{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 6560584.915409509, "end_time": 6563750.257955012, "total_evaluation_time_secondes": "3165.342545502819", "model_name": "deepseek-ai/deepseek-coder-33b-instruct", "model_sha": "6f09197224af9638c32c01a9060e78b0cf5a4479", "model_dtype": "torch.bfloat16", "model_size": "62.62 GB", "config": null }, "results": { "lighteval|arc:challenge|25": { "acc": 0.4197952218430034, "acc_stderr": 0.014422181226303026, "acc_norm": 0.454778156996587, "acc_norm_stderr": 0.014551507060836355 } }, "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": "e6f0c83f056d99a3", "hash_input_tokens": "52a91d5a1fce80ed", "hash_cont_tokens": "4ec87421bc371ccb" }, "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": "d59a834a0a0ad118", "hash_input_tokens": "130e7d6d03acbb7d", "hash_cont_tokens": "b02cc1a30d4b8048" }, "truncated": 0, "non_truncated": 1172, "padded": 4671, "non_padded": 16, "num_truncated_few_shots": 0 } }