open-r1-eval-leaderboard
/
eval_results
/deepseek-ai
/DeepSeek-R1-Distill-Qwen-7B
/main
/aime24
/results_2025-02-22T10-12-36.722234.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": -1, | |
"max_samples": null, | |
"job_id": 0, | |
"start_time": 471908.114420919, | |
"end_time": 472363.393353541, | |
"total_evaluation_time_secondes": "455.2789326219936", | |
"model_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", | |
"model_sha": "", | |
"model_dtype": null, | |
"model_size": null | |
}, | |
"results": { | |
"custom|aime24|0": { | |
"extractive_match": 0.5666666666666667, | |
"extractive_match_stderr": 0.0920186554465537 | |
}, | |
"all": { | |
"extractive_match": 0.5666666666666667, | |
"extractive_match_stderr": 0.0920186554465537 | |
} | |
}, | |
"versions": { | |
"custom|aime24|0": 1 | |
}, | |
"config_tasks": { | |
"custom|aime24": { | |
"name": "aime24", | |
"prompt_function": "aime_prompt_fn", | |
"hf_repo": "HuggingFaceH4/aime_2024", | |
"hf_subset": "default", | |
"metric": [ | |
{ | |
"metric_name": "extractive_match", | |
"higher_is_better": true, | |
"category": "3", | |
"use_case": "1", | |
"sample_level_fn": "sample_level_fn", | |
"corpus_level_fn": "mean" | |
} | |
], | |
"hf_revision": null, | |
"hf_filter": null, | |
"hf_avail_splits": [ | |
"train" | |
], | |
"trust_dataset": false, | |
"evaluation_splits": [ | |
"train" | |
], | |
"few_shots_split": null, | |
"few_shots_select": null, | |
"generation_size": 32768, | |
"generation_grammar": null, | |
"stop_sequence": [], | |
"num_samples": null, | |
"suite": [ | |
"custom" | |
], | |
"original_num_docs": 30, | |
"effective_num_docs": 30, | |
"must_remove_duplicate_docs": false, | |
"version": 1 | |
} | |
}, | |
"summary_tasks": { | |
"custom|aime24|0": { | |
"hashes": { | |
"hash_examples": "2b4996a1ea5c3a78", | |
"hash_full_prompts": "f2e5411cc127fa29", | |
"hash_input_tokens": "f4f2081595f761ea", | |
"hash_cont_tokens": "333dafb68ecbe619" | |
}, | |
"truncated": 0, | |
"non_truncated": 30, | |
"padded": 0, | |
"non_padded": 30, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "de04e8d2e1423321", | |
"hash_full_prompts": "9ca9d6b878c9a788", | |
"hash_input_tokens": "c1fd76fb11a98fb1", | |
"hash_cont_tokens": "0bbe9f8e5e344dc8" | |
}, | |
"truncated": 0, | |
"non_truncated": 30, | |
"padded": 0, | |
"non_padded": 30, | |
"num_truncated_few_shots": 0 | |
} | |
} |