Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-kto-i0
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
00d8246
phi-2-kto-i0
/
runs
1 contributor
History:
52 commits
BraylonDash
Training in progress, step 1220
00d8246
verified
3 days ago
Sep27_16-14-25_gpu-119-0
Training in progress, step 100
4 days ago
Sep27_17-14-49_gpu4-119-5
Training in progress, step 280
3 days ago
Sep28_14-30-36_gpu4-119-5
Training in progress, step 280
3 days ago
Sep28_14-38-55_gpu4-119-5
Training in progress, step 380
3 days ago
Sep28_15-16-37_gpu4-119-5
Training in progress, step 680
3 days ago
Sep28_16-23-39_gpu4-119-5
Training in progress, step 780
3 days ago
Sep28_16-49-09_gpu4-119-5
Training in progress, step 860
3 days ago
Sep28_17-12-29_gpu4-119-5
Training in progress, step 860
3 days ago
Sep28_17-16-49_gpu4-119-5
Training in progress, step 1020
3 days ago
Sep28_17-55-57_gpu4-119-5
Training in progress, step 1220
3 days ago