GPT2 on Hugging face(pytorch transformers) RuntimeError: grad can be implicitly created only for scalar outputs

I am trying to fine-tune gpt2 with a custom dataset of mine. I created a basic example with the documentation from hugging-face transformers. I receive the mentioned error. I know what it means: (basically it is calling backward on a non-scalar tensor) but since I almost use only API calls, I have no idea how to fix this issue. Any suggestions?

from pathlib import Path
from absl import flags, app
import IPython
import torch
from transformers import GPT2LMHeadModel, Trainer,  TrainingArguments
from data_reader import GetDataAsPython

# this is my custom data, but i get the same error for the basic case below
# data = GetDataAsPython('data.json')
# data = [data_point.GetText2Text() for data_point in data]
# print("Number of data samples is", len(data))

data = ["this is a trial text", "this is another trial text"]

train_texts = data

from transformers import GPT2Tokenizer
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')

special_tokens_dict = {'pad_token': '<PAD>'}
num_added_toks = tokenizer.add_special_tokens(special_tokens_dict)
train_encodigs = tokenizer(train_texts, truncation=True, padding=True)


class BugFixDataset(torch.utils.data.Dataset):
    def __init__(self, encodings):
        self.encodings = encodings
    
    def __getitem__(self, index):
        item = {key: torch.tensor(val[index]) for key, val in self.encodings.items()}
        return item

    def __len__(self):
        return len(self.encodings['input_ids'])

train_dataset = BugFixDataset(train_encodigs)

training_args = TrainingArguments(
    output_dir='./results',          
    num_train_epochs=3,              
    per_device_train_batch_size=1,  
    per_device_eval_batch_size=1,   
    warmup_steps=500,                
    weight_decay=0.01,               
    logging_dir='./logs',
    logging_steps=10,
)

model = GPT2LMHeadModel.from_pretrained('gpt2', return_dict=True)
model.resize_token_embeddings(len(tokenizer))

trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=train_dataset,
)

trainer.train()