
2023-01-22 09:26:01.975436: step: 140/77, loss: 0.11312386393547058
2023-01-22 09:26:03.439824: step: 144/77, loss: 0.07943280786275864
2023-01-22 09:26:04.959098: step: 148/77, loss: 0.03293665871024132
2023-01-22 09:26:06.410537: step: 152/77, loss: 0.06744928658008575
2023-01-22 09:26:07.887959: step: 156/77, loss: 0.08263631165027618
2023-01-22 09:26:09.353786: step: 160/77, loss: 0.079817034304142
2023-01-22 09:26:10.855005: step: 164/77, loss: 0.03467145934700966
2023-01-22 09:26:12.300871: step: 168/77, loss: 0.025395743548870087
2023-01-22 09:26:13.775990: step: 172/77, loss: 0.06069394573569298
2023-01-22 09:26:15.282880: step: 176/77, loss: 0.01779540255665779
2023-01-22 09:26:16.729807: step: 180/77, loss: 0.03509168699383736
2023-01-22 09:26:18.187202: step: 184/77, loss: 0.03671012073755264
2023-01-22 09:26:19.693102: step: 188/77, loss: 0.04279708117246628
2023-01-22 09:26:21.201280: step: 192/77, loss: 0.031519681215286255
2023-01-22 09:26:22.669869: step: 196/77, loss: 0.03178836405277252
2023-01-22 09:26:24.139367: step: 200/77, loss: 0.03438074141740799
2023-01-22 09:26:25.581256: step: 204/77, loss: 0.013872837647795677
2023-01-22 09:26:27.062092: step: 208/77, loss: 0.0239429734647274
2023-01-22 09:26:28.464359: step: 212/77, loss: 0.04659315571188927
2023-01-22 09:26:29.920577: step: 216/77, loss: 0.00971127487719059
2023-01-22 09:26:31.441681: step: 220/77, loss: 0.06695039570331573
2023-01-22 09:26:32.915078: step: 224/77, loss: 0.06293109059333801
2023-01-22 09:26:34.460207: step: 228/77, loss: 0.0710817202925682
2023-01-22 09:26:35.959331: step: 232/77, loss: 0.018637798726558685
2023-01-22 09:26:37.474038: step: 236/77, loss: 0.11581932008266449
2023-01-22 09:26:38.929561: step: 240/77, loss: 0.04097363352775574
2023-01-22 09:26:40.398845: step: 244/77, loss: 0.014920370653271675
2023-01-22 09:26:41.903309: step: 248/77, loss: 0.01983986236155033
2023-01-22 09:26:43.324117: step: 252/77, loss: 0.024595849215984344
2023-01-22 09:26:44.811163: step: 256/77, loss: 0.04437322914600372
2023-01-22 09:26:46.300303: step: 260/77, loss: 0.014827568084001541
2023-01-22 09:26:47.813190: step: 264/77, loss: 0.05651269108057022
2023-01-22 09:26:49.264530: step: 268/77, loss: 0.05368447303771973
2023-01-22 09:26:50.762605: step: 272/77, loss: 0.008875405415892601
2023-01-22 09:26:52.250194: step: 276/77, loss: 0.08118952065706253
2023-01-22 09:26:53.701178: step: 280/77, loss: 0.044285401701927185
2023-01-22 09:26:55.156481: step: 284/77, loss: 0.021020062267780304
2023-01-22 09:26:56.641652: step: 288/77, loss: 0.04102979600429535
2023-01-22 09:26:58.125474: step: 292/77, loss: 0.08634628355503082
2023-01-22 09:26:59.568001: step: 296/77, loss: 0.10369566082954407
2023-01-22 09:27:01.068467: step: 300/77, loss: 0.1591092050075531
2023-01-22 09:27:02.601644: step: 304/77, loss: 0.0445716418325901
2023-01-22 09:27:04.083288: step: 308/77, loss: 0.044002607464790344
2023-01-22 09:27:05.577172: step: 312/77, loss: 0.12348321080207825
2023-01-22 09:27:07.016959: step: 316/77, loss: 0.04513373598456383
2023-01-22 09:27:08.509542: step: 320/77, loss: 0.07740610092878342
2023-01-22 09:27:10.033723: step: 324/77, loss: 0.017783014103770256
2023-01-22 09:27:11.492641: step: 328/77, loss: 0.016946876421570778
2023-01-22 09:27:13.079334: step: 332/77, loss: 0.011803146451711655
2023-01-22 09:27:14.570511: step: 336/77, loss: 0.07661925256252289
2023-01-22 09:27:16.015640: step: 340/77, loss: 0.02661910280585289
2023-01-22 09:27:17.505975: step: 344/77, loss: 0.03145609050989151
2023-01-22 09:27:19.000145: step: 348/77, loss: 0.019618254154920578
2023-01-22 09:27:20.487969: step: 352/77, loss: 0.07848714292049408
2023-01-22 09:27:21.958059: step: 356/77, loss: 0.04304105043411255
2023-01-22 09:27:23.437633: step: 360/77, loss: 0.04550347849726677
2023-01-22 09:27:24.941445: step: 364/77, loss: 0.019600503146648407
2023-01-22 09:27:26.457428: step: 368/77, loss: 0.0321541503071785
2023-01-22 09:27:28.056675: step: 372/77, loss: 0.08753525465726852
2023-01-22 09:27:29.581313: step: 376/77, loss: 0.041867706924676895
2023-01-22 09:27:31.066705: step: 380/77, loss: 0.03870141878724098
2023-01-22 09:27:32.497934: step: 384/77, loss: 0.05822906270623207
2023-01-22 09:27:33.954013: step: 388/77, loss: 0.03057796321809292
==================================================
Loss: 0.069
--------------------
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': 2}
Test Chinese: {'template': {'p': 0.9384615384615385, 'r': 0.46564885496183206, 'f1': 0.6224489795918368}, 'slot': {'p': 0.6153846153846154, 'r': 0.013805004314063849, 'f1': 0.027004219409282704}, 'combined': 0.016808748815982093, 'epoch': 2}
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': 2}
Test Korean: {'template': {'p': 0.9230769230769231, 'r': 0.4580152671755725, 'f1': 0.6122448979591837}, 'slot': {'p': 0.6153846153846154, 'r': 0.013805004314063849, 'f1': 0.027004219409282704}, 'combined': 0.016533195556703698, 'epoch': 2}
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': 2}
Test Russian: {'template': {'p': 0.9230769230769231, 'r': 0.4580152671755725, 'f1': 0.6122448979591837}, 'slot': {'p': 0.6153846153846154, 'r': 0.013805004314063849, 'f1': 0.027004219409282704}, 'combined': 0.016533195556703698, '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': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, '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': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05085442919642522, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.9384615384615385, 'r': 0.46564885496183206, 'f1': 0.6224489795918368}, 'slot': {'p': 0.6153846153846154, 'r': 0.013805004314063849, 'f1': 0.027004219409282704}, 'combined': 0.016808748815982093, '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': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05085442919642522, 'epoch': 2}
Test for Korean: {'template': {'p': 0.9230769230769231, 'r': 0.4580152671755725, 'f1': 0.6122448979591837}, 'slot': {'p': 0.6153846153846154, 'r': 0.013805004314063849, 'f1': 0.027004219409282704}, 'combined': 0.016533195556703698, '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': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.05085442919642522, 'epoch': 2}
Test for Russian: {'template': {'p': 0.9230769230769231, 'r': 0.4580152671755725, 'f1': 0.6122448979591837}, 'slot': {'p': 0.6153846153846154, 'r': 0.013805004314063849, 'f1': 0.027004219409282704}, 'combined': 0.016533195556703698, 'epoch': 2}
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': 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 09:29:32.738737: step: 4/77, loss: 0.012912862002849579
2023-01-22 09:29:34.077166: step: 8/77, loss: 0.04591010510921478
2023-01-22 09:29:35.633658: step: 12/77, loss: 0.02694067917764187
2023-01-22 09:29:37.131225: step: 16/77, loss: 0.01571756601333618
2023-01-22 09:29:38.512850: step: 20/77, loss: 0.01355262566357851
2023-01-22 09:29:39.970573: step: 24/77, loss: 0.03795113414525986
2023-01-22 09:29:41.451435: step: 28/77, loss: 0.03535859286785126
2023-01-22 09:29:42.870307: step: 32/77, loss: 0.015470536425709724
2023-01-22 09:29:44.313918: step: 36/77, loss: 0.015092505142092705
2023-01-22 09:29:45.809234: step: 40/77, loss: 0.1292186826467514
2023-01-22 09:29:47.217436: step: 44/77, loss: 0.07205881923437119
2023-01-22 09:29:48.716272: step: 48/77, loss: 0.03737745061516762
2023-01-22 09:29:50.198967: step: 52/77, loss: 0.011360120959579945
2023-01-22 09:29:51.695470: step: 56/77, loss: 0.007079091854393482
2023-01-22 09:29:53.230182: step: 60/77, loss: 0.021989651024341583
2023-01-22 09:29:54.654772: step: 64/77, loss: 0.11524832248687744
2023-01-22 09:29:56.132508: step: 68/77, loss: 0.029087066650390625
2023-01-22 09:29:57.654451: step: 72/77, loss: 0.025555476546287537
2023-01-22 09:29:59.076549: step: 76/77, loss: 0.05321405082941055
2023-01-22 09:30:00.601288: step: 80/77, loss: 0.021694185212254524
2023-01-22 09:30:02.169140: step: 84/77, loss: 0.026616228744387627
2023-01-22 09:30:03.609810: step: 88/77, loss: 0.025496210902929306
2023-01-22 09:30:05.045097: step: 92/77, loss: 0.02640456147491932
2023-01-22 09:30:06.611763: step: 96/77, loss: 0.014219501987099648
2023-01-22 09:30:07.999119: step: 100/77, loss: 0.04648306965827942
2023-01-22 09:30:09.507815: step: 104/77, loss: 0.003235041629523039
2023-01-22 09:30:10.983375: step: 108/77, loss: 0.016798511147499084
2023-01-22 09:30:12.465405: step: 112/77, loss: 0.033600855618715286
2023-01-22 09:30:13.966666: step: 116/77, loss: 0.015783516690135002
2023-01-22 09:30:15.401296: step: 120/77, loss: 0.05280846357345581
2023-01-22 09:30:16.895098: step: 124/77, loss: 0.00289800763130188
2023-01-22 09:30:18.364632: step: 128/77, loss: 0.034957654774188995
2023-01-22 09:30:19.829523: step: 132/77, loss: 0.08969595283269882
2023-01-22 09:30:21.276399: step: 136/77, loss: 0.04882393777370453
2023-01-22 09:30:22.763615: step: 140/77, loss: 0.02632911317050457
2023-01-22 09:30:24.229183: step: 144/77, loss: 0.002386486390605569
2023-01-22 09:30:25.757042: step: 148/77, loss: 0.04905037209391594
2023-01-22 09:30:27.267492: step: 152/77, loss: 0.007842171005904675
2023-01-22 09:30:28.724971: step: 156/77, loss: 0.02815202623605728
2023-01-22 09:30:30.223015: step: 160/77, loss: 0.005176716484129429
2023-01-22 09:30:31.712201: step: 164/77, loss: 0.017684893682599068
2023-01-22 09:30:33.172885: step: 168/77, loss: 0.015900595113635063
2023-01-22 09:30:34.737282: step: 172/77, loss: 0.006918495055288076
2023-01-22 09:30:36.179798: step: 176/77, loss: 0.02818692848086357
2023-01-22 09:30:37.678240: step: 180/77, loss: 0.03534059599041939
2023-01-22 09:30:39.145300: step: 184/77, loss: 0.026743004098534584
2023-01-22 09:30:40.672544: step: 188/77, loss: 0.027218960225582123
2023-01-22 09:30:42.124286: step: 192/77, loss: 0.00607309490442276
2023-01-22 09:30:43.674566: step: 196/77, loss: 0.009721008129417896
2023-01-22 09:30:45.228368: step: 200/77, loss: 0.026713203638792038
2023-01-22 09:30:46.667549: step: 204/77, loss: 0.04019925370812416
2023-01-22 09:30:48.090936: step: 208/77, loss: 0.08135680109262466
2023-01-22 09:30:49.558235: step: 212/77, loss: 0.07656152546405792
2023-01-22 09:30:51.035494: step: 216/77, loss: 0.024162959307432175
2023-01-22 09:30:52.493167: step: 220/77, loss: 0.01666862890124321
2023-01-22 09:30:53.977652: step: 224/77, loss: 0.03890030086040497
2023-01-22 09:30:55.408298: step: 228/77, loss: 0.045673124492168427
2023-01-22 09:30:56.903682: step: 232/77, loss: 0.010527916252613068
2023-01-22 09:30:58.389590: step: 236/77, loss: 0.006743155419826508
2023-01-22 09:30:59.886656: step: 240/77, loss: 0.011435626074671745
2023-01-22 09:31:01.402916: step: 244/77, loss: 0.0381687693297863
2023-01-22 09:31:02.920323: step: 248/77, loss: 0.022242587059736252
2023-01-22 09:31:04.360965: step: 252/77, loss: 0.04305797815322876
2023-01-22 09:31:05.819296: step: 256/77, loss: 0.009767288342118263
2023-01-22 09:31:07.348484: step: 260/77, loss: 0.12234492599964142
2023-01-22 09:31:08.857945: step: 264/77, loss: 0.03097294643521309
2023-01-22 09:31:10.327885: step: 268/77, loss: 0.0573321133852005
2023-01-22 09:31:11.787825: step: 272/77, loss: 0.22089190781116486
2023-01-22 09:31:13.266451: step: 276/77, loss: 0.05211479216814041
2023-01-22 09:31:14.803621: step: 280/77, loss: 0.02089191973209381
2023-01-22 09:31:16.196923: step: 284/77, loss: 0.06037844344973564
2023-01-22 09:31:17.660571: step: 288/77, loss: 0.018641719594597816
2023-01-22 09:31:19.171804: step: 292/77, loss: 0.010771493427455425
2023-01-22 09:31:20.630452: step: 296/77, loss: 0.02911381423473358
2023-01-22 09:31:22.106721: step: 300/77, loss: 0.056641578674316406
2023-01-22 09:31:23.578859: step: 304/77, loss: 0.020282302051782608
2023-01-22 09:31:25.076372: step: 308/77, loss: 0.10549724102020264
2023-01-22 09:31:26.538391: step: 312/77, loss: 0.12837551534175873
2023-01-22 09:31:28.006218: step: 316/77, loss: 0.008430239744484425
2023-01-22 09:31:29.460169: step: 320/77, loss: 0.022032450884580612
2023-01-22 09:31:30.886275: step: 324/77, loss: 0.07047325372695923
2023-01-22 09:31:32.318347: step: 328/77, loss: 0.018198523670434952
2023-01-22 09:31:33.807823: step: 332/77, loss: 0.016754793003201485
2023-01-22 09:31:35.277315: step: 336/77, loss: 0.042492322623729706
2023-01-22 09:31:36.736543: step: 340/77, loss: 0.029950454831123352
2023-01-22 09:31:38.175708: step: 344/77, loss: 0.05285784602165222
2023-01-22 09:31:39.667787: step: 348/77, loss: 0.06085269898176193
2023-01-22 09:31:41.107137: step: 352/77, loss: 0.014680081978440285
2023-01-22 09:31:42.600869: step: 356/77, loss: 0.050214581191539764
2023-01-22 09:31:44.032122: step: 360/77, loss: 0.03656889870762825
2023-01-22 09:31:45.474909: step: 364/77, loss: 0.014042508788406849
2023-01-22 09:31:47.010852: step: 368/77, loss: 0.04989948868751526
2023-01-22 09:31:48.519951: step: 372/77, loss: 0.048607222735881805
2023-01-22 09:31:50.018960: step: 376/77, loss: 0.04302738979458809
2023-01-22 09:31:51.462196: step: 380/77, loss: 0.02379428781569004
2023-01-22 09:31:52.967475: step: 384/77, loss: 0.013878141529858112
2023-01-22 09:31:54.496104: step: 388/77, loss: 0.008634086698293686
==================================================
Loss: 0.036
--------------------
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': 3}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 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': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 3}
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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 09:33:52.332313: step: 4/77, loss: 0.01413442101329565
2023-01-22 09:33:53.812819: step: 8/77, loss: 0.03007185272872448
2023-01-22 09:33:55.279400: step: 12/77, loss: 0.03499831259250641
2023-01-22 09:33:56.707476: step: 16/77, loss: 0.05546431988477707
2023-01-22 09:33:58.139104: step: 20/77, loss: 0.002329618204385042
2023-01-22 09:33:59.613308: step: 24/77, loss: 0.03021444007754326
2023-01-22 09:34:01.148891: step: 28/77, loss: 0.002550596371293068
2023-01-22 09:34:02.646327: step: 32/77, loss: 0.06376893818378448
2023-01-22 09:34:04.125986: step: 36/77, loss: 0.013936012983322144
2023-01-22 09:34:05.567508: step: 40/77, loss: 0.024293333292007446
2023-01-22 09:34:07.046401: step: 44/77, loss: 0.003448844887316227
2023-01-22 09:34:08.512476: step: 48/77, loss: 0.04759862273931503
2023-01-22 09:34:09.962432: step: 52/77, loss: 0.02035803720355034
2023-01-22 09:34:11.493917: step: 56/77, loss: 0.006649450398981571
2023-01-22 09:34:12.933830: step: 60/77, loss: 0.010570206679403782
2023-01-22 09:34:14.379390: step: 64/77, loss: 0.05664711818099022
2023-01-22 09:34:15.836393: step: 68/77, loss: 0.015202310867607594
2023-01-22 09:34:17.362715: step: 72/77, loss: 0.03192824497818947
2023-01-22 09:34:18.806777: step: 76/77, loss: 0.04990002512931824
2023-01-22 09:34:20.299316: step: 80/77, loss: 0.004372069146484137
2023-01-22 09:34:21.792354: step: 84/77, loss: 0.06885036081075668
2023-01-22 09:34:23.301218: step: 88/77, loss: 0.002442281460389495
2023-01-22 09:34:24.776424: step: 92/77, loss: 0.003796561621129513
2023-01-22 09:34:26.228797: step: 96/77, loss: 0.04918007180094719
2023-01-22 09:34:27.726377: step: 100/77, loss: 0.0023976361844688654
2023-01-22 09:34:29.160331: step: 104/77, loss: 0.060220494866371155
2023-01-22 09:34:30.664001: step: 108/77, loss: 0.019232070073485374
2023-01-22 09:34:32.070809: step: 112/77, loss: 0.03376259282231331
2023-01-22 09:34:33.566581: step: 116/77, loss: 0.03330276161432266
2023-01-22 09:34:35.054149: step: 120/77, loss: 0.01623927801847458
2023-01-22 09:34:36.615184: step: 124/77, loss: 0.008382521569728851
2023-01-22 09:34:38.100027: step: 128/77, loss: 0.025504330173134804
2023-01-22 09:34:39.583413: step: 132/77, loss: 0.016718082129955292
2023-01-22 09:34:41.062503: step: 136/77, loss: 0.03711515665054321
2023-01-22 09:34:42.564011: step: 140/77, loss: 0.04266016557812691
2023-01-22 09:34:44.069898: step: 144/77, loss: 0.05167564004659653
2023-01-22 09:34:45.531091: step: 148/77, loss: 0.003722875379025936
2023-01-22 09:34:46.992922: step: 152/77, loss: 0.009192441590130329
2023-01-22 09:34:48.496737: step: 156/77, loss: 0.03469576686620712
2023-01-22 09:34:49.999285: step: 160/77, loss: 0.034946829080581665
2023-01-22 09:34:51.424392: step: 164/77, loss: 0.007201574742794037
2023-01-22 09:34:52.939853: step: 168/77, loss: 0.004851900972425938
2023-01-22 09:34:54.426635: step: 172/77, loss: 0.03253195434808731
2023-01-22 09:34:55.872219: step: 176/77, loss: 0.02325173281133175
2023-01-22 09:34:57.333636: step: 180/77, loss: 0.026802418753504753
2023-01-22 09:34:58.857650: step: 184/77, loss: 0.01016119122505188
2023-01-22 09:35:00.290000: step: 188/77, loss: 0.03971070796251297
2023-01-22 09:35:01.760638: step: 192/77, loss: 0.018513280898332596
2023-01-22 09:35:03.357169: step: 196/77, loss: 0.017288243398070335
2023-01-22 09:35:04.876718: step: 200/77, loss: 0.021497106179594994
2023-01-22 09:35:06.332224: step: 204/77, loss: 0.01803465560078621
2023-01-22 09:35:07.824302: step: 208/77, loss: 0.01829645223915577
2023-01-22 09:35:09.295501: step: 212/77, loss: 0.005914963781833649
2023-01-22 09:35:10.804388: step: 216/77, loss: 0.0278038140386343
2023-01-22 09:35:12.253037: step: 220/77, loss: 0.016222145408391953
2023-01-22 09:35:13.677756: step: 224/77, loss: 0.010350292548537254
2023-01-22 09:35:15.135751: step: 228/77, loss: 0.034529589116573334
2023-01-22 09:35:16.595822: step: 232/77, loss: 0.006905150134116411
2023-01-22 09:35:17.999620: step: 236/77, loss: 0.014340376481413841
2023-01-22 09:35:19.516108: step: 240/77, loss: 0.043415144085884094
2023-01-22 09:35:20.937646: step: 244/77, loss: 0.0488872304558754
2023-01-22 09:35:22.425369: step: 248/77, loss: 0.003966958727687597
2023-01-22 09:35:23.886673: step: 252/77, loss: 0.030302058905363083
2023-01-22 09:35:25.313130: step: 256/77, loss: 0.012804752215743065
2023-01-22 09:35:26.818511: step: 260/77, loss: 0.08690030872821808
2023-01-22 09:35:28.312294: step: 264/77, loss: 0.01370689831674099
2023-01-22 09:35:29.859754: step: 268/77, loss: 0.14590376615524292
2023-01-22 09:35:31.288090: step: 272/77, loss: 0.003179072868078947
2023-01-22 09:35:32.749230: step: 276/77, loss: 0.0042409347370266914
2023-01-22 09:35:34.229977: step: 280/77, loss: 0.007665436249226332
2023-01-22 09:35:35.664886: step: 284/77, loss: 0.061556752771139145
2023-01-22 09:35:37.198618: step: 288/77, loss: 0.12139555811882019
2023-01-22 09:35:38.728500: step: 292/77, loss: 0.10933557152748108
2023-01-22 09:35:40.189869: step: 296/77, loss: 0.0040985699743032455
2023-01-22 09:35:41.610169: step: 300/77, loss: 0.012230083346366882
2023-01-22 09:35:43.105382: step: 304/77, loss: 0.11386236548423767
2023-01-22 09:35:44.609225: step: 308/77, loss: 0.0003976405132561922
2023-01-22 09:35:46.163889: step: 312/77, loss: 0.043285876512527466
2023-01-22 09:35:47.617039: step: 316/77, loss: 0.001523602637462318
2023-01-22 09:35:49.072575: step: 320/77, loss: 0.1256551891565323
2023-01-22 09:35:50.552235: step: 324/77, loss: 0.07823194563388824
2023-01-22 09:35:52.048896: step: 328/77, loss: 0.0037024905905127525
2023-01-22 09:35:53.575684: step: 332/77, loss: 0.05983438342809677
2023-01-22 09:35:54.995179: step: 336/77, loss: 0.052032772451639175
2023-01-22 09:35:56.506229: step: 340/77, loss: 0.0024174668360501528
2023-01-22 09:35:58.034598: step: 344/77, loss: 0.0021779723465442657
2023-01-22 09:35:59.571981: step: 348/77, loss: 0.13080300390720367
2023-01-22 09:36:01.056501: step: 352/77, loss: 0.0091065289452672
2023-01-22 09:36:02.530961: step: 356/77, loss: 0.030503802001476288
2023-01-22 09:36:04.017390: step: 360/77, loss: 0.00729318056255579
2023-01-22 09:36:05.516894: step: 364/77, loss: 0.05925387516617775
2023-01-22 09:36:07.032660: step: 368/77, loss: 0.015410172753036022
2023-01-22 09:36:08.565224: step: 372/77, loss: 0.013694683089852333
2023-01-22 09:36:10.052369: step: 376/77, loss: 0.09178860485553741
2023-01-22 09:36:11.432571: step: 380/77, loss: 0.022821731865406036
2023-01-22 09:36:12.971834: step: 384/77, loss: 0.10924479365348816
2023-01-22 09:36:14.482621: step: 388/77, loss: 0.020602600648999214
==================================================
Loss: 0.032
--------------------
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': 4}
Test Chinese: {'template': {'p': 0.8767123287671232, 'r': 0.48854961832061067, 'f1': 0.6274509803921569}, 'slot': {'p': 0.45454545454545453, 'r': 0.012942191544434857, 'f1': 0.025167785234899324}, 'combined': 0.01579155151993683, 'epoch': 4}
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': 4}
Test Korean: {'template': {'p': 0.8888888888888888, 'r': 0.48854961832061067, 'f1': 0.6305418719211823}, 'slot': {'p': 0.46875, 'r': 0.012942191544434857, 'f1': 0.025188916876574305}, 'combined': 0.015882666799022224, 'epoch': 4}
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': 4}
Test Russian: {'template': {'p': 0.8767123287671232, 'r': 0.48854961832061067, 'f1': 0.6274509803921569}, 'slot': {'p': 0.45454545454545453, 'r': 0.012942191544434857, 'f1': 0.025167785234899324}, 'combined': 0.01579155151993683, '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': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, 'epoch': 4}
==================================================
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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 09:37:52.167539: step: 4/77, loss: 0.024476751685142517
2023-01-22 09:37:53.699545: step: 8/77, loss: 0.11043231189250946
2023-01-22 09:37:55.213340: step: 12/77, loss: 0.040273018181324005
2023-01-22 09:37:56.709880: step: 16/77, loss: 0.007355161011219025
2023-01-22 09:37:58.192353: step: 20/77, loss: 0.02030954509973526
2023-01-22 09:37:59.635002: step: 24/77, loss: 0.009412623941898346
2023-01-22 09:38:01.130870: step: 28/77, loss: 0.030328869819641113
2023-01-22 09:38:02.582625: step: 32/77, loss: 0.019532401114702225
2023-01-22 09:38:04.050266: step: 36/77, loss: 0.0017457769718021154
2023-01-22 09:38:05.470697: step: 40/77, loss: 0.028483323752880096
2023-01-22 09:38:06.936214: step: 44/77, loss: 0.18267452716827393
2023-01-22 09:38:08.485868: step: 48/77, loss: 0.01519215852022171
2023-01-22 09:38:09.998133: step: 52/77, loss: 0.023144662380218506
2023-01-22 09:38:11.510273: step: 56/77, loss: 0.02538256347179413
2023-01-22 09:38:13.013008: step: 60/77, loss: 0.008262258023023605
2023-01-22 09:38:14.552869: step: 64/77, loss: 0.019567331299185753
2023-01-22 09:38:15.991053: step: 68/77, loss: 0.004387851804494858
2023-01-22 09:38:17.460406: step: 72/77, loss: 0.03609474003314972
2023-01-22 09:38:18.952640: step: 76/77, loss: 0.027372196316719055
2023-01-22 09:38:20.421826: step: 80/77, loss: 0.08391016721725464
2023-01-22 09:38:21.905361: step: 84/77, loss: 0.05477209761738777
2023-01-22 09:38:23.392817: step: 88/77, loss: 0.018585750833153725
2023-01-22 09:38:24.858682: step: 92/77, loss: 0.03730151802301407
2023-01-22 09:38:26.372738: step: 96/77, loss: 0.04512316733598709
2023-01-22 09:38:27.849968: step: 100/77, loss: 0.057060979306697845
2023-01-22 09:38:29.327867: step: 104/77, loss: 0.032657966017723083
2023-01-22 09:38:30.850536: step: 108/77, loss: 0.016146738082170486
2023-01-22 09:38:32.357769: step: 112/77, loss: 0.0069486647844314575
2023-01-22 09:38:33.843548: step: 116/77, loss: 0.1186465322971344
2023-01-22 09:38:35.302478: step: 120/77, loss: 0.017615636810660362
2023-01-22 09:38:36.778732: step: 124/77, loss: 0.009101053699851036
2023-01-22 09:38:38.257250: step: 128/77, loss: 0.002567005343735218
2023-01-22 09:38:39.745185: step: 132/77, loss: 0.027679648250341415
2023-01-22 09:38:41.205319: step: 136/77, loss: 0.016381870955228806
2023-01-22 09:38:42.670921: step: 140/77, loss: 0.10870490223169327
2023-01-22 09:38:44.183794: step: 144/77, loss: 0.02034395933151245
2023-01-22 09:38:45.704939: step: 148/77, loss: 0.02121562510728836
2023-01-22 09:38:47.214632: step: 152/77, loss: 0.01823749952018261
2023-01-22 09:38:48.778229: step: 156/77, loss: 0.0024375556968152523
2023-01-22 09:38:50.282131: step: 160/77, loss: 0.022238213568925858
2023-01-22 09:38:51.752607: step: 164/77, loss: 0.018150899559259415
2023-01-22 09:38:53.261027: step: 168/77, loss: 0.062192972749471664
2023-01-22 09:38:54.739265: step: 172/77, loss: 0.04013078287243843
2023-01-22 09:38:56.238333: step: 176/77, loss: 0.033303748816251755
2023-01-22 09:38:57.784967: step: 180/77, loss: 0.019885744899511337
2023-01-22 09:38:59.291802: step: 184/77, loss: 0.02491719275712967
2023-01-22 09:39:00.848099: step: 188/77, loss: 0.013048075139522552
2023-01-22 09:39:02.390745: step: 192/77, loss: 0.023345254361629486
2023-01-22 09:39:03.864940: step: 196/77, loss: 0.037435151636600494
2023-01-22 09:39:05.310018: step: 200/77, loss: 0.018141061067581177
2023-01-22 09:39:06.761252: step: 204/77, loss: 0.03752421215176582
2023-01-22 09:39:08.257178: step: 208/77, loss: 0.01851789653301239
2023-01-22 09:39:09.681116: step: 212/77, loss: 0.0015066369669511914
2023-01-22 09:39:11.136651: step: 216/77, loss: 0.050621166825294495
2023-01-22 09:39:12.689363: step: 220/77, loss: 0.08110310137271881
2023-01-22 09:39:14.173810: step: 224/77, loss: 0.04713662341237068
2023-01-22 09:39:15.698794: step: 228/77, loss: 0.017320964485406876
2023-01-22 09:39:17.101465: step: 232/77, loss: 0.025410648435354233
2023-01-22 09:39:18.653441: step: 236/77, loss: 0.011799340136349201
2023-01-22 09:39:20.139742: step: 240/77, loss: 0.10319054871797562
2023-01-22 09:39:21.643238: step: 244/77, loss: 0.01371192466467619
2023-01-22 09:39:23.063764: step: 248/77, loss: 0.011762048117816448
2023-01-22 09:39:24.549827: step: 252/77, loss: 0.07716451585292816
2023-01-22 09:39:26.057806: step: 256/77, loss: 0.006613610312342644
2023-01-22 09:39:27.517482: step: 260/77, loss: 0.04181970655918121
2023-01-22 09:39:29.017676: step: 264/77, loss: 0.00952971912920475
2023-01-22 09:39:30.544113: step: 268/77, loss: 0.007909356616437435
2023-01-22 09:39:31.964137: step: 272/77, loss: 0.025044672191143036
2023-01-22 09:39:33.407691: step: 276/77, loss: 0.003298920812085271
2023-01-22 09:39:34.906222: step: 280/77, loss: 0.07326558977365494
2023-01-22 09:39:36.367539: step: 284/77, loss: 0.07228539884090424
2023-01-22 09:39:37.789355: step: 288/77, loss: 0.018365979194641113
2023-01-22 09:39:39.239661: step: 292/77, loss: 0.0013023103820160031
2023-01-22 09:39:40.743076: step: 296/77, loss: 0.01624615490436554
2023-01-22 09:39:42.237625: step: 300/77, loss: 0.03355495631694794
2023-01-22 09:39:43.689084: step: 304/77, loss: 0.0013003923231735826
2023-01-22 09:39:45.181754: step: 308/77, loss: 0.007164771668612957
2023-01-22 09:39:46.632947: step: 312/77, loss: 0.05500699207186699
2023-01-22 09:39:48.103240: step: 316/77, loss: 0.019462941214442253
2023-01-22 09:39:49.544796: step: 320/77, loss: 0.0029178541153669357
