Fix #2407: Fix get_wikitext2 tokenization bug causing sequence length warning - #2450
Draft
nandanadileep wants to merge 1 commit into
Draft
Conversation
…ence length w Signed-off-by: nandanadileep <nandanadileep29@gmail.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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #2407
Changed
get_wikitext2from concatenating 1000 entries into a single string and tokenizing all at once (producing 73K+ token sequences that exceed the model's max length), to per-sample tokenization with a retry loop matchingget_c4/get_c4_new.Local test infra unavailable in CI sandbox.
This change was prepared with AI assistance under human direction and review.