Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-renew2-b0.001-vllm-merge-20k-complete-refSFT-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
Deploy
Use this model
main
phi-2-gpo-renew2-b0.001-vllm-merge-20k-complete-refSFT-i1
Commit History
End of training
85b0774
verified
BraylonDash
commited on
May 10, 2024
Model save
aabee42
verified
BraylonDash
commited on
May 10, 2024
Training in progress, step 1200
cf268a8
verified
BraylonDash
commited on
May 10, 2024
Training in progress, step 1100
af787ea
verified
BraylonDash
commited on
May 10, 2024
Training in progress, step 1000
aa934ae
verified
BraylonDash
commited on
May 10, 2024
Training in progress, step 800
8e849cf
verified
BraylonDash
commited on
May 10, 2024
Training in progress, step 700
6f33984
verified
BraylonDash
commited on
May 10, 2024
Training in progress, step 500
56b4495
verified
BraylonDash
commited on
May 10, 2024
Training in progress, step 400
0b6a752
verified
BraylonDash
commited on
May 10, 2024
Training in progress, step 300
b669620
verified
BraylonDash
commited on
May 10, 2024
Training in progress, step 200
07a038b
verified
BraylonDash
commited on
May 10, 2024
Training in progress, step 100
70d8c4c
verified
BraylonDash
commited on
May 10, 2024
initial commit
d9ac4b9
verified
BraylonDash
commited on
May 10, 2024
BraylonDash
commited on
