open-r1-eval-leaderboard
/
eval_results
/databricks
/dbrx-instruct
/main
/ifeval
/results_2024-04-25T10-22-32.175133.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 4358.745391853, | |
"end_time": 12387.557099267, | |
"total_evaluation_time_secondes": "8028.811707414", | |
"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": 0.48613678373382624, | |
"prompt_level_strict_acc_stderr": 0.02150830206785605, | |
"inst_level_strict_acc": 0.5911270983213429, | |
"inst_level_strict_acc_stderr": 0.000539492186730242, | |
"prompt_level_loose_acc": 0.5304990757855823, | |
"prompt_level_loose_acc_stderr": 0.021476507681143002, | |
"inst_level_loose_acc": 0.6414868105515588, | |
"inst_level_loose_acc_stderr": 0.0005189880785498665 | |
}, | |
"all": { | |
"prompt_level_strict_acc": 0.48613678373382624, | |
"prompt_level_strict_acc_stderr": 0.02150830206785605, | |
"inst_level_strict_acc": 0.5911270983213429, | |
"inst_level_strict_acc_stderr": 0.000539492186730242, | |
"prompt_level_loose_acc": 0.5304990757855823, | |
"prompt_level_loose_acc_stderr": 0.021476507681143002, | |
"inst_level_loose_acc": 0.6414868105515588, | |
"inst_level_loose_acc_stderr": 0.0005189880785498665 | |
} | |
}, | |
"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": "6a2c6e35df691ba3", | |
"hash_input_tokens": "392a26e72e56230b", | |
"hash_cont_tokens": "0e17dfe15ac6141a" | |
}, | |
"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": "853afd6c0bbf0c6f", | |
"hash_input_tokens": "238a6c196c7ffc29", | |
"hash_cont_tokens": "51d33c66b4bc1936" | |
}, | |
"truncated": 541, | |
"non_truncated": 0, | |
"padded": 108, | |
"non_padded": 433, | |
"num_truncated_few_shots": 0 | |
} | |
} |