OLMoE-0125-Instruct-Compressed-Experimental/evaluation_results.json

{
  "scope": "experimental_single_seed",
  "base_model": "allenai/OLMoE-1B-7B-0125-Instruct",
  "base_revision": "b89a7c4bc24fb9e55ce2543c9458ce0ca5c4650e",
  "seed": 42,
  "measurement_status": "complete",
  "pending_categories": {
    "base": [],
    "cut": [],
    "healed": []
  },
  "measurements": {
    "arc_science": {
      "base": {
        "acc": 0.455,
        "n": 200
      },
      "cut": {
        "acc": 0.445,
        "n": 200
      },
      "healed": {
        "acc": 0.45,
        "n": 200
      }
    },
    "bbq_safety": {
      "base": {
        "acc": 0.415,
        "n": 200
      },
      "cut": {
        "acc": 0.425,
        "n": 200
      },
      "healed": {
        "acc": 0.395,
        "n": 200
      }
    },
    "gpqa_reasoning": {
      "base": {
        "acc": 0.22727272727272727,
        "n": 198
      },
      "cut": {
        "acc": 0.1919191919191919,
        "n": 198
      },
      "healed": {
        "acc": 0.16666666666666666,
        "n": 198
      }
    },
    "gsm8k_math": {
      "base": {
        "acc": 0.65,
        "n": 200
      },
      "cut": {
        "acc": 0.64,
        "n": 200
      },
      "healed": {
        "acc": 0.43,
        "n": 200
      }
    },
    "hellaswag_commonsense": {
      "base": {
        "acc": 0.67,
        "n": 200
      },
      "cut": {
        "acc": 0.65,
        "n": 200
      },
      "healed": {
        "acc": 0.66,
        "n": 200
      }
    },
    "ifeval_instruction_following": {
      "base": {
        "acc": 0.6126760563380281,
        "n": 142,
        "ifeval_coverage": 0.6153846153846154,
        "ifeval_n_scored": 142,
        "ifeval_n_excluded": 58,
        "ifeval_budget": {
          "max_new": 1024,
          "n": 200
        }
      },
      "cut": {
        "acc": 0.528169014084507,
        "n": 142,
        "ifeval_coverage": 0.6153846153846154,
        "ifeval_n_scored": 142,
        "ifeval_n_excluded": 58,
        "ifeval_budget": {
          "max_new": 1024,
          "n": 200
        }
      },
      "healed": {
        "acc": 0.5563380281690141,
        "n": 142,
        "ifeval_coverage": 0.6153846153846154,
        "ifeval_n_scored": 142,
        "ifeval_n_excluded": 58,
        "ifeval_budget": {
          "max_new": 1024,
          "n": 200
        }
      }
    },
    "mmlu_knowledge": {
      "base": {
        "acc": 0.305,
        "n": 200
      },
      "cut": {
        "acc": 0.275,
        "n": 200
      },
      "healed": {
        "acc": 0.265,
        "n": 200
      }
    },
    "multilingual_knowledge": {
      "base": {
        "acc": 0.28,
        "n": 200
      },
      "cut": {
        "acc": 0.275,
        "n": 200
      },
      "healed": {
        "acc": 0.265,
        "n": 200
      }
    },
    "wikitext_language": {
      "base": {
        "ppl": 18.305546793311198,
        "n": 64
      },
      "cut": {
        "ppl": 23.76837327292051,
        "n": 64
      },
      "healed": {
        "ppl": 21.6319395015557,
        "n": 64
      }
    }
  },
  "source_measurement_sha256": {
    "base": "ec64b19dd0644e3ec6dff0daeb3f42df443d220fa16df73677b7f5e74ffe79dd",
    "cut": "197c37ff224cf1b640017b9814f3cadb7d7123b1e059523c80ed4aaff49cfe49",
    "healed": "9e9829a40df64823278bb55737625e4e2803ea84ab7cf3d6c3ac2952a9276466"
  },
  "healed_parameters": 6012897280,
  "standalone_model_and_tokenizer_reload": true,
  "quality_improvement_claim": false,
