fairseq/optim/fp16_optimizer.py [180:194]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        overflow = DynamicLossScaler.has_overflow(grad_norm)
        self.scaler.update_scale(overflow)
        if overflow:
            if self.scaler.loss_scale <= self.args.min_loss_scale:
                # Use FloatingPointError as an uncommon error that parent
                # functions can safely catch to stop training.
                raise FloatingPointError((
                    'Minimum loss scale reached ({}). Your loss is probably exploding. '
                    'Try lowering the learning rate, using gradient clipping or '
                    'increasing the batch size.'
                ).format(self.args.min_loss_scale))
            raise OverflowError('setting loss scale to: ' + str(self.scaler.loss_scale))
        return grad_norm

    def step(self, closure=None):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



fairseq/optim/fp16_optimizer.py [352:367]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        overflow = DynamicLossScaler.has_overflow(grad_norm)
        self.scaler.update_scale(overflow)
        if overflow:
            if self.scaler.loss_scale <= self.args.min_loss_scale:
                # Use FloatingPointError as an uncommon error that parent
                # functions can safely catch to stop training.
                raise FloatingPointError((
                    'Minimum loss scale reached ({}). Your loss is probably exploding. '
                    'Try lowering the learning rate, using gradient clipping or '
                    'increasing the batch size.'
                ).format(self.args.min_loss_scale))
            raise OverflowError('setting loss scale to: ' + str(self.scaler.loss_scale))

        return grad_norm

    def step(self, closure=None):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -