"two_layer_net.ipynb" Solver section default setting problem

[HumbleHumbert]

I have encounterd isues when tring to run the solver in default learning rate 1e-2, when looking for other people's answers, I notice that everyone basically change it to 1e-3 instead, that could work, but I wonder why would you do that so uniformly? I mean is there any official announcement to make it fixed like that?

[mantasu]

I think the task requires constructing a Solver instance such that it would be able to train the model that achieves at least 36% accuracy. There are no restrictions on instantiating it; they even provide an example of how to do so in the Solver class documentation (where they also use lr of 1e-3).