Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v10-i1
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
main
phi-2-gpo-v10-i1
/
adapter_model.safetensors
Commit History
Model save
c35c185
verified
lole25
commited on
May 12
Training in progress, step 900
3231ff9
verified
lole25
commited on
May 12
Training in progress, step 800
207ade9
verified
lole25
commited on
May 12
Training in progress, step 600
7caf544
verified
lole25
commited on
May 12
Training in progress, step 500
e83dae7
verified
lole25
commited on
May 12
Training in progress, step 400
c069970
verified
lole25
commited on
May 12
Training in progress, step 300
abfab86
verified
lole25
commited on
May 12
Training in progress, step 200
e0477e0
verified
lole25
commited on
May 12
Training in progress, step 100
a7d4703
verified
lole25
commited on
May 12