2023-01-22 09:39:50.986570: step: 324/77, loss: 0.06747382134199142
2023-01-22 09:39:52.439946: step: 328/77, loss: 0.013694136403501034
2023-01-22 09:39:53.929883: step: 332/77, loss: 0.028184257447719574
2023-01-22 09:39:55.346332: step: 336/77, loss: 0.1709933876991272
2023-01-22 09:39:56.778320: step: 340/77, loss: 0.013454165309667587
2023-01-22 09:39:58.253284: step: 344/77, loss: 0.019300248473882675
2023-01-22 09:39:59.819349: step: 348/77, loss: 0.007079022936522961
2023-01-22 09:40:01.313232: step: 352/77, loss: 0.06331252306699753
2023-01-22 09:40:02.820994: step: 356/77, loss: 0.018890781328082085
2023-01-22 09:40:04.259961: step: 360/77, loss: 0.07067049294710159
2023-01-22 09:40:05.792672: step: 364/77, loss: 0.004420126788318157
2023-01-22 09:40:07.322753: step: 368/77, loss: 0.02071470208466053
2023-01-22 09:40:08.790742: step: 372/77, loss: 0.03721703961491585
2023-01-22 09:40:10.311871: step: 376/77, loss: 0.0021472936496138573
2023-01-22 09:40:11.822050: step: 380/77, loss: 0.0019225344294682145
2023-01-22 09:40:13.297387: step: 384/77, loss: 0.0833422914147377
2023-01-22 09:40:14.759495: step: 388/77, loss: 0.019889041781425476
==================================================
Loss: 0.033
--------------------
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': 0.9027777777777778, 'r': 0.4961832061068702, 'f1': 0.6403940886699507}, 'slot': {'p': 0.4473684210526316, 'r': 0.014667817083692839, 'f1': 0.028404344193817876}, 'combined': 0.018189974114267607, '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': 0.9142857142857143, 'r': 0.48854961832061067, 'f1': 0.6368159203980099}, 'slot': {'p': 0.4594594594594595, 'r': 0.014667817083692839, 'f1': 0.028428093645484948}, 'combined': 0.018103462620010315, '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': 0.8888888888888888, 'r': 0.48854961832061067, 'f1': 0.6305418719211823}, 'slot': {'p': 0.42105263157894735, 'r': 0.013805004314063849, 'f1': 0.026733500417710946}, 'combined': 0.01685659139638917, '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}
==================================================
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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 09:41:52.763290: step: 4/77, loss: 0.03039437159895897
2023-01-22 09:41:54.267337: step: 8/77, loss: 0.0026546369772404432
2023-01-22 09:41:55.765624: step: 12/77, loss: 0.028612440451979637
2023-01-22 09:41:57.223525: step: 16/77, loss: 0.030664879828691483
2023-01-22 09:41:58.668361: step: 20/77, loss: 0.0023875534534454346
2023-01-22 09:42:00.156602: step: 24/77, loss: 0.0006607776740565896
2023-01-22 09:42:01.588952: step: 28/77, loss: 0.007618624716997147
2023-01-22 09:42:03.082524: step: 32/77, loss: 0.028325766324996948
2023-01-22 09:42:04.561269: step: 36/77, loss: 0.012421460822224617
2023-01-22 09:42:05.991661: step: 40/77, loss: 0.016435008496046066
2023-01-22 09:42:07.437680: step: 44/77, loss: 0.0659736841917038
2023-01-22 09:42:08.956996: step: 48/77, loss: 0.010327223688364029
2023-01-22 09:42:10.457910: step: 52/77, loss: 0.0065464754588902
2023-01-22 09:42:12.001236: step: 56/77, loss: 0.057871297001838684
2023-01-22 09:42:13.403308: step: 60/77, loss: 0.002542986534535885
2023-01-22 09:42:14.953046: step: 64/77, loss: 0.006201583426445723
2023-01-22 09:42:16.465404: step: 68/77, loss: 0.01481205690652132
2023-01-22 09:42:17.920655: step: 72/77, loss: 0.0031775743700563908
2023-01-22 09:42:19.394363: step: 76/77, loss: 0.026160014793276787
2023-01-22 09:42:20.810084: step: 80/77, loss: 0.012620776891708374
2023-01-22 09:42:22.313627: step: 84/77, loss: 0.0677712932229042
2023-01-22 09:42:23.774717: step: 88/77, loss: 0.0394502654671669
2023-01-22 09:42:25.253539: step: 92/77, loss: 0.07249009609222412
2023-01-22 09:42:26.708699: step: 96/77, loss: 0.009052613750100136
2023-01-22 09:42:28.229439: step: 100/77, loss: 0.08241299539804459
2023-01-22 09:42:29.736586: step: 104/77, loss: 0.02526727318763733
2023-01-22 09:42:31.219135: step: 108/77, loss: 0.023446206003427505
2023-01-22 09:42:32.744643: step: 112/77, loss: 0.003657972440123558
2023-01-22 09:42:34.256716: step: 116/77, loss: 0.04917879030108452
2023-01-22 09:42:35.739026: step: 120/77, loss: 0.029167205095291138
2023-01-22 09:42:37.195087: step: 124/77, loss: 0.00030399844399653375
2023-01-22 09:42:38.682291: step: 128/77, loss: 0.02055046521127224
2023-01-22 09:42:40.170703: step: 132/77, loss: 0.03628047555685043
2023-01-22 09:42:41.648732: step: 136/77, loss: 0.000510257261339575
2023-01-22 09:42:43.197198: step: 140/77, loss: 1.6263384168269113e-05
2023-01-22 09:42:44.649178: step: 144/77, loss: 0.04925939813256264
2023-01-22 09:42:46.201747: step: 148/77, loss: 0.01939420960843563
2023-01-22 09:42:47.699406: step: 152/77, loss: 0.023076839745044708
2023-01-22 09:42:49.137325: step: 156/77, loss: 0.019336925819516182
2023-01-22 09:42:50.695589: step: 160/77, loss: 0.052915360778570175
2023-01-22 09:42:52.217082: step: 164/77, loss: 0.010208374820649624
2023-01-22 09:42:53.676094: step: 168/77, loss: 0.010052263736724854
2023-01-22 09:42:55.215614: step: 172/77, loss: 0.018969284370541573
2023-01-22 09:42:56.697677: step: 176/77, loss: 0.011579119600355625
2023-01-22 09:42:58.138638: step: 180/77, loss: 0.0002825237170327455
2023-01-22 09:42:59.684698: step: 184/77, loss: 0.0627252608537674
2023-01-22 09:43:01.180844: step: 188/77, loss: 0.005596342496573925
2023-01-22 09:43:02.655248: step: 192/77, loss: 0.07881352305412292
2023-01-22 09:43:04.109537: step: 196/77, loss: 0.10441139340400696
2023-01-22 09:43:05.551273: step: 200/77, loss: 0.06772737950086594
2023-01-22 09:43:07.121574: step: 204/77, loss: 0.018566543236374855
2023-01-22 09:43:08.620538: step: 208/77, loss: 0.08514667302370071
2023-01-22 09:43:10.150304: step: 212/77, loss: 0.003423793241381645
2023-01-22 09:43:11.576758: step: 216/77, loss: 0.017923181876540184
2023-01-22 09:43:13.081896: step: 220/77, loss: 0.05222643166780472
2023-01-22 09:43:14.510055: step: 224/77, loss: 0.008815684355795383
2023-01-22 09:43:16.013648: step: 228/77, loss: 0.0019420962780714035
2023-01-22 09:43:17.471662: step: 232/77, loss: 0.11282327771186829
2023-01-22 09:43:18.979719: step: 236/77, loss: 0.01948855072259903
2023-01-22 09:43:20.461605: step: 240/77, loss: 0.06035421043634415
2023-01-22 09:43:21.910695: step: 244/77, loss: 0.09459991753101349
2023-01-22 09:43:23.353618: step: 248/77, loss: 0.006792946252971888
2023-01-22 09:43:24.786826: step: 252/77, loss: 0.06218063831329346
2023-01-22 09:43:26.222837: step: 256/77, loss: 0.023452896624803543
2023-01-22 09:43:27.738807: step: 260/77, loss: 0.0018449525814503431
2023-01-22 09:43:29.131649: step: 264/77, loss: 0.05207361653447151
2023-01-22 09:43:30.610163: step: 268/77, loss: 0.00742388516664505
2023-01-22 09:43:32.069762: step: 272/77, loss: 0.00440608337521553
2023-01-22 09:43:33.522951: step: 276/77, loss: 0.013198236003518105
2023-01-22 09:43:34.956297: step: 280/77, loss: 0.011632833629846573
2023-01-22 09:43:36.506066: step: 284/77, loss: 0.006646803580224514
2023-01-22 09:43:37.964241: step: 288/77, loss: 0.010615387000143528
2023-01-22 09:43:39.501906: step: 292/77, loss: 0.012356102466583252
2023-01-22 09:43:41.011010: step: 296/77, loss: 0.0011919524986296892
2023-01-22 09:43:42.485725: step: 300/77, loss: 0.04278775304555893
2023-01-22 09:43:43.961113: step: 304/77, loss: 0.05970532447099686
2023-01-22 09:43:45.418934: step: 308/77, loss: 0.03060147911310196
2023-01-22 09:43:46.929888: step: 312/77, loss: 0.01697326824069023
2023-01-22 09:43:48.368199: step: 316/77, loss: 0.040285106748342514
2023-01-22 09:43:49.824165: step: 320/77, loss: 0.020163346081972122
2023-01-22 09:43:51.340802: step: 324/77, loss: 0.007350889965891838
2023-01-22 09:43:52.777368: step: 328/77, loss: 0.01338155660778284
2023-01-22 09:43:54.267877: step: 332/77, loss: 0.022605765610933304
2023-01-22 09:43:55.797414: step: 336/77, loss: 0.03450581803917885
2023-01-22 09:43:57.268696: step: 340/77, loss: 0.03401753678917885
2023-01-22 09:43:58.734102: step: 344/77, loss: 0.011614415794610977
2023-01-22 09:44:00.282116: step: 348/77, loss: 0.04379738122224808
2023-01-22 09:44:01.735091: step: 352/77, loss: 0.16224682331085205
2023-01-22 09:44:03.209994: step: 356/77, loss: 0.00017778918845579028
2023-01-22 09:44:04.678799: step: 360/77, loss: 0.002048301976174116
2023-01-22 09:44:06.093122: step: 364/77, loss: 0.02142212726175785
2023-01-22 09:44:07.580841: step: 368/77, loss: 0.007760262116789818
2023-01-22 09:44:09.126775: step: 372/77, loss: 0.017139358446002007
2023-01-22 09:44:10.589903: step: 376/77, loss: 0.007925149984657764
2023-01-22 09:44:12.054681: step: 380/77, loss: 0.028815656900405884
2023-01-22 09:44:13.481260: step: 384/77, loss: 0.0073576332069933414
2023-01-22 09:44:14.910297: step: 388/77, loss: 0.0014327471144497395
==================================================
Loss: 0.028
--------------------
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': 6}
Test Chinese: {'template': {'p': 0.875, 'r': 0.48091603053435117, 'f1': 0.6206896551724138}, 'slot': {'p': 0.3695652173913043, 'r': 0.014667817083692839, 'f1': 0.028215767634854772}, 'combined': 0.017513235083702963, 'epoch': 6}
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': 6}
Test Korean: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.391304347826087, 'r': 0.015530629853321829, 'f1': 0.029875518672199168}, 'combined': 0.018452526238711256, 'epoch': 6}
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': 6}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3695652173913043, 'r': 0.014667817083692839, 'f1': 0.028215767634854772}, 'combined': 0.017427385892116187, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 09:45:52.200879: step: 4/77, loss: 0.012997529469430447
2023-01-22 09:45:53.673456: step: 8/77, loss: 0.020570045337080956
2023-01-22 09:45:55.132764: step: 12/77, loss: 0.04421515017747879
2023-01-22 09:45:56.534802: step: 16/77, loss: 0.032468900084495544
2023-01-22 09:45:58.054092: step: 20/77, loss: 0.03809467703104019
2023-01-22 09:45:59.587210: step: 24/77, loss: 0.011496270075440407
2023-01-22 09:46:01.055831: step: 28/77, loss: 0.019316416233778
2023-01-22 09:46:02.542186: step: 32/77, loss: 0.005474533885717392
2023-01-22 09:46:04.046817: step: 36/77, loss: 0.005868466105312109
2023-01-22 09:46:05.483386: step: 40/77, loss: 0.013153919950127602
2023-01-22 09:46:06.981316: step: 44/77, loss: 0.0031642599496990442
2023-01-22 09:46:08.408699: step: 48/77, loss: 0.005004220642149448
2023-01-22 09:46:09.846096: step: 52/77, loss: 0.01386738196015358
2023-01-22 09:46:11.295552: step: 56/77, loss: 0.013531411997973919
2023-01-22 09:46:12.881680: step: 60/77, loss: 0.01102381944656372
2023-01-22 09:46:14.349200: step: 64/77, loss: 0.012573636136949062
2023-01-22 09:46:15.808974: step: 68/77, loss: 0.0019415427232161164
2023-01-22 09:46:17.273744: step: 72/77, loss: 0.12153831124305725
2023-01-22 09:46:18.756851: step: 76/77, loss: 0.01277611218392849
2023-01-22 09:46:20.233346: step: 80/77, loss: 0.02256181091070175
2023-01-22 09:46:21.732317: step: 84/77, loss: 0.0024817378725856543
2023-01-22 09:46:23.211984: step: 88/77, loss: 0.012858950532972813
2023-01-22 09:46:24.738546: step: 92/77, loss: 6.024163303663954e-05
2023-01-22 09:46:26.223733: step: 96/77, loss: 0.012603029608726501
2023-01-22 09:46:27.698466: step: 100/77, loss: 0.00898762233555317
2023-01-22 09:46:29.209340: step: 104/77, loss: 0.01040840707719326
2023-01-22 09:46:30.631623: step: 108/77, loss: 0.009314004331827164
2023-01-22 09:46:32.206720: step: 112/77, loss: 0.002158994786441326
2023-01-22 09:46:33.676430: step: 116/77, loss: 0.001862498465925455
2023-01-22 09:46:35.087096: step: 120/77, loss: 0.004027359187602997
2023-01-22 09:46:36.616310: step: 124/77, loss: 0.0019363107858225703
2023-01-22 09:46:38.054245: step: 128/77, loss: 0.0674593448638916
2023-01-22 09:46:39.473290: step: 132/77, loss: 0.07844030112028122
2023-01-22 09:46:40.981136: step: 136/77, loss: 0.0004071201547048986
2023-01-22 09:46:42.508753: step: 140/77, loss: 0.040196869522333145
2023-01-22 09:46:43.950466: step: 144/77, loss: 0.02462776005268097
2023-01-22 09:46:45.404263: step: 148/77, loss: 0.018356427550315857
2023-01-22 09:46:46.854585: step: 152/77, loss: 0.02162858285009861
2023-01-22 09:46:48.258665: step: 156/77, loss: 0.009433625265955925
2023-01-22 09:46:49.774119: step: 160/77, loss: 0.009734027087688446
2023-01-22 09:46:51.290489: step: 164/77, loss: 0.0023181047290563583
2023-01-22 09:46:52.811548: step: 168/77, loss: 0.017527658492326736
2023-01-22 09:46:54.305023: step: 172/77, loss: 0.00703967921435833
2023-01-22 09:46:55.764501: step: 176/77, loss: 0.008034227415919304
2023-01-22 09:46:57.259859: step: 180/77, loss: 0.06797732412815094
2023-01-22 09:46:58.720809: step: 184/77, loss: 0.028809472918510437
2023-01-22 09:47:00.215185: step: 188/77, loss: 0.01280111912637949
2023-01-22 09:47:01.719529: step: 192/77, loss: 0.006291474215686321
2023-01-22 09:47:03.213739: step: 196/77, loss: 0.019357847049832344
2023-01-22 09:47:04.668193: step: 200/77, loss: 0.01437158789485693
2023-01-22 09:47:06.114775: step: 204/77, loss: 0.004847629461437464
2023-01-22 09:47:07.584621: step: 208/77, loss: 0.04459906369447708
2023-01-22 09:47:09.051986: step: 212/77, loss: 0.0019956021569669247
2023-01-22 09:47:10.527985: step: 216/77, loss: 0.008743159472942352
2023-01-22 09:47:11.975111: step: 220/77, loss: 0.06492185592651367
2023-01-22 09:47:13.417550: step: 224/77, loss: 0.04172681272029877
2023-01-22 09:47:14.943385: step: 228/77, loss: 0.03955743834376335
2023-01-22 09:47:16.346821: step: 232/77, loss: 0.0006398952100425959
2023-01-22 09:47:17.862289: step: 236/77, loss: 0.009599082171916962
2023-01-22 09:47:19.408364: step: 240/77, loss: 0.01301715150475502
2023-01-22 09:47:20.910966: step: 244/77, loss: 0.00035458861384540796
2023-01-22 09:47:22.384345: step: 248/77, loss: 0.007781412452459335
2023-01-22 09:47:23.906072: step: 252/77, loss: 0.02035202831029892
2023-01-22 09:47:25.414224: step: 256/77, loss: 0.012641222216188908
2023-01-22 09:47:26.884775: step: 260/77, loss: 0.05043390765786171
2023-01-22 09:47:28.321893: step: 264/77, loss: 0.011204622685909271
2023-01-22 09:47:29.830752: step: 268/77, loss: 0.004016530700027943
2023-01-22 09:47:31.250459: step: 272/77, loss: 0.002317877020686865
2023-01-22 09:47:32.847425: step: 276/77, loss: 0.0009432684746570885
2023-01-22 09:47:34.345160: step: 280/77, loss: 0.0006387169123627245
2023-01-22 09:47:35.880637: step: 284/77, loss: 0.0016859809402376413
2023-01-22 09:47:37.400121: step: 288/77, loss: 0.03399414196610451
2023-01-22 09:47:38.928453: step: 292/77, loss: 0.015151074156165123
2023-01-22 09:47:40.436670: step: 296/77, loss: 0.02047363668680191
2023-01-22 09:47:41.869593: step: 300/77, loss: 0.038063161075115204
2023-01-22 09:47:43.289237: step: 304/77, loss: 0.00330452062189579
2023-01-22 09:47:44.719067: step: 308/77, loss: 0.011480795219540596
2023-01-22 09:47:46.167739: step: 312/77, loss: 0.019310910254716873
2023-01-22 09:47:47.610195: step: 316/77, loss: 0.015391256660223007
2023-01-22 09:47:49.150950: step: 320/77, loss: 0.010779057629406452
2023-01-22 09:47:50.586629: step: 324/77, loss: 0.007522165309637785
2023-01-22 09:47:52.081875: step: 328/77, loss: 0.02136208489537239
2023-01-22 09:47:53.560280: step: 332/77, loss: 0.01059940829873085
2023-01-22 09:47:55.038031: step: 336/77, loss: 0.00015911197988316417
2023-01-22 09:47:56.550828: step: 340/77, loss: 0.050910405814647675
2023-01-22 09:47:57.972476: step: 344/77, loss: 0.00024434231454506516
2023-01-22 09:47:59.436262: step: 348/77, loss: 0.010583743453025818
2023-01-22 09:48:00.938190: step: 352/77, loss: 0.025950804352760315
2023-01-22 09:48:02.370318: step: 356/77, loss: 0.024648727849125862
2023-01-22 09:48:03.827629: step: 360/77, loss: 0.010220241732895374
2023-01-22 09:48:05.320418: step: 364/77, loss: 0.042353857308626175
2023-01-22 09:48:06.750440: step: 368/77, loss: 0.01584051176905632
2023-01-22 09:48:08.235482: step: 372/77, loss: 0.02006104774773121
2023-01-22 09:48:09.778195: step: 376/77, loss: 0.020328937098383904
2023-01-22 09:48:11.275467: step: 380/77, loss: 0.020396513864398003
2023-01-22 09:48:12.767660: step: 384/77, loss: 0.03346937522292137
2023-01-22 09:48:14.300505: step: 388/77, loss: 0.061174191534519196
==================================================
Loss: 0.019
--------------------
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': 7}
Test Chinese: {'template': {'p': 0.8955223880597015, 'r': 0.4580152671755725, 'f1': 0.6060606060606061}, 'slot': {'p': 0.45, 'r': 0.015530629853321829, 'f1': 0.030025020850708923}, 'combined': 0.018196982333762983, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.55, 'f1': 0.7096774193548387}, 'slot': {'p': 0.5, 'r': 0.035916824196597356, 'f1': 0.0670194003527337}, 'combined': 0.04756215508903682, 'epoch': 7}
Test Korean: {'template': {'p': 0.8939393939393939, 'r': 0.45038167938931295, 'f1': 0.598984771573604}, 'slot': {'p': 0.4594594594594595, 'r': 0.014667817083692839, 'f1': 0.028428093645484948}, 'combined': 0.017027995178513826, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.55, 'f1': 0.7096774193548387}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.04988944951527864, 'epoch': 7}
Test Russian: {'template': {'p': 0.9076923076923077, 'r': 0.45038167938931295, 'f1': 0.6020408163265306}, 'slot': {'p': 0.4864864864864865, 'r': 0.015530629853321829, 'f1': 0.030100334448160532}, 'combined': 0.018121629922872157, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 09:49:51.960733: step: 4/77, loss: 0.0067916191183030605
2023-01-22 09:49:53.405304: step: 8/77, loss: 0.013048367574810982
2023-01-22 09:49:54.886275: step: 12/77, loss: 0.03453684225678444
2023-01-22 09:49:56.337849: step: 16/77, loss: 0.00477053876966238
2023-01-22 09:49:57.812172: step: 20/77, loss: 0.022574584931135178
2023-01-22 09:49:59.304647: step: 24/77, loss: 0.03624827042222023
2023-01-22 09:50:00.769432: step: 28/77, loss: 0.013998491689562798
2023-01-22 09:50:02.322729: step: 32/77, loss: 0.007175574544817209
2023-01-22 09:50:03.844935: step: 36/77, loss: 0.029678918421268463
2023-01-22 09:50:05.324979: step: 40/77, loss: 0.026228811591863632
2023-01-22 09:50:06.748117: step: 44/77, loss: 0.0012878580018877983
2023-01-22 09:50:08.236983: step: 48/77, loss: 0.010943735018372536
2023-01-22 09:50:09.733571: step: 52/77, loss: 0.0012138265883550048
2023-01-22 09:50:11.197671: step: 56/77, loss: 0.017435984686017036
2023-01-22 09:50:12.699860: step: 60/77, loss: 0.00820908322930336
2023-01-22 09:50:14.210046: step: 64/77, loss: 0.21635589003562927
2023-01-22 09:50:15.768997: step: 68/77, loss: 0.09472758322954178
2023-01-22 09:50:17.214973: step: 72/77, loss: 0.030867278575897217
2023-01-22 09:50:18.708833: step: 76/77, loss: 0.008024647831916809
2023-01-22 09:50:20.182964: step: 80/77, loss: 0.0015849823830649257
2023-01-22 09:50:21.664263: step: 84/77, loss: 0.019332479685544968
2023-01-22 09:50:23.141368: step: 88/77, loss: 0.003665961092337966
2023-01-22 09:50:24.574408: step: 92/77, loss: 0.04837939888238907
2023-01-22 09:50:26.059983: step: 96/77, loss: 0.007896811701357365
2023-01-22 09:50:27.587954: step: 100/77, loss: 0.017443090677261353
2023-01-22 09:50:29.216757: step: 104/77, loss: 0.04705725982785225
2023-01-22 09:50:30.628773: step: 108/77, loss: 0.0034224099945276976
2023-01-22 09:50:32.080309: step: 112/77, loss: 0.0312179122120142
2023-01-22 09:50:33.603576: step: 116/77, loss: 0.029161768034100533
2023-01-22 09:50:35.086350: step: 120/77, loss: 0.005436992272734642
2023-01-22 09:50:36.562274: step: 124/77, loss: 0.008618153631687164
2023-01-22 09:50:38.027396: step: 128/77, loss: 0.0025659631937742233
2023-01-22 09:50:39.509682: step: 132/77, loss: 0.004739833064377308
2023-01-22 09:50:40.977449: step: 136/77, loss: 0.12532849609851837
2023-01-22 09:50:42.429753: step: 140/77, loss: 0.012651849538087845
2023-01-22 09:50:43.846756: step: 144/77, loss: 0.0029987136367708445
2023-01-22 09:50:45.351487: step: 148/77, loss: 0.0017156063113361597
2023-01-22 09:50:46.838590: step: 152/77, loss: 0.011197465471923351
2023-01-22 09:50:48.269256: step: 156/77, loss: 0.05191802978515625
2023-01-22 09:50:49.798160: step: 160/77, loss: 0.01135370321571827
2023-01-22 09:50:51.295069: step: 164/77, loss: 0.03425750881433487
2023-01-22 09:50:52.770447: step: 168/77, loss: 0.009411108680069447
2023-01-22 09:50:54.208750: step: 172/77, loss: 0.010142726823687553
2023-01-22 09:50:55.618565: step: 176/77, loss: 0.0025873896665871143
2023-01-22 09:50:57.163285: step: 180/77, loss: 0.017334995791316032
2023-01-22 09:50:58.660736: step: 184/77, loss: 0.004583724774420261
2023-01-22 09:51:00.131824: step: 188/77, loss: 0.006915468256920576
2023-01-22 09:51:01.503854: step: 192/77, loss: 0.013365627266466618
2023-01-22 09:51:02.945146: step: 196/77, loss: 0.0026318528689444065
2023-01-22 09:51:04.392257: step: 200/77, loss: 0.013050251640379429
2023-01-22 09:51:05.892533: step: 204/77, loss: 0.01102149672806263
2023-01-22 09:51:07.405317: step: 208/77, loss: 0.005182032473385334
2023-01-22 09:51:08.946882: step: 212/77, loss: 0.032337501645088196
2023-01-22 09:51:10.444511: step: 216/77, loss: 0.025232627987861633
2023-01-22 09:51:11.973863: step: 220/77, loss: 0.026668911799788475
2023-01-22 09:51:13.428469: step: 224/77, loss: 0.0707787573337555
2023-01-22 09:51:14.920268: step: 228/77, loss: 0.018818672746419907
2023-01-22 09:51:16.324398: step: 232/77, loss: 0.0017937154043465853
2023-01-22 09:51:17.816610: step: 236/77, loss: 0.0008982113795354962
2023-01-22 09:51:19.371800: step: 240/77, loss: 0.08587608486413956
2023-01-22 09:51:20.826555: step: 244/77, loss: 0.021022209897637367
2023-01-22 09:51:22.255904: step: 248/77, loss: 0.05474882945418358
2023-01-22 09:51:23.786696: step: 252/77, loss: 0.004854440223425627
2023-01-22 09:51:25.203631: step: 256/77, loss: 0.013054034672677517
2023-01-22 09:51:26.698021: step: 260/77, loss: 0.022247303277254105
2023-01-22 09:51:28.190891: step: 264/77, loss: 0.010746228508651257
2023-01-22 09:51:29.582031: step: 268/77, loss: 0.06552846729755402
2023-01-22 09:51:31.092205: step: 272/77, loss: 0.005899173207581043
2023-01-22 09:51:32.609725: step: 276/77, loss: 0.006159973330795765
2023-01-22 09:51:34.112797: step: 280/77, loss: 0.12346875667572021
2023-01-22 09:51:35.520368: step: 284/77, loss: 0.011204426176846027
2023-01-22 09:51:36.934682: step: 288/77, loss: 0.018768085166811943
2023-01-22 09:51:38.324323: step: 292/77, loss: 0.008486710488796234
2023-01-22 09:51:39.777787: step: 296/77, loss: 0.036354124546051025
2023-01-22 09:51:41.262850: step: 300/77, loss: 0.0038927635177969933
2023-01-22 09:51:42.664310: step: 304/77, loss: 0.002151659457013011
2023-01-22 09:51:44.158145: step: 308/77, loss: 0.0006010127253830433
2023-01-22 09:51:45.687082: step: 312/77, loss: 0.038890399038791656
2023-01-22 09:51:47.090838: step: 316/77, loss: 0.015262553468346596
2023-01-22 09:51:48.565050: step: 320/77, loss: 0.004743649158626795
2023-01-22 09:51:50.055542: step: 324/77, loss: 0.05304583162069321
2023-01-22 09:51:51.521395: step: 328/77, loss: 0.021255943924188614
2023-01-22 09:51:52.946215: step: 332/77, loss: 0.004364157095551491
2023-01-22 09:51:54.399282: step: 336/77, loss: 0.010830073617398739
2023-01-22 09:51:55.874909: step: 340/77, loss: 0.013078930787742138
2023-01-22 09:51:57.416519: step: 344/77, loss: 0.10247281193733215
2023-01-22 09:51:58.843909: step: 348/77, loss: 0.04736286401748657
2023-01-22 09:52:00.252258: step: 352/77, loss: 0.033875543624162674
2023-01-22 09:52:01.731845: step: 356/77, loss: 0.0046717822551727295
2023-01-22 09:52:03.210232: step: 360/77, loss: 0.011814633384346962
2023-01-22 09:52:04.600323: step: 364/77, loss: 0.0285545215010643
2023-01-22 09:52:05.956716: step: 368/77, loss: 0.015754615887999535
2023-01-22 09:52:07.415678: step: 372/77, loss: 0.05176156014204025
2023-01-22 09:52:08.955564: step: 376/77, loss: 0.01782143861055374
2023-01-22 09:52:10.451119: step: 380/77, loss: 0.011716475710272789
2023-01-22 09:52:11.968754: step: 384/77, loss: 0.0015753823099657893
2023-01-22 09:52:13.452421: step: 388/77, loss: 0.04279303923249245
==================================================
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': 8}
Test Chinese: {'template': {'p': 0.8805970149253731, 'r': 0.45038167938931295, 'f1': 0.5959595959595959}, 'slot': {'p': 0.45714285714285713, 'r': 0.013805004314063849, 'f1': 0.02680067001675042}, 'combined': 0.015972116474629035, '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': 0.8939393939393939, 'r': 0.45038167938931295, 'f1': 0.598984771573604}, 'slot': {'p': 0.45714285714285713, 'r': 0.013805004314063849, 'f1': 0.02680067001675042}, 'combined': 0.016053193208002785, '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': 0.8823529411764706, 'r': 0.4580152671755725, 'f1': 0.6030150753768845}, 'slot': {'p': 0.43243243243243246, 'r': 0.013805004314063849, 'f1': 0.026755852842809368}, 'combined': 0.01613418261877952, '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': 0.25, 'f1': 0.4}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 09:53:50.718140: step: 4/77, loss: 0.00931814406067133
2023-01-22 09:53:52.195921: step: 8/77, loss: 0.016727566719055176
2023-01-22 09:53:53.633580: step: 12/77, loss: 0.02211870439350605
2023-01-22 09:53:55.064600: step: 16/77, loss: 0.011608324013650417
2023-01-22 09:53:56.565966: step: 20/77, loss: 0.010061085224151611
2023-01-22 09:53:58.048904: step: 24/77, loss: 0.010383963584899902
2023-01-22 09:53:59.497414: step: 28/77, loss: 0.03394642099738121
2023-01-22 09:54:00.986490: step: 32/77, loss: 0.0005709524848498404
2023-01-22 09:54:02.521165: step: 36/77, loss: 0.010349091142416
2023-01-22 09:54:03.992882: step: 40/77, loss: 0.002377279568463564
2023-01-22 09:54:05.499991: step: 44/77, loss: 0.009859619662165642
2023-01-22 09:54:07.027526: step: 48/77, loss: 0.010785480029881
2023-01-22 09:54:08.537814: step: 52/77, loss: 0.021909940987825394
2023-01-22 09:54:10.017469: step: 56/77, loss: 0.0010997147765010595
2023-01-22 09:54:11.517140: step: 60/77, loss: 0.005814129486680031
2023-01-22 09:54:13.066943: step: 64/77, loss: 0.0011625312035903335
2023-01-22 09:54:14.522434: step: 68/77, loss: 0.02374696359038353
2023-01-22 09:54:16.045012: step: 72/77, loss: 0.010308654978871346
2023-01-22 09:54:17.539047: step: 76/77, loss: 0.0102377999573946
2023-01-22 09:54:19.046797: step: 80/77, loss: 0.012174428440630436
2023-01-22 09:54:20.579062: step: 84/77, loss: 0.00158389238640666
2023-01-22 09:54:22.057681: step: 88/77, loss: 0.0022693369537591934
2023-01-22 09:54:23.534122: step: 92/77, loss: 0.0003267589781899005
2023-01-22 09:54:24.960117: step: 96/77, loss: 0.03900589048862457
2023-01-22 09:54:26.445860: step: 100/77, loss: 0.01670156605541706
2023-01-22 09:54:27.903905: step: 104/77, loss: 0.001030667801387608
