every_eval_ever/gpqa_diamond.json
| 1 | { |
| 2 | "schema_version": "0.2.2", |
| 3 | "evaluation_id": "gpqa:diamond|0/RedHatAI/gemma-4-31B-it-FP8-block/1781736052.859433", |
| 4 | "evaluation_timestamp": "507424", |
| 5 | "retrieved_timestamp": "1781736052.859433", |
| 6 | "source_metadata": { |
| 7 | "source_name": "lighteval", |
| 8 | "source_type": "evaluation_run", |
| 9 | "source_organization_name": "RedHatAI", |
| 10 | "evaluator_relationship": "third_party" |
| 11 | }, |
| 12 | "eval_library": { |
| 13 | "name": "lighteval", |
| 14 | "version": "v0.13.0" |
| 15 | }, |
| 16 | "model_info": { |
| 17 | "name": "RedHatAI/gemma-4-31B-it-FP8-block", |
| 18 | "id": "RedHatAI/gemma-4-31B-it-FP8-block", |
| 19 | "developer": "RedHatAI", |
| 20 | "inference_engine": { |
| 21 | "name": "vllm" |
| 22 | }, |
| 23 | "additional_details": { |
| 24 | "provider": "hosted_vllm", |
| 25 | "base_url": "http://127.0.0.1:8000/v1", |
| 26 | "concurrent_requests": "128", |
| 27 | "verbose": "False", |
| 28 | "api_max_retry": "8", |
| 29 | "api_retry_sleep": "1.0", |
| 30 | "api_retry_multiplier": "2.0", |
| 31 | "timeout": "3600.0", |
| 32 | "num_seeds_merged": "3" |
| 33 | } |
| 34 | }, |
| 35 | "evaluation_results": [ |
| 36 | { |
| 37 | "evaluation_name": "gpqa:diamond", |
| 38 | "source_data": { |
| 39 | "dataset_name": "gpqa:diamond", |
| 40 | "source_type": "hf_dataset", |
| 41 | "hf_repo": "Idavidrein/gpqa", |
| 42 | "hf_split": "train", |
| 43 | "additional_details": { |
| 44 | "hf_subset": "gpqa_diamond" |
| 45 | } |
| 46 | }, |
| 47 | "metric_config": { |
| 48 | "evaluation_description": "gpqa_pass@k:k=1", |
| 49 | "lower_is_better": false, |
| 50 | "score_type": "continuous", |
| 51 | "min_score": 0.0, |
| 52 | "max_score": 1.0 |
| 53 | }, |
| 54 | "score_details": { |
| 55 | "score": 0.7794612794612794, |
| 56 | "details": { |
| 57 | "seed_scores": "[0.7676767676767676, 0.7777777777777778, 0.7929292929292929]", |
| 58 | "evaluation_timestamps": "[507424, 507534, 507660]", |
| 59 | "seed_values": "[1234, 2345, 3456]" |
| 60 | }, |
| 61 | "uncertainty": { |
| 62 | "standard_error": { |
| 63 | "value": 0.0073382137096644475, |
| 64 | "method": "across_seeds" |
| 65 | }, |
| 66 | "num_samples": 3 |
| 67 | } |
| 68 | }, |
| 69 | "generation_config": { |
| 70 | "generation_args": { |
| 71 | "temperature": 1.0, |
| 72 | "top_p": 0.95, |
| 73 | "top_k": 64.0, |
| 74 | "max_tokens": 65536, |
| 75 | "max_attempts": 1 |
| 76 | }, |
| 77 | "additional_details": { |
| 78 | "seed": "1234", |
| 79 | "num_fewshot": "0" |
| 80 | } |
| 81 | } |
| 82 | } |
| 83 | ] |
| 84 | } |