metadata
license: apache-2.0
base_model: neuralsentry/distilbert-git-commits-mlm
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: vulnfixClassification-DistilBERT-DCMB
results: []
vulnfixClassification-DistilBERT-DCMB
This model is a fine-tuned version of neuralsentry/distilbert-git-commits-mlm on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1769
- Accuracy: 0.9713
- Precision: 0.9778
- Recall: 0.9667
- F1: 0.9722
- Roc Auc: 0.9715
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: 256
- eval_batch_size: 256
- seed: 420
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Roc Auc |
|---|---|---|---|---|---|---|---|---|
| 0.2594 | 1.0 | 110 | 0.1452 | 0.9520 | 0.9672 | 0.9395 | 0.9532 | 0.9525 |
| 0.0966 | 2.0 | 220 | 0.1103 | 0.9644 | 0.9714 | 0.9599 | 0.9656 | 0.9646 |
| 0.0499 | 3.0 | 330 | 0.1193 | 0.9640 | 0.9679 | 0.9626 | 0.9653 | 0.9641 |
| 0.0251 | 4.0 | 440 | 0.1289 | 0.9623 | 0.9577 | 0.9703 | 0.9640 | 0.9619 |
| 0.0132 | 5.0 | 550 | 0.1495 | 0.9660 | 0.9660 | 0.9687 | 0.9673 | 0.9659 |
| 0.0086 | 6.0 | 660 | 0.1759 | 0.9684 | 0.9830 | 0.9558 | 0.9692 | 0.9689 |
| 0.0054 | 7.0 | 770 | 0.1568 | 0.9700 | 0.9788 | 0.9632 | 0.9709 | 0.9703 |
| 0.0023 | 8.0 | 880 | 0.1775 | 0.9707 | 0.9754 | 0.9681 | 0.9717 | 0.9708 |
| 0.0023 | 9.0 | 990 | 0.1752 | 0.9710 | 0.9794 | 0.9646 | 0.9719 | 0.9713 |
| 0.0011 | 10.0 | 1100 | 0.1769 | 0.9713 | 0.9778 | 0.9667 | 0.9722 | 0.9715 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.2
- Tokenizers 0.13.3