{
  "seed": 20261027,
  "parameters": 485,
  "epochs_executed": 2000,
  "selected_epoch": 2000,
  "selection": "Minimum development loss; test states excluded from training and selection.",
  "train_seconds": 0.589,
  "dataset_sha256": "cd77d8e741510791f9dfa8b1106dc4ebab2379c32eef1e017d90551f69e69ea4",
  "trainer_sha256": "65a3e474c0e18a1f33a1743285c44668632d070e2dc28a8e406a52a2ed33ea44",
  "model_sha256": "68e3854b256c2059a99258cf486a35015b198f30bc749d53f15883ea14a5fe02",
  "split": {
    "train": [
      3,
      28,
      58,
      17,
      5,
      71,
      69,
      48,
      15,
      55,
      57,
      30,
      27,
      40,
      45,
      43,
      1,
      36,
      62,
      32,
      70,
      4,
      12,
      56,
      24,
      0,
      50,
      46,
      29,
      6,
      10,
      51,
      33,
      65,
      20,
      9,
      26,
      78,
      13,
      34,
      76,
      52,
      79,
      53,
      21,
      14,
      22,
      23,
      41,
      59,
      7,
      18,
      72,
      66,
      60,
      68,
      61,
      74,
      49,
      25,
      63,
      11,
      73,
      42
    ],
    "dev": [
      35,
      38,
      54,
      2,
      64,
      67,
      47,
      37
    ],
    "test": [
      75,
      19,
      31,
      16,
      39,
      77,
      8,
      44
    ]
  },
  "metrics": {
    "untrained": {
      "train": {
        "correct": 26,
        "total": 64,
        "unsafe_actions": 19
      },
      "dev": {
        "correct": 2,
        "total": 8,
        "unsafe_actions": 1
      },
      "test": {
        "correct": 3,
        "total": 8,
        "unsafe_actions": 4
      },
      "exhaustive": {
        "correct": 31,
        "total": 80,
        "unsafe_actions": 24
      }
    },
    "trained": {
      "train": {
        "correct": 64,
        "total": 64,
        "unsafe_actions": 0
      },
      "dev": {
        "correct": 8,
        "total": 8,
        "unsafe_actions": 0
      },
      "test": {
        "correct": 8,
        "total": 8,
        "unsafe_actions": 0
      },
      "exhaustive": {
        "correct": 80,
        "total": 80,
        "unsafe_actions": 0
      }
    }
  },
  "history": [
    {
      "epoch": 1,
      "loss": 1.4768440661237996,
      "dev_loss": 1.3901131042263035
    },
    {
      "epoch": 25,
      "loss": 0.22175550457653392,
      "dev_loss": 0.3746721601320776
    },
    {
      "epoch": 50,
      "loss": 0.03088207332494298,
      "dev_loss": 0.0736195600225193
    },
    {
      "epoch": 75,
      "loss": 0.010070582153108092,
      "dev_loss": 0.026290774787605296
    },
    {
      "epoch": 100,
      "loss": 0.005691863199109577,
      "dev_loss": 0.01642813541133887
    },
    {
      "epoch": 125,
      "loss": 0.0038393561900367888,
      "dev_loss": 0.011470883892664754
    },
    {
      "epoch": 150,
      "loss": 0.002735779917673301,
      "dev_loss": 0.008456014787691087
    },
    {
      "epoch": 175,
      "loss": 0.0020590852104891413,
      "dev_loss": 0.006452336317440586
    },
    {
      "epoch": 200,
      "loss": 0.0016215589607575564,
      "dev_loss": 0.005215893115086606
    },
    {
      "epoch": 225,
      "loss": 0.001316532125690471,
      "dev_loss": 0.004365454160646759
    },
    {
      "epoch": 250,
      "loss": 0.001094009005148275,
      "dev_loss": 0.0037262709557206505
    },
    {
      "epoch": 275,
      "loss": 0.0009264048650033586,
      "dev_loss": 0.0032347027183563743
    },
    {
      "epoch": 300,
      "loss": 0.000795887948742699,
      "dev_loss": 0.0028424939218948094
    },
    {
      "epoch": 325,
      "loss": 0.0006916126605349658,
      "dev_loss": 0.0025262850566118407
    },
    {
      "epoch": 350,
