{
  "best_metric": 0.994671729544341,
  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-255",
  "epoch": 4.995102840352596,
  "eval_steps": 500,
  "global_step": 1275,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.039177277179236046,
      "grad_norm": 9.329336166381836,
      "learning_rate": 3.90625e-06,
      "loss": 0.7,
      "step": 10
    },
    {
      "epoch": 0.07835455435847209,
      "grad_norm": 4.470575332641602,
      "learning_rate": 7.8125e-06,
      "loss": 0.4115,
      "step": 20
    },
    {
      "epoch": 0.11753183153770813,
      "grad_norm": 1.0650607347488403,
      "learning_rate": 1.171875e-05,
      "loss": 0.1272,
      "step": 30
    },
    {
      "epoch": 0.15670910871694418,
      "grad_norm": 0.7108937501907349,
      "learning_rate": 1.5625e-05,
      "loss": 0.0479,
      "step": 40
    },
    {
      "epoch": 0.1958863858961802,
      "grad_norm": 1.0625723600387573,
      "learning_rate": 1.953125e-05,
      "loss": 0.0359,
      "step": 50
    },
    {
      "epoch": 0.23506366307541626,
      "grad_norm": 0.1246357336640358,
      "learning_rate": 2.34375e-05,
      "loss": 0.0227,
      "step": 60
    },
    {
      "epoch": 0.2742409402546523,
      "grad_norm": 0.5148888826370239,
      "learning_rate": 2.734375e-05,
      "loss": 0.0295,
      "step": 70
    },
    {
      "epoch": 0.31341821743388837,
      "grad_norm": 0.9743920564651489,
      "learning_rate": 3.125e-05,
      "loss": 0.0294,
      "step": 80
    },
    {
      "epoch": 0.3525954946131244,
      "grad_norm": 0.31461623311042786,
      "learning_rate": 3.5156250000000004e-05,
      "loss": 0.0289,
      "step": 90
    },
    {
      "epoch": 0.3917727717923604,
      "grad_norm": 1.0115059614181519,
      "learning_rate": 3.90625e-05,
      "loss": 0.0391,
      "step": 100
    },
    {
      "epoch": 0.4309500489715965,
      "grad_norm": 0.08507003635168076,
      "learning_rate": 4.2968750000000004e-05,
      "loss": 0.018,
      "step": 110
    },
    {
      "epoch": 0.4701273261508325,
      "grad_norm": 0.1573338657617569,
      "learning_rate": 4.6875e-05,
      "loss": 0.0214,
      "step": 120
    },
    {
      "epoch": 0.5093046033300686,
      "grad_norm": 0.4784347712993622,
      "learning_rate": 4.9912816041848304e-05,
      "loss": 0.0264,
      "step": 130
    },
    {
      "epoch": 0.5484818805093046,
      "grad_norm": 0.2329588085412979,
      "learning_rate": 4.94768962510898e-05,
      "loss": 0.0277,
      "step": 140
    },
    {
      "epoch": 0.5876591576885406,
      "grad_norm": 0.05806314945220947,
      "learning_rate": 4.90409764603313e-05,
      "loss": 0.0221,
      "step": 150
    },
    {
      "epoch": 0.6268364348677767,
      "grad_norm": 1.9614442586898804,
      "learning_rate": 4.86050566695728e-05,
      "loss": 0.0311,
      "step": 160
    },
    {
      "epoch": 0.6660137120470128,
      "grad_norm": 1.0261849164962769,
      "learning_rate": 4.8169136878814306e-05,
      "loss": 0.0334,
      "step": 170
    },
    {
      "epoch": 0.7051909892262488,
      "grad_norm": 0.30455902218818665,
      "learning_rate": 4.7733217088055796e-05,
      "loss": 0.0271,
      "step": 180
    },
    {
      "epoch": 0.7443682664054848,
      "grad_norm": 0.38795918226242065,
      "learning_rate": 4.72972972972973e-05,
      "loss": 0.018,
      "step": 190
    },
    {
