open-r1-eval-leaderboard
/
eval_results
/Qwen
/Qwen1.5-0.5B-Chat
/main
/aimo_kaggle
/results_2024-04-22T15-27-33.072805.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 977156.574444742, | |
"end_time": 977305.86296132, | |
"total_evaluation_time_secondes": "149.2885165780317", | |
"model_name": "Qwen/Qwen1.5-0.5B-Chat", | |
"model_sha": "f82bd3692de0283f4a4b31e06d164dd8467fb52e", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "1.05 GB", | |
"config": null | |
}, | |
"results": { | |
"custom|aimo_kaggle|0": { | |
"qem": 0.16666666666666666, | |
"qem_stderr": 0.04247059928646881 | |
}, | |
"all": { | |
"qem": 0.16666666666666666, | |
"qem_stderr": 0.04247059928646881 | |
} | |
}, | |
"versions": { | |
"custom|aimo_kaggle|0": 0 | |
}, | |
"config_tasks": { | |
"custom|aimo_kaggle": { | |
"name": "aimo_kaggle", | |
"prompt_function": "kaggle_prompt_fn", | |
"hf_repo": "AI-MO/kaggle-validation-set-v1", | |
"hf_subset": "default", | |
"metric": [ | |
"quasi_exact_match_math" | |
], | |
"hf_avail_splits": [ | |
"train" | |
], | |
"evaluation_splits": [ | |
"train" | |
], | |
"few_shots_split": null, | |
"few_shots_select": null, | |
"generation_size": 2048, | |
"stop_sequence": null, | |
"output_regex": null, | |
"frozen": false, | |
"suite": [ | |
"custom" | |
], | |
"original_num_docs": 78, | |
"effective_num_docs": 78, | |
"trust_dataset": null, | |
"must_remove_duplicate_docs": null | |
} | |
}, | |
"summary_tasks": { | |
"custom|aimo_kaggle|0": { | |
"hashes": { | |
"hash_examples": "df0b9e4031e0ac93", | |
"hash_full_prompts": "149fbbece304ca8c", | |
"hash_input_tokens": "87638e69ae967323", | |
"hash_cont_tokens": "4fd6feaaaa3f87ca" | |
}, | |
"truncated": 78, | |
"non_truncated": 0, | |
"padded": 45, | |
"non_padded": 33, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "f5b0a912024169d0", | |
"hash_full_prompts": "69ac57f47ce9940f", | |
"hash_input_tokens": "3260a6fe0e574b57", | |
"hash_cont_tokens": "918d06800f3b0c0a" | |
}, | |
"truncated": 78, | |
"non_truncated": 0, | |
"padded": 45, | |
"non_padded": 33, | |
"num_truncated_few_shots": 0 | |
} | |
} |