open-r1-eval-leaderboard
/
eval_results
/mistralai
/Mixtral-8x7B-Instruct-v0.1
/main
/ifeval
/results_2024-03-02T19-39-49.974051.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 1718023.074120519, | |
"end_time": 1722400.171275446, | |
"total_evaluation_time_secondes": "4377.097154926974", | |
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1", | |
"model_sha": "1e637f2d7cb0a9d6fb1922f305cb784995190a83", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "87.49 GB", | |
"config": null | |
}, | |
"results": { | |
"custom|ifeval|0": { | |
"prompt_level_strict_acc": 0.49722735674676527, | |
"prompt_level_strict_acc_stderr": 0.021516243323548123, | |
"inst_level_strict_acc": 0.605515587529976, | |
"inst_level_strict_acc_stderr": 0.0004956773219686272, | |
"prompt_level_loose_acc": 0.5508317929759704, | |
"prompt_level_loose_acc_stderr": 0.0214050932335883, | |
"inst_level_loose_acc": 0.6510791366906474, | |
"inst_level_loose_acc_stderr": 0.0004942945051618118 | |
} | |
}, | |
"versions": { | |
"custom|ifeval|0": 0 | |
}, | |
"config_tasks": { | |
"custom|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, | |
"frozen": false, | |
"suite": [ | |
"custom" | |
], | |
"original_num_docs": 541, | |
"effective_num_docs": 541 | |
} | |
}, | |
"summary_tasks": { | |
"custom|ifeval|0": { | |
"hashes": { | |
"hash_examples": "e99cbf567588d7c6", | |
"hash_full_prompts": "50f8a8f5a08077cd", | |
"hash_input_tokens": "fb1ed90207cf652b", | |
"hash_cont_tokens": "4eed2bab8b8ba6c7" | |
}, | |
"truncated": 0, | |
"non_truncated": 541, | |
"padded": 0, | |
"non_padded": 541, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "ea046ab2c6fc5928", | |
"hash_full_prompts": "9c04db679f2c9132", | |
"hash_input_tokens": "af9a63ef7d2de8ba", | |
"hash_cont_tokens": "8bfcf41538522c12" | |
}, | |
"truncated": 0, | |
"non_truncated": 541, | |
"padded": 0, | |
"non_padded": 541, | |
"num_truncated_few_shots": 0 | |
} | |
} |