</>SkillRecallRECALL WHAT YOU KNOW
Sign in
Explore Library
AI Engineering / Working with LLMsFine-tuning & Model Customization

12 items

1

Dataset Size and Quality

Flashcard
2

Train/Validation/Test Splits

Flashcard
3

Instruction Fine-Tuning (SFT)

Flashcard
4

Adapters and Prefix/Prompt Tuning

Flashcard
5

LoRA (Low-Rank Adaptation)

Flashcard
6

Full vs Parameter-Efficient Fine-Tuning

Flashcard
7

What is Fine-Tuning

Flashcard
8

Preparing Training Datasets

Flashcard
9

RLHF

Flashcard
10

DPO and Preference Alignment

Flashcard
11

Fine-Tune vs Prompting vs RAG

Flashcard
12

QLoRA and Quantized Fine-Tuning

Flashcard
Flashcard

Train/Validation/Test Splits

Split data into train, validation, and test sets to tune, monitor, and honestly evaluate fine-tuning.

Question

Why split fine-tuning data into train/validation/test sets?

Click to reveal answer