2023-01-22 09:54:29.341706: step: 108/77, loss: 0.00393590796738863
2023-01-22 09:54:30.806573: step: 112/77, loss: 0.04139762371778488
2023-01-22 09:54:32.271962: step: 116/77, loss: 0.0035628098994493484
2023-01-22 09:54:33.732152: step: 120/77, loss: 0.027284199371933937
2023-01-22 09:54:35.185154: step: 124/77, loss: 0.010536571964621544
2023-01-22 09:54:36.632383: step: 128/77, loss: 0.012623676098883152
2023-01-22 09:54:38.102457: step: 132/77, loss: 0.13224123418331146
2023-01-22 09:54:39.543293: step: 136/77, loss: 0.11464852094650269
2023-01-22 09:54:40.951740: step: 140/77, loss: 0.0009070251835510135
2023-01-22 09:54:42.450349: step: 144/77, loss: 0.034760989248752594
2023-01-22 09:54:43.933849: step: 148/77, loss: 0.025749383494257927
2023-01-22 09:54:45.461486: step: 152/77, loss: 0.026630792766809464
2023-01-22 09:54:46.853340: step: 156/77, loss: 0.00897565670311451
2023-01-22 09:54:48.313944: step: 160/77, loss: 0.029134489595890045
2023-01-22 09:54:49.784873: step: 164/77, loss: 0.0009648214327171445
2023-01-22 09:54:51.292238: step: 168/77, loss: 0.0089799165725708
2023-01-22 09:54:52.827704: step: 172/77, loss: 0.06454553455114365
2023-01-22 09:54:54.252409: step: 176/77, loss: 0.0012069199001416564
2023-01-22 09:54:55.741077: step: 180/77, loss: 0.05223080515861511
2023-01-22 09:54:57.194978: step: 184/77, loss: 0.015568587929010391
2023-01-22 09:54:58.654828: step: 188/77, loss: 0.011848854832351208
2023-01-22 09:55:00.115039: step: 192/77, loss: 0.013729307800531387
2023-01-22 09:55:01.578957: step: 196/77, loss: 0.012604327872395515
2023-01-22 09:55:03.045774: step: 200/77, loss: 0.032689254730939865
2023-01-22 09:55:04.488474: step: 204/77, loss: 0.009877309203147888
2023-01-22 09:55:05.961624: step: 208/77, loss: 0.008456312119960785
2023-01-22 09:55:07.407102: step: 212/77, loss: 0.009990466758608818
2023-01-22 09:55:08.890771: step: 216/77, loss: 0.012410677969455719
2023-01-22 09:55:10.442170: step: 220/77, loss: 0.0003021705197170377
2023-01-22 09:55:11.975159: step: 224/77, loss: 0.07351236045360565
2023-01-22 09:55:13.521195: step: 228/77, loss: 0.0010626473231241107
2023-01-22 09:55:14.959593: step: 232/77, loss: 0.030719848349690437
2023-01-22 09:55:16.389959: step: 236/77, loss: 0.017361463978886604
2023-01-22 09:55:17.842234: step: 240/77, loss: 0.005429819226264954
2023-01-22 09:55:19.340533: step: 244/77, loss: 0.0007189378957264125
2023-01-22 09:55:20.821556: step: 248/77, loss: 0.02332794852554798
2023-01-22 09:55:22.191639: step: 252/77, loss: 6.61729573039338e-05
2023-01-22 09:55:23.677303: step: 256/77, loss: 0.017682623118162155
2023-01-22 09:55:25.207191: step: 260/77, loss: 0.00020931556355208158
2023-01-22 09:55:26.696245: step: 264/77, loss: 0.004470092244446278
2023-01-22 09:55:28.253240: step: 268/77, loss: 0.0027932701632380486
2023-01-22 09:55:29.735751: step: 272/77, loss: 0.00921584665775299
2023-01-22 09:55:31.182254: step: 276/77, loss: 0.0022591277956962585
2023-01-22 09:55:32.675682: step: 280/77, loss: 0.00729965977370739
2023-01-22 09:55:34.174615: step: 284/77, loss: 0.06238330900669098
2023-01-22 09:55:35.658207: step: 288/77, loss: 0.04654904827475548
2023-01-22 09:55:37.196233: step: 292/77, loss: 0.017025865614414215
2023-01-22 09:55:38.759012: step: 296/77, loss: 0.010817298665642738
2023-01-22 09:55:40.214376: step: 300/77, loss: 0.009884810075163841
2023-01-22 09:55:41.669747: step: 304/77, loss: 0.0028474931605160236
2023-01-22 09:55:43.161442: step: 308/77, loss: 0.054710544645786285
2023-01-22 09:55:44.625953: step: 312/77, loss: 0.0037204334512352943
2023-01-22 09:55:46.142732: step: 316/77, loss: 0.014074725098907948
2023-01-22 09:55:47.629417: step: 320/77, loss: 0.014103882946074009
2023-01-22 09:55:49.173900: step: 324/77, loss: 0.01592918299138546
2023-01-22 09:55:50.698053: step: 328/77, loss: 0.018581323325634003
2023-01-22 09:55:52.184437: step: 332/77, loss: 0.015413613058626652
2023-01-22 09:55:53.636265: step: 336/77, loss: 0.011257076635956764
2023-01-22 09:55:55.135176: step: 340/77, loss: 0.006358277052640915
2023-01-22 09:55:56.609555: step: 344/77, loss: 0.00376639561727643
2023-01-22 09:55:58.058986: step: 348/77, loss: 0.0034146499820053577
2023-01-22 09:55:59.591227: step: 352/77, loss: 0.0217830128967762
2023-01-22 09:56:01.080141: step: 356/77, loss: 0.008566494099795818
2023-01-22 09:56:02.543501: step: 360/77, loss: 0.024732094258069992
2023-01-22 09:56:03.998811: step: 364/77, loss: 0.020356018096208572
2023-01-22 09:56:05.461696: step: 368/77, loss: 5.2446688641794026e-05
2023-01-22 09:56:06.783469: step: 372/77, loss: 0.0001511536247562617
2023-01-22 09:56:08.248587: step: 376/77, loss: 0.01291133277118206
2023-01-22 09:56:09.770278: step: 380/77, loss: 0.006426115054637194
2023-01-22 09:56:11.284619: step: 384/77, loss: 0.15697544813156128
2023-01-22 09:56:12.801908: step: 388/77, loss: 0.08485838770866394
==================================================
Loss: 0.019
--------------------
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': 0.9090909090909091, 'r': 0.4580152671755725, 'f1': 0.6091370558375634}, 'slot': {'p': 0.5, 'r': 0.013805004314063849, 'f1': 0.026868178001679264}, 'combined': 0.016366402843662493, 'epoch': 9}
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': 9}
Test Korean: {'template': {'p': 0.9104477611940298, 'r': 0.46564885496183206, 'f1': 0.6161616161616161}, 'slot': {'p': 0.4838709677419355, 'r': 0.012942191544434857, 'f1': 0.025210084033613443}, 'combined': 0.015533486121721413, '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': 0.9104477611940298, 'r': 0.46564885496183206, 'f1': 0.6161616161616161}, 'slot': {'p': 0.5151515151515151, 'r': 0.014667817083692839, 'f1': 0.02852348993288591}, 'combined': 0.01757507965561657, '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': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 09:57:50.480286: step: 4/77, loss: 0.0037124394439160824
2023-01-22 09:57:51.893403: step: 8/77, loss: 0.018964888527989388
2023-01-22 09:57:53.389318: step: 12/77, loss: 0.010961982421576977
2023-01-22 09:57:54.783029: step: 16/77, loss: 0.00022207949950825423
2023-01-22 09:57:56.278311: step: 20/77, loss: 0.02525768056511879
2023-01-22 09:57:57.805904: step: 24/77, loss: 0.006949287373572588
2023-01-22 09:57:59.257181: step: 28/77, loss: 0.017542913556098938
2023-01-22 09:58:00.733764: step: 32/77, loss: 0.007600500714033842
2023-01-22 09:58:02.251071: step: 36/77, loss: 0.07663308084011078
2023-01-22 09:58:03.740055: step: 40/77, loss: 0.01322341151535511
2023-01-22 09:58:05.223176: step: 44/77, loss: 0.0020390732679516077
2023-01-22 09:58:06.703483: step: 48/77, loss: 0.01980689913034439
2023-01-22 09:58:08.157390: step: 52/77, loss: 0.00036896448000334203
2023-01-22 09:58:09.661692: step: 56/77, loss: 0.012697389349341393
2023-01-22 09:58:11.178892: step: 60/77, loss: 0.04382698982954025
2023-01-22 09:58:12.708092: step: 64/77, loss: 0.009921489283442497
2023-01-22 09:58:14.103880: step: 68/77, loss: 0.0007633566856384277
2023-01-22 09:58:15.536141: step: 72/77, loss: 0.004064435604959726
2023-01-22 09:58:16.970951: step: 76/77, loss: 0.02458122745156288
2023-01-22 09:58:18.471857: step: 80/77, loss: 0.023752877488732338
2023-01-22 09:58:19.907038: step: 84/77, loss: 0.0001711217628326267
2023-01-22 09:58:21.460031: step: 88/77, loss: 0.06998871266841888
2023-01-22 09:58:22.924523: step: 92/77, loss: 0.009247813373804092
2023-01-22 09:58:24.406896: step: 96/77, loss: 0.005743591580539942
2023-01-22 09:58:25.815043: step: 100/77, loss: 0.01699553057551384
2023-01-22 09:58:27.303196: step: 104/77, loss: 0.011396847665309906
2023-01-22 09:58:28.867658: step: 108/77, loss: 0.08990509808063507
2023-01-22 09:58:30.302386: step: 112/77, loss: 0.004237010609358549
2023-01-22 09:58:31.762768: step: 116/77, loss: 0.0958765372633934
2023-01-22 09:58:33.260127: step: 120/77, loss: 0.014597264118492603
2023-01-22 09:58:34.788541: step: 124/77, loss: 0.021818269044160843
2023-01-22 09:58:36.296466: step: 128/77, loss: 0.0006683270330540836
2023-01-22 09:58:37.713604: step: 132/77, loss: 0.016099683940410614
2023-01-22 09:58:39.266722: step: 136/77, loss: 0.004529166035354137
2023-01-22 09:58:40.804574: step: 140/77, loss: 0.007304504048079252
2023-01-22 09:58:42.296308: step: 144/77, loss: 0.0021621109917759895
2023-01-22 09:58:43.798220: step: 148/77, loss: 0.038148678839206696
2023-01-22 09:58:45.305131: step: 152/77, loss: 0.002339947270229459
2023-01-22 09:58:46.813001: step: 156/77, loss: 0.010671212337911129
2023-01-22 09:58:48.228238: step: 160/77, loss: 0.0012018646812066436
2023-01-22 09:58:49.725941: step: 164/77, loss: 0.0007029086700640619
2023-01-22 09:58:51.170508: step: 168/77, loss: 0.05930791795253754
2023-01-22 09:58:52.701873: step: 172/77, loss: 0.06313134729862213
2023-01-22 09:58:54.258031: step: 176/77, loss: 0.0035771233960986137
2023-01-22 09:58:55.788509: step: 180/77, loss: 0.033747103065252304
2023-01-22 09:58:57.292097: step: 184/77, loss: 0.01955796591937542
2023-01-22 09:58:58.778431: step: 188/77, loss: 0.0012469518696889281
2023-01-22 09:59:00.244097: step: 192/77, loss: 0.03592196851968765
2023-01-22 09:59:01.726251: step: 196/77, loss: 0.009159698151051998
2023-01-22 09:59:03.226543: step: 200/77, loss: 0.05379951000213623
2023-01-22 09:59:04.628567: step: 204/77, loss: 0.0014175847172737122
2023-01-22 09:59:06.126833: step: 208/77, loss: 0.0003584384103305638
2023-01-22 09:59:07.612814: step: 212/77, loss: 0.0024745934642851353
2023-01-22 09:59:09.082504: step: 216/77, loss: 0.003314611967653036
2023-01-22 09:59:10.666140: step: 220/77, loss: 0.028728632256388664
2023-01-22 09:59:12.070645: step: 224/77, loss: 0.00189878954552114
2023-01-22 09:59:13.549984: step: 228/77, loss: 0.001966055715456605
2023-01-22 09:59:14.974036: step: 232/77, loss: 0.01825111173093319
2023-01-22 09:59:16.480771: step: 236/77, loss: 0.09419666230678558
2023-01-22 09:59:17.874237: step: 240/77, loss: 0.019170410931110382
2023-01-22 09:59:19.348976: step: 244/77, loss: 0.020276600494980812
2023-01-22 09:59:20.754659: step: 248/77, loss: 0.0032611675560474396
2023-01-22 09:59:22.281716: step: 252/77, loss: 0.09802025556564331
2023-01-22 09:59:23.679168: step: 256/77, loss: 0.011103980243206024
2023-01-22 09:59:25.087762: step: 260/77, loss: 0.016340192407369614
2023-01-22 09:59:26.610081: step: 264/77, loss: 0.001242226455360651
2023-01-22 09:59:28.094385: step: 268/77, loss: 0.03747468814253807
2023-01-22 09:59:29.528261: step: 272/77, loss: 0.028045082464814186
2023-01-22 09:59:30.996412: step: 276/77, loss: 0.016944503411650658
2023-01-22 09:59:32.523782: step: 280/77, loss: 0.01631280407309532
2023-01-22 09:59:33.961584: step: 284/77, loss: 0.030796894803643227
2023-01-22 09:59:35.415896: step: 288/77, loss: 0.005280392710119486
2023-01-22 09:59:36.838405: step: 292/77, loss: 0.10407906025648117
2023-01-22 09:59:38.314708: step: 296/77, loss: 0.00925945583730936
2023-01-22 09:59:39.805257: step: 300/77, loss: 0.005232213530689478
2023-01-22 09:59:41.297737: step: 304/77, loss: 0.03128921985626221
2023-01-22 09:59:42.757046: step: 308/77, loss: 0.00042872564517892897
2023-01-22 09:59:44.272718: step: 312/77, loss: 0.06519351154565811
2023-01-22 09:59:45.771789: step: 316/77, loss: 0.0005023244884796441
2023-01-22 09:59:47.199387: step: 320/77, loss: 0.0007901216158643365
2023-01-22 09:59:48.730186: step: 324/77, loss: 0.038823582231998444
2023-01-22 09:59:50.155024: step: 328/77, loss: 0.03915676474571228
2023-01-22 09:59:51.612806: step: 332/77, loss: 0.004828822799026966
2023-01-22 09:59:53.061151: step: 336/77, loss: 0.008032601326704025
2023-01-22 09:59:54.574800: step: 340/77, loss: 0.02326280064880848
2023-01-22 09:59:56.048142: step: 344/77, loss: 0.0006932779215276241
2023-01-22 09:59:57.535496: step: 348/77, loss: 0.0041923802345991135
2023-01-22 09:59:58.988369: step: 352/77, loss: 0.021920569241046906
2023-01-22 10:00:00.503348: step: 356/77, loss: 0.0004425476072356105
2023-01-22 10:00:01.968321: step: 360/77, loss: 0.05860942602157593
2023-01-22 10:00:03.415328: step: 364/77, loss: 0.010078839026391506
2023-01-22 10:00:04.948143: step: 368/77, loss: 0.00035972020123153925
2023-01-22 10:00:06.472823: step: 372/77, loss: 0.02206575870513916
2023-01-22 10:00:07.910077: step: 376/77, loss: 0.06646309792995453
2023-01-22 10:00:09.376970: step: 380/77, loss: 0.07609245181083679
2023-01-22 10:00:10.831565: step: 384/77, loss: 0.05032084882259369
2023-01-22 10:00:12.315884: step: 388/77, loss: 0.009962482377886772
==================================================
Loss: 0.022
--------------------
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': 0.9230769230769231, 'r': 0.4580152671755725, 'f1': 0.6122448979591837}, 'slot': {'p': 0.4857142857142857, 'r': 0.014667817083692839, 'f1': 0.02847571189279732}, 'combined': 0.01743410932212081, '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': 0.9242424242424242, 'r': 0.46564885496183206, 'f1': 0.6192893401015228}, 'slot': {'p': 0.4722222222222222, 'r': 0.014667817083692839, 'f1': 0.028451882845188285}, 'combined': 0.01761994775184249, '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': 0.9230769230769231, 'r': 0.4580152671755725, 'f1': 0.6122448979591837}, 'slot': {'p': 0.4857142857142857, 'r': 0.014667817083692839, 'f1': 0.02847571189279732}, 'combined': 0.01743410932212081, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 10:01:49.845722: step: 4/77, loss: 0.018249448388814926
2023-01-22 10:01:51.276802: step: 8/77, loss: 0.02742091938853264
2023-01-22 10:01:52.751145: step: 12/77, loss: 0.008343767374753952
2023-01-22 10:01:54.254411: step: 16/77, loss: 0.024018079042434692
2023-01-22 10:01:55.789957: step: 20/77, loss: 0.025947896763682365
2023-01-22 10:01:57.293754: step: 24/77, loss: 0.02267858199775219
2023-01-22 10:01:58.748271: step: 28/77, loss: 3.0612878617830575e-05
2023-01-22 10:02:00.247058: step: 32/77, loss: 0.0003211384464520961
2023-01-22 10:02:01.724890: step: 36/77, loss: 0.05688820034265518
2023-01-22 10:02:03.265476: step: 40/77, loss: 0.006101340986788273
2023-01-22 10:02:04.663927: step: 44/77, loss: 0.050070710480213165
2023-01-22 10:02:06.132698: step: 48/77, loss: 0.004720164462924004
2023-01-22 10:02:07.617429: step: 52/77, loss: 0.015022655948996544
2023-01-22 10:02:09.105679: step: 56/77, loss: 0.03563885763287544
2023-01-22 10:02:10.577915: step: 60/77, loss: 0.0330636128783226
2023-01-22 10:02:12.039786: step: 64/77, loss: 0.0014286059886217117
2023-01-22 10:02:13.533077: step: 68/77, loss: 0.000816542305983603
2023-01-22 10:02:15.016870: step: 72/77, loss: 0.01442760694772005
2023-01-22 10:02:16.496556: step: 76/77, loss: 9.378043614560738e-05
2023-01-22 10:02:17.973498: step: 80/77, loss: 0.0005923286080360413
2023-01-22 10:02:19.445085: step: 84/77, loss: 0.020105646923184395
2023-01-22 10:02:20.936963: step: 88/77, loss: 0.009484020993113518
2023-01-22 10:02:22.410204: step: 92/77, loss: 0.012684566900134087
2023-01-22 10:02:23.908081: step: 96/77, loss: 0.04148320108652115
2023-01-22 10:02:25.478786: step: 100/77, loss: 7.08875959389843e-05
2023-01-22 10:02:26.926550: step: 104/77, loss: 0.005405884236097336
2023-01-22 10:02:28.434153: step: 108/77, loss: 0.07155608385801315
2023-01-22 10:02:29.932278: step: 112/77, loss: 0.0010453937575221062
2023-01-22 10:02:31.364901: step: 116/77, loss: 0.009059806354343891
2023-01-22 10:02:32.770312: step: 120/77, loss: 0.02621476724743843
2023-01-22 10:02:34.259252: step: 124/77, loss: 0.002740699565038085
2023-01-22 10:02:35.688694: step: 128/77, loss: 0.010486319661140442
2023-01-22 10:02:37.187699: step: 132/77, loss: 0.01720418594777584
2023-01-22 10:02:38.657280: step: 136/77, loss: 0.00957572739571333
2023-01-22 10:02:40.123293: step: 140/77, loss: 0.003676429158076644
2023-01-22 10:02:41.628181: step: 144/77, loss: 0.009357225149869919
2023-01-22 10:02:43.106144: step: 148/77, loss: 0.03653610125184059
2023-01-22 10:02:44.557910: step: 152/77, loss: 0.04308353364467621
2023-01-22 10:02:46.047777: step: 156/77, loss: 0.05171763524413109
2023-01-22 10:02:47.520178: step: 160/77, loss: 0.004753998946398497
2023-01-22 10:02:48.995810: step: 164/77, loss: 3.090988684562035e-05
2023-01-22 10:02:50.499016: step: 168/77, loss: 0.013740334659814835
2023-01-22 10:02:51.999115: step: 172/77, loss: 0.015785954892635345
2023-01-22 10:02:53.457886: step: 176/77, loss: 0.019747678190469742
2023-01-22 10:02:54.983811: step: 180/77, loss: 0.009812500327825546
2023-01-22 10:02:56.520665: step: 184/77, loss: 0.022340651601552963
2023-01-22 10:02:57.989759: step: 188/77, loss: 0.013165976852178574
2023-01-22 10:02:59.428552: step: 192/77, loss: 0.0026761272456496954
2023-01-22 10:03:00.972122: step: 196/77, loss: 0.0722554549574852
2023-01-22 10:03:02.403410: step: 200/77, loss: 0.014125137589871883
2023-01-22 10:03:03.800592: step: 204/77, loss: 0.00012538768351078033
2023-01-22 10:03:05.217615: step: 208/77, loss: 0.015420390293002129
2023-01-22 10:03:06.614757: step: 212/77, loss: 0.035006795078516006
2023-01-22 10:03:08.124607: step: 216/77, loss: 0.016030533239245415
2023-01-22 10:03:09.608290: step: 220/77, loss: 0.00042447782470844686
2023-01-22 10:03:11.109489: step: 224/77, loss: 0.011341025121510029
2023-01-22 10:03:12.570532: step: 228/77, loss: 0.01798064447939396
2023-01-22 10:03:14.080807: step: 232/77, loss: 0.03821370005607605
2023-01-22 10:03:15.534798: step: 236/77, loss: 0.08387462049722672
2023-01-22 10:03:17.009415: step: 240/77, loss: 0.011262631975114346
2023-01-22 10:03:18.469025: step: 244/77, loss: 0.04161141812801361
2023-01-22 10:03:19.912291: step: 248/77, loss: 0.023375479504466057
2023-01-22 10:03:21.402646: step: 252/77, loss: 0.03386523202061653
2023-01-22 10:03:22.857579: step: 256/77, loss: 0.03562305495142937
2023-01-22 10:03:24.286647: step: 260/77, loss: 0.008851949125528336
2023-01-22 10:03:25.746483: step: 264/77, loss: 0.009420386515557766
2023-01-22 10:03:27.210482: step: 268/77, loss: 0.01851673051714897
2023-01-22 10:03:28.595831: step: 272/77, loss: 0.008063890039920807
2023-01-22 10:03:30.083733: step: 276/77, loss: 0.004955152980983257
2023-01-22 10:03:31.602580: step: 280/77, loss: 0.11314801871776581
2023-01-22 10:03:33.104720: step: 284/77, loss: 0.009548168629407883
2023-01-22 10:03:34.509105: step: 288/77, loss: 0.00019546764087863266
2023-01-22 10:03:36.085923: step: 292/77, loss: 0.09462368488311768
2023-01-22 10:03:37.613334: step: 296/77, loss: 7.842419290682301e-05
2023-01-22 10:03:39.061691: step: 300/77, loss: 0.0013920800993219018
2023-01-22 10:03:40.569423: step: 304/77, loss: 0.04698015749454498
2023-01-22 10:03:42.046486: step: 308/77, loss: 0.002782592084258795
2023-01-22 10:03:43.467607: step: 312/77, loss: 2.5230790924979374e-05
2023-01-22 10:03:44.917193: step: 316/77, loss: 0.007181983441114426
2023-01-22 10:03:46.431552: step: 320/77, loss: 0.022983960807323456
2023-01-22 10:03:47.893345: step: 324/77, loss: 0.00940174050629139
2023-01-22 10:03:49.297438: step: 328/77, loss: 0.02167385257780552
2023-01-22 10:03:50.721154: step: 332/77, loss: 0.009350062347948551
2023-01-22 10:03:52.223083: step: 336/77, loss: 0.063703753054142
2023-01-22 10:03:53.741556: step: 340/77, loss: 0.002021544612944126
2023-01-22 10:03:55.249559: step: 344/77, loss: 0.0050396379083395
2023-01-22 10:03:56.708543: step: 348/77, loss: 0.008820513263344765
2023-01-22 10:03:58.162263: step: 352/77, loss: 0.003946100827306509
2023-01-22 10:03:59.626444: step: 356/77, loss: 0.003359707072377205
2023-01-22 10:04:01.129911: step: 360/77, loss: 0.008270454593002796
2023-01-22 10:04:02.659694: step: 364/77, loss: 9.894469985738397e-05
2023-01-22 10:04:04.168682: step: 368/77, loss: 0.002662702463567257
2023-01-22 10:04:05.688431: step: 372/77, loss: 0.002308095572516322
2023-01-22 10:04:07.135249: step: 376/77, loss: 0.013296185992658138
2023-01-22 10:04:08.535840: step: 380/77, loss: 0.049899984151124954
2023-01-22 10:04:10.059484: step: 384/77, loss: 0.0031746437307447195
2023-01-22 10:04:11.569201: step: 388/77, loss: 0.08022551983594894
==================================================
Loss: 0.020
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.04686584651435266, 'epoch': 11}
Test Chinese: {'template': {'p': 0.9104477611940298, 'r': 0.46564885496183206, 'f1': 0.6161616161616161}, 'slot': {'p': 0.42424242424242425, 'r': 0.012079378774805867, 'f1': 0.02348993288590604}, 'combined': 0.014473595010507762, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.4666666666666667, 'f1': 0.6363636363636364}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.04473558076370027, 'epoch': 11}
Test Korean: {'template': {'p': 0.9253731343283582, 'r': 0.4732824427480916, 'f1': 0.6262626262626263}, 'slot': {'p': 0.45714285714285713, 'r': 0.013805004314063849, 'f1': 0.02680067001675042}, 'combined': 0.016784257990288143, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.48333333333333334, 'f1': 0.6516853932584269}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.045812681424142486, 'epoch': 11}
Test Russian: {'template': {'p': 0.8970588235294118, 'r': 0.46564885496183206, 'f1': 0.6130653266331658}, 'slot': {'p': 0.46875, 'r': 0.012942191544434857, 'f1': 0.025188916876574305}, 'combined': 0.015442451552472689, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 10:05:50.293554: step: 4/77, loss: 0.04436550661921501
2023-01-22 10:05:51.756363: step: 8/77, loss: 0.004802200943231583
2023-01-22 10:05:53.224326: step: 12/77, loss: 0.11278200894594193
2023-01-22 10:05:54.686470: step: 16/77, loss: 0.004204769618809223
2023-01-22 10:05:56.197999: step: 20/77, loss: 0.002979584503918886
2023-01-22 10:05:57.661551: step: 24/77, loss: 0.011945674195885658
2023-01-22 10:05:59.108090: step: 28/77, loss: 0.004289418924599886
2023-01-22 10:06:00.675161: step: 32/77, loss: 0.005253539886325598
2023-01-22 10:06:02.138712: step: 36/77, loss: 0.0008780001080594957
2023-01-22 10:06:03.587046: step: 40/77, loss: 0.001079891575500369
2023-01-22 10:06:05.104864: step: 44/77, loss: 0.015719100832939148
2023-01-22 10:06:06.563926: step: 48/77, loss: 0.032325148582458496
2023-01-22 10:06:08.054692: step: 52/77, loss: 0.0008553061634302139
2023-01-22 10:06:09.608326: step: 56/77, loss: 0.001794558484107256
2023-01-22 10:06:11.178552: step: 60/77, loss: 0.03624221682548523
2023-01-22 10:06:12.692245: step: 64/77, loss: 0.0045928796753287315
2023-01-22 10:06:14.186706: step: 68/77, loss: 0.05722226947546005
2023-01-22 10:06:15.675574: step: 72/77, loss: 0.0012267765123397112
2023-01-22 10:06:17.216126: step: 76/77, loss: 0.0031581628136336803
2023-01-22 10:06:18.686860: step: 80/77, loss: 0.01436734851449728
2023-01-22 10:06:20.220666: step: 84/77, loss: 0.013682027347385883
2023-01-22 10:06:21.737466: step: 88/77, loss: 0.004203316755592823
2023-01-22 10:06:23.196647: step: 92/77, loss: 0.005488214548677206
2023-01-22 10:06:24.685035: step: 96/77, loss: 0.0018630167469382286
2023-01-22 10:06:26.132051: step: 100/77, loss: 0.00012121098552597687
2023-01-22 10:06:27.588373: step: 104/77, loss: 0.0013276045210659504
2023-01-22 10:06:29.128738: step: 108/77, loss: 0.005005714017897844
2023-01-22 10:06:30.514225: step: 112/77, loss: 0.006716449744999409
2023-01-22 10:06:32.037570: step: 116/77, loss: 0.009621203877031803
2023-01-22 10:06:33.540370: step: 120/77, loss: 0.003736691316589713
2023-01-22 10:06:35.014277: step: 124/77, loss: 0.02548018842935562
2023-01-22 10:06:36.457501: step: 128/77, loss: 0.015529114753007889
2023-01-22 10:06:37.960669: step: 132/77, loss: 0.0020801310893148184
2023-01-22 10:06:39.416937: step: 136/77, loss: 0.0016847447259351611
2023-01-22 10:06:40.959421: step: 140/77, loss: 0.0012095924466848373
2023-01-22 10:06:42.409459: step: 144/77, loss: 0.0006464039324782789
2023-01-22 10:06:43.881697: step: 148/77, loss: 0.0005958712426945567
2023-01-22 10:06:45.404342: step: 152/77, loss: 0.00440417742356658
2023-01-22 10:06:46.868019: step: 156/77, loss: 0.024716690182685852
2023-01-22 10:06:48.332765: step: 160/77, loss: 0.009818075224757195
2023-01-22 10:06:49.825410: step: 164/77, loss: 0.01651581935584545
2023-01-22 10:06:51.251660: step: 168/77, loss: 0.0026334517169743776
2023-01-22 10:06:52.659410: step: 172/77, loss: 7.838180317776278e-05
2023-01-22 10:06:54.122630: step: 176/77, loss: 0.0017036596545949578
2023-01-22 10:06:55.546384: step: 180/77, loss: 0.0021797381341457367
2023-01-22 10:06:57.021043: step: 184/77, loss: 0.002597886137664318
2023-01-22 10:06:58.469630: step: 188/77, loss: 0.0011595187243074179
2023-01-22 10:06:59.874721: step: 192/77, loss: 0.0011745744850486517
2023-01-22 10:07:01.366577: step: 196/77, loss: 0.0181453675031662
2023-01-22 10:07:02.860791: step: 200/77, loss: 0.011830981820821762
2023-01-22 10:07:04.427471: step: 204/77, loss: 0.022019436582922935
2023-01-22 10:07:05.918524: step: 208/77, loss: 0.04811529070138931
2023-01-22 10:07:07.357845: step: 212/77, loss: 0.020062996074557304
2023-01-22 10:07:08.831857: step: 216/77, loss: 0.0033560858573764563
2023-01-22 10:07:10.321880: step: 220/77, loss: 0.012346186675131321
2023-01-22 10:07:11.747795: step: 224/77, loss: 0.00652111042290926
2023-01-22 10:07:13.243885: step: 228/77, loss: 3.144413494737819e-05
2023-01-22 10:07:14.729873: step: 232/77, loss: 0.018586190417408943
2023-01-22 10:07:16.145408: step: 236/77, loss: 0.046308234333992004
2023-01-22 10:07:17.612637: step: 240/77, loss: 0.0010744313476607203
2023-01-22 10:07:19.057463: step: 244/77, loss: 0.013715185225009918
2023-01-22 10:07:20.588885: step: 248/77, loss: 0.0011830773437395692
2023-01-22 10:07:22.045289: step: 252/77, loss: 0.035007935017347336
2023-01-22 10:07:23.498621: step: 256/77, loss: 0.00036713789450004697
2023-01-22 10:07:24.963439: step: 260/77, loss: 0.003876642556861043
2023-01-22 10:07:26.396925: step: 264/77, loss: 0.03178451210260391
2023-01-22 10:07:27.877629: step: 268/77, loss: 0.004363094922155142
2023-01-22 10:07:29.327161: step: 272/77, loss: 0.00016332468658220023
2023-01-22 10:07:30.823287: step: 276/77, loss: 2.408213185844943e-05
2023-01-22 10:07:32.247357: step: 280/77, loss: 0.016927000135183334
2023-01-22 10:07:33.713662: step: 284/77, loss: 0.025983309373259544
2023-01-22 10:07:35.147377: step: 288/77, loss: 0.0042741927318274975
2023-01-22 10:07:36.602564: step: 292/77, loss: 0.017417028546333313
2023-01-22 10:07:38.072941: step: 296/77, loss: 0.014634665101766586
2023-01-22 10:07:39.514749: step: 300/77, loss: 0.009720695205032825
2023-01-22 10:07:41.048841: step: 304/77, loss: 0.0002194459520978853
2023-01-22 10:07:42.564146: step: 308/77, loss: 6.72009409754537e-05
2023-01-22 10:07:44.040568: step: 312/77, loss: 0.05025641992688179
2023-01-22 10:07:45.501623: step: 316/77, loss: 0.012442845851182938
2023-01-22 10:07:47.010699: step: 320/77, loss: 0.0018316482892259955
2023-01-22 10:07:48.568495: step: 324/77, loss: 0.0017850275617092848
2023-01-22 10:07:50.084969: step: 328/77, loss: 0.00014143706357572228
2023-01-22 10:07:51.601855: step: 332/77, loss: 0.003508616704493761
2023-01-22 10:07:53.089302: step: 336/77, loss: 0.046058665961027145
2023-01-22 10:07:54.565812: step: 340/77, loss: 0.03320928290486336
2023-01-22 10:07:56.050715: step: 344/77, loss: 0.004275294486433268
2023-01-22 10:07:57.481993: step: 348/77, loss: 0.001723662600852549
2023-01-22 10:07:58.949036: step: 352/77, loss: 0.002751779742538929
2023-01-22 10:08:00.358290: step: 356/77, loss: 0.0015267680864781141
2023-01-22 10:08:01.821457: step: 360/77, loss: 0.009214522317051888
2023-01-22 10:08:03.298337: step: 364/77, loss: 0.0674782544374466
2023-01-22 10:08:04.753718: step: 368/77, loss: 0.01894235797226429
2023-01-22 10:08:06.291555: step: 372/77, loss: 0.00815523136407137
2023-01-22 10:08:07.737528: step: 376/77, loss: 0.010504646226763725
2023-01-22 10:08:09.216818: step: 380/77, loss: 0.004112462513148785
2023-01-22 10:08:10.716397: step: 384/77, loss: 0.003164243418723345
2023-01-22 10:08:12.256870: step: 388/77, loss: 0.02831357903778553
==================================================
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': 0.9402985074626866, 'r': 0.48091603053435117, 'f1': 0.6363636363636365}, 'slot': {'p': 0.5, 'r': 0.013805004314063849, 'f1': 0.026868178001679264}, 'combined': 0.01709793145561408, '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': 0.9402985074626866, 'r': 0.48091603053435117, 'f1': 0.6363636363636365}, 'slot': {'p': 0.5483870967741935, 'r': 0.014667817083692839, 'f1': 0.02857142857142857}, 'combined': 0.018181818181818184, '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': 0.9411764705882353, 'r': 0.48854961832061067, 'f1': 0.6432160804020101}, 'slot': {'p': 0.5483870967741935, 'r': 0.014667817083692839, 'f1': 0.02857142857142857}, 'combined': 0.01837760229720029, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 10:09:50.392803: step: 4/77, loss: 0.02979923039674759
2023-01-22 10:09:51.886780: step: 8/77, loss: 0.0011581765720620751
2023-01-22 10:09:53.418468: step: 12/77, loss: 0.01394204143434763
2023-01-22 10:09:54.799032: step: 16/77, loss: 0.016473228111863136
2023-01-22 10:09:56.288815: step: 20/77, loss: 0.003298100782558322
2023-01-22 10:09:57.760066: step: 24/77, loss: 0.02194811776280403
2023-01-22 10:09:59.260602: step: 28/77, loss: 0.01043167244642973
2023-01-22 10:10:00.710610: step: 32/77, loss: 0.06836826354265213
2023-01-22 10:10:02.228791: step: 36/77, loss: 0.000960124540142715
2023-01-22 10:10:03.704010: step: 40/77, loss: 0.06304540485143661
2023-01-22 10:10:05.189435: step: 44/77, loss: 0.00409977650269866
2023-01-22 10:10:06.676850: step: 48/77, loss: 0.00018478457059245557
2023-01-22 10:10:08.133856: step: 52/77, loss: 0.046891722828149796
2023-01-22 10:10:09.566001: step: 56/77, loss: 0.01876625046133995
2023-01-22 10:10:11.044139: step: 60/77, loss: 3.593548899516463e-05
2023-01-22 10:10:12.519337: step: 64/77, loss: 6.849043711554259e-05
2023-01-22 10:10:13.995510: step: 68/77, loss: 0.0011330159613862634
2023-01-22 10:10:15.439031: step: 72/77, loss: 0.0002272444253321737
2023-01-22 10:10:16.892032: step: 76/77, loss: 1.507402066636132e-05
2023-01-22 10:10:18.429606: step: 80/77, loss: 0.002101314952597022
2023-01-22 10:10:19.867994: step: 84/77, loss: 0.033360376954078674
2023-01-22 10:10:21.314894: step: 88/77, loss: 0.10507829487323761
2023-01-22 10:10:22.842846: step: 92/77, loss: 0.00254506035707891
2023-01-22 10:10:24.265012: step: 96/77, loss: 0.015117666684091091
2023-01-22 10:10:25.804646: step: 100/77, loss: 0.011987771838903427
2023-01-22 10:10:27.262945: step: 104/77, loss: 0.0020428854040801525
2023-01-22 10:10:28.674799: step: 108/77, loss: 1.1954606634390075e-05
2023-01-22 10:10:30.123953: step: 112/77, loss: 0.0017031385796144605
2023-01-22 10:10:31.593521: step: 116/77, loss: 0.04721391946077347
2023-01-22 10:10:33.036319: step: 120/77, loss: 0.00435302872210741
2023-01-22 10:10:34.516037: step: 124/77, loss: 0.006813234183937311
2023-01-22 10:10:35.943435: step: 128/77, loss: 0.0010583556722849607
2023-01-22 10:10:37.485313: step: 132/77, loss: 0.0035780100151896477
2023-01-22 10:10:38.943901: step: 136/77, loss: 0.00271525327116251
2023-01-22 10:10:40.458880: step: 140/77, loss: 0.0007694312371313572
2023-01-22 10:10:41.971358: step: 144/77, loss: 0.0012259716168045998
2023-01-22 10:10:43.440799: step: 148/77, loss: 0.0017704784404486418
2023-01-22 10:10:44.949362: step: 152/77, loss: 0.00048166397027671337
2023-01-22 10:10:46.481927: step: 156/77, loss: 0.01880849339067936
2023-01-22 10:10:47.899553: step: 160/77, loss: 0.008621509186923504
2023-01-22 10:10:49.303385: step: 164/77, loss: 0.010005577467381954
2023-01-22 10:10:50.793167: step: 168/77, loss: 0.011141312308609486
2023-01-22 10:10:52.278258: step: 172/77, loss: 0.0018681518267840147
2023-01-22 10:10:53.791712: step: 176/77, loss: 0.0004037081089336425
2023-01-22 10:10:55.186121: step: 180/77, loss: 0.009404388256371021
2023-01-22 10:10:56.716509: step: 184/77, loss: 0.0016339367721229792
2023-01-22 10:10:58.192770: step: 188/77, loss: 0.014390097931027412
2023-01-22 10:10:59.685350: step: 192/77, loss: 0.0010596985230222344
2023-01-22 10:11:01.139311: step: 196/77, loss: 0.054352860897779465
2023-01-22 10:11:02.565605: step: 200/77, loss: 0.03959896042943001
2023-01-22 10:11:04.070890: step: 204/77, loss: 9.916317503666505e-05
2023-01-22 10:11:05.520882: step: 208/77, loss: 0.013791847974061966
2023-01-22 10:11:06.974660: step: 212/77, loss: 0.0007248240290209651
2023-01-22 10:11:08.507365: step: 216/77, loss: 0.0002708295651245862
2023-01-22 10:11:09.937528: step: 220/77, loss: 0.0004911398864351213
2023-01-22 10:11:11.453266: step: 224/77, loss: 0.0047632548958063126
2023-01-22 10:11:12.885492: step: 228/77, loss: 0.0011701977346092463
2023-01-22 10:11:14.372773: step: 232/77, loss: 0.00042671553092077374
2023-01-22 10:11:15.894781: step: 236/77, loss: 0.03621303662657738
2023-01-22 10:11:17.419332: step: 240/77, loss: 0.0006495914421975613
2023-01-22 10:11:18.887085: step: 244/77, loss: 0.0029841335490345955
2023-01-22 10:11:20.454433: step: 248/77, loss: 0.02200494334101677
2023-01-22 10:11:21.988895: step: 252/77, loss: 0.0032038982026278973
2023-01-22 10:11:23.428478: step: 256/77, loss: 0.004941218066960573
2023-01-22 10:11:24.799961: step: 260/77, loss: 0.027301592752337456
2023-01-22 10:11:26.333479: step: 264/77, loss: 0.010927285067737103
2023-01-22 10:11:27.854611: step: 268/77, loss: 0.010645708069205284
2023-01-22 10:11:29.362381: step: 272/77, loss: 0.00907566212117672
2023-01-22 10:11:30.910551: step: 276/77, loss: 0.0008718777680769563
2023-01-22 10:11:32.358246: step: 280/77, loss: 0.004993719980120659
2023-01-22 10:11:33.847914: step: 284/77, loss: 0.0007454871665686369
2023-01-22 10:11:35.344616: step: 288/77, loss: 0.05532342940568924
2023-01-22 10:11:36.839460: step: 292/77, loss: 0.00028806107002310455
2023-01-22 10:11:38.359066: step: 296/77, loss: 0.00247851456515491
2023-01-22 10:11:39.866743: step: 300/77, loss: 0.012744927778840065
2023-01-22 10:11:41.376039: step: 304/77, loss: 0.033811114728450775
2023-01-22 10:11:42.839564: step: 308/77, loss: 0.0008661256870254874
2023-01-22 10:11:44.291341: step: 312/77, loss: 0.0006619691848754883
2023-01-22 10:11:45.823172: step: 316/77, loss: 0.006505975965410471
2023-01-22 10:11:47.336111: step: 320/77, loss: 0.03772088512778282
2023-01-22 10:11:48.768166: step: 324/77, loss: 0.015472686849534512
2023-01-22 10:11:50.232932: step: 328/77, loss: 0.006314371712505817
2023-01-22 10:11:51.729305: step: 332/77, loss: 2.2619480660068803e-05
2023-01-22 10:11:53.243337: step: 336/77, loss: 0.021693747490644455
2023-01-22 10:11:54.715002: step: 340/77, loss: 0.00468218931928277
2023-01-22 10:11:56.224063: step: 344/77, loss: 0.001238841563463211
2023-01-22 10:11:57.711243: step: 348/77, loss: 0.0005457285442389548
2023-01-22 10:11:59.255059: step: 352/77, loss: 0.008669009432196617
2023-01-22 10:12:00.733823: step: 356/77, loss: 0.004476443864405155
2023-01-22 10:12:02.176479: step: 360/77, loss: 0.01310722716152668
2023-01-22 10:12:03.710546: step: 364/77, loss: 0.0666121393442154
2023-01-22 10:12:05.178394: step: 368/77, loss: 0.0067118373699486256
2023-01-22 10:12:06.592582: step: 372/77, loss: 0.00446122232824564
2023-01-22 10:12:08.069960: step: 376/77, loss: 0.0023765151854604483
2023-01-22 10:12:09.575364: step: 380/77, loss: 0.007924961857497692
2023-01-22 10:12:11.057854: step: 384/77, loss: 0.010871789418160915
2023-01-22 10:12:12.510396: step: 388/77, loss: 0.00019569540745578706
==================================================
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': 13}
Test Chinese: {'template': {'p': 0.8625, 'r': 0.5267175572519084, 'f1': 0.6540284360189573}, 'slot': {'p': 0.42857142857142855, 'r': 0.015530629853321829, 'f1': 0.029975020815986676}, 'combined': 0.019604515983915455, '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': 0.875, 'r': 0.5343511450381679, 'f1': 0.6635071090047393}, 'slot': {'p': 0.4318181818181818, 'r': 0.01639344262295082, 'f1': 0.03158769742310889}, 'combined': 0.020958661797323436, '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': 0.8625, 'r': 0.5267175572519084, 'f1': 0.6540284360189573}, 'slot': {'p': 0.42857142857142855, 'r': 0.015530629853321829, 'f1': 0.029975020815986676}, 'combined': 0.019604515983915455, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 10:13:49.945548: step: 4/77, loss: 0.05021757259964943
2023-01-22 10:13:51.449952: step: 8/77, loss: 0.013492027297616005
2023-01-22 10:13:52.856611: step: 12/77, loss: 0.01188771240413189
2023-01-22 10:13:54.296990: step: 16/77, loss: 0.004332687705755234
2023-01-22 10:13:55.775533: step: 20/77, loss: 0.0068397969007492065
2023-01-22 10:13:57.183015: step: 24/77, loss: 0.03639312461018562
2023-01-22 10:13:58.657593: step: 28/77, loss: 0.010193396359682083
2023-01-22 10:14:00.125735: step: 32/77, loss: 0.0002720890333876014
2023-01-22 10:14:01.584382: step: 36/77, loss: 0.0033012309577316046
2023-01-22 10:14:02.994154: step: 40/77, loss: 0.06803090870380402
2023-01-22 10:14:04.447184: step: 44/77, loss: 0.002303973538801074
2023-01-22 10:14:05.892211: step: 48/77, loss: 0.01426534354686737
2023-01-22 10:14:07.326928: step: 52/77, loss: 0.01106639951467514
2023-01-22 10:14:08.812677: step: 56/77, loss: 0.013820632360875607
2023-01-22 10:14:10.270901: step: 60/77, loss: 0.001012542168609798
2023-01-22 10:14:11.761353: step: 64/77, loss: 0.003073731204494834
2023-01-22 10:14:13.269530: step: 68/77, loss: 0.0074550556018948555
2023-01-22 10:14:14.742364: step: 72/77, loss: 0.03673708066344261
2023-01-22 10:14:16.254848: step: 76/77, loss: 0.009585902094841003
2023-01-22 10:14:17.737006: step: 80/77, loss: 0.0049670119769871235
2023-01-22 10:14:19.174801: step: 84/77, loss: 0.0012508973013609648
2023-01-22 10:14:20.644359: step: 88/77, loss: 0.04550894722342491
2023-01-22 10:14:22.192604: step: 92/77, loss: 0.0476241372525692
2023-01-22 10:14:23.653287: step: 96/77, loss: 0.0003463767934590578
2023-01-22 10:14:25.121430: step: 100/77, loss: 0.0013855427969247103
2023-01-22 10:14:26.583017: step: 104/77, loss: 6.948120426386595e-05
2023-01-22 10:14:28.039511: step: 108/77, loss: 0.0025392724201083183
2023-01-22 10:14:29.491099: step: 112/77, loss: 0.0023203599266707897
2023-01-22 10:14:31.023165: step: 116/77, loss: 0.002155708149075508
2023-01-22 10:14:32.508147: step: 120/77, loss: 0.010432385839521885
2023-01-22 10:14:33.977244: step: 124/77, loss: 0.0015561548061668873
2023-01-22 10:14:35.432408: step: 128/77, loss: 0.0022515016607940197
2023-01-22 10:14:36.863586: step: 132/77, loss: 0.0063758837059140205
2023-01-22 10:14:38.327640: step: 136/77, loss: 0.00816910620778799
2023-01-22 10:14:39.772504: step: 140/77, loss: 0.0004892628057859838
2023-01-22 10:14:41.253142: step: 144/77, loss: 0.006460327655076981
2023-01-22 10:14:42.745362: step: 148/77, loss: 0.0022336977999657393
2023-01-22 10:14:44.234862: step: 152/77, loss: 0.04381607472896576
2023-01-22 10:14:45.673018: step: 156/77, loss: 0.01606643944978714
2023-01-22 10:14:47.134622: step: 160/77, loss: 0.01276947371661663
2023-01-22 10:14:48.686265: step: 164/77, loss: 8.410248847212642e-05
2023-01-22 10:14:50.177139: step: 168/77, loss: 0.01344869751483202
2023-01-22 10:14:51.638297: step: 172/77, loss: 0.01566564477980137
2023-01-22 10:14:53.144766: step: 176/77, loss: 3.885049591190182e-05
2023-01-22 10:14:54.644009: step: 180/77, loss: 0.002805543364956975
2023-01-22 10:14:56.181146: step: 184/77, loss: 5.492310265253764e-06
2023-01-22 10:14:57.582725: step: 188/77, loss: 0.004818313755095005
2023-01-22 10:14:59.090250: step: 192/77, loss: 0.00019668742606882006
2023-01-22 10:15:00.545674: step: 196/77, loss: 0.0005715168663300574
2023-01-22 10:15:02.129249: step: 200/77, loss: 0.013614819385111332
2023-01-22 10:15:03.628716: step: 204/77, loss: 0.006921195425093174
2023-01-22 10:15:05.127107: step: 208/77, loss: 0.000296951737254858
2023-01-22 10:15:06.584772: step: 212/77, loss: 0.000808404351118952
2023-01-22 10:15:08.113889: step: 216/77, loss: 0.0011310662375763059
2023-01-22 10:15:09.616881: step: 220/77, loss: 0.1592380404472351
2023-01-22 10:15:11.093149: step: 224/77, loss: 0.0025794643443077803
2023-01-22 10:15:12.529034: step: 228/77, loss: 0.0009930891683325171
2023-01-22 10:15:14.042661: step: 232/77, loss: 0.0015125039499253035
2023-01-22 10:15:15.489108: step: 236/77, loss: 0.005088160280138254
2023-01-22 10:15:17.045895: step: 240/77, loss: 0.0073650190606713295
2023-01-22 10:15:18.517081: step: 244/77, loss: 0.007640082389116287
2023-01-22 10:15:20.015688: step: 248/77, loss: 0.0062585556879639626
2023-01-22 10:15:21.491038: step: 252/77, loss: 0.02538384683430195
2023-01-22 10:15:22.958029: step: 256/77, loss: 0.0007471991702914238
2023-01-22 10:15:24.457241: step: 260/77, loss: 0.000744312594179064
2023-01-22 10:15:25.909292: step: 264/77, loss: 6.348014721879736e-05
2023-01-22 10:15:27.452319: step: 268/77, loss: 0.0054208822548389435
2023-01-22 10:15:28.946148: step: 272/77, loss: 0.004874257370829582
2023-01-22 10:15:30.425065: step: 276/77, loss: 0.0018353211926296353
2023-01-22 10:15:31.862650: step: 280/77, loss: 0.01595592312514782
2023-01-22 10:15:33.429081: step: 284/77, loss: 0.010417342185974121
2023-01-22 10:15:34.905950: step: 288/77, loss: 0.015512584708631039
2023-01-22 10:15:36.366099: step: 292/77, loss: 0.05964883044362068
2023-01-22 10:15:37.807625: step: 296/77, loss: 0.021162962540984154
2023-01-22 10:15:39.273979: step: 300/77, loss: 0.005686973687261343
2023-01-22 10:15:40.694665: step: 304/77, loss: 0.007818142883479595
2023-01-22 10:15:42.169066: step: 308/77, loss: 0.006607674062252045
2023-01-22 10:15:43.612309: step: 312/77, loss: 0.00150693254545331
2023-01-22 10:15:45.084795: step: 316/77, loss: 0.014010453596711159
2023-01-22 10:15:46.567218: step: 320/77, loss: 0.0010493621230125427
2023-01-22 10:15:48.075970: step: 324/77, loss: 0.004597794730216265
2023-01-22 10:15:49.609741: step: 328/77, loss: 0.001323473872616887
2023-01-22 10:15:51.092498: step: 332/77, loss: 0.003567654872313142
2023-01-22 10:15:52.602123: step: 336/77, loss: 0.023809565231204033
2023-01-22 10:15:54.078376: step: 340/77, loss: 0.0202918890863657
2023-01-22 10:15:55.638816: step: 344/77, loss: 0.05709415674209595
2023-01-22 10:15:57.050120: step: 348/77, loss: 0.06244867295026779
2023-01-22 10:15:58.578601: step: 352/77, loss: 0.0023825361859053373
2023-01-22 10:15:59.996986: step: 356/77, loss: 0.015587534755468369
2023-01-22 10:16:01.505535: step: 360/77, loss: 0.003471288364380598
2023-01-22 10:16:02.992842: step: 364/77, loss: 0.004319621250033379
2023-01-22 10:16:04.491688: step: 368/77, loss: 0.014541847631335258
2023-01-22 10:16:06.014058: step: 372/77, loss: 0.00017313337593805045
2023-01-22 10:16:07.393113: step: 376/77, loss: 0.002016652375459671
2023-01-22 10:16:08.890035: step: 380/77, loss: 0.021287081763148308
2023-01-22 10:16:10.381067: step: 384/77, loss: 0.0034362124279141426
2023-01-22 10:16:11.815830: step: 388/77, loss: 0.002922603627666831
==================================================
Loss: 0.013
--------------------
Dev Chinese: {'template': {'p': 0.9459459459459459, 'r': 0.5833333333333334, 'f1': 0.7216494845360825}, 'slot': {'p': 0.43478260869565216, 'r': 0.03780718336483932, 'f1': 0.06956521739130435}, 'combined': 0.0502017032720753, 'epoch': 14}
Test Chinese: {'template': {'p': 0.9014084507042254, 'r': 0.48854961832061067, 'f1': 0.6336633663366336}, 'slot': {'p': 0.4, 'r': 0.015530629853321829, 'f1': 0.029900332225913623}, 'combined': 0.018946745172856154, 'epoch': 14}
Dev Korean: {'template': {'p': 0.9459459459459459, 'r': 0.5833333333333334, 'f1': 0.7216494845360825}, 'slot': {'p': 0.43478260869565216, 'r': 0.03780718336483932, 'f1': 0.06956521739130435}, 'combined': 0.0502017032720753, 'epoch': 14}
Test Korean: {'template': {'p': 0.9014084507042254, 'r': 0.48854961832061067, 'f1': 0.6336633663366336}, 'slot': {'p': 0.391304347826087, 'r': 0.015530629853321829, 'f1': 0.029875518672199168}, 'combined': 0.018931021732878677, 'epoch': 14}
Dev Russian: {'template': {'p': 0.9459459459459459, 'r': 0.5833333333333334, 'f1': 0.7216494845360825}, 'slot': {'p': 0.43478260869565216, 'r': 0.03780718336483932, 'f1': 0.06956521739130435}, 'combined': 0.0502017032720753, 'epoch': 14}
Test Russian: {'template': {'p': 0.8873239436619719, 'r': 0.48091603053435117, 'f1': 0.6237623762376238}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01762919434088047, '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': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 10:17:49.168404: step: 4/77, loss: 0.008644331246614456
2023-01-22 10:17:50.637435: step: 8/77, loss: 0.011979562230408192
2023-01-22 10:17:52.196476: step: 12/77, loss: 0.014013068750500679
2023-01-22 10:17:53.640997: step: 16/77, loss: 0.008621701039373875
2023-01-22 10:17:55.101687: step: 20/77, loss: 0.021316878497600555
2023-01-22 10:17:56.606946: step: 24/77, loss: 0.051223039627075195
2023-01-22 10:17:58.134426: step: 28/77, loss: 0.002289854222908616
2023-01-22 10:17:59.658207: step: 32/77, loss: 0.004393209703266621
2023-01-22 10:18:01.184267: step: 36/77, loss: 5.282249730953481e-06
2023-01-22 10:18:02.710137: step: 40/77, loss: 0.01075073517858982
2023-01-22 10:18:04.222285: step: 44/77, loss: 0.0020622683223336935
2023-01-22 10:18:05.719334: step: 48/77, loss: 0.03781045228242874
2023-01-22 10:18:07.177167: step: 52/77, loss: 0.0880887433886528
2023-01-22 10:18:08.708472: step: 56/77, loss: 0.03132542222738266
2023-01-22 10:18:10.225183: step: 60/77, loss: 0.00321400398388505
2023-01-22 10:18:11.663565: step: 64/77, loss: 0.004773072432726622
2023-01-22 10:18:13.046192: step: 68/77, loss: 0.017901595681905746
2023-01-22 10:18:14.509130: step: 72/77, loss: 0.038539398461580276
2023-01-22 10:18:16.010595: step: 76/77, loss: 0.133880615234375
2023-01-22 10:18:17.498263: step: 80/77, loss: 0.0034761850256472826
2023-01-22 10:18:18.993961: step: 84/77, loss: 0.013166949152946472
2023-01-22 10:18:20.458079: step: 88/77, loss: 0.00681588239967823
2023-01-22 10:18:21.906843: step: 92/77, loss: 0.009442516602575779
2023-01-22 10:18:23.398944: step: 96/77, loss: 0.023162730038166046
2023-01-22 10:18:24.890911: step: 100/77, loss: 0.017544515430927277
2023-01-22 10:18:26.365257: step: 104/77, loss: 0.016073524951934814
2023-01-22 10:18:27.872523: step: 108/77, loss: 0.03755786269903183
2023-01-22 10:18:29.431881: step: 112/77, loss: 0.0028731636703014374
2023-01-22 10:18:30.919167: step: 116/77, loss: 0.006997175980359316
2023-01-22 10:18:32.413348: step: 120/77, loss: 0.002053946955129504
2023-01-22 10:18:33.904577: step: 124/77, loss: 0.0005283099017105997
2023-01-22 10:18:35.391178: step: 128/77, loss: 0.007918376475572586
2023-01-22 10:18:36.879098: step: 132/77, loss: 0.0013505109818652272
2023-01-22 10:18:38.380710: step: 136/77, loss: 0.006453365087509155
2023-01-22 10:18:39.831287: step: 140/77, loss: 0.008280211128294468
2023-01-22 10:18:41.286749: step: 144/77, loss: 0.02169647254049778
2023-01-22 10:18:42.786768: step: 148/77, loss: 0.008906039409339428
2023-01-22 10:18:44.282604: step: 152/77, loss: 9.285704436479136e-05
2023-01-22 10:18:45.729720: step: 156/77, loss: 0.061494454741477966
2023-01-22 10:18:47.189985: step: 160/77, loss: 0.0007124262629076838
2023-01-22 10:18:48.678368: step: 164/77, loss: 0.0020129838958382607
2023-01-22 10:18:50.129744: step: 168/77, loss: 0.00560009153559804
2023-01-22 10:18:51.624069: step: 172/77, loss: 0.030477937310934067
2023-01-22 10:18:53.072129: step: 176/77, loss: 0.005781487561762333
2023-01-22 10:18:54.495016: step: 180/77, loss: 0.002156471135094762
2023-01-22 10:18:55.965711: step: 184/77, loss: 0.01489571388810873
2023-01-22 10:18:57.467792: step: 188/77, loss: 0.01714280992746353
2023-01-22 10:18:58.941701: step: 192/77, loss: 0.014948004856705666
2023-01-22 10:19:00.462422: step: 196/77, loss: 0.0004343294131103903
2023-01-22 10:19:01.961508: step: 200/77, loss: 0.0468200147151947
2023-01-22 10:19:03.452803: step: 204/77, loss: 0.00364921847358346
2023-01-22 10:19:04.891391: step: 208/77, loss: 0.006669571157544851
2023-01-22 10:19:06.387095: step: 212/77, loss: 0.03793036937713623
2023-01-22 10:19:07.885081: step: 216/77, loss: 0.0024284652899950743
2023-01-22 10:19:09.358408: step: 220/77, loss: 0.002885939320549369
2023-01-22 10:19:10.806824: step: 224/77, loss: 0.05066582188010216
2023-01-22 10:19:12.243875: step: 228/77, loss: 0.0012308210134506226
2023-01-22 10:19:13.757090: step: 232/77, loss: 0.03428790718317032
2023-01-22 10:19:15.219016: step: 236/77, loss: 0.005835465621203184
2023-01-22 10:19:16.673405: step: 240/77, loss: 0.035248078405857086
2023-01-22 10:19:18.140824: step: 244/77, loss: 0.011382810771465302
2023-01-22 10:19:19.589736: step: 248/77, loss: 0.0028067068196833134
2023-01-22 10:19:21.068507: step: 252/77, loss: 0.00026669781072996557
2023-01-22 10:19:22.533886: step: 256/77, loss: 0.0037234588526189327
2023-01-22 10:19:24.050808: step: 260/77, loss: 0.004366753157228231
2023-01-22 10:19:25.499945: step: 264/77, loss: 0.01697009615600109
2023-01-22 10:19:26.949893: step: 268/77, loss: 0.06928707659244537
2023-01-22 10:19:28.400433: step: 272/77, loss: 0.00224512442946434
2023-01-22 10:19:29.857972: step: 276/77, loss: 0.00021704388200305402
2023-01-22 10:19:31.388842: step: 280/77, loss: 0.007994461804628372
2023-01-22 10:19:32.823801: step: 284/77, loss: 0.0010824492201209068
2023-01-22 10:19:34.245772: step: 288/77, loss: 0.005412569735199213
2023-01-22 10:19:35.806700: step: 292/77, loss: 0.014690631069242954
2023-01-22 10:19:37.242870: step: 296/77, loss: 0.07107909023761749
2023-01-22 10:19:38.777966: step: 300/77, loss: 0.003367634490132332
2023-01-22 10:19:40.239352: step: 304/77, loss: 0.0009482861496508121
2023-01-22 10:19:41.703710: step: 308/77, loss: 0.0010064172092825174
2023-01-22 10:19:43.174489: step: 312/77, loss: 0.03311848267912865
2023-01-22 10:19:44.692696: step: 316/77, loss: 0.00782004464417696
2023-01-22 10:19:46.176001: step: 320/77, loss: 0.00015082456229720265
2023-01-22 10:19:47.673799: step: 324/77, loss: 0.00022852692927699536
2023-01-22 10:19:49.112254: step: 328/77, loss: 0.012201538309454918
2023-01-22 10:19:50.646138: step: 332/77, loss: 0.04965365678071976
2023-01-22 10:19:52.105628: step: 336/77, loss: 0.00021343353728298098
2023-01-22 10:19:53.572261: step: 340/77, loss: 0.0032562892884016037
2023-01-22 10:19:54.963476: step: 344/77, loss: 0.0028177325148135424
2023-01-22 10:19:56.423629: step: 348/77, loss: 0.00022388799698092043
2023-01-22 10:19:57.884664: step: 352/77, loss: 0.00048760930076241493
2023-01-22 10:19:59.369867: step: 356/77, loss: 0.033975739032030106
2023-01-22 10:20:00.831599: step: 360/77, loss: 0.07614095509052277
2023-01-22 10:20:02.312234: step: 364/77, loss: 0.020101221278309822
2023-01-22 10:20:03.838808: step: 368/77, loss: 0.013422614894807339
2023-01-22 10:20:05.239102: step: 372/77, loss: 0.01529695838689804
2023-01-22 10:20:06.760845: step: 376/77, loss: 0.0003953626146540046
2023-01-22 10:20:08.302425: step: 380/77, loss: 0.026907581835985184
2023-01-22 10:20:09.697669: step: 384/77, loss: 0.0025897109881043434
2023-01-22 10:20:11.110393: step: 388/77, loss: 0.020302483811974525
==================================================
Loss: 0.017
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.04686584651435266, 'epoch': 15}
Test Chinese: {'template': {'p': 0.8783783783783784, 'r': 0.4961832061068702, 'f1': 0.6341463414634146}, 'slot': {'p': 0.3829787234042553, 'r': 0.015530629853321829, 'f1': 0.029850746268656716}, 'combined': 0.01892974153622133, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.4666666666666667, 'f1': 0.6363636363636364}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.04473558076370027, 'epoch': 15}
Test Korean: {'template': {'p': 0.8666666666666667, 'r': 0.4961832061068702, 'f1': 0.6310679611650485}, 'slot': {'p': 0.40425531914893614, 'r': 0.01639344262295082, 'f1': 0.03150912106135987}, 'combined': 0.019884396786295062, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.48333333333333334, 'f1': 0.6516853932584269}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.045812681424142486, 'epoch': 15}
Test Russian: {'template': {'p': 0.8666666666666667, 'r': 0.4961832061068702, 'f1': 0.6310679611650485}, 'slot': {'p': 0.40425531914893614, 'r': 0.01639344262295082, 'f1': 0.03150912106135987}, 'combined': 0.019884396786295062, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 10:21:49.087104: step: 4/77, loss: 0.02240251749753952
2023-01-22 10:21:50.579512: step: 8/77, loss: 0.02771635353565216
2023-01-22 10:21:52.074614: step: 12/77, loss: 0.00028855435084551573
2023-01-22 10:21:53.531972: step: 16/77, loss: 0.0013435601722449064
2023-01-22 10:21:55.029070: step: 20/77, loss: 0.04604283347725868
2023-01-22 10:21:56.453931: step: 24/77, loss: 0.00026520941173657775
2023-01-22 10:21:57.856494: step: 28/77, loss: 0.00022504819207824767
2023-01-22 10:21:59.314397: step: 32/77, loss: 0.0024469781201332808
2023-01-22 10:22:00.808457: step: 36/77, loss: 0.06819023936986923
2023-01-22 10:22:02.278441: step: 40/77, loss: 0.004971928894519806
2023-01-22 10:22:03.759450: step: 44/77, loss: 0.016732260584831238
2023-01-22 10:22:05.227349: step: 48/77, loss: 0.0035637859255075455
2023-01-22 10:22:06.669151: step: 52/77, loss: 2.8777996703865938e-05
2023-01-22 10:22:08.111469: step: 56/77, loss: 0.00130385288503021
2023-01-22 10:22:09.648229: step: 60/77, loss: 0.011374658904969692
2023-01-22 10:22:11.141418: step: 64/77, loss: 0.0029410512652248144
2023-01-22 10:22:12.653778: step: 68/77, loss: 0.023517031222581863
2023-01-22 10:22:14.117974: step: 72/77, loss: 0.029339302331209183
2023-01-22 10:22:15.672121: step: 76/77, loss: 0.01185949519276619
2023-01-22 10:22:17.132855: step: 80/77, loss: 0.05707313492894173
2023-01-22 10:22:18.625866: step: 84/77, loss: 0.06443598121404648
2023-01-22 10:22:20.161964: step: 88/77, loss: 0.000236800653510727
