train.py

from transformers import BertTokenizer, BertForSequenceClassification, Trainer, TrainingArguments
import numpy as np
import pandas as pd
from datasets import Dataset
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, precision_recall_fscore_support

# Load dataset
df = pd.read_csv("AI_Human.csv")
train_df, eval_df = train_test_split(df, test_size=0.2)

# Tokenizer
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')

def tokenize_function(examples):
    return tokenizer(examples["text"], padding="max_length", truncation=True, max_length=512)

# Convert DataFrames to Datasets and apply tokenization
train_dataset = Dataset.from_pandas(train_df)
eval_dataset = Dataset.from_pandas(eval_df)

train_dataset = train_dataset.map(tokenize_function, batched=True)
train_dataset.set_format(type='torch', columns=['input_ids', 'attention_mask', 'labels'])

eval_dataset = eval_dataset.map(tokenize_function, batched=True)
eval_dataset.set_format(type='torch', columns=['input_ids', 'attention_mask', 'labels'])

# Model
model = BertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2)

# Training Arguments
training_args = TrainingArguments(
    output_dir="./results",
    num_train_epochs=3,
    per_device_train_batch_size=8,
    per_device_eval_batch_size=8,
    warmup_steps=500,
    weight_decay=0.01,
    logging_dir='./logs',
    evaluation_strategy="steps",
    save_steps=500,
    logging_steps=100,
)

def compute_metrics(pred):
    labels = pred.label_ids
    preds = np.argmax(pred.predictions, axis=-1)
    precision, recall, f1, _ = precision_recall_fscore_support(labels, preds, average='binary')
    acc = accuracy_score(labels, preds)
    return {
        'accuracy': acc,
        'f1': f1,
        'precision': precision,
        'recall': recall
    }

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

trainer.train()
model.save_pretrained("./trained_model")
tokenizer.save_pretrained("./trained_model")