metadata

base_model: neuralsentry/starencoder-git-commits-mlm
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: starencoder-vulnfix-classification
    results: []

starencoder-vulnfix-classification

This model is a fine-tuned version of neuralsentry/starencoder-git-commits-mlm on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1191
Accuracy: 0.9703
Precision: 0.9769
Recall: 0.96
F1: 0.9684
Roc Auc: 0.9698

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: 0.0001
train_batch_size: 128
eval_batch_size: 128
seed: 420
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Roc Auc
0.3716	0.33	66	0.2018	0.9296	0.9368	0.9133	0.9249	0.9288
0.1745	0.67	132	0.1468	0.9533	0.9711	0.9293	0.9498	0.9522
0.1346	1.0	198	0.1091	0.9657	0.9761	0.951	0.9634	0.9650
0.0917	1.33	264	0.1294	0.9647	0.9790	0.946	0.9622	0.9638
0.0877	1.67	330	0.1090	0.9668	0.9619	0.9683	0.9651	0.9669
0.0731	2.0	396	0.1042	0.9688	0.9746	0.9593	0.9669	0.9684
0.0342	2.33	462	0.1291	0.9692	0.9686	0.9663	0.9675	0.9690
0.0375	2.67	528	0.1202	0.9706	0.9753	0.9623	0.9688	0.9702
0.0342	3.0	594	0.1191	0.9703	0.9769	0.96	0.9684	0.9698

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu118
Datasets 2.14.0
Tokenizers 0.13.3