open-r1-eval-leaderboard
/
eval_results
/NousResearch
/Hermes-2-Pro-Mistral-7B
/main
/ifeval
/results_2024-03-28T19-53-41.347489.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 1250990.191459896, | |
"end_time": 1251691.434393512, | |
"total_evaluation_time_secondes": "701.2429336160421", | |
"model_name": "NousResearch/Hermes-2-Pro-Mistral-7B", | |
"model_sha": "4d50786bb33ce7c31697932a0ebe01fd8a373a4a", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "13.99 GB", | |
"config": null | |
}, | |
"results": { | |
"extended|ifeval|0": { | |
"prompt_level_strict_acc": 0.5083179297597042, | |
"prompt_level_strict_acc_stderr": 0.021513596564021183, | |
"inst_level_strict_acc": 0.6247002398081535, | |
"inst_level_strict_acc_stderr": 0.000523733511365831, | |
"prompt_level_loose_acc": 0.5415896487985212, | |
"prompt_level_loose_acc_stderr": 0.021442010560476534, | |
"inst_level_loose_acc": 0.6606714628297362, | |
"inst_level_loose_acc_stderr": 0.0005031302430479284 | |
}, | |
"all": { | |
"prompt_level_strict_acc": 0.5083179297597042, | |
"prompt_level_strict_acc_stderr": 0.021513596564021183, | |
"inst_level_strict_acc": 0.6247002398081535, | |
"inst_level_strict_acc_stderr": 0.000523733511365831, | |
"prompt_level_loose_acc": 0.5415896487985212, | |
"prompt_level_loose_acc_stderr": 0.021442010560476534, | |
"inst_level_loose_acc": 0.6606714628297362, | |
"inst_level_loose_acc_stderr": 0.0005031302430479284 | |
} | |
}, | |
"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": "cbf56a3804371c84", | |
"hash_cont_tokens": "0dcd3591fb4d2c9a" | |
}, | |
"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": "45f8422f6ad2da79", | |
"hash_input_tokens": "e8f96928ae2b5d8c", | |
"hash_cont_tokens": "8d5c07043ba70e59" | |
}, | |
"truncated": 541, | |
"non_truncated": 0, | |
"padded": 123, | |
"non_padded": 418, | |
"num_truncated_few_shots": 0 | |
} | |
} |