{
  "best_metric": 0.8104314804077148,
  "best_model_checkpoint": "/media/mldrive/kcardenas/limb_classification_person_crop/beit-large-patch16-384/8_1e-4_1e-3_0.1/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": 1217842.375,
      "learning_rate": 5e-06,
      "loss": 1.5829,
      "step": 25
    },
    {
      "epoch": 0.2336448598130841,
      "grad_norm": 743310.1875,
      "learning_rate": 1e-05,
      "loss": 1.4705,
      "step": 50
    },
    {
      "epoch": 0.35046728971962615,
      "grad_norm": 651590.4375,
      "learning_rate": 1.5e-05,
      "loss": 1.411,
      "step": 75
    },
    {
      "epoch": 0.4672897196261682,
      "grad_norm": 442779.90625,
      "learning_rate": 2e-05,
      "loss": 1.4027,
      "step": 100
    },
    {
      "epoch": 0.5841121495327103,
      "grad_norm": 468140.84375,
      "learning_rate": 2.5e-05,
      "loss": 1.3717,
      "step": 125
    },
    {
      "epoch": 0.7009345794392523,
      "grad_norm": 354567.5625,
      "learning_rate": 3e-05,
      "loss": 1.3302,
      "step": 150
    },
    {
      "epoch": 0.8177570093457944,
      "grad_norm": 512739.0625,
      "learning_rate": 3.5e-05,
      "loss": 1.3142,
      "step": 175
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": 557678.25,
      "learning_rate": 4e-05,
      "loss": 1.2934,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.45854063018242125,
      "eval_loss": 1.310935139656067,
      "eval_runtime": 14.7436,
      "eval_samples_per_second": 81.798,
      "eval_steps_per_second": 2.577,
      "step": 214
    },
    {
      "epoch": 1.0514018691588785,
      "grad_norm": 342119.03125,
      "learning_rate": 4.5e-05,
      "loss": 1.2604,
      "step": 225
    },
    {
      "epoch": 1.1682242990654206,
      "grad_norm": 267202.78125,
      "learning_rate": 5e-05,
      "loss": 1.2483,
      "step": 250
    },
    {
      "epoch": 1.2850467289719627,
      "grad_norm": 231700.59375,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.2028,
      "step": 275
    },
    {
      "epoch": 1.4018691588785046,
      "grad_norm": 240836.390625,
      "learning_rate": 6e-05,
      "loss": 1.2499,
      "step": 300
    },
    {
      "epoch": 1.5186915887850467,
      "grad_norm": 343488.6875,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.2375,
      "step": 325
    },
    {
      "epoch": 1.6355140186915889,
      "grad_norm": 235778.375,
      "learning_rate": 7e-05,
      "loss": 1.2126,
      "step": 350
    },
    {
      "epoch": 1.7523364485981308,
      "grad_norm": 217530.28125,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.2085,
      "step": 375
    },
    {
      "epoch": 1.8691588785046729,
      "grad_norm": 488959.4375,
      "learning_rate": 8e-05,
      "loss": 1.1709,
      "step": 400
    },
    {
      "epoch": 1.985981308411215,
      "grad_norm": 343188.84375,
      "learning_rate": 8.5e-05,
      "loss": 1.1806,
      "step": 425
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5563847429519071,
      "eval_loss": 1.109222650527954,
      "eval_runtime": 15.1212,
      "eval_samples_per_second": 79.756,
      "eval_steps_per_second": 2.513,
      "step": 428
    },
    {
      "epoch": 2.102803738317757,
      "grad_norm": 510198.4375,
      "learning_rate": 9e-05,
      "loss": 1.223,
      "step": 450
    },
    {
      "epoch": 2.2196261682242993,
      "grad_norm": 249117.484375,
      "learning_rate": 9.5e-05,
      "loss": 1.1548,
      "step": 475
    },
    {
      "epoch": 2.336448598130841,
      "grad_norm": 222429.15625,
      "learning_rate": 0.0001,
      "loss": 1.1652,
      "step": 500
    },
    {
      "epoch": 2.453271028037383,
      "grad_norm": 283511.53125,
      "learning_rate": 9.847560975609756e-05,
      "loss": 1.2161,
      "step": 525
    },
    {
      "epoch": 2.5700934579439254,
      "grad_norm": 183689.015625,
      "learning_rate": 9.695121951219512e-05,
      "loss": 1.2039,
      "step": 550
    },
    {
      "epoch": 2.6869158878504673,
      "grad_norm": 217182.84375,
      "learning_rate": 9.542682926829268e-05,
      "loss": 1.1824,
      "step": 575
    },
    {
      "epoch": 2.803738317757009,
