[MLPerf 6.1][GRPO] Add RLVR GRPO reference #890
Open
jepio wants to merge 24 commits into
Open
Conversation
Add data instructions
…uctions update data instructions
Use placeholders for some parameters that still need to be fixed.
* explicitly mention RLVR * expand GRPO * remove commit
update swe rl grpo benchmark definition for Qwen 3.5
|
MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅ |
Author
|
recheck |
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 a new GRPO MLPerf Training reference benchmark: a Qwen 3.5 397B A17B MoE model trained using RLVR (Reinforcement Learning with Verifiable Rewards) and Group Relative Policy Optimization (GRPO) on the software engineering R2E-Gym dataset using the OpenHands agent environment. The reference implementation is carried as a git submodule under
llm_moe_grpo/RL.What this adds