Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-test-iter-0
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
7270627
phi-2-gpo-test-iter-0
/
trainer_state.json
Commit History
Model save
86bf3d3
verified
BraylonDash
commited on
Mar 20
Model save
27ac205
verified
BraylonDash
commited on
Mar 20
Model save
ca3bff4
verified
BraylonDash
commited on
Mar 20
Model save
a8a62f3
verified
BraylonDash
commited on
Mar 20
Model save
3de3973
verified
BraylonDash
commited on
Mar 20
Model save
23d0840
verified
BraylonDash
commited on
Mar 20
Model save
ad3638b
verified
BraylonDash
commited on
Mar 20