bootstrapping for stddev: perplexity
{
  "results": {
    "arc_challenge": {
      "acc,none": 0.18344709897610922,
      "acc_stderr,none": 0.011310170179554536,
      "acc_norm,none": 0.22184300341296928,
      "acc_norm_stderr,none": 0.012141659068147887
    },
    "arc_easy": {
      "acc,none": 0.39225589225589225,
      "acc_stderr,none": 0.010018744689650043,
      "acc_norm,none": 0.35858585858585856,
      "acc_norm_stderr,none": 0.009840882301225297
    },
    "boolq": {
      "acc,none": 0.6180428134556575,
      "acc_stderr,none": 0.008497851998427189
    },
    "hellaswag": {
      "acc,none": 0.2614021111332404,
      "acc_stderr,none": 0.004385004998923414,
      "acc_norm,none": 0.2674765982871938,
      "acc_norm_stderr,none": 0.004417384102398648
    },
    "lambada_openai": {
      "perplexity,none": 205.15639768675794,
      "perplexity_stderr,none": 11.85910091929417,
      "acc,none": 0.23015718998641568,
      "acc_stderr,none": 0.005864424171439992
    },
    "openbookqa": {
      "acc,none": 0.134,
      "acc_stderr,none": 0.015249692003854497,
      "acc_norm,none": 0.244,
      "acc_norm_stderr,none": 0.019226734893614567
    },
    "piqa": {
      "acc,none": 0.5952121871599565,
      "acc_stderr,none": 0.011452361375057025,
      "acc_norm,none": 0.5854189336235038,
      "acc_norm_stderr,none": 0.011494326682255168
    },
    "sciq": {
      "acc,none": 0.63,
      "acc_stderr,none": 0.015275252316519359,
      "acc_norm,none": 0.572,
      "acc_norm_stderr,none": 0.01565442624502928
    },
    "wikitext": {
      "word_perplexity,none": 180.27069075802413,
      "byte_perplexity,none": 2.3545097616343265,
      "bits_per_byte,none": 1.2354267039635143
    },
    "winogrande": {
      "acc,none": 0.5209155485398579,
      "acc_stderr,none": 0.014040185494212949
    }
  },
  "configs": {
    "arc_challenge": {
      "task": "arc_challenge",
      "group": [
        "ai2_arc",
        "multiple_choice"
      ],
      "dataset_path": "ai2_arc",
      "dataset_name": "ARC-Challenge",
      "training_split": "train",
      "validation_split": "validation",
      "test_split": "test",
      "doc_to_text": "Question: {{question}}\nAnswer:",
      "doc_to_target": "{{choices.label.index(answerKey)}}",
      "doc_to_choice": "{{choices.text}}",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "acc",
          "aggregation": "mean",
          "higher_is_better": true
        },
        {
          "metric": "acc_norm",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "multiple_choice",
      "repeats": 1,
      "should_decontaminate": true,
      "doc_to_decontamination_query": "Question: {{question}}\nAnswer:"
    },
    "arc_easy": {
      "task": "arc_easy",
      "group": [
        "ai2_arc",
        "multiple_choice"
      ],
      "dataset_path": "ai2_arc",
      "dataset_name": "ARC-Easy",
      "training_split": "train",
      "validation_split": "validation",
      "test_split": "test",
      "doc_to_text": "Question: {{question}}\nAnswer:",
      "doc_to_target": "{{choices.label.index(answerKey)}}",
      "doc_to_choice": "{{choices.text}}",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "acc",
          "aggregation": "mean",
          "higher_is_better": true
        },
        {
          "metric": "acc_norm",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "multiple_choice",
      "repeats": 1,
      "should_decontaminate": true,
      "doc_to_decontamination_query": "Question: {{question}}\nAnswer:"
    },
    "boolq": {
      "task": "boolq",
      "group": [
        "super-glue-lm-eval-v1"
      ],
      "dataset_path": "super_glue",
      "dataset_name": "boolq",
      "training_split": "train",
      "validation_split": "validation",
      "doc_to_text": "{{passage}}\nQuestion: {{question}}?\nAnswer:",
      "doc_to_target": "label",
