Defa Zhu

### ❓ The question What determines whether a metric uses acc or len_norm? It seems the only difference between them is whether the score for the continuation is divided by...

Thank you for your excellent work. If I want to use DCLM-BASELINE for pretraining and conduct a rigorous comparison with the DCLM-BASELINE 7B model, what hyper-parameters should I use? Could...