JunjieHu

Hi sorry for the late response. I know the error happens during the test time. But I didn't print out the logprobs during the training, I am not sure whether...

Hi @masonreznov unfortunately I didn't solve the NAN problem. Maybe @artetxem could suggest a fix to this.

@ethan5437 Sorry for the late response! Please check this [link](https://drive.google.com/file/d/1QBjKZVynWOSA6PsQJofNMU4WknBs1mq8/view?usp=sharing) for the generated outputs.

Even when I use CPU to train the model, I got another error. Do you know how to fix it? Thanks! ` $ th train_telling.lua -gpuid -1 -mc_evaluation -verbose -finetune_cnn_after...

Hi @yukezhu Thanks for your reply. Changing unpack to table.unpack does solve my second problem. On the other hand, changing the batch_size from 64 to 1 doesn't solve the out-of-memory...

Hi, @yukezhu Thanks for your help! I solve all the configuration problems and everything works well. I notice that the repo only contains the telling questions, would you plan to...

Hi @maksym-del Here are my answers to your questions. 1. Mostly we used the hyper-parameters provided in the scripts/*.sh. For tasks except the QA parts, I used lr=2e-5, effective batch_size=32,...

I have the same problem of executing mira.py. I try cdec-2014-10-12 version provided on the cdec website. I get the same error on both mac and ubuntu 14.04. `./training/mira/mira.py -d...

Hi Chris @redpony I find the same problem when I compile the program. How to fix it? Thanks. `libextractor.a(data_array.cc.o): In function`igzstream::~igzstream()': /home/jjhu/Research/cdec/extractor/../utils/gzstream.h:98: undefined reference to `gzstreambase::~gzstreambase()' libextractor.a(data_array.cc.o): In function`~igzstream': /home/jjhu/Research/cdec/extractor/../utils/gzstream.h:98:...

Hi @zphang Thanks a lot for pointing out the issues w/ detailed cases! 1. The *.gitignore* file made me miss the *lib* folder. I've just uploaded my modified conll.py file....