Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-kto-0-20-i1
like
0
Follow
DUAL Group
2
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
b828dac
phi-2-kto-0-20-i1
/
runs
/
Sep29_00-10-54_gpu4-119-5
1 contributor
History:
29 commits
BraylonDash
Training in progress, step 600
b828dac
verified
4 months ago
events.out.tfevents.1727533197.gpu4-119-5.124621.0
43.4 kB
LFS
Training in progress, step 600
4 months ago