{
  "best_metric": 0.5220404863357544,
  "best_model_checkpoint": "vit_epochs5_batch64_lr0.001_size224_tiles1_seed1_vit_old_transform_old_hp/checkpoint-1175",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1175,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02127659574468085,
      "grad_norm": 1.5236927270889282,
      "learning_rate": 0.000995744680851064,
      "loss": 0.8552,
      "step": 5
    },
    {
      "epoch": 0.0425531914893617,
      "grad_norm": 0.1933981478214264,
      "learning_rate": 0.0009914893617021276,
      "loss": 0.6984,
      "step": 10
    },
    {
      "epoch": 0.06382978723404255,
      "grad_norm": 0.2786834239959717,
      "learning_rate": 0.0009872340425531915,
      "loss": 0.684,
      "step": 15
    },
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 0.3437531888484955,
      "learning_rate": 0.0009829787234042554,
      "loss": 0.699,
      "step": 20
    },
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 0.17921054363250732,
      "learning_rate": 0.0009787234042553192,
      "loss": 0.6876,
      "step": 25
    },
    {
      "epoch": 0.1276595744680851,
      "grad_norm": 0.2969794273376465,
      "learning_rate": 0.0009744680851063829,
      "loss": 0.7084,
      "step": 30
    },
    {
      "epoch": 0.14893617021276595,
      "grad_norm": 0.2975955307483673,
      "learning_rate": 0.0009702127659574468,
      "loss": 0.6938,
      "step": 35
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 0.049827929586172104,
      "learning_rate": 0.0009659574468085106,
      "loss": 0.6834,
      "step": 40
    },
    {
      "epoch": 0.19148936170212766,
      "grad_norm": 0.6071491837501526,
      "learning_rate": 0.0009617021276595745,
      "loss": 0.6737,
      "step": 45
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 0.1733636111021042,
      "learning_rate": 0.0009574468085106384,
      "loss": 0.6401,
      "step": 50
    },
    {
      "epoch": 0.23404255319148937,
      "grad_norm": 0.6925361752510071,
      "learning_rate": 0.0009531914893617022,
      "loss": 0.6786,
      "step": 55
    },
    {
      "epoch": 0.2553191489361702,
      "grad_norm": 1.0148730278015137,
      "learning_rate": 0.000948936170212766,
      "loss": 0.6925,
      "step": 60
    },
    {
      "epoch": 0.2765957446808511,
      "grad_norm": 0.4391551911830902,
      "learning_rate": 0.0009446808510638298,
      "loss": 0.7001,
      "step": 65
    },
    {
      "epoch": 0.2978723404255319,
      "grad_norm": 0.10365554690361023,
      "learning_rate": 0.0009404255319148937,
      "loss": 0.661,
      "step": 70
    },
    {
      "epoch": 0.3191489361702128,
      "grad_norm": 0.5373475551605225,
      "learning_rate": 0.0009361702127659575,
      "loss": 0.6646,
      "step": 75
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 0.26909396052360535,
      "learning_rate": 0.0009319148936170214,
      "loss": 0.6496,
      "step": 80
    },
    {
      "epoch": 0.3617021276595745,
      "grad_norm": 0.7345396876335144,
      "learning_rate": 0.0009276595744680851,
      "loss": 0.6809,
      "step": 85
    },
    {
      "epoch": 0.3829787234042553,
      "grad_norm": 0.17642471194267273,
      "learning_rate": 0.0009234042553191489,
      "loss": 0.6689,
      "step": 90
    },
    {
      "epoch": 0.40425531914893614,
      "grad_norm": 0.24865615367889404,
      "learning_rate": 0.0009191489361702128,
      "loss": 0.6668,
      "step": 95
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 0.0725848600268364,
      "learning_rate": 0.0009148936170212766,
      "loss": 0.6955,
      "step": 100
    },
    {
      "epoch": 0.44680851063829785,
      "grad_norm": 0.6779701113700867,
      "learning_rate": 0.0009106382978723405,
      "loss": 0.6643,
      "step": 105
    },
    {
      "epoch": 0.46808510638297873,
      "grad_norm": 0.2594638466835022,
      "learning_rate": 0.0009063829787234043,
      "loss": 0.6774,
      "step": 110
    },
    {
      "epoch": 0.48936170212765956,
      "grad_norm": 0.41974830627441406,
      "learning_rate": 0.000902127659574468,
      "loss": 0.6632,
      "step": 115
    },
    {
      "epoch": 0.5106382978723404,
      "grad_norm": 0.2086678445339203,
      "learning_rate": 0.0008978723404255319,
      "loss": 0.6264,
      "step": 120
    },
    {
      "epoch": 0.5319148936170213,
      "grad_norm": 0.45617616176605225,
      "learning_rate": 0.0008936170212765957,
      "loss": 0.6538,
      "step": 125
    },
    {
      "epoch": 0.5531914893617021,
      "grad_norm": 0.32972219586372375,
      "learning_rate": 0.0008893617021276596,
      "loss": 0.6471,
      "step": 130
    },
    {
      "epoch": 0.574468085106383,
      "grad_norm": 0.5587528347969055,
      "learning_rate": 0.0008851063829787234,
      "loss": 0.624,
      "step": 135
    },
    {
      "epoch": 0.5957446808510638,
      "grad_norm": 0.5918276906013489,
      "learning_rate": 0.0008808510638297873,
      "loss": 0.6576,
      "step": 140
    },
    {
      "epoch": 0.6170212765957447,
      "grad_norm": 0.35423263907432556,
      "learning_rate": 0.0008765957446808511,
      "loss": 0.6376,
      "step": 145
    },
    {
      "epoch": 0.6382978723404256,
      "grad_norm": 0.49659672379493713,
      "learning_rate": 0.0008723404255319149,
      "loss": 0.6555,
      "step": 150
    },
    {
      "epoch": 0.6595744680851063,
      "grad_norm": 0.26542067527770996,
      "learning_rate": 0.0008680851063829788,
      "loss": 0.6457,
      "step": 155
    },
    {
      "epoch": 0.6808510638297872,
      "grad_norm": 0.5932815670967102,
      "learning_rate": 0.0008638297872340426,
      "loss": 0.6706,
      "step": 160
    },
    {
      "epoch": 0.7021276595744681,
      "grad_norm": 0.18936298787593842,
      "learning_rate": 0.0008595744680851064,
      "loss": 0.6923,
      "step": 165
    },
    {
      "epoch": 0.723404255319149,
      "grad_norm": 0.2216617614030838,
      "learning_rate": 0.0008553191489361703,
      "loss": 0.6805,
      "step": 170
    },
    {
      "epoch": 0.7446808510638298,
      "grad_norm": 0.2572282552719116,
      "learning_rate": 0.000851063829787234,
      "loss": 0.6803,
      "step": 175
    },
    {
      "epoch": 0.7659574468085106,
      "grad_norm": 0.2624934911727905,
      "learning_rate": 0.0008468085106382979,
      "loss": 0.6796,
      "step": 180
    },
    {
      "epoch": 0.7872340425531915,
      "grad_norm": 0.3983383774757385,
      "learning_rate": 0.0008425531914893617,
      "loss": 0.652,
      "step": 185
    },
    {
      "epoch": 0.8085106382978723,
      "grad_norm": 0.7851768136024475,
      "learning_rate": 0.0008382978723404256,
      "loss": 0.6972,
      "step": 190
    },
    {
      "epoch": 0.8297872340425532,
      "grad_norm": 0.08407687395811081,
      "learning_rate": 0.0008340425531914894,
      "loss": 0.7127,
      "step": 195
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 0.2317022830247879,
      "learning_rate": 0.0008297872340425531,
      "loss": 0.6879,
      "step": 200
    },
    {
      "epoch": 0.8723404255319149,
      "grad_norm": 0.10921870172023773,
      "learning_rate": 0.000825531914893617,
      "loss": 0.6909,
      "step": 205
    },
    {
      "epoch": 0.8936170212765957,
      "grad_norm": 0.06697387248277664,
      "learning_rate": 0.0008212765957446808,
      "loss": 0.6858,
      "step": 210
    },
    {
      "epoch": 0.9148936170212766,
      "grad_norm": 0.16396264731884003,
      "learning_rate": 0.0008170212765957447,
      "loss": 0.6836,
      "step": 215
    },
    {
      "epoch": 0.9361702127659575,
      "grad_norm": 0.07334744930267334,
      "learning_rate": 0.0008127659574468085,
      "loss": 0.6835,
      "step": 220
    },
    {
      "epoch": 0.9574468085106383,
      "grad_norm": 0.28075695037841797,
      "learning_rate": 0.0008085106382978723,
      "loss": 0.6616,
      "step": 225
    },
    {
      "epoch": 0.9787234042553191,
      "grad_norm": 0.32385650277137756,
      "learning_rate": 0.0008042553191489363,
      "loss": 0.6763,
      "step": 230
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6150110960006714,
      "learning_rate": 0.0008,
      "loss": 0.6668,
      "step": 235
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5725333333333333,
      "eval_loss": 0.6652818918228149,
      "eval_runtime": 52.8415,
      "eval_samples_per_second": 70.967,
      "eval_steps_per_second": 1.117,
      "step": 235
    },
    {
      "epoch": 1.0212765957446808,
      "grad_norm": 0.36133354902267456,
      "learning_rate": 0.0007957446808510639,
      "loss": 0.6505,
      "step": 240
    },
    {
      "epoch": 1.0425531914893618,
      "grad_norm": 0.2631653845310211,
      "learning_rate": 0.0007914893617021277,
      "loss": 0.6666,
      "step": 245
    },
    {
      "epoch": 1.0638297872340425,
      "grad_norm": 0.40402382612228394,
      "learning_rate": 0.0007872340425531915,
      "loss": 0.6406,
      "step": 250
    },
    {
      "epoch": 1.0851063829787233,
      "grad_norm": 0.22335675358772278,
      "learning_rate": 0.0007829787234042554,
      "loss": 0.6584,
      "step": 255
    },
    {
      "epoch": 1.1063829787234043,
      "grad_norm": 0.38019102811813354,
      "learning_rate": 0.0007787234042553192,
      "loss": 0.6773,
      "step": 260
    },
    {
      "epoch": 1.127659574468085,
      "grad_norm": 0.6945547461509705,
      "learning_rate": 0.000774468085106383,
      "loss": 0.66,
      "step": 265
    },
    {
      "epoch": 1.148936170212766,
      "grad_norm": 0.2084246724843979,
      "learning_rate": 0.0007702127659574468,
      "loss": 0.6512,
      "step": 270
    },
    {
      "epoch": 1.1702127659574468,
      "grad_norm": 0.1295584738254547,
      "learning_rate": 0.0007659574468085106,
      "loss": 0.6521,
      "step": 275
    },
    {
      "epoch": 1.1914893617021276,
      "grad_norm": 0.12610581517219543,
      "learning_rate": 0.0007617021276595745,
      "loss": 0.6281,
      "step": 280
    },
    {
      "epoch": 1.2127659574468086,
      "grad_norm": 0.5777516961097717,
      "learning_rate": 0.0007574468085106383,
      "loss": 0.6315,
      "step": 285
    },
    {
      "epoch": 1.2340425531914894,
      "grad_norm": 0.4698016047477722,
      "learning_rate": 0.0007531914893617022,
      "loss": 0.6736,
      "step": 290
    },
    {
      "epoch": 1.2553191489361701,
      "grad_norm": 0.306220680475235,
      "learning_rate": 0.0007489361702127659,
      "loss": 0.6616,
      "step": 295
    },
    {
      "epoch": 1.2765957446808511,
      "grad_norm": 0.1651347577571869,
      "learning_rate": 0.0007446808510638298,
      "loss": 0.6624,
      "step": 300
    },
    {
      "epoch": 1.297872340425532,
      "grad_norm": 0.1671248823404312,
      "learning_rate": 0.0007404255319148936,
      "loss": 0.6537,
      "step": 305
    },
    {
      "epoch": 1.3191489361702127,
      "grad_norm": 0.5579215288162231,
      "learning_rate": 0.0007361702127659574,
      "loss": 0.6547,
      "step": 310
    },
    {
      "epoch": 1.3404255319148937,
      "grad_norm": 0.20245681703090668,
      "learning_rate": 0.0007319148936170213,
      "loss": 0.6477,
      "step": 315
    },
    {
      "epoch": 1.3617021276595744,
      "grad_norm": 0.1913478672504425,
      "learning_rate": 0.0007276595744680852,
      "loss": 0.6311,
      "step": 320
    },
    {
      "epoch": 1.3829787234042552,
      "grad_norm": 0.4945693016052246,
      "learning_rate": 0.000723404255319149,
      "loss": 0.5979,
      "step": 325
    },
    {
      "epoch": 1.4042553191489362,
      "grad_norm": 0.1921028196811676,
      "learning_rate": 0.0007191489361702128,
      "loss": 0.7027,
      "step": 330
    },
    {
      "epoch": 1.425531914893617,
      "grad_norm": 0.26029083132743835,
      "learning_rate": 0.0007148936170212766,
      "loss": 0.6733,
      "step": 335
    },
    {
      "epoch": 1.4468085106382977,
      "grad_norm": 0.3045407831668854,
      "learning_rate": 0.0007106382978723405,
      "loss": 0.6619,
      "step": 340
    },
    {
      "epoch": 1.4680851063829787,
      "grad_norm": 0.12488707154989243,
      "learning_rate": 0.0007063829787234043,
      "loss": 0.666,
      "step": 345
    },
    {
      "epoch": 1.4893617021276595,
      "grad_norm": 0.15467241406440735,
      "learning_rate": 0.0007021276595744682,
      "loss": 0.634,
      "step": 350
    },
    {
      "epoch": 1.5106382978723403,
      "grad_norm": 0.23499886691570282,
      "learning_rate": 0.0006978723404255319,
      "loss": 0.6257,
      "step": 355
    },
    {
      "epoch": 1.5319148936170213,
      "grad_norm": 0.48748576641082764,
      "learning_rate": 0.0006936170212765957,
      "loss": 0.6369,
      "step": 360
    },
    {
      "epoch": 1.5531914893617023,
      "grad_norm": 0.3014831244945526,
      "learning_rate": 0.0006893617021276596,
      "loss": 0.6274,
      "step": 365
    },
    {
      "epoch": 1.574468085106383,
      "grad_norm": 0.12689495086669922,
      "learning_rate": 0.0006851063829787234,
      "loss": 0.6427,
      "step": 370
    },
    {
      "epoch": 1.5957446808510638,
      "grad_norm": 0.3490160405635834,
      "learning_rate": 0.0006808510638297873,
      "loss": 0.6885,
      "step": 375
    },
    {
      "epoch": 1.6170212765957448,
      "grad_norm": 0.2676607370376587,
      "learning_rate": 0.000676595744680851,
      "loss": 0.6436,
      "step": 380
    },
    {
      "epoch": 1.6382978723404256,
      "grad_norm": 0.26951488852500916,
      "learning_rate": 0.0006723404255319148,
      "loss": 0.6387,
      "step": 385
    },
    {
      "epoch": 1.6595744680851063,
      "grad_norm": 0.3769073784351349,
      "learning_rate": 0.0006680851063829787,
      "loss": 0.6003,
      "step": 390
    },
    {
      "epoch": 1.6808510638297873,
      "grad_norm": 0.43915122747421265,
      "learning_rate": 0.0006638297872340425,
      "loss": 0.6477,
      "step": 395
    },
    {
      "epoch": 1.702127659574468,
      "grad_norm": 0.2419726401567459,
      "learning_rate": 0.0006595744680851064,
      "loss": 0.6174,
      "step": 400
    },
    {
      "epoch": 1.7234042553191489,
      "grad_norm": 0.5210821628570557,
      "learning_rate": 0.0006553191489361702,
      "loss": 0.625,
      "step": 405
    },
    {
      "epoch": 1.7446808510638299,
      "grad_norm": 0.5546556115150452,
      "learning_rate": 0.0006510638297872342,
      "loss": 0.604,
      "step": 410
    },
    {
      "epoch": 1.7659574468085106,
      "grad_norm": 0.5459072589874268,
      "learning_rate": 0.0006468085106382979,
      "loss": 0.6322,
      "step": 415
    },
    {
      "epoch": 1.7872340425531914,
      "grad_norm": 0.28615137934684753,
      "learning_rate": 0.0006425531914893617,
      "loss": 0.6288,
      "step": 420
    },
    {
      "epoch": 1.8085106382978724,
      "grad_norm": 0.25826430320739746,
      "learning_rate": 0.0006382978723404256,
      "loss": 0.6377,
      "step": 425
    },
    {
      "epoch": 1.8297872340425532,
      "grad_norm": 0.27113598585128784,
      "learning_rate": 0.0006340425531914894,
      "loss": 0.6155,
      "step": 430
    },
    {
      "epoch": 1.851063829787234,
      "grad_norm": 0.3145448565483093,
      "learning_rate": 0.0006297872340425533,
      "loss": 0.6258,
      "step": 435
    },
    {
      "epoch": 1.872340425531915,
      "grad_norm": 0.221902996301651,
      "learning_rate": 0.000625531914893617,
      "loss": 0.6133,
      "step": 440
    },
    {
      "epoch": 1.8936170212765957,
      "grad_norm": 0.2308581918478012,
      "learning_rate": 0.0006212765957446808,
      "loss": 0.5883,
      "step": 445
    },
    {
      "epoch": 1.9148936170212765,
      "grad_norm": 0.2169838696718216,
