{
  "best_metric": 0.9959458017710445,
  "best_model_checkpoint": "PlantDiseaseDetectorVit2/checkpoint-879",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 879,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034129692832764506,
      "grad_norm": 0.6686996817588806,
      "learning_rate": 5.681818181818182e-06,
      "loss": 3.7946,
      "step": 10
    },
    {
      "epoch": 0.06825938566552901,
      "grad_norm": 0.6528059244155884,
      "learning_rate": 1.1363636363636365e-05,
      "loss": 3.7634,
      "step": 20
    },
    {
      "epoch": 0.10238907849829351,
      "grad_norm": 0.7110876441001892,
      "learning_rate": 1.7045454545454546e-05,
      "loss": 3.6945,
      "step": 30
    },
    {
      "epoch": 0.13651877133105803,
      "grad_norm": 0.7198315858840942,
      "learning_rate": 2.272727272727273e-05,
      "loss": 3.5857,
      "step": 40
    },
    {
      "epoch": 0.17064846416382254,
      "grad_norm": 0.8180440068244934,
      "learning_rate": 2.8409090909090912e-05,
      "loss": 3.4298,
      "step": 50
    },
    {
      "epoch": 0.20477815699658702,
      "grad_norm": 0.8139916658401489,
      "learning_rate": 3.409090909090909e-05,
      "loss": 3.2427,
      "step": 60
    },
    {
      "epoch": 0.23890784982935154,
      "grad_norm": 0.8880642056465149,
      "learning_rate": 3.9772727272727275e-05,
      "loss": 3.013,
      "step": 70
    },
    {
      "epoch": 0.27303754266211605,
      "grad_norm": 0.8926830291748047,
      "learning_rate": 4.545454545454546e-05,
      "loss": 2.7552,
      "step": 80
    },
    {
      "epoch": 0.30716723549488056,
      "grad_norm": 1.002000093460083,
      "learning_rate": 4.9873577749683945e-05,
      "loss": 2.5021,
      "step": 90
    },
    {
      "epoch": 0.3412969283276451,
      "grad_norm": 0.9452126622200012,
      "learning_rate": 4.924146649810367e-05,
      "loss": 2.2347,
      "step": 100
    },
    {
      "epoch": 0.37542662116040953,
      "grad_norm": 1.039056420326233,
      "learning_rate": 4.860935524652339e-05,
      "loss": 2.0152,
      "step": 110
    },
    {
      "epoch": 0.40955631399317405,
      "grad_norm": 0.9824926853179932,
      "learning_rate": 4.797724399494311e-05,
      "loss": 1.8409,
      "step": 120
    },
    {
      "epoch": 0.44368600682593856,
      "grad_norm": 1.0370389223098755,
      "learning_rate": 4.734513274336283e-05,
      "loss": 1.6624,
      "step": 130
    },
    {
      "epoch": 0.4778156996587031,
      "grad_norm": 0.9628086090087891,
      "learning_rate": 4.6713021491782554e-05,
      "loss": 1.5434,
      "step": 140
    },
    {
      "epoch": 0.5119453924914675,
      "grad_norm": 1.0051034688949585,
      "learning_rate": 4.608091024020228e-05,
      "loss": 1.4022,
      "step": 150
    },
    {
      "epoch": 0.5460750853242321,
      "grad_norm": 0.9724010825157166,
      "learning_rate": 4.5448798988622e-05,
      "loss": 1.2981,
      "step": 160
    },
    {
      "epoch": 0.5802047781569966,
      "grad_norm": 1.2477946281433105,
      "learning_rate": 4.4816687737041726e-05,
      "loss": 1.2025,
      "step": 170
    },
    {
      "epoch": 0.6143344709897611,
      "grad_norm": 0.9471719861030579,
      "learning_rate": 4.418457648546144e-05,
      "loss": 1.1202,
      "step": 180
    },
    {
      "epoch": 0.6484641638225256,
      "grad_norm": 0.9492740631103516,
      "learning_rate": 4.355246523388117e-05,
      "loss": 1.053,
      "step": 190
    },
    {
      "epoch": 0.6825938566552902,
      "grad_norm": 0.9678471088409424,
      "learning_rate": 4.2920353982300885e-05,
      "loss": 0.9739,
      "step": 200
    },
    {
      "epoch": 0.7167235494880546,
      "grad_norm": 0.902233362197876,
      "learning_rate": 4.2288242730720607e-05,
      "loss": 0.9053,
      "step": 210
    },
    {
      "epoch": 0.7508532423208191,
      "grad_norm": 1.190834879875183,
      "learning_rate": 4.165613147914033e-05,
      "loss": 0.8599,
      "step": 220
    },
    {
      "epoch": 0.7849829351535836,
      "grad_norm": 1.094313144683838,
