{
  "best_metric": 0.018021462485194206,
  "best_model_checkpoint": "./vit-base-beans-tutorial/checkpoint-300",
  "epoch": 5.0,
  "eval_steps": 100,
  "global_step": 325,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15,
      "learning_rate": 0.00019384615384615385,
      "loss": 0.7357,
      "step": 10
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001876923076923077,
      "loss": 0.3568,
      "step": 20
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00018153846153846155,
      "loss": 0.2762,
      "step": 30
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001753846153846154,
      "loss": 0.2463,
      "step": 40
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00016923076923076923,
      "loss": 0.2958,
      "step": 50
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001630769230769231,
      "loss": 0.3082,
      "step": 60
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00015692307692307693,
      "loss": 0.1819,
      "step": 70
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00015076923076923077,
      "loss": 0.0583,
      "step": 80
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0001446153846153846,
      "loss": 0.0947,
      "step": 90
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00013846153846153847,
      "loss": 0.0469,
      "step": 100
    },
    {
      "epoch": 1.54,
      "eval_accuracy": 0.9624060150375939,
      "eval_loss": 0.13196179270744324,
      "eval_runtime": 1.9015,
      "eval_samples_per_second": 69.944,
      "eval_steps_per_second": 8.94,
      "step": 100
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0001323076923076923,
      "loss": 0.0891,
      "step": 110
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00012615384615384615,
      "loss": 0.1318,
      "step": 120
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00012,
      "loss": 0.1383,
      "step": 130
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00011384615384615384,
      "loss": 0.0751,
      "step": 140
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0001076923076923077,
      "loss": 0.0241,
      "step": 150
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00010153846153846153,
      "loss": 0.0238,
      "step": 160
    },
    {
      "epoch": 2.62,
      "learning_rate": 9.53846153846154e-05,
      "loss": 0.0422,
      "step": 170
    },
    {
      "epoch": 2.77,
      "learning_rate": 8.923076923076924e-05,
      "loss": 0.0745,
      "step": 180
    },
    {
      "epoch": 2.92,
      "learning_rate": 8.307692307692309e-05,
      "loss": 0.0547,
      "step": 190
    },
    {
      "epoch": 3.08,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.0186,
      "step": 200
    },
    {
      "epoch": 3.08,
      "eval_accuracy": 0.9924812030075187,
      "eval_loss": 0.031496379524469376,
      "eval_runtime": 2.3261,
      "eval_samples_per_second": 57.177,
      "eval_steps_per_second": 7.308,
      "step": 200
    },
    {
      "epoch": 3.23,
      "learning_rate": 7.076923076923078e-05,
      "loss": 0.0359,
      "step": 210
    },
    {
      "epoch": 3.38,
      "learning_rate": 6.461538461538462e-05,
      "loss": 0.0128,
      "step": 220
    },
    {
      "epoch": 3.54,
      "learning_rate": 5.846153846153847e-05,
      "loss": 0.0171,
      "step": 230
    },
    {
      "epoch": 3.69,
      "learning_rate": 5.230769230769231e-05,
      "loss": 0.0361,
      "step": 240
    },
    {
      "epoch": 3.85,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.0114,
      "step": 250
    },
    {
      "epoch": 4.0,
      "learning_rate": 4e-05,
      "loss": 0.0106,
      "step": 260
    },
    {
      "epoch": 4.15,
      "learning_rate": 3.384615384615385e-05,
      "loss": 0.0091,
      "step": 270
    },
    {
      "epoch": 4.31,
      "learning_rate": 2.7692307692307694e-05,
      "loss": 0.0089,
      "step": 280
    },
    {
      "epoch": 4.46,
      "learning_rate": 2.1538461538461542e-05,
      "loss": 0.0086,
      "step": 290
    },
    {
      "epoch": 4.62,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.0084,
      "step": 300
    },
    {
      "epoch": 4.62,
      "eval_accuracy": 0.9924812030075187,
      "eval_loss": 0.018021462485194206,
      "eval_runtime": 1.9286,
      "eval_samples_per_second": 68.962,
      "eval_steps_per_second": 8.815,
      "step": 300
    },
    {
      "epoch": 4.77,
      "learning_rate": 9.230769230769232e-06,
      "loss": 0.0082,
      "step": 310
    },
    {
      "epoch": 4.92,
      "learning_rate": 3.0769230769230774e-06,
      "loss": 0.0085,
      "step": 320
    },
    {
      "epoch": 5.0,
      "step": 325,
      "total_flos": 4.006371770595533e+17,
      "train_loss": 0.10624572600309666,
      "train_runtime": 142.6688,
      "train_samples_per_second": 36.238,
      "train_steps_per_second": 2.278
    }
  ],
  "logging_steps": 10,
  "max_steps": 325,
  "num_train_epochs": 5,
  "save_steps": 100,
  "total_flos": 4.006371770595533e+17,
  "trial_name": null,
  "trial_params": null
}