2023-01-22 10:22:21.655372: step: 92/77, loss: 0.0030893548391759396
2023-01-22 10:22:23.103936: step: 96/77, loss: 0.005407319869846106
2023-01-22 10:22:24.528421: step: 100/77, loss: 0.0009325853898189962
2023-01-22 10:22:26.009321: step: 104/77, loss: 0.0016836941940709949
2023-01-22 10:22:27.511433: step: 108/77, loss: 0.0005430675228126347
2023-01-22 10:22:29.024538: step: 112/77, loss: 0.0018001548014581203
2023-01-22 10:22:30.572362: step: 116/77, loss: 0.011139596812427044
2023-01-22 10:22:32.059689: step: 120/77, loss: 0.009026577696204185
2023-01-22 10:22:33.506495: step: 124/77, loss: 0.013764426112174988
2023-01-22 10:22:35.006296: step: 128/77, loss: 0.13721467554569244
2023-01-22 10:22:36.566741: step: 132/77, loss: 0.05707092583179474
2023-01-22 10:22:38.104605: step: 136/77, loss: 0.002023660810664296
2023-01-22 10:22:39.595179: step: 140/77, loss: 0.0009388293838128448
2023-01-22 10:22:41.027507: step: 144/77, loss: 1.7927572116605006e-05
2023-01-22 10:22:42.536172: step: 148/77, loss: 0.007441079709678888
2023-01-22 10:22:44.012024: step: 152/77, loss: 1.1405087207094766e-05
2023-01-22 10:22:45.541252: step: 156/77, loss: 0.01594318449497223
2023-01-22 10:22:47.021604: step: 160/77, loss: 0.009689363650977612
2023-01-22 10:22:48.449929: step: 164/77, loss: 0.00965337734669447
2023-01-22 10:22:49.930536: step: 168/77, loss: 0.00018008879851549864
2023-01-22 10:22:51.448546: step: 172/77, loss: 0.0013620827812701464
2023-01-22 10:22:52.952215: step: 176/77, loss: 0.009706384502351284
2023-01-22 10:22:54.391223: step: 180/77, loss: 0.00011257622099947184
2023-01-22 10:22:55.880072: step: 184/77, loss: 5.58066058147233e-05
2023-01-22 10:22:57.297110: step: 188/77, loss: 0.0010068108094856143
2023-01-22 10:22:58.790821: step: 192/77, loss: 0.0033298954367637634
2023-01-22 10:23:00.289719: step: 196/77, loss: 0.002340085804462433
2023-01-22 10:23:01.745843: step: 200/77, loss: 4.1069710277952254e-05
2023-01-22 10:23:03.282817: step: 204/77, loss: 4.162640470894985e-05
2023-01-22 10:23:04.765075: step: 208/77, loss: 0.0057720597833395
2023-01-22 10:23:06.270424: step: 212/77, loss: 0.045091234147548676
2023-01-22 10:23:07.754255: step: 216/77, loss: 0.0005430678138509393
2023-01-22 10:23:09.288184: step: 220/77, loss: 0.02244877815246582
2023-01-22 10:23:10.710744: step: 224/77, loss: 0.015751518309116364
2023-01-22 10:23:12.235928: step: 228/77, loss: 0.03594440221786499
2023-01-22 10:23:13.829878: step: 232/77, loss: 0.001045037410221994
2023-01-22 10:23:15.372299: step: 236/77, loss: 0.00036588916555047035
2023-01-22 10:23:16.872610: step: 240/77, loss: 0.0008532066131010652
2023-01-22 10:23:18.355323: step: 244/77, loss: 1.4190770343702752e-05
2023-01-22 10:23:19.878832: step: 248/77, loss: 0.002486072713509202
2023-01-22 10:23:21.343072: step: 252/77, loss: 0.0003959749301429838
2023-01-22 10:23:22.844932: step: 256/77, loss: 4.7969617298804224e-05
2023-01-22 10:23:24.320397: step: 260/77, loss: 0.02460763230919838
2023-01-22 10:23:25.820703: step: 264/77, loss: 0.026778748258948326
2023-01-22 10:23:27.336074: step: 268/77, loss: 0.00020856253104284406
2023-01-22 10:23:28.819756: step: 272/77, loss: 0.06297913193702698
2023-01-22 10:23:30.322172: step: 276/77, loss: 0.02976994216442108
2023-01-22 10:23:31.762539: step: 280/77, loss: 0.09210612624883652
2023-01-22 10:23:33.283080: step: 284/77, loss: 0.0030472474172711372
2023-01-22 10:23:34.783501: step: 288/77, loss: 0.0022248579189181328
2023-01-22 10:23:36.235558: step: 292/77, loss: 0.0329422801733017
2023-01-22 10:23:37.700492: step: 296/77, loss: 0.0012546322541311383
2023-01-22 10:23:39.182385: step: 300/77, loss: 0.012546733021736145
2023-01-22 10:23:40.612988: step: 304/77, loss: 0.002945370739325881
2023-01-22 10:23:42.077323: step: 308/77, loss: 0.0017267671646550298
2023-01-22 10:23:43.578848: step: 312/77, loss: 0.0015203878283500671
2023-01-22 10:23:44.993636: step: 316/77, loss: 0.009436001069843769
2023-01-22 10:23:46.399012: step: 320/77, loss: 0.00017988021136261523
2023-01-22 10:23:47.852022: step: 324/77, loss: 0.0006251703598536551
2023-01-22 10:23:49.338391: step: 328/77, loss: 0.004496883600950241
2023-01-22 10:23:50.853374: step: 332/77, loss: 0.0008476347429677844
2023-01-22 10:23:52.281094: step: 336/77, loss: 0.0237599965184927
2023-01-22 10:23:53.782087: step: 340/77, loss: 0.0004581378889270127
2023-01-22 10:23:55.250676: step: 344/77, loss: 0.0019197032088413835
2023-01-22 10:23:56.754088: step: 348/77, loss: 5.6227523600682616e-05
2023-01-22 10:23:58.239510: step: 352/77, loss: 2.4058379494817927e-05
2023-01-22 10:23:59.711188: step: 356/77, loss: 0.048158254474401474
2023-01-22 10:24:01.135308: step: 360/77, loss: 0.07158225774765015
2023-01-22 10:24:02.685934: step: 364/77, loss: 0.006104794796556234
2023-01-22 10:24:04.195897: step: 368/77, loss: 0.010368650779128075
2023-01-22 10:24:05.641645: step: 372/77, loss: 0.018325114622712135
2023-01-22 10:24:07.120327: step: 376/77, loss: 0.07363635301589966
2023-01-22 10:24:08.596537: step: 380/77, loss: 0.002189134480431676
2023-01-22 10:24:10.007692: step: 384/77, loss: 0.0005988850025460124
2023-01-22 10:24:11.416972: step: 388/77, loss: 0.00013736364780925214
==================================================
Loss: 0.014
--------------------
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': 16}
Test Chinese: {'template': {'p': 0.9054054054054054, 'r': 0.5114503816793893, 'f1': 0.6536585365853658}, 'slot': {'p': 0.3953488372093023, 'r': 0.014667817083692839, 'f1': 0.028286189683860232}, 'combined': 0.018489509354328148, 'epoch': 16}
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': 16}
Test Korean: {'template': {'p': 0.9054054054054054, 'r': 0.5114503816793893, 'f1': 0.6536585365853658}, 'slot': {'p': 0.3953488372093023, 'r': 0.014667817083692839, 'f1': 0.028286189683860232}, 'combined': 0.018489509354328148, 'epoch': 16}
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': 16}
Test Russian: {'template': {'p': 0.8918918918918919, 'r': 0.5038167938931297, 'f1': 0.6439024390243903}, 'slot': {'p': 0.3902439024390244, 'r': 0.013805004314063849, 'f1': 0.02666666666666667}, 'combined': 0.017170731707317075, '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': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 10:25:48.928608: step: 4/77, loss: 0.004096877295523882
2023-01-22 10:25:50.382327: step: 8/77, loss: 0.004776291083544493
2023-01-22 10:25:51.851843: step: 12/77, loss: 0.005598829127848148
2023-01-22 10:25:53.397545: step: 16/77, loss: 0.002439585980027914
2023-01-22 10:25:54.830907: step: 20/77, loss: 3.45842563547194e-05
2023-01-22 10:25:56.342019: step: 24/77, loss: 0.0013430280378088355
2023-01-22 10:25:57.838077: step: 28/77, loss: 0.0018386875744909048
2023-01-22 10:25:59.340234: step: 32/77, loss: 0.0015910633374005556
2023-01-22 10:26:00.822160: step: 36/77, loss: 0.0009483025060035288
2023-01-22 10:26:02.307074: step: 40/77, loss: 0.007047180086374283
2023-01-22 10:26:03.775497: step: 44/77, loss: 0.00018717434431891888
2023-01-22 10:26:05.287874: step: 48/77, loss: 0.001299167750403285
2023-01-22 10:26:06.740831: step: 52/77, loss: 0.0006834648665972054
2023-01-22 10:26:08.246690: step: 56/77, loss: 0.002170323161408305
2023-01-22 10:26:09.755994: step: 60/77, loss: 0.002382697071880102
2023-01-22 10:26:11.190824: step: 64/77, loss: 0.000798621098510921
2023-01-22 10:26:12.736417: step: 68/77, loss: 0.003686311189085245
2023-01-22 10:26:14.173148: step: 72/77, loss: 0.06565132737159729
2023-01-22 10:26:15.663639: step: 76/77, loss: 0.005340840667486191
2023-01-22 10:26:17.107722: step: 80/77, loss: 0.0011033548507839441
2023-01-22 10:26:18.625794: step: 84/77, loss: 0.0021340290550142527
2023-01-22 10:26:20.053498: step: 88/77, loss: 0.0003320540417917073
2023-01-22 10:26:21.542824: step: 92/77, loss: 0.001845193444751203
2023-01-22 10:26:22.987302: step: 96/77, loss: 0.0006272225291468203
2023-01-22 10:26:24.466647: step: 100/77, loss: 0.0001363737101200968
2023-01-22 10:26:25.984172: step: 104/77, loss: 5.750182026531547e-05
2023-01-22 10:26:27.467967: step: 108/77, loss: 0.05694460868835449
2023-01-22 10:26:28.920359: step: 112/77, loss: 0.050074946135282516
2023-01-22 10:26:30.341338: step: 116/77, loss: 0.0011947468155995011
2023-01-22 10:26:31.817471: step: 120/77, loss: 0.0027722204104065895
2023-01-22 10:26:33.265920: step: 124/77, loss: 0.0018663202645257115
2023-01-22 10:26:34.800114: step: 128/77, loss: 0.0026401153299957514
2023-01-22 10:26:36.229299: step: 132/77, loss: 0.006284075789153576
2023-01-22 10:26:37.690425: step: 136/77, loss: 0.0007562717655673623
2023-01-22 10:26:39.222600: step: 140/77, loss: 0.035824716091156006
2023-01-22 10:26:40.694185: step: 144/77, loss: 0.026698850095272064
2023-01-22 10:26:42.212932: step: 148/77, loss: 0.00026182507281191647
2023-01-22 10:26:43.723836: step: 152/77, loss: 0.00024711183505132794
2023-01-22 10:26:45.146418: step: 156/77, loss: 0.042546238750219345
2023-01-22 10:26:46.645987: step: 160/77, loss: 0.13341380655765533
2023-01-22 10:26:48.156068: step: 164/77, loss: 0.00846744142472744
2023-01-22 10:26:49.728979: step: 168/77, loss: 0.08409827202558517
2023-01-22 10:26:51.207086: step: 172/77, loss: 0.0067952219396829605
2023-01-22 10:26:52.636013: step: 176/77, loss: 0.0042352499440312386
2023-01-22 10:26:53.992657: step: 180/77, loss: 0.00029177599935792387
2023-01-22 10:26:55.483299: step: 184/77, loss: 0.00332057336345315
2023-01-22 10:26:56.990854: step: 188/77, loss: 0.002562582725659013
2023-01-22 10:26:58.475472: step: 192/77, loss: 0.14900614321231842
2023-01-22 10:26:59.924495: step: 196/77, loss: 0.006481688003987074
2023-01-22 10:27:01.375823: step: 200/77, loss: 0.00015579882892780006
2023-01-22 10:27:02.834500: step: 204/77, loss: 0.019360896199941635
2023-01-22 10:27:04.318172: step: 208/77, loss: 0.004088334273546934
2023-01-22 10:27:05.775189: step: 212/77, loss: 0.00019180560775566846
2023-01-22 10:27:07.130242: step: 216/77, loss: 0.0003879494033753872
2023-01-22 10:27:08.596243: step: 220/77, loss: 0.0012808794854208827
2023-01-22 10:27:10.053527: step: 224/77, loss: 0.00027431672788225114
2023-01-22 10:27:11.567656: step: 228/77, loss: 0.00030285323737189174
2023-01-22 10:27:13.101313: step: 232/77, loss: 9.394896915182471e-05
2023-01-22 10:27:14.576755: step: 236/77, loss: 0.005379479378461838
2023-01-22 10:27:16.052769: step: 240/77, loss: 0.00025858887238427997
2023-01-22 10:27:17.516734: step: 244/77, loss: 0.020550856366753578
2023-01-22 10:27:19.005600: step: 248/77, loss: 0.005961176007986069
2023-01-22 10:27:20.532066: step: 252/77, loss: 0.0003792982315644622
2023-01-22 10:27:22.033793: step: 256/77, loss: 0.00023473313194699585
2023-01-22 10:27:23.505371: step: 260/77, loss: 0.0024014206137508154
2023-01-22 10:27:24.978855: step: 264/77, loss: 2.4127570213750005e-05
2023-01-22 10:27:26.405641: step: 268/77, loss: 0.0009776921942830086
2023-01-22 10:27:27.841492: step: 272/77, loss: 0.010743441991508007
2023-01-22 10:27:29.327677: step: 276/77, loss: 0.007811921648681164
2023-01-22 10:27:30.818547: step: 280/77, loss: 0.002057426143437624
2023-01-22 10:27:32.326106: step: 284/77, loss: 0.0005255554569885135
2023-01-22 10:27:33.849796: step: 288/77, loss: 9.64771315921098e-05
2023-01-22 10:27:35.343539: step: 292/77, loss: 0.0022660386748611927
2023-01-22 10:27:36.888176: step: 296/77, loss: 0.0022366391494870186
2023-01-22 10:27:38.301350: step: 300/77, loss: 0.0016711915377527475
2023-01-22 10:27:39.763957: step: 304/77, loss: 0.0007188515737652779
2023-01-22 10:27:41.233937: step: 308/77, loss: 0.020181728526949883
2023-01-22 10:27:42.733469: step: 312/77, loss: 0.00023877693456597626
2023-01-22 10:27:44.165251: step: 316/77, loss: 0.002911501796916127
2023-01-22 10:27:45.644958: step: 320/77, loss: 0.0006735376664437354
2023-01-22 10:27:47.087094: step: 324/77, loss: 0.0001844169746618718
2023-01-22 10:27:48.539597: step: 328/77, loss: 0.06680993735790253
2023-01-22 10:27:49.990544: step: 332/77, loss: 0.00025244487915188074
2023-01-22 10:27:51.502300: step: 336/77, loss: 0.0013559891376644373
2023-01-22 10:27:52.981337: step: 340/77, loss: 0.021186305209994316
2023-01-22 10:27:54.457792: step: 344/77, loss: 0.0040461840108036995
2023-01-22 10:27:55.901273: step: 348/77, loss: 0.0058979676105082035
2023-01-22 10:27:57.372716: step: 352/77, loss: 1.0261072020512074e-05
2023-01-22 10:27:58.884580: step: 356/77, loss: 0.002143705729395151
2023-01-22 10:28:00.399434: step: 360/77, loss: 0.06320623308420181
2023-01-22 10:28:01.911329: step: 364/77, loss: 0.00015051935042720288
2023-01-22 10:28:03.373955: step: 368/77, loss: 1.2711274393950589e-05
2023-01-22 10:28:04.806653: step: 372/77, loss: 0.21453514695167542
2023-01-22 10:28:06.278679: step: 376/77, loss: 0.014170726761221886
2023-01-22 10:28:07.680431: step: 380/77, loss: 6.4277210185537115e-06
2023-01-22 10:28:09.185018: step: 384/77, loss: 0.022878451272845268
2023-01-22 10:28:10.661181: step: 388/77, loss: 0.02404708042740822
==================================================
Loss: 0.013
--------------------
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': 17}
Test Chinese: {'template': {'p': 0.8552631578947368, 'r': 0.4961832061068702, 'f1': 0.6280193236714976}, 'slot': {'p': 0.4166666666666667, 'r': 0.012942191544434857, 'f1': 0.02510460251046025}, 'combined': 0.015766175489661027, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5333333333333333, 'f1': 0.6956521739130436}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.04890349201497669, 'epoch': 17}
Test Korean: {'template': {'p': 0.8648648648648649, 'r': 0.48854961832061067, 'f1': 0.624390243902439}, 'slot': {'p': 0.43243243243243246, 'r': 0.013805004314063849, 'f1': 0.026755852842809368}, 'combined': 0.016706093482339507, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.55, 'f1': 0.7096774193548387}, 'slot': {'p': 0.5, 'r': 0.03780718336483932, 'f1': 0.07029876977152899}, 'combined': 0.04988944951527864, 'epoch': 17}
Test Russian: {'template': {'p': 0.8648648648648649, 'r': 0.48854961832061067, 'f1': 0.624390243902439}, 'slot': {'p': 0.4594594594594595, 'r': 0.014667817083692839, 'f1': 0.028428093645484948}, 'combined': 0.017750224324985724, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 10:29:48.180955: step: 4/77, loss: 0.0028756712563335896
2023-01-22 10:29:49.681624: step: 8/77, loss: 0.045157160609960556
2023-01-22 10:29:51.131110: step: 12/77, loss: 0.012379593215882778
2023-01-22 10:29:52.583507: step: 16/77, loss: 0.02100391685962677
2023-01-22 10:29:54.066888: step: 20/77, loss: 0.0064195566810667515
2023-01-22 10:29:55.536601: step: 24/77, loss: 0.003383409697562456
2023-01-22 10:29:56.956472: step: 28/77, loss: 0.000816413841675967
2023-01-22 10:29:58.392001: step: 32/77, loss: 0.013582956977188587
2023-01-22 10:29:59.903787: step: 36/77, loss: 0.010575263760983944
2023-01-22 10:30:01.331508: step: 40/77, loss: 0.0007761925226077437
2023-01-22 10:30:02.823424: step: 44/77, loss: 0.005285558756440878
2023-01-22 10:30:04.326003: step: 48/77, loss: 0.001977279782295227
2023-01-22 10:30:05.784741: step: 52/77, loss: 0.001641746610403061
2023-01-22 10:30:07.248377: step: 56/77, loss: 6.50401216262253e-06
2023-01-22 10:30:08.736596: step: 60/77, loss: 0.02756490930914879
2023-01-22 10:30:10.193239: step: 64/77, loss: 0.0005078827380202711
2023-01-22 10:30:11.586704: step: 68/77, loss: 0.005699621979147196
2023-01-22 10:30:13.039388: step: 72/77, loss: 0.0027254566084593534
2023-01-22 10:30:14.535446: step: 76/77, loss: 2.5649595045251772e-05
2023-01-22 10:30:16.029067: step: 80/77, loss: 1.5124951460165903e-05
2023-01-22 10:30:17.455929: step: 84/77, loss: 0.03806731477379799
2023-01-22 10:30:18.982063: step: 88/77, loss: 0.001081199967302382
2023-01-22 10:30:20.440525: step: 92/77, loss: 1.783421430445742e-05
2023-01-22 10:30:21.820902: step: 96/77, loss: 0.04326368868350983
2023-01-22 10:30:23.302073: step: 100/77, loss: 0.006358175538480282
2023-01-22 10:30:24.793837: step: 104/77, loss: 0.0016182229155674577
2023-01-22 10:30:26.249851: step: 108/77, loss: 0.007719434332102537
2023-01-22 10:30:27.726569: step: 112/77, loss: 0.08727987110614777
2023-01-22 10:30:29.187950: step: 116/77, loss: 6.309882155619562e-05
2023-01-22 10:30:30.631011: step: 120/77, loss: 0.009384812787175179
2023-01-22 10:30:32.137298: step: 124/77, loss: 0.0004629144095815718
2023-01-22 10:30:33.653093: step: 128/77, loss: 0.0019581338856369257
2023-01-22 10:30:35.099860: step: 132/77, loss: 0.0017693155677989125
2023-01-22 10:30:36.531468: step: 136/77, loss: 5.7300036132801324e-05
2023-01-22 10:30:38.036982: step: 140/77, loss: 0.0002848027506843209
2023-01-22 10:30:39.474825: step: 144/77, loss: 0.0009141655173152685
2023-01-22 10:30:40.988389: step: 148/77, loss: 0.0034261501859873533
2023-01-22 10:30:42.514699: step: 152/77, loss: 0.09311222285032272
2023-01-22 10:30:43.955620: step: 156/77, loss: 0.0011829708237200975
2023-01-22 10:30:45.406166: step: 160/77, loss: 0.0006447265041060746
2023-01-22 10:30:46.934448: step: 164/77, loss: 0.007240463979542255
2023-01-22 10:30:48.416397: step: 168/77, loss: 0.020239055156707764
2023-01-22 10:30:49.862809: step: 172/77, loss: 0.00021344999549910426
2023-01-22 10:30:51.300551: step: 176/77, loss: 0.0005965419695712626
2023-01-22 10:30:52.796396: step: 180/77, loss: 0.0009922974277287722
2023-01-22 10:30:54.344392: step: 184/77, loss: 0.0048019420355558395
2023-01-22 10:30:55.834993: step: 188/77, loss: 0.0009401412680745125
2023-01-22 10:30:57.339817: step: 192/77, loss: 0.0022180110681802034
2023-01-22 10:30:58.901148: step: 196/77, loss: 0.00930736307054758
2023-01-22 10:31:00.376876: step: 200/77, loss: 0.0036351527087390423
2023-01-22 10:31:01.914836: step: 204/77, loss: 0.00014229273074306548
2023-01-22 10:31:03.316731: step: 208/77, loss: 0.0007904646918177605
2023-01-22 10:31:04.782902: step: 212/77, loss: 0.003755400190129876
2023-01-22 10:31:06.248385: step: 216/77, loss: 9.308937296736985e-05
2023-01-22 10:31:07.705802: step: 220/77, loss: 3.324115095892921e-05
2023-01-22 10:31:09.168544: step: 224/77, loss: 0.0007430835394188762
2023-01-22 10:31:10.599090: step: 228/77, loss: 0.01505276933312416
2023-01-22 10:31:12.149587: step: 232/77, loss: 0.0008096634410321712
2023-01-22 10:31:13.577717: step: 236/77, loss: 0.0005306456587277353
2023-01-22 10:31:15.041090: step: 240/77, loss: 0.0006985433283261955
2023-01-22 10:31:16.589508: step: 244/77, loss: 0.0006532074767164886
2023-01-22 10:31:18.052755: step: 248/77, loss: 1.2684857210842893e-05
2023-01-22 10:31:19.513571: step: 252/77, loss: 3.6554571124725044e-05
2023-01-22 10:31:21.011949: step: 256/77, loss: 0.0003153039433527738
2023-01-22 10:31:22.545178: step: 260/77, loss: 0.0004511611768975854
2023-01-22 10:31:24.014108: step: 264/77, loss: 0.04475802928209305
2023-01-22 10:31:25.471703: step: 268/77, loss: 8.685257489560172e-05
2023-01-22 10:31:26.929568: step: 272/77, loss: 0.00020022218814119697
2023-01-22 10:31:28.408586: step: 276/77, loss: 0.004787555430084467
2023-01-22 10:31:29.870544: step: 280/77, loss: 0.0038822393398731947
2023-01-22 10:31:31.382574: step: 284/77, loss: 0.05055629462003708
2023-01-22 10:31:32.881393: step: 288/77, loss: 0.002044880762696266
2023-01-22 10:31:34.363647: step: 292/77, loss: 0.00030714101740159094
2023-01-22 10:31:35.864789: step: 296/77, loss: 0.0073666879907250404
2023-01-22 10:31:37.398460: step: 300/77, loss: 0.000893754418939352
2023-01-22 10:31:38.853227: step: 304/77, loss: 0.004460779018700123
2023-01-22 10:31:40.371823: step: 308/77, loss: 0.0016178349032998085
2023-01-22 10:31:41.778276: step: 312/77, loss: 0.0005586580373346806
2023-01-22 10:31:43.220256: step: 316/77, loss: 0.0004077023477293551
2023-01-22 10:31:44.751048: step: 320/77, loss: 0.0034647120628505945
2023-01-22 10:31:46.263212: step: 324/77, loss: 0.0008419217774644494
2023-01-22 10:31:47.688296: step: 328/77, loss: 0.00011264411295996979
2023-01-22 10:31:49.213388: step: 332/77, loss: 0.0011876357020810246
2023-01-22 10:31:50.741184: step: 336/77, loss: 0.011139290407299995
2023-01-22 10:31:52.210712: step: 340/77, loss: 0.0006338097155094147
2023-01-22 10:31:53.737739: step: 344/77, loss: 0.00022002437617629766
2023-01-22 10:31:55.198256: step: 348/77, loss: 4.005714799859561e-05
2023-01-22 10:31:56.682209: step: 352/77, loss: 0.0015249974094331264
2023-01-22 10:31:58.153963: step: 356/77, loss: 0.003730625845491886
2023-01-22 10:31:59.581256: step: 360/77, loss: 0.0007901267963461578
2023-01-22 10:32:01.014277: step: 364/77, loss: 0.00011056935181841254
2023-01-22 10:32:02.551118: step: 368/77, loss: 0.005171317607164383
2023-01-22 10:32:04.024005: step: 372/77, loss: 0.005288761109113693
2023-01-22 10:32:05.541735: step: 376/77, loss: 0.006044285371899605
2023-01-22 10:32:07.047853: step: 380/77, loss: 0.0016455070581287146
2023-01-22 10:32:08.542578: step: 384/77, loss: 0.0005599971045739949
2023-01-22 10:32:09.939662: step: 388/77, loss: 0.003552208887413144
==================================================
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': 18}
Test Chinese: {'template': {'p': 0.881578947368421, 'r': 0.5114503816793893, 'f1': 0.6473429951690821}, 'slot': {'p': 0.4473684210526316, 'r': 0.014667817083692839, 'f1': 0.028404344193817876}, 'combined': 0.01838735324623959, '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': 0.8933333333333333, 'r': 0.5114503816793893, 'f1': 0.6504854368932039}, 'slot': {'p': 0.4722222222222222, 'r': 0.014667817083692839, 'f1': 0.028451882845188285}, 'combined': 0.018507535442986556, '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': 0.9054054054054054, 'r': 0.5114503816793893, 'f1': 0.6536585365853658}, 'slot': {'p': 0.4857142857142857, 'r': 0.014667817083692839, 'f1': 0.02847571189279732}, 'combined': 0.01861339216407239, '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': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 10:33:47.467246: step: 4/77, loss: 0.00014098669635131955
2023-01-22 10:33:48.952491: step: 8/77, loss: 0.037430573254823685
2023-01-22 10:33:50.398166: step: 12/77, loss: 9.992123523261398e-06
2023-01-22 10:33:51.828765: step: 16/77, loss: 0.027012495324015617
2023-01-22 10:33:53.305199: step: 20/77, loss: 0.0012325807474553585
2023-01-22 10:33:54.807292: step: 24/77, loss: 0.00010384414781583473
2023-01-22 10:33:56.272673: step: 28/77, loss: 0.05970339477062225
2023-01-22 10:33:57.817392: step: 32/77, loss: 0.010155356489121914
2023-01-22 10:33:59.332498: step: 36/77, loss: 0.019072813913226128
2023-01-22 10:34:00.802820: step: 40/77, loss: 0.00041514128679409623
2023-01-22 10:34:02.307913: step: 44/77, loss: 0.0005081351846456528
2023-01-22 10:34:03.727666: step: 48/77, loss: 5.959239206276834e-05
2023-01-22 10:34:05.237569: step: 52/77, loss: 0.00889910850673914
2023-01-22 10:34:06.694602: step: 56/77, loss: 0.03261871263384819
2023-01-22 10:34:08.127470: step: 60/77, loss: 0.00019574278849177063
2023-01-22 10:34:09.586844: step: 64/77, loss: 7.374716369668022e-05
2023-01-22 10:34:11.050907: step: 68/77, loss: 0.001230890746228397
2023-01-22 10:34:12.534082: step: 72/77, loss: 0.03803974390029907
2023-01-22 10:34:13.958492: step: 76/77, loss: 0.00023354985751211643
2023-01-22 10:34:15.491259: step: 80/77, loss: 0.0221809484064579
2023-01-22 10:34:16.897001: step: 84/77, loss: 0.00018142740009352565
2023-01-22 10:34:18.380261: step: 88/77, loss: 0.027372796088457108
2023-01-22 10:34:19.888165: step: 92/77, loss: 0.0009225103422068059
2023-01-22 10:34:21.393646: step: 96/77, loss: 0.0002753528533503413
2023-01-22 10:34:22.842602: step: 100/77, loss: 0.04084169119596481
2023-01-22 10:34:24.296854: step: 104/77, loss: 0.033095426857471466
2023-01-22 10:34:25.771233: step: 108/77, loss: 0.019844137132167816
2023-01-22 10:34:27.194050: step: 112/77, loss: 0.00010307527554687113
2023-01-22 10:34:28.586338: step: 116/77, loss: 0.07973741739988327
2023-01-22 10:34:30.084998: step: 120/77, loss: 0.007755426689982414
2023-01-22 10:34:31.504352: step: 124/77, loss: 0.0020310066174715757
2023-01-22 10:34:32.973322: step: 128/77, loss: 0.0014131821226328611
2023-01-22 10:34:34.428911: step: 132/77, loss: 0.0007622442790307105
2023-01-22 10:34:35.906926: step: 136/77, loss: 0.0013501873472705483
2023-01-22 10:34:37.328943: step: 140/77, loss: 0.003476389916613698
2023-01-22 10:34:38.870499: step: 144/77, loss: 0.004717133939266205
2023-01-22 10:34:40.337320: step: 148/77, loss: 0.034023940563201904
2023-01-22 10:34:41.867982: step: 152/77, loss: 0.0025565975811332464
2023-01-22 10:34:43.480068: step: 156/77, loss: 0.0021379715763032436
2023-01-22 10:34:44.944678: step: 160/77, loss: 0.008405786007642746
2023-01-22 10:34:46.430278: step: 164/77, loss: 0.0002632577088661492
2023-01-22 10:34:47.963457: step: 168/77, loss: 0.007901491597294807
2023-01-22 10:34:49.458001: step: 172/77, loss: 0.0023893998004496098
2023-01-22 10:34:50.982301: step: 176/77, loss: 0.00036748748971149325
2023-01-22 10:34:52.466862: step: 180/77, loss: 6.505564670078456e-06
2023-01-22 10:34:54.001775: step: 184/77, loss: 0.002341366373002529
2023-01-22 10:34:55.457055: step: 188/77, loss: 0.00022118315973784775
2023-01-22 10:34:56.878916: step: 192/77, loss: 1.2627208889171015e-05
2023-01-22 10:34:58.382286: step: 196/77, loss: 0.0001342456671409309
2023-01-22 10:34:59.928471: step: 200/77, loss: 0.028776878491044044
2023-01-22 10:35:01.422118: step: 204/77, loss: 0.00026175566017627716
2023-01-22 10:35:02.935137: step: 208/77, loss: 0.0006376546807587147
2023-01-22 10:35:04.399715: step: 212/77, loss: 0.0004763914621435106
2023-01-22 10:35:05.865642: step: 216/77, loss: 3.821781137958169e-05
2023-01-22 10:35:07.361119: step: 220/77, loss: 0.00015172931307461113
2023-01-22 10:35:08.864488: step: 224/77, loss: 1.782135996108991e-06
2023-01-22 10:35:10.341322: step: 228/77, loss: 6.226929144759197e-06
2023-01-22 10:35:11.830719: step: 232/77, loss: 0.0005442426190711558
2023-01-22 10:35:13.240025: step: 236/77, loss: 6.345907604554668e-05
2023-01-22 10:35:14.729698: step: 240/77, loss: 8.847442222759128e-05
2023-01-22 10:35:16.192416: step: 244/77, loss: 0.0030105954501777887
2023-01-22 10:35:17.646593: step: 248/77, loss: 1.6285044694086537e-05
2023-01-22 10:35:19.202189: step: 252/77, loss: 0.00028308553737588227
2023-01-22 10:35:20.622448: step: 256/77, loss: 7.794688281137496e-05
2023-01-22 10:35:22.062470: step: 260/77, loss: 0.004675406496971846
2023-01-22 10:35:23.504771: step: 264/77, loss: 0.009595395065844059
2023-01-22 10:35:25.005204: step: 268/77, loss: 0.09094759076833725
2023-01-22 10:35:26.534284: step: 272/77, loss: 0.00025511524290777743
2023-01-22 10:35:28.033300: step: 276/77, loss: 8.626453200122342e-05
2023-01-22 10:35:29.471625: step: 280/77, loss: 2.5752302462933585e-05
2023-01-22 10:35:30.939939: step: 284/77, loss: 0.00047939157229848206
2023-01-22 10:35:32.482471: step: 288/77, loss: 0.0007043445948511362
2023-01-22 10:35:33.957545: step: 292/77, loss: 3.5091293284494895e-06
