Can't solve the issue that 'nan's keep appearing in Loss if the parameter in train.py is greater than 1.96

[Holowila]

If I set the args.nonlinearityLTP or args.nonlinearityLTD greater than 1.96, the 'nan's will keep appearing in Loss at training phase and it will report an error while converting the decimal data to binary data in hook.py.

First I tried to adjust the learning rate and it didn't work. Then I tried to add normalization before the converting but it didn't work either. I don't know when the 'nan's appear and how to fix it.

[uhvardhan]

Hi! Were you able to fix this issue? I face the same thing in some situations and wasn't able to figure out a solution.