Upload folder using huggingface_hub

run_transformers_training.py

@@ -117,8 +117,9 @@ def load_env_variables():
         # Try to load from .env file if not in a Space
         try:
             from dotenv import load_dotenv
-            # Updated path to .env file in the new directory structure
-            env_path = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "shared", ".env")
+            # First check the current directory
+            env_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), ".env")
+            
             if os.path.exists(env_path):
                 load_dotenv(env_path)
                 logging.info(f"Loaded environment variables from {env_path}")
@@ -126,10 +127,22 @@ def load_env_variables():
                 logging.info(f"HF_USERNAME loaded from .env file: {bool(os.environ.get('HF_USERNAME'))}")
                 logging.info(f"HF_SPACE_NAME loaded from .env file: {bool(os.environ.get('HF_SPACE_NAME'))}")
             else:
-                logging.warning(f"No .env file found at {env_path}")
+                # Try the shared directory as fallback
+                shared_env_path = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "shared", ".env")
+                if os.path.exists(shared_env_path):
+                    load_dotenv(shared_env_path)
+                    logging.info(f"Loaded environment variables from {shared_env_path}")
+                    logging.info(f"HF_TOKEN loaded from shared .env file: {bool(os.environ.get('HF_TOKEN'))}")
+                    logging.info(f"HF_USERNAME loaded from shared .env file: {bool(os.environ.get('HF_USERNAME'))}")
+                    logging.info(f"HF_SPACE_NAME loaded from shared .env file: {bool(os.environ.get('HF_SPACE_NAME'))}")
+                else:
+                    logging.warning(f"No .env file found in current or shared directory")
         except ImportError:
             logging.warning("python-dotenv not installed, not loading from .env file")
     
+    if not os.environ.get("HF_TOKEN"):
+        logger.warning("HF_TOKEN is not set. Pushing to Hugging Face Hub will not work.")
+        
     if not os.environ.get("HF_USERNAME"):
         logger.warning("HF_USERNAME is not set. Using default username.")
     
@@ -671,6 +684,70 @@ def check_dependencies():
     
     return True
 
+def update_huggingface_space():
+    """Update the Hugging Face Space with the current code."""
+    log_info("Updating Hugging Face Space...")
+    update_script = os.path.join(os.path.dirname(os.path.abspath(__file__)), "update_space.py")
+    
+    if not os.path.exists(update_script):
+        logger.warning(f"Update space script not found at {update_script}")
+        return False
+    
+    try:
+        import subprocess
+        result = subprocess.run([sys.executable, update_script, "--force"], 
+                               capture_output=True, text=True, check=False)
+        
+        if result.returncode == 0:
+            log_info("Hugging Face Space updated successfully!")
+            log_info(f"Space URL: https://huggingface.co/spaces/{os.environ.get('HF_USERNAME', 'George-API')}/{os.environ.get('HF_SPACE_NAME', 'phi4training')}")
+            return True
+        else:
+            logger.error(f"Failed to update Hugging Face Space: {result.stderr}")
+            return False
+    except Exception as e:
+        logger.error(f"Error updating Hugging Face Space: {str(e)}")
+        return False
+
+def validate_huggingface_credentials():
+    """Validate Hugging Face credentials to ensure they work correctly."""
+    if not os.environ.get("HF_TOKEN"):
+        logger.warning("HF_TOKEN not found. Skipping Hugging Face credentials validation.")
+        return False
+    
+    try:
+        # Import here to avoid requiring huggingface_hub if not needed
+        from huggingface_hub import HfApi, login
+        
+        # Try to login with the token
+        login(token=os.environ.get("HF_TOKEN"))
+        
+        # Check if we can access the API
+        api = HfApi()
+        username = os.environ.get("HF_USERNAME", "George-API")
+        space_name = os.environ.get("HF_SPACE_NAME", "phi4training")
+        
+        # Try to get whoami info
+        user_info = api.whoami()
+        logger.info(f"Successfully authenticated with Hugging Face as {user_info['name']}")
+        
+        # Check if the space exists
+        try:
+            space_id = f"{username}/{space_name}"
+            space_info = api.space_info(repo_id=space_id)
+            logger.info(f"Space {space_id} is accessible")
+            return True
+        except Exception as e:
+            logger.warning(f"Could not access Space {username}/{space_name}: {str(e)}")
+            logger.warning("Space updating may not work correctly")
+            return False
+    except ImportError:
+        logger.warning("huggingface_hub not installed. Cannot validate Hugging Face credentials.")
+        return False
+    except Exception as e:
+        logger.warning(f"Error validating Hugging Face credentials: {str(e)}")
+        return False
+
 def main():
     # Set up logging
     logger.info("Starting training process")
@@ -686,6 +763,9 @@ def main():
     # Load environment variables
     load_env_variables()
     
+    # Validate Hugging Face credentials if we're going to use them
+    validate_huggingface_credentials()
+    
     # Load configuration
     try:
         transformers_config = load_configs(args.config)
@@ -941,6 +1021,10 @@ def main():
                 log_info(f"Pushing model to Hugging Face Hub as {hub_id}...")
                 trainer.push_to_hub()
                 log_info("Model successfully pushed to Hub")
+            
+            # Update the Hugging Face Space with current code
+            if os.environ.get("HF_TOKEN") and os.environ.get("HF_USERNAME") and os.environ.get("HF_SPACE_NAME"):
+                update_huggingface_space()
                 
             return 0
         except Exception as e:

update_space.py

@@ -204,30 +204,43 @@ def create_space(username, space_name):
         raise RuntimeError(f"Error with Space {space_id}: {str(e)}")
 
 def main():
-    parser = argparse.ArgumentParser(description='Update Hugging Face Space for Phi-4 training')
-    parser.add_argument('--space_name', type=str, help='Space name (default: from env)')
-    parser.add_argument('--force', action='store_true', help='Skip confirmation')
-    args = parser.parse_args()
-    
-    if not args.force:
-        print("\n" + "!"*80)
-        print("WARNING: Updating the Space will INTERRUPT any ongoing training!")
-        print("Make sure all checkpoints are saved before proceeding.")
-        print("!"*80 + "\n")
-        
-        confirm = input("Type 'update' to confirm: ")
-        if confirm.lower() != 'update':
-            logger.info("Update cancelled")
-            return False
-    
+    """Main function to update the Space."""
     try:
+        # Parse command line arguments
+        parser = argparse.ArgumentParser(description='Update Hugging Face Space for Phi-4 training')
+        parser.add_argument('--space_name', type=str, help='Space name (default: from env)')
+        parser.add_argument('--force', action='store_true', help='Skip confirmation when updating Space')
+        args = parser.parse_args()
+        
         # Load environment variables
         env_vars = load_env_variables()
+        verify_configs()
+        
+        # Verify we have the necessary variables
+        if not all(k in env_vars and env_vars[k] for k in ["HF_TOKEN", "HF_USERNAME", "HF_SPACE_NAME"]):
+            logger.error("Missing required environment variables. Please check your .env file.")
+            logger.error(f"HF_TOKEN: {'Set' if 'HF_TOKEN' in env_vars and env_vars['HF_TOKEN'] else 'Not Set'}")
+            logger.error(f"HF_USERNAME: {'Set' if 'HF_USERNAME' in env_vars and env_vars['HF_USERNAME'] else 'Not Set'}")
+            logger.error(f"HF_SPACE_NAME: {'Set' if 'HF_SPACE_NAME' in env_vars and env_vars['HF_SPACE_NAME'] else 'Not Set'}")
+            return False
+            
         logger.info(f"Environment variables loaded: USERNAME={env_vars['HF_USERNAME']}, SPACE_NAME={env_vars['HF_SPACE_NAME']}")
         
-        # Verify configurations
-        verify_configs()
-        logger.info("All configuration files verified successfully")
+        # Ask for confirmation unless forced
+        if not args.force:
+            print("\nWARNING: Updating the Space will INTERRUPT any ongoing training!")
+            confirm = input("Are you sure you want to update the Space? Type 'yes' to confirm: ")
+            if confirm.lower() != 'yes':
+                logger.info("Update cancelled by user")
+                return False
+            
+            # Additional password check for safety
+            password = getpass.getpass("Enter your password to confirm update: ")
+            if password.strip() == "":
+                logger.info("No password entered. Update cancelled.")
+                return False
+        else:
+            logger.info("Skipping confirmation due to --force flag")
         
         # Update requirements
         update_requirements()