      "epoch": 0.7835455435847208,
      "grad_norm": 0.25275129079818726,
      "learning_rate": 4.68613775065388e-05,
      "loss": 0.0331,
      "step": 200
    },
    {
      "epoch": 0.8227228207639569,
      "grad_norm": 0.15323331952095032,
      "learning_rate": 4.642545771578029e-05,
      "loss": 0.0242,
      "step": 210
    },
    {
      "epoch": 0.861900097943193,
      "grad_norm": 0.4740907847881317,
      "learning_rate": 4.59895379250218e-05,
      "loss": 0.0232,
      "step": 220
    },
    {
      "epoch": 0.901077375122429,
      "grad_norm": 0.5308133363723755,
      "learning_rate": 4.55536181342633e-05,
      "loss": 0.0177,
      "step": 230
    },
    {
      "epoch": 0.940254652301665,
      "grad_norm": 0.985102653503418,
      "learning_rate": 4.51176983435048e-05,
      "loss": 0.0301,
      "step": 240
    },
    {
      "epoch": 0.9794319294809011,
      "grad_norm": 0.6651228070259094,
      "learning_rate": 4.4681778552746294e-05,
      "loss": 0.0268,
      "step": 250
    },
    {
      "epoch": 0.9990205680705191,
      "eval_accuracy": 0.994671729544341,
      "eval_loss": 0.025641364976763725,
      "eval_runtime": 164.878,
      "eval_samples_per_second": 99.031,
      "eval_steps_per_second": 1.553,
      "step": 255
    },
    {
      "epoch": 1.018609206660137,
      "grad_norm": 0.157534658908844,
      "learning_rate": 4.42458587619878e-05,
      "loss": 0.0175,
      "step": 260
    },
    {
      "epoch": 1.0577864838393731,
      "grad_norm": 0.3950434923171997,
      "learning_rate": 4.3809938971229295e-05,
      "loss": 0.0205,
      "step": 270
    },
    {
      "epoch": 1.0969637610186092,
      "grad_norm": 0.771115243434906,
      "learning_rate": 4.337401918047079e-05,
      "loss": 0.032,
      "step": 280
    },
    {
      "epoch": 1.1361410381978452,
      "grad_norm": 0.24406306445598602,
      "learning_rate": 4.2938099389712295e-05,
      "loss": 0.0261,
      "step": 290
    },
    {
      "epoch": 1.1753183153770812,
      "grad_norm": 0.5867096781730652,
      "learning_rate": 4.250217959895379e-05,
      "loss": 0.0297,
      "step": 300
    },
    {
      "epoch": 1.2144955925563172,
      "grad_norm": 0.3914402723312378,
      "learning_rate": 4.2066259808195296e-05,
      "loss": 0.0245,
      "step": 310
    },
    {
      "epoch": 1.2536728697355533,
      "grad_norm": 0.2989954352378845,
      "learning_rate": 4.163034001743679e-05,
      "loss": 0.0275,
      "step": 320
    },
    {
      "epoch": 1.2928501469147895,
      "grad_norm": 0.46654826402664185,
      "learning_rate": 4.119442022667829e-05,
      "loss": 0.031,
      "step": 330
    },
    {
      "epoch": 1.3320274240940255,
      "grad_norm": 0.17611253261566162,
      "learning_rate": 4.0758500435919793e-05,
      "loss": 0.0247,
      "step": 340
    },
    {
      "epoch": 1.3712047012732616,
      "grad_norm": 0.31176942586898804,
      "learning_rate": 4.032258064516129e-05,
      "loss": 0.0242,
      "step": 350
    },
    {
      "epoch": 1.4103819784524976,
      "grad_norm": 0.5007725954055786,
      "learning_rate": 3.9886660854402794e-05,
      "loss": 0.033,
      "step": 360
    },
    {
      "epoch": 1.4495592556317336,
      "grad_norm": 0.6336463093757629,
      "learning_rate": 3.945074106364429e-05,
      "loss": 0.0127,
      "step": 370
    },
    {
      "epoch": 1.4887365328109696,
