[Question] 运行twitter-17-txt.yaml和twitter-17-img.yaml出错

[qingxiangNo1]

What is your question?

运行twitter-17-txt.yaml和twitter-17-img.yaml出错

What have you tried?

No response

Code (if necessary)

Traceback (most recent call last):
File "/home/nlp/.pycharm_helpers/pydev/pydevd.py", line 1496, in _exec
pydev_imports.execfile(file, globals, locals) # execute the script
File "/home/nlp/.pycharm_helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/home/nlp/code/AdaSeq/examples/MoRe/train.py", line 37, in
train_model_from_args(args)
File "/home/nlp/code/AdaSeq/adaseq/commands/train.py", line 93, in train_model_from_args
checkpoint_path=args.checkpoint_path,
File "/home/nlp/code/AdaSeq/adaseq/commands/train.py", line 164, in train_model
trainer.train(checkpoint_path)
File "/home/nlp/code/AdaSeq/adaseq/training/default_trainer.py", line 146, in train
return super().train(checkpoint_path=checkpoint_path, *args, **kwargs)
File "/home/nlp/anaconda3/envs/MoRe/lib/python3.7/site-packages/modelscope/trainers/trainer.py", line 676, in train
self.train_loop(self.train_dataloader)
File "/home/nlp/anaconda3/envs/MoRe/lib/python3.7/site-packages/modelscope/trainers/trainer.py", line 1171, in train_loop
self.train_step(self.model, data_batch, **kwargs)
File "/home/nlp/anaconda3/envs/MoRe/lib/python3.7/site-packages/modelscope/trainers/trainer.py", line 841, in train_step
train_outputs = model.forward(**inputs)
File "/home/nlp/code/AdaSeq/adaseq/models/sequence_labeling_model.py", line 129, in forward
loss = self._calculate_loss(logits, label_ids, crf_mask)
File "/home/nlp/code/AdaSeq/adaseq/models/sequence_labeling_model.py", line 176, in _calculate_loss
targets = targets * mask
RuntimeError: The size of tensor a (269) must match the size of tensor b (270) at non-singleton dimension 1

Traceback (most recent call last):
File "/home/nlp/.pycharm_helpers/pydev/pydevd.py", line 1496, in _exec
pydev_imports.execfile(file, globals, locals) # execute the script
File "/home/nlp/.pycharm_helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/home/nlp/code/AdaSeq/examples/MoRe/train.py", line 37, in
train_model_from_args(args)
File "/home/nlp/code/AdaSeq/adaseq/commands/train.py", line 93, in train_model_from_args
checkpoint_path=args.checkpoint_path,
File "/home/nlp/code/AdaSeq/adaseq/commands/train.py", line 164, in train_model
trainer.train(checkpoint_path)
File "/home/nlp/code/AdaSeq/adaseq/training/default_trainer.py", line 146, in train
return super().train(checkpoint_path=checkpoint_path, *args, **kwargs)
File "/home/nlp/anaconda3/envs/MoRe/lib/python3.7/site-packages/modelscope/trainers/trainer.py", line 676, in train
self.train_loop(self.train_dataloader)
File "/home/nlp/anaconda3/envs/MoRe/lib/python3.7/site-packages/modelscope/trainers/trainer.py", line 1171, in train_loop
self.train_step(self.model, data_batch, **kwargs)
File "/home/nlp/anaconda3/envs/MoRe/lib/python3.7/site-packages/modelscope/trainers/trainer.py", line 841, in train_step
train_outputs = model.forward(**inputs)
File "/home/nlp/code/AdaSeq/adaseq/models/sequence_labeling_model.py", line 129, in forward
loss = self._calculate_loss(logits, label_ids, crf_mask)
File "/home/nlp/code/AdaSeq/adaseq/models/sequence_labeling_model.py", line 176, in _calculate_loss
targets = targets * mask
RuntimeError: The size of tensor a (299) must match the size of tensor b (300) at non-singleton dimension 1

请问这个问题如何解决

What's your environment?

• AdaSeq Version (e.g., 1.0 or master):
• ModelScope Version (e.g., 1.0 or master):
• PyTorch Version (e.g., 1.12.1):
• OS (e.g., Ubuntu 20.04):
• Python version:
• CUDA/cuDNN version:
• GPU models and configuration:
• Any other relevant information:

Code of Conduct

• I agree to follow this project's Code of Conduct

[ccyeol]

I encountered the same problem, how did you solve it in the end?