{
  "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": 8.993468091981985e-05,
      "loss": 0.6403,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.973891330515646e-05,
      "loss": 0.5248,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.941326548314407e-05,
      "loss": 0.5079,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.895868283228029e-05,
      "loss": 0.5916,
      "step": 40
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.837648503792598e-05,
      "loss": 0.5116,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.766836226116608e-05,
      "loss": 0.5206,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.683637023215313e-05,
      "loss": 0.535,
      "step": 70
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.588292428217834e-05,
      "loss": 0.6067,
      "step": 80
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.481079233179524e-05,
      "loss": 0.6139,
      "step": 90
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.362308685535183e-05,
      "loss": 0.5015,
      "step": 100
    },
    {
      "epoch": 0.17,
      "eval_accuracy": 0.0,
      "eval_loss": 0.5284319519996643,
      "eval_runtime": 27.5165,
      "eval_samples_per_second": 141.406,
      "eval_steps_per_second": 23.586,
      "step": 100
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.232325584525909e-05,
      "loss": 0.6008,
      "step": 110
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.091507280222672e-05,
      "loss": 0.549,
      "step": 120
    },
    {
      "epoch": 0.22,
      "learning_rate": 7.940262578052567e-05,
      "loss": 0.5512,
      "step": 130
    },
    {
      "epoch": 0.24,
      "learning_rate": 7.779030552007946e-05,
      "loss": 0.4872,
      "step": 140
    },
    {
      "epoch": 0.26,
      "learning_rate": 7.608279269983776e-05,
      "loss": 0.505,
      "step": 150
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.428504434943677e-05,
      "loss": 0.4774,
      "step": 160
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.240227945859396e-05,
      "loss": 0.5005,
      "step": 170
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.043996382601448e-05,
      "loss": 0.4286,
      "step": 180
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.840379419179358e-05,
      "loss": 0.4746,
      "step": 190
    },
    {
      "epoch": 0.34,
      "learning_rate": 6.629968169938006e-05,
      "loss": 0.4259,
      "step": 200
    },
    {
      "epoch": 0.34,
      "eval_accuracy": 0.0,
      "eval_loss": 0.3847603499889374,
      "eval_runtime": 28.0384,
      "eval_samples_per_second": 138.774,
      "eval_steps_per_second": 23.147,
      "step": 200
    },
    {
      "epoch": 0.36,
      "learning_rate": 6.41337347351117e-05,
      "loss": 0.4118,
      "step": 210
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.191224119514072e-05,
      "loss": 0.3758,
      "step": 220
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.9641650231229666e-05,
      "loss": 0.4376,
      "step": 230
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.7328553528410896e-05,
      "loss": 0.4189,
      "step": 240
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.497966616886201e-05,
      "loss": 0.3686,
      "step": 250
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.2601807137550664e-05,
      "loss": 0.377,
      "step": 260
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.020187952624234e-05,
      "loss": 0.3708,
      "step": 270
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.7786850493340155e-05,
      "loss": 0.4092,
      "step": 280
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.536373103773464e-05,
      "loss": 0.3521,
      "step": 290
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.293955564538168e-05,
      "loss": 0.3808,
      "step": 300
    },
    {
      "epoch": 0.51,
      "eval_accuracy": 0.0,
      "eval_loss": 0.2961568832397461,
      "eval_runtime": 27.3269,
      "eval_samples_per_second": 142.387,
      "eval_steps_per_second": 23.749,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.052136186769563e-05,
      "loss": 0.3133,
      "step": 310
    },
    {
      "epoch": 0.55,
      "learning_rate": 3.811616989104347e-05,
      "loss": 0.3472,
      "step": 320
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.573096215665058e-05,
      "loss": 0.3731,
      "step": 330
    },
    {
      "epoch": 0.58,
      "learning_rate": 3.337266309008359e-05,
      "loss": 0.3228,
      "step": 340
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.104811899915661e-05,
      "loss": 0.3134,
      "step": 350
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.87640781986189e-05,
      "loss": 0.3279,
      "step": 360
    },
    {
      "epoch": 0.63,
      "learning_rate": 2.652717141932312e-05,
      "loss": 0.3049,
      "step": 370
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.4343892558748025e-05,
      "loss": 0.2683,
      "step": 380
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.2220579828758074e-05,
      "loss": 0.2857,
      "step": 390
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.0163397355329138e-05,
      "loss": 0.3328,
      "step": 400
    },
    {
      "epoch": 0.69,
      "eval_accuracy": 0.0,
      "eval_loss": 0.25916174054145813,
      "eval_runtime": 28.4607,
      "eval_samples_per_second": 136.715,
      "eval_steps_per_second": 22.803,
      "step": 400
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.817831728365798e-05,
      "loss": 0.2938,
      "step": 410
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.627110244060532e-05,
      "loss": 0.2557,
      "step": 420
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.444728960480465e-05,
      "loss": 0.2855,
      "step": 430
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.2712173433005089e-05,
      "loss": 0.2658,
      "step": 440
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.107079108931101e-05,
      "loss": 0.2842,
      "step": 450
    },
    {
      "epoch": 0.79,
      "learning_rate": 9.527907621940789e-06,
      "loss": 0.2442,
      "step": 460
    },
    {
      "epoch": 0.81,
      "learning_rate": 8.08800212995727e-06,
      "loss": 0.3001,
      "step": 470
    },
    {
      "epoch": 0.82,
      "learning_rate": 6.7552547601285726e-06,
      "loss": 0.2603,
      "step": 480
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.533534571668464e-06,
      "loss": 0.2707,
      "step": 490
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.426388304085724e-06,
      "loss": 0.2086,
      "step": 500
    },
    {
      "epoch": 0.86,
      "eval_accuracy": 0.0,
      "eval_loss": 0.24190260469913483,
      "eval_runtime": 27.2731,
      "eval_samples_per_second": 142.668,
      "eval_steps_per_second": 23.796,
      "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
}