Hugging Face's logo

hewittlab
/
monitor_cot_for_hack-baseline-length-implicit_intent-gpt-oss-20b

Safetensors
tinker
lora
reward-hacking
chain-of-thought
monitorability
Model card Files
xet
 Community
monitor_cot_for_hack-baseline-length-implicit_intent-gpt-oss-20b

Commit History

14 days ago

  1. config.yaml: outputs/baseline_training and outputs/reward_description_training

    LorenaYannnnn
    Verified signature
    1fa19cf

15 days ago

  1. config.yaml: drop eval_output_dir, no wandb entity

    LorenaYannnnn
    Verified signature
    c5fe374

  2. Current config schema; description.txt

    LorenaYannnnn
    Verified signature
    f5efae8

  3. Drop base-model download note from README

    LorenaYannnnn
    Verified signature
    c0ea9cf

18 days ago

  1. seed_2/misaligned_model step 120 <- tinker://0d4872db-d42d-51b2-96c7-5dbec8b8f198:train:0/weights/step_000120

    LorenaYannnnn
    Verified signature
    383ef29

  2. seed_2/misaligned_model step 110 <- tinker://0d4872db-d42d-51b2-96c7-5dbec8b8f198:train:0/weights/step_000110

    LorenaYannnnn
    Verified signature
    9252892

  3. seed_2/misaligned_model step 100 <- tinker://0d4872db-d42d-51b2-96c7-5dbec8b8f198:train:0/weights/step_000100

    LorenaYannnnn
    Verified signature
    9644656

  4. seed_2/misaligned_model step 90 <- tinker://0d4872db-d42d-51b2-96c7-5dbec8b8f198:train:0/weights/step_000090

    LorenaYannnnn
    Verified signature
    a1cdfd0

  5. seed_2/misaligned_model step 80 <- tinker://0d4872db-d42d-51b2-96c7-5dbec8b8f198:train:0/weights/step_000080

    LorenaYannnnn
    Verified signature
    202ca08

  6. seed_2/misaligned_model step 70 <- tinker://0d4872db-d42d-51b2-96c7-5dbec8b8f198:train:0/weights/step_000070

    LorenaYannnnn
    Verified signature
    ab71760

  7. seed_2/misaligned_model step 60 <- tinker://0d4872db-d42d-51b2-96c7-5dbec8b8f198:train:0/weights/step_000060

    LorenaYannnnn
    Verified signature
    f1333ab

  8. seed_2/misaligned_model step 50 <- tinker://0d4872db-d42d-51b2-96c7-5dbec8b8f198:train:0/weights/step_000050

    LorenaYannnnn
    Verified signature
    bdb5279

  9. seed_2/misaligned_model step 40 <- tinker://0d4872db-d42d-51b2-96c7-5dbec8b8f198:train:0/weights/step_000040

    LorenaYannnnn
    Verified signature
    2fc6852

  10. seed_2/misaligned_model step 30 <- tinker://0d4872db-d42d-51b2-96c7-5dbec8b8f198:train:0/weights/step_000030

    LorenaYannnnn
    Verified signature
    a0a562c

  11. seed_2/misaligned_model step 20 <- tinker://0d4872db-d42d-51b2-96c7-5dbec8b8f198:train:0/weights/step_000020

    LorenaYannnnn
    Verified signature
    9b6782d

  12. seed_2/misaligned_model step 10 <- tinker://0d4872db-d42d-51b2-96c7-5dbec8b8f198:train:0/weights/step_000010

    LorenaYannnnn
    Verified signature
    43207ee

  13. seed_2/control_model step 120 <- tinker://25ab4acb-2e42-5198-8f73-b3994c8f52e8:train:0/weights/step_000120

    LorenaYannnnn
    Verified signature
    377ef16

  14. seed_2/control_model step 110 <- tinker://25ab4acb-2e42-5198-8f73-b3994c8f52e8:train:0/weights/step_000110

    LorenaYannnnn
    Verified signature
    b40af91

  15. seed_2/control_model step 100 <- tinker://25ab4acb-2e42-5198-8f73-b3994c8f52e8:train:0/weights/step_000100

    LorenaYannnnn
    Verified signature
    88e29a4

  16. seed_2/control_model step 90 <- tinker://25ab4acb-2e42-5198-8f73-b3994c8f52e8:train:0/weights/step_000090

    LorenaYannnnn
    Verified signature
    95ce188

  17. seed_2/control_model step 80 <- tinker://25ab4acb-2e42-5198-8f73-b3994c8f52e8:train:0/weights/step_000080

    LorenaYannnnn
    Verified signature
    3d63199

  18. seed_2/control_model step 70 <- tinker://25ab4acb-2e42-5198-8f73-b3994c8f52e8:train:0/weights/step_000070

    LorenaYannnnn
    Verified signature
    9d0c4e0

  19. seed_2/control_model step 60 <- tinker://25ab4acb-2e42-5198-8f73-b3994c8f52e8:train:0/weights/step_000060

    LorenaYannnnn
    Verified signature
    5ac0381

  20. seed_2/control_model step 50 <- tinker://25ab4acb-2e42-5198-8f73-b3994c8f52e8:train:0/weights/step_000050

    LorenaYannnnn
    Verified signature
    85c1171

  21. seed_2/control_model step 40 <- tinker://25ab4acb-2e42-5198-8f73-b3994c8f52e8:train:0/weights/step_000040

