training custom dataset for 40 class it gives dtype error in dataloader function

[vijay180396]

1.system configuration ->[os]windows 10 ->[gpu]Geforce RTX 3060 ti vram 8gb

2.pretrained weight file using -> resnet101__.pth

3.i have trained 3 classes with own custom dataset of images 476 it train successfully. i can also able to detect images with created weight file

4. And then i try to training for 40 classes with own custom dataset of images 1632. -> it shows an expection like: [ 0] 570 || B: 2.338 | C: 3.751 | M: 4.859 | S: 0.322 | T: 11.270 || ETA: 84 days, 11:22:34 || timer: 0.213 Traceback (most recent call last): File "train.py", line 504, in train() File "train.py", line 270, in train for datum in data_loader: File "C:\Users\admin\anaconda3\envs\yolact\lib\site-packages\torch\utils\data\dataloader.py", line 517, in next data = self._next_data() File "C:\Users\admin\anaconda3\envs\yolact\lib\site-packages\torch\utils\data\dataloader.py", line 1179, in _next_data return self._process_data(data) File "C:\Users\admin\anaconda3\envs\yolact\lib\site-packages\torch\utils\data\dataloader.py", line 1225, in _process_data data.reraise() File "C:\Users\admin\anaconda3\envs\yolact\lib\site-packages\torch_utils.py", line 429, in reraise raise self.exc_type(msg) TypeError: init() missing 1 required positional argument: 'dtype'

and please mention if i need to add..