scripts/train.py

#!/usr/bin/env python3
"""
Training Launcher — DevOps RL Agent

Usage:
    # Test the RL loop (No GPU, uses rule-based Baseline Agent)
    python scripts/train.py --test --episodes 100

    # Real GRPO Training (Requires GPU, uses Unsloth + Llama 3.2 3B)
    python scripts/train.py --real --episodes 1000
"""

import argparse
import sys
import os

sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

from training.train_grpo import GRPODevOpsTrainer

def main():
    parser = argparse.ArgumentParser(description="Launch DevOps Agent Training")
    parser.add_argument("--test", action="store_true", help="Run test training (no GPU, uses baseline agent)")
    parser.add_argument("--real", action="store_true", help="Run real GRPO training (requires GPU)")
    parser.add_argument("--episodes", type=int, default=500, help="Number of episodes to run")
    parser.add_argument("--model", type=str, default="unsloth/llama-3.2-3b-instruct", help="Base model for real training")
    
    args = parser.parse_args()

    if not args.test and not args.real:
        print("Please specify --test or --real. E.g., python scripts/train.py --test")
        sys.exit(1)

    use_grpo = args.real

    trainer = GRPODevOpsTrainer(
        model_name=args.model,
        max_steps=args.episodes,
        save_steps=100
    )
    
    print(f"Starting {'REAL' if use_grpo else 'TEST'} training for {args.episodes} episodes...")
    trainer.train(num_episodes=args.episodes, use_grpo=use_grpo)

if __name__ == "__main__":
    main()