Bakobiibizo/nimble-bert-v2

TextAttack Model Card

        This `lstm` model was fine-tuned using TextAttackand the *yelp_polarity* dataset loaded using the huggingface library. The model was fine-tuned for 50 epochs with a batch size of 8, a maximum sequence length of 128, and an initial learning rate of 1e-05.
        Since this was a classification task, the model was trained with a cross-entropy loss function. The best score the model achieved on this task was 0.9174473684210527, as measured by the eval set accuracy, found after 28 epochs.

        For more information on the source repo, check out [TextAttack on Github](https://github.com/QData/TextAttack).