Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-dpo-renew1
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
5f0ee0b
phi-2-dpo-renew1
/
runs
/
Apr09_11-23-20_gpu4-119-5
1 contributor
History:
39 commits
BraylonDash
Model save
783733b
verified
5 months ago
events.out.tfevents.1712626138.gpu4-119-5.200164.0
276 kB
LFS
Model save
5 months ago
events.out.tfevents.1712682927.gpu4-119-5.200164.1
828 Bytes
LFS
Model save
5 months ago