{
  "best_metric": 1.0,
  "best_model_checkpoint": "deit-base-distilled-patch16-224-hasta-75-fold1/checkpoint-17",
  "epoch": 100.0,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4166666666666667,
      "eval_loss": 1.0838725566864014,
      "eval_runtime": 0.1691,
      "eval_samples_per_second": 70.976,
      "eval_steps_per_second": 5.915,
      "step": 1
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_loss": 0.8911231160163879,
      "eval_runtime": 0.1696,
      "eval_samples_per_second": 70.757,
      "eval_steps_per_second": 5.896,
      "step": 2
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.75,
      "eval_loss": 0.5836748480796814,
      "eval_runtime": 0.1676,
      "eval_samples_per_second": 71.579,
      "eval_steps_per_second": 5.965,
      "step": 3
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.34806403517723083,
      "eval_runtime": 0.1645,
      "eval_samples_per_second": 72.934,
      "eval_steps_per_second": 6.078,
      "step": 4
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.2815200686454773,
      "eval_runtime": 0.164,
      "eval_samples_per_second": 73.162,
      "eval_steps_per_second": 6.097,
      "step": 5
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.28391170501708984,
      "eval_runtime": 0.1402,
      "eval_samples_per_second": 85.569,
      "eval_steps_per_second": 7.131,
      "step": 6
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.2837619185447693,
      "eval_runtime": 0.1695,
      "eval_samples_per_second": 70.809,
      "eval_steps_per_second": 5.901,
      "step": 7
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.26923567056655884,
      "eval_runtime": 0.1682,
      "eval_samples_per_second": 71.361,
      "eval_steps_per_second": 5.947,
      "step": 8
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.27014538645744324,
      "eval_runtime": 0.159,
      "eval_samples_per_second": 75.493,
      "eval_steps_per_second": 6.291,
      "step": 9
    },
    {
      "epoch": 10.0,
      "grad_norm": 1.2129414081573486,
      "learning_rate": 5e-05,
      "loss": 0.3107,
      "step": 10
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.33633777499198914,
      "eval_runtime": 0.1692,
      "eval_samples_per_second": 70.904,
      "eval_steps_per_second": 5.909,
      "step": 10
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.38160809874534607,
      "eval_runtime": 0.1738,
      "eval_samples_per_second": 69.048,
      "eval_steps_per_second": 5.754,
      "step": 11
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.3427475392818451,
      "eval_runtime": 0.1732,
      "eval_samples_per_second": 69.302,
      "eval_steps_per_second": 5.775,
      "step": 12
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.27277496457099915,
      "eval_runtime": 0.1761,
      "eval_samples_per_second": 68.13,
      "eval_steps_per_second": 5.677,
      "step": 13
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.22727306187152863,
      "eval_runtime": 0.1733,
      "eval_samples_per_second": 69.232,
      "eval_steps_per_second": 5.769,
      "step": 14
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.20517520606517792,
      "eval_runtime": 0.1738,
      "eval_samples_per_second": 69.061,
      "eval_steps_per_second": 5.755,
      "step": 15
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.18395300209522247,
      "eval_runtime": 0.1698,
      "eval_samples_per_second": 70.673,
      "eval_steps_per_second": 5.889,
      "step": 16
    },
    {
      "epoch": 17.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.19073201715946198,
      "eval_runtime": 0.172,
      "eval_samples_per_second": 69.748,
      "eval_steps_per_second": 5.812,
      "step": 17
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.17612700164318085,
      "eval_runtime": 0.1704,
      "eval_samples_per_second": 70.428,
      "eval_steps_per_second": 5.869,
      "step": 18
    },
    {
      "epoch": 19.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.13020874559879303,
      "eval_runtime": 0.1765,
      "eval_samples_per_second": 67.981,
      "eval_steps_per_second": 5.665,
      "step": 19
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.7908862829208374,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.1503,
      "step": 20
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.09369927644729614,
      "eval_runtime": 0.1701,
      "eval_samples_per_second": 70.561,
      "eval_steps_per_second": 5.88,
      "step": 20
    },
    {
      "epoch": 21.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.07672286778688431,
      "eval_runtime": 0.1649,
      "eval_samples_per_second": 72.764,
      "eval_steps_per_second": 6.064,
      "step": 21
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0641578882932663,
      "eval_runtime": 0.1749,
      "eval_samples_per_second": 68.596,
      "eval_steps_per_second": 5.716,
      "step": 22
    },
    {
      "epoch": 23.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0730399563908577,
      "eval_runtime": 0.1666,
      "eval_samples_per_second": 72.022,
      "eval_steps_per_second": 6.002,
      "step": 23
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0937485471367836,
      "eval_runtime": 0.1714,
      "eval_samples_per_second": 70.03,
      "eval_steps_per_second": 5.836,
      "step": 24
    },
    {
      "epoch": 25.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.07131379097700119,
      "eval_runtime": 0.1686,
      "eval_samples_per_second": 71.16,
      "eval_steps_per_second": 5.93,
      "step": 25
    },
    {
      "epoch": 26.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0475582480430603,
      "eval_runtime": 0.1744,
      "eval_samples_per_second": 68.813,
      "eval_steps_per_second": 5.734,
      "step": 26
    },
    {
      "epoch": 27.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.04617106541991234,
      "eval_runtime": 0.1731,
      "eval_samples_per_second": 69.315,
      "eval_steps_per_second": 5.776,
      "step": 27
    },
    {
      "epoch": 28.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.05526432394981384,
      "eval_runtime": 0.1758,
      "eval_samples_per_second": 68.273,
      "eval_steps_per_second": 5.689,
      "step": 28
    },
    {
      "epoch": 29.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.06893330812454224,
      "eval_runtime": 0.1778,
      "eval_samples_per_second": 67.474,
      "eval_steps_per_second": 5.623,
      "step": 29
    },
    {
      "epoch": 30.0,
      "grad_norm": 1.3284376859664917,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.068,
      "step": 30
    },
    {
      "epoch": 30.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.06763923913240433,
      "eval_runtime": 0.1692,
      "eval_samples_per_second": 70.913,
      "eval_steps_per_second": 5.909,
      "step": 30
    },
    {
      "epoch": 31.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.05344026908278465,
      "eval_runtime": 0.1748,
      "eval_samples_per_second": 68.65,
      "eval_steps_per_second": 5.721,
      "step": 31
    },
    {
      "epoch": 32.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.04723837599158287,
      "eval_runtime": 0.1773,
      "eval_samples_per_second": 67.677,
      "eval_steps_per_second": 5.64,
      "step": 32
    },
    {
      "epoch": 33.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.057503703981637955,
      "eval_runtime": 0.171,
      "eval_samples_per_second": 70.184,
      "eval_steps_per_second": 5.849,
      "step": 33
    },
    {
      "epoch": 34.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.061442967504262924,
      "eval_runtime": 0.1735,
      "eval_samples_per_second": 69.145,
      "eval_steps_per_second": 5.762,
      "step": 34
    },
    {
      "epoch": 35.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.05957895517349243,
      "eval_runtime": 0.1743,
      "eval_samples_per_second": 68.863,
      "eval_steps_per_second": 5.739,
      "step": 35
    },
    {
      "epoch": 36.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0503091923892498,
      "eval_runtime": 0.1743,
      "eval_samples_per_second": 68.828,
      "eval_steps_per_second": 5.736,
      "step": 36
    },
    {
      "epoch": 37.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.05713028088212013,
      "eval_runtime": 0.1741,
      "eval_samples_per_second": 68.934,
      "eval_steps_per_second": 5.745,
      "step": 37
    },
    {
      "epoch": 38.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.06938361376523972,
      "eval_runtime": 0.1755,
      "eval_samples_per_second": 68.376,
      "eval_steps_per_second": 5.698,
      "step": 38
    },
    {
      "epoch": 39.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.0869433656334877,
      "eval_runtime": 0.1709,
      "eval_samples_per_second": 70.212,
      "eval_steps_per_second": 5.851,
      "step": 39
    },
    {
      "epoch": 40.0,
      "grad_norm": 1.0563879013061523,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0416,
      "step": 40
    },
    {
      "epoch": 40.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.10385680943727493,
      "eval_runtime": 0.1741,
      "eval_samples_per_second": 68.935,
      "eval_steps_per_second": 5.745,
      "step": 40
    },
    {
      "epoch": 41.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.11296293884515762,
      "eval_runtime": 0.1682,
      "eval_samples_per_second": 71.335,
      "eval_steps_per_second": 5.945,
      "step": 41
    },
    {
      "epoch": 42.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.1127309575676918,
      "eval_runtime": 0.1673,
      "eval_samples_per_second": 71.714,
      "eval_steps_per_second": 5.976,
      "step": 42
    },
    {
