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.

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

AttributeError: 'Qwen2ForCausalLM' object has no attribute 'optimizer' during GRPO training with ZERO-3 #2782

Open
5 tasks done
Co1lin opened this issue Feb 6, 2025 · 0 comments
Labels
🐛 bug Something isn't working 🏋 GRPO Related to GRPO

Comments

@Co1lin
Copy link

Co1lin commented Feb 6, 2025

Reproduction

See here, basically training qwen-2.5 models with GRPO using the latest trl library.

It is also mentioned here.

System Info

trl  0.15.0.dev0
transformers  4.49.0.dev0
deepspeed  0.16.3

Checklist

  • I have checked that my issue isn't already filed (see open issues)
  • I have included my system information
  • Any code provided is minimal, complete, and reproducible (more on MREs)
  • Any code provided is properly formatted in code blocks, (no screenshot, more on code blocks)
  • Any traceback provided is complete
@Co1lin Co1lin changed the title AttributeError: 'Qwen2ForCausalLM' object has no attribute 'optimizer' during DRPO training AttributeError: 'Qwen2ForCausalLM' object has no attribute 'optimizer' during GRPO training with ZERO-3 Feb 6, 2025
@github-actions github-actions bot added 🐛 bug Something isn't working 🏋 GRPO Related to GRPO labels Feb 6, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
🐛 bug Something isn't working 🏋 GRPO Related to GRPO
Projects
None yet
Development

No branches or pull requests

1 participant