Repository navigation
Add a workflow to re-grade merged routers on GitHub runners - #244
Merged
Merged
Conversation
Manual workflow (workflow_dispatch) that re-grades each merged prediction file with the current evaluator, one router per job, and uploads the re-graded file and its metrics as an artifact. LiveCodeBench grading runs submitted code, so this belongs on the runners rather than a local machine. Runner setup matches the PR evaluation workflow. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds
.github/workflows/regrade-all.yml, a manual (workflow_dispatch) workflow that re-grades merged prediction files with the current evaluator.uv, dataset prep and 10 GB of swap.llm_evaluation/run.py <router> full --forceand uploads the re-graded prediction file (per-row accuracy and cost) and itsmetrics.jsonas an artifact.routersinput limits the run to named routers; by default every prediction file on the branch is re-graded.Why now: three LiveCodeBench scorer fixes (#230, #234, #239) and the METEOR cap (#216) have landed, and several stored scores predate them. LiveCodeBench grading executes submitted code, so the re-grade runs on GitHub's runners. The results will come in a separate PR.
The workflow only reads the repository (
contents: read) and changes nothing by itself.🤖 Generated with Claude Code