Difference between validation loss and validation accuracy?

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

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.