{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.903225806451613,
  "eval_steps": 30,
  "global_step": 360,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008064516129032258,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 2.8821,
      "num_input_tokens_seen": 2460,
      "step": 1,
      "train_runtime": 20.2008,
      "train_tokens_per_second": 121.777
    },
    {
      "epoch": 0.016129032258064516,
      "grad_norm": 2.2230546474456787,
      "learning_rate": 0.0,
      "loss": 2.8396,
      "num_input_tokens_seen": 4964,
      "step": 2,
      "train_runtime": 29.3232,
      "train_tokens_per_second": 169.286
    },
    {
      "epoch": 0.024193548387096774,
      "grad_norm": 2.2324392795562744,
      "learning_rate": 4e-05,
      "loss": 2.8582,
      "num_input_tokens_seen": 7402,
      "step": 3,
      "train_runtime": 37.5642,
      "train_tokens_per_second": 197.05
    },
    {
      "epoch": 0.03225806451612903,
      "grad_norm": 2.004035234451294,
      "learning_rate": 8e-05,
      "loss": 2.7738,
      "num_input_tokens_seen": 9844,
      "step": 4,
      "train_runtime": 45.3627,
      "train_tokens_per_second": 217.006
    },
    {
      "epoch": 0.04032258064516129,
      "grad_norm": 1.749263048171997,
      "learning_rate": 0.00012,
      "loss": 2.6939,
      "num_input_tokens_seen": 12411,
      "step": 5,
      "train_runtime": 53.1839,
      "train_tokens_per_second": 233.36
    },
    {
      "epoch": 0.04838709677419355,
      "grad_norm": 1.2987128496170044,
      "learning_rate": 0.00016,
      "loss": 2.4797,
      "num_input_tokens_seen": 14846,
      "step": 6,
      "train_runtime": 60.5056,
      "train_tokens_per_second": 245.366
    },
    {
      "epoch": 0.056451612903225805,
      "grad_norm": 1.2643777132034302,
      "learning_rate": 0.0002,
      "loss": 2.2646,
      "num_input_tokens_seen": 17165,
      "step": 7,
      "train_runtime": 67.4129,
      "train_tokens_per_second": 254.625
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 1.3214221000671387,
      "learning_rate": 0.00019999967645432384,
      "loss": 2.1451,
      "num_input_tokens_seen": 19599,
      "step": 8,
      "train_runtime": 74.7551,
      "train_tokens_per_second": 262.176
    },
    {
      "epoch": 0.07258064516129033,
      "grad_norm": 1.5586612224578857,
      "learning_rate": 0.00019999870581938894,
      "loss": 1.9267,
      "num_input_tokens_seen": 21933,
      "step": 9,
      "train_runtime": 81.9279,
      "train_tokens_per_second": 267.711
    },
    {
      "epoch": 0.08064516129032258,
      "grad_norm": 1.82594895362854,
      "learning_rate": 0.0001999970881014762,
      "loss": 1.7155,
      "num_input_tokens_seen": 24314,
      "step": 10,
      "train_runtime": 89.3509,
      "train_tokens_per_second": 272.118
    },
    {
      "epoch": 0.08870967741935484,
      "grad_norm": 1.8575149774551392,
      "learning_rate": 0.00019999482331105377,
      "loss": 1.4564,
      "num_input_tokens_seen": 26599,
      "step": 11,
      "train_runtime": 96.7349,
      "train_tokens_per_second": 274.968
    },
    {
      "epoch": 0.0967741935483871,
      "grad_norm": 1.5813839435577393,
      "learning_rate": 0.0001999919114627769,
      "loss": 1.4559,
      "num_input_tokens_seen": 29110,
      "step": 12,
      "train_runtime": 104.7926,
      "train_tokens_per_second": 277.787
    },
    {
      "epoch": 0.10483870967741936,
      "grad_norm": 1.6002471446990967,
      "learning_rate": 0.00019998835257548786,
      "loss": 1.1945,
      "num_input_tokens_seen": 31455,
      "step": 13,
      "train_runtime": 112.5233,
      "train_tokens_per_second": 279.542
    },
    {
      "epoch": 0.11290322580645161,
      "grad_norm": 1.4724524021148682,
      "learning_rate": 0.00019998414667221596,
      "loss": 1.1141,
      "num_input_tokens_seen": 33938,
      "step": 14,
      "train_runtime": 120.5539,
      "train_tokens_per_second": 281.517
    },
    {
      "epoch": 0.12096774193548387,
      "grad_norm": 1.295906662940979,
      "learning_rate": 0.00019997929378017725,
      "loss": 0.9111,
      "num_input_tokens_seen": 36328,
      "step": 15,
      "train_runtime": 128.1664,
      "train_tokens_per_second": 283.444
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 1.1280094385147095,
      "learning_rate": 0.00019997379393077428,
      "loss": 0.8585,
      "num_input_tokens_seen": 38720,
      "step": 16,
      "train_runtime": 135.6984,
      "train_tokens_per_second": 285.339
    },
    {
      "epoch": 0.13709677419354838,
      "grad_norm": 1.0555989742279053,
      "learning_rate": 0.00019996764715959618,
      "loss": 0.8459,
      "num_input_tokens_seen": 41264,
      "step": 17,
      "train_runtime": 143.6519,
      "train_tokens_per_second": 287.25
    },
    {
      "epoch": 0.14516129032258066,
      "grad_norm": 0.980623722076416,
      "learning_rate": 0.0001999608535064182,
      "loss": 0.7354,
      "num_input_tokens_seen": 43719,
      "step": 18,
      "train_runtime": 151.2792,
      "train_tokens_per_second": 288.995
    },
    {
      "epoch": 0.1532258064516129,
      "grad_norm": 0.9247991442680359,
      "learning_rate": 0.0001999534130152014,
      "loss": 0.6762,
      "num_input_tokens_seen": 46087,
      "step": 19,
      "train_runtime": 158.66,
      "train_tokens_per_second": 290.476
    },
    {
      "epoch": 0.16129032258064516,
      "grad_norm": 29.37914276123047,
      "learning_rate": 0.00019994532573409262,
      "loss": 0.7271,
      "num_input_tokens_seen": 48529,
      "step": 20,
      "train_runtime": 166.2671,
      "train_tokens_per_second": 291.874
    },
    {
      "epoch": 0.1693548387096774,
      "grad_norm": 0.9571717977523804,
      "learning_rate": 0.0001999365917154239,
      "loss": 0.5222,
      "num_input_tokens_seen": 50785,
      "step": 21,
      "train_runtime": 173.3922,
      "train_tokens_per_second": 292.891
    },
    {
      "epoch": 0.1774193548387097,
      "grad_norm": 0.5547913908958435,
      "learning_rate": 0.00019992721101571236,
      "loss": 0.5921,
      "num_input_tokens_seen": 53131,
      "step": 22,
      "train_runtime": 180.821,
      "train_tokens_per_second": 293.832
    },
    {
      "epoch": 0.18548387096774194,
      "grad_norm": 0.5877758264541626,
      "learning_rate": 0.0001999171836956597,
      "loss": 0.6327,
      "num_input_tokens_seen": 55531,
      "step": 23,
      "train_runtime": 188.3614,
      "train_tokens_per_second": 294.811
    },
    {
      "epoch": 0.1935483870967742,
      "grad_norm": 0.5965892672538757,
      "learning_rate": 0.0001999065098201518,
      "loss": 0.7097,
      "num_input_tokens_seen": 58012,
      "step": 24,
      "train_runtime": 196.1428,
      "train_tokens_per_second": 295.764
    },
    {
      "epoch": 0.20161290322580644,
      "grad_norm": 0.47157740592956543,
      "learning_rate": 0.00019989518945825844,
      "loss": 0.5306,
      "num_input_tokens_seen": 60347,
      "step": 25,
      "train_runtime": 203.5991,
      "train_tokens_per_second": 296.401
    },
    {
      "epoch": 0.20967741935483872,
      "grad_norm": 0.5811465382575989,
      "learning_rate": 0.00019988322268323268,
      "loss": 0.637,
      "num_input_tokens_seen": 62789,
      "step": 26,
      "train_runtime": 211.3235,
      "train_tokens_per_second": 297.123
    },
    {
      "epoch": 0.21774193548387097,
      "grad_norm": 0.5013178586959839,
      "learning_rate": 0.00019987060957251047,
      "loss": 0.6434,
      "num_input_tokens_seen": 65259,
      "step": 27,
      "train_runtime": 219.162,
      "train_tokens_per_second": 297.766
    },
    {
      "epoch": 0.22580645161290322,
      "grad_norm": 0.4896971583366394,
      "learning_rate": 0.00019985735020771017,
      "loss": 0.6165,
      "num_input_tokens_seen": 67627,
      "step": 28,
      "train_runtime": 226.7103,
      "train_tokens_per_second": 298.297
    },
    {
      "epoch": 0.23387096774193547,
      "grad_norm": 0.5190575122833252,
      "learning_rate": 0.00019984344467463197,
      "loss": 0.683,
      "num_input_tokens_seen": 70097,
      "step": 29,
      "train_runtime": 234.4542,
      "train_tokens_per_second": 298.979
    },
    {
      "epoch": 0.24193548387096775,
      "grad_norm": 0.485100656747818,
      "learning_rate": 0.0001998288930632574,
      "loss": 0.7283,
      "num_input_tokens_seen": 72599,
      "step": 30,
      "train_runtime": 242.2724,
      "train_tokens_per_second": 299.659
    },
    {
      "epoch": 0.24193548387096775,
      "eval_loss": 0.6429173946380615,
      "eval_runtime": 20.6444,
      "eval_samples_per_second": 2.519,
      "eval_steps_per_second": 1.259,
      "num_input_tokens_seen": 72599,
      "step": 30
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.42926788330078125,
      "learning_rate": 0.00019981369546774865,
      "loss": 0.5616,
      "num_input_tokens_seen": 74963,
      "step": 31,
      "train_runtime": 270.939,
      "train_tokens_per_second": 276.678
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 0.4984983503818512,
      "learning_rate": 0.00019979785198644806,
      "loss": 0.6284,
      "num_input_tokens_seen": 77373,
      "step": 32,
      "train_runtime": 278.5531,
      "train_tokens_per_second": 277.768
    },
    {
      "epoch": 0.2661290322580645,
      "grad_norm": 0.47428232431411743,
      "learning_rate": 0.00019978136272187747,
      "loss": 0.6354,
      "num_input_tokens_seen": 79803,
      "step": 33,
      "train_runtime": 286.3198,
      "train_tokens_per_second": 278.72
    },
    {
      "epoch": 0.27419354838709675,
      "grad_norm": 0.5008767247200012,
      "learning_rate": 0.0001997642277807374,
      "loss": 0.6537,
      "num_input_tokens_seen": 82278,
      "step": 34,
      "train_runtime": 294.1164,
      "train_tokens_per_second": 279.746
    },
    {
      "epoch": 0.28225806451612906,
      "grad_norm": 0.42406603693962097,
      "learning_rate": 0.00019974644727390665,
      "loss": 0.5861,
      "num_input_tokens_seen": 84716,
      "step": 35,
      "train_runtime": 301.7918,
      "train_tokens_per_second": 280.71
    },
    {
      "epoch": 0.2903225806451613,
      "grad_norm": 0.4029514491558075,
      "learning_rate": 0.00019972802131644127,
      "loss": 0.5435,
      "num_input_tokens_seen": 87042,
      "step": 36,
      "train_runtime": 309.1953,
      "train_tokens_per_second": 281.511
    },
    {
      "epoch": 0.29838709677419356,
      "grad_norm": 0.3857174217700958,
      "learning_rate": 0.00019970895002757413,
      "loss": 0.4691,
      "num_input_tokens_seen": 89337,
      "step": 37,
      "train_runtime": 316.4937,
      "train_tokens_per_second": 282.271
    },
    {
      "epoch": 0.3064516129032258,
      "grad_norm": 0.5377873182296753,
      "learning_rate": 0.00019968923353071377,
      "loss": 0.6391,
      "num_input_tokens_seen": 91831,
      "step": 38,
      "train_runtime": 324.2416,
      "train_tokens_per_second": 283.218
    },
    {
      "epoch": 0.31451612903225806,
      "grad_norm": 0.4515826404094696,
      "learning_rate": 0.00019966887195344403,
      "loss": 0.5323,
      "num_input_tokens_seen": 94226,
      "step": 39,
      "train_runtime": 331.748,
      "train_tokens_per_second": 284.029
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 0.3910655677318573,
      "learning_rate": 0.0001996478654275229,
      "loss": 0.5125,
      "num_input_tokens_seen": 96510,
      "step": 40,
      "train_runtime": 338.8924,
      "train_tokens_per_second": 284.781
    },
    {
      "epoch": 0.33064516129032256,
      "grad_norm": 0.5480923056602478,
      "learning_rate": 0.00019962621408888177,
      "loss": 0.6256,
      "num_input_tokens_seen": 98963,
      "step": 41,
      "train_runtime": 346.5461,
      "train_tokens_per_second": 285.57
    },
    {
      "epoch": 0.3387096774193548,
      "grad_norm": 0.4644400477409363,
      "learning_rate": 0.00019960391807762463,
      "loss": 0.6775,
