{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 870053.49817877, "end_time": 870644.004147917, "total_evaluation_time_secondes": "590.5059691470815", "model_name": "alignment-handbook/zephyr-2b-gemma-dpo-v2.3", "model_sha": "05de867ca01a6e052ba25674971a5520f440d22e", "model_dtype": "torch.bfloat16", "model_size": "4.68 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.2144177449168207, "prompt_level_strict_acc_stderr": 0.017661570312173927, "inst_level_strict_acc": 0.3657074340527578, "inst_level_strict_acc_stderr": 0.000493889332806223, "prompt_level_loose_acc": 0.2365988909426987, "prompt_level_loose_acc_stderr": 0.01828882758262565, "inst_level_loose_acc": 0.381294964028777, "inst_level_loose_acc_stderr": 0.0005081550108021382 } }, "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": "7ea7bf2a8edba8f4", "hash_input_tokens": "89df3fff41e770ad", "hash_cont_tokens": "5c4144bb996269a0" }, "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": "45f8422f6ad2da79", "hash_input_tokens": "917957472cc73e8e", "hash_cont_tokens": "bdbbfcd0ed4d4173" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }