{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 1887916.866927724, "end_time": 1888002.029025332, "total_evaluation_time_secondes": "85.1620976079721", "model_name": "HuggingFaceH4/qwen-1.5-1.8b-dpo", "model_sha": "7019026eb75158337ebc7076644edaa152e5f76a", "model_dtype": "torch.bfloat16", "model_size": "3.79 GB", "config": null }, "results": { "leaderboard|truthfulqa:mc|0": { "truthfulqa_mc1": 0.2729498164014688, "truthfulqa_mc1_stderr": 0.015594753632006523, "truthfulqa_mc2": 0.4331479895726319, "truthfulqa_mc2_stderr": 0.0163952129556762 } }, "versions": { "leaderboard|truthfulqa:mc|0": 0 }, "config_tasks": { "leaderboard|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": [ "leaderboard" ], "original_num_docs": 817, "effective_num_docs": 817, "trust_dataset": true } }, "summary_tasks": { "leaderboard|truthfulqa:mc|0": { "hashes": { "hash_examples": "36a6d90e75d92d4a", "hash_full_prompts": "17e9d0dc9f923ba3", "hash_input_tokens": "01fd12cf9a0a72f8", "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": "81a2e5a97bc8b7e3", "hash_input_tokens": "aefcbd35b2c0f9aa", "hash_cont_tokens": "b7b1973c20b71975" }, "truncated": 0, "non_truncated": 817, "padded": 9192, "non_padded": 804, "num_truncated_few_shots": 0 } }