Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-newSFT-b0.001-i0
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-newSFT-b0.001-i0
/
runs
/
May10_17-48-57_gpu4-119-5
/
events.out.tfevents.1715327400.gpu4-119-5.3130064.0
Commit History
Model save
7f721c2
verified
BraylonDash
commited on
May 10
Training in progress, step 1200
f3b6db4
verified
BraylonDash
commited on
May 10
Training in progress, step 1100
315d0d8
verified
BraylonDash
commited on
May 10
Training in progress, step 1000
b2418e1
verified
BraylonDash
commited on
May 10
Training in progress, step 900
15aa321
verified
BraylonDash
commited on
May 10
Training in progress, step 800
53ebf3a
verified
BraylonDash
commited on
May 10
Training in progress, step 700
5f6af5d
verified
BraylonDash
commited on
May 10
Training in progress, step 600
cfeec04
verified
BraylonDash
commited on
May 10
Training in progress, step 500
fa4267c
verified
BraylonDash
commited on
May 10
Training in progress, step 300
9e1ac1e
verified
BraylonDash
commited on
May 10
Training in progress, step 200
ff8e364
verified
BraylonDash
commited on
May 10
Training in progress, step 100
23a5ce1
verified
BraylonDash
commited on
May 10
