{
  "best_metric": 0.87679523229599,
  "best_model_checkpoint": "/media/mldrive/kcardenas/limb_classification_person_crop/beit-large-patch16-384/8_1e-4_5e-4_0.15/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": 1159652.375,
      "learning_rate": 5e-06,
      "loss": 1.5842,
      "step": 25
    },
    {
      "epoch": 0.2336448598130841,
      "grad_norm": 665793.625,
      "learning_rate": 1e-05,
      "loss": 1.4698,
      "step": 50
    },
    {
      "epoch": 0.35046728971962615,
      "grad_norm": 641848.25,
      "learning_rate": 1.5e-05,
      "loss": 1.4099,
      "step": 75
    },
    {
      "epoch": 0.4672897196261682,
      "grad_norm": 361838.5625,
      "learning_rate": 2e-05,
      "loss": 1.4008,
      "step": 100
    },
    {
      "epoch": 0.5841121495327103,
      "grad_norm": 444083.375,
      "learning_rate": 2.5e-05,
      "loss": 1.3763,
      "step": 125
    },
    {
      "epoch": 0.7009345794392523,
      "grad_norm": 672154.375,
      "learning_rate": 3e-05,
      "loss": 1.3726,
      "step": 150
    },
    {
      "epoch": 0.8177570093457944,
      "grad_norm": 3515615.75,
      "learning_rate": 3.5e-05,
      "loss": 1.3777,
      "step": 175
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": 1527419.75,
      "learning_rate": 4e-05,
      "loss": 1.3768,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2769485903814262,
      "eval_loss": 1.456185221672058,
      "eval_runtime": 15.2495,
      "eval_samples_per_second": 79.084,
      "eval_steps_per_second": 2.492,
      "step": 214
    },
    {
      "epoch": 1.0514018691588785,
      "grad_norm": 375564.53125,
      "learning_rate": 4.5e-05,
      "loss": 1.3807,
      "step": 225
    },
    {
      "epoch": 1.1682242990654206,
      "grad_norm": 285680.1875,
      "learning_rate": 5e-05,
      "loss": 1.367,
      "step": 250
    },
    {
      "epoch": 1.2850467289719627,
      "grad_norm": 428490.6875,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.3338,
      "step": 275
    },
    {
      "epoch": 1.4018691588785046,
      "grad_norm": 184152.671875,
      "learning_rate": 6e-05,
      "loss": 1.3453,
      "step": 300
    },
    {
      "epoch": 1.5186915887850467,
      "grad_norm": 180530.9375,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.2934,
      "step": 325
    },
    {
      "epoch": 1.6355140186915889,
      "grad_norm": 219887.5,
      "learning_rate": 7e-05,
      "loss": 1.3062,
      "step": 350
    },
    {
      "epoch": 1.7523364485981308,
      "grad_norm": 325509.625,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.2702,
      "step": 375
    },
    {
      "epoch": 1.8691588785046729,
      "grad_norm": 285242.25,
      "learning_rate": 8e-05,
      "loss": 1.2373,
      "step": 400
    },
    {
      "epoch": 1.985981308411215,
      "grad_norm": 233574.765625,
      "learning_rate": 8.5e-05,
      "loss": 1.2642,
      "step": 425
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5439469320066335,
      "eval_loss": 1.149614930152893,
      "eval_runtime": 15.5858,
      "eval_samples_per_second": 77.378,
      "eval_steps_per_second": 2.438,
      "step": 428
    },
    {
      "epoch": 2.102803738317757,
      "grad_norm": 361034.4375,
      "learning_rate": 9e-05,
      "loss": 1.2327,
      "step": 450
    },
    {
      "epoch": 2.2196261682242993,
      "grad_norm": 268217.28125,
      "learning_rate": 9.5e-05,
      "loss": 1.2506,
      "step": 475
    },
    {
      "epoch": 2.336448598130841,
      "grad_norm": 183026.546875,
      "learning_rate": 0.0001,
      "loss": 1.2404,
      "step": 500
    },
    {
      "epoch": 2.453271028037383,
      "grad_norm": 292976.4375,
      "learning_rate": 9.847560975609756e-05,
      "loss": 1.2289,
      "step": 525
    },
    {
      "epoch": 2.5700934579439254,
      "grad_norm": 165711.53125,
      "learning_rate": 9.695121951219512e-05,
      "loss": 1.2293,
      "step": 550
    },
    {
      "epoch": 2.6869158878504673,
      "grad_norm": 171990.359375,
      "learning_rate": 9.542682926829268e-05,
      "loss": 1.2409,
      "step": 575
    },
    {
      "epoch": 2.803738317757009,
