Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-v14-i1
like
0
Follow
DUAL Group
2
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
f485a3e
phi-2-gpo-v14-i1
Commit History
End of training
f485a3e
verified
lole25
commited on
May 13
Model save
62e2276
verified
lole25
commited on
May 13
Training in progress, step 1800
f570a60
verified
lole25
commited on
May 13
Training in progress, step 1700
92cce56
verified
lole25
commited on
May 13
Training in progress, step 1600
51b6be8
verified
lole25
commited on
May 13
Training in progress, step 1500
365777f
verified
lole25
commited on
May 13
Training in progress, step 1400
d46b3a6
verified
lole25
commited on
May 13
Training in progress, step 1200
0062820
verified
lole25
commited on
May 13
Training in progress, step 1100
5f141c3
verified
lole25
commited on
May 13
Training in progress, step 1000
4e9365c
verified
lole25
commited on
May 13
Training in progress, step 900
7d26d6e
verified
lole25
commited on
May 13
Training in progress, step 800
a324def
verified
lole25
commited on
May 13
Training in progress, step 700
526c6b1
verified
lole25
commited on
May 13
Training in progress, step 600
d3ce492
verified
lole25
commited on
May 13
Training in progress, step 500
1f48b9a
verified
lole25
commited on
May 13
Training in progress, step 400
07afd6c
verified
lole25
commited on
May 13
Training in progress, step 300
3702f42
verified
lole25
commited on
May 13
Training in progress, step 200
705bd86
verified
lole25
commited on
May 13
initial commit
49e3e9e
verified
lole25
commited on
May 13
lole25
commited on
