Skip to content

[Algorithm] GRPO scripts #2970

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 111 commits into from
Jun 8, 2025
Merged

[Algorithm] GRPO scripts #2970

merged 111 commits into from
Jun 8, 2025

Conversation

vmoens
Copy link
Collaborator

@vmoens vmoens commented May 22, 2025 •
edited
Loading

Stack from ghstack (oldest at bottom):

Update
7007d83 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request May 22, 2025
[Algorithm] GRPO scripts
b80312c 
ghstack-source-id: 22a66ef
Pull-Request-resolved: #2970
@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented May 22, 2025 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2970

Note: Links to docs will display an error until the docs builds have been completed.

❌ 1 New Failure, 33 Pending

As of commit c0b8623 with merge base 023c965 (image):

NEW FAILURE - The following job has failed:

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label May 22, 2025
Update
4c3cbaf 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request May 22, 2025
[Algorithm] GRPO scripts
3447885 
ghstack-source-id: c1fad8d
Pull-Request-resolved: #2970
Update
2c3f757 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request May 22, 2025
[Algorithm] GRPO scripts
0dcee7b 
ghstack-source-id: 09cda67
Pull-Request-resolved: #2970
@vmoens vmoens added the new algo New algorithm request or PR label May 22, 2025
Update
995faa8 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request May 22, 2025
[Algorithm] GRPO scripts
b198877 
ghstack-source-id: a711348
Pull-Request-resolved: #2970
Update
6fce4e6 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request May 22, 2025
[Algorithm] GRPO scripts
af77c5a 
ghstack-source-id: 160d734
Pull-Request-resolved: #2970
Update
8a48708 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request May 22, 2025
[Algorithm] GRPO scripts
c7ecd98 
ghstack-source-id: b20e61e
Pull-Request-resolved: #2970
Update
b187eb2 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request May 22, 2025
[Algorithm] GRPO scripts
70918f2 
ghstack-source-id: 879f74a
Pull-Request-resolved: #2970
Update
0173e4b 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request May 22, 2025
[Algorithm] GRPO scripts
b9d55f5 
ghstack-source-id: 0741c8f
Pull-Request-resolved: #2970
Update
0a10089 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request May 22, 2025
[Algorithm] GRPO scripts
c3bcc90 
ghstack-source-id: 6a8fa1e
Pull-Request-resolved: #2970
Update
b5f0e8c 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request May 22, 2025
[Algorithm] GRPO scripts
faa948a 
ghstack-source-id: 6768b25
Pull-Request-resolved: #2970
Update
8f11a43 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request May 23, 2025
[Algorithm] GRPO scripts
664b1e3 
ghstack-source-id: 9308ae6
Pull-Request-resolved: #2970
Update
b565b27 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request May 23, 2025
[Algorithm] GRPO scripts
c365741 
ghstack-source-id: b3c20dd
Pull-Request-resolved: #2970
Update
938a338 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request May 23, 2025
[Algorithm] GRPO scripts
fa71ab7 
ghstack-source-id: 5bd176f
Pull-Request-resolved: #2970
Update
9734c79 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Jun 7, 2025
@vmoens
[Algorithm] GRPO scripts
d55f296 
ghstack-source-id: 05b32bf
Pull-Request-resolved: #2970
@vmoens
Update
e624ac1 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Jun 7, 2025
@vmoens
[Algorithm] GRPO scripts
44403a3 
ghstack-source-id: 6654235
Pull-Request-resolved: #2970
@vmoens
Update
85bc8de 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Jun 7, 2025
@vmoens
[Algorithm] GRPO scripts
1085ac7 
ghstack-source-id: df09d5f
Pull-Request-resolved: #2970
@vmoens
Update
bcfa77f 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Jun 7, 2025
@vmoens
[Algorithm] GRPO scripts
5258ca5 
ghstack-source-id: c47691d
Pull-Request-resolved: #2970
@vmoens
Update
dae84e2 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Jun 7, 2025
@vmoens
[Algorithm] GRPO scripts
c7cd519 
ghstack-source-id: 37e42fa
Pull-Request-resolved: #2970
@vmoens
Update
13e199f 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Jun 7, 2025
@vmoens
[Algorithm] GRPO scripts
efc4e47 
ghstack-source-id: ef81464
Pull-Request-resolved: #2970
@vmoens
Update
203365c 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Jun 7, 2025
@vmoens
[Algorithm] GRPO scripts
904a1e9 
ghstack-source-id: 03b33ea
Pull-Request-resolved: #2970
@vmoens
Update
ace577a 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Jun 7, 2025
@vmoens
[Algorithm] GRPO scripts
2ddf3f6 
ghstack-source-id: 4b80be9
Pull-Request-resolved: #2970
@vmoens
Update
fa89fc0 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Jun 7, 2025
@vmoens
[Algorithm] GRPO scripts
2de5c26 
ghstack-source-id: a5aa8e1
Pull-Request-resolved: #2970
@vmoens
Update
4def870 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Jun 7, 2025
@vmoens
[Algorithm] GRPO scripts
e5fe479 
ghstack-source-id: 4651d10
Pull-Request-resolved: #2970
@vmoens
Update
83f4285 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Jun 8, 2025
@vmoens
[Algorithm] GRPO scripts
003924e 
ghstack-source-id: d8ddac5
Pull-Request-resolved: #2970
@vmoens
Update
4428a6e 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Jun 8, 2025
@vmoens
[Algorithm] GRPO scripts
7696a58 
ghstack-source-id: e92bb2c
Pull-Request-resolved: #2970
@vmoens
Update
e46ce79 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Jun 8, 2025
@vmoens
[Algorithm] GRPO scripts
9c42192 
ghstack-source-id: d31ebb6
Pull-Request-resolved: #2970
@vmoens
Update
c0b8623 
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Jun 8, 2025
@vmoens
[Algorithm] GRPO scripts
3a728d3 
ghstack-source-id: 6acd4e3
Pull-Request-resolved: #2970
@vmoens vmoens merged commit c0b8623 into gh/vmoens/142/base Jun 8, 2025
77 of 87 checks passed
vmoens pushed a commit that referenced this pull request Jun 8, 2025
@vmoens
[Algorithm] GRPO scripts
c6440df 
ghstack-source-id: 6acd4e3
Pull-Request-resolved: #2970
@vmoens vmoens deleted the gh/vmoens/142/head branch June 8, 2025 01:06
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. new algo New algorithm request or PR
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@vmoens @facebook-github-bot