lole25
/

phi-2-gpo-lora-ultrafeedback-test-1

alignment-handbook

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

phi-2-gpo-lora-ultrafeedback-test-1 / runs

5.85 kB

1 contributor

History: 1 commit

lole25's picture

Model save

b3af158 verified over 1 year ago

Mar18_23-34-57_gpu4-119-4
Model save over 1 year ago