verl-project/verl

[FR] Tests for gradient accumulation

Open

#907 opened on Apr 3, 2025

View on GitHub
 (0 comments) (0 reactions) (0 assignees)Python (21,533 stars) (3,940 forks)auto 404
enhancementgood first issue

Description

Summary

Promise from #906.

Add tests to assert the losses on the same mini-batch are equal

  • between w/o & w/ gradient accumulation
  • using all the different loss aggregation modes

Plan

We might went to test end-to-end to avoid potential implication by any other changes.

Plan Pro
A) Inherit a new Trainer class to test Standalone without affecting the main config
B) Add a config term and modify update_* to test 1) Minimal code modification 2) Compatibility to any Trainer

Contributor guide

Tech stack
pythonpytorch
Domain
testing
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
PythonPyTorchgradient accumulation
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70
Research direction
Investigate the two proposed plans: A) creating a new Trainer subclass for testing to avoid affecting main config, or B) adding a config term and modifying update * methods. The tests should assert that losses on the same mini batch are equal with and without gradient accumulation across all loss aggregation modes. Look at the existing test suite in the repository to understand the testing structure and consider implementing both options if feasible. Examine the gradient accumulation implementation in the trainer to identify the update * methods and loss aggregation modes.