Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
zephyr-7b-gpo-v5-i1
like
0
Follow
DUAL Group
2
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
mit
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
8a0519c
zephyr-7b-gpo-v5-i1
/
runs
/
May07_07-49-30_gpu4-119-5
/
events.out.tfevents.1715032249.gpu4-119-5.2972564.0
Commit History
Training in progress, step 4800
8a0519c
verified
lole25
commited on
May 7
Training in progress, step 4600
e6b5114
verified
lole25
commited on
May 7
Training in progress, step 4500
82ebb32
verified
lole25
commited on
May 7
Training in progress, step 4100
3d2235e
verified
lole25
commited on
May 7
Training in progress, step 4000
c058472
verified
lole25
commited on
May 7
Training in progress, step 3900
c0d16e3
verified
lole25
commited on
May 7
Training in progress, step 3600
0ae8526
verified
lole25
commited on
May 7
Training in progress, step 3300
7190700
verified
lole25
commited on
May 7
Training in progress, step 3100
1b7c843
verified
lole25
commited on
May 6
Training in progress, step 3000
4f94c2e
verified
lole25
commited on
May 6
Training in progress, step 2700
02a7f4e
verified
lole25
commited on
May 6
Training in progress, step 2600
fe210d7
verified
lole25
commited on
May 6
Training in progress, step 2500
3ec4992
verified
lole25
commited on
May 6
Training in progress, step 2300
452c1e9
verified
lole25
commited on
May 6
Training in progress, step 2200
b5842bf
verified
lole25
commited on
May 6
Training in progress, step 2100
e487bcd
verified
lole25
commited on
May 6