{
  "best_metric": 1.3534746170043945,
  "best_model_checkpoint": "/media/mldrive/kcardenas/limb_classification_person_crop/beit-large-patch16-384/8_5e-5_1e-3_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": 1226482.25,
      "learning_rate": 2.5e-06,
      "loss": 1.5898,
      "step": 25
    },
    {
      "epoch": 0.2336448598130841,
      "grad_norm": 883115.375,
      "learning_rate": 5e-06,
      "loss": 1.5063,
      "step": 50
    },
    {
      "epoch": 0.35046728971962615,
      "grad_norm": 729111.75,
      "learning_rate": 7.5e-06,
      "loss": 1.4618,
      "step": 75
    },
    {
      "epoch": 0.4672897196261682,
      "grad_norm": 401205.5,
      "learning_rate": 1e-05,
      "loss": 1.4029,
      "step": 100
    },
    {
      "epoch": 0.5841121495327103,
      "grad_norm": 392407.21875,
      "learning_rate": 1.25e-05,
      "loss": 1.3853,
      "step": 125
    },
    {
      "epoch": 0.7009345794392523,
      "grad_norm": 296861.40625,
      "learning_rate": 1.5e-05,
      "loss": 1.3715,
      "step": 150
    },
    {
      "epoch": 0.8177570093457944,
      "grad_norm": 644126.5,
      "learning_rate": 1.75e-05,
      "loss": 1.344,
      "step": 175
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": 561771.25,
      "learning_rate": 2e-05,
      "loss": 1.3404,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.39800995024875624,
      "eval_loss": 1.4185985326766968,
      "eval_runtime": 15.0137,
      "eval_samples_per_second": 80.326,
      "eval_steps_per_second": 2.531,
      "step": 214
    },
    {
      "epoch": 1.0514018691588785,
      "grad_norm": 450167.59375,
      "learning_rate": 2.25e-05,
      "loss": 1.2961,
      "step": 225
    },
    {
      "epoch": 1.1682242990654206,
      "grad_norm": 275605.5625,
      "learning_rate": 2.5e-05,
      "loss": 1.2836,
      "step": 250
    },
    {
      "epoch": 1.2850467289719627,
      "grad_norm": 417004.96875,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 1.2374,
      "step": 275
    },
    {
      "epoch": 1.4018691588785046,
      "grad_norm": 313505.09375,
      "learning_rate": 3e-05,
      "loss": 1.2688,
      "step": 300
    },
    {
      "epoch": 1.5186915887850467,
      "grad_norm": 345997.34375,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 1.2501,
      "step": 325
    },
    {
      "epoch": 1.6355140186915889,
      "grad_norm": 95028.7734375,
      "learning_rate": 3.5e-05,
      "loss": 1.33,
      "step": 350
    },
    {
      "epoch": 1.7523364485981308,
      "grad_norm": 115577.6171875,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.3968,
      "step": 375
    },
    {
      "epoch": 1.8691588785046729,
      "grad_norm": 259988.078125,
      "learning_rate": 4e-05,
      "loss": 1.3944,
      "step": 400
    },
    {
      "epoch": 1.985981308411215,
      "grad_norm": 61302.6796875,
      "learning_rate": 4.25e-05,
      "loss": 1.3839,
      "step": 425
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2703150912106136,
      "eval_loss": 1.3841294050216675,
      "eval_runtime": 14.7215,
      "eval_samples_per_second": 81.921,
      "eval_steps_per_second": 2.581,
      "step": 428
    },
    {
      "epoch": 2.102803738317757,
      "grad_norm": 278573.625,
      "learning_rate": 4.5e-05,
      "loss": 1.3805,
      "step": 450
    },
    {
      "epoch": 2.2196261682242993,
      "grad_norm": 224828.75,
      "learning_rate": 4.75e-05,
      "loss": 1.3793,
      "step": 475
    },
    {
      "epoch": 2.336448598130841,
      "grad_norm": 104505.984375,
      "learning_rate": 5e-05,
      "loss": 1.391,
      "step": 500
    },
    {
      "epoch": 2.453271028037383,
      "grad_norm": 198013.84375,
      "learning_rate": 4.923780487804878e-05,
      "loss": 1.3894,
      "step": 525
    },
    {
      "epoch": 2.5700934579439254,
      "grad_norm": 148076.09375,
      "learning_rate": 4.847560975609756e-05,
      "loss": 1.3911,
      "step": 550
    },
    {
      "epoch": 2.6869158878504673,
      "grad_norm": 113111.859375,
      "learning_rate": 4.771341463414634e-05,
      "loss": 1.3855,
      "step": 575
    },
    {
      "epoch": 2.803738317757009,
      "grad_norm": 224499.625,
      "learning_rate": 4.695121951219512e-05,
      "loss": 1.3932,
      "step": 600
    },
    {
      "epoch": 2.9205607476635516,
      "grad_norm": 271534.34375,
      "learning_rate": 4.618902439024391e-05,
      "loss": 1.3931,
      "step": 625
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2744610281923715,
      "eval_loss": 1.386692762374878,
      "eval_runtime": 15.8236,
      "eval_samples_per_second": 76.215,
      "eval_steps_per_second": 2.401,
      "step": 642
    },
    {
      "epoch": 3.0373831775700935,
      "grad_norm": 219634.640625,
      "learning_rate": 4.542682926829269e-05,
      "loss": 1.3891,
      "step": 650
    },
    {
      "epoch": 3.1542056074766354,
      "grad_norm": 111519.75,
      "learning_rate": 4.466463414634147e-05,
      "loss": 1.392,
      "step": 675
    },
    {
      "epoch": 3.2710280373831777,
      "grad_norm": 172780.359375,
      "learning_rate": 4.390243902439025e-05,
      "loss": 1.3815,
      "step": 700
    },
    {
      "epoch": 3.3878504672897196,
      "grad_norm": 132606.328125,
      "learning_rate": 4.314024390243903e-05,
      "loss": 1.3917,
      "step": 725
    },
    {
      "epoch": 3.5046728971962615,
      "grad_norm": 99811.65625,
      "learning_rate": 4.237804878048781e-05,
      "loss": 1.3847,
      "step": 750
    },
    {
      "epoch": 3.621495327102804,
      "grad_norm": 143071.3125,
      "learning_rate": 4.161585365853659e-05,
      "loss": 1.3851,
      "step": 775
    },
    {
      "epoch": 3.7383177570093458,
      "grad_norm": 184519.203125,
      "learning_rate": 4.085365853658537e-05,
      "loss": 1.3833,
      "step": 800
    },
    {
      "epoch": 3.8551401869158877,
      "grad_norm": 125933.3671875,
      "learning_rate": 4.0091463414634153e-05,
      "loss": 1.3809,
      "step": 825
    },
    {
      "epoch": 3.97196261682243,
      "grad_norm": 208119.21875,
      "learning_rate": 3.932926829268293e-05,
      "loss": 1.3889,
      "step": 850
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.2744610281923715,
      "eval_loss": 1.3884413242340088,
      "eval_runtime": 14.7098,
      "eval_samples_per_second": 81.986,
      "eval_steps_per_second": 2.583,
      "step": 856
    },
    {
      "epoch": 4.088785046728972,
      "grad_norm": 59083.99609375,
      "learning_rate": 3.856707317073171e-05,
      "loss": 1.3896,
      "step": 875
    },
    {
      "epoch": 4.205607476635514,
      "grad_norm": 232480.921875,
      "learning_rate": 3.780487804878049e-05,
      "loss": 1.3892,
      "step": 900
    },
    {
      "epoch": 4.322429906542056,
      "grad_norm": 259920.0,
      "learning_rate": 3.704268292682927e-05,
      "loss": 1.3894,
      "step": 925
    },
    {
      "epoch": 4.4392523364485985,
      "grad_norm": 141156.375,
      "learning_rate": 3.628048780487805e-05,
      "loss": 1.3894,
      "step": 950
    },
    {
      "epoch": 4.55607476635514,
      "grad_norm": 160513.3125,
      "learning_rate": 3.551829268292683e-05,
      "loss": 1.3835,
      "step": 975
    },
    {
      "epoch": 4.672897196261682,
      "grad_norm": 165691.796875,
      "learning_rate": 3.475609756097561e-05,
      "loss": 1.3853,
      "step": 1000
    },
    {
      "epoch": 4.789719626168225,
      "grad_norm": 148144.03125,
      "learning_rate": 3.399390243902439e-05,
      "loss": 1.3829,
      "step": 1025
    },
    {
      "epoch": 4.906542056074766,
      "grad_norm": 192222.125,
      "learning_rate": 3.323170731707317e-05,
      "loss": 1.3864,
      "step": 1050
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.27611940298507465,
      "eval_loss": 1.384167194366455,
      "eval_runtime": 14.7587,
      "eval_samples_per_second": 81.715,
      "eval_steps_per_second": 2.575,
      "step": 1070
    },
    {
      "epoch": 5.0233644859813085,
      "grad_norm": 248749.515625,
      "learning_rate": 3.246951219512195e-05,
      "loss": 1.3877,
      "step": 1075
    },
    {
      "epoch": 5.140186915887851,
      "grad_norm": 126036.1015625,
      "learning_rate": 3.170731707317073e-05,
      "loss": 1.3842,
      "step": 1100
    },
    {