      "grad_norm": 192889.6875,
      "learning_rate": 9.390243902439024e-05,
      "loss": 1.2113,
      "step": 600
    },
    {
      "epoch": 2.9205607476635516,
      "grad_norm": 192437.53125,
      "learning_rate": 9.237804878048782e-05,
      "loss": 1.2246,
      "step": 625
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6351575456053068,
      "eval_loss": 1.0498127937316895,
      "eval_runtime": 14.89,
      "eval_samples_per_second": 80.994,
      "eval_steps_per_second": 2.552,
      "step": 642
    },
    {
      "epoch": 3.0373831775700935,
      "grad_norm": 164391.703125,
      "learning_rate": 9.085365853658538e-05,
      "loss": 1.1982,
      "step": 650
    },
    {
      "epoch": 3.1542056074766354,
      "grad_norm": 165748.15625,
      "learning_rate": 8.932926829268294e-05,
      "loss": 1.1914,
      "step": 675
    },
    {
      "epoch": 3.2710280373831777,
      "grad_norm": 208878.25,
      "learning_rate": 8.78048780487805e-05,
      "loss": 1.1913,
      "step": 700
    },
    {
      "epoch": 3.3878504672897196,
      "grad_norm": 203566.75,
      "learning_rate": 8.628048780487805e-05,
      "loss": 1.194,
      "step": 725
    },
    {
      "epoch": 3.5046728971962615,
      "grad_norm": 148600.484375,
      "learning_rate": 8.475609756097561e-05,
      "loss": 1.1976,
      "step": 750
    },
    {
      "epoch": 3.621495327102804,
      "grad_norm": 173605.671875,
      "learning_rate": 8.323170731707317e-05,
      "loss": 1.1612,
      "step": 775
    },
    {
      "epoch": 3.7383177570093458,
      "grad_norm": 163473.796875,
      "learning_rate": 8.170731707317073e-05,
      "loss": 1.1965,
      "step": 800
    },
    {
      "epoch": 3.8551401869158877,
      "grad_norm": 173422.8125,
      "learning_rate": 8.018292682926831e-05,
      "loss": 1.1541,
      "step": 825
    },
    {
      "epoch": 3.97196261682243,
      "grad_norm": 193907.46875,
      "learning_rate": 7.865853658536587e-05,
      "loss": 1.1502,
      "step": 850
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6011608623548922,
      "eval_loss": 1.087031602859497,
      "eval_runtime": 15.7814,
      "eval_samples_per_second": 76.419,
      "eval_steps_per_second": 2.408,
      "step": 856
    },
    {
      "epoch": 4.088785046728972,
      "grad_norm": 196479.796875,
      "learning_rate": 7.713414634146343e-05,
      "loss": 1.1351,
      "step": 875
    },
    {
      "epoch": 4.205607476635514,
      "grad_norm": 123101.3671875,
      "learning_rate": 7.560975609756099e-05,
      "loss": 1.1463,
      "step": 900
    },
    {
      "epoch": 4.322429906542056,
      "grad_norm": 232118.515625,
      "learning_rate": 7.408536585365855e-05,
      "loss": 1.1351,
      "step": 925
    },
    {
      "epoch": 4.4392523364485985,
      "grad_norm": 227418.765625,
      "learning_rate": 7.25609756097561e-05,
      "loss": 1.1155,
      "step": 950
    },
    {
      "epoch": 4.55607476635514,
      "grad_norm": 145508.546875,
      "learning_rate": 7.103658536585366e-05,
      "loss": 1.121,
      "step": 975
    },
    {
      "epoch": 4.672897196261682,
      "grad_norm": 148252.265625,
      "learning_rate": 6.951219512195122e-05,
      "loss": 1.0959,
      "step": 1000
    },
    {
      "epoch": 4.789719626168225,
      "grad_norm": 191745.4375,
      "learning_rate": 6.798780487804878e-05,
      "loss": 1.1182,
      "step": 1025
    },
    {
      "epoch": 4.906542056074766,
      "grad_norm": 164514.484375,
      "learning_rate": 6.646341463414634e-05,
      "loss": 1.1322,
      "step": 1050
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.693200663349917,
      "eval_loss": 0.9698711037635803,
      "eval_runtime": 15.748,
      "eval_samples_per_second": 76.581,
      "eval_steps_per_second": 2.413,
      "step": 1070
    },
    {
      "epoch": 5.0233644859813085,
      "grad_norm": 210620.15625,
      "learning_rate": 6.49390243902439e-05,
      "loss": 1.1317,
      "step": 1075
    },
    {
      "epoch": 5.140186915887851,
      "grad_norm": 192808.234375,
      "learning_rate": 6.341463414634146e-05,
      "loss": 1.0846,
      "step": 1100
    },
    {
      "epoch": 5.257009345794392,
      "grad_norm": 239944.546875,
      "learning_rate": 6.189024390243902e-05,
      "loss": 1.0816,
      "step": 1125
    },
    {
      "epoch": 5.373831775700935,
      "grad_norm": 150305.15625,
      "learning_rate": 6.036585365853659e-05,
      "loss": 1.0886,
      "step": 1150
    },
    {
      "epoch": 5.490654205607477,
      "grad_norm": 221186.4375,
      "learning_rate": 5.884146341463415e-05,
      "loss": 1.0788,
      "step": 1175
    },
    {
      "epoch": 5.607476635514018,
      "grad_norm": 163830.375,
      "learning_rate": 5.731707317073171e-05,
      "loss": 1.1041,
      "step": 1200
    },
    {
      "epoch": 5.724299065420561,
      "grad_norm": 155212.859375,
      "learning_rate": 5.5792682926829274e-05,
      "loss": 1.1092,
      "step": 1225
    },
    {
      "epoch": 5.841121495327103,
      "grad_norm": 161311.390625,
      "learning_rate": 5.4268292682926834e-05,
      "loss": 1.0742,
      "step": 1250
    },
    {
      "epoch": 5.957943925233645,
      "grad_norm": 125866.4296875,
      "learning_rate": 5.2743902439024394e-05,
      "loss": 1.0696,
      "step": 1275
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7039800995024875,
      "eval_loss": 0.9538396000862122,
      "eval_runtime": 15.035,
      "eval_samples_per_second": 80.213,
      "eval_steps_per_second": 2.527,
      "step": 1284
    },
    {
      "epoch": 6.074766355140187,
      "grad_norm": 206136.15625,
      "learning_rate": 5.121951219512195e-05,
      "loss": 1.054,
      "step": 1300
    },
    {
      "epoch": 6.191588785046729,
      "grad_norm": 201560.484375,
      "learning_rate": 4.969512195121951e-05,
      "loss": 1.0383,
      "step": 1325
    },
    {
      "epoch": 6.308411214953271,
      "grad_norm": 151493.71875,
      "learning_rate": 4.817073170731707e-05,
      "loss": 1.059,
      "step": 1350
    },
    {
      "epoch": 6.425233644859813,
      "grad_norm": 221694.390625,
      "learning_rate": 4.664634146341464e-05,
      "loss": 1.005,
      "step": 1375
    },
    {
      "epoch": 6.542056074766355,
      "grad_norm": 171523.03125,
      "learning_rate": 4.51219512195122e-05,
      "loss": 1.0513,
      "step": 1400
    },
    {
      "epoch": 6.658878504672897,
      "grad_norm": 194379.046875,
      "learning_rate": 4.359756097560976e-05,
      "loss": 1.0218,
      "step": 1425
    },
    {
      "epoch": 6.775700934579439,
      "grad_norm": 157827.703125,
      "learning_rate": 4.207317073170732e-05,
      "loss": 1.0534,
      "step": 1450
    },
    {
      "epoch": 6.892523364485982,
      "grad_norm": 189870.078125,
      "learning_rate": 4.0548780487804884e-05,
      "loss": 1.0189,
      "step": 1475
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7172470978441128,
      "eval_loss": 0.9233611226081848,
      "eval_runtime": 14.8072,
      "eval_samples_per_second": 81.447,
      "eval_steps_per_second": 2.566,
      "step": 1498
    },
    {
      "epoch": 7.009345794392523,
      "grad_norm": 170561.5625,
      "learning_rate": 3.9024390243902444e-05,
      "loss": 1.0216,
      "step": 1500
    },
    {
      "epoch": 7.126168224299065,
      "grad_norm": 199614.921875,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.9941,
      "step": 1525
    },
    {
      "epoch": 7.242990654205608,
      "grad_norm": 168135.65625,
      "learning_rate": 3.597560975609756e-05,
      "loss": 1.0454,
      "step": 1550
    },
    {
      "epoch": 7.359813084112149,
      "grad_norm": 185285.3125,
      "learning_rate": 3.445121951219512e-05,
      "loss": 0.9979,
      "step": 1575
    },
    {
      "epoch": 7.4766355140186915,
      "grad_norm": 165282.078125,
      "learning_rate": 3.292682926829269e-05,
      "loss": 0.9869,
      "step": 1600
    },
    {
      "epoch": 7.593457943925234,
      "grad_norm": 169526.53125,
      "learning_rate": 3.140243902439025e-05,
      "loss": 1.0213,
      "step": 1625
    },
    {
      "epoch": 7.710280373831775,
      "grad_norm": 149986.765625,
      "learning_rate": 2.9878048780487805e-05,
      "loss": 1.02,
      "step": 1650
    },
    {
      "epoch": 7.827102803738318,
