lvwerra/bert-imdb

BERT (bert-large-cased) trained for sentiment classification on the IMDB dataset . The full experiment is available in the tlr repo . The model achieved 90% classification accuracy on the validation set . The library uses a learning rate schedule and learning rate of 1e-5 with the simpletransformers library . It was trained on 80% of the . IMDB . dataset for sentiment . classification for three . epochs with the learning rate . library using the simple transformers library. The library is available to download in the . tlr . repository. It is free to download and use the . tool to test and test your knowledge of the dataset. The full repo is available,