Lr_find error

Part 1 (2019)
1

Hi,
I jumped right into IMDB course and trying to customize the notebook for my own dataset which is a simple dataframe instead of text files in some folders. I went through the Language model training part and get elegant accuracy but when I try to apply similar code to build a binary classifier, this error shows for lr_find(): “TypeError: ‘str’ object cannot be interpreted as an integer”

My code is like this after having a language model:

data_clas = (TextClasDataBunch.from_df(’’, rev_train_set, rev_val_set, text_cols=0, label_cols=1, vocab=review_lm.vocab))

data_clas.save(‘data_clas.pkl’)

data_clas = TextClasDataBunch.load(’’, ‘data_clas.pkl’, bs=40)

learn = text_classifier_learner(data_clas, ‘AWD_LSTM’, drop_mult=0.5)

learn.load_encoder(‘fine_tuned_enc’)

learn.lr_find()

(I’ve also tried updating my fastai package to version 1.0.58 but still not working…)
Please LMK any thoughts on it! Thanks!

2

Could you double check to see if you wrote or copied your code correctly? Just something I see that is confusing with the code:
learn = text_classifier_learner(data_clas, ‘AWD_LSTM’, drop_mult=0.5) --> AWD_LSTM isn’t a string, rather it’s a variable that is imported with all the fastai text stuff.