Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-renew2-b0.001-vllm-merge-20k-complete-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-renew2-b0.001-vllm-merge-20k-complete-i1
Commit History
End of training
ba34175
verified
BraylonDash
commited on
May 8
Model save
cba029c
verified
BraylonDash
commited on
May 8
Training in progress, step 1100
28555e7
verified
BraylonDash
commited on
May 8
Training in progress, step 800
0afd7a7
verified
BraylonDash
commited on
May 8
Training in progress, step 700
2a7b41f
verified
BraylonDash
commited on
May 8
Training in progress, step 600
7597670
verified
BraylonDash
commited on
May 8
Training in progress, step 400
d98320b
verified
BraylonDash
commited on
May 8
Training in progress, step 300
acd6eca
verified
BraylonDash
commited on
May 8
initial commit
db2146d
verified
BraylonDash
commited on
May 8