train_text.py

from transformers import BertTokenizer, BertForSequenceClassification 
from torch.utils.data import DataLoader
import torch

tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
model = BertForSequenceClassification.from_pretrained(
    "bert-base-uncased", num_labels=2
)

texts = ["This is human written text", "This essay was generated by AI"]
labels = [0, 1]

encodings = tokenizer(texts, truncation=True, padding=True, return_tensors="pt")
dataset = torch.utils.data.TensorDataset(
    encodings["input_ids"], torch.tensor(labels)
)

loader = DataLoader(dataset, batch_size=2, shuffle=True)
optimizer = torch.optim.AdamW(model.parameters(), lr=2e-5)

model.train()
for epoch in range(3):
    for batch in loader:
        optimizer.zero_grad()
        outputs = model(batch[0], labels=batch[1])
        loss = outputs.loss
        loss.backward()
        optimizer.step()

print("Text AI Detector trained successfully")