{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 770991.516644159, "end_time": 771674.501580869, "total_evaluation_time_secondes": "682.9849367099814", "model_name": "abacaj/phi-2-super", "model_sha": "f1e578c868e6cc20fb1ea8eeee427ddf6e0e2ee4", "model_dtype": "torch.bfloat16", "model_size": "5.19 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.2476894639556377, "prompt_level_strict_acc_stderr": 0.018576139285185183, "inst_level_strict_acc": 0.3657074340527578, "inst_level_strict_acc_stderr": 0.0005242757258425296, "prompt_level_loose_acc": 0.2809611829944547, "prompt_level_loose_acc_stderr": 0.019342047683777005, "inst_level_loose_acc": 0.40047961630695444, "inst_level_loose_acc_stderr": 0.0005229809220065132 } }, "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": "b3cf2afae2cdd517", "hash_input_tokens": "dd39068592068ba5", "hash_cont_tokens": "9b65fb0ae540b597" }, "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": "ba67cfefd62e0550", "hash_input_tokens": "e0a5833eb7ed0885", "hash_cont_tokens": "0789d5afa3915c88" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }