{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 673935.251424269, "end_time": 674103.840031105, "total_evaluation_time_secondes": "168.58860683592502", "model_name": "Qwen/Qwen1.5-14B-Chat", "model_sha": "17e11c306ed235e970c9bb8e5f7233527140cdcf", "model_dtype": "torch.bfloat16", "model_size": "27.01 GB", "config": null }, "results": { "lighteval|truthfulqa:mc|0": { "truthfulqa_mc1": 0.42472460220318237, "truthfulqa_mc1_stderr": 0.017304000957167477, "truthfulqa_mc2": 0.609034324809779, "truthfulqa_mc2_stderr": 0.015927536919990177 } }, "versions": { "lighteval|truthfulqa:mc|0": 0 }, "config_tasks": { "lighteval|truthfulqa:mc": { "name": "truthfulqa:mc", "prompt_function": "truthful_qa_multiple_choice", "hf_repo": "truthful_qa", "hf_subset": "multiple_choice", "metric": [ "truthfulqa_mc_metrics" ], "hf_avail_splits": [ "validation" ], "evaluation_splits": [ "validation" ], "few_shots_split": null, "few_shots_select": null, "generation_size": -1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "lighteval" ], "original_num_docs": 817, "effective_num_docs": 817 } }, "summary_tasks": { "lighteval|truthfulqa:mc|0": { "hashes": { "hash_examples": "36a6d90e75d92d4a", "hash_full_prompts": "0ee9c8dfb7ba5726", "hash_input_tokens": "e3613aaf606e098f", "hash_cont_tokens": "5077664e752b6f79" }, "truncated": 0, "non_truncated": 817, "padded": 9192, "non_padded": 804, "effective_few_shots": 0.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "aed1dfc67e53d0f2", "hash_full_prompts": "8e0ba83d3aa3f868", "hash_input_tokens": "449cc57eb13ad0cb", "hash_cont_tokens": "b7b1973c20b71975" }, "truncated": 0, "non_truncated": 817, "padded": 9192, "non_padded": 804, "num_truncated_few_shots": 0 } }