Adam

Thanks for the response! I am probably missing something, but I thought the `train` directory only had data for sections 02-21 for wsj, whereas the test set is for sections...

Yeah I guess so. I am asking about the test data in particular. Which appears to be section 23 of PTB. So running `./bin/basic/extract_test_from_ptb.sh` only extracts `words` and `synts` from...

I think I am on the hook to finally do this. Current thoughts after looking at previous discussions: - A user specifies a `--batch_size` - Optionally, a user can specify...

> Let's define two things: "notional batch size" is the number of elements per training step, and "effective batch size" is the size of the minibatches of which there is...

> > Yeah previously I had a script for running sweeps that does 3) when converting sweep hyperparameters to yoyodyne training. But to do this I set a `--max_batch_size` manually....

> > Sorry so you mean should we combine 2) and 3) by subclassing the PTL trainer? I guess this factors into your comments about a separate cli `yoyodyne-tune`. Is...

I just rebased a ton of commits and want to make sure I didn't break anything. EDIT: Hmmm I did not realize that all rebased commits would appear as changes...

Yeah sounds good. > vocab_map would be better just called index and we should throw out the SymbolMap class. Does this mean we would call it like `index.index` (consider that...

Ok I was working on replacing the indexing with one method as you suggested but there is an issue here: our output space should be `target_vocab_size`. We *could* set this...

I think I can make this work with some tricky offsets to map target indices drawn from {0, ..., target_size} to the embedding matrix indices of {0, ..., source+target+features size}....