metadata
base_model: microsoft/codebert-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: microsoft-codebert-base-finetuned-defect-detection
results: []
microsoft-codebert-base-finetuned-defect-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: 0.6534
- Accuracy: 0.7342
- F1: 0.7413
- Precision: 0.7066
- Recall: 0.7795
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 | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.6396 | 1.0 | 996 | 0.5277 | 0.6905 | 0.6502 | 0.7258 | 0.5889 |
| 0.4862 | 2.0 | 1993 | 0.5331 | 0.7176 | 0.7393 | 0.6733 | 0.8196 |
| 0.4043 | 3.0 | 2989 | 0.5521 | 0.7339 | 0.7343 | 0.7167 | 0.7528 |
| 0.3439 | 4.0 | 3986 | 0.5945 | 0.7357 | 0.7422 | 0.7087 | 0.7790 |
| 0.2946 | 5.0 | 4980 | 0.6534 | 0.7342 | 0.7413 | 0.7066 | 0.7795 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2