Set mlflow experiment and run name for evaluation

[sfmig]

• If not passed as cli argument: experiment_name is defined from the training job's name + '_evaluation'
• If not specified via CLI: the run name is set to be _

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 9.09091% with 30 lines in your changes missing coverage. Please review.

Project coverage is 39.13%. Comparing base (ff59d84) to head (00e0dc6).

Files	Patch %	Lines
crabs/detector/utils/evaluate.py	11.53%	23 Missing ⚠️
crabs/detector/evaluate_model.py	0.00%	4 Missing ⚠️
crabs/detector/datamodules.py	0.00%	3 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #219      +/-   ##
==========================================
- Coverage   39.52%   39.13%   -0.39%     
==========================================
  Files          24       24              
  Lines        1417     1431      +14     
==========================================
  Hits          560      560              
- Misses        857      871      +14     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[sfmig]

Closing because combined with #220