{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 1836474.402691832, "end_time": 1836865.935514845, "total_evaluation_time_secondes": "391.5328230129089", "model_name": "AI-MO/deepseek-math-7b-sft", "model_sha": "6d9b2ab05af9908eac6d5eeb8e37ae2c8ea22dba", "model_dtype": "torch.bfloat16", "model_size": "12.93 GB", "config": null }, "results": { "lighteval|gsm8k|5": { "qem": 0.533737680060652, "qem_stderr": 0.01374109641222676 }, "all": { "qem": 0.533737680060652, "qem_stderr": 0.01374109641222676 } }, "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:" ], "output_regex": null, "frozen": false, "suite": [ "lighteval" ], "original_num_docs": 1319, "effective_num_docs": 1319, "trust_dataset": true, "must_remove_duplicate_docs": null } }, "summary_tasks": { "lighteval|gsm8k|5": { "hashes": { "hash_examples": "0ed016e24e7512fd", "hash_full_prompts": "b6d97958f0ed1df8", "hash_input_tokens": "3f58ee5e568409ec", "hash_cont_tokens": "2b7d292f91d596af" }, "truncated": 1319, "non_truncated": 0, "padded": 611, "non_padded": 708, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "bc71463e88551d0e", "hash_full_prompts": "b5a5dacaed0816ff", "hash_input_tokens": "e4e0fd8eba82bd47", "hash_cont_tokens": "ecec1047a09d9b69" }, "truncated": 1319, "non_truncated": 0, "padded": 611, "non_padded": 708, "num_truncated_few_shots": 0 } }