0

我正在尝试使用 SimpleTransformers 训练文本分类器。我正在利用 TurkuNLP 语言模型来尝试训练分类器（利用我计算机的 GPU）。

我的代码：

model = ClassificationModel('bert', 'TurkuNLP/wikibert-base-he-cased', num_labels=11, use_cuda=True,
                            args={'reprocess_input_data': True, 'overwrite_output_dir': True, 'fp16': False,
                                   "num_train_epochs": 3, 'sliding_window': True, 'train_batch_size': 6}) 

# You can set class weights by using the optional weight argument

# Train the model
model.train_model(train_df)

# Evaluate the model
result, model_outputs, wrong_predictions = model.eval_model(test_df)

然后我开始训练分类器。但是，一旦第一个训练时期结束，我就会收到警告：

WARNING  py.warnings:99: [JupyterRequire] C:\Users\work\Anaconda3\envs\py35\lib\site-packages\torch\optim\lr_scheduler.py:216: 
UserWarning: Please also save or load the state of the optimizer when saving or loading the scheduler.
warnings.warn(SAVE_STATE_WARNING, UserWarning)

然后，一旦第二个纪元开始，我就会收到以下错误：

---------------------------------------------------------------------------
Empty                                     Traceback (most recent call last)
~\Anaconda3\envs\py35\lib\site-packages\torch\utils\data\dataloader.py
in _try_get_data(self, timeout)
    871         try:
--> 872             data = self._data_queue.get(timeout=timeout)
    873             return (True, data)

~\Anaconda3\envs\py35\lib\multiprocessing\queues.py in get(self, block, timeout)
    104                     if not self._poll(timeout):
--> 105                         raise Empty
    106                 elif not self._poll():

Empty: 

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

RuntimeError                              Traceback (most recent call last)
<ipython-input-31-6ab367d014c4> in <module>
     22 
     23 # Train the model
---> 24 model.train_model(train_df)
     25 
     26 # Evaluate the model

~\AppData\Roaming\Python\Python36\site-packages\simpletransformers\classification\classification_model.py
in train_model(self, train_df, multi_label, output_dir, show_running_loss, args, eval_df, verbose, **kwargs)
    409             eval_df=eval_df,
    410             verbose=verbose,
--> 411             **kwargs,
    412         )
    413 

~\AppData\Roaming\Python\Python36\site-packages\simpletransformers\classification\classification_model.py
in train(self, train_dataloader, output_dir, multi_label, show_running_loss, eval_df, verbose, **kwargs)
    627                 mininterval=0,
    628             )
--> 629             for step, batch in enumerate(batch_iterator):
    630                 if steps_trained_in_current_epoch > 0:
    631                     steps_trained_in_current_epoch -= 1

~\Anaconda3\envs\py35\lib\site-packages\tqdm\notebook.py in __iter__(self, *args, **kwargs)
    232     def __iter__(self, *args, **kwargs):
    233         try:
--> 234             for obj in super(tqdm_notebook, self).__iter__(*args, **kwargs):
    235                 # return super(tqdm...) will not catch exception
    236                 yield obj

~\Anaconda3\envs\py35\lib\site-packages\tqdm\std.py in __iter__(self)
   1169 
   1170         try:
-> 1171             for obj in iterable:
   1172                 yield obj
   1173                 # Update and possibly print the progressbar.

~\Anaconda3\envs\py35\lib\site-packages\torch\utils\data\dataloader.py
in __next__(self)
    433         if self._sampler_iter is None:
    434             self._reset()
--> 435         data = self._next_data()
    436         self._num_yielded += 1
    437         if self._dataset_kind == _DatasetKind.Iterable and \

~\Anaconda3\envs\py35\lib\site-packages\torch\utils\data\dataloader.py
in _next_data(self)
   1066 
   1067             assert not self._shutdown and self._tasks_outstanding > 0
-> 1068             idx, data = self._get_data()
   1069             self._tasks_outstanding -= 1
   1070             if self._dataset_kind == _DatasetKind.Iterable:

~\Anaconda3\envs\py35\lib\site-packages\torch\utils\data\dataloader.py
in _get_data(self)
   1032         else:
   1033             while True:
-> 1034                 success, data = self._try_get_data()
   1035                 if success:
   1036                     return data

~\Anaconda3\envs\py35\lib\site-packages\torch\utils\data\dataloader.py
in _try_get_data(self, timeout)
    883             if len(failed_workers) > 0:
    884                 pids_str = ', '.join(str(w.pid) for w in failed_workers)
--> 885                 raise RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly'.format(pids_str)) from e
    886             if isinstance(e, queue.Empty):
    887                 return (False, None)

RuntimeError: DataLoader worker (pid(s) 15784, 13540, 16356, 15852, 2700, 10548, 21112, 21788, 23504, 23484, 23100, 20344, 22120, 22668, 21924) exited unexpectedly

有任何想法吗？谢谢 ：）

4

0 回答 0