Vincent Andreas

@deepakbulani you can read Squad paper https://nlp.stanford.edu/pubs/rajpurkar2016squad.pdf , in there have the reason for three answer

@HarnishLJ but the strange thing is we still in epoch 1, even we already defined how many epoch when we run the main.py . I'm curious too, how we use...

@HarnishLJ ooh, I don't realize it have default value in the flags, and I don't change the num_epoch parameter too, thanks for realize me.

in flag mode, you can choose to 'show_examples', that will show random question, predicted answer, and the true answer. I have an idea to edit the code, so it can...

@HarnishLJ The flag is ```mode=show_examples```. (from the previous is ```mode=train```)And this is the result when I execute that code. ``` !python /content/gdrive/"My Drive"/"Colab Notebooks"/cs224n-Squad-Project-master/code/main.py --experiment_name=aku_nyoba --dropout=0.15 --batch_size=60 --hidden_size_encoder=150 --embedding_size=100 --do_char_embed=False...

hey @HarnishLJ, I found how to test using your own testing data, just make a json file, then use official_eval mode. ``` !python /content/gdrive/"My Drive"/"Colab Notebooks"/cs224n-Squad-Project-master/code/main.py --experiment_name=aku_nyoba --dropout=0.15 --batch_size=60 --hidden_size_encoder=150...

> @HarnishLJ The flag is `mode=show_examples`. (from the previous is `mode=train`)And this is the result when I execute that code. > > ``` > !python /content/gdrive/"My Drive"/"Colab Notebooks"/cs224n-Squad-Project-master/code/main.py --experiment_name=aku_nyoba --dropout=0.15...

Sure @mstoykov I'll wait other discussion related to this, thx for your suggestion