open-r1-eval-leaderboard
/
eval_results
/NousResearch
/Nous-Hermes-2-Yi-34B
/main
/truthfulqa
/results_2024-03-04T20-41-39.837328.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 1, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 893858.983607086, | |
"end_time": 894643.810767877, | |
"total_evaluation_time_secondes": "784.8271607910283", | |
"model_name": "NousResearch/Nous-Hermes-2-Yi-34B", | |
"model_sha": "fcb0a8847e76aea14aba9aa44009d4418ad7c18f", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "64.17 GB", | |
"config": null | |
}, | |
"results": { | |
"lighteval|truthfulqa:mc|0": { | |
"truthfulqa_mc1": 0.4394124847001224, | |
"truthfulqa_mc1_stderr": 0.01737452048251371, | |
"truthfulqa_mc2": 0.6144205158564372, | |
"truthfulqa_mc2_stderr": 0.015169061713386714 | |
} | |
}, | |
"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": "17e9d0dc9f923ba3", | |
"hash_input_tokens": "a6e4c9ae272a9435", | |
"hash_cont_tokens": "2527aef31c06e15b" | |
}, | |
"truncated": 0, | |
"non_truncated": 817, | |
"padded": 9121, | |
"non_padded": 875, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "aed1dfc67e53d0f2", | |
"hash_full_prompts": "81a2e5a97bc8b7e3", | |
"hash_input_tokens": "768c58b9dd3e40bf", | |
"hash_cont_tokens": "c802a2075f697197" | |
}, | |
"truncated": 0, | |
"non_truncated": 817, | |
"padded": 9121, | |
"non_padded": 875, | |
"num_truncated_few_shots": 0 | |
} | |
} |