src/textSummarizer/entity/__init__.py

from dataclasses import dataclass
from pathlib import Path

@dataclass(frozen=True)
class DataIngestionConfig:
    root_dir : Path
    source_URL : str
    local_data_file : Path
    unzip_dir : Path
    
    
@dataclass(frozen=True)
class DataValidationConfig:
    root_dir : Path
    STATUS_FILE : str
    ALL_REQUIRED_FILES : list
    data_dir : Path
    
    
@dataclass(frozen=True)
class DataTransformationConfig:
    root_dir: Path
    data_path: Path
    tokenizer_name: str
    # dev quick-run options
    dev_run: bool = False
    dev_model: str | None = None
    
    
    
@dataclass(frozen=True)
class ModelTrainerConfig:
    root_dir: Path
    data_path: Path
    model_ckpt: str
    num_train_epochs: int
    warmup_steps: int
    per_device_train_batch_size: int
    weight_decay: float
    logging_steps: int
    eval_strategy: str
    eval_steps: int
    save_steps: float
    gradient_accumulation_steps: int   
    # dev / quick-train options
    dev_run: bool = False
    dev_model: str | None = None
    dev_subset: int = 0
    
    
@dataclass(frozen=True)
class ModelEvaluationConfig:
    root_dir: Path
    data_path: Path
    model_path: Path
    tokenizer_path: Path
    metric_file_name: Path
    # Hub model ID used as fallback when the local fine-tuned model is absent
    hub_model_id: str = "google/pegasus-cnn_dailymail"