Hugging Face's logo

RL-Forgetting-Experiments-3
/
code-q25_3b-replay-lam0p1

Reinforcement Learning
Safetensors
grpo
code-generation
mbpp
catastrophic-forgetting
Model card Files
xet
 Community
code-q25_3b-replay-lam0p1

Commit History

  1. Add MBPP+ training-set eval pass@k summaries (10 checkpoints)

    smilani
    Verified signature
    99514a7

  1. qwen3b_mbpp_hardcd_lam0p1 global_step_300

    Evangelinejy
    Verified signature
    7c48d1e

  2. qwen3b_mbpp_hardcd_lam0p1 global_step_270

    Evangelinejy
    Verified signature
    06c1092

  3. qwen3b_mbpp_hardcd_lam0p1 global_step_240

    Evangelinejy
    Verified signature
    4e2eb5f

  4. qwen3b_mbpp_hardcd_lam0p1 global_step_210

    Evangelinejy
    Verified signature
    ad70d91

  5. qwen3b_mbpp_hardcd_lam0p1 global_step_180

    Evangelinejy
    Verified signature
    351f56a

  6. qwen3b_mbpp_hardcd_lam0p1 global_step_150

    Evangelinejy
    Verified signature
    d594f2f

  7. qwen3b_mbpp_hardcd_lam0p1 global_step_120

    Evangelinejy
    Verified signature
    bb53010

  8. qwen3b_mbpp_hardcd_lam0p1 global_step_90

    Evangelinejy
    Verified signature
    a692fbe

  9. qwen3b_mbpp_hardcd_lam0p1 global_step_60

    Evangelinejy
    Verified signature
    4d00947

  10. qwen3b_mbpp_hardcd_lam0p1 global_step_30

    Evangelinejy
    Verified signature
    9c44e26

  11. model card

    Evangelinejy
    Verified signature
    27c2cf0

  12. initial commit

    Evangelinejy
    Verified signature
    060c02a