Hugging Face's logo

hewittlab
/
monitor_cot_for_hack-baseline-coding-explicit_intent-gpt-oss-120b

Safetensors
tinker
lora
reward-hacking
chain-of-thought
monitorability
Model card Files
xet
 Community
monitor_cot_for_hack-baseline-coding-explicit_intent-gpt-oss-120b

Commit History

3 days ago

  1. seed_2/misaligned_model step 800 <- tinker://3741c783-ddd3-5d14-b3bd-10b845c6ba62:train:0/weights/step_000800

    LorenaYannnnn
    Verified signature
    4b8b747

  2. seed_2/misaligned_model step 720 <- tinker://3741c783-ddd3-5d14-b3bd-10b845c6ba62:train:0/weights/step_000720

    LorenaYannnnn
    Verified signature
    9c4e30e

  3. seed_2/misaligned_model step 640 <- tinker://3741c783-ddd3-5d14-b3bd-10b845c6ba62:train:0/weights/step_000640

    LorenaYannnnn
    Verified signature
    e72fdc1

  4. seed_2/misaligned_model step 560 <- tinker://3741c783-ddd3-5d14-b3bd-10b845c6ba62:train:0/weights/step_000560

    LorenaYannnnn
    Verified signature
    55a0e30

  5. seed_2/misaligned_model step 480 <- tinker://3741c783-ddd3-5d14-b3bd-10b845c6ba62:train:0/weights/step_000480

    LorenaYannnnn
    Verified signature
    c96ff81

  6. seed_2/misaligned_model step 400 <- tinker://3741c783-ddd3-5d14-b3bd-10b845c6ba62:train:0/weights/step_000400

    LorenaYannnnn
    Verified signature
    6170286

  7. seed_2/misaligned_model step 320 <- tinker://3741c783-ddd3-5d14-b3bd-10b845c6ba62:train:0/weights/step_000320

    LorenaYannnnn
    Verified signature
    cddba83

  8. seed_2/misaligned_model step 240 <- tinker://3741c783-ddd3-5d14-b3bd-10b845c6ba62:train:0/weights/step_000240

    LorenaYannnnn
    Verified signature
    dd14d5f

  9. seed_2/misaligned_model step 160 <- tinker://3741c783-ddd3-5d14-b3bd-10b845c6ba62:train:0/weights/step_000160

    LorenaYannnnn
    Verified signature
    b2128e1

  10. seed_2/misaligned_model step 80 <- tinker://3741c783-ddd3-5d14-b3bd-10b845c6ba62:train:0/weights/step_000080

    LorenaYannnnn
    Verified signature
    2c50af4

  11. seed_2/control_model step 800 <- tinker://cfb2a76c-dd58-5d17-b910-5e4652062159:train:0/weights/step_000800

    LorenaYannnnn
    Verified signature
    28e65a5

  12. seed_2/control_model step 720 <- tinker://cfb2a76c-dd58-5d17-b910-5e4652062159:train:0/weights/step_000720

    LorenaYannnnn
    Verified signature
    4536813

  13. seed_2/control_model step 640 <- tinker://cfb2a76c-dd58-5d17-b910-5e4652062159:train:0/weights/step_000640

    LorenaYannnnn
    Verified signature
    5ca135e

  14. seed_2/control_model step 560 <- tinker://cfb2a76c-dd58-5d17-b910-5e4652062159:train:0/weights/step_000560

    LorenaYannnnn
    Verified signature
    5aa13db

  15. seed_2/control_model step 480 <- tinker://cfb2a76c-dd58-5d17-b910-5e4652062159:train:0/weights/step_000480

    LorenaYannnnn
    Verified signature
    884d9c8

  16. seed_2/control_model step 400 <- tinker://cfb2a76c-dd58-5d17-b910-5e4652062159:train:0/weights/step_000400

    LorenaYannnnn
    Verified signature
    d2d4f2a

  17. seed_2/control_model step 320 <- tinker://cfb2a76c-dd58-5d17-b910-5e4652062159:train:0/weights/step_000320

    LorenaYannnnn
    Verified signature
    c12efd4

  18. seed_2/control_model step 240 <- tinker://cfb2a76c-dd58-5d17-b910-5e4652062159:train:0/weights/step_000240

    LorenaYannnnn
    Verified signature
    5eececb

  19. seed_2/control_model step 160 <- tinker://cfb2a76c-dd58-5d17-b910-5e4652062159:train:0/weights/step_000160

    LorenaYannnnn
    Verified signature
    b36f859

  20. seed_2/control_model step 80 <- tinker://cfb2a76c-dd58-5d17-b910-5e4652062159:train:0/weights/step_000080

    LorenaYannnnn
    Verified signature
    309e799

  21. seed_1/misaligned_model step 800 <- tinker://b32abc6e-bb85-59ca-8c20-adcf92261a9a:train:0/weights/step_000800

    LorenaYannnnn
    Verified signature
    df8bc3a

  22. seed_1/misaligned_model step 720 <- tinker://b32abc6e-bb85-59ca-8c20-adcf92261a9a:train:0/weights/step_000720

    LorenaYannnnn
    Verified signature
    72eb54c

  23. seed_1/misaligned_model step 640 <- tinker://b32abc6e-bb85-59ca-8c20-adcf92261a9a:train:0/weights/step_000640

    LorenaYannnnn
    Verified signature
    f82c8a2

  24. seed_1/misaligned_model step 560 <- tinker://b32abc6e-bb85-59ca-8c20-adcf92261a9a:train:0/weights/step_000560

