---
library_name: peft
base_model: Vulnerability-Detection/codet5_merged
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: results_v3
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# results_v3

This model is a fine-tuned version of [Vulnerability-Detection/codet5_merged](https://huggingface.co/Vulnerability-Detection/codet5_merged) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5477
- Accuracy: 0.7452
- Precision: 0.1235
- Recall: 0.7658
- F1 Score: 0.2128
- F2 Score: 0.3754
- Gmean: 0.7549

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score | F2 Score | Gmean  |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:--------:|:------:|
| 0.4724        | 1.0   | 197  | 0.5542          | 0.7347   | 0.1212    | 0.7838 | 0.2099   | 0.3744   | 0.7577 |
| 0.4822        | 2.0   | 394  | 0.5152          | 0.7566   | 0.1265    | 0.7477 | 0.2164   | 0.3773   | 0.7524 |
| 0.4859        | 3.0   | 591  | 0.5477          | 0.7452   | 0.1235    | 0.7658 | 0.2128   | 0.3754   | 0.7549 |


### Framework versions

- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0