2023-01-22 10:35:35.416243: step: 296/77, loss: 0.004549146164208651
2023-01-22 10:35:36.947090: step: 300/77, loss: 0.0013034878065809608
2023-01-22 10:35:38.392898: step: 304/77, loss: 7.059721247060224e-05
2023-01-22 10:35:39.790265: step: 308/77, loss: 0.028981227427721024
2023-01-22 10:35:41.234569: step: 312/77, loss: 5.120259811519645e-05
2023-01-22 10:35:42.642097: step: 316/77, loss: 0.0703129917383194
2023-01-22 10:35:44.140421: step: 320/77, loss: 8.140176760207396e-06
2023-01-22 10:35:45.633609: step: 324/77, loss: 0.02896547131240368
2023-01-22 10:35:47.122657: step: 328/77, loss: 1.8530841771280393e-05
2023-01-22 10:35:48.606897: step: 332/77, loss: 0.0004325577465351671
2023-01-22 10:35:50.064352: step: 336/77, loss: 0.0001609406026545912
2023-01-22 10:35:51.573361: step: 340/77, loss: 0.0032217581756412983
2023-01-22 10:35:53.083181: step: 344/77, loss: 0.00014991796342656016
2023-01-22 10:35:54.520923: step: 348/77, loss: 0.041126806288957596
2023-01-22 10:35:55.996219: step: 352/77, loss: 0.00013102588127367198
2023-01-22 10:35:57.517895: step: 356/77, loss: 0.00045040063560009
2023-01-22 10:35:59.039117: step: 360/77, loss: 5.666089418809861e-05
2023-01-22 10:36:00.475913: step: 364/77, loss: 0.0007076942129060626
2023-01-22 10:36:01.911602: step: 368/77, loss: 0.0002744776720646769
2023-01-22 10:36:03.441859: step: 372/77, loss: 1.4699688108521514e-05
2023-01-22 10:36:04.894781: step: 376/77, loss: 0.006560564041137695
2023-01-22 10:36:06.363936: step: 380/77, loss: 0.017250539734959602
2023-01-22 10:36:07.808280: step: 384/77, loss: 0.007945503108203411
2023-01-22 10:36:09.260792: step: 388/77, loss: 0.0006101108156144619
==================================================
Loss: 0.009
--------------------
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': 19}
Test Chinese: {'template': {'p': 0.9178082191780822, 'r': 0.5114503816793893, 'f1': 0.6568627450980392}, 'slot': {'p': 0.4857142857142857, 'r': 0.014667817083692839, 'f1': 0.02847571189279732}, 'combined': 0.018704634282523728, 'epoch': 19}
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': 19}
Test Korean: {'template': {'p': 0.9295774647887324, 'r': 0.5038167938931297, 'f1': 0.6534653465346535}, 'slot': {'p': 0.5, 'r': 0.014667817083692839, 'f1': 0.028499580888516347}, 'combined': 0.018623488501406722, 'epoch': 19}
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': 19}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5038167938931297, 'f1': 0.6534653465346535}, 'slot': {'p': 0.5, 'r': 0.014667817083692839, 'f1': 0.028499580888516347}, 'combined': 0.018623488501406722, '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': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 10:37:46.815008: step: 4/77, loss: 8.427352440776303e-05
2023-01-22 10:37:48.261401: step: 8/77, loss: 0.003391423961147666
2023-01-22 10:37:49.808242: step: 12/77, loss: 0.00022610797896049917
2023-01-22 10:37:51.198622: step: 16/77, loss: 0.012872123159468174
2023-01-22 10:37:52.649560: step: 20/77, loss: 7.742694288026541e-05
2023-01-22 10:37:54.112477: step: 24/77, loss: 0.00036254245787858963
2023-01-22 10:37:55.629096: step: 28/77, loss: 0.0004164370766375214
2023-01-22 10:37:57.080144: step: 32/77, loss: 0.0007234312943182886
2023-01-22 10:37:58.611175: step: 36/77, loss: 0.005771125201135874
2023-01-22 10:37:59.992025: step: 40/77, loss: 0.003106000367552042
2023-01-22 10:38:01.405953: step: 44/77, loss: 0.017629720270633698
2023-01-22 10:38:02.917309: step: 48/77, loss: 0.02136806771159172
2023-01-22 10:38:04.403492: step: 52/77, loss: 0.00046486067003570497
2023-01-22 10:38:05.890750: step: 56/77, loss: 0.001176183228380978
2023-01-22 10:38:07.386876: step: 60/77, loss: 0.006411808542907238
2023-01-22 10:38:08.858107: step: 64/77, loss: 0.0006058060680516064
2023-01-22 10:38:10.397854: step: 68/77, loss: 2.3365575543721206e-05
2023-01-22 10:38:11.887713: step: 72/77, loss: 0.008123316802084446
2023-01-22 10:38:13.376812: step: 76/77, loss: 1.5268948118318804e-05
2023-01-22 10:38:14.873572: step: 80/77, loss: 6.315793143585324e-05
2023-01-22 10:38:16.385091: step: 84/77, loss: 0.00023585847520735115
2023-01-22 10:38:17.865332: step: 88/77, loss: 0.00752745708450675
2023-01-22 10:38:19.324544: step: 92/77, loss: 0.0002199528826167807
2023-01-22 10:38:20.799224: step: 96/77, loss: 0.0004972168244421482
2023-01-22 10:38:22.324815: step: 100/77, loss: 0.0022977537009865046
2023-01-22 10:38:23.818340: step: 104/77, loss: 8.510050975019112e-05
2023-01-22 10:38:25.420014: step: 108/77, loss: 0.000818159431219101
2023-01-22 10:38:26.899654: step: 112/77, loss: 3.944763739127666e-05
2023-01-22 10:38:28.370914: step: 116/77, loss: 0.005611030850559473
2023-01-22 10:38:29.871928: step: 120/77, loss: 0.027019493281841278
2023-01-22 10:38:31.360614: step: 124/77, loss: 0.00016905099619179964
2023-01-22 10:38:32.835751: step: 128/77, loss: 0.000452701176982373
2023-01-22 10:38:34.355525: step: 132/77, loss: 0.001107914256863296
2023-01-22 10:38:35.857712: step: 136/77, loss: 3.4447726648068056e-05
2023-01-22 10:38:37.290596: step: 140/77, loss: 0.0005560338613577187
2023-01-22 10:38:38.803115: step: 144/77, loss: 0.00014413423195946962
2023-01-22 10:38:40.303276: step: 148/77, loss: 0.00014533651119563729
2023-01-22 10:38:41.734176: step: 152/77, loss: 0.005465753376483917
2023-01-22 10:38:43.268672: step: 156/77, loss: 1.3785129340249114e-05
2023-01-22 10:38:44.747951: step: 160/77, loss: 0.0049934606067836285
2023-01-22 10:38:46.255569: step: 164/77, loss: 0.001129616517573595
2023-01-22 10:38:47.728890: step: 168/77, loss: 0.003189380746334791
2023-01-22 10:38:49.140955: step: 172/77, loss: 6.476558610302163e-06
2023-01-22 10:38:50.627731: step: 176/77, loss: 0.02472682110965252
2023-01-22 10:38:52.115509: step: 180/77, loss: 5.072112344350899e-06
2023-01-22 10:38:53.587894: step: 184/77, loss: 0.0020358862821012735
2023-01-22 10:38:55.013436: step: 188/77, loss: 0.0002398270444246009
2023-01-22 10:38:56.521548: step: 192/77, loss: 0.05871470272541046
2023-01-22 10:38:58.090059: step: 196/77, loss: 0.002355430740863085
2023-01-22 10:38:59.608702: step: 200/77, loss: 0.0007327854400500655
2023-01-22 10:39:01.150621: step: 204/77, loss: 0.0006290523451752961
2023-01-22 10:39:02.664318: step: 208/77, loss: 0.00018614571308717132
2023-01-22 10:39:04.156304: step: 212/77, loss: 0.00010260358249070123
2023-01-22 10:39:05.644525: step: 216/77, loss: 0.022568479180336
2023-01-22 10:39:07.082054: step: 220/77, loss: 0.0005458329687826335
2023-01-22 10:39:08.518473: step: 224/77, loss: 0.0008564339368604124
2023-01-22 10:39:09.944923: step: 228/77, loss: 0.0035173415672034025
2023-01-22 10:39:11.369137: step: 232/77, loss: 0.016759483143687248
2023-01-22 10:39:12.891125: step: 236/77, loss: 0.03251827880740166
2023-01-22 10:39:14.285812: step: 240/77, loss: 0.00995706394314766
2023-01-22 10:39:15.706137: step: 244/77, loss: 0.0006280227098613977
2023-01-22 10:39:17.174872: step: 248/77, loss: 0.04479119926691055
2023-01-22 10:39:18.697670: step: 252/77, loss: 0.00023071595933288336
2023-01-22 10:39:20.169548: step: 256/77, loss: 0.0007097484776750207
2023-01-22 10:39:21.655003: step: 260/77, loss: 0.00010665479203453287
2023-01-22 10:39:23.087072: step: 264/77, loss: 0.0001831296249292791
2023-01-22 10:39:24.547085: step: 268/77, loss: 0.0060518416576087475
2023-01-22 10:39:26.003227: step: 272/77, loss: 0.0017663311446085572
2023-01-22 10:39:27.502967: step: 276/77, loss: 0.0004453969595488161
2023-01-22 10:39:28.935773: step: 280/77, loss: 0.0013352977111935616
2023-01-22 10:39:30.393193: step: 284/77, loss: 0.002567255636677146
2023-01-22 10:39:31.865004: step: 288/77, loss: 1.810535104596056e-05
2023-01-22 10:39:33.351426: step: 292/77, loss: 0.0020445568952709436
2023-01-22 10:39:34.890176: step: 296/77, loss: 1.9323746528243646e-05
2023-01-22 10:39:36.353161: step: 300/77, loss: 0.002380709396675229
2023-01-22 10:39:37.796121: step: 304/77, loss: 0.0007935311878100038
2023-01-22 10:39:39.289001: step: 308/77, loss: 0.0022404869087040424
2023-01-22 10:39:40.768735: step: 312/77, loss: 0.05067255347967148
2023-01-22 10:39:42.233221: step: 316/77, loss: 0.00011900630488526076
2023-01-22 10:39:43.683017: step: 320/77, loss: 0.0002168344653910026
2023-01-22 10:39:45.145736: step: 324/77, loss: 0.0004526789125520736
2023-01-22 10:39:46.640382: step: 328/77, loss: 0.000879471015650779
2023-01-22 10:39:48.141532: step: 332/77, loss: 0.0030491615179926157
2023-01-22 10:39:49.620774: step: 336/77, loss: 0.006456117145717144
2023-01-22 10:39:51.060034: step: 340/77, loss: 0.010428737848997116
2023-01-22 10:39:52.473742: step: 344/77, loss: 0.0005070596816949546
2023-01-22 10:39:54.007572: step: 348/77, loss: 0.00023114164650905877
2023-01-22 10:39:55.514182: step: 352/77, loss: 0.03697359934449196
2023-01-22 10:39:56.950542: step: 356/77, loss: 0.011408147402107716
2023-01-22 10:39:58.480492: step: 360/77, loss: 0.015400312840938568
2023-01-22 10:39:59.952487: step: 364/77, loss: 1.4918558008503169e-05
2023-01-22 10:40:01.397760: step: 368/77, loss: 0.0003141985216643661
2023-01-22 10:40:02.905273: step: 372/77, loss: 0.03331225365400314
2023-01-22 10:40:04.314531: step: 376/77, loss: 0.0009111135732382536
2023-01-22 10:40:05.759317: step: 380/77, loss: 0.0017461779061704874
2023-01-22 10:40:07.192451: step: 384/77, loss: 1.2481615158321802e-05
2023-01-22 10:40:08.654080: step: 388/77, loss: 0.032015111297369
==================================================
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': 0.9142857142857143, 'r': 0.48854961832061067, 'f1': 0.6368159203980099}, 'slot': {'p': 0.4722222222222222, 'r': 0.014667817083692839, 'f1': 0.028451882845188285}, 'combined': 0.018118611961114927, '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': 0.9130434782608695, 'r': 0.48091603053435117, 'f1': 0.63}, 'slot': {'p': 0.4857142857142857, 'r': 0.014667817083692839, 'f1': 0.02847571189279732}, 'combined': 0.01793969849246231, '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': 0.9142857142857143, 'r': 0.48854961832061067, 'f1': 0.6368159203980099}, 'slot': {'p': 0.4594594594594595, 'r': 0.014667817083692839, 'f1': 0.028428093645484948}, 'combined': 0.018103462620010315, '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': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 10:41:46.260960: step: 4/77, loss: 8.27891708468087e-05
2023-01-22 10:41:47.713312: step: 8/77, loss: 0.00043526801164261997
2023-01-22 10:41:49.175838: step: 12/77, loss: 9.745121133164503e-06
2023-01-22 10:41:50.681466: step: 16/77, loss: 2.9559068934759125e-05
2023-01-22 10:41:52.188549: step: 20/77, loss: 0.0003522019542288035
2023-01-22 10:41:53.687402: step: 24/77, loss: 0.00022706623713020235
2023-01-22 10:41:55.162911: step: 28/77, loss: 0.009877260774374008
2023-01-22 10:41:56.648861: step: 32/77, loss: 0.006384177133440971
2023-01-22 10:41:58.168194: step: 36/77, loss: 0.00014239516167435795
2023-01-22 10:41:59.662708: step: 40/77, loss: 0.0005055277142673731
2023-01-22 10:42:01.154604: step: 44/77, loss: 0.05409137159585953
2023-01-22 10:42:02.681036: step: 48/77, loss: 3.8041166590119246e-06
2023-01-22 10:42:04.216185: step: 52/77, loss: 8.18027911009267e-06
2023-01-22 10:42:05.732137: step: 56/77, loss: 9.932726243278012e-05
2023-01-22 10:42:07.216522: step: 60/77, loss: 0.00014925358118489385
2023-01-22 10:42:08.671214: step: 64/77, loss: 0.0002240837930003181
2023-01-22 10:42:10.112030: step: 68/77, loss: 5.057529415353201e-05
2023-01-22 10:42:11.595596: step: 72/77, loss: 9.591747584636323e-06
2023-01-22 10:42:13.187785: step: 76/77, loss: 6.70036433803034e-06
2023-01-22 10:42:14.694819: step: 80/77, loss: 0.0002989994827657938
2023-01-22 10:42:16.163273: step: 84/77, loss: 0.0007450602715834975
2023-01-22 10:42:17.691420: step: 88/77, loss: 0.02040993794798851
2023-01-22 10:42:19.130444: step: 92/77, loss: 1.1034421731892508e-05
2023-01-22 10:42:20.552855: step: 96/77, loss: 6.633730663452297e-05
2023-01-22 10:42:21.984782: step: 100/77, loss: 0.00017172204388771206
2023-01-22 10:42:23.478155: step: 104/77, loss: 2.5287281459895894e-05
2023-01-22 10:42:24.884432: step: 108/77, loss: 0.0019874691497534513
2023-01-22 10:42:26.380672: step: 112/77, loss: 0.0028940557967871428
2023-01-22 10:42:27.900227: step: 116/77, loss: 1.3265988854982425e-05
2023-01-22 10:42:29.356593: step: 120/77, loss: 1.3763572496827692e-05
2023-01-22 10:42:30.805388: step: 124/77, loss: 5.456419967231341e-05
2023-01-22 10:42:32.312310: step: 128/77, loss: 3.199049024260603e-05
2023-01-22 10:42:33.866203: step: 132/77, loss: 0.00015985312347766012
2023-01-22 10:42:35.315153: step: 136/77, loss: 0.0018992533441632986
2023-01-22 10:42:36.799876: step: 140/77, loss: 1.3396806025411934e-05
2023-01-22 10:42:38.306162: step: 144/77, loss: 0.0006888278294354677
2023-01-22 10:42:39.714245: step: 148/77, loss: 0.001850732951425016
2023-01-22 10:42:41.148175: step: 152/77, loss: 0.0010139790829271078
2023-01-22 10:42:42.651792: step: 156/77, loss: 4.4166750740259886e-05
2023-01-22 10:42:44.073134: step: 160/77, loss: 3.8711961678927764e-05
2023-01-22 10:42:45.532675: step: 164/77, loss: 4.7252186050172895e-05
2023-01-22 10:42:47.004631: step: 168/77, loss: 0.0015337056247517467
2023-01-22 10:42:48.424379: step: 172/77, loss: 1.5749639715068042e-05
2023-01-22 10:42:49.938807: step: 176/77, loss: 2.1206040401011705e-05
2023-01-22 10:42:51.384996: step: 180/77, loss: 0.00034399217111058533
2023-01-22 10:42:52.859078: step: 184/77, loss: 5.2080049499636516e-05
2023-01-22 10:42:54.423030: step: 188/77, loss: 0.017733346670866013
2023-01-22 10:42:55.931426: step: 192/77, loss: 0.07597655057907104
2023-01-22 10:42:57.424294: step: 196/77, loss: 0.24772121012210846
2023-01-22 10:42:58.873163: step: 200/77, loss: 9.717977081891149e-05
2023-01-22 10:43:00.381739: step: 204/77, loss: 0.00013973054592497647
2023-01-22 10:43:01.925613: step: 208/77, loss: 0.024061929434537888
2023-01-22 10:43:03.356389: step: 212/77, loss: 0.0001402836642228067
2023-01-22 10:43:04.868165: step: 216/77, loss: 0.00044021164649166167
2023-01-22 10:43:06.338120: step: 220/77, loss: 4.2444888094905764e-05
2023-01-22 10:43:07.803736: step: 224/77, loss: 0.00022847886430099607
2023-01-22 10:43:09.294916: step: 228/77, loss: 0.0002529481425881386
2023-01-22 10:43:10.722973: step: 232/77, loss: 2.9905932024121284e-06
2023-01-22 10:43:12.241175: step: 236/77, loss: 0.002287093782797456
2023-01-22 10:43:13.769439: step: 240/77, loss: 5.147743650013581e-06
2023-01-22 10:43:15.242280: step: 244/77, loss: 0.0014095694059506059
2023-01-22 10:43:16.676466: step: 248/77, loss: 2.9975240977364592e-05
2023-01-22 10:43:18.274774: step: 252/77, loss: 0.013966652564704418
2023-01-22 10:43:19.724634: step: 256/77, loss: 0.019837338477373123
2023-01-22 10:43:21.265972: step: 260/77, loss: 0.0011463196715340018
2023-01-22 10:43:22.767287: step: 264/77, loss: 9.620159835321829e-05
2023-01-22 10:43:24.238630: step: 268/77, loss: 0.00427041482180357
2023-01-22 10:43:25.650170: step: 272/77, loss: 0.00024166949151549488
2023-01-22 10:43:27.147406: step: 276/77, loss: 0.0034298989921808243
2023-01-22 10:43:28.602038: step: 280/77, loss: 2.2885571524966508e-05
2023-01-22 10:43:30.096756: step: 284/77, loss: 0.0002919553080573678
2023-01-22 10:43:31.603571: step: 288/77, loss: 0.0018753650365397334
2023-01-22 10:43:33.115641: step: 292/77, loss: 0.0005949947517365217
2023-01-22 10:43:34.563939: step: 296/77, loss: 0.003798791905865073
2023-01-22 10:43:36.038575: step: 300/77, loss: 1.837530180637259e-05
2023-01-22 10:43:37.530346: step: 304/77, loss: 9.359028808830772e-06
2023-01-22 10:43:38.936101: step: 308/77, loss: 0.03410165011882782
2023-01-22 10:43:40.395260: step: 312/77, loss: 0.005747949704527855
2023-01-22 10:43:41.819541: step: 316/77, loss: 0.0071901543997228146
2023-01-22 10:43:43.231232: step: 320/77, loss: 0.014834891073405743
2023-01-22 10:43:44.753605: step: 324/77, loss: 3.8532862163265236e-06
2023-01-22 10:43:46.190024: step: 328/77, loss: 0.0001279481512028724
2023-01-22 10:43:47.613397: step: 332/77, loss: 0.0006787201855331659
2023-01-22 10:43:49.089590: step: 336/77, loss: 0.00013982687960378826
2023-01-22 10:43:50.577316: step: 340/77, loss: 2.8490972908912227e-05
2023-01-22 10:43:52.058746: step: 344/77, loss: 0.014455622062087059
2023-01-22 10:43:53.593250: step: 348/77, loss: 0.13285669684410095
2023-01-22 10:43:55.021899: step: 352/77, loss: 0.00019437828450463712
2023-01-22 10:43:56.524627: step: 356/77, loss: 0.002372733550146222
2023-01-22 10:43:57.999105: step: 360/77, loss: 0.009212651289999485
2023-01-22 10:43:59.485515: step: 364/77, loss: 0.060634076595306396
2023-01-22 10:44:00.938078: step: 368/77, loss: 1.0017057320510503e-05
2023-01-22 10:44:02.422290: step: 372/77, loss: 0.0002461381664033979
2023-01-22 10:44:03.887337: step: 376/77, loss: 2.5817340429057367e-05
2023-01-22 10:44:05.385852: step: 380/77, loss: 0.0008293167338706553
2023-01-22 10:44:06.897802: step: 384/77, loss: 7.01223143551033e-06
2023-01-22 10:44:08.418895: step: 388/77, loss: 0.03312050551176071
==================================================
Loss: 0.009
--------------------
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': 0.9230769230769231, 'r': 0.4580152671755725, 'f1': 0.6122448979591837}, 'slot': {'p': 0.48484848484848486, 'r': 0.013805004314063849, 'f1': 0.02684563758389262}, 'combined': 0.016436104643199563, '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': 0.9206349206349206, 'r': 0.44274809160305345, 'f1': 0.5979381443298969}, 'slot': {'p': 0.5294117647058824, 'r': 0.015530629853321829, 'f1': 0.03017602682313495}, 'combined': 0.018043397481874505, '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': 0.9206349206349206, 'r': 0.44274809160305345, 'f1': 0.5979381443298969}, 'slot': {'p': 0.48484848484848486, 'r': 0.013805004314063849, 'f1': 0.02684563758389262}, 'combined': 0.01605203072026569, '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': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 10:45:46.035701: step: 4/77, loss: 0.005217066500335932
2023-01-22 10:45:47.521034: step: 8/77, loss: 1.7110400222009048e-05
2023-01-22 10:45:48.948442: step: 12/77, loss: 0.013908019289374352
2023-01-22 10:45:50.427459: step: 16/77, loss: 0.060203030705451965
2023-01-22 10:45:51.935794: step: 20/77, loss: 0.0001018143302644603
2023-01-22 10:45:53.427188: step: 24/77, loss: 0.00033130700467154384
2023-01-22 10:45:54.952034: step: 28/77, loss: 0.0022158983629196882
2023-01-22 10:45:56.469937: step: 32/77, loss: 0.001340493792667985
2023-01-22 10:45:57.906194: step: 36/77, loss: 9.457357373321429e-05
2023-01-22 10:45:59.383523: step: 40/77, loss: 0.007253519259393215
2023-01-22 10:46:00.849519: step: 44/77, loss: 0.01193111203610897
2023-01-22 10:46:02.372645: step: 48/77, loss: 1.947039709193632e-05
2023-01-22 10:46:03.801868: step: 52/77, loss: 0.010435977019369602
2023-01-22 10:46:05.238874: step: 56/77, loss: 0.00014408468268811703
2023-01-22 10:46:06.700451: step: 60/77, loss: 0.01907634176313877
2023-01-22 10:46:08.168128: step: 64/77, loss: 0.048381563276052475
2023-01-22 10:46:09.631522: step: 68/77, loss: 0.0009525776840746403
2023-01-22 10:46:11.105055: step: 72/77, loss: 0.040768206119537354
2023-01-22 10:46:12.605681: step: 76/77, loss: 0.0001661547867115587
2023-01-22 10:46:14.023985: step: 80/77, loss: 0.0006874087848700583
2023-01-22 10:46:15.520601: step: 84/77, loss: 2.096245952998288e-05
2023-01-22 10:46:16.996651: step: 88/77, loss: 0.007326844148337841
2023-01-22 10:46:18.447909: step: 92/77, loss: 0.024552563205361366
2023-01-22 10:46:19.919325: step: 96/77, loss: 0.0018240232020616531
2023-01-22 10:46:21.378666: step: 100/77, loss: 1.764373701007571e-05
2023-01-22 10:46:22.844928: step: 104/77, loss: 0.0007256006938405335
2023-01-22 10:46:24.306709: step: 108/77, loss: 0.0015230000717565417
2023-01-22 10:46:25.826887: step: 112/77, loss: 2.4019012926146388e-05
2023-01-22 10:46:27.242229: step: 116/77, loss: 3.794354779529385e-05
2023-01-22 10:46:28.717545: step: 120/77, loss: 0.0011226541828364134
2023-01-22 10:46:30.152797: step: 124/77, loss: 0.014624684117734432
2023-01-22 10:46:31.610332: step: 128/77, loss: 0.0008393382304348052
2023-01-22 10:46:33.055361: step: 132/77, loss: 3.3838718991319183e-06
2023-01-22 10:46:34.582570: step: 136/77, loss: 0.0315176360309124
2023-01-22 10:46:35.991403: step: 140/77, loss: 0.0003097353910561651
2023-01-22 10:46:37.404203: step: 144/77, loss: 3.469519651844166e-05
2023-01-22 10:46:38.838823: step: 148/77, loss: 8.082071144599468e-05
2023-01-22 10:46:40.309947: step: 152/77, loss: 0.001497301273047924
2023-01-22 10:46:41.793851: step: 156/77, loss: 3.961978109146003e-06
2023-01-22 10:46:43.296613: step: 160/77, loss: 0.004871972370892763
2023-01-22 10:46:44.748311: step: 164/77, loss: 0.0010909107513725758
2023-01-22 10:46:46.190170: step: 168/77, loss: 8.584916213294491e-05
2023-01-22 10:46:47.657676: step: 172/77, loss: 0.010070906020700932
2023-01-22 10:46:49.110798: step: 176/77, loss: 0.0017261668108403683
2023-01-22 10:46:50.622274: step: 180/77, loss: 0.0006850729114376009
2023-01-22 10:46:52.089231: step: 184/77, loss: 0.029952459037303925
2023-01-22 10:46:53.554849: step: 188/77, loss: 1.568080551805906e-05
2023-01-22 10:46:55.110074: step: 192/77, loss: 0.02392057701945305
2023-01-22 10:46:56.621176: step: 196/77, loss: 0.00026258424622938037
2023-01-22 10:46:58.089191: step: 200/77, loss: 0.018205387517809868
2023-01-22 10:46:59.562583: step: 204/77, loss: 3.9935000017976563e-07
2023-01-22 10:47:01.016711: step: 208/77, loss: 0.0023173026274889708
2023-01-22 10:47:02.509962: step: 212/77, loss: 0.017787277698516846
2023-01-22 10:47:03.947135: step: 216/77, loss: 4.1314960981253535e-06
2023-01-22 10:47:05.433769: step: 220/77, loss: 4.357820944278501e-05
2023-01-22 10:47:06.868569: step: 224/77, loss: 7.372977415798232e-05
2023-01-22 10:47:08.363146: step: 228/77, loss: 0.0021139492746442556
2023-01-22 10:47:09.778319: step: 232/77, loss: 0.00020499885431490839
2023-01-22 10:47:11.230431: step: 236/77, loss: 4.148268635617569e-05
2023-01-22 10:47:12.688310: step: 240/77, loss: 6.6961051743419375e-06
2023-01-22 10:47:14.192734: step: 244/77, loss: 0.11798547953367233
2023-01-22 10:47:15.606475: step: 248/77, loss: 0.0022454713471233845
2023-01-22 10:47:17.158456: step: 252/77, loss: 0.061752669513225555
2023-01-22 10:47:18.615345: step: 256/77, loss: 9.347809827886522e-05
2023-01-22 10:47:20.137645: step: 260/77, loss: 2.206732824561186e-05
2023-01-22 10:47:21.647235: step: 264/77, loss: 0.09364143759012222
2023-01-22 10:47:23.158667: step: 268/77, loss: 1.2169822184660006e-05
2023-01-22 10:47:24.647298: step: 272/77, loss: 6.98716685292311e-05
2023-01-22 10:47:26.151685: step: 276/77, loss: 8.472028639516793e-06
2023-01-22 10:47:27.635176: step: 280/77, loss: 0.028671029955148697
2023-01-22 10:47:29.021400: step: 284/77, loss: 4.439530675881542e-05
2023-01-22 10:47:30.514335: step: 288/77, loss: 3.467196165729547e-06
2023-01-22 10:47:31.976657: step: 292/77, loss: 0.027677757665514946
2023-01-22 10:47:33.438624: step: 296/77, loss: 0.07804442197084427
2023-01-22 10:47:34.901520: step: 300/77, loss: 0.04617539048194885
2023-01-22 10:47:36.396773: step: 304/77, loss: 8.539891132386401e-05
2023-01-22 10:47:37.839360: step: 308/77, loss: 4.726528914034134e-06
2023-01-22 10:47:39.331385: step: 312/77, loss: 0.0016289966879412532
2023-01-22 10:47:40.769533: step: 316/77, loss: 8.53421715873992e-06
2023-01-22 10:47:42.256643: step: 320/77, loss: 0.0001842157798819244
2023-01-22 10:47:43.692356: step: 324/77, loss: 0.013489406555891037
2023-01-22 10:47:45.146983: step: 328/77, loss: 0.0041824206709861755
2023-01-22 10:47:46.640311: step: 332/77, loss: 5.475835860124789e-05
2023-01-22 10:47:48.152521: step: 336/77, loss: 0.0028862636536359787
2023-01-22 10:47:49.663469: step: 340/77, loss: 0.015338265337049961
2023-01-22 10:47:51.184036: step: 344/77, loss: 4.800434908247553e-05
2023-01-22 10:47:52.654454: step: 348/77, loss: 0.003050778992474079
2023-01-22 10:47:54.133441: step: 352/77, loss: 0.00028969853883609176
2023-01-22 10:47:55.629571: step: 356/77, loss: 6.305790066107875e-06
2023-01-22 10:47:57.111041: step: 360/77, loss: 3.759312312467955e-05
2023-01-22 10:47:58.594796: step: 364/77, loss: 0.0016704229637980461
2023-01-22 10:48:00.069631: step: 368/77, loss: 7.791905227350071e-05
2023-01-22 10:48:01.542572: step: 372/77, loss: 0.0015094865811988711
2023-01-22 10:48:03.044665: step: 376/77, loss: 0.0017382418736815453
2023-01-22 10:48:04.515659: step: 380/77, loss: 5.582388894254109e-06
2023-01-22 10:48:05.951555: step: 384/77, loss: 4.877383980783634e-05
2023-01-22 10:48:07.394619: step: 388/77, loss: 5.6000149925239384e-05
==================================================
Loss: 0.010
--------------------
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': 0.9090909090909091, 'r': 0.4580152671755725, 'f1': 0.6091370558375634}, 'slot': {'p': 0.5161290322580645, 'r': 0.013805004314063849, 'f1': 0.02689075630252101}, 'combined': 0.01638015612336305, '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': 0.9090909090909091, 'r': 0.4580152671755725, 'f1': 0.6091370558375634}, 'slot': {'p': 0.5161290322580645, 'r': 0.013805004314063849, 'f1': 0.02689075630252101}, 'combined': 0.01638015612336305, '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': 0.9230769230769231, 'r': 0.4580152671755725, 'f1': 0.6122448979591837}, 'slot': {'p': 0.5333333333333333, 'r': 0.013805004314063849, 'f1': 0.026913372582001684}, 'combined': 0.016477575050205112, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 10:49:45.541060: step: 4/77, loss: 4.509889549808577e-05
2023-01-22 10:49:47.028959: step: 8/77, loss: 0.0002913977950811386
2023-01-22 10:49:48.476281: step: 12/77, loss: 0.01139332540333271
2023-01-22 10:49:49.934130: step: 16/77, loss: 0.004326066002249718
2023-01-22 10:49:51.415456: step: 20/77, loss: 2.7513986424310133e-05
2023-01-22 10:49:52.855595: step: 24/77, loss: 1.3975003639643546e-05
2023-01-22 10:49:54.297714: step: 28/77, loss: 0.007240791339427233
2023-01-22 10:49:55.736797: step: 32/77, loss: 0.00022055639419704676
2023-01-22 10:49:57.202863: step: 36/77, loss: 0.005759728141129017
2023-01-22 10:49:58.609404: step: 40/77, loss: 3.934923824999714e-06
2023-01-22 10:50:00.017902: step: 44/77, loss: 0.00020762631902471185
2023-01-22 10:50:01.529022: step: 48/77, loss: 0.017258862033486366
2023-01-22 10:50:03.062821: step: 52/77, loss: 0.01816752925515175
2023-01-22 10:50:04.515338: step: 56/77, loss: 7.464773807441816e-05
2023-01-22 10:50:05.949402: step: 60/77, loss: 6.470151856774464e-05
2023-01-22 10:50:07.467569: step: 64/77, loss: 0.03022352047264576
2023-01-22 10:50:09.018127: step: 68/77, loss: 0.030080357566475868
2023-01-22 10:50:10.464031: step: 72/77, loss: 0.0005232697003521025
2023-01-22 10:50:11.964661: step: 76/77, loss: 5.357146437745541e-05
2023-01-22 10:50:13.452707: step: 80/77, loss: 3.602316428441554e-05