      "learning_rate": 4.102402022756005e-05,
      "loss": 0.8202,
      "step": 230
    },
    {
      "epoch": 0.8191126279863481,
      "grad_norm": 0.8496561050415039,
      "learning_rate": 4.039190897597978e-05,
      "loss": 0.7651,
      "step": 240
    },
    {
      "epoch": 0.8532423208191127,
      "grad_norm": 0.8702057003974915,
      "learning_rate": 3.9759797724399494e-05,
      "loss": 0.7268,
      "step": 250
    },
    {
      "epoch": 0.8873720136518771,
      "grad_norm": 0.9215129017829895,
      "learning_rate": 3.912768647281922e-05,
      "loss": 0.6796,
      "step": 260
    },
    {
      "epoch": 0.9215017064846417,
      "grad_norm": 1.1348512172698975,
      "learning_rate": 3.849557522123894e-05,
      "loss": 0.6446,
      "step": 270
    },
    {
      "epoch": 0.9556313993174061,
      "grad_norm": 0.8226602077484131,
      "learning_rate": 3.7863463969658666e-05,
      "loss": 0.6234,
      "step": 280
    },
    {
      "epoch": 0.9897610921501706,
      "grad_norm": 0.9013721942901611,
      "learning_rate": 3.723135271807838e-05,
      "loss": 0.5919,
      "step": 290
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9869838898965112,
      "eval_loss": 0.5612290501594543,
      "eval_runtime": 136.7393,
      "eval_samples_per_second": 68.546,
      "eval_steps_per_second": 1.075,
      "step": 293
    },
    {
      "epoch": 1.023890784982935,
      "grad_norm": 0.7781492471694946,
      "learning_rate": 3.659924146649811e-05,
      "loss": 0.5557,
      "step": 300
    },
    {
      "epoch": 1.0580204778156996,
      "grad_norm": 0.8166685104370117,
      "learning_rate": 3.5967130214917824e-05,
      "loss": 0.5387,
      "step": 310
    },
    {
      "epoch": 1.0921501706484642,
      "grad_norm": 0.9886695742607117,
      "learning_rate": 3.533501896333755e-05,
      "loss": 0.5075,
      "step": 320
    },
    {
      "epoch": 1.1262798634812285,
      "grad_norm": 0.90567946434021,
      "learning_rate": 3.470290771175727e-05,
      "loss": 0.4924,
      "step": 330
    },
    {
      "epoch": 1.1604095563139931,
      "grad_norm": 0.720587432384491,
      "learning_rate": 3.407079646017699e-05,
      "loss": 0.4753,
      "step": 340
    },
    {
      "epoch": 1.1945392491467577,
      "grad_norm": 0.8734786510467529,
      "learning_rate": 3.343868520859672e-05,
      "loss": 0.4488,
      "step": 350
    },
    {
      "epoch": 1.2286689419795223,
      "grad_norm": 1.006568431854248,
      "learning_rate": 3.280657395701643e-05,
      "loss": 0.4436,
      "step": 360
    },
    {
      "epoch": 1.2627986348122868,
      "grad_norm": 0.6803867816925049,
      "learning_rate": 3.217446270543616e-05,
      "loss": 0.4152,
      "step": 370
    },
    {
      "epoch": 1.2969283276450512,
      "grad_norm": 0.6060165166854858,
      "learning_rate": 3.1542351453855877e-05,
      "loss": 0.4105,
      "step": 380
    },
    {
      "epoch": 1.3310580204778157,
      "grad_norm": 0.6753475069999695,
      "learning_rate": 3.0910240202275605e-05,
      "loss": 0.3933,
      "step": 390
    },
    {
      "epoch": 1.36518771331058,
      "grad_norm": 0.6579934358596802,
      "learning_rate": 3.0278128950695323e-05,
      "loss": 0.3822,
      "step": 400
    },
    {
      "epoch": 1.3993174061433447,
      "grad_norm": 0.511236310005188,
      "learning_rate": 2.964601769911505e-05,
      "loss": 0.3665,
      "step": 410
    },
    {
      "epoch": 1.4334470989761092,
      "grad_norm": 0.6013672947883606,
      "learning_rate": 2.9013906447534767e-05,
      "loss": 0.3581,
      "step": 420
    },
    {
      "epoch": 1.4675767918088738,
      "grad_norm": 0.9311569929122925,
      "learning_rate": 2.8381795195954492e-05,
      "loss": 0.3556,
      "step": 430
    },
    {
      "epoch": 1.5017064846416384,
      "grad_norm": 0.6122246980667114,
      "learning_rate": 2.774968394437421e-05,
      "loss": 0.3421,
      "step": 440
    },
    {
      "epoch": 1.5358361774744027,
      "grad_norm": 0.5536355376243591,
      "learning_rate": 2.7117572692793936e-05,
      "loss": 0.327,
