Merged
Conversation
sjmielke
approved these changes
May 16, 2025
Collaborator
sjmielke
left a comment
There was a problem hiding this comment.
Small suggestions, though i'd also be curious whether the decision to couple MLM and InfoNCE loss like this will work out well with different batch size requirements for either (CLIP uses like what 32k batch size I think for the contrastive loss, so I don't know if that's also the range we're thinking of for these combined batches---and of course, all of this is assuming we can fit that much in memory without tiling the similarity matrix computation... maybe it's fine for now just to see if it kinda works :) )
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add an option to run InfoNCE and MLM at the same time.
(1 - self.contrastive_loss_weight) * mlm_loss + self.contrastive_loss_weight * contrastive_loss