{
  "best_metric": 0.3553876280784607,
  "best_model_checkpoint": "./vit-base-tm/checkpoint-1000",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 1836,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.00019891067538126362,
      "loss": 1.0656,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019782135076252725,
      "loss": 0.9841,
      "step": 20
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019673202614379085,
      "loss": 0.9086,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019564270152505449,
      "loss": 0.848,
      "step": 40
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001945533769063181,
      "loss": 0.7769,
      "step": 50
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001934640522875817,
      "loss": 0.7644,
      "step": 60
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019237472766884533,
      "loss": 0.7184,
      "step": 70
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019128540305010894,
      "loss": 0.7307,
      "step": 80
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019019607843137254,
      "loss": 0.7106,
      "step": 90
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018910675381263617,
      "loss": 0.661,
      "step": 100
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001880174291938998,
      "loss": 0.6511,
      "step": 110
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001869281045751634,
      "loss": 0.6362,
      "step": 120
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018583877995642702,
      "loss": 0.6309,
      "step": 130
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00018474945533769062,
      "loss": 0.6234,
      "step": 140
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00018366013071895426,
      "loss": 0.6143,
      "step": 150
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001825708061002179,
      "loss": 0.5857,
      "step": 160
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001814814814814815,
      "loss": 0.5685,
      "step": 170
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001803921568627451,
      "loss": 0.5813,
      "step": 180
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00017930283224400873,
      "loss": 0.566,
      "step": 190
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017821350762527234,
      "loss": 0.5763,
      "step": 200
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017712418300653594,
      "loss": 0.5667,
      "step": 210
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00017603485838779955,
      "loss": 0.5535,
      "step": 220
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001749455337690632,
      "loss": 0.5493,
      "step": 230
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00017385620915032682,
      "loss": 0.5399,
      "step": 240
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00017276688453159042,
      "loss": 0.5481,
      "step": 250
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00017167755991285403,
      "loss": 0.538,
      "step": 260
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00017058823529411766,
      "loss": 0.5244,
      "step": 270
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00016949891067538126,
      "loss": 0.5112,
      "step": 280
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001684095860566449,
      "loss": 0.4929,
      "step": 290
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001673202614379085,
      "loss": 0.5079,
      "step": 300
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00016623093681917214,
      "loss": 0.5041,
      "step": 310
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00016514161220043574,
      "loss": 0.4833,
      "step": 320
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00016405228758169935,
      "loss": 0.477,
      "step": 330
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00016296296296296295,
      "loss": 0.4774,
      "step": 340
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00016187363834422659,
      "loss": 0.4814,
      "step": 350
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00016078431372549022,
      "loss": 0.476,
      "step": 360
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00015969498910675382,
      "loss": 0.4721,
      "step": 370
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00015860566448801743,
      "loss": 0.4571,
      "step": 380
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00015751633986928106,
      "loss": 0.4494,
      "step": 390
