Error training

[HarvsG]

root@9ed087ccfe98:~/torch-rnn# th train.lua -input_h5 data/BurtonCrew.h5 -input_json data/BurtonCrew.json -gpu -1
Running in CPU mode	
/root/torch/install/bin/luajit: bad argument #2 to '?' (end index out of bound at /tmp/luarocks_torch-scm-1-437/torch7/generic/Tensor.c:969)
stack traceback:
	[C]: at 0x7ff387c55b20
	[C]: in function '__index'
	./util/DataLoader.lua:30: in function '__init'
	/root/torch/install/share/lua/5.1/torch/init.lua:91: in function </root/torch/install/share/lua/5.1/torch/init.lua:87>
	[C]: in function 'DataLoader'
	train.lua:76: in main chunk
	[C]: in function 'dofile'
	/root/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:145: in main chunk
	[C]: at 0x00406670

[antihutka]

It looks like you might be running an old version of torch-rnn with a small dataset and hitting #135. Update and try again.