      "grad_norm": 574460.0625,
      "learning_rate": 9.390243902439024e-05,
      "loss": 1.1651,
      "step": 600
    },
    {
      "epoch": 2.9205607476635516,
      "grad_norm": 194637.703125,
      "learning_rate": 9.237804878048782e-05,
      "loss": 1.181,
      "step": 625
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6077943615257048,
      "eval_loss": 1.038699746131897,
      "eval_runtime": 14.808,
      "eval_samples_per_second": 81.442,
      "eval_steps_per_second": 2.566,
      "step": 642
    },
    {
      "epoch": 3.0373831775700935,
      "grad_norm": 174755.5,
      "learning_rate": 9.085365853658538e-05,
      "loss": 1.1829,
      "step": 650
    },
    {
      "epoch": 3.1542056074766354,
      "grad_norm": 206334.171875,
      "learning_rate": 8.932926829268294e-05,
      "loss": 1.1063,
      "step": 675
    },
    {
      "epoch": 3.2710280373831777,
      "grad_norm": 214731.515625,
      "learning_rate": 8.78048780487805e-05,
      "loss": 1.1616,
      "step": 700
    },
    {
      "epoch": 3.3878504672897196,
      "grad_norm": 247518.84375,
      "learning_rate": 8.628048780487805e-05,
      "loss": 1.1424,
      "step": 725
    },
    {
      "epoch": 3.5046728971962615,
      "grad_norm": 206443.25,
      "learning_rate": 8.475609756097561e-05,
      "loss": 1.152,
      "step": 750
    },
    {
      "epoch": 3.621495327102804,
      "grad_norm": 189756.421875,
      "learning_rate": 8.323170731707317e-05,
      "loss": 1.114,
      "step": 775
    },
    {
      "epoch": 3.7383177570093458,
      "grad_norm": 202614.625,
      "learning_rate": 8.170731707317073e-05,
      "loss": 1.1359,
      "step": 800
    },
    {
      "epoch": 3.8551401869158877,
      "grad_norm": 240795.953125,
      "learning_rate": 8.018292682926831e-05,
      "loss": 1.1248,
      "step": 825
    },
    {
      "epoch": 3.97196261682243,
      "grad_norm": 222365.71875,
      "learning_rate": 7.865853658536587e-05,
      "loss": 1.1188,
      "step": 850
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_loss": 0.9512582421302795,
      "eval_runtime": 15.1388,
      "eval_samples_per_second": 79.663,
      "eval_steps_per_second": 2.51,
      "step": 856
    },
    {
      "epoch": 4.088785046728972,
      "grad_norm": 259224.40625,
      "learning_rate": 7.713414634146343e-05,
      "loss": 1.0856,
      "step": 875
    },
    {
      "epoch": 4.205607476635514,
      "grad_norm": 197973.890625,
      "learning_rate": 7.560975609756099e-05,
      "loss": 1.1044,
      "step": 900
    },
    {
      "epoch": 4.322429906542056,
      "grad_norm": 331749.875,
      "learning_rate": 7.408536585365855e-05,
      "loss": 1.083,
      "step": 925
    },
    {
      "epoch": 4.4392523364485985,
      "grad_norm": 229539.890625,
      "learning_rate": 7.25609756097561e-05,
      "loss": 1.0673,
      "step": 950
    },
    {
      "epoch": 4.55607476635514,
      "grad_norm": 199168.28125,
      "learning_rate": 7.103658536585366e-05,
      "loss": 1.0665,
      "step": 975
    },
    {
      "epoch": 4.672897196261682,
      "grad_norm": 162672.40625,
      "learning_rate": 6.951219512195122e-05,
      "loss": 1.0367,
      "step": 1000
    },
    {
      "epoch": 4.789719626168225,
      "grad_norm": 198779.140625,
      "learning_rate": 6.798780487804878e-05,
      "loss": 1.0551,
      "step": 1025
    },
    {
      "epoch": 4.906542056074766,
      "grad_norm": 198510.765625,
      "learning_rate": 6.646341463414634e-05,
      "loss": 1.0883,
      "step": 1050
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6849087893864013,
      "eval_loss": 0.9217574000358582,
      "eval_runtime": 15.6174,
      "eval_samples_per_second": 77.222,
      "eval_steps_per_second": 2.433,
      "step": 1070
    },
    {
      "epoch": 5.0233644859813085,
      "grad_norm": 330993.65625,
      "learning_rate": 6.49390243902439e-05,
      "loss": 1.0981,
      "step": 1075
    },
    {
      "epoch": 5.140186915887851,
      "grad_norm": 271345.6875,
      "learning_rate": 6.341463414634146e-05,
      "loss": 1.0346,
      "step": 1100
    },
    {
      "epoch": 5.257009345794392,
      "grad_norm": 257730.21875,
      "learning_rate": 6.189024390243902e-05,
      "loss": 1.0354,
      "step": 1125
    },
    {
      "epoch": 5.373831775700935,
      "grad_norm": 214900.15625,
      "learning_rate": 6.036585365853659e-05,
      "loss": 1.0315,
      "step": 1150
    },
    {
      "epoch": 5.490654205607477,
      "grad_norm": 271099.71875,
      "learning_rate": 5.884146341463415e-05,
      "loss": 1.0092,
      "step": 1175
    },
    {
      "epoch": 5.607476635514018,
      "grad_norm": 213789.734375,
      "learning_rate": 5.731707317073171e-05,
      "loss": 1.0221,
      "step": 1200
    },
    {
      "epoch": 5.724299065420561,
      "grad_norm": 232312.421875,
      "learning_rate": 5.5792682926829274e-05,
      "loss": 1.0395,
      "step": 1225
    },
    {
      "epoch": 5.841121495327103,
      "grad_norm": 144164.546875,
      "learning_rate": 5.4268292682926834e-05,
      "loss": 1.0129,
      "step": 1250
    },
    {
      "epoch": 5.957943925233645,
      "grad_norm": 169016.9375,
      "learning_rate": 5.2743902439024394e-05,
      "loss": 1.0148,
      "step": 1275
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7106135986733002,
      "eval_loss": 0.8751299381256104,
      "eval_runtime": 15.15,
      "eval_samples_per_second": 79.604,
      "eval_steps_per_second": 2.508,
      "step": 1284
    },
    {
      "epoch": 6.074766355140187,
      "grad_norm": 314712.125,
      "learning_rate": 5.121951219512195e-05,
      "loss": 0.9848,
      "step": 1300
    },
    {
      "epoch": 6.191588785046729,
      "grad_norm": 259893.6875,
      "learning_rate": 4.969512195121951e-05,
      "loss": 1.0045,
      "step": 1325
    },
    {
      "epoch": 6.308411214953271,
      "grad_norm": 160624.953125,
      "learning_rate": 4.817073170731707e-05,
      "loss": 1.0013,
      "step": 1350
    },
    {
      "epoch": 6.425233644859813,
      "grad_norm": 298028.3125,
      "learning_rate": 4.664634146341464e-05,
      "loss": 0.9589,
      "step": 1375
    },
    {
      "epoch": 6.542056074766355,
      "grad_norm": 221959.015625,
      "learning_rate": 4.51219512195122e-05,
      "loss": 0.9671,
      "step": 1400
    },
    {
      "epoch": 6.658878504672897,
      "grad_norm": 219538.75,
      "learning_rate": 4.359756097560976e-05,
      "loss": 0.9495,
      "step": 1425
    },
    {
      "epoch": 6.775700934579439,
      "grad_norm": 188839.3125,
      "learning_rate": 4.207317073170732e-05,
      "loss": 0.9806,
      "step": 1450
    },
    {
      "epoch": 6.892523364485982,
      "grad_norm": 242229.4375,
      "learning_rate": 4.0548780487804884e-05,
      "loss": 0.9767,
      "step": 1475
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.746268656716418,
      "eval_loss": 0.8361870646476746,
      "eval_runtime": 15.1552,
      "eval_samples_per_second": 79.576,
      "eval_steps_per_second": 2.507,
      "step": 1498
    },
    {
      "epoch": 7.009345794392523,
      "grad_norm": 210763.171875,
      "learning_rate": 3.9024390243902444e-05,
      "loss": 0.963,
      "step": 1500
    },
    {
      "epoch": 7.126168224299065,
      "grad_norm": 201932.671875,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.9168,
      "step": 1525
    },
    {
      "epoch": 7.242990654205608,
      "grad_norm": 167061.890625,
      "learning_rate": 3.597560975609756e-05,
      "loss": 0.9903,
      "step": 1550
    },
    {
      "epoch": 7.359813084112149,
      "grad_norm": 317654.1875,
      "learning_rate": 3.445121951219512e-05,
      "loss": 0.9235,
      "step": 1575
    },
    {
      "epoch": 7.4766355140186915,
      "grad_norm": 163850.625,
      "learning_rate": 3.292682926829269e-05,
      "loss": 0.9153,
      "step": 1600
    },
    {
      "epoch": 7.593457943925234,
      "grad_norm": 166939.59375,
      "learning_rate": 3.140243902439025e-05,
      "loss": 0.9669,
      "step": 1625
    },
    {
      "epoch": 7.710280373831775,
      "grad_norm": 187720.734375,
      "learning_rate": 2.9878048780487805e-05,
      "loss": 0.9397,
      "step": 1650
    },
    {
      "epoch": 7.827102803738318,
      "grad_norm": 279596.0625,
