{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 41543.725764118, "end_time": 41620.619181665, "total_evaluation_time_secondes": "76.89341754700581", "model_name": "alignment-handbook/zephyr-2b-gemma-dpo-mix7-beta-0.05-epoch-6", "model_sha": "1ecb6ade923a19d209a5ffe161833e4fe42c3580", "model_dtype": "torch.bfloat16", "model_size": "4.68 GB", "config": null }, "results": { "lighteval|truthfulqa:mc|0": { "truthfulqa_mc1": 0.2974296205630355, "truthfulqa_mc1_stderr": 0.016002651487361005, "truthfulqa_mc2": 0.4115471422284327, "truthfulqa_mc2_stderr": 0.015141838528517422 } }, "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": "a2fafe1cd099f3f2", "hash_input_tokens": "027fadb028b6bc90", "hash_cont_tokens": "856a0c14e73e2579" }, "truncated": 0, "non_truncated": 817, "padded": 9512, "non_padded": 484, "effective_few_shots": 0.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "aed1dfc67e53d0f2", "hash_full_prompts": "0e986fa3ce840092", "hash_input_tokens": "5692b62e76ec5e99", "hash_cont_tokens": "05a6e7c601fa09e0" }, "truncated": 0, "non_truncated": 817, "padded": 9512, "non_padded": 484, "num_truncated_few_shots": 0 } }