{
  "best_metric": 0.9979173897952099,
  "best_model_checkpoint": "vit-base-aihub_model/checkpoint-505",
  "epoch": 4.975369458128079,
  "global_step": 505,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 9.803921568627451e-06,
      "loss": 0.01,
      "step": 10
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9607843137254903e-05,
      "loss": 0.0086,
      "step": 20
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 0.0052,
      "step": 30
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.9215686274509805e-05,
      "loss": 0.0047,
      "step": 40
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.901960784313725e-05,
      "loss": 0.0057,
      "step": 50
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.900881057268723e-05,
      "loss": 0.0097,
      "step": 60
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.790748898678414e-05,
      "loss": 0.0138,
      "step": 70
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.680616740088106e-05,
      "loss": 0.0115,
      "step": 80
    },
    {
      "epoch": 0.89,
      "learning_rate": 4.5704845814977974e-05,
      "loss": 0.017,
      "step": 90
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.46035242290749e-05,
      "loss": 0.015,
      "step": 100
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9937521693856299,
      "eval_f1": 0.992844052055387,
      "eval_loss": 0.022941650822758675,
      "eval_precision": 0.9928152895572064,
      "eval_recall": 0.9929099097030748,
      "eval_runtime": 76.6131,
      "eval_samples_per_second": 75.209,
      "eval_steps_per_second": 0.6,
      "step": 101
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.3502202643171806e-05,
      "loss": 0.0212,
      "step": 110
    },
    {
      "epoch": 1.18,
      "learning_rate": 4.240088105726873e-05,
      "loss": 0.0209,
      "step": 120
    },
    {
      "epoch": 1.28,
      "learning_rate": 4.129955947136564e-05,
      "loss": 0.034,
      "step": 130
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.019823788546256e-05,
      "loss": 0.0176,
      "step": 140
    },
    {
      "epoch": 1.48,
      "learning_rate": 3.909691629955947e-05,
      "loss": 0.0149,
      "step": 150
    },
    {
      "epoch": 1.58,
      "learning_rate": 3.799559471365639e-05,
      "loss": 0.0108,
      "step": 160
    },
    {
      "epoch": 1.67,
      "learning_rate": 3.689427312775331e-05,
      "loss": 0.0124,
      "step": 170
    },
    {
      "epoch": 1.77,
      "learning_rate": 3.579295154185022e-05,
      "loss": 0.0077,
      "step": 180
    },
    {
      "epoch": 1.87,
      "learning_rate": 3.469162995594714e-05,
      "loss": 0.014,
      "step": 190
    },
    {
      "epoch": 1.97,
      "learning_rate": 3.3590308370044054e-05,
      "loss": 0.0177,
      "step": 200
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9913224574800417,
      "eval_f1": 0.9903379714818227,
      "eval_loss": 0.03158613294363022,
      "eval_precision": 0.9927986181574738,
      "eval_recall": 0.9880460334448341,
      "eval_runtime": 75.7784,
      "eval_samples_per_second": 76.037,
      "eval_steps_per_second": 0.607,
      "step": 203
    },
    {
      "epoch": 2.07,
      "learning_rate": 3.2488986784140976e-05,
      "loss": 0.0164,
      "step": 210
    },
    {
      "epoch": 2.17,
      "learning_rate": 3.1387665198237885e-05,
      "loss": 0.0172,
      "step": 220
    },
    {
      "epoch": 2.27,
      "learning_rate": 3.0286343612334804e-05,
      "loss": 0.0185,
      "step": 230
    },
    {
      "epoch": 2.36,
      "learning_rate": 2.918502202643172e-05,
      "loss": 0.0197,
      "step": 240
    },
    {
      "epoch": 2.46,
      "learning_rate": 2.8083700440528636e-05,
      "loss": 0.0238,
      "step": 250
    },
    {
      "epoch": 2.56,
      "learning_rate": 2.698237885462555e-05,
      "loss": 0.0175,
      "step": 260
    },
    {
      "epoch": 2.66,
      "learning_rate": 2.588105726872247e-05,
      "loss": 0.0146,
      "step": 270
    },
    {
      "epoch": 2.76,
      "learning_rate": 2.4779735682819386e-05,
      "loss": 0.0206,
      "step": 280
