{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.113590263691684,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 16.835479736328125,
      "learning_rate": 0.0002,
      "loss": 3.766,
      "step": 10
    },
    {
      "epoch": 0.16,
      "grad_norm": 15.441985130310059,
      "learning_rate": 0.0002,
      "loss": 1.4106,
      "step": 20
    },
    {
      "epoch": 0.24,
      "grad_norm": 13.51206111907959,
      "learning_rate": 0.0002,
      "loss": 1.1355,
      "step": 30
    },
    {
      "epoch": 0.32,
      "grad_norm": 14.920987129211426,
      "learning_rate": 0.0002,
      "loss": 0.9941,
      "step": 40
    },
    {
      "epoch": 0.41,
      "grad_norm": 8.289106369018555,
      "learning_rate": 0.0002,
      "loss": 0.8887,
      "step": 50
    },
    {
      "epoch": 0.49,
      "grad_norm": 8.003510475158691,
      "learning_rate": 0.0002,
      "loss": 0.8275,
      "step": 60
    },
    {
      "epoch": 0.57,
      "grad_norm": 7.877600193023682,
      "learning_rate": 0.0002,
      "loss": 0.798,
      "step": 70
    },
    {
      "epoch": 0.65,
      "grad_norm": 2.8833744525909424,
      "learning_rate": 0.0002,
      "loss": 0.8464,
      "step": 80
    },
    {
      "epoch": 0.73,
      "grad_norm": 8.206995964050293,
      "learning_rate": 0.0002,
      "loss": 0.7849,
      "step": 90
    },
    {
      "epoch": 0.81,
      "grad_norm": 7.678927421569824,
      "learning_rate": 0.0002,
      "loss": 0.7184,
      "step": 100
    },
    {
      "epoch": 0.89,
      "grad_norm": 7.089763164520264,
      "learning_rate": 0.0002,
      "loss": 0.7099,
      "step": 110
    },
    {
      "epoch": 0.97,
      "grad_norm": 5.643054485321045,
      "learning_rate": 0.0002,
      "loss": 0.6989,
      "step": 120
    },
    {
      "epoch": 1.05,
      "grad_norm": 7.985189914703369,
      "learning_rate": 0.0002,
      "loss": 0.6394,
      "step": 130
    },
    {
      "epoch": 1.14,
      "grad_norm": 7.676026344299316,
      "learning_rate": 0.0002,
      "loss": 0.5882,
      "step": 140
    },
    {
      "epoch": 1.22,
      "grad_norm": 8.714900016784668,
      "learning_rate": 0.0002,
      "loss": 0.5707,
      "step": 150
    },
    {
      "epoch": 1.3,
      "grad_norm": 5.221066474914551,
      "learning_rate": 0.0002,
      "loss": 0.5345,
      "step": 160
    },
    {
      "epoch": 1.38,
      "grad_norm": 9.008663177490234,
      "learning_rate": 0.0002,
      "loss": 0.5568,
      "step": 170
    },
    {
      "epoch": 1.46,
      "grad_norm": 6.81847620010376,
      "learning_rate": 0.0002,
      "loss": 0.5249,
      "step": 180
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.8458152413368225,
      "learning_rate": 0.0002,
      "loss": 0.491,
      "step": 190
    },
    {
      "epoch": 1.62,
      "grad_norm": 7.401742935180664,
      "learning_rate": 0.0002,
      "loss": 0.514,
      "step": 200
    },
    {
      "epoch": 1.7,
      "grad_norm": 7.641871452331543,
      "learning_rate": 0.0002,
      "loss": 0.5557,
      "step": 210
    },
    {
      "epoch": 1.78,
      "grad_norm": 5.442512512207031,
      "learning_rate": 0.0002,
      "loss": 0.5314,
      "step": 220
    },
    {
      "epoch": 1.87,
      "grad_norm": 8.104277610778809,
      "learning_rate": 0.0002,
      "loss": 0.4907,
      "step": 230
    },
    {
      "epoch": 1.95,
      "grad_norm": 6.416436195373535,
      "learning_rate": 0.0002,
      "loss": 0.5092,
      "step": 240
    },
    {
      "epoch": 2.03,
      "grad_norm": 3.008178949356079,
      "learning_rate": 0.0002,
      "loss": 0.4633,
