DS-LLM-TEMPLATE-FINETUNING/scripts/styling/train.py

#!/usr/bin/env python3
"""
Styling Training Script
Provides a command-line interface to run the styling training pipeline
"""

import sys
import os
import subprocess
import argparse
from pathlib import Path

def run_training_with_config(config_path: str, dataset_path: str = None, **cli_overrides):
    """Run the styling training pipeline with YAML configuration"""
    print(f"Starting styling training with config: {config_path}")
    if dataset_path:
        print(f"Training dataset: {dataset_path}")
    else:
        print("Training dataset: Will use output_dir from YAML config")
    print()
    
    # Build command
    cmd = ["python", "pipelines/styling/train.py", "--config", config_path]
    
    # Add dataset path if provided
    if dataset_path:
        cmd.extend(["--dataset", dataset_path])
    
    # Add CLI overrides
    for key, value in cli_overrides.items():
        if value is not None:
            if key == "output_dir":
                cmd.extend(["--output-dir", str(value)])
            elif key == "epochs":
                cmd.extend(["--epochs", str(value)])
            elif key == "batch_size":
                cmd.extend(["--batch-size", str(value)])
            elif key == "learning_rate":
                cmd.extend(["--learning-rate", str(value)])
            elif key == "max_steps":
                cmd.extend(["--max-steps", str(value)])
    
    print(f"Running: {' '.join(cmd)}")
    print()
    
    try:
        result = subprocess.run(cmd, check=True, capture_output=True, text=True)
        print("Training completed successfully!")
        print(result.stdout)
        return True
    except subprocess.CalledProcessError as e:
        print(f"Training failed: {e}")
        print(f"Error output: {e.stderr}")
        return False

def show_training_features():
    """Show the features of the styling training pipeline"""
    print("=== Styling Training Pipeline Features ===")
    print()
    print("1. **Model Support**:")
    print("   - Unsloth optimized models (4x faster)")
    print("   - LoRA fine-tuning for efficiency")
    print("   - Support for Llama-3.1, Mistral, Phi-3, Gemma")
    print()
    print("2. **Training Features**:")
    print("   - SFTTrainer with instruction tuning")
    print("   - Automatic mixed precision (FP16/BF16)")
    print("   - Gradient checkpointing for memory efficiency")
    print("   - Configurable LoRA parameters")
    print()
    print("3. **Configuration**:")
    print("   - YAML configuration files")
    print("   - CLI argument overrides")
    print("   - Automatic device detection")
    print()
    print("4. **Output**:")
    print("   - Saved LoRA models")
    print("   - Training logs and checkpoints")
    print("   - Ready for inference")

def create_training_example():
    """Create a training example using the formal style configuration"""
    print("=== Training Example: Formal Style Transfer ===")
    print()
    
    # Check if we have the required files
    config_path = "configs/styling/formal.yaml"
    
    if not Path(config_path).exists():
        print(f"Configuration file not found: {config_path}")
        print("   Please run the data processor first to create the configuration")
        return False
    
    print("Found required files!")
    print(f"   Config: {config_path}")
    print("   Dataset: Will use output_dir from YAML config")
    print("   The training pipeline will automatically:")
    print("   - Load data from the output_dir specified in YAML")
    print("   - Convert JSONL files to HuggingFace dataset format")
    print("   - Apply formatting with EOS tokens")
    print("   - Train the model using SFTTrainer")
    print()
    
    # Run training without explicit dataset path - will use YAML config
    success = run_training_with_config(
        config_path=config_path,
        dataset_path=None,  # Use output_dir from YAML config
        epochs=1,
        batch_size=2,
        learning_rate=2e-4
    )
    
    if success:
        print("Training example completed!")
        print("   Model saved to: ./models/styling")
        print("   Ready for inference!")
    
    return success

def main():
    """Main function"""
    parser = argparse.ArgumentParser(description="Styling Training Script")
    
    # Subcommands
    parser.add_argument("command", choices=["train", "example", "features"], 
                       help="Command to run")
    
    # Training arguments
    parser.add_argument("--config", type=str, help="Path to YAML configuration file")
    parser.add_argument("--dataset", type=str, help="Path to training dataset")
    parser.add_argument("--output-dir", type=str, help="Output directory for model")
    parser.add_argument("--epochs", type=int, help="Number of training epochs")
    parser.add_argument("--batch-size", type=int, help="Training batch size")
    parser.add_argument("--learning-rate", type=float, help="Learning rate")
    parser.add_argument("--max-steps", type=int, help="Maximum training steps")
    
    args = parser.parse_args()
    
    if args.command == "features":
        show_training_features()
    
    elif args.command == "example":
        create_training_example()
    
    elif args.command == "train":
        if not args.config:
            print("❌ --config is required for training")
            print("Usage: python scripts/styling/train.py train --config config.yaml")
            sys.exit(1)
        
        # If dataset is not provided, try to use output_dir from config
        dataset_path = args.dataset if args.dataset else None
        
        success = run_training_with_config(
            config_path=args.config,
            dataset_path=dataset_path,
            output_dir=args.output_dir,
            epochs=args.epochs,
            batch_size=args.batch_size,
            learning_rate=args.learning_rate,
            max_steps=args.max_steps
        )
        
        if not success:
            sys.exit(1)

if __name__ == "__main__":
    main()