{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 773840.35949618, "end_time": 780025.538152071, "total_evaluation_time_secondes": "6185.178655890981", "model_name": "Qwen/Qwen1.5-72B-Chat", "model_sha": "1a6ccc1215278f962c794b1848c710c29ef4053d", "model_dtype": "torch.bfloat16", "model_size": "135.9 GB", "config": null }, "results": { "lighteval|gsm8k|5": { "qem": 0.25549658832448824, "qem_stderr": 0.012013462405460069 } }, "versions": { "lighteval|gsm8k|5": 0 }, "config_tasks": { "lighteval|gsm8k": { "name": "gsm8k", "prompt_function": "gsm8k", "hf_repo": "gsm8k", "hf_subset": "main", "metric": [ "quasi_exact_match_gsm8k" ], "hf_avail_splits": [ "train", "test" ], "evaluation_splits": [ "test" ], "few_shots_split": null, "few_shots_select": "random_sampling_from_train", "generation_size": 256, "stop_sequence": [ ":", "Question:", "Question" ], "output_regex": null, "frozen": false, "suite": [ "lighteval" ], "original_num_docs": 1319, "effective_num_docs": 1319 } }, "summary_tasks": { "lighteval|gsm8k|5": { "hashes": { "hash_examples": "0ed016e24e7512fd", "hash_full_prompts": "66ff2108d151c6de", "hash_input_tokens": "aa57736f8c45c33c", "hash_cont_tokens": "5a5dde5ac923bda1" }, "truncated": 0, "non_truncated": 1319, "padded": 0, "non_padded": 1319, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "bc71463e88551d0e", "hash_full_prompts": "84c6a9cfa115dda5", "hash_input_tokens": "5aac43a2850ca464", "hash_cont_tokens": "faa652455076dc28" }, "truncated": 0, "non_truncated": 1319, "padded": 0, "non_padded": 1319, "num_truncated_few_shots": 0 } }