trainer_state.json

{
  "best_metric": 0.10942860692739487,
  "best_model_checkpoint": "./vit-base-beans/checkpoint-200",
  "epoch": 3.571428571428571,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18,
      "learning_rate": 0.00019107142857142858,
      "loss": 1.5687,
      "step": 10
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00018214285714285714,
      "loss": 0.9862,
      "step": 20
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00017321428571428574,
      "loss": 0.6791,
      "step": 30
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00016428571428571428,
      "loss": 0.4272,
      "step": 40
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00015535714285714287,
      "loss": 0.3579,
      "step": 50
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00014642857142857141,
      "loss": 0.2258,
      "step": 60
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001375,
      "loss": 0.1523,
      "step": 70
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00012857142857142858,
      "loss": 0.1718,
      "step": 80
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00011964285714285714,
      "loss": 0.0991,
      "step": 90
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00011071428571428572,
      "loss": 0.1059,
      "step": 100
    },
    {
      "epoch": 1.79,
      "eval_accuracy": 0.9715447154471545,
      "eval_loss": 0.16246800124645233,
      "eval_runtime": 4.2911,
      "eval_samples_per_second": 57.328,
      "eval_steps_per_second": 7.224,
      "step": 100
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00010178571428571428,
      "loss": 0.1066,
      "step": 110
    },
    {
      "epoch": 2.14,
      "learning_rate": 9.285714285714286e-05,
      "loss": 0.1433,
      "step": 120
    },
    {
      "epoch": 2.32,
      "learning_rate": 8.392857142857144e-05,
      "loss": 0.0684,
      "step": 130
    },
    {
      "epoch": 2.5,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0576,
      "step": 140
    },
    {
      "epoch": 2.68,
      "learning_rate": 6.607142857142857e-05,
      "loss": 0.0583,
      "step": 150
    },
    {
      "epoch": 2.86,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.0505,
      "step": 160
    },
    {
      "epoch": 3.04,
      "learning_rate": 4.8214285714285716e-05,
      "loss": 0.0474,
      "step": 170
    },
    {
      "epoch": 3.21,
      "learning_rate": 3.928571428571429e-05,
      "loss": 0.0459,
      "step": 180
    },
    {
      "epoch": 3.39,
      "learning_rate": 3.0357142857142857e-05,
      "loss": 0.0439,
      "step": 190
    },
    {
      "epoch": 3.57,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.0433,
      "step": 200
    },
    {
      "epoch": 3.57,
      "eval_accuracy": 0.975609756097561,
      "eval_loss": 0.10942860692739487,
      "eval_runtime": 4.2642,
      "eval_samples_per_second": 57.689,
      "eval_steps_per_second": 7.27,
      "step": 200
    }
  ],
  "max_steps": 224,
  "num_train_epochs": 4,
  "total_flos": 2.4519564270312653e+17,
  "trial_name": null,
  "trial_params": null
}