{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 1163608.425196265, "end_time": 1173616.769654949, "total_evaluation_time_secondes": "10008.34445868386", "model_name": "databricks/dbrx-instruct", "model_sha": "464e701f50aef4c1b59c81fb5667819a5d08e108", "model_dtype": "torch.bfloat16", "model_size": "245.12 GB", "config": null }, "results": { "extended|ifeval|0": { "prompt_level_strict_acc": 0.4676524953789279, "prompt_level_strict_acc_stderr": 0.021471498720517193, "inst_level_strict_acc": 0.5827338129496403, "inst_level_strict_acc_stderr": 0.0005426412268373989, "prompt_level_loose_acc": 0.5212569316081331, "prompt_level_loose_acc_stderr": 0.021497120515987747, "inst_level_loose_acc": 0.6366906474820144, "inst_level_loose_acc_stderr": 0.0005192825502082345 } }, "versions": { "extended|ifeval|0": 0 }, "config_tasks": { "extended|ifeval": { "name": "ifeval", "prompt_function": "ifeval_prompt", "hf_repo": "wis-k/instruction-following-eval", "hf_subset": "default", "metric": [ "ifeval_metric" ], "hf_avail_splits": [ "train" ], "evaluation_splits": [ "train" ], "few_shots_split": "train", "few_shots_select": "random_sampling", "generation_size": 1280, "stop_sequence": [], "output_regex": null, "frozen": false, "suite": [ "extended" ], "original_num_docs": 541, "effective_num_docs": 541, "trust_dataset": null, "must_remove_duplicate_docs": null } }, "summary_tasks": { "extended|ifeval|0": { "hashes": { "hash_examples": "e99cbf567588d7c6", "hash_full_prompts": "6a2c6e35df691ba3", "hash_input_tokens": "392a26e72e56230b", "hash_cont_tokens": "59a09c165cc80a40" }, "truncated": 541, "non_truncated": 0, "padded": 108, "non_padded": 433, "effective_few_shots": 0.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "ea046ab2c6fc5928", "hash_full_prompts": "853afd6c0bbf0c6f", "hash_input_tokens": "238a6c196c7ffc29", "hash_cont_tokens": "6cb715a2af9e4b00" }, "truncated": 541, "non_truncated": 0, "padded": 108, "non_padded": 433, "num_truncated_few_shots": 0 } }