Set eval_metric for xgboost

[freddyaboulton]

Pull Request Description

Fixes #2570

Perf tests here

I didn't see any difference in performance with changing the value of eval_metric so just picking logloss (new default).

---

After creating the pull request: in order to pass the release_notes_updated check you will need to update the "Future Release" section of docs/source/release_notes.rst to include this pull request by adding :pr:123.

[codecov]

Codecov Report

Merging #2741 (759414a) into main (9c8dd1d) will increase coverage by 0.1%.
The diff coverage is 100.0%.

@@           Coverage Diff           @@
##            main   #2741     +/-   ##
=======================================
+ Coverage   99.9%   99.9%   +0.1%     
=======================================
  Files        301     301             
  Lines      27819   27827      +8     
=======================================
+ Hits       27770   27778      +8     
  Misses        49      49             

Impacted Files	Coverage Δ
...nents/estimators/classifiers/xgboost_classifier.py	100.0% <ø> (ø)
evalml/tests/component_tests/test_components.py	100.0% <ø> (ø)
...l/tests/component_tests/test_xgboost_classifier.py	100.0% <100.0%> (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 9c8dd1d...759414a. Read the comment docs.

[eccabay]

LGTM! Looking forward to having that warning disappear.

[bchen1116]

LGTM!

[chukarsten]

Nice! Thanks for swapping the perf test results in - I thought I was crazy.