eval_results/AI-MO/deepseek-math-7b-sft/aimo_v03.00/math/results_2024-04-26T03-29-04.824719.json

{
  "config_general": {
    "lighteval_sha": "?",
    "num_fewshot_seeds": 1,
    "override_batch_size": 2,
    "max_samples": null,
    "job_id": "",
    "start_time": 5321793.845179343,
    "end_time": 5331731.526041984,
    "total_evaluation_time_secondes": "9937.680862640962",
    "model_name": "AI-MO/deepseek-math-7b-sft",
    "model_sha": "f500a523198914c8fa81f759aed450551064ab3a",
    "model_dtype": "torch.bfloat16",
    "model_size": "12.93 GB",
    "config": null
  },
  "results": {
    "lighteval|math:algebra|0": {
      "qem": 0.6537489469250211,
      "qem_stderr": 0.013815248721392347
    },
    "lighteval|math:counting_and_probability|0": {
      "qem": 0.31645569620253167,
      "qem_stderr": 0.021384998424064838
    },
    "lighteval|math:geometry|0": {
      "qem": 0.31524008350730687,
      "qem_stderr": 0.02125083179556455
    },
    "lighteval|math:intermediate_algebra|0": {
      "qem": 0.2369878183831672,
      "qem_stderr": 0.014158768420812005
    },
    "lighteval|math:number_theory|0": {
      "qem": 0.34444444444444444,
      "qem_stderr": 0.02046774326022808
    },
    "lighteval|math:prealgebra|0": {
      "qem": 0.6360505166475315,
      "qem_stderr": 0.01631198194826093
    },
    "lighteval|math:precalculus|0": {
      "qem": 0.2967032967032967,
      "qem_stderr": 0.019567359566881232
    },
    "lighteval|math:_average|0": {
      "qem": 0.3999472575447571,
      "qem_stderr": 0.01813670459102914
    },
    "all": {
      "qem": 0.3999472575447571,
      "qem_stderr": 0.01813670459102914
    }
  },
  "versions": {
    "lighteval|math:algebra|0": 0,
    "lighteval|math:counting_and_probability|0": 0,
    "lighteval|math:geometry|0": 0,
    "lighteval|math:intermediate_algebra|0": 0,
    "lighteval|math:number_theory|0": 0,
    "lighteval|math:prealgebra|0": 0,
    "lighteval|math:precalculus|0": 0
  },
  "config_tasks": {
    "lighteval|math:algebra": {
      "name": "math:algebra",
      "prompt_function": "math",
      "hf_repo": "lighteval/MATH",
      "hf_subset": "algebra",
      "metric": [
        "quasi_exact_match_math"
      ],
      "hf_avail_splits": [
        "train",
        "test",
        "validation"
      ],
      "evaluation_splits": [
        "test"
      ],
      "few_shots_split": null,
      "few_shots_select": null,
      "generation_size": 2048,
      "stop_sequence": [
        "\n"
      ],
      "output_regex": null,
      "frozen": false,
      "suite": [
        "lighteval",
        "math"
      ],
      "original_num_docs": 1187,
      "effective_num_docs": 1187,
      "trust_dataset": true,
      "must_remove_duplicate_docs": null
    },
    "lighteval|math:counting_and_probability": {
      "name": "math:counting_and_probability",
      "prompt_function": "math",
      "hf_repo": "lighteval/MATH",
      "hf_subset": "counting_and_probability",
      "metric": [
        "quasi_exact_match_math"
      ],
      "hf_avail_splits": [
        "train",
        "test",
        "validation"
      ],
      "evaluation_splits": [
        "test"
      ],
      "few_shots_split": null,
      "few_shots_select": null,
      "generation_size": 2048,
      "stop_sequence": [
        "\n"
      ],
      "output_regex": null,
      "frozen": false,
      "suite": [
        "lighteval",
        "math"
      ],
      "original_num_docs": 474,
      "effective_num_docs": 474,
      "trust_dataset": true,
      "must_remove_duplicate_docs": null
    },
    "lighteval|math:geometry": {
      "name": "math:geometry",
