open-r1-eval-leaderboard
/
eval_results
/mistralai
/Mistral-7B-Instruct-v0.2
/main
/truthfulqa
/results_2024-03-02T15-35-01.329789.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 1, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 5624023.189326192, | |
"end_time": 5624140.530756273, | |
"total_evaluation_time_secondes": "117.34143008105457", | |
"model_name": "mistralai/Mistral-7B-Instruct-v0.2", | |
"model_sha": "cf47bb3e18fe41a5351bc36eef76e9c900847c89", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "13.99 GB", | |
"config": null | |
}, | |
"results": { | |
"lighteval|truthfulqa:mc|0": { | |
"truthfulqa_mc1": 0.5532435740514076, | |
"truthfulqa_mc1_stderr": 0.017403977522557144, | |
"truthfulqa_mc2": 0.7068493386366792, | |
"truthfulqa_mc2_stderr": 0.01532497053134458 | |
} | |
}, | |
"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": "bc19700dcc192702", | |
"hash_input_tokens": "15d7c94ad93d0bcb", | |
"hash_cont_tokens": "5a8d4bb398b1c3c0" | |
}, | |
"truncated": 0, | |
"non_truncated": 817, | |
"padded": 9429, | |
"non_padded": 567, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "aed1dfc67e53d0f2", | |
"hash_full_prompts": "046a77ce3ce1d5d3", | |
"hash_input_tokens": "45a12d916792d80d", | |
"hash_cont_tokens": "3d7ab832fa043aff" | |
}, | |
"truncated": 0, | |
"non_truncated": 817, | |
"padded": 9429, | |
"non_padded": 567, | |
"num_truncated_few_shots": 0 | |
} | |
} |