请问下这是什么问题啊？我看网上说是标签越界了

[cst781]

Traceback (most recent call last): File "run.py", line 70, in main(cmd_args) File "run.py", line 52, in main trainer.train(train_loader=train_loader) File "/home/shaotianc/OpenTransformer/otrans/train.py", line 91, in train train_loss = self.train_one_epoch(epoch, train_loader.loader) File "/home/shaotianc/OpenTransformer/otrans/train.py", line 137, in train_oneepoch loss = self.model(*batch) File "/home/shaotianc/miniconda3/envs/py35/lib/python3.5/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(input, **kwargs) File "/home/shaotianc/OpenTransformer/otrans/model/transformer.py", line 54, in forward logits, = self.decoder(target_in, targets_length, enc_states, enc_mask) File "/home/shaotianc/miniconda3/envs/py35/lib/python3.5/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(*input, *kwargs) File "/home/shaotianc/OpenTransformer/otrans/decoder.py", line 39, in forward dec_output = self.pos_encoding(dec_output) File "/home/shaotianc/miniconda3/envs/py35/lib/python3.5/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(input, **kwargs) File "/home/shaotianc/OpenTransformer/otrans/module.py", line 51, in forward self.extend_pe(x) File "/home/shaotianc/OpenTransformer/otrans/module.py", line 30, in extend_pe self.pe = self.pe.to(dtype=x.dtype, device=x.device) RuntimeError: CUDA error: device-side assert triggered