      "num_input_tokens_seen": 101522,
      "step": 42,
      "train_runtime": 354.466,
      "train_tokens_per_second": 286.408
    },
    {
      "epoch": 0.3467741935483871,
      "grad_norm": 0.45509329438209534,
      "learning_rate": 0.00019958097753802693,
      "loss": 0.5968,
      "num_input_tokens_seen": 103938,
      "step": 43,
      "train_runtime": 361.9713,
      "train_tokens_per_second": 287.144
    },
    {
      "epoch": 0.3548387096774194,
      "grad_norm": 0.5333311557769775,
      "learning_rate": 0.00019955739261853504,
      "loss": 0.6604,
      "num_input_tokens_seen": 106416,
      "step": 44,
      "train_runtime": 369.6866,
      "train_tokens_per_second": 287.855
    },
    {
      "epoch": 0.3629032258064516,
      "grad_norm": 0.421058714389801,
      "learning_rate": 0.00019953316347176488,
      "loss": 0.4962,
      "num_input_tokens_seen": 108748,
      "step": 45,
      "train_runtime": 377.0273,
      "train_tokens_per_second": 288.435
    },
    {
      "epoch": 0.3709677419354839,
      "grad_norm": 0.4439956843852997,
      "learning_rate": 0.00019950829025450114,
      "loss": 0.5743,
      "num_input_tokens_seen": 111155,
      "step": 46,
      "train_runtime": 384.5601,
      "train_tokens_per_second": 289.045
    },
    {
      "epoch": 0.3790322580645161,
      "grad_norm": 0.5222911834716797,
      "learning_rate": 0.0001994827731276963,
      "loss": 0.5686,
      "num_input_tokens_seen": 113593,
      "step": 47,
      "train_runtime": 392.1126,
      "train_tokens_per_second": 289.695
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": 0.4172716736793518,
      "learning_rate": 0.00019945661225646946,
      "loss": 0.5262,
      "num_input_tokens_seen": 115968,
      "step": 48,
      "train_runtime": 399.5667,
      "train_tokens_per_second": 290.234
    },
    {
      "epoch": 0.3951612903225806,
      "grad_norm": 0.43297383189201355,
      "learning_rate": 0.0001994298078101054,
      "loss": 0.6139,
      "num_input_tokens_seen": 118476,
      "step": 49,
      "train_runtime": 407.3814,
      "train_tokens_per_second": 290.823
    },
    {
      "epoch": 0.4032258064516129,
      "grad_norm": 0.49559882283210754,
      "learning_rate": 0.00019940235996205333,
      "loss": 0.6726,
      "num_input_tokens_seen": 120946,
      "step": 50,
      "train_runtime": 415.0753,
      "train_tokens_per_second": 291.383
    },
    {
      "epoch": 0.4112903225806452,
      "grad_norm": 0.4947301149368286,
      "learning_rate": 0.0001993742688899259,
      "loss": 0.5937,
      "num_input_tokens_seen": 123371,
      "step": 51,
      "train_runtime": 422.6813,
      "train_tokens_per_second": 291.877
    },
    {
      "epoch": 0.41935483870967744,
      "grad_norm": 0.38399311900138855,
      "learning_rate": 0.00019934553477549794,
      "loss": 0.5638,
      "num_input_tokens_seen": 125783,
      "step": 52,
      "train_runtime": 430.2413,
      "train_tokens_per_second": 292.355
    },
    {
      "epoch": 0.4274193548387097,
      "grad_norm": 0.5241729617118835,
      "learning_rate": 0.00019931615780470558,
      "loss": 0.591,
      "num_input_tokens_seen": 128227,
      "step": 53,
      "train_runtime": 437.9384,
      "train_tokens_per_second": 292.797
    },
    {
      "epoch": 0.43548387096774194,
      "grad_norm": 0.5647182464599609,
      "learning_rate": 0.00019928613816764458,
      "loss": 0.5098,
      "num_input_tokens_seen": 130614,
      "step": 54,
      "train_runtime": 445.5243,
      "train_tokens_per_second": 293.169
    },
    {
      "epoch": 0.4435483870967742,
      "grad_norm": 0.5013054013252258,
      "learning_rate": 0.00019925547605856934,
      "loss": 0.6388,
      "num_input_tokens_seen": 133047,
      "step": 55,
      "train_runtime": 453.1951,
      "train_tokens_per_second": 293.576
    },
    {
      "epoch": 0.45161290322580644,
      "grad_norm": 0.5751994848251343,
      "learning_rate": 0.00019922417167589183,
      "loss": 0.5489,
      "num_input_tokens_seen": 135442,
      "step": 56,
      "train_runtime": 460.7707,
      "train_tokens_per_second": 293.947
    },
    {
      "epoch": 0.4596774193548387,
      "grad_norm": 0.5764442086219788,
      "learning_rate": 0.00019919222522217996,
      "loss": 0.6618,
      "num_input_tokens_seen": 137936,
      "step": 57,
      "train_runtime": 468.5965,
      "train_tokens_per_second": 294.36
    },
    {
      "epoch": 0.46774193548387094,
      "grad_norm": 0.48759251832962036,
      "learning_rate": 0.00019915963690415647,
      "loss": 0.5633,
      "num_input_tokens_seen": 140352,
      "step": 58,
      "train_runtime": 476.2388,
      "train_tokens_per_second": 294.709
    },
    {
      "epoch": 0.47580645161290325,
      "grad_norm": 1.1273839473724365,
      "learning_rate": 0.00019912640693269752,
      "loss": 0.557,
      "num_input_tokens_seen": 142729,
      "step": 59,
      "train_runtime": 483.8414,
      "train_tokens_per_second": 294.991
    },
    {
      "epoch": 0.4838709677419355,
      "grad_norm": 0.43796879053115845,
      "learning_rate": 0.00019909253552283143,
      "loss": 0.5718,
      "num_input_tokens_seen": 145195,
      "step": 60,
      "train_runtime": 491.5972,
      "train_tokens_per_second": 295.354
    },
    {
      "epoch": 0.4838709677419355,
      "eval_loss": 0.588404655456543,
      "eval_runtime": 17.1502,
      "eval_samples_per_second": 3.032,
      "eval_steps_per_second": 1.516,
      "num_input_tokens_seen": 145195,
      "step": 60
    },
    {
      "epoch": 0.49193548387096775,
      "grad_norm": 0.41540732979774475,
      "learning_rate": 0.00019905802289373715,
      "loss": 0.5533,
      "num_input_tokens_seen": 147570,
      "step": 61,
      "train_runtime": 516.8658,
      "train_tokens_per_second": 285.509
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.4697861075401306,
      "learning_rate": 0.0001990228692687429,
      "loss": 0.659,
      "num_input_tokens_seen": 150082,
      "step": 62,
      "train_runtime": 524.7607,
      "train_tokens_per_second": 286.001
    },
    {
      "epoch": 0.5080645161290323,
      "grad_norm": 0.4594587981700897,
      "learning_rate": 0.00019898707487532474,
      "loss": 0.5754,
      "num_input_tokens_seen": 152502,
      "step": 63,
      "train_runtime": 532.3943,
      "train_tokens_per_second": 286.446
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 0.45399630069732666,
      "learning_rate": 0.0001989506399451051,
      "loss": 0.5575,
      "num_input_tokens_seen": 154888,
      "step": 64,
      "train_runtime": 539.9509,
      "train_tokens_per_second": 286.856
    },
    {
      "epoch": 0.5241935483870968,
      "grad_norm": 0.4408513307571411,
      "learning_rate": 0.0001989135647138513,
      "loss": 0.578,
      "num_input_tokens_seen": 157296,
      "step": 65,
      "train_runtime": 547.6373,
      "train_tokens_per_second": 287.227
    },
    {
      "epoch": 0.532258064516129,
      "grad_norm": 0.5508686304092407,
      "learning_rate": 0.00019887584942147394,
      "loss": 0.5551,
      "num_input_tokens_seen": 159619,
      "step": 66,
      "train_runtime": 555.0465,
      "train_tokens_per_second": 287.578
    },
    {
      "epoch": 0.5403225806451613,
      "grad_norm": 0.4901481568813324,
      "learning_rate": 0.0001988374943120254,
      "loss": 0.6144,
      "num_input_tokens_seen": 162016,
      "step": 67,
      "train_runtime": 562.5856,
      "train_tokens_per_second": 287.985
    },
    {
      "epoch": 0.5483870967741935,
      "grad_norm": 0.6244992017745972,
      "learning_rate": 0.00019879849963369827,
      "loss": 0.657,
      "num_input_tokens_seen": 164573,
      "step": 68,
      "train_runtime": 570.5194,
      "train_tokens_per_second": 288.462
    },
    {
      "epoch": 0.5564516129032258,
      "grad_norm": 0.4478534162044525,
      "learning_rate": 0.00019875886563882375,
      "loss": 0.5517,
      "num_input_tokens_seen": 167048,
      "step": 69,
      "train_runtime": 578.2943,
      "train_tokens_per_second": 288.863
    },
    {
      "epoch": 0.5645161290322581,
      "grad_norm": 0.6100202202796936,
      "learning_rate": 0.00019871859258387,
      "loss": 0.619,
      "num_input_tokens_seen": 169510,
      "step": 70,
      "train_runtime": 586.0262,
      "train_tokens_per_second": 289.253
    },
    {
      "epoch": 0.5725806451612904,
      "grad_norm": 0.4547867178916931,
      "learning_rate": 0.00019867768072944045,
      "loss": 0.5046,
      "num_input_tokens_seen": 171885,
      "step": 71,
      "train_runtime": 593.5521,
      "train_tokens_per_second": 289.587
    },
    {
      "epoch": 0.5806451612903226,
      "grad_norm": 0.43076831102371216,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.6065,
      "num_input_tokens_seen": 174375,
      "step": 72,
      "train_runtime": 601.3642,
      "train_tokens_per_second": 289.966
    },
    {
      "epoch": 0.5887096774193549,
      "grad_norm": 0.45889994502067566,
      "learning_rate": 0.0001985939416852343,
      "loss": 0.5827,
      "num_input_tokens_seen": 176790,
      "step": 73,
      "train_runtime": 608.9783,
      "train_tokens_per_second": 290.306
    },
    {
      "epoch": 0.5967741935483871,
      "grad_norm": 0.5129091143608093,
      "learning_rate": 0.00019855111503732574,
      "loss": 0.4935,
      "num_input_tokens_seen": 179140,
      "step": 74,
      "train_runtime": 616.4507,
      "train_tokens_per_second": 290.599
    },
    {
      "epoch": 0.6048387096774194,
      "grad_norm": 0.4756077527999878,
      "learning_rate": 0.00019850765067367412,
      "loss": 0.4864,
      "num_input_tokens_seen": 181433,
      "step": 75,
      "train_runtime": 623.788,
      "train_tokens_per_second": 290.857
    },
    {
      "epoch": 0.6129032258064516,
      "grad_norm": 0.5090617537498474,
      "learning_rate": 0.00019846354887553358,
      "loss": 0.5477,
      "num_input_tokens_seen": 183817,
      "step": 76,
      "train_runtime": 631.336,
      "train_tokens_per_second": 291.156
    },
    {
      "epoch": 0.6209677419354839,
      "grad_norm": 0.4573401212692261,
      "learning_rate": 0.00019841880992828306,
      "loss": 0.5305,
      "num_input_tokens_seen": 186158,
      "step": 77,
      "train_runtime": 638.7889,
      "train_tokens_per_second": 291.423
    },
    {
      "epoch": 0.6290322580645161,
      "grad_norm": 0.43317022919654846,
      "learning_rate": 0.0001983734341214244,
      "loss": 0.4796,
      "num_input_tokens_seen": 188490,
      "step": 78,
      "train_runtime": 646.2095,
      "train_tokens_per_second": 291.686
    },
    {
      "epoch": 0.6370967741935484,
      "grad_norm": 0.5083560943603516,
      "learning_rate": 0.00019832742174858052,
      "loss": 0.5368,
      "num_input_tokens_seen": 190868,
      "step": 79,
      "train_runtime": 653.7184,
      "train_tokens_per_second": 291.973
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 0.5274792313575745,
      "learning_rate": 0.0001982807731074935,
      "loss": 0.6258,
      "num_input_tokens_seen": 193343,
      "step": 80,
      "train_runtime": 661.5295,
      "train_tokens_per_second": 292.267
    },
    {
      "epoch": 0.6532258064516129,
      "grad_norm": 0.46456336975097656,
      "learning_rate": 0.00019823348850002268,
      "loss": 0.5115,
      "num_input_tokens_seen": 195723,
      "step": 81,
      "train_runtime": 669.1413,
      "train_tokens_per_second": 292.499
    },
    {
      "epoch": 0.6612903225806451,
      "grad_norm": 0.4614492356777191,
      "learning_rate": 0.00019818556823214268,
      "loss": 0.5547,
      "num_input_tokens_seen": 198142,
      "step": 82,
      "train_runtime": 676.7932,
      "train_tokens_per_second": 292.766
    },
    {
      "epoch": 0.6693548387096774,
      "grad_norm": 0.431631863117218,
      "learning_rate": 0.00019813701261394136,
      "loss": 0.5297,
      "num_input_tokens_seen": 200459,
      "step": 83,
      "train_runtime": 684.2475,
