Add neftune #531
Merged
Add neftune #531
Conversation
This file contains 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
pascal-pfeiffer
approved these changes
Dec 7, 2023
There was a problem hiding this comment.
Thank you @maxjeblick , very clean code
lgtm
we should check for potential needed changes in #513 , though it currently works flawless with deepspeed, too.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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 neftune as proposed by NEFTune: Noisy Embeddings Improve Instruction Finetuning https://arxiv.org/abs/2310.05914.
I've tested the functionality manually with ddp and deepspeed enabled/disabled.
@tmostak reported some improvements while testing this feature on this branch (see #492)
Fixes #492