DUAL-GPO
/

phi-2-gpo-20k-40k-60k-lora512-i2

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

phi-2-gpo-20k-40k-60k-lora512-i2 / train_results.json

Commit History

Model save

f61ddb0
verified

BraylonDash commited on May 18

Model save

3ad9947
verified

BraylonDash commited on May 18