      "learning_rate": 0.0006170212765957447,
      "loss": 0.6219,
      "step": 450
    },
    {
      "epoch": 1.9361702127659575,
      "grad_norm": 0.32386860251426697,
      "learning_rate": 0.0006127659574468085,
      "loss": 0.6102,
      "step": 455
    },
    {
      "epoch": 1.9574468085106385,
      "grad_norm": 0.13700896501541138,
      "learning_rate": 0.0006085106382978724,
      "loss": 0.6436,
      "step": 460
    },
    {
      "epoch": 1.978723404255319,
      "grad_norm": 0.18552586436271667,
      "learning_rate": 0.0006042553191489362,
      "loss": 0.6524,
      "step": 465
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5744425058364868,
      "learning_rate": 0.0006,
      "loss": 0.6527,
      "step": 470
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6528,
      "eval_loss": 0.6233171224594116,
      "eval_runtime": 52.0761,
      "eval_samples_per_second": 72.01,
      "eval_steps_per_second": 1.133,
      "step": 470
    },
    {
      "epoch": 2.021276595744681,
      "grad_norm": 0.39053860306739807,
      "learning_rate": 0.0005957446808510638,
      "loss": 0.5832,
      "step": 475
    },
    {
      "epoch": 2.0425531914893615,
      "grad_norm": 0.2939192056655884,
      "learning_rate": 0.0005914893617021276,
      "loss": 0.5808,
      "step": 480
    },
    {
      "epoch": 2.0638297872340425,
      "grad_norm": 0.5998929142951965,
      "learning_rate": 0.0005872340425531915,
      "loss": 0.6119,
      "step": 485
    },
    {
      "epoch": 2.0851063829787235,
      "grad_norm": 0.48165130615234375,
      "learning_rate": 0.0005829787234042553,
      "loss": 0.5868,
      "step": 490
    },
    {
      "epoch": 2.106382978723404,
      "grad_norm": 0.2857578694820404,
      "learning_rate": 0.0005787234042553191,
      "loss": 0.5843,
      "step": 495
    },
    {
      "epoch": 2.127659574468085,
      "grad_norm": 0.28461429476737976,
      "learning_rate": 0.0005744680851063831,
      "loss": 0.5843,
      "step": 500
    },
    {
      "epoch": 2.148936170212766,
      "grad_norm": 0.30877211689949036,
      "learning_rate": 0.0005702127659574468,
      "loss": 0.5652,
      "step": 505
    },
    {
      "epoch": 2.1702127659574466,
      "grad_norm": 0.7491441369056702,
      "learning_rate": 0.0005659574468085107,
      "loss": 0.5687,
      "step": 510
    },
    {
      "epoch": 2.1914893617021276,
      "grad_norm": 0.29466772079467773,
      "learning_rate": 0.0005617021276595745,
      "loss": 0.6339,
      "step": 515
    },
    {
      "epoch": 2.2127659574468086,
      "grad_norm": 0.44021138548851013,
      "learning_rate": 0.0005574468085106383,
      "loss": 0.5629,
      "step": 520
    },
    {
      "epoch": 2.2340425531914896,
      "grad_norm": 0.19135086238384247,
      "learning_rate": 0.0005531914893617022,
      "loss": 0.6169,
      "step": 525
    },
    {
      "epoch": 2.25531914893617,
      "grad_norm": 0.6730530858039856,
      "learning_rate": 0.000548936170212766,
      "loss": 0.6063,
      "step": 530
    },
    {
      "epoch": 2.276595744680851,
      "grad_norm": 0.4451698362827301,
      "learning_rate": 0.0005446808510638298,
      "loss": 0.614,
      "step": 535
    },
    {
      "epoch": 2.297872340425532,
      "grad_norm": 0.19956566393375397,
      "learning_rate": 0.0005404255319148936,
      "loss": 0.5848,
      "step": 540
    },
    {
      "epoch": 2.3191489361702127,
      "grad_norm": 0.3573627471923828,
      "learning_rate": 0.0005361702127659575,
      "loss": 0.5963,
      "step": 545
    },
    {
      "epoch": 2.3404255319148937,
      "grad_norm": 0.22617582976818085,
      "learning_rate": 0.0005319148936170213,
      "loss": 0.5512,
      "step": 550
    },
    {
      "epoch": 2.3617021276595747,
      "grad_norm": 0.2276870310306549,
      "learning_rate": 0.0005276595744680851,
      "loss": 0.5801,
      "step": 555
    },
    {
      "epoch": 2.382978723404255,
      "grad_norm": 0.3912278413772583,
      "learning_rate": 0.000523404255319149,
      "loss": 0.6101,
      "step": 560
    },
    {
      "epoch": 2.404255319148936,
      "grad_norm": 0.20038598775863647,
      "learning_rate": 0.0005191489361702127,
      "loss": 0.5842,
      "step": 565
    },
    {
      "epoch": 2.425531914893617,
      "grad_norm": 0.27847474813461304,
      "learning_rate": 0.0005148936170212766,
      "loss": 0.5597,
      "step": 570
    },
    {
      "epoch": 2.4468085106382977,
      "grad_norm": 0.49357470870018005,
      "learning_rate": 0.0005106382978723404,
      "loss": 0.5374,
      "step": 575
    },
    {
      "epoch": 2.4680851063829787,
      "grad_norm": 0.22584182024002075,
      "learning_rate": 0.0005063829787234042,
      "loss": 0.6416,
      "step": 580
    },
    {
      "epoch": 2.4893617021276597,
      "grad_norm": 0.4970340430736542,
      "learning_rate": 0.0005021276595744681,
      "loss": 0.6101,
      "step": 585
    },
    {
      "epoch": 2.5106382978723403,
      "grad_norm": 0.23562884330749512,
      "learning_rate": 0.000497872340425532,
      "loss": 0.5728,
      "step": 590
    },
    {
      "epoch": 2.5319148936170213,
      "grad_norm": 0.2772935926914215,
      "learning_rate": 0.0004936170212765957,
      "loss": 0.5969,
      "step": 595
    },
    {
      "epoch": 2.5531914893617023,
      "grad_norm": 0.466553658246994,
      "learning_rate": 0.0004893617021276596,
      "loss": 0.5722,
      "step": 600
    },
    {
      "epoch": 2.574468085106383,
      "grad_norm": 0.1931866854429245,
      "learning_rate": 0.0004851063829787234,
      "loss": 0.5947,
      "step": 605
    },
    {
      "epoch": 2.595744680851064,
      "grad_norm": 0.3345823884010315,
      "learning_rate": 0.00048085106382978723,
      "loss": 0.5464,
      "step": 610
    },
    {
      "epoch": 2.617021276595745,
      "grad_norm": 0.8605038523674011,
      "learning_rate": 0.0004765957446808511,
      "loss": 0.616,
      "step": 615
    },
    {
      "epoch": 2.6382978723404253,
      "grad_norm": 0.467629611492157,
      "learning_rate": 0.0004723404255319149,
      "loss": 0.5997,
      "step": 620
    },
    {
      "epoch": 2.6595744680851063,
      "grad_norm": 0.30429497361183167,
      "learning_rate": 0.00046808510638297874,
      "loss": 0.5498,
      "step": 625
    },
    {
      "epoch": 2.6808510638297873,
      "grad_norm": 0.2898688316345215,
      "learning_rate": 0.00046382978723404257,
      "loss": 0.5526,
      "step": 630
    },
    {
      "epoch": 2.702127659574468,
      "grad_norm": 0.24966174364089966,
      "learning_rate": 0.0004595744680851064,
      "loss": 0.568,
      "step": 635
    },
    {
      "epoch": 2.723404255319149,
      "grad_norm": 0.31960707902908325,
      "learning_rate": 0.00045531914893617024,
      "loss": 0.5573,
      "step": 640
    },
    {
      "epoch": 2.74468085106383,
      "grad_norm": 0.17629045248031616,
      "learning_rate": 0.000451063829787234,
      "loss": 0.5793,
      "step": 645
    },
    {
      "epoch": 2.7659574468085104,
      "grad_norm": 0.3344897925853729,
      "learning_rate": 0.00044680851063829785,
      "loss": 0.5782,
      "step": 650
    },
    {
      "epoch": 2.7872340425531914,
      "grad_norm": 0.6426132917404175,
      "learning_rate": 0.0004425531914893617,
      "loss": 0.6065,
      "step": 655
    },
    {
      "epoch": 2.8085106382978724,
      "grad_norm": 0.4149859547615051,
      "learning_rate": 0.00043829787234042557,
      "loss": 0.6095,
      "step": 660
    },
    {
      "epoch": 2.829787234042553,
      "grad_norm": 0.2638397812843323,
      "learning_rate": 0.0004340425531914894,
      "loss": 0.5651,
      "step": 665
    },
    {
      "epoch": 2.851063829787234,
      "grad_norm": 0.47826263308525085,
      "learning_rate": 0.0004297872340425532,
      "loss": 0.6366,
      "step": 670
    },
    {
      "epoch": 2.872340425531915,
      "grad_norm": 0.47488388419151306,
      "learning_rate": 0.000425531914893617,
      "loss": 0.5498,
      "step": 675
    },
    {
      "epoch": 2.8936170212765955,
      "grad_norm": 0.29856908321380615,
      "learning_rate": 0.00042127659574468085,
      "loss": 0.5576,
      "step": 680
    },
    {
      "epoch": 2.9148936170212765,
      "grad_norm": 0.3228590488433838,
      "learning_rate": 0.0004170212765957447,
      "loss": 0.5527,
      "step": 685
    },
    {
      "epoch": 2.9361702127659575,
      "grad_norm": 0.28109100461006165,
      "learning_rate": 0.0004127659574468085,
      "loss": 0.5421,
      "step": 690
    },
    {
      "epoch": 2.9574468085106385,
      "grad_norm": 0.43624716997146606,
      "learning_rate": 0.00040851063829787235,
      "loss": 0.5419,
      "step": 695
    },
    {
      "epoch": 2.978723404255319,
      "grad_norm": 0.33003830909729004,
      "learning_rate": 0.00040425531914893613,
      "loss": 0.5614,
      "step": 700
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.8071190118789673,
      "learning_rate": 0.0004,
      "loss": 0.5628,
      "step": 705
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7048,
      "eval_loss": 0.5658010244369507,
      "eval_runtime": 52.264,
      "eval_samples_per_second": 71.751,
      "eval_steps_per_second": 1.129,
      "step": 705
    },
    {
      "epoch": 3.021276595744681,
      "grad_norm": 0.34832167625427246,
      "learning_rate": 0.00039574468085106385,
      "loss": 0.5412,
      "step": 710
    },
    {
      "epoch": 3.0425531914893615,
      "grad_norm": 0.3105883002281189,
      "learning_rate": 0.0003914893617021277,
      "loss": 0.5428,
      "step": 715
    },
    {
      "epoch": 3.0638297872340425,
      "grad_norm": 0.48978525400161743,
      "learning_rate": 0.0003872340425531915,
      "loss": 0.5074,
      "step": 720
    },
    {
      "epoch": 3.0851063829787235,
      "grad_norm": 0.3323807120323181,
      "learning_rate": 0.0003829787234042553,
      "loss": 0.5388,
      "step": 725
    },
    {
      "epoch": 3.106382978723404,
      "grad_norm": 0.23931725323200226,
      "learning_rate": 0.00037872340425531913,
      "loss": 0.5329,
      "step": 730
    },
    {
      "epoch": 3.127659574468085,
      "grad_norm": 0.4094422459602356,
      "learning_rate": 0.00037446808510638297,
      "loss": 0.5256,
      "step": 735
    },
    {
      "epoch": 3.148936170212766,
      "grad_norm": 0.2427910566329956,
      "learning_rate": 0.0003702127659574468,
      "loss": 0.4994,
      "step": 740
    },
    {
      "epoch": 3.1702127659574466,
