Fix L1/L2 regularization

[rohitgr7]

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?

Regularization loss should also be normalized over batch_size. Also, L2 regularization was wrong there.

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 #216 into master will increase coverage by 0.04%.
The diff coverage is 90.00%.

@@            Coverage Diff             @@
##           master     #216      +/-   ##
==========================================
+ Coverage   89.14%   89.18%   +0.04%     
==========================================
  Files          74       74              
  Lines        3297     3291       -6     
==========================================
- Hits         2939     2935       -4     
+ Misses        358      356       -2     

Flag	Coverage Δ
#unittests	89.18% <90.00%> (+0.04%)	⬆️

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

Impacted Files	Coverage Δ
pl_bolts/models/regression/logistic_regression.py	97.18% <75.00%> (+2.58%)	⬆️
pl_bolts/models/regression/linear_regression.py	100.00% <100.00%> (ø)

---

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 25f8b03...d3f592a. Read the comment docs.