EllieS
/

zephyr-7b-dpo-lora-ultrafeedback

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-dpo-lora-ultrafeedback / runs /Jan15_16-46-47_hrsung-a100-b

Commit History

Model save

87d88a2
verified

EllieS commited on Jan 16

Training in progress, step 4500

9c47bb3
verified

EllieS commited on Jan 16

Training in progress, step 3500

2979816
verified

EllieS commited on Jan 16

Training in progress, step 1500

cc34ad2
verified

EllieS commited on Jan 15

Training in progress, step 1000

c497384
verified

EllieS commited on Jan 15

Training in progress, step 500

d952c6f
verified

EllieS commited on Jan 15