{
  "schema_version": "0.2.2",
  "evaluation_id": "ifeval/RedHatAI/MiniMax-M2.5-quantized.w4a16/1777302591.528493",
  "evaluation_timestamp": "1776886012",
  "retrieved_timestamp": "1777302591.528493",
  "source_metadata": {
    "source_name": "lm-evaluation-harness",
    "source_type": "evaluation_run",
    "source_organization_name": "RedHatAI",
    "evaluator_relationship": "third_party"
  },
  "eval_library": {
    "name": "lm_eval",
    "version": "0.4.12.dev0"
  },
  "model_info": {
    "name": "RedHatAI/MiniMax-M2.5-quantized.w4a16",
    "id": "RedHatAI/MiniMax-M2.5-quantized.w4a16",
    "developer": "RedHatAI",
    "additional_details": {
      "model_args": "{'model': 'RedHatAI/MiniMax-M2.5-quantized.w4a16', 'max_length': 196608, 'base_url': 'http://0.0.0.0:8000/v1/chat/completions', 'num_concurrent': 128, 'max_retries': 3, 'tokenized_requests': False, 'tokenizer_backend': None, 'timeout': 2400}",
      "seed": "1234",
      "num_seeds_merged": "3"
    }
  },
  "evaluation_results": [
    {
      "evaluation_name": "ifeval",
      "source_data": {
        "dataset_name": "ifeval",
        "source_type": "hf_dataset",
        "hf_repo": "google/IFEval",
        "hf_split": "train"
      },
      "evaluation_timestamp": "1776888058",
      "metric_config": {
        "evaluation_description": "prompt_level_strict_acc",
        "lower_is_better": false,
        "score_type": "continuous",
        "min_score": 0.0,
        "max_score": 1.0
      },
      "score_details": {
        "score": 0.8558225508317929,
        "details": {
          "seed_scores": "[0.8595194085027726, 0.8576709796672828, 0.8502772643253235]",
          "seed_values": "[1234, 4158, 42]"
        },
        "uncertainty": {
          "standard_error": {
            "value": 0.0028235216851237458,
            "method": "across_seeds"
          },
          "num_samples": 3
        }
      },
      "generation_config": {
        "generation_args": {
          "temperature": 1.0,
          "top_p": 0.95,
          "top_k": 40.0,
          "max_tokens": 64000,
          "max_attempts": 1
        },
        "additional_details": {
          "until": "[]",
          "do_sample": "true",
          "min_p": "0.0",
          "presence_penalty": "1.5",
          "repetition_penalty": "1.0",
          "seed": "1234",
          "num_fewshot": "0"
        }
      }
    },
    {
      "evaluation_name": "ifeval",
      "source_data": {
        "dataset_name": "ifeval",
        "source_type": "hf_dataset",
        "hf_repo": "google/IFEval",
        "hf_split": "train"
      },
      "evaluation_timestamp": "1776888058",
      "metric_config": {
        "evaluation_description": "inst_level_strict_acc",
        "lower_is_better": false,
        "score_type": "continuous",
        "min_score": 0.0,
        "max_score": 1.0
      },
      "score_details": {
        "score": 0.904476418864908,
        "details": {
          "seed_scores": "[0.9088729016786571, 0.9040767386091128, 0.9004796163069544]",
          "seed_values": "[1234, 4158, 42]"
        },
        "uncertainty": {
          "standard_error": {
            "value": 0.0024311600840520617,
            "method": "across_seeds"
          },
          "num_samples": 3
        }
      },
      "generation_config": {
        "generation_args": {
          "temperature": 1.0,
          "top_p": 0.95,
          "top_k": 40.0,
          "max_tokens": 64000,
          "max_attempts": 1
        },
        "additional_details": {
          "until": "[]",
          "do_sample": "true",
          "min_p": "0.0",
          "presence_penalty": "1.5",
          "repetition_penalty": "1.0",
          "seed": "1234",
          "num_fewshot": "0"
        }
      }
    },
    {
      "evaluation_name": "ifeval",
      "source_data": {
        "dataset_name": "ifeval",
        "source_type": "hf_dataset",
        "hf_repo": "google/IFEval",
        "hf_split": "train"
      },
      "evaluation_timestamp": "1776888058",
      "metric_config": {
        "evaluation_description": "prompt_level_loose_acc",
        "lower_is_better": false,
        "score_type": "continuous",
        "min_score": 0.0,
        "max_score": 1.0
      },
      "score_details": {
        "score": 0.88909426987061,
        "details": {
          "seed_scores": "[0.8909426987060998, 0.88909426987061, 0.8872458410351202]",
          "seed_values": "[1234, 4158, 42]"
        },
        "uncertainty": {
          "standard_error": {
            "value": 0.0010671908857479034,
            "method": "across_seeds"
          },
          "num_samples": 3
        }
      },
      "generation_config": {
        "generation_args": {
          "temperature": 1.0,
          "top_p": 0.95,
          "top_k": 40.0,
          "max_tokens": 64000,
          "max_attempts": 1
        },
        "additional_details": {
          "until": "[]",
          "do_sample": "true",
          "min_p": "0.0",
          "presence_penalty": "1.5",
          "repetition_penalty": "1.0",
          "seed": "1234",
          "num_fewshot": "0"
        }
      }
    },
    {
      "evaluation_name": "ifeval",
      "source_data": {
        "dataset_name": "ifeval",
        "source_type": "hf_dataset",
        "hf_repo": "google/IFEval",
        "hf_split": "train"
      },
      "evaluation_timestamp": "1776888058",
      "metric_config": {
        "evaluation_description": "inst_level_loose_acc",
        "lower_is_better": false,
        "score_type": "continuous",
        "min_score": 0.0,
        "max_score": 1.0
      },
      "score_details": {
        "score": 0.9260591526778578,
        "details": {
          "seed_scores": "[0.9292565947242206, 0.9244604316546763, 0.9244604316546763]",
          "seed_values": "[1234, 4158, 42]"
        },
        "uncertainty": {
          "standard_error": {
            "value": 0.001598721023181445,
            "method": "across_seeds"
          },
          "num_samples": 3
        }
      },
      "generation_config": {
        "generation_args": {
          "temperature": 1.0,
          "top_p": 0.95,
          "top_k": 40.0,
          "max_tokens": 64000,
          "max_attempts": 1
        },
        "additional_details": {
          "until": "[]",
          "do_sample": "true",
          "min_p": "0.0",
          "presence_penalty": "1.5",
          "repetition_penalty": "1.0",
          "seed": "1234",
          "num_fewshot": "0"
        }
      }
    }
  ]
}