      "train_tokens_per_second": 292.963
    },
    {
      "epoch": 0.6774193548387096,
      "grad_norm": 0.5262055397033691,
      "learning_rate": 0.00019808782195961797,
      "loss": 0.6186,
      "num_input_tokens_seen": 202979,
      "step": 84,
      "train_runtime": 692.1971,
      "train_tokens_per_second": 293.239
    },
    {
      "epoch": 0.6854838709677419,
      "grad_norm": 0.4315405786037445,
      "learning_rate": 0.00019803799658748094,
      "loss": 0.5863,
      "num_input_tokens_seen": 205408,
      "step": 85,
      "train_runtime": 699.9238,
      "train_tokens_per_second": 293.472
    },
    {
      "epoch": 0.6935483870967742,
      "grad_norm": 0.5156344771385193,
      "learning_rate": 0.000197987536819946,
      "loss": 0.6342,
      "num_input_tokens_seen": 207851,
      "step": 86,
      "train_runtime": 707.6972,
      "train_tokens_per_second": 293.7
    },
    {
      "epoch": 0.7016129032258065,
      "grad_norm": 0.610248327255249,
      "learning_rate": 0.0001979364429835339,
      "loss": 0.5762,
      "num_input_tokens_seen": 210293,
      "step": 87,
      "train_runtime": 715.4358,
      "train_tokens_per_second": 293.937
    },
    {
      "epoch": 0.7096774193548387,
      "grad_norm": 0.4106084704399109,
      "learning_rate": 0.00019788471540886844,
      "loss": 0.5651,
      "num_input_tokens_seen": 212741,
      "step": 88,
      "train_runtime": 723.1383,
      "train_tokens_per_second": 294.191
    },
    {
      "epoch": 0.717741935483871,
      "grad_norm": 0.4682006239891052,
      "learning_rate": 0.0001978323544306743,
      "loss": 0.5914,
      "num_input_tokens_seen": 215252,
      "step": 89,
      "train_runtime": 731.0074,
      "train_tokens_per_second": 294.459
    },
    {
      "epoch": 0.7258064516129032,
      "grad_norm": 0.39659127593040466,
      "learning_rate": 0.00019777936038777483,
      "loss": 0.4184,
      "num_input_tokens_seen": 217500,
      "step": 90,
      "train_runtime": 738.2319,
      "train_tokens_per_second": 294.623
    },
    {
      "epoch": 0.7258064516129032,
      "eval_loss": 0.5797551870346069,
      "eval_runtime": 17.1625,
      "eval_samples_per_second": 3.03,
      "eval_steps_per_second": 1.515,
      "num_input_tokens_seen": 217500,
      "step": 90
    },
    {
      "epoch": 0.7338709677419355,
      "grad_norm": 0.4853302538394928,
      "learning_rate": 0.0001977257336230899,
      "loss": 0.5532,
      "num_input_tokens_seen": 219939,
      "step": 91,
      "train_runtime": 763.6262,
      "train_tokens_per_second": 288.019
    },
    {
      "epoch": 0.7419354838709677,
      "grad_norm": 0.42730966210365295,
      "learning_rate": 0.00019767147448363366,
      "loss": 0.41,
      "num_input_tokens_seen": 222184,
      "step": 92,
      "train_runtime": 770.8107,
      "train_tokens_per_second": 288.247
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.5217856764793396,
      "learning_rate": 0.00019761658332051235,
      "loss": 0.5564,
      "num_input_tokens_seen": 224608,
      "step": 93,
      "train_runtime": 778.427,
      "train_tokens_per_second": 288.541
    },
    {
      "epoch": 0.7580645161290323,
      "grad_norm": 0.6025580167770386,
      "learning_rate": 0.00019756106048892186,
      "loss": 0.5735,
      "num_input_tokens_seen": 227024,
      "step": 94,
      "train_runtime": 786.0237,
      "train_tokens_per_second": 288.826
    },
    {
      "epoch": 0.7661290322580645,
      "grad_norm": 0.47863927483558655,
      "learning_rate": 0.00019750490634814572,
      "loss": 0.6207,
      "num_input_tokens_seen": 229482,
      "step": 95,
      "train_runtime": 793.6569,
      "train_tokens_per_second": 289.145
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 0.6842419505119324,
      "learning_rate": 0.00019744812126155245,
      "loss": 0.5606,
      "num_input_tokens_seen": 231915,
      "step": 96,
      "train_runtime": 801.2741,
      "train_tokens_per_second": 289.433
    },
    {
      "epoch": 0.782258064516129,
      "grad_norm": 0.4753873348236084,
      "learning_rate": 0.00019739070559659347,
      "loss": 0.5656,
      "num_input_tokens_seen": 234337,
      "step": 97,
      "train_runtime": 808.959,
      "train_tokens_per_second": 289.677
    },
    {
      "epoch": 0.7903225806451613,
      "grad_norm": 0.4512401521205902,
      "learning_rate": 0.0001973326597248006,
      "loss": 0.54,
      "num_input_tokens_seen": 236729,
      "step": 98,
      "train_runtime": 816.542,
      "train_tokens_per_second": 289.916
    },
    {
      "epoch": 0.7983870967741935,
      "grad_norm": 0.41799741983413696,
      "learning_rate": 0.0001972739840217836,
      "loss": 0.504,
      "num_input_tokens_seen": 239095,
      "step": 99,
      "train_runtime": 824.0737,
      "train_tokens_per_second": 290.138
    },
    {
      "epoch": 0.8064516129032258,
      "grad_norm": 0.5296741724014282,
      "learning_rate": 0.00019721467886722792,
      "loss": 0.5715,
      "num_input_tokens_seen": 241541,
      "step": 100,
      "train_runtime": 831.8131,
      "train_tokens_per_second": 290.379
    },
    {
      "epoch": 0.8145161290322581,
      "grad_norm": 0.5183069705963135,
      "learning_rate": 0.00019715474464489208,
      "loss": 0.583,
      "num_input_tokens_seen": 244053,
      "step": 101,
      "train_runtime": 839.7441,
      "train_tokens_per_second": 290.628
    },
    {
      "epoch": 0.8225806451612904,
      "grad_norm": 0.5080683827400208,
      "learning_rate": 0.0001970941817426052,
      "loss": 0.6712,
      "num_input_tokens_seen": 246631,
      "step": 102,
      "train_runtime": 847.7725,
      "train_tokens_per_second": 290.916
    },
    {
      "epoch": 0.8306451612903226,
      "grad_norm": 0.47352856397628784,
      "learning_rate": 0.00019703299055226468,
      "loss": 0.5361,
      "num_input_tokens_seen": 249081,
      "step": 103,
      "train_runtime": 855.5397,
      "train_tokens_per_second": 291.139
    },
    {
      "epoch": 0.8387096774193549,
      "grad_norm": 0.4344908893108368,
      "learning_rate": 0.00019697117146983334,
      "loss": 0.3872,
      "num_input_tokens_seen": 251298,
      "step": 104,
      "train_runtime": 862.6163,
      "train_tokens_per_second": 291.321
    },
    {
      "epoch": 0.8467741935483871,
      "grad_norm": 0.6570983529090881,
      "learning_rate": 0.0001969087248953371,
      "loss": 0.5698,
      "num_input_tokens_seen": 253742,
      "step": 105,
      "train_runtime": 870.3871,
      "train_tokens_per_second": 291.528
    },
    {
      "epoch": 0.8548387096774194,
      "grad_norm": 0.46201083064079285,
      "learning_rate": 0.00019684565123286244,
      "loss": 0.567,
      "num_input_tokens_seen": 256212,
      "step": 106,
      "train_runtime": 878.1695,
      "train_tokens_per_second": 291.757
    },
    {
      "epoch": 0.8629032258064516,
      "grad_norm": 0.48119398951530457,
      "learning_rate": 0.00019678195089055346,
      "loss": 0.5579,
      "num_input_tokens_seen": 258577,
      "step": 107,
      "train_runtime": 885.714,
      "train_tokens_per_second": 291.942
    },
    {
      "epoch": 0.8709677419354839,
      "grad_norm": 0.5357433557510376,
      "learning_rate": 0.00019671762428060966,
      "loss": 0.6103,
      "num_input_tokens_seen": 261064,
      "step": 108,
      "train_runtime": 893.5704,
      "train_tokens_per_second": 292.158
    },
    {
      "epoch": 0.8790322580645161,
      "grad_norm": 0.44740840792655945,
      "learning_rate": 0.00019665267181928292,
      "loss": 0.5168,
      "num_input_tokens_seen": 263473,
      "step": 109,
      "train_runtime": 901.2705,
      "train_tokens_per_second": 292.335
    },
    {
      "epoch": 0.8870967741935484,
      "grad_norm": 0.470734566450119,
      "learning_rate": 0.00019658709392687506,
      "loss": 0.6253,
      "num_input_tokens_seen": 265968,
      "step": 110,
      "train_runtime": 909.1802,
      "train_tokens_per_second": 292.536
    },
    {
      "epoch": 0.8951612903225806,
      "grad_norm": 0.561008870601654,
      "learning_rate": 0.00019652089102773488,
      "loss": 0.5867,
      "num_input_tokens_seen": 268347,
      "step": 111,
      "train_runtime": 916.7609,
      "train_tokens_per_second": 292.712
    },
    {
      "epoch": 0.9032258064516129,
      "grad_norm": 0.42769816517829895,
      "learning_rate": 0.00019645406355025565,
      "loss": 0.4869,
      "num_input_tokens_seen": 270668,
      "step": 112,
      "train_runtime": 924.116,
      "train_tokens_per_second": 292.894
    },
    {
      "epoch": 0.9112903225806451,
      "grad_norm": 0.4861026108264923,
      "learning_rate": 0.00019638661192687216,
      "loss": 0.5352,
      "num_input_tokens_seen": 273106,
      "step": 113,
      "train_runtime": 931.8203,
      "train_tokens_per_second": 293.089
    },
    {
      "epoch": 0.9193548387096774,
      "grad_norm": 0.47908815741539,
      "learning_rate": 0.00019631853659405807,
      "loss": 0.5608,
      "num_input_tokens_seen": 275567,
      "step": 114,
      "train_runtime": 939.5584,
      "train_tokens_per_second": 293.294
    },
    {
      "epoch": 0.9274193548387096,
      "grad_norm": 0.5197163820266724,
      "learning_rate": 0.000196249837992323,
      "loss": 0.6687,
      "num_input_tokens_seen": 278145,
      "step": 115,
      "train_runtime": 947.5681,
      "train_tokens_per_second": 293.536
    },
    {
      "epoch": 0.9354838709677419,
      "grad_norm": 0.4960262179374695,
      "learning_rate": 0.0001961805165662096,
      "loss": 0.5896,
      "num_input_tokens_seen": 280661,
      "step": 116,
      "train_runtime": 955.4052,
      "train_tokens_per_second": 293.761
    },
    {
      "epoch": 0.9435483870967742,
      "grad_norm": 0.4456697702407837,
      "learning_rate": 0.00019611057276429085,
      "loss": 0.4862,
      "num_input_tokens_seen": 283075,
      "step": 117,
      "train_runtime": 962.9938,
      "train_tokens_per_second": 293.953
    },
    {
      "epoch": 0.9516129032258065,
      "grad_norm": 0.4729059338569641,
      "learning_rate": 0.00019604000703916705,
      "loss": 0.5744,
      "num_input_tokens_seen": 285541,
      "step": 118,
      "train_runtime": 970.7902,
      "train_tokens_per_second": 294.133
    },
    {
      "epoch": 0.9596774193548387,
      "grad_norm": 0.47211745381355286,
      "learning_rate": 0.00019596881984746287,
      "loss": 0.512,
      "num_input_tokens_seen": 287946,
      "step": 119,
      "train_runtime": 978.3472,
      "train_tokens_per_second": 294.319
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 0.44912973046302795,
      "learning_rate": 0.00019589701164982452,
      "loss": 0.4114,
      "num_input_tokens_seen": 290184,
      "step": 120,
      "train_runtime": 985.5069,
      "train_tokens_per_second": 294.452
    },
    {
      "epoch": 0.967741935483871,
      "eval_loss": 0.5635989904403687,
      "eval_runtime": 17.033,
      "eval_samples_per_second": 3.053,
      "eval_steps_per_second": 1.526,
      "num_input_tokens_seen": 290184,
      "step": 120
    },
    {
      "epoch": 0.9758064516129032,
      "grad_norm": 0.43237707018852234,
      "learning_rate": 0.00019582458291091663,
      "loss": 0.4564,
      "num_input_tokens_seen": 292471,
      "step": 121,
      "train_runtime": 1010.3192,
      "train_tokens_per_second": 289.484
    },
    {
      "epoch": 0.9838709677419355,
      "grad_norm": 0.5699084997177124,
      "learning_rate": 0.0001957515340994193,
      "loss": 0.5604,
      "num_input_tokens_seen": 294924,
      "step": 122,
      "train_runtime": 1018.0245,
      "train_tokens_per_second": 289.702
    },
    {
      "epoch": 0.9919354838709677,
      "grad_norm": 0.5040406584739685,
      "learning_rate": 0.000195677865688025,
      "loss": 0.6539,
      "num_input_tokens_seen": 297473,
      "step": 123,
      "train_runtime": 1025.9426,
      "train_tokens_per_second": 289.951
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3699295222759247,
