---
title: "Discussion on \"What Does Fine-Tuning Actually Learn? Testing QLoRA with Deliberately Controlled Data\" | Hashnode"
description: "Discussion on \"What Does Fine-Tuning Actually Learn? Testing QLoRA with Deliberately Controlled Data\". A controlled QLoRA experiment: format is learned first, facts come later, and brand drift turns out to just be about epoch count."
url: "https://hashnode.com/posts/what-does-llm-fine-tuning-actually-learn/6ab685bad8756b66d8d3aa49"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [What Does Fine-Tuning Actually Learn? Testing QLoRA with Deliberately Controlled Data](https://shaka-ai.hashnode.dev/what-does-llm-fine-tuning-actually-learn?utm_source=hashnode&utm_medium=feed)

A controlled QLoRA experiment: format is learned first, facts come later, and brand drift turns out to just be about epoch count.

Sep 25 · 7 min read · shaka-ai.hashnode.dev  
Read the article

-   [#llm](https://hashnode.com/tag/llm)
-   [#finetuning](https://hashnode.com/tag/finetuning)
-   [#machine-learning](https://hashnode.com/tag/machine-learning)

## Written by

[Muhammad Ariel Shakaramiro](https://hashnode.com/@arielshakaramiro)

@arielshakaramiro

  
[View profile](https://hashnode.com/@arielshakaramiro)

Newbie for AI Learning | Builder | Developer | AI Enthusiast

## Responses

Markdown supported · ⌘↵ to post

No responses yet.