open-r1-eval-leaderboard
/
eval_results
/Nexusflow
/Starling-LM-7B-beta
/main
/ifeval
/results_2024-03-28T19-55-03.124753.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 844185.044409935, | |
"end_time": 844914.690654436, | |
"total_evaluation_time_secondes": "729.6462445009965", | |
"model_name": "Nexusflow/Starling-LM-7B-beta", | |
"model_sha": "aa21e7f117d41f9463b6d48d2e127bbf2e93256d", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "13.61 GB", | |
"config": null | |
}, | |
"results": { | |
"extended|ifeval|0": { | |
"prompt_level_strict_acc": 0.3678373382624769, | |
"prompt_level_strict_acc_stderr": 0.02075130655602969, | |
"inst_level_strict_acc": 0.5, | |
"inst_level_strict_acc_stderr": 0.0005235955482871635, | |
"prompt_level_loose_acc": 0.4399260628465804, | |
"prompt_level_loose_acc_stderr": 0.021360708220801983, | |
"inst_level_loose_acc": 0.5635491606714629, | |
"inst_level_loose_acc_stderr": 0.000529766309911881 | |
}, | |
"all": { | |
"prompt_level_strict_acc": 0.3678373382624769, | |
"prompt_level_strict_acc_stderr": 0.02075130655602969, | |
"inst_level_strict_acc": 0.5, | |
"inst_level_strict_acc_stderr": 0.0005235955482871635, | |
"prompt_level_loose_acc": 0.4399260628465804, | |
"prompt_level_loose_acc_stderr": 0.021360708220801983, | |
"inst_level_loose_acc": 0.5635491606714629, | |
"inst_level_loose_acc_stderr": 0.000529766309911881 | |
} | |
}, | |
"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": "9f5e4b72daf2ebe9", | |
"hash_input_tokens": "2e90eebf15fbab7c", | |
"hash_cont_tokens": "bcec1bab3592c9d0" | |
}, | |
"truncated": 541, | |
"non_truncated": 0, | |
"padded": 116, | |
"non_padded": 425, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "ea046ab2c6fc5928", | |
"hash_full_prompts": "35db515f08aedd85", | |
"hash_input_tokens": "f60ee03e2d3f1c00", | |
"hash_cont_tokens": "9630e394922a7462" | |
}, | |
"truncated": 541, | |
"non_truncated": 0, | |
"padded": 116, | |
"non_padded": 425, | |
"num_truncated_few_shots": 0 | |
} | |
} |