      "learning_rate": 0.00019560357815343577,
      "loss": 0.4415,
      "num_input_tokens_seen": 299768,
      "step": 124,
      "train_runtime": 1033.2914,
      "train_tokens_per_second": 290.11
    },
    {
      "epoch": 1.0080645161290323,
      "grad_norm": 0.5218486189842224,
      "learning_rate": 0.00019552867197635974,
      "loss": 0.4879,
      "num_input_tokens_seen": 302171,
      "step": 125,
      "train_runtime": 1040.8815,
      "train_tokens_per_second": 290.303
    },
    {
      "epoch": 1.0161290322580645,
      "grad_norm": 0.4307507872581482,
      "learning_rate": 0.00019545314764150837,
      "loss": 0.4855,
      "num_input_tokens_seen": 304584,
      "step": 126,
      "train_runtime": 1048.4955,
      "train_tokens_per_second": 290.496
    },
    {
      "epoch": 1.0241935483870968,
      "grad_norm": 0.46481820940971375,
      "learning_rate": 0.00019537700563759304,
      "loss": 0.5719,
      "num_input_tokens_seen": 307077,
      "step": 127,
      "train_runtime": 1056.3966,
      "train_tokens_per_second": 290.683
    },
    {
      "epoch": 1.032258064516129,
      "grad_norm": 0.4697766602039337,
      "learning_rate": 0.00019530024645732206,
      "loss": 0.5109,
      "num_input_tokens_seen": 309504,
      "step": 128,
      "train_runtime": 1064.077,
      "train_tokens_per_second": 290.866
    },
    {
      "epoch": 1.0403225806451613,
      "grad_norm": 0.43352261185646057,
      "learning_rate": 0.00019522287059739753,
      "loss": 0.4387,
      "num_input_tokens_seen": 311825,
      "step": 129,
      "train_runtime": 1071.4691,
      "train_tokens_per_second": 291.026
    },
    {
      "epoch": 1.0483870967741935,
      "grad_norm": 0.5191429257392883,
      "learning_rate": 0.00019514487855851184,
      "loss": 0.5712,
      "num_input_tokens_seen": 314337,
      "step": 130,
      "train_runtime": 1079.3989,
      "train_tokens_per_second": 291.215
    },
    {
      "epoch": 1.0564516129032258,
      "grad_norm": 0.4604818820953369,
      "learning_rate": 0.00019506627084534483,
      "loss": 0.4592,
      "num_input_tokens_seen": 316689,
      "step": 131,
      "train_runtime": 1086.9019,
      "train_tokens_per_second": 291.369
    },
    {
      "epoch": 1.064516129032258,
      "grad_norm": 0.4899859130382538,
      "learning_rate": 0.00019498704796656018,
      "loss": 0.5826,
      "num_input_tokens_seen": 319182,
      "step": 132,
      "train_runtime": 1094.7114,
      "train_tokens_per_second": 291.567
    },
    {
      "epoch": 1.0725806451612903,
      "grad_norm": 0.4882298409938812,
      "learning_rate": 0.00019490721043480226,
      "loss": 0.4948,
      "num_input_tokens_seen": 321575,
      "step": 133,
      "train_runtime": 1102.329,
      "train_tokens_per_second": 291.723
    },
    {
      "epoch": 1.0806451612903225,
      "grad_norm": 0.5484714508056641,
      "learning_rate": 0.00019482675876669286,
      "loss": 0.509,
      "num_input_tokens_seen": 323985,
      "step": 134,
      "train_runtime": 1109.9819,
      "train_tokens_per_second": 291.883
    },
    {
      "epoch": 1.0887096774193548,
      "grad_norm": 0.49963870644569397,
      "learning_rate": 0.00019474569348282774,
      "loss": 0.5362,
      "num_input_tokens_seen": 326450,
      "step": 135,
      "train_runtime": 1117.7341,
      "train_tokens_per_second": 292.064
    },
    {
      "epoch": 1.096774193548387,
      "grad_norm": 0.47701138257980347,
      "learning_rate": 0.0001946640151077734,
      "loss": 0.4584,
      "num_input_tokens_seen": 328784,
      "step": 136,
      "train_runtime": 1125.1692,
      "train_tokens_per_second": 292.208
    },
    {
      "epoch": 1.1048387096774193,
      "grad_norm": 0.518075168132782,
      "learning_rate": 0.00019458172417006347,
      "loss": 0.5822,
      "num_input_tokens_seen": 331217,
      "step": 137,
      "train_runtime": 1132.8395,
      "train_tokens_per_second": 292.378
    },
    {
      "epoch": 1.1129032258064515,
      "grad_norm": 0.540624737739563,
      "learning_rate": 0.00019449882120219555,
      "loss": 0.5769,
      "num_input_tokens_seen": 333726,
      "step": 138,
      "train_runtime": 1140.6942,
      "train_tokens_per_second": 292.564
    },
    {
      "epoch": 1.120967741935484,
      "grad_norm": 0.4455350637435913,
      "learning_rate": 0.00019441530674062753,
      "loss": 0.4574,
      "num_input_tokens_seen": 336111,
      "step": 139,
      "train_runtime": 1148.2429,
      "train_tokens_per_second": 292.718
    },
    {
      "epoch": 1.129032258064516,
      "grad_norm": 0.47862115502357483,
      "learning_rate": 0.0001943311813257743,
      "loss": 0.5124,
      "num_input_tokens_seen": 338553,
      "step": 140,
      "train_runtime": 1155.9576,
      "train_tokens_per_second": 292.877
    },
    {
      "epoch": 1.1370967741935485,
      "grad_norm": 0.5344946980476379,
      "learning_rate": 0.00019424644550200415,
      "loss": 0.5678,
      "num_input_tokens_seen": 341110,
      "step": 141,
      "train_runtime": 1163.8909,
      "train_tokens_per_second": 293.077
    },
    {
      "epoch": 1.1451612903225807,
      "grad_norm": 0.5066844820976257,
      "learning_rate": 0.00019416109981763526,
      "loss": 0.5531,
      "num_input_tokens_seen": 343583,
      "step": 142,
      "train_runtime": 1171.6216,
      "train_tokens_per_second": 293.254
    },
    {
      "epoch": 1.153225806451613,
      "grad_norm": 0.6196443438529968,
      "learning_rate": 0.00019407514482493214,
      "loss": 0.5097,
      "num_input_tokens_seen": 346053,
      "step": 143,
      "train_runtime": 1179.384,
      "train_tokens_per_second": 293.418
    },
    {
      "epoch": 1.1612903225806452,
      "grad_norm": 0.5004581809043884,
      "learning_rate": 0.00019398858108010217,
      "loss": 0.5073,
      "num_input_tokens_seen": 348502,
      "step": 144,
      "train_runtime": 1187.1001,
      "train_tokens_per_second": 293.574
    },
    {
      "epoch": 1.1693548387096775,
      "grad_norm": 0.4805152714252472,
      "learning_rate": 0.0001939014091432918,
      "loss": 0.436,
      "num_input_tokens_seen": 350803,
      "step": 145,
      "train_runtime": 1194.4056,
      "train_tokens_per_second": 293.705
    },
    {
      "epoch": 1.1774193548387097,
      "grad_norm": 0.5441202521324158,
      "learning_rate": 0.00019381362957858312,
      "loss": 0.582,
      "num_input_tokens_seen": 353320,
      "step": 146,
      "train_runtime": 1202.2979,
      "train_tokens_per_second": 293.871
    },
    {
      "epoch": 1.185483870967742,
      "grad_norm": 0.4514954388141632,
      "learning_rate": 0.00019372524295399013,
      "loss": 0.3974,
      "num_input_tokens_seen": 355630,
      "step": 147,
      "train_runtime": 1209.6036,
      "train_tokens_per_second": 294.005
    },
    {
      "epoch": 1.1935483870967742,
      "grad_norm": 0.49513113498687744,
      "learning_rate": 0.00019363624984145502,
      "loss": 0.5247,
      "num_input_tokens_seen": 358051,
      "step": 148,
      "train_runtime": 1217.2149,
      "train_tokens_per_second": 294.156
    },
    {
      "epoch": 1.2016129032258065,
      "grad_norm": 0.5256295204162598,
      "learning_rate": 0.00019354665081684446,
      "loss": 0.5084,
      "num_input_tokens_seen": 360569,
      "step": 149,
      "train_runtime": 1225.0281,
      "train_tokens_per_second": 294.335
    },
    {
      "epoch": 1.2096774193548387,
      "grad_norm": 0.4719817638397217,
      "learning_rate": 0.0001934564464599461,
      "loss": 0.5317,
      "num_input_tokens_seen": 363020,
      "step": 150,
      "train_runtime": 1232.7421,
      "train_tokens_per_second": 294.482
    },
    {
      "epoch": 1.2096774193548387,
      "eval_loss": 0.5541179180145264,
      "eval_runtime": 17.0756,
      "eval_samples_per_second": 3.045,
      "eval_steps_per_second": 1.523,
      "num_input_tokens_seen": 363020,
      "step": 150
    },
    {
      "epoch": 1.217741935483871,
      "grad_norm": 0.5494084358215332,
      "learning_rate": 0.00019336563735446446,
      "loss": 0.5502,
      "num_input_tokens_seen": 365462,
      "step": 151,
      "train_runtime": 1258.0076,
      "train_tokens_per_second": 290.509
    },
    {
      "epoch": 1.2258064516129032,
      "grad_norm": 0.5102791786193848,
      "learning_rate": 0.00019327422408801744,
      "loss": 0.5907,
      "num_input_tokens_seen": 367982,
      "step": 152,
      "train_runtime": 1265.9004,
      "train_tokens_per_second": 290.688
    },
    {
      "epoch": 1.2338709677419355,
      "grad_norm": 0.5099480152130127,
      "learning_rate": 0.0001931822072521323,
      "loss": 0.5405,
      "num_input_tokens_seen": 370446,
      "step": 153,
      "train_runtime": 1273.5949,
      "train_tokens_per_second": 290.866
    },
    {
      "epoch": 1.2419354838709677,
      "grad_norm": 0.49685347080230713,
      "learning_rate": 0.00019308958744224217,
      "loss": 0.434,
      "num_input_tokens_seen": 372753,
      "step": 154,
      "train_runtime": 1281.0,
      "train_tokens_per_second": 290.986
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.5306271910667419,
      "learning_rate": 0.00019299636525768173,
      "loss": 0.5416,
      "num_input_tokens_seen": 375291,
      "step": 155,
      "train_runtime": 1288.923,
      "train_tokens_per_second": 291.166
    },
    {
      "epoch": 1.2580645161290323,
      "grad_norm": 0.4725121259689331,
      "learning_rate": 0.00019290254130168374,
      "loss": 0.4697,
      "num_input_tokens_seen": 377667,
      "step": 156,
      "train_runtime": 1296.4986,
      "train_tokens_per_second": 291.298
    },
    {
      "epoch": 1.2661290322580645,
      "grad_norm": 0.5130587220191956,
      "learning_rate": 0.00019280811618137484,
      "loss": 0.6108,
      "num_input_tokens_seen": 380238,
      "step": 157,
      "train_runtime": 1304.4722,
      "train_tokens_per_second": 291.488
    },
    {
      "epoch": 1.2741935483870968,
      "grad_norm": 0.5222141146659851,
      "learning_rate": 0.00019271309050777183,
      "loss": 0.5384,
      "num_input_tokens_seen": 382696,
      "step": 158,
      "train_runtime": 1312.2639,
      "train_tokens_per_second": 291.63
    },
    {
      "epoch": 1.282258064516129,
      "grad_norm": 0.47143712639808655,
      "learning_rate": 0.00019261746489577765,
      "loss": 0.4202,
      "num_input_tokens_seen": 385011,
      "step": 159,
      "train_runtime": 1319.6181,
      "train_tokens_per_second": 291.759
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 0.6677728295326233,
      "learning_rate": 0.00019252123996417738,
      "loss": 0.5565,
      "num_input_tokens_seen": 387512,
      "step": 160,
      "train_runtime": 1327.4482,
      "train_tokens_per_second": 291.923
    },
    {
      "epoch": 1.2983870967741935,
      "grad_norm": 0.48728442192077637,
      "learning_rate": 0.00019242441633563417,
      "loss": 0.5279,
      "num_input_tokens_seen": 389928,
      "step": 161,
      "train_runtime": 1335.0869,
      "train_tokens_per_second": 292.062
    },
    {
      "epoch": 1.3064516129032258,
      "grad_norm": 0.5674954056739807,
      "learning_rate": 0.00019232699463668542,
      "loss": 0.5222,
      "num_input_tokens_seen": 392411,
      "step": 162,
      "train_runtime": 1342.9323,
      "train_tokens_per_second": 292.205
    },
    {
      "epoch": 1.314516129032258,
      "grad_norm": 0.5219017267227173,
      "learning_rate": 0.00019222897549773848,
      "loss": 0.4657,
      "num_input_tokens_seen": 394800,
      "step": 163,
      "train_runtime": 1350.5582,
      "train_tokens_per_second": 292.324
    },
    {
      "epoch": 1.3225806451612903,
      "grad_norm": 0.571649968624115,
      "learning_rate": 0.0001921303595530667,
      "loss": 0.5388,
      "num_input_tokens_seen": 397315,
      "step": 164,
      "train_runtime": 1358.4396,
      "train_tokens_per_second": 292.479
    },
    {
      "epoch": 1.3306451612903225,
      "grad_norm": 0.5281589031219482,
