DeepSpeed icon indicating copy to clipboard operation
DeepSpeed copied to clipboard

[BUG]What is the meaning of setting "actor_lora_module_name" without "only_optimize_lora"?

Open NostalgiaOfTime opened this issue 1 year ago • 3 comments

I see much shell file include "--actor_lora_module_name" but without "only_optimize_lora". According to the source code, this will cause all the model parameters will be trained instead of only LoRA layers.

so could tell me the meaning of setting actor_lora_module_name without only_optimize_lora

NostalgiaOfTime avatar Apr 24 '23 09:04 NostalgiaOfTime

Is any update, I still confuse about it

NostalgiaOfTime avatar May 18 '23 09:05 NostalgiaOfTime

I am also confused about the parameter "--only_optimize_lora". What is the fundamental difference between setting and not setting this parameter?

xinghuang2050 avatar Nov 20 '23 07:11 xinghuang2050

@NostalgiaOfTime @xinghuang2050 - hi, actor_lora_module_name is used to filter which linear should be changed to lora linear. And only_optimize_lora is used to select whether optimize full-parameters or only the Lora matrix A and B.

EeyoreLee avatar Dec 22 '23 06:12 EeyoreLee