MultiStepLR is a scheduler that decays the learning rate with a certain multiplicative factor set by the user when a certain milestone is reached. The milestone is the number of epochs which is set by the user.
They are a pair of values that sets the number of epochs after which the learning rate is scaled.
It is the multiplicative factor by which the learning rate is scaled.
Let us demonstrate the functioning of the MultiStepLR with a simple calculation.
If Milestones are set to be 30 and 80 base learning rate being 0.05, and gamma 0.1, then
for, €€0<=epoch<30€€ , €€lr=0.05€€
for, €€30<=epoch<80€€ , €€lr=0.05*0.1=0.005€€
for , €€epoch>=80€€ , €€lr=0.05*0.1^2=0.0005€€
import torch model = [Parameter(torch.randn(2, 2, requires_grad=True))] optimizer = torch.optim.AdamW(model.parameters(), lr=learning_rate, weight_decay=0.01, amsgrad=False) scheduler=torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones=[30,80], gamma=0.1, last_epoch=-1, verbose=False) for epoch in range(20): for input, target in dataset: optimizer.zero_grad() output = model(input) loss = loss_fn(output, target) loss.backward() optimizer.step() scheduler.step()