samplesam.py

from sam import SAM
...

model = YourModel()
base_optimizer = torch.optim.SGD  # define an optimizer for the "sharpness-aware" update
optimizer = SAM(model.parameters(), base_optimizer, lr=0.1, momentum=0.9)
...

for input, output in data:

  # first forward-backward pass
  loss = loss_function(output, model(input))  # use this loss for any training statistics
  loss.backward()
  optimizer.first_step(zero_grad=True)
  
  # second forward-backward pass
  loss_function(output, model(input)).backward()  # make sure to do a full forward pass
  optimizer.second_step(zero_grad=True)
...