{
  "best_global_step": 100,
  "best_metric": 0.1291341334581375,
  "best_model_checkpoint": "./vit_focus/checkpoint-100",
  "epoch": 18.0,
  "eval_steps": 500,
  "global_step": 180,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.11766688525676727,
      "eval_mae": 0.3475768268108368,
      "eval_mse": 0.1613956242799759,
      "eval_runtime": 10.0195,
      "eval_samples_per_second": 7.585,
      "eval_steps_per_second": 0.998,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.09316065162420273,
      "eval_mae": 0.32877787947654724,
      "eval_mse": 0.14106006920337677,
      "eval_runtime": 9.4019,
      "eval_samples_per_second": 8.083,
      "eval_steps_per_second": 1.064,
      "step": 20
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.09138184040784836,
      "eval_mae": 0.3351140022277832,
      "eval_mse": 0.14778681099414825,
      "eval_runtime": 9.4168,
      "eval_samples_per_second": 8.071,
      "eval_steps_per_second": 1.062,
      "step": 30
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.422793388366699,
      "learning_rate": 7.833333333333333e-05,
      "loss": 0.3379,
      "step": 40
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.07990685850381851,
      "eval_mae": 0.3216111361980438,
      "eval_mse": 0.1368674337863922,
      "eval_runtime": 9.6691,
      "eval_samples_per_second": 7.86,
      "eval_steps_per_second": 1.034,
      "step": 40
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.07730501145124435,
      "eval_mae": 0.3210676312446594,
      "eval_mse": 0.1364751160144806,
      "eval_runtime": 9.6377,
      "eval_samples_per_second": 7.886,
      "eval_steps_per_second": 1.038,
      "step": 50
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.08424032479524612,
      "eval_mae": 0.3250683844089508,
      "eval_mse": 0.14131243526935577,
      "eval_runtime": 9.4489,
      "eval_samples_per_second": 8.043,
      "eval_steps_per_second": 1.058,
      "step": 60
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.08766830712556839,
      "eval_mae": 0.3169863820075989,
      "eval_mse": 0.13288582861423492,
      "eval_runtime": 10.5663,
      "eval_samples_per_second": 7.193,
      "eval_steps_per_second": 0.946,
      "step": 70
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.210268020629883,
      "learning_rate": 5.6111111111111114e-05,
      "loss": 0.2829,
      "step": 80
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.08300431817770004,
      "eval_mae": 0.3192159831523895,
      "eval_mse": 0.1370069533586502,
      "eval_runtime": 9.75,
      "eval_samples_per_second": 7.795,
      "eval_steps_per_second": 1.026,
      "step": 80
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.08274427056312561,
      "eval_mae": 0.32542383670806885,
      "eval_mse": 0.140847310423851,
      "eval_runtime": 9.5472,
      "eval_samples_per_second": 7.96,
      "eval_steps_per_second": 1.047,
      "step": 90
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.08588916808366776,
      "eval_mae": 0.3119707405567169,
      "eval_mse": 0.1291341334581375,
      "eval_runtime": 10.6888,
      "eval_samples_per_second": 7.11,
      "eval_steps_per_second": 0.936,
      "step": 100
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.10085263103246689,
      "eval_mae": 0.330853134393692,
      "eval_mse": 0.14782297611236572,
      "eval_runtime": 9.484,
      "eval_samples_per_second": 8.013,
      "eval_steps_per_second": 1.054,
      "step": 110
    },
    {
      "epoch": 12.0,
      "grad_norm": 2.0312862396240234,
      "learning_rate": 3.388888888888889e-05,
      "loss": 0.2461,
      "step": 120
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.08102226257324219,
      "eval_mae": 0.3174217641353607,
      "eval_mse": 0.135166734457016,
      "eval_runtime": 9.5097,
      "eval_samples_per_second": 7.992,
      "eval_steps_per_second": 1.052,
      "step": 120
    },
    {
      "epoch": 13.0,
      "eval_loss": 0.08370836824178696,
      "eval_mae": 0.31886667013168335,
      "eval_mse": 0.13684500753879547,
      "eval_runtime": 9.4388,
      "eval_samples_per_second": 8.052,
      "eval_steps_per_second": 1.059,
      "step": 130
    },
    {
      "epoch": 14.0,
      "eval_loss": 0.08873885869979858,
      "eval_mae": 0.32301220297813416,
      "eval_mse": 0.1409922093153,
      "eval_runtime": 9.629,
      "eval_samples_per_second": 7.893,
      "eval_steps_per_second": 1.039,
      "step": 140
    },
    {
      "epoch": 15.0,
      "eval_loss": 0.08366208523511887,
      "eval_mae": 0.31394028663635254,
      "eval_mse": 0.13212691247463226,
      "eval_runtime": 9.4772,
      "eval_samples_per_second": 8.019,
      "eval_steps_per_second": 1.055,
      "step": 150
    },
    {
      "epoch": 16.0,
      "grad_norm": 2.5568466186523438,
      "learning_rate": 1.1666666666666668e-05,
      "loss": 0.2104,
      "step": 160
    },
    {
      "epoch": 16.0,
      "eval_loss": 0.09077440947294235,
      "eval_mae": 0.3225802481174469,
      "eval_mse": 0.14043577015399933,
      "eval_runtime": 9.6623,
      "eval_samples_per_second": 7.866,
      "eval_steps_per_second": 1.035,
      "step": 160
    },
    {
      "epoch": 17.0,
      "eval_loss": 0.08574231714010239,
      "eval_mae": 0.31825631856918335,
      "eval_mse": 0.13667234778404236,
      "eval_runtime": 9.4595,
      "eval_samples_per_second": 8.034,
      "eval_steps_per_second": 1.057,
      "step": 170
    },
    {
      "epoch": 18.0,
      "eval_loss": 0.08340632170438766,
      "eval_mae": 0.3171162009239197,
      "eval_mse": 0.13509555160999298,
      "eval_runtime": 9.4982,
      "eval_samples_per_second": 8.002,
      "eval_steps_per_second": 1.053,
      "step": 180
    },
    {
      "epoch": 18.0,
      "step": 180,
      "total_flos": 0.0,
      "train_loss": 0.2600840449333191,
      "train_runtime": 1002.0455,
      "train_samples_per_second": 6.048,
      "train_steps_per_second": 0.18
    }
  ],
  "logging_steps": 40,
  "max_steps": 180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}