{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 668121.272123906, "end_time": 668717.330829345, "total_evaluation_time_secondes": "596.0587054390926", "model_name": "Qwen/Qwen1.5-7B-Chat", "model_sha": "a2662f4bc1afe913a91cd49f794d229a8c28f97e", "model_dtype": "torch.bfloat16", "model_size": "14.88 GB", "config": null }, "results": { "extended|ifeval|0": { "prompt_level_strict_acc": 0.36414048059149723, "prompt_level_strict_acc_stderr": 0.020707047958591986, "inst_level_strict_acc": 0.48081534772182255, "inst_level_strict_acc_stderr": 0.0005389541620950422, "prompt_level_loose_acc": 0.40850277264325324, "prompt_level_loose_acc_stderr": 0.02115324409872036, "inst_level_loose_acc": 0.5239808153477218, "inst_level_loose_acc_stderr": 0.0005337352169361823 } }, "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": "2fb0d0953a819f20" }, "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": "d0e068c70912d569" }, "truncated": 541, "non_truncated": 0, "padded": 111, "non_padded": 430, "num_truncated_few_shots": 0 } }