      "grad_norm": 0.349540650844574,
      "learning_rate": 3.9014821272885795e-05,
      "loss": 0.0327,
      "step": 380
    },
    {
      "epoch": 1.5279138099902057,
      "grad_norm": 0.48749464750289917,
      "learning_rate": 3.857890148212729e-05,
      "loss": 0.0247,
      "step": 390
    },
    {
      "epoch": 1.5670910871694417,
      "grad_norm": 0.21512505412101746,
      "learning_rate": 3.814298169136879e-05,
      "loss": 0.0244,
      "step": 400
    },
    {
      "epoch": 1.606268364348678,
      "grad_norm": 0.1843574196100235,
      "learning_rate": 3.770706190061029e-05,
      "loss": 0.0238,
      "step": 410
    },
    {
      "epoch": 1.645445641527914,
      "grad_norm": 0.17209237813949585,
      "learning_rate": 3.727114210985179e-05,
      "loss": 0.0159,
      "step": 420
    },
    {
      "epoch": 1.68462291870715,
      "grad_norm": 0.17134279012680054,
      "learning_rate": 3.6835222319093286e-05,
      "loss": 0.0147,
      "step": 430
    },
    {
      "epoch": 1.723800195886386,
      "grad_norm": 0.3783511519432068,
      "learning_rate": 3.639930252833479e-05,
      "loss": 0.026,
      "step": 440
    },
    {
      "epoch": 1.762977473065622,
      "grad_norm": 0.20875829458236694,
      "learning_rate": 3.596338273757629e-05,
      "loss": 0.0169,
      "step": 450
    },
    {
      "epoch": 1.802154750244858,
      "grad_norm": 0.061811015009880066,
      "learning_rate": 3.552746294681778e-05,
      "loss": 0.0115,
      "step": 460
    },
    {
      "epoch": 1.841332027424094,
      "grad_norm": 0.5182923078536987,
      "learning_rate": 3.509154315605929e-05,
      "loss": 0.0217,
      "step": 470
    },
    {
      "epoch": 1.88050930460333,
      "grad_norm": 0.3887523114681244,
      "learning_rate": 3.465562336530079e-05,
      "loss": 0.0189,
      "step": 480
    },
    {
      "epoch": 1.9196865817825661,
      "grad_norm": 0.13711315393447876,
      "learning_rate": 3.421970357454228e-05,
      "loss": 0.0132,
      "step": 490
    },
    {
      "epoch": 1.9588638589618022,
      "grad_norm": 0.3663609027862549,
      "learning_rate": 3.3783783783783784e-05,
      "loss": 0.025,
      "step": 500
    },
    {
      "epoch": 1.9980411361410382,
      "grad_norm": 0.28243473172187805,
      "learning_rate": 3.334786399302529e-05,
      "loss": 0.0167,
      "step": 510
    },
    {
      "epoch": 1.9980411361410382,
      "eval_accuracy": 0.994671729544341,
      "eval_loss": 0.027501454576849937,
      "eval_runtime": 109.9626,
      "eval_samples_per_second": 148.487,
      "eval_steps_per_second": 2.328,
      "step": 510
    },
    {
      "epoch": 2.037218413320274,
      "grad_norm": 0.20075927674770355,
      "learning_rate": 3.2911944202266785e-05,
      "loss": 0.0189,
      "step": 520
    },
    {
      "epoch": 2.0763956904995102,
      "grad_norm": 0.5090253353118896,
      "learning_rate": 3.247602441150828e-05,
      "loss": 0.0158,
      "step": 530
    },
    {
      "epoch": 2.1155729676787463,
      "grad_norm": 0.20879769325256348,
      "learning_rate": 3.2040104620749785e-05,
      "loss": 0.0198,
      "step": 540
    },
    {
      "epoch": 2.1547502448579823,
      "grad_norm": 0.7945526242256165,
      "learning_rate": 3.160418482999128e-05,
      "loss": 0.0244,
      "step": 550
    },
    {
      "epoch": 2.1939275220372183,
      "grad_norm": 0.49813878536224365,
