{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 1798737.733049839, "end_time": 1798824.068123693, "total_evaluation_time_secondes": "86.33507385407574", "model_name": "abacaj/phi-2-super", "model_sha": "f1e578c868e6cc20fb1ea8eeee427ddf6e0e2ee4", "model_dtype": "torch.bfloat16", "model_size": "5.19 GB", "config": null }, "results": { "lighteval|truthfulqa:mc|0": { "truthfulqa_mc1": 0.3671970624235006, "truthfulqa_mc1_stderr": 0.01687480500145318, "truthfulqa_mc2": 0.5179345810283795, "truthfulqa_mc2_stderr": 0.01573435341292855 } }, "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": "b3bf46b4e41d5f65", "hash_input_tokens": "066082b84ecba0c0", "hash_cont_tokens": "17ec5f41a7e613c2" }, "truncated": 0, "non_truncated": 817, "padded": 9625, "non_padded": 371, "effective_few_shots": 0.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "aed1dfc67e53d0f2", "hash_full_prompts": "ff04aa94620d7648", "hash_input_tokens": "e9cbe2776c8e8681", "hash_cont_tokens": "cd0d718d0501d64f" }, "truncated": 0, "non_truncated": 817, "padded": 9625, "non_padded": 371, "num_truncated_few_shots": 0 } }