{
  "best_metric": 0.172527477145195,
  "best_model_checkpoint": "./vit-base-beans/checkpoint-400",
  "epoch": 4.0,
  "global_step": 444,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "learning_rate": 0.0001954954954954955,
      "loss": 1.552,
      "step": 10
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000190990990990991,
      "loss": 1.0968,
      "step": 20
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001864864864864865,
      "loss": 0.8214,
      "step": 30
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000181981981981982,
      "loss": 0.655,
      "step": 40
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001774774774774775,
      "loss": 0.5131,
      "step": 50
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000172972972972973,
      "loss": 0.5863,
      "step": 60
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00016846846846846846,
      "loss": 0.4228,
      "step": 70
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00016396396396396395,
      "loss": 0.4562,
      "step": 80
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00015945945945945947,
      "loss": 0.4817,
      "step": 90
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00015495495495495496,
      "loss": 0.5217,
      "step": 100
    },
    {
      "epoch": 0.9,
      "eval_accuracy": 0.8871951219512195,
      "eval_loss": 0.37025415897369385,
      "eval_runtime": 82.1306,
      "eval_samples_per_second": 3.994,
      "eval_steps_per_second": 0.499,
      "step": 100
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00015045045045045046,
      "loss": 0.4543,
      "step": 110
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00014594594594594595,
      "loss": 0.2195,
      "step": 120
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00014144144144144144,
      "loss": 0.2413,
      "step": 130
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00013693693693693693,
      "loss": 0.2153,
      "step": 140
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00013243243243243243,
      "loss": 0.2376,
      "step": 150
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00012792792792792795,
      "loss": 0.215,
      "step": 160
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00012342342342342344,
      "loss": 0.1317,
      "step": 170
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00011891891891891893,
      "loss": 0.143,
      "step": 180
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00011441441441441443,
      "loss": 0.2173,
      "step": 190
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00010990990990990993,
      "loss": 0.1637,
      "step": 200
    },
    {
      "epoch": 1.8,
      "eval_accuracy": 0.8597560975609756,
      "eval_loss": 0.5076180696487427,
      "eval_runtime": 4.074,
      "eval_samples_per_second": 80.511,
      "eval_steps_per_second": 10.064,
      "step": 200
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0001054054054054054,
      "loss": 0.3325,
      "step": 210
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00010090090090090089,
      "loss": 0.2099,
      "step": 220
    },
    {
      "epoch": 2.07,
      "learning_rate": 9.639639639639641e-05,
      "loss": 0.1132,
      "step": 230
    },
    {
      "epoch": 2.16,
      "learning_rate": 9.18918918918919e-05,
      "loss": 0.1517,
      "step": 240
    },
    {
      "epoch": 2.25,
      "learning_rate": 8.738738738738738e-05,
      "loss": 0.0624,
      "step": 250
    },
    {
      "epoch": 2.34,
      "learning_rate": 8.288288288288289e-05,
      "loss": 0.0905,
      "step": 260
    },
    {
      "epoch": 2.43,
      "learning_rate": 7.837837837837838e-05,
      "loss": 0.0586,
      "step": 270
    },
    {
      "epoch": 2.52,
      "learning_rate": 7.387387387387387e-05,
      "loss": 0.071,
      "step": 280
    },
    {
      "epoch": 2.61,
      "learning_rate": 6.936936936936938e-05,
      "loss": 0.0393,
      "step": 290
    },
    {
      "epoch": 2.7,
      "learning_rate": 6.486486486486487e-05,
      "loss": 0.0291,
      "step": 300
    },
    {
      "epoch": 2.7,
      "eval_accuracy": 0.9420731707317073,
      "eval_loss": 0.2087339609861374,
      "eval_runtime": 4.0634,
      "eval_samples_per_second": 80.72,
      "eval_steps_per_second": 10.09,
      "step": 300
    },
    {
      "epoch": 2.79,
      "learning_rate": 6.0360360360360365e-05,
      "loss": 0.075,
      "step": 310
    },
    {
      "epoch": 2.88,
      "learning_rate": 5.585585585585585e-05,
      "loss": 0.1357,
      "step": 320
    },
    {
      "epoch": 2.97,
      "learning_rate": 5.135135135135135e-05,
      "loss": 0.0312,
      "step": 330
    },
    {
      "epoch": 3.06,
      "learning_rate": 4.684684684684685e-05,
      "loss": 0.0753,
      "step": 340
    },
    {
      "epoch": 3.15,
      "learning_rate": 4.234234234234234e-05,
      "loss": 0.0231,
      "step": 350
    },
    {
      "epoch": 3.24,
      "learning_rate": 3.783783783783784e-05,
      "loss": 0.0266,
      "step": 360
    },
    {
      "epoch": 3.33,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.023,
      "step": 370
    },
    {
      "epoch": 3.42,
      "learning_rate": 2.882882882882883e-05,
      "loss": 0.0224,
      "step": 380
    },
    {
      "epoch": 3.51,
      "learning_rate": 2.4324324324324327e-05,
      "loss": 0.0251,
      "step": 390
    },
    {
      "epoch": 3.6,
      "learning_rate": 1.981981981981982e-05,
      "loss": 0.025,
      "step": 400
    },
    {
      "epoch": 3.6,
      "eval_accuracy": 0.9573170731707317,
      "eval_loss": 0.172527477145195,
      "eval_runtime": 4.0556,
      "eval_samples_per_second": 80.877,
      "eval_steps_per_second": 10.11,
      "step": 400
    },
    {
      "epoch": 3.69,
      "learning_rate": 1.5315315315315316e-05,
      "loss": 0.0544,
      "step": 410
    },
    {
      "epoch": 3.78,
      "learning_rate": 1.0810810810810812e-05,
      "loss": 0.0472,
      "step": 420
    },
    {
      "epoch": 3.87,
      "learning_rate": 6.306306306306306e-06,
      "loss": 0.0478,
      "step": 430
    },
    {
      "epoch": 3.96,
      "learning_rate": 1.801801801801802e-06,
      "loss": 0.0209,
      "step": 440
    },
    {
      "epoch": 4.0,
      "step": 444,
      "total_flos": 5.480429975941939e+17,
      "train_loss": 0.2510145430092339,
      "train_runtime": 644.0352,
      "train_samples_per_second": 10.981,
      "train_steps_per_second": 0.689
    }
  ],
  "max_steps": 444,
  "num_train_epochs": 4,
  "total_flos": 5.480429975941939e+17,
  "trial_name": null,
  "trial_params": null
}