Commit History

  1. Update model card for intermediate checkpoints

    Verified signature
    a79ceda
  2. Upload extrapolation intermediate checkpoints

    Verified signature
    469791c
  3. Add root model card

    yichenw
    816f61f
  4. Add OPD sweep eval artifacts

    yichenw
    d1d86a6
  5. Upload extrapolation artifact: 050302 OPD Ref-KL step20 score report

    Verified signature
    7d62058
  6. Upload extrapolation artifact: 050302 OPD Ref-KL step20 graph aggregate results

    Verified signature
    acacd48
  7. Upload extrapolation artifact: 050302 OPD Ref-KL step20 metrics

    Verified signature
    c31b45c
  8. Upload extrapolation artifact: 050302 OPD Ref-KL step20 summary JSON

    Verified signature
    3dd83c7
  9. Upload extrapolation artifact: 050302 OPD Ref-KL step20 summary CSV

    Verified signature
    2a92446
  10. Upload extrapolation model: 050302 OPD Ref-KL step180

    Verified signature
    65d4ccb
  11. Upload extrapolation model: 050302 OPD Ref-KL step160

    Verified signature
    29d79db
  12. Upload extrapolation model: 050302 OPD Ref-KL step140

    Verified signature
    2960516
  13. Upload extrapolation model: 050302 OPD Ref-KL step120

    Verified signature
    be0131c
  14. Upload extrapolation model: 050302 OPD Ref-KL step100

    Verified signature
    e4b48ba
  15. Upload extrapolation model: 050302 OPD Ref-KL step80

    Verified signature
    69b8302
  16. Upload extrapolation model: 050302 OPD Ref-KL step60

    Verified signature
    86e47e5
  17. Upload extrapolation model: 050302 OPD Ref-KL step40

    Verified signature
    f429906
  18. Upload extrapolation model: 050302 OPD Ref-KL step20

    Verified signature
    0de2862
  19. Upload extrapolation artifact: 050302 OPD Ref-KL OP13-20 step200 OOD per-sample graph results

    Verified signature
    a7364b5
  20. Upload extrapolation artifact: 050302 OPD Ref-KL OP13-20 step200 ID per-sample graph results

    Verified signature
    7ee795c
  21. Upload extrapolation artifact: 050302 RL OP15-20 step200 OOD per-sample graph results

    Verified signature
    d7c9e58
  22. Upload extrapolation artifact: 050302 RL OP15-20 step200 ID per-sample graph results

    Verified signature
    4a7d538
  23. Upload extrapolation artifact: 050302 RL OP13-20 step200 OOD per-sample graph results

    Verified signature
    d6721b6
  24. Upload extrapolation artifact: 050302 RL OP13-20 step200 ID per-sample graph results

    Verified signature
    ac266d7
  25. Upload extrapolation artifact: 050302 RL OP11-14 step200 OOD per-sample graph results

    Verified signature
    6b8f8a8
  26. Upload extrapolation artifact: 050302 RL OP11-14 step200 ID per-sample graph results

    Verified signature
    af91f4a
  27. Upload extrapolation artifact: 050302 pretrain checkpoint-18586 OOD per-sample graph results

    Verified signature
    e8b7725
  28. Upload extrapolation artifact: 050302 pretrain checkpoint-18586 ID per-sample graph results

    Verified signature
    541567d
  29. Upload extrapolation artifact: 020305 OPD Ref-KL OP11-14 step200 OOD per-sample graph results

    Verified signature
    5bf85b3
  30. Upload extrapolation artifact: 020305 OPD Ref-KL OP11-14 step200 ID per-sample graph results

    Verified signature
    060b169
  31. Upload extrapolation artifact: 020305 RL OP15-20 step200 OOD per-sample graph results

    Verified signature
    782aded
  32. Upload extrapolation artifact: 020305 RL OP15-20 step200 ID per-sample graph results

    Verified signature
    7823903
  33. Upload extrapolation artifact: 020305 RL OP13-20 step200 OOD per-sample graph results

    Verified signature
    2ca16b8
  34. Upload extrapolation artifact: 020305 RL OP13-20 step200 ID per-sample graph results

    Verified signature
    e0e1654
  35. Upload extrapolation artifact: 020305 RL OP11-14 step200 OOD per-sample graph results

    Verified signature
    69742ff
  36. Upload extrapolation artifact: 020305 RL OP11-14 step200 ID per-sample graph results

    Verified signature
    09e9ffc
  37. Upload extrapolation artifact: 020305 pretrain checkpoint-18809 OOD per-sample graph results

    Verified signature
    6eb08a7
  38. Upload extrapolation artifact: 020305 pretrain checkpoint-18809 ID per-sample graph results

    Verified signature
    8c8a3bc
  39. Upload extrapolation artifact: opd_ckpt18809_refkl_op11_14_s200_merged_hf far-OOD generations

    Verified signature
    21168a1
  40. Upload extrapolation artifact: rl_ckpt18809_op11_14_step200_merged_hf far-OOD generations

    Verified signature
    4468aae
  41. Upload extrapolation artifact: pretrain_ckpt18809 far-OOD generations

    Verified signature
    db0a617
  42. Upload extrapolation artifact: 050302 OPD Ref-KL OP13-20 step200 OOD generations

    Verified signature
    b823521
  43. Upload extrapolation artifact: 050302 OPD Ref-KL OP13-20 step200 ID generations

    Verified signature
    e10251a
  44. Upload extrapolation artifact: 050302 RL OP15-20 step200 OOD generations

    Verified signature
    7b90e5a
  45. Upload extrapolation artifact: 050302 RL OP15-20 step200 ID generations

    Verified signature
    3c71c9b
  46. Upload extrapolation artifact: 050302 RL OP13-20 step200 OOD generations

    Verified signature
    c2411d4
  47. Upload extrapolation artifact: 050302 RL OP13-20 step200 ID generations

    Verified signature
    5283d4f
  48. Upload extrapolation artifact: 050302 RL OP11-14 step200 OOD generations

    Verified signature
    4d2fc67
  49. Upload extrapolation artifact: 050302 RL OP11-14 step200 ID generations

    Verified signature
    0341646
  50. Upload extrapolation artifact: 050302 pretrain checkpoint-18586 OOD generations

    Verified signature
    3774fa5