train.py

### 3. train.py
```python
#!/usr/bin/env python3
"""
Training script for POSNEG dataset sentiment classification
"""

import torch
from torch.utils.data import DataLoader
from transformers import (
    AutoTokenizer,
    AutoModelForSequenceClassification,
    TrainingArguments,
    Trainer,
)
from datasets import load_dataset
import numpy as np
from sklearn.metrics import accuracy_score, precision_recall_fscore_support

class POSNEGDataset(torch.utils.data.Dataset):
    def __init__(self, texts, labels, tokenizer, max_length=512):
        self.texts = texts
        self.labels = labels
        self.tokenizer = tokenizer
        self.max_length = max_length
    
    def __len__(self):
        return len(self.texts)
    
    def __getitem__(self, idx):
        text = str(self.texts[idx])
        label = self.labels[idx]
        
        encoding = self.tokenizer(
            text,
            truncation=True,
            padding='max_length',
            max_length=self.max_length,
            return_tensors='pt'
        )
        
        return {
            'input_ids': encoding['input_ids'].flatten(),
            'attention_mask': encoding['attention_mask'].flatten(),
            'labels': torch.tensor(label, dtype=torch.long)
        }

def compute_metrics(eval_pred):
    predictions, labels = eval_pred
    predictions = np.argmax(predictions, axis=1)
    precision, recall, f1, _ = precision_recall_fscore_support(labels, predictions, average='weighted')
    acc = accuracy_score(labels, predictions)
    return {
        'accuracy': acc,
        'f1': f1,
        'precision': precision,
        'recall': recall
    }

def main():
    # Load POSNEG dataset
    print("Loading POSNEG dataset...")
    dataset = load_dataset("chaosbringerc/POSNEG")  # Your dataset
    
    # Initialize tokenizer and model
    model_name = "bert-base-uncased"
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForSequenceClassification.from_pretrained(
        model_name, 
        num_labels=2,
        id2label={0: "NEGATIVE", 1: "POSITIVE"},
        label2id={"NEGATIVE": 0, "POSITIVE": 1}
    )
    
    # Prepare datasets
    train_dataset = POSNEGDataset(
        texts=dataset['train']['text'],
        labels=dataset['train']['label'],
        tokenizer=tokenizer
    )
    
    eval_dataset = POSNEGDataset(
        texts=dataset['validation']['text'],
        labels=dataset['validation']['label'],
        tokenizer=tokenizer
    )
    
    # Training arguments
    training_args = TrainingArguments(
        output_dir='./results',
        num_train_epochs=3,
        per_device_train_batch_size=16,
        per_device_eval_batch_size=16,
        warmup_steps=500,
        weight_decay=0.01,
        logging_dir='./logs',
        logging_steps=10,
        evaluation_strategy="epoch",
        save_strategy="epoch",
        load_best_model_at_end=True,
    )
    
    # Initialize trainer
    trainer = Trainer(
        model=model,
        args=training_args,
        train_dataset=train_dataset,
        eval_dataset=eval_dataset,
        compute_metrics=compute_metrics,
    )
    
    # Train the model
    print("Starting training...")
    trainer.train()
    
    # Save the model
    print("Saving model...")
    trainer.save_model()
    tokenizer.save_pretrained('./results')
    
    print("Training completed!")

if __name__ == "__main__":
    main()