metadata
base_model: microsoft/codebert-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: CodeBertForDefect-Detection
results: []
CodeBertForDefect-Detection
This model is a fine-tuned version of microsoft/codebert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9039
- Accuracy: 0.6435
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 13112.4
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6483 | 1.0 | 1366 | 0.6494 | 0.5637 |
| 0.6213 | 2.0 | 2732 | 0.5968 | 0.6380 |
| 0.5927 | 3.0 | 4098 | 0.5767 | 0.6457 |
| 0.5615 | 4.0 | 5464 | 0.5855 | 0.6669 |
| 0.5271 | 5.0 | 6830 | 0.6677 | 0.6643 |
| 0.4488 | 6.0 | 8196 | 0.7177 | 0.6237 |
| 0.4576 | 7.0 | 9562 | 0.6643 | 0.6398 |
| 0.45 | 8.0 | 10928 | 0.7414 | 0.6479 |
| 0.4156 | 9.0 | 12294 | 0.9852 | 0.6519 |
| 0.3362 | 10.0 | 13660 | 0.9039 | 0.6435 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0