{
  "best_metric": 1.2660315036773682,
  "best_model_checkpoint": "./vit-base-beans/checkpoint-100",
  "epoch": 1.7241379310344827,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17,
      "learning_rate": 0.0001931034482758621,
      "loss": 1.7999,
      "step": 10
    },
    {
      "epoch": 0.17,
      "eval_accuracy": 0.25555555555555554,
      "eval_loss": 1.9382611513137817,
      "eval_runtime": 128.8894,
      "eval_samples_per_second": 2.095,
      "eval_steps_per_second": 0.264,
      "step": 10
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00018620689655172415,
      "loss": 1.5424,
      "step": 20
    },
    {
      "epoch": 0.34,
      "eval_accuracy": 0.4148148148148148,
      "eval_loss": 1.5738633871078491,
      "eval_runtime": 7.0871,
      "eval_samples_per_second": 38.097,
      "eval_steps_per_second": 4.797,
      "step": 20
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001793103448275862,
      "loss": 1.257,
      "step": 30
    },
    {
      "epoch": 0.52,
      "eval_accuracy": 0.5777777777777777,
      "eval_loss": 1.3710002899169922,
      "eval_runtime": 8.6728,
      "eval_samples_per_second": 31.132,
      "eval_steps_per_second": 3.92,
      "step": 30
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00017241379310344826,
      "loss": 1.0721,
      "step": 40
    },
    {
      "epoch": 0.69,
      "eval_accuracy": 0.5074074074074074,
      "eval_loss": 1.4735559225082397,
      "eval_runtime": 7.1381,
      "eval_samples_per_second": 37.825,
      "eval_steps_per_second": 4.763,
      "step": 40
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016551724137931035,
      "loss": 1.1026,
      "step": 50
    },
    {
      "epoch": 0.86,
      "eval_accuracy": 0.6370370370370371,
      "eval_loss": 1.2928471565246582,
      "eval_runtime": 8.3556,
      "eval_samples_per_second": 32.314,
      "eval_steps_per_second": 4.069,
      "step": 50
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00015862068965517243,
      "loss": 0.9359,
      "step": 60
    },
    {
      "epoch": 1.03,
      "eval_accuracy": 0.6074074074074074,
      "eval_loss": 1.2788481712341309,
      "eval_runtime": 7.1042,
      "eval_samples_per_second": 38.006,
      "eval_steps_per_second": 4.786,
      "step": 60
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00015172413793103449,
      "loss": 0.7,
      "step": 70
    },
    {
      "epoch": 1.21,
      "eval_accuracy": 0.6592592592592592,
      "eval_loss": 1.2249455451965332,
      "eval_runtime": 7.5614,
      "eval_samples_per_second": 35.708,
      "eval_steps_per_second": 4.497,
      "step": 70
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00014482758620689657,
      "loss": 0.5367,
      "step": 80
    },
    {
      "epoch": 1.38,
      "eval_accuracy": 0.6222222222222222,
      "eval_loss": 1.3300864696502686,
      "eval_runtime": 7.852,
      "eval_samples_per_second": 34.386,
      "eval_steps_per_second": 4.33,
      "step": 80
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00013793103448275863,
      "loss": 0.6017,
      "step": 90
    },
    {
      "epoch": 1.55,
      "eval_accuracy": 0.6666666666666666,
      "eval_loss": 1.2042837142944336,
      "eval_runtime": 8.2241,
      "eval_samples_per_second": 32.83,
      "eval_steps_per_second": 4.134,
      "step": 90
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00013103448275862068,
      "loss": 0.6007,
      "step": 100
    },
    {
      "epoch": 1.72,
      "eval_accuracy": 0.6703703703703704,
      "eval_loss": 1.2660315036773682,
      "eval_runtime": 8.6405,
      "eval_samples_per_second": 31.248,
      "eval_steps_per_second": 3.935,
      "step": 100
    }
  ],
  "max_steps": 290,
  "num_train_epochs": 5,
  "total_flos": 1.2298640089197773e+17,
  "trial_name": null,
  "trial_params": null
}