How to use the lightwood.constants.lightwood.ENCODER_AIM.BALANCE function in lightwood

self.desired_error = 0.01
        self.max_training_time = 7200
        self._head = None
        # Possible: speed, balance, accuracy
        self.aim = aim

        if self.aim == ENCODER_AIM.SPEED:
            # uses more memory, takes very long to train and outputs weird debugging statements to the command line,
            # consider waiting until it gets better or try to investigate why this happens
            # (changing the pretrained model doesn't seem to help)
            self._classifier_model_class = AlbertForSequenceClassification
            self._embeddings_model_class = AlbertModel
            self._tokenizer_class = AlbertTokenizer
            self._pretrained_model_name = 'albert-base-v2'
            self._model_max_len = 768
        if self.aim == ENCODER_AIM.BALANCE:
            self._classifier_model_class = DistilBertForSequenceClassification
            self._embeddings_model_class = DistilBertModel
            self._tokenizer_class = DistilBertTokenizer
            self._pretrained_model_name = 'distilbert-base-uncased'
            self._model_max_len = 768
        if self.aim == ENCODER_AIM.ACCURACY:
            self._classifier_model_class = DistilBertForSequenceClassification
            self._embeddings_model_class = DistilBertModel
            self._tokenizer_class = DistilBertTokenizer
            self._pretrained_model_name = 'distilbert-base-uncased'
            self._model_max_len = 768

        self.device, _ = get_devices()

    def __init__(self, is_target=False, aim=ENCODER_AIM.BALANCE):
        self._prepared = False
        self.aim = aim
        self._pytorch_wrapper = torch.FloatTensor
        if self.aim == ENCODER_AIM.SPEED:
            self.ngram_range = (1,3)
            self.max_features = 200
        elif self.aim == ENCODER_AIM.BALANCE:
            self.ngram_range = (1,5)
            self.max_features = 500
        elif self.aim == ENCODER_AIM.ACCURACY:
            self.ngram_range = (1,8)
            self.max_features = None

def __init__(self, is_target=False, aim=ENCODER_AIM.BALANCE):
        self._prepared = False
        self.aim = aim
        self._pytorch_wrapper = torch.FloatTensor
        if self.aim == ENCODER_AIM.SPEED:
            self.ngram_range = (1,3)
            self.max_features = 200
        elif self.aim == ENCODER_AIM.BALANCE:
            self.ngram_range = (1,5)
            self.max_features = 500
        elif self.aim == ENCODER_AIM.ACCURACY:
            self.ngram_range = (1,8)
            self.max_features = None

    def __init__(self, is_target=False, aim=ENCODER_AIM.BALANCE):
        self.name = 'Text Transformer Encoder'
        self._tokenizer = None
        self._model = None
        self._pad_id = None
        self._pytorch_wrapper = torch.FloatTensor
        self._max_len = None
        self._max_ele = None
        self._prepared = False
        self._model_type = None
        self.desired_error = 0.01
        self.max_training_time = 7200
        self._head = None
        # Possible: speed, balance, accuracy
        self.aim = aim

        if self.aim == ENCODER_AIM.SPEED:

def prepare_encoder(self, priming_data):
        if self._prepared:
            raise Exception('You can only call "prepare_encoder" once for a given encoder.')

        if self.model is None:
            if self.aim == ENCODER_AIM.SPEED:
                self.model = Img2Vec(model='resnet-18')
            elif self.aim == ENCODER_AIM.BALANCE:
                self.model = Img2Vec(model='resnext-50-small')
            elif self.aim == ENCODER_AIM.ACCURACY:
                self.model = Img2Vec(model='resnext-50')
            else:
                self.model = Img2Vec()
        self._prepared = True