[General Issue] Training loss

[kkpssr]

训练loss越来越高，eval准确率召回率越来越低，前10个epoch结果还好(eval结果miou 0.6)，再跑10个epoch miou直接归0

[shiyutang]

训练结果不理想有很多原因导致，包含学习率过大，训练数据中出现脏数据等，建议给出数据集、模型、代码中修改内容等详细信息用于问题排查。

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.