      "learning_rate": 3.116826503923278e-05,
      "loss": 0.0325,
      "step": 560
    },
    {
      "epoch": 2.2331047992164543,
      "grad_norm": 0.417555034160614,
      "learning_rate": 3.073234524847428e-05,
      "loss": 0.0245,
      "step": 570
    },
    {
      "epoch": 2.2722820763956904,
      "grad_norm": 0.13541927933692932,
      "learning_rate": 3.0296425457715783e-05,
      "loss": 0.0176,
      "step": 580
    },
    {
      "epoch": 2.3114593535749264,
      "grad_norm": 0.22694525122642517,
      "learning_rate": 2.9860505666957283e-05,
      "loss": 0.0199,
      "step": 590
    },
    {
      "epoch": 2.3506366307541624,
      "grad_norm": 0.06209595128893852,
      "learning_rate": 2.942458587619878e-05,
      "loss": 0.0127,
      "step": 600
    },
    {
      "epoch": 2.389813907933399,
      "grad_norm": 0.4733225703239441,
      "learning_rate": 2.898866608544028e-05,
      "loss": 0.0334,
      "step": 610
    },
    {
      "epoch": 2.4289911851126345,
      "grad_norm": 0.37968209385871887,
      "learning_rate": 2.855274629468178e-05,
      "loss": 0.028,
      "step": 620
    },
    {
      "epoch": 2.468168462291871,
      "grad_norm": 0.1550379991531372,
      "learning_rate": 2.8116826503923278e-05,
      "loss": 0.0227,
      "step": 630
    },
    {
      "epoch": 2.5073457394711065,
      "grad_norm": 0.4125171899795532,
      "learning_rate": 2.7680906713164778e-05,
      "loss": 0.0149,
      "step": 640
    },
    {
      "epoch": 2.546523016650343,
      "grad_norm": 0.6104760766029358,
      "learning_rate": 2.724498692240628e-05,
      "loss": 0.0256,
      "step": 650
    },
    {
      "epoch": 2.585700293829579,
      "grad_norm": 0.4356853663921356,
      "learning_rate": 2.6809067131647782e-05,
      "loss": 0.0222,
      "step": 660
    },
    {
      "epoch": 2.624877571008815,
      "grad_norm": 0.3686465322971344,
      "learning_rate": 2.6373147340889275e-05,
      "loss": 0.0213,
      "step": 670
    },
    {
      "epoch": 2.664054848188051,
      "grad_norm": 0.30900245904922485,
      "learning_rate": 2.5937227550130776e-05,
      "loss": 0.0226,
      "step": 680
    },
    {
      "epoch": 2.703232125367287,
      "grad_norm": 0.1763727217912674,
      "learning_rate": 2.550130775937228e-05,
      "loss": 0.0175,
      "step": 690
    },
    {
      "epoch": 2.742409402546523,
      "grad_norm": 0.7033935785293579,
      "learning_rate": 2.5065387968613773e-05,
      "loss": 0.0161,
      "step": 700
    },
    {
      "epoch": 2.781586679725759,
      "grad_norm": 0.4877593219280243,
      "learning_rate": 2.4629468177855277e-05,
      "loss": 0.0245,
      "step": 710
    },
    {
      "epoch": 2.820763956904995,
      "grad_norm": 0.22476495802402496,
      "learning_rate": 2.4193548387096777e-05,
      "loss": 0.0158,
      "step": 720
    },
    {
      "epoch": 2.859941234084231,
      "grad_norm": 0.5083233118057251,
      "learning_rate": 2.3757628596338274e-05,
      "loss": 0.02,
      "step": 730
    },
    {
      "epoch": 2.899118511263467,
      "grad_norm": 0.131087526679039,
      "learning_rate": 2.3321708805579774e-05,
      "loss": 0.021,
      "step": 740
    },
    {
      "epoch": 2.9382957884427032,
      "grad_norm": 0.2617853581905365,
      "learning_rate": 2.2885789014821274e-05,
      "loss": 0.0204,
      "step": 750
    },
    {
