sfulay
/

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

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

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

Commit History

Model save

bd38509
verified

sfulay commited on Sep 3

Training in progress, step 436

7b08247
verified

sfulay commited on Sep 3

Training in progress, step 400

03f77ed
verified

sfulay commited on Sep 3

Training in progress, step 300

3f979a2
verified

sfulay commited on Sep 2

Training in progress, step 200

89a8449
verified

sfulay commited on Sep 2

Training in progress, step 100

b54d083
verified

sfulay commited on Sep 2

initial commit

deeb6d9
verified

sfulay commited on Sep 2