Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v7-i1
like
0
Follow
DUAL Group
2
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-v7-i1
Commit History
End of training
a272054
verified
lole25
commited on
May 12, 2024
Model save
9c0f043
verified
lole25
commited on
May 12, 2024
Training in progress, step 600
79086a0
verified
lole25
commited on
May 12, 2024
Training in progress, step 500
218fc68
verified
lole25
commited on
May 12, 2024
Training in progress, step 400
83e4d58
verified
lole25
commited on
May 12, 2024
Training in progress, step 300
851f56e
verified
lole25
commited on
May 12, 2024
Training in progress, step 200
b70fdc0
verified
lole25
commited on
May 12, 2024
initial commit
4cfa77f
verified
lole25
commited on
May 12, 2024