直接运行ner_ElectraTrain_dist.sh，在半个epoch F1可以达到90以上。你再检查下数据或模型是不是有问题？ about textbrewer

[houpanpan]

在ElectraTrain base模型是可以复现结果的，但是把教师模型改为bert模型，为啥finetune的结果非常差呢，是需要改哪些参数嘛

[airaria]

中文Electra的学习率较大。用bert时你把学习率调小到3e-5、2e-5试试 在 2021-03-22 08:43:23，"houpanpan" ***@***.***> 写道： 在ElectraTrain base模型是可以复现结果的，但是把教师模型改为bert模型，为啥finetune的结果非常差呢，是需要改哪些参数嘛 — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

[houpanpan]

前辈您好，NER任务的finetune过程，我将模型改为bert-base后，学习率改为2e-5/3e-5，衰减系数为1，反复试验多次，结果均很差很差，是我哪里设置出了问题嘛，按理说F1结果应该在90%才对啊，求指导，谢谢。

[stale]

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

[stale]

Closing the issue, since no updates observed. Feel free to re-open if you need any further assistance.