sfulay
/

zephyr-7b-dpo-full-ultrabin-reward-scale-05

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

zephyr-7b-dpo-full-ultrabin-reward-scale-05

Commit History

End of training

62601f5
verified

sfulay commited on Aug 8

Model save

8e960b5
verified

sfulay commited on Aug 8

Training in progress, step 478

e8d5292
verified

sfulay commited on Aug 8

Training in progress, step 400

e1d4a91
verified

sfulay commited on Aug 8

Training in progress, step 300

17bad86
verified

sfulay commited on Aug 8

Training in progress, step 100

9f0794a
verified

sfulay commited on Aug 7

initial commit

e8d7763
verified

sfulay commited on Aug 3