Made val & test loss like train loss in LogisticRegression

[garryod]

What does this PR do?

Fixes dissimilarity between train & val/test losses introduced by #655

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 your PR does only one thing, instead of bundling different changes together?
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests? [not needed for typos/docs]
• Did you verify new and existing tests pass locally with your changes?
• If you made a notable change (that affects users), did you update the CHANGELOG?

PR review

• Is this pull request ready for review? (if not, please submit in draft mode)

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 #664 (380a378) into master (01269af) will decrease coverage by 53.50%.
The diff coverage is 36.52%.

❗ Current head 380a378 differs from pull request most recent head f418994. Consider uploading reports for the commit f418994 to get more accurate results

@@             Coverage Diff             @@
##           master     #664       +/-   ##
===========================================
- Coverage   79.04%   25.54%   -53.51%     
===========================================
  Files         102      118       +16     
  Lines        5912     7110     +1198     
===========================================
- Hits         4673     1816     -2857     
- Misses       1239     5294     +4055     

Flag	Coverage Δ
cpu	25.54% <36.52%> (-0.24%)	⬇️
pytest	25.54% <36.52%> (-0.24%)	⬇️
unittests	?

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

Impacted Files	Coverage Δ
pl_bolts/callbacks/byol_updates.py	45.45% <0.00%> (-54.55%)	⬇️
pl_bolts/callbacks/variational.py	29.78% <0.00%> (-66.14%)	⬇️
pl_bolts/datasets/dummy_dataset.py	38.33% <0.00%> (-61.67%)	⬇️
pl_bolts/datasets/ssl_amdim_datasets.py	19.17% <0.00%> (-57.85%)	⬇️
pl_bolts/models/gans/basic/basic_gan_module.py	19.35% <0.00%> (-76.00%)	⬇️
pl_bolts/models/regression/linear_regression.py	23.68% <0.00%> (-74.83%)	⬇️
pl_bolts/models/rl/__init__.py	0.00% <0.00%> (-88.89%)	⬇️
pl_bolts/models/rl/common/agents.py	0.00% <0.00%> (-100.00%)	⬇️
pl_bolts/models/rl/common/gym_wrappers.py	0.00% <0.00%> (-91.60%)	⬇️
pl_bolts/models/rl/double_dqn_model.py	0.00% <0.00%> (-95.66%)	⬇️
... and 164 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 aad3d24...f418994. Read the comment docs.