{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 637935.715615063, "end_time": 642190.846575283, "total_evaluation_time_secondes": "4255.130960220005", "model_name": "Qwen/Qwen1.5-72B-Chat", "model_sha": "1a6ccc1215278f962c794b1848c710c29ef4053d", "model_dtype": "torch.bfloat16", "model_size": "135.9 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.5268022181146026, "prompt_level_strict_acc_stderr": 0.02148563866193796, "inst_level_strict_acc": 0.6354916067146283, "inst_level_strict_acc_stderr": 0.0005235606886787948, "prompt_level_loose_acc": 0.5730129390018485, "prompt_level_loose_acc_stderr": 0.021285933050061316, "inst_level_loose_acc": 0.6762589928057554, "inst_level_loose_acc_stderr": 0.000499137810429491 } }, "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": "1d8bccd45ca3707b", "hash_input_tokens": "4aede348bfb0e38d", "hash_cont_tokens": "1a17035c5f3288ed" }, "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": "41a5572cc1263dc7", "hash_input_tokens": "dc284e5de619e6a7", "hash_cont_tokens": "8429dd2e1027d504" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }