Merge changes from original

comments: fix the alignement of type_ids

fixed usable

It seems the [] on CLS and SEP were added after and the masking was not
realigned

fix typo

Minor documentation fix

Fix the colab hostname in README.md.

External references should all be to colab.research.

Fix typos.

The current version reads the entire train file into memory and then
loads it with Dataset.from_tensor_slices. This can result in very large
allocations which can either OOM or cause a bad_alloc. To avoid this,
the new version now writes a TFRecord file to the `output_dir`.

Fix (are -> care) typo in README.md

Minor typo fixes

minor README spelling

preemptable -> preemtible