Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
BraylonDash
/
phi-2-gpo-test-iter-0
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
License:
mit
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
0372e21
phi-2-gpo-test-iter-0
/
runs
1 contributor
History:
10 commits
BraylonDash
Model save
63b442d
verified
7 months ago
Mar19_12-45-07_Braylon
Model save
7 months ago
Mar19_13-57-28_Braylon
Model save
7 months ago
Mar19_14-05-25_Braylon
Model save
7 months ago
Mar19_14-11-36_Braylon
Model save
7 months ago
Mar19_14-21-21_Braylon
Model save
7 months ago
Mar19_14-26-24_Braylon
Model save
7 months ago
Mar19_14-42-17_Braylon
Model save
7 months ago
Mar19_14-44-38_Braylon
Model save
7 months ago
Mar19_14-53-05_Braylon
Model save
7 months ago
Mar19_14-55-26_Braylon
Model save
7 months ago
Mar19_15-00-46_Braylon
Model save
7 months ago
Mar19_15-03-13_Braylon
Model save
7 months ago
Mar19_15-10-26_Braylon
Model save
7 months ago