[FIX] MM Eval Mask Sizes #1920
Merged
[FIX] MM Eval Mask Sizes #1920
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/torchtune/1920
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit e988093 with merge base d338066 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
RdoubleA
reviewed
Oct 29, 2024
| _, _, img_seq = concat_masks.shape | ||
| concat_masks = F.pad( | ||
| concat_masks, (0, pad_max_images * image_seq_len - img_seq) | ||
| concat_masks, |
There was a problem hiding this comment.
where does the pad to max images happen? this is just padding the masks to max num images? and would pad direction affect image padding at all?
There was a problem hiding this comment.
You don’t actually need to add them or you’d waste compute on them. If you have a I cache for 7 images, then you want to mask out the additional images. It’s similar to how you mask extra token positions during inference but don’t add padding tokens.
joecummings
approved these changes
Oct 30, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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Outdated suggestions cannot be applied.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.
Context
What is the purpose of this PR? Is it to
Issue first reported in #1874 found that eval fails for llama3.2 vision 11B. This issue found was that the VisionCrossAttentionMask was padding the masks to 4 tiles during inference while at the same time the padded_collate_tiled_images_and_mask function was assuming that the masks weren't padded and inferring incorrect shape information.
The solution is to remove any inference time padding logic from the mask transform and pass pad_max_tiles=4 to the collate function during inference and eval to let the collate function handle all the padding.
During this investigation I found that padded_collate_tiled_images_and_mask was using "image_seq_len" variable from the last definition in a loop, meaning that if there were multiple images with different sizes the variable would be wrong at the end. Updated this as well.
Changelog
What are the changes made in this PR?
Test plan
Please make sure to do each of the following if applicable to your PR. If you're unsure about any one of these just ask and we will happily help. We also have a contributing page for some guidance on contributing.
pre-commit install)pytest testspytest tests -m integration_testRan as usual
tune run dev/generate_v2 --config llama3_2_vision/generation_v2
Ran as usual
tune run full_finetune_single_device --config llama2_2_vision/11B_full_single_device
Fixed
tune run eleuther_eval --config llama3_2_vision/evaluation