opencompass测评结果为--，没有显示内容

运行代码是教程里的demo代码：
`python run.py --datasets ceval_gen --hf-path /share/temp/model_repos/internlm-chat-7b/ --tokenizer-path /share/temp/model_repos/internlm-chat-7b/ --tokenizer-kwargs padding_side='left' truncation='left' trust_remote_code=True --model-kwargs trust_remote_code=True device_map='auto' --max-seq-len 2048 --max-out-len 16 --batch-size 4 --num-gpus 1 --debug`
我的batch size设了1 2 4，都试过了，debug的过程一直有error。
报错图片如下

Start with the tutorial demo command in run.py and reproduce the ceval_gen evaluation with the reported model and batch-size settings. Inspect the errors shown during --debug, then identify why the evaluation result is displayed as '--'; done means the command completes with visible evaluation content.

Vom Indexierungsmodell aus dem Issue-Text verfasst.