Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Posts
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

DrishtiSharma
/
dolphin-2.1-mistral-7b-dpo-ultrafeedback-binarized-preferences-ipo

PEFT
TensorBoard
Safetensors
trl
dpo
Generated from Trainer
Model card Files Files and versions Metrics Training metrics Community
dolphin-2.1-mistral-7b-dpo-ultrafeedback-binarized-preferences-ipo / runs /Feb22_14-08-12_2187d9e528a5
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
DrishtiSharma's picture
DrishtiSharma
Training in progress, step 500
65f3aec verified about 1 year ago
  • events.out.tfevents.1708610990.2187d9e528a5.3558.0
    17.5 kB
    LFS
    Training in progress, step 500 about 1 year ago