open-r1-eval-leaderboard
/
eval_results
/deepseek-ai
/deepseek-llm-67b-chat
/main
/truthfulqa
/results_2024-03-04T22-35-30.012534.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 1, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 587844.743644515, | |
"end_time": 589091.714850323, | |
"total_evaluation_time_secondes": "1246.9712058079895", | |
"model_name": "deepseek-ai/deepseek-llm-67b-chat", | |
"model_sha": "79648bef7658bb824e4630740f6e1484c1b0620b", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "125.78 GB", | |
"config": null | |
}, | |
"results": { | |
"lighteval|truthfulqa:mc|0": { | |
"truthfulqa_mc1": 0.3953488372093023, | |
"truthfulqa_mc1_stderr": 0.017115815632418194, | |
"truthfulqa_mc2": 0.5777617502968477, | |
"truthfulqa_mc2_stderr": 0.01518469965998509 | |
} | |
}, | |
"versions": { | |
"lighteval|truthfulqa:mc|0": 0 | |
}, | |
"config_tasks": { | |
"lighteval|truthfulqa:mc": { | |
"name": "truthfulqa:mc", | |
"prompt_function": "truthful_qa_multiple_choice", | |
"hf_repo": "truthful_qa", | |
"hf_subset": "multiple_choice", | |
"metric": [ | |
"truthfulqa_mc_metrics" | |
], | |
"hf_avail_splits": [ | |
"validation" | |
], | |
"evaluation_splits": [ | |
"validation" | |
], | |
"few_shots_split": null, | |
"few_shots_select": null, | |
"generation_size": -1, | |
"stop_sequence": [ | |
"\n" | |
], | |
"output_regex": null, | |
"frozen": false, | |
"suite": [ | |
"lighteval" | |
], | |
"original_num_docs": 817, | |
"effective_num_docs": 817 | |
} | |
}, | |
"summary_tasks": { | |
"lighteval|truthfulqa:mc|0": { | |
"hashes": { | |
"hash_examples": "36a6d90e75d92d4a", | |
"hash_full_prompts": "d5b15b8b0f9c1799", | |
"hash_input_tokens": "deb676712cb16d1b", | |
"hash_cont_tokens": "a6f01973bc49bc4e" | |
}, | |
"truncated": 0, | |
"non_truncated": 817, | |
"padded": 9161, | |
"non_padded": 835, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "aed1dfc67e53d0f2", | |
"hash_full_prompts": "66d3b62aa61973e4", | |
"hash_input_tokens": "d95ced18fcaa9c3d", | |
"hash_cont_tokens": "31b0a37fb78e673a" | |
}, | |
"truncated": 0, | |
"non_truncated": 817, | |
"padded": 9161, | |
"non_padded": 835, | |
"num_truncated_few_shots": 0 | |
} | |
} |