{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 718917.512737757, "end_time": 719622.125553648, "total_evaluation_time_secondes": "704.6128158910433", "model_name": "openchat/openchat-3.5-0106", "model_sha": "9619fb7d2a8e25fa6b0633c0f57f7f4aa79b45c4", "model_dtype": "torch.bfloat16", "model_size": "13.61 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.5157116451016636, "prompt_level_strict_acc_stderr": 0.021505948540061583, "inst_level_strict_acc": 0.6235011990407674, "inst_level_strict_acc_stderr": 0.0005124397246951698, "prompt_level_loose_acc": 0.5471349353049908, "prompt_level_loose_acc_stderr": 0.02142075394952957, "inst_level_loose_acc": 0.6546762589928058, "inst_level_loose_acc_stderr": 0.0005075711074192088 } }, "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": "9f5e4b72daf2ebe9", "hash_input_tokens": "2e90eebf15fbab7c", "hash_cont_tokens": "bc1b7097488393e6" }, "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": "35db515f08aedd85", "hash_input_tokens": "f60ee03e2d3f1c00", "hash_cont_tokens": "3ad1b02f8c461868" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }