{
  "best_global_step": 1053,
  "best_metric": 0.9728,
  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-1053",
  "epoch": 2.992181947405828,
  "eval_steps": 500,
  "global_step": 1053,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028429282160625444,
      "grad_norm": 3.7549822330474854,
      "learning_rate": 4.716981132075472e-06,
      "loss": 2.3642,
      "step": 10
    },
    {
      "epoch": 0.05685856432125089,
      "grad_norm": 4.3167524337768555,
      "learning_rate": 9.433962264150944e-06,
      "loss": 2.2894,
      "step": 20
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 4.120803356170654,
      "learning_rate": 1.4150943396226415e-05,
      "loss": 2.1748,
      "step": 30
    },
    {
      "epoch": 0.11371712864250177,
      "grad_norm": 4.778192043304443,
      "learning_rate": 1.8867924528301888e-05,
      "loss": 1.9726,
      "step": 40
    },
    {
      "epoch": 0.14214641080312723,
      "grad_norm": 6.351480960845947,
      "learning_rate": 2.358490566037736e-05,
      "loss": 1.6153,
      "step": 50
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 8.011857986450195,
      "learning_rate": 2.830188679245283e-05,
      "loss": 1.3063,
      "step": 60
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 10.897187232971191,
      "learning_rate": 3.30188679245283e-05,
      "loss": 1.0459,
      "step": 70
    },
    {
      "epoch": 0.22743425728500355,
      "grad_norm": 11.66580581665039,
      "learning_rate": 3.7735849056603776e-05,
      "loss": 0.8935,
      "step": 80
    },
    {
      "epoch": 0.255863539445629,
      "grad_norm": 9.333466529846191,
      "learning_rate": 4.245283018867925e-05,
      "loss": 0.8089,
      "step": 90
    },
    {
      "epoch": 0.28429282160625446,
      "grad_norm": 10.605915069580078,
      "learning_rate": 4.716981132075472e-05,
      "loss": 0.7529,
      "step": 100
    },
    {
      "epoch": 0.31272210376687987,
      "grad_norm": 13.530115127563477,
      "learning_rate": 4.978880675818374e-05,
      "loss": 0.6793,
      "step": 110
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 16.129487991333008,
      "learning_rate": 4.9260823653643085e-05,
      "loss": 0.7098,
      "step": 120
    },
    {
      "epoch": 0.3695806680881308,
      "grad_norm": 10.853135108947754,
      "learning_rate": 4.8732840549102435e-05,
      "loss": 0.6768,
      "step": 130
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 15.441333770751953,
      "learning_rate": 4.820485744456177e-05,
      "loss": 0.6994,
      "step": 140
    },
    {
      "epoch": 0.42643923240938164,
      "grad_norm": 15.366798400878906,
      "learning_rate": 4.767687434002112e-05,
      "loss": 0.6091,
      "step": 150
    },
    {
      "epoch": 0.4548685145700071,
      "grad_norm": 9.057019233703613,
      "learning_rate": 4.7148891235480466e-05,
      "loss": 0.5447,
      "step": 160
    },
    {
      "epoch": 0.48329779673063256,
      "grad_norm": 11.785883903503418,
      "learning_rate": 4.662090813093981e-05,
      "loss": 0.5824,
      "step": 170
    },
    {
      "epoch": 0.511727078891258,
      "grad_norm": 10.493522644042969,
      "learning_rate": 4.609292502639916e-05,
      "loss": 0.527,
      "step": 180
    },
    {
      "epoch": 0.5401563610518835,
      "grad_norm": 10.710103034973145,
      "learning_rate": 4.55649419218585e-05,
      "loss": 0.5574,
      "step": 190
    },
    {
      "epoch": 0.5685856432125089,
      "grad_norm": 10.442607879638672,
      "learning_rate": 4.503695881731785e-05,
      "loss": 0.5617,
      "step": 200
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 8.90545654296875,
      "learning_rate": 4.45089757127772e-05,
      "loss": 0.5034,
      "step": 210
    },
    {
      "epoch": 0.6254442075337597,
      "grad_norm": 13.07169246673584,
      "learning_rate": 4.398099260823654e-05,
      "loss": 0.5332,
      "step": 220
    },
    {
      "epoch": 0.6538734896943852,
      "grad_norm": 10.371030807495117,
      "learning_rate": 4.3453009503695884e-05,
      "loss": 0.4784,
      "step": 230
    },
    {
      "epoch": 0.6823027718550106,
      "grad_norm": 9.855475425720215,
      "learning_rate": 4.292502639915523e-05,
      "loss": 0.5059,
      "step": 240
    },
    {
      "epoch": 0.7107320540156361,
      "grad_norm": 10.05436897277832,
      "learning_rate": 4.239704329461457e-05,
      "loss": 0.4563,
      "step": 250
    },
    {
      "epoch": 0.7391613361762616,
      "grad_norm": 10.342894554138184,
      "learning_rate": 4.186906019007392e-05,
      "loss": 0.4704,
      "step": 260
    },
    {
      "epoch": 0.767590618336887,
      "grad_norm": 9.998404502868652,
      "learning_rate": 4.1341077085533265e-05,
      "loss": 0.4532,
      "step": 270
    },
    {
      "epoch": 0.7960199004975125,
      "grad_norm": 9.41798210144043,
      "learning_rate": 4.081309398099261e-05,
      "loss": 0.4811,
      "step": 280
    },
    {
      "epoch": 0.8244491826581379,
      "grad_norm": 12.316587448120117,
      "learning_rate": 4.028511087645195e-05,
      "loss": 0.5105,
      "step": 290
    },
    {
      "epoch": 0.8528784648187633,
      "grad_norm": 13.802250862121582,
      "learning_rate": 3.97571277719113e-05,
      "loss": 0.5178,
      "step": 300
    },
    {
      "epoch": 0.8813077469793887,
      "grad_norm": 11.238789558410645,
      "learning_rate": 3.9229144667370646e-05,
      "loss": 0.4478,
      "step": 310
    },
    {
      "epoch": 0.9097370291400142,
      "grad_norm": 9.923989295959473,
      "learning_rate": 3.870116156282999e-05,
      "loss": 0.4973,
      "step": 320
    },
    {
      "epoch": 0.9381663113006397,
      "grad_norm": 10.5370512008667,
      "learning_rate": 3.817317845828934e-05,
      "loss": 0.4734,
      "step": 330
    },
    {
      "epoch": 0.9665955934612651,
      "grad_norm": 7.8266448974609375,
      "learning_rate": 3.764519535374868e-05,
      "loss": 0.4087,
      "step": 340
    },
    {
      "epoch": 0.9950248756218906,
      "grad_norm": 7.531087398529053,
      "learning_rate": 3.711721224920803e-05,
      "loss": 0.4642,
      "step": 350
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9532,
      "eval_loss": 0.13443532586097717,
      "eval_runtime": 30.1227,
      "eval_samples_per_second": 165.988,
      "eval_steps_per_second": 5.212,
      "step": 352
    },
    {
      "epoch": 1.0227434257285004,
      "grad_norm": 8.728900909423828,
      "learning_rate": 3.658922914466738e-05,
      "loss": 0.4293,
      "step": 360
    },
    {
      "epoch": 1.0511727078891258,
      "grad_norm": 7.730119705200195,
      "learning_rate": 3.6061246040126714e-05,
      "loss": 0.4392,
      "step": 370
    },
    {
      "epoch": 1.0796019900497513,
      "grad_norm": 13.757883071899414,
      "learning_rate": 3.5533262935586064e-05,
      "loss": 0.4193,
      "step": 380
    },
    {
      "epoch": 1.1080312722103767,
      "grad_norm": 9.790868759155273,
      "learning_rate": 3.500527983104541e-05,
      "loss": 0.4604,
      "step": 390
    },
    {
      "epoch": 1.136460554371002,
      "grad_norm": 9.005698204040527,
      "learning_rate": 3.447729672650475e-05,
      "loss": 0.4085,
      "step": 400
    },
    {
      "epoch": 1.1648898365316276,
      "grad_norm": 9.621892929077148,
      "learning_rate": 3.3949313621964095e-05,
      "loss": 0.4185,
      "step": 410
    },
    {
      "epoch": 1.193319118692253,
      "grad_norm": 8.165648460388184,
      "learning_rate": 3.3421330517423445e-05,
      "loss": 0.3593,
      "step": 420
    },
    {
      "epoch": 1.2217484008528785,
      "grad_norm": 9.228168487548828,
      "learning_rate": 3.289334741288279e-05,
