Fix IndexError in get_transfer_index_dynamic in llada/generate.py for batch_size > 1 #33
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
…n batch_size > 1 - Add check for empty mask tokens to prevent IndexError - Handle edge case where num_transfer_tokens[j] == 0 Fixes issue where batch_size > 1 causes IndexError when accessing threshs[0] on empty list.
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Outdated suggestions cannot be applied.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
Fix IndexError that occurs when using batch_size > 1 in
get_transfer_index_dynamicfunction.Problem
When
batch_size > 1, different samples may have different numbers of masked tokens. If a sample has no masked tokens (num_transfer_tokens[j] == 0), thethreshslist becomes empty, causing an IndexError when accessingthreshs[0].Solution
Added a check to skip samples with no masked tokens before accessing the
threshslist.Changes
if num_transfer_tokens[j] == 0: continuecheck