      "grad_norm": 248981.28125,
      "learning_rate": 2.8353658536585365e-05,
      "loss": 0.9901,
      "step": 1675
    },
    {
      "epoch": 7.94392523364486,
      "grad_norm": 132692.34375,
      "learning_rate": 2.682926829268293e-05,
      "loss": 0.9874,
      "step": 1700
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.74212271973466,
      "eval_loss": 0.9064252972602844,
      "eval_runtime": 14.7597,
      "eval_samples_per_second": 81.709,
      "eval_steps_per_second": 2.575,
      "step": 1712
    },
    {
      "epoch": 8.060747663551401,
      "grad_norm": 256718.34375,
      "learning_rate": 2.530487804878049e-05,
      "loss": 0.9658,
      "step": 1725
    },
    {
      "epoch": 8.177570093457945,
      "grad_norm": 187598.078125,
      "learning_rate": 2.378048780487805e-05,
      "loss": 0.9418,
      "step": 1750
    },
    {
      "epoch": 8.294392523364486,
      "grad_norm": 274552.46875,
      "learning_rate": 2.225609756097561e-05,
      "loss": 0.9644,
      "step": 1775
    },
    {
      "epoch": 8.411214953271028,
      "grad_norm": 212352.921875,
      "learning_rate": 2.073170731707317e-05,
      "loss": 0.946,
      "step": 1800
    },
    {
      "epoch": 8.52803738317757,
      "grad_norm": 171896.203125,
      "learning_rate": 1.9207317073170733e-05,
      "loss": 0.9599,
      "step": 1825
    },
    {
      "epoch": 8.644859813084112,
      "grad_norm": 168001.296875,
      "learning_rate": 1.7682926829268292e-05,
      "loss": 0.9624,
      "step": 1850
    },
    {
      "epoch": 8.761682242990654,
      "grad_norm": 150168.40625,
      "learning_rate": 1.6158536585365855e-05,
      "loss": 0.9326,
      "step": 1875
    },
    {
      "epoch": 8.878504672897197,
      "grad_norm": 228498.40625,
      "learning_rate": 1.4634146341463415e-05,
      "loss": 0.9507,
      "step": 1900
    },
    {
      "epoch": 8.995327102803738,
      "grad_norm": 153940.3125,
      "learning_rate": 1.3109756097560976e-05,
      "loss": 0.9228,
      "step": 1925
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.7562189054726368,
      "eval_loss": 0.8793113231658936,
      "eval_runtime": 14.9438,
      "eval_samples_per_second": 80.702,
      "eval_steps_per_second": 2.543,
      "step": 1926
    },
    {
      "epoch": 9.11214953271028,
      "grad_norm": 203478.21875,
      "learning_rate": 1.1585365853658537e-05,
      "loss": 0.8734,
      "step": 1950
    },
    {
      "epoch": 9.228971962616823,
      "grad_norm": 196428.75,
      "learning_rate": 1.0060975609756099e-05,
      "loss": 0.939,
      "step": 1975
    },
    {
      "epoch": 9.345794392523365,
      "grad_norm": 162436.5,
      "learning_rate": 8.53658536585366e-06,
      "loss": 0.9088,
      "step": 2000
    },
    {
      "epoch": 9.462616822429906,
      "grad_norm": 194883.640625,
      "learning_rate": 7.0121951219512205e-06,
      "loss": 0.8676,
      "step": 2025
    },
    {
      "epoch": 9.57943925233645,
      "grad_norm": 221290.5,
      "learning_rate": 5.487804878048781e-06,
      "loss": 0.9405,
      "step": 2050
    },
    {
      "epoch": 9.69626168224299,
      "grad_norm": 246742.265625,
      "learning_rate": 3.9634146341463414e-06,
      "loss": 0.9241,
      "step": 2075
    },
    {
      "epoch": 9.813084112149532,
      "grad_norm": 194605.296875,
      "learning_rate": 2.4390243902439027e-06,
      "loss": 0.9265,
      "step": 2100
    },
    {
      "epoch": 9.929906542056075,
      "grad_norm": 242350.640625,
      "learning_rate": 9.146341463414634e-07,
      "loss": 0.9201,
      "step": 2125
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.763681592039801,
      "eval_loss": 0.87679523229599,
      "eval_runtime": 15.2158,
      "eval_samples_per_second": 79.26,
      "eval_steps_per_second": 2.497,
      "step": 2140
    },
    {
      "epoch": 10.0,
      "step": 2140,
      "total_flos": 5.510586115727032e+19,
      "train_loss": 1.1243137065495286,
      "train_runtime": 1922.3745,
      "train_samples_per_second": 35.529,
      "train_steps_per_second": 1.113
    }
  ],
  "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
}