      "epoch": 5.257009345794392,
      "grad_norm": 133823.828125,
      "learning_rate": 3.094512195121951e-05,
      "loss": 1.3842,
      "step": 1125
    },
    {
      "epoch": 5.373831775700935,
      "grad_norm": 150464.3125,
      "learning_rate": 3.0182926829268294e-05,
      "loss": 1.3873,
      "step": 1150
    },
    {
      "epoch": 5.490654205607477,
      "grad_norm": 198916.296875,
      "learning_rate": 2.9420731707317074e-05,
      "loss": 1.3853,
      "step": 1175
    },
    {
      "epoch": 5.607476635514018,
      "grad_norm": 128553.09375,
      "learning_rate": 2.8658536585365854e-05,
      "loss": 1.3773,
      "step": 1200
    },
    {
      "epoch": 5.724299065420561,
      "grad_norm": 121626.6171875,
      "learning_rate": 2.7896341463414637e-05,
      "loss": 1.3763,
      "step": 1225
    },
    {
      "epoch": 5.841121495327103,
      "grad_norm": 126122.3828125,
      "learning_rate": 2.7134146341463417e-05,
      "loss": 1.3797,
      "step": 1250
    },
    {
      "epoch": 5.957943925233645,
      "grad_norm": 167410.4375,
      "learning_rate": 2.6371951219512197e-05,
      "loss": 1.3892,
      "step": 1275
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.2877280265339967,
      "eval_loss": 1.3801555633544922,
      "eval_runtime": 14.9729,
      "eval_samples_per_second": 80.545,
      "eval_steps_per_second": 2.538,
      "step": 1284
    },
    {
      "epoch": 6.074766355140187,
      "grad_norm": 204724.40625,
      "learning_rate": 2.5609756097560977e-05,
      "loss": 1.3823,
      "step": 1300
    },
    {
      "epoch": 6.191588785046729,
      "grad_norm": 119223.4296875,
      "learning_rate": 2.4847560975609756e-05,
      "loss": 1.371,
      "step": 1325
    },
    {
      "epoch": 6.308411214953271,
      "grad_norm": 141183.390625,
      "learning_rate": 2.4085365853658536e-05,
      "loss": 1.3678,
      "step": 1350
    },
    {
      "epoch": 6.425233644859813,
      "grad_norm": 126927.609375,
      "learning_rate": 2.332317073170732e-05,
      "loss": 1.3762,
      "step": 1375
    },
    {
      "epoch": 6.542056074766355,
      "grad_norm": 60989.0625,
      "learning_rate": 2.25609756097561e-05,
      "loss": 1.3783,
      "step": 1400
    },
    {
      "epoch": 6.658878504672897,
      "grad_norm": 99197.3203125,
      "learning_rate": 2.179878048780488e-05,
      "loss": 1.3652,
      "step": 1425
    },
    {
      "epoch": 6.775700934579439,
      "grad_norm": 94052.6015625,
      "learning_rate": 2.103658536585366e-05,
      "loss": 1.3785,
      "step": 1450
    },
    {
      "epoch": 6.892523364485982,
      "grad_norm": 114499.0703125,
      "learning_rate": 2.0274390243902442e-05,
      "loss": 1.369,
      "step": 1475
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3142620232172471,
      "eval_loss": 1.3726152181625366,
      "eval_runtime": 14.9337,
      "eval_samples_per_second": 80.757,
      "eval_steps_per_second": 2.545,
      "step": 1498
    },
    {
      "epoch": 7.009345794392523,
      "grad_norm": 197232.515625,
      "learning_rate": 1.9512195121951222e-05,
      "loss": 1.3783,
      "step": 1500
    },
    {
      "epoch": 7.126168224299065,
      "grad_norm": 143105.90625,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 1.3774,
      "step": 1525
    },
    {
      "epoch": 7.242990654205608,
      "grad_norm": 89834.8125,
      "learning_rate": 1.798780487804878e-05,
      "loss": 1.3641,
      "step": 1550
    },
    {
      "epoch": 7.359813084112149,
      "grad_norm": 140115.375,
      "learning_rate": 1.722560975609756e-05,
      "loss": 1.3509,
      "step": 1575
    },
    {
      "epoch": 7.4766355140186915,
      "grad_norm": 159272.546875,
      "learning_rate": 1.6463414634146345e-05,
      "loss": 1.3614,
      "step": 1600
    },
    {
      "epoch": 7.593457943925234,
      "grad_norm": 77884.375,
      "learning_rate": 1.5701219512195124e-05,
      "loss": 1.3649,
      "step": 1625
    },
    {
      "epoch": 7.710280373831775,
      "grad_norm": 124513.578125,
      "learning_rate": 1.4939024390243902e-05,
      "loss": 1.3747,
      "step": 1650
    },
    {
      "epoch": 7.827102803738318,
      "grad_norm": 152671.921875,
      "learning_rate": 1.4176829268292682e-05,
      "loss": 1.3626,
      "step": 1675
    },
    {
      "epoch": 7.94392523364486,
      "grad_norm": 127847.6640625,
      "learning_rate": 1.3414634146341466e-05,
      "loss": 1.3545,
      "step": 1700
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.3275290215588723,
      "eval_loss": 1.3627326488494873,
      "eval_runtime": 15.0566,
      "eval_samples_per_second": 80.098,
      "eval_steps_per_second": 2.524,
      "step": 1712
    },
    {
      "epoch": 8.060747663551401,
      "grad_norm": 178315.984375,
      "learning_rate": 1.2652439024390245e-05,
      "loss": 1.3554,
      "step": 1725
    },
    {
      "epoch": 8.177570093457945,
      "grad_norm": 133679.765625,
      "learning_rate": 1.1890243902439025e-05,
      "loss": 1.364,
      "step": 1750
    },
    {
      "epoch": 8.294392523364486,
      "grad_norm": 107949.953125,
      "learning_rate": 1.1128048780487805e-05,
      "loss": 1.3625,
      "step": 1775
    },
    {
      "epoch": 8.411214953271028,
      "grad_norm": 88464.8046875,
      "learning_rate": 1.0365853658536585e-05,
      "loss": 1.3447,
      "step": 1800
    },
    {
      "epoch": 8.52803738317757,
      "grad_norm": 87399.6171875,
      "learning_rate": 9.603658536585366e-06,
      "loss": 1.3497,
      "step": 1825
    },
    {
      "epoch": 8.644859813084112,
      "grad_norm": 99827.875,
      "learning_rate": 8.841463414634146e-06,
      "loss": 1.3633,
      "step": 1850
    },
    {
      "epoch": 8.761682242990654,
      "grad_norm": 136905.25,
      "learning_rate": 8.079268292682928e-06,
      "loss": 1.3559,
      "step": 1875
    },
    {
      "epoch": 8.878504672897197,
      "grad_norm": 92091.828125,
      "learning_rate": 7.317073170731707e-06,
      "loss": 1.3568,
      "step": 1900
    },
    {
      "epoch": 8.995327102803738,
      "grad_norm": 122825.078125,
      "learning_rate": 6.554878048780488e-06,
      "loss": 1.3626,
      "step": 1925
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.33913764510779437,
      "eval_loss": 1.3594319820404053,
      "eval_runtime": 15.4853,
      "eval_samples_per_second": 77.881,
      "eval_steps_per_second": 2.454,
      "step": 1926
    },
    {
      "epoch": 9.11214953271028,
      "grad_norm": 186335.28125,
      "learning_rate": 5.792682926829269e-06,
      "loss": 1.351,
      "step": 1950
    },
    {
      "epoch": 9.228971962616823,
      "grad_norm": 269060.90625,
      "learning_rate": 5.030487804878049e-06,
      "loss": 1.3576,
      "step": 1975
    },
    {
      "epoch": 9.345794392523365,
      "grad_norm": 141771.921875,
      "learning_rate": 4.26829268292683e-06,
      "loss": 1.3473,
      "step": 2000
    },
    {
      "epoch": 9.462616822429906,
      "grad_norm": 164899.0625,
      "learning_rate": 3.5060975609756102e-06,
      "loss": 1.3503,
      "step": 2025
    },
    {
      "epoch": 9.57943925233645,
      "grad_norm": 198283.234375,
      "learning_rate": 2.7439024390243905e-06,
      "loss": 1.3505,
      "step": 2050
    },
    {
      "epoch": 9.69626168224299,
      "grad_norm": 83706.109375,
      "learning_rate": 1.9817073170731707e-06,
      "loss": 1.362,
      "step": 2075
    },
    {
      "epoch": 9.813084112149532,
      "grad_norm": 101845.78125,
      "learning_rate": 1.2195121951219514e-06,
      "loss": 1.3364,
      "step": 2100
    },
    {
      "epoch": 9.929906542056075,
      "grad_norm": 134814.96875,
      "learning_rate": 4.573170731707317e-07,
      "loss": 1.3464,
      "step": 2125
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.3482587064676617,
      "eval_loss": 1.3534746170043945,
      "eval_runtime": 15.5044,
      "eval_samples_per_second": 77.784,
      "eval_steps_per_second": 2.451,
      "step": 2140
    },
    {
      "epoch": 10.0,
      "step": 2140,
      "total_flos": 5.510586115727032e+19,
      "train_loss": 1.3723564032082245,
      "train_runtime": 1908.126,
      "train_samples_per_second": 35.794,
      "train_steps_per_second": 1.122
    }
  ],
  "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
}