Draft
Conversation
Add reusable EvalOnDataset callback that runs evaluation functions on arbitrary datasets every N epochs with DDP support, and a callback_to_evaluator adapter that wraps existing Lightning callbacks (CLIPZeroShot, OnlineKNN, OnlineProbe) into evaluator functions. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace single name/data/evaluators params with a list of EvalDatasetEntry dataclasses so one callback handles all eval runs sequentially with a single DDP barrier, matching the original ZeroShotEvalCallback behavior. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Let Lightning handle rank coordination and logger dispatch via log_dict(sync_dist=True) instead of manually checking is_global_zero and calling trainer.logger.log_metrics. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Create a callback to run evals on arbitrary datasets. Also add a function for mapping callbacks to accepted eval functions.
Working example here https://github.com/galilai-group/clipa/blob/eval-on-dataset-rewrite/clip.py
Checklist