Skip to content

[feat] Support DAPO #6263

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 27 commits into from
Apr 25, 2025
Merged

[feat] Support DAPO #6263

merged 27 commits into from
Apr 25, 2025

Conversation

YeAnbang
Copy link
Contributor

📌 Checklist before creating the PR

  • I have created an issue for this PR for traceability
  • The title follows the standard format: [doc/gemini/tensor/...]: A concise description
  • I have added relevant tags if possible for us to better distinguish different PRs
  • I have installed pre-commit: pip install pre-commit && pre-commit install

🚨 Issue number

Link this PR to your issue with words like fixed to automatically close the linked issue upon merge

e.g. fixed #1234, closed #1234, resolved #1234

📝 What does this PR do?

Summarize your work here.
if you have any plots/diagrams/screenshots/tables, please attach them here.

💥 Checklist before requesting a review

  • I have linked my PR to an issue (instruction)
  • My issue clearly describes the problem/feature/proposal, with diagrams/charts/table/code if possible
  • I have performed a self-review of my code
  • I have added thorough tests.
  • I have added docstrings for all the functions/methods I implemented

⭐️ Do you enjoy contributing to Colossal-AI?

  • 🌝 Yes, I do.
  • 🌚 No, I don't.

Tell us more if you don't enjoy contributing to Colossal-AI.

@YeAnbang YeAnbang requested a review from a team as a code owner April 16, 2025 09:57
@YeAnbang YeAnbang closed this Apr 16, 2025
@YeAnbang YeAnbang reopened this Apr 16, 2025
@YeAnbang YeAnbang requested a review from TongLi3701 April 17, 2025 01:49
@TongLi3701 TongLi3701 changed the base branch from grpo-latest to feature/ray-rlhf April 21, 2025 02:44
@TongLi3701 TongLi3701 changed the base branch from feature/ray-rlhf to grpo-latest April 21, 2025 02:45
TongLi3701
TongLi3701 reviewed Apr 22, 2025
View reviewed changes
Copy link
Member

@TongLi3701 TongLi3701 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks Anbang.

Some comments.

@YeAnbang YeAnbang requested a review from TongLi3701 April 24, 2025 08:28
TongLi3701
TongLi3701 reviewed Apr 25, 2025
View reviewed changes
Copy link
Member

@TongLi3701 TongLi3701 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks Anbang.

Some comments.

applications/ColossalChat/coati/distributed/consumer.py Outdated
batch = bind_batch(batches)
batch = post_recv(batch)
loss = self.step(i, **batch)
loss, num_excessive_rollouts = self.step(i, pbar, **batch)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Seems here should be num of excessive prompts.

TongLi3701
TongLi3701 reviewed Apr 25, 2025
View reviewed changes
Copy link
Member

@TongLi3701 TongLi3701 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks Anbang.

@TongLi3701 TongLi3701 merged commit 26d859f into grpo-latest Apr 25, 2025
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@TongLi3701 TongLi3701 TongLi3701 left review comments

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@YeAnbang @TongLi3701