      "prompt_function": "math",
      "hf_repo": "lighteval/MATH",
      "hf_subset": "geometry",
      "metric": [
        "quasi_exact_match_math"
      ],
      "hf_avail_splits": [
        "train",
        "test",
        "validation"
      ],
      "evaluation_splits": [
        "test"
      ],
      "few_shots_split": null,
      "few_shots_select": null,
      "generation_size": 2048,
      "stop_sequence": [
        "\n"
      ],
      "output_regex": null,
      "frozen": false,
      "suite": [
        "lighteval",
        "math"
      ],
      "original_num_docs": 479,
      "effective_num_docs": 479,
      "trust_dataset": true,
      "must_remove_duplicate_docs": null
    },
    "lighteval|math:intermediate_algebra": {
      "name": "math:intermediate_algebra",
      "prompt_function": "math",
      "hf_repo": "lighteval/MATH",
      "hf_subset": "intermediate_algebra",
      "metric": [
        "quasi_exact_match_math"
      ],
      "hf_avail_splits": [
        "train",
        "test",
        "validation"
      ],
      "evaluation_splits": [
        "test"
      ],
      "few_shots_split": null,
      "few_shots_select": null,
      "generation_size": 2048,
      "stop_sequence": [
        "\n"
      ],
      "output_regex": null,
      "frozen": false,
      "suite": [
        "lighteval",
        "math"
      ],
      "original_num_docs": 903,
      "effective_num_docs": 903,
      "trust_dataset": true,
      "must_remove_duplicate_docs": null
    },
    "lighteval|math:number_theory": {
      "name": "math:number_theory",
      "prompt_function": "math",
      "hf_repo": "lighteval/MATH",
      "hf_subset": "number_theory",
      "metric": [
        "quasi_exact_match_math"
      ],
      "hf_avail_splits": [
        "train",
        "test",
        "validation"
      ],
      "evaluation_splits": [
        "test"
      ],
      "few_shots_split": null,
      "few_shots_select": null,
      "generation_size": 2048,
      "stop_sequence": [
        "\n"
      ],
      "output_regex": null,
      "frozen": false,
      "suite": [
        "lighteval",
        "math"
      ],
      "original_num_docs": 540,
      "effective_num_docs": 540,
      "trust_dataset": true,
      "must_remove_duplicate_docs": null
    },
    "lighteval|math:prealgebra": {
      "name": "math:prealgebra",
      "prompt_function": "math",
      "hf_repo": "lighteval/MATH",
      "hf_subset": "prealgebra",
      "metric": [
        "quasi_exact_match_math"
      ],
      "hf_avail_splits": [
        "train",
        "test",
        "validation"
      ],
      "evaluation_splits": [
        "test"
      ],
      "few_shots_split": null,
      "few_shots_select": null,
      "generation_size": 2048,
      "stop_sequence": [
        "\n"
      ],
      "output_regex": null,
      "frozen": false,
      "suite": [
        "lighteval",
        "math"
      ],
      "original_num_docs": 871,
      "effective_num_docs": 871,
      "trust_dataset": true,
      "must_remove_duplicate_docs": null
    },
    "lighteval|math:precalculus": {
      "name": "math:precalculus",
      "prompt_function": "math",
      "hf_repo": "lighteval/MATH",
      "hf_subset": "precalculus",
      "metric": [
        "quasi_exact_match_math"
      ],
      "hf_avail_splits": [
        "train",
        "test",
        "validation"
      ],
      "evaluation_splits": [
        "test"
      ],
      "few_shots_split": null,
      "few_shots_select": null,
      "generation_size": 2048,
      "stop_sequence": [
        "\n"
      ],
      "output_regex": null,
      "frozen": false,
      "suite": [
        "lighteval",
        "math"
      ],
      "original_num_docs": 546,
      "effective_num_docs": 546,
      "trust_dataset": true,
      "must_remove_duplicate_docs": null
    }
  },
  "summary_tasks": {
    "lighteval|math:algebra|0": {
      "hashes": {
        "hash_examples": "37a2fd2f076d2e49",
        "hash_full_prompts": "461f2ab197cdfd01",
        "hash_input_tokens": "bd3e731d75bc03e6",
        "hash_cont_tokens": "31a8151f29375e6f"
      },
      "truncated": 1187,
      "non_truncated": 0,
      "padded": 63,
      "non_padded": 1124,
      "effective_few_shots": 0.0,
      "num_truncated_few_shots": 0
    },
    "lighteval|math:counting_and_probability|0": {
      "hashes": {
        "hash_examples": "97b4892e28bc078b",
        "hash_full_prompts": "e2cc9eb28ca159b1",
        "hash_input_tokens": "55728dc6558ad660",
        "hash_cont_tokens": "6f61ec4b61683a6b"
      },
      "truncated": 474,
      "non_truncated": 0,
      "padded": 17,
      "non_padded": 457,
      "effective_few_shots": 0.0,
      "num_truncated_few_shots": 0
    },
    "lighteval|math:geometry|0": {
      "hashes": {
        "hash_examples": "9e9f0228b8b3d093",
        "hash_full_prompts": "e581f42fefeed8c9",
        "hash_input_tokens": "6615f77877bf8cef",
        "hash_cont_tokens": "fcac05a87c8615b2"
      },
      "truncated": 479,
      "non_truncated": 0,
      "padded": 60,
      "non_padded": 419,
      "effective_few_shots": 0.0,
      "num_truncated_few_shots": 0
    },
    "lighteval|math:intermediate_algebra|0": {
      "hashes": {
        "hash_examples": "cfe73a8e28ae94de",
        "hash_full_prompts": "7557d30ba2cc15ef",
        "hash_input_tokens": "608f04e5c215ffad",
        "hash_cont_tokens": "c5f1ce8e762a2fb6"
      },
      "truncated": 903,
      "non_truncated": 0,
      "padded": 15,
      "non_padded": 888,
      "effective_few_shots": 0.0,
      "num_truncated_few_shots": 0
    },
    "lighteval|math:number_theory|0": {
      "hashes": {
        "hash_examples": "4ee5237cf144afac",
        "hash_full_prompts": "7b983a6fe1e3d0a8",
        "hash_input_tokens": "0a9b44cdfde7644d",
        "hash_cont_tokens": "d6cc423845c09305"
      },
      "truncated": 539,
      "non_truncated": 1,
      "padded": 1,
      "non_padded": 539,
      "effective_few_shots": 0.0,
      "num_truncated_few_shots": 0
    },
    "lighteval|math:prealgebra|0": {
      "hashes": {
        "hash_examples": "3fb3afeb885f73d8",
        "hash_full_prompts": "736a03165dbf8f49",
        "hash_input_tokens": "434f9915c1b3fd21",
        "hash_cont_tokens": "50a82b4c2a2092dc"
      },
      "truncated": 871,
      "non_truncated": 0,
      "padded": 18,
      "non_padded": 853,
      "effective_few_shots": 0.0,
      "num_truncated_few_shots": 0
    },
    "lighteval|math:precalculus|0": {
      "hashes": {
        "hash_examples": "753e25ab9ec4b46c",
        "hash_full_prompts": "632ca5aa79f53b59",
        "hash_input_tokens": "7808ce9bbfbc6f20",
        "hash_cont_tokens": "a0cc77f37c6898dd"
      },
      "truncated": 546,
      "non_truncated": 0,
      "padded": 4,
      "non_padded": 542,
      "effective_few_shots": 0.0,
      "num_truncated_few_shots": 0
    }
  },
  "summary_general": {
    "hashes": {
      "hash_examples": "b76099aa9092a203",
      "hash_full_prompts": "2d2e105e1a0eeab9",
      "hash_input_tokens": "ec60d48c4ec91205",
      "hash_cont_tokens": "d3d9b056295e355f"
    },
    "truncated": 4999,
    "non_truncated": 1,
    "padded": 178,
    "non_padded": 4822,
    "num_truncated_few_shots": 0
  }
}