Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-20k-40k-60k-lora512-i2
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
f61ddb0
phi-2-gpo-20k-40k-60k-lora512-i2
/
runs
/
May18_13-37-52_ip-10-192-12-154
Commit History
Training in progress, step 100
4f91141
verified
BraylonDash
commited on
May 18