Loosing my target variable when encoding

Beginners
1

Hello everyone,

I have created a Dataset Dictionary containing my training and testing dataset which looks like this:

DatasetDict({
    train: Dataset({
        features: ['Score', 'Review'],
        num_rows: 3014
    })
    test: Dataset({
        features: ['Score', 'Review'],
        num_rows: 754
    })
})

I want to fine-tune a Bert model for Sentiment Analysis. Therefore, I encode my Datasets:

model_name = "nlptown/bert-base-multilingual-uncased-sentiment"
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=num_labels)

def tokenize(batch):
    return tokenizer(batch['Review'], padding=True, truncation=True)

data_encoded = data_dict.map(tokenize, batched=True, batch_size=None)

data_encoded.set_format("torch", columns=["input_ids", "attention_mask", "Score"])

After encoding and setting the format, my target variable “Score” is missing in the torch.Tensor. Does anyone has an idea what the problem is over here? Does the Target variable has to be set to a specific format/datatype? I am having 5 different labels (from 0 to 4).

Cheers