{
  "best_metric": 0.75,
  "best_model_checkpoint": "swinv2-base-patch4-window8-256-dmae-humeda-DAV15/checkpoint-80",
  "epoch": 41.869565217391305,
  "eval_steps": 500,
  "global_step": 210,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8695652173913043,
      "eval_accuracy": 0.3076923076923077,
      "eval_loss": 1.5972468852996826,
      "eval_runtime": 1.8054,
      "eval_samples_per_second": 28.802,
      "eval_steps_per_second": 1.108,
      "step": 5
    },
    {
      "epoch": 1.8695652173913042,
      "grad_norm": 10.893352508544922,
      "learning_rate": 9.523809523809525e-06,
      "loss": 6.7562,
      "step": 10
    },
    {
      "epoch": 1.8695652173913042,
      "eval_accuracy": 0.3076923076923077,
      "eval_loss": 1.5356961488723755,
      "eval_runtime": 1.4107,
      "eval_samples_per_second": 36.861,
      "eval_steps_per_second": 1.418,
      "step": 10
    },
    {
      "epoch": 2.869565217391304,
      "eval_accuracy": 0.40384615384615385,
      "eval_loss": 1.4953821897506714,
      "eval_runtime": 1.4409,
      "eval_samples_per_second": 36.088,
      "eval_steps_per_second": 1.388,
      "step": 15
    },
    {
      "epoch": 3.869565217391304,
      "grad_norm": 9.43877124786377,
      "learning_rate": 1.904761904761905e-05,
      "loss": 6.2842,
      "step": 20
    },
    {
      "epoch": 3.869565217391304,
      "eval_accuracy": 0.34615384615384615,
      "eval_loss": 1.461243987083435,
      "eval_runtime": 1.6776,
      "eval_samples_per_second": 30.997,
      "eval_steps_per_second": 1.192,
      "step": 20
    },
    {
      "epoch": 4.869565217391305,
      "eval_accuracy": 0.3269230769230769,
      "eval_loss": 1.387509822845459,
      "eval_runtime": 1.4405,
      "eval_samples_per_second": 36.1,
      "eval_steps_per_second": 1.388,
      "step": 25
    },
    {
      "epoch": 5.869565217391305,
      "grad_norm": 13.647711753845215,
      "learning_rate": 1.9888308262251286e-05,
      "loss": 4.9858,
      "step": 30
    },
    {
      "epoch": 5.869565217391305,
      "eval_accuracy": 0.34615384615384615,
      "eval_loss": 1.3369739055633545,
      "eval_runtime": 1.4598,
      "eval_samples_per_second": 35.622,
      "eval_steps_per_second": 1.37,
      "step": 30
    },
    {
      "epoch": 6.869565217391305,
      "eval_accuracy": 0.4423076923076923,
      "eval_loss": 1.2739052772521973,
      "eval_runtime": 1.8216,
      "eval_samples_per_second": 28.546,
      "eval_steps_per_second": 1.098,
      "step": 35
    },
    {
      "epoch": 7.869565217391305,
      "grad_norm": 18.52330207824707,
      "learning_rate": 1.9505415489478293e-05,
      "loss": 3.5596,
      "step": 40
    },
    {
      "epoch": 7.869565217391305,
      "eval_accuracy": 0.4807692307692308,
      "eval_loss": 1.1773827075958252,
      "eval_runtime": 1.4754,
      "eval_samples_per_second": 35.244,
      "eval_steps_per_second": 1.356,
      "step": 40
    },
    {
      "epoch": 8.869565217391305,
      "eval_accuracy": 0.4807692307692308,
      "eval_loss": 1.121440052986145,
      "eval_runtime": 1.4488,
      "eval_samples_per_second": 35.893,
      "eval_steps_per_second": 1.38,
      "step": 45
    },
    {
      "epoch": 9.869565217391305,
      "grad_norm": 18.99748420715332,
      "learning_rate": 1.8860495104301346e-05,
      "loss": 2.6814,
      "step": 50
    },
    {
      "epoch": 9.869565217391305,
      "eval_accuracy": 0.5192307692307693,
      "eval_loss": 1.0998505353927612,
      "eval_runtime": 1.5002,
      "eval_samples_per_second": 34.663,
      "eval_steps_per_second": 1.333,
      "step": 50
    },
    {
      "epoch": 10.869565217391305,
      "eval_accuracy": 0.46153846153846156,
      "eval_loss": 1.1773051023483276,
      "eval_runtime": 1.8237,
      "eval_samples_per_second": 28.513,
      "eval_steps_per_second": 1.097,
      "step": 55
    },
    {
      "epoch": 11.869565217391305,
      "grad_norm": 22.57859992980957,
      "learning_rate": 1.7971325072229227e-05,
      "loss": 2.3236,
      "step": 60
    },
    {
      "epoch": 11.869565217391305,
      "eval_accuracy": 0.5192307692307693,
      "eval_loss": 0.9873736500740051,
      "eval_runtime": 1.8064,
      "eval_samples_per_second": 28.786,
      "eval_steps_per_second": 1.107,
      "step": 60
    },
    {
      "epoch": 12.869565217391305,
      "eval_accuracy": 0.5,
      "eval_loss": 1.1123789548873901,
      "eval_runtime": 1.4402,
      "eval_samples_per_second": 36.106,
      "eval_steps_per_second": 1.389,
      "step": 65
    },
    {
      "epoch": 13.869565217391305,
      "grad_norm": 28.97609519958496,
      "learning_rate": 1.686241637868734e-05,
      "loss": 1.8037,
      "step": 70
    },
    {
      "epoch": 13.869565217391305,
      "eval_accuracy": 0.6538461538461539,
      "eval_loss": 0.8936060667037964,
      "eval_runtime": 1.4709,
      "eval_samples_per_second": 35.353,
      "eval_steps_per_second": 1.36,
      "step": 70
    },
    {
      "epoch": 14.869565217391305,
      "eval_accuracy": 0.4423076923076923,
      "eval_loss": 1.2063868045806885,
      "eval_runtime": 1.855,
      "eval_samples_per_second": 28.032,
      "eval_steps_per_second": 1.078,
      "step": 75
    },
    {
      "epoch": 15.869565217391305,
      "grad_norm": 27.648298263549805,
      "learning_rate": 1.5564337355766412e-05,
      "loss": 1.6474,
      "step": 80
    },
    {
      "epoch": 15.869565217391305,
      "eval_accuracy": 0.75,
      "eval_loss": 0.842289388179779,
      "eval_runtime": 1.7992,
      "eval_samples_per_second": 28.901,
      "eval_steps_per_second": 1.112,
      "step": 80
    },
    {
      "epoch": 16.869565217391305,
      "eval_accuracy": 0.6346153846153846,
      "eval_loss": 1.0133720636367798,
      "eval_runtime": 1.4225,
      "eval_samples_per_second": 36.554,
      "eval_steps_per_second": 1.406,
      "step": 85
    },
    {
      "epoch": 17.869565217391305,
      "grad_norm": 20.62474250793457,
      "learning_rate": 1.4112871031306118e-05,
      "loss": 1.5505,
      "step": 90
    },
    {
      "epoch": 17.869565217391305,
      "eval_accuracy": 0.6923076923076923,
      "eval_loss": 0.8965399861335754,
      "eval_runtime": 1.4632,
      "eval_samples_per_second": 35.54,
      "eval_steps_per_second": 1.367,
      "step": 90
    },
    {
      "epoch": 18.869565217391305,
      "eval_accuracy": 0.6538461538461539,
      "eval_loss": 0.9214943647384644,
      "eval_runtime": 1.4703,
      "eval_samples_per_second": 35.368,
      "eval_steps_per_second": 1.36,
      "step": 95
    },
    {
      "epoch": 19.869565217391305,
      "grad_norm": 31.890165328979492,
      "learning_rate": 1.2548028728946548e-05,
      "loss": 1.2697,
      "step": 100
    },
    {
      "epoch": 19.869565217391305,
      "eval_accuracy": 0.6153846153846154,
      "eval_loss": 1.0155353546142578,
      "eval_runtime": 1.4323,
      "eval_samples_per_second": 36.306,
      "eval_steps_per_second": 1.396,
      "step": 100
    },
    {
      "epoch": 20.869565217391305,
      "eval_accuracy": 0.7115384615384616,
      "eval_loss": 0.8500422835350037,
      "eval_runtime": 1.4418,
      "eval_samples_per_second": 36.065,
      "eval_steps_per_second": 1.387,
      "step": 105
    },
    {
      "epoch": 21.869565217391305,
      "grad_norm": 16.111915588378906,
      "learning_rate": 1.0912947110386484e-05,
      "loss": 1.1783,
      "step": 110
    },
    {
      "epoch": 21.869565217391305,
      "eval_accuracy": 0.6538461538461539,
      "eval_loss": 0.9573343992233276,
      "eval_runtime": 1.4883,
      "eval_samples_per_second": 34.938,
      "eval_steps_per_second": 1.344,
      "step": 110
    },
    {
      "epoch": 22.869565217391305,
      "eval_accuracy": 0.6923076923076923,
      "eval_loss": 0.8914616107940674,
      "eval_runtime": 1.7921,
      "eval_samples_per_second": 29.016,
      "eval_steps_per_second": 1.116,
      "step": 115
    },
    {
      "epoch": 23.869565217391305,
      "grad_norm": 16.878934860229492,
      "learning_rate": 9.252699064135759e-06,
      "loss": 1.0235,
      "step": 120
    },
    {
      "epoch": 23.869565217391305,
      "eval_accuracy": 0.6538461538461539,
      "eval_loss": 0.9831422567367554,
      "eval_runtime": 1.4719,
      "eval_samples_per_second": 35.328,
      "eval_steps_per_second": 1.359,
      "step": 120
    },
    {
      "epoch": 24.869565217391305,
      "eval_accuracy": 0.6538461538461539,
      "eval_loss": 0.9464498162269592,
      "eval_runtime": 1.4685,
      "eval_samples_per_second": 35.409,
      "eval_steps_per_second": 1.362,
      "step": 125
    },
    {
      "epoch": 25.869565217391305,
      "grad_norm": 22.73305892944336,
      "learning_rate": 7.613051219968624e-06,
      "loss": 0.9706,
      "step": 130
    },
    {
      "epoch": 25.869565217391305,
      "eval_accuracy": 0.6923076923076923,
      "eval_loss": 0.9413173198699951,
      "eval_runtime": 1.7224,
      "eval_samples_per_second": 30.191,
      "eval_steps_per_second": 1.161,
      "step": 130
    },
    {
      "epoch": 26.869565217391305,
      "eval_accuracy": 0.6346153846153846,
      "eval_loss": 1.0248907804489136,
      "eval_runtime": 1.7923,
      "eval_samples_per_second": 29.013,
      "eval_steps_per_second": 1.116,
      "step": 135
    },
    {
      "epoch": 27.869565217391305,
      "grad_norm": 21.775854110717773,
      "learning_rate": 6.039202339608432e-06,
      "loss": 0.9409,
      "step": 140
    },
    {
      "epoch": 27.869565217391305,
      "eval_accuracy": 0.6538461538461539,
      "eval_loss": 0.9753580093383789,
      "eval_runtime": 1.8553,
      "eval_samples_per_second": 28.028,
      "eval_steps_per_second": 1.078,
      "step": 140
    },
    {
      "epoch": 28.869565217391305,
      "eval_accuracy": 0.7115384615384616,
      "eval_loss": 0.9530434012413025,
      "eval_runtime": 1.7906,
      "eval_samples_per_second": 29.04,
      "eval_steps_per_second": 1.117,
      "step": 145
    },
    {
      "epoch": 29.869565217391305,
      "grad_norm": 16.502880096435547,
      "learning_rate": 4.5745373613424075e-06,
      "loss": 0.9447,
      "step": 150
    },
    {
      "epoch": 29.869565217391305,
      "eval_accuracy": 0.6538461538461539,
      "eval_loss": 1.02655827999115,
      "eval_runtime": 1.4711,
      "eval_samples_per_second": 35.348,
      "eval_steps_per_second": 1.36,
      "step": 150
    },
    {
      "epoch": 30.869565217391305,
      "eval_accuracy": 0.6538461538461539,
      "eval_loss": 1.0819494724273682,
      "eval_runtime": 1.4452,
      "eval_samples_per_second": 35.981,
      "eval_steps_per_second": 1.384,
      "step": 155
    },
    {
      "epoch": 31.869565217391305,
      "grad_norm": 14.975761413574219,
      "learning_rate": 3.2594314447468457e-06,
      "loss": 0.8352,
      "step": 160
    },
    {
      "epoch": 31.869565217391305,
      "eval_accuracy": 0.6923076923076923,
      "eval_loss": 0.9921611547470093,
      "eval_runtime": 1.6676,
      "eval_samples_per_second": 31.182,
      "eval_steps_per_second": 1.199,
      "step": 160
    },
    {
      "epoch": 32.869565217391305,
      "eval_accuracy": 0.6923076923076923,
      "eval_loss": 0.9754781126976013,
      "eval_runtime": 1.4838,
