Modelpublic

RayenLLM/Vulnerability_Detection_Using_CodeBERT

sourceHugging Faceupdated 1y agoView on Hugging Face

1likes48downloads

Model Card

VulnerabilityDetectionUsing_CodeBERT

This model is a fine-tuned version of microsoft/codebert-base on the None dataset. It achieves the following results on the evaluation set:

—Loss: 0.0740
—Accuracy: 1.0
—Auc: 1.0
—Precision: 1.0

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: 0.0002
—trainbatchsize: 8
—evalbatchsize: 8
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Auc	Precision
0.2971	1.0	26	0.1815	0.925	1.0	0.81
0.2407	2.0	52	0.1349	0.981	1.0	0.944
0.2619	3.0	78	0.1668	0.887	1.0	0.739
0.2207	4.0	104	0.1081	1.0	1.0	1.0
0.1543	5.0	130	0.1037	0.981	1.0	1.0
0.1428	6.0	156	0.0974	0.981	1.0	0.944
0.1598	7.0	182	0.0916	0.981	1.0	1.0
0.1324	8.0	208	0.1024	0.981	1.0	0.944
0.1445	9.0	234	0.0726	1.0	1.0	1.0
0.1287	10.0	260	0.0740	1.0	1.0	1.0

Framework versions

—Transformers 4.50.0
—Pytorch 2.6.0+cu124
—Datasets 3.5.0
—Tokenizers 0.21.1