  "cut_checkpoint_revision": "376988e3a817b9d7f4ed7eb71ab7007c483b59ce",
  "weights": [
    {
      "path_in_repo": "model.safetensors",
      "sha256": "e7b3d37beb32930d2c9b1cea775b50f15d79d06dab5d0b39782d206c8ba99573",
      "size": 12026140856
    }
  ],
  "base_weight_bytes": 13838721960,
  "healed_weight_bytes": 12026140856,
  "weight_storage_savings_pct": 13.097893788452119,
  "format_comparison": {
    "measurement_status": "incomplete",
    "bf16_representation": "Hugging Face safetensors",
    "rows": [
      {
        "format": "BF16",
        "size_bytes": 12026140856,
        "sha256": "e7b3d37beb32930d2c9b1cea775b50f15d79d06dab5d0b39782d206c8ba99573",
        "published": true,
        "metrics": [
          {
            "benchmark": "arc_science",
            "metric": "acc",
            "value": 0.45,
            "n": 200,
            "artifact_sha256": "e7b3d37beb32930d2c9b1cea775b50f15d79d06dab5d0b39782d206c8ba99573"
          },
          {
            "benchmark": "bbq_safety",
            "metric": "acc",
            "value": 0.395,
            "n": 200,
            "artifact_sha256": "e7b3d37beb32930d2c9b1cea775b50f15d79d06dab5d0b39782d206c8ba99573"
          },
          {
            "benchmark": "gpqa_reasoning",
            "metric": "acc",
            "value": 0.16666666666666666,
            "n": 198,
            "artifact_sha256": "e7b3d37beb32930d2c9b1cea775b50f15d79d06dab5d0b39782d206c8ba99573"
          },
          {
            "benchmark": "gsm8k_math",
            "metric": "acc",
            "value": 0.43,
            "n": 200,
            "artifact_sha256": "e7b3d37beb32930d2c9b1cea775b50f15d79d06dab5d0b39782d206c8ba99573"
          },
          {
            "benchmark": "hellaswag_commonsense",
            "metric": "acc",
            "value": 0.66,
            "n": 200,
            "artifact_sha256": "e7b3d37beb32930d2c9b1cea775b50f15d79d06dab5d0b39782d206c8ba99573"
          },
          {
            "benchmark": "ifeval_instruction_following",
            "metric": "acc",
            "value": 0.5563380281690141,
            "n": 142,
            "artifact_sha256": "e7b3d37beb32930d2c9b1cea775b50f15d79d06dab5d0b39782d206c8ba99573"
          },
          {
            "benchmark": "mmlu_knowledge",
            "metric": "acc",
            "value": 0.265,
            "n": 200,
            "artifact_sha256": "e7b3d37beb32930d2c9b1cea775b50f15d79d06dab5d0b39782d206c8ba99573"
          },
          {
            "benchmark": "multilingual_knowledge",
            "metric": "acc",
            "value": 0.265,
            "n": 200,
            "artifact_sha256": "e7b3d37beb32930d2c9b1cea775b50f15d79d06dab5d0b39782d206c8ba99573"
          },
          {
            "benchmark": "wikitext_language",
            "metric": "ppl",
            "value": 21.6319395015557,
            "n": 64,
            "artifact_sha256": "e7b3d37beb32930d2c9b1cea775b50f15d79d06dab5d0b39782d206c8ba99573"
          }
        ]
      },
      {
        "format": "Q8_0",
        "size_bytes": null,
        "sha256": "",
        "published": false,
        "metrics": []
      },
      {
        "format": "Q4_K_M",
        "size_bytes": 3663796064,
        "sha256": "4f7fe283cd9a714a3c96824f30a83e7e4d70e55f16a9b9e0aea8f644e68e620f",
        "published": false,
        "metrics": []
      },
      {
        "format": "Q2_K",
        "size_bytes": null,
        "sha256": "",
        "published": false,
        "metrics": []
      }
    ]
  }
}