comprehensive_results_tactic.json

{
  "val": {
    "loss": 0.2741684317588806,
    "accuracy": 0.9154929577464789,
    "macro_f1": 0.9149011138355096,
    "weighted_f1": 0.9152502181169738,
    "distortion_precision": 0.8918918918918919,
    "distortion_recall": 0.9428571428571428,
    "distortion_f1": 0.9166666666666666,
    "trivialization_precision": 0.8974358974358975,
    "trivialization_recall": 0.9459459459459459,
    "trivialization_f1": 0.9210526315789473,
    "coercion_precision": 0.9428571428571428,
    "coercion_recall": 0.9166666666666666,
    "coercion_f1": 0.9295774647887324,
    "knowledge_precision": 0.9354838709677419,
    "knowledge_recall": 0.8529411764705882,
    "knowledge_f1": 0.8923076923076924,
    "runtime": 12.4031,
    "samples_per_second": 11.449,
    "steps_per_second": 0.726,
    "confusion_matrix": [
      [
        33,
        1,
        0,
        1
      ],
      [
        0,
        35,
        1,
        1
      ],
      [
        1,
        2,
        33,
        0
      ],
      [
        3,
        1,
        1,
        29
      ]
    ]
  },
  "test_id": {
    "loss": 0.27421480417251587,
    "accuracy": 0.9084507042253521,
    "macro_f1": 0.9085461883825343,
    "weighted_f1": 0.9084405799722616,
    "distortion_precision": 0.9117647058823529,
    "distortion_recall": 0.8611111111111112,
    "distortion_f1": 0.8857142857142857,
    "trivialization_precision": 0.8611111111111112,
    "trivialization_recall": 0.9393939393939394,
    "trivialization_f1": 0.8985507246376812,
    "coercion_precision": 0.9285714285714286,
    "coercion_recall": 0.9285714285714286,
    "coercion_f1": 0.9285714285714286,
    "knowledge_precision": 0.9318181818181818,
    "knowledge_recall": 0.9111111111111111,
    "knowledge_f1": 0.9213483146067416,
    "runtime": 12.2783,
    "samples_per_second": 11.565,
    "steps_per_second": 0.733,
    "confusion_matrix": [
      [
        31,
        3,
        1,
        1
      ],
      [
        0,
        31,
        0,
        2
      ],
      [
        1,
        1,
        26,
        0
      ],
      [
        2,
        1,
        1,
        41
      ]
    ]
  },
  "test_ood": {
    "loss": 1.1873223781585693,
    "accuracy": 0.6086956521739131,
    "macro_f1": 0.5871759832188721,
    "weighted_f1": 0.6067226831556392,
    "distortion_precision": 0.6787564766839378,
    "distortion_recall": 0.645320197044335,
    "distortion_f1": 0.6616161616161617,
    "trivialization_precision": 0.4918032786885246,
    "trivialization_recall": 0.7692307692307693,
    "trivialization_f1": 0.6,
    "coercion_precision": 0.5625,
    "coercion_recall": 0.5510204081632653,
    "coercion_f1": 0.5567010309278351,
    "knowledge_precision": 0.6486486486486487,
    "knowledge_recall": 0.4485981308411215,
    "knowledge_f1": 0.5303867403314917,
    "runtime": 13.0062,
    "samples_per_second": 33.599,
    "steps_per_second": 2.153,
    "confusion_matrix": [
      [
        131,
        47,
        12,
        13
      ],
      [
        10,
        60,
        2,
        6
      ],
      [
        9,
        6,
        27,
        7
      ],
      [
        43,
        9,
        7,
        48
      ]
    ]
  },
  "delta_f1": 0.3213702051636622,
  "delta_f1_interpretation": "\u274c Significant overfitting (domain adaptation needed)"
}