Add validation in Task.__len__() to ensure stop parameter does not exceed
the actual dataset size. This prevents IndexError crashes during training
when invalid stop values are provided.
The validation is centralized in the base Task class and preserves the
original lazy evaluation behavior - num_examples() is only called when
needed (for validation when stop is provided, or for default value when
stop is None).
Fixes issue where training would crash with IndexError when iterating
over Task instances with stop > dataset_size.
