Dataset: iris (classification)
Penalty: 0.1
Seed: 42
Best fitness: -0.10330625859606479
Final val loss: 0.08993925
Final penalty: 0.02456140
Model saved to: exp_1/logs/classification/iris/HYPERPARAM_MUTATION_PROB/HYPERPARAM_MUTATION_PROB=0.4/models/best_model_penalty_0.1_seed_42.pth

Final architecture & hyperparameters:
  num_layers: 2
  layer_sizes: [2, 4]
  activations: [4, 4]
  dropout_rates: [0.014, 0.014]
  batch_norms: [0, 0]
  learning_rate: 0.0223
  batch_size: 16
  patience: 22
  optimizer_type: 0
  init_type: 3
  l2_penalty: 0.0

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