Downloading and preparing dataset super_glue/boolq to /home/laura/.cache/huggingface/datasets/super_glue/boolq/1.0.3/bb9675f958ebfee0d5d6dc5476fafe38c79123727a7258d515c450873dbdbbed...
Dataset super_glue downloaded and prepared to /home/laura/.cache/huggingface/datasets/super_glue/boolq/1.0.3/bb9675f958ebfee0d5d6dc5476fafe38c79123727a7258d515c450873dbdbbed. Subsequent calls will reuse this data.
Downloading and preparing dataset openbookqa/main to /home/laura/.cache/huggingface/datasets/openbookqa/main/1.0.1/f338ccacfbc86fb8c2de3aa1c06d2ce686933de3bca284dba97d32592c52b33f...
Dataset openbookqa downloaded and prepared to /home/laura/.cache/huggingface/datasets/openbookqa/main/1.0.1/f338ccacfbc86fb8c2de3aa1c06d2ce686933de3bca284dba97d32592c52b33f. Subsequent calls will reuse this data.
Downloading and preparing dataset piqa/plain_text to /home/laura/.cache/huggingface/datasets/piqa/plain_text/1.1.0/6c611c1a9bf220943c4174e117d3b660859665baf1d43156230116185312d011...
Dataset piqa downloaded and prepared to /home/laura/.cache/huggingface/datasets/piqa/plain_text/1.1.0/6c611c1a9bf220943c4174e117d3b660859665baf1d43156230116185312d011. Subsequent calls will reuse this data.
Downloading and preparing dataset sciq/default to /home/laura/.cache/huggingface/datasets/sciq/default/0.1.0/50e5c6e3795b55463819d399ec417bfd4c3c621105e00295ddb5f3633d708493...
Dataset sciq downloaded and prepared to /home/laura/.cache/huggingface/datasets/sciq/default/0.1.0/50e5c6e3795b55463819d399ec417bfd4c3c621105e00295ddb5f3633d708493. Subsequent calls will reuse this data.
Downloading and preparing dataset winogrande/winogrande_xl to /home/laura/.cache/huggingface/datasets/winogrande/winogrande_xl/1.1.0/a826c3d3506aefe0e9e9390dcb53271070536586bab95849876b2c1743df56e2...
Dataset winogrande downloaded and prepared to /home/laura/.cache/huggingface/datasets/winogrande/winogrande_xl/1.1.0/a826c3d3506aefe0e9e9390dcb53271070536586bab95849876b2c1743df56e2. Subsequent calls will reuse this data.
bootstrapping for stddev: perplexity
{
  "results": {
    "arc_challenge": {
      "acc,none": 0.21843003412969283,
      "acc_stderr,none": 0.012074291605700959,
      "acc_norm,none": 0.2645051194539249,
      "acc_norm_stderr,none": 0.012889272949313368
    },
    "arc_easy": {
      "acc,none": 0.54503367003367,
      "acc_stderr,none": 0.010218084454602589,
      "acc_norm,none": 0.5370370370370371,
      "acc_norm_stderr,none": 0.010231597249131058
    },
    "boolq": {
      "acc,none": 0.4871559633027523,
      "acc_stderr,none": 0.008742169169427067
    },
    "hellaswag": {
      "acc,none": 0.33827922724556864,
      "acc_stderr,none": 0.004721571443354456,
      "acc_norm,none": 0.40818562039434375,
      "acc_norm_stderr,none": 0.004904933500255884
    },
    "lambada_openai": {
      "perplexity,none": 14.485555582236119,
      "perplexity_stderr,none": 0.4358013409476018,
      "acc,none": 0.4422666407917718,
      "acc_stderr,none": 0.006919384666875831
    },
    "openbookqa": {
      "acc,none": 0.188,
      "acc_stderr,none": 0.01749067888034625,
      "acc_norm,none": 0.28,
      "acc_norm_stderr,none": 0.020099950647503237
    },
    "piqa": {
      "acc,none": 0.6806311207834603,
      "acc_stderr,none": 0.010877964076613737,
      "acc_norm,none": 0.6692056583242655,
      "acc_norm_stderr,none": 0.010977520584714429
    },
    "sciq": {
      "acc,none": 0.892,
      "acc_stderr,none": 0.009820001651345682,
      "acc_norm,none": 0.887,
      "acc_norm_stderr,none": 0.01001655286669685
    },
    "wikitext": {
      "word_perplexity,none": 34.50450469911897,
      "byte_perplexity,none": 1.7927778872125213,
      "bits_per_byte,none": 0.842196759334895
    },
    "winogrande": {
      "acc,none": 0.5335438042620363,
      "acc_stderr,none": 0.014020826677598103
    }
  },
  "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": 5,
      "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": 5,
      "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": 5,
      "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": 5,
      "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": 5,
      "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": 5,
      "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": 5,
      "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": 5,
      "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 0x7efb86530040>",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 5,
      "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 0x7efb86502ef0>",
      "doc_to_target": "<function doc_to_target at 0x7efb86503370>",
      "doc_to_choice": "<function doc_to_choice at 0x7efb865035b0>",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 5,
      "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=EleutherAI/pythia-410m",
    "num_fewshot": 5,
    "batch_size": 16,
    "batch_sizes": [],
    "device": "cuda:0",
    "use_cache": null,
    "limit": null,
    "bootstrap_iters": 100000
  },
  "git_hash": "4e44f0a"
}
hf (pretrained=EleutherAI/pythia-410m), limit: None, num_fewshot: 5, batch_size: 16
|     Task     |Version|Filter|    Metric     | Value |   |Stderr|
|--------------|-------|------|---------------|------:|---|-----:|
|arc_challenge |Yaml   |none  |acc            | 0.2184|±  |0.0121|
|              |       |none  |acc_norm       | 0.2645|±  |0.0129|
|arc_easy      |Yaml   |none  |acc            | 0.5450|±  |0.0102|
|              |       |none  |acc_norm       | 0.5370|±  |0.0102|
|boolq         |Yaml   |none  |acc            | 0.4872|±  |0.0087|
|hellaswag     |Yaml   |none  |acc            | 0.3383|±  |0.0047|
|              |       |none  |acc_norm       | 0.4082|±  |0.0049|
|lambada_openai|Yaml   |none  |perplexity     |14.4856|±  |0.4358|
|              |       |none  |acc            | 0.4423|±  |0.0069|
|openbookqa    |Yaml   |none  |acc            | 0.1880|±  |0.0175|
|              |       |none  |acc_norm       | 0.2800|±  |0.0201|
|piqa          |Yaml   |none  |acc            | 0.6806|±  |0.0109|
|              |       |none  |acc_norm       | 0.6692|±  |0.0110|
|sciq          |Yaml   |none  |acc            | 0.8920|±  |0.0098|
|              |       |none  |acc_norm       | 0.8870|±  |0.0100|
|wikitext      |Yaml   |none  |word_perplexity|34.5045|   |      |
|              |       |none  |byte_perplexity| 1.7928|   |      |
|              |       |none  |bits_per_byte  | 0.8422|   |      |
|winogrande    |Yaml   |none  |acc            | 0.5335|±  |0.0140|