{
  "architecture": {
    "data": "datasets/synthetic-v1",
    "output": "models/v000-mean",
    "encoder": "mean",
    "no_lexical": false,
    "epochs": 16,
    "width": 64,
    "seed": 1729
  },
  "parameter_count": 128900,
  "threads": 2,
  "device": "cpu",
  "training_seconds": 12.39197339990642,
  "dataset_manifest": {
    "train": {
      "count": 2400,
      "seed": 101,
      "templates": [
        "fieldset",
        "grid",
        "stack"
      ],
      "sha256": "3f24899383d914465232cfaac27f654eae7217ed3fb37894cf07e551120c56e5"
    },
    "validation": {
      "count": 480,
      "seed": 202,
      "templates": [
        "fieldset",
        "grid",
        "stack"
      ],
      "sha256": "1cf777e5703257e3471c3f67b2e421fd3de505de429fbf57223f452648c477a8"
    },
    "test": {
      "count": 480,
      "seed": 303,
      "templates": [
        "nested",
        "table"
      ],
      "sha256": "849ccce76126296a01ee5ef756f2790470dea0e87fad94802d66c6e43fee20ac"
    },
    "novel_wording": {
      "count": 480,
      "seed": 404,
      "templates": [
        "nested",
        "table"
      ],
      "sha256": "8b467567370321ad5fbe604b282b89de6ceaaa4b679621fa0f3685708fa6e1c2"
    },
    "limitations": "Single-step generated tasks; test layouts held out but vocabulary shared. No arbitrary-site claim."
  },
  "history": [
    {
      "epoch": 1,
      "loss": 1.7651557216518803,
      "validation": {
        "samples": 480,
        "action_accuracy": 0.9937499761581421,
        "target_accuracy": 0.9979166388511658,
        "joint_step_accuracy": 0.9916666746139526,
        "action_ece": 0.2162406847346574,
        "target_ece": 0.05524349887855351,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 2,
      "loss": 0.10179991137824561,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.021068825386464596,
        "target_ece": 0.014485297608189285,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 3,
      "loss": 0.018946192423371894,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.009046673774719238,
        "target_ece": 0.009317956049926579,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 4,
      "loss": 0.010617268835439495,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.0054672956466674805,
        "target_ece": 0.006611444754526019,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 5,
      "loss": 0.007092831405124774,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.0039865970611572266,
        "target_ece": 0.0050632000202313066,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 6,
      "loss": 0.005264362638914271,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.0029689669609069824,
        "target_ece": 0.00398828461766243,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 7,
      "loss": 0.004050923848377639,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.002372443675994873,
        "target_ece": 0.0031936721643432975,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 8,
      "loss": 0.003259014102360724,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.0018841028213500977,
        "target_ece": 0.002662156126461923,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 9,
      "loss": 0.002767322266376332,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.001614987850189209,
        "target_ece": 0.002215902553871274,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 10,
      "loss": 0.002234648154913693,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.001338183879852295,
        "target_ece": 0.001958910725079477,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 11,
      "loss": 0.00194322145743124,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.0011820197105407715,
        "target_ece": 0.0016488697146996856,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 12,
      "loss": 0.0016326695990037958,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.0010241270065307617,
        "target_ece": 0.0014443512918660417,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 13,
      "loss": 0.001446679870193628,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.0009126663208007812,
        "target_ece": 0.0012873411178588867,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 14,
      "loss": 0.001253041722137775,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.000838935375213623,
        "target_ece": 0.0011112093925476074,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 15,
      "loss": 0.001146693759150558,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.0007374286651611328,
        "target_ece": 0.0010060667991638184,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 16,
      "loss": 0.000992622820807523,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.0006838440895080566,
        "target_ece": 0.0008993744850158691,
        "candidate_recall": 1.0
      }
    }
  ],
  "evaluation": {
    "validation": {
      "samples": 480,
      "action_accuracy": 1.0,
      "target_accuracy": 1.0,
      "joint_step_accuracy": 1.0,
      "action_ece": 0.0,
      "target_ece": 2.86102294921875e-06,
      "candidate_recall": 1.0
    },
    "test": {
      "samples": 480,
      "action_accuracy": 1.0,
      "target_accuracy": 1.0,
      "joint_step_accuracy": 1.0,
      "action_ece": 0.0,
      "target_ece": 6.4373016357421875e-06,
      "candidate_recall": 1.0
    },
    "novel_wording": {
      "samples": 480,
      "action_accuracy": 0.574999988079071,
      "target_accuracy": 0.9208333492279053,
      "joint_step_accuracy": 0.5583333373069763,
      "action_ece": 0.418779332539998,
      "target_ece": 0.06966802896931767,
      "candidate_recall": 1.0
    }
  },
  "limitations": "Synthetic single-step action/target prediction; not arbitrary-site task success.",
  "production_promoted": false
}