As the others have said, if your main objective is to create a game, it's best to start with a small project.
If you still want to work on a specific project that's too complex for now, what you can do is extract a smaller game from it.
For example, you keep just one gameplay loop, one character, one sub-story from your dream project and turn it into a smaller stand-alone game.
This keeps you motivated because not only are you making technical progress, but you're also working on a project that interests you.
Now if your main objective is to learn the technical side of game creation, it's a bit more complicated. It's important to have small projects to validate certain skills, but you also need a complex project.
The reason for this is that a complex project is not just "a small project but bigger". You'll be confronted with problems you'd never have encountered on a small project (extreme code reuse, automation, tools development, etc.).
I'd also like to point out that whatever choice you make, you can expect to spend a lot of time on your project, even for things that looks simple. So only go for it if it's something you really want to do for fun.
I forgot the most important thing : Good luck!