{
  "best_metric": 0.8342028856277466,
  "best_model_checkpoint": "/media/mldrive/kcardenas/limb_classification_person_crop/vit-large-patch32-384/8_5e-5_0.005_0.005/checkpoint-2140",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 2140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11682242990654206,
      "grad_norm": 348905.625,
      "learning_rate": 2.5e-06,
      "loss": 1.4798,
      "step": 25
    },
    {
      "epoch": 0.2336448598130841,
      "grad_norm": 366192.9375,
      "learning_rate": 5e-06,
      "loss": 1.4282,
      "step": 50
    },
    {
      "epoch": 0.35046728971962615,
      "grad_norm": 442668.375,
      "learning_rate": 7.5e-06,
      "loss": 1.4099,
      "step": 75
    },
    {
      "epoch": 0.4672897196261682,
      "grad_norm": 323321.59375,
      "learning_rate": 1e-05,
      "loss": 1.4424,
      "step": 100
    },
    {
      "epoch": 0.5841121495327103,
      "grad_norm": 323121.90625,
      "learning_rate": 1.25e-05,
      "loss": 1.4154,
      "step": 125
    },
    {
      "epoch": 0.7009345794392523,
      "grad_norm": 301725.59375,
      "learning_rate": 1.5e-05,
      "loss": 1.4072,
      "step": 150
    },
    {
      "epoch": 0.8177570093457944,
      "grad_norm": 393494.1875,
      "learning_rate": 1.75e-05,
      "loss": 1.3967,
      "step": 175
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": 421164.375,
      "learning_rate": 2e-05,
      "loss": 1.3972,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.29767827529021557,
      "eval_loss": 1.3777544498443604,
      "eval_runtime": 9.2886,
      "eval_samples_per_second": 129.837,
      "eval_steps_per_second": 4.091,
      "step": 214
    },
    {
      "epoch": 1.0514018691588785,
      "grad_norm": 324575.9375,
      "learning_rate": 2.25e-05,
      "loss": 1.3658,
      "step": 225
    },
    {
      "epoch": 1.1682242990654206,
      "grad_norm": 247780.0625,
      "learning_rate": 2.5e-05,
      "loss": 1.344,
      "step": 250
    },
    {
      "epoch": 1.2850467289719627,
      "grad_norm": 287698.3125,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 1.3529,
      "step": 275
    },
    {
      "epoch": 1.4018691588785046,
      "grad_norm": 188844.34375,
      "learning_rate": 3e-05,
      "loss": 1.3357,
      "step": 300
    },
    {
      "epoch": 1.5186915887850467,
      "grad_norm": 331473.5625,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 1.3553,
      "step": 325
    },
    {
      "epoch": 1.6355140186915889,
      "grad_norm": 155202.671875,
      "learning_rate": 3.5e-05,
      "loss": 1.3125,
      "step": 350
    },
    {
      "epoch": 1.7523364485981308,
      "grad_norm": 212343.203125,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.3201,
      "step": 375
    },
    {
      "epoch": 1.8691588785046729,
      "grad_norm": 235704.59375,
      "learning_rate": 4e-05,
      "loss": 1.2996,
      "step": 400
    },
    {
      "epoch": 1.985981308411215,
      "grad_norm": 171497.125,
      "learning_rate": 4.25e-05,
      "loss": 1.3229,
      "step": 425
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.34328358208955223,
      "eval_loss": 1.2777554988861084,
      "eval_runtime": 8.9455,
      "eval_samples_per_second": 134.816,
      "eval_steps_per_second": 4.248,
      "step": 428
    },
    {
      "epoch": 2.102803738317757,
      "grad_norm": 403048.375,
      "learning_rate": 4.5e-05,
      "loss": 1.2835,
      "step": 450
    },
    {
      "epoch": 2.2196261682242993,
      "grad_norm": 313509.96875,
      "learning_rate": 4.75e-05,
      "loss": 1.2446,
      "step": 475
    },
    {
      "epoch": 2.336448598130841,
      "grad_norm": 118995.53125,
      "learning_rate": 5e-05,
      "loss": 1.2531,
      "step": 500
    },
    {
      "epoch": 2.453271028037383,
      "grad_norm": 196832.5,
      "learning_rate": 4.923780487804878e-05,
      "loss": 1.2664,
      "step": 525
    },
    {
      "epoch": 2.5700934579439254,
      "grad_norm": 184626.796875,
      "learning_rate": 4.847560975609756e-05,
      "loss": 1.2543,
      "step": 550
    },
    {
      "epoch": 2.6869158878504673,
      "grad_norm": 206699.9375,
      "learning_rate": 4.771341463414634e-05,
      "loss": 1.2434,
      "step": 575
    },
    {
      "epoch": 2.803738317757009,
      "grad_norm": 161357.40625,
      "learning_rate": 4.695121951219512e-05,
      "loss": 1.2038,
      "step": 600
    },
    {
      "epoch": 2.9205607476635516,
      "grad_norm": 238538.046875,
      "learning_rate": 4.618902439024391e-05,
      "loss": 1.1861,
      "step": 625
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5240464344941956,
      "eval_loss": 1.0543369054794312,
      "eval_runtime": 8.6134,
      "eval_samples_per_second": 140.015,
      "eval_steps_per_second": 4.412,
      "step": 642
    },
    {
      "epoch": 3.0373831775700935,
      "grad_norm": 189993.671875,
      "learning_rate": 4.542682926829269e-05,
      "loss": 1.1849,
      "step": 650
    },
    {
      "epoch": 3.1542056074766354,
      "grad_norm": 152301.78125,
      "learning_rate": 4.466463414634147e-05,
      "loss": 1.1327,
      "step": 675
    },
    {
      "epoch": 3.2710280373831777,
      "grad_norm": 138904.296875,
      "learning_rate": 4.390243902439025e-05,
      "loss": 1.1319,
      "step": 700
    },
    {
      "epoch": 3.3878504672897196,
      "grad_norm": 237533.421875,
      "learning_rate": 4.314024390243903e-05,
      "loss": 1.1714,
      "step": 725
    },
    {
      "epoch": 3.5046728971962615,
      "grad_norm": 143892.265625,
      "learning_rate": 4.237804878048781e-05,
      "loss": 1.123,
      "step": 750
    },
    {
      "epoch": 3.621495327102804,
      "grad_norm": 169788.375,
      "learning_rate": 4.161585365853659e-05,
      "loss": 1.1269,
      "step": 775
    },
    {
      "epoch": 3.7383177570093458,
      "grad_norm": 152439.515625,
      "learning_rate": 4.085365853658537e-05,
      "loss": 1.096,
      "step": 800
    },
    {
      "epoch": 3.8551401869158877,
      "grad_norm": 243971.859375,
      "learning_rate": 4.0091463414634153e-05,
      "loss": 1.0856,
      "step": 825
    },
    {
      "epoch": 3.97196261682243,
      "grad_norm": 258901.046875,
      "learning_rate": 3.932926829268293e-05,
      "loss": 1.0712,
      "step": 850
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5829187396351575,
      "eval_loss": 0.9633036255836487,
      "eval_runtime": 8.6125,
      "eval_samples_per_second": 140.029,
      "eval_steps_per_second": 4.412,
      "step": 856
    },
    {
      "epoch": 4.088785046728972,
      "grad_norm": 167292.515625,
      "learning_rate": 3.856707317073171e-05,
      "loss": 1.0565,
      "step": 875
    },
    {
      "epoch": 4.205607476635514,
      "grad_norm": 186235.359375,
      "learning_rate": 3.780487804878049e-05,
      "loss": 1.052,
      "step": 900
    },
    {
      "epoch": 4.322429906542056,
      "grad_norm": 284606.71875,
      "learning_rate": 3.704268292682927e-05,
      "loss": 1.0331,
      "step": 925
    },
    {
      "epoch": 4.4392523364485985,
      "grad_norm": 254899.765625,
      "learning_rate": 3.628048780487805e-05,
      "loss": 1.0621,
      "step": 950
    },
    {
      "epoch": 4.55607476635514,
      "grad_norm": 180315.921875,
      "learning_rate": 3.551829268292683e-05,
      "loss": 1.0256,
      "step": 975
    },
    {
      "epoch": 4.672897196261682,
      "grad_norm": 199703.140625,
      "learning_rate": 3.475609756097561e-05,
      "loss": 1.0629,
      "step": 1000
    },
    {
      "epoch": 4.789719626168225,
      "grad_norm": 223656.703125,
      "learning_rate": 3.399390243902439e-05,
      "loss": 1.052,
      "step": 1025
    },
    {
      "epoch": 4.906542056074766,
      "grad_norm": 128887.3828125,
      "learning_rate": 3.323170731707317e-05,
      "loss": 1.0372,
      "step": 1050
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5787728026533997,
      "eval_loss": 0.9747114181518555,
      "eval_runtime": 9.3609,
      "eval_samples_per_second": 128.834,
      "eval_steps_per_second": 4.059,
      "step": 1070
    },
    {
      "epoch": 5.0233644859813085,
      "grad_norm": 185444.609375,
      "learning_rate": 3.246951219512195e-05,
      "loss": 1.0064,
      "step": 1075
    },
    {
      "epoch": 5.140186915887851,
      "grad_norm": 195000.546875,
      "learning_rate": 3.170731707317073e-05,
      "loss": 0.9703,
