Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO-2
/
phi-2-gpo-renew2-i0
like
0
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
4f984f1
phi-2-gpo-renew2-i0
/
runs
/
Apr09_13-55-32_gpu4-119-5
1 contributor
History:
38 commits
BraylonDash
Model save
2f18277
verified
5 months ago
events.out.tfevents.1712634984.gpu4-119-5.259196.0
276 kB
LFS
Model save
5 months ago
events.out.tfevents.1712691265.gpu4-119-5.259196.1
828 Bytes
LFS
Model save
5 months ago