Hugging Face's logo

ale-bay
/
zephyr-7b-dpo-qlora

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
zephyr-7b-dpo-qlora / runs /Mar07_10-37-47_ale-dpo-1-0-0

Commit History

End of training
fdadbc0
verified

ale-bay commited on

Model save
d304fa9
verified

ale-bay commited on

Training in progress, step 1900
4eb9c1b
verified

ale-bay commited on

Training in progress, step 1800
ff780c9
verified

ale-bay commited on

Training in progress, step 1700
f177721
verified

ale-bay commited on

Training in progress, step 1600
0d255bf
verified

ale-bay commited on

Training in progress, step 1500
5806036
verified

ale-bay commited on

Training in progress, step 1400
bd7e89e
verified

ale-bay commited on

Training in progress, step 1300
f8c00fc
verified

ale-bay commited on

Training in progress, step 1100
47f1eda
verified

ale-bay commited on

Training in progress, step 1000
fdc8fa8
verified

ale-bay commited on

Training in progress, step 900
f78d939
verified

ale-bay commited on

Training in progress, step 800
3b2e00f
verified

ale-bay commited on

Training in progress, step 700
50d8b97
verified

ale-bay commited on

Training in progress, step 600
41d78ef
verified

ale-bay commited on

Training in progress, step 500
0213964
verified

ale-bay commited on

Training in progress, step 400
6c6f29b
verified

ale-bay commited on

Training in progress, step 300
d7005f4
verified

ale-bay commited on

Training in progress, step 200
95a80b3
verified

ale-bay commited on

Training in progress, step 100
8683198
verified

ale-bay commited on