{
  "results": {
    "arc_challenge": {
      "acc,none": 0.3199658703071672,
      "acc_stderr,none": 0.013631345807016193,
      "acc_norm,none": 0.3532423208191126,
      "acc_norm_stderr,none": 0.013967822714840055
    },
    "arc_easy": {
      "acc,none": 0.6721380471380471,
      "acc_stderr,none": 0.009632587076170016,
      "acc_norm,none": 0.5955387205387206,
      "acc_norm_stderr,none": 0.010070746648278783
    },
    "lambada_openai": {
      "perplexity,none": 4.855671424502843,
      "perplexity_stderr,none": 0.11455715396173873,
      "acc,none": 0.6574810789831166,
      "acc_stderr,none": 0.006611438859225025
    },
    "logiqa": {
      "acc,none": 0.23348694316436253,
      "acc_stderr,none": 0.016593362460570887,
      "acc_norm,none": 0.2749615975422427,
      "acc_norm_stderr,none": 0.017512971782225207
    },
    "piqa": {
      "acc,none": 0.7557127312295974,
      "acc_stderr,none": 0.010024765172284218,
      "acc_norm,none": 0.7665941240478781,
      "acc_norm_stderr,none": 0.009869247889521015
    },
    "sciq": {
      "acc,none": 0.898,
      "acc_stderr,none": 0.009575368801653895,
      "acc_norm,none": 0.837,
      "acc_norm_stderr,none": 0.011686212712746839
    },
    "winogrande": {
      "acc,none": 0.6172059984214681,
      "acc_stderr,none": 0.013660946109442016
    },
    "wsc": {
      "acc,none": 0.36538461538461536,
      "acc_stderr,none": 0.0474473339327792
    }
  },
  "configs": {
    "arc_challenge": {
      "task": "arc_challenge",
      "group": [
        "ai2_arc"
      ],
      "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"
      ],
      "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:"
    },
    "lambada_openai": {
      "task": "lambada_openai",
      "group": [
        "lambada"
      ],
      "dataset_path": "EleutherAI/lambada_openai",
      "dataset_name": "default",
      "test_split": "test",
      "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}}"
    },
    "logiqa": {
      "task": "logiqa",
      "dataset_path": "EleutherAI/logiqa",
      "dataset_name": "logiqa",
      "training_split": "train",
      "validation_split": "validation",
      "test_split": "test",
      "doc_to_text": "<function doc_to_text at 0x7f38920d0dc0>",
      "doc_to_target": "<function doc_to_target at 0x7f38920d1120>",
      "doc_to_choice": "{{options}}",
      "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": "{{context}}"
    },
    "piqa": {
      "task": "piqa",
      "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",
      "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}}"
    },
    "winogrande": {
      "task": "winogrande",
      "dataset_path": "winogrande",
      "dataset_name": "winogrande_xl",
      "training_split": "train",
      "validation_split": "validation",
      "doc_to_text": "<function doc_to_text at 0x7f3892141000>",
      "doc_to_target": "<function doc_to_target at 0x7f3892141360>",
      "doc_to_choice": "<function doc_to_choice at 0x7f38921416c0>",
      "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": true,
      "doc_to_decontamination_query": "sentence"
    },
    "wsc": {
      "task": "wsc",
      "group": [
        "super-glue-lm-eval-v1"
      ],
      "dataset_path": "super_glue",
      "dataset_name": "wsc.fixed",
      "training_split": "train",
      "validation_split": "validation",
      "doc_to_text": "<function default_doc_to_text at 0x7f3891fd0a60>",
      "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": false
    }
  },
  "versions": {
    "arc_challenge": "Yaml",
    "arc_easy": "Yaml",
    "lambada_openai": "Yaml",
    "logiqa": "Yaml",
    "piqa": "Yaml",
    "sciq": "Yaml",
    "winogrande": "Yaml",
    "wsc": "Yaml"
  },
  "config": {
    "model": "hf",
    "model_args": "pretrained=usvsnsp/pythia-6.9b-ppo,dtype=float16",
    "batch_size": 1,
    "batch_sizes": [],
    "device": null,
    "use_cache": null,
    "limit": null,
    "bootstrap_iters": 100000
  },
  "git_hash": "0aa37743"
}