Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v24-i1
like
0
Follow
DUAL Group
2
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
main
phi-2-gpo-v24-i1
Commit History
End of training
8a6263b
verified
lole25
commited on
May 14
Model save
378741a
verified
lole25
commited on
May 14
Training in progress, step 500
b46b743
verified
lole25
commited on
May 14
Training in progress, step 400
9c0c4d9
verified
lole25
commited on
May 14
Training in progress, step 200
eaad7c2
verified
lole25
commited on
May 14
Training in progress, step 100
508ce2d
verified
lole25
commited on
May 14
initial commit
167f3cd
verified
lole25
commited on
May 14