Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v25-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
fa95666
phi-2-gpo-v25-i1
Commit History
End of training
fa95666
verified
lole25
commited on
May 15
Model save
25a262a
verified
lole25
commited on
May 15
Training in progress, step 300
3f08b69
verified
lole25
commited on
May 15
Training in progress, step 200
2af0351
verified
lole25
commited on
May 15
Training in progress, step 100
55ef435
verified
lole25
commited on
May 15
initial commit
5af89a6
verified
lole25
commited on
May 15