Use data_train in validation curve

[ArturoAmorQ]

As reported in this forum post, in the instructions for the validation curve in the Exercise M6.03 it says

For both the gradient-boosting and random forest models, create a validation curve using the training set to assess the impact of the number of trees on the performance of each model.

But then in the solution we don't use the data_train but all data for the validation curve.

I guess we can take the opportunity to also emphasize that n_estimators should not be tuned, and that the validation curve in the notebook was only computed for educational purposes.