Train steps and batchsize

Open xiang-jian-wen opened this issue 4 years ago • 2 comments

Hi, Thanks for your excellent work, i have a question, how many steps did you train on each dataset? and dose the batchsize you mentioned in your paper refer to a single GPU? Thank you!

Mar 11 '22 01:03 xiang-jian-wen

Hi, thanks for your interest. The batchsize is for one card which has been mentioned in our readme file. Besides, we also included the number of training steps for each dataset in the readme file (in the commond).

Best Regards, Jun

Mar 12 '22 12:03 Markin-Wang

Hi, thanks for your interest. The batchsize is for one card which has been mentioned in our readme file. Besides, we also included the number of training steps for each dataset in the readme file (in the commond).

Best Regards, Jun

Thank you for your reply, I have seen the batchsize and train steps you mentioned in the readme file. thank you again.

Mar 12 '22 13:03 xiang-jian-wen