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 / training_args.bin

Commit History

Model save

3a19881
verified

lole25 commited on Mar 7

Model save

be46998
verified

lole25 commited on Mar 5

Training in progress, step 100

01cfcf2
verified

lole25 commited on Mar 4