Repository navigation
WIP: Judge tuning (1/6): Add held-out arena partitions - #134
Draft
ErlisLushtaku wants to merge 5 commits into
Draft
ErlisLushtaku wants to merge 5 commits into
ErlisLushtaku wants to merge 5 commits into
Conversation
Judge tuning needs to select configurations on one partition of the human-labeled arena and report on another. Battles are assigned by a salted hash of their first user prompt, so repeated prompts never cross partitions and changing run.seed cannot move battles between them.
This was referenced Oct 7, 2026
…u/feat/judge-tuning-01-arena-split
ErlisLushtaku
changed the base branch from
main
to
erlislushtaku/fix/vllm-openai-compat
October 7, 2026 13:51
…u/feat/judge-tuning-01-arena-split
ErlisLushtaku
changed the title
ErlisLushtaku
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
WIP. Not ready for review yet.
Adds prompt-hashed validation/test partitions to meta-eval so repeated prompts stay in one partition independently of the sampling seed. Existing arena task definitions are unchanged.
Part 1 of 6, stacked on #137. Merge order is #137, #134, #135, #140, #133, #139, then #136. Merge the independent context-failure prerequisite #138 before #140. All remain WIP.