data/artifacts/models/bloom_classifier/metrics.json

{
  "model_name": "bloom_classifier",
  "model_version": "bloom_classifier_v2_baseline_001",
  "dataset_version": "2.0.0",
  "trained_at": "2026-05-21T05:59:09.626503+00:00",
  "seed": 42,
  "split_counts": {
    "train": 3912,
    "validation": 1033,
    "test": 875
  },
  "metrics": {
    "validation": {
      "macro_f1": 0.6434,
      "weighted_f1": 0.6634,
      "per_class": {
        "Analyze": {
          "precision": 0.614,
          "recall": 0.6774,
          "f1": 0.6442,
          "support": 155
        },
        "Apply": {
          "precision": 0.65,
          "recall": 0.5778,
          "f1": 0.6118,
          "support": 270
        },
        "Create": {
          "precision": 0.8947,
          "recall": 1.0,
          "f1": 0.9444,
          "support": 17
        },
        "Evaluate": {
          "precision": 1.0,
          "recall": 0.1522,
          "f1": 0.2642,
          "support": 46
        },
        "Remember": {
          "precision": 0.7438,
          "recall": 0.5732,
          "f1": 0.6475,
          "support": 157
        },
        "Understand": {
          "precision": 0.68,
          "recall": 0.8325,
          "f1": 0.7486,
          "support": 388
        }
      },
      "confusion_matrix": [
        [
          105,
          50,
          0,
          0,
          0,
          0
        ],
        [
          27,
          156,
          0,
          0,
          0,
          87
        ],
        [
          0,
          0,
          17,
          0,
          0,
          0
        ],
        [
          37,
          0,
          2,
          7,
          0,
          0
        ],
        [
          0,
          2,
          0,
          0,
          90,
          65
        ],
        [
          2,
          32,
          0,
          0,
          31,
          323
        ]
      ]
    },
    "test": {
      "macro_f1": 0.6178,
      "weighted_f1": 0.6654,
      "per_class": {
        "Analyze": {
          "precision": 0.7,
          "recall": 0.6853,
          "f1": 0.6926,
          "support": 143
        },
        "Apply": {
          "precision": 0.6411,
          "recall": 0.5678,
          "f1": 0.6022,
          "support": 236
        },
        "Create": {
          "precision": 0.8333,
          "recall": 0.9375,
          "f1": 0.8824,
          "support": 16
        },
        "Evaluate": {
          "precision": 0.6667,
          "recall": 0.0588,
          "f1": 0.1081,
          "support": 34
        },
        "Remember": {
          "precision": 0.7677,
          "recall": 0.608,
          "f1": 0.6786,
          "support": 125
        },
        "Understand": {
          "precision": 0.665,
          "recall": 0.8411,
          "f1": 0.7428,
          "support": 321
        }
      },
      "confusion_matrix": [
        [
          98,
          45,
          0,
          0,
          0,
          0
        ],
        [
          13,
          134,
          0,
          0,
          0,
          89
        ],
        [
          0,
          0,
          15,
          1,
          0,
          0
        ],
        [
          29,
          0,
          3,
          2,
          0,
          0
        ],
        [
          0,
          2,
          0,
          0,
          76,
          47
        ],
        [
          0,
          28,
          0,
          0,
          23,
          270
        ]
      ]
    }
  },
  "limitations": [
    "Trained on synthetic data only.",
    "6 classes with imbalanced distribution \u2014 Create (~2%) and Evaluate (~4%) are rare.",
    "Macro F1 is the primary metric; per-class recall may be low for rare classes.",
    "TF-IDF features do not capture semantic similarity beyond n-gram overlap."
  ]
}