fix(template): replace rejected responses after the last user message - #10127
Open
Excelius-Wang wants to merge 1 commit into
Open
Excelius-Wang wants to merge 1 commit into
Excelius-Wang wants to merge 1 commit into
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Agent preference data using
toolmessages currently inherits chosen tool calls and results when buildingrejected_messagesfromrejected_response. Keep the documented replacement boundary at the last user message by adding an opt-out for tool boundaries to the existing helper. Its default behavior, including the last-round loss fix in #9923, remains unchanged.Validation: 10 tests and 12 subtests passed, including an actual JSONL/OpenAI tool-call loading regression and the existing loss-scale tests. Local CPU encoding checks covered 48 official-example variants and 192 cases from three public preference datasets; all match explicit rejected-message references after the fix. Six two-step tiny-model DPO runs produced identical losses and trained weights for compact versus explicit representations on each dataset. Changed-file pre-commit checks and
git diff --checkpassed.