open-r1-eval-leaderboard
/
eval_results
/databricks
/dbrx-instruct
/main
/ifeval
/results_2024-04-25T11-00-38.856435.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 139451.981561641, | |
"end_time": 147812.086958982, | |
"total_evaluation_time_secondes": "8360.105397340987", | |
"model_name": "databricks/dbrx-instruct", | |
"model_sha": "c0a9245908c187da8f43a81e538e67ff360904ea", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "245.12 GB", | |
"config": null | |
}, | |
"results": { | |
"extended|ifeval|0": { | |
"prompt_level_strict_acc": 0.47504621072088726, | |
"prompt_level_strict_acc_stderr": 0.02148976105896734, | |
"inst_level_strict_acc": 0.5911270983213429, | |
"inst_level_strict_acc_stderr": 0.0005131981820598614, | |
"prompt_level_loose_acc": 0.5360443622920518, | |
"prompt_level_loose_acc_stderr": 0.021460592823736725, | |
"inst_level_loose_acc": 0.657074340527578, | |
"inst_level_loose_acc_stderr": 0.0004814390796113403 | |
}, | |
"all": { | |
"prompt_level_strict_acc": 0.47504621072088726, | |
"prompt_level_strict_acc_stderr": 0.02148976105896734, | |
"inst_level_strict_acc": 0.5911270983213429, | |
"inst_level_strict_acc_stderr": 0.0005131981820598614, | |
"prompt_level_loose_acc": 0.5360443622920518, | |
"prompt_level_loose_acc_stderr": 0.021460592823736725, | |
"inst_level_loose_acc": 0.657074340527578, | |
"inst_level_loose_acc_stderr": 0.0004814390796113403 | |
} | |
}, | |
"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": "1d8bccd45ca3707b", | |
"hash_input_tokens": "3a6a71dfd1c6ca36", | |
"hash_cont_tokens": "2a4e71b173825156" | |
}, | |
"truncated": 541, | |
"non_truncated": 0, | |
"padded": 108, | |
"non_padded": 433, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "ea046ab2c6fc5928", | |
"hash_full_prompts": "41a5572cc1263dc7", | |
"hash_input_tokens": "54a3aa3c72288b71", | |
"hash_cont_tokens": "95396c5eb63ebb91" | |
}, | |
"truncated": 541, | |
"non_truncated": 0, | |
"padded": 108, | |
"non_padded": 433, | |
"num_truncated_few_shots": 0 | |
} | |
} |