      "learning_rate": 0.00019203114744080542,
      "loss": 0.5208,
      "num_input_tokens_seen": 399749,
      "step": 165,
      "train_runtime": 1366.1378,
      "train_tokens_per_second": 292.613
    },
    {
      "epoch": 1.3387096774193548,
      "grad_norm": 0.5312926769256592,
      "learning_rate": 0.0001919313398029475,
      "loss": 0.4603,
      "num_input_tokens_seen": 402110,
      "step": 166,
      "train_runtime": 1373.5564,
      "train_tokens_per_second": 292.751
    },
    {
      "epoch": 1.346774193548387,
      "grad_norm": 0.4809509813785553,
      "learning_rate": 0.00019183093728533966,
      "loss": 0.4728,
      "num_input_tokens_seen": 404491,
      "step": 167,
      "train_runtime": 1381.0939,
      "train_tokens_per_second": 292.877
    },
    {
      "epoch": 1.3548387096774195,
      "grad_norm": 0.5114589929580688,
      "learning_rate": 0.00019172994053767784,
      "loss": 0.5131,
      "num_input_tokens_seen": 406930,
      "step": 168,
      "train_runtime": 1388.7721,
      "train_tokens_per_second": 293.014
    },
    {
      "epoch": 1.3629032258064515,
      "grad_norm": 0.508705198764801,
      "learning_rate": 0.0001916283502135033,
      "loss": 0.4703,
      "num_input_tokens_seen": 409324,
      "step": 169,
      "train_runtime": 1396.2705,
      "train_tokens_per_second": 293.155
    },
    {
      "epoch": 1.370967741935484,
      "grad_norm": 0.5240468382835388,
      "learning_rate": 0.00019152616697019822,
      "loss": 0.3741,
      "num_input_tokens_seen": 411559,
      "step": 170,
      "train_runtime": 1403.353,
      "train_tokens_per_second": 293.268
    },
    {
      "epoch": 1.379032258064516,
      "grad_norm": 0.5561989545822144,
      "learning_rate": 0.0001914233914689815,
      "loss": 0.5322,
      "num_input_tokens_seen": 413970,
      "step": 171,
      "train_runtime": 1410.8552,
      "train_tokens_per_second": 293.418
    },
    {
      "epoch": 1.3870967741935485,
      "grad_norm": 0.4767642021179199,
      "learning_rate": 0.00019132002437490458,
      "loss": 0.4484,
      "num_input_tokens_seen": 416332,
      "step": 172,
      "train_runtime": 1418.2579,
      "train_tokens_per_second": 293.552
    },
    {
      "epoch": 1.3951612903225805,
      "grad_norm": 0.5309658646583557,
      "learning_rate": 0.00019121606635684696,
      "loss": 0.5277,
      "num_input_tokens_seen": 418754,
      "step": 173,
      "train_runtime": 1425.805,
      "train_tokens_per_second": 293.697
    },
    {
      "epoch": 1.403225806451613,
      "grad_norm": 0.5297260880470276,
      "learning_rate": 0.00019111151808751196,
      "loss": 0.5296,
      "num_input_tokens_seen": 421237,
      "step": 174,
      "train_runtime": 1433.5035,
      "train_tokens_per_second": 293.851
    },
    {
      "epoch": 1.4112903225806452,
      "grad_norm": 0.44537508487701416,
      "learning_rate": 0.00019100638024342244,
      "loss": 0.414,
      "num_input_tokens_seen": 423547,
      "step": 175,
      "train_runtime": 1440.7719,
      "train_tokens_per_second": 293.972
    },
    {
      "epoch": 1.4193548387096775,
      "grad_norm": 0.6102742552757263,
      "learning_rate": 0.00019090065350491626,
      "loss": 0.5886,
      "num_input_tokens_seen": 426041,
      "step": 176,
      "train_runtime": 1448.4454,
      "train_tokens_per_second": 294.137
    },
    {
      "epoch": 1.4274193548387097,
      "grad_norm": 0.4876335561275482,
      "learning_rate": 0.00019079433855614201,
      "loss": 0.5759,
      "num_input_tokens_seen": 428526,
      "step": 177,
      "train_runtime": 1456.2038,
      "train_tokens_per_second": 294.276
    },
    {
      "epoch": 1.435483870967742,
      "grad_norm": 0.5169773101806641,
      "learning_rate": 0.00019068743608505455,
      "loss": 0.4094,
      "num_input_tokens_seen": 430831,
      "step": 178,
      "train_runtime": 1463.4832,
      "train_tokens_per_second": 294.387
    },
    {
      "epoch": 1.4435483870967742,
      "grad_norm": 0.48358380794525146,
      "learning_rate": 0.0001905799467834105,
      "loss": 0.4663,
      "num_input_tokens_seen": 433206,
      "step": 179,
      "train_runtime": 1470.9104,
      "train_tokens_per_second": 294.516
    },
    {
      "epoch": 1.4516129032258065,
      "grad_norm": 0.558736264705658,
      "learning_rate": 0.00019047187134676387,
      "loss": 0.497,
      "num_input_tokens_seen": 435677,
      "step": 180,
      "train_runtime": 1478.6376,
      "train_tokens_per_second": 294.648
    },
    {
      "epoch": 1.4516129032258065,
      "eval_loss": 0.5531938076019287,
      "eval_runtime": 17.116,
      "eval_samples_per_second": 3.038,
      "eval_steps_per_second": 1.519,
      "num_input_tokens_seen": 435677,
      "step": 180
    },
    {
      "epoch": 1.4596774193548387,
      "grad_norm": 0.58433598279953,
      "learning_rate": 0.0001903632104744614,
      "loss": 0.5675,
      "num_input_tokens_seen": 438193,
      "step": 181,
      "train_runtime": 1504.1217,
      "train_tokens_per_second": 291.328
    },
    {
      "epoch": 1.467741935483871,
      "grad_norm": 0.5542019009590149,
      "learning_rate": 0.00019025396486963827,
      "loss": 0.4435,
      "num_input_tokens_seen": 440535,
      "step": 182,
      "train_runtime": 1511.568,
      "train_tokens_per_second": 291.442
    },
    {
      "epoch": 1.4758064516129032,
      "grad_norm": 0.6918825507164001,
      "learning_rate": 0.0001901441352392133,
      "loss": 0.5289,
      "num_input_tokens_seen": 442946,
      "step": 183,
      "train_runtime": 1519.2246,
      "train_tokens_per_second": 291.561
    },
    {
      "epoch": 1.4838709677419355,
      "grad_norm": 0.5807278156280518,
      "learning_rate": 0.00019003372229388452,
      "loss": 0.5884,
      "num_input_tokens_seen": 445434,
      "step": 184,
      "train_runtime": 1527.0904,
      "train_tokens_per_second": 291.688
    },
    {
      "epoch": 1.4919354838709677,
      "grad_norm": 0.4809093475341797,
      "learning_rate": 0.0001899227267481246,
      "loss": 0.5106,
      "num_input_tokens_seen": 447865,
      "step": 185,
      "train_runtime": 1534.7557,
      "train_tokens_per_second": 291.815
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.5059263706207275,
      "learning_rate": 0.00018981114932017609,
      "loss": 0.5066,
      "num_input_tokens_seen": 450249,
      "step": 186,
      "train_runtime": 1542.3188,
      "train_tokens_per_second": 291.93
    },
    {
      "epoch": 1.5080645161290323,
      "grad_norm": 0.5323978662490845,
      "learning_rate": 0.00018969899073204686,
      "loss": 0.5413,
      "num_input_tokens_seen": 452720,
      "step": 187,
      "train_runtime": 1550.0997,
      "train_tokens_per_second": 292.059
    },
    {
      "epoch": 1.5161290322580645,
      "grad_norm": 0.5239408016204834,
      "learning_rate": 0.00018958625170950545,
      "loss": 0.4529,
      "num_input_tokens_seen": 455060,
      "step": 188,
      "train_runtime": 1557.5355,
      "train_tokens_per_second": 292.167
    },
    {
      "epoch": 1.5241935483870968,
      "grad_norm": 0.5529743432998657,
      "learning_rate": 0.00018947293298207635,
      "loss": 0.5093,
      "num_input_tokens_seen": 457475,
      "step": 189,
      "train_runtime": 1565.1928,
      "train_tokens_per_second": 292.28
    },
    {
      "epoch": 1.532258064516129,
      "grad_norm": 0.4671318233013153,
      "learning_rate": 0.00018935903528303523,
      "loss": 0.4162,
      "num_input_tokens_seen": 459738,
      "step": 190,
      "train_runtime": 1572.4177,
      "train_tokens_per_second": 292.377
    },
    {
      "epoch": 1.5403225806451613,
      "grad_norm": 0.4464218318462372,
      "learning_rate": 0.0001892445593494042,
      "loss": 0.465,
      "num_input_tokens_seen": 462172,
      "step": 191,
      "train_runtime": 1580.1066,
      "train_tokens_per_second": 292.494
    },
    {
      "epoch": 1.5483870967741935,
      "grad_norm": 0.4810047745704651,
      "learning_rate": 0.0001891295059219472,
      "loss": 0.4945,
      "num_input_tokens_seen": 464558,
      "step": 192,
      "train_runtime": 1587.6273,
      "train_tokens_per_second": 292.611
    },
    {
      "epoch": 1.5564516129032258,
      "grad_norm": 0.5889862179756165,
      "learning_rate": 0.00018901387574516497,
      "loss": 0.4944,
      "num_input_tokens_seen": 466950,
      "step": 193,
      "train_runtime": 1595.149,
      "train_tokens_per_second": 292.731
    },
    {
      "epoch": 1.564516129032258,
      "grad_norm": 0.6099379658699036,
      "learning_rate": 0.00018889766956729044,
      "loss": 0.483,
      "num_input_tokens_seen": 469382,
      "step": 194,
      "train_runtime": 1602.8182,
      "train_tokens_per_second": 292.848
    },
    {
      "epoch": 1.5725806451612905,
      "grad_norm": 0.5440390110015869,
      "learning_rate": 0.00018878088814028364,
      "loss": 0.4593,
      "num_input_tokens_seen": 471803,
      "step": 195,
      "train_runtime": 1610.4242,
      "train_tokens_per_second": 292.968
    },
    {
      "epoch": 1.5806451612903225,
      "grad_norm": 0.5005755424499512,
      "learning_rate": 0.00018866353221982718,
      "loss": 0.4294,
      "num_input_tokens_seen": 474211,
      "step": 196,
      "train_runtime": 1618.001,
      "train_tokens_per_second": 293.084
    },
    {
      "epoch": 1.588709677419355,
      "grad_norm": 0.6077679991722107,
      "learning_rate": 0.000188545602565321,
      "loss": 0.5771,
      "num_input_tokens_seen": 476689,
      "step": 197,
      "train_runtime": 1625.6796,
      "train_tokens_per_second": 293.224
    },
    {
      "epoch": 1.596774193548387,
      "grad_norm": 0.4779480993747711,
      "learning_rate": 0.00018842709993987776,
      "loss": 0.4385,
      "num_input_tokens_seen": 479013,
      "step": 198,
      "train_runtime": 1633.0479,
      "train_tokens_per_second": 293.325
    },
    {
      "epoch": 1.6048387096774195,
      "grad_norm": 0.4863346815109253,
      "learning_rate": 0.00018830802511031762,
      "loss": 0.4334,
      "num_input_tokens_seen": 481374,
      "step": 199,
      "train_runtime": 1640.4972,
      "train_tokens_per_second": 293.432
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 0.518204391002655,
      "learning_rate": 0.0001881883788471636,
      "loss": 0.4768,
      "num_input_tokens_seen": 483799,
      "step": 200,
      "train_runtime": 1648.0818,
      "train_tokens_per_second": 293.553
    },
    {
      "epoch": 1.620967741935484,
      "grad_norm": 0.5243327021598816,
      "learning_rate": 0.00018806816192463625,
      "loss": 0.5814,
      "num_input_tokens_seen": 486348,
      "step": 201,
      "train_runtime": 1655.9994,
      "train_tokens_per_second": 293.689
    },
    {
      "epoch": 1.629032258064516,
      "grad_norm": 0.5013379454612732,
      "learning_rate": 0.0001879473751206489,
      "loss": 0.4501,
      "num_input_tokens_seen": 488725,
      "step": 202,
      "train_runtime": 1663.4446,
      "train_tokens_per_second": 293.803
    },
    {
      "epoch": 1.6370967741935485,
      "grad_norm": 0.524978756904602,
      "learning_rate": 0.00018782601921680256,
      "loss": 0.5842,
      "num_input_tokens_seen": 491239,
      "step": 203,
      "train_runtime": 1671.245,
      "train_tokens_per_second": 293.936
    },
    {
      "epoch": 1.6451612903225805,
      "grad_norm": 0.5189937353134155,
      "learning_rate": 0.00018770409499838073,
      "loss": 0.5237,
      "num_input_tokens_seen": 493653,
      "step": 204,
      "train_runtime": 1678.7904,
      "train_tokens_per_second": 294.053
    },
    {
      "epoch": 1.653225806451613,
      "grad_norm": 0.4908079504966736,
      "learning_rate": 0.0001875816032543445,
      "loss": 0.4633,
      "num_input_tokens_seen": 496049,
      "step": 205,
      "train_runtime": 1686.2657,
      "train_tokens_per_second": 294.17
    },
    {
      "epoch": 1.661290322580645,
      "grad_norm": 0.45395177602767944,
