Commit History

Today

  1. Save plain SFT/RL web-heavy__16m__reward_modeling

    Verified signature
    03dad9e
  2. Save plain SFT/RL baseline__16m__reward_modeling

    Verified signature
    135bab9
  3. Save plain SFT/RL math-heavy__8m__reward_modeling

    Verified signature
    9e74782
  4. Save plain SFT/RL code-heavy__64m__reward_modeling

    Verified signature
    39aa993
  5. Save plain SFT/RL code-heavy__32m__reward_modeling

    Verified signature
    db77417
  6. Save plain SFT/RL code-heavy__64m__reward_modeling

    Verified signature
    99a8523
  7. Save plain SFT/RL code-heavy__16m__reward_modeling

    Verified signature
    e64ebba
  8. Save plain SFT/RL code-heavy__32m__reward_modeling

    Verified signature
    c88d914
  9. Save plain SFT/RL chat-heavy__64m__reward_modeling

    Verified signature
    42f6e81
  10. Save plain SFT/RL code-heavy__16m__reward_modeling

    Verified signature
    de9562d
  11. Save plain SFT/RL code-heavy__8m__reward_modeling

    Verified signature
    c7f04f6
  12. Save plain SFT/RL code-heavy__8m__reward_modeling

    Verified signature
    baf031d
  13. Save plain SFT/RL web-heavy__32m__reward_modeling

    Verified signature
    2f57f45
  14. Save plain SFT/RL chat-heavy__16m__reward_modeling

    Verified signature
    022ffcf
  15. Save plain SFT/RL chat-heavy__8m__reward_modeling

    Verified signature
    76f468f
  16. Save plain SFT/RL math-heavy__64m__reward_modeling

    Verified signature
    3e4df43
  17. Save plain SFT/RL baseline__64m__reward_modeling

    Verified signature
    8b04b7f
  18. Save plain SFT/RL math-heavy__32m__reward_modeling

    Verified signature
    4fabb38
  19. Save plain SFT/RL math-heavy__16m__reward_modeling

    Verified signature
    77c7141
  20. Save plain SFT/RL baseline__32m__reward_modeling

    Verified signature
    3710cbd
  21. Save plain SFT/RL web-heavy__8m__reward_modeling

    Verified signature
    f3feb99
  22. Save plain SFT/RL web-heavy__16m__reward_modeling

    Verified signature
    5724113
  23. Save plain SFT/RL baseline__16m__reward_modeling

    Verified signature
    c368773
  24. Save plain SFT/RL baseline__8m__reward_modeling

    Verified signature
    ac21bc0
  25. initial commit

    Verified signature
    599202e