khanhtran0111/codebert-java-vul4j-ft

1---2library_name: transformers3license: apache-2.04base_model: mangsense/codebert_java5tags:6- generated_from_trainer7metrics:8- accuracy9- f110model-index:11- name: codebert-java-vul4j-ft12  results: []13---14 15<!-- This model card has been generated automatically according to the information the Trainer had access to. You16should probably proofread and complete it, then remove this comment. -->17 18# codebert-java-vul4j-ft19 20This model is a fine-tuned version of [mangsense/codebert_java](https://huggingface.co/mangsense/codebert_java) on an unknown dataset.21It achieves the following results on the evaluation set:22- Loss: 0.554723- Accuracy: 0.714324- F1: 0.428625 26## Model description27 28More information needed29 30## Intended uses & limitations31 32More information needed33 34## Training and evaluation data35 36More information needed37 38## Training procedure39 40### Training hyperparameters41 42The following hyperparameters were used during training:43- learning_rate: 2e-0544- train_batch_size: 1645- eval_batch_size: 3246- seed: 4247- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments48- lr_scheduler_type: linear49- num_epochs: 550- mixed_precision_training: Native AMP51 52### Training results53 54| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |55|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|56| No log        | 1.0   | 66   | 0.4762          | 0.6988   | 0.3243 |57| No log        | 2.0   | 132  | 0.3536          | 0.8313   | 0.125  |58| No log        | 3.0   | 198  | 0.4353          | 0.8434   | 0.0    |59 60 61### Framework versions62 63- Transformers 4.57.164- Pytorch 2.8.0+cu12665- Datasets 4.4.266- Tokenizers 0.22.167