AI正在发生 未来正在更新bert-base-uncased-yelp-polarity
This `bert-base-uncased` model was fine-tuned for sequence classification using TextAttack and the yelp_polarity dataset loaded using the `nlp` library. The model was fine-tuned for 5 epochs with a batch size of 16, a learning rate of 5e-05, and a maximum sequence length of 256. 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 0.9699473684210527, as measured by the eval set accuracy, found after 4 epochs.
译文尚未就绪，显示来源原文
This `bert-base-uncased` model was fine-tuned for sequence classification using TextAttack and the yelp_polarity dataset loaded using the `nlp` library. The model was fine-tuned for 5 epochs with a batch size of 16, a learning rate of 5e-05, and a maximum sequence length of 256. 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 0.9699473684210527, as measured by the eval set accuracy, found after 4 epochs.