open-r1-eval-leaderboard
/
eval_results
/HuggingFaceH4
/pythia-70m-orpo
/v0.0
/ifeval
/results_2024-03-28T21-57-20.345799.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 261811.486323429, | |
"end_time": 261984.720804454, | |
"total_evaluation_time_secondes": "173.23448102499242", | |
"model_name": "HuggingFaceH4/pythia-70m-orpo", | |
"model_sha": "743cc204a050343e0672742d8d91cc9350488df8", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "138.78 MB", | |
"config": null | |
}, | |
"results": { | |
"extended|ifeval|0": { | |
"prompt_level_strict_acc": 0.11275415896487985, | |
"prompt_level_strict_acc_stderr": 0.013611042535042866, | |
"inst_level_strict_acc": 0.22062350119904076, | |
"inst_level_strict_acc_stderr": 0.0004405035258712648, | |
"prompt_level_loose_acc": 0.12014787430683918, | |
"prompt_level_loose_acc_stderr": 0.013991555826864791, | |
"inst_level_loose_acc": 0.23501199040767387, | |
"inst_level_loose_acc_stderr": 0.00045253435349457827 | |
}, | |
"all": { | |
"prompt_level_strict_acc": 0.11275415896487985, | |
"prompt_level_strict_acc_stderr": 0.013611042535042866, | |
"inst_level_strict_acc": 0.22062350119904076, | |
"inst_level_strict_acc_stderr": 0.0004405035258712648, | |
"prompt_level_loose_acc": 0.12014787430683918, | |
"prompt_level_loose_acc_stderr": 0.013991555826864791, | |
"inst_level_loose_acc": 0.23501199040767387, | |
"inst_level_loose_acc_stderr": 0.00045253435349457827 | |
} | |
}, | |
"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": "7ea7bf2a8edba8f4", | |
"hash_input_tokens": "fb456ead7bf50a43", | |
"hash_cont_tokens": "4a925438ff430b2d" | |
}, | |
"truncated": 541, | |
"non_truncated": 0, | |
"padded": 103, | |
"non_padded": 438, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "ea046ab2c6fc5928", | |
"hash_full_prompts": "45f8422f6ad2da79", | |
"hash_input_tokens": "e7e3c2e620c8104f", | |
"hash_cont_tokens": "ad463c057a61052c" | |
}, | |
"truncated": 541, | |
"non_truncated": 0, | |
"padded": 103, | |
"non_padded": 438, | |
"num_truncated_few_shots": 0 | |
} | |
} |