Did the number of parameters take into account the parameters in the tunable classification head?

[ShengdingHu]

Thanks for releasing the code! I noticed that the reporting number of parameters of Lora module is 0.3 M for roberta-base. After experiments, I found that there are 0.5M parameters tunable in the sequence classification head (but it's the same for all baselines, so I am not arguing about the fairness). I wonder was I correct about the setting? Did the performances in the paper were the ones that also tune a classification head for classification tasks?

[edwardjhu]

Hi Shengding,

You are right. We didn't include the classification head when counting parameters for all baselines, even though they were trained (otherwise they would be random). We'll add a note in our manuscript stating this explicitly.

P.S. My apology for the delayed response. I left Microsoft late last year and stopped receiving notifications.