WIP: Adding verifier for STEM datasets #95

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

Draft

gupta-abhay wants to merge 1 commit into main from abhay/stem_verifiers

Collaborator

gupta-abhay commented Jun 18, 2025 •

edited

Loading

We are going to rely on STEM evals (MMLU-Pro and GPQA-Diamond) as our 3rd subset in Reasoning Gauntlet
This adds a verifier for these datasets (including extensions for different formats etc.)
Also, this is WIP, needs testing and refinement - since the current regex pattern is very broad.


          adding string matching reward

b533026

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

bcui-db Awaiting requested review from bcui-db bcui-db will be requested when the pull request is marked ready for review bcui-db is a code owner

dakinggg Awaiting requested review from dakinggg dakinggg will be requested when the pull request is marked ready for review dakinggg is a code owner

abaheti95 Awaiting requested review from abaheti95 abaheti95 will be requested when the pull request is marked ready for review abaheti95 is a code owner

jdchang1 Awaiting requested review from jdchang1 jdchang1 will be requested when the pull request is marked ready for review jdchang1 is a code owner

At least 1 approving review is required to merge this pull request.

Labels

None yet