How do we know when we should stop changing the parameters `m`

and `b`

? How will we know when our program has learned enough?

To answer this, we have to define convergence. **Convergence** is when the loss stops changing (or changes very slowly) when parameters are changed.

Hopefully, the algorithm will converge at the best values for the parameters `m`

and `b`

.

### Instructions

**1.**

Run the file. Look at the graph. This graph shows how much the parameter `b`

changed with each iteration of a gradient descent runner.

**2.**

How many iterations did it take for this program to converge?

Enter your answer in a variable called `num_iterations`

.

**3.**

At what `b`

value did this program converge?

Enter your answer in a variable called `convergence_b`

.

# Sign up to start coding

By signing up for Codecademy, you agree to Codecademy's Terms of Service & Privacy Policy.