█
LastWrite
  • > Curriculum
  • > Pricing
  • > For Educators
  • > About
  • > Contact
Log InGet Started

Questions, concerns, bug reports, or suggestions? We read every message, write to us at [email protected].

More ways to reach us →
LastWrite

Structured computer science lessons for aspiring developers and security professionals.

[email protected]

(201) 785-7951

Mon–Fri, 9 AM–5 PM EST

Learn

  • Curriculum
  • Pricing

Company

  • About
  • For Educators & Schools
  • Contact Us

Legal

  • Terms of Service
  • Privacy Policy
© 2026 LastWrite. All rights reserved.
Curriculum/LLM Research and NLP/Fine-Tuning and Adaptation/The Adaptation Lifecycle
30 minIntermediate

The Adaptation Lifecycle

After this lesson, you will be able to: Map the pretraining to supervised-fine-tuning to alignment lifecycle, and decide between prompting, retrieval, and fine-tuning for a given problem.

Fine-tuning is the research skill that turns a general base model into something specific. But it is often the wrong tool. This intro frames the adaptation lifecycle and the honest decision of when to fine-tune at all.

This is a free introductory lesson. No purchase required.

The adaptation lifecycle

A usable assistant is built in stages. Pretraining produces a base model that completes text. Supervised fine-tuning (SFT) on instruction/response pairs teaches it to follow instructions. Preference optimization (RLHF or DPO) aligns it with human preferences for helpfulness and harmlessness. Each stage uses less data than the last and changes the model's behavior more than its raw knowledge. As a researcher you will almost always start from a pretrained (and often instruction-tuned) open model and run one of the later stages, not pretrain from scratch.

💡 Fine-tune, prompt, or retrieve?

The most common research and engineering mistake is fine-tuning when you did not need to. Prompt (including few-shot) when the base model already has the capability and you just need to elicit it. Use retrieval (RAG) when the problem is missing knowledge or freshness, since fine-tuning teaches behavior and style, not reliable new facts. Fine-tune when you need a consistent format/behavior the prompt cannot reliably produce, a smaller/cheaper model to match a bigger one on a narrow task, or a capability the base model lacks. For a paper, be able to justify why fine-tuning was the right intervention.

What fine-tuning is good and bad at

Good at: format and style (always output JSON, always answer in this tone), narrow task performance (classification, extraction, a specific generation task), and distilling a large model's behavior into a small one. Bad at: injecting large amounts of new factual knowledge reliably (it tends to learn the form of answers, not the facts, and can increase hallucination if you fine-tune on facts it half-learns). Knowing this boundary is exactly what separates a sound experimental design from a doomed one.

Back to Fine-Tuning and Adaptation
Full Fine-Tuning vs PEFT→