Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-20k-40k-60k-lora512-i2
like
0
Follow
DUAL Group
2
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-20k-40k-60k-lora512-i2
/
runs
/
May18_18-44-20_ip-10-192-15-31
1 contributor
History:
1 commit
BraylonDash
Model save
f61ddb0
verified
6 months ago
events.out.tfevents.1716058048.ip-10-192-15-31.2560.0
5.89 kB
LFS
Model save
6 months ago