{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 468806.504287818, "end_time": 484689.513194686, "total_evaluation_time_secondes": "15883.008906867995", "model_name": "alpindale/WizardLM-2-8x22B", "model_sha": "dd9964910e87b3876a2959911a29cbdb1d518180", "model_dtype": "torch.bfloat16", "model_size": "263.68 GB", "config": null }, "results": { "extended|ifeval|0": { "prompt_level_strict_acc": 0.5619223659889094, "prompt_level_strict_acc_stderr": 0.02135093113549094, "inst_level_strict_acc": 0.670263788968825, "inst_level_strict_acc_stderr": 0.000496105791739948, "prompt_level_loose_acc": 0.6247689463955638, "prompt_level_loose_acc_stderr": 0.020835898065035694, "inst_level_loose_acc": 0.7206235011990407, "inst_level_loose_acc_stderr": 0.0004853658799765977 }, "all": { "prompt_level_strict_acc": 0.5619223659889094, "prompt_level_strict_acc_stderr": 0.02135093113549094, "inst_level_strict_acc": 0.670263788968825, "inst_level_strict_acc_stderr": 0.000496105791739948, "prompt_level_loose_acc": 0.6247689463955638, "prompt_level_loose_acc_stderr": 0.020835898065035694, "inst_level_loose_acc": 0.7206235011990407, "inst_level_loose_acc_stderr": 0.0004853658799765977 } }, "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": "65ce6f78dff49b9b", "hash_input_tokens": "2210f07150c9e23a", "hash_cont_tokens": "52c4f16e94e6f5b4" }, "truncated": 541, "non_truncated": 0, "padded": 118, "non_padded": 423, "effective_few_shots": 0.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "ea046ab2c6fc5928", "hash_full_prompts": "d0f34a7fe2118466", "hash_input_tokens": "e13bde2327c2d4fe", "hash_cont_tokens": "c956d685a038b1bc" }, "truncated": 541, "non_truncated": 0, "padded": 118, "non_padded": 423, "num_truncated_few_shots": 0 } }