      "epoch": 43.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.1028260588645935,
      "eval_runtime": 0.1773,
      "eval_samples_per_second": 67.664,
      "eval_steps_per_second": 5.639,
      "step": 43
    },
    {
      "epoch": 44.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.08404495567083359,
      "eval_runtime": 0.1803,
      "eval_samples_per_second": 66.548,
      "eval_steps_per_second": 5.546,
      "step": 44
    },
    {
      "epoch": 45.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.07033081352710724,
      "eval_runtime": 0.1683,
      "eval_samples_per_second": 71.306,
      "eval_steps_per_second": 5.942,
      "step": 45
    },
    {
      "epoch": 46.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.056403230875730515,
      "eval_runtime": 0.1695,
      "eval_samples_per_second": 70.785,
      "eval_steps_per_second": 5.899,
      "step": 46
    },
    {
      "epoch": 47.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.05716688930988312,
      "eval_runtime": 0.1751,
      "eval_samples_per_second": 68.533,
      "eval_steps_per_second": 5.711,
      "step": 47
    },
    {
      "epoch": 48.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.06894658505916595,
      "eval_runtime": 0.1733,
      "eval_samples_per_second": 69.246,
      "eval_steps_per_second": 5.77,
      "step": 48
    },
    {
      "epoch": 49.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.09668171405792236,
      "eval_runtime": 0.1834,
      "eval_samples_per_second": 65.426,
      "eval_steps_per_second": 5.452,
      "step": 49
    },
    {
      "epoch": 50.0,
      "grad_norm": 1.5291131734848022,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.048,
      "step": 50
    },
    {
      "epoch": 50.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.14398609101772308,
      "eval_runtime": 0.163,
      "eval_samples_per_second": 73.617,
      "eval_steps_per_second": 6.135,
      "step": 50
    },
    {
      "epoch": 51.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.16672177612781525,
      "eval_runtime": 0.1711,
      "eval_samples_per_second": 70.115,
      "eval_steps_per_second": 5.843,
      "step": 51
    },
    {
      "epoch": 52.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.1823185831308365,
      "eval_runtime": 0.1741,
      "eval_samples_per_second": 68.928,
      "eval_steps_per_second": 5.744,
      "step": 52
    },
    {
      "epoch": 53.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.17343102395534515,
      "eval_runtime": 0.1673,
      "eval_samples_per_second": 71.742,
      "eval_steps_per_second": 5.979,
      "step": 53
    },
    {
      "epoch": 54.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.154280886054039,
      "eval_runtime": 0.1801,
      "eval_samples_per_second": 66.619,
      "eval_steps_per_second": 5.552,
      "step": 54
    },
    {
      "epoch": 55.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.13834944367408752,
      "eval_runtime": 0.1765,
      "eval_samples_per_second": 68.007,
      "eval_steps_per_second": 5.667,
      "step": 55
    },
    {
      "epoch": 56.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.12664343416690826,
      "eval_runtime": 0.1668,
      "eval_samples_per_second": 71.951,
      "eval_steps_per_second": 5.996,
      "step": 56
    },
    {
      "epoch": 57.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.10125861316919327,
      "eval_runtime": 0.1697,
      "eval_samples_per_second": 70.734,
      "eval_steps_per_second": 5.894,
      "step": 57
    },
    {
      "epoch": 58.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.08296892791986465,
      "eval_runtime": 0.1741,
      "eval_samples_per_second": 68.927,
      "eval_steps_per_second": 5.744,
      "step": 58
    },
    {
      "epoch": 59.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.07803661376237869,
      "eval_runtime": 0.1724,
      "eval_samples_per_second": 69.607,
      "eval_steps_per_second": 5.801,
      "step": 59
    },
    {
      "epoch": 60.0,
      "grad_norm": 0.15691009163856506,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.0118,
      "step": 60
    },
    {
      "epoch": 60.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.07563833892345428,
      "eval_runtime": 0.1682,
      "eval_samples_per_second": 71.331,
      "eval_steps_per_second": 5.944,
      "step": 60
    },
    {
      "epoch": 61.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.07225405424833298,
      "eval_runtime": 0.1725,
      "eval_samples_per_second": 69.554,
      "eval_steps_per_second": 5.796,
      "step": 61
    },
    {
      "epoch": 62.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.056341033428907394,
      "eval_runtime": 0.1665,
      "eval_samples_per_second": 72.093,
      "eval_steps_per_second": 6.008,
      "step": 62
    },
    {
      "epoch": 63.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.04702509567141533,
