[Evals] Headless evals with Docker #4121
Merged
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Outdated suggestions cannot be applied.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.
Description
Allows for headless execution of evals in a Docker container.
Note that headless evals can only run without concurrency for now; attempting to run with concurrency introduces errors.
Future work will include integrating headless evals with a cloud runner and sharding across jobs
Important
Adds Docker support for headless evals, updates CLI for Docker-specific conditions, and includes Docker scripts in package.json.
Dockerfilefor setting up a headless eval environment with necessary dependencies..dockerignoreto exclude unnecessary files from Docker build.runExerciseinindex.tsto handle Docker environment, including concurrency checks and command adjustments.package.jsonwith Docker-related scripts:docker:build,docker:run,docker:start,docker:shell,docker:stop,docker:rm, anddocker:clean.This description was created by
for a302414. You can customize this summary. It will automatically update as commits are pushed.