      "grad_norm": 0.46753978729248047,
      "learning_rate": 0.00036595744680851063,
      "loss": 0.5841,
      "step": 745
    },
    {
      "epoch": 3.1914893617021276,
      "grad_norm": 0.60309898853302,
      "learning_rate": 0.0003617021276595745,
      "loss": 0.5018,
      "step": 750
    },
    {
      "epoch": 3.2127659574468086,
      "grad_norm": 0.32367798686027527,
      "learning_rate": 0.0003574468085106383,
      "loss": 0.5112,
      "step": 755
    },
    {
      "epoch": 3.2340425531914896,
      "grad_norm": 0.31850096583366394,
      "learning_rate": 0.00035319148936170213,
      "loss": 0.5197,
      "step": 760
    },
    {
      "epoch": 3.25531914893617,
      "grad_norm": 0.40993842482566833,
      "learning_rate": 0.00034893617021276597,
      "loss": 0.491,
      "step": 765
    },
    {
      "epoch": 3.276595744680851,
      "grad_norm": 0.31502920389175415,
      "learning_rate": 0.0003446808510638298,
      "loss": 0.5134,
      "step": 770
    },
    {
      "epoch": 3.297872340425532,
      "grad_norm": 0.34986236691474915,
      "learning_rate": 0.00034042553191489364,
      "loss": 0.5093,
      "step": 775
    },
    {
      "epoch": 3.3191489361702127,
      "grad_norm": 0.30818113684654236,
      "learning_rate": 0.0003361702127659574,
      "loss": 0.4668,
      "step": 780
    },
    {
      "epoch": 3.3404255319148937,
      "grad_norm": 0.45690372586250305,
      "learning_rate": 0.00033191489361702125,
      "loss": 0.4793,
      "step": 785
    },
    {
      "epoch": 3.3617021276595747,
      "grad_norm": 0.431671142578125,
      "learning_rate": 0.0003276595744680851,
      "loss": 0.5449,
      "step": 790
    },
    {
      "epoch": 3.382978723404255,
      "grad_norm": 0.6079233288764954,
      "learning_rate": 0.00032340425531914897,
      "loss": 0.5055,
      "step": 795
    },
    {
      "epoch": 3.404255319148936,
      "grad_norm": 0.25394123792648315,
      "learning_rate": 0.0003191489361702128,
      "loss": 0.5137,
      "step": 800
    },
    {
      "epoch": 3.425531914893617,
      "grad_norm": 0.2768719494342804,
      "learning_rate": 0.00031489361702127664,
      "loss": 0.5378,
      "step": 805
    },
    {
      "epoch": 3.4468085106382977,
      "grad_norm": 0.33412039279937744,
      "learning_rate": 0.0003106382978723404,
      "loss": 0.5529,
      "step": 810
    },
    {
      "epoch": 3.4680851063829787,
      "grad_norm": 0.45218709111213684,
      "learning_rate": 0.00030638297872340425,
      "loss": 0.514,
      "step": 815
    },
    {
      "epoch": 3.4893617021276597,
      "grad_norm": 0.29416921734809875,
      "learning_rate": 0.0003021276595744681,
      "loss": 0.471,
      "step": 820
    },
    {
      "epoch": 3.5106382978723403,
      "grad_norm": 0.4108869433403015,
      "learning_rate": 0.0002978723404255319,
      "loss": 0.5222,
      "step": 825
    },
    {
      "epoch": 3.5319148936170213,
      "grad_norm": 0.5049691200256348,
      "learning_rate": 0.00029361702127659575,
      "loss": 0.5103,
      "step": 830
    },
    {
      "epoch": 3.5531914893617023,
      "grad_norm": 0.37521079182624817,
      "learning_rate": 0.00028936170212765953,
      "loss": 0.5088,
      "step": 835
    },
    {
      "epoch": 3.574468085106383,
      "grad_norm": 0.6042494177818298,
      "learning_rate": 0.0002851063829787234,
      "loss": 0.4886,
      "step": 840
    },
    {
      "epoch": 3.595744680851064,
      "grad_norm": 0.3379281163215637,
      "learning_rate": 0.00028085106382978725,
      "loss": 0.4878,
      "step": 845
    },
    {
      "epoch": 3.617021276595745,
      "grad_norm": 0.42538291215896606,
      "learning_rate": 0.0002765957446808511,
      "loss": 0.5241,
      "step": 850
    },
    {
      "epoch": 3.6382978723404253,
      "grad_norm": 0.34973302483558655,
      "learning_rate": 0.0002723404255319149,
      "loss": 0.497,
      "step": 855
    },
    {
      "epoch": 3.6595744680851063,
      "grad_norm": 0.5937588214874268,
      "learning_rate": 0.00026808510638297875,
      "loss": 0.5004,
      "step": 860
    },
    {
      "epoch": 3.6808510638297873,
      "grad_norm": 0.3566235601902008,
      "learning_rate": 0.00026382978723404253,
      "loss": 0.5192,
      "step": 865
    },
    {
      "epoch": 3.702127659574468,
      "grad_norm": 0.7297813296318054,
      "learning_rate": 0.00025957446808510637,
      "loss": 0.5313,
      "step": 870
    },
    {
      "epoch": 3.723404255319149,
      "grad_norm": 0.3060586452484131,
      "learning_rate": 0.0002553191489361702,
      "loss": 0.5057,
      "step": 875
    },
    {
      "epoch": 3.74468085106383,
      "grad_norm": 0.3572905361652374,
      "learning_rate": 0.00025106382978723403,
      "loss": 0.5078,
      "step": 880
    },
    {
      "epoch": 3.7659574468085104,
      "grad_norm": 0.5359181761741638,
      "learning_rate": 0.00024680851063829787,
      "loss": 0.4953,
      "step": 885
    },
    {
      "epoch": 3.7872340425531914,
      "grad_norm": 0.676404595375061,
      "learning_rate": 0.0002425531914893617,
      "loss": 0.4878,
      "step": 890
    },
    {
      "epoch": 3.8085106382978724,
      "grad_norm": 0.7736416459083557,
      "learning_rate": 0.00023829787234042556,
      "loss": 0.4897,
      "step": 895
    },
    {
      "epoch": 3.829787234042553,
      "grad_norm": 0.6416388154029846,
      "learning_rate": 0.00023404255319148937,
      "loss": 0.5031,
      "step": 900
    },
    {
      "epoch": 3.851063829787234,
      "grad_norm": 1.1011937856674194,
      "learning_rate": 0.0002297872340425532,
      "loss": 0.4563,
      "step": 905
    },
    {
      "epoch": 3.872340425531915,
      "grad_norm": 0.4412100613117218,
      "learning_rate": 0.000225531914893617,
      "loss": 0.525,
      "step": 910
    },
    {
      "epoch": 3.8936170212765955,
      "grad_norm": 0.6614885926246643,
      "learning_rate": 0.00022127659574468084,
      "loss": 0.5163,
      "step": 915
    },
    {
      "epoch": 3.9148936170212765,
      "grad_norm": 0.38106369972229004,
      "learning_rate": 0.0002170212765957447,
      "loss": 0.5182,
      "step": 920
    },
    {
      "epoch": 3.9361702127659575,
      "grad_norm": 0.44818058609962463,
      "learning_rate": 0.0002127659574468085,
      "loss": 0.4875,
      "step": 925
    },
    {
      "epoch": 3.9574468085106385,
      "grad_norm": 0.3101024925708771,
      "learning_rate": 0.00020851063829787234,
      "loss": 0.5498,
      "step": 930
    },
    {
      "epoch": 3.978723404255319,
      "grad_norm": 0.4035079777240753,
      "learning_rate": 0.00020425531914893618,
      "loss": 0.5139,
      "step": 935
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.4626338481903076,
      "learning_rate": 0.0002,
      "loss": 0.4683,
      "step": 940
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7290666666666666,
      "eval_loss": 0.5313977003097534,
      "eval_runtime": 52.259,
      "eval_samples_per_second": 71.758,
      "eval_steps_per_second": 1.129,
      "step": 940
    },
    {
      "epoch": 4.0212765957446805,
      "grad_norm": 0.3656058609485626,
      "learning_rate": 0.00019574468085106384,
      "loss": 0.4576,
      "step": 945
    },
    {
      "epoch": 4.042553191489362,
      "grad_norm": 0.6442248225212097,
      "learning_rate": 0.00019148936170212765,
      "loss": 0.4869,
      "step": 950
    },
    {
      "epoch": 4.0638297872340425,
      "grad_norm": 0.8725343942642212,
      "learning_rate": 0.00018723404255319148,
      "loss": 0.4081,
      "step": 955
    },
    {
      "epoch": 4.085106382978723,
      "grad_norm": 0.5488789677619934,
      "learning_rate": 0.00018297872340425532,
      "loss": 0.3774,
      "step": 960
    },
    {
      "epoch": 4.1063829787234045,
      "grad_norm": 0.45871075987815857,
      "learning_rate": 0.00017872340425531915,
      "loss": 0.3895,
      "step": 965
    },
    {
      "epoch": 4.127659574468085,
      "grad_norm": 0.7183250784873962,
      "learning_rate": 0.00017446808510638298,
      "loss": 0.4216,
      "step": 970
    },
    {
      "epoch": 4.148936170212766,
      "grad_norm": 0.43252503871917725,
      "learning_rate": 0.00017021276595744682,
      "loss": 0.4306,
      "step": 975
    },
    {
      "epoch": 4.170212765957447,
      "grad_norm": 0.5714681148529053,
      "learning_rate": 0.00016595744680851062,
      "loss": 0.4607,
      "step": 980
    },
    {
      "epoch": 4.191489361702128,
      "grad_norm": 0.5099291801452637,
      "learning_rate": 0.00016170212765957449,
      "loss": 0.372,
      "step": 985
    },
    {
      "epoch": 4.212765957446808,
      "grad_norm": 0.5010551810264587,
      "learning_rate": 0.00015744680851063832,
      "loss": 0.4414,
      "step": 990
    },
    {
      "epoch": 4.23404255319149,
      "grad_norm": 0.6585486531257629,
      "learning_rate": 0.00015319148936170213,
      "loss": 0.4191,
      "step": 995
    },
    {
      "epoch": 4.25531914893617,
      "grad_norm": 0.5043871402740479,
      "learning_rate": 0.00014893617021276596,
      "loss": 0.4273,
      "step": 1000
    },
    {
      "epoch": 4.276595744680851,
      "grad_norm": 0.4368508756160736,
      "learning_rate": 0.00014468085106382977,
      "loss": 0.4329,
      "step": 1005
    },
    {
      "epoch": 4.297872340425532,
      "grad_norm": 0.5174155235290527,
      "learning_rate": 0.00014042553191489363,
      "loss": 0.4256,
      "step": 1010
    },
    {
      "epoch": 4.319148936170213,
      "grad_norm": 0.7088821530342102,
      "learning_rate": 0.00013617021276595746,
      "loss": 0.4025,
      "step": 1015
    },
    {
      "epoch": 4.340425531914893,
      "grad_norm": 0.41731932759284973,
      "learning_rate": 0.00013191489361702127,
      "loss": 0.4018,
      "step": 1020
    },
    {
      "epoch": 4.361702127659575,
      "grad_norm": 0.47780218720436096,
      "learning_rate": 0.0001276595744680851,
      "loss": 0.4683,
      "step": 1025
    },
    {
      "epoch": 4.382978723404255,
      "grad_norm": 0.49915027618408203,
      "learning_rate": 0.00012340425531914893,
      "loss": 0.4643,
      "step": 1030
    },
    {
      "epoch": 4.404255319148936,
      "grad_norm": 0.5682059526443481,
      "learning_rate": 0.00011914893617021278,
      "loss": 0.4259,
      "step": 1035
    },
    {
      "epoch": 4.425531914893617,
      "grad_norm": 0.36220914125442505,
      "learning_rate": 0.0001148936170212766,
      "loss": 0.4116,
      "step": 1040
    },
    {
