The mert optimization is unlikely to be a bottleneck unless you've changed the size of the n-best list, which I believe defaults to 100. At that setting it can usually finish in a few minutes on a single processor. At a high setting of 1000, it can take over an hour in later iterations.
Cheers Adam On 9 Jun 2008, at 02:30, Philipp Koehn wrote: > Hi, > > there is also a stage in the mert training (the actual mert > optimization, > not running the decoder) that is currently not parallelized, so you > cannot expect any gains on that. It is my understanding that we will > have a better implementation of mert that also parallelizes the > optimization loop, but Nicola could correct me on that. > > -phi > > On Sun, Jun 8, 2008 at 7:52 AM, Yee Seng Chan > <[EMAIL PROTECTED]> wrote: >> Thanks, increasing to 1G seem to "unstuck" the processes. >> My training pairs is only about 250K of sentences, so I had thought >> 0.5G should >> be sufficient; perhaps the issue is with the size of the LM. >> >> Nevertheless, I'm doing mert on a dev-set which has only about 1000 >> source >> sentences. For this setup, I found that parallel mert only >> marginally reduces >> the time for each mert iteration. Non-parallel mert needs 60 >> minutes per >> iteration; while parallel-mert on 5 nodes needs 40-50 minutes per >> iteration. >> >> I know that the speedup from parallel mert is non-linear in the no. >> of nodes, >> due to the time needed to coordinate among the sub-processes. >> >> Best regards, >> Yee Seng. >> >> >> >> >> >> >> _______________________________________________ >> Moses-support mailing list >> Moses-support@mit.edu >> http://mailman.mit.edu/mailman/listinfo/moses-support >> >> > _______________________________________________ > Moses-support mailing list > Moses-support@mit.edu > http://mailman.mit.edu/mailman/listinfo/moses-support -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. _______________________________________________ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
