textattack/albert-base-v2-STS-B

Albert-base-v2 model was fine-tuned for sequence classification using TextAttack . The best score the model achieved on this task was 0.9064220351504577, as measured by the eval set pearson correlation, found after 3 epochs . The model was trained with a mean squared error loss function . For more information, check out TextAttack on Github and the nlp library on the TextAttack website . For example, TextAttack has been updated with a new version of TextAttack and the latest version of this article has been published on the website. For more info, visit TextAttack.com/textAttack.io . Back to the page you,