The accuracy of MATH test set trained on 7B is not consistent with paper.

[caihaunqai]

Hello，Using MetaMATH dataset and codes, I reproduce the experiments on 7B base model. Howerver, The accuracy I get is as follows, 17.14%, which is not consistent with yours 19.8%. Is there anything wrong with your results in the paper or anything wrong with my experiments? Can you help me? Thank you.

start=== 0 , end==== 9223372036854775807
length==== 5000 , acc==== 0.1714

[2018211801]

Hi, I train 100k subset of Metamath on 7B base model, while get 0 with math test and 0.5 with gsm8k. Is there anything wrong with my experiments?