2023-01-22 10:50:14.890073: step: 84/77, loss: 1.2637017789529637e-05
2023-01-22 10:50:16.384997: step: 88/77, loss: 0.0014475014759227633
2023-01-22 10:50:17.904243: step: 92/77, loss: 0.036904722452163696
2023-01-22 10:50:19.368423: step: 96/77, loss: 3.237287455704063e-05
2023-01-22 10:50:20.883874: step: 100/77, loss: 0.022598525509238243
2023-01-22 10:50:22.327529: step: 104/77, loss: 0.0006198819610290229
2023-01-22 10:50:23.832179: step: 108/77, loss: 0.037170566618442535
2023-01-22 10:50:25.313949: step: 112/77, loss: 2.7292508093523793e-05
2023-01-22 10:50:26.867147: step: 116/77, loss: 0.037723708897829056
2023-01-22 10:50:28.371742: step: 120/77, loss: 0.020332274958491325
2023-01-22 10:50:29.826203: step: 124/77, loss: 0.0104548754170537
2023-01-22 10:50:31.316564: step: 128/77, loss: 0.00011534785153344274
2023-01-22 10:50:32.784453: step: 132/77, loss: 0.018704598769545555
2023-01-22 10:50:34.204643: step: 136/77, loss: 5.230163424130296e-06
2023-01-22 10:50:35.689731: step: 140/77, loss: 0.005852022208273411
2023-01-22 10:50:37.198352: step: 144/77, loss: 0.0001379873719997704
2023-01-22 10:50:38.696198: step: 148/77, loss: 0.0046800170093774796
2023-01-22 10:50:40.133192: step: 152/77, loss: 0.0003418435517232865
2023-01-22 10:50:41.668592: step: 156/77, loss: 0.0001083689639926888
2023-01-22 10:50:43.154720: step: 160/77, loss: 0.00015809066826477647
2023-01-22 10:50:44.680833: step: 164/77, loss: 3.1797608244232833e-06
2023-01-22 10:50:46.129632: step: 168/77, loss: 5.667543882736936e-05
2023-01-22 10:50:47.640642: step: 172/77, loss: 3.554875002009794e-05
2023-01-22 10:50:49.124033: step: 176/77, loss: 0.0007138706278055906
2023-01-22 10:50:50.627847: step: 180/77, loss: 0.0003262606624048203
2023-01-22 10:50:52.185328: step: 184/77, loss: 0.01835954189300537
2023-01-22 10:50:53.629484: step: 188/77, loss: 5.6338943977607414e-05
2023-01-22 10:50:55.119659: step: 192/77, loss: 2.4946128178271465e-05
2023-01-22 10:50:56.641287: step: 196/77, loss: 8.789340063231066e-05
2023-01-22 10:50:58.106318: step: 200/77, loss: 5.236292054178193e-05
2023-01-22 10:50:59.539214: step: 204/77, loss: 0.001034987042658031
2023-01-22 10:51:01.120467: step: 208/77, loss: 1.9261453417129815e-05
2023-01-22 10:51:02.619974: step: 212/77, loss: 0.00017419336654711515
2023-01-22 10:51:04.150647: step: 216/77, loss: 0.027231387794017792
2023-01-22 10:51:05.583804: step: 220/77, loss: 0.003382456488907337
2023-01-22 10:51:07.001769: step: 224/77, loss: 0.00829127337783575
2023-01-22 10:51:08.447501: step: 228/77, loss: 0.016746779903769493
2023-01-22 10:51:09.886465: step: 232/77, loss: 0.0023354680743068457
2023-01-22 10:51:11.379341: step: 236/77, loss: 0.00019349480862729251
2023-01-22 10:51:12.835720: step: 240/77, loss: 5.5896136473165825e-05
2023-01-22 10:51:14.296286: step: 244/77, loss: 6.264793682930758e-06
2023-01-22 10:51:15.760290: step: 248/77, loss: 0.014695419929921627
2023-01-22 10:51:17.237997: step: 252/77, loss: 0.0002196079440182075
2023-01-22 10:51:18.641224: step: 256/77, loss: 0.00027947252965532243
2023-01-22 10:51:20.098273: step: 260/77, loss: 0.07945749908685684
2023-01-22 10:51:21.593445: step: 264/77, loss: 2.668962588359136e-05
2023-01-22 10:51:23.046350: step: 268/77, loss: 4.155714123044163e-06
2023-01-22 10:51:24.556253: step: 272/77, loss: 1.8812963389791548e-05
2023-01-22 10:51:26.111419: step: 276/77, loss: 0.00014113544602878392
2023-01-22 10:51:27.537163: step: 280/77, loss: 0.002064595464617014
2023-01-22 10:51:29.013373: step: 284/77, loss: 0.0031714034266769886
2023-01-22 10:51:30.504591: step: 288/77, loss: 2.7988609872409143e-05
2023-01-22 10:51:32.026582: step: 292/77, loss: 1.8803808416123502e-05
2023-01-22 10:51:33.511714: step: 296/77, loss: 0.0007328785723075271
2023-01-22 10:51:35.015364: step: 300/77, loss: 0.04188724607229233
2023-01-22 10:51:36.458758: step: 304/77, loss: 2.3720574517938076e-06
2023-01-22 10:51:37.955140: step: 308/77, loss: 0.00018719259242061526
2023-01-22 10:51:39.414541: step: 312/77, loss: 0.0003036497510038316
2023-01-22 10:51:40.894848: step: 316/77, loss: 3.775849108933471e-06
2023-01-22 10:51:42.312907: step: 320/77, loss: 0.00034413387766107917
2023-01-22 10:51:43.849009: step: 324/77, loss: 0.0007906183018349111
2023-01-22 10:51:45.317146: step: 328/77, loss: 2.5849119992926717e-05
2023-01-22 10:51:46.788342: step: 332/77, loss: 0.015596098266541958
2023-01-22 10:51:48.217962: step: 336/77, loss: 4.1424982555327006e-07
2023-01-22 10:51:49.709524: step: 340/77, loss: 4.976780473953113e-06
2023-01-22 10:51:51.218956: step: 344/77, loss: 0.0038793461862951517
2023-01-22 10:51:52.733992: step: 348/77, loss: 0.027320679277181625
2023-01-22 10:51:54.182817: step: 352/77, loss: 8.697208613739349e-06
2023-01-22 10:51:55.599592: step: 356/77, loss: 0.011141828261315823
2023-01-22 10:51:57.030460: step: 360/77, loss: 0.01932971365749836
2023-01-22 10:51:58.515125: step: 364/77, loss: 0.00039088045014068484
2023-01-22 10:51:59.992252: step: 368/77, loss: 1.4817132978350855e-05
2023-01-22 10:52:01.479802: step: 372/77, loss: 0.0013533779419958591
2023-01-22 10:52:02.984561: step: 376/77, loss: 0.000289235933450982
2023-01-22 10:52:04.485147: step: 380/77, loss: 6.28348789177835e-05
2023-01-22 10:52:05.981436: step: 384/77, loss: 0.011985783465206623
2023-01-22 10:52:07.529244: step: 388/77, loss: 9.261792001780123e-06
==================================================
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': 23}
Test Chinese: {'template': {'p': 0.8873239436619719, 'r': 0.48091603053435117, 'f1': 0.6237623762376238}, 'slot': {'p': 0.5, 'r': 0.014667817083692839, 'f1': 0.028499580888516347}, 'combined': 0.017776966296797325, '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': 0.9, 'r': 0.48091603053435117, 'f1': 0.6268656716417911}, 'slot': {'p': 0.5, 'r': 0.014667817083692839, 'f1': 0.028499580888516347}, 'combined': 0.017865408915189354, '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': 0.8873239436619719, 'r': 0.48091603053435117, 'f1': 0.6237623762376238}, 'slot': {'p': 0.45714285714285713, 'r': 0.013805004314063849, 'f1': 0.02680067001675042}, 'combined': 0.016717249614408677, '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': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 10:53:45.978829: step: 4/77, loss: 7.372148502327036e-06
2023-01-22 10:53:47.472245: step: 8/77, loss: 0.002566393930464983
2023-01-22 10:53:48.957498: step: 12/77, loss: 0.00975698884576559
2023-01-22 10:53:50.375647: step: 16/77, loss: 0.00012423066073097289
2023-01-22 10:53:51.861986: step: 20/77, loss: 7.469201955245808e-05
2023-01-22 10:53:53.321129: step: 24/77, loss: 1.7883849068311974e-05
2023-01-22 10:53:54.823411: step: 28/77, loss: 1.3897247299610171e-05
2023-01-22 10:53:56.280046: step: 32/77, loss: 0.000126511775306426
2023-01-22 10:53:57.759959: step: 36/77, loss: 0.00047933805035427213
2023-01-22 10:53:59.225747: step: 40/77, loss: 0.011026003398001194
2023-01-22 10:54:00.676774: step: 44/77, loss: 0.0017197122797369957
2023-01-22 10:54:02.188366: step: 48/77, loss: 0.011792484670877457
2023-01-22 10:54:03.714936: step: 52/77, loss: 0.02285902015864849
2023-01-22 10:54:05.223389: step: 56/77, loss: 0.0004306872433517128
2023-01-22 10:54:06.728509: step: 60/77, loss: 7.246661698445678e-05
2023-01-22 10:54:08.137028: step: 64/77, loss: 0.0010392410913482308
2023-01-22 10:54:09.637959: step: 68/77, loss: 1.759197584760841e-05
2023-01-22 10:54:11.180834: step: 72/77, loss: 0.00021055589604657143
2023-01-22 10:54:12.696986: step: 76/77, loss: 0.0056786141358315945
2023-01-22 10:54:14.252854: step: 80/77, loss: 2.048878059213166e-06
2023-01-22 10:54:15.644374: step: 84/77, loss: 0.00010283981100656092
2023-01-22 10:54:17.221940: step: 88/77, loss: 6.372314237523824e-05
2023-01-22 10:54:18.712716: step: 92/77, loss: 7.664812437724322e-05
2023-01-22 10:54:20.222564: step: 96/77, loss: 0.001548820873722434
2023-01-22 10:54:21.758978: step: 100/77, loss: 0.0007104914984665811
2023-01-22 10:54:23.261941: step: 104/77, loss: 0.0004165653372183442
2023-01-22 10:54:24.755480: step: 108/77, loss: 0.014097335748374462
2023-01-22 10:54:26.246147: step: 112/77, loss: 0.022480204701423645
2023-01-22 10:54:27.771441: step: 116/77, loss: 0.00048142069135792553
2023-01-22 10:54:29.263006: step: 120/77, loss: 0.002312499564141035
2023-01-22 10:54:30.704163: step: 124/77, loss: 7.586013816762716e-05
2023-01-22 10:54:32.278525: step: 128/77, loss: 1.1175856684531027e-07
2023-01-22 10:54:33.781940: step: 132/77, loss: 0.00231208186596632
2023-01-22 10:54:35.222550: step: 136/77, loss: 0.000274372985586524
2023-01-22 10:54:36.723859: step: 140/77, loss: 6.377603085638839e-07
2023-01-22 10:54:38.188085: step: 144/77, loss: 0.009999795816838741
2023-01-22 10:54:39.728848: step: 148/77, loss: 2.1054979697510134e-06
2023-01-22 10:54:41.229198: step: 152/77, loss: 0.014564106240868568
2023-01-22 10:54:42.741157: step: 156/77, loss: 0.008510801941156387
2023-01-22 10:54:44.216061: step: 160/77, loss: 0.0003925769997294992
2023-01-22 10:54:45.722506: step: 164/77, loss: 0.15949967503547668
2023-01-22 10:54:47.166104: step: 168/77, loss: 0.002451444510370493
2023-01-22 10:54:48.646593: step: 172/77, loss: 2.3691179649176775e-06
2023-01-22 10:54:50.060442: step: 176/77, loss: 1.0802951919686166e-06
2023-01-22 10:54:51.555227: step: 180/77, loss: 3.7903109841863625e-06
2023-01-22 10:54:53.012432: step: 184/77, loss: 0.03973957896232605
2023-01-22 10:54:54.413510: step: 188/77, loss: 4.1733612306416035e-05
2023-01-22 10:54:55.913148: step: 192/77, loss: 0.04006608948111534
2023-01-22 10:54:57.370670: step: 196/77, loss: 7.700354763073847e-05
2023-01-22 10:54:58.844390: step: 200/77, loss: 9.149542165687308e-05
2023-01-22 10:55:00.308386: step: 204/77, loss: 2.995125214511063e-07
2023-01-22 10:55:01.772532: step: 208/77, loss: 0.011563536711037159
2023-01-22 10:55:03.269413: step: 212/77, loss: 0.0006145972874946892
2023-01-22 10:55:04.815723: step: 216/77, loss: 0.001980900764465332
2023-01-22 10:55:06.318053: step: 220/77, loss: 4.839376560994424e-05
2023-01-22 10:55:07.695791: step: 224/77, loss: 8.927112503442913e-05
2023-01-22 10:55:09.174045: step: 228/77, loss: 7.5996690611646045e-06
2023-01-22 10:55:10.641697: step: 232/77, loss: 1.1799502317444421e-05
2023-01-22 10:55:12.153398: step: 236/77, loss: 0.00021003717847634107
2023-01-22 10:55:13.662539: step: 240/77, loss: 8.29909276944818e-06
2023-01-22 10:55:15.144786: step: 244/77, loss: 1.0683887694540317e-06
2023-01-22 10:55:16.608715: step: 248/77, loss: 0.0002714066649787128
2023-01-22 10:55:18.112268: step: 252/77, loss: 0.015390491113066673
2023-01-22 10:55:19.595485: step: 256/77, loss: 0.027384832501411438
2023-01-22 10:55:21.120096: step: 260/77, loss: 0.02881324291229248
2023-01-22 10:55:22.631092: step: 264/77, loss: 0.00021542828471865505
2023-01-22 10:55:24.049929: step: 268/77, loss: 3.8738376133551355e-06
2023-01-22 10:55:25.539881: step: 272/77, loss: 0.005717065185308456
2023-01-22 10:55:27.040505: step: 276/77, loss: 0.0003914251283276826
2023-01-22 10:55:28.575233: step: 280/77, loss: 0.0007405400392599404
2023-01-22 10:55:30.070789: step: 284/77, loss: 2.542083166190423e-06
2023-01-22 10:55:31.476821: step: 288/77, loss: 1.5962510587996803e-05
2023-01-22 10:55:33.005914: step: 292/77, loss: 5.124079962115502e-06
2023-01-22 10:55:34.529145: step: 296/77, loss: 0.00012356540537439287
2023-01-22 10:55:36.010986: step: 300/77, loss: 0.000246676238020882
2023-01-22 10:55:37.489810: step: 304/77, loss: 0.00015589930990245193
2023-01-22 10:55:38.959947: step: 308/77, loss: 0.0006130424444563687
2023-01-22 10:55:40.466609: step: 312/77, loss: 6.260881491471082e-05
2023-01-22 10:55:41.910317: step: 316/77, loss: 0.0031988155096769333
2023-01-22 10:55:43.436855: step: 320/77, loss: 0.004418224096298218
2023-01-22 10:55:44.870999: step: 324/77, loss: 0.0009965308709070086
2023-01-22 10:55:46.345632: step: 328/77, loss: 7.539941293543961e-07
2023-01-22 10:55:47.800917: step: 332/77, loss: 0.003678370965644717
2023-01-22 10:55:49.274605: step: 336/77, loss: 0.0003343412245158106
2023-01-22 10:55:50.716902: step: 340/77, loss: 0.00017664878396317363
2023-01-22 10:55:52.252531: step: 344/77, loss: 0.04077373445034027
2023-01-22 10:55:53.696154: step: 348/77, loss: 3.8742859942431096e-07
2023-01-22 10:55:55.200112: step: 352/77, loss: 0.001119026681408286
2023-01-22 10:55:56.662061: step: 356/77, loss: 0.04550314322113991
2023-01-22 10:55:58.160807: step: 360/77, loss: 1.2471847412598436e-06
2023-01-22 10:55:59.641002: step: 364/77, loss: 1.2867828445450868e-05
2023-01-22 10:56:01.137948: step: 368/77, loss: 0.008402790874242783
2023-01-22 10:56:02.608289: step: 372/77, loss: 0.0688982605934143
2023-01-22 10:56:04.074924: step: 376/77, loss: 0.011048972606658936
2023-01-22 10:56:05.521351: step: 380/77, loss: 0.00045871181646361947
2023-01-22 10:56:06.923182: step: 384/77, loss: 0.0016792448004707694
2023-01-22 10:56:08.383912: step: 388/77, loss: 0.00023599954147357494
==================================================
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': 24}
Test Chinese: {'template': {'p': 0.88, 'r': 0.5038167938931297, 'f1': 0.640776699029126}, 'slot': {'p': 0.47058823529411764, 'r': 0.013805004314063849, 'f1': 0.02682313495389774}, 'combined': 0.017187639873371362, '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': 0.8783783783783784, 'r': 0.4961832061068702, 'f1': 0.6341463414634146}, 'slot': {'p': 0.4857142857142857, 'r': 0.014667817083692839, 'f1': 0.02847571189279732}, 'combined': 0.018057768517383666, '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': 0.8888888888888888, 'r': 0.48854961832061067, 'f1': 0.6305418719211823}, 'slot': {'p': 0.4857142857142857, 'r': 0.014667817083692839, 'f1': 0.02847571189279732}, 'combined': 0.017955128681172695, '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': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 10:57:46.570060: step: 4/77, loss: 4.059045750182122e-05
2023-01-22 10:57:48.090887: step: 8/77, loss: 0.030835065990686417
2023-01-22 10:57:49.526094: step: 12/77, loss: 5.7991685025626794e-05
2023-01-22 10:57:50.971092: step: 16/77, loss: 4.914428427582607e-05
2023-01-22 10:57:52.498213: step: 20/77, loss: 3.874687899951823e-05
2023-01-22 10:57:53.954757: step: 24/77, loss: 2.7834380489366595e-06
2023-01-22 10:57:55.413970: step: 28/77, loss: 6.2171811805455945e-06
2023-01-22 10:57:56.926305: step: 32/77, loss: 1.473645966143522e-06
2023-01-22 10:57:58.380432: step: 36/77, loss: 6.257622590055689e-05
2023-01-22 10:57:59.838114: step: 40/77, loss: 0.0005334470770321786
2023-01-22 10:58:01.326503: step: 44/77, loss: 0.04825974255800247
2023-01-22 10:58:02.842092: step: 48/77, loss: 6.16902980254963e-07
2023-01-22 10:58:04.254427: step: 52/77, loss: 2.3803200747352093e-05
2023-01-22 10:58:05.758212: step: 56/77, loss: 1.7761865365173435e-06
2023-01-22 10:58:07.303382: step: 60/77, loss: 0.002082192339003086
2023-01-22 10:58:08.756601: step: 64/77, loss: 2.617944664962124e-05
2023-01-22 10:58:10.241173: step: 68/77, loss: 0.021399078890681267
2023-01-22 10:58:11.711068: step: 72/77, loss: 0.036595191806554794
2023-01-22 10:58:13.223274: step: 76/77, loss: 4.119883669773117e-05
2023-01-22 10:58:14.794260: step: 80/77, loss: 0.0001858456089394167
2023-01-22 10:58:16.299821: step: 84/77, loss: 2.6728503144113347e-05
2023-01-22 10:58:17.709405: step: 88/77, loss: 3.4449337817932246e-06
2023-01-22 10:58:19.165312: step: 92/77, loss: 0.00030246900860220194
2023-01-22 10:58:20.708151: step: 96/77, loss: 0.0003325316938571632
2023-01-22 10:58:22.207646: step: 100/77, loss: 9.07470052879944e-07
2023-01-22 10:58:23.674648: step: 104/77, loss: 0.00027373951161280274
2023-01-22 10:58:25.153754: step: 108/77, loss: 3.2495640880370047e-06
2023-01-22 10:58:26.642092: step: 112/77, loss: 0.0010588520672172308
2023-01-22 10:58:28.084817: step: 116/77, loss: 0.02988281659781933
2023-01-22 10:58:29.561115: step: 120/77, loss: 3.7877066461078357e-06
2023-01-22 10:58:30.990646: step: 124/77, loss: 1.281479626413784e-06
2023-01-22 10:58:32.501715: step: 128/77, loss: 0.0009377918904647231
2023-01-22 10:58:34.034873: step: 132/77, loss: 0.00032386762904934585
2023-01-22 10:58:35.512860: step: 136/77, loss: 0.0004764663754031062
2023-01-22 10:58:37.027004: step: 140/77, loss: 0.0033441728446632624
2023-01-22 10:58:38.473164: step: 144/77, loss: 0.008817191235721111
2023-01-22 10:58:40.017813: step: 148/77, loss: 0.0001582540717208758
2023-01-22 10:58:41.508879: step: 152/77, loss: 1.4754637049918529e-05
2023-01-22 10:58:42.958158: step: 156/77, loss: 1.8953408016386675e-06
2023-01-22 10:58:44.430175: step: 160/77, loss: 0.007105558179318905
2023-01-22 10:58:45.899373: step: 164/77, loss: 0.00016064877854660153
2023-01-22 10:58:47.406334: step: 168/77, loss: 0.006513113155961037
2023-01-22 10:58:48.875466: step: 172/77, loss: 0.004730660002678633
2023-01-22 10:58:50.326869: step: 176/77, loss: 0.012969336472451687
2023-01-22 10:58:51.808414: step: 180/77, loss: 2.9611353966174647e-05
2023-01-22 10:58:53.273792: step: 184/77, loss: 3.134362486889586e-05
2023-01-22 10:58:54.718070: step: 188/77, loss: 4.576904757414013e-06
2023-01-22 10:58:56.186714: step: 192/77, loss: 7.770049705868587e-06
2023-01-22 10:58:57.674269: step: 196/77, loss: 0.002541177673265338
2023-01-22 10:58:59.152488: step: 200/77, loss: 0.0008257463341578841
2023-01-22 10:59:00.580364: step: 204/77, loss: 3.1156530440057395e-06
2023-01-22 10:59:02.066928: step: 208/77, loss: 2.0965369913028553e-05
2023-01-22 10:59:03.564792: step: 212/77, loss: 6.824683964623546e-07
2023-01-22 10:59:05.047572: step: 216/77, loss: 0.01078418642282486
2023-01-22 10:59:06.525750: step: 220/77, loss: 0.0002531272766645998
2023-01-22 10:59:07.898559: step: 224/77, loss: 0.0014299320755526423
2023-01-22 10:59:09.333810: step: 228/77, loss: 0.0007252601790241897
2023-01-22 10:59:10.749425: step: 232/77, loss: 4.472882665140787e-06
2023-01-22 10:59:12.286986: step: 236/77, loss: 0.004823240917176008
2023-01-22 10:59:13.825232: step: 240/77, loss: 0.01945425011217594
2023-01-22 10:59:15.330087: step: 244/77, loss: 0.0003206911205779761
2023-01-22 10:59:16.815161: step: 248/77, loss: 3.069389322263305e-06
2023-01-22 10:59:18.260064: step: 252/77, loss: 0.0044409167021512985
2023-01-22 10:59:19.719256: step: 256/77, loss: 0.0038761033210903406
2023-01-22 10:59:21.155603: step: 260/77, loss: 1.8266971892444417e-05
2023-01-22 10:59:22.660416: step: 264/77, loss: 0.0022358319256454706
2023-01-22 10:59:24.119173: step: 268/77, loss: 3.647561607067473e-05
2023-01-22 10:59:25.628300: step: 272/77, loss: 2.4451919671264477e-06
2023-01-22 10:59:27.105466: step: 276/77, loss: 6.576570740435272e-05
2023-01-22 10:59:28.622779: step: 280/77, loss: 0.0027494183741509914
2023-01-22 10:59:30.068400: step: 284/77, loss: 1.141419488703832e-06
2023-01-22 10:59:31.618617: step: 288/77, loss: 0.0010258633410558105
2023-01-22 10:59:33.059241: step: 292/77, loss: 1.6540182912194723e-07
2023-01-22 10:59:34.599113: step: 296/77, loss: 0.0002123012236552313
2023-01-22 10:59:35.999569: step: 300/77, loss: 3.2169398309633834e-06
2023-01-22 10:59:37.543764: step: 304/77, loss: 0.0015341609250754118
2023-01-22 10:59:39.093366: step: 308/77, loss: 2.290213160449639e-06
2023-01-22 10:59:40.544720: step: 312/77, loss: 2.740030140557792e-06
2023-01-22 10:59:42.002432: step: 316/77, loss: 5.185409827390686e-05
2023-01-22 10:59:43.558213: step: 320/77, loss: 4.31674015999306e-06
2023-01-22 10:59:45.059821: step: 324/77, loss: 2.0086281438125297e-06
2023-01-22 10:59:46.518847: step: 328/77, loss: 2.9443667699524667e-06
2023-01-22 10:59:47.990907: step: 332/77, loss: 1.6882592035472044e-06
2023-01-22 10:59:49.447026: step: 336/77, loss: 3.605149686336517e-05
2023-01-22 10:59:50.855848: step: 340/77, loss: 3.4285606034245575e-06
2023-01-22 10:59:52.251584: step: 344/77, loss: 0.04269392788410187
2023-01-22 10:59:53.692887: step: 348/77, loss: 6.202944405231392e-06
2023-01-22 10:59:55.235406: step: 352/77, loss: 5.522930223378353e-06
2023-01-22 10:59:56.704994: step: 356/77, loss: 3.839743385469774e-06
2023-01-22 10:59:58.175773: step: 360/77, loss: 6.6556758611113764e-06
2023-01-22 10:59:59.607867: step: 364/77, loss: 1.2227968909428455e-05
2023-01-22 11:00:01.030001: step: 368/77, loss: 1.5571474705211585e-06
2023-01-22 11:00:02.560362: step: 372/77, loss: 1.3326905900612473e-05
2023-01-22 11:00:04.083941: step: 376/77, loss: 1.5645682651665993e-06
2023-01-22 11:00:05.509771: step: 380/77, loss: 0.00039393804036080837
2023-01-22 11:00:07.002689: step: 384/77, loss: 6.189832492964342e-05
2023-01-22 11:00:08.532662: step: 388/77, loss: 0.0002459617971908301
==================================================
Loss: 0.003
--------------------
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': 25}
Test Chinese: {'template': {'p': 0.9166666666666666, 'r': 0.5038167938931297, 'f1': 0.6502463054187191}, 'slot': {'p': 0.5151515151515151, 'r': 0.014667817083692839, 'f1': 0.02852348993288591}, 'combined': 0.01854729394650709, 'epoch': 25}
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': 25}
Test Korean: {'template': {'p': 0.9142857142857143, 'r': 0.48854961832061067, 'f1': 0.6368159203980099}, 'slot': {'p': 0.53125, 'r': 0.014667817083692839, 'f1': 0.028547439126784216}, 'combined': 0.01817946372252925, 'epoch': 25}
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': 25}
Test Russian: {'template': {'p': 0.9285714285714286, 'r': 0.4961832061068702, 'f1': 0.6467661691542288}, 'slot': {'p': 0.5483870967741935, 'r': 0.014667817083692839, 'f1': 0.02857142857142857}, 'combined': 0.018479033404406535, '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': 0.25, 'f1': 0.4}, 'slot': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 11:01:46.677181: step: 4/77, loss: 0.0004410330147948116
2023-01-22 11:01:48.145984: step: 8/77, loss: 6.347841008391697e-07
2023-01-22 11:01:49.631438: step: 12/77, loss: 0.00019786340999417007
2023-01-22 11:01:51.082864: step: 16/77, loss: 1.8058998421111028e-06
2023-01-22 11:01:52.580552: step: 20/77, loss: 1.4379454569279915e-06
2023-01-22 11:01:54.078920: step: 24/77, loss: 0.001322779105976224
2023-01-22 11:01:55.510210: step: 28/77, loss: 8.72594173415564e-05
2023-01-22 11:01:57.008350: step: 32/77, loss: 9.983496966015082e-06
2023-01-22 11:01:58.464643: step: 36/77, loss: 7.26973712517065e-06
2023-01-22 11:01:59.959202: step: 40/77, loss: 4.976939749212761e-07
2023-01-22 11:02:01.450386: step: 44/77, loss: 0.007929427549242973
2023-01-22 11:02:03.020875: step: 48/77, loss: 8.099547812889796e-06
2023-01-22 11:02:04.490036: step: 52/77, loss: 0.0005367292324081063
2023-01-22 11:02:06.036636: step: 56/77, loss: 5.662437985165525e-08
2023-01-22 11:02:07.421473: step: 60/77, loss: 1.0163690603803843e-05
2023-01-22 11:02:08.828532: step: 64/77, loss: 3.014777939824853e-05
2023-01-22 11:02:10.316750: step: 68/77, loss: 0.004237155895680189
2023-01-22 11:02:11.746134: step: 72/77, loss: 1.9191624232917093e-05
2023-01-22 11:02:13.197514: step: 76/77, loss: 0.00026323023485019803
2023-01-22 11:02:14.637918: step: 80/77, loss: 2.7281901111564366e-06
2023-01-22 11:02:16.168794: step: 84/77, loss: 6.288236136242631e-07
2023-01-22 11:02:17.660015: step: 88/77, loss: 0.022111790254712105
2023-01-22 11:02:19.165438: step: 92/77, loss: 1.6018191672628745e-05
2023-01-22 11:02:20.662649: step: 96/77, loss: 2.7297407996229595e-06
2023-01-22 11:02:22.117009: step: 100/77, loss: 3.272101366746938e-06
2023-01-22 11:02:23.677244: step: 104/77, loss: 0.0006118750898167491
2023-01-22 11:02:25.203104: step: 108/77, loss: 0.09048576653003693
2023-01-22 11:02:26.656223: step: 112/77, loss: 7.00344287452026e-07
2023-01-22 11:02:28.076750: step: 116/77, loss: 2.5460256438236684e-05
2023-01-22 11:02:29.535403: step: 120/77, loss: 0.0005740249762311578
2023-01-22 11:02:31.067047: step: 124/77, loss: 1.1066706065321341e-05
2023-01-22 11:02:32.525041: step: 128/77, loss: 0.00012074044934706762
2023-01-22 11:02:33.951275: step: 132/77, loss: 0.0003262482932768762
2023-01-22 11:02:35.372527: step: 136/77, loss: 0.0011029550805687904
2023-01-22 11:02:36.859725: step: 140/77, loss: 3.281430326751433e-05
2023-01-22 11:02:38.372759: step: 144/77, loss: 0.015173608437180519
2023-01-22 11:02:39.870462: step: 148/77, loss: 0.011440704576671124
2023-01-22 11:02:41.410887: step: 152/77, loss: 0.00012958000297658145
2023-01-22 11:02:42.903377: step: 156/77, loss: 0.016136083751916885
2023-01-22 11:02:44.449917: step: 160/77, loss: 9.393112850375473e-05
2023-01-22 11:02:45.915136: step: 164/77, loss: 0.002286059781908989
2023-01-22 11:02:47.392289: step: 168/77, loss: 0.009524857625365257
2023-01-22 11:02:48.866102: step: 172/77, loss: 0.027265436947345734
2023-01-22 11:02:50.329382: step: 176/77, loss: 5.697094456991181e-05
2023-01-22 11:02:51.862411: step: 180/77, loss: 0.0001194120486616157
2023-01-22 11:02:53.313662: step: 184/77, loss: 0.0003231299633625895
2023-01-22 11:02:54.785808: step: 188/77, loss: 4.0711223846301436e-05
2023-01-22 11:02:56.286643: step: 192/77, loss: 0.0005879050586372614
2023-01-22 11:02:57.755723: step: 196/77, loss: 0.056800760328769684
2023-01-22 11:02:59.233695: step: 200/77, loss: 4.6171685426088516e-06
2023-01-22 11:03:00.804968: step: 204/77, loss: 1.0742302038124762e-05
2023-01-22 11:03:02.328615: step: 208/77, loss: 0.06644407659769058
2023-01-22 11:03:03.787419: step: 212/77, loss: 0.0002735485613811761
2023-01-22 11:03:05.263184: step: 216/77, loss: 3.1349229629995534e-06
2023-01-22 11:03:06.789750: step: 220/77, loss: 8.984311534732115e-06
2023-01-22 11:03:08.149525: step: 224/77, loss: 0.0023781578056514263
2023-01-22 11:03:09.693246: step: 228/77, loss: 0.02856743521988392
2023-01-22 11:03:11.168833: step: 232/77, loss: 0.03514505922794342
2023-01-22 11:03:12.640897: step: 236/77, loss: 9.761759429238737e-06
2023-01-22 11:03:14.114379: step: 240/77, loss: 7.212029231595807e-07
2023-01-22 11:03:15.640936: step: 244/77, loss: 4.139644079259597e-05
2023-01-22 11:03:17.145795: step: 248/77, loss: 2.2276112758845557e-06
2023-01-22 11:03:18.671310: step: 252/77, loss: 1.6014524589991197e-05
2023-01-22 11:03:20.126057: step: 256/77, loss: 1.4529955478792544e-05
2023-01-22 11:03:21.640328: step: 260/77, loss: 0.001574151567183435
2023-01-22 11:03:23.155256: step: 264/77, loss: 0.003839747281745076
2023-01-22 11:03:24.604504: step: 268/77, loss: 0.0009322985424660146
2023-01-22 11:03:26.032360: step: 272/77, loss: 0.0005584964528679848
2023-01-22 11:03:27.524948: step: 276/77, loss: 0.00011649419320747256
2023-01-22 11:03:28.994267: step: 280/77, loss: 0.0008474696660414338
2023-01-22 11:03:30.504697: step: 284/77, loss: 0.1427866369485855
2023-01-22 11:03:31.997850: step: 288/77, loss: 9.221310028806329e-05
2023-01-22 11:03:33.480796: step: 292/77, loss: 5.444014459499158e-05
2023-01-22 11:03:34.969653: step: 296/77, loss: 3.405211100471206e-05