      "step": 250
    },
    {
      "epoch": 2.11,
      "grad_norm": 9.349288940429688,
      "learning_rate": 0.0002,
      "loss": 0.378,
      "step": 260
    },
    {
      "epoch": 2.19,
      "grad_norm": 6.459526062011719,
      "learning_rate": 0.0002,
      "loss": 0.3765,
      "step": 270
    },
    {
      "epoch": 2.27,
      "grad_norm": 7.634103775024414,
      "learning_rate": 0.0002,
      "loss": 0.3819,
      "step": 280
    },
    {
      "epoch": 2.35,
      "grad_norm": 9.084547996520996,
      "learning_rate": 0.0002,
      "loss": 0.3703,
      "step": 290
    },
    {
      "epoch": 2.43,
      "grad_norm": 2.535707473754883,
      "learning_rate": 0.0002,
      "loss": 0.3501,
      "step": 300
    },
    {
      "epoch": 2.52,
      "grad_norm": 7.023160457611084,
      "learning_rate": 0.0002,
      "loss": 0.3491,
      "step": 310
    },
    {
      "epoch": 2.6,
      "grad_norm": 9.15241527557373,
      "learning_rate": 0.0002,
      "loss": 0.3592,
      "step": 320
    },
    {
      "epoch": 2.68,
      "grad_norm": 3.0726027488708496,
      "learning_rate": 0.0002,
      "loss": 0.3641,
      "step": 330
    },
    {
      "epoch": 2.76,
      "grad_norm": 5.8857879638671875,
      "learning_rate": 0.0002,
      "loss": 0.3553,
      "step": 340
    },
    {
      "epoch": 2.84,
      "grad_norm": 8.316734313964844,
      "learning_rate": 0.0002,
      "loss": 0.36,
      "step": 350
    },
    {
      "epoch": 2.92,
      "grad_norm": 3.8568618297576904,
      "learning_rate": 0.0002,
      "loss": 0.3607,
      "step": 360
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.664178848266602,
      "learning_rate": 0.0002,
      "loss": 0.3716,
      "step": 370
    },
    {
      "epoch": 3.08,
      "grad_norm": 9.07357406616211,
      "learning_rate": 0.0002,
      "loss": 0.242,
      "step": 380
    },
    {
      "epoch": 3.16,
      "grad_norm": 4.3498921394348145,
      "learning_rate": 0.0002,
      "loss": 0.2588,
      "step": 390
    },
    {
      "epoch": 3.25,
      "grad_norm": 6.539889812469482,
      "learning_rate": 0.0002,
      "loss": 0.2523,
      "step": 400
    },
    {
      "epoch": 3.33,
      "grad_norm": 8.80722427368164,
      "learning_rate": 0.0002,
      "loss": 0.2388,
      "step": 410
    },
    {
      "epoch": 3.41,
      "grad_norm": 5.052772521972656,
      "learning_rate": 0.0002,
      "loss": 0.2524,
      "step": 420
    },
    {
      "epoch": 3.49,
      "grad_norm": 5.22416877746582,
      "learning_rate": 0.0002,
      "loss": 0.2452,
      "step": 430
    },
    {
      "epoch": 3.57,
      "grad_norm": 8.989995956420898,
      "learning_rate": 0.0002,
      "loss": 0.2558,
      "step": 440
    },
    {
      "epoch": 3.65,
      "grad_norm": 2.628777027130127,
      "learning_rate": 0.0002,
      "loss": 0.2449,
      "step": 450
    },
    {
      "epoch": 3.73,
      "grad_norm": 5.890882968902588,
      "learning_rate": 0.0002,
      "loss": 0.2591,
      "step": 460
    },
    {
      "epoch": 3.81,
      "grad_norm": 8.577589988708496,
      "learning_rate": 0.0002,
      "loss": 0.2557,
      "step": 470
    },
    {
      "epoch": 3.89,
      "grad_norm": 5.092458724975586,
      "learning_rate": 0.0002,
      "loss": 0.2603,
      "step": 480
    },
    {
      "epoch": 3.98,
      "grad_norm": 5.97870397567749,
      "learning_rate": 0.0002,
      "loss": 0.2676,
      "step": 490
    },
    {
      "epoch": 4.06,
      "grad_norm": 8.259415626525879,
      "learning_rate": 0.0002,
      "loss": 0.2051,
      "step": 500
    },
    {
      "epoch": 4.14,
