---
language:
- ar
license: llama3
base_model: meta-llama/Llama-3.1-8B
tags:
- arabic
- medical
- question-answering
- fine-tuned
- full
---

# Omaratef3221/llama-3.1-8b-s1-full-s2-lora-medarabench

**Base model:** `meta-llama/Llama-3.1-8B`  
**Training stage:** Stage 2 — Task Fine-tuning (MedAraBench)  
**Stage 1 method:** full  
**Stage 2 method:** lora  

## Paper

_LoRA vs. Full Fine-Tuning for Arabic Medical Question Answering: A Systematic Comparison Across General-Purpose and Arabic-Centric Large Language Models_

## Training data

| Stage | Dataset | Samples |
|-------|---------|---------|
| Stage 1 | AraMed (open-ended Arabic medical QA) | ~110K |
| Stage 2 | MedAraBench (Arabic MCQ) | ~17.6K (cleaned) |

## Evaluation

Evaluated on MedAraBench test set (4,959 MCQ samples) using log-probability selection.
Metrics: **Accuracy** and **Macro F1** across answer classes A–E.

## Experiment metadata

```json
{
  "model_name": "meta-llama/Llama-3.1-8B",
  "stage1_method": "full",
  "stage2_method": "lora",
  "stage": "task_specific",
  "num_epochs": 3,
  "config_path": "/home/oelgendy/arabic-medical-llm/script/configs/lora.yaml",
  "stage1_checkpoint": "outputs/exp04_llama_full_lora/stage1",
  "train_samples": 16756,
  "val_samples": 882
}
```