2023-01-22 11:03:36.498033: step: 300/77, loss: 0.007121166680008173
2023-01-22 11:03:37.938951: step: 304/77, loss: 0.028989192098379135
2023-01-22 11:03:39.433868: step: 308/77, loss: 0.005328961182385683
2023-01-22 11:03:40.860426: step: 312/77, loss: 0.04974348098039627
2023-01-22 11:03:42.339034: step: 316/77, loss: 0.006064072251319885
2023-01-22 11:03:43.800574: step: 320/77, loss: 4.2640358515200205e-06
2023-01-22 11:03:45.237915: step: 324/77, loss: 2.233498526038602e-05
2023-01-22 11:03:46.764986: step: 328/77, loss: 2.7715998385247076e-07
2023-01-22 11:03:48.235299: step: 332/77, loss: 2.317662801942788e-05
2023-01-22 11:03:49.669478: step: 336/77, loss: 0.06426730006933212
2023-01-22 11:03:51.189407: step: 340/77, loss: 0.00011196612467756495
2023-01-22 11:03:52.710864: step: 344/77, loss: 8.359479579667095e-07
2023-01-22 11:03:54.152186: step: 348/77, loss: 4.4287400669418275e-05
2023-01-22 11:03:55.599371: step: 352/77, loss: 0.05372339114546776
2023-01-22 11:03:57.112486: step: 356/77, loss: 6.985371783230221e-06
2023-01-22 11:03:58.634035: step: 360/77, loss: 0.00024018401745706797
2023-01-22 11:04:00.120279: step: 364/77, loss: 7.439233013428748e-05
2023-01-22 11:04:01.631726: step: 368/77, loss: 0.0001586980652064085
2023-01-22 11:04:03.170180: step: 372/77, loss: 0.00013080626376904547
2023-01-22 11:04:04.648001: step: 376/77, loss: 7.703786764068354e-07
2023-01-22 11:04:06.081168: step: 380/77, loss: 1.3012524505029432e-05
2023-01-22 11:04:07.502365: step: 384/77, loss: 0.008434685878455639
2023-01-22 11:04:08.976088: step: 388/77, loss: 2.2103627998149022e-05
==================================================
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': 26}
Test Chinese: {'template': {'p': 0.9178082191780822, 'r': 0.5114503816793893, 'f1': 0.6568627450980392}, 'slot': {'p': 0.425, 'r': 0.014667817083692839, 'f1': 0.02835696413678065}, 'combined': 0.018626633305532388, 'epoch': 26}
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': 26}
Test Korean: {'template': {'p': 0.9166666666666666, 'r': 0.5038167938931297, 'f1': 0.6502463054187191}, 'slot': {'p': 0.4473684210526316, 'r': 0.014667817083692839, 'f1': 0.028404344193817876}, 'combined': 0.018469819869871718, 'epoch': 26}
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': 26}
Test Russian: {'template': {'p': 0.9295774647887324, 'r': 0.5038167938931297, 'f1': 0.6534653465346535}, 'slot': {'p': 0.4722222222222222, 'r': 0.014667817083692839, 'f1': 0.028451882845188285}, 'combined': 0.018592319482994325, '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': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 11:05:47.132975: step: 4/77, loss: 1.4326322343549691e-05
2023-01-22 11:05:48.643637: step: 8/77, loss: 0.024663139134645462
2023-01-22 11:05:50.157280: step: 12/77, loss: 0.0004897532053291798
2023-01-22 11:05:51.640498: step: 16/77, loss: 0.0061692120507359505
2023-01-22 11:05:53.079244: step: 20/77, loss: 0.00023279106244444847
2023-01-22 11:05:54.506925: step: 24/77, loss: 6.758703966625035e-05
2023-01-22 11:05:55.963069: step: 28/77, loss: 6.1161990743130445e-06
2023-01-22 11:05:57.391749: step: 32/77, loss: 2.1376172298914753e-05
2023-01-22 11:05:58.832038: step: 36/77, loss: 9.568851965013891e-05
2023-01-22 11:06:00.274771: step: 40/77, loss: 3.833698883681791e-06
2023-01-22 11:06:01.875248: step: 44/77, loss: 0.00012776638322975487
2023-01-22 11:06:03.364579: step: 48/77, loss: 0.0004679126723203808
2023-01-22 11:06:04.815490: step: 52/77, loss: 1.3973161003377754e-05
2023-01-22 11:06:06.291397: step: 56/77, loss: 1.3835771824233234e-05
2023-01-22 11:06:07.787434: step: 60/77, loss: 1.6599069567746483e-06
2023-01-22 11:06:09.276779: step: 64/77, loss: 7.525195542257279e-05
2023-01-22 11:06:10.757539: step: 68/77, loss: 5.3652707720175385e-05
2023-01-22 11:06:12.191890: step: 72/77, loss: 0.000490330159664154
2023-01-22 11:06:13.656879: step: 76/77, loss: 6.186037353472784e-05
2023-01-22 11:06:15.091901: step: 80/77, loss: 9.387572390551213e-07
2023-01-22 11:06:16.503896: step: 84/77, loss: 0.00446065329015255
2023-01-22 11:06:17.974167: step: 88/77, loss: 3.517463119351305e-05
2023-01-22 11:06:19.457682: step: 92/77, loss: 0.0010564837139099836
2023-01-22 11:06:20.893273: step: 96/77, loss: 0.0038536631036549807
2023-01-22 11:06:22.327685: step: 100/77, loss: 0.000469402177259326
2023-01-22 11:06:23.832444: step: 104/77, loss: 8.486769365845248e-05
2023-01-22 11:06:25.299695: step: 108/77, loss: 3.024913439730881e-07
2023-01-22 11:06:26.808913: step: 112/77, loss: 2.229935307695996e-05
2023-01-22 11:06:28.300361: step: 116/77, loss: 8.681615872774273e-05
2023-01-22 11:06:29.732622: step: 120/77, loss: 0.00025649185408838093
2023-01-22 11:06:31.169787: step: 124/77, loss: 1.7866010466605076e-06
2023-01-22 11:06:32.666118: step: 128/77, loss: 1.3009529538976494e-05
2023-01-22 11:06:34.143079: step: 132/77, loss: 2.220266424046713e-07
2023-01-22 11:06:35.609571: step: 136/77, loss: 5.0626226766326e-06
2023-01-22 11:06:37.090213: step: 140/77, loss: 3.058028596569784e-05
2023-01-22 11:06:38.584825: step: 144/77, loss: 2.7159321689396165e-05
2023-01-22 11:06:40.108455: step: 148/77, loss: 1.4751408343727235e-06
2023-01-22 11:06:41.572277: step: 152/77, loss: 3.5762763417324095e-08
2023-01-22 11:06:43.066647: step: 156/77, loss: 3.208236739737913e-05
2023-01-22 11:06:44.563711: step: 160/77, loss: 0.0027070590294897556
2023-01-22 11:06:46.037812: step: 164/77, loss: 0.0012007926125079393
2023-01-22 11:06:47.468276: step: 168/77, loss: 7.897610032614466e-08
2023-01-22 11:06:48.969944: step: 172/77, loss: 0.0011402148520573974
2023-01-22 11:06:50.510109: step: 176/77, loss: 1.2129133892813115e-06
2023-01-22 11:06:52.024949: step: 180/77, loss: 6.869350386295991e-07
2023-01-22 11:06:53.482169: step: 184/77, loss: 0.0020278082229197025
2023-01-22 11:06:54.982780: step: 188/77, loss: 2.4167438823496923e-06
2023-01-22 11:06:56.523939: step: 192/77, loss: 0.0004763460601679981
2023-01-22 11:06:58.011770: step: 196/77, loss: 0.00020171045616734773
2023-01-22 11:06:59.513548: step: 200/77, loss: 0.006428330205380917
2023-01-22 11:07:00.959848: step: 204/77, loss: 0.054347168654203415
2023-01-22 11:07:02.437001: step: 208/77, loss: 9.391622006660327e-05
2023-01-22 11:07:03.955286: step: 212/77, loss: 5.589288048213348e-05
2023-01-22 11:07:05.386797: step: 216/77, loss: 1.017721160678775e-06
2023-01-22 11:07:06.816334: step: 220/77, loss: 5.111033942739596e-07
2023-01-22 11:07:08.238202: step: 224/77, loss: 1.4677115132144536e-06
2023-01-22 11:07:09.710302: step: 228/77, loss: 0.040604718029499054
2023-01-22 11:07:11.150943: step: 232/77, loss: 0.00016247703752014786
2023-01-22 11:07:12.632609: step: 236/77, loss: 6.460230360971764e-05
2023-01-22 11:07:14.121462: step: 240/77, loss: 0.00135130959097296
2023-01-22 11:07:15.537983: step: 244/77, loss: 0.00023467946448363364
2023-01-22 11:07:17.072517: step: 248/77, loss: 7.356399873970076e-05
2023-01-22 11:07:18.598994: step: 252/77, loss: 0.006442447658628225
2023-01-22 11:07:20.103184: step: 256/77, loss: 0.01619216613471508
2023-01-22 11:07:21.565089: step: 260/77, loss: 1.4328755241876934e-05
2023-01-22 11:07:23.028298: step: 264/77, loss: 2.5376413759659044e-05
2023-01-22 11:07:24.448717: step: 268/77, loss: 0.12852409482002258
2023-01-22 11:07:25.988972: step: 272/77, loss: 1.3841839063388761e-05
2023-01-22 11:07:27.484245: step: 276/77, loss: 0.00680402759462595
2023-01-22 11:07:28.930546: step: 280/77, loss: 0.00011101227573817596
2023-01-22 11:07:30.429370: step: 284/77, loss: 0.00027165425126440823
2023-01-22 11:07:31.961531: step: 288/77, loss: 0.00021375974756665528
2023-01-22 11:07:33.541686: step: 292/77, loss: 0.027166698127985
2023-01-22 11:07:35.012537: step: 296/77, loss: 0.000678533164318651
2023-01-22 11:07:36.565432: step: 300/77, loss: 8.930165677156765e-06
2023-01-22 11:07:38.121655: step: 304/77, loss: 0.0004659105616156012
2023-01-22 11:07:39.560711: step: 308/77, loss: 2.5572109734639525e-05
2023-01-22 11:07:41.033963: step: 312/77, loss: 0.0006945566856302321
2023-01-22 11:07:42.525520: step: 316/77, loss: 0.0002417838986730203
2023-01-22 11:07:43.990533: step: 320/77, loss: 5.098254405311309e-05
2023-01-22 11:07:45.483059: step: 324/77, loss: 5.953685104032047e-05
2023-01-22 11:07:46.951132: step: 328/77, loss: 0.013821378350257874
2023-01-22 11:07:48.377939: step: 332/77, loss: 0.0018615383887663484
2023-01-22 11:07:49.906019: step: 336/77, loss: 1.4126595488050953e-05
2023-01-22 11:07:51.358002: step: 340/77, loss: 2.8266451863601105e-06
2023-01-22 11:07:52.889991: step: 344/77, loss: 1.291919033974409e-06
2023-01-22 11:07:54.338444: step: 348/77, loss: 3.385403397260234e-05
2023-01-22 11:07:55.816460: step: 352/77, loss: 4.066002929903334e-06
2023-01-22 11:07:57.276249: step: 356/77, loss: 1.440505002392456e-05
2023-01-22 11:07:58.750510: step: 360/77, loss: 8.49277203087695e-05
2023-01-22 11:08:00.202931: step: 364/77, loss: 4.555952273221919e-06
2023-01-22 11:08:01.716318: step: 368/77, loss: 2.5610373995732516e-05
2023-01-22 11:08:03.172489: step: 372/77, loss: 0.028466036543250084
2023-01-22 11:08:04.638534: step: 376/77, loss: 2.1152529370738193e-05
2023-01-22 11:08:06.127253: step: 380/77, loss: 9.026997759065125e-06
2023-01-22 11:08:07.569717: step: 384/77, loss: 1.4021417200638098e-06
2023-01-22 11:08:08.992306: step: 388/77, loss: 0.00033527766936458647
==================================================
Loss: 0.004
--------------------
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': 0.9154929577464789, 'r': 0.4961832061068702, 'f1': 0.6435643564356436}, 'slot': {'p': 0.5, 'r': 0.014667817083692839, 'f1': 0.028499580888516347}, 'combined': 0.018341314433203592, 'epoch': 27}
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': 27}
Test Korean: {'template': {'p': 0.9154929577464789, 'r': 0.4961832061068702, 'f1': 0.6435643564356436}, 'slot': {'p': 0.5151515151515151, 'r': 0.014667817083692839, 'f1': 0.02852348993288591}, 'combined': 0.01835670144195628, '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': 0.9285714285714286, 'r': 0.4961832061068702, 'f1': 0.6467661691542288}, 'slot': {'p': 0.5483870967741935, 'r': 0.014667817083692839, 'f1': 0.02857142857142857}, 'combined': 0.018479033404406535, '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': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 11:09:47.101671: step: 4/77, loss: 6.341078551486135e-05
2023-01-22 11:09:48.660225: step: 8/77, loss: 1.2370970580377616e-05
2023-01-22 11:09:50.113248: step: 12/77, loss: 0.0004744845209643245
2023-01-22 11:09:51.606957: step: 16/77, loss: 6.40781627225806e-06
2023-01-22 11:09:53.136636: step: 20/77, loss: 6.124305400589947e-07
2023-01-22 11:09:54.578120: step: 24/77, loss: 7.749309588689357e-06
2023-01-22 11:09:55.995301: step: 28/77, loss: 1.6838266958529857e-07
2023-01-22 11:09:57.493190: step: 32/77, loss: 0.0009012370137497783
2023-01-22 11:09:59.033004: step: 36/77, loss: 0.00016497840988449752
2023-01-22 11:10:00.462959: step: 40/77, loss: 0.031463008373975754
2023-01-22 11:10:01.962739: step: 44/77, loss: 0.00010549923172220588
2023-01-22 11:10:03.385736: step: 48/77, loss: 0.00022325686586555094
2023-01-22 11:10:04.897581: step: 52/77, loss: 2.074153599096462e-06
2023-01-22 11:10:06.405488: step: 56/77, loss: 9.855855751084164e-05
2023-01-22 11:10:07.841913: step: 60/77, loss: 1.778966179699637e-05
2023-01-22 11:10:09.333572: step: 64/77, loss: 4.362392246548552e-06
2023-01-22 11:10:10.823965: step: 68/77, loss: 1.3663729987456463e-06
2023-01-22 11:10:12.288185: step: 72/77, loss: 0.004756465088576078
2023-01-22 11:10:13.735657: step: 76/77, loss: 4.683442966779694e-05
2023-01-22 11:10:15.222662: step: 80/77, loss: 0.00019577420607674867
2023-01-22 11:10:16.704680: step: 84/77, loss: 0.00035057426430284977
2023-01-22 11:10:18.168785: step: 88/77, loss: 0.0017822480294853449
2023-01-22 11:10:19.664632: step: 92/77, loss: 0.000780368922278285
2023-01-22 11:10:21.195955: step: 96/77, loss: 6.379641126841307e-05
2023-01-22 11:10:22.628747: step: 100/77, loss: 2.9951229407743085e-07
2023-01-22 11:10:24.083698: step: 104/77, loss: 7.06719310983317e-06
2023-01-22 11:10:25.624580: step: 108/77, loss: 1.3345738807402086e-05
2023-01-22 11:10:27.063687: step: 112/77, loss: 0.04274173080921173
2023-01-22 11:10:28.530282: step: 116/77, loss: 9.51277106651105e-05
2023-01-22 11:10:29.988578: step: 120/77, loss: 2.816310029629676e-07
2023-01-22 11:10:31.402837: step: 124/77, loss: 0.028377747163176537
2023-01-22 11:10:32.893047: step: 128/77, loss: 7.620793894602684e-06
2023-01-22 11:10:34.386003: step: 132/77, loss: 7.897602927187108e-08
2023-01-22 11:10:35.864009: step: 136/77, loss: 8.433857874479145e-05
2023-01-22 11:10:37.403463: step: 140/77, loss: 0.042357299476861954
2023-01-22 11:10:38.834772: step: 144/77, loss: 2.6225916371913627e-07
2023-01-22 11:10:40.267685: step: 148/77, loss: 1.937150173603186e-08
2023-01-22 11:10:41.734707: step: 152/77, loss: 0.00019146957492921501
2023-01-22 11:10:43.210738: step: 156/77, loss: 4.1731591409188695e-06
2023-01-22 11:10:44.714557: step: 160/77, loss: 1.1456423635536339e-05
2023-01-22 11:10:46.178714: step: 164/77, loss: 4.647242349165026e-06
2023-01-22 11:10:47.686427: step: 168/77, loss: 1.8775331511733384e-07
2023-01-22 11:10:49.145357: step: 172/77, loss: 0.000803797913249582
2023-01-22 11:10:50.636297: step: 176/77, loss: 0.00011625502520473674
2023-01-22 11:10:52.098547: step: 180/77, loss: 0.02850656770169735
2023-01-22 11:10:53.552489: step: 184/77, loss: 0.023709582164883614
2023-01-22 11:10:55.070211: step: 188/77, loss: 0.001574437483213842
2023-01-22 11:10:56.563676: step: 192/77, loss: 4.412966518430039e-06
2023-01-22 11:10:58.048951: step: 196/77, loss: 0.028234709054231644
2023-01-22 11:10:59.544376: step: 200/77, loss: 5.9604619906394873e-08
2023-01-22 11:11:01.012282: step: 204/77, loss: 0.007427121512591839
2023-01-22 11:11:02.439726: step: 208/77, loss: 1.28149778788611e-07
2023-01-22 11:11:03.916455: step: 212/77, loss: 1.8853193978429772e-05
2023-01-22 11:11:05.329332: step: 216/77, loss: 0.00016453364514745772
2023-01-22 11:11:06.771735: step: 220/77, loss: 0.04771774262189865
2023-01-22 11:11:08.294458: step: 224/77, loss: 0.00020399382628966123
2023-01-22 11:11:09.700602: step: 228/77, loss: 4.151056145929033e-06
2023-01-22 11:11:11.178472: step: 232/77, loss: 0.0006100233877077699
2023-01-22 11:11:12.708107: step: 236/77, loss: 0.0030997106805443764
2023-01-22 11:11:14.139059: step: 240/77, loss: 0.0016627665609121323
2023-01-22 11:11:15.691407: step: 244/77, loss: 1.3559860008172109e-06
2023-01-22 11:11:17.228881: step: 248/77, loss: 0.00033372087636962533
2023-01-22 11:11:18.709326: step: 252/77, loss: 2.2440113752963953e-05
2023-01-22 11:11:20.176387: step: 256/77, loss: 1.2248431175976293e-06
2023-01-22 11:11:21.618512: step: 260/77, loss: 3.861261939164251e-05
2023-01-22 11:11:23.157527: step: 264/77, loss: 7.700593414483592e-05
2023-01-22 11:11:24.662730: step: 268/77, loss: 6.907177157700062e-05
2023-01-22 11:11:26.156161: step: 272/77, loss: 0.0003736157377716154
2023-01-22 11:11:27.627356: step: 276/77, loss: 0.03906060755252838
2023-01-22 11:11:29.149042: step: 280/77, loss: 1.0371045391366351e-06
2023-01-22 11:11:30.672506: step: 284/77, loss: 2.6862755476031452e-05
2023-01-22 11:11:32.177548: step: 288/77, loss: 0.00017517435480840504
2023-01-22 11:11:33.613859: step: 292/77, loss: 3.055980641875067e-06
2023-01-22 11:11:35.193627: step: 296/77, loss: 0.0014680877793580294
2023-01-22 11:11:36.688007: step: 300/77, loss: 3.172190918121487e-05
2023-01-22 11:11:38.140744: step: 304/77, loss: 8.607449854025617e-05
2023-01-22 11:11:39.594553: step: 308/77, loss: 0.01271668728441
2023-01-22 11:11:41.119431: step: 312/77, loss: 4.753455016270891e-07
2023-01-22 11:11:42.537634: step: 316/77, loss: 1.7221045709447935e-05
2023-01-22 11:11:43.990422: step: 320/77, loss: 0.0009752624318934977
2023-01-22 11:11:45.454359: step: 324/77, loss: 1.535144474473782e-05
2023-01-22 11:11:46.960308: step: 328/77, loss: 6.94218761054799e-05
2023-01-22 11:11:48.439940: step: 332/77, loss: 0.00026013870956376195
2023-01-22 11:11:49.980853: step: 336/77, loss: 0.00010290901263942942
2023-01-22 11:11:51.428162: step: 340/77, loss: 1.2418715414241888e-05
2023-01-22 11:11:52.941660: step: 344/77, loss: 3.4568495266285026e-06
2023-01-22 11:11:54.351451: step: 348/77, loss: 0.0007589494343847036
2023-01-22 11:11:55.785368: step: 352/77, loss: 4.990630259271711e-05
2023-01-22 11:11:57.337862: step: 356/77, loss: 1.3291570439832867e-06
2023-01-22 11:11:58.777204: step: 360/77, loss: 4.246799960583303e-07
2023-01-22 11:12:00.270042: step: 364/77, loss: 7.510137152166863e-07
2023-01-22 11:12:01.712111: step: 368/77, loss: 0.010786645114421844
2023-01-22 11:12:03.262018: step: 372/77, loss: 1.5899097434157738e-06
2023-01-22 11:12:04.751561: step: 376/77, loss: 7.986807872839563e-07
2023-01-22 11:12:06.291668: step: 380/77, loss: 8.875988896761555e-06
2023-01-22 11:12:07.806124: step: 384/77, loss: 1.1134283340652473e-05
2023-01-22 11:12:09.294735: step: 388/77, loss: 2.2824442567070946e-05
==================================================
Loss: 0.004
--------------------
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': 28}
Test Chinese: {'template': {'p': 0.8947368421052632, 'r': 0.5190839694656488, 'f1': 0.6570048309178743}, 'slot': {'p': 0.40540540540540543, 'r': 0.012942191544434857, 'f1': 0.02508361204013378}, 'combined': 0.01648005428723765, 'epoch': 28}
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': 28}
Test Korean: {'template': {'p': 0.8947368421052632, 'r': 0.5190839694656488, 'f1': 0.6570048309178743}, 'slot': {'p': 0.4166666666666667, 'r': 0.012942191544434857, 'f1': 0.02510460251046025}, 'combined': 0.01649384512764538, 'epoch': 28}
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': 28}
Test Russian: {'template': {'p': 0.9178082191780822, 'r': 0.5114503816793893, 'f1': 0.6568627450980392}, 'slot': {'p': 0.4411764705882353, 'r': 0.012942191544434857, 'f1': 0.025146689019279123}, 'combined': 0.016517923179330405, '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': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}
******************************
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 11:13:47.463719: step: 4/77, loss: 3.6937315144314198e-06
2023-01-22 11:13:49.038194: step: 8/77, loss: 4.1574102738195506e-07
2023-01-22 11:13:50.536261: step: 12/77, loss: 0.0003356757224537432
2023-01-22 11:13:52.028710: step: 16/77, loss: 0.06527945399284363
2023-01-22 11:13:53.579394: step: 20/77, loss: 0.0002221096510766074
2023-01-22 11:13:55.037589: step: 24/77, loss: 0.00017310661496594548
2023-01-22 11:13:56.496983: step: 28/77, loss: 4.425617419201444e-07
2023-01-22 11:13:57.958635: step: 32/77, loss: 8.567985787522048e-06
2023-01-22 11:13:59.448875: step: 36/77, loss: 1.175110628537368e-05
2023-01-22 11:14:00.975583: step: 40/77, loss: 6.787302118027583e-05
2023-01-22 11:14:02.463440: step: 44/77, loss: 0.0003931297978851944
2023-01-22 11:14:03.953644: step: 48/77, loss: 0.0005336487083695829
2023-01-22 11:14:05.395692: step: 52/77, loss: 0.004889761097729206
2023-01-22 11:14:06.886063: step: 56/77, loss: 1.2963991480319237e-07
2023-01-22 11:14:08.308948: step: 60/77, loss: 0.006010737735778093
2023-01-22 11:14:09.795087: step: 64/77, loss: 0.002367202192544937
2023-01-22 11:14:11.222966: step: 68/77, loss: 0.005203723441809416
2023-01-22 11:14:12.653065: step: 72/77, loss: 0.0011668759398162365
2023-01-22 11:14:14.095621: step: 76/77, loss: 4.994434675609227e-06
2023-01-22 11:14:15.541459: step: 80/77, loss: 0.0210029948502779
2023-01-22 11:14:17.019964: step: 84/77, loss: 4.144196645938791e-05
2023-01-22 11:14:18.557471: step: 88/77, loss: 0.003072816878557205
2023-01-22 11:14:20.048821: step: 92/77, loss: 8.771360444370657e-05
2023-01-22 11:14:21.505615: step: 96/77, loss: 2.2703750801156275e-05
2023-01-22 11:14:22.927685: step: 100/77, loss: 0.0005149574135430157
2023-01-22 11:14:24.319302: step: 104/77, loss: 6.4182363530562725e-06
2023-01-22 11:14:25.765997: step: 108/77, loss: 2.364353531447705e-05
2023-01-22 11:14:27.209328: step: 112/77, loss: 1.475209217005613e-07
2023-01-22 11:14:28.701001: step: 116/77, loss: 1.2321707799856085e-05
2023-01-22 11:14:30.260272: step: 120/77, loss: 0.0019780858419835567
2023-01-22 11:14:31.761061: step: 124/77, loss: 2.781839384624618e-06
2023-01-22 11:14:33.295915: step: 128/77, loss: 0.002130064181983471
2023-01-22 11:14:34.779730: step: 132/77, loss: 5.453763947116386e-07
2023-01-22 11:14:36.270702: step: 136/77, loss: 0.00013564022083301097
2023-01-22 11:14:37.770359: step: 140/77, loss: 7.915633432276081e-06
2023-01-22 11:14:39.204980: step: 144/77, loss: 8.597708074375987e-07
2023-01-22 11:14:40.729496: step: 148/77, loss: 0.0005095271626487374
2023-01-22 11:14:42.171886: step: 152/77, loss: 5.636212790705031e-06
2023-01-22 11:14:43.679889: step: 156/77, loss: 6.559267785632983e-05
2023-01-22 11:14:45.132499: step: 160/77, loss: 2.820798908942379e-05
2023-01-22 11:14:46.643169: step: 164/77, loss: 1.3960838259663433e-05
2023-01-22 11:14:48.110186: step: 168/77, loss: 1.0728827959383125e-07
2023-01-22 11:14:49.546612: step: 172/77, loss: 1.5794829550941358e-06
2023-01-22 11:14:51.084098: step: 176/77, loss: 0.14907880127429962
2023-01-22 11:14:52.594890: step: 180/77, loss: 2.362069790251553e-05
2023-01-22 11:14:54.054611: step: 184/77, loss: 3.7997801882738713e-07
2023-01-22 11:14:55.506647: step: 188/77, loss: 0.0001900776260299608
2023-01-22 11:14:57.033286: step: 192/77, loss: 5.02228613186162e-06
2023-01-22 11:14:58.527483: step: 196/77, loss: 4.827723842026899e-06
2023-01-22 11:15:00.067379: step: 200/77, loss: 4.217001219330996e-07
2023-01-22 11:15:01.523925: step: 204/77, loss: 0.0013312987284734845
2023-01-22 11:15:03.033501: step: 208/77, loss: 8.674228411109652e-06
2023-01-22 11:15:04.514852: step: 212/77, loss: 2.571580080257263e-05
2023-01-22 11:15:05.976966: step: 216/77, loss: 8.191204688046128e-05
2023-01-22 11:15:07.481984: step: 220/77, loss: 2.35874153986515e-06
2023-01-22 11:15:08.921155: step: 224/77, loss: 0.0007027069223113358
2023-01-22 11:15:10.343528: step: 228/77, loss: 5.2166076784487814e-05
2023-01-22 11:15:11.807084: step: 232/77, loss: 0.00013188117009121925
2023-01-22 11:15:13.255526: step: 236/77, loss: 1.0763304089778103e-05
2023-01-22 11:15:14.772144: step: 240/77, loss: 6.738617230439559e-06
2023-01-22 11:15:16.214153: step: 244/77, loss: 6.242575182113796e-05
2023-01-22 11:15:17.733514: step: 248/77, loss: 7.897473324192106e-07
2023-01-22 11:15:19.174710: step: 252/77, loss: 0.0017958583775907755
2023-01-22 11:15:20.642507: step: 256/77, loss: 6.188504357851343e-06
2023-01-22 11:15:22.139107: step: 260/77, loss: 0.0002860073291230947
2023-01-22 11:15:23.604921: step: 264/77, loss: 1.5450248611159623e-05
2023-01-22 11:15:25.064237: step: 268/77, loss: 2.9504178655770374e-07
2023-01-22 11:15:26.533869: step: 272/77, loss: 4.7683684556432127e-08
2023-01-22 11:15:27.945367: step: 276/77, loss: 2.3002725356491283e-05
2023-01-22 11:15:29.413995: step: 280/77, loss: 0.0012365533038973808
2023-01-22 11:15:30.890866: step: 284/77, loss: 3.7278171021171147e-06
2023-01-22 11:15:32.362132: step: 288/77, loss: 4.2184408812318e-05
2023-01-22 11:15:33.796735: step: 292/77, loss: 0.011463784612715244
2023-01-22 11:15:35.256568: step: 296/77, loss: 0.02129548415541649
2023-01-22 11:15:36.684507: step: 300/77, loss: 0.02072848007082939
2023-01-22 11:15:38.147155: step: 304/77, loss: 0.03113666921854019
2023-01-22 11:15:39.560217: step: 308/77, loss: 8.225305236919667e-07
2023-01-22 11:15:41.080937: step: 312/77, loss: 3.0233147754188394e-06
2023-01-22 11:15:42.558970: step: 316/77, loss: 5.078814865555614e-06
2023-01-22 11:15:44.017272: step: 320/77, loss: 3.300204525658046e-06
2023-01-22 11:15:45.430785: step: 324/77, loss: 1.2367942758828576e-07
2023-01-22 11:15:46.902058: step: 328/77, loss: 6.798368758609286e-06
2023-01-22 11:15:48.425318: step: 332/77, loss: 2.697095453640941e-07
2023-01-22 11:15:49.928173: step: 336/77, loss: 0.07185610383749008
2023-01-22 11:15:51.505269: step: 340/77, loss: 0.011198935098946095
2023-01-22 11:15:53.010921: step: 344/77, loss: 0.0010905108647421002
2023-01-22 11:15:54.463570: step: 348/77, loss: 3.576277407546513e-08
2023-01-22 11:15:55.902903: step: 352/77, loss: 0.000372204085579142
2023-01-22 11:15:57.352419: step: 356/77, loss: 0.0019713786896318197
2023-01-22 11:15:58.794653: step: 360/77, loss: 0.00993399415165186
2023-01-22 11:16:00.263391: step: 364/77, loss: 0.00010721880971686915
2023-01-22 11:16:01.702834: step: 368/77, loss: 0.00018293378525413573
2023-01-22 11:16:03.158735: step: 372/77, loss: 3.2212028600042686e-05
2023-01-22 11:16:04.631405: step: 376/77, loss: 0.018035752698779106
2023-01-22 11:16:06.176947: step: 380/77, loss: 1.722459273878485e-06
2023-01-22 11:16:07.681280: step: 384/77, loss: 6.50309902994195e-06
2023-01-22 11:16:09.195028: step: 388/77, loss: 3.4866245641751448e-06
==================================================
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': 29}
Test Chinese: {'template': {'p': 0.8933333333333333, 'r': 0.5114503816793893, 'f1': 0.6504854368932039}, 'slot': {'p': 0.4, 'r': 0.012079378774805867, 'f1': 0.023450586264656615}, 'combined': 0.015254264851766926, 'epoch': 29}
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': 29}
Test Korean: {'template': {'p': 0.9054054054054054, 'r': 0.5114503816793893, 'f1': 0.6536585365853658}, 'slot': {'p': 0.42424242424242425, 'r': 0.012079378774805867, 'f1': 0.02348993288590604}, 'combined': 0.0153543951546898, 'epoch': 29}
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': 29}
Test Russian: {'template': {'p': 0.8947368421052632, 'r': 0.5190839694656488, 'f1': 0.6570048309178743}, 'slot': {'p': 0.3888888888888889, 'r': 0.012079378774805867, 'f1': 0.02343096234309623}, 'combined': 0.01539425545246902, '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': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5, 'r': 0.034482758620689655, 'f1': 0.06451612903225806}, 'combined': 0.04301075268817204, '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': 3}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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': 3}
--------------------
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': 3}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37777777777777777, 'r': 0.014667817083692839, 'f1': 0.028239202657807307}, 'combined': 0.01735677821894498, 'epoch': 3}
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}
--------------------
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': 3}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.38636363636363635, 'r': 0.014667817083692839, 'f1': 0.02826267664172901}, 'combined': 0.01745635910224439, 'epoch': 3}
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': 3}