# Learning rate controls how big steps we take during optimization
# Too small: slow convergence, too large: might overshoot minimum

learning_rates = [0.1, 1.0, 10.0]
plt.figure(figsize=(12, 4))

for i, lr in enumerate(learning_rates):
    plt.subplot(1, 3, i+1)

    # Train with this learning rate
    _, _, _, _, losses = train_network(X, y, epochs=500, learning_rate=lr)

    plt.plot(losses)
    plt.title(f'Learning Rate = {lr}')
    plt.xlabel('Epoch')
    plt.ylabel('Loss')
    plt.yscale('log')
    plt.grid(True, alpha=0.3)

plt.tight_layout()
plt.show()