Following the tutorial about text model on fastai V1, instead of fine tuning the WT103_1 model, I’d like to create a new model and train it from scratch. But I got the error: VauleError: can't optimize a non-leaf Tensor
. The code is as follows:
path = untar_data(URLs.IMDB_SAMPLE)
data_lm = TextLMDataBunch.from_csv(path, ‘texts.csv’)
learn = language_model_learner(data_lm, drop_mult=0.5)
learn.fit(1) (caused the error)