helloworldSnow

> 先说一下我的运行环境：这份代码貌似问题有点儿多啊！（1）DGLREDataloader 类中的使用for循环对mapping的zero_（）操作是否有点儿冗余，直接将外层声明tensor的语句放到for循环内部不就可以了吗？`dgl 0.6.1 torch 1.8.0` 您好，可以详细说一下您的环境配置吗？

have you solved this problem？

> Loaded train features Loaded dev features Loaded test features Some weights of the model checkpoint at bert-base-cased were not used when initializing BertModel: ['cls.predictions.decoder.weight', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.seq_relationship.weight', 'cls.predictions.bias', 'cls.seq_relationship.bias',...

> 我已经想通了。这是一个顶点的错误。[英伟达/apex@BA027dd #r100574972](https://github.com/NVIDIA/apex/commit/ba027dd0bac621a5c3d16bfb90d73e2d48d2588e#r100574972) may i ask how you solved this problem