{ "config_general": { "lighteval_sha": "d3fad8bc430df2c96132a56decf820e760575531", "num_fewshot_seeds": 1, "override_batch_size": -1, "max_samples": null, "job_id": "", "start_time": 1651620.991836474, "end_time": 1652240.273853538, "total_evaluation_time_secondes": "619.282017064048", "model_name": "meta-llama/Meta-Llama-3.1-70B-Instruct", "model_sha": "", "model_dtype": null, "model_size": null }, "results": { "custom|musr:murder_mysteries|0": { "pem": 0.0, "pem_stderr": 0.0, "acc": 0.536, "acc_stderr": 0.031603975145223735 }, "all": { "pem": 0.0, "pem_stderr": 0.0, "acc": 0.536, "acc_stderr": 0.031603975145223735 } }, "versions": { "custom|musr:murder_mysteries|0": 0 }, "config_tasks": { "custom|musr:murder_mysteries": { "name": "musr:murder_mysteries", "prompt_function": "musr_prompt_mm", "hf_repo": "TAUR-Lab/MuSR", "hf_subset": "default", "metric": [ { "metric_name": "acc", "higher_is_better": true, "category": "8", "use_case": "1", "sample_level_fn": "compute", "corpus_level_fn": "mean" }, { "metric_name": "pem", "higher_is_better": true, "category": "3", "use_case": "1", "sample_level_fn": "compute", "corpus_level_fn": "mean" } ], "hf_avail_splits": [ "murder_mysteries" ], "evaluation_splits": [ "murder_mysteries" ], "few_shots_split": "", "few_shots_select": "random_sampling", "generation_size": 10000, "generation_grammar": null, "stop_sequence": [], "output_regex": null, "num_samples": null, "frozen": false, "suite": [ "custom" ], "original_num_docs": 250, "effective_num_docs": 250, "trust_dataset": null, "must_remove_duplicate_docs": null, "version": 0 } }, "summary_tasks": { "custom|musr:murder_mysteries|0": { "hashes": { "hash_examples": "e57d289b06a7b768", "hash_full_prompts": "ef87de16b29e1ad6", "hash_input_tokens": "261a3362fb1e3a49", "hash_cont_tokens": "4ccd93a3cc7758cc" }, "truncated": 0, "non_truncated": 500, "padded": 0, "non_padded": 750, "effective_few_shots": 0.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "12857cef73fec968", "hash_full_prompts": "b4d2c9f7b84e6c86", "hash_input_tokens": "9492dc004d54bb27", "hash_cont_tokens": "b9e0dc01cae2cba0" }, "truncated": 0, "non_truncated": 500, "padded": 0, "non_padded": 750, "num_truncated_few_shots": 0 } }