{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 1518975.682519105, "end_time": 1524330.669084378, "total_evaluation_time_secondes": "5354.986565273022", "model_name": "meta-llama/Meta-Llama-3-70B-Instruct", "model_sha": "359ec69a0f92259a3cd2da3bb01d31e16c260cfc", "model_dtype": "torch.bfloat16", "model_size": "131.73 GB", "config": null }, "results": { "extended|ifeval|0": { "prompt_level_strict_acc": 0.7800369685767098, "prompt_level_strict_acc_stderr": 0.017825247192217113, "inst_level_strict_acc": 0.8453237410071942, "inst_level_strict_acc_stderr": 0.00039885503173309563, "prompt_level_loose_acc": 0.8391866913123844, "prompt_level_loose_acc_stderr": 0.015808599888607083, "inst_level_loose_acc": 0.8920863309352518, "inst_level_loose_acc_stderr": 0.0003385840294307306 }, "all": { "prompt_level_strict_acc": 0.7800369685767098, "prompt_level_strict_acc_stderr": 0.017825247192217113, "inst_level_strict_acc": 0.8453237410071942, "inst_level_strict_acc_stderr": 0.00039885503173309563, "prompt_level_loose_acc": 0.8391866913123844, "prompt_level_loose_acc_stderr": 0.015808599888607083, "inst_level_loose_acc": 0.8920863309352518, "inst_level_loose_acc_stderr": 0.0003385840294307306 } }, "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, "num_samples": null, "frozen": false, "suite": [ "extended" ], "original_num_docs": 541, "effective_num_docs": 541, "trust_dataset": null, "must_remove_duplicate_docs": null, "version": 0 } }, "summary_tasks": { "extended|ifeval|0": { "hashes": { "hash_examples": "e99cbf567588d7c6", "hash_full_prompts": "30fe3a1c6acd1de0", "hash_input_tokens": "8897069e6973d945", "hash_cont_tokens": "b5e56978f507fa25" }, "truncated": 541, "non_truncated": 0, "padded": 116, "non_padded": 425, "effective_few_shots": 0.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "ea046ab2c6fc5928", "hash_full_prompts": "bcd0aa2470bb7894", "hash_input_tokens": "b8bbae42101c2e4a", "hash_cont_tokens": "4afe7ea46274cdc5" }, "truncated": 541, "non_truncated": 0, "padded": 116, "non_padded": 425, "num_truncated_few_shots": 0 } }