metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: distilbert-git-commits-bugfix-classification
results: []
distilbert-git-commits-bugfix-classification
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: 0.5037
- Accuracy: 0.9231
- Precision: 0.85
- Recall: 1.0
- F1: 0.9189
- Roc Auc: 0.9318
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|---|---|---|---|
| 0.6837 | 1.0 | 22 | 0.6040 | 0.5897 | 0.5161 | 0.9412 | 0.6667 | 0.6297 |
| 0.3852 | 2.0 | 44 | 0.2881 | 0.9231 | 0.85 | 1.0 | 0.9189 | 0.9318 |
| 0.2148 | 3.0 | 66 | 0.3807 | 0.9231 | 0.85 | 1.0 | 0.9189 | 0.9318 |
| 0.0701 | 4.0 | 88 | 0.4934 | 0.8718 | 0.7727 | 1.0 | 0.8718 | 0.8864 |
| 0.0164 | 5.0 | 110 | 0.4892 | 0.8974 | 0.8095 | 1.0 | 0.8947 | 0.9091 |
| 0.0039 | 6.0 | 132 | 0.4929 | 0.8974 | 0.8095 | 1.0 | 0.8947 | 0.9091 |
| 0.0012 | 7.0 | 154 | 0.4065 | 0.9231 | 0.85 | 1.0 | 0.9189 | 0.9318 |
| 0.0008 | 8.0 | 176 | 0.4837 | 0.9231 | 0.85 | 1.0 | 0.9189 | 0.9318 |
| 0.0007 | 9.0 | 198 | 0.5000 | 0.9231 | 0.85 | 1.0 | 0.9189 | 0.9318 |
| 0.0006 | 10.0 | 220 | 0.5037 | 0.9231 | 0.85 | 1.0 | 0.9189 | 0.9318 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3