{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 1547797.902405845, "end_time": 1548661.626435689, "total_evaluation_time_secondes": "863.7240298439283", "model_name": "HuggingFaceH4/mistral-7b-kto", "model_sha": "ba517352d0ccbfbbb40cb6c11b66286784ea857a", "model_dtype": "torch.bfloat16", "model_size": "13.99 GB", "config": null }, "results": { "extended|ifeval|0": { "prompt_level_strict_acc": 0.36229205175600737, "prompt_level_strict_acc_stderr": 0.020684424314965394, "inst_level_strict_acc": 0.48201438848920863, "inst_level_strict_acc_stderr": 0.0005185520930111485, "prompt_level_loose_acc": 0.4029574861367837, "prompt_level_loose_acc_stderr": 0.02110743025673165, "inst_level_loose_acc": 0.5215827338129496, "inst_level_loose_acc_stderr": 0.000528089714232759 } }, "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": "46932ca113ba6b0c", "hash_input_tokens": "8b2e0300fbfb70bc", "hash_cont_tokens": "2e4a57fefc0ef41b" }, "truncated": 541, "non_truncated": 0, "padded": 123, "non_padded": 418, "effective_few_shots": 0.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "ea046ab2c6fc5928", "hash_full_prompts": "8ed52f7b74eb0590", "hash_input_tokens": "9f4b7e9e7ff95d4a", "hash_cont_tokens": "ea248e8e9f08d5f3" }, "truncated": 541, "non_truncated": 0, "padded": 123, "non_padded": 418, "num_truncated_few_shots": 0 } }