Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix SFTDataset sample generation #1568

Merged
merged 7 commits into from
Jul 10, 2024
Merged

Fix SFTDataset sample generation #1568

merged 7 commits into from
Jul 10, 2024

Conversation

alealv
Copy link
Contributor

@alealv alealv commented Jul 9, 2024

Fixes #1567.

litgpt/data/base.py Outdated Show resolved Hide resolved
litgpt/data/base.py Outdated Show resolved Hide resolved
@rasbt
Copy link
Collaborator

rasbt commented Jul 9, 2024

Also tagging @Andrei-Aksionov for insights here, who has done a lot of tokenizer work in LitGPT

litgpt/data/base.py Outdated Show resolved Hide resolved
@Andrei-Aksionov
Copy link
Collaborator

Hello @alealv
Nice catch!
Just update the test and I think the PR is ready.

@rasbt
Copy link
Collaborator

rasbt commented Jul 10, 2024

Thanks for addressing all our feedback @alealv ! It looks good to me now!

@rasbt rasbt merged commit d85d92b into Lightning-AI:main Jul 10, 2024
9 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Current way masking training data creates issues with the Tokenizer
4 participants