[
  {
    "loss": 1.3593,
    "grad_norm": 0.07132186740636826,
    "learning_rate": 0.00012,
    "epoch": 0.03546099290780142,
    "step": 10
  },
  {
    "loss": 1.2212,
    "grad_norm": 0.06576087325811386,
    "learning_rate": 0.00019988926445681492,
    "epoch": 0.07092198581560284,
    "step": 20
  },
  {
    "loss": 1.4382,
    "grad_norm": 0.064721018075943,
    "learning_rate": 0.0001986463043917528,
    "epoch": 0.10638297872340426,
    "step": 30
  },
  {
    "loss": 1.1636,
    "grad_norm": 0.06784526258707047,
    "learning_rate": 0.00019603921063437793,
    "epoch": 0.14184397163120568,
    "step": 40
  },
  {
    "loss": 1.1023,
    "grad_norm": 0.06855457276105881,
    "learning_rate": 0.0001921040354671897,
    "epoch": 0.1773049645390071,
    "step": 50
  },
  {
    "loss": 1.159,
    "grad_norm": 0.0872117206454277,
    "learning_rate": 0.00018689519659051467,
    "epoch": 0.2127659574468085,
    "step": 60
  },
  {
    "loss": 1.2097,
    "grad_norm": 0.06708938628435135,
    "learning_rate": 0.00018048472460553257,
    "epoch": 0.24822695035460993,
    "step": 70
  },
  {
    "loss": 1.1172,
    "grad_norm": 0.07587900757789612,
    "learning_rate": 0.00017296126693671884,
    "epoch": 0.28368794326241137,
    "step": 80
  },
  {
    "loss": 1.0976,
    "grad_norm": 0.07327847182750702,
    "learning_rate": 0.00016442886196799464,
    "epoch": 0.3191489361702128,
    "step": 90
  },
  {
    "loss": 1.1342,
    "grad_norm": 0.07166396826505661,
    "learning_rate": 0.00015500550034448413,
    "epoch": 0.3546099290780142,
    "step": 100
  },
  {
    "loss": 1.1876,
    "grad_norm": 0.08132865279912949,
    "learning_rate": 0.00014482149333496454,
    "epoch": 0.3900709219858156,
    "step": 110
  },
  {
    "loss": 1.2186,
    "grad_norm": 0.08324161171913147,
    "learning_rate": 0.0001340176708181637,
    "epoch": 0.425531914893617,
    "step": 120
  },
  {
    "loss": 1.2672,
    "grad_norm": 0.08210298418998718,
    "learning_rate": 0.00012274343381211066,
    "epoch": 0.46099290780141844,
    "step": 130
  },
  {
    "loss": 1.1838,
    "grad_norm": 0.06662478297948837,
    "learning_rate": 0.00011115468847720245,
    "epoch": 0.49645390070921985,
    "step": 140
  },
  {
    "loss": 1.161,
    "grad_norm": 0.08010110259056091,
    "learning_rate": 9.941169016269379e-05,
    "epoch": 0.5319148936170213,
    "step": 150
  },
  {
    "loss": 1.2318,
    "grad_norm": 0.09503161162137985,
    "learning_rate": 8.767682731028415e-05,
    "epoch": 0.5673758865248227,
    "step": 160
  },
  {
    "loss": 1.1064,
    "grad_norm": 0.06613818556070328,
    "learning_rate": 7.611237586016557e-05,
    "epoch": 0.6028368794326241,
    "step": 170
  },
  {
    "loss": 1.1023,
    "grad_norm": 0.08144712448120117,
    "learning_rate": 6.487825521280109e-05,
    "epoch": 0.6382978723404256,
    "step": 180
  },
  {
    "loss": 1.0777,
    "grad_norm": 0.07447583973407745,
    "learning_rate": 5.4129816778190936e-05,
    "epoch": 0.6737588652482269,
    "step": 190
  },
  {
    "loss": 1.0299,
    "grad_norm": 0.08357255160808563,
    "learning_rate": 4.401569569374668e-05,
    "epoch": 0.7092198581560284,
    "step": 200
  },
  {
    "loss": 1.1504,
    "grad_norm": 0.07654684036970139,
    "learning_rate": 3.467575541836305e-05,
    "epoch": 0.7446808510638298,
    "step": 210
  },
  {
    "loss": 1.0784,
    "grad_norm": 0.07995031774044037,
    "learning_rate": 2.6239153625937784e-05,
    "epoch": 0.7801418439716312,
    "step": 220
  },
  {
    "loss": 1.0866,
    "grad_norm": 0.08516442775726318,
    "learning_rate": 1.882255614419376e-05,
    "epoch": 0.8156028368794326,
    "step": 230
  },
  {
    "loss": 1.1881,
    "grad_norm": 0.06854885816574097,
    "learning_rate": 1.2528523637410838e-05,
    "epoch": 0.851063829787234,
    "step": 240
  },
  {
    "loss": 1.1803,
    "grad_norm": 0.07308827340602875,
    "learning_rate": 7.4440933428779e-06,
    "epoch": 0.8865248226950354,
    "step": 250
  },
  {
    "loss": 1.252,
    "grad_norm": 0.082114577293396,
    "learning_rate": 3.6395754735699894e-06,
    "epoch": 0.9219858156028369,
    "step": 260
  },
  {
    "loss": 0.9981,
    "grad_norm": 0.08104278147220612,
    "learning_rate": 1.1675809310361497e-06,
    "epoch": 0.9574468085106383,
    "step": 270
  },
  {
    "loss": 1.0975,
    "grad_norm": 0.1148340180516243,
    "learning_rate": 6.229377380218005e-08,
    "epoch": 0.9929078014184397,
    "step": 280
  },
  {
    "train_runtime": 5043.2773,
    "train_samples_per_second": 0.892,
    "train_steps_per_second": 0.056,
    "total_flos": 7.853598969744589e+16,
    "train_loss": 1.1630526971309743,
    "epoch": 1.0,
    "step": 282
  }
]