{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 3893039.938987827, "end_time": 3894273.558074105, "total_evaluation_time_secondes": "1233.6190862781368", "model_name": "meta-llama/Llama-2-13b-chat-hf", "model_sha": "c2f3ec81aac798ae26dcc57799a994dfbf521496", "model_dtype": "torch.bfloat16", "model_size": "24.32 GB", "config": null }, "results": { "lighteval|gsm8k|5": { "qem": 0.177407126611069, "qem_stderr": 0.01052253301689078 } }, "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": "d3068fe5f2428f31", "hash_input_tokens": "b126bd67db6462db", "hash_cont_tokens": "b1035445a7d47bee" }, "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": "040b4bcee19b92b6", "hash_input_tokens": "6b553e2ed7719e00", "hash_cont_tokens": "969aad7289d383f6" }, "truncated": 0, "non_truncated": 1319, "padded": 0, "non_padded": 1319, "num_truncated_few_shots": 0 } }