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00015642701525054467,
      "loss": 0.4479,
      "step": 400
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001553376906318083,
      "loss": 0.4542,
      "step": 410
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001542483660130719,
      "loss": 0.4495,
      "step": 420
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001531590413943355,
      "loss": 0.44,
      "step": 430
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00015206971677559914,
      "loss": 0.4399,
      "step": 440
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00015098039215686275,
      "loss": 0.4468,
      "step": 450
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00014989106753812636,
      "loss": 0.4324,
      "step": 460
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00014880174291939,
      "loss": 0.3651,
      "step": 470
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00014771241830065362,
      "loss": 0.3462,
      "step": 480
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00014662309368191723,
      "loss": 0.3539,
      "step": 490
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00014553376906318083,
      "loss": 0.3618,
      "step": 500
    },
    {
      "epoch": 1.09,
      "eval_accuracy": 0.8273005071984374,
      "eval_loss": 0.4216799736022949,
      "eval_runtime": 229.0953,
      "eval_samples_per_second": 138.558,
      "eval_steps_per_second": 17.32,
      "step": 500
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00014444444444444444,
      "loss": 0.3515,
      "step": 510
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00014335511982570807,
      "loss": 0.3366,
      "step": 520
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00014226579520697168,
      "loss": 0.3351,
      "step": 530
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001411764705882353,
      "loss": 0.3493,
      "step": 540
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00014008714596949891,
      "loss": 0.3515,
      "step": 550
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00013899782135076255,
      "loss": 0.3332,
      "step": 560
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00013790849673202615,
      "loss": 0.3391,
      "step": 570
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00013681917211328976,
      "loss": 0.3403,
      "step": 580
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00013572984749455336,
      "loss": 0.348,
      "step": 590
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.000134640522875817,
      "loss": 0.3339,
      "step": 600
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00013355119825708063,
      "loss": 0.3472,
      "step": 610
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00013246187363834424,
      "loss": 0.3528,
      "step": 620
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00013137254901960784,
      "loss": 0.3509,
      "step": 630
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00013028322440087147,
      "loss": 0.3353,
      "step": 640
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00012919389978213508,
      "loss": 0.3356,
      "step": 650
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00012810457516339868,
      "loss": 0.3341,
      "step": 660
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00012701525054466232,
      "loss": 0.3528,
      "step": 670
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00012592592592592592,
      "loss": 0.3373,
      "step": 680
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00012483660130718956,
      "loss": 0.3326,
      "step": 690
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00012374727668845316,
      "loss": 0.3192,
      "step": 700
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00012265795206971677,
      "loss": 0.3245,
      "step": 710
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00012156862745098039,
      "loss": 0.3185,
      "step": 720
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00012047930283224402,
      "loss": 0.325,
      "step": 730
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00011938997821350764,
      "loss": 0.3214,
      "step": 740
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00011830065359477124,
      "loss": 0.3032,
      "step": 750
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00011721132897603486,
      "loss": 0.3044,
      "step": 760
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00011612200435729847,