      "doc_to_choice": [
        "no",
        "yes"
      ],
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "acc"
        }
      ],
      "output_type": "multiple_choice",
      "repeats": 1,
      "should_decontaminate": true,
      "doc_to_decontamination_query": "passage"
    },
    "hellaswag": {
      "task": "hellaswag",
      "group": [
        "multiple_choice"
      ],
      "dataset_path": "hellaswag",
      "training_split": "train",
      "validation_split": "validation",
      "doc_to_text": "{% set text = activity_label ~ ': ' ~ ctx_a ~ ' ' ~ ctx_b.capitalize() %}{{text|trim|replace(' [title]', '. ')|regex_replace('\\[.*?\\]', '')|replace('  ', ' ')}}",
      "doc_to_target": "{{label}}",
      "doc_to_choice": "{{endings|map('trim')|map('replace', ' [title]', '. ')|map('regex_replace', '\\[.*?\\]', '')|map('replace', '  ', ' ')|list}}",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "acc",
          "aggregation": "mean",
          "higher_is_better": true
        },
        {
          "metric": "acc_norm",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "multiple_choice",
      "repeats": 1,
      "should_decontaminate": false
    },
    "lambada_openai": {
      "task": "lambada_openai",
      "group": [
        "lambada",
        "loglikelihood",
        "perplexity"
      ],
      "dataset_path": "EleutherAI/lambada_openai",
      "dataset_name": "default",
      "test_split": "test",
      "template_aliases": "",
      "doc_to_text": "{{text.split(' ')[:-1]|join(' ')}}",
      "doc_to_target": "{{' '+text.split(' ')[-1]}}",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "perplexity",
          "aggregation": "perplexity",
          "higher_is_better": false
        },
        {
          "metric": "acc",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "loglikelihood",
      "repeats": 1,
      "should_decontaminate": true,
      "doc_to_decontamination_query": "{{text}}"
    },
    "openbookqa": {
      "task": "openbookqa",
      "group": [
        "multiple_choice"
      ],
      "dataset_path": "openbookqa",
      "dataset_name": "main",
      "training_split": "train",
      "validation_split": "validation",
      "test_split": "test",
      "doc_to_text": "question_stem",
      "doc_to_target": "{{choices.label.index(answerKey.lstrip())}}",
      "doc_to_choice": "{{choices.text}}",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "acc",
          "aggregation": "mean",
          "higher_is_better": true
        },
        {
          "metric": "acc_norm",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "multiple_choice",
      "repeats": 1,
      "should_decontaminate": true,
      "doc_to_decontamination_query": "question_stem"
    },
    "piqa": {
      "task": "piqa",
      "group": [
        "multiple_choice"
      ],
      "dataset_path": "piqa",
      "training_split": "train",
      "validation_split": "validation",
      "doc_to_text": "Question: {{goal}}\nAnswer:",
      "doc_to_target": "label",
      "doc_to_choice": "{{[sol1, sol2]}}",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "acc",
          "aggregation": "mean",
          "higher_is_better": true
        },
        {
          "metric": "acc_norm",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "multiple_choice",
      "repeats": 1,
      "should_decontaminate": true,
      "doc_to_decontamination_query": "goal"
    },
    "sciq": {
      "task": "sciq",
      "group": [
        "multiple_choice"
      ],
      "dataset_path": "sciq",
      "training_split": "train",
      "validation_split": "validation",
      "test_split": "test",
      "doc_to_text": "{{support.lstrip()}}\nQuestion: {{question}}\nAnswer:",
      "doc_to_target": 3,
      "doc_to_choice": "{{[distractor1, distractor2, distractor3, correct_answer]}}",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "acc",