    LorenaYannnnn
    Verified signature
    1cd39e4

  22. seed_2/control_model step 30 <- tinker://25ab4acb-2e42-5198-8f73-b3994c8f52e8:train:0/weights/step_000030

    LorenaYannnnn
    Verified signature
    99b8396

  23. seed_2/control_model step 20 <- tinker://25ab4acb-2e42-5198-8f73-b3994c8f52e8:train:0/weights/step_000020

    LorenaYannnnn
    Verified signature
    5ad454c

  24. seed_2/control_model step 10 <- tinker://25ab4acb-2e42-5198-8f73-b3994c8f52e8:train:0/weights/step_000010

    LorenaYannnnn
    Verified signature
    e67e24f

  25. seed_1/misaligned_model step 120 <- tinker://892e5c5a-20a8-5058-95c0-e57f9a927f41:train:0/weights/step_000120

    LorenaYannnnn
    Verified signature
    ab7a320

  26. seed_1/misaligned_model step 110 <- tinker://892e5c5a-20a8-5058-95c0-e57f9a927f41:train:0/weights/step_000110

    LorenaYannnnn
    Verified signature
    8bc6538

  27. seed_1/misaligned_model step 100 <- tinker://892e5c5a-20a8-5058-95c0-e57f9a927f41:train:0/weights/step_000100

    LorenaYannnnn
    Verified signature
    ecc1442

  28. seed_1/misaligned_model step 90 <- tinker://892e5c5a-20a8-5058-95c0-e57f9a927f41:train:0/weights/step_000090

    LorenaYannnnn
    Verified signature
    0a66e35

  29. seed_1/misaligned_model step 80 <- tinker://892e5c5a-20a8-5058-95c0-e57f9a927f41:train:0/weights/step_000080

    LorenaYannnnn
    Verified signature
    3f94834

  30. seed_1/misaligned_model step 70 <- tinker://892e5c5a-20a8-5058-95c0-e57f9a927f41:train:0/weights/step_000070

    LorenaYannnnn
    Verified signature
    6fc24a6

  31. seed_1/misaligned_model step 60 <- tinker://892e5c5a-20a8-5058-95c0-e57f9a927f41:train:0/weights/step_000060

    LorenaYannnnn
    Verified signature
    2be2e81

  32. seed_1/misaligned_model step 50 <- tinker://892e5c5a-20a8-5058-95c0-e57f9a927f41:train:0/weights/step_000050

    LorenaYannnnn
    Verified signature
    95f192e

  33. seed_1/misaligned_model step 40 <- tinker://892e5c5a-20a8-5058-95c0-e57f9a927f41:train:0/weights/step_000040

    LorenaYannnnn
    Verified signature
    44b1c59

  34. seed_1/misaligned_model step 30 <- tinker://892e5c5a-20a8-5058-95c0-e57f9a927f41:train:0/weights/step_000030

    LorenaYannnnn
    Verified signature
    8d16f24

  35. seed_1/misaligned_model step 20 <- tinker://892e5c5a-20a8-5058-95c0-e57f9a927f41:train:0/weights/step_000020

    LorenaYannnnn
    Verified signature
    43c8b40

  36. seed_1/misaligned_model step 10 <- tinker://892e5c5a-20a8-5058-95c0-e57f9a927f41:train:0/weights/step_000010

    LorenaYannnnn
    Verified signature
    f43a294

  37. seed_1/control_model step 120 <- tinker://274b5a8c-7232-5394-8211-3c7761fa7f10:train:0/weights/step_000120

    LorenaYannnnn
    Verified signature
    246d26b

  38. seed_1/control_model step 110 <- tinker://274b5a8c-7232-5394-8211-3c7761fa7f10:train:0/weights/step_000110

    LorenaYannnnn
    Verified signature
    af93210

  39. seed_1/control_model step 100 <- tinker://274b5a8c-7232-5394-8211-3c7761fa7f10:train:0/weights/step_000100

    LorenaYannnnn
    Verified signature
    f6d3c5c

  40. seed_1/control_model step 90 <- tinker://274b5a8c-7232-5394-8211-3c7761fa7f10:train:0/weights/step_000090

    LorenaYannnnn
    Verified signature
    ea73f3e

  41. seed_1/control_model step 80 <- tinker://274b5a8c-7232-5394-8211-3c7761fa7f10:train:0/weights/step_000080

    LorenaYannnnn
    Verified signature
    dc473f1

  42. seed_1/control_model step 70 <- tinker://274b5a8c-7232-5394-8211-3c7761fa7f10:train:0/weights/step_000070

    LorenaYannnnn
    Verified signature
    28f7129

  43. seed_1/control_model step 60 <- tinker://274b5a8c-7232-5394-8211-3c7761fa7f10:train:0/weights/step_000060

    LorenaYannnnn
    Verified signature
    ef93b05

  44. seed_1/control_model step 50 <- tinker://274b5a8c-7232-5394-8211-3c7761fa7f10:train:0/weights/step_000050

    LorenaYannnnn
    Verified signature
    0d00ac0

  45. seed_1/control_model step 40 <- tinker://274b5a8c-7232-5394-8211-3c7761fa7f10:train:0/weights/step_000040

    LorenaYannnnn
    Verified signature
    50e6d2d

  46. seed_1/control_model step 30 <- tinker://274b5a8c-7232-5394-8211-3c7761fa7f10:train:0/weights/step_000030

    LorenaYannnnn
    Verified signature
    980af82