# Errors while fine-tuning using Keras **URL:** \ **Category:** 🤗Transformers\ **Created:** [February 17, 2022, 11:03pm UTC](https://discuss.huggingface.co/t/errors-while-fine-tuning-using-keras/14842 "2022-02-17T23:03:27Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![jwei4](https://avatars.discourse-cdn.com/v4/letter/j/ccd318/32.png) [@jwei4](https://discuss.huggingface.co/u/jwei4)\ **Post date:** [February 17, 2022, 11:03pm UTC](https://discuss.huggingface.co/t/errors-while-fine-tuning-using-keras/14842/1 "2022-02-17T23:03:27Z")
Hello there, I am trying to fine-tune the bart model using pre-downloaded “imdb” datasets following the exact same code from the example [Fine-tuning a pretrained model](https://huggingface.co/docs/transformers/training#finetuning-with-keras) But, I got the value errors message while I am trying to apply model.fit(). I would greatly appreciate if anyone would have any suggestions or comments on this problem. Please let me know! My Code: ```auto from datasets import load_dataset import datasets raw_dataset = datasets.load_from_disk('./train') from transformers import TFAutoModelForSequenceClassification model = TFAutoModelForSequenceClassification.from_pretrained("bert-base-cased", num_labels=2) tokenizer = AutoTokenizer.from_pretrained("bert-base-cased") def tokenize_function(examples): return tokenizer(examples["text"], padding="max_length", truncation=True) tokenized_datasets = raw_dataset.map(tokenize_function, batched=True) small_train_dataset = tokenized_datasets["train"].shuffle(seed=42).select(range(1000)) small_eval_dataset = tokenized_datasets["test"].shuffle(seed=42).select(range(1000)) tf_train_dataset = small_train_dataset.remove_columns(["text"]).with_format("tensorflow") tf_eval_dataset = small_eval_dataset.remove_columns(["text"]).with_format("tensorflow") train_features = {x: tf_train_dataset[x] for x in tokenizer.model_input_names} eval_features = {x: tf_eval_dataset[x] for x in tokenizer.model_input_names} train_tf_dataset = tf.data.Dataset.from_tensor_slices((train_features, tf_train_dataset["label"])) train_tf_dataset = train_tf_dataset.shuffle(len(tf_train_dataset)).batch(8) eval_tf_dataset = tf.data.Dataset.from_tensor_slices((eval_features, tf_eval_dataset["label"])) eval_tf_dataset = train_tf_dataset.batch(8) model.compile( optimizer=tf.keras.optimizers.Adam(learning_rate=5e-5), loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=tf.metrics.SparseCategoricalAccuracy(), ) model.fit(train_tf_dataset, validation_data=eval_tf_dataset, epochs=3) ``` ```auto --------------------------------------------------------------------------- ValueError Traceback (most recent call last) Input In [16], in 1 model.compile( 2 optimizer=tf.keras.optimizers.Adam(learning_rate=5e-5), 3 loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), 4 metrics=tf.metrics.SparseCategoricalAccuracy(), 5 ) ----> 7 model.fit(train_tf_dataset, validation_data=eval_tf_dataset, epochs=3) File ~/work/.local/lib/python3.8/site-packages/keras/engine/training.py:1184, in Model.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) 1177 with tf.profiler.experimental.Trace( 1178 'train', 1179 epoch_num=epoch, 1180 step_num=step, 1181 batch_size=batch_size, 1182 _r=1): 1183 callbacks.on_train_batch_begin(step) -> 1184 tmp_logs = self.train_function(iterator) 1185 if data_handler.should_sync: 1186 context.async_wait() File ~/work/.local/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py:885, in Function. __call__ (self, *args, **kwds) 882 compiler = "xla" if self._jit_compile else "nonXla" 884 with OptionalXlaContext(self._jit_compile): --> 885 result = self._call(*args, **kwds) 887 new_tracing_count = self.experimental_get_tracing_count() 888 without_tracing = (tracing_count == new_tracing_count) File ~/work/.local/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py:933, in Function._call(self, *args, **kwds) 930 try: 931 # This is the first call of __call__ , so we have to initialize. 932 initializers = [] --> 933 self._initialize(args, kwds, add_initializers_to=initializers) 934 finally: 935 # At this point we know that the initialization is complete (or less 936 # interestingly an exception was raised) so we no longer need a lock. 937 self._lock.release() File ~/work/.local/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py:759, in Function._initialize(self, args, kwds, add_initializers_to) 756 self._lifted_initializer_graph = lifted_initializer_graph 757 self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph) 758 self._concrete_stateful_fn = ( --> 759 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access 760 *args, **kwds)) 762 def invalid_creator_scope(*unused_args, **unused_kwds): 763 """Disables variable creation.""" File ~/work/.local/lib/python3.8/site-packages/tensorflow/python/eager/function.py:3066, in Function._get_concrete_function_internal_garbage_collected(self, *args, **kwargs) 3064 args, kwargs = None, None 3065 with self._lock: -> 3066 graph_function, _ = self._maybe_define_function(args, kwargs) 3067 return graph_function File ~/work/.local/lib/python3.8/site-packages/tensorflow/python/eager/function.py:3463, in Function._maybe_define_function(self, args, kwargs) 3459 return self._define_function_with_shape_relaxation( 3460 args, kwargs, flat_args, filtered_flat_args, cache_key_context) 3462 self._function_cache.missed.add(call_context_key) -> 3463 graph_function = self._create_graph_function(args, kwargs) 3464 self._function_cache.primary[cache_key] = graph_function 3466 return graph_function, filtered_flat_args File ~/work/.local/lib/python3.8/site-packages/tensorflow/python/eager/function.py:3298, in Function._create_graph_function(self, args, kwargs, override_flat_arg_shapes) 3293 missing_arg_names = [ 3294 "%s_%d" % (arg, i) for i, arg in enumerate(missing_arg_names) 3295 ] 3296 arg_names = base_arg_names + missing_arg_names 3297 graph_function = ConcreteFunction( -> 3298 func_graph_module.func_graph_from_py_func( 3299 self._name, 3300 self._python_function, 3301 args, 3302 kwargs, 3303 self.input_signature, 3304 autograph=self._autograph, 3305 autograph_options=self._autograph_options, 3306 arg_names=arg_names, 3307 override_flat_arg_shapes=override_flat_arg_shapes, 3308 capture_by_value=self._capture_by_value), 3309 self._function_attributes, 3310 function_spec=self.function_spec, 3311 # Tell the ConcreteFunction to clean up its graph once it goes out of 3312 # scope. This is not the default behavior since it gets used in some 3313 # places (like Keras) where the FuncGraph lives longer than the 3314 # ConcreteFunction. 3315 shared_func_graph=False) 3316 return graph_function File ~/work/.local/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py:1007, in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes, acd_record_initial_resource_uses) 1004 else: 1005 _, original_func = tf_decorator.unwrap(python_func) -> 1007 func_outputs = python_func(*func_args, **func_kwargs) 1009 # invariant: `func_outputs` contains only Tensors, CompositeTensors, 1010 # TensorArrays and `None`s. 1011 func_outputs = nest.map_structure(convert, func_outputs, 1012 expand_composites=True) File ~/work/.local/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py:668, in Function._defun_with_scope..wrapped_fn(*args, **kwds) 664 with default_graph._variable_creator_scope(scope, priority=50): # pylint: disable=protected-access 665 # __wrapped__ allows AutoGraph to swap in a converted function. We give 666 # the function a weak reference to itself to avoid a reference cycle. 667 with OptionalXlaContext(compile_with_xla): --> 668 out = weak_wrapped_fn(). __wrapped__ (*args, **kwds) 669 return out File ~/work/.local/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py:994, in func_graph_from_py_func..wrapper(*args, **kwargs) 992 except Exception as e: # pylint:disable=broad-except 993 if hasattr(e, "ag_error_metadata"): --> 994 raise e.ag_error_metadata.to_exception(e) 995 else: 996 raise ValueError: in user code: /home/jovyan/work/.local/lib/python3.8/site-packages/keras/engine/training.py:853 train_function * return step_function(self, iterator) /home/jovyan/work/.local/lib/python3.8/site-packages/transformers/models/bert/modeling_tf_bert.py:1421 call * outputs = self.bert( /home/jovyan/work/.local/lib/python3.8/site-packages/transformers/models/bert/modeling_tf_bert.py:646 call * raise ValueError("You have to specify either input_ids or inputs_embeds") ValueError: You have to specify either input_ids or inputs_embeds ``` ---
**Author:** ![sgugger](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/sgugger/32/2291_2.png) [@sgugger](https://discuss.huggingface.co/u/sgugger)\ **Post date:** [February 18, 2022, 8:57am UTC](https://discuss.huggingface.co/t/errors-while-fine-tuning-using-keras/14842/2 "2022-02-18T08:57:19Z")
Note that this example, has recently been updated (see the [master doc](https://huggingface.co/docs/transformers/master/en/training#finetune-with-keras)). ---
**Author:** ![jwei4](https://avatars.discourse-cdn.com/v4/letter/j/ccd318/32.png) [@jwei4](https://discuss.huggingface.co/u/jwei4)\ **Post date:** [February 18, 2022, 6:58pm UTC](https://discuss.huggingface.co/t/errors-while-fine-tuning-using-keras/14842/3 "2022-02-18T18:58:48Z")
Thank you! But, I am wondering if I did anything wrong with my current code? Why it would raise value error? If you could share any your thoughts, that would be really helpful!