training loop for iris data

training.py

costs = []  # initially empty list, this will store all the costs after a certain number of epochs

# Start training
for epoch in range(number_of_epochs):

    # ------------------------- forward-prop -------------------------
    Z1.forward(X_train)
    A1.forward(Z1.Z)
    
    # ---------------------- Compute Cost ----------------------------
    cost, dZ1 = compute_stable_bce_cost(Y_train, Z1.Z)
    # print and store Costs every 100 iterations and of the last iteration.
    if (epoch % 100) == 0 or epoch == number_of_epochs - 1:
        print("Cost at epoch#{}: {}".format(epoch, cost))
        costs.append(cost)    

    # ------------------------- back-prop ----------------------------        
    Z1.backward(dZ1)
      
    # ----------------------- Update weights and bias ----------------
    Z1.update_params(learning_rate=learning_rate)