eval_results/HuggingFaceH4/mistral-7b-ift/v41.11/ifeval/results_2024-03-08T14-09-19.350081.json

{
  "config_general": {
    "lighteval_sha": "?",
    "num_fewshot_seeds": 1,
    "override_batch_size": 4,
    "max_samples": null,
    "job_id": "",
    "start_time": 2220328.975879202,
    "end_time": 2220968.708606255,
    "total_evaluation_time_secondes": "639.7327270526439",
    "model_name": "HuggingFaceH4/mistral-7b-ift",
    "model_sha": "a1bc966883026e5911c7c62a5a2a63029d0fd686",
    "model_dtype": "torch.bfloat16",
    "model_size": "13.99 GB",
    "config": null
  },
  "results": {
    "custom|ifeval|0": {
      "prompt_level_strict_acc": 0.34750462107208874,
      "prompt_level_strict_acc_stderr": 0.02049142365341572,
      "inst_level_strict_acc": 0.46522781774580335,
      "inst_level_strict_acc_stderr": 0.0005241845414797677,
      "prompt_level_loose_acc": 0.3789279112754159,
      "prompt_level_loose_acc_stderr": 0.020876246883668938,
      "inst_level_loose_acc": 0.49760191846522783,
      "inst_level_loose_acc_stderr": 0.0005237767519428235
    }
  },
  "versions": {
    "custom|ifeval|0": 0
  },
  "config_tasks": {
    "custom|ifeval": {
      "name": "ifeval",
      "prompt_function": "ifeval_prompt",
      "hf_repo": "wis-k/instruction-following-eval",
      "hf_subset": "default",
      "metric": [
        "ifeval_metric"
      ],
      "hf_avail_splits": [
        "train"
      ],
      "evaluation_splits": [
        "train"
      ],
      "few_shots_split": "train",
      "few_shots_select": "random_sampling",
      "generation_size": 1280,
      "stop_sequence": [],
      "output_regex": null,
      "frozen": false,
      "suite": [
        "custom"
      ],
      "original_num_docs": 541,
      "effective_num_docs": 541
    }
  },
  "summary_tasks": {
    "custom|ifeval|0": {
      "hashes": {
        "hash_examples": "e99cbf567588d7c6",
        "hash_full_prompts": "46932ca113ba6b0c",
        "hash_input_tokens": "8b2e0300fbfb70bc",
        "hash_cont_tokens": "be73ffa25946d43f"
      },
      "truncated": 0,
      "non_truncated": 541,
      "padded": 0,
      "non_padded": 541,
      "effective_few_shots": 0.0,
      "num_truncated_few_shots": 0
    }
  },
  "summary_general": {
    "hashes": {
      "hash_examples": "ea046ab2c6fc5928",
      "hash_full_prompts": "8ed52f7b74eb0590",
      "hash_input_tokens": "9f4b7e9e7ff95d4a",
      "hash_cont_tokens": "65bc5a6338734904"
    },
    "truncated": 0,
    "non_truncated": 541,
    "padded": 0,
    "non_padded": 541,
    "num_truncated_few_shots": 0
  }
}