---
base_model: microsoft/codebert-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: microsoft-codebert-base-finetuned-defect-detection
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# microsoft-codebert-base-finetuned-defect-detection

This model is a fine-tuned version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6197
- Accuracy: 0.7382
- Roc Auc: 0.7394
- Precision: 0.7070
- Recall: 0.7924

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------:|:---------:|:------:|
| 0.6456        | 1.0   | 996  | 0.5435          | 0.6832   | 0.6810  | 0.7151    | 0.5843 |
| 0.5086        | 2.0   | 1993 | 0.5373          | 0.7113   | 0.7139  | 0.6654    | 0.8227 |
| 0.4173        | 3.0   | 2989 | 0.5476          | 0.7289   | 0.7293  | 0.7125    | 0.7461 |
| 0.3543        | 4.0   | 3986 | 0.5803          | 0.7357   | 0.7369  | 0.7051    | 0.7888 |
| 0.3059        | 5.0   | 4980 | 0.6197          | 0.7382   | 0.7394  | 0.7070    | 0.7924 |


### Framework versions

- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2