      "loss": 0.3171,
      "step": 770
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00011503267973856209,
      "loss": 0.3077,
      "step": 780
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00011394335511982572,
      "loss": 0.298,
      "step": 790
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00011285403050108934,
      "loss": 0.3061,
      "step": 800
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00011176470588235294,
      "loss": 0.3001,
      "step": 810
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00011067538126361656,
      "loss": 0.2966,
      "step": 820
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00010958605664488017,
      "loss": 0.3052,
      "step": 830
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00010849673202614379,
      "loss": 0.2941,
      "step": 840
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00010740740740740742,
      "loss": 0.2853,
      "step": 850
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00010631808278867104,
      "loss": 0.2939,
      "step": 860
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00010522875816993465,
      "loss": 0.2928,
      "step": 870
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00010413943355119827,
      "loss": 0.2996,
      "step": 880
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00010305010893246187,
      "loss": 0.2912,
      "step": 890
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00010196078431372549,
      "loss": 0.272,
      "step": 900
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0001008714596949891,
      "loss": 0.2822,
      "step": 910
    },
    {
      "epoch": 2.0,
      "learning_rate": 9.978213507625273e-05,
      "loss": 0.2329,
      "step": 920
    },
    {
      "epoch": 2.03,
      "learning_rate": 9.869281045751635e-05,
      "loss": 0.2018,
      "step": 930
    },
    {
      "epoch": 2.05,
      "learning_rate": 9.760348583877997e-05,
      "loss": 0.1763,
      "step": 940
    },
    {
      "epoch": 2.07,
      "learning_rate": 9.651416122004357e-05,
      "loss": 0.1682,
      "step": 950
    },
    {
      "epoch": 2.09,
      "learning_rate": 9.54248366013072e-05,
      "loss": 0.1718,
      "step": 960
    },
    {
      "epoch": 2.11,
      "learning_rate": 9.433551198257081e-05,
      "loss": 0.1859,
      "step": 970
    },
    {
      "epoch": 2.14,
      "learning_rate": 9.324618736383443e-05,
      "loss": 0.1757,
      "step": 980
    },
    {
      "epoch": 2.16,
      "learning_rate": 9.215686274509804e-05,
      "loss": 0.1895,
      "step": 990
    },
    {
      "epoch": 2.18,
      "learning_rate": 9.106753812636167e-05,
      "loss": 0.1805,
      "step": 1000
    },
    {
      "epoch": 2.18,
      "eval_accuracy": 0.8674353400749771,
      "eval_loss": 0.3553876280784607,
      "eval_runtime": 215.1066,
      "eval_samples_per_second": 147.569,
      "eval_steps_per_second": 18.447,
      "step": 1000
    },
    {
      "epoch": 2.2,
      "learning_rate": 8.997821350762527e-05,
      "loss": 0.1868,
      "step": 1010
    },
    {
      "epoch": 2.22,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.1725,
      "step": 1020
    },
    {
      "epoch": 2.24,
      "learning_rate": 8.779956427015251e-05,
      "loss": 0.1837,
      "step": 1030
    },
    {
      "epoch": 2.27,
      "learning_rate": 8.671023965141613e-05,
      "loss": 0.175,
      "step": 1040
    },
    {
      "epoch": 2.29,
      "learning_rate": 8.562091503267974e-05,
      "loss": 0.1726,
      "step": 1050
    },
    {
      "epoch": 2.31,
      "learning_rate": 8.453159041394336e-05,
      "loss": 0.1747,
      "step": 1060
    },
    {
      "epoch": 2.33,
      "learning_rate": 8.344226579520698e-05,
      "loss": 0.1893,
      "step": 1070
    },
    {
      "epoch": 2.35,
      "learning_rate": 8.23529411764706e-05,
      "loss": 0.1769,
      "step": 1080
    },
    {
      "epoch": 2.37,
      "learning_rate": 8.126361655773421e-05,
      "loss": 0.181,
      "step": 1090
    },
    {
      "epoch": 2.4,
      "learning_rate": 8.017429193899782e-05,
      "loss": 0.1761,
      "step": 1100
    },
    {
      "epoch": 2.42,
      "learning_rate": 7.908496732026144e-05,
      "loss": 0.1727,
      "step": 1110
    },
    {
      "epoch": 2.44,
      "learning_rate": 7.799564270152506e-05,
      "loss": 0.1836,
      "step": 1120
    },
    {
      "epoch": 2.46,
      "learning_rate": 7.690631808278868e-05,
      "loss": 0.1666,
      "step": 1130
    },
    {