          "aggregation": "mean",
          "higher_is_better": true
        },
        {
          "metric": "acc_norm",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "multiple_choice",
      "repeats": 1,
      "should_decontaminate": true,
      "doc_to_decontamination_query": "{{support}} {{question}}"
    },
    "wikitext": {
      "task": "wikitext",
      "group": [
        "perplexity",
        "loglikelihood_rolling"
      ],
      "dataset_path": "EleutherAI/wikitext_document_level",
      "dataset_name": "wikitext-2-raw-v1",
      "training_split": "train",
      "validation_split": "validation",
      "test_split": "test",
      "template_aliases": "",
      "doc_to_text": "",
      "doc_to_target": "<function wikitext_detokenizer at 0x7f78469f8040>",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "word_perplexity"
        },
        {
          "metric": "byte_perplexity"
        },
        {
          "metric": "bits_per_byte"
        }
      ],
      "output_type": "loglikelihood_rolling",
      "repeats": 1,
      "should_decontaminate": true,
      "doc_to_decontamination_query": "{{page}}"
    },
    "winogrande": {
      "task": "winogrande",
      "dataset_path": "winogrande",
      "dataset_name": "winogrande_xl",
      "training_split": "train",
      "validation_split": "validation",
      "doc_to_text": "<function doc_to_text at 0x7f78469caef0>",
      "doc_to_target": "<function doc_to_target at 0x7f78469cb370>",
      "doc_to_choice": "<function doc_to_choice at 0x7f78469cb5b0>",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "acc",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "multiple_choice",
      "repeats": 1,
      "should_decontaminate": false
    }
  },
  "versions": {
    "arc_challenge": "Yaml",
    "arc_easy": "Yaml",
    "boolq": "Yaml",
    "hellaswag": "Yaml",
    "lambada_openai": "Yaml",
    "openbookqa": "Yaml",
    "piqa": "Yaml",
    "sciq": "Yaml",
    "wikitext": "Yaml",
    "winogrande": "Yaml"
  },
  "config": {
    "model": "hf",
    "model_args": "pretrained=lomahony/eleuther-pythia70m-hh-sft",
    "num_fewshot": 0,
    "batch_size": 16,
    "batch_sizes": [],
    "device": "cuda:0",
    "use_cache": null,
    "limit": null,
    "bootstrap_iters": 100000
  },
  "git_hash": "4e44f0a"
}
hf (pretrained=lomahony/eleuther-pythia70m-hh-sft), limit: None, num_fewshot: 0, batch_size: 16
|     Task     |Version|Filter|    Metric     | Value  |   |Stderr |
|--------------|-------|------|---------------|-------:|---|------:|
|arc_challenge |Yaml   |none  |acc            |  0.1834|±  | 0.0113|
|              |       |none  |acc_norm       |  0.2218|±  | 0.0121|
|arc_easy      |Yaml   |none  |acc            |  0.3923|±  | 0.0100|
|              |       |none  |acc_norm       |  0.3586|±  | 0.0098|
|boolq         |Yaml   |none  |acc            |  0.6180|±  | 0.0085|
|hellaswag     |Yaml   |none  |acc            |  0.2614|±  | 0.0044|
|              |       |none  |acc_norm       |  0.2675|±  | 0.0044|
|lambada_openai|Yaml   |none  |perplexity     |205.1564|±  |11.8591|
|              |       |none  |acc            |  0.2302|±  | 0.0059|
|openbookqa    |Yaml   |none  |acc            |  0.1340|±  | 0.0152|
|              |       |none  |acc_norm       |  0.2440|±  | 0.0192|
|piqa          |Yaml   |none  |acc            |  0.5952|±  | 0.0115|
|              |       |none  |acc_norm       |  0.5854|±  | 0.0115|
|sciq          |Yaml   |none  |acc            |  0.6300|±  | 0.0153|
|              |       |none  |acc_norm       |  0.5720|±  | 0.0157|
|wikitext      |Yaml   |none  |word_perplexity|180.2707|   |       |
|              |       |none  |byte_perplexity|  2.3545|   |       |
|              |       |none  |bits_per_byte  |  1.2354|   |       |
|winogrande    |Yaml   |none  |acc            |  0.5209|±  | 0.0140|