Yeah, this happens to everyone at the start you’re not alone 😄

Basically, your model is getting really good at remembering the training data, not at understanding the problem in general. So it looks awesome during training, but when you show it new data (validation), it kind of struggles.

Think of it like this: it memorized the answers for one test, but didn’t actually learn the subject.

Most of the time, it’s just overfitting, especially if the dataset is small or the model is a bit heavy. Sometimes it can also be simple stuff like data splits or preprocessing being slightly off.

An easy check: if training keeps getting better but validation gets worse, that’s overfitting. And honestly, this is just part of learning deep learning you only start noticing this once you’re doing things right.