{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 1241227.484189211, "end_time": 1241772.943003077, "total_evaluation_time_secondes": "545.4588138661347", "model_name": "meta-llama/Llama-2-7b-chat-hf", "model_sha": "c1b0db933684edbfe29a06fa47eb19cc48025e93", "model_dtype": "torch.bfloat16", "model_size": "12.62 GB", "config": null }, "results": { "lighteval|hellaswag|10": { "acc": 0.5252937661820355, "acc_stderr": 0.004983392650570961, "acc_norm": 0.6645090619398526, "acc_norm_stderr": 0.004711968379069027 } }, "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": "6104833828ff575a", "hash_input_tokens": "5027c68d3297b1e8", "hash_cont_tokens": "ae402a85d6dcc6db" }, "truncated": 0, "non_truncated": 10042, "padded": 39998, "non_padded": 170, "effective_few_shots": 10.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "63bc2cf8bae03fbc", "hash_full_prompts": "da2873b4d522a102", "hash_input_tokens": "4ae6d8a7bf354d03", "hash_cont_tokens": "24deb3b55a6388c3" }, "truncated": 0, "non_truncated": 10042, "padded": 39998, "non_padded": 170, "num_truncated_few_shots": 0 } }