sfulay
/

zephyr-7b-dpo-full-ultrabin-reward-scale-01

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

zephyr-7b-dpo-full-ultrabin-reward-scale-01 / model-00003-of-00003.safetensors

Commit History

Training in progress, step 478

c8790c2
verified

sfulay commited on Aug 8

Training in progress, step 400

fe5df90
verified

sfulay commited on Aug 8

Training in progress, step 300

e539826
verified

sfulay commited on Aug 8

Training in progress, step 200

19b6e31
verified

sfulay commited on Aug 8

Training in progress, step 100

f62f449
verified

sfulay commited on Aug 8