      "eval_runtime": 0.1841,
      "eval_samples_per_second": 65.192,
      "eval_steps_per_second": 5.433,
      "step": 63
    },
    {
      "epoch": 64.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.046886246651411057,
      "eval_runtime": 0.1732,
      "eval_samples_per_second": 69.274,
      "eval_steps_per_second": 5.773,
      "step": 64
    },
    {
      "epoch": 65.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.052169691771268845,
      "eval_runtime": 0.1736,
      "eval_samples_per_second": 69.127,
      "eval_steps_per_second": 5.761,
      "step": 65
    },
    {
      "epoch": 66.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.05759477615356445,
      "eval_runtime": 0.1746,
      "eval_samples_per_second": 68.735,
      "eval_steps_per_second": 5.728,
      "step": 66
    },
    {
      "epoch": 67.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.06394201517105103,
      "eval_runtime": 0.1687,
      "eval_samples_per_second": 71.123,
      "eval_steps_per_second": 5.927,
      "step": 67
    },
    {
      "epoch": 68.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.08266932517290115,
      "eval_runtime": 0.1723,
      "eval_samples_per_second": 69.652,
      "eval_steps_per_second": 5.804,
      "step": 68
    },
    {
      "epoch": 69.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.10889662057161331,
      "eval_runtime": 0.1757,
      "eval_samples_per_second": 68.286,
      "eval_steps_per_second": 5.691,
      "step": 69
    },
    {
      "epoch": 70.0,
      "grad_norm": 0.38948971033096313,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0271,
      "step": 70
    },
    {
      "epoch": 70.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.13427671790122986,
      "eval_runtime": 0.171,
      "eval_samples_per_second": 70.179,
      "eval_steps_per_second": 5.848,
      "step": 70
    },
    {
      "epoch": 71.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.15138830244541168,
      "eval_runtime": 0.1681,
      "eval_samples_per_second": 71.38,
      "eval_steps_per_second": 5.948,
      "step": 71
    },
    {
      "epoch": 72.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.15523149073123932,
      "eval_runtime": 0.1734,
      "eval_samples_per_second": 69.188,
      "eval_steps_per_second": 5.766,
      "step": 72
    },
    {
      "epoch": 73.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.1500328928232193,
      "eval_runtime": 0.1728,
      "eval_samples_per_second": 69.463,
      "eval_steps_per_second": 5.789,
      "step": 73
    },
    {
      "epoch": 74.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.13924731314182281,
      "eval_runtime": 0.1749,
      "eval_samples_per_second": 68.628,
      "eval_steps_per_second": 5.719,
      "step": 74
    },
    {
      "epoch": 75.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.12288343161344528,
      "eval_runtime": 0.1757,
      "eval_samples_per_second": 68.307,
      "eval_steps_per_second": 5.692,
      "step": 75
    },
    {
      "epoch": 76.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.10091481357812881,
      "eval_runtime": 0.1739,
      "eval_samples_per_second": 69.008,
      "eval_steps_per_second": 5.751,
      "step": 76
    },
    {
      "epoch": 77.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.08581729978322983,
      "eval_runtime": 0.168,
      "eval_samples_per_second": 71.423,
      "eval_steps_per_second": 5.952,
      "step": 77
    },
    {
      "epoch": 78.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.08439955860376358,
      "eval_runtime": 0.1701,
      "eval_samples_per_second": 70.534,
      "eval_steps_per_second": 5.878,
      "step": 78
    },
    {
      "epoch": 79.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.08550930768251419,
      "eval_runtime": 0.1809,
      "eval_samples_per_second": 66.325,
      "eval_steps_per_second": 5.527,
      "step": 79
    },
    {
      "epoch": 80.0,
      "grad_norm": 1.0177083015441895,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.0462,
      "step": 80
    },
    {
      "epoch": 80.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.0972227081656456,
      "eval_runtime": 0.1692,
      "eval_samples_per_second": 70.917,
      "eval_steps_per_second": 5.91,
      "step": 80
    },
    {
      "epoch": 81.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.11395915597677231,
      "eval_runtime": 0.1682,
      "eval_samples_per_second": 71.336,
      "eval_steps_per_second": 5.945,
      "step": 81
    },
    {
      "epoch": 82.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.13984452188014984,
      "eval_runtime": 0.17,
      "eval_samples_per_second": 70.587,
      "eval_steps_per_second": 5.882,
      "step": 82
    },
    {
      "epoch": 83.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.16390566527843475,
