Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO-2
/
phi-2-irepo-chatml-v21-i1
like
0
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-irepo-chatml-v21-i1
Commit History
End of training
24781c8
verified
lole25
commited on
May 21
Model save
c4c592e
verified
lole25
commited on
May 21
Training in progress, step 900
5797199
verified
lole25
commited on
May 21
Training in progress, step 800
ec67c76
verified
lole25
commited on
May 21
Training in progress, step 700
ab0fc0a
verified
lole25
commited on
May 21
Training in progress, step 600
cfaadb3
verified
lole25
commited on
May 21
Training in progress, step 500
20b4b43
verified
lole25
commited on
May 21
Training in progress, step 400
7894c4b
verified
lole25
commited on
May 21
Training in progress, step 300
50c862d
verified
lole25
commited on
May 21
Training in progress, step 200
d3c08e0
verified
lole25
commited on
May 21
Training in progress, step 100
2bcd39e
verified
lole25
commited on
May 21
initial commit
0b01708
verified
lole25
commited on
May 21
lole25
commited on