      "epoch": 2.48,
      "learning_rate": 7.581699346405228e-05,
      "loss": 0.173,
      "step": 1140
    },
    {
      "epoch": 2.51,
      "learning_rate": 7.472766884531592e-05,
      "loss": 0.1717,
      "step": 1150
    },
    {
      "epoch": 2.53,
      "learning_rate": 7.363834422657952e-05,
      "loss": 0.1848,
      "step": 1160
    },
    {
      "epoch": 2.55,
      "learning_rate": 7.254901960784314e-05,
      "loss": 0.1552,
      "step": 1170
    },
    {
      "epoch": 2.57,
      "learning_rate": 7.145969498910676e-05,
      "loss": 0.1556,
      "step": 1180
    },
    {
      "epoch": 2.59,
      "learning_rate": 7.037037037037038e-05,
      "loss": 0.1679,
      "step": 1190
    },
    {
      "epoch": 2.61,
      "learning_rate": 6.928104575163398e-05,
      "loss": 0.1657,
      "step": 1200
    },
    {
      "epoch": 2.64,
      "learning_rate": 6.81917211328976e-05,
      "loss": 0.1542,
      "step": 1210
    },
    {
      "epoch": 2.66,
      "learning_rate": 6.710239651416122e-05,
      "loss": 0.1823,
      "step": 1220
    },
    {
      "epoch": 2.68,
      "learning_rate": 6.601307189542484e-05,
      "loss": 0.162,
      "step": 1230
    },
    {
      "epoch": 2.7,
      "learning_rate": 6.492374727668845e-05,
      "loss": 0.1571,
      "step": 1240
    },
    {
      "epoch": 2.72,
      "learning_rate": 6.383442265795208e-05,
      "loss": 0.1717,
      "step": 1250
    },
    {
      "epoch": 2.75,
      "learning_rate": 6.274509803921569e-05,
      "loss": 0.1654,
      "step": 1260
    },
    {
      "epoch": 2.77,
      "learning_rate": 6.16557734204793e-05,
      "loss": 0.1633,
      "step": 1270
    },
    {
      "epoch": 2.79,
      "learning_rate": 6.0566448801742924e-05,
      "loss": 0.1489,
      "step": 1280
    },
    {
      "epoch": 2.81,
      "learning_rate": 5.9477124183006536e-05,
      "loss": 0.1651,
      "step": 1290
    },
    {
      "epoch": 2.83,
      "learning_rate": 5.838779956427015e-05,
      "loss": 0.161,
      "step": 1300
    },
    {
      "epoch": 2.85,
      "learning_rate": 5.7298474945533774e-05,
      "loss": 0.1564,
      "step": 1310
    },
    {
      "epoch": 2.88,
      "learning_rate": 5.620915032679739e-05,
      "loss": 0.1521,
      "step": 1320
    },
    {
      "epoch": 2.9,
      "learning_rate": 5.5119825708061e-05,
      "loss": 0.1593,
      "step": 1330
    },
    {
      "epoch": 2.92,
      "learning_rate": 5.4030501089324625e-05,
      "loss": 0.1401,
      "step": 1340
    },
    {
      "epoch": 2.94,
      "learning_rate": 5.294117647058824e-05,
      "loss": 0.1478,
      "step": 1350
    },
    {
      "epoch": 2.96,
      "learning_rate": 5.185185185185185e-05,
      "loss": 0.1415,
      "step": 1360
    },
    {
      "epoch": 2.98,
      "learning_rate": 5.0762527233115476e-05,
      "loss": 0.1473,
      "step": 1370
    },
    {
      "epoch": 3.01,
      "learning_rate": 4.967320261437909e-05,
      "loss": 0.1325,
      "step": 1380
    },
    {
      "epoch": 3.03,
      "learning_rate": 4.85838779956427e-05,
      "loss": 0.0714,
      "step": 1390
    },
    {
      "epoch": 3.05,
      "learning_rate": 4.749455337690632e-05,
      "loss": 0.0817,
      "step": 1400
    },
    {
      "epoch": 3.07,
      "learning_rate": 4.640522875816994e-05,
      "loss": 0.0661,
      "step": 1410
    },
    {
      "epoch": 3.09,
      "learning_rate": 4.531590413943355e-05,
      "loss": 0.064,
      "step": 1420
    },
    {
      "epoch": 3.12,
      "learning_rate": 4.422657952069717e-05,
      "loss": 0.0747,
      "step": 1430
    },
    {
      "epoch": 3.14,
      "learning_rate": 4.313725490196079e-05,
      "loss": 0.0613,
      "step": 1440
    },
    {
      "epoch": 3.16,
      "learning_rate": 4.20479302832244e-05,
      "loss": 0.0767,
      "step": 1450
    },
    {
      "epoch": 3.18,
      "learning_rate": 4.095860566448802e-05,
      "loss": 0.0684,
      "step": 1460
    },
    {
      "epoch": 3.2,
      "learning_rate": 3.986928104575164e-05,
      "loss": 0.0631,
      "step": 1470
    },
    {
      "epoch": 3.22,
      "learning_rate": 3.877995642701525e-05,
      "loss": 0.0635,
      "step": 1480
    },
    {
      "epoch": 3.25,
      "learning_rate": 3.769063180827887e-05,
      "loss": 0.0649,
      "step": 1490
    },
    {
      "epoch": 3.27,
      "learning_rate": 3.6601307189542484e-05,
      "loss": 0.0803,
      "step": 1500
    },
    {
      "epoch": 3.27,
      "eval_accuracy": 0.8922597108023816,
