lole25
/

phi-2-gpo-ultrafeedback-lora

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

phi-2-gpo-ultrafeedback-lora / runs /Mar05_10-41-15_gpu4-119-4 /events.out.tfevents.1709595839.gpu4-119-4.3155837.0

Commit History

Model save

be46998
verified

lole25 commited on Mar 5