{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 344036.970517098, "end_time": 344731.535762563, "total_evaluation_time_secondes": "694.5652454650262", "model_name": "teknium/OpenHermes-2.5-Mistral-7B", "model_sha": "24c0bea14d53e6f67f1fbe2eca5bfe7cae389b33", "model_dtype": "torch.bfloat16", "model_size": "13.99 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.5046210720887245, "prompt_level_strict_acc_stderr": 0.021515655182902067, "inst_level_strict_acc": 0.6151079136690647, "inst_level_strict_acc_stderr": 0.0005189929135992171, "prompt_level_loose_acc": 0.5268022181146026, "prompt_level_loose_acc_stderr": 0.021485638661937968, "inst_level_loose_acc": 0.6474820143884892, "inst_level_loose_acc_stderr": 0.0005046158597123635 } }, "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": "7ea7bf2a8edba8f4", "hash_input_tokens": "cbf56a3804371c84", "hash_cont_tokens": "cfdf2bfd89d384e5" }, "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": "45f8422f6ad2da79", "hash_input_tokens": "e8f96928ae2b5d8c", "hash_cont_tokens": "8e3b0780e153cc00" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }