Thanks for your work, when I finetuned the huge model in the setting of 1 percent of labels, I met a question about precision. when I used mixed precision, I always got the loss nan question.
but when I use fp32 precision, the accuracy of the classifier is 79.4.
So how can I solve this question? Thank you very much.
Thanks for your work, when I finetuned the huge model in the setting of 1 percent of labels, I met a question about precision. when I used mixed precision, I always got the loss nan question.
but when I use fp32 precision, the accuracy of the classifier is 79.4.
So how can I solve this question? Thank you very much.