{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 6591063.161907463, "end_time": 6592696.222461101, "total_evaluation_time_secondes": "1633.0605536373332", "model_name": "meta-llama/Llama-2-70b-chat-hf", "model_sha": "e1ce257bd76895e0864f3b4d6c7ed3c4cdec93e2", "model_dtype": "torch.bfloat16", "model_size": "128.64 GB", "config": null }, "results": { "lighteval|arc:challenge|25": { "acc": 0.5494880546075085, "acc_stderr": 0.014539646098471627, "acc_norm": 0.5699658703071673, "acc_norm_stderr": 0.014467631559137986 } }, "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": "8877bdb6395a501d", "hash_input_tokens": "c67ed683408af090", "hash_cont_tokens": "e8abf848493b50f7" }, "truncated": 0, "non_truncated": 1172, "padded": 4661, "non_padded": 26, "effective_few_shots": 25.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "aaa6929c6d3771fb", "hash_full_prompts": "ccba71d46636db2f", "hash_input_tokens": "ef37bb2604f905d8", "hash_cont_tokens": "ba41a41319a6da52" }, "truncated": 0, "non_truncated": 1172, "padded": 4661, "non_padded": 26, "num_truncated_few_shots": 0 } }