{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 429885.622058687, "end_time": 430723.459598687, "total_evaluation_time_secondes": "837.8375400000368", "model_name": "abacaj/phi-2-super", "model_sha": "f1e578c868e6cc20fb1ea8eeee427ddf6e0e2ee4", "model_dtype": "torch.bfloat16", "model_size": "5.19 GB", "config": null }, "results": { "lighteval|gsm8k|5": { "qem": 0.510235026535254, "qem_stderr": 0.013769598923012388 } }, "versions": { "lighteval|gsm8k|5": 0 }, "config_tasks": { "lighteval|gsm8k": { "name": "gsm8k", "prompt_function": "gsm8k", "hf_repo": "gsm8k", "hf_subset": "main", "metric": [ "quasi_exact_match_gsm8k" ], "hf_avail_splits": [ "train", "test" ], "evaluation_splits": [ "test" ], "few_shots_split": null, "few_shots_select": "random_sampling_from_train", "generation_size": 256, "stop_sequence": [ ":", "Question:", "Question" ], "output_regex": null, "frozen": false, "suite": [ "lighteval" ], "original_num_docs": 1319, "effective_num_docs": 1319 } }, "summary_tasks": { "lighteval|gsm8k|5": { "hashes": { "hash_examples": "0ed016e24e7512fd", "hash_full_prompts": "90fe3f2059a73bc5", "hash_input_tokens": "46519b6ed3709938", "hash_cont_tokens": "d9861407886baeca" }, "truncated": 0, "non_truncated": 1319, "padded": 0, "non_padded": 1319, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "bc71463e88551d0e", "hash_full_prompts": "65a563534d4eec47", "hash_input_tokens": "86d8c83e6806c248", "hash_cont_tokens": "e122e6d68aa4d91a" }, "truncated": 0, "non_truncated": 1319, "padded": 0, "non_padded": 1319, "num_truncated_few_shots": 0 } }