open-r1-eval-leaderboard
/
eval_results
/AI-MO
/deepseek-math-7b-sft
/aimo_v00.00
/math
/results_2024-04-25T18-40-15.619458.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 1, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 529398.467011022, | |
"end_time": 547997.799857469, | |
"total_evaluation_time_secondes": "18599.33284644701", | |
"model_name": "AI-MO/deepseek-math-7b-sft", | |
"model_sha": "748a5f5e457052be6c9476d87222e596fedefdb7", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "12.93 GB", | |
"config": null | |
}, | |
"results": { | |
"lighteval|math:algebra|0": { | |
"qem": 0.5602358887952822, | |
"qem_stderr": 0.01441295433625673 | |
}, | |
"lighteval|math:counting_and_probability|0": { | |
"qem": 0.2742616033755274, | |
"qem_stderr": 0.020513604844067376 | |
}, | |
"lighteval|math:geometry|0": { | |
"qem": 0.29227557411273486, | |
"qem_stderr": 0.020802446090971965 | |
}, | |
"lighteval|math:intermediate_algebra|0": { | |
"qem": 0.17829457364341086, | |
"qem_stderr": 0.01274453139767248 | |
}, | |
"lighteval|math:number_theory|0": { | |
"qem": 0.23703703703703705, | |
"qem_stderr": 0.018317468375814456 | |
}, | |
"lighteval|math:prealgebra|0": { | |
"qem": 0.5568312284730195, | |
"qem_stderr": 0.016841731538953138 | |
}, | |
"lighteval|math:precalculus|0": { | |
"qem": 0.22344322344322345, | |
"qem_stderr": 0.01784316739379989 | |
}, | |
"lighteval|math:_average|0": { | |
"qem": 0.3317684469828908, | |
"qem_stderr": 0.017353700568219433 | |
}, | |
"all": { | |
"qem": 0.3317684469828908, | |
"qem_stderr": 0.017353700568219433 | |
} | |
}, | |
"versions": { | |
"lighteval|math:algebra|0": 0, | |
"lighteval|math:counting_and_probability|0": 0, | |
"lighteval|math:geometry|0": 0, | |
"lighteval|math:intermediate_algebra|0": 0, | |
"lighteval|math:number_theory|0": 0, | |
"lighteval|math:prealgebra|0": 0, | |
"lighteval|math:precalculus|0": 0 | |
}, | |
"config_tasks": { | |
"lighteval|math:algebra": { | |
"name": "math:algebra", | |
"prompt_function": "math", | |
"hf_repo": "lighteval/MATH", | |
"hf_subset": "algebra", | |
"metric": [ | |
"quasi_exact_match_math" | |
], | |
"hf_avail_splits": [ | |
"train", | |
"test", | |
"validation" | |
], | |
"evaluation_splits": [ | |
"test" | |
], | |
"few_shots_split": null, | |
"few_shots_select": null, | |
"generation_size": 2048, | |
"stop_sequence": [ | |
"\n" | |
], | |
"output_regex": null, | |
"frozen": false, | |
"suite": [ | |
"lighteval", | |
"math" | |
], | |
"original_num_docs": 1187, | |
"effective_num_docs": 1187, | |
"trust_dataset": true, | |
"must_remove_duplicate_docs": null | |
}, | |
"lighteval|math:counting_and_probability": { | |
"name": "math:counting_and_probability", | |
"prompt_function": "math", | |
"hf_repo": "lighteval/MATH", | |
"hf_subset": "counting_and_probability", | |
"metric": [ | |
"quasi_exact_match_math" | |
], | |
"hf_avail_splits": [ | |
"train", | |
"test", | |
"validation" | |
], | |
"evaluation_splits": [ | |
"test" | |
], | |
"few_shots_split": null, | |
"few_shots_select": null, | |
"generation_size": 2048, | |
"stop_sequence": [ | |
"\n" | |
], | |
"output_regex": null, | |
"frozen": false, | |
"suite": [ | |
"lighteval", | |
"math" | |
], | |
"original_num_docs": 474, | |
"effective_num_docs": 474, | |
"trust_dataset": true, | |
"must_remove_duplicate_docs": null | |
}, | |
"lighteval|math:geometry": { | |
"name": "math:geometry", | |
"prompt_function": "math", | |
"hf_repo": "lighteval/MATH", | |
"hf_subset": "geometry", | |
"metric": [ | |
"quasi_exact_match_math" | |
], | |
"hf_avail_splits": [ | |
"train", | |
"test", | |
"validation" | |
], | |
"evaluation_splits": [ | |
"test" | |
], | |
"few_shots_split": null, | |
"few_shots_select": null, | |
"generation_size": 2048, | |
"stop_sequence": [ | |
"\n" | |
], | |
"output_regex": null, | |
"frozen": false, | |
"suite": [ | |
"lighteval", | |
"math" | |
], | |
"original_num_docs": 479, | |
"effective_num_docs": 479, | |
"trust_dataset": true, | |
"must_remove_duplicate_docs": null | |
}, | |
"lighteval|math:intermediate_algebra": { | |
"name": "math:intermediate_algebra", | |
"prompt_function": "math", | |
"hf_repo": "lighteval/MATH", | |
"hf_subset": "intermediate_algebra", | |
"metric": [ | |
"quasi_exact_match_math" | |
], | |
"hf_avail_splits": [ | |
"train", | |
"test", | |
"validation" | |
], | |
"evaluation_splits": [ | |
"test" | |
], | |
"few_shots_split": null, | |
"few_shots_select": null, | |
"generation_size": 2048, | |
"stop_sequence": [ | |
"\n" | |
], | |
"output_regex": null, | |
"frozen": false, | |
"suite": [ | |
"lighteval", | |
"math" | |
], | |
"original_num_docs": 903, | |
"effective_num_docs": 903, | |
"trust_dataset": true, | |
"must_remove_duplicate_docs": null | |
}, | |
"lighteval|math:number_theory": { | |
"name": "math:number_theory", | |
"prompt_function": "math", | |
"hf_repo": "lighteval/MATH", | |
"hf_subset": "number_theory", | |
"metric": [ | |
"quasi_exact_match_math" | |
], | |
"hf_avail_splits": [ | |
"train", | |
"test", | |
"validation" | |
], | |
"evaluation_splits": [ | |
"test" | |
], | |
"few_shots_split": null, | |
"few_shots_select": null, | |
"generation_size": 2048, | |
"stop_sequence": [ | |
"\n" | |
], | |
"output_regex": null, | |
"frozen": false, | |
"suite": [ | |
"lighteval", | |
"math" | |
], | |
"original_num_docs": 540, | |
"effective_num_docs": 540, | |
"trust_dataset": true, | |
"must_remove_duplicate_docs": null | |
}, | |
"lighteval|math:prealgebra": { | |
"name": "math:prealgebra", | |
"prompt_function": "math", | |
"hf_repo": "lighteval/MATH", | |
"hf_subset": "prealgebra", | |
"metric": [ | |
"quasi_exact_match_math" | |
], | |
"hf_avail_splits": [ | |
"train", | |
"test", | |
"validation" | |
], | |
"evaluation_splits": [ | |
"test" | |
], | |
"few_shots_split": null, | |
"few_shots_select": null, | |
"generation_size": 2048, | |
"stop_sequence": [ | |
"\n" | |
], | |
"output_regex": null, | |
"frozen": false, | |
"suite": [ | |
"lighteval", | |
"math" | |
], | |
"original_num_docs": 871, | |
"effective_num_docs": 871, | |
"trust_dataset": true, | |
"must_remove_duplicate_docs": null | |
}, | |
"lighteval|math:precalculus": { | |
"name": "math:precalculus", | |
"prompt_function": "math", | |
"hf_repo": "lighteval/MATH", | |
"hf_subset": "precalculus", | |
"metric": [ | |
"quasi_exact_match_math" | |
], | |
"hf_avail_splits": [ | |
"train", | |
"test", | |
"validation" | |
], | |
"evaluation_splits": [ | |
"test" | |
], | |
"few_shots_split": null, | |
"few_shots_select": null, | |