      "learning_rate": 0.00018745854477732733,
      "loss": 0.4658,
      "num_input_tokens_seen": 498435,
      "step": 206,
      "train_runtime": 1693.8087,
      "train_tokens_per_second": 294.269
    },
    {
      "epoch": 1.6693548387096775,
      "grad_norm": 0.47721126675605774,
      "learning_rate": 0.00018733492036363005,
      "loss": 0.5109,
      "num_input_tokens_seen": 500909,
      "step": 207,
      "train_runtime": 1701.5132,
      "train_tokens_per_second": 294.39
    },
    {
      "epoch": 1.6774193548387095,
      "grad_norm": 0.48570311069488525,
      "learning_rate": 0.0001872107308132155,
      "loss": 0.4805,
      "num_input_tokens_seen": 503339,
      "step": 208,
      "train_runtime": 1709.082,
      "train_tokens_per_second": 294.508
    },
    {
      "epoch": 1.685483870967742,
      "grad_norm": 0.46823814511299133,
      "learning_rate": 0.00018708597692970353,
      "loss": 0.4247,
      "num_input_tokens_seen": 505708,
      "step": 209,
      "train_runtime": 1716.5731,
      "train_tokens_per_second": 294.603
    },
    {
      "epoch": 1.6935483870967742,
      "grad_norm": 0.5073066353797913,
      "learning_rate": 0.00018696065952036571,
      "loss": 0.4316,
      "num_input_tokens_seen": 507981,
      "step": 210,
      "train_runtime": 1723.7836,
      "train_tokens_per_second": 294.69
    },
    {
      "epoch": 1.6935483870967742,
      "eval_loss": 0.5447993874549866,
      "eval_runtime": 17.1405,
      "eval_samples_per_second": 3.034,
      "eval_steps_per_second": 1.517,
      "num_input_tokens_seen": 507981,
      "step": 210
    },
    {
      "epoch": 1.7016129032258065,
      "grad_norm": 0.5070942044258118,
      "learning_rate": 0.00018683477939612021,
      "loss": 0.4498,
      "num_input_tokens_seen": 510398,
      "step": 211,
      "train_runtime": 1748.9718,
      "train_tokens_per_second": 291.827
    },
    {
      "epoch": 1.7096774193548387,
      "grad_norm": 0.5081866383552551,
      "learning_rate": 0.0001867083373715264,
      "loss": 0.5194,
      "num_input_tokens_seen": 512927,
      "step": 212,
      "train_runtime": 1756.9223,
      "train_tokens_per_second": 291.946
    },
    {
      "epoch": 1.717741935483871,
      "grad_norm": 0.5030050277709961,
      "learning_rate": 0.00018658133426477965,
      "loss": 0.576,
      "num_input_tokens_seen": 515446,
      "step": 213,
      "train_runtime": 1764.7796,
      "train_tokens_per_second": 292.074
    },
    {
      "epoch": 1.7258064516129032,
      "grad_norm": 0.46002885699272156,
      "learning_rate": 0.00018645377089770616,
      "loss": 0.3902,
      "num_input_tokens_seen": 517761,
      "step": 214,
      "train_runtime": 1772.0597,
      "train_tokens_per_second": 292.18
    },
    {
      "epoch": 1.7338709677419355,
      "grad_norm": 0.5473560690879822,
      "learning_rate": 0.00018632564809575742,
      "loss": 0.5174,
      "num_input_tokens_seen": 520212,
      "step": 215,
      "train_runtime": 1779.8104,
      "train_tokens_per_second": 292.285
    },
    {
      "epoch": 1.7419354838709677,
      "grad_norm": 0.5015368461608887,
      "learning_rate": 0.00018619696668800492,
      "loss": 0.4974,
      "num_input_tokens_seen": 522595,
      "step": 216,
      "train_runtime": 1787.3722,
      "train_tokens_per_second": 292.382
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.5964553952217102,
      "learning_rate": 0.00018606772750713504,
      "loss": 0.531,
      "num_input_tokens_seen": 525075,
      "step": 217,
      "train_runtime": 1795.0892,
      "train_tokens_per_second": 292.506
    },
    {
      "epoch": 1.7580645161290323,
      "grad_norm": 0.47636234760284424,
      "learning_rate": 0.00018593793138944328,
      "loss": 0.4391,
      "num_input_tokens_seen": 527478,
      "step": 218,
      "train_runtime": 1802.6529,
      "train_tokens_per_second": 292.612
    },
    {
      "epoch": 1.7661290322580645,
      "grad_norm": 0.5664883255958557,
      "learning_rate": 0.0001858075791748291,
      "loss": 0.5283,
      "num_input_tokens_seen": 529954,
      "step": 219,
      "train_runtime": 1810.4252,
      "train_tokens_per_second": 292.724
    },
    {
      "epoch": 1.7741935483870968,
      "grad_norm": 0.5361610054969788,
      "learning_rate": 0.0001856766717067904,
      "loss": 0.5343,
      "num_input_tokens_seen": 532412,
      "step": 220,
      "train_runtime": 1818.1176,
      "train_tokens_per_second": 292.837
    },
    {
      "epoch": 1.782258064516129,
      "grad_norm": 0.48824912309646606,
      "learning_rate": 0.00018554520983241814,
      "loss": 0.5223,
      "num_input_tokens_seen": 534838,
      "step": 221,
      "train_runtime": 1825.728,
      "train_tokens_per_second": 292.945
    },
    {
      "epoch": 1.7903225806451613,
      "grad_norm": 0.5257652401924133,
      "learning_rate": 0.00018541319440239066,
      "loss": 0.508,
      "num_input_tokens_seen": 537339,
      "step": 222,
      "train_runtime": 1833.5362,
      "train_tokens_per_second": 293.062
    },
    {
      "epoch": 1.7983870967741935,
      "grad_norm": 0.4608156681060791,
      "learning_rate": 0.00018528062627096845,
      "loss": 0.4316,
      "num_input_tokens_seen": 539716,
      "step": 223,
      "train_runtime": 1841.1084,
      "train_tokens_per_second": 293.147
    },
    {
      "epoch": 1.8064516129032258,
      "grad_norm": 0.6113476157188416,
      "learning_rate": 0.0001851475062959884,
      "loss": 0.5363,
      "num_input_tokens_seen": 542226,
      "step": 224,
      "train_runtime": 1848.9709,
      "train_tokens_per_second": 293.258
    },
    {
      "epoch": 1.814516129032258,
      "grad_norm": 0.5347176194190979,
      "learning_rate": 0.00018501383533885837,
      "loss": 0.4869,
      "num_input_tokens_seen": 544617,
      "step": 225,
      "train_runtime": 1856.5371,
      "train_tokens_per_second": 293.351
    },
    {
      "epoch": 1.8225806451612905,
      "grad_norm": 0.5930202603340149,
      "learning_rate": 0.00018487961426455157,
      "loss": 0.5905,
      "num_input_tokens_seen": 547121,
      "step": 226,
      "train_runtime": 1864.3896,
      "train_tokens_per_second": 293.459
    },
    {
      "epoch": 1.8306451612903225,
      "grad_norm": 0.5011629462242126,
      "learning_rate": 0.0001847448439416009,
      "loss": 0.5145,
      "num_input_tokens_seen": 549555,
      "step": 227,
      "train_runtime": 1872.0413,
      "train_tokens_per_second": 293.559
    },
    {
      "epoch": 1.838709677419355,
      "grad_norm": 0.6015912890434265,
      "learning_rate": 0.00018460952524209355,
      "loss": 0.4399,
      "num_input_tokens_seen": 551862,
      "step": 228,
      "train_runtime": 1879.419,
      "train_tokens_per_second": 293.634
    },
    {
      "epoch": 1.846774193548387,
      "grad_norm": 0.5135874152183533,
      "learning_rate": 0.0001844736590416651,
      "loss": 0.4815,
      "num_input_tokens_seen": 554312,
      "step": 229,
      "train_runtime": 1887.1751,
      "train_tokens_per_second": 293.726
    },
    {
      "epoch": 1.8548387096774195,
      "grad_norm": 0.5236052870750427,
      "learning_rate": 0.00018433724621949392,
      "loss": 0.5149,
      "num_input_tokens_seen": 556789,
      "step": 230,
      "train_runtime": 1894.9542,
      "train_tokens_per_second": 293.827
    },
    {
      "epoch": 1.8629032258064515,
      "grad_norm": 0.46906578540802,
      "learning_rate": 0.00018420028765829568,
      "loss": 0.4666,
      "num_input_tokens_seen": 559163,
      "step": 231,
      "train_runtime": 1902.5378,
      "train_tokens_per_second": 293.904
    },
    {
      "epoch": 1.870967741935484,
      "grad_norm": 0.5261631011962891,
      "learning_rate": 0.00018406278424431736,
      "loss": 0.4782,
      "num_input_tokens_seen": 561579,
      "step": 232,
      "train_runtime": 1910.1668,
      "train_tokens_per_second": 293.995
    },
    {
      "epoch": 1.879032258064516,
      "grad_norm": 0.5413320064544678,
      "learning_rate": 0.00018392473686733163,
      "loss": 0.5822,
      "num_input_tokens_seen": 564116,
      "step": 233,
      "train_runtime": 1918.1419,
      "train_tokens_per_second": 294.095
    },
    {
      "epoch": 1.8870967741935485,
      "grad_norm": 0.4339919686317444,
      "learning_rate": 0.00018378614642063115,
      "loss": 0.3655,
      "num_input_tokens_seen": 566348,
      "step": 234,
      "train_runtime": 1925.3367,
      "train_tokens_per_second": 294.155
    },
    {
      "epoch": 1.8951612903225805,
      "grad_norm": 0.4839528501033783,
      "learning_rate": 0.00018364701380102266,
      "loss": 0.3749,
      "num_input_tokens_seen": 568609,
      "step": 235,
      "train_runtime": 1932.5907,
      "train_tokens_per_second": 294.221
    },
    {
      "epoch": 1.903225806451613,
      "grad_norm": 0.5061867833137512,
      "learning_rate": 0.0001835073399088214,
      "loss": 0.564,
      "num_input_tokens_seen": 571056,
      "step": 236,
      "train_runtime": 1940.3213,
      "train_tokens_per_second": 294.31
    },
    {
      "epoch": 1.911290322580645,
      "grad_norm": 0.492093026638031,
      "learning_rate": 0.00018336712564784503,
      "loss": 0.5252,
      "num_input_tokens_seen": 573516,
      "step": 237,
      "train_runtime": 1948.0561,
      "train_tokens_per_second": 294.404
    },
    {
      "epoch": 1.9193548387096775,
      "grad_norm": 0.48326292634010315,
      "learning_rate": 0.00018322637192540785,
      "loss": 0.4631,
      "num_input_tokens_seen": 575864,
      "step": 238,
      "train_runtime": 1955.6449,
      "train_tokens_per_second": 294.462
    },
    {
      "epoch": 1.9274193548387095,
      "grad_norm": 0.5116320848464966,
      "learning_rate": 0.00018308507965231508,
      "loss": 0.4509,
      "num_input_tokens_seen": 578253,
      "step": 239,
      "train_runtime": 1963.2546,
      "train_tokens_per_second": 294.538
    },
    {
      "epoch": 1.935483870967742,
      "grad_norm": 0.4807403087615967,
      "learning_rate": 0.00018294324974285677,
      "loss": 0.4697,
      "num_input_tokens_seen": 580659,
      "step": 240,
      "train_runtime": 1970.8614,
      "train_tokens_per_second": 294.622
    },
    {
      "epoch": 1.935483870967742,
      "eval_loss": 0.5381087064743042,
      "eval_runtime": 17.118,
      "eval_samples_per_second": 3.038,
      "eval_steps_per_second": 1.519,
      "num_input_tokens_seen": 580659,
      "step": 240
    },
    {
      "epoch": 1.9435483870967742,
      "grad_norm": 0.4913121163845062,
      "learning_rate": 0.00018280088311480201,
      "loss": 0.4832,
      "num_input_tokens_seen": 583091,
      "step": 241,
      "train_runtime": 1996.1377,
      "train_tokens_per_second": 292.11
    },
    {
      "epoch": 1.9516129032258065,
      "grad_norm": 0.4860823154449463,
      "learning_rate": 0.00018265798068939294,
      "loss": 0.4735,
      "num_input_tokens_seen": 585429,
      "step": 242,
      "train_runtime": 2003.6251,
      "train_tokens_per_second": 292.185
    },
    {
      "epoch": 1.9596774193548387,
      "grad_norm": 0.501605212688446,
      "learning_rate": 0.0001825145433913388,
      "loss": 0.4724,
      "num_input_tokens_seen": 587740,
      "step": 243,
      "train_runtime": 2010.9061,
      "train_tokens_per_second": 292.276
    },
    {
      "epoch": 1.967741935483871,
      "grad_norm": 0.6114291548728943,
      "learning_rate": 0.00018237057214880994,
      "loss": 0.5296,
      "num_input_tokens_seen": 590200,
      "step": 244,
      "train_runtime": 2018.6341,
      "train_tokens_per_second": 292.376
    },
    {
      "epoch": 1.9758064516129032,
      "grad_norm": 0.5196385383605957,
      "learning_rate": 0.00018222606789343183,
      "loss": 0.4503,
      "num_input_tokens_seen": 592568,
      "step": 245,
      "train_runtime": 2026.0979,
      "train_tokens_per_second": 292.468
    },
    {
      "epoch": 1.9838709677419355,
      "grad_norm": 0.5557199120521545,
