open-r1-eval-leaderboard
/
eval_results
/deepseek-ai
/deepseek-llm-67b-chat
/main
/gsm8k
/results_2024-03-05T03-25-43.517014.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 1, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 3919223.617895711, | |
"end_time": 3937883.673200297, | |
"total_evaluation_time_secondes": "18660.055304585956", | |
"model_name": "deepseek-ai/deepseek-llm-67b-chat", | |
"model_sha": "79648bef7658bb824e4630740f6e1484c1b0620b", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "125.78 GB", | |
"config": null | |
}, | |
"results": { | |
"lighteval|gsm8k|5": { | |
"qem": 0.7611827141774071, | |
"qem_stderr": 0.011744097081003806 | |
} | |
}, | |
"versions": { | |
"lighteval|gsm8k|5": 0 | |
}, | |
"config_tasks": { | |
"lighteval|gsm8k": { | |
"name": "gsm8k", | |
"prompt_function": "gsm8k", | |
"hf_repo": "gsm8k", | |
"hf_subset": "main", | |
"metric": [ | |
"quasi_exact_match_gsm8k" | |
], | |
"hf_avail_splits": [ | |
"train", | |
"test" | |
], | |
"evaluation_splits": [ | |
"test" | |
], | |
"few_shots_split": null, | |
"few_shots_select": "random_sampling_from_train", | |
"generation_size": 256, | |
"stop_sequence": [ | |
":", | |
"Question:", | |
"Question" | |
], | |
"output_regex": null, | |
"frozen": false, | |
"suite": [ | |
"lighteval" | |
], | |
"original_num_docs": 1319, | |
"effective_num_docs": 1319 | |
} | |
}, | |
"summary_tasks": { | |
"lighteval|gsm8k|5": { | |
"hashes": { | |
"hash_examples": "0ed016e24e7512fd", | |
"hash_full_prompts": "5581e030d7742f26", | |
"hash_input_tokens": "d4a5cbfebe88bfef", | |
"hash_cont_tokens": "c41eee6e55243361" | |
}, | |
"truncated": 0, | |
"non_truncated": 1319, | |
"padded": 0, | |
"non_padded": 1319, | |
"effective_few_shots": 5.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "bc71463e88551d0e", | |
"hash_full_prompts": "3c5cdb57beb5684c", | |
"hash_input_tokens": "8bb4e28ee24d32b0", | |
"hash_cont_tokens": "dcbb83e525e791b9" | |
}, | |
"truncated": 0, | |
"non_truncated": 1319, | |
"padded": 0, | |
"non_padded": 1319, | |
"num_truncated_few_shots": 0 | |
} | |
} |