    },
    {
      "epoch": 2.86,
      "learning_rate": 2.3678414096916302e-05,
      "loss": 0.0154,
      "step": 290
    },
    {
      "epoch": 2.96,
      "learning_rate": 2.2577092511013218e-05,
      "loss": 0.0177,
      "step": 300
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.99583477959042,
      "eval_f1": 0.9954331496170975,
      "eval_loss": 0.012670599855482578,
      "eval_precision": 0.9953560460932506,
      "eval_recall": 0.9955319756621362,
      "eval_runtime": 78.0072,
      "eval_samples_per_second": 73.865,
      "eval_steps_per_second": 0.59,
      "step": 304
    },
    {
      "epoch": 3.05,
      "learning_rate": 2.1475770925110134e-05,
      "loss": 0.0163,
      "step": 310
    },
    {
      "epoch": 3.15,
      "learning_rate": 2.037444933920705e-05,
      "loss": 0.0165,
      "step": 320
    },
    {
      "epoch": 3.25,
      "learning_rate": 1.9273127753303965e-05,
      "loss": 0.0153,
      "step": 330
    },
    {
      "epoch": 3.35,
      "learning_rate": 1.817180616740088e-05,
      "loss": 0.0132,
      "step": 340
    },
    {
      "epoch": 3.45,
      "learning_rate": 1.7070484581497796e-05,
      "loss": 0.0191,
      "step": 350
    },
    {
      "epoch": 3.55,
      "learning_rate": 1.5969162995594712e-05,
      "loss": 0.0166,
      "step": 360
    },
    {
      "epoch": 3.65,
      "learning_rate": 1.486784140969163e-05,
      "loss": 0.0215,
      "step": 370
    },
    {
      "epoch": 3.74,
      "learning_rate": 1.3766519823788545e-05,
      "loss": 0.0203,
      "step": 380
    },
    {
      "epoch": 3.84,
      "learning_rate": 1.2665198237885464e-05,
      "loss": 0.014,
      "step": 390
    },
    {
      "epoch": 3.94,
      "learning_rate": 1.1563876651982378e-05,
      "loss": 0.0145,
      "step": 400
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9967025338424158,
      "eval_f1": 0.996523677440153,
      "eval_loss": 0.012865510769188404,
      "eval_precision": 0.9970401517231021,
      "eval_recall": 0.9960174161283625,
      "eval_runtime": 77.6129,
      "eval_samples_per_second": 74.24,
      "eval_steps_per_second": 0.593,
      "step": 406
    },
    {
      "epoch": 4.04,
      "learning_rate": 1.0462555066079296e-05,
      "loss": 0.0143,
      "step": 410
    },
    {
      "epoch": 4.14,
      "learning_rate": 9.361233480176213e-06,
      "loss": 0.011,
      "step": 420
    },
    {
      "epoch": 4.24,
      "learning_rate": 8.259911894273129e-06,
      "loss": 0.012,
      "step": 430
    },
    {
      "epoch": 4.33,
      "learning_rate": 7.1585903083700445e-06,
      "loss": 0.013,
      "step": 440
    },
    {
      "epoch": 4.43,
      "learning_rate": 6.05726872246696e-06,
      "loss": 0.0113,
      "step": 450
    },
    {
      "epoch": 4.53,
      "learning_rate": 4.955947136563877e-06,
      "loss": 0.0092,
      "step": 460
    },
    {
      "epoch": 4.63,
      "learning_rate": 3.854625550660793e-06,
      "loss": 0.0144,
      "step": 470
    },
    {
      "epoch": 4.73,
      "learning_rate": 2.7533039647577095e-06,
      "loss": 0.0126,
      "step": 480
    },
    {
      "epoch": 4.83,
      "learning_rate": 1.6519823788546256e-06,
      "loss": 0.0096,
      "step": 490
    },
    {
      "epoch": 4.93,
      "learning_rate": 5.506607929515419e-07,
      "loss": 0.0101,
      "step": 500
    },
    {
      "epoch": 4.98,
      "eval_accuracy": 0.9979173897952099,
      "eval_f1": 0.9978801278905362,
      "eval_loss": 0.007995981723070145,
      "eval_precision": 0.9981546674586633,
      "eval_recall": 0.9976078463525905,
      "eval_runtime": 74.8289,
      "eval_samples_per_second": 77.002,
      "eval_steps_per_second": 0.615,
      "step": 505
    },
    {
      "epoch": 4.98,
      "step": 505,
      "total_flos": 2.0000469621477704e+19,
      "train_loss": 0.014720117418777824,
      "train_runtime": 3834.7537,
      "train_samples_per_second": 67.605,
      "train_steps_per_second": 0.132
    }
  ],
  "max_steps": 505,
  "num_train_epochs": 5,
  "total_flos": 2.0000469621477704e+19,
  "trial_name": null,
  "trial_params": null
}