      "learning_rate": 0.00018208103156027897,
      "loss": 0.4142,
      "num_input_tokens_seen": 594859,
      "step": 246,
      "train_runtime": 2033.4129,
      "train_tokens_per_second": 292.542
    },
    {
      "epoch": 1.9919354838709677,
      "grad_norm": 0.46165671944618225,
      "learning_rate": 0.00018193546408786898,
      "loss": 0.4176,
      "num_input_tokens_seen": 597173,
      "step": 247,
      "train_runtime": 2040.7772,
      "train_tokens_per_second": 292.62
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.47444823384284973,
      "learning_rate": 0.00018178936641815636,
      "loss": 0.5027,
      "num_input_tokens_seen": 599536,
      "step": 248,
      "train_runtime": 2048.2447,
      "train_tokens_per_second": 292.707
    },
    {
      "epoch": 2.0080645161290325,
      "grad_norm": 0.4732966721057892,
      "learning_rate": 0.0001816427394965265,
      "loss": 0.4184,
      "num_input_tokens_seen": 601912,
      "step": 249,
      "train_runtime": 2055.7988,
      "train_tokens_per_second": 292.787
    },
    {
      "epoch": 2.0161290322580645,
      "grad_norm": 0.4494001567363739,
      "learning_rate": 0.00018149558427178956,
      "loss": 0.3894,
      "num_input_tokens_seen": 604356,
      "step": 250,
      "train_runtime": 2063.5321,
      "train_tokens_per_second": 292.875
    },
    {
      "epoch": 2.024193548387097,
      "grad_norm": 0.44498300552368164,
      "learning_rate": 0.00018134790169617419,
      "loss": 0.3898,
      "num_input_tokens_seen": 606702,
      "step": 251,
      "train_runtime": 2070.9435,
      "train_tokens_per_second": 292.959
    },
    {
      "epoch": 2.032258064516129,
      "grad_norm": 0.4384775161743164,
      "learning_rate": 0.00018119969272532166,
      "loss": 0.3653,
      "num_input_tokens_seen": 609049,
      "step": 252,
      "train_runtime": 2078.4436,
      "train_tokens_per_second": 293.031
    },
    {
      "epoch": 2.0403225806451615,
      "grad_norm": 0.5194664597511292,
      "learning_rate": 0.00018105095831827934,
      "loss": 0.4256,
      "num_input_tokens_seen": 611538,
      "step": 253,
      "train_runtime": 2086.2988,
      "train_tokens_per_second": 293.121
    },
    {
      "epoch": 2.0483870967741935,
      "grad_norm": 0.591899037361145,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.4612,
      "num_input_tokens_seen": 613951,
      "step": 254,
      "train_runtime": 2093.9481,
      "train_tokens_per_second": 293.203
    },
    {
      "epoch": 2.056451612903226,
      "grad_norm": 0.45229119062423706,
      "learning_rate": 0.0001807519170488092,
      "loss": 0.3442,
      "num_input_tokens_seen": 616318,
      "step": 255,
      "train_runtime": 2101.4584,
      "train_tokens_per_second": 293.281
    },
    {
      "epoch": 2.064516129032258,
      "grad_norm": 0.5321218371391296,
      "learning_rate": 0.00018060161212145155,
      "loss": 0.3251,
      "num_input_tokens_seen": 618622,
      "step": 256,
      "train_runtime": 2108.7139,
      "train_tokens_per_second": 293.365
    },
    {
      "epoch": 2.0725806451612905,
      "grad_norm": 0.534270167350769,
      "learning_rate": 0.00018045078562803203,
      "loss": 0.5195,
      "num_input_tokens_seen": 621111,
      "step": 257,
      "train_runtime": 2116.5523,
      "train_tokens_per_second": 293.454
    },
    {
      "epoch": 2.0806451612903225,
      "grad_norm": 0.5846385359764099,
      "learning_rate": 0.00018029943854453576,
      "loss": 0.5031,
      "num_input_tokens_seen": 623620,
      "step": 258,
      "train_runtime": 2124.4123,
      "train_tokens_per_second": 293.549
    },
    {
      "epoch": 2.088709677419355,
      "grad_norm": 0.47890356183052063,
      "learning_rate": 0.00018014757185031671,
      "loss": 0.3725,
      "num_input_tokens_seen": 625929,
      "step": 259,
      "train_runtime": 2131.761,
      "train_tokens_per_second": 293.621
    },
    {
      "epoch": 2.096774193548387,
      "grad_norm": 0.5304666757583618,
      "learning_rate": 0.0001799951865280911,
      "loss": 0.385,
      "num_input_tokens_seen": 628263,
      "step": 260,
      "train_runtime": 2139.2295,
      "train_tokens_per_second": 293.687
    },
    {
      "epoch": 2.1048387096774195,
      "grad_norm": 0.5279107689857483,
      "learning_rate": 0.00017984228356393117,
      "loss": 0.437,
      "num_input_tokens_seen": 630646,
      "step": 261,
      "train_runtime": 2146.7966,
      "train_tokens_per_second": 293.761
    },
    {
      "epoch": 2.1129032258064515,
      "grad_norm": 0.5816720128059387,
      "learning_rate": 0.00017968886394725874,
      "loss": 0.451,
      "num_input_tokens_seen": 633104,
      "step": 262,
      "train_runtime": 2154.5982,
      "train_tokens_per_second": 293.839
    },
    {
      "epoch": 2.120967741935484,
      "grad_norm": 0.5712978839874268,
      "learning_rate": 0.00017953492867083895,
      "loss": 0.5002,
      "num_input_tokens_seen": 635619,
      "step": 263,
      "train_runtime": 2162.5316,
      "train_tokens_per_second": 293.924
    },
    {
      "epoch": 2.129032258064516,
      "grad_norm": 0.49511051177978516,
      "learning_rate": 0.00017938047873077362,
      "loss": 0.4396,
      "num_input_tokens_seen": 638049,
      "step": 264,
      "train_runtime": 2170.2108,
      "train_tokens_per_second": 294.003
    },
    {
      "epoch": 2.1370967741935485,
      "grad_norm": 0.5378257632255554,
      "learning_rate": 0.00017922551512649496,
      "loss": 0.4671,
      "num_input_tokens_seen": 640517,
      "step": 265,
      "train_runtime": 2178.0065,
      "train_tokens_per_second": 294.084
    },
    {
      "epoch": 2.1451612903225805,
      "grad_norm": 0.5713797807693481,
      "learning_rate": 0.00017907003886075904,
      "loss": 0.4272,
      "num_input_tokens_seen": 642961,
      "step": 266,
      "train_runtime": 2185.7486,
      "train_tokens_per_second": 294.161
    },
    {
      "epoch": 2.153225806451613,
      "grad_norm": 0.5059149861335754,
      "learning_rate": 0.00017891405093963938,
      "loss": 0.4128,
      "num_input_tokens_seen": 645335,
      "step": 267,
      "train_runtime": 2193.2848,
      "train_tokens_per_second": 294.232
    },
    {
      "epoch": 2.161290322580645,
      "grad_norm": 0.5088847875595093,
      "learning_rate": 0.00017875755237252027,
      "loss": 0.3906,
      "num_input_tokens_seen": 647684,
      "step": 268,
      "train_runtime": 2200.7799,
      "train_tokens_per_second": 294.297
    },
    {
      "epoch": 2.1693548387096775,
      "grad_norm": 0.5963711142539978,
      "learning_rate": 0.00017860054417209042,
      "loss": 0.4691,
      "num_input_tokens_seen": 650205,
      "step": 269,
      "train_runtime": 2208.6495,
      "train_tokens_per_second": 294.39
    },
    {
      "epoch": 2.1774193548387095,
      "grad_norm": 0.6186060905456543,
      "learning_rate": 0.00017844302735433635,
      "loss": 0.4597,
      "num_input_tokens_seen": 652668,
      "step": 270,
      "train_runtime": 2216.3826,
      "train_tokens_per_second": 294.474
    },
    {
      "epoch": 2.1774193548387095,
      "eval_loss": 0.5312316417694092,
      "eval_runtime": 17.1243,
      "eval_samples_per_second": 3.037,
      "eval_steps_per_second": 1.518,
      "num_input_tokens_seen": 652668,
      "step": 270
    },
    {
      "epoch": 2.185483870967742,
      "grad_norm": 0.5696012377738953,
      "learning_rate": 0.00017828500293853576,
      "loss": 0.4434,
      "num_input_tokens_seen": 655108,
      "step": 271,
      "train_runtime": 2241.6839,
      "train_tokens_per_second": 292.239
    },
    {
      "epoch": 2.193548387096774,
      "grad_norm": 0.4818873107433319,
      "learning_rate": 0.00017812647194725094,
      "loss": 0.3463,
      "num_input_tokens_seen": 657419,
      "step": 272,
      "train_runtime": 2249.0146,
      "train_tokens_per_second": 292.314
    },
    {
      "epoch": 2.2016129032258065,
      "grad_norm": 0.5452220439910889,
      "learning_rate": 0.00017796743540632223,
      "loss": 0.3752,
      "num_input_tokens_seen": 659850,
      "step": 273,
      "train_runtime": 2256.6279,
      "train_tokens_per_second": 292.405
    },
    {
      "epoch": 2.2096774193548385,
      "grad_norm": 0.6274825930595398,
      "learning_rate": 0.0001778078943448614,
      "loss": 0.4796,
      "num_input_tokens_seen": 662308,
      "step": 274,
      "train_runtime": 2264.3474,
      "train_tokens_per_second": 292.494
    },
    {
      "epoch": 2.217741935483871,
      "grad_norm": 0.5836248397827148,
      "learning_rate": 0.00017764784979524477,
      "loss": 0.3798,
      "num_input_tokens_seen": 664650,
      "step": 275,
      "train_runtime": 2271.7662,
      "train_tokens_per_second": 292.57
    },
    {
      "epoch": 2.225806451612903,
      "grad_norm": 0.6024234294891357,
      "learning_rate": 0.00017748730279310685,
      "loss": 0.4063,
      "num_input_tokens_seen": 667075,
      "step": 276,
      "train_runtime": 2279.3952,
      "train_tokens_per_second": 292.654
    },
    {
      "epoch": 2.2338709677419355,
      "grad_norm": 0.5628243088722229,
      "learning_rate": 0.00017732625437733335,
      "loss": 0.4282,
      "num_input_tokens_seen": 669468,
      "step": 277,
      "train_runtime": 2286.8838,
      "train_tokens_per_second": 292.742
    },
    {
      "epoch": 2.241935483870968,
      "grad_norm": 0.5293336510658264,
      "learning_rate": 0.00017716470559005473,
      "loss": 0.4309,
      "num_input_tokens_seen": 671950,
      "step": 278,
      "train_runtime": 2294.6117,
      "train_tokens_per_second": 292.838
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.5426146984100342,
      "learning_rate": 0.0001770026574766391,
      "loss": 0.4052,
      "num_input_tokens_seen": 674433,
      "step": 279,
      "train_runtime": 2302.3887,
      "train_tokens_per_second": 292.928
    },
    {
      "epoch": 2.258064516129032,
      "grad_norm": 0.6207026839256287,
      "learning_rate": 0.00017684011108568592,
      "loss": 0.5071,
      "num_input_tokens_seen": 676912,
      "step": 280,
      "train_runtime": 2310.1413,
      "train_tokens_per_second": 293.018
    },
    {
      "epoch": 2.2661290322580645,
      "grad_norm": 0.5530769228935242,
      "learning_rate": 0.0001766770674690187,
      "loss": 0.4343,
      "num_input_tokens_seen": 679269,
      "step": 281,
      "train_runtime": 2317.5627,
      "train_tokens_per_second": 293.096
    },
    {
      "epoch": 2.274193548387097,
      "grad_norm": 0.564753532409668,
      "learning_rate": 0.0001765135276816787,
      "loss": 0.4786,
      "num_input_tokens_seen": 681764,
      "step": 282,
      "train_runtime": 2325.405,
      "train_tokens_per_second": 293.181
    },
    {
      "epoch": 2.282258064516129,
      "grad_norm": 0.5628737807273865,
      "learning_rate": 0.0001763494927819177,
      "loss": 0.446,
      "num_input_tokens_seen": 684242,
      "step": 283,
      "train_runtime": 2333.1186,
      "train_tokens_per_second": 293.274
    },
    {
      "epoch": 2.2903225806451615,
      "grad_norm": 0.5662450194358826,
      "learning_rate": 0.00017618496383119128,
      "loss": 0.4688,
      "num_input_tokens_seen": 686667,
      "step": 284,
      "train_runtime": 2340.7592,
      "train_tokens_per_second": 293.352
    },
    {
      "epoch": 2.2983870967741935,
      "grad_norm": 0.5666800737380981,
      "learning_rate": 0.0001760199418941521,
      "loss": 0.453,
      "num_input_tokens_seen": 689157,
      "step": 285,
      "train_runtime": 2348.5315,
      "train_tokens_per_second": 293.442
    },
    {
      "epoch": 2.306451612903226,
      "grad_norm": 0.557955265045166,
      "learning_rate": 0.00017585442803864294,
      "loss": 0.4425,
      "num_input_tokens_seen": 691634,
      "step": 286,
      "train_runtime": 2356.2504,
      "train_tokens_per_second": 293.532
    },
    {
      "epoch": 2.314516129032258,
      "grad_norm": 0.48944398760795593,
      "learning_rate": 0.00017568842333568952,
