eval_results/edbeeching/mixtral-8x7b-instruct-v0.1_merged/v0.2/arc/results_2024-04-14T13-11-24.629818.json

{
  "config_general": {
    "lighteval_sha": "?",
    "num_fewshot_seeds": 1,
    "override_batch_size": 1,
    "max_samples": null,
    "job_id": "",
    "start_time": 3249169.019665027,
    "end_time": 3252105.538397305,
    "total_evaluation_time_secondes": "2936.518732278142",
    "model_name": "edbeeching/mixtral-8x7b-instruct-v0.1_merged",
    "model_sha": "02e5e37da870d6382b35fd16e9545bbab51dd218",
    "model_dtype": "torch.bfloat16",
    "model_size": "87.49 GB",
    "config": null
  },
  "results": {
    "leaderboard|arc:challenge|25": {
      "acc": 0.5068259385665529,
      "acc_stderr": 0.014610029151379813,
      "acc_norm": 0.5503412969283277,
      "acc_norm_stderr": 0.014537144444284748
    },
    "all": {
      "acc": 0.5068259385665529,
      "acc_stderr": 0.014610029151379813,
      "acc_norm": 0.5503412969283277,
      "acc_norm_stderr": 0.014537144444284748
    }
  },
  "versions": {
    "leaderboard|arc:challenge|25": 0
  },
  "config_tasks": {
    "leaderboard|arc:challenge": {
      "name": "arc:challenge",
      "prompt_function": "arc",
      "hf_repo": "ai2_arc",
      "hf_subset": "ARC-Challenge",
      "metric": [
        "loglikelihood_acc",
        "loglikelihood_acc_norm_nospace"
      ],
      "hf_avail_splits": [
        "train",
        "test"
      ],
      "evaluation_splits": [
        "test"
      ],
      "few_shots_split": null,
      "few_shots_select": "random_sampling_from_train",
      "generation_size": 1,
      "stop_sequence": [
        "\n"
      ],
      "output_regex": null,
      "frozen": false,
      "suite": [
        "leaderboard",
        "arc"
      ],
      "original_num_docs": 1172,
      "effective_num_docs": 1172,
      "trust_dataset": true,
      "must_remove_duplicate_docs": null
    }
  },
  "summary_tasks": {
    "leaderboard|arc:challenge|25": {
      "hashes": {
        "hash_examples": "17b0cae357c0259e",
        "hash_full_prompts": "d44b17600302e2b8",
        "hash_input_tokens": "0149ae15d3f432fa",
        "hash_cont_tokens": "289aa98c400841d8"
      },
      "truncated": 0,
      "non_truncated": 1172,
      "padded": 4660,
      "non_padded": 27,
      "effective_few_shots": 25.0,
      "num_truncated_few_shots": 0
    }
  },
  "summary_general": {
    "hashes": {
      "hash_examples": "aaa6929c6d3771fb",
      "hash_full_prompts": "b29ea0f4ca87b218",
      "hash_input_tokens": "6064dbfd3e9d9140",
      "hash_cont_tokens": "a2928b768b852bf8"
    },
    "truncated": 0,
    "non_truncated": 1172,
    "padded": 4660,
    "non_padded": 27,
    "num_truncated_few_shots": 0
  }
}