from datasets import load_dataset
from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer, TrainingArguments

# Load your dataset
dataset = load_dataset('text', data_files={'train': 'cleaned_data.txt'})

# Preprocess the dataset
tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
def tokenize_function(examples):
    return tokenizer(examples['text'], padding="max_length", truncation=True)

tokenized_datasets = dataset.map(tokenize_function, batched=True)

# Load model
model = AutoModelForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2)

# Define training arguments
training_args = TrainingArguments(
    output_dir="./results",
    evaluation_strategy="epoch",
    per_device_train_batch_size=8,
    per_device_eval_batch_size=8,
    num_train_epochs=3,
    weight_decay=0.01,
)

# Create Trainer
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=tokenized_datasets["train"],
    eval_dataset=tokenized_datasets["train"],
)

# Train the model
trainer.train()