{ "schema_version": "0.2.2", "evaluation_id": "math_500|0/RedHatAI/gemma-4-31B-it-FP8-Dynamic/1781646637.962591", "evaluation_timestamp": "351873", "retrieved_timestamp": "1781646637.962591", "source_metadata": { "source_name": "lighteval", "source_type": "evaluation_run", "source_organization_name": "RedHatAI", "evaluator_relationship": "third_party" }, "eval_library": { "name": "lighteval", "version": "v0.13.0" }, "model_info": { "name": "RedHatAI/gemma-4-31B-it-FP8-Dynamic", "id": "RedHatAI/gemma-4-31B-it-FP8-Dynamic", "developer": "RedHatAI", "inference_engine": { "name": "vllm" }, "additional_details": { "provider": "hosted_vllm", "base_url": "http://127.0.0.1:8000/v1", "concurrent_requests": "128", "verbose": "False", "api_max_retry": "8", "api_retry_sleep": "1.0", "api_retry_multiplier": "2.0", "timeout": "3600.0", "num_seeds_merged": "3" } }, "evaluation_results": [ { "evaluation_name": "math_500", "source_data": { "dataset_name": "math_500", "source_type": "hf_dataset", "hf_repo": "HuggingFaceH4/MATH-500", "hf_split": "test" }, "metric_config": { "evaluation_description": "pass@k:k=1&n=1", "lower_is_better": false, "score_type": "continuous", "min_score": 0.0, "max_score": 1.0 }, "score_details": { "score": 0.9026666666666667, "details": { "seed_scores": "[0.894, 0.9, 0.914]", "evaluation_timestamps": "[351873, 352049, 352202]", "seed_values": "[1234, 2345, 3456]" }, "uncertainty": { "standard_error": { "value": 0.005925462944877065, "method": "across_seeds" }, "num_samples": 3 } }, "generation_config": { "generation_args": { "temperature": 1.0, "top_p": 0.95, "top_k": 64.0, "max_tokens": 65536, "max_attempts": 1 }, "additional_details": { "seed": "1234", "num_fewshot": "0" } } } ] }