{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 106387.194013317, "end_time": 106909.684808261, "total_evaluation_time_secondes": "522.4907949439948", "model_name": "stabilityai/stablelm-zephyr-3b", "model_sha": "8b471c751c0e78cb46cf9f47738dd0eb45392071", "model_dtype": "torch.bfloat16", "model_size": "5.22 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.3142329020332717, "prompt_level_strict_acc_stderr": 0.019976402065150667, "inst_level_strict_acc": 0.43764988009592326, "inst_level_strict_acc_stderr": 0.0005214944830394094, "prompt_level_loose_acc": 0.34750462107208874, "prompt_level_loose_acc_stderr": 0.02049142365341572, "inst_level_loose_acc": 0.47721822541966424, "inst_level_loose_acc_stderr": 0.0005235589866510415 } }, "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": "2322762de886f312", "hash_input_tokens": "054eb49a96820682", "hash_cont_tokens": "3a1d1a16a8e26a81" }, "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": "79c7738726f2efa9", "hash_input_tokens": "37890a7c2b46ac73", "hash_cont_tokens": "6bc4be4ab5856f78" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }