Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-renew2-b0.001-v4-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
1
Use this model
62d8773
phi-2-gpo-renew2-b0.001-v4-i1
/
runs
/
Apr26_16-26-17_gpu4-119-5
1 contributor
History:
1 commit
BraylonDash
Training in progress, step 100
b356c83
verified
7 months ago
events.out.tfevents.1714112839.gpu4-119-5.1443627.0
Safe
4.85 kB
LFS
Training in progress, step 100
7 months ago