      "loss": 0.3602,
      "step": 430
    },
    {
      "epoch": 1.2501776830135038,
      "grad_norm": 8.772619247436523,
      "learning_rate": 3.236536430834213e-05,
      "loss": 0.4727,
      "step": 440
    },
    {
      "epoch": 1.2786069651741294,
      "grad_norm": 10.873198509216309,
      "learning_rate": 3.183738120380148e-05,
      "loss": 0.4686,
      "step": 450
    },
    {
      "epoch": 1.3070362473347548,
      "grad_norm": 8.746286392211914,
      "learning_rate": 3.130939809926082e-05,
      "loss": 0.3997,
      "step": 460
    },
    {
      "epoch": 1.33546552949538,
      "grad_norm": 11.572668075561523,
      "learning_rate": 3.078141499472017e-05,
      "loss": 0.4251,
      "step": 470
    },
    {
      "epoch": 1.3638948116560057,
      "grad_norm": 7.098505973815918,
      "learning_rate": 3.0253431890179517e-05,
      "loss": 0.3824,
      "step": 480
    },
    {
      "epoch": 1.3923240938166312,
      "grad_norm": 11.592111587524414,
      "learning_rate": 2.972544878563886e-05,
      "loss": 0.4104,
      "step": 490
    },
    {
      "epoch": 1.4207533759772566,
      "grad_norm": 10.93486499786377,
      "learning_rate": 2.9197465681098207e-05,
      "loss": 0.3884,
      "step": 500
    },
    {
      "epoch": 1.449182658137882,
      "grad_norm": 9.60152816772461,
      "learning_rate": 2.8669482576557548e-05,
      "loss": 0.4238,
      "step": 510
    },
    {
      "epoch": 1.4776119402985075,
      "grad_norm": 10.507494926452637,
      "learning_rate": 2.8141499472016898e-05,
      "loss": 0.4234,
      "step": 520
    },
    {
      "epoch": 1.5060412224591329,
      "grad_norm": 8.032126426696777,
      "learning_rate": 2.7613516367476245e-05,
      "loss": 0.3762,
      "step": 530
    },
    {
      "epoch": 1.5344705046197582,
      "grad_norm": 8.108844757080078,
      "learning_rate": 2.7085533262935585e-05,
      "loss": 0.436,
      "step": 540
    },
    {
      "epoch": 1.5628997867803838,
      "grad_norm": 10.481697082519531,
      "learning_rate": 2.6557550158394935e-05,
      "loss": 0.3651,
      "step": 550
    },
    {
      "epoch": 1.5913290689410093,
      "grad_norm": 8.025532722473145,
      "learning_rate": 2.6029567053854276e-05,
      "loss": 0.4054,
      "step": 560
    },
    {
      "epoch": 1.6197583511016347,
      "grad_norm": 6.820096492767334,
      "learning_rate": 2.5501583949313622e-05,
      "loss": 0.4018,
      "step": 570
    },
    {
      "epoch": 1.64818763326226,
      "grad_norm": 9.175089836120605,
      "learning_rate": 2.497360084477297e-05,
      "loss": 0.4268,
      "step": 580
    },
    {
      "epoch": 1.6766169154228856,
      "grad_norm": 10.221317291259766,
      "learning_rate": 2.4445617740232313e-05,
      "loss": 0.3801,
      "step": 590
    },
    {
      "epoch": 1.7050461975835112,
      "grad_norm": 8.72017765045166,
      "learning_rate": 2.391763463569166e-05,
      "loss": 0.3949,
      "step": 600
    },
    {
      "epoch": 1.7334754797441365,
      "grad_norm": 8.293012619018555,
      "learning_rate": 2.3389651531151003e-05,
      "loss": 0.3985,
      "step": 610
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 6.780423641204834,
      "learning_rate": 2.286166842661035e-05,
      "loss": 0.3703,
      "step": 620
    },
    {
      "epoch": 1.7903340440653874,
      "grad_norm": 8.803313255310059,
      "learning_rate": 2.2333685322069694e-05,
      "loss": 0.3901,
      "step": 630
    },
    {
      "epoch": 1.8187633262260128,
      "grad_norm": 8.275494575500488,
      "learning_rate": 2.180570221752904e-05,
      "loss": 0.397,
      "step": 640
    },
    {
      "epoch": 1.8471926083866381,
      "grad_norm": 8.815279006958008,
      "learning_rate": 2.1277719112988384e-05,
      "loss": 0.4184,
      "step": 650
    },
    {
      "epoch": 1.8756218905472637,
