Perplexity: Compute scores correlated to HellaSwag#2312
Merged
klosax merged 6 commits intoggml-org:masterfrom Jul 22, 2023
Merged
Perplexity: Compute scores correlated to HellaSwag#2312klosax merged 6 commits intoggml-org:masterfrom
klosax merged 6 commits intoggml-org:masterfrom
Conversation
ggerganov
approved these changes
Jul 22, 2023
Member
ggerganov
left a comment
There was a problem hiding this comment.
Thanks for adding this.
It would be interesting to see what are the HellaSwag numbers for the different quantizations that we have and how they compare to F16.
We can merge and do the evaluations later, or if can post some numbers here in the PR
Merged
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR adds a
--perplexity-linesparameter to the perplexity tool. In this mode the perplexity is calculated over each line of the prompt instead of over each ctx window.HellaSwag scores is a great way to measure how much of the English language the model understands.
Make two runs on a model, one prompted with a file containing "correct" sentences (one per line) and another run with a file containing "wrong" sentences. The measured perplexity from both files can be used to compute a score that is linearly correlated to the HellaSwag score.
ppl_correct= Cumulative perplexity on each line of hellaswag_val_correct.txt, lower values are better.ppl_wrong= Cumulative perplexity on each line of hellaswag_val_wrong.txt, higher values are better.The formula
(ppl_wrong - ppl_correct) / ppl_correctcorrelates linearly with HellaSwag scores on Open LLM Leaderboard.Test files: klosax/ppl_hellaswag.
Open LLaMA 3B