Ptt 大爆卦 | Train BERT - 前往 https://www.quora.com/How-much-training-data-is-needed-to-fine-tune-a-BERT-like-model-for-a-closed-domain-problem

你即將離開本站

並前往https://www.quora.com/How-much-training-data-is-needed-to-fine-tune-a-BERT-like-model-for-a-closed-domain-problem

How much training data is needed to fine-tune a BERT-like ...

It very likely depends on your downstream task but from personal experience it does not take too much data to adapt a pretrained BERT model to specific ...

確定！回上一頁

查詢「Train BERT」的人也找了：

BertForSequenceClassification