At the first epochs, what will segmentation model get?

I am working at a semantic segmentation problem now, with 5-classes task. But when I running on validation function and output my probablities map.

I found that with the background class (the extra class for nnUNet, named class-0), the probalities always up to nearly 1, even when running on much epochs.

But the other foreground classes (as class-1 to class-6), probalities can't range to 1.0 the highest. But at least that I can recognize the outline of the target, but each fore-ground probabilities map seems goes to the same look.

I am confused that, can this validation result be a clue that proves something in my code goes wrong?

Best,