Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-kto-i0
like
0
Follow
DUAL Group
2
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
b75b9f5
phi-2-kto-i0
/
runs
/
Sep28_14-38-55_gpu4-119-5
Commit History
Training in progress, step 380
7fc02de
verified
BraylonDash
commited on
Sep 28, 2024
Training in progress, step 360
925af30
verified
BraylonDash
commited on
Sep 28, 2024
Training in progress, step 340
f9feb84
verified
BraylonDash
commited on
Sep 28, 2024
Training in progress, step 320
b9fbc90
verified
BraylonDash
commited on
Sep 28, 2024
Training in progress, step 300
8ea3e65
verified
BraylonDash
commited on
Sep 28, 2024