---
title: "Chapter 03: The Experiments"
description: "Sweep rank, steps, dataset size, target modules, and adapter scale. Build the contact sheet — the artifact you'll refer back to all course."
type: lesson
order: 3
chapter: "01-lora-eyes-open"
---

# Chapter 03: The Experiments

This is the actual coursework of Part 1. Run each experiment, generate the same fixed prompt from each adapter, and put the outputs side by side.

## The Sweep

| Experiment | Vary | What you're looking for |
|---|---|---|
| A | rank 4 / 16 / 64 | Where does capacity stop helping? |
| B | steps 200 / 600 / 2000 | Where does it flip from underfit to memorized? |
| C | dataset 5 / 15 / 30 images | The data/capacity tradeoff |
| D | attention-only vs. all-linear targets | Community finding: attention layers alone are often enough. Verify it. |
| E | adapter at scale 0.3 / 0.7 / 1.0 | Adapters are *dials*, not switches |

For E, bake a scaled adapter with:

```bash
mflux-save --lora-paths /path/to/lora.safetensors --lora-scales 0.7
```

## Deliverable

**A contact sheet** — one grid image, same prompt, every adapter variant labeled. Pin it somewhere. You will refer back to it every time a text LoRA in Parts 2–5 behaves strangely and you're trying to name what you're seeing.

## Exit Criteria

You can look at a generation and say "that's overfit" or "that's underbaked" without checking any numbers. You can predict, before running, roughly what rank 64 on 5 images will do.

## The One Failure Mode That Matters Here

**Spending three days on this.** It's rung one. Get the contact sheet, move on.

---

[← Chapter 02](/fine-tune-local-agent/01-lora-eyes-open/02-train-an-adapter/) · [Next: Part 2 →](/fine-tune-local-agent/02-the-pipeline/)