{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 1707040.484343151, "end_time": 1707598.834166149, "total_evaluation_time_secondes": "558.349822997814", "model_name": "Qwen/Qwen1.5-1.8B-Chat", "model_sha": "3aede71902ad578aac72678f9f8b6199ca6ab53b", "model_dtype": "torch.bfloat16", "model_size": "3.8 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.1645101663585952, "prompt_level_strict_acc_stderr": 0.015954017926718037, "inst_level_strict_acc": 0.27218225419664266, "inst_level_strict_acc_stderr": 0.000500744307898394, "prompt_level_loose_acc": 0.18853974121996303, "prompt_level_loose_acc_stderr": 0.016832096060176906, "inst_level_loose_acc": 0.2973621103117506, "inst_level_loose_acc_stderr": 0.0005238430230470437 } }, "versions": { "custom|ifeval|0": 0 }, "config_tasks": { "custom|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": [ "custom" ], "original_num_docs": 541, "effective_num_docs": 541 } }, "summary_tasks": { "custom|ifeval|0": { "hashes": { "hash_examples": "e99cbf567588d7c6", "hash_full_prompts": "1d8bccd45ca3707b", "hash_input_tokens": "4aede348bfb0e38d", "hash_cont_tokens": "aa9a5e3f3d7eacf9" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "effective_few_shots": 0.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "ea046ab2c6fc5928", "hash_full_prompts": "41a5572cc1263dc7", "hash_input_tokens": "dc284e5de619e6a7", "hash_cont_tokens": "4d51f0d66da20a0f" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }