{
  "best_metric": 0.9718,
  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-1053",
  "epoch": 2.9936034115138592,
  "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": 4.971463680267334,
      "learning_rate": 4.716981132075472e-06,
      "loss": 2.2968,
      "step": 10
    },
    {
      "epoch": 0.05685856432125089,
      "grad_norm": 5.59540319442749,
      "learning_rate": 9.433962264150944e-06,
      "loss": 2.2627,
      "step": 20
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 5.504016876220703,
      "learning_rate": 1.4150943396226415e-05,
      "loss": 2.1275,
      "step": 30
    },
    {
      "epoch": 0.11371712864250177,
      "grad_norm": 7.983016014099121,
      "learning_rate": 1.8867924528301888e-05,
      "loss": 1.9415,
      "step": 40
    },
    {
      "epoch": 0.14214641080312723,
      "grad_norm": 9.81259822845459,
      "learning_rate": 2.358490566037736e-05,
      "loss": 1.6536,
      "step": 50
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 11.285735130310059,
      "learning_rate": 2.830188679245283e-05,
      "loss": 1.3794,
      "step": 60
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 10.141653060913086,
      "learning_rate": 3.30188679245283e-05,
      "loss": 1.1817,
      "step": 70
    },
    {
      "epoch": 0.22743425728500355,
      "grad_norm": 12.977154731750488,
      "learning_rate": 3.7735849056603776e-05,
      "loss": 1.0396,
      "step": 80
    },
    {
      "epoch": 0.255863539445629,
      "grad_norm": 13.638314247131348,
      "learning_rate": 4.245283018867925e-05,
      "loss": 0.9584,
      "step": 90
    },
    {
      "epoch": 0.28429282160625446,
      "grad_norm": 10.283329010009766,
      "learning_rate": 4.716981132075472e-05,
      "loss": 0.8318,
      "step": 100
    },
    {
      "epoch": 0.31272210376687987,
      "grad_norm": 25.351537704467773,
      "learning_rate": 4.978880675818374e-05,
      "loss": 0.7506,
      "step": 110
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 14.995630264282227,
      "learning_rate": 4.9260823653643085e-05,
      "loss": 0.6918,
      "step": 120
    },
    {
      "epoch": 0.3695806680881308,
      "grad_norm": 14.786783218383789,
      "learning_rate": 4.8732840549102435e-05,
      "loss": 0.6667,
      "step": 130
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 14.435614585876465,
      "learning_rate": 4.820485744456177e-05,
      "loss": 0.7042,
      "step": 140
    },
    {
      "epoch": 0.42643923240938164,
      "grad_norm": 11.776712417602539,
      "learning_rate": 4.767687434002112e-05,
      "loss": 0.6771,
      "step": 150
    },
    {
      "epoch": 0.4548685145700071,
      "grad_norm": 12.549166679382324,
      "learning_rate": 4.7148891235480466e-05,
      "loss": 0.6342,
      "step": 160
    },
    {
      "epoch": 0.48329779673063256,
      "grad_norm": 16.95928192138672,
      "learning_rate": 4.662090813093981e-05,
      "loss": 0.6551,
      "step": 170
    },
    {
      "epoch": 0.511727078891258,
      "grad_norm": 13.063802719116211,
      "learning_rate": 4.609292502639916e-05,
      "loss": 0.5945,
      "step": 180
    },
    {
      "epoch": 0.5401563610518835,
      "grad_norm": 11.535209655761719,
      "learning_rate": 4.55649419218585e-05,
      "loss": 0.6421,
      "step": 190
    },
    {
      "epoch": 0.5685856432125089,
      "grad_norm": 12.215719223022461,
      "learning_rate": 4.503695881731785e-05,
      "loss": 0.5967,
      "step": 200
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 10.35771656036377,
      "learning_rate": 4.45089757127772e-05,
      "loss": 0.5809,
      "step": 210
    },
    {
      "epoch": 0.6254442075337597,
      "grad_norm": 9.158855438232422,
      "learning_rate": 4.398099260823654e-05,
      "loss": 0.5752,
      "step": 220
    },
    {
      "epoch": 0.6538734896943852,
      "grad_norm": 9.909387588500977,
      "learning_rate": 4.3453009503695884e-05,
      "loss": 0.5822,
      "step": 230
    },
    {
      "epoch": 0.6823027718550106,
      "grad_norm": 11.583661079406738,
      "learning_rate": 4.292502639915523e-05,
      "loss": 0.5183,
      "step": 240
    },
    {
      "epoch": 0.7107320540156361,
      "grad_norm": 10.360766410827637,
      "learning_rate": 4.239704329461457e-05,
      "loss": 0.5096,
      "step": 250
    },
    {
      "epoch": 0.7391613361762616,
      "grad_norm": 12.021404266357422,
      "learning_rate": 4.186906019007392e-05,
      "loss": 0.5412,
      "step": 260
    },
    {
      "epoch": 0.767590618336887,
      "grad_norm": 10.050119400024414,
      "learning_rate": 4.1341077085533265e-05,
      "loss": 0.4948,
      "step": 270
    },
    {
      "epoch": 0.7960199004975125,
      "grad_norm": 11.555167198181152,
      "learning_rate": 4.081309398099261e-05,
      "loss": 0.5185,
      "step": 280
    },
    {
      "epoch": 0.8244491826581379,
      "grad_norm": 14.718985557556152,
      "learning_rate": 4.028511087645195e-05,
      "loss": 0.5021,
      "step": 290
    },
    {
      "epoch": 0.8528784648187633,
      "grad_norm": 11.871549606323242,
      "learning_rate": 3.97571277719113e-05,
      "loss": 0.5114,
      "step": 300
    },
    {
      "epoch": 0.8813077469793887,
      "grad_norm": 12.034425735473633,
      "learning_rate": 3.9229144667370646e-05,
      "loss": 0.5387,
      "step": 310
    },
    {
      "epoch": 0.9097370291400142,
      "grad_norm": 11.914613723754883,
      "learning_rate": 3.870116156282999e-05,
      "loss": 0.5383,
      "step": 320
    },
    {
      "epoch": 0.9381663113006397,
      "grad_norm": 10.041810989379883,
      "learning_rate": 3.817317845828934e-05,
      "loss": 0.4729,
      "step": 330
    },
    {
      "epoch": 0.9665955934612651,
      "grad_norm": 11.924065589904785,
      "learning_rate": 3.764519535374868e-05,
      "loss": 0.5136,
      "step": 340
    },
    {
      "epoch": 0.9950248756218906,
      "grad_norm": 9.479151725769043,
      "learning_rate": 3.711721224920803e-05,
      "loss": 0.4789,
      "step": 350
    },
    {
      "epoch": 0.997867803837953,
      "eval_accuracy": 0.9496,
      "eval_loss": 0.1450212448835373,
      "eval_runtime": 31.1345,
      "eval_samples_per_second": 160.593,
      "eval_steps_per_second": 5.043,
      "step": 351
    },
    {
      "epoch": 1.023454157782516,
      "grad_norm": 11.358855247497559,
      "learning_rate": 3.658922914466738e-05,
      "loss": 0.5254,
      "step": 360
    },
    {
      "epoch": 1.0518834399431414,
      "grad_norm": 9.534340858459473,
      "learning_rate": 3.6061246040126714e-05,
      "loss": 0.5126,
      "step": 370
    },
    {
      "epoch": 1.080312722103767,
      "grad_norm": 8.744548797607422,
      "learning_rate": 3.5533262935586064e-05,
      "loss": 0.4884,
      "step": 380
    },
    {
      "epoch": 1.1087420042643923,
      "grad_norm": 8.237000465393066,
      "learning_rate": 3.500527983104541e-05,
      "loss": 0.4586,
      "step": 390
    },
    {
      "epoch": 1.1371712864250179,
      "grad_norm": 8.221174240112305,
      "learning_rate": 3.447729672650475e-05,
      "loss": 0.448,
      "step": 400
    },
    {
      "epoch": 1.1656005685856432,
      "grad_norm": 6.845401763916016,
      "learning_rate": 3.3949313621964095e-05,
      "loss": 0.4653,
      "step": 410
    },
    {
      "epoch": 1.1940298507462686,
      "grad_norm": 10.27818489074707,
      "learning_rate": 3.3421330517423445e-05,
      "loss": 0.4045,
      "step": 420
    },
    {
      "epoch": 1.2224591329068941,
      "grad_norm": 8.333521842956543,
      "learning_rate": 3.289334741288279e-05,
      "loss": 0.4314,
      "step": 430
    },
    {
      "epoch": 1.2508884150675195,
      "grad_norm": 12.734621047973633,
      "learning_rate": 3.236536430834213e-05,
      "loss": 0.476,
      "step": 440
    },
    {
      "epoch": 1.279317697228145,
      "grad_norm": 9.579340934753418,
      "learning_rate": 3.183738120380148e-05,
      "loss": 0.4701,
      "step": 450
    },
    {
      "epoch": 1.3077469793887704,
      "grad_norm": 9.905597686767578,
      "learning_rate": 3.130939809926082e-05,
      "loss": 0.4382,
      "step": 460
    },
    {
      "epoch": 1.336176261549396,
      "grad_norm": 7.915118217468262,
      "learning_rate": 3.078141499472017e-05,
      "loss": 0.4535,
      "step": 470
    },
    {
      "epoch": 1.3646055437100213,
      "grad_norm": 8.826480865478516,
      "learning_rate": 3.0253431890179517e-05,
      "loss": 0.4704,
      "step": 480
    },
    {
      "epoch": 1.3930348258706466,
      "grad_norm": 7.914577007293701,
      "learning_rate": 2.972544878563886e-05,
      "loss": 0.4711,
      "step": 490
    },
    {
      "epoch": 1.4214641080312722,
      "grad_norm": 6.795777320861816,
      "learning_rate": 2.9197465681098207e-05,
      "loss": 0.4635,
      "step": 500
    },
    {
      "epoch": 1.4498933901918978,
      "grad_norm": 8.031927108764648,
      "learning_rate": 2.8669482576557548e-05,
      "loss": 0.4269,
      "step": 510
    },
    {
      "epoch": 1.4783226723525231,
      "grad_norm": 9.724798202514648,
      "learning_rate": 2.8141499472016898e-05,
      "loss": 0.4335,
      "step": 520
    },
    {
      "epoch": 1.5067519545131485,
      "grad_norm": 9.283247947692871,
      "learning_rate": 2.7613516367476245e-05,
      "loss": 0.4389,
      "step": 530
    },
    {
      "epoch": 1.535181236673774,
      "grad_norm": 9.640780448913574,
      "learning_rate": 2.7085533262935585e-05,
      "loss": 0.5012,
      "step": 540
    },
    {
      "epoch": 1.5636105188343994,
      "grad_norm": 7.612826347351074,
      "learning_rate": 2.6557550158394935e-05,
      "loss": 0.436,
      "step": 550
    },
    {
      "epoch": 1.5920398009950247,
      "grad_norm": 8.124228477478027,
      "learning_rate": 2.6029567053854276e-05,
      "loss": 0.4408,
      "step": 560
    },
    {
      "epoch": 1.6204690831556503,
      "grad_norm": 10.85289478302002,
      "learning_rate": 2.5501583949313622e-05,
      "loss": 0.4196,
      "step": 570
    },
    {
      "epoch": 1.6488983653162759,
      "grad_norm": 8.266470909118652,
      "learning_rate": 2.497360084477297e-05,
      "loss": 0.4241,
      "step": 580
    },
    {
      "epoch": 1.6773276474769012,
      "grad_norm": 8.443300247192383,
      "learning_rate": 2.4445617740232313e-05,
      "loss": 0.4388,
      "step": 590
    },
    {
      "epoch": 1.7057569296375266,
      "grad_norm": 8.459017753601074,
      "learning_rate": 2.391763463569166e-05,
      "loss": 0.4282,
      "step": 600
    },
    {
      "epoch": 1.7341862117981521,
      "grad_norm": 8.036330223083496,
      "learning_rate": 2.3389651531151003e-05,
      "loss": 0.4252,
      "step": 610
    },
    {
      "epoch": 1.7626154939587777,
      "grad_norm": 9.3660888671875,
      "learning_rate": 2.286166842661035e-05,
      "loss": 0.4178,
      "step": 620
    },
    {
      "epoch": 1.7910447761194028,
      "grad_norm": 8.20159912109375,
      "learning_rate": 2.2333685322069694e-05,
      "loss": 0.4225,
      "step": 630
    },
    {
      "epoch": 1.8194740582800284,
      "grad_norm": 9.5265531539917,
      "learning_rate": 2.180570221752904e-05,
      "loss": 0.4049,
      "step": 640
    },
    {
      "epoch": 1.847903340440654,
      "grad_norm": 8.839706420898438,
      "learning_rate": 2.1277719112988384e-05,
      "loss": 0.4212,
      "step": 650
    },
    {
      "epoch": 1.8763326226012793,
      "grad_norm": 7.823642253875732,