    LorenaYannnnn
    Verified signature
    9b2f5cc

  25. seed_1/misaligned_model step 480 <- tinker://b32abc6e-bb85-59ca-8c20-adcf92261a9a:train:0/weights/step_000480

    LorenaYannnnn
    Verified signature
    af86ea1

  26. seed_1/misaligned_model step 400 <- tinker://b32abc6e-bb85-59ca-8c20-adcf92261a9a:train:0/weights/step_000400

    LorenaYannnnn
    Verified signature
    b0459db

  27. seed_1/misaligned_model step 320 <- tinker://b32abc6e-bb85-59ca-8c20-adcf92261a9a:train:0/weights/step_000320

    LorenaYannnnn
    Verified signature
    a4f4e01

  28. seed_1/misaligned_model step 240 <- tinker://b32abc6e-bb85-59ca-8c20-adcf92261a9a:train:0/weights/step_000240

    LorenaYannnnn
    Verified signature
    1340ef6

  29. seed_1/misaligned_model step 160 <- tinker://b32abc6e-bb85-59ca-8c20-adcf92261a9a:train:0/weights/step_000160

    LorenaYannnnn
    Verified signature
    5b1c233

  30. seed_1/misaligned_model step 80 <- tinker://b32abc6e-bb85-59ca-8c20-adcf92261a9a:train:0/weights/step_000080

    LorenaYannnnn
    Verified signature
    23795a9

  31. seed_1/control_model step 800 <- tinker://b66586aa-6680-5f2e-b1c5-7108414da548:train:0/weights/step_000800

    LorenaYannnnn
    Verified signature
    1fa381d

  32. seed_1/control_model step 720 <- tinker://b66586aa-6680-5f2e-b1c5-7108414da548:train:0/weights/step_000720

    LorenaYannnnn
    Verified signature
    2e86e4a

  33. seed_1/control_model step 640 <- tinker://b66586aa-6680-5f2e-b1c5-7108414da548:train:0/weights/step_000640

    LorenaYannnnn
    Verified signature
    1665db1

  34. seed_1/control_model step 560 <- tinker://b66586aa-6680-5f2e-b1c5-7108414da548:train:0/weights/step_000560

    LorenaYannnnn
    Verified signature
    c9ab3f7

4 days ago

  1. seed_1/control_model step 480 <- tinker://b66586aa-6680-5f2e-b1c5-7108414da548:train:0/weights/step_000480

    LorenaYannnnn
    Verified signature
    c09323c

  2. seed_1/control_model step 400 <- tinker://b66586aa-6680-5f2e-b1c5-7108414da548:train:0/weights/step_000400

    LorenaYannnnn
    Verified signature
    5980738

  3. seed_1/control_model step 320 <- tinker://b66586aa-6680-5f2e-b1c5-7108414da548:train:0/weights/step_000320

    LorenaYannnnn
    Verified signature
    b9866ca

  4. seed_1/control_model step 240 <- tinker://b66586aa-6680-5f2e-b1c5-7108414da548:train:0/weights/step_000240

    LorenaYannnnn
    Verified signature
    e6659aa

  5. seed_1/control_model step 160 <- tinker://b66586aa-6680-5f2e-b1c5-7108414da548:train:0/weights/step_000160

    LorenaYannnnn
    Verified signature
    1475c00

  6. seed_1/control_model step 80 <- tinker://b66586aa-6680-5f2e-b1c5-7108414da548:train:0/weights/step_000080

    LorenaYannnnn
    Verified signature
    3a16557

  7. seed_0/misaligned_model step 800 <- tinker://eaaa02b7-672a-5378-a170-7bd38893a71c:train:0/weights/step_000800

    LorenaYannnnn
    Verified signature
    c644d65

  8. seed_0/misaligned_model step 720 <- tinker://eaaa02b7-672a-5378-a170-7bd38893a71c:train:0/weights/step_000720

    LorenaYannnnn
    Verified signature
    60dbf91

  9. seed_0/misaligned_model step 640 <- tinker://eaaa02b7-672a-5378-a170-7bd38893a71c:train:0/weights/step_000640

    LorenaYannnnn
    Verified signature
    3045d17

  10. seed_0/misaligned_model step 560 <- tinker://eaaa02b7-672a-5378-a170-7bd38893a71c:train:0/weights/step_000560

    LorenaYannnnn
    Verified signature
    fdd4071

  11. seed_0/misaligned_model step 480 <- tinker://eaaa02b7-672a-5378-a170-7bd38893a71c:train:0/weights/step_000480

    LorenaYannnnn
    Verified signature
    47098af

  12. seed_0/misaligned_model step 400 <- tinker://eaaa02b7-672a-5378-a170-7bd38893a71c:train:0/weights/step_000400

    LorenaYannnnn
    Verified signature
    5b2aee3

  13. seed_0/misaligned_model step 320 <- tinker://eaaa02b7-672a-5378-a170-7bd38893a71c:train:0/weights/step_000320

    LorenaYannnnn
    Verified signature
    7edfe1a

  14. seed_0/misaligned_model step 240 <- tinker://eaaa02b7-672a-5378-a170-7bd38893a71c:train:0/weights/step_000240

    LorenaYannnnn
    Verified signature
    19a8b75

  15. seed_0/misaligned_model step 160 <- tinker://eaaa02b7-672a-5378-a170-7bd38893a71c:train:0/weights/step_000160

    LorenaYannnnn
    Verified signature
    95985b4

  16. seed_0/misaligned_model step 80 <- tinker://eaaa02b7-672a-5378-a170-7bd38893a71c:train:0/weights/step_000080

    LorenaYannnnn
    Verified signature
    ec578fb