Why best performance MSE does not align with final MSE?

ANN model outputs

1. The model stopped at epoch 22 with an MSE of 0.0242
2. The best performance was observed at epoch 16 with an MSE of 0.031
3. However, the final MSE between actual and predicted values is 0.0308

Shouldn't the third data align with the best performance (second) value ?

[Ganesh]

Hi,

MSE of 0.031 is higher than 0.0242. Which means your model is having a greater error, implying the model is performing worse.

When you say "final" MSE, what do you mean? Do you mean that is the MSE you achieve when you predict on a test set?

[Sunita]

Final MSE means , MSE between actual and predicted values once training is done

[the cyclist]

Is it just a rounding issue in a displayed value? 0.0308 is equal to 0.031, rounded to three decimal places.

[Mahi]

MSE at epoch 22 is better than the epoch 16. There is always a difference between training and testing error and accuracy values . Your final value of MSE is higher than your training mse .which I think is good.otherwise it may mean that your model is over fitted

[pathakunta]

The model stopped at epoch 22 with an MSE of 0.0242

Answer 1

[Ganesh]

MSE you achieve at epoch 22 is for that specific minibatch used at epoch 22. That would not mean that you achieve the same MSE for all of the dataset. It's quite possible that you achieve a lower or a higher MSE on the test set.