我是huggingface的新手，在阅读文档后，我一直在尝试在我的简单数据集上微调DNABERT 2。
基本上，这个想法是我有一些标记为“1”或“0”的DNA序列，我想使用预训练的DNABERT 2模型来预测标签。
范例：

AATTGGC    1
TCTC       0 
TGTTA      1

字符串
我想我已经把所有的步骤都写下来了--但是在最后一行遇到了一个错误--TypeError: '_TensorSliceDataset' object is not subscriptable。
下面是我使用的所有代码（从这里派生的步骤：https://github.com/huggingface/notebooks/blob/main/transformers_doc/en/training.ipynb）：

import pandas as pd
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("zhihan1996/DNABERT-2-117M", trust_remote_code=True)
model = AutoModel.from_pretrained("zhihan1996/DNABERT-2-117M", trust_remote_code=True).to('cuda')

# Assuming 'sequences' is a list of DNA sequences and 'labels' is a list of binary labels (0 or 1)

# Split the data into training and testing sets
df = pd.read_csv('/content/dev.csv', nrows=10)
df1 = pd.read_csv('/content/test.csv', nrows=10)

train_sequences=df.iloc[:, 0].tolist()
test_sequences=df1.iloc[:, 0].tolist()
train_labels=df.iloc[:, 1].tolist()
test_labels =df1.iloc[:, 1].tolist()

# Tokenize and format the data
train_encodings = tokenizer(train_sequences, truncation=True, padding=True)
test_encodings = tokenizer(test_sequences, truncation=True, padding=True)

# convert encodings

import tensorflow as tf

train_dataset = tf.data.Dataset.from_tensor_slices((
    dict(train_encodings),
    train_labels
))

test_dataset = tf.data.Dataset.from_tensor_slices((
    dict(test_encodings),
    test_labels
))

from transformers import TrainingArguments

training_args = TrainingArguments(output_dir="test_trainer")


import numpy as np
import evaluate

metric = evaluate.load("accuracy")

def compute_metrics(eval_pred):
    logits, labels = eval_pred
    predictions = np.argmax(logits, axis=-1)
    return metric.compute(predictions=predictions, references=labels)


from transformers import TrainingArguments, Trainer

training_args = TrainingArguments(output_dir="test_trainer", evaluation_strategy="epoch")

trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=train_dataset,
    eval_dataset=test_dataset,
    compute_metrics=compute_metrics,
)

型
一切都很顺利，直到我运行最后一行：

trainer.train()

型