      "grad_norm": 6.734531402587891,
      "learning_rate": 2.074973600844773e-05,
      "loss": 0.3941,
      "step": 660
    },
    {
      "epoch": 1.9040511727078893,
      "grad_norm": 6.036601543426514,
      "learning_rate": 2.0221752903907075e-05,
      "loss": 0.3907,
      "step": 670
    },
    {
      "epoch": 1.9324804548685146,
      "grad_norm": 9.15225601196289,
      "learning_rate": 1.9693769799366422e-05,
      "loss": 0.4078,
      "step": 680
    },
    {
      "epoch": 1.96090973702914,
      "grad_norm": 10.416858673095703,
      "learning_rate": 1.9165786694825765e-05,
      "loss": 0.3725,
      "step": 690
    },
    {
      "epoch": 1.9893390191897655,
      "grad_norm": 8.242061614990234,
      "learning_rate": 1.863780359028511e-05,
      "loss": 0.367,
      "step": 700
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9688,
      "eval_loss": 0.08839573711156845,
      "eval_runtime": 30.1589,
      "eval_samples_per_second": 165.789,
      "eval_steps_per_second": 5.206,
      "step": 704
    },
    {
      "epoch": 2.0170575692963753,
      "grad_norm": 8.470636367797852,
      "learning_rate": 1.810982048574446e-05,
      "loss": 0.3583,
      "step": 710
    },
    {
      "epoch": 2.045486851457001,
      "grad_norm": 11.136754035949707,
      "learning_rate": 1.7581837381203803e-05,
      "loss": 0.3168,
      "step": 720
    },
    {
      "epoch": 2.073916133617626,
      "grad_norm": 9.741412162780762,
      "learning_rate": 1.7053854276663146e-05,
      "loss": 0.3108,
      "step": 730
    },
    {
      "epoch": 2.1023454157782515,
      "grad_norm": 8.964203834533691,
      "learning_rate": 1.6525871172122493e-05,
      "loss": 0.3775,
      "step": 740
    },
    {
      "epoch": 2.130774697938877,
      "grad_norm": 8.144142150878906,
      "learning_rate": 1.5997888067581837e-05,
      "loss": 0.3406,
      "step": 750
    },
    {
      "epoch": 2.1592039800995027,
      "grad_norm": 6.743160724639893,
      "learning_rate": 1.5469904963041184e-05,
      "loss": 0.3383,
      "step": 760
    },
    {
      "epoch": 2.1876332622601278,
      "grad_norm": 9.67287826538086,
      "learning_rate": 1.4941921858500529e-05,
      "loss": 0.3196,
      "step": 770
    },
    {
      "epoch": 2.2160625444207533,
      "grad_norm": 9.108183860778809,
      "learning_rate": 1.4413938753959874e-05,
      "loss": 0.3598,
      "step": 780
    },
    {
      "epoch": 2.244491826581379,
      "grad_norm": 8.00169849395752,
      "learning_rate": 1.388595564941922e-05,
      "loss": 0.3518,
      "step": 790
    },
    {
      "epoch": 2.272921108742004,
      "grad_norm": 8.659334182739258,
      "learning_rate": 1.3357972544878563e-05,
      "loss": 0.2976,
      "step": 800
    },
    {
      "epoch": 2.3013503909026296,
      "grad_norm": 10.701913833618164,
      "learning_rate": 1.2829989440337912e-05,
      "loss": 0.3627,
      "step": 810
    },
    {
      "epoch": 2.329779673063255,
      "grad_norm": 11.164308547973633,
      "learning_rate": 1.2302006335797255e-05,
      "loss": 0.3649,
      "step": 820
    },
    {
      "epoch": 2.3582089552238807,
      "grad_norm": 8.511822700500488,
      "learning_rate": 1.17740232312566e-05,
      "loss": 0.3818,
      "step": 830
    },
    {
      "epoch": 2.386638237384506,
      "grad_norm": 8.833267211914062,
      "learning_rate": 1.1246040126715946e-05,
      "loss": 0.3465,
      "step": 840
    },
    {
      "epoch": 2.4150675195451314,
      "grad_norm": 7.075978755950928,
      "learning_rate": 1.0718057022175291e-05,
      "loss": 0.3173,
      "step": 850
    },
    {
      "epoch": 2.443496801705757,
      "grad_norm": 7.614409923553467,
      "learning_rate": 1.0190073917634636e-05,
      "loss": 0.3323,
      "step": 860
    },
    {
      "epoch": 2.471926083866382,
      "grad_norm": 12.305047035217285,
