open-r1-eval-leaderboard
/
eval_results
/lewtun
/zephyr-2b-gemma-sft-mix3
/main
/ifeval
/results_2024-03-06T12-34-06.805908.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 310260.582966179, | |
"end_time": 310852.717862596, | |
"total_evaluation_time_secondes": "592.1348964169738", | |
"model_name": "lewtun/zephyr-2b-gemma-sft-mix3", | |
"model_sha": "cc241ce1491a284439fda0de879f1a53e65b5c0f", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "4.68 GB", | |
"config": null | |
}, | |
"results": { | |
"custom|ifeval|0": { | |
"prompt_level_strict_acc": 0.21256931608133087, | |
"prompt_level_strict_acc_stderr": 0.017605954482106622, | |
"inst_level_strict_acc": 0.35731414868105515, | |
"inst_level_strict_acc_stderr": 0.0004739376750337015, | |
"prompt_level_loose_acc": 0.21811460258780038, | |
"prompt_level_loose_acc_stderr": 0.017771211776653854, | |
"inst_level_loose_acc": 0.3657074340527578, | |
"inst_level_loose_acc_stderr": 0.00047327144568788215 | |
} | |
}, | |
"versions": { | |
"custom|ifeval|0": 0 | |
}, | |
"config_tasks": { | |
"custom|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": [ | |
"custom" | |
], | |
"original_num_docs": 541, | |
"effective_num_docs": 541 | |
} | |
}, | |
"summary_tasks": { | |
"custom|ifeval|0": { | |
"hashes": { | |
"hash_examples": "e99cbf567588d7c6", | |
"hash_full_prompts": "7ea7bf2a8edba8f4", | |
"hash_input_tokens": "89df3fff41e770ad", | |
"hash_cont_tokens": "43682f19ef916037" | |
}, | |
"truncated": 0, | |
"non_truncated": 541, | |
"padded": 0, | |
"non_padded": 541, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "ea046ab2c6fc5928", | |
"hash_full_prompts": "45f8422f6ad2da79", | |
"hash_input_tokens": "917957472cc73e8e", | |
"hash_cont_tokens": "1022a066eb3a2419" | |
}, | |
"truncated": 0, | |
"non_truncated": 541, | |
"padded": 0, | |
"non_padded": 541, | |
"num_truncated_few_shots": 0 | |
} | |
} |