eval_results.json

[
  {
    "task": "hellaswag",
    "benchmark": "HellaSwag",
    "metric": "acc_norm",
    "score": 0.2672774347739494,
    "shots": 0,
    "runtime_sec": 152.49,
    "status": "success"
  },
  {
    "task": "piqa",
    "benchmark": "PIQA",
    "metric": "acc_norm",
    "score": 0.5032644178454843,
    "shots": 0,
    "runtime_sec": 29.83,
    "status": "success"
  },
  {
    "task": "winogrande",
    "benchmark": "WinoGrande",
    "metric": "acc",
    "score": 0.4964483030781373,
    "shots": 0,
    "runtime_sec": 22.5,
    "status": "success"
  },
  {
    "task": "boolq",
    "benchmark": "BoolQ",
    "metric": "acc",
    "score": 0.3782874617737003,
    "shots": 0,
    "runtime_sec": 54.69,
    "status": "success"
  },
  {
    "task": "arc_easy",
    "benchmark": "ARC-Easy",
    "metric": "acc_norm",
    "score": 0.2769360269360269,
    "shots": 0,
    "runtime_sec": 38.91,
    "status": "success"
  },
  {
    "task": "arc_challenge",
    "benchmark": "ARC-Challenge",
    "metric": "acc_norm",
    "score": 0.27474402730375425,
    "shots": 0,
    "runtime_sec": 29.25,
    "status": "success"
  },
  {
    "task": "openbookqa",
    "benchmark": "OpenBookQA",
    "metric": "acc_norm",
    "score": 0.308,
    "shots": 0,
    "runtime_sec": 23.18,
    "status": "success"
  },
  {
    "task": "commonsense_qa",
    "benchmark": "CommonsenseQA",
    "metric": "acc",
    "score": 0.18591318591318592,
    "shots": 0,
    "runtime_sec": 27.0,
    "status": "success"
  },
  {
    "task": "lambada_openai",
    "benchmark": "LAMBADA",
    "metric": "acc",
    "score": 0.0,
    "shots": 0,
    "runtime_sec": 71.7,
    "status": "success"
  },
  {
    "task": "blimp",
    "benchmark": "BLiMP",
    "metric": "acc",
    "score": 0.5428358208955224,
    "shots": 0,
    "runtime_sec": 367.52,
    "status": "success"
  },
  {
    "task": "mmlu",
    "benchmark": "MMLU",
    "metric": "acc",
    "score": 0.2543797179888905,
    "shots": 0,
    "runtime_sec": 295.22,
    "status": "success"
  },
  {
    "task": "wikitext",
    "benchmark": "WikiText-2",
    "metric": "word_perplexity",
    "score": 88520100.69650024,
    "shots": 0,
    "runtime_sec": 34.96,
    "status": "success"
  },
  {
    "task": "wikitext",
    "benchmark": "WikiText-2",
    "metric": "byte_perplexity",
    "score": 30.629263941602346,
    "shots": 0,
    "runtime_sec": 31.49,
    "status": "success"
  },
  {
    "task": "sciq",
    "benchmark": "SciQ",
    "metric": "acc_norm",
    "score": 0.215,
    "shots": 0,
    "runtime_sec": 41.48,
    "status": "success"
  },
  {
    "task": "copa",
    "benchmark": "COPA",
    "metric": "acc",
    "score": 0.57,
    "shots": 0,
    "runtime_sec": 18.99,
    "status": "success"
  },
  {
    "task": "race",
    "benchmark": "RACE",
    "metric": "acc",
    "score": 0.22775119617224882,
    "shots": 0,
    "runtime_sec": 100.93,
    "status": "success"
  },
  {
    "task": "swag",
    "benchmark": "SWAG",
    "metric": "acc_norm",
    "score": 0.2575227431770469,
    "shots": 0,
    "runtime_sec": 153.63,
    "status": "success"
  },
  {
    "task": "truthfulqa_mc2",
    "benchmark": "TruthfulQA MC2",
    "metric": "acc",
    "score": 0.4874513485881811,
    "shots": 0,
    "runtime_sec": 49.19,
    "status": "success"
  }
]