      "learning_rate": 2.8353658536585365e-05,
      "loss": 0.9164,
      "step": 1675
    },
    {
      "epoch": 7.94392523364486,
      "grad_norm": 190616.0625,
      "learning_rate": 2.682926829268293e-05,
      "loss": 0.9218,
      "step": 1700
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.746268656716418,
      "eval_loss": 0.8222536444664001,
      "eval_runtime": 15.1444,
      "eval_samples_per_second": 79.633,
      "eval_steps_per_second": 2.509,
      "step": 1712
    },
    {
      "epoch": 8.060747663551401,
      "grad_norm": 212519.125,
      "learning_rate": 2.530487804878049e-05,
      "loss": 0.9206,
      "step": 1725
    },
    {
      "epoch": 8.177570093457945,
      "grad_norm": 177413.6875,
      "learning_rate": 2.378048780487805e-05,
      "loss": 0.8684,
      "step": 1750
    },
    {
      "epoch": 8.294392523364486,
      "grad_norm": 223749.203125,
      "learning_rate": 2.225609756097561e-05,
      "loss": 0.9026,
      "step": 1775
    },
    {
      "epoch": 8.411214953271028,
      "grad_norm": 237978.796875,
      "learning_rate": 2.073170731707317e-05,
      "loss": 0.8628,
      "step": 1800
    },
    {
      "epoch": 8.52803738317757,
      "grad_norm": 195313.34375,
      "learning_rate": 1.9207317073170733e-05,
      "loss": 0.8996,
      "step": 1825
    },
    {
      "epoch": 8.644859813084112,
      "grad_norm": 206904.25,
      "learning_rate": 1.7682926829268292e-05,
      "loss": 0.8929,
      "step": 1850
    },
    {
      "epoch": 8.761682242990654,
      "grad_norm": 185694.890625,
      "learning_rate": 1.6158536585365855e-05,
      "loss": 0.8662,
      "step": 1875
    },
    {
      "epoch": 8.878504672897197,
      "grad_norm": 235396.53125,
      "learning_rate": 1.4634146341463415e-05,
      "loss": 0.8701,
      "step": 1900
    },
    {
      "epoch": 8.995327102803738,
      "grad_norm": 163277.984375,
      "learning_rate": 1.3109756097560976e-05,
      "loss": 0.8507,
      "step": 1925
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.7620232172470979,
      "eval_loss": 0.8148385286331177,
      "eval_runtime": 15.03,
      "eval_samples_per_second": 80.24,
      "eval_steps_per_second": 2.528,
      "step": 1926
    },
    {
      "epoch": 9.11214953271028,
      "grad_norm": 202752.34375,
      "learning_rate": 1.1585365853658537e-05,
      "loss": 0.7827,
      "step": 1950
    },
    {
      "epoch": 9.228971962616823,
      "grad_norm": 229156.890625,
      "learning_rate": 1.0060975609756099e-05,
      "loss": 0.8734,
      "step": 1975
    },
    {
      "epoch": 9.345794392523365,
      "grad_norm": 162009.6875,
      "learning_rate": 8.53658536585366e-06,
      "loss": 0.8241,
      "step": 2000
    },
    {
      "epoch": 9.462616822429906,
      "grad_norm": 203122.65625,
      "learning_rate": 7.0121951219512205e-06,
      "loss": 0.772,
      "step": 2025
    },
    {
      "epoch": 9.57943925233645,
      "grad_norm": 201357.0625,
      "learning_rate": 5.487804878048781e-06,
      "loss": 0.8671,
      "step": 2050
    },
    {
      "epoch": 9.69626168224299,
      "grad_norm": 326030.46875,
      "learning_rate": 3.9634146341463414e-06,
      "loss": 0.8559,
      "step": 2075
    },
    {
      "epoch": 9.813084112149532,
      "grad_norm": 297982.5625,
      "learning_rate": 2.4390243902439027e-06,
      "loss": 0.8573,
      "step": 2100
    },
    {
      "epoch": 9.929906542056075,
      "grad_norm": 219615.546875,
      "learning_rate": 9.146341463414634e-07,
      "loss": 0.8348,
      "step": 2125
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.7628524046434494,
      "eval_loss": 0.8104314804077148,
      "eval_runtime": 15.5758,
      "eval_samples_per_second": 77.428,
      "eval_steps_per_second": 2.44,
      "step": 2140
    },
    {
      "epoch": 10.0,
      "step": 2140,
      "total_flos": 5.510586115727032e+19,
      "train_loss": 1.064676717062977,
      "train_runtime": 1932.3079,
      "train_samples_per_second": 35.346,
      "train_steps_per_second": 1.107
    }
  ],
  "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": 5.510586115727032e+19,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}