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
d189836
phi-2-gpo-v18-i1
/
adapter_model.safetensors
Commit History
Model save
8214ff1
verified
lole25
commited on
May 14
Training in progress, step 900
2313d45
verified
lole25
commited on
May 14
Training in progress, step 800
30d001e
verified
lole25
commited on
May 14
Training in progress, step 700
dc344d8
verified
lole25
commited on
May 14
Training in progress, step 600
08cad84
verified
lole25
commited on
May 14
Training in progress, step 400
cf8280e
verified
lole25
commited on
May 14
Training in progress, step 300
e1e82c0
verified
lole25
commited on
May 13
Training in progress, step 200
32c4106
verified
lole25
commited on
May 13
Training in progress, step 100
4ff24db
verified
lole25
commited on
May 13