Drop_path_rate rule #185
Description
Hi, thank you for your extraordinary work, I don't understand according to which rule do you set the drop path rate? Sometimes in smaller model is 0.1 and sometimes in bigger model is 0.3 and 0.4
{{ message }}
Hi, thank you for your extraordinary work, I don't understand according to which rule do you set the drop path rate? Sometimes in smaller model is 0.1 and sometimes in bigger model is 0.3 and 0.4