Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-kto-i0
like
0
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
7cf1c2a
phi-2-kto-i0
/
runs
/
Sep28_15-16-37_gpu4-119-5
/
events.out.tfevents.1727500646.gpu4-119-5.3937930.0
Commit History
Training in progress, step 640
7cf1c2a
verified
BraylonDash
commited on
4 days ago
Training in progress, step 620
2e1d364
verified
BraylonDash
commited on
4 days ago
Training in progress, step 600
2f580b5
verified
BraylonDash
commited on
4 days ago
Training in progress, step 560
384af49
verified
BraylonDash
commited on
4 days ago
Training in progress, step 540
ae3874e
verified
BraylonDash
commited on
4 days ago
Training in progress, step 520
8e1e3b9
verified
BraylonDash
commited on
4 days ago
Training in progress, step 500
efb32c5
verified
BraylonDash
commited on
4 days ago
Training in progress, step 480
f46a2ab
verified
BraylonDash
commited on
4 days ago
Training in progress, step 460
b15b390
verified
BraylonDash
commited on
4 days ago
Training in progress, step 440
f5e281d
verified
BraylonDash
commited on
4 days ago
Training in progress, step 420
0937855
verified
BraylonDash
commited on
4 days ago
Training in progress, step 400
2df2224
verified
BraylonDash
commited on
4 days ago
Training in progress, step 380
7fc02de
verified
BraylonDash
commited on
4 days ago