{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 642743.52095145, "end_time": 649327.103836348, "total_evaluation_time_secondes": "6583.58288489806", "model_name": "abhishek/autotrain-llama3-70b-math-v1", "model_sha": "15adc71ad9fb7de113f10d750b97fd1d0329218d", "model_dtype": "torch.float16", "model_size": "131.73 GB", "config": null }, "results": { "lighteval|gsm8k|5": { "qem": 0.890068233510235, "qem_stderr": 0.008616195587865418 }, "all": { "qem": 0.890068233510235, "qem_stderr": 0.008616195587865418 } }, "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:" ], "output_regex": null, "frozen": false, "suite": [ "lighteval" ], "original_num_docs": 1319, "effective_num_docs": 1319, "trust_dataset": true, "must_remove_duplicate_docs": null } }, "summary_tasks": { "lighteval|gsm8k|5": { "hashes": { "hash_examples": "0ed016e24e7512fd", "hash_full_prompts": "f7ab209f6467841e", "hash_input_tokens": "77a960cfa0f9a228", "hash_cont_tokens": "4c754c5cd76bf8cc" }, "truncated": 1319, "non_truncated": 0, "padded": 592, "non_padded": 727, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "bc71463e88551d0e", "hash_full_prompts": "c29e3bdf1c4887c9", "hash_input_tokens": "d542b5652a8c7ba6", "hash_cont_tokens": "075a7cda5b6e5cf0" }, "truncated": 1319, "non_truncated": 0, "padded": 592, "non_padded": 727, "num_truncated_few_shots": 0 } }