{
  "best_global_step": 705,
  "best_metric": 0.09983178973197937,
  "best_model_checkpoint": "/content/drive/MyDrive/efficientnet-b4-nails-model/checkpoint-705",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1175,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 3.302157402038574,
      "learning_rate": 4.919148936170213e-05,
      "loss": 1.7304580688476563,
      "step": 20
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 3.1470284461975098,
      "learning_rate": 4.8340425531914896e-05,
      "loss": 1.5841476440429687,
      "step": 40
    },
    {
      "epoch": 0.2553191489361702,
      "grad_norm": 3.53950834274292,
      "learning_rate": 4.748936170212766e-05,
      "loss": 1.4375492095947267,
      "step": 60
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 3.167618989944458,
      "learning_rate": 4.6638297872340424e-05,
      "loss": 1.2950922012329102,
      "step": 80
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 3.141378402709961,
      "learning_rate": 4.5787234042553194e-05,
      "loss": 1.0708379745483398,
      "step": 100
    },
    {
      "epoch": 0.5106382978723404,
      "grad_norm": 3.1946516036987305,
      "learning_rate": 4.493617021276596e-05,
      "loss": 0.8597142219543457,
      "step": 120
    },
    {
      "epoch": 0.5957446808510638,
      "grad_norm": 3.6128246784210205,
      "learning_rate": 4.408510638297872e-05,
      "loss": 0.7868041515350341,
      "step": 140
    },
    {
      "epoch": 0.6808510638297872,
      "grad_norm": 5.161598205566406,
      "learning_rate": 4.3234042553191486e-05,
      "loss": 0.698690128326416,
      "step": 160
    },
    {
      "epoch": 0.7659574468085106,
      "grad_norm": 4.21470308303833,
      "learning_rate": 4.238297872340426e-05,
      "loss": 0.6200400829315186,
      "step": 180
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 2.677668809890747,
      "learning_rate": 4.153191489361702e-05,
      "loss": 0.5314934253692627,
      "step": 200
    },
    {
      "epoch": 0.9361702127659575,
      "grad_norm": 1.6603856086730957,
      "learning_rate": 4.068085106382979e-05,
      "loss": 0.44487762451171875,
      "step": 220
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.3377927541732788,
      "eval_runtime": 7.8572,
      "eval_samples_per_second": 11.582,
      "eval_steps_per_second": 0.764,
      "step": 235
    },
    {
      "epoch": 1.0212765957446808,
      "grad_norm": 4.087282657623291,
      "learning_rate": 3.9829787234042556e-05,
      "loss": 0.45683655738830564,
      "step": 240
    },
    {
      "epoch": 1.1063829787234043,
      "grad_norm": 1.5097193717956543,
      "learning_rate": 3.897872340425532e-05,
      "loss": 0.3067047357559204,
      "step": 260
    },
    {
      "epoch": 1.1914893617021276,
      "grad_norm": 3.3649184703826904,
      "learning_rate": 3.812765957446809e-05,
      "loss": 0.2815602540969849,
      "step": 280
    },
    {
      "epoch": 1.2765957446808511,
      "grad_norm": 2.988518238067627,
      "learning_rate": 3.7276595744680855e-05,
      "loss": 0.2793550968170166,
      "step": 300
    },
    {
      "epoch": 1.3617021276595744,
      "grad_norm": 2.940647840499878,
      "learning_rate": 3.642553191489362e-05,
      "loss": 0.28877763748168944,
      "step": 320
    },
    {
      "epoch": 1.4468085106382977,
      "grad_norm": 4.576767444610596,
      "learning_rate": 3.557446808510638e-05,
      "loss": 0.22904467582702637,
      "step": 340
    },
    {
      "epoch": 1.5319148936170213,
      "grad_norm": 4.684735298156738,
      "learning_rate": 3.4723404255319154e-05,
      "loss": 0.26979527473449705,
      "step": 360
    },
    {
      "epoch": 1.6170212765957448,
      "grad_norm": 3.732126235961914,
      "learning_rate": 3.387234042553192e-05,
      "loss": 0.2422767162322998,
      "step": 380
    },
    {
      "epoch": 1.702127659574468,
      "grad_norm": 3.40220046043396,
      "learning_rate": 3.302127659574468e-05,
      "loss": 0.24794645309448243,
