Skip to content
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

Unable to reproduce the performance of "mathematical reasoning" #223

Open
jasonaidm opened this issue Feb 7, 2025 · 0 comments
Open

Unable to reproduce the performance of "mathematical reasoning" #223

jasonaidm opened this issue Feb 7, 2025 · 0 comments

Comments

@jasonaidm
Copy link

Hi,
Thanks for your effort!

I cannot reproduce the performance of "mathematical reasoning" when I using the command:
ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/zero2.yaml --num_processes=7 src/open_r1/grpo.py --config recipes/deepseek/DeepSeek-R1-Distill-Qwen-7B/grpo/config_base_math_smalllr.yaml

The training curve is as follows：

Image
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@jasonaidm