{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 76498.369638914, "end_time": 77168.209755496, "total_evaluation_time_secondes": "669.8401165820105", "model_name": "HuggingFaceH4/mistral-7b-ift", "model_sha": "5c89cda93fe538e3c4d965998cfa7e606fa1f0f5", "model_dtype": "torch.bfloat16", "model_size": "13.99 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.39186691312384475, "prompt_level_strict_acc_stderr": 0.021007372406188347, "inst_level_strict_acc": 0.4892086330935252, "inst_level_strict_acc_stderr": 0.0005370057284818438, "prompt_level_loose_acc": 0.43068391866913125, "prompt_level_loose_acc_stderr": 0.021308808857898928, "inst_level_loose_acc": 0.5359712230215827, "inst_level_loose_acc_stderr": 0.0005286296286804733 } }, "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": "46932ca113ba6b0c", "hash_input_tokens": "8b2e0300fbfb70bc", "hash_cont_tokens": "af884daffbcc2801" }, "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": "8ed52f7b74eb0590", "hash_input_tokens": "9f4b7e9e7ff95d4a", "hash_cont_tokens": "6885021d5213e4e5" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }