Closed dsindex closed 5 years ago
@dsindex
Thanks for your suggestions. Indeed, --max_seq_length=128
will have a better result.
@dsindex
if len(tokens) >= max_seq_length - 1:
tokens = tokens[0:(max_seq_length - 2)]
labels = labels[0:(max_seq_length - 2)]
I found the problem. In this part, I did not trim the length of the labels. Besides, >= is necessary. i have update the code and add recall f-score evaluation. Thanks for your help.
hi kyzhouhzau~
thank you for this project :) there is a minor error which i'd like to report.
tokenizer.convert_tokens_to_ids(ntokens)
would generate longer list thanmax_seq_length
when we are using--max_seq_length=128
.so, i ran with
--max_seq_length=150
. it was fine.