Chen

Hi, I think the problem is the small dataset you are using, only 50k examples. try the full set - I get to ppl 30 on val this way. The...

You are right, it seems like even when the model should memorize the dataset it still gives the same response every time.. I'll investigate further and update you soon.

using this settings - (takes less than an hour to start seeing results) th train.lua --batchSize 128 --hiddenSize 512 --cuda --numLayers 1 --vocabSize 10000 --dropout 0 --weightDecay 0 --earlyStopOnTrain --dataset...

Hi @macournoyer, @vikram-gupta , I added a commit that turn off seqLSTM by default(use LSTM instead) and allows to switch it back on using the flag --seqLstm. My experiments show...