      "learning_rate": 2.074973600844773e-05,
      "loss": 0.4129,
      "step": 660
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 11.941854476928711,
      "learning_rate": 2.0221752903907075e-05,
      "loss": 0.3794,
      "step": 670
    },
    {
      "epoch": 1.9331911869225302,
      "grad_norm": 8.150591850280762,
      "learning_rate": 1.9693769799366422e-05,
      "loss": 0.406,
      "step": 680
    },
    {
      "epoch": 1.9616204690831558,
      "grad_norm": 8.394612312316895,
      "learning_rate": 1.9165786694825765e-05,
      "loss": 0.3759,
      "step": 690
    },
    {
      "epoch": 1.9900497512437811,
      "grad_norm": 7.265615463256836,
      "learning_rate": 1.863780359028511e-05,
      "loss": 0.3963,
      "step": 700
    },
    {
      "epoch": 1.9985785358919688,
      "eval_accuracy": 0.9678,
      "eval_loss": 0.09611168503761292,
      "eval_runtime": 31.5514,
      "eval_samples_per_second": 158.472,
      "eval_steps_per_second": 4.976,
      "step": 703
    },
    {
      "epoch": 2.0184790334044065,
      "grad_norm": 9.056930541992188,
      "learning_rate": 1.810982048574446e-05,
      "loss": 0.3587,
      "step": 710
    },
    {
      "epoch": 2.046908315565032,
      "grad_norm": 9.776238441467285,
      "learning_rate": 1.7581837381203803e-05,
      "loss": 0.376,
      "step": 720
    },
    {
      "epoch": 2.0753375977256576,
      "grad_norm": 7.041496753692627,
      "learning_rate": 1.7053854276663146e-05,
      "loss": 0.3584,
      "step": 730
    },
    {
      "epoch": 2.1037668798862827,
      "grad_norm": 8.942048072814941,
      "learning_rate": 1.6525871172122493e-05,
      "loss": 0.366,
      "step": 740
    },
    {
      "epoch": 2.1321961620469083,
      "grad_norm": 7.969531059265137,
      "learning_rate": 1.5997888067581837e-05,
      "loss": 0.3385,
      "step": 750
    },
    {
      "epoch": 2.160625444207534,
      "grad_norm": 5.983547687530518,
      "learning_rate": 1.5469904963041184e-05,
      "loss": 0.3678,
      "step": 760
    },
    {
      "epoch": 2.189054726368159,
      "grad_norm": 8.535104751586914,
      "learning_rate": 1.4941921858500529e-05,
      "loss": 0.3623,
      "step": 770
    },
    {
      "epoch": 2.2174840085287846,
      "grad_norm": 9.320777893066406,
      "learning_rate": 1.4413938753959874e-05,
      "loss": 0.3614,
      "step": 780
    },
    {
      "epoch": 2.24591329068941,
      "grad_norm": 12.175688743591309,
      "learning_rate": 1.388595564941922e-05,
      "loss": 0.3924,
      "step": 790
    },
    {
      "epoch": 2.2743425728500357,
      "grad_norm": 7.2256059646606445,
      "learning_rate": 1.3357972544878563e-05,
      "loss": 0.3445,
      "step": 800
    },
    {
      "epoch": 2.302771855010661,
      "grad_norm": 10.370970726013184,
      "learning_rate": 1.2829989440337912e-05,
      "loss": 0.4136,
      "step": 810
    },
    {
      "epoch": 2.3312011371712864,
      "grad_norm": 9.5155668258667,
      "learning_rate": 1.2302006335797255e-05,
      "loss": 0.3414,
      "step": 820
    },
    {
      "epoch": 2.359630419331912,
      "grad_norm": 9.32805061340332,
      "learning_rate": 1.17740232312566e-05,
      "loss": 0.3967,
      "step": 830
    },
    {
      "epoch": 2.388059701492537,
      "grad_norm": 10.42844295501709,
      "learning_rate": 1.1246040126715946e-05,
      "loss": 0.3816,
      "step": 840
    },
    {
      "epoch": 2.4164889836531627,
      "grad_norm": 6.44063138961792,
      "learning_rate": 1.0718057022175291e-05,
      "loss": 0.3792,
      "step": 850
    },
    {
      "epoch": 2.4449182658137882,
      "grad_norm": 12.695724487304688,
      "learning_rate": 1.0190073917634636e-05,
      "loss": 0.3985,
      "step": 860
    },
    {
      "epoch": 2.473347547974414,
      "grad_norm": 7.094071388244629,
