GPU下train 模型出现nan

When training on GPU, the error "Model diverged with loss = NaN" is often caused by a sotmax that's getting a symbol larger than vocab_size

   

转载于:https://www.cnblogs.com/wuxiangli/p/10344259.html

总结

以上是生活随笔为你收集整理的GPU下train 模型出现nan的全部内容，希望文章能够帮你解决所遇到的问题。

如果觉得生活随笔网站内容还不错，欢迎将生活随笔推荐给好友。