metadata
license: apache-2.0
base_model: Salesforce/codet5-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: CodeT5ForDefect-Detection
results: []
CodeT5ForDefect-Detection
This model is a fine-tuned version of Salesforce/codet5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7645
- Accuracy: 0.6647
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 9178.68
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6821 | 1.0 | 2732 | 0.6957 | 0.5187 |
| 0.6692 | 2.0 | 5464 | 0.6373 | 0.6116 |
| 0.6411 | 3.0 | 8196 | 0.6130 | 0.6014 |
| 0.5706 | 4.0 | 10928 | 0.5804 | 0.6611 |
| 0.539 | 5.0 | 13660 | 0.6378 | 0.6446 |
| 0.419 | 6.0 | 16392 | 0.6895 | 0.6336 |
| 0.4162 | 7.0 | 19124 | 0.7645 | 0.6647 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0