shuffle in the model.fit of keras

It will shuffle your entire dataset (x, y and sample_weight together) first and then make batches according to the batch_size argument you passed to fit.

Edit

As @yuk pointed out in the comment, the code has been changed significantly since 2018. The documentation for the shuffle parameter now seems more clear on its own. You can choose to shuffle the entire training data or just shuffle the batch:

        shuffle: Boolean (whether to shuffle the training data
            before each epoch) or str (for 'batch'). This argument is ignored
            when `x` is a generator. 'batch' is a special option for dealing
            with the limitations of HDF5 data; it shuffles in batch-sized
            chunks. Has no effect when `steps_per_epoch` is not `None`.