| { |
| "schema_version": "0.2.2", |
| "evaluation_id": "ifeval/RedHatAI/MiniMax-M2.5-quantized.w8a8/1777568653.331068", |
| "evaluation_timestamp": "1777485653", |
| "retrieved_timestamp": "1777568653.331068", |
| "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': 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": "1777488144", |
| "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": 0.8644485520640789, |
| "details": { |
| "seed_scores": "[0.8595194085027726, 0.8576709796672828, 0.8761552680221811]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.005877629090677424, |
| "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": "1777488144", |
| "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": 0.903277378097522, |
| "details": { |
| "seed_scores": "[0.8980815347721822, 0.8968824940047961, 0.9148681055155875]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.005805691065681036, |
| "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": "1777488144", |
| "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": 0.895871842267406, |
| "details": { |
| "seed_scores": "[0.8817005545286506, 0.88909426987061, 0.9168207024029574]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.010689680574798186, |
| "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": "1777488144", |
| "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": 0.9240607513988809, |
| "details": { |
| "seed_scores": "[0.9136690647482014, 0.9172661870503597, 0.9412470023980816]", |
| "seed_values": "[1234, 4158, 42]" |
| }, |
| "uncertainty": { |
| "standard_error": { |
| "value": 0.008655638620186958, |
| "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" |
| } |
| } |
| } |
| ] |
| } |
