{
  "best_metric": 0.9850746268656716,
  "best_model_checkpoint": "./outputs/checkpoint-48",
  "epoch": 4.0,
  "global_step": 192,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21,
      "learning_rate": 1.8958333333333334e-05,
      "loss": 0.0325,
      "step": 10
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.7916666666666667e-05,
      "loss": 0.031,
      "step": 20
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.6875e-05,
      "loss": 0.0295,
      "step": 30
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5833333333333333e-05,
      "loss": 0.0283,
      "step": 40
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9850746268656716,
      "eval_loss": 0.04340995103120804,
      "eval_runtime": 1.9606,
      "eval_samples_per_second": 34.174,
      "eval_steps_per_second": 4.59,
      "step": 48
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.479166666666667e-05,
      "loss": 0.0268,
      "step": 50
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.375e-05,
      "loss": 0.0249,
      "step": 60
    },
    {
      "epoch": 1.46,
      "learning_rate": 1.2708333333333333e-05,
      "loss": 0.0236,
      "step": 70
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.1666666666666668e-05,
      "loss": 0.023,
      "step": 80
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.0625e-05,
      "loss": 0.0224,
      "step": 90
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9850746268656716,
      "eval_loss": 0.05477194860577583,
      "eval_runtime": 1.9694,
      "eval_samples_per_second": 34.021,
      "eval_steps_per_second": 4.57,
      "step": 96
    },
    {
      "epoch": 2.08,
      "learning_rate": 9.583333333333335e-06,
      "loss": 0.0216,
      "step": 100
    },
    {
      "epoch": 2.29,
      "learning_rate": 8.541666666666666e-06,
      "loss": 0.0213,
      "step": 110
    },
    {
      "epoch": 2.5,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.0205,
      "step": 120
    },
    {
      "epoch": 2.71,
      "learning_rate": 6.458333333333334e-06,
      "loss": 0.0206,
      "step": 130
    },
    {
      "epoch": 2.92,
      "learning_rate": 5.416666666666667e-06,
      "loss": 0.0203,
      "step": 140
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9850746268656716,
      "eval_loss": 0.04450145736336708,
      "eval_runtime": 1.9416,
      "eval_samples_per_second": 34.507,
      "eval_steps_per_second": 4.635,
      "step": 144
    },
    {
      "epoch": 3.12,
      "learning_rate": 4.3750000000000005e-06,
      "loss": 0.02,
      "step": 150
    },
    {
      "epoch": 3.33,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.0196,
      "step": 160
    },
    {
      "epoch": 3.54,
      "learning_rate": 2.2916666666666666e-06,
      "loss": 0.0196,
      "step": 170
    },
    {
      "epoch": 3.75,
      "learning_rate": 1.25e-06,
      "loss": 0.0194,
      "step": 180
    },
    {
      "epoch": 3.96,
      "learning_rate": 2.0833333333333333e-07,
      "loss": 0.0195,
      "step": 190
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9850746268656716,
      "eval_loss": 0.053447265177965164,
      "eval_runtime": 1.9698,
      "eval_samples_per_second": 34.013,
      "eval_steps_per_second": 4.569,
      "step": 192
    },
    {
      "epoch": 4.0,
      "step": 192,
      "total_flos": 0.0,
      "train_loss": 0.023352553563502926,
      "train_runtime": 233.1724,
      "train_samples_per_second": 6.57,
      "train_steps_per_second": 0.823
    }
  ],
  "max_steps": 192,
  "num_train_epochs": 4,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}