{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 424981.441238658, "end_time": 425367.382682658, "total_evaluation_time_secondes": "385.9414439999964", "model_name": "stabilityai/stablelm-zephyr-3b", "model_sha": "8b471c751c0e78cb46cf9f47738dd0eb45392071", "model_dtype": "torch.bfloat16", "model_size": "5.22 GB", "config": null }, "results": { "lighteval|hellaswag|10": { "acc": 0.5624377614021111, "acc_stderr": 0.004950723480149756, "acc_norm": 0.7156940848436566, "acc_norm_stderr": 0.004501613226126026 } }, "versions": { "lighteval|hellaswag|10": 0 }, "config_tasks": { "lighteval|hellaswag": { "name": "hellaswag", "prompt_function": "hellaswag_harness", "hf_repo": "hellaswag", "hf_subset": "default", "metric": [ "loglikelihood_acc", "loglikelihood_acc_norm" ], "hf_avail_splits": [ "train", "test", "validation" ], "evaluation_splits": [ "validation" ], "few_shots_split": null, "few_shots_select": "random_sampling_from_train", "generation_size": -1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "lighteval" ], "original_num_docs": 10042, "effective_num_docs": 10042 } }, "summary_tasks": { "lighteval|hellaswag|10": { "hashes": { "hash_examples": "31985c805c3a737e", "hash_full_prompts": "f5524d324a080cbf", "hash_input_tokens": "cf03dfc31ec6b6f7", "hash_cont_tokens": "a7467d6b83aab9e6" }, "truncated": 0, "non_truncated": 10042, "padded": 39847, "non_padded": 321, "effective_few_shots": 10.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "63bc2cf8bae03fbc", "hash_full_prompts": "c601367b0f164b10", "hash_input_tokens": "e819bbb85d31132d", "hash_cont_tokens": "0b20dadf79c1a231" }, "truncated": 0, "non_truncated": 10042, "padded": 39847, "non_padded": 321, "num_truncated_few_shots": 0 } }