{
  "best_metric": 0.6840345500139314,
  "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-FER2013-9e-05/checkpoint-672",
  "epoch": 2.997772828507795,
  "global_step": 672,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 1.323529411764706e-05,
      "loss": 1.9205,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.647058823529412e-05,
      "loss": 1.7213,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 3.970588235294118e-05,
      "loss": 1.5455,
      "step": 30
    },
    {
      "epoch": 0.18,
      "learning_rate": 5.294117647058824e-05,
      "loss": 1.4512,
      "step": 40
    },
    {
      "epoch": 0.22,
      "learning_rate": 6.61764705882353e-05,
      "loss": 1.4027,
      "step": 50
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.941176470588236e-05,
      "loss": 1.3752,
      "step": 60
    },
    {
      "epoch": 0.31,
      "learning_rate": 8.97019867549669e-05,
      "loss": 1.3787,
      "step": 70
    },
    {
      "epoch": 0.36,
      "learning_rate": 8.821192052980134e-05,
      "loss": 1.275,
      "step": 80
    },
    {
      "epoch": 0.4,
      "learning_rate": 8.672185430463577e-05,
      "loss": 1.3066,
      "step": 90
    },
    {
      "epoch": 0.45,
      "learning_rate": 8.52317880794702e-05,
      "loss": 1.3146,
      "step": 100
    },
    {
      "epoch": 0.49,
      "learning_rate": 8.374172185430464e-05,
      "loss": 1.2811,
      "step": 110
    },
    {
      "epoch": 0.53,
      "learning_rate": 8.225165562913908e-05,
      "loss": 1.2602,
      "step": 120
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.076158940397351e-05,
      "loss": 1.1923,
      "step": 130
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.927152317880794e-05,
      "loss": 1.2981,
      "step": 140
    },
    {
      "epoch": 0.67,
      "learning_rate": 7.778145695364238e-05,
      "loss": 1.2406,
      "step": 150
    },
    {
      "epoch": 0.71,
      "learning_rate": 7.629139072847683e-05,
      "loss": 1.3138,
      "step": 160
    },
    {
      "epoch": 0.76,
      "learning_rate": 7.480132450331127e-05,
      "loss": 1.2256,
      "step": 170
    },
    {
      "epoch": 0.8,
      "learning_rate": 7.33112582781457e-05,
      "loss": 1.1977,
      "step": 180
    },
    {
      "epoch": 0.85,
      "learning_rate": 7.182119205298013e-05,
      "loss": 1.2222,
      "step": 190
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.033112582781457e-05,
      "loss": 1.1974,
      "step": 200
    },
    {
      "epoch": 0.94,
      "learning_rate": 6.884105960264902e-05,
      "loss": 1.1744,
      "step": 210
    },
    {
      "epoch": 0.98,
      "learning_rate": 6.735099337748346e-05,
      "loss": 1.1839,
      "step": 220
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6120089161326274,
      "eval_loss": 1.026611089706421,
      "eval_runtime": 62.7487,
      "eval_samples_per_second": 114.393,
      "eval_steps_per_second": 3.586,
      "step": 224
    },
    {
      "epoch": 1.03,
      "learning_rate": 6.586092715231789e-05,
      "loss": 1.228,
      "step": 230
    },
    {
      "epoch": 1.07,
      "learning_rate": 6.437086092715232e-05,
      "loss": 1.1007,
      "step": 240
    },
    {
      "epoch": 1.12,
      "learning_rate": 6.288079470198676e-05,
      "loss": 1.1172,
      "step": 250
    },
    {
      "epoch": 1.16,
      "learning_rate": 6.13907284768212e-05,
      "loss": 1.1499,
      "step": 260
    },
    {
      "epoch": 1.2,
      "learning_rate": 5.9900662251655627e-05,
      "loss": 1.1565,
      "step": 270
    },
    {
      "epoch": 1.25,
      "learning_rate": 5.841059602649007e-05,
      "loss": 1.1459,
      "step": 280
    },
    {
      "epoch": 1.29,
      "learning_rate": 5.6920529801324506e-05,
      "loss": 1.1547,
      "step": 290
    },
    {
      "epoch": 1.34,
      "learning_rate": 5.543046357615895e-05,
      "loss": 1.0678,
      "step": 300
    },
    {
      "epoch": 1.38,
      "learning_rate": 5.394039735099338e-05,
      "loss": 1.13,
      "step": 310
    },
    {
      "epoch": 1.43,
      "learning_rate": 5.2450331125827815e-05,
      "loss": 1.1797,
      "step": 320
    },
    {
      "epoch": 1.47,
      "learning_rate": 5.096026490066226e-05,
      "loss": 1.0447,
      "step": 330
    },
    {
      "epoch": 1.52,
      "learning_rate": 4.9470198675496694e-05,
      "loss": 1.0492,
      "step": 340
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.7980132450331124e-05,
      "loss": 1.0945,
      "step": 350
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.6490066225165567e-05,