      "grad_norm": 7.2230072021484375,
      "learning_rate": 0.0002,
      "loss": 0.1467,
      "step": 510
    },
    {
      "epoch": 4.22,
      "grad_norm": 6.01918888092041,
      "learning_rate": 0.0002,
      "loss": 0.1713,
      "step": 520
    },
    {
      "epoch": 4.3,
      "grad_norm": 8.41965103149414,
      "learning_rate": 0.0002,
      "loss": 0.1803,
      "step": 530
    },
    {
      "epoch": 4.38,
      "grad_norm": 4.342984676361084,
      "learning_rate": 0.0002,
      "loss": 0.1769,
      "step": 540
    },
    {
      "epoch": 4.46,
      "grad_norm": 6.167740821838379,
      "learning_rate": 0.0002,
      "loss": 0.1763,
      "step": 550
    },
    {
      "epoch": 4.54,
      "grad_norm": 8.30461597442627,
      "learning_rate": 0.0002,
      "loss": 0.1716,
      "step": 560
    },
    {
      "epoch": 4.62,
      "grad_norm": 3.77854323387146,
      "learning_rate": 0.0002,
      "loss": 0.1679,
      "step": 570
    },
    {
      "epoch": 4.71,
      "grad_norm": 5.807821273803711,
      "learning_rate": 0.0002,
      "loss": 0.1775,
      "step": 580
    },
    {
      "epoch": 4.79,
      "grad_norm": 7.620412349700928,
      "learning_rate": 0.0002,
      "loss": 0.1769,
      "step": 590
    },
    {
      "epoch": 4.87,
      "grad_norm": 6.027496814727783,
      "learning_rate": 0.0002,
      "loss": 0.1828,
      "step": 600
    },
    {
      "epoch": 4.95,
      "grad_norm": 5.835544109344482,
      "learning_rate": 0.0002,
      "loss": 0.1783,
      "step": 610
    },
    {
      "epoch": 5.03,
      "grad_norm": 7.455280780792236,
      "learning_rate": 0.0002,
      "loss": 0.1545,
      "step": 620
    },
    {
      "epoch": 5.11,
      "grad_norm": 3.6531035900115967,
      "learning_rate": 0.0002,
      "loss": 0.1213,
      "step": 630
    },
    {
      "epoch": 5.19,
      "grad_norm": 6.005002498626709,
      "learning_rate": 0.0002,
      "loss": 0.1211,
      "step": 640
    },
    {
      "epoch": 5.27,
      "grad_norm": 8.0129976272583,
      "learning_rate": 0.0002,
      "loss": 0.1268,
      "step": 650
    },
    {
      "epoch": 5.35,
      "grad_norm": 4.5181169509887695,
      "learning_rate": 0.0002,
      "loss": 0.1215,
      "step": 660
    },
    {
      "epoch": 5.44,
      "grad_norm": 5.109263896942139,
      "learning_rate": 0.0002,
      "loss": 0.1264,
      "step": 670
    },
    {
      "epoch": 5.52,
      "grad_norm": 7.003955364227295,
      "learning_rate": 0.0002,
      "loss": 0.1332,
      "step": 680
    },
    {
      "epoch": 5.6,
      "grad_norm": 4.416803359985352,
      "learning_rate": 0.0002,
      "loss": 0.1333,
      "step": 690
    },
    {
      "epoch": 5.68,
      "grad_norm": 4.775448322296143,
      "learning_rate": 0.0002,
      "loss": 0.1384,
      "step": 700
    },
    {
      "epoch": 5.76,
      "grad_norm": 6.8711018562316895,
      "learning_rate": 0.0002,
      "loss": 0.1388,
      "step": 710
    },
    {
      "epoch": 5.84,
      "grad_norm": 4.3299760818481445,
      "learning_rate": 0.0002,
      "loss": 0.1392,
      "step": 720
    },
    {
      "epoch": 5.92,
      "grad_norm": 4.7512006759643555,
      "learning_rate": 0.0002,
      "loss": 0.1477,
      "step": 730
    },
    {
      "epoch": 6.0,
      "grad_norm": 6.701217174530029,
      "learning_rate": 0.0002,
      "loss": 0.1401,
      "step": 740
    },
    {
      "epoch": 6.09,
      "grad_norm": 4.163561820983887,
      "learning_rate": 0.0002,
      "loss": 0.099,
      "step": 750
    },
    {
      "epoch": 6.17,
      "grad_norm": 4.784251689910889,
      "learning_rate": 0.0002,
      "loss": 0.1025,
      "step": 760
    },
    {
      "epoch": 6.25,
      "grad_norm": 7.253482341766357,
      "learning_rate": 0.0002,
      "loss": 0.1019,
      "step": 770
    },
    {
      "epoch": 6.33,
      "grad_norm": 4.389810085296631,
      "learning_rate": 0.0002,
      "loss": 0.1052,
      "step": 780
    },
    {
      "epoch": 6.41,
      "grad_norm": 4.857180595397949,
      "learning_rate": 0.0002,
      "loss": 0.1065,
      "step": 790
    },
    {
      "epoch": 6.49,
      "grad_norm": 6.876203536987305,
      "learning_rate": 0.0002,
      "loss": 0.1092,
      "step": 800
    },
    {
      "epoch": 6.57,
      "grad_norm": 4.4614715576171875,
      "learning_rate": 0.0002,
      "loss": 0.112,
      "step": 810
    },
    {
      "epoch": 6.65,
      "grad_norm": 5.019026756286621,
      "learning_rate": 0.0002,
      "loss": 0.1127,
      "step": 820
    },
    {
      "epoch": 6.73,
      "grad_norm": 6.864689350128174,
      "learning_rate": 0.0002,
      "loss": 0.1131,
      "step": 830
    },
    {
      "epoch": 6.82,
      "grad_norm": 4.057292938232422,
      "learning_rate": 0.0002,
      "loss": 0.113,
      "step": 840
    },
    {
      "epoch": 6.9,
      "grad_norm": 4.780605792999268,
      "learning_rate": 0.0002,
      "loss": 0.1122,
      "step": 850
    },
    {
      "epoch": 6.98,
      "grad_norm": 6.377821445465088,
      "learning_rate": 0.0002,
      "loss": 0.1153,
      "step": 860
    },
    {
      "epoch": 7.06,
      "grad_norm": 3.6482489109039307,
      "learning_rate": 0.0002,
      "loss": 0.0962,
      "step": 870
    },
    {
      "epoch": 7.14,
      "grad_norm": 4.848484516143799,
      "learning_rate": 0.0002,
      "loss": 0.0892,
      "step": 880
    },
    {
      "epoch": 7.22,
      "grad_norm": 6.297725677490234,
      "learning_rate": 0.0002,
      "loss": 0.0913,
      "step": 890
    },
    {
      "epoch": 7.3,
      "grad_norm": 3.4698007106781006,
      "learning_rate": 0.0002,
      "loss": 0.0927,
      "step": 900
    },
    {
      "epoch": 7.38,
      "grad_norm": 4.614325523376465,
      "learning_rate": 0.0002,
      "loss": 0.0933,
      "step": 910
    },
    {
      "epoch": 7.46,
      "grad_norm": 6.8649163246154785,
      "learning_rate": 0.0002,
      "loss": 0.0951,
      "step": 920
    },
    {
      "epoch": 7.55,
      "grad_norm": 3.5742478370666504,
      "learning_rate": 0.0002,
      "loss": 0.0975,
      "step": 930
    },
    {
      "epoch": 7.63,
      "grad_norm": 4.66102409362793,
      "learning_rate": 0.0002,
      "loss": 0.0971,
      "step": 940
    },
    {
      "epoch": 7.71,
      "grad_norm": 6.615488052368164,
      "learning_rate": 0.0002,
      "loss": 0.0992,
      "step": 950
    },
    {
      "epoch": 7.79,
      "grad_norm": 4.218813419342041,
      "learning_rate": 0.0002,
      "loss": 0.1021,
      "step": 960
    },
    {
      "epoch": 7.87,
      "grad_norm": 4.6225905418396,
      "learning_rate": 0.0002,
      "loss": 0.1012,
      "step": 970
    },
    {
      "epoch": 7.95,
      "grad_norm": 6.005787372589111,
      "learning_rate": 0.0002,
      "loss": 0.1059,
      "step": 980
    },
    {
      "epoch": 8.03,
      "grad_norm": 3.2653019428253174,
      "learning_rate": 0.0002,
      "loss": 0.0929,
      "step": 990
    },
    {
      "epoch": 8.11,
      "grad_norm": 5.000682353973389,
      "learning_rate": 0.0002,
      "loss": 0.0787,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 10,
  "total_flos": 1.9346683868368896e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}