Using a Bidirectional Layer causes errror: CancelledError: [_Derived_]RecvAsync is cancelled

I am having an issue where whenever I include a Bidirectional Layer wrapper in my model, it causes a crash during training with the following error:

CancelledError                            Traceback (most recent call last)
<ipython-input-7-7944b517869f> in <module>
      1 history = model.fit(train_dataset, epochs=10,
      2                     validation_data=test_dataset,
----> 3                     validation_steps=30)

D:\Python\anaconda\envs\tf-gpu\lib\site-packages\tensorflow\python\keras\engine\training.py in _method_wrapper(self, *args, **kwargs)
    106   def _method_wrapper(self, *args, **kwargs):
    107     if not self._in_multi_worker_mode():  # pylint: disable=protected-access
--> 108       return method(self, *args, **kwargs)
    109 
    110     # Running inside `run_distribute_coordinator` already.

D:\Python\anaconda\envs\tf-gpu\lib\site-packages\tensorflow\python\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
   1096                 batch_size=batch_size):
   1097               callbacks.on_train_batch_begin(step)
-> 1098               tmp_logs = train_function(iterator)
   1099               if data_handler.should_sync:
   1100                 context.async_wait()

D:\Python\anaconda\envs\tf-gpu\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
    778       else:
    779         compiler = "nonXla"
--> 780         result = self._call(*args, **kwds)
    781 
    782       new_tracing_count = self._get_tracing_count()

D:\Python\anaconda\envs\tf-gpu\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
    805       # In this case we have created variables on the first call, so we run the
    806       # defunned version which is guaranteed to never create variables.
--> 807       return self._stateless_fn(*args, **kwds)  # pylint: disable=not-callable
    808     elif self._stateful_fn is not None:
    809       # Release the lock early so that multiple threads can perform the call

D:\Python\anaconda\envs\tf-gpu\lib\site-packages\tensorflow\python\eager\function.py in __call__(self, *args, **kwargs)
   2827     with self._lock:
   2828       graph_function, args, kwargs = self._maybe_define_function(args, kwargs)
-> 2829     return graph_function._filtered_call(args, kwargs)  # pylint: disable=protected-access
   2830 
   2831   @property

D:\Python\anaconda\envs\tf-gpu\lib\site-packages\tensorflow\python\eager\function.py in _filtered_call(self, args, kwargs, cancellation_manager)
   1846                            resource_variable_ops.BaseResourceVariable))],
   1847         captured_inputs=self.captured_inputs,
-> 1848         cancellation_manager=cancellation_manager)
   1849 
   1850   def _call_flat(self, args, captured_inputs, cancellation_manager=None):

D:\Python\anaconda\envs\tf-gpu\lib\site-packages\tensorflow\python\eager\function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
   1922       # No tape is watching; skip to running the function.
   1923       return self._build_call_outputs(self._inference_function.call(
-> 1924           ctx, args, cancellation_manager=cancellation_manager))
   1925     forward_backward = self._select_forward_and_backward_functions(
   1926         args,

D:\Python\anaconda\envs\tf-gpu\lib\site-packages\tensorflow\python\eager\function.py in call(self, ctx, args, cancellation_manager)
    548               inputs=args,
    549               attrs=attrs,
--> 550               ctx=ctx)
    551         else:
    552           outputs = execute.execute_with_cancellation(

D:\Python\anaconda\envs\tf-gpu\lib\site-packages\tensorflow\python\eager\execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     58     ctx.ensure_initialized()
     59     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 60                                         inputs, attrs, num_outputs)
     61   except core._NotOkStatusException as e:
     62     if name is not None:

CancelledError:  [_Derived_]RecvAsync is cancelled.
     [[{{node gradient_tape/sequential/embedding/embedding_lookup/Reshape/_38}}]] [Op:__inference_train_function_5988]

Function call stack:
train_function

I am running the exact code from the Tensorflow tutorial here: https://www.tensorflow.org/tutorials/text/text_classification_rnn#prepare_the_data_for_training.

Furthermore, I have tried including the lines ''' physical_devices = tf.config.list_physical_devices('GPU') tf.config.experimental.set_memory_growth(physical_devices[0], True) ''' at the start of my program, and I get the same issue.

My Tensorflow version is 2.3.0, Cuda version is 10.1.243, and CUDNN version is 7.6.5.

Does anyone know a possible solution for this problem?