# Not able to properly tune Neural Network via Back Propagation properly

I have a custom code Neural Network(not using keras or any package...Trying to learn the essence of Neural Network from scratch)...

Code can be found here

I have the per iteration training output(red) versus actual expected(gray):

As you can see, the predicted values is moving like a layer rather than having a differential values in an attempt to mimic the cubic equation...

z = xi**3 + yi + 1.5

can anyone help me where I am making a mistake?