deepagents-rl-coding / kaggle /train_grpo.py

Commit History

23 days ago

  1. TRL: inject text/JSON tool calls + forced ls into tool loop

    Verified signature
    c658700
  2. Force first tool + tool_choice required nudge

    Verified signature
    0ecc38b
  3. Fix Langfuse ckpt/heldout child trace_context

    Verified signature
    d5f40a1
  4. Smoke mode + detailed train entry

    Verified signature
    e1bfc06
  5. Add kaggle/train_grpo.py

    Verified signature
    dfbd12e
  6. Add kaggle/train_grpo.py

    Verified signature
    681342c
  7. Add kaggle/train_grpo.py

    Verified signature
    147b723
  8. Add kaggle/train_grpo.py

    Verified signature
    4b87130
  9. Add kaggle/train_grpo.py

    Verified signature
    f5cb9ca
  10. Add kaggle/train_grpo.py

    Verified signature
    a48afd7
  11. Add kaggle/train_grpo.py

    Verified signature
    488f5fc
  12. Add kaggle/train_grpo.py

    Verified signature
    deddf9f
  13. Add kaggle/train_grpo.py

    Verified signature
    7ca973d
  14. Add kaggle/train_grpo.py

    Verified signature
    5ee5b9f
  15. Add kaggle/train_grpo.py

    Verified signature
    aa44576
  16. Add kaggle/train_grpo.py

    Verified signature
    a4f498d
  17. Add kaggle/train_grpo.py

    Verified signature
    4a87f27
  18. Add kaggle/train_grpo.py

    Verified signature
    eb61e79
  19. Add kaggle/train_grpo.py

    Verified signature
    a54bfe0