Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-newSFT-b0.001-i1
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
main
phi-2-gpo-newSFT-b0.001-i1
/
runs
/
May11_17-21-22_gpu4-119-5
Commit History
Model save
7051ffb
verified
BraylonDash
commited on
May 11
Training in progress, step 1200
b572b6e
verified
BraylonDash
commited on
May 11
Training in progress, step 1100
50a57e9
verified
BraylonDash
commited on
May 11
Training in progress, step 1000
2c1363a
verified
BraylonDash
commited on
May 11
Training in progress, step 800
f3ac551
verified
BraylonDash
commited on
May 11
Training in progress, step 700
1658161
verified
BraylonDash
commited on
May 11
Training in progress, step 600
b83436e
verified
BraylonDash
commited on
May 11
Training in progress, step 500
8a27700
verified
BraylonDash
commited on
May 11
Training in progress, step 400
53e2456
verified
BraylonDash
commited on
May 11
Training in progress, step 300
aa3a6f7
verified
BraylonDash
commited on
May 11
Training in progress, step 200
d42693b
verified
BraylonDash
commited on
May 11
Training in progress, step 100
995e35d
verified
BraylonDash
commited on
May 11