{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 107219.931128316, "end_time": 107314.642864227, "total_evaluation_time_secondes": "94.71173591099796", "model_name": "stabilityai/stablelm-zephyr-3b", "model_sha": "8b471c751c0e78cb46cf9f47738dd0eb45392071", "model_dtype": "torch.bfloat16", "model_size": "5.22 GB", "config": null }, "results": { "lighteval|arc:challenge|25": { "acc": 0.45307167235494883, "acc_stderr": 0.01454689205200563, "acc_norm": 0.45819112627986347, "acc_norm_stderr": 0.014560220308714702 } }, "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": "8a73030d9b86cf57", "hash_input_tokens": "0eee958805b1ec44", "hash_cont_tokens": "427c1ce301478113" }, "truncated": 0, "non_truncated": 1172, "padded": 4648, "non_padded": 39, "effective_few_shots": 25.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "aaa6929c6d3771fb", "hash_full_prompts": "dcd278ac08ccf0ee", "hash_input_tokens": "d645b1d58fc95792", "hash_cont_tokens": "b1ded4e124ebbadf" }, "truncated": 0, "non_truncated": 1172, "padded": 4648, "non_padded": 39, "num_truncated_few_shots": 0 } }