open-r1-eval-leaderboard
/
eval_results
/abhishek
/autotrain-llama3-70b-orpo-v1
/main
/truthfulqa
/results_2024-05-03T07-47-52.114693.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 10685.718400181, | |
"end_time": 13849.044584464, | |
"total_evaluation_time_secondes": "3163.3261842829997", | |
"model_name": "abhishek/autotrain-llama3-70b-orpo-v1", | |
"model_sha": "053236c6846cc561c1503ba05e2b28c94855a432", | |
"model_dtype": "torch.float16", | |
"model_size": "131.73 GB", | |
"config": null | |
}, | |
"results": { | |
"leaderboard|truthfulqa:mc|0": { | |
"truthfulqa_mc1": 0.40636474908200737, | |
"truthfulqa_mc1_stderr": 0.017193835812093904, | |
"truthfulqa_mc2": 0.5920375074921421, | |
"truthfulqa_mc2_stderr": 0.014784841560722257 | |
}, | |
"all": { | |
"truthfulqa_mc1": 0.40636474908200737, | |
"truthfulqa_mc1_stderr": 0.017193835812093904, | |
"truthfulqa_mc2": 0.5920375074921421, | |
"truthfulqa_mc2_stderr": 0.014784841560722257 | |
} | |
}, | |
"versions": { | |
"leaderboard|truthfulqa:mc|0": 0 | |
}, | |
"config_tasks": { | |
"leaderboard|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": [ | |
"leaderboard" | |
], | |
"original_num_docs": 817, | |
"effective_num_docs": 817, | |
"trust_dataset": true, | |
"must_remove_duplicate_docs": null | |
} | |
}, | |
"summary_tasks": { | |
"leaderboard|truthfulqa:mc|0": { | |
"hashes": { | |
"hash_examples": "36a6d90e75d92d4a", | |
"hash_full_prompts": "17e9d0dc9f923ba3", | |
"hash_input_tokens": "af29a7a62df137db", | |
"hash_cont_tokens": "7b0cf70e8cc3141f" | |
}, | |
"truncated": 0, | |
"non_truncated": 817, | |
"padded": 9369, | |
"non_padded": 627, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "aed1dfc67e53d0f2", | |
"hash_full_prompts": "81a2e5a97bc8b7e3", | |
"hash_input_tokens": "4ed9e1b8b3b38c46", | |
"hash_cont_tokens": "9af180ca417c4e9b" | |
}, | |
"truncated": 0, | |
"non_truncated": 817, | |
"padded": 9369, | |
"non_padded": 627, | |
"num_truncated_few_shots": 0 | |
} | |
} |