{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 3474876.776366862, "end_time": 3474973.212055677, "total_evaluation_time_secondes": "96.43568881507963", "model_name": "google/gemma-2b-it", "model_sha": "718cb189da9c5b2e55abe86f2eeffee9b4ae0dad", "model_dtype": "torch.bfloat16", "model_size": "4.68 GB", "config": null }, "results": { "lighteval|arc:challenge|25": { "acc": 0.38993174061433444, "acc_stderr": 0.01425295984889288, "acc_norm": 0.3993174061433447, "acc_norm_stderr": 0.014312094557946707 } }, "versions": { "lighteval|arc:challenge|25": 0 }, "config_tasks": { "lighteval|arc:challenge": { "name": "arc:challenge", "prompt_function": "arc", "hf_repo": "ai2_arc", "hf_subset": "ARC-Challenge", "metric": [ "loglikelihood_acc", "loglikelihood_acc_norm_nospace" ], "hf_avail_splits": [ "train", "test" ], "evaluation_splits": [ "test" ], "few_shots_split": null, "few_shots_select": "random_sampling_from_train", "generation_size": 1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "lighteval", "arc" ], "original_num_docs": 1172, "effective_num_docs": 1172 } }, "summary_tasks": { "lighteval|arc:challenge|25": { "hashes": { "hash_examples": "17b0cae357c0259e", "hash_full_prompts": "bb2d0be2053210f5", "hash_input_tokens": "2843abb81b6f6bdf", "hash_cont_tokens": "3bb85634c18ea13e" }, "truncated": 0, "non_truncated": 1172, "padded": 4671, "non_padded": 16, "effective_few_shots": 25.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "aaa6929c6d3771fb", "hash_full_prompts": "a565a36f7666c62d", "hash_input_tokens": "37e0c149ab88e5d9", "hash_cont_tokens": "274bfa3146be24a9" }, "truncated": 0, "non_truncated": 1172, "padded": 4671, "non_padded": 16, "num_truncated_few_shots": 0 } }