open-r1-eval-leaderboard
/
eval_results
/kaist-ai
/mistral-orpo-alpha
/main
/ifeval
/results_2024-03-28T19-22-25.177450.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 1131181.258134521, | |
"end_time": 1131915.611567847, | |
"total_evaluation_time_secondes": "734.3534333258867", | |
"model_name": "kaist-ai/mistral-orpo-alpha", | |
"model_sha": "fe1724b77567a2a3579e74240a69a66622191735", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "13.99 GB", | |
"config": null | |
}, | |
"results": { | |
"extended|ifeval|0": { | |
"prompt_level_strict_acc": 0.5157116451016636, | |
"prompt_level_strict_acc_stderr": 0.021505948540061576, | |
"inst_level_strict_acc": 0.6306954436450839, | |
"inst_level_strict_acc_stderr": 0.0005051962926297809, | |
"prompt_level_loose_acc": 0.5508317929759704, | |
"prompt_level_loose_acc_stderr": 0.021405093233588305, | |
"inst_level_loose_acc": 0.658273381294964, | |
"inst_level_loose_acc_stderr": 0.0005003499501301376 | |
}, | |
"all": { | |
"prompt_level_strict_acc": 0.5157116451016636, | |
"prompt_level_strict_acc_stderr": 0.021505948540061576, | |
"inst_level_strict_acc": 0.6306954436450839, | |
"inst_level_strict_acc_stderr": 0.0005051962926297809, | |
"prompt_level_loose_acc": 0.5508317929759704, | |
"prompt_level_loose_acc_stderr": 0.021405093233588305, | |
"inst_level_loose_acc": 0.658273381294964, | |
"inst_level_loose_acc_stderr": 0.0005003499501301376 | |
} | |
}, | |
"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": "46932ca113ba6b0c", | |
"hash_input_tokens": "8b2e0300fbfb70bc", | |
"hash_cont_tokens": "8c6eebe85d1e1464" | |
}, | |
"truncated": 541, | |
"non_truncated": 0, | |
"padded": 123, | |
"non_padded": 418, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "ea046ab2c6fc5928", | |
"hash_full_prompts": "8ed52f7b74eb0590", | |
"hash_input_tokens": "9f4b7e9e7ff95d4a", | |
"hash_cont_tokens": "9fa4b5d52478071d" | |
}, | |
"truncated": 541, | |
"non_truncated": 0, | |
"padded": 123, | |
"non_padded": 418, | |
"num_truncated_few_shots": 0 | |
} | |
} |