Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v23-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
Use this model
main
phi-2-gpo-v23-i1
/
runs
/
May15_02-45-37_gpu4-119-5
/
events.out.tfevents.1715705213.gpu4-119-5.2308029.0
Commit History
Model save
e61fd83
verified
lole25
commited on
May 14
Training in progress, step 500
37b7536
verified
lole25
commited on
May 14
Training in progress, step 400
49c5c21
verified
lole25
commited on
May 14
Training in progress, step 300
16cdfcb
verified
lole25
commited on
May 14
Training in progress, step 200
509fdf3
verified
lole25
commited on
May 14
Training in progress, step 100
a028690
verified
lole25
commited on
May 14