import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix, roc_curve, auc
from datasets import load_dataset
from transformers import AutoTokenizer, AutoModelForSequenceClassification, TrainingArguments, Trainer

# Variables to set the number of epochs and samples
num_epochs = 10
num_samples = 100  # set this to -1 to use all data