So I started to use Autotrain to create token classification model, specifically, NER. I have two csv files I am using to train the model I chose, the training csv file which consists of 46,198 rows with each one consisting of either a single word or punctuation symbol and the validation csv which consists of 20,343 rows consisting of either a single word or punctuation symbol and with the first volume being the words/punctuations themselves and the second column being the indicator. The Autotrain has been stuck on the getting ready part for the past 30 minutes to a hour and I was wondering how long it normally takes to get ready?
After a time, I get the error:
Error type: ValueError
Details: Failed to parse ‘Super’ as a sequence at row 0: malformed node or string: <_ast.Name object at 0x7f64ba860c70>
how do I fix this?
it seems to be a issue with my dataset, I will have to figure out how to properly format it so that auto train can use it