Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v20-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-v20-i1
Commit History
End of training
31ea247
verified
lole25
commited on
May 14, 2024
Model save
0e8bad8
verified
lole25
commited on
May 14, 2024
Training in progress, step 500
4d9d40e
verified
lole25
commited on
May 14, 2024
Training in progress, step 400
313879f
verified
lole25
commited on
May 14, 2024
Training in progress, step 300
ea7ed07
verified
lole25
commited on
May 14, 2024
Training in progress, step 200
e4b23b3
verified
lole25
commited on
May 14, 2024
Training in progress, step 100
c55027b
verified
lole25
commited on
May 14, 2024
initial commit
5cac266
verified
lole25
commited on
May 14, 2024