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 /control_model

Commit History

8 days ago

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

    LorenaYannnnn
    Verified signature
    42c9339

9 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

12 days ago

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

    LorenaYannnnn
    Verified signature
    1fa381d

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

    LorenaYannnnn
    Verified signature
    2e86e4a

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

    LorenaYannnnn
    Verified signature
    1665db1

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

    LorenaYannnnn
    Verified signature
    c9ab3f7

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

    LorenaYannnnn
    Verified signature
    faedb70