Error when running #Evaluate:

[lethanh26061998]

"Code_colab":
#Evaluate
BERT_MODEL = 'fake-news.tar.gz', a = b, where did this come from???
So, I got this error:
ERROR:pytorch_pretrained_bert.modeling:Model name 'cache/fake-news.tar.gz' was not found in model name list (bert-base-uncased, bert-large-uncased, bert-base-cased, bert-large-cased, bert-base-multilingual-uncased, bert-base-multilingual-cased, bert-base-chinese). We assumed 'cache/fake-news.tar.gz' was a path or url but couldn't find any file associated to this path or url.
I look forward to your explanation, thanks a lot!

[ac4mm]

Hi,
sorry for the long waiting, but i just added fake-news.tar.gz file that i forgot to commit due to the long size file.
thanks for the interest and i hope everything must be self-declared or for any doubt i'm available.

[lethanh26061998]

Thanks for answering my question, However, the problem I am wondering is, I used your colab code with my dataset, but when I did the evaluation (#evaluate), I didn't know "BERT_MODEL = 'fake-news.tar.gz' " where will it be obtained ? Look forward to your help, thanks a lot! Vào Th 3, 3 thg 11, 2020 vào lúc 17:47 ac4mm <notifications@github.com> đã viết:

…

Closed #1 <#1>. — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#1 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AKJNEZR5TY7BARA3ETR77QTSN7NVHANCNFSM4S4S7R7Q> .

-- Le Thi Thanh, Infomation System Student Hanoi University of Science and Technology Phone: +84967374782

[ac4mm]

Hi, this file was created by two different dataset: AG_news and Fake_news (just look for them in Google), merged them and applied different operation for obtain what i wanted to achieve.
This image below shows what i just said:

these files pytorch_model.bin and config.json were obtained in detect_FN_with_BERT colab file, after processing were zipped in .tar and after .tar.gz format and used in step further on.