      "step": 1100
    },
    {
      "epoch": 5.257009345794392,
      "grad_norm": 224770.140625,
      "learning_rate": 3.094512195121951e-05,
      "loss": 0.9642,
      "step": 1125
    },
    {
      "epoch": 5.373831775700935,
      "grad_norm": 268917.96875,
      "learning_rate": 3.0182926829268294e-05,
      "loss": 0.9616,
      "step": 1150
    },
    {
      "epoch": 5.490654205607477,
      "grad_norm": 297243.84375,
      "learning_rate": 2.9420731707317074e-05,
      "loss": 0.9612,
      "step": 1175
    },
    {
      "epoch": 5.607476635514018,
      "grad_norm": 144216.828125,
      "learning_rate": 2.8658536585365854e-05,
      "loss": 1.005,
      "step": 1200
    },
    {
      "epoch": 5.724299065420561,
      "grad_norm": 267840.3125,
      "learning_rate": 2.7896341463414637e-05,
      "loss": 0.9913,
      "step": 1225
    },
    {
      "epoch": 5.841121495327103,
      "grad_norm": 208278.78125,
      "learning_rate": 2.7134146341463417e-05,
      "loss": 0.9447,
      "step": 1250
    },
    {
      "epoch": 5.957943925233645,
      "grad_norm": 220790.625,
      "learning_rate": 2.6371951219512197e-05,
      "loss": 0.9167,
      "step": 1275
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6185737976782753,
      "eval_loss": 0.9168270230293274,
      "eval_runtime": 8.774,
      "eval_samples_per_second": 137.451,
      "eval_steps_per_second": 4.331,
      "step": 1284
    },
    {
      "epoch": 6.074766355140187,
      "grad_norm": 244035.71875,
      "learning_rate": 2.5609756097560977e-05,
      "loss": 0.931,
      "step": 1300
    },
    {
      "epoch": 6.191588785046729,
      "grad_norm": 395175.90625,
      "learning_rate": 2.4847560975609756e-05,
      "loss": 0.8896,
      "step": 1325
    },
    {
      "epoch": 6.308411214953271,
      "grad_norm": 211588.765625,
      "learning_rate": 2.4085365853658536e-05,
      "loss": 0.9447,
      "step": 1350
    },
    {
      "epoch": 6.425233644859813,
      "grad_norm": 182786.671875,
      "learning_rate": 2.332317073170732e-05,
      "loss": 0.8793,
      "step": 1375
    },
    {
      "epoch": 6.542056074766355,
      "grad_norm": 217798.046875,
      "learning_rate": 2.25609756097561e-05,
      "loss": 0.9258,
      "step": 1400
    },
    {
      "epoch": 6.658878504672897,
      "grad_norm": 204464.8125,
      "learning_rate": 2.179878048780488e-05,
      "loss": 0.8926,
      "step": 1425
    },
    {
      "epoch": 6.775700934579439,
      "grad_norm": 207556.859375,
      "learning_rate": 2.103658536585366e-05,
      "loss": 0.9401,
      "step": 1450
    },
    {
      "epoch": 6.892523364485982,
      "grad_norm": 207020.09375,
      "learning_rate": 2.0274390243902442e-05,
      "loss": 0.9135,
      "step": 1475
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6127694859038143,
      "eval_loss": 0.9436032176017761,
      "eval_runtime": 8.5981,
      "eval_samples_per_second": 140.263,
      "eval_steps_per_second": 4.42,
      "step": 1498
    },
    {
      "epoch": 7.009345794392523,
      "grad_norm": 271914.59375,
      "learning_rate": 1.9512195121951222e-05,
      "loss": 0.9312,
      "step": 1500
    },
    {
      "epoch": 7.126168224299065,
      "grad_norm": 217887.953125,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 0.8364,
      "step": 1525
    },
    {
      "epoch": 7.242990654205608,
      "grad_norm": 205730.78125,
      "learning_rate": 1.798780487804878e-05,
      "loss": 0.8752,
      "step": 1550
    },
    {
      "epoch": 7.359813084112149,
      "grad_norm": 195772.34375,
      "learning_rate": 1.722560975609756e-05,
      "loss": 0.8142,
      "step": 1575
    },
    {
      "epoch": 7.4766355140186915,
      "grad_norm": 180570.6875,
      "learning_rate": 1.6463414634146345e-05,
      "loss": 0.8658,
      "step": 1600
    },
    {
      "epoch": 7.593457943925234,
      "grad_norm": 305636.625,
      "learning_rate": 1.5701219512195124e-05,
      "loss": 0.9042,
      "step": 1625
    },
    {
      "epoch": 7.710280373831775,
      "grad_norm": 192999.390625,
      "learning_rate": 1.4939024390243902e-05,
      "loss": 0.8942,
      "step": 1650
    },
    {
      "epoch": 7.827102803738318,
