def second_step()

in grok/training.py [0:0]

• 9 lines of code
• 5 McCabe index (conditional complexity)

    def second_step(self, zero_grad=False):
        for group in self.param_groups:
            for p in group["params"]:
                if p.grad is None:
                    continue
                p.sub_(self.state[p]["e_w"])  # get back to "w" from "w + e(w)"

        self.base_optimizer.step()  # do the actual "sharpness-aware" update

        if zero_grad:
            self.zero_grad()