open-r1-eval-leaderboard
/
eval_results
/mistralai
/Mixtral-8x22B-Instruct-v0.1
/main
/ifeval
/results_2024-05-25T13-25-15.094728.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 951249.479526532, | |
"end_time": 962884.943179727, | |
"total_evaluation_time_secondes": "11635.46365319495", | |
"model_name": "mistralai/Mixtral-8x22B-Instruct-v0.1", | |
"model_sha": "95d063951382d47385fe7b36e202b68639e5c066", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "263.69 GB", | |
"config": null | |
}, | |
"results": { | |
"extended|ifeval|0": { | |
"prompt_level_strict_acc": 0.6728280961182994, | |
"prompt_level_strict_acc_stderr": 0.02019031896690635, | |
"inst_level_strict_acc": 0.7601918465227818, | |
"inst_level_strict_acc_stderr": 0.0004705041463000014, | |
"prompt_level_loose_acc": 0.7042513863216266, | |
"prompt_level_loose_acc_stderr": 0.019639405361071127, | |
"inst_level_loose_acc": 0.7865707434052758, | |
"inst_level_loose_acc_stderr": 0.0004436877125173785 | |
}, | |
"all": { | |
"prompt_level_strict_acc": 0.6728280961182994, | |
"prompt_level_strict_acc_stderr": 0.02019031896690635, | |
"inst_level_strict_acc": 0.7601918465227818, | |
"inst_level_strict_acc_stderr": 0.0004705041463000014, | |
"prompt_level_loose_acc": 0.7042513863216266, | |
"prompt_level_loose_acc_stderr": 0.019639405361071127, | |
"inst_level_loose_acc": 0.7865707434052758, | |
"inst_level_loose_acc_stderr": 0.0004436877125173785 | |
} | |
}, | |
"versions": { | |
"extended|ifeval|0": 0 | |
}, | |
"config_tasks": { | |
"extended|ifeval": { | |
"name": "ifeval", | |
"prompt_function": "ifeval_prompt", | |
"hf_repo": "wis-k/instruction-following-eval", | |
"hf_subset": "default", | |
"metric": [ | |
"ifeval_metric" | |
], | |
"hf_avail_splits": [ | |
"train" | |
], | |
"evaluation_splits": [ | |
"train" | |
], | |
"few_shots_split": "train", | |
"few_shots_select": "random_sampling", | |
"generation_size": 1280, | |
"stop_sequence": [], | |
"output_regex": null, | |
"num_samples": null, | |
"frozen": false, | |
"suite": [ | |
"extended" | |
], | |
"original_num_docs": 541, | |
"effective_num_docs": 541, | |
"trust_dataset": null, | |
"must_remove_duplicate_docs": null, | |
"version": 0 | |
} | |
}, | |
"summary_tasks": { | |
"extended|ifeval|0": { | |
"hashes": { | |
"hash_examples": "e99cbf567588d7c6", | |
"hash_full_prompts": "de8a0ef3cca868ab", | |
"hash_input_tokens": "ffd86ac3b437afa7", | |
"hash_cont_tokens": "6540f3faefd61da4" | |
}, | |
"truncated": 541, | |
"non_truncated": 0, | |
"padded": 116, | |
"non_padded": 425, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "ea046ab2c6fc5928", | |
"hash_full_prompts": "dca596c8a030146c", | |
"hash_input_tokens": "7b3b17799cb3faf3", | |
"hash_cont_tokens": "e683d5576ede528c" | |
}, | |
"truncated": 541, | |
"non_truncated": 0, | |
"padded": 116, | |
"non_padded": 425, | |
"num_truncated_few_shots": 0 | |
} | |
} |