How to know what causes improvement (Paramchange vs Randomness)

[AMusic (Anel)]

The solution to this problem you will find here:

A recipe for a reproducible randomization

Finally, I am able to reproduce results ! In a nutshell: In order to reproduce your results for demonstration purposes etc. use fastaiV1 not fastaiV2 @stas provided a code snippet that you must place at the top of your notebook (original post at the top) call: random_ctl(bad_seed) first in every cell when randomness comes into play which is: before you create your databunch, before you create your learner, before you call fit_one_cycle —> HINT: set bad_seed != 0 for reproducibility If done …