mojave-pku / TextLevelGCN

source code of our paper presents in EMNLP 2019. https://www.aclweb.org/anthology/D19-1345/
GNU General Public License v3.0
54 stars 15 forks source link

the cuda machine you used and the training time? #1

Closed bright1993ff66 closed 4 years ago

bright1993ff66 commented 4 years ago

Hi Lianzhe,

I am very interested in your paper. But what cuda machine did you use to train your model? How long does it take to train one epoch?

mojave-pku commented 4 years ago
font{
    line-height: 1.6;
}
ul,ol{
    padding-left: 20px;
    list-style-position: inside;
}

GTX 1080Ti,I can't remember the specific time of each epoch, but the model can usually get the best results in 1-2 hours when running on the r8 and r52 datasets.

On 12/9/2019 14:37,Bright Chang<notifications@github.com> wrote: 

Hi Lianzhe, I am very interested in your paper. But what cuda machine did you use to train your model? How long does it take to train one epoch?

—You are receiving this because you are subscribed to this thread.Reply to this email directly, view it on GitHub, or unsubscribe.

    font{
        line-height: 1.6;
    }

    font{
        line-height: 1.6;
    }

    font{
        line-height: 1.6;
    }
bright1993ff66 commented 4 years ago

@HuangLianzhe Thank you for your prompt reply!