Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v18-i1
like
0
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
dc344d8
phi-2-gpo-v18-i1
/
runs
/
May14_04-41-15_gpu4-119-5
1 contributor
History:
3 commits
lole25
Training in progress, step 300
e1e82c0
verified
5 months ago
events.out.tfevents.1715625823.gpu4-119-5.1052661.0
21.2 kB
LFS
Training in progress, step 300
5 months ago