Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO-2
/
phi-2-gpo-v6-i2
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
main
phi-2-gpo-v6-i2
/
adapter_model.safetensors
Commit History
Model save
48fc3f8
verified
lole25
commited on
May 18
Training in progress, step 600
29edf2c
verified
lole25
commited on
May 18
Training in progress, step 500
26ce781
verified
lole25
commited on
May 18
Training in progress, step 400
633e1be
verified
lole25
commited on
May 17
Training in progress, step 300
2d51a99
verified
lole25
commited on
May 17
Training in progress, step 200
14a85bd
verified
lole25
commited on
May 17
Training in progress, step 100
66e7401
verified
lole25
commited on
May 17