Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-renew2-b0.001-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
47c7a97
phi-2-gpo-renew2-b0.001-i1
/
runs
/
Apr22_14-25-39_gpu4-119-5
1 contributor
History:
2 commits
BraylonDash
Model save
47c7a97
verified
3 months ago
events.out.tfevents.1713760022.gpu4-119-5.2990958.0
20 kB
LFS
Model save
3 months ago
events.out.tfevents.1713763154.gpu4-119-5.2990958.1
828 Bytes
LFS
Model save
3 months ago