      "loss": 0.0006070951695462364,
      "dev_loss": 0.002266977190544736
    },
    {
      "epoch": 375,
      "loss": 0.0005375794866634399,
      "dev_loss": 0.0020590840769053012
    },
    {
      "epoch": 400,
      "loss": 0.0004797477348364858,
      "dev_loss": 0.0018834280819274058
    },
    {
      "epoch": 425,
      "loss": 0.000431074186973584,
      "dev_loss": 0.0017316213692755082
    },
    {
      "epoch": 450,
      "loss": 0.0003896659270489219,
      "dev_loss": 0.0016008563628628755
    },
    {
      "epoch": 475,
      "loss": 0.00035403873426153687,
      "dev_loss": 0.0014872237010838622
    },
    {
      "epoch": 500,
      "loss": 0.00032319989871115186,
      "dev_loss": 0.001385494454454445
    },
    {
      "epoch": 525,
      "loss": 0.00029629648137570566,
      "dev_loss": 0.0012950531306579957
    },
    {
      "epoch": 550,
      "loss": 0.00027268498924976764,
      "dev_loss": 0.0012151457210301557
    },
    {
      "epoch": 575,
      "loss": 0.0002518219068739324,
      "dev_loss": 0.0011426298917815239
    },
    {
      "epoch": 600,
      "loss": 0.0002332811458037489,
      "dev_loss": 0.001077941816323998
    },
    {
      "epoch": 625,
      "loss": 0.00021670455303139793,
      "dev_loss": 0.001019070990023181
    },
    {
      "epoch": 650,
      "loss": 0.000201853604829002,
      "dev_loss": 0.00096452684466085
    },
    {
      "epoch": 675,
      "loss": 0.00018848914312671574,
      "dev_loss": 0.0009147054564529642
    },
    {
      "epoch": 700,
      "loss": 0.0001764188491020715,
      "dev_loss": 0.0008694990332488552
    },
    {
      "epoch": 725,
      "loss": 0.0001654788677513443,
      "dev_loss": 0.0008277228314507248
    },
    {
      "epoch": 750,
      "loss": 0.0001555340648286737,
      "dev_loss": 0.0007890006960101973
    },
    {
      "epoch": 775,
      "loss": 0.000146458830782964,
      "dev_loss": 0.0007534927467848875
    },
    {
      "epoch": 800,
      "loss": 0.00013815610642196923,
      "dev_loss": 0.0007203733291841893
    },
    {
      "epoch": 825,
      "loss": 0.00013053938057328864,
      "dev_loss": 0.0006899658995609425
    },
    {
      "epoch": 850,
      "loss": 0.00012353256133494682,
      "dev_loss": 0.0006615913998892078
    },
    {
      "epoch": 875,
      "loss": 0.00011707203321712308,
      "dev_loss": 0.0006347500436670318
    },
    {
      "epoch": 900,
      "loss": 0.0001111117345723799,
      "dev_loss": 0.0006099433137827053
    },
    {
      "epoch": 925,
      "loss": 0.00010560422566781522,
      "dev_loss": 0.0005862683063670847
    },
    {
      "epoch": 950,
      "loss": 0.00010049338443700107,
      "dev_loss": 0.000564238985743988
    },
    {
      "epoch": 975,
      "loss": 9.573909838826695e-05,
      "dev_loss": 0.000543696701752529
    },
    {
      "epoch": 1000,
      "loss": 9.1307409527737e-05,
      "dev_loss": 0.0005239801121006316
    },
    {
      "epoch": 1025,
      "loss": 8.717169006445989e-05,
      "dev_loss": 0.0005057333535120089
    },
    {
      "epoch": 1050,
      "loss": 8.330895792176322e-05,
      "dev_loss": 0.00048811680700342505
    },
    {
      "epoch": 1075,
      "loss": 7.969368867095808e-05,
      "dev_loss": 0.00047153867321573324
    },
    {
      "epoch": 1100,
      "loss": 7.629827645943139e-05,
      "dev_loss": 0.00045616619328171803
    },
    {
      "epoch": 1125,
      "loss": 7.31098805968974e-05,
      "dev_loss": 0.00044097096182414865
    },
    {
      "epoch": 1150,
      "loss": 7.010989074730418e-05,
      "dev_loss": 0.00042698343996800563
    },
    {
      "epoch": 1175,
      "loss": 6.728699192247895e-05,
      "dev_loss": 0.00041350577524311183
    },
    {
      "epoch": 1200,
