Skip to content

Fail fast on non-finite RL metrics - #22

Closed
ISEEKYAN wants to merge 1 commit into
mainfrom
fix/k3-rl-finite-gate
Closed

Fail fast on non-finite RL metrics#22
ISEEKYAN wants to merge 1 commit into
mainfrom
fix/k3-rl-finite-gate

Conversation

@ISEEKYAN

@ISEEKYAN ISEEKYAN commented Aug 3, 2026

Copy link
Copy Markdown
Owner

Summary

  • add a CPU-only streaming gate for non-finite ppo_kl, loss, and grad_norm metrics
  • exit with status 42 on the first NaN or infinity while preserving the rejected line
  • expose k3-rl-finite-gate and document the pipefail/tee launcher integration

Verification

  • focused finite-gate tests: 12 passed
  • repository Ruff format check: 58 files already formatted
  • repository Ruff lint check: passed
  • diff whitespace check: passed

The tests include an actual Bash pipefail pipeline and verify that a non-finite metric propagates exit status 42 through tee.

@ISEEKYAN ISEEKYAN closed this Aug 3, 2026
@ISEEKYAN

ISEEKYAN commented Aug 3, 2026

Copy link
Copy Markdown
Owner Author

Closed per repo owner's standing freeze on new k3 PRs (2026-08-01): k3 has a single open delivery PR (#20) and all further changes must land as commits on its branch feat/k3-three-stage-rl-clean. The change itself (fail-fast on non-finite RL metrics) is accepted and will be re-landed there — closing this PR is a process correction, not a rejection of the fix.

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

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant