bert-authorship-verification

Trained on 50K pairs from the swan07/authorship-verification dataset using: - Learning rate: 2e-5 - Batch size: 16 - Epochs: 4 - Loss: CosineSimilarityLoss swan07/authorship-verification - 325K text pairs from 12 sources including PAN competitions (2011-2020).

译文尚未就绪，显示来源原文