{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 6807718.359599984, "end_time": 6807799.391669435, "total_evaluation_time_secondes": "81.03206945117563", "model_name": "alignment-handbook/zephyr-2b-gemma-sft-mix7", "model_sha": "48ef9bcbaa26b4e12aa4638c8b14f62dc66065b5", "model_dtype": "torch.bfloat16", "model_size": "4.68 GB", "config": null }, "results": { "lighteval|truthfulqa:mc|0": { "truthfulqa_mc1": 0.3011015911872705, "truthfulqa_mc1_stderr": 0.016058999026100612, "truthfulqa_mc2": 0.4288617889285198, "truthfulqa_mc2_stderr": 0.015031776750809233 } }, "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 } }