      "eval_samples_per_second": 35.046,
      "eval_steps_per_second": 1.348,
      "step": 165
    },
    {
      "epoch": 33.869565217391305,
      "grad_norm": 16.957916259765625,
      "learning_rate": 2.130136983393112e-06,
      "loss": 0.8055,
      "step": 170
    },
    {
      "epoch": 33.869565217391305,
      "eval_accuracy": 0.7115384615384616,
      "eval_loss": 0.9768009185791016,
      "eval_runtime": 1.4548,
      "eval_samples_per_second": 35.745,
      "eval_steps_per_second": 1.375,
      "step": 170
    },
    {
      "epoch": 34.869565217391305,
      "eval_accuracy": 0.6923076923076923,
      "eval_loss": 0.9950000047683716,
      "eval_runtime": 1.6477,
      "eval_samples_per_second": 31.56,
      "eval_steps_per_second": 1.214,
      "step": 175
    },
    {
      "epoch": 35.869565217391305,
      "grad_norm": 13.693328857421875,
      "learning_rate": 1.2177842662977136e-06,
      "loss": 0.7481,
      "step": 180
    },
    {
      "epoch": 35.869565217391305,
      "eval_accuracy": 0.6923076923076923,
      "eval_loss": 1.0135220289230347,
      "eval_runtime": 1.4654,
      "eval_samples_per_second": 35.486,
      "eval_steps_per_second": 1.365,
      "step": 180
    },
    {
      "epoch": 36.869565217391305,
      "eval_accuracy": 0.6923076923076923,
      "eval_loss": 1.0168299674987793,
      "eval_runtime": 1.4666,
      "eval_samples_per_second": 35.456,
      "eval_steps_per_second": 1.364,
      "step": 185
    },
    {
      "epoch": 37.869565217391305,
      "grad_norm": 16.68096923828125,
      "learning_rate": 5.475233360227516e-07,
      "loss": 0.7483,
      "step": 190
    },
    {
      "epoch": 37.869565217391305,
      "eval_accuracy": 0.6923076923076923,
      "eval_loss": 1.009111762046814,
      "eval_runtime": 1.4779,
      "eval_samples_per_second": 35.184,
      "eval_steps_per_second": 1.353,
      "step": 190
    },
    {
      "epoch": 38.869565217391305,
      "eval_accuracy": 0.6923076923076923,
      "eval_loss": 1.005540370941162,
      "eval_runtime": 1.5862,
      "eval_samples_per_second": 32.783,
      "eval_steps_per_second": 1.261,
      "step": 195
    },
    {
      "epoch": 39.869565217391305,
      "grad_norm": 27.558324813842773,
      "learning_rate": 1.3783069908621772e-07,
      "loss": 0.8145,
      "step": 200
    },
    {
      "epoch": 39.869565217391305,
      "eval_accuracy": 0.6923076923076923,
      "eval_loss": 1.0039584636688232,
      "eval_runtime": 1.47,
      "eval_samples_per_second": 35.373,
      "eval_steps_per_second": 1.361,
      "step": 200
    },
    {
      "epoch": 40.869565217391305,
      "eval_accuracy": 0.6923076923076923,
      "eval_loss": 1.0038609504699707,
      "eval_runtime": 1.466,
      "eval_samples_per_second": 35.471,
      "eval_steps_per_second": 1.364,
      "step": 205
    },
    {
      "epoch": 41.869565217391305,
      "grad_norm": 17.93744468688965,
      "learning_rate": 0.0,
      "loss": 0.7501,
      "step": 210
    },
    {
      "epoch": 41.869565217391305,
      "eval_accuracy": 0.6923076923076923,
      "eval_loss": 1.0038418769836426,
      "eval_runtime": 1.8649,
      "eval_samples_per_second": 27.884,
      "eval_steps_per_second": 1.072,
      "step": 210
    },
    {
      "epoch": 41.869565217391305,
      "step": 210,
      "total_flos": 2.8899664857724355e+18,
      "train_loss": 2.0296274548485167,
      "train_runtime": 2115.3253,
      "train_samples_per_second": 14.474,
      "train_steps_per_second": 0.099
    }
  ],
  "logging_steps": 10,
  "max_steps": 210,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 42,
  "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": 2.8899664857724355e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}