metadata
license: bsd-3-clause
base_model: Salesforce/codet5p-770m
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: Salesforce-codet5p-770m-finetuned-defect-detection
results: []
Salesforce-codet5p-770m-finetuned-defect-detection
This model is a fine-tuned version of Salesforce/codet5p-770m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5699
- Accuracy: 0.7505
- Roc Auc: 0.7509
- Precision: 0.7343
- Recall: 0.7667
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 4711
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Roc Auc | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.6826 | 1.0 | 996 | 0.5735 | 0.6923 | 0.6925 | 0.6791 | 0.7014 |
| 0.528 | 2.0 | 1993 | 0.4960 | 0.7191 | 0.7211 | 0.6785 | 0.8078 |
| 0.4308 | 3.0 | 2989 | 0.4821 | 0.7415 | 0.7419 | 0.7234 | 0.7621 |
| 0.3495 | 4.0 | 3986 | 0.5010 | 0.7455 | 0.7463 | 0.7217 | 0.7795 |
| 0.2731 | 5.0 | 4980 | 0.5699 | 0.7505 | 0.7509 | 0.7343 | 0.7667 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2