Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
zephyr-7b-gpo-v7-i3
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
main
zephyr-7b-gpo-v7-i3
/
runs
/
May15_10-27-10_gpu4-119-5
/
events.out.tfevents.1715732933.gpu4-119-5.2951744.0
Commit History
Model save
e582bc1
verified
lole25
commited on
May 15
Training in progress, step 1800
3124a9b
verified
lole25
commited on
May 15
Training in progress, step 1600
8aee000
verified
lole25
commited on
May 15
Training in progress, step 1500
8f429f9
verified
lole25
commited on
May 15
Training in progress, step 1400
417bde4
verified
lole25
commited on
May 15
Training in progress, step 1300
2a395db
verified
lole25
commited on
May 15
Training in progress, step 1100
39a110d
verified
lole25
commited on
May 15
Training in progress, step 500
3119895
verified
lole25
commited on
May 15
Training in progress, step 400
dc121d9
verified
lole25
commited on
May 15
Training in progress, step 300
bda3eaa
verified
lole25
commited on
May 15
Training in progress, step 100
80d4ebe
verified
lole25
commited on
May 15