training setting for reproduce the paper about gill HOT 4 CLOSED

Thank you for your quick reply!
I look forward to seeing the results of your research.

from gill.

Hi, the training parameters detailed in Sec 3.4 (page 6) of the paper should be the same as the defaults in the code:

I think the line you are referencing (batch size of 180 for 1 epoch) is from our other paper Fromage. If you're interested in that work, the code is available in this repo.

from gill.

@kohjingyu
I'm sorry. As you say, the training settings I mentioned (batch size of 180 for 1 epoch) came up with a different paper, not GILL.
But I'm still a little puzzled.
In your code, the model learns 90 epochs and each epoch consists of 2000 steps, so it processes 180000 (180K) steps in total. Is 180K steps in your code equivalent to 20K iterations in your paper?

from gill.

Ah yes, you are right. The default setting of epochs should actually be 10 (10 * 2000 = 20K iterations), which is now updated by a18045a. Thanks for catching this!

from gill.