Feat: Drop long samples and shuffle rl samples #2040
Merged
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
winglian
approved these changes
Nov 19, 2024
djsaunde
pushed a commit
that referenced
this pull request
Dec 17, 2024
* feat: LOG warn if samples are dropped due to seq length * feat: add drop long samples for RL * feat: add ipo * fix: remove num_proc for map as subprocesses are prone to die * feat: shuffle rl dataset * fix: support preprocess for kto * chore: use set instead of list * feat: add simpo
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Outdated suggestions cannot be applied.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.
Description
This PR aims to solve three issues:
ˈɛmptireported TRL does not drop long samples which could lead them to being truncated.Caitlyn G.andˈɛmptialso reported about shuffling issues with KTO. KTOTrainer does not perform shuffling prior-training anymore and uses sequentialsampler. https://github.com/huggingface/trl/pull/2248/filesMotivation and Context
How has this been tested?
Run preprocess and check dropped samples:
Screenshots (if appropriate)
Types of changes
Social Handles (Optional)