eval_results/HuggingFaceH4/zephyr-7b-beta-ift/v0.3/ifeval/results_2024-03-14T23-22-03.186605.json

{
  "config_general": {
    "lighteval_sha": "?",
    "num_fewshot_seeds": 1,
    "override_batch_size": 4,
    "max_samples": null,
    "job_id": "",
    "start_time": 1682787.621648727,
    "end_time": 1683587.877186361,
    "total_evaluation_time_secondes": "800.255537634017",
    "model_name": "HuggingFaceH4/zephyr-7b-beta-ift",
    "model_sha": "a8ded750732ee39fc1e2418fc72d26025e6ed1f2",
    "model_dtype": "torch.bfloat16",
    "model_size": "13.99 GB",
    "config": null
  },
  "results": {
    "custom|ifeval|0": {
      "prompt_level_strict_acc": 0.36229205175600737,
      "prompt_level_strict_acc_stderr": 0.020684424314965397,
      "inst_level_strict_acc": 0.4784172661870504,
      "inst_level_strict_acc_stderr": 0.0005317971001927052,
      "prompt_level_loose_acc": 0.39926062846580407,
      "prompt_level_loose_acc_stderr": 0.02107533133270135,
      "inst_level_loose_acc": 0.513189448441247,
      "inst_level_loose_acc_stderr": 0.0005316741410630218
    }
  },
  "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,
      "trust_dataset": null
    }
  },
  "summary_tasks": {
    "custom|ifeval|0": {
      "hashes": {
        "hash_examples": "e99cbf567588d7c6",
        "hash_full_prompts": "46932ca113ba6b0c",
        "hash_input_tokens": "8b2e0300fbfb70bc",
        "hash_cont_tokens": "aae191c99d543958"
      },
      "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": "79a7e59f5b1aaee8"
    },
    "truncated": 0,
    "non_truncated": 541,
    "padded": 0,
    "non_padded": 541,
    "num_truncated_few_shots": 0
  }
}