def step()

in low_rank_comparisons/src/optimizer.py [0:0]

• 31 lines of code
• 13 McCabe index (conditional complexity)

    def step(self, closure=None):
        """Performs a single optimization step.
        Arguments:
            closure (callable, optional): A closure that reevaluates the model
                and returns the loss.
        """
        loss = None
        if closure is not None:
            loss = closure()
        
        for group in self.param_groups:
            for p in group["params"]:
                if p.grad is None:
                    continue
                grad = p.grad.data
                if grad.is_sparse:
                    raise RuntimeError("Adam does not support sparse gradients, please consider SparseAdam instead")

                state = self.state[p]

                # State initialization
                if len(state) == 0:
                    state["step"] = 0
                    # Exponential moving average of gradient values
                    state["exp_avg"] = torch.zeros_like(p.data)
                    # Exponential moving average of squared gradient values
                    state["exp_avg_sq"] = torch.zeros_like(p.data)

                exp_avg, exp_avg_sq = state["exp_avg"], state["exp_avg_sq"]
                beta1, beta2 = group["betas"]

                state["step"] += 1

                # Decay the first and second moment running average coefficient
                # In-place operations to update the averages at the same time
                exp_avg.mul_(beta1).add_(grad, alpha=1.0 - beta1)
                exp_avg_sq.mul_(beta2).addcmul_(grad, grad, value=1.0 - beta2)
                denom = exp_avg_sq.sqrt().add_(group["eps"])

                step_size = group["lr"]
                if 'correct_bias' in group and group["correct_bias"]:  # No bias correction for Bert
                    bias_correction1 = 1.0 - beta1 ** state["step"]
                    bias_correction2 = 1.0 - beta2 ** state["step"]
                    step_size = step_size * math.sqrt(bias_correction2) / bias_correction1

                p.data.addcdiv_(-step_size, exp_avg, denom)

                # Just adding the square of the weights to the loss function is *not*
                # the correct way of using L2 regularization/weight decay with Adam,
                # since that will interact with the m and v parameters in strange ways.
                #
                # Instead we want to decay the weights in a manner that doesn't interact
                # with the m/v parameters. This is equivalent to adding the square
                # of the weights to the loss with plain (non-momentum) SGD.
                # Add weight decay at the end (fixed version)
                if group["weight_decay"] > 0.0:
                    p.data.add_(p.data, alpha=-group["lr"] * group["weight_decay"])

        return loss