Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO-2
/
phi-2-gpo-v35-i1
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
a92810a
phi-2-gpo-v35-i1
Commit History
Model save
a92810a
verified
lole25
commited on
May 16
Training in progress, step 900
7955a1d
verified
lole25
commited on
May 16
Training in progress, step 700
203406e
verified
lole25
commited on
May 16
Training in progress, step 600
ac72724
verified
lole25
commited on
May 16
Training in progress, step 500
a22294a
verified
lole25
commited on
May 16
Training in progress, step 400
1413a36
verified
lole25
commited on
May 16
Training in progress, step 300
df59127
verified
lole25
commited on
May 16
Training in progress, step 100
f1b29ce
verified
lole25
commited on
May 16
initial commit
87f326d
verified
lole25
commited on
May 16