Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-test-longest-iter-0
like
0
Follow
DUAL Group
2
PEFT
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
License:
mit
Model card
Files
Files and versions
Community
Use this model
c34600d
phi-2-gpo-test-longest-iter-0
Commit History
End of training
c34600d
verified
BraylonDash
commited on
Mar 21
Model save
79d9d19
verified
BraylonDash
commited on
Mar 21
Training in progress, step 100
de0b05c
verified
BraylonDash
commited on
Mar 21
End of training
ed8be06
verified
BraylonDash
commited on
Mar 20
Model save
c10ebbf
verified
BraylonDash
commited on
Mar 20
End of training
356743e
verified
BraylonDash
commited on
Mar 20
Model save
a534c44
verified
BraylonDash
commited on
Mar 20
End of training
1ba2d9f
verified
BraylonDash
commited on
Mar 20
Model save
aa84d88
verified
BraylonDash
commited on
Mar 20
End of training
a7e3cda
verified
BraylonDash
commited on
Mar 20
Model save
dca548a
verified
BraylonDash
commited on
Mar 20
End of training
c4868ba
verified
BraylonDash
commited on
Mar 20
Model save
26d21df
verified
BraylonDash
commited on
Mar 20
End of training
7c1e52e
verified
BraylonDash
commited on
Mar 20
Model save
7648e22
verified
BraylonDash
commited on
Mar 20
initial commit
6444689
verified
BraylonDash
commited on
Mar 20
BraylonDash
commited on