      "step": 400
    },
    {
      "epoch": 1.7872340425531914,
      "grad_norm": 3.6664037704467773,
      "learning_rate": 3.2170212765957446e-05,
      "loss": 0.2186866044998169,
      "step": 420
    },
    {
      "epoch": 1.872340425531915,
      "grad_norm": 6.066251277923584,
      "learning_rate": 3.131914893617021e-05,
      "loss": 0.24691376686096192,
      "step": 440
    },
    {
      "epoch": 1.9574468085106385,
      "grad_norm": 4.297804832458496,
      "learning_rate": 3.046808510638298e-05,
      "loss": 0.18424748182296752,
      "step": 460
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.22569075226783752,
      "eval_runtime": 1.026,
      "eval_samples_per_second": 88.69,
      "eval_steps_per_second": 5.848,
      "step": 470
    },
    {
      "epoch": 2.0425531914893615,
      "grad_norm": 3.1135361194610596,
      "learning_rate": 2.9617021276595748e-05,
      "loss": 0.24354701042175292,
      "step": 480
    },
    {
      "epoch": 2.127659574468085,
      "grad_norm": 1.9686609506607056,
      "learning_rate": 2.8765957446808512e-05,
      "loss": 0.17706258296966554,
      "step": 500
    },
    {
      "epoch": 2.2127659574468086,
      "grad_norm": 0.9864359498023987,
      "learning_rate": 2.7914893617021276e-05,
      "loss": 0.10903202295303345,
      "step": 520
    },
    {
      "epoch": 2.297872340425532,
      "grad_norm": 2.598639965057373,
      "learning_rate": 2.7063829787234047e-05,
      "loss": 0.1576436400413513,
      "step": 540
    },
    {
      "epoch": 2.382978723404255,
      "grad_norm": 4.634835243225098,
      "learning_rate": 2.621276595744681e-05,
      "loss": 0.22807636260986328,
      "step": 560
    },
    {
      "epoch": 2.4680851063829787,
      "grad_norm": 6.271443843841553,
      "learning_rate": 2.5361702127659575e-05,
      "loss": 0.13264695405960084,
      "step": 580
    },
    {
      "epoch": 2.5531914893617023,
      "grad_norm": 4.2818098068237305,
      "learning_rate": 2.451063829787234e-05,
      "loss": 0.1266018271446228,
      "step": 600
    },
    {
      "epoch": 2.6382978723404253,
      "grad_norm": 5.939896583557129,
      "learning_rate": 2.3659574468085106e-05,
      "loss": 0.13802480697631836,
      "step": 620
    },
    {
      "epoch": 2.723404255319149,
      "grad_norm": 3.1643519401550293,
      "learning_rate": 2.2808510638297874e-05,
      "loss": 0.09551984667778016,
      "step": 640
    },
    {
      "epoch": 2.8085106382978724,
      "grad_norm": 0.462363600730896,
      "learning_rate": 2.195744680851064e-05,
      "loss": 0.1383751630783081,
      "step": 660
    },
    {
      "epoch": 2.8936170212765955,
      "grad_norm": 0.4047956168651581,
      "learning_rate": 2.1106382978723405e-05,
      "loss": 0.13573260307312013,
      "step": 680
    },
    {
      "epoch": 2.978723404255319,
      "grad_norm": 6.376397132873535,
      "learning_rate": 2.0255319148936172e-05,
      "loss": 0.1275852680206299,
      "step": 700
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.09983178973197937,
      "eval_runtime": 1.0418,
      "eval_samples_per_second": 87.352,
      "eval_steps_per_second": 5.759,
      "step": 705
    },
    {
      "epoch": 3.0638297872340425,
      "grad_norm": 0.7334774136543274,
      "learning_rate": 1.9404255319148936e-05,
      "loss": 0.0730510413646698,
      "step": 720
    },
    {
      "epoch": 3.148936170212766,
      "grad_norm": 0.931010901927948,
      "learning_rate": 1.8553191489361704e-05,
      "loss": 0.07135066390037537,
      "step": 740
    },
    {
      "epoch": 3.2340425531914896,
      "grad_norm": 0.6278732419013977,
      "learning_rate": 1.7702127659574468e-05,
      "loss": 0.0836083710193634,
      "step": 760
    },
    {
      "epoch": 3.3191489361702127,
      "grad_norm": 3.368824005126953,
      "learning_rate": 1.6851063829787235e-05,
      "loss": 0.08626257181167603,
      "step": 780
    },
    {
      "epoch": 3.404255319148936,
