Repository navigation
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Evaluation and capture coordinate the same episodes separately
Recipe evaluation and retained capture share policy loading and rollout, but each coordinates model initialization, episode execution and settings. This leaves two places to maintain native evaluation behavior.
Record evidence around shared native evaluation
Use one recipe settings resolver and episode runner for Torch evaluation, with synchronous recording hooks for capture. Preserve root-seed expansion, explicit capture seeds, failed attempts and retries. Optional policy seeds make programmatic evaluations reproducible across worker counts without changing the existing command defaults.
Based on #41. Related to #31.