🔒 Help my understand my Gradient descent plots

[deft zealot]

These are my gradient descent plots with a different step size each time. As you can see, a small step size stops at a local minimum, and does not reach the minimum. A bigger step size plummets and therefore the stepsize is too large to reach the minimum.

My first question is, does this mean the optimum step size is 0,4?

Second question, how can I improve my 0.01 step size implementation? Reduce the domain? Also, how do I improve my 0.5 step size implementation?

Thanks in advance.

[frozen mica]

@deft zealot

Python help channel opened

Remember to:

• Ask your Python question, not if you can ask or if there's an expert who can help.
• Show a code sample as text (rather than a screenshot) and the error message, if you've got one.
• Explain what you expect to happen and what actually happens.

:warning: Do not pip install anything that isn't related to your question, especially if asked to over DMs.

Closes after a period of inactivity, or when you send !close.

[deft zealot]

Update, so increasing the number of epochs improved the 0.01 steps gradient descent

[frozen mica]

@deft zealot

Python help channel closed

This help channel has been closed and it's no longer possible to send messages here. If your question wasn't answered, feel free to create a new post in #1035199133436354600. To maximize your chances of getting a response, check out this guide on asking good questions.