{
  "results": {
    "ifeval": {
      "prompt_level_strict_acc,none": 0.0036968576709796672,
      "prompt_level_strict_acc_stderr,none": 0.0026116515685375786,
      "inst_level_strict_acc,none": 0.004796163069544364,
      "inst_level_strict_acc_stderr,none": "N/A",
      "prompt_level_loose_acc,none": 0.0036968576709796672,
      "prompt_level_loose_acc_stderr,none": 0.0026116515685375786,
      "inst_level_loose_acc,none": 0.005995203836930456,
      "inst_level_loose_acc_stderr,none": "N/A",
      "alias": "ifeval"
    }
  },
  "configs": {
    "ifeval": {
      "task": "ifeval",
      "dataset_path": "wis-k/instruction-following-eval",
      "test_split": "train",
      "doc_to_text": "prompt",
      "doc_to_target": 0,
      "process_results": "def process_results(doc, results):\n    eval_logger.warning(\n        \"This task is meant for chat-finetuned models, and may not give meaningful results for models other than `openai` or `anthropic` if `doc_to_text` in its YAML is not wrapped in the appropriate chat template string. This warning will be removed when chat templating support is added natively to local models\"\n    )\n\n    inp = InputExample(\n        key=doc[\"key\"],\n        instruction_id_list=doc[\"instruction_id_list\"],\n        prompt=doc[\"prompt\"],\n        kwargs=doc[\"kwargs\"],\n    )\n    response = results[0]\n\n    out_strict = test_instruction_following_strict(inp, response)\n    out_loose = test_instruction_following_loose(inp, response)\n\n    return {\n        \"prompt_level_strict_acc\": out_strict.follow_all_instructions,\n        \"inst_level_strict_acc\": out_strict.follow_instruction_list,\n        \"prompt_level_loose_acc\": out_loose.follow_all_instructions,\n        \"inst_level_loose_acc\": out_loose.follow_instruction_list,\n    }\n",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "prompt_level_strict_acc",
          "aggregation": "mean",
          "higher_is_better": true
        },
        {
          "metric": "inst_level_strict_acc",
          "aggregation": "def agg_inst_level_acc(items):\n    flat_items = [item for sublist in items for item in sublist]\n    inst_level_acc = sum(flat_items) / len(flat_items)\n    return inst_level_acc\n",
          "higher_is_better": true
        },
        {
          "metric": "prompt_level_loose_acc",
          "aggregation": "mean",
          "higher_is_better": true
        },
        {
          "metric": "inst_level_loose_acc",
          "aggregation": "def agg_inst_level_acc(items):\n    flat_items = [item for sublist in items for item in sublist]\n    inst_level_acc = sum(flat_items) / len(flat_items)\n    return inst_level_acc\n",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [],
        "do_sample": false,
        "temperature": 0.0,
        "max_gen_toks": 1280
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 2.0
      }
    }
  },
  "versions": {
    "ifeval": 2.0
  },
  "n-shot": {
    "ifeval": 0
  },
  "config": {
    "model": "hf",
    "model_args": "pretrained=Qwen/Qwen1.5-0.5B-Chat,revision=main,dtype=bfloat16",
    "batch_size": "auto",
    "batch_sizes": [],
    "device": null,
    "use_cache": null,
    "limit": null,
    "bootstrap_iters": 100000,
    "gen_kwargs": null
  },
  "git_hash": "2d2e67f"
}