You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
官方例子使用gpu微调,但我的显卡不支持最低的配置要求。我试图把finetune.py中的model.half()改为model.float(),然后运行finetune_pt脚本,看起来似乎可以进行微调。虽然很慢(我降低了MAX_STEP为100)但仍然可以得到输出的pytorch_model.bin。
现在的问题是,我在运行inference.py传入--pt-checkpoint测试时,模型似乎并没有学习到我微调给予的问答知识。
我感觉还是哪里做得不对,请问官方能否给一个只用cpu进行微调的例子?毕竟微调显卡对多数人可能仍然要求过高,需要租借或购买不是很方便,能否给个cpu微调方案或者例子,谢谢!
Beta Was this translation helpful? Give feedback.
All reactions