Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v5-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-v5-i1
Commit History
End of training
45d1ea0
verified
lole25
commited on
May 12
Model save
9b945ab
verified
lole25
commited on
May 12
Training in progress, step 600
7efea8a
verified
lole25
commited on
May 12
Training in progress, step 500
cec83e6
verified
lole25
commited on
May 12
Training in progress, step 400
1696c4c
verified
lole25
commited on
May 12
Training in progress, step 300
035df45
verified
lole25
commited on
May 12
Training in progress, step 100
0bde179
verified
lole25
commited on
May 12
initial commit
668ef0b
verified
lole25
commited on
May 12