Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-ipo-chatml-lora-40k-60k-i2
like
0
Follow
DUAL Group
2
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
main
phi-2-ipo-chatml-lora-40k-60k-i2
/
adapter_model.safetensors
Commit History
Model save
7324230
verified
BraylonDash
commited on
Sep 17
Training in progress, step 1200
939440e
verified
BraylonDash
commited on
Sep 17
Training in progress, step 1100
830d47a
verified
BraylonDash
commited on
Sep 17
Training in progress, step 1000
2a4c86b
verified
BraylonDash
commited on
Sep 17
Training in progress, step 900
7e5bb86
verified
BraylonDash
commited on
Sep 17
Training in progress, step 800
837d676
verified
BraylonDash
commited on
Sep 17
Training in progress, step 500
695f2db
verified
BraylonDash
commited on
Sep 17
Training in progress, step 400
b91bfe6
verified
BraylonDash
commited on
Sep 17
Training in progress, step 300
85e9fce
verified
BraylonDash
commited on
Sep 17
Training in progress, step 200
c9a78be
verified
BraylonDash
commited on
Sep 17
Training in progress, step 100
2e3f778
verified
BraylonDash
commited on
Sep 17