APiaoG

Hello, I have also encountered the same problem. Have you resolved this issue?

我猜测这可能与gsm8k 训练集和测试集传入eval_loss的方式有关，我采用的是question + ‘ ’ + answer的方式构造类似Skywork/mock_gsm8k_test数据集的text传入进行计算，我想问一下您实现的时候是如何构造的呢？

> 我们也是直接拼接起来的，和您的拼接方式似乎没有什么区别，下面是两条我们拼接的样例。 {"text": "Tina makes $18.00 an hour. If she works more than 8 hours per shift, she is eligible for overtime, which is paid by your hourly wage +...