{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8567511994516792,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 8.993468091981983e-06,
      "loss": 0.6658,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.973891330515647e-06,
      "loss": 0.4496,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.941326548314408e-06,
      "loss": 0.3875,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.895868283228027e-06,
      "loss": 0.3646,
      "step": 40
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.837648503792598e-06,
      "loss": 0.3664,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.766836226116608e-06,
      "loss": 0.3676,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.683637023215312e-06,
      "loss": 0.3075,
      "step": 70
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.588292428217834e-06,
      "loss": 0.2945,
      "step": 80
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.481079233179522e-06,
      "loss": 0.3539,
      "step": 90
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.362308685535184e-06,
      "loss": 0.2699,
      "step": 100
    },
    {
      "epoch": 0.17,
      "eval_accuracy": 0.0,
      "eval_loss": 0.27337193489074707,
      "eval_runtime": 53.8814,
      "eval_samples_per_second": 72.214,
      "eval_steps_per_second": 12.045,
      "step": 100
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.232325584525908e-06,
      "loss": 0.2544,
      "step": 110
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.091507280222673e-06,
      "loss": 0.2776,
      "step": 120
    },
    {
      "epoch": 0.22,
      "learning_rate": 7.940262578052568e-06,
      "loss": 0.2941,
      "step": 130
    },
    {
      "epoch": 0.24,
      "learning_rate": 7.779030552007946e-06,
      "loss": 0.2615,
      "step": 140
    },
    {
      "epoch": 0.26,
      "learning_rate": 7.608279269983776e-06,
      "loss": 0.2673,
      "step": 150
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.428504434943677e-06,
      "loss": 0.2524,
      "step": 160
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.240227945859397e-06,
      "loss": 0.2732,
      "step": 170
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.043996382601448e-06,
      "loss": 0.2184,
      "step": 180
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.840379419179357e-06,
      "loss": 0.2578,
      "step": 190
    },
    {
      "epoch": 0.34,
      "learning_rate": 6.629968169938005e-06,
      "loss": 0.2827,
      "step": 200
    },
    {
      "epoch": 0.34,
      "eval_accuracy": 0.0,
      "eval_loss": 0.2310507595539093,
      "eval_runtime": 54.2245,
      "eval_samples_per_second": 71.757,
      "eval_steps_per_second": 11.969,
      "step": 200
    },
    {
      "epoch": 0.36,
      "learning_rate": 6.41337347351117e-06,
      "loss": 0.2426,
      "step": 210
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.191224119514071e-06,
      "loss": 0.2142,
      "step": 220
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.964165023122967e-06,
      "loss": 0.264,
      "step": 230
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.73285535284109e-06,
      "loss": 0.2039,
      "step": 240
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.4979666168862e-06,
      "loss": 0.2163,
      "step": 250
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.260180713755066e-06,
      "loss": 0.2363,
      "step": 260
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.020187952624234e-06,
      "loss": 0.21,
      "step": 270
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.7786850493340155e-06,
      "loss": 0.235,
      "step": 280
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.536373103773464e-06,
      "loss": 0.2067,
      "step": 290
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.2939555645381675e-06,
      "loss": 0.2001,
      "step": 300
    },
    {
      "epoch": 0.51,
      "eval_accuracy": 0.0,
      "eval_loss": 0.19201719760894775,
      "eval_runtime": 53.8375,
      "eval_samples_per_second": 72.273,
      "eval_steps_per_second": 12.055,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.052136186769563e-06,
      "loss": 0.1799,
      "step": 310
    },
    {
      "epoch": 0.55,
      "learning_rate": 3.811616989104347e-06,
      "loss": 0.2202,
      "step": 320
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.573096215665058e-06,
      "loss": 0.1974,
      "step": 330
    },
    {
      "epoch": 0.58,
      "learning_rate": 3.337266309008359e-06,
      "loss": 0.1872,
      "step": 340
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.104811899915661e-06,
      "loss": 0.1746,
      "step": 350
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.87640781986189e-06,
      "loss": 0.1728,
      "step": 360
    },
    {
      "epoch": 0.63,
      "learning_rate": 2.652717141932312e-06,
      "loss": 0.1656,
      "step": 370
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.4343892558748025e-06,
      "loss": 0.1716,
      "step": 380
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.222057982875807e-06,
      "loss": 0.1698,
      "step": 390
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.0163397355329136e-06,
      "loss": 0.1955,
      "step": 400
    },
    {
      "epoch": 0.69,
      "eval_accuracy": 0.0,
      "eval_loss": 0.17988212406635284,
      "eval_runtime": 54.3033,
      "eval_samples_per_second": 71.653,
      "eval_steps_per_second": 11.951,
      "step": 400
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.817831728365798e-06,
      "loss": 0.2,
      "step": 410
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.6271102440605319e-06,
      "loss": 0.1686,
      "step": 420
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.444728960480465e-06,
      "loss": 0.1618,
      "step": 430
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.2712173433005088e-06,
      "loss": 0.1637,
      "step": 440
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.107079108931101e-06,
      "loss": 0.1856,
      "step": 450
    },
    {
      "epoch": 0.79,
      "learning_rate": 9.527907621940788e-07,
      "loss": 0.1895,
      "step": 460
    },
    {
      "epoch": 0.81,
      "learning_rate": 8.08800212995727e-07,
      "loss": 0.1871,
      "step": 470
    },
    {
      "epoch": 0.82,
      "learning_rate": 6.755254760128572e-07,
      "loss": 0.1874,
      "step": 480
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.533534571668463e-07,
      "loss": 0.1925,
      "step": 490
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.4263883040857247e-07,
      "loss": 0.1334,
      "step": 500
    },
    {
      "epoch": 0.86,
      "eval_accuracy": 0.0,
      "eval_loss": 0.17077727615833282,
      "eval_runtime": 54.0155,
      "eval_samples_per_second": 72.035,
      "eval_steps_per_second": 12.015,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 583,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}