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
monitor_cot_for_hack-baseline-coding-explicit_intent-gpt-oss-20b / seed_2 /misaligned_model

Commit History

Today

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

    LorenaYannnnn
    Verified signature
    07f0500

Yesterday

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

    LorenaYannnnn
    Verified signature
    ab67836

  2. Current config schema; description.txt

    LorenaYannnnn
    Verified signature
    a8c3804

5 days ago

  1. seed_2/misaligned_model step 800 <- tinker://5c8be229-a16e-57e4-a07e-aa276a5f157f:train:0/weights/step_000800

    LorenaYannnnn
    Verified signature
    267472a

  2. seed_2/misaligned_model step 720 <- tinker://5c8be229-a16e-57e4-a07e-aa276a5f157f:train:0/weights/step_000720

    LorenaYannnnn
    Verified signature
    b2a8d93

  3. seed_2/misaligned_model step 640 <- tinker://5c8be229-a16e-57e4-a07e-aa276a5f157f:train:0/weights/step_000640

    LorenaYannnnn
    Verified signature
    76ac296

  4. seed_2/misaligned_model step 560 <- tinker://5c8be229-a16e-57e4-a07e-aa276a5f157f:train:0/weights/step_000560

    LorenaYannnnn
    Verified signature
    f1f50f8

  5. seed_2/misaligned_model step 480 <- tinker://5c8be229-a16e-57e4-a07e-aa276a5f157f:train:0/weights/step_000480

    LorenaYannnnn
    Verified signature
    d7ab5ac

  6. seed_2/misaligned_model step 400 <- tinker://5c8be229-a16e-57e4-a07e-aa276a5f157f:train:0/weights/step_000400

    LorenaYannnnn
    Verified signature
    589e0d9

  7. seed_2/misaligned_model step 320 <- tinker://5c8be229-a16e-57e4-a07e-aa276a5f157f:train:0/weights/step_000320

    LorenaYannnnn
    Verified signature
    7075919

  8. seed_2/misaligned_model step 240 <- tinker://5c8be229-a16e-57e4-a07e-aa276a5f157f:train:0/weights/step_000240

    LorenaYannnnn
    Verified signature
    b6f437a

  9. seed_2/misaligned_model step 160 <- tinker://5c8be229-a16e-57e4-a07e-aa276a5f157f:train:0/weights/step_000160

    LorenaYannnnn
    Verified signature
    4eb5112

  10. seed_2/misaligned_model step 80 <- tinker://5c8be229-a16e-57e4-a07e-aa276a5f157f:train:0/weights/step_000080

    LorenaYannnnn
    Verified signature
    19ba753

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

    LorenaYannnnn
    Verified signature
    146007b