You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Based upon some testing, I am starting to think that the default learning rate of 1e-4 is probably too low for our applications and might be better to bump it up to 5e-3 or even 1e-2. This is mostly based on empirical observations that the higher learning rates tend to get "similar" looking models even with differing architectures, batch sizes, and number of epochs. It also helps that we have the Adam optimizer which can attenuate the rate as training goes forward.
The text was updated successfully, but these errors were encountered:
Based upon some testing, I am starting to think that the default learning rate of 1e-4 is probably too low for our applications and might be better to bump it up to 5e-3 or even 1e-2. This is mostly based on empirical observations that the higher learning rates tend to get "similar" looking models even with differing architectures, batch sizes, and number of epochs. It also helps that we have the Adam optimizer which can attenuate the rate as training goes forward.
The text was updated successfully, but these errors were encountered: