Transformer Error

[wac81]

try run code:
./train_all_data_at_once.sh Transformer

then get error

Traceback (most recent call last):
  File "run.py", line 352, in <module>
    main()
  File "run.py", line 329, in main
    train(args, model, tokenizer, device, optimizer, tbwriter)
  File "/home/wac/SentenceSimilarity/random_train.py", line 55, in train
    output = model(input_1, input_2)
  File "/home/wac/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/wac/SentenceSimilarity/models/rcnn_transformer.py", line 82, in forward
    res_sub = self.fc_sub(sentence1, sentence2)
  File "/home/wac/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/wac/SentenceSimilarity/models/rcnn_elements.py", line 17, in forward
    out = self.dense(res_sub_mul)
  File "/home/wac/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/wac/.local/lib/python3.6/site-packages/torch/nn/modules/linear.py", line 91, in forward
    return F.linear(input, self.weight, self.bias)
  File "/home/wac/.local/lib/python3.6/site-packages/torch/nn/functional.py", line 1674, in linear
    ret = torch.addmm(bias, input, weight.t())
RuntimeError: mat1 dim 1 must match mat2 dim 0

maybe dim sentence1 different from sentence2?