| { |
| "schema_version": "0.2.2", |
| "evaluation_id": "mmlu_pro_chat/RedHatAI/MiniMax-M2.5-quantized.w8a8/1777980581.186022", |
| "evaluation_timestamp": "1777572326", |
| "retrieved_timestamp": "1777980581.186022", |
| "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.w8a8", |
| "id": "RedHatAI/MiniMax-M2.5-quantized.w8a8", |
| "developer": "RedHatAI", |
| "additional_details": { |
| "model_args": "{'model': 'RedHatAI/MiniMax-M2.5-quantized.w8a8', 'max_length': 196608, 'base_url': 'http://0.0.0.0:8000/v1/chat/completions', 'num_concurrent': 28, 'max_retries': 3, 'tokenized_requests': False, 'tokenizer_backend': None, 'timeout': 2400}", |
| "seed": "1234", |
| "num_seeds_merged": "3" |
| } |
| }, |
| "evaluation_results": [ |
| { |
| "evaluation_name": "mmlu_pro_chat_biology/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1777599905", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.905160390516039, |
| "details": { |
| "seed_scores": "[0.905160390516039, 0.9065550906555091, 0.9037656903765691]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.0008052305009618233, |
| "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": "mmlu_pro_chat_business/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1777599905", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.8694550063371357, |
| "details": { |
| "seed_scores": "[0.870722433460076, 0.8631178707224335, 0.8745247148288974]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.003353296972198461, |
| "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": "mmlu_pro_chat_chemistry/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1777599905", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.8610129564193169, |
| "details": { |
| "seed_scores": "[0.8657243816254417, 0.8613074204946997, 0.8560070671378092]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.002809008249166527, |
| "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": "mmlu_pro_chat_computer_science/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1777599905", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.8569105691056911, |
| "details": { |
| "seed_scores": "[0.8609756097560975, 0.8512195121951219, 0.8585365853658536]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.00293134250037723, |
| "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": "mmlu_pro_chat_economics/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1777599905", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.8609794628751974, |
| "details": { |
| "seed_scores": "[0.8637440758293838, 0.8542654028436019, 0.8649289099526066]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.00337440906213173, |
| "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": "mmlu_pro_chat_engineering/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1777599905", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.7189542483660131, |
| "details": { |
| "seed_scores": "[0.7285861713106295, 0.7058823529411765, 0.7223942208462333]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.006775959959956034, |
| "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": "mmlu_pro_chat_health/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1777599905", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.7844335778321109, |
| "details": { |
| "seed_scores": "[0.7897310513447433, 0.7860635696821516, 0.7775061124694377]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.0036219211154505265, |
| "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": "mmlu_pro_chat_history/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1777599905", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.6937882764654418, |
| "details": { |
| "seed_scores": "[0.6824146981627297, 0.7007874015748031, 0.6981627296587927]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.005737041578566912, |
| "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": "mmlu_pro_chat_law/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1777599905", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.6094459582198002, |
| "details": { |
| "seed_scores": "[0.6067211625794732, 0.6148955495004541, 0.6067211625794732]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.002724795640326979, |
| "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": "mmlu_pro_chat_math/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1777599905", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.930175178879842, |
| "details": { |
| "seed_scores": "[0.9326424870466321, 0.930421909696521, 0.927461139896373]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.0015008049667649247, |
| "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": "mmlu_pro_chat_other/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1777599905", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.7828282828282829, |
| "details": { |
| "seed_scores": "[0.7792207792207793, 0.7813852813852814, 0.7878787878787878]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.0026014078466550937, |
| "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": "mmlu_pro_chat_philosophy/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1777599905", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.7254509018036072, |
| "details": { |
| "seed_scores": "[0.7274549098196392, 0.7234468937875751, 0.7254509018036072]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.0011570145675142813, |
| "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": "mmlu_pro_chat_physics/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1777599905", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.8665640236079035, |
| "details": { |
| "seed_scores": "[0.8637413394919169, 0.8706697459584296, 0.8652809853733642]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.002100424113901068, |
| "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": "mmlu_pro_chat_psychology/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "hf_dataset", |
| "hf_repo": "TIGER-Lab/MMLU-Pro", |
| "hf_split": "test" |
| }, |
| "evaluation_timestamp": "1777599905", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.810359231411863, |
| "details": { |
| "seed_scores": "[0.8107769423558897, 0.8132832080200502, 0.8070175438596491]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.0018207597926235294, |
| "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": "mmlu_pro_chat/custom-extract", |
| "source_data": { |
| "dataset_name": "mmlu_pro_chat", |
| "source_type": "other" |
| }, |
| "evaluation_timestamp": "1777599905", |
| "metric_config": { |
| "evaluation_description": "exact_match (filter: custom-extract)", |
| "lower_is_better": false, |
| "score_type": "continuous", |
| "min_score": 0.0, |
| "max_score": 1.0 |
| }, |
| "score_details": { |
| "score": 0.8124722960992907, |
| "details": { |
| "seed_scores": "[0.8136635638297872, 0.811751994680851, 0.812001329787234]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.0005999669721771889, |
| "method": "across_seeds" |
| }, |
| "num_samples": 3 |
| } |
| } |
| } |
| ] |
| } |
