metadata
license: bigscience-openrail-m
base_model: ehsanaghaei/SecureBERT
tags:
- generated_from_trainer
- cybersecurity
metrics:
- accuracy
model-index:
- name: vuln-cat-secbert
results: []
widget:
- text: A NULL pointer dereference flaw was found in KubeVirt.
vuln-cat-secbert
This model is a fine-tuned version of ehsanaghaei/SecureBERT on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6754
- Accuracy: 0.8977
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 110 | 0.5211 | 0.8886 |
| No log | 2.0 | 220 | 0.5437 | 0.8932 |
| No log | 3.0 | 330 | 0.5760 | 0.8909 |
| No log | 4.0 | 440 | 0.6122 | 0.8955 |
| 0.103 | 5.0 | 550 | 0.6467 | 0.8932 |
| 0.103 | 6.0 | 660 | 0.6633 | 0.8977 |
| 0.103 | 7.0 | 770 | 0.6719 | 0.8977 |
| 0.103 | 8.0 | 880 | 0.6754 | 0.8977 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2