Weight sync in actual GRPO #128
Closed
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
… (#127) * update installation script for conda/ubuntu users without sudo access * remove older functions from the script
…Is. (#115) * vllm + ts fix * fix example after policy service APIs. * prive methods with underscore
meta-cla
bot
added
the
CLA Signed
* Update reference_actor.py * add tests, clean up * messed up history...
* pull and install torchstore in CI * prepend `python -m` * fix * Update unit_test.yaml
* first changes * core updates * batch update * fix typo * missing import * debug merge * more fixes * Remove dtype warnings * Stub * It runs * Add in ref * Pass linting? * Remove extraneous 'calculations' * Stub out push weights * Remove tokenizer, add back in formatting * Cleanup * Updated default group * update CI * added tyro * reverted build changes
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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Outdated suggestions cannot be applied.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.
https://wandb.ai/jcummings/grpo-training/workspace?nw=nwuserjcummings