sfulay
/

zephyr-7b-dpo-full-ultrabin-high-margin-3-epochs

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

zephyr-7b-dpo-full-ultrabin-high-margin-3-epochs / model-00001-of-00003.safetensors

Commit History

Training in progress, step 429

7ebedb9
verified

sfulay commited on Aug 9

Training in progress, step 400

f19c357
verified

sfulay commited on Aug 9

Training in progress, step 300

8a9fc1f
verified

sfulay commited on Aug 9

Training in progress, step 200

2c8054d
verified

sfulay commited on Aug 9

Training in progress, step 100

82b0d50
verified

sfulay commited on Aug 9