open-r1-eval-leaderboard
/
eval_results
/Qwen
/Qwen1.5-14B-Chat
/main
/ifeval
/results_2024-03-02T15-38-01.269009.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 622681.334182683, | |
"end_time": 623456.274803791, | |
"total_evaluation_time_secondes": "774.9406211079331", | |
"model_name": "Qwen/Qwen1.5-14B-Chat", | |
"model_sha": "17e11c306ed235e970c9bb8e5f7233527140cdcf", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "27.01 GB", | |
"config": null | |
}, | |
"results": { | |
"custom|ifeval|0": { | |
"prompt_level_strict_acc": 0.4232902033271719, | |
"prompt_level_strict_acc_stderr": 0.021261842325248456, | |
"inst_level_strict_acc": 0.5419664268585132, | |
"inst_level_strict_acc_stderr": 0.0005248195253962884, | |
"prompt_level_loose_acc": 0.47504621072088726, | |
"prompt_level_loose_acc_stderr": 0.021489761058967344, | |
"inst_level_loose_acc": 0.5911270983213429, | |
"inst_level_loose_acc_stderr": 0.0005140692853692289 | |
} | |
}, | |
"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": "1d8bccd45ca3707b", | |
"hash_input_tokens": "4aede348bfb0e38d", | |
"hash_cont_tokens": "2c73ee0dcf34aa12" | |
}, | |
"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": "41a5572cc1263dc7", | |
"hash_input_tokens": "dc284e5de619e6a7", | |
"hash_cont_tokens": "3608acf71c3d8397" | |
}, | |
"truncated": 0, | |
"non_truncated": 541, | |
"padded": 0, | |
"non_padded": 541, | |
"num_truncated_few_shots": 0 | |
} | |
} |