chanchan7
/

llama-7b-dpo-qlora-relu

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

llama-7b-dpo-qlora-relu / runs /Mar06_15-19-45_SYS-4029GP-TRT /events.out.tfevents.1709709637.SYS-4029GP-TRT.2249910.0

Commit History

Training in progress, step 100

c3da2f0
verified

chanchan7 commited on Mar 7