Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO-2
/
phi-2-gpo-renew2-b0.001-v2-i1
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
7643338
phi-2-gpo-renew2-b0.001-v2-i1
/
runs
/
Apr22_16-59-25_gpu4-119-5
1 contributor
History:
1 commit
BraylonDash
Training in progress, step 100
7643338
verified
6 months ago
events.out.tfevents.1713769246.gpu4-119-5.3043320.0
12.4 kB
LFS
Training in progress, step 100
6 months ago