      "step": 450
    },
    {
      "epoch": 1.5699658703071673,
      "grad_norm": 0.5841261744499207,
      "learning_rate": 2.6485461441213654e-05,
      "loss": 0.3227,
      "step": 460
    },
    {
      "epoch": 1.6040955631399316,
      "grad_norm": 1.0431301593780518,
      "learning_rate": 2.5853350189633372e-05,
      "loss": 0.3152,
      "step": 470
    },
    {
      "epoch": 1.6382252559726962,
      "grad_norm": 0.8714063167572021,
      "learning_rate": 2.5221238938053098e-05,
      "loss": 0.3142,
      "step": 480
    },
    {
      "epoch": 1.6723549488054608,
      "grad_norm": 0.7647233605384827,
      "learning_rate": 2.458912768647282e-05,
      "loss": 0.3049,
      "step": 490
    },
    {
      "epoch": 1.7064846416382253,
      "grad_norm": 1.1779247522354126,
      "learning_rate": 2.3957016434892544e-05,
      "loss": 0.2965,
      "step": 500
    },
    {
      "epoch": 1.74061433447099,
      "grad_norm": 1.051600694656372,
      "learning_rate": 2.3324905183312266e-05,
      "loss": 0.29,
      "step": 510
    },
    {
      "epoch": 1.7747440273037542,
      "grad_norm": 0.7569793462753296,
      "learning_rate": 2.2692793931731988e-05,
      "loss": 0.2962,
      "step": 520
    },
    {
      "epoch": 1.8088737201365188,
      "grad_norm": 0.6314426064491272,
      "learning_rate": 2.206068268015171e-05,
      "loss": 0.2763,
      "step": 530
    },
    {
      "epoch": 1.8430034129692832,
      "grad_norm": 0.6302042603492737,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.2653,
      "step": 540
    },
    {
      "epoch": 1.8771331058020477,
      "grad_norm": 0.8586634993553162,
      "learning_rate": 2.079646017699115e-05,
      "loss": 0.2651,
      "step": 550
    },
    {
      "epoch": 1.9112627986348123,
      "grad_norm": 0.5459042191505432,
      "learning_rate": 2.016434892541087e-05,
      "loss": 0.256,
      "step": 560
    },
    {
      "epoch": 1.9453924914675769,
      "grad_norm": 0.4690670669078827,
      "learning_rate": 1.9532237673830593e-05,
      "loss": 0.2542,
      "step": 570
    },
    {
      "epoch": 1.9795221843003414,
      "grad_norm": 0.6143674850463867,
      "learning_rate": 1.8900126422250315e-05,
      "loss": 0.2529,
      "step": 580
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9951989757815001,
      "eval_loss": 0.24359659850597382,
      "eval_runtime": 134.2967,
      "eval_samples_per_second": 69.793,
      "eval_steps_per_second": 1.095,
      "step": 586
    },
    {
      "epoch": 2.013651877133106,
      "grad_norm": 0.40023496747016907,
      "learning_rate": 1.8268015170670037e-05,
      "loss": 0.2421,
      "step": 590
    },
    {
      "epoch": 2.04778156996587,
      "grad_norm": 0.5167109370231628,
      "learning_rate": 1.7635903919089762e-05,
      "loss": 0.2371,
      "step": 600
    },
    {
      "epoch": 2.0819112627986347,
      "grad_norm": 0.5056605935096741,
      "learning_rate": 1.7003792667509484e-05,
      "loss": 0.232,
      "step": 610
    },
    {
      "epoch": 2.1160409556313993,
      "grad_norm": 0.8010804057121277,
      "learning_rate": 1.6371681415929206e-05,
      "loss": 0.2306,
      "step": 620
    },
    {
      "epoch": 2.150170648464164,
      "grad_norm": 0.47784796357154846,
      "learning_rate": 1.5739570164348927e-05,
      "loss": 0.2229,
      "step": 630
    },
    {
      "epoch": 2.1843003412969284,
      "grad_norm": 0.5715758204460144,
      "learning_rate": 1.510745891276865e-05,
      "loss": 0.2255,
      "step": 640
    },
    {
      "epoch": 2.218430034129693,
      "grad_norm": 0.3998388350009918,
      "learning_rate": 1.4475347661188371e-05,
      "loss": 0.219,
      "step": 650
    },
    {
      "epoch": 2.252559726962457,
      "grad_norm": 0.6502085328102112,
      "learning_rate": 1.3843236409608093e-05,
      "loss": 0.2155,
      "step": 660
    },
    {
      "epoch": 2.2866894197952217,
      "grad_norm": 0.5454604625701904,
      "learning_rate": 1.3211125158027813e-05,
      "loss": 0.2113,
      "step": 670
    },
    {
      "epoch": 2.3208191126279862,
