bert processor about matchzoo-py

[RoshanGurung93]

BERT has max sequence token length less than 512. I think you have token length greater than 512. Check the token length. Quick solution could be: if you have paragraph of 800, split into two 400 paragraph length and then tokenize.

[xumingying0612]

你好，我想问下，当我使用bert训练模型时候，在最后trainer.run()这里，老是报“Expected tensor for argument #1 'indices' to have scalar type Long; but got torch.cuda.IntTensor instead (while checking arguments for embedding)”这个错，一直没找出到底该改动哪里，能否给解决一下啊 非常非常感谢~~

[Chriskuei]

你好，我想问下，当我使用bert训练模型时候，在最后trainer.run()这里，老是报“Expected tensor for argument #1 'indices' to have scalar type Long; but got torch.cuda.IntTensor instead (while checking arguments for embedding)”这个错，一直没找出到底该改动哪里，能否给解决一下啊 非常非常感谢~~

Please provide more details, e.g. code snippets

[xumingying0612]

就是在https://github.com/NTMC-Community/MatchZoo-py/blob/master/tutorials/ranking/bert.ipynb中运行到最后一步trainer.run()报错了。求教 感谢感谢！