      "epoch": 2.9774730656219393,
      "grad_norm": 0.19207285344600677,
      "learning_rate": 2.244986922406277e-05,
      "loss": 0.0177,
      "step": 760
    },
    {
      "epoch": 2.997061704211557,
      "eval_accuracy": 0.9935693287604116,
      "eval_loss": 0.026763953268527985,
      "eval_runtime": 112.7695,
      "eval_samples_per_second": 144.791,
      "eval_steps_per_second": 2.27,
      "step": 765
    },
    {
      "epoch": 3.0166503428011753,
      "grad_norm": 0.7242885231971741,
      "learning_rate": 2.2013949433304275e-05,
      "loss": 0.0206,
      "step": 770
    },
    {
      "epoch": 3.0558276199804113,
      "grad_norm": 0.6204590201377869,
      "learning_rate": 2.1578029642545772e-05,
      "loss": 0.0167,
      "step": 780
    },
    {
      "epoch": 3.0950048971596473,
      "grad_norm": 0.14467577636241913,
      "learning_rate": 2.1142109851787272e-05,
      "loss": 0.0207,
      "step": 790
    },
    {
      "epoch": 3.1341821743388834,
      "grad_norm": 0.3296276032924652,
      "learning_rate": 2.0706190061028772e-05,
      "loss": 0.0177,
      "step": 800
    },
    {
      "epoch": 3.1733594515181194,
      "grad_norm": 0.7694735527038574,
      "learning_rate": 2.0270270270270273e-05,
      "loss": 0.0141,
      "step": 810
    },
    {
      "epoch": 3.2125367286973554,
      "grad_norm": 0.35446447134017944,
      "learning_rate": 1.983435047951177e-05,
      "loss": 0.0206,
      "step": 820
    },
    {
      "epoch": 3.2517140058765914,
      "grad_norm": 1.089401125907898,
      "learning_rate": 1.939843068875327e-05,
      "loss": 0.0326,
      "step": 830
    },
    {
      "epoch": 3.2908912830558275,
      "grad_norm": 0.21801254153251648,
      "learning_rate": 1.896251089799477e-05,
      "loss": 0.0162,
      "step": 840
    },
    {
      "epoch": 3.3300685602350635,
      "grad_norm": 0.42867550253868103,
      "learning_rate": 1.8526591107236267e-05,
      "loss": 0.0195,
      "step": 850
    },
    {
      "epoch": 3.3692458374143,
      "grad_norm": 0.24043036997318268,
      "learning_rate": 1.809067131647777e-05,
      "loss": 0.0155,
      "step": 860
    },
    {
      "epoch": 3.4084231145935355,
      "grad_norm": 0.4469415545463562,
      "learning_rate": 1.7654751525719268e-05,
      "loss": 0.0193,
      "step": 870
    },
    {
      "epoch": 3.447600391772772,
      "grad_norm": 0.14562171697616577,
      "learning_rate": 1.7218831734960768e-05,
      "loss": 0.0169,
      "step": 880
    },
    {
      "epoch": 3.486777668952008,
      "grad_norm": 0.4943673610687256,
      "learning_rate": 1.6782911944202268e-05,
      "loss": 0.0281,
      "step": 890
    },
    {
      "epoch": 3.525954946131244,
      "grad_norm": 0.5602672696113586,
      "learning_rate": 1.6346992153443765e-05,
      "loss": 0.0252,
      "step": 900
    },
    {
      "epoch": 3.56513222331048,
      "grad_norm": 0.6581624150276184,
      "learning_rate": 1.591107236268527e-05,
      "loss": 0.0202,
      "step": 910
    },
    {
      "epoch": 3.604309500489716,
      "grad_norm": 0.45326659083366394,
      "learning_rate": 1.5475152571926766e-05,
      "loss": 0.0257,
      "step": 920
    },
    {
      "epoch": 3.643486777668952,
      "grad_norm": 1.0565999746322632,
      "learning_rate": 1.5039232781168266e-05,
      "loss": 0.02,
      "step": 930
    },
    {
      "epoch": 3.682664054848188,
