Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v6-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
2a21b28
phi-2-gpo-v6-i1
Commit History
Training in progress, step 100
2a21b28
verified
lole25
commited on
May 15
End of training
72c121c
verified
lole25
commited on
May 12
Model save
3d2a338
verified
lole25
commited on
May 12
Training in progress, step 1300
2f2ba37
verified
lole25
commited on
May 12
Training in progress, step 1200
c0943bf
verified
lole25
commited on
May 12
Training in progress, step 1100
83793c3
verified
lole25
commited on
May 12
Training in progress, step 900
324006a
verified
lole25
commited on
May 12
Training in progress, step 800
a9a7771
verified
lole25
commited on
May 12
Training in progress, step 700
6bbb8b8
verified
lole25
commited on
May 12
Training in progress, step 600
db6daf5
verified
lole25
commited on
May 12
Training in progress, step 400
9eba6d8
verified
lole25
commited on
May 12
Training in progress, step 300
2ef8728
verified
lole25
commited on
May 12
Training in progress, step 200
c02dd03
verified
lole25
commited on
May 12
Training in progress, step 100
d882f13
verified
lole25
commited on
May 12
initial commit
44a4691
verified
lole25
commited on
May 12