Problem in Running the Code

[Guardian99]

After parsing the sets, the output folder size is roughly around 3 GB. After running dataset.py on the parsed files, the pickled files are only of size 1 kb.
After running train.py trn_x, trn_y_raw = zip(*sorted(trn_data.items())) throws an error because the dictionary line is empty.

Has anyone able to run the code fully?

[slash-under]

I'm working on getting the code running, based off the example.ipynb file, for use with Colaboratory, in my fork.