open-r1-eval-leaderboard
/
eval_results
/mistralai
/Mistral-7B-Instruct-v0.1
/main
/ifeval
/results_2024-03-28T17-57-27.009185.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 837108.9440716, | |
"end_time": 837855.735161022, | |
"total_evaluation_time_secondes": "746.7910894220695", | |
"model_name": "mistralai/Mistral-7B-Instruct-v0.1", | |
"model_sha": "73068f3702d050a2fd5aa2ca1e612e5036429398", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "13.99 GB", | |
"config": null | |
}, | |
"results": { | |
"extended|ifeval|0": { | |
"prompt_level_strict_acc": 0.3974121996303142, | |
"prompt_level_strict_acc_stderr": 0.021058812847519866, | |
"inst_level_strict_acc": 0.49760191846522783, | |
"inst_level_strict_acc_stderr": 0.0005390891114432318, | |
"prompt_level_loose_acc": 0.4269870609981516, | |
"prompt_level_loose_acc_stderr": 0.021285933050061313, | |
"inst_level_loose_acc": 0.5323741007194245, | |
"inst_level_loose_acc_stderr": 0.0005378503905090047 | |
}, | |
"all": { | |
"prompt_level_strict_acc": 0.3974121996303142, | |
"prompt_level_strict_acc_stderr": 0.021058812847519866, | |
"inst_level_strict_acc": 0.49760191846522783, | |
"inst_level_strict_acc_stderr": 0.0005390891114432318, | |
"prompt_level_loose_acc": 0.4269870609981516, | |
"prompt_level_loose_acc_stderr": 0.021285933050061313, | |
"inst_level_loose_acc": 0.5323741007194245, | |
"inst_level_loose_acc_stderr": 0.0005378503905090047 | |
} | |
}, | |
"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, | |
"frozen": false, | |
"suite": [ | |
"extended" | |
], | |
"original_num_docs": 541, | |
"effective_num_docs": 541, | |
"trust_dataset": null, | |
"must_remove_duplicate_docs": null | |
} | |
}, | |
"summary_tasks": { | |
"extended|ifeval|0": { | |
"hashes": { | |
"hash_examples": "e99cbf567588d7c6", | |
"hash_full_prompts": "50f8a8f5a08077cd", | |
"hash_input_tokens": "fb1ed90207cf652b", | |
"hash_cont_tokens": "86efaf3c9d7e9562" | |
}, | |
"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": "9c04db679f2c9132", | |
"hash_input_tokens": "af9a63ef7d2de8ba", | |
"hash_cont_tokens": "8a8e24e6d741211b" | |
}, | |
"truncated": 541, | |
"non_truncated": 0, | |
"padded": 116, | |
"non_padded": 425, | |
"num_truncated_few_shots": 0 | |
} | |
} |