{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 679593.549497914, "end_time": 680608.914513206, "total_evaluation_time_secondes": "1015.3650152919581", "model_name": "teknium/OpenHermes-2.5-Mistral-7B", "model_sha": "24c0bea14d53e6f67f1fbe2eca5bfe7cae389b33", "model_dtype": "torch.bfloat16", "model_size": "13.99 GB", "config": null }, "results": { "lighteval|gsm8k|5": { "qem": 0.5405610310841547, "qem_stderr": 0.013727093010429788 } }, "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": "a9c6515c2ecd2d07", "hash_input_tokens": "b28aa8e3b3b87471", "hash_cont_tokens": "2f9928bdb1296170" }, "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": "f49691ec139bfeac", "hash_input_tokens": "2d83818f189ec0f2", "hash_cont_tokens": "1d222ea20774acaa" }, "truncated": 0, "non_truncated": 1319, "padded": 0, "non_padded": 1319, "num_truncated_few_shots": 0 } }