scripts/training/train_wrapper.py

#!/usr/bin/env python3
"""
Training wrapper with checkpoint support and better logging
"""

import sys
import os
import shutil
from pathlib import Path

# Clear cache before training
print("🧹 Clearing HuggingFace cache...")
cache_dir = Path("/workspace/.hf_home/hub/models--mistralai--Mistral-7B-v0.1")
if cache_dir.exists():
    try:
        shutil.rmtree(cache_dir)
        print("✓ Cache cleared")
    except Exception as e:
        print(f"⚠️  Cache clear warning: {e}")

# Force unbuffered output for real-time logs
sys.stdout = os.fdopen(sys.stdout.fileno(), 'w', buffering=1)
sys.stderr = os.fdopen(sys.stderr.fileno(), 'w', buffering=1)

print("=" * 70)
print("🚀 Starting Training with Real-time Logging")
print("=" * 70)
sys.stdout.flush()

# Import and run training
sys.path.insert(0, "/workspace/ftt/ft/models/msp")
from ft.finetune_mistral7b import main

if __name__ == "__main__":
    main()