      "loss": 6.46244024869075e-05,
      "dev_loss": 0.000400855076011069
    },
    {
      "epoch": 1225,
      "loss": 6.211191183485949e-05,
      "dev_loss": 0.00038875270455785056
    },
    {
      "epoch": 1250,
      "loss": 5.97401254169804e-05,
      "dev_loss": 0.0003773006651232755
    },
    {
      "epoch": 1275,
      "loss": 5.749589145492439e-05,
      "dev_loss": 0.00036645735199996264
    },
    {
      "epoch": 1300,
      "loss": 5.537159643121884e-05,
      "dev_loss": 0.00035603365030035047
    },
    {
      "epoch": 1325,
      "loss": 5.335789611764419e-05,
      "dev_loss": 0.0003461314371390591
    },
    {
      "epoch": 1350,
      "loss": 5.144782170937293e-05,
      "dev_loss": 0.00033648481921423287
    },
    {
      "epoch": 1375,
      "loss": 4.963419087443882e-05,
      "dev_loss": 0.00032737458845419635
    },
    {
      "epoch": 1400,
      "loss": 4.790986834913864e-05,
      "dev_loss": 0.00031859313227952104
    },
    {
      "epoch": 1425,
      "loss": 4.626998144227592e-05,
      "dev_loss": 0.00031028486770629925
    },
    {
      "epoch": 1450,
      "loss": 4.470821393072366e-05,
      "dev_loss": 0.00030228515211987725
    },
    {
      "epoch": 1475,
      "loss": 4.322059995552455e-05,
      "dev_loss": 0.00029442308968611166
    },
    {
      "epoch": 1500,
      "loss": 4.180204043153089e-05,
      "dev_loss": 0.00028706669532212897
    },
    {
      "epoch": 1525,
      "loss": 4.044765115696025e-05,
      "dev_loss": 0.00027994841746296884
    },
    {
      "epoch": 1550,
      "loss": 3.9154953998919445e-05,
      "dev_loss": 0.00027322118846876716
    },
    {
      "epoch": 1575,
      "loss": 3.7919163363985846e-05,
      "dev_loss": 0.000266600035020789
    },
    {
      "epoch": 1600,
      "loss": 3.6737558335669064e-05,
      "dev_loss": 0.0002602518021159247
    },
    {
      "epoch": 1625,
      "loss": 3.56072235474996e-05,
      "dev_loss": 0.0002541272217246045
    },
    {
      "epoch": 1650,
      "loss": 3.452418509786438e-05,
      "dev_loss": 0.00024835112727507466
    },
    {
      "epoch": 1675,
      "loss": 3.348713501044306e-05,
      "dev_loss": 0.00024263200295144248
    },
    {
      "epoch": 1700,
      "loss": 3.2489450690962056e-05,
      "dev_loss": 0.00023741693354149964
    },
    {
      "epoch": 1725,
      "loss": 3.151907299315299e-05,
      "dev_loss": 0.00023364681456121804
    },
    {
      "epoch": 1750,
      "loss": 3.0585787302462135e-05,
      "dev_loss": 0.00023025375634607527
    },
    {
      "epoch": 1775,
      "loss": 2.9691764936742624e-05,
      "dev_loss": 0.00022689643171838793
    },
    {
      "epoch": 1800,
      "loss": 2.8834475848758185e-05,
      "dev_loss": 0.00022347317947771608
    },
    {
      "epoch": 1825,
      "loss": 2.8012864983334696e-05,
      "dev_loss": 0.00022027732042613065
    },
    {
      "epoch": 1850,
      "loss": 2.7223847722966822e-05,
      "dev_loss": 0.0002170169125828924
    },
    {
      "epoch": 1875,
      "loss": 2.6466025759196202e-05,
      "dev_loss": 0.00021379098685931204
    },
    {
      "epoch": 1900,
      "loss": 2.5736509705879045e-05,
      "dev_loss": 0.00021070516433010575
    },
    {
      "epoch": 1925,
      "loss": 2.503544251631462e-05,
      "dev_loss": 0.00020757570844962486
    },
    {
      "epoch": 1950,
      "loss": 2.436078846578258e-05,
      "dev_loss": 0.00020444520361650648
    },
    {
      "epoch": 1975,
      "loss": 2.3711234051349316e-05,
      "dev_loss": 0.0002012968800037696
    },
    {
      "epoch": 2000,
      "loss": 2.3084937556070717e-05,
      "dev_loss": 0.00019833017311970155
    }
  ],
  "limits": "80 discrete local states, not vision, language modelling or continuous robotics."
}