      "grad_norm": 0.2989865839481354,
      "learning_rate": 1.4603312990409764e-05,
      "loss": 0.0163,
      "step": 940
    },
    {
      "epoch": 3.721841332027424,
      "grad_norm": 0.09961768984794617,
      "learning_rate": 1.4167393199651266e-05,
      "loss": 0.0121,
      "step": 950
    },
    {
      "epoch": 3.76101860920666,
      "grad_norm": 0.6661494970321655,
      "learning_rate": 1.3731473408892765e-05,
      "loss": 0.0123,
      "step": 960
    },
    {
      "epoch": 3.8001958863858962,
      "grad_norm": 0.4994729459285736,
      "learning_rate": 1.3295553618134264e-05,
      "loss": 0.0261,
      "step": 970
    },
    {
      "epoch": 3.8393731635651323,
      "grad_norm": 0.5843683481216431,
      "learning_rate": 1.2859633827375764e-05,
      "loss": 0.0222,
      "step": 980
    },
    {
      "epoch": 3.8785504407443683,
      "grad_norm": 0.30400168895721436,
      "learning_rate": 1.2423714036617264e-05,
      "loss": 0.0217,
      "step": 990
    },
    {
      "epoch": 3.9177277179236043,
      "grad_norm": 0.1775442361831665,
      "learning_rate": 1.1987794245858763e-05,
      "loss": 0.0194,
      "step": 1000
    },
    {
      "epoch": 3.9569049951028403,
      "grad_norm": 0.754188060760498,
      "learning_rate": 1.1551874455100261e-05,
      "loss": 0.0235,
      "step": 1010
    },
    {
      "epoch": 3.9960822722820764,
      "grad_norm": 0.2706276774406433,
      "learning_rate": 1.1115954664341762e-05,
      "loss": 0.0158,
      "step": 1020
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9944879960803528,
      "eval_loss": 0.023838121443986893,
      "eval_runtime": 105.6855,
      "eval_samples_per_second": 154.496,
      "eval_steps_per_second": 2.422,
      "step": 1021
    },
    {
      "epoch": 4.035259549461313,
      "grad_norm": 0.7036624550819397,
      "learning_rate": 1.0680034873583262e-05,
      "loss": 0.0212,
      "step": 1030
    },
    {
      "epoch": 4.074436826640548,
      "grad_norm": 0.3211575746536255,
      "learning_rate": 1.024411508282476e-05,
      "loss": 0.0158,
      "step": 1040
    },
    {
      "epoch": 4.113614103819785,
      "grad_norm": 0.28554221987724304,
      "learning_rate": 9.80819529206626e-06,
      "loss": 0.0166,
      "step": 1050
    },
    {
      "epoch": 4.1527913809990205,
      "grad_norm": 0.23619802296161652,
      "learning_rate": 9.372275501307761e-06,
      "loss": 0.022,
      "step": 1060
    },
    {
      "epoch": 4.191968658178257,
      "grad_norm": 0.24213068187236786,
      "learning_rate": 8.93635571054926e-06,
      "loss": 0.0201,
      "step": 1070
    },
    {
      "epoch": 4.2311459353574925,
      "grad_norm": 0.5181974172592163,
      "learning_rate": 8.500435919790758e-06,
      "loss": 0.0289,
      "step": 1080
    },
    {
      "epoch": 4.270323212536729,
      "grad_norm": 0.9876229166984558,
      "learning_rate": 8.064516129032258e-06,
      "loss": 0.0198,
      "step": 1090
    },
    {
      "epoch": 4.3095004897159646,
      "grad_norm": 1.2217401266098022,
      "learning_rate": 7.628596338273758e-06,
      "loss": 0.0197,
      "step": 1100
    },
    {
      "epoch": 4.348677766895201,
      "grad_norm": 0.6681068539619446,
      "learning_rate": 7.192676547515258e-06,
      "loss": 0.0217,
      "step": 1110
    },
    {
      "epoch": 4.387855044074437,
      "grad_norm": 0.2516974210739136,
