关于loss变得异常大的问题

[tomtang110]

loss在某一部分数据变得异常大，最后导致验证集所有分数为0. 请问，是怎么产生的呢？

[pluto-junzeng]

您好，我也遇到了，这类情况，请问您解决了吗，可以分享下吗

[pluto-junzeng]

total_loss += loss * len(batch['raw_data'])

[tomtang110]

换模型吧，QA模型对中文数据集敏感太大。 获取 Outlook for Android<https://aka.ms/ghei36>

…

________________________________ From: 曾俊 <notifications@github.com> Sent: Monday, March 25, 2019 11:01:06 PM To: SeanLee97/QANet_dureader Cc: tomtang110; Author Subject: Re: [SeanLee97/QANet_dureader] 关于loss变得异常大的问题 (#8) 您好，我也遇到了，这类情况，请问您解决了吗，可以分享下吗 ― You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub<#8 (comment)>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AfwcQhhPHWl_cyxYiKoXlDaofMye6gKzks5vaLqCgaJpZM4aJC_z>.

[YeDeming]

我也遇到了这种情况

[fanweifengdw]

拿全部数据集训练也有这个问题，确定代码没问题？？

[tomtang110]

检验过代码确实没啥明显问题 获取 Outlook for Android<https://aka.ms/ghei36>

…

________________________________ From: fanweifengdw <notifications@github.com> Sent: Thursday, June 6, 2019 1:06:33 PM To: SeanLee97/QANet_dureader Cc: tomtang110; Author Subject: Re: [SeanLee97/QANet_dureader] 关于loss变得异常大的问题 (#8) 拿全部数据集训练也有这个问题，确定代码没问题？？ ― You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub<#8?email_source=notifications&email_token=AH6BYQUANL4IPVGATA4CXS3PZB5LTA5CNFSM4GREF7Z2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODXBS6XI#issuecomment-499330909>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AH6BYQQS6ISW2GXGB4QUSTTPZB5LTANCNFSM4GREF7ZQ>.

[sarahyq]

有没有报错的代码吗？我直接用代码报TypeError: Failed to convert object of type <class 'list'> to Tensor. Contents: [32000, 20, Dimension(32)]. Consider casting elements to a supported type.错误

[tomtang110]

这个真不适合中文，都什么年代了用bert吧，可以训练但是中文数据集不好 获取 Outlook for Android<https://aka.ms/ghei36>

…

________________________________ From: sarahyq <notifications@github.com> Sent: Thursday, June 20, 2019 7:42:10 PM To: SeanLee97/QANet_dureader Cc: tomtang110; Author Subject: Re: [SeanLee97/QANet_dureader] 关于loss变得异常大的问题 (#8) 有没有报错的代码吗？我直接用代码报TypeError: Failed to convert object of type <class 'list'> to Tensor. Contents: [32000, 20, Dimension(32)]. Consider casting elements to a supported type.错误 ― You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub<#8?email_source=notifications&email_token=AH6BYQVNIAXMOPTPP7NAFYLP3NGHFA5CNFSM4GREF7Z2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODYE4OMY#issuecomment-503957299>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AH6BYQQX6M7KM5Q2NGABWELP3NGHFANCNFSM4GREF7ZQ>.

[sarahyq]

换模型吧，QA模型对中文数据集敏感太大。 获取 Outlook for Androidhttps://aka.ms/ghei36
…
________________________________ From: 曾俊 notifications@github.com Sent: Monday, March 25, 2019 11:01:06 PM To: SeanLee97/QANet_dureader Cc: tomtang110; Author Subject: Re: [SeanLee97/QANet_dureader] 关于loss变得异常大的问题 (#8) 您好，我也遇到了，这类情况，请问您解决了吗，可以分享下吗 ― You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub<#8 (comment)>, or mute the threadhttps://github.com/notifications/unsubscribe-auth/AfwcQhhPHWl_cyxYiKoXlDaofMye6gKzks5vaLqCgaJpZM4aJC_z.
有分析出为什么中文不好吗？

[tomtang110]

这种情况非常罕见，我觉得可能涉及到，语义的一些东西在里面，只能说QAnet这个网络设计的不够general。你看同是selfattention机制，bert和今天才出的xlnet就具有泛化。 获取 Outlook for Android<https://aka.ms/ghei36>

…

________________________________ From: sarahyq <notifications@github.com> Sent: Thursday, June 20, 2019 8:26:32 PM To: SeanLee97/QANet_dureader Cc: tomtang110; Author Subject: Re: [SeanLee97/QANet_dureader] 关于loss变得异常大的问题 (#8) 换模型吧，QA模型对中文数据集敏感太大。 获取 Outlook for Androidhttps://aka.ms/ghei36 …

________________________________ From: 曾俊 notifications@github.com<mailto:notifications@github.com> Sent: Monday, March 25, 2019 11:01:06 PM To: SeanLee97/QANet_dureader Cc: tomtang110; Author Subject: Re: [SeanLee97/QANet_dureader] 关于loss变得异常大的问题 (#8<#8>) 您好，我也遇到了，这类情况，请问您解决了吗，可以分享下吗 D You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub<#8 (comment)<#8 (comment)>>, or mute the threadhttps://github.com/notifications/unsubscribe-auth/AfwcQhhPHWl_cyxYiKoXlDaofMye6gKzks5vaLqCgaJpZM4aJC_z. 有分析出为什么中文不好吗？ ― You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub<#8?email_source=notifications&email_token=AH6BYQXBMMROYHGXXABG6MLP3NLNRA5CNFSM4GREF7Z2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODYFAAMI#issuecomment-503971889>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AH6BYQU6GFB763LRYERUUKTP3NLNRANCNFSM4GREF7ZQ>.

[weinixuehao]

The model can be used for production?