diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index 2484957167..61218dea89 100644 --- a/.github/PULL_REQUEST_TEMPLATE.md +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -1,12 +1,23 @@ -## Description +Include a summary of the changes and the related issue if any. -Fixes #(issue number) +A good description is a paragraph or so describing the changes you made and the +motivation. You may follow this with a few bullets for specific changes, but +try to keep it concise. -[Please include a summary of the changes and the related issue.] +e.g. +Title: [RL] Fix loss: use global token normalization instead of per-example -## Checklist +""" +This fixes a regression in the DAPO loss computation by switching +from per-example normalization (/ n_i) back to global token +normalization (/ N). Per-example normalization gives shorter responses +disproportionately more gradient weight, which hurts math reasoning +tasks where correct answers often require detailed, longer derivations. +Global normalization weights all examples equally regardless of response +length. +""" -- [ ] You ran `uv run python infra/pre-commit.py --all-files` to lint/format your code -- [ ] You ran 'pytest' to test your code -- [ ] Delete this checklist + + +Fixes #