      "epoch": 4.446808510638298,
      "grad_norm": 0.5478158593177795,
      "learning_rate": 0.00011063829787234042,
      "loss": 0.4299,
      "step": 1045
    },
    {
      "epoch": 4.468085106382979,
      "grad_norm": 0.5897641181945801,
      "learning_rate": 0.00010638297872340425,
      "loss": 0.3619,
      "step": 1050
    },
    {
      "epoch": 4.48936170212766,
      "grad_norm": 1.084243893623352,
      "learning_rate": 0.00010212765957446809,
      "loss": 0.4211,
      "step": 1055
    },
    {
      "epoch": 4.51063829787234,
      "grad_norm": 0.7980880737304688,
      "learning_rate": 9.787234042553192e-05,
      "loss": 0.4053,
      "step": 1060
    },
    {
      "epoch": 4.531914893617021,
      "grad_norm": 0.9330500364303589,
      "learning_rate": 9.361702127659574e-05,
      "loss": 0.4183,
      "step": 1065
    },
    {
      "epoch": 4.553191489361702,
      "grad_norm": 0.40023094415664673,
      "learning_rate": 8.936170212765958e-05,
      "loss": 0.4343,
      "step": 1070
    },
    {
      "epoch": 4.574468085106383,
      "grad_norm": 0.6411470770835876,
      "learning_rate": 8.510638297872341e-05,
      "loss": 0.4096,
      "step": 1075
    },
    {
      "epoch": 4.595744680851064,
      "grad_norm": 0.4613640308380127,
      "learning_rate": 8.085106382978724e-05,
      "loss": 0.4089,
      "step": 1080
    },
    {
      "epoch": 4.617021276595745,
      "grad_norm": 0.5364215970039368,
      "learning_rate": 7.659574468085106e-05,
      "loss": 0.406,
      "step": 1085
    },
    {
      "epoch": 4.638297872340425,
      "grad_norm": 0.7170926928520203,
      "learning_rate": 7.234042553191488e-05,
      "loss": 0.3827,
      "step": 1090
    },
    {
      "epoch": 4.659574468085106,
      "grad_norm": 0.5427092909812927,
      "learning_rate": 6.808510638297873e-05,
      "loss": 0.4274,
      "step": 1095
    },
    {
      "epoch": 4.680851063829787,
      "grad_norm": 0.44160687923431396,
      "learning_rate": 6.382978723404255e-05,
      "loss": 0.4182,
      "step": 1100
    },
    {
      "epoch": 4.702127659574468,
      "grad_norm": 0.5841237902641296,
      "learning_rate": 5.957446808510639e-05,
      "loss": 0.4459,
      "step": 1105
    },
    {
      "epoch": 4.723404255319149,
      "grad_norm": 0.6145776510238647,
      "learning_rate": 5.531914893617021e-05,
      "loss": 0.4415,
      "step": 1110
    },
    {
      "epoch": 4.74468085106383,
      "grad_norm": 0.44807735085487366,
      "learning_rate": 5.1063829787234044e-05,
      "loss": 0.4248,
      "step": 1115
    },
    {
      "epoch": 4.76595744680851,
      "grad_norm": 0.7016127109527588,
      "learning_rate": 4.680851063829787e-05,
      "loss": 0.3613,
      "step": 1120
    },
    {
      "epoch": 4.787234042553192,
      "grad_norm": 0.5572742819786072,
      "learning_rate": 4.2553191489361704e-05,
      "loss": 0.4027,
      "step": 1125
    },
    {
      "epoch": 4.808510638297872,
      "grad_norm": 0.5368435978889465,
      "learning_rate": 3.829787234042553e-05,
      "loss": 0.4111,
      "step": 1130
    },
    {
      "epoch": 4.829787234042553,
      "grad_norm": 0.4862489700317383,
      "learning_rate": 3.4042553191489365e-05,
      "loss": 0.3663,
      "step": 1135
    },
    {
      "epoch": 4.851063829787234,
      "grad_norm": 0.6198825240135193,
      "learning_rate": 2.9787234042553195e-05,
      "loss": 0.3791,
      "step": 1140
    },
    {
      "epoch": 4.872340425531915,
      "grad_norm": 0.5688868165016174,
      "learning_rate": 2.5531914893617022e-05,
      "loss": 0.393,
      "step": 1145
    },
    {
      "epoch": 4.8936170212765955,
      "grad_norm": 0.44319066405296326,
      "learning_rate": 2.1276595744680852e-05,
      "loss": 0.3728,
      "step": 1150
    },
    {
      "epoch": 4.914893617021277,
      "grad_norm": 0.6268962621688843,
      "learning_rate": 1.7021276595744682e-05,
      "loss": 0.3832,
      "step": 1155
    },
    {
      "epoch": 4.9361702127659575,
      "grad_norm": 0.41478314995765686,
      "learning_rate": 1.2765957446808511e-05,
      "loss": 0.3647,
      "step": 1160
    },
    {
      "epoch": 4.957446808510638,
      "grad_norm": 0.8043156266212463,
      "learning_rate": 8.510638297872341e-06,
      "loss": 0.3705,
      "step": 1165
    },
    {
      "epoch": 4.9787234042553195,
      "grad_norm": 0.5503541827201843,
      "learning_rate": 4.255319148936171e-06,
      "loss": 0.3862,
      "step": 1170
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6788877844810486,
      "learning_rate": 0.0,
      "loss": 0.3694,
      "step": 1175
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7538666666666667,
      "eval_loss": 0.5220404863357544,
      "eval_runtime": 52.803,
      "eval_samples_per_second": 71.019,
      "eval_steps_per_second": 1.117,
      "step": 1175
    },
    {
      "epoch": 5.0,
      "step": 1175,
      "total_flos": 5.8118992210944e+18,
      "train_loss": 0.5645027552259729,
      "train_runtime": 2886.1261,
      "train_samples_per_second": 25.986,
      "train_steps_per_second": 0.407
    }
  ],
  "logging_steps": 5,
  "max_steps": 1175,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 5.8118992210944e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}