{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.6955768564499367,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "learning_rate": 0.00019993414517786287,
      "loss": 0.4211,
      "step": 50
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001997366674486034,
      "loss": 0.2148,
      "step": 100
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019940782690943637,
      "loss": 0.1821,
      "step": 150
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019894805667506615,
      "loss": 0.1588,
      "step": 200
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019835796230723287,
      "loss": 0.142,
      "step": 250
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019763832101712928,
      "loss": 0.1332,
      "step": 300
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019679008064173867,
      "loss": 0.1303,
      "step": 350
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019581435839544203,
      "loss": 0.126,
      "step": 400
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019471243939853908,
      "loss": 0.1089,
      "step": 450
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001934857749846208,
      "loss": 0.1077,
      "step": 500
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001921359807890232,
      "loss": 0.0967,
      "step": 550
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001906648346208798,
      "loss": 0.0829,
      "step": 600
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00018907427412157533,
      "loss": 0.0772,
      "step": 650
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00018736639421268545,
      "loss": 0.0744,
      "step": 700
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001855434443367628,
      "loss": 0.0699,
      "step": 750
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001836078254946042,
      "loss": 0.0742,
      "step": 800
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00018156208708290121,
      "loss": 0.0679,
      "step": 850
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00017940892353643866,
      "loss": 0.0655,
      "step": 900
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00017715117077926422,
      "loss": 0.0695,
      "step": 950
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00017479180248950295,
      "loss": 0.0619,
      "step": 1000
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00017233392618273645,
      "loss": 0.0638,
      "step": 1050
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00016978077911910502,
      "loss": 0.053,
      "step": 1100
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00016713572403952403,
      "loss": 0.0403,
      "step": 1150
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0001644022447366296,
      "loss": 0.0474,
      "step": 1200
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0001615839414662879,
      "loss": 0.0402,
      "step": 1250
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00015868452620571087,
      "loss": 0.0456,
      "step": 1300
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00015570781776442426,
      "loss": 0.0426,
      "step": 1350
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.00015265773675452718,
      "loss": 0.0416,
      "step": 1400
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.0001495383004268678,
      "loss": 0.0422,
      "step": 1450
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.00014635361737993667,
      "loss": 0.0395,
      "step": 1500
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.00014310788214844618,
      "loss": 0.0364,
      "step": 1550
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.00013980536967872378,
      "loss": 0.0353,
      "step": 1600
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.00013645042969819544,
      "loss": 0.0285,
      "step": 1650
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.0001330474809863752,
      "loss": 0.0234,
      "step": 1700
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.00012960100555490617,
      "loss": 0.0234,
      "step": 1750
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.0001261155427443192,
      "loss": 0.0243,
      "step": 1800
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.00012259568324528335,
      "loss": 0.0251,
      "step": 1850
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.00011904606305222381,
      "loss": 0.0234,
      "step": 1900
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.00011547135735726992,
      "loss": 0.0216,
      "step": 1950
    },
    {
      "epoch": 3.7,
      "learning_rate": 0.00011187627439257638,
      "loss": 0.0195,
      "step": 2000
    }
  ],
  "logging_steps": 50,
  "max_steps": 4328,
  "num_train_epochs": 8,
  "save_steps": 500,
  "total_flos": 8.384347351782605e+17,
  "trial_name": null,
  "trial_params": null
}