Thank you Hieu for Moses2 tips! BTW, is Moses2 backwards compatible for models trained with old Moses?
Regards, Liling On Mon, Dec 11, 2017 at 7:39 PM, Hieu Hoang <[email protected]> wrote: > if you want fast decoding with more than 16 threads, use Moses2. > http://www.statmt.org/moses/?n=Site.Moses2 > > Hieu Hoang > http://moses-smt.org/ > > > On 11 December 2017 at 09:20, liling tan <[email protected]> wrote: > >> Dear Moses community/developers, >> >> I have a question on how to handle large models created using moses. >> >> I've a vanilla phrase-based model with >> >> - PhraseDictionary num-features=4 input-factor=0 output-factor=0 >> - LexicalReordering num-features=6 input-factor=0 output-factor=0 >> - KENLM order=5 factor=0 >> >> The size of the model is: >> >> - compressed phrase table is 5.4GB, >> - compressed reordering table is 1.9GB and >> - quantized LM is 600MB >> >> >> I'm running on a single 56 cores machine with 256GB RAM. Whenever I'm >> decoding I use -threads 56 parameter. >> >> It's takes really long to load the table and after loading, it breaks >> inconsistently at different lines when decoding, I notice that the RAM goes >> into swap before it breaks. >> >> I've tried compact phrased table and get a >> >> - 3.2GB .minphr >> - 1.5GV .minlexr >> >> And the same kind of random breakage happens when RAM goes into swap >> after loading the phrase-table. >> >> Strangely, it still manage to decode ~500K sentences before it breaks. >> >> Then I've tried with ondisk phrasetable and it's around 37GB >> uncompressed. Using the ondisk PT didn't cause breakage but the decoding >> time is significantly increased, now it can only decode 15K sentences in an >> hour. >> >> The setup is a little different from normal where we have the >> train/dev/test split. Currently, my task is to decode the train set. I've >> tried filtering the table with the trainset with >> filter-model-given-input.pl but the size of the compressed table didn't >> really decrease much. >> >> The entire training set is made up of 5M sentence pairs and it's taking >> 3+ days just to decode ~1.5M sentences with ondisk PT. >> >> >> My questions are: >> >> - Are there best practices with regards to deploying large Moses models? >> - Why does the 5+GB phrase table take up > 250GB RAM when decoding? >> - How else should I filter/compress the phrase table? >> - Is it normal to decode only ~500K sentence a day given the machine >> specs and the model size? >> >> I understand that I could split the train set up into two and train 2 >> models then cross-decode but if the training size is 10M sentence pairs, >> we'll face the same issues. >> >> Thank you for reading the long post and thank you in advances for any >> answers, discussions and enlightenment on this issue =) >> >> Regards, >> LIling >> >> _______________________________________________ >> Moses-support mailing list >> [email protected] >> http://mailman.mit.edu/mailman/listinfo/moses-support >> >> >
_______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
