{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": -1, "max_samples": null, "job_id": 0, "start_time": 135335.060949194, "end_time": 135820.915881711, "total_evaluation_time_secondes": "485.8549325169879", "model_name": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B", "model_sha": "", "model_dtype": null, "model_size": null }, "results": { "custom|math_500|0": { "extractive_match": 0.854, "extractive_match_stderr": 0.01580720517583485 }, "all": { "extractive_match": 0.854, "extractive_match_stderr": 0.01580720517583485 } }, "versions": { "custom|math_500|0": 1 }, "config_tasks": { "custom|math_500": { "name": "math_500", "prompt_function": "prompt_fn", "hf_repo": "HuggingFaceH4/MATH-500", "hf_subset": "default", "metric": [ { "metric_name": "extractive_match", "higher_is_better": true, "category": "3", "use_case": "1", "sample_level_fn": "sample_level_fn", "corpus_level_fn": "mean" } ], "hf_revision": null, "hf_filter": null, "hf_avail_splits": [ "test" ], "trust_dataset": false, "evaluation_splits": [ "test" ], "few_shots_split": null, "few_shots_select": null, "generation_size": 32768, "generation_grammar": null, "stop_sequence": [], "num_samples": null, "suite": [ "custom" ], "original_num_docs": 500, "effective_num_docs": 500, "must_remove_duplicate_docs": false, "version": 1 } }, "summary_tasks": { "custom|math_500|0": { "hashes": { "hash_examples": "eac05bd67b8179c3", "hash_full_prompts": "9043592f69431f18", "hash_input_tokens": "a6dd0b2c8017a31e", "hash_cont_tokens": "73a683e89547befe" }, "truncated": 0, "non_truncated": 500, "padded": 0, "non_padded": 500, "effective_few_shots": 0.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "d6b3f24200421bb2", "hash_full_prompts": "1a4bc197befd9b91", "hash_input_tokens": "11a6a8141b926588", "hash_cont_tokens": "87ef792246644d83" }, "truncated": 0, "non_truncated": 500, "padded": 0, "non_padded": 500, "num_truncated_few_shots": 0 } }