"generation_size": 2048, | |
"stop_sequence": [ | |
"\n" | |
], | |
"output_regex": null, | |
"frozen": false, | |
"suite": [ | |
"lighteval", | |
"math" | |
], | |
"original_num_docs": 546, | |
"effective_num_docs": 546, | |
"trust_dataset": true, | |
"must_remove_duplicate_docs": null | |
} | |
}, | |
"summary_tasks": { | |
"lighteval|math:algebra|0": { | |
"hashes": { | |
"hash_examples": "37a2fd2f076d2e49", | |
"hash_full_prompts": "461f2ab197cdfd01", | |
"hash_input_tokens": "8209eebabb8132e4", | |
"hash_cont_tokens": "a7c7578ff9dbd29c" | |
}, | |
"truncated": 1187, | |
"non_truncated": 0, | |
"padded": 0, | |
"non_padded": 1187, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
}, | |
"lighteval|math:counting_and_probability|0": { | |
"hashes": { | |
"hash_examples": "97b4892e28bc078b", | |
"hash_full_prompts": "e2cc9eb28ca159b1", | |
"hash_input_tokens": "3c116046c93accc7", | |
"hash_cont_tokens": "65c0650c48a15ca4" | |
}, | |
"truncated": 474, | |
"non_truncated": 0, | |
"padded": 0, | |
"non_padded": 474, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
}, | |
"lighteval|math:geometry|0": { | |
"hashes": { | |
"hash_examples": "9e9f0228b8b3d093", | |
"hash_full_prompts": "e581f42fefeed8c9", | |
"hash_input_tokens": "91420fc689743b29", | |
"hash_cont_tokens": "0dbdc8586d3b160d" | |
}, | |
"truncated": 479, | |
"non_truncated": 0, | |
"padded": 0, | |
"non_padded": 479, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
}, | |
"lighteval|math:intermediate_algebra|0": { | |
"hashes": { | |
"hash_examples": "cfe73a8e28ae94de", | |
"hash_full_prompts": "7557d30ba2cc15ef", | |
"hash_input_tokens": "e47e75b9d3b1247a", | |
"hash_cont_tokens": "381192e43f59c164" | |
}, | |
"truncated": 903, | |
"non_truncated": 0, | |
"padded": 0, | |
"non_padded": 903, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
}, | |
"lighteval|math:number_theory|0": { | |
"hashes": { | |
"hash_examples": "4ee5237cf144afac", | |
"hash_full_prompts": "7b983a6fe1e3d0a8", | |
"hash_input_tokens": "8f8d85639345093d", | |
"hash_cont_tokens": "d54090608e16798f" | |
}, | |
"truncated": 540, | |
"non_truncated": 0, | |
"padded": 0, | |
"non_padded": 540, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
}, | |
"lighteval|math:prealgebra|0": { | |
"hashes": { | |
"hash_examples": "3fb3afeb885f73d8", | |
"hash_full_prompts": "736a03165dbf8f49", | |
"hash_input_tokens": "e1c72cbbee4a9c7f", | |
"hash_cont_tokens": "58e295af0f1bb5b1" | |
}, | |
"truncated": 871, | |
"non_truncated": 0, | |
"padded": 0, | |
"non_padded": 871, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
}, | |
"lighteval|math:precalculus|0": { | |
"hashes": { | |
"hash_examples": "753e25ab9ec4b46c", | |
"hash_full_prompts": "632ca5aa79f53b59", | |
"hash_input_tokens": "8218370d326a70ad", | |
"hash_cont_tokens": "1e7d60c4f5419491" | |
}, | |
"truncated": 546, | |
"non_truncated": 0, | |
"padded": 0, | |
"non_padded": 546, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "b76099aa9092a203", | |
"hash_full_prompts": "2d2e105e1a0eeab9", | |
"hash_input_tokens": "59674354dfc8622f", | |
"hash_cont_tokens": "f053e2410a9282cf" | |
}, | |
"truncated": 5000, | |
"non_truncated": 0, | |
"padded": 0, | |
"non_padded": 5000, | |
"num_truncated_few_shots": 0 | |
} | |
} |