Hugging Face's logo

MeowFR
/
mistral-7b-humanization-grpo-v4-stable

Reinforcement Learning
Transformers
PyTorch
Safetensors
trl
ppo
Model card Files
xet
 Community
mistral-7b-humanization-grpo-v4-stable / pytorch_model.bin

Commit History

  1. Step 960 MA=0.690

    MeowFR
    Verified signature
    b1ec08d

  2. Step 900 MA=0.695

    MeowFR
    Verified signature
    e1d53cc

  3. Step 800 MA=0.670

    MeowFR
    Verified signature
    db0a51a

  4. Step 700 MA=0.656

    MeowFR
    Verified signature
    13b0f54

  5. Step 600 MA=0.663

    MeowFR
    Verified signature
    b680204

  6. Step 500 MA=0.643

    MeowFR
    Verified signature
    b6a0bcb

  7. Step 400 MA=0.665

    MeowFR
    Verified signature
    0a7e75c

  1. Step 300 MA=0.648

    MeowFR
    Verified signature
    909d74b

  2. Step 200 MA=0.657

    MeowFR
    Verified signature
    889d8d2

  3. Step 100 MA=0.665

    MeowFR
    Verified signature
    a13a7e5