Force loading on the CPU which always has more memory than a
single GPU.  This is useful for models that cannot be loaded onto
a single GPU.

When using flag `-s` which prints the compression scheduler
pruning mask keys, we also print a table with the fine-grain
sparsity of each mask.

* Replace the optional 'best_top1' parameter with a generic
  optional dict which the caller can populate as needed.
* Saved in the checkpoint under the key 'extras'

Temporary fix for dependency on distiller class hierarchy when
serializing a model that contains a thinning recipe.