am3 icon indicating copy to clipboard operation
am3 copied to clipboard
verified publisher icon ServiceNow

How long it would take to train this model?

Open luckycookiecookie opened this issue 6 years ago • 1 comments

Hi there,

  • I have run the code and found that it would take about 12 hours to train 12000 steps on NVIDIA GTX 1080 Ti. Is there anything wrong? Or it would take a long time to train this model indeed.

  • And at 12000 steps, the accuracy is no longer improved, the highest is 57.4%. I didn't modify any parameters.Is there anything wrong?

  • The program consumes most of the CPU resources but the GPU is rarely used. Also, it only occupies the 159M GPU memory. Is that correct?

luckycookiecookie avatar Nov 28 '19 08:11 luckycookiecookie

@luckycookiecookie I also can not reproduce the performance. Can you solve it?

blue-blue272 avatar Aug 18 '20 03:08 blue-blue272