Gs-Zhang

flags.DEFINE_string( "albert_config_file", 'albert_base/albert_config.json', "The config json file corresponding to the pre-trained ALBERT model. " "This specifies the model architecture.") flags.DEFINE_string("vocab_file", 'albert_xlarge/30k-clean.vocab', "The vocabulary file that the ALBERT model was trained...

And the feature file is not exist, it is generated when I am running the .py.

I have download the datasets ,but it can't be used for your project. Is there something need I to do? @hyhouyong 

Sorry,I also don't find the dataset as the same as what he use.But maybe you can do it yourself,and modify the code.There is a dataset on internet,and you can use...

是torch版本的问题么？torch1.9