{
  "format": "d1a-mlx",
  "format_version": 1,
  "base": "google/gemma-4-E2B",
  "base_revision": "d29ff6b45f081a49ee2733a859c9c9c2d95d1a6f",
  "source": "JohnP1/d1a-e2b",
  "source_revision": "5517e8213504de567175e0b644b9c674c91af771",
  "adapter_sha256": "247f222314c8ceee158140d38a0be1c304da81719034ef6e71ee02506e334c1b",
  "lora": 16,
  "head_dim": 256,
  "hidden_size": 1536,
  "temperature": 1.447269237440378,
  "leading_ids": [
    2
  ],
  "bos_id": 2,
  "delimiter_ids": [
    6,
    7,
    8,
    9,
    10
  ],
  "pad_id": 0,
  "dtype": "bfloat16",
  "quantization": {
    "group_size": 64,
    "bits": 8,
    "mode": "affine",
    "language_model.model.embed_tokens_per_layer": {
      "group_size": 64,
      "bits": 4,
      "mode": "affine"
    },
    "embeddings": true
  },
  "head": "head.safetensors",
  "temperature_fit": {
    "rows": [
      "cal/rows.json",
      "calpr/rows.json"
    ],
    "n": 3178,
    "method": "min micro mean NLL over a 121-point log grid 0.25..4",
    "cross_validation": {
      "raw": {
        "n": 3178,
        "ece": 0.0505561988092814,
        "brier": 0.2952905648331223,
        "nll": 0.5648973549274169,
        "confident_error_rate": 0.02957835116425425,
        "coverage_at_5pct_error": 0.5613593455003146
      },
      "out_of_fold": {
        "n": 3178,
        "ece": 0.023704548579686884,
        "brier": 0.2896952220920997,
        "nll": 0.5324486179012022,
        "confident_error_rate": 0.017935808684707365,
        "coverage_at_5pct_error": 0.5556954059156702
      },
      "ece_ci95": {
        "raw": [
          0.04102750015575881,
          0.06377306530700594
        ],
        "out_of_fold": [
          0.016511069955034523,
          0.03860363764230206
        ],
        "delta": [
          -0.04016350379193325,
          -0.010727297381358629
        ]
      },
      "separated": true,
      "temperatures": [
        1.447269237440378,
        1.447269237440378,
        1.4142135623730947,
        1.4810975522865641,
        1.447269237440378
      ],
      "folds": 5,
      "seed": 0,
      "samples": 1000,
      "groups": 1670,
      "unit": "source-stratified (source, group); sibling questions and variants stay together"
    },
    "interval": {
      "level": 0.9,
      "samples": 2000,
      "seed": 0,
      "lower": 1.381912879967776,
      "upper": 1.5157165665103978,
      "questions": 3178
    },
    "fit_rows": [
      {
        "rows": "cal/rows.json",
        "suite": "evals/v7/decision-v7",
        "split": "calibration",
        "questions": 1148
      },
      {
        "rows": "calpr/rows.json",
        "suite": "evals/d1a/pr-labels",
        "split": "development",
        "questions": 2030
      }
    ],
    "training_suites": [
      "evals/devtools-v1",
      "evals/documents-v1",
      "evals/hard-v1",
      "evals/v7/decision-v7"
    ],
    "training_partitions": [
      "evals/d1a/ja-jglue:train",
      "evals/d1a/pr-labels:train",
      "evals/d1a/pr-labels:train-blast",
      "evals/d1a/pr-labels:train-ja",
      "evals/d1a/routing:factory-train",
      "evals/d1a/routing:generic-train"
    ],
    "same_corpus": [
      "calpr/rows.json: SAME CORPUS: evals/d1a/pr-labels:development is an eval partition of evals/d1a/pr-labels, whose train partitions ['evals/d1a/pr-labels:train', 'evals/d1a/pr-labels:train-blast', 'evals/d1a/pr-labels:train-ja'] the checkpoint trained on"
    ],
    "in_distribution": {
      "allowed": true,
      "problems": [
        "cal/rows.json: evals/v7/decision-v7 is training data of the checkpoint",
        "cal/rows.json: it pools 12 training source(s) ['agnews', 'amazon', 'banking77', 'boolq', 'compositional', 'dbpedia14', 'imdb', 'legacy_policy'] ...",
        "cal/rows.json: it reads the calibration partition of evals/v7/decision-v7, a training corpus",
        "calpr/rows.json: SAME CORPUS: evals/d1a/pr-labels:development is an eval partition of evals/d1a/pr-labels, whose train partitions ['evals/d1a/pr-labels:train', 'evals/d1a/pr-labels:train-blast', 'evals/d1a/pr-labels:train-ja'] the checkpoint trained on",
        "cannot list the sources of --data data/train-e2b-v06.jsonl (outside evals/, no sidecar train-e2b-v06.jsonl.json naming its sources), training data of d1"
      ]
    }
  },
  "use_case_temperatures": {},
  "use_case_temperature_fits": {}
}