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 / seed_2

Commit History

5 days ago

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

    LorenaYannnnn
    Verified signature
    42c9339

6 days ago

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

    LorenaYannnnn
    Verified signature
    7cb4e6e

  2. Current config schema; description.txt

    LorenaYannnnn
    Verified signature
    61dd52b

9 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

10 days ago

  1. Upload seed_2/misaligned_model/config.yaml with huggingface_hub

    LorenaYannnnn
    Verified signature
    d60ee5e

  2. Upload seed_2/control_model/config.yaml with huggingface_hub

    LorenaYannnnn
    Verified signature
    aa0686e