README.md

---
license: other
base_model: deepseek-ai/deepseek-coder-1.3b-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: deepseek-ai-deepseek-coder-1.3b-base-finetuned-defect-cwe-group-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. -->

# deepseek-ai-deepseek-coder-1.3b-base-finetuned-defect-cwe-group-detection

This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5777
- Accuracy: 0.7586
- F1: 0.7499
- Precision: 0.7513
- Recall: 0.7586

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| No log        | 1.0   | 462  | 0.4832          | 0.7743   | 0.7594 | 0.7720    | 0.7743 |
| 0.5829        | 2.0   | 924  | 0.4705          | 0.7788   | 0.7700 | 0.7737    | 0.7788 |
| 0.3078        | 3.0   | 1386 | 0.5777          | 0.7586   | 0.7499 | 0.7513    | 0.7586 |


### Framework versions

- Transformers 4.37.0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1