NO-ISSUE: add --from-report to the stock-vs-tuned sweep - #5
Merged
Conversation
Picking keep_exact_match_rate over false_redaction_rate previously meant re-running every engine: --freeze only worked inside a run that had just measured the trials, even though sweep_report.json carries every trial's overall and per_stratum block. Selection is now select_from_trials(), shared by both paths, so the printed report and tuned_configs.json cannot disagree about which config won. --from-report merges per-engine shards, refuses shards from different dev sets or a duplicated engine, and re-applies the D-13.4 scored-set guard to the dev set the report records so the offline route is not a way around it. Offline output is written as reselected_report.json, never sweep_report.json. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
arnavdhar07
changed the title
arnavdhar07
changed the title
arnavdhar07
changed the title
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Picking keep_exact_match_rate over false_redaction_rate previously meant re-running every engine: --freeze only worked inside a run that had just measured the trials, even though sweep_report.json carries every trial's overall and per_stratum block.
Selection is now select_from_trials(), shared by both paths, so the printed report and tuned_configs.json cannot disagree about which config won. --from-report merges per-engine shards, refuses shards from different dev sets or a duplicated engine, and re-applies the D-13.4 scored-set guard to the dev set the report records so the offline route is not a way around it. Offline output is written as reselected_report.json, never sweep_report.json. done