      "learning_rate": 9.662090813093982e-06,
      "loss": 0.3363,
      "step": 870
    },
    {
      "epoch": 2.501776830135039,
      "grad_norm": 11.00616455078125,
      "learning_rate": 9.134107708553327e-06,
      "loss": 0.3647,
      "step": 880
    },
    {
      "epoch": 2.5302061122956645,
      "grad_norm": 6.449082374572754,
      "learning_rate": 8.606124604012672e-06,
      "loss": 0.3662,
      "step": 890
    },
    {
      "epoch": 2.55863539445629,
      "grad_norm": 8.83302116394043,
      "learning_rate": 8.078141499472017e-06,
      "loss": 0.3736,
      "step": 900
    },
    {
      "epoch": 2.587064676616915,
      "grad_norm": 10.547133445739746,
      "learning_rate": 7.5501583949313625e-06,
      "loss": 0.3744,
      "step": 910
    },
    {
      "epoch": 2.6154939587775408,
      "grad_norm": 8.548726081848145,
      "learning_rate": 7.022175290390708e-06,
      "loss": 0.3674,
      "step": 920
    },
    {
      "epoch": 2.6439232409381663,
      "grad_norm": 10.724135398864746,
      "learning_rate": 6.494192185850054e-06,
      "loss": 0.3719,
      "step": 930
    },
    {
      "epoch": 2.672352523098792,
      "grad_norm": 11.502964973449707,
      "learning_rate": 5.966209081309398e-06,
      "loss": 0.3483,
      "step": 940
    },
    {
      "epoch": 2.7007818052594175,
      "grad_norm": 5.129545211791992,
      "learning_rate": 5.438225976768744e-06,
      "loss": 0.3498,
      "step": 950
    },
    {
      "epoch": 2.7292110874200426,
      "grad_norm": 8.819750785827637,
      "learning_rate": 4.910242872228089e-06,
      "loss": 0.3764,
      "step": 960
    },
    {
      "epoch": 2.757640369580668,
      "grad_norm": 11.780941009521484,
      "learning_rate": 4.382259767687434e-06,
      "loss": 0.3568,
      "step": 970
    },
    {
      "epoch": 2.7860696517412933,
      "grad_norm": 7.845065593719482,
      "learning_rate": 3.854276663146779e-06,
      "loss": 0.3498,
      "step": 980
    },
    {
      "epoch": 2.814498933901919,
      "grad_norm": 9.012118339538574,
      "learning_rate": 3.326293558606125e-06,
      "loss": 0.3565,
      "step": 990
    },
    {
      "epoch": 2.8429282160625444,
      "grad_norm": 11.06425952911377,
      "learning_rate": 2.79831045406547e-06,
      "loss": 0.3465,
      "step": 1000
    },
    {
      "epoch": 2.87135749822317,
      "grad_norm": 8.146778106689453,
      "learning_rate": 2.2703273495248154e-06,
      "loss": 0.3291,
      "step": 1010
    },
    {
      "epoch": 2.8997867803837956,
      "grad_norm": 9.340612411499023,
      "learning_rate": 1.7423442449841606e-06,
      "loss": 0.3222,
      "step": 1020
    },
    {
      "epoch": 2.9282160625444207,
      "grad_norm": 8.15194320678711,
      "learning_rate": 1.2143611404435059e-06,
      "loss": 0.3564,
      "step": 1030
    },
    {
      "epoch": 2.9566453447050463,
      "grad_norm": 8.63049030303955,
      "learning_rate": 6.863780359028511e-07,
      "loss": 0.3379,
      "step": 1040
    },
    {
      "epoch": 2.9850746268656714,
      "grad_norm": 10.885421752929688,
      "learning_rate": 1.5839493136219642e-07,
      "loss": 0.3134,
      "step": 1050
    },
    {
      "epoch": 2.9936034115138592,
      "eval_accuracy": 0.9718,
      "eval_loss": 0.08586699515581131,
      "eval_runtime": 31.0052,
      "eval_samples_per_second": 161.263,
      "eval_steps_per_second": 5.064,
      "step": 1053
    },
    {
      "epoch": 2.9936034115138592,
      "step": 1053,
      "total_flos": 3.3497451642252165e+18,
      "train_loss": 0.5538646526146479,
      "train_runtime": 2114.6386,
      "train_samples_per_second": 63.841,
      "train_steps_per_second": 0.498
    }
  ],
  "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": 3.3497451642252165e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}