open-r1-eval-leaderboard
/
eval_results
/deepseek-ai
/deepseek-llm-67b-chat
/main
/ifeval
/results_2024-03-05T03-30-18.059805.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 3048910.253903816, | |
"end_time": 3067826.362818127, | |
"total_evaluation_time_secondes": "18916.108914311044", | |
"model_name": "deepseek-ai/deepseek-llm-67b-chat", | |
"model_sha": "79648bef7658bb824e4630740f6e1484c1b0620b", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "125.78 GB", | |
"config": null | |
}, | |
"results": { | |
"custom|ifeval|0": { | |
"prompt_level_strict_acc": 0.5046210720887245, | |
"prompt_level_strict_acc_stderr": 0.021515655182902067, | |
"inst_level_strict_acc": 0.6187050359712231, | |
"inst_level_strict_acc_stderr": 0.0004886473327186499, | |
"prompt_level_loose_acc": 0.5526802218114603, | |
"prompt_level_loose_acc_stderr": 0.02139681502042596, | |
"inst_level_loose_acc": 0.6546762589928058, | |
"inst_level_loose_acc_stderr": 0.00047924837463123813 | |
} | |
}, | |
"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": "9e50b497b0bfea1b", | |
"hash_input_tokens": "410760e9186aa2a8", | |
"hash_cont_tokens": "4cfe6ce2c00e8570" | |
}, | |
"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": "1907749e7908081b", | |
"hash_input_tokens": "66ea2dc43333b4f6", | |
"hash_cont_tokens": "028fee03012cef08" | |
}, | |
"truncated": 0, | |
"non_truncated": 541, | |
"padded": 0, | |
"non_padded": 541, | |
"num_truncated_few_shots": 0 | |
} | |
} |