open-r1-eval-leaderboard
/
eval_results
/AI-MO
/deepseek-math-7b-sft
/aimo_v00.02
/math
/results_2024-04-25T18-28-40.271556.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 1, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 219572.123918093, | |
"end_time": 237509.33886572, | |
"total_evaluation_time_secondes": "17937.214947626984", | |
"model_name": "AI-MO/deepseek-math-7b-sft", | |
"model_sha": "126790e71c2f21297aa9819fbc652e05f67b99fa", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "12.93 GB", | |
"config": null | |
}, | |
"results": { | |
"lighteval|math:algebra|0": { | |
"qem": 0.5282224094355518, | |
"qem_stderr": 0.014495550739305954 | |
}, | |
"lighteval|math:counting_and_probability|0": { | |
"qem": 0.24472573839662448, | |
"qem_stderr": 0.019767948269352843 | |
}, | |
"lighteval|math:geometry|0": { | |
"qem": 0.2881002087682672, | |
"qem_stderr": 0.020714157351995742 | |
}, | |
"lighteval|math:intermediate_algebra|0": { | |
"qem": 0.18383167220376523, | |
"qem_stderr": 0.012897239623643511 | |
}, | |
"lighteval|math:number_theory|0": { | |
"qem": 0.2740740740740741, | |
"qem_stderr": 0.019212582650083635 | |
}, | |
"lighteval|math:prealgebra|0": { | |
"qem": 0.5499425947187141, | |
"qem_stderr": 0.016866812180762258 | |
}, | |
"lighteval|math:precalculus|0": { | |
"qem": 0.2600732600732601, | |
"qem_stderr": 0.01879074335201598 | |
}, | |
"lighteval|math:_average|0": { | |
"qem": 0.3327099939528938, | |
"qem_stderr": 0.01753500488102285 | |
}, | |
"all": { | |
"qem": 0.3327099939528938, | |
"qem_stderr": 0.01753500488102285 | |
} | |
}, | |
"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": "b2549470315aabe6" | |
}, | |
"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": "a57ec0adfd7bc63a" | |
}, | |
"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": "f119b5a77d8f33f0" | |
}, | |
"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": "6c5fdd86cb7e228e" | |
}, | |
"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": "ea016177a0d0c3e8" | |
}, | |
"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": "020fe703d4f2845d" | |
}, | |
"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": "1ce94ddb94d9f1f8" | |
}, | |
"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": "69785584c3ffa3a4" | |
}, | |
"truncated": 5000, | |
"non_truncated": 0, | |
"padded": 0, | |
"non_padded": 5000, | |
"num_truncated_few_shots": 0 | |
} | |
} |