Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-newSFT-b0.001-renew-30k-i1
like
0
Follow
DUAL Group
2
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
main
phi-2-gpo-newSFT-b0.001-renew-30k-i1
Commit History
End of training
f7b8a57
verified
BraylonDash
commited on
May 14, 2024
Model save
0329836
verified
BraylonDash
commited on
May 14, 2024
Training in progress, step 1400
45b3b22
verified
BraylonDash
commited on
May 14, 2024
Training in progress, step 1300
a9e1d67
verified
BraylonDash
commited on
May 14, 2024
Training in progress, step 1100
622950d
verified
BraylonDash
commited on
May 14, 2024
Training in progress, step 1000
6d5c2b6
verified
BraylonDash
commited on
May 14, 2024
Training in progress, step 800
ec90679
verified
BraylonDash
commited on
May 14, 2024
Training in progress, step 700
5b82cfd
verified
BraylonDash
commited on
May 14, 2024
Training in progress, step 600
11f3e71
verified
BraylonDash
commited on
May 14, 2024
Training in progress, step 500
86567a0
verified
BraylonDash
commited on
May 14, 2024
Training in progress, step 400
04be21d
verified
BraylonDash
commited on
May 14, 2024
Training in progress, step 200
74a3893
verified
BraylonDash
commited on
May 14, 2024
Training in progress, step 100
55d6378
verified
BraylonDash
commited on
May 14, 2024
initial commit
b5fda08
verified
BraylonDash
commited on
May 14, 2024
BraylonDash
commited on
