eval_results/google/gemma-2b-it/main/ifeval/results_2024-03-02T15-39-45.758970.json

{
  "config_general": {
    "lighteval_sha": "?",
    "num_fewshot_seeds": 1,
    "override_batch_size": 4,
    "max_samples": null,
    "job_id": "",
    "start_time": 1795047.390320911,
    "end_time": 1795356.647872697,
    "total_evaluation_time_secondes": "309.2575517860241",
    "model_name": "google/gemma-2b-it",
    "model_sha": "718cb189da9c5b2e55abe86f2eeffee9b4ae0dad",
    "model_dtype": "torch.bfloat16",
    "model_size": "4.68 GB",
    "config": null
  },
  "results": {
    "custom|ifeval|0": {
      "prompt_level_strict_acc": 0.21811460258780038,
      "prompt_level_strict_acc_stderr": 0.017771211776653858,
      "inst_level_strict_acc": 0.3333333333333333,
      "inst_level_strict_acc_stderr": 0.0004901521262712775,
      "prompt_level_loose_acc": 0.24953789279112754,
      "prompt_level_loose_acc_stderr": 0.01862240450980586,
      "inst_level_loose_acc": 0.3645083932853717,
      "inst_level_loose_acc_stderr": 0.0005178950282977614
    }
  },
  "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": "11515114fa95b586",
        "hash_input_tokens": "bf53f9d6df0fe042",
        "hash_cont_tokens": "28663f5270fde297"
      },
      "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": "ffc22c3f62f84b94",
      "hash_input_tokens": "b03f367762032386",
      "hash_cont_tokens": "ff2f641c58527477"
    },
    "truncated": 0,
    "non_truncated": 541,
    "padded": 0,
    "non_padded": 541,
    "num_truncated_few_shots": 0
  }
}