Hey! This is a quick visual guide to what the learning rates look like while training our model for 1 or more epochs with the fit_one_cycle
method. This also shows what some of the function function parameters do : div
, div_final
, pct_start
.
Some of the questions it addresses:
- From what value does the lr increase?
- When does it reverse it’s directions? (what is the stepsize?)
- Does the learning rate go up and down every epoch?
Hope this helps!