added style mimicking piepelines
This commit is contained in:
OwusuBlessing
@@ -0,0 +1,168 @@
|
||||
#!/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()
|
||||
Reference in New Issue
Block a user