alchowiw

> Hi all, apologies for the late reply.大家好，很抱歉回复晚了。 > > Yes, this is definitely a typo in the table, sorry about that.是的，这绝对是表格中的拼写错误，很抱歉。 > > I can try to dig up...

> [@QingyangZhang](https://github.com/QingyangZhang) maybe you can try the following:也许您可以尝试以下方法： > > * reduce `lora_r` and `lora_r` in `base_training_args.sh`减少`base_training_args.sh中的lora_r`和`lora_r` > * use a subset of training data, change `train_files` in `warmup_lora_train.sh` with...