# Comprehensive Custom Dataset Classification Configuration
# This file defines all parameters for processing custom classification datasets
# Organized by level: data processing, model, training, and inference

# Task Configuration
task:
  name: "classification"                    # Task type: classification, completion, styling, matching
  type: "sequence_classification"          # Model type: sequence_classification, token_classification, etc.

# Data Processing Configuration
data:
  source: "custom"                         # Data source: "huggingface" or "custom"
  dataset_name: null                       # HuggingFace dataset name (not used for custom data)
  data_path: "./data/classification/train.jsonl"  # Path to custom data file (required for custom source)
  data_format: "jsonl"                     # Data format: "jsonl", "csv", "json"
  
  # Field Mapping
  input_field: "text"                      # Field name containing input text
  label_field: "label"                     # Field name containing labels
  id_field: "id"                           # Optional ID field name (set to null if not available)
  
  # Processing Parameters
  max_samples: 1000                        # Maximum samples to process (null for all samples)
  train_split: 0.8                         # Training split ratio (0.0 to 1.0)
  validation_split: 0.1                    # Validation split ratio (0.0 to 1.0)
  test_split: 0.1                          # Test split ratio (0.0 to 1.0)
  
  # Text Preprocessing
  clean_text: true                         # Clean and normalize text
  remove_special_chars: false              # Remove special characters from text
  lowercase: true                          # Convert text to lowercase
  min_length: 10                           # Minimum text length (filter out shorter texts)
  max_length: 1000                         # Maximum text length (truncate longer texts)
  
  # Label Processing
  label_encoding: "auto"                   # Label encoding: "auto", "numeric", "string"
  multilabel: false                        # Enable multilabel classification
  label_separator: ","                     # Separator for multilabel datasets
  
  # Output Configuration
  output_format: "classification"          # Output format: "classification", "instruction", "conversation", "qa"
  output_dir: "./data/processed/classification/custom_dataset"  # Specific output directory for custom dataset
  
  # HuggingFace Specific (not used for custom data)
  hf_split: "train"                        # HuggingFace dataset split to use
  hf_cache_dir: null                       # HuggingFace cache directory (null for default)
  
  # Split Configuration (Advanced)
  test_split_from: "train"                 # Source for test split: "train", "use_test_if_available", "use_val_if_available"
  val_split_from: "train"                  # Source for validation split: "train", "use_val_if_available"
  
  # Custom Data Specific
  encoding: "utf-8"                        # File encoding for custom data
  delimiter: ","                           # Delimiter for CSV files

# Model Configuration
model:
  name: "bert-base-uncased"                # Model name from HuggingFace Hub
  max_length: 512                          # Maximum sequence length for tokenization
  num_labels: 3                            # Number of classification labels (adjust based on your data)

# Training Configuration
training:
  num_epochs: 3                            # Number of training epochs
  batch_size: 16                           # Training batch size
  learning_rate: 2e-5                      # Learning rate (typical range: 1e-5 to 5e-5)
  weight_decay: 0.01                       # Weight decay for optimizer (typical range: 0.01 to 0.1)
  lr_scheduler_type: "linear"              # Scheduler type: "linear", "cosine", "polynomial"
  warmup_ratio: 0.1                        # Warmup ratio for scheduler (0.0 to 1.0)
  data_dir: "./data/processed/classification/custom_dataset"  # Directory containing train/validation/test JSONL files
  output_dir: "./results/classification/custom_model"  # Output directory for saved model

# Inference Configuration
inference:
  model_path: "./results/classification/custom_model"  # Path to saved model directory
  device: "auto"                           # Device: "auto", "cuda", "cpu"
  batch_size: 32                           # Batch size for inference
  return_probabilities: true                # Return all class probabilities
  return_top_k: 3                          # Return top K predictions