{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 6592934.51856476, "end_time": 6600969.205609469, "total_evaluation_time_secondes": "8034.68704470899", "model_name": "deepseek-ai/deepseek-llm-67b-chat", "model_sha": "79648bef7658bb824e4630740f6e1484c1b0620b", "model_dtype": "torch.bfloat16", "model_size": "125.78 GB", "config": null }, "results": { "lighteval|hellaswag|10": { "acc": 0.6544513045210117, "acc_stderr": 0.004745749538752324, "acc_norm": 0.8393746265684127, "acc_norm_stderr": 0.0036643462998943964 } }, "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": "b36c4a85aa08e9de", "hash_input_tokens": "3bde4fe5a0346fa1", "hash_cont_tokens": "fc902c8630a1e07b" }, "truncated": 0, "non_truncated": 10042, "padded": 39945, "non_padded": 223, "effective_few_shots": 10.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "63bc2cf8bae03fbc", "hash_full_prompts": "55e29d94e2f2f228", "hash_input_tokens": "ebaa5ce12ff66f7e", "hash_cont_tokens": "c4b4d15ab4a54c66" }, "truncated": 0, "non_truncated": 10042, "padded": 39945, "non_padded": 223, "num_truncated_few_shots": 0 } }