Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-newSFT-b0.001-15k-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-newSFT-b0.001-15k-i1
/
adapter_model.safetensors
Commit History
Model save
4cbd7b3
verified
BraylonDash
commited on
May 11
Training in progress, step 900
fd2f7d0
verified
BraylonDash
commited on
May 11
Training in progress, step 800
292e301
verified
BraylonDash
commited on
May 11
Training in progress, step 700
11cf9b6
verified
BraylonDash
commited on
May 11
Training in progress, step 500
c729f0b
verified
BraylonDash
commited on
May 11
Training in progress, step 400
fed9e56
verified
BraylonDash
commited on
May 11
Training in progress, step 300
0888587
verified
BraylonDash
commited on
May 11
Training in progress, step 200
22db4c5
verified
BraylonDash
commited on
May 11
Training in progress, step 100
0733f76
verified
BraylonDash
commited on
May 11