{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 1047145.391913304, "end_time": 1047603.810201325, "total_evaluation_time_secondes": "458.41828802099917", "model_name": "Qwen/Qwen1.5-0.5B-Chat", "model_sha": "6c705984bb8b5591dd4e1a9e66e1a127965fd08d", "model_dtype": "torch.bfloat16", "model_size": "1.05 GB", "config": null }, "results": { "extended|ifeval|0": { "prompt_level_strict_acc": 0.1256931608133087, "prompt_level_strict_acc_stderr": 0.014265627567173856, "inst_level_strict_acc": 0.22422062350119903, "inst_level_strict_acc_stderr": 0.00045298878267336024, "prompt_level_loose_acc": 0.14972273567467653, "prompt_level_loose_acc_stderr": 0.015354203073785802, "inst_level_loose_acc": 0.2517985611510791, "inst_level_loose_acc_stderr": 0.0004624756013461203 } }, "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": "1d8bccd45ca3707b", "hash_input_tokens": "4aede348bfb0e38d", "hash_cont_tokens": "3ecdc4c863d5ba4e" }, "truncated": 541, "non_truncated": 0, "padded": 111, "non_padded": 430, "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": "e8dcf25ae2c76d07" }, "truncated": 541, "non_truncated": 0, "padded": 111, "non_padded": 430, "num_truncated_few_shots": 0 } }