      "learning_rate": 9.662090813093982e-06,
      "loss": 0.3603,
      "step": 870
    },
    {
      "epoch": 2.5003553660270077,
      "grad_norm": 9.996665954589844,
      "learning_rate": 9.134107708553327e-06,
      "loss": 0.3105,
      "step": 880
    },
    {
      "epoch": 2.5287846481876333,
      "grad_norm": 10.400426864624023,
      "learning_rate": 8.606124604012672e-06,
      "loss": 0.3555,
      "step": 890
    },
    {
      "epoch": 2.557213930348259,
      "grad_norm": 11.872201919555664,
      "learning_rate": 8.078141499472017e-06,
      "loss": 0.3697,
      "step": 900
    },
    {
      "epoch": 2.5856432125088844,
      "grad_norm": 10.102994918823242,
      "learning_rate": 7.5501583949313625e-06,
      "loss": 0.3389,
      "step": 910
    },
    {
      "epoch": 2.6140724946695095,
      "grad_norm": 11.179094314575195,
      "learning_rate": 7.022175290390708e-06,
      "loss": 0.3466,
      "step": 920
    },
    {
      "epoch": 2.642501776830135,
      "grad_norm": 7.167893886566162,
      "learning_rate": 6.494192185850054e-06,
      "loss": 0.356,
      "step": 930
    },
    {
      "epoch": 2.67093105899076,
      "grad_norm": 10.360447883605957,
      "learning_rate": 5.966209081309398e-06,
      "loss": 0.3719,
      "step": 940
    },
    {
      "epoch": 2.699360341151386,
      "grad_norm": 8.36248779296875,
      "learning_rate": 5.438225976768744e-06,
      "loss": 0.3199,
      "step": 950
    },
    {
      "epoch": 2.7277896233120114,
      "grad_norm": 10.92849063873291,
      "learning_rate": 4.910242872228089e-06,
      "loss": 0.3278,
      "step": 960
    },
    {
      "epoch": 2.756218905472637,
      "grad_norm": 7.335627555847168,
      "learning_rate": 4.382259767687434e-06,
      "loss": 0.3017,
      "step": 970
    },
    {
      "epoch": 2.7846481876332625,
      "grad_norm": 8.422759056091309,
      "learning_rate": 3.854276663146779e-06,
      "loss": 0.2855,
      "step": 980
    },
    {
      "epoch": 2.8130774697938876,
      "grad_norm": 7.285062313079834,
      "learning_rate": 3.326293558606125e-06,
      "loss": 0.3194,
      "step": 990
    },
    {
      "epoch": 2.841506751954513,
      "grad_norm": 5.810029029846191,
      "learning_rate": 2.79831045406547e-06,
      "loss": 0.3056,
      "step": 1000
    },
    {
      "epoch": 2.8699360341151388,
      "grad_norm": 8.25550365447998,
      "learning_rate": 2.2703273495248154e-06,
      "loss": 0.2828,
      "step": 1010
    },
    {
      "epoch": 2.898365316275764,
      "grad_norm": 7.528290271759033,
      "learning_rate": 1.7423442449841606e-06,
      "loss": 0.3165,
      "step": 1020
    },
    {
      "epoch": 2.9267945984363894,
      "grad_norm": 8.811773300170898,
      "learning_rate": 1.2143611404435059e-06,
      "loss": 0.3423,
      "step": 1030
    },
    {
      "epoch": 2.955223880597015,
      "grad_norm": 8.768060684204102,
      "learning_rate": 6.863780359028511e-07,
      "loss": 0.3498,
      "step": 1040
    },
    {
      "epoch": 2.9836531627576406,
      "grad_norm": 10.878323554992676,
      "learning_rate": 1.5839493136219642e-07,
      "loss": 0.3387,
      "step": 1050
    },
    {
      "epoch": 2.992181947405828,
      "eval_accuracy": 0.9728,
      "eval_loss": 0.07574349641799927,
      "eval_runtime": 29.6661,
      "eval_samples_per_second": 168.543,
      "eval_steps_per_second": 5.292,
      "step": 1053
    },
    {
      "epoch": 2.992181947405828,
      "step": 1053,
      "total_flos": 3.3481540253275914e+18,
      "train_loss": 0.518996418711127,
      "train_runtime": 2019.6102,
      "train_samples_per_second": 66.845,
      "train_steps_per_second": 0.521
    }
  ],
  "logging_steps": 10,
  "max_steps": 1053,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 3.3481540253275914e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}