      "learning_rate": 6.7567567567567575e-06,
      "loss": 0.015,
      "step": 1120
    },
    {
      "epoch": 4.427032321253673,
      "grad_norm": 0.6431485414505005,
      "learning_rate": 6.320836965998257e-06,
      "loss": 0.0165,
      "step": 1130
    },
    {
      "epoch": 4.466209598432909,
      "grad_norm": 0.8847171664237976,
      "learning_rate": 5.884917175239756e-06,
      "loss": 0.0169,
      "step": 1140
    },
    {
      "epoch": 4.505386875612145,
      "grad_norm": 0.13626788556575775,
      "learning_rate": 5.448997384481256e-06,
      "loss": 0.0135,
      "step": 1150
    },
    {
      "epoch": 4.544564152791381,
      "grad_norm": 0.19009195268154144,
      "learning_rate": 5.013077593722755e-06,
      "loss": 0.0082,
      "step": 1160
    },
    {
      "epoch": 4.583741429970617,
      "grad_norm": 0.5194115042686462,
      "learning_rate": 4.577157802964255e-06,
      "loss": 0.0186,
      "step": 1170
    },
    {
      "epoch": 4.622918707149853,
      "grad_norm": 0.3963209092617035,
      "learning_rate": 4.141238012205754e-06,
      "loss": 0.0211,
      "step": 1180
    },
    {
      "epoch": 4.662095984329089,
      "grad_norm": 0.392490953207016,
      "learning_rate": 3.7053182214472536e-06,
      "loss": 0.0121,
      "step": 1190
    },
    {
      "epoch": 4.701273261508325,
      "grad_norm": 0.2609846293926239,
      "learning_rate": 3.2693984306887534e-06,
      "loss": 0.024,
      "step": 1200
    },
    {
      "epoch": 4.740450538687561,
      "grad_norm": 0.9114863872528076,
      "learning_rate": 2.8334786399302533e-06,
      "loss": 0.022,
      "step": 1210
    },
    {
      "epoch": 4.779627815866798,
      "grad_norm": 0.3400118947029114,
      "learning_rate": 2.3975588491717523e-06,
      "loss": 0.0139,
      "step": 1220
    },
    {
      "epoch": 4.818805093046033,
      "grad_norm": 0.8354482650756836,
      "learning_rate": 1.961639058413252e-06,
      "loss": 0.0168,
      "step": 1230
    },
    {
      "epoch": 4.857982370225269,
      "grad_norm": 0.4545687139034271,
      "learning_rate": 1.5257192676547516e-06,
      "loss": 0.0176,
      "step": 1240
    },
    {
      "epoch": 4.897159647404505,
      "grad_norm": 0.6158453226089478,
      "learning_rate": 1.0897994768962512e-06,
      "loss": 0.0169,
      "step": 1250
    },
    {
      "epoch": 4.936336924583742,
      "grad_norm": 0.11892726272344589,
      "learning_rate": 6.538796861377506e-07,
      "loss": 0.0196,
      "step": 1260
    },
    {
      "epoch": 4.975514201762977,
      "grad_norm": 0.5337911248207092,
      "learning_rate": 2.179598953792502e-07,
      "loss": 0.0112,
      "step": 1270
    },
    {
      "epoch": 4.995102840352596,
      "eval_accuracy": 0.9943655071043606,
      "eval_loss": 0.02594069205224514,
      "eval_runtime": 104.7525,
      "eval_samples_per_second": 155.872,
      "eval_steps_per_second": 2.444,
      "step": 1275
    },
    {
      "epoch": 4.995102840352596,
      "step": 1275,
      "total_flos": 8.109813238393209e+18,
      "train_loss": 0.030976083857171675,
      "train_runtime": 4473.2861,
      "train_samples_per_second": 73.002,
      "train_steps_per_second": 0.285
    }
  ],
  "logging_steps": 10,
  "max_steps": 1275,
  "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": 8.109813238393209e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}