      "grad_norm": 331613.21875,
      "learning_rate": 1.4176829268292682e-05,
      "loss": 0.8732,
      "step": 1675
    },
    {
      "epoch": 7.94392523364486,
      "grad_norm": 275174.1875,
      "learning_rate": 1.3414634146341466e-05,
      "loss": 0.7999,
      "step": 1700
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_loss": 0.8458028435707092,
      "eval_runtime": 9.0274,
      "eval_samples_per_second": 133.593,
      "eval_steps_per_second": 4.209,
      "step": 1712
    },
    {
      "epoch": 8.060747663551401,
      "grad_norm": 276855.21875,
      "learning_rate": 1.2652439024390245e-05,
      "loss": 0.8101,
      "step": 1725
    },
    {
      "epoch": 8.177570093457945,
      "grad_norm": 336038.875,
      "learning_rate": 1.1890243902439025e-05,
      "loss": 0.8169,
      "step": 1750
    },
    {
      "epoch": 8.294392523364486,
      "grad_norm": 558232.125,
      "learning_rate": 1.1128048780487805e-05,
      "loss": 0.8482,
      "step": 1775
    },
    {
      "epoch": 8.411214953271028,
      "grad_norm": 267053.75,
      "learning_rate": 1.0365853658536585e-05,
      "loss": 0.8382,
      "step": 1800
    },
    {
      "epoch": 8.52803738317757,
      "grad_norm": 283212.71875,
      "learning_rate": 9.603658536585366e-06,
      "loss": 0.7774,
      "step": 1825
    },
    {
      "epoch": 8.644859813084112,
      "grad_norm": 278512.0,
      "learning_rate": 8.841463414634146e-06,
      "loss": 0.8045,
      "step": 1850
    },
    {
      "epoch": 8.761682242990654,
      "grad_norm": 248051.796875,
      "learning_rate": 8.079268292682928e-06,
      "loss": 0.834,
      "step": 1875
    },
    {
      "epoch": 8.878504672897197,
      "grad_norm": 263587.0625,
      "learning_rate": 7.317073170731707e-06,
      "loss": 0.796,
      "step": 1900
    },
    {
      "epoch": 8.995327102803738,
      "grad_norm": 246924.71875,
      "learning_rate": 6.554878048780488e-06,
      "loss": 0.7583,
      "step": 1925
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.6724709784411277,
      "eval_loss": 0.8397244215011597,
      "eval_runtime": 8.8544,
      "eval_samples_per_second": 136.204,
      "eval_steps_per_second": 4.292,
      "step": 1926
    },
    {
      "epoch": 9.11214953271028,
      "grad_norm": 268465.4375,
      "learning_rate": 5.792682926829269e-06,
      "loss": 0.7832,
      "step": 1950
    },
    {
      "epoch": 9.228971962616823,
      "grad_norm": 285287.53125,
      "learning_rate": 5.030487804878049e-06,
      "loss": 0.8099,
      "step": 1975
    },
    {
      "epoch": 9.345794392523365,
      "grad_norm": 259878.71875,
      "learning_rate": 4.26829268292683e-06,
      "loss": 0.7559,
      "step": 2000
    },
    {
      "epoch": 9.462616822429906,
      "grad_norm": 248615.9375,
      "learning_rate": 3.5060975609756102e-06,
      "loss": 0.7361,
      "step": 2025
    },
    {
      "epoch": 9.57943925233645,
      "grad_norm": 320537.875,
      "learning_rate": 2.7439024390243905e-06,
      "loss": 0.7354,
      "step": 2050
    },
    {
      "epoch": 9.69626168224299,
      "grad_norm": 353997.875,
      "learning_rate": 1.9817073170731707e-06,
      "loss": 0.8389,
      "step": 2075
    },
    {
      "epoch": 9.813084112149532,
      "grad_norm": 309298.5625,
      "learning_rate": 1.2195121951219514e-06,
      "loss": 0.7722,
      "step": 2100
    },
    {
      "epoch": 9.929906542056075,
      "grad_norm": 285044.71875,
      "learning_rate": 4.573170731707317e-07,
      "loss": 0.8234,
      "step": 2125
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.6733001658374793,
      "eval_loss": 0.8342028856277466,
      "eval_runtime": 9.1401,
      "eval_samples_per_second": 131.946,
      "eval_steps_per_second": 4.158,
      "step": 2140
    },
    {
      "epoch": 10.0,
      "step": 2140,
      "total_flos": 5.540203890258739e+19,
      "train_loss": 1.0475434699905253,
      "train_runtime": 1600.6029,
      "train_samples_per_second": 42.671,
      "train_steps_per_second": 1.337
    }
  ],
  "logging_steps": 25,
  "max_steps": 2140,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 5.540203890258739e+19,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}