Add support for scoring metrics to Runtime.cross_validate()

[raghukiran1224]

Overview

Current implementation does not accept user specified scoring metric(s). For example,
cross_val_score(pipeline, X_test, y_test, scoring="neg_mean_squared_error", cv=10)
The list of sklearn model evaluation metrics are listed here
https://scikit-learn.org/stable/modules/model_evaluation.html#scoring-parameter

Acceptance Criteria

One common use case documented below is supported by codeflare pipeline.
https://scikit-learn.org/stable/auto_examples/model_selection/plot_underfitting_overfitting.html#sphx-glr-auto-examples-model-selection-plot-underfitting-overfitting-py

Questions

Assumptions

Reference

[raghukiran1224]

created by @yuanchi2807