Base-model PPL vs post-RL math accuracy (issue #6096).
Created
June 23, 2026 00:21
-
-
Save Helw150/fca0e45e3fa10b7d0c0a8ecb4c79fbfa to your computer and use it in GitHub Desktop.
SimpleRL-Zoo: base PPL vs post-RL math accuracy (issue 6096)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
