Input 0 of layer "functional_1" is incompatible with the layer: expected shape=(None, 64, 1), found shape=(256, 20)

I am currently on the final assignment in the week 4 of the final course of the TensorFlow developer specialization

In the notebook, I am using the following architecture -

[code removed by mentor]

The unittests are passing and it also shows that my model is compatible with the windowed dataset. I am also achieving the required values of MSE and MAE. But when I submit for grading it gives me the following error -

Failed test case: your model could not be used for prediction with a windowed dataset.
Expected:
No exceptions,
but got:
Input 0 of layer "functional_1" is incompatible with the layer: expected shape=(None, 64, 1), found shape=(256, 20).

Can someone help here ?

To help me assist you,

Please click on my name to start a private message. Then, attach your notebook as a .ipynb file. Please note that mentors cannot access your Coursera Jupyter workspace, so sending the notebook in a .ipynb format is essential.