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 / trainer_state.json

Commit History

Model save

be46998
verified

lole25 commited on Mar 5

Model save

b6cf0f6
verified

lole25 commited on Mar 4