Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO-2
/
phi-2-gpo-v3-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
ca87756
phi-2-gpo-v3-i2
Commit History
End of training
ca87756
verified
lole25
commited on
May 17
Model save
15c03e5
verified
lole25
commited on
May 17
Training in progress, step 600
87cc17d
verified
lole25
commited on
May 17
Training in progress, step 400
b8e6b8a
verified
lole25
commited on
May 17
Training in progress, step 200
7ee2710
verified
lole25
commited on
May 17
Training in progress, step 100
f0497ad
verified
lole25
commited on
May 17
initial commit
00f580d
verified
lole25
commited on
May 17