Select runs that logged avg_loss
to visualize data in this line chart.
to visualize data in this line chart.
torn apart
a look at what the rnn is doing step-by-step
Created on June 13|Last edited on June 17
Comment
Did I get the deets right? It really seems like it may be the candecay value of 0.99 that is the secret sauce, at least for getting results that pass the basic test of a repeated sequence of length 2. Let's see if it's that value that really fixes things.
is it the number of layers??
Of course, my initial test had a curve upwards near the end. I think a different learning rate helped with that.
Add a comment