{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 7285.668073205, "end_time": 7870.174226571, "total_evaluation_time_secondes": "584.506153366", "model_name": "lewtun/zephyr-2b-gemma-sft-mix4", "model_sha": "a451b8601d489b76c3e1f63a74bbfbebf2e3017c", "model_dtype": "torch.bfloat16", "model_size": "4.68 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.2088724584103512, "prompt_level_strict_acc_stderr": 0.01749310734779332, "inst_level_strict_acc": 0.34532374100719426, "inst_level_strict_acc_stderr": 0.00048583277330137026, "prompt_level_loose_acc": 0.2255083179297597, "prompt_level_loose_acc_stderr": 0.017984268664495595, "inst_level_loose_acc": 0.35851318944844124, "inst_level_loose_acc_stderr": 0.0004869762794365826 } }, "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": "8573f6eab8d56eef" }, "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": "98199091a6acc90c" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }