TF DeBERTa fit raise an error

Is there anyone who successfully use DeBERTa with model.fit?
When I use fit, the following error is raised.

Traceback (most recent call last):
  File "/usr/lib/python3.8/runpy.py", line 194, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/usr/lib/python3.8/runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "/app/plm_finetune/__main__.py", line 46, in <module>
    tasks[args.task].run(config)
  File "/app/plm_finetune/abusing/train.py", line 267, in run
    model.fit(
  File "/usr/local/lib/python3.8/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/framework/func_graph.py", line 1129, in autograph_handler
    raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:

    File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 878, in train_function  *
        return step_function(self, iterator)
    File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 867, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 860, in run_step  **
        outputs = model.train_step(data)
    File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 808, in train_step
        y_pred = self(x, training=True)
    File "/usr/local/lib/python3.8/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler
        raise e.with_traceback(filtered_tb) from None

    ValueError: Exception encountered when calling layer "text_classification_head" (type TextClassificationHead).
    
    in user code:
    
        File "/app/plm_finetune/common/heads.py", line 32, in call  *
            encoder_outputs = self.model(plm_input_features, training=training)
        File "/usr/local/lib/python3.8/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler  **
            raise e.with_traceback(filtered_tb) from None
    
        ValueError: Exception encountered when calling layer "tf_deberta_model" (type TFDebertaModel).
        
        in user code:
        
            File "/usr/local/lib/python3.8/dist-packages/transformers/modeling_tf_utils.py", line 1093, in run_call_with_unpacked_inputs  *
                return func(self, **unpacked_inputs)
            File "/usr/local/lib/python3.8/dist-packages/transformers/models/deberta/modeling_tf_deberta.py", line 1099, in call  *
                outputs = self.deberta(
            File "/usr/local/lib/python3.8/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler  **
                raise e.with_traceback(filtered_tb) from None
        
            ValueError: Exception encountered when calling layer "deberta" (type TFDebertaMainLayer).
            
            in user code:
            
                File "/usr/local/lib/python3.8/dist-packages/transformers/modeling_tf_utils.py", line 1093, in run_call_with_unpacked_inputs  *
                    return func(self, **unpacked_inputs)
                File "/usr/local/lib/python3.8/dist-packages/transformers/models/deberta/modeling_tf_deberta.py", line 957, in call  *
                    encoder_outputs = self.encoder(
                File "/usr/local/lib/python3.8/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler  **
                    raise e.with_traceback(filtered_tb) from None
            
                ValueError: Exception encountered when calling layer "encoder" (type TFDebertaEncoder).
                
                in user code:
                
                    File "/usr/local/lib/python3.8/dist-packages/transformers/models/deberta/modeling_tf_deberta.py", line 359, in call  *
                        layer_outputs = layer_module(
                    File "/usr/local/lib/python3.8/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler  **
                        raise e.with_traceback(filtered_tb) from None
                
                    ValueError: Exception encountered when calling layer "layer_._0" (type TFDebertaLayer).
                    
                    in user code:
                    
                        File "/usr/local/lib/python3.8/dist-packages/transformers/models/deberta/modeling_tf_deberta.py", line 270, in call  *
                            attention_outputs = self.attention(
                        File "/usr/local/lib/python3.8/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler  **
                            raise e.with_traceback(filtered_tb) from None
                    
                        ValueError: Exception encountered when calling layer "attention" (type TFDebertaAttention).
                        
                        in user code:
                        
                            File "/usr/local/lib/python3.8/dist-packages/transformers/models/deberta/modeling_tf_deberta.py", line 205, in call  *
                                attention_output = self.dense_output(
                            File "/usr/local/lib/python3.8/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler  **
                                raise e.with_traceback(filtered_tb) from None
                        
                            ValueError: Exception encountered when calling layer "output" (type TFDebertaSelfOutput).
                            
                            in user code:
                            
                                File "/usr/local/lib/python3.8/dist-packages/transformers/models/deberta/modeling_tf_deberta.py", line 171, in call  *
                                    hidden_states = self.dense(hidden_states)
                                File "/usr/local/lib/python3.8/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler  **
                                    raise e.with_traceback(filtered_tb) from None
                                File "/usr/local/lib/python3.8/dist-packages/keras/layers/core/dense.py", line 139, in build
                                    raise ValueError('The last dimension of the inputs to a Dense layer '
                            
                                ValueError: The last dimension of the inputs to a Dense layer should be defined. Found None. Full input shape received: (None, 128, None)
                            
                            
                            Call arguments received:
                              • hidden_states=tf.Tensor(shape=(None, 128, None), dtype=float32)
                              • input_tensor=tf.Tensor(shape=(None, 128, 768), dtype=float32)
                              • training=True
                        
                        
                        Call arguments received:
                          • input_tensor=tf.Tensor(shape=(None, 128, 768), dtype=float32)
                          • attention_mask=tf.Tensor(shape=(None, 1, 128, 128), dtype=uint8)
                          • query_states=None
                          • relative_pos=None
                          • rel_embeddings=None
                          • output_attentions=False
                          • training=True
                    
                    
                    Call arguments received:
                      • hidden_states=tf.Tensor(shape=(None, 128, 768), dtype=float32)
                      • attention_mask=tf.Tensor(shape=(None, 1, 128, 128), dtype=uint8)
                      • query_states=None
                      • relative_pos=None
                      • rel_embeddings=None
                      • output_attentions=False
                      • training=True
                
                
                Call arguments received:
                  • hidden_states=tf.Tensor(shape=(None, 128, 768), dtype=float32)
                  • attention_mask=tf.Tensor(shape=(None, 128), dtype=float32)
                  • query_states=None
                  • relative_pos=None
                  • output_attentions=False
                  • output_hidden_states=False
                  • return_dict=True
                  • training=True
            
            
            Call arguments received:
              • self=tf.Tensor(shape=(None, 128), dtype=int32)
              • input_ids=None
              • attention_mask=tf.Tensor(shape=(None, 128), dtype=float32)
              • token_type_ids=None
              • position_ids=None
              • inputs_embeds=None
              • output_attentions=False
              • output_hidden_states=False
              • return_dict=True
              • training=True
        
        
        Call arguments received:
          • self=('tf.Tensor(shape=(None, 128), dtype=int32)', 'tf.Tensor(shape=(None, 128), dtype=float32)')
          • input_ids=None
          • attention_mask=None
          • token_type_ids=None
          • position_ids=None
          • inputs_embeds=None
          • output_attentions=None
          • output_hidden_states=None
          • return_dict=None
          • training=True
    
    
    Call arguments received:
      • plm_input_features=('tf.Tensor(shape=(None, 128), dtype=int32)', 'tf.Tensor(shape=(None, 128), dtype=float32)')
      • training=True