      "eval_runtime": 0.1702,
      "eval_samples_per_second": 70.502,
      "eval_steps_per_second": 5.875,
      "step": 83
    },
    {
      "epoch": 84.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.18424014747142792,
      "eval_runtime": 0.1721,
      "eval_samples_per_second": 69.737,
      "eval_steps_per_second": 5.811,
      "step": 84
    },
    {
      "epoch": 85.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.1938496083021164,
      "eval_runtime": 0.1864,
      "eval_samples_per_second": 64.387,
      "eval_steps_per_second": 5.366,
      "step": 85
    },
    {
      "epoch": 86.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.20000122487545013,
      "eval_runtime": 0.1802,
      "eval_samples_per_second": 66.596,
      "eval_steps_per_second": 5.55,
      "step": 86
    },
    {
      "epoch": 87.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.20081685483455658,
      "eval_runtime": 0.1707,
      "eval_samples_per_second": 70.294,
      "eval_steps_per_second": 5.858,
      "step": 87
    },
    {
      "epoch": 88.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.19491897523403168,
      "eval_runtime": 0.1725,
      "eval_samples_per_second": 69.551,
      "eval_steps_per_second": 5.796,
      "step": 88
    },
    {
      "epoch": 89.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.18955135345458984,
      "eval_runtime": 0.1729,
      "eval_samples_per_second": 69.415,
      "eval_steps_per_second": 5.785,
      "step": 89
    },
    {
      "epoch": 90.0,
      "grad_norm": 1.028542399406433,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.022,
      "step": 90
    },
    {
      "epoch": 90.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.17976105213165283,
      "eval_runtime": 0.1649,
      "eval_samples_per_second": 72.769,
      "eval_steps_per_second": 6.064,
      "step": 90
    },
    {
      "epoch": 91.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.16998781263828278,
      "eval_runtime": 0.1686,
      "eval_samples_per_second": 71.156,
      "eval_steps_per_second": 5.93,
      "step": 91
    },
    {
      "epoch": 92.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.161741703748703,
      "eval_runtime": 0.1757,
      "eval_samples_per_second": 68.313,
      "eval_steps_per_second": 5.693,
      "step": 92
    },
    {
      "epoch": 93.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.1549077183008194,
      "eval_runtime": 0.1813,
      "eval_samples_per_second": 66.195,
      "eval_steps_per_second": 5.516,
      "step": 93
    },
    {
      "epoch": 94.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.14918744564056396,
      "eval_runtime": 0.1697,
      "eval_samples_per_second": 70.715,
      "eval_steps_per_second": 5.893,
      "step": 94
    },
    {
      "epoch": 95.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.14473901689052582,
      "eval_runtime": 0.1757,
      "eval_samples_per_second": 68.292,
      "eval_steps_per_second": 5.691,
      "step": 95
    },
    {
      "epoch": 96.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.14346013963222504,
      "eval_runtime": 0.1696,
      "eval_samples_per_second": 70.75,
      "eval_steps_per_second": 5.896,
      "step": 96
    },
    {
      "epoch": 97.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.14305876195430756,
      "eval_runtime": 0.168,
      "eval_samples_per_second": 71.43,
      "eval_steps_per_second": 5.952,
      "step": 97
    },
    {
      "epoch": 98.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.1418064534664154,
      "eval_runtime": 0.1807,
      "eval_samples_per_second": 66.421,
      "eval_steps_per_second": 5.535,
      "step": 98
    },
    {
      "epoch": 99.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.14111365377902985,
      "eval_runtime": 0.1677,
      "eval_samples_per_second": 71.558,
      "eval_steps_per_second": 5.963,
      "step": 99
    },
    {
      "epoch": 100.0,
      "grad_norm": 1.2945746183395386,
      "learning_rate": 0.0,
      "loss": 0.0236,
      "step": 100
    },
    {
      "epoch": 100.0,
      "eval_accuracy": 0.9166666666666666,
      "eval_loss": 0.1407879739999771,
      "eval_runtime": 0.1684,
      "eval_samples_per_second": 71.262,
      "eval_steps_per_second": 5.938,
      "step": 100
    },
    {
      "epoch": 100.0,
      "step": 100,
      "total_flos": 4.804632427843584e+17,
      "train_loss": 0.07493457712233066,
      "train_runtime": 422.9864,
      "train_samples_per_second": 14.658,
      "train_steps_per_second": 0.236
    },
    {
      "epoch": 100.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.19073201715946198,
      "eval_runtime": 0.2201,
      "eval_samples_per_second": 54.512,
      "eval_steps_per_second": 4.543,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.804632427843584e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}