Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO-2
/
phi-2-gpo-renew2-b0.001-extra-v2-i1
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
2190ad7
phi-2-gpo-renew2-b0.001-extra-v2-i1
/
runs
Commit History
Training in progress, step 1500
2190ad7
verified
BraylonDash
commited on
Apr 24
Training in progress, step 1400
5beaa95
verified
BraylonDash
commited on
Apr 24
Training in progress, step 1300
7378820
verified
BraylonDash
commited on
Apr 24
Training in progress, step 1200
66d98a8
verified
BraylonDash
commited on
Apr 24
Training in progress, step 1100
58c3fb9
verified
BraylonDash
commited on
Apr 24
Training in progress, step 1000
c04e760
verified
BraylonDash
commited on
Apr 24
Training in progress, step 900
d91f0c4
verified
BraylonDash
commited on
Apr 24
Training in progress, step 800
1e2388a
verified
BraylonDash
commited on
Apr 24
Training in progress, step 700
270e8b2
verified
BraylonDash
commited on
Apr 24
Training in progress, step 600
6f63015
verified
BraylonDash
commited on
Apr 24
Training in progress, step 500
2c21a7d
verified
BraylonDash
commited on
Apr 24
Training in progress, step 400
1387e72
verified
BraylonDash
commited on
Apr 24
Training in progress, step 300
85bfe42
verified
BraylonDash
commited on
Apr 24
Training in progress, step 200
d0504c4
verified
BraylonDash
commited on
Apr 24
Training in progress, step 100
140aece
verified
BraylonDash
commited on
Apr 24