Difference between validation loss and validation accuracy?

[tthrift (Terry Thrift)]

I found an interesting response by radek to a similar question.

Validation Loss VS Accuracy

Empirically, accuracy seems like quite a limited measure of quality of predictions. To predict whether an example belongs to some class, our model outputs a number (whatever we put through sigmoid or softmax) between 0 and 1. To calculate accuracy, we take some arbitrary threshold (0.5 by default) and every prediction above means examples belong to some class and below they don’t. This threshold of 0.5 gets dicey really fast if we don’t have perfectly balanced class (50% positive and 50% negati…

After cycle 4 or 5 is your model getting better or worse?

• Accuracy improves on the same validation set.
• Cross entropy loss degrades on the same validation set.

I think you might be right that it is less confident.
Despite doing better on that validation set it starts losing generality wrt cross entropy around the end of your 5th cycle.