Hugging Face's logo

hewittlab
/
monitor_cot_for_hack-baseline-coding-explicit_intent-gpt-oss-20b

Safetensors
tinker
lora
reward-hacking
chain-of-thought
monitorability
Model card Files
xet
 Community
1
monitor_cot_for_hack-baseline-coding-explicit_intent-gpt-oss-20b / seed_1

Commit History

8 days ago

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

    LorenaYannnnn
    Verified signature
    07f0500

9 days ago

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

    LorenaYannnnn
    Verified signature
    ab67836

  2. Current config schema; description.txt

    LorenaYannnnn
    Verified signature
    a8c3804

13 days ago

  1. seed_1/misaligned_model step 800 <- tinker://5d8867f7-e39a-5538-9b4e-e57f2811b7a6:train:0/weights/step_000800

    LorenaYannnnn
    Verified signature
    5e676cd

  2. seed_1/misaligned_model step 720 <- tinker://5d8867f7-e39a-5538-9b4e-e57f2811b7a6:train:0/weights/step_000720

    LorenaYannnnn
    Verified signature
    31e8b35

  3. seed_1/misaligned_model step 640 <- tinker://5d8867f7-e39a-5538-9b4e-e57f2811b7a6:train:0/weights/step_000640

    LorenaYannnnn
    Verified signature
    0d8cf87

  4. seed_1/misaligned_model step 560 <- tinker://5d8867f7-e39a-5538-9b4e-e57f2811b7a6:train:0/weights/step_000560

    LorenaYannnnn
    Verified signature
    ad9ad6a

  5. seed_1/misaligned_model step 480 <- tinker://5d8867f7-e39a-5538-9b4e-e57f2811b7a6:train:0/weights/step_000480

    LorenaYannnnn
    Verified signature
    347d269

  6. seed_1/misaligned_model step 400 <- tinker://5d8867f7-e39a-5538-9b4e-e57f2811b7a6:train:0/weights/step_000400

    LorenaYannnnn
    Verified signature
    9920a10

  7. seed_1/misaligned_model step 320 <- tinker://5d8867f7-e39a-5538-9b4e-e57f2811b7a6:train:0/weights/step_000320

    LorenaYannnnn
    Verified signature
    506f099

  8. seed_1/misaligned_model step 240 <- tinker://5d8867f7-e39a-5538-9b4e-e57f2811b7a6:train:0/weights/step_000240

    LorenaYannnnn
    Verified signature
    c8ab9fe

  9. seed_1/misaligned_model step 160 <- tinker://5d8867f7-e39a-5538-9b4e-e57f2811b7a6:train:0/weights/step_000160

    LorenaYannnnn
    Verified signature
    e9900fd

  10. seed_1/misaligned_model step 80 <- tinker://5d8867f7-e39a-5538-9b4e-e57f2811b7a6:train:0/weights/step_000080

    LorenaYannnnn
    Verified signature
    0257d46

  11. Upload seed_1/misaligned_model/config.yaml with huggingface_hub

    LorenaYannnnn
    Verified signature
    b35307a

  12. seed_1/control_model step 800 <- tinker://434608e0-a15f-583c-809e-045a13bf256a:train:0/weights/step_000800

    LorenaYannnnn
    Verified signature
    dca2b1d

  13. seed_1/control_model step 720 <- tinker://434608e0-a15f-583c-809e-045a13bf256a:train:0/weights/step_000720

    LorenaYannnnn
    Verified signature
    74828b0

  14. seed_1/control_model step 640 <- tinker://434608e0-a15f-583c-809e-045a13bf256a:train:0/weights/step_000640

    LorenaYannnnn
    Verified signature
    60aefe0

  15. seed_1/control_model step 560 <- tinker://434608e0-a15f-583c-809e-045a13bf256a:train:0/weights/step_000560

    LorenaYannnnn
    Verified signature
    e01ce6d

  16. seed_1/control_model step 480 <- tinker://434608e0-a15f-583c-809e-045a13bf256a:train:0/weights/step_000480

    LorenaYannnnn
    Verified signature
    6ac4021

  17. seed_1/control_model step 400 <- tinker://434608e0-a15f-583c-809e-045a13bf256a:train:0/weights/step_000400

    LorenaYannnnn
    Verified signature
    710384a

  18. seed_1/control_model step 320 <- tinker://434608e0-a15f-583c-809e-045a13bf256a:train:0/weights/step_000320

    LorenaYannnnn
    Verified signature
    17c5c42

  19. seed_1/control_model step 240 <- tinker://434608e0-a15f-583c-809e-045a13bf256a:train:0/weights/step_000240

    LorenaYannnnn
    Verified signature
    2f2280c

  20. seed_1/control_model step 160 <- tinker://434608e0-a15f-583c-809e-045a13bf256a:train:0/weights/step_000160

    LorenaYannnnn
    Verified signature
    4624fd2

  21. seed_1/control_model step 80 <- tinker://434608e0-a15f-583c-809e-045a13bf256a:train:0/weights/step_000080

    LorenaYannnnn
    Verified signature
    1e86494

  22. Upload seed_1/control_model/config.yaml with huggingface_hub

    LorenaYannnnn
    Verified signature
    bae09a0