Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v3-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-v3-i1
/
runs
Commit History
Model save
4969246
verified
lole25
commited on
May 12
Training in progress, step 600
a976a8a
verified
lole25
commited on
May 12
Training in progress, step 400
11c30e4
verified
lole25
commited on
May 12
Training in progress, step 300
30c5675
verified
lole25
commited on
May 12
Training in progress, step 100
8a5eeeb
verified
lole25
commited on
May 12