      "grad_norm": 0.669148862361908,
      "learning_rate": 1.2579013906447535e-05,
      "loss": 0.2124,
      "step": 680
    },
    {
      "epoch": 2.354948805460751,
      "grad_norm": 0.4781040847301483,
      "learning_rate": 1.1946902654867258e-05,
      "loss": 0.2116,
      "step": 690
    },
    {
      "epoch": 2.3890784982935154,
      "grad_norm": 0.2730717360973358,
      "learning_rate": 1.1314791403286978e-05,
      "loss": 0.2064,
      "step": 700
    },
    {
      "epoch": 2.42320819112628,
      "grad_norm": 0.30644622445106506,
      "learning_rate": 1.06826801517067e-05,
      "loss": 0.2022,
      "step": 710
    },
    {
      "epoch": 2.4573378839590445,
      "grad_norm": 0.4491395354270935,
      "learning_rate": 1.0050568900126423e-05,
      "loss": 0.2083,
      "step": 720
    },
    {
      "epoch": 2.491467576791809,
      "grad_norm": 0.3245304524898529,
      "learning_rate": 9.418457648546145e-06,
      "loss": 0.1992,
      "step": 730
    },
    {
      "epoch": 2.5255972696245736,
      "grad_norm": 0.4015863537788391,
      "learning_rate": 8.786346396965867e-06,
      "loss": 0.1993,
      "step": 740
    },
    {
      "epoch": 2.5597269624573378,
      "grad_norm": 0.7087588310241699,
      "learning_rate": 8.154235145385589e-06,
      "loss": 0.2034,
      "step": 750
    },
    {
      "epoch": 2.5938566552901023,
      "grad_norm": 0.27920275926589966,
      "learning_rate": 7.52212389380531e-06,
      "loss": 0.1951,
      "step": 760
    },
    {
      "epoch": 2.627986348122867,
      "grad_norm": 0.686769425868988,
      "learning_rate": 6.890012642225031e-06,
      "loss": 0.1956,
      "step": 770
    },
    {
      "epoch": 2.6621160409556315,
      "grad_norm": 0.293285995721817,
      "learning_rate": 6.257901390644753e-06,
      "loss": 0.1898,
      "step": 780
    },
    {
      "epoch": 2.696245733788396,
      "grad_norm": 0.3410426080226898,
      "learning_rate": 5.625790139064476e-06,
      "loss": 0.1905,
      "step": 790
    },
    {
      "epoch": 2.73037542662116,
      "grad_norm": 0.5243946313858032,
      "learning_rate": 4.993678887484197e-06,
      "loss": 0.1892,
      "step": 800
    },
    {
      "epoch": 2.7645051194539247,
      "grad_norm": 0.39842483401298523,
      "learning_rate": 4.361567635903919e-06,
      "loss": 0.1902,
      "step": 810
    },
    {
      "epoch": 2.7986348122866893,
      "grad_norm": 0.26469987630844116,
      "learning_rate": 3.729456384323641e-06,
      "loss": 0.1906,
      "step": 820
    },
    {
      "epoch": 2.832764505119454,
      "grad_norm": 0.33791306614875793,
      "learning_rate": 3.097345132743363e-06,
      "loss": 0.1864,
      "step": 830
    },
    {
      "epoch": 2.8668941979522184,
      "grad_norm": 0.6516376733779907,
      "learning_rate": 2.465233881163085e-06,
      "loss": 0.1858,
      "step": 840
    },
    {
      "epoch": 2.901023890784983,
      "grad_norm": 0.28408199548721313,
      "learning_rate": 1.8331226295828066e-06,
      "loss": 0.1933,
      "step": 850
    },
    {
      "epoch": 2.9351535836177476,
      "grad_norm": 0.2557958960533142,
      "learning_rate": 1.2010113780025286e-06,
      "loss": 0.1877,
      "step": 860
    },
    {
      "epoch": 2.969283276450512,
      "grad_norm": 0.4732515811920166,
      "learning_rate": 5.689001264222504e-07,
      "loss": 0.1886,
      "step": 870
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9959458017710445,
      "eval_loss": 0.18922357261180878,
      "eval_runtime": 134.1896,
      "eval_samples_per_second": 69.849,
      "eval_steps_per_second": 1.095,
      "step": 879
    },
    {
      "epoch": 3.0,
      "step": 879,
      "total_flos": 1.7439237705052348e+19,
      "train_loss": 0.789499712071728,
      "train_runtime": 9726.3121,
      "train_samples_per_second": 23.129,
      "train_steps_per_second": 0.09
    }
  ],
  "logging_steps": 10,
  "max_steps": 879,
  "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": 1.7439237705052348e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}