Lightning-AI / Lightning-AI/litgpt

Why Alpaca is only mask_prompt=False??

Open
#1,987 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

help wanted question
Dominant language
Python
Stars
13.7k
Forks
1.5k
Avg merge
15h 37m
Merged PRs (30d)
1

Description

litgpt/data/alpaca.py is a default data module.

but, It's mask_prompt=False... I don't know why.. I think loss must be calculated in generated answer... not prompt...

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading litgpt/data/alpaca.py and trace how mask_prompt=False affects the training loss. Compare the module's behavior with the issue's expected prompt masking, then confirm the desired loss behavior with the surrounding data-module conventions. Done means the Alpaca module calculates loss only for generated answers, with appropriate coverage if an existing test path is available.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.