Xia Qiang Tang
Xia Qiang Tang
i think the randomness is caused by the usage of nondeterministic-algorithms , which means even you set all the random seed ,the result will still have some randomness. check it...
> Hello, Thanks for your nice project. > > I tried to train the model several times without code editing, then I found that the difference in performance of each...
Thanks for clearance, after evaluation I got following results, seems match with paper: `Number of questions: 1639 Average precision over questions: 0.785 Average recall over questions: 0.814 Average f1 over...
Reward 在policy_gradient_loss就用于训练了，后面的二值化后处理只是为了借用reward计算在数据集上的精度
I believe this is created when running https://github.com/[starsuzi/Adaptive-RAG](https://github.com/starsuzi/Adaptive-RAG). If you reproduce their work, you can get this file.