data/de_sentiment , path has train.csv/test.csv with labels, text as columns, even by shuffling as well show batch is tokenizing, Not sure why it is populaitng as such, any help is greatly apprecisted.,
My problem statement that is trying is as follows:
1) Get german pretrained using multifit.from_pretrained("de_multifit_paper_version")
2) create custom classifer dataset and fine tune on top of german pretrained
3) classify custom dataset
suryapa1
commented
4 years ago 
exp = multifit.from_pretrained("de_multifit_paper_version") cls_dataset = exp.arch.dataset(Path('data/de_sentiment'), exp.pretrain_lm.tokenizer) cls_dataset.load_clas_databunch(bs=exp.finetune_lm.bs).show_batch()
data/de_sentiment , path has train.csv/test.csv with labels, text as columns, even by shuffling as well show batch is tokenizing, Not sure why it is populaitng as such, any help is greatly apprecisted.,
My problem statement that is trying is as follows: 1) Get german pretrained using multifit.from_pretrained("de_multifit_paper_version") 2) create custom classifer dataset and fine tune on top of german pretrained 3) classify custom dataset
Any example is greatly appreciated as well,