search

keyu-tian / SparK

[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"
https://arxiv.org/abs/2301.03580
MIT License
1.41k stars 82 forks source link

训练问题 #48

Closed Wuqiman closed 11 months ago

Wuqiman commented 1 year ago

请问有在训练过程中出现这个问题吗？ image

keyu-tian commented 1 year ago

我们没有遇到过这种问题，可以google一下看看