Why does my deep learning model do well on training data but poorly on validation?

Unfollow Follow

Naomi Teng

Updated 4 days ago in

I’m new to deep learning and currently training my first few neural network models.

During training, the accuracy keeps improving and the loss goes down nicely. But when I evaluate the model on validation data, the performance drops a lot. This feels confusing because the training results look “good” at first glance.

I’m trying to understand this at a conceptual level, not just apply fixes blindly.

Some things I’m wondering about:

What are the most common reasons this happens for beginners?
How do you tell if this is overfitting versus a data or setup issue?
Are there simple checks or habits I should build early to avoid this?
At what point should I worry, and when is this just part of learning?

Looking for intuition, mental models, and beginner-friendly explanations rather than advanced math or theory.

Cancel

Deep Learning

1
19
4 days ago
0

Write your reply here to join the conversation

YOUR PREVIEW

Avatar

Subscriber

Vidhi Shah 2 days ago

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.

Liked by

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.

Cancel