      "eval_loss": 0.35698094964027405,
      "eval_runtime": 218.7233,
      "eval_samples_per_second": 145.129,
      "eval_steps_per_second": 18.142,
      "step": 1500
    },
    {
      "epoch": 3.29,
      "learning_rate": 3.55119825708061e-05,
      "loss": 0.0703,
      "step": 1510
    },
    {
      "epoch": 3.31,
      "learning_rate": 3.442265795206972e-05,
      "loss": 0.0635,
      "step": 1520
    },
    {
      "epoch": 3.33,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0739,
      "step": 1530
    },
    {
      "epoch": 3.36,
      "learning_rate": 3.2244008714596954e-05,
      "loss": 0.0722,
      "step": 1540
    },
    {
      "epoch": 3.38,
      "learning_rate": 3.115468409586057e-05,
      "loss": 0.0662,
      "step": 1550
    },
    {
      "epoch": 3.4,
      "learning_rate": 3.0065359477124182e-05,
      "loss": 0.0602,
      "step": 1560
    },
    {
      "epoch": 3.42,
      "learning_rate": 2.89760348583878e-05,
      "loss": 0.0686,
      "step": 1570
    },
    {
      "epoch": 3.44,
      "learning_rate": 2.788671023965142e-05,
      "loss": 0.0687,
      "step": 1580
    },
    {
      "epoch": 3.46,
      "learning_rate": 2.6797385620915033e-05,
      "loss": 0.06,
      "step": 1590
    },
    {
      "epoch": 3.49,
      "learning_rate": 2.5708061002178652e-05,
      "loss": 0.0626,
      "step": 1600
    },
    {
      "epoch": 3.51,
      "learning_rate": 2.4618736383442268e-05,
      "loss": 0.0602,
      "step": 1610
    },
    {
      "epoch": 3.53,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 0.0615,
      "step": 1620
    },
    {
      "epoch": 3.55,
      "learning_rate": 2.24400871459695e-05,
      "loss": 0.0704,
      "step": 1630
    },
    {
      "epoch": 3.57,
      "learning_rate": 2.135076252723312e-05,
      "loss": 0.0602,
      "step": 1640
    },
    {
      "epoch": 3.59,
      "learning_rate": 2.0261437908496734e-05,
      "loss": 0.0625,
      "step": 1650
    },
    {
      "epoch": 3.62,
      "learning_rate": 1.917211328976035e-05,
      "loss": 0.0682,
      "step": 1660
    },
    {
      "epoch": 3.64,
      "learning_rate": 1.8082788671023966e-05,
      "loss": 0.0635,
      "step": 1670
    },
    {
      "epoch": 3.66,
      "learning_rate": 1.6993464052287582e-05,
      "loss": 0.065,
      "step": 1680
    },
    {
      "epoch": 3.68,
      "learning_rate": 1.5904139433551197e-05,
      "loss": 0.0611,
      "step": 1690
    },
    {
      "epoch": 3.7,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.0562,
      "step": 1700
    },
    {
      "epoch": 3.73,
      "learning_rate": 1.3725490196078432e-05,
      "loss": 0.0614,
      "step": 1710
    },
    {
      "epoch": 3.75,
      "learning_rate": 1.2636165577342048e-05,
      "loss": 0.0604,
      "step": 1720
    },
    {
      "epoch": 3.77,
      "learning_rate": 1.1546840958605664e-05,
      "loss": 0.0562,
      "step": 1730
    },
    {
      "epoch": 3.79,
      "learning_rate": 1.0457516339869281e-05,
      "loss": 0.0558,
      "step": 1740
    },
    {
      "epoch": 3.81,
      "learning_rate": 9.368191721132897e-06,
      "loss": 0.0544,
      "step": 1750
    },
    {
      "epoch": 3.83,
      "learning_rate": 8.278867102396515e-06,
      "loss": 0.0603,
      "step": 1760
    },
    {
      "epoch": 3.86,
      "learning_rate": 7.1895424836601305e-06,
      "loss": 0.0611,
      "step": 1770
    },
    {
      "epoch": 3.88,
      "learning_rate": 6.100217864923748e-06,
      "loss": 0.0546,
      "step": 1780
    },
    {
      "epoch": 3.9,
      "learning_rate": 5.010893246187364e-06,
      "loss": 0.0617,
      "step": 1790
    },
    {
      "epoch": 3.92,
      "learning_rate": 3.92156862745098e-06,
      "loss": 0.0592,
      "step": 1800
    },
    {
      "epoch": 3.94,
      "learning_rate": 2.832244008714597e-06,
      "loss": 0.051,
      "step": 1810
    },
    {
      "epoch": 3.97,
      "learning_rate": 1.7429193899782138e-06,
      "loss": 0.05,
      "step": 1820
    },
    {
      "epoch": 3.99,
      "learning_rate": 6.535947712418301e-07,
      "loss": 0.0571,
      "step": 1830
    },
    {
      "epoch": 4.0,
      "step": 1836,
      "total_flos": 7.2689377616381805e+19,
      "train_loss": 0.28534620919128906,
      "train_runtime": 7364.2492,
      "train_samples_per_second": 127.374,
      "train_steps_per_second": 0.249
    }
  ],
  "logging_steps": 10,
  "max_steps": 1836,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 7.2689377616381805e+19,
  "trial_name": null,
  "trial_params": null
}