      "loss": 1.0536,
      "step": 360
    },
    {
      "epoch": 1.65,
      "learning_rate": 4.5e-05,
      "loss": 1.075,
      "step": 370
    },
    {
      "epoch": 1.69,
      "learning_rate": 4.350993377483444e-05,
      "loss": 1.148,
      "step": 380
    },
    {
      "epoch": 1.74,
      "learning_rate": 4.2019867549668875e-05,
      "loss": 1.1247,
      "step": 390
    },
    {
      "epoch": 1.78,
      "learning_rate": 4.052980132450332e-05,
      "loss": 1.0691,
      "step": 400
    },
    {
      "epoch": 1.83,
      "learning_rate": 3.903973509933775e-05,
      "loss": 1.051,
      "step": 410
    },
    {
      "epoch": 1.87,
      "learning_rate": 3.754966887417219e-05,
      "loss": 1.1058,
      "step": 420
    },
    {
      "epoch": 1.92,
      "learning_rate": 3.605960264900663e-05,
      "loss": 1.0431,
      "step": 430
    },
    {
      "epoch": 1.96,
      "learning_rate": 3.4569536423841064e-05,
      "loss": 1.0333,
      "step": 440
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6607690164391196,
      "eval_loss": 0.9063372015953064,
      "eval_runtime": 61.8075,
      "eval_samples_per_second": 116.135,
      "eval_steps_per_second": 3.64,
      "step": 448
    },
    {
      "epoch": 2.01,
      "learning_rate": 3.30794701986755e-05,
      "loss": 1.0725,
      "step": 450
    },
    {
      "epoch": 2.05,
      "learning_rate": 3.1589403973509936e-05,
      "loss": 0.9962,
      "step": 460
    },
    {
      "epoch": 2.1,
      "learning_rate": 3.0099337748344372e-05,
      "loss": 1.0569,
      "step": 470
    },
    {
      "epoch": 2.14,
      "learning_rate": 2.8609271523178812e-05,
      "loss": 0.9909,
      "step": 480
    },
    {
      "epoch": 2.19,
      "learning_rate": 2.7119205298013245e-05,
      "loss": 1.0458,
      "step": 490
    },
    {
      "epoch": 2.23,
      "learning_rate": 2.5629139072847685e-05,
      "loss": 1.0103,
      "step": 500
    },
    {
      "epoch": 2.28,
      "learning_rate": 2.4139072847682117e-05,
      "loss": 1.0123,
      "step": 510
    },
    {
      "epoch": 2.32,
      "learning_rate": 2.2649006622516557e-05,
      "loss": 1.005,
      "step": 520
    },
    {
      "epoch": 2.37,
      "learning_rate": 2.1158940397350997e-05,
      "loss": 1.0186,
      "step": 530
    },
    {
      "epoch": 2.41,
      "learning_rate": 1.9668874172185433e-05,
      "loss": 0.9912,
      "step": 540
    },
    {
      "epoch": 2.45,
      "learning_rate": 1.817880794701987e-05,
      "loss": 0.971,
      "step": 550
    },
    {
      "epoch": 2.5,
      "learning_rate": 1.6688741721854306e-05,
      "loss": 1.0455,
      "step": 560
    },
    {
      "epoch": 2.54,
      "learning_rate": 1.5198675496688744e-05,
      "loss": 0.9897,
      "step": 570
    },
    {
      "epoch": 2.59,
      "learning_rate": 1.370860927152318e-05,
      "loss": 1.0151,
      "step": 580
    },
    {
      "epoch": 2.63,
      "learning_rate": 1.2218543046357616e-05,
      "loss": 1.0069,
      "step": 590
    },
    {
      "epoch": 2.68,
      "learning_rate": 1.0728476821192054e-05,
      "loss": 1.0242,
      "step": 600
    },
    {
      "epoch": 2.72,
      "learning_rate": 9.23841059602649e-06,
      "loss": 1.0147,
      "step": 610
    },
    {
      "epoch": 2.77,
      "learning_rate": 7.748344370860927e-06,
      "loss": 0.9892,
      "step": 620
    },
    {
      "epoch": 2.81,
      "learning_rate": 6.258278145695364e-06,
      "loss": 0.9651,
      "step": 630
    },
    {
      "epoch": 2.86,
      "learning_rate": 4.768211920529802e-06,
      "loss": 0.9636,
      "step": 640
    },
    {
      "epoch": 2.9,
      "learning_rate": 3.2781456953642384e-06,
      "loss": 0.9405,
      "step": 650
    },
    {
      "epoch": 2.94,
      "learning_rate": 1.7880794701986758e-06,
      "loss": 1.0278,
      "step": 660
    },
    {
      "epoch": 2.99,
      "learning_rate": 2.980132450331126e-07,
      "loss": 0.9655,
      "step": 670
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6840345500139314,
      "eval_loss": 0.8481202721595764,
      "eval_runtime": 64.028,
      "eval_samples_per_second": 112.107,
      "eval_steps_per_second": 3.514,
      "step": 672
    },
    {
      "epoch": 3.0,
      "step": 672,
      "total_flos": 6.668732964123095e+18,
      "train_loss": 1.1477188680853163,
      "train_runtime": 2102.1014,
      "train_samples_per_second": 40.972,
      "train_steps_per_second": 0.32
    }
  ],
  "max_steps": 672,
  "num_train_epochs": 3,
  "total_flos": 6.668732964123095e+18,
  "trial_name": null,
  "trial_params": null
}