metadata
license: bsd-3-clause
base_model: Salesforce/codet5p-220m
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: Salesforce-codet5p-220m-finetuned-defect-detection
results: []
Salesforce-codet5p-220m-finetuned-defect-detection
This model is a fine-tuned version of Salesforce/codet5p-220m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5331
- Accuracy: 0.7289
- Roc Auc: 0.7292
- Precision: 0.7152
- Recall: 0.7395
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 |
|---|---|---|---|---|---|---|---|
| 0.6935 | 1.0 | 996 | 0.5783 | 0.6689 | 0.6657 | 0.7197 | 0.5277 |
| 0.5694 | 2.0 | 1993 | 0.5279 | 0.7013 | 0.7026 | 0.6723 | 0.7580 |
| 0.4812 | 3.0 | 2989 | 0.5058 | 0.7181 | 0.7179 | 0.7129 | 0.7081 |
| 0.4235 | 4.0 | 3986 | 0.5088 | 0.7292 | 0.7291 | 0.7213 | 0.7261 |
| 0.3658 | 5.0 | 4980 | 0.5331 | 0.7289 | 0.7292 | 0.7152 | 0.7395 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2