training 设置报错

[xy-derrick]

training 设置报错

[ChenCyril]

我也有点奇怪...用GPU跑就报这个错，CPU跑倒是没问题emmm...

[enchantee00]

change
bert_param = list(self.rec_model.module.bert.named_parameters())
to
bert_param = list(self.rec_model.bert.named_parameters())

Can fix this error

[nguyenminhduc392002]

"Traceback (most recent call last):
File "/opt/conda/lib/python3.10/site-packages/nltk/util.py", line 468, in ngrams
history.append(next(sequence))
StopIteration

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/kaggle/working/CRSLab-main/run_crslab.py", line 43, in
run_crslab(config, args.save_data, args.restore_data, args.save_system, args.restore_system, args.interact,
File "/kaggle/working/CRSLab-main/crslab/quick_start/quick_start.py", line 73, in run_crslab
CRS.fit()
File "/kaggle/working/CRSLab-main/crslab/system/inspired.py", line 206, in fit
self.train_conversation()
File "/kaggle/working/CRSLab-main/crslab/system/inspired.py", line 188, in train_conversation
self.step((batch), stage='conv', mode='val')
File "/kaggle/working/CRSLab-main/crslab/system/inspired.py", line 120, in step
self.conv_evaluate(pred, batch[-1])
File "/kaggle/working/CRSLab-main/crslab/system/inspired.py", line 89, in conv_evaluate
self.evaluator.gen_evaluate(p_str, [r_str])
File "/kaggle/working/CRSLab-main/crslab/evaluator/standard.py", line 80, in gen_evaluate
for token in ngrams(hyp, k):
RuntimeError: generator raised StopIteration" Can you help me fix this error?