Dataset: iris (classification)
Penalty: 0.1
Seed: 42
Best fitness: -0.17606066093404313
Final val loss: 0.10428962
Final penalty: 0.06578947
Model saved to: exp_1/logs/classification/iris/LAYER_MUTATION_PROB/LAYER_MUTATION_PROB=0.1/models/best_model_penalty_0.1_seed_42.pth

Final architecture & hyperparameters:
  num_layers: 3
  layer_sizes: [3, 5, 6]
  activations: [3, 3, 4]
  dropout_rates: [0.051, 0.02, 0.332]
  batch_norms: [0, 0, 1]
  learning_rate: 0.0147
  batch_size: 16
  patience: 28
  optimizer_type: 2
  init_type: 3
  l2_penalty: 0.0008

Validation metrics (final):
  accuracy: 95.45454545454545
  precision: 95.83333333333334
  recall: 95.23809523809524
  f1_score: 95.21367521367522
  confusion_matrix: [[8, 0, 0], [0, 7, 0], [0, 1, 6]]
  num_classes: 3
  class_distribution: {0: 8, 1: 7, 2: 7}

Test metrics (final):
  accuracy: 100.0
  precision: 100.0
  recall: 100.0
  f1_score: 100.0
  confusion_matrix: [[7, 0, 0], [0, 8, 0], [0, 0, 8]]
  num_classes: 3
  class_distribution: {0: 7, 1: 8, 2: 8}
