ChibuUkachi's picture
add every eval results
6cfaff9
{
"schema_version": "0.2.2",
"evaluation_id": "math_500/inference-optimization/MiniMax-M2.5-NVFP4/1777382453.327009",
"evaluation_timestamp": "3278606",
"retrieved_timestamp": "1777382453.327009",
"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": "inference-optimization/MiniMax-M2.5-NVFP4",
"id": "inference-optimization/MiniMax-M2.5-NVFP4",
"developer": "inference-optimization",
"inference_engine": {
"name": "vllm"
},
"additional_details": {
"provider": "hosted_vllm",
"base_url": "http://0.0.0.0:8003/v1",
"concurrent_requests": "8",
"verbose": "False",
"api_max_retry": "8",
"api_retry_sleep": "1.0",
"api_retry_multiplier": "2.0",
"timeout": "2400.0",
"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"
},
"evaluation_timestamp": "3280699",
"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": 0.8773333333333333,
"details": {
"seed_scores": "[0.882, 0.878, 0.872]",
"seed_values": "[1234, 4158, 42]"
},
"uncertainty": {
"standard_error": {
"value": 0.0029059326290271185,
"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": {
"repetition_penalty": "1.0",
"presence_penalty": "1.5",
"seed": "1234",
"min_p": "0.0"
}
}
}
]
}