In this PyTorch Tutorial we learn how to use a Learning Rate (LR) Scheduler to adjust the LR during training. Models often benefit from this technique once learning stagnates, and you get better results. We will go over the different methods we can use and I'll show some code examples that apply the scheduler.

• torch.optim.lr_scheduler provides several methods to adjust the learning rate based on the number of epochs.
• `torch.optim.lr_scheduler.ReduceLROnPlateau allows dynamic learning rate reducing based on some validation measurements.

Documentation:

https://pytorch.org/docs/stable/optim.html