I could not understand a paragraph in super-convergence paper by LN Smith

[jithinrocs (Jithin James)]

Leslie Smith:

Research Paper Recommendations

[image] I am sorry for the confusion on the 1cycle policy. It is one cycle but I let the cycle end a little bit before the end of training (and keep the learning rate constant at the smallest value) to allow the weights to settle into the local minima.

https://forums.fast.ai/uploads/default/original/2X/3/351077871b8d6936ca7a9c392fbb81eae9bfd9b5.png