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.

Sign up for GitHub

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

Jump to bottom

Model eval #1047

Open
iankur opened this issue Jun 4, 2024 · 2 comments · May be fixed by #1049
Open

Model eval #1047

iankur opened this issue Jun 4, 2024 · 2 comments · May be fixed by #1049
Assignees
@joecummings
Labels
bug Something isn't working good first issue Good for newcomers

Comments

@iankur
Copy link

iankur commented Jun 4, 2024

Does the elether_eval recipe call model.eval() somewhere? I tried to find it but could not. It's there in the lm evaluation harness but we have overriden the constructor in eval wrapper. Also, my results change when I switch model to eval mode.
@joecummings joecummings self-assigned this Jun 4, 2024
@joecummings joecummings linked a pull request Jun 4, 2024 that will close this issue
Draft
@joecummings
Copy link
Contributor

Great catch @iankur! I've created a PR to address this change - feel free to follow along there.

@iankur
Copy link
Author

iankur commented Jul 2, 2024

Thanks @joecummings. Do you mind sharing why does eleuther_eval recipe use evaluate instead of simple_evaluate method from lm-eval-harness? The reason I am asking is evaluate does not allow few shot evaluation whereas simple_evaluate accepts num_fewshot argument for the same.

@felipemello1 felipemello1 added bug Something isn't working good first issue Good for newcomers labels Jul 2, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@joecummings joecummings

Labels
bug Something isn't working good first issue Good for newcomers
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Put model in eval mode for evaluation joecummings/torchtune
3 participants
@iankur @joecummings @felipemello1