open-r1-eval-leaderboard
/
eval_results
/meta-llama
/Meta-Llama-3-8B-Instruct
/main
/ifeval
/results_2024-04-22T11-59-54.794597.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 3296235.044956083, | |
"end_time": 3297280.831163053, | |
"total_evaluation_time_secondes": "1045.7862069699913", | |
"model_name": "meta-llama/Meta-Llama-3-8B-Instruct", | |
"model_sha": "1448453bdb895762499deb4176c1dd83b145fac1", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "15.08 GB", | |
"config": null | |
}, | |
"results": { | |
"extended|ifeval|0": { | |
"prompt_level_strict_acc": 0.36229205175600737, | |
"prompt_level_strict_acc_stderr": 0.020684424314965397, | |
"inst_level_strict_acc": 0.5047961630695443, | |
"inst_level_strict_acc_stderr": 0.0005127278090058267, | |
"prompt_level_loose_acc": 0.3789279112754159, | |
"prompt_level_loose_acc_stderr": 0.02087624688366893, | |
"inst_level_loose_acc": 0.5215827338129496, | |
"inst_level_loose_acc_stderr": 0.0005211323729099975 | |
}, | |
"all": { | |
"prompt_level_strict_acc": 0.36229205175600737, | |
"prompt_level_strict_acc_stderr": 0.020684424314965397, | |
"inst_level_strict_acc": 0.5047961630695443, | |
"inst_level_strict_acc_stderr": 0.0005127278090058267, | |
"prompt_level_loose_acc": 0.3789279112754159, | |
"prompt_level_loose_acc_stderr": 0.02087624688366893, | |
"inst_level_loose_acc": 0.5215827338129496, | |
"inst_level_loose_acc_stderr": 0.0005211323729099975 | |
} | |
}, | |
"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": "30fe3a1c6acd1de0", | |
"hash_input_tokens": "1d6107f4cf33c68a", | |
"hash_cont_tokens": "ae1f74e3428fa94e" | |
}, | |
"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": "bcd0aa2470bb7894", | |
"hash_input_tokens": "7d90b44b7e9fb16b", | |
"hash_cont_tokens": "94756b261aca022c" | |
}, | |
"truncated": 541, | |
"non_truncated": 0, | |
"padded": 116, | |
"non_padded": 425, | |
"num_truncated_few_shots": 0 | |
} | |
} |