{ "base_sha256": "71330800b6de065580e9d7341399d451547f9a7e1eb4220ceba9ed00c4c50e6b", "baseline": { "correct": 4, "mean_cross_entropy": 0.710581, "predictions": [ { "expected": "deployment", "id": "heldout-1", "predicted": "deployment" }, { "expected": "deployment", "id": "heldout-2", "predicted": "deployment" }, { "expected": "deployment", "id": "heldout-3", "predicted": "deployment" }, { "expected": "rollback", "id": "heldout-4", "predicted": "deployment" }, { "expected": "rollback", "id": "heldout-5", "predicted": "deployment" }, { "expected": "rollback", "id": "heldout-6", "predicted": "deployment" }, { "expected": "credentials", "id": "heldout-7", "predicted": "deployment" }, { "expected": "credentials", "id": "heldout-8", "predicted": "deployment" }, { "expected": "credentials", "id": "heldout-9", "predicted": "credentials" } ], "total": 9 }, "epochs": 200, "evaluation_feature_duplicates": 0, "heldout_sha256": "46bac3b951adb5f015d8bc748d547a6832fd22bf5db4abfed71678de29d5a289", "learning_rate": 0.12, "results": { "full": { "base_unchanged": true, "heldout": { "correct": 9, "mean_cross_entropy": 0.086381, "predictions": [ { "expected": "deployment", "id": "heldout-1", "predicted": "deployment" }, { "expected": "deployment", "id": "heldout-2", "predicted": "deployment" }, { "expected": "deployment", "id": "heldout-3", "predicted": "deployment" }, { "expected": "rollback", "id": "heldout-4", "predicted": "rollback" }, { "expected": "rollback", "id": "heldout-5", "predicted": "rollback" }, { "expected": "rollback", "id": "heldout-6", "predicted": "rollback" }, { "expected": "credentials", "id": "heldout-7", "predicted": "credentials" }, { "expected": "credentials", "id": "heldout-8", "predicted": "credentials" }, { "expected": "credentials", "id": "heldout-9", "predicted": "credentials" } ], "total": 9 }, "train": { "correct": 12, "mean_cross_entropy": 0.016239, "predictions": [ { "expected": "deployment", "id": "train-1", "predicted": "deployment" }, { "expected": "deployment", "id": "train-2", "predicted": "deployment" }, { "expected": "deployment", "id": "train-3", "predicted": "deployment" }, { "expected": "rollback", "id": "train-4", "predicted": "rollback" }, { "expected": "rollback", "id": "train-5", "predicted": "rollback" }, { "expected": "rollback", "id": "train-6", "predicted": "rollback" }, { "expected": "rollback", "id": "train-7", "predicted": "rollback" }, { "expected": "credentials", "id": "train-8", "predicted": "credentials" }, { "expected": "credentials", "id": "train-9", "predicted": "credentials" }, { "expected": "credentials", "id": "train-10", "predicted": "credentials" }, { "expected": "credentials", "id": "train-11", "predicted": "credentials" }, { "expected": "credentials", "id": "train-12", "predicted": "credentials" } ], "total": 12 }, "trainable_parameters": 30 }, "lora_rank_1": { "base_unchanged": true, "heldout": { "correct": 9, "mean_cross_entropy": 0.115805, "predictions": [ { "expected": "deployment", "id": "heldout-1", "predicted": "deployment" }, { "expected": "deployment", "id": "heldout-2", "predicted": "deployment" }, { "expected": "deployment", "id": "heldout-3", "predicted": "deployment" }, { "expected": "rollback", "id": "heldout-4", "predicted": "rollback" }, { "expected": "rollback", "id": "heldout-5", "predicted": "rollback" }, { "expected": "rollback", "id": "heldout-6", "predicted": "rollback" }, { "expected": "credentials", "id": "heldout-7", "predicted": "credentials" }, { "expected": "credentials", "id": "heldout-8", "predicted": "credentials" }, { "expected": "credentials", "id": "heldout-9", "predicted": "credentials" } ], "total": 9 }, "train": { "correct": 12, "mean_cross_entropy": 0.06405, "predictions": [ { "expected": "deployment", "id": "train-1", "predicted": "deployment" }, { "expected": "deployment", "id": "train-2", "predicted": "deployment" }, { "expected": "deployment", "id": "train-3", "predicted": "deployment" }, { "expected": "rollback", "id": "train-4", "predicted": "rollback" }, { "expected": "rollback", "id": "train-5", "predicted": "rollback" }, { "expected": "rollback", "id": "train-6", "predicted": "rollback" }, { "expected": "rollback", "id": "train-7", "predicted": "rollback" }, { "expected": "credentials", "id": "train-8", "predicted": "credentials" }, { "expected": "credentials", "id": "train-9", "predicted": "credentials" }, { "expected": "credentials", "id": "train-10", "predicted": "credentials" }, { "expected": "credentials", "id": "train-11", "predicted": "credentials" }, { "expected": "credentials", "id": "train-12", "predicted": "credentials" } ], "total": 12 }, "trainable_parameters": 13 }, "lora_rank_2": { "base_unchanged": true, "heldout": { "correct": 9, "mean_cross_entropy": 0.027204, "predictions": [ { "expected": "deployment", "id": "heldout-1", "predicted": "deployment" }, { "expected": "deployment", "id": "heldout-2", "predicted": "deployment" }, { "expected": "deployment", "id": "heldout-3", "predicted": "deployment" }, { "expected": "rollback", "id": "heldout-4", "predicted": "rollback" }, { "expected": "rollback", "id": "heldout-5", "predicted": "rollback" }, { "expected": "rollback", "id": "heldout-6", "predicted": "rollback" }, { "expected": "credentials", "id": "heldout-7", "predicted": "credentials" }, { "expected": "credentials", "id": "heldout-8", "predicted": "credentials" }, { "expected": "credentials", "id": "heldout-9", "predicted": "credentials" } ], "total": 9 }, "train": { "correct": 12, "mean_cross_entropy": 0.001077, "predictions": [ { "expected": "deployment", "id": "train-1", "predicted": "deployment" }, { "expected": "deployment", "id": "train-2", "predicted": "deployment" }, { "expected": "deployment", "id": "train-3", "predicted": "deployment" }, { "expected": "rollback", "id": "train-4", "predicted": "rollback" }, { "expected": "rollback", "id": "train-5", "predicted": "rollback" }, { "expected": "rollback", "id": "train-6", "predicted": "rollback" }, { "expected": "rollback", "id": "train-7", "predicted": "rollback" }, { "expected": "credentials", "id": "train-8", "predicted": "credentials" }, { "expected": "credentials", "id": "train-9", "predicted": "credentials" }, { "expected": "credentials", "id": "train-10", "predicted": "credentials" }, { "expected": "credentials", "id": "train-11", "predicted": "credentials" }, { "expected": "credentials", "id": "train-12", "predicted": "credentials" } ], "total": 12 }, "trainable_parameters": 26 } }, "seed": 31, "task": "small bag-of-words intent classifier; not a pretrained LLM", "train_sha256": "f7da4b0b5143f626465d1c7911908871c9f41bf20fa20cdff078bffa413aeb2a" }