Optimiser SGD leads to KL vanishing

[ZhuohanX]

Hi,

Thank you so much for your code, it helped me a lot.

I am wondering about optimiser, I think in the paper, they say they used SGD, but when I changed the optimiser to SGD in your code, I got the KL vanishing problem. It is okay if I use Adam, I don't know why this happens, I am wondering if you have insights about this, thank you so much!