[rl] Add optional Verifiers rollout integration - #4356
Draft
wwwjn wants to merge 8 commits into
Draft
Conversation
wwwjn
commented
Aug 28, 2026
|
|
||
| @dataclass(kw_only=True, slots=True) | ||
| class Config(VerifiersRollouter.Config): | ||
| train_dataset: VerifiersTaskDataset.Config = field( |
Contributor
Author
There was a problem hiding this comment.
Dataset is defined through verifiers
wwwjn
force-pushed
the
verifiers-dapo-math
branch
from
August 31, 2026 23:51
762930e to
36c417d
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
WIP: need to be cleaned up.
Summary
torchtitan/experiments/rl/rollout/verifiers.verifiersexample that reuses the existing DAPO Math datasets, training configuration, and reward logic while delegating episode execution to Verifiers.nullharness with a local subprocess runtime. No Docker or remote sandbox is required, and no tools are exposed to the model.verifierspackage.dapo_mathimplementation unchanged.The example can be launched with:
100-step comparison
Both runs used Qwen3-4B-Base on 8 GPUs with identical overrides:
dapo_mathverifiersW&B runs:
The rollout distribution are similar:

This single-run comparison does not show an end-to-end throughput penalty from the Verifiers integration. The decode metric was slower, but generated responses were also longer, and model-state synchronization variance dominated the total step time.