Closed
Conversation
This removes the BestOfNSampler class as it's considered out of scope for the TRL library. The class provided a "Best of N" sampling strategy for PPO fine-tuning, but this functionality is not a core part of TRL's reinforcement learning training capabilities. Changes: - Removed implementation: trl/extras/best_of_n_sampler.py - Removed tests: tests/test_best_of_n_sampler.py - Removed documentation: docs/source/best_of_n.md - Removed example notebook: examples/notebooks/best_of_n.ipynb - Updated imports: trl/__init__.py, trl/extras/__init__.py - Updated documentation references: docs/source/_toctree.yml, docs/source/example_overview.md, examples/notebooks/README.md
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This PR removes the
BestOfNSamplerclass from the TRL library. The class is considered out of scope as it's not a core part of TRL's reinforcement learning training capabilities.Rationale
The
BestOfNSamplerclass provided a "Best of N" sampling strategy for PPO fine-tuning, but this functionality doesn't align with TRL's core focus on RLHF training methods.Changes
trl/extras/best_of_n_sampler.pytests/test_best_of_n_sampler.pydocs/source/best_of_n.mdexamples/notebooks/best_of_n.ipynbtrl/__init__.py,trl/extras/__init__.pydocs/source/_toctree.yml,docs/source/example_overview.md,examples/notebooks/README.mdTesting
Verified no remaining references to
BestOfNSamplerorbest_of_nin the codebase (excluding git history).