search

lizekang / ITDD

The source code of our ACL2019 paper "Incremental Transformer with Deliberation Decoder for Document Grounded Conversations "
MIT License
86 stars 17 forks source link

got Floating point exception when change -knl_seq_length_trunc from 200 to 100 #7

Closed happyMinionVic closed 5 years ago

happyMinionVic commented 5 years ago

I had run the code successfully with the given config. But when I tried to reduce the knowledge sentence padding length in the preprocess by reducing the padding length of knl from 200 to 100, I got an Floating point exception (core dumped) error and no other traceback. Could you figure out how could this happed and be fixed ? Thanks.

happyMinionVic commented 5 years ago

By the way, the error occurs in the start of training rather than running preprocess.py

lizekang commented 5 years ago

Could you provide the other configs when you run the preprocess.py?

happyMinionVic commented 5 years ago

Here is the config, the only difference is -knl_seq_length_trunc 100: python preprocess.py \ --train_src data/src-train-tokenized.txt \ --valid_src data/src-valid-tokenized.txt \ --train_knl data/knl-train-tokenized.txt \ --valid_knl data/knl-valid-tokenized.txt \ --train_tgt data/tgt-train-tokenized.txt \ --valid_tgt data/tgt-valid-tokenized.txt \ --save_data data/cmu_movie \ -dynamic_dict \ -share_vocab \ -src_seq_length_trunc 50 \ -tgt_seq_length_trunc 50 \ -knl_seq_length_trunc 100 \ -src_seq_length 150 \ -knl_seq_length 800

lizekang commented 5 years ago

You can try -knl_seq_length 400 and modify the code in onmt/encoders/mtransformer.py. Note that we use three previous dialogs as context so that the knl_seq_length is quadruple of knl_seq_length_trunc.

happyMinionVic commented 5 years ago

Ok, I will try this right now. And is there any other restrictions on the sequence length in the preprocessing? Such as -src_seq_length is three times as -src_seq_length_trunc?

lizekang commented 5 years ago

Yes. You can modify the code in onmt/encoders/mtransformer.py to change this setting.

lizekang commented 5 years ago

Yes

happyMinionVic commented 5 years ago

Where is the knl[600:800 ]? Are they just ignored?

lizekang commented 5 years ago

No, knl[600:800] is used in the deocding process.

happyMinionVic commented 5 years ago

I had modified all the related parameters in mtransformer.py and still got the the error Floating point exception My pytorch is 1.0.0 and torchtext is 0.4.0. Where is this bug from ?

lizekang commented 5 years ago

Oh, sorry, you should also modify the parameters in onmt/models/model.py.