Bug fixes in reward utils #3

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

Open

insop wants to merge 1 commit into main from codex/find-and-fix-a-bug-in-codebase

Owner

insop commented Jun 8, 2025

Summary

prevent in-place modification of labels when computing log probabilities
correct return type for format_reward_func

Testing

python -m py_compile kernel-coder/utils.py kernel-coder/nano_r1_script.py scripts/kernelllm.py

https://chatgpt.com/codex/tasks/task_e_68461478a650832cbca1e1eb3396a49f


          Fix reward function type and prevent label mutation

9e514c4

insop added the codex label

— with

ChatGPT Connector

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

Labels