metadata
license: bsd-3-clause
base_model: Salesforce/codet5p-770m
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- 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: 0.4831
- Accuracy: 0.7337
- F1: 0.7377
- Precision: 0.7108
- 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: 2
- eval_batch_size: 2
- seed: 4711
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.6813 | 1.0 | 996 | 0.5630 | 0.6898 | 0.6580 | 0.7128 | 0.6110 |
| 0.5483 | 2.0 | 1992 | 0.5040 | 0.7103 | 0.7071 | 0.6986 | 0.7158 |
| 0.4502 | 3.0 | 2988 | 0.4831 | 0.7337 | 0.7377 | 0.7108 | 0.7667 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0