{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 678434.327268481, "end_time": 678568.779543351, "total_evaluation_time_secondes": "134.45227487001102", "model_name": "Qwen/Qwen1.5-7B-Chat", "model_sha": "a2662f4bc1afe913a91cd49f794d229a8c28f97e", "model_dtype": "torch.bfloat16", "model_size": "14.88 GB", "config": null }, "results": { "lighteval|truthfulqa:mc|0": { "truthfulqa_mc1": 0.39657282741738065, "truthfulqa_mc1_stderr": 0.017124930942023518, "truthfulqa_mc2": 0.5636457190278117, "truthfulqa_mc2_stderr": 0.016265310326186867 } }, "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 } }