Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO-2
/
phi-2-gpo-v37-i1
like
0
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
main
phi-2-gpo-v37-i1
/
runs
Commit History
Model save
be27de9
verified
lole25
commited on
May 17
Training in progress, step 900
521c4e1
verified
lole25
commited on
May 17
Training in progress, step 800
0ac383f
verified
lole25
commited on
May 17
Training in progress, step 700
9ee7331
verified
lole25
commited on
May 17
Training in progress, step 600
575b612
verified
lole25
commited on
May 17
Training in progress, step 500
4bebd6b
verified
lole25
commited on
May 16
Training in progress, step 400
3357e19
verified
lole25
commited on
May 16
Training in progress, step 300
198928f
verified
lole25
commited on
May 16
Training in progress, step 200
2fc7106
verified
lole25
commited on
May 16
Training in progress, step 100
470222d
verified
lole25
commited on
May 16