eval_results/abhishek/autotrain-llama3-70b-orpo-v1/main/hellaswag/results_2024-05-03T09-21-59.464924.json

{
  "config_general": {
    "lighteval_sha": "?",
    "num_fewshot_seeds": 1,
    "override_batch_size": 4,
    "max_samples": null,
    "job_id": "",
    "start_time": 291443.637692272,
    "end_time": 300254.288037253,
    "total_evaluation_time_secondes": "8810.650344980997",
    "model_name": "abhishek/autotrain-llama3-70b-orpo-v1",
    "model_sha": "053236c6846cc561c1503ba05e2b28c94855a432",
    "model_dtype": "torch.float16",
    "model_size": "131.73 GB",
    "config": null
  },
  "results": {
    "leaderboard|hellaswag|10": {
      "acc": 0.6535550687114121,
      "acc_stderr": 0.004748645133281571,
      "acc_norm": 0.8561043616809401,
      "acc_norm_stderr": 0.003502665674197143
    },
    "all": {
      "acc": 0.6535550687114121,
      "acc_stderr": 0.004748645133281571,
      "acc_norm": 0.8561043616809401,
      "acc_norm_stderr": 0.003502665674197143
    }
  },
  "versions": {
    "leaderboard|hellaswag|10": 0
  },
  "config_tasks": {
    "leaderboard|hellaswag": {
      "name": "hellaswag",
      "prompt_function": "hellaswag_harness",
      "hf_repo": "hellaswag",
      "hf_subset": "default",
      "metric": [
        "loglikelihood_acc",
        "loglikelihood_acc_norm"
      ],
      "hf_avail_splits": [
        "train",
        "test",
        "validation"
      ],
      "evaluation_splits": [
        "validation"
      ],
      "few_shots_split": null,
      "few_shots_select": "random_sampling_from_train",
      "generation_size": -1,
      "stop_sequence": [
        "\n"
      ],
      "output_regex": null,
      "frozen": false,
      "suite": [
        "leaderboard"
      ],
      "original_num_docs": 10042,
      "effective_num_docs": 10042,
      "trust_dataset": true,
      "must_remove_duplicate_docs": null
    }
  },
  "summary_tasks": {
    "leaderboard|hellaswag|10": {
      "hashes": {
        "hash_examples": "31985c805c3a737e",
        "hash_full_prompts": "451e22e8c3aaeeb6",
        "hash_input_tokens": "1d3a37070a440e02",
        "hash_cont_tokens": "b2a14e103560984a"
      },
      "truncated": 0,
      "non_truncated": 10042,
      "padded": 39887,
      "non_padded": 281,
      "effective_few_shots": 10.0,
      "num_truncated_few_shots": 0
    }
  },
  "summary_general": {
    "hashes": {
      "hash_examples": "63bc2cf8bae03fbc",
      "hash_full_prompts": "b2452b7405d0326a",
      "hash_input_tokens": "9a84c589bab75f98",
      "hash_cont_tokens": "032ea180b01f16fd"
    },
    "truncated": 0,
    "non_truncated": 10042,
    "padded": 39887,
    "non_padded": 281,
    "num_truncated_few_shots": 0
  }
}