cleaning last preds

[Borda]

Before submitting

• Was this discussed/approved via a Github issue? (no need for typos and docs improvements)
• Did you read the contributor guideline, Pull Request section?
• Did you make sure to update the docs?
• Did you write any new necessary tests?

What does this PR do?

unify the last pred to be preds as everywhere

PR review

Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.

Did you have fun?

Make sure you had fun coding 🙃

[codecov]

Codecov Report

Merging #191 (459463a) into master (dcdca51) will not change coverage.
The diff coverage is 100.00%.

@@            Coverage Diff            @@
##           master     #191     +/-   ##
=========================================
  Coverage   96.75%   96.75%             
=========================================
  Files          90      180     +90     
  Lines        2864     5728   +2864     
=========================================
+ Hits         2771     5542   +2771     
- Misses         93      186     +93     

Flag	Coverage Δ
Linux	79.95% <100.00%> (ø)
Windows	79.95% <100.00%> (ø)
cpu	96.75% <100.00%> (ø)
gpu	96.75% <ø> (?)
macOS	96.75% <100.00%> (ø)
pytest	96.75% <100.00%> (ø)
python3.6	95.65% <100.00%> (ø)
python3.8	96.71% <100.00%> (ø)
python3.9	96.61% <100.00%> (ø)
torch1.3.1	95.65% <100.00%> (ø)
torch1.4.0	95.77% <100.00%> (ø)
torch1.8.1	96.61% <100.00%> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
torchmetrics/functional/regression/spearman.py	93.02% <ø> (ø)
torchmetrics/functional/regression/ssim.py	100.00% <ø> (ø)
torchmetrics/functional/classification/dice.py	92.59% <100.00%> (ø)
torchmetrics/utilities/checks.py	92.43% <100.00%> (ø)
..._w/1/s/torchmetrics/retrieval/retrieval_fallout.py	100.00% <0.00%> (ø)
__w/1/s/torchmetrics/__about__.py	100.00% <0.00%> (ø)
.../1/s/torchmetrics/functional/retrieval/fall_out.py	92.30% <0.00%> (ø)
.../1/s/torchmetrics/retrieval/retrieval_precision.py	100.00% <0.00%> (ø)
__w/1/s/torchmetrics/classification/f_beta.py	100.00% <0.00%> (ø)
...s/torchmetrics/functional/classification/f_beta.py	100.00% <0.00%> (ø)
... and 84 more

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update dcdca51...459463a. Read the comment docs.