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_1 /misaligned_model

Commit History

Yesterday

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

    LorenaYannnnn
    Verified signature
    42c9339

2 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

5 days ago

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

    LorenaYannnnn
    Verified signature
    df8bc3a

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

    LorenaYannnnn
    Verified signature
    72eb54c

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

    LorenaYannnnn
    Verified signature
    f82c8a2

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

    LorenaYannnnn
    Verified signature
    9b2f5cc

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

    LorenaYannnnn
    Verified signature
    af86ea1

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

    LorenaYannnnn
    Verified signature
    b0459db

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

    LorenaYannnnn
    Verified signature
    a4f4e01

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

    LorenaYannnnn
    Verified signature
    1340ef6

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

    LorenaYannnnn
    Verified signature
    5b1c233

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

    LorenaYannnnn
    Verified signature
    23795a9

6 days ago

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

    LorenaYannnnn
    Verified signature
    4405d6b