      "grad_norm": 0.11537643522024155,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.11819881200790405,
      "step": 800
    },
    {
      "epoch": 3.4893617021276597,
      "grad_norm": 0.9512754678726196,
      "learning_rate": 1.5148936170212765e-05,
      "loss": 0.06863199472427368,
      "step": 820
    },
    {
      "epoch": 3.574468085106383,
      "grad_norm": 0.27522802352905273,
      "learning_rate": 1.4297872340425534e-05,
      "loss": 0.07966882586479188,
      "step": 840
    },
    {
      "epoch": 3.6595744680851063,
      "grad_norm": 0.0916527658700943,
      "learning_rate": 1.3446808510638298e-05,
      "loss": 0.05501900911331177,
      "step": 860
    },
    {
      "epoch": 3.74468085106383,
      "grad_norm": 1.5424407720565796,
      "learning_rate": 1.2595744680851065e-05,
      "loss": 0.07910426259040833,
      "step": 880
    },
    {
      "epoch": 3.829787234042553,
      "grad_norm": 2.654416799545288,
      "learning_rate": 1.174468085106383e-05,
      "loss": 0.08968157172203065,
      "step": 900
    },
    {
      "epoch": 3.9148936170212765,
      "grad_norm": 5.711701393127441,
      "learning_rate": 1.0893617021276597e-05,
      "loss": 0.07239373326301575,
      "step": 920
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.0758056640625,
      "learning_rate": 1.0042553191489363e-05,
      "loss": 0.06431445479393005,
      "step": 940
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.17178592085838318,
      "eval_runtime": 1.0527,
      "eval_samples_per_second": 86.443,
      "eval_steps_per_second": 5.7,
      "step": 940
    },
    {
      "epoch": 4.085106382978723,
      "grad_norm": 0.8240408301353455,
      "learning_rate": 9.191489361702128e-06,
      "loss": 0.05246338844299316,
      "step": 960
    },
    {
      "epoch": 4.170212765957447,
      "grad_norm": 2.452493190765381,
      "learning_rate": 8.340425531914894e-06,
      "loss": 0.08099527955055237,
      "step": 980
    },
    {
      "epoch": 4.25531914893617,
      "grad_norm": 2.292018413543701,
      "learning_rate": 7.489361702127661e-06,
      "loss": 0.08736226558685303,
      "step": 1000
    },
    {
      "epoch": 4.340425531914893,
      "grad_norm": 0.20962312817573547,
      "learning_rate": 6.6382978723404254e-06,
      "loss": 0.09467198252677918,
      "step": 1020
    },
    {
      "epoch": 4.425531914893617,
      "grad_norm": 0.47298091650009155,
      "learning_rate": 5.787234042553192e-06,
      "loss": 0.033312416076660155,
      "step": 1040
    },
    {
      "epoch": 4.51063829787234,
      "grad_norm": 0.2106722593307495,
      "learning_rate": 4.936170212765958e-06,
      "loss": 0.04081133008003235,
      "step": 1060
    },
    {
      "epoch": 4.595744680851064,
      "grad_norm": 4.993804454803467,
      "learning_rate": 4.085106382978723e-06,
      "loss": 0.09599153995513916,
      "step": 1080
    },
    {
      "epoch": 4.680851063829787,
      "grad_norm": 0.2829795181751251,
      "learning_rate": 3.2340425531914895e-06,
      "loss": 0.05948078632354736,
      "step": 1100
    },
    {
      "epoch": 4.76595744680851,
      "grad_norm": 4.379271030426025,
      "learning_rate": 2.3829787234042557e-06,
      "loss": 0.07318262457847595,
      "step": 1120
    },
    {
      "epoch": 4.851063829787234,
      "grad_norm": 6.142686367034912,
      "learning_rate": 1.5319148936170212e-06,
      "loss": 0.08857622146606445,
      "step": 1140
    },
    {
      "epoch": 4.9361702127659575,
      "grad_norm": 1.5748469829559326,
      "learning_rate": 6.808510638297873e-07,
      "loss": 0.06185862421989441,
      "step": 1160
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.1980006843805313,
      "eval_runtime": 1.1408,
      "eval_samples_per_second": 79.768,
      "eval_steps_per_second": 5.259,
      "step": 1175
    }
  ],
  "logging_steps": 20,
  "max_steps": 1175,
  "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": 8.57125301637024e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}