# Is there any standard or normal range for the amount of LSTM loss function?

I am working on a LSTM network that I get loss amounts around 4.7 e-4 . It seems adding more layers and increasing epochs don't help to decreasing it. I also using a Dropout = 0.2 for each of my layers and implemented all the jobs with Keras library.

I like to know about this loss amount? is this large or is OK> Are there any rule of thumb for loss?

And why I can't decrease my loss amount? Is there any problem here?

• 0.2 is very very small. You are almost vanishing the signal. Try something like .85 – Media Feb 27 '19 at 20:10
• @Media: You mean I must eliminate 85% of my hidden units during each iteration? – WDR Feb 27 '19 at 20:51
• You should keep them. .85 means you keep 85 percent of them. – Media Feb 27 '19 at 20:54
• @Wow! I thought the opposite! – WDR Feb 27 '19 at 21:06
• Can you give more details? What are your features like? Are you normalizing? BatchNorm? etc? – kylec123 Feb 27 '19 at 21:14