{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 1255369.749503207, "end_time": 1255459.029867951, "total_evaluation_time_secondes": "89.28036474413238", "model_name": "Qwen/Qwen1.5-1.8B-Chat", "model_sha": "3aede71902ad578aac72678f9f8b6199ca6ab53b", "model_dtype": "torch.bfloat16", "model_size": "3.8 GB", "config": null }, "results": { "lighteval|arc:challenge|25": { "acc": 0.3822525597269625, "acc_stderr": 0.014200454049979291, "acc_norm": 0.37457337883959047, "acc_norm_stderr": 0.014144193471893437 } }, "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": "4613138cb84a1c53", "hash_input_tokens": "85ecaa299a6a917a", "hash_cont_tokens": "da3689055cb5fa28" }, "truncated": 0, "non_truncated": 1172, "padded": 4651, "non_padded": 36, "effective_few_shots": 25.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "aaa6929c6d3771fb", "hash_full_prompts": "de0ea2e1cc95d72a", "hash_input_tokens": "549aeedee8982096", "hash_cont_tokens": "da91173bce47858f" }, "truncated": 0, "non_truncated": 1172, "padded": 4651, "non_padded": 36, "num_truncated_few_shots": 0 } }