Lesi Chen
Lesi Chen
同问，训练过程似乎不收敛
> when running with bash run_wt103_base.sh train --work_dir TRAIN_wt103, the same problem happens to me as well. The pytorch version is 1.12, gpu is 3090 and cuda version is 11.3....
> Might be relevant to my observations as well. See #4 Thanks a lot.
> Hi, thank you for your interest in our work! Did it happen a lot over a wide range of queries after training or just a small number? > >...
Thanks a lot for your reply! I will keep trying.
I think I may have found the reason. The "use_gt_labels" in the file `train_cllm_global.py` should be set to **False**, instead of the default setting of **True**. After this modification, the...
I use exactly the same dataset and train for a whole epoch, but no matter whether setting use_gt_labels as True/ False can not have the desired result.
But after this modification, the accuracy becomes 0.0. It seems that this modification is not correct.
But it is strange that setting use_gt_labels=False still does not solve this problem.