{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 2042180.076507038, "end_time": 2043185.861900278, "total_evaluation_time_secondes": "1005.7853932399303", "model_name": "meta-llama/Llama-2-13b-chat-hf", "model_sha": "c2f3ec81aac798ae26dcc57799a994dfbf521496", "model_dtype": "torch.bfloat16", "model_size": "24.32 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.32717190388170053, "prompt_level_strict_acc_stderr": 0.020190318966906352, "inst_level_strict_acc": 0.44244604316546765, "inst_level_strict_acc_stderr": 0.000524422065932127, "prompt_level_loose_acc": 0.45286506469500926, "prompt_level_loose_acc_stderr": 0.021420753949529567, "inst_level_loose_acc": 0.5695443645083933, "inst_level_loose_acc_stderr": 0.0005175712607558221 } }, "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": "65ce6f78dff49b9b", "hash_input_tokens": "948a776e66685f18", "hash_cont_tokens": "764d33d3636aa504" }, "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": "d0f34a7fe2118466", "hash_input_tokens": "a33aa38cc652a8a9", "hash_cont_tokens": "409bd14d994368a2" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }