Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
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
ec53d03
phi-2-kto-i0
/
runs
/
Sep28_15-16-37_gpu4-119-5
Commit History
Training in progress, step 680
ef78dee
verified
BraylonDash
commited on
Sep 28
Training in progress, step 660
d191174
verified
BraylonDash
commited on
Sep 28
Training in progress, step 640
7cf1c2a
verified
BraylonDash
commited on
Sep 28
Training in progress, step 620
2e1d364
verified
BraylonDash
commited on
Sep 28
Training in progress, step 600
2f580b5
verified
BraylonDash
commited on
Sep 28
Training in progress, step 560
384af49
verified
BraylonDash
commited on
Sep 28
Training in progress, step 540
ae3874e
verified
BraylonDash
commited on
Sep 28
Training in progress, step 520
8e1e3b9
verified
BraylonDash
commited on
Sep 28
Training in progress, step 500
efb32c5
verified
BraylonDash
commited on
Sep 28
Training in progress, step 480
f46a2ab
verified
BraylonDash
commited on
Sep 28
Training in progress, step 460
b15b390
verified
BraylonDash
commited on
Sep 28
Training in progress, step 440
f5e281d
verified
BraylonDash
commited on
Sep 28
Training in progress, step 420
0937855
verified
BraylonDash
commited on
Sep 28
Training in progress, step 400
2df2224
verified
BraylonDash
commited on
Sep 28
Training in progress, step 380
7fc02de
verified
BraylonDash
commited on
Sep 28