      "loss": 0.3574,
      "num_input_tokens_seen": 693987,
      "step": 287,
      "train_runtime": 2363.644,
      "train_tokens_per_second": 293.609
    },
    {
      "epoch": 2.3225806451612905,
      "grad_norm": 0.5263356566429138,
      "learning_rate": 0.00017552192885949395,
      "loss": 0.4162,
      "num_input_tokens_seen": 696441,
      "step": 288,
      "train_runtime": 2371.3258,
      "train_tokens_per_second": 293.693
    },
    {
      "epoch": 2.3306451612903225,
      "grad_norm": 0.5621548891067505,
      "learning_rate": 0.0001753549456874276,
      "loss": 0.4279,
      "num_input_tokens_seen": 698839,
      "step": 289,
      "train_runtime": 2378.8114,
      "train_tokens_per_second": 293.777
    },
    {
      "epoch": 2.338709677419355,
      "grad_norm": 0.611740231513977,
      "learning_rate": 0.00017518747490002413,
      "loss": 0.4416,
      "num_input_tokens_seen": 701344,
      "step": 290,
      "train_runtime": 2386.6276,
      "train_tokens_per_second": 293.864
    },
    {
      "epoch": 2.346774193548387,
      "grad_norm": 0.6447325944900513,
      "learning_rate": 0.00017501951758097257,
      "loss": 0.4726,
      "num_input_tokens_seen": 703751,
      "step": 291,
      "train_runtime": 2394.2032,
      "train_tokens_per_second": 293.94
    },
    {
      "epoch": 2.3548387096774195,
      "grad_norm": 0.5147153735160828,
      "learning_rate": 0.00017485107481711012,
      "loss": 0.385,
      "num_input_tokens_seen": 706194,
      "step": 292,
      "train_runtime": 2401.889,
      "train_tokens_per_second": 294.016
    },
    {
      "epoch": 2.3629032258064515,
      "grad_norm": 0.5166308879852295,
      "learning_rate": 0.0001746821476984154,
      "loss": 0.3878,
      "num_input_tokens_seen": 708576,
      "step": 293,
      "train_runtime": 2409.389,
      "train_tokens_per_second": 294.089
    },
    {
      "epoch": 2.370967741935484,
      "grad_norm": 0.5455900430679321,
      "learning_rate": 0.00017451273731800115,
      "loss": 0.4115,
      "num_input_tokens_seen": 710954,
      "step": 294,
      "train_runtime": 2416.8337,
      "train_tokens_per_second": 294.168
    },
    {
      "epoch": 2.379032258064516,
      "grad_norm": 0.6575648188591003,
      "learning_rate": 0.00017434284477210735,
      "loss": 0.4544,
      "num_input_tokens_seen": 713370,
      "step": 295,
      "train_runtime": 2424.3973,
      "train_tokens_per_second": 294.246
    },
    {
      "epoch": 2.3870967741935485,
      "grad_norm": 0.5806699991226196,
      "learning_rate": 0.00017417247116009388,
      "loss": 0.4084,
      "num_input_tokens_seen": 715800,
      "step": 296,
      "train_runtime": 2431.961,
      "train_tokens_per_second": 294.33
    },
    {
      "epoch": 2.3951612903225805,
      "grad_norm": 0.6843745112419128,
      "learning_rate": 0.00017400161758443375,
      "loss": 0.5063,
      "num_input_tokens_seen": 718378,
      "step": 297,
      "train_runtime": 2439.9431,
      "train_tokens_per_second": 294.424
    },
    {
      "epoch": 2.403225806451613,
      "grad_norm": 0.6058449149131775,
      "learning_rate": 0.0001738302851507056,
      "loss": 0.4703,
      "num_input_tokens_seen": 720905,
      "step": 298,
      "train_runtime": 2447.8089,
      "train_tokens_per_second": 294.51
    },
    {
      "epoch": 2.411290322580645,
      "grad_norm": 0.5916767716407776,
      "learning_rate": 0.00017365847496758684,
      "loss": 0.456,
      "num_input_tokens_seen": 723346,
      "step": 299,
      "train_runtime": 2455.4811,
      "train_tokens_per_second": 294.584
    },
    {
      "epoch": 2.4193548387096775,
      "grad_norm": 0.6260201930999756,
      "learning_rate": 0.0001734861881468463,
      "loss": 0.3953,
      "num_input_tokens_seen": 725766,
      "step": 300,
      "train_runtime": 2463.1406,
      "train_tokens_per_second": 294.651
    },
    {
      "epoch": 2.4193548387096775,
      "eval_loss": 0.527380108833313,
      "eval_runtime": 17.1648,
      "eval_samples_per_second": 3.029,
      "eval_steps_per_second": 1.515,
      "num_input_tokens_seen": 725766,
      "step": 300
    },
    {
      "epoch": 2.4274193548387095,
      "grad_norm": 0.5748977661132812,
      "learning_rate": 0.00017331342580333706,
      "loss": 0.355,
      "num_input_tokens_seen": 728220,
      "step": 301,
      "train_runtime": 2488.5272,
      "train_tokens_per_second": 292.631
    },
    {
      "epoch": 2.435483870967742,
      "grad_norm": 0.5469366908073425,
      "learning_rate": 0.00017314018905498931,
      "loss": 0.4119,
      "num_input_tokens_seen": 730550,
      "step": 302,
      "train_runtime": 2495.9929,
      "train_tokens_per_second": 292.689
    },
    {
      "epoch": 2.443548387096774,
      "grad_norm": 0.5869015455245972,
      "learning_rate": 0.00017296647902280312,
      "loss": 0.4636,
      "num_input_tokens_seen": 733009,
      "step": 303,
      "train_runtime": 2503.7702,
      "train_tokens_per_second": 292.762
    },
    {
      "epoch": 2.4516129032258065,
      "grad_norm": 0.5205616354942322,
      "learning_rate": 0.00017279229683084103,
      "loss": 0.4071,
      "num_input_tokens_seen": 735380,
      "step": 304,
      "train_runtime": 2511.3332,
      "train_tokens_per_second": 292.825
    },
    {
      "epoch": 2.4596774193548385,
      "grad_norm": 0.5007433891296387,
      "learning_rate": 0.00017261764360622102,
      "loss": 0.315,
      "num_input_tokens_seen": 737686,
      "step": 305,
      "train_runtime": 2518.7119,
      "train_tokens_per_second": 292.882
    },
    {
      "epoch": 2.467741935483871,
      "grad_norm": 0.6229686141014099,
      "learning_rate": 0.00017244252047910892,
      "loss": 0.4113,
      "num_input_tokens_seen": 740115,
      "step": 306,
      "train_runtime": 2526.4292,
      "train_tokens_per_second": 292.949
    },
    {
      "epoch": 2.475806451612903,
      "grad_norm": 0.616976261138916,
      "learning_rate": 0.00017226692858271134,
      "loss": 0.3898,
      "num_input_tokens_seen": 742496,
      "step": 307,
      "train_runtime": 2533.9623,
      "train_tokens_per_second": 293.018
    },
    {
      "epoch": 2.4838709677419355,
      "grad_norm": 0.5927110314369202,
      "learning_rate": 0.00017209086905326833,
      "loss": 0.4703,
      "num_input_tokens_seen": 745018,
      "step": 308,
      "train_runtime": 2541.882,
      "train_tokens_per_second": 293.097
    },
    {
      "epoch": 2.491935483870968,
      "grad_norm": 0.5572441816329956,
      "learning_rate": 0.0001719143430300458,
      "loss": 0.4004,
      "num_input_tokens_seen": 747345,
      "step": 309,
      "train_runtime": 2549.3485,
      "train_tokens_per_second": 293.151
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.5831232666969299,
      "learning_rate": 0.00017173735165532846,
      "loss": 0.4868,
      "num_input_tokens_seen": 749829,
      "step": 310,
      "train_runtime": 2557.1615,
      "train_tokens_per_second": 293.227
    },
    {
      "epoch": 2.508064516129032,
      "grad_norm": 0.6402316689491272,
      "learning_rate": 0.00017155989607441213,
      "loss": 0.4885,
      "num_input_tokens_seen": 752333,
      "step": 311,
      "train_runtime": 2564.9857,
      "train_tokens_per_second": 293.309
    },
    {
      "epoch": 2.5161290322580645,
      "grad_norm": 0.570831298828125,
      "learning_rate": 0.00017138197743559654,
      "loss": 0.4276,
      "num_input_tokens_seen": 754723,
      "step": 312,
      "train_runtime": 2572.5142,
      "train_tokens_per_second": 293.38
    },
    {
      "epoch": 2.524193548387097,
      "grad_norm": 0.579409122467041,
      "learning_rate": 0.0001712035968901778,
      "loss": 0.4517,
      "num_input_tokens_seen": 757147,
      "step": 313,
      "train_runtime": 2580.1465,
      "train_tokens_per_second": 293.451
    },
    {
      "epoch": 2.532258064516129,
      "grad_norm": 0.5915924906730652,
      "learning_rate": 0.00017102475559244105,
      "loss": 0.4085,
      "num_input_tokens_seen": 759595,
      "step": 314,
      "train_runtime": 2587.8168,
      "train_tokens_per_second": 293.527
    },
    {
      "epoch": 2.540322580645161,
      "grad_norm": 0.5570502281188965,
      "learning_rate": 0.00017084545469965283,
      "loss": 0.4807,
      "num_input_tokens_seen": 762102,
      "step": 315,
      "train_runtime": 2595.6436,
      "train_tokens_per_second": 293.608
    },
    {
      "epoch": 2.5483870967741935,
      "grad_norm": 0.5616797208786011,
      "learning_rate": 0.00017066569537205371,
      "loss": 0.4255,
      "num_input_tokens_seen": 764592,
      "step": 316,
      "train_runtime": 2603.4661,
      "train_tokens_per_second": 293.682
    },
    {
      "epoch": 2.556451612903226,
      "grad_norm": 0.5703938007354736,
      "learning_rate": 0.00017048547877285077,
      "loss": 0.4487,
      "num_input_tokens_seen": 767057,
      "step": 317,
      "train_runtime": 2611.2278,
      "train_tokens_per_second": 293.753
    },
    {
      "epoch": 2.564516129032258,
      "grad_norm": 0.520163893699646,
      "learning_rate": 0.00017030480606821,
      "loss": 0.3109,
      "num_input_tokens_seen": 769376,
      "step": 318,
      "train_runtime": 2618.6114,
      "train_tokens_per_second": 293.811
    },
    {
      "epoch": 2.5725806451612905,
      "grad_norm": 0.5977119207382202,
      "learning_rate": 0.00017012367842724887,
      "loss": 0.4699,
      "num_input_tokens_seen": 771849,
      "step": 319,
      "train_runtime": 2626.3552,
      "train_tokens_per_second": 293.886
    },
    {
      "epoch": 2.5806451612903225,
      "grad_norm": 0.5811707377433777,
      "learning_rate": 0.00016994209702202867,
      "loss": 0.4879,
      "num_input_tokens_seen": 774330,
      "step": 320,
      "train_runtime": 2634.1356,
      "train_tokens_per_second": 293.96
    },
    {
      "epoch": 2.588709677419355,
      "grad_norm": 0.4585582911968231,
      "learning_rate": 0.00016976006302754702,
      "loss": 0.3106,
      "num_input_tokens_seen": 776532,
      "step": 321,
      "train_runtime": 2641.1848,
      "train_tokens_per_second": 294.009
    },
    {
      "epoch": 2.596774193548387,
      "grad_norm": 0.5964781641960144,
      "learning_rate": 0.0001695775776217301,
      "loss": 0.4633,
      "num_input_tokens_seen": 779041,
      "step": 322,
      "train_runtime": 2649.044,
      "train_tokens_per_second": 294.084
    },
    {
      "epoch": 2.6048387096774195,
      "grad_norm": 0.5717709064483643,
      "learning_rate": 0.00016939464198542523,
      "loss": 0.4271,
      "num_input_tokens_seen": 781447,
      "step": 323,
      "train_runtime": 2656.6235,
      "train_tokens_per_second": 294.15
    },
    {
      "epoch": 2.6129032258064515,
      "grad_norm": 0.6638820171356201,
      "learning_rate": 0.00016921125730239307,
      "loss": 0.4948,
      "num_input_tokens_seen": 783883,
      "step": 324,
      "train_runtime": 2664.2512,
      "train_tokens_per_second": 294.223
    },
    {
      "epoch": 2.620967741935484,
      "grad_norm": 0.5894833207130432,
      "learning_rate": 0.00016902742475930006,
      "loss": 0.4224,
      "num_input_tokens_seen": 786317,
      "step": 325,
      "train_runtime": 2671.9046,
      "train_tokens_per_second": 294.291
    },
    {
      "epoch": 2.629032258064516,
      "grad_norm": 0.5976919531822205,
      "learning_rate": 0.00016884314554571064,
      "loss": 0.4773,
      "num_input_tokens_seen": 788765,
      "step": 326,
      "train_runtime": 2679.5878,
      "train_tokens_per_second": 294.361
    },
    {
      "epoch": 2.6370967741935485,
      "grad_norm": 0.5534376502037048,
      "learning_rate": 0.0001686584208540797,
      "loss": 0.3417,
      "num_input_tokens_seen": 791059,
      "step": 327,
      "train_runtime": 2686.9383,
      "train_tokens_per_second": 294.409
    },
    {
      "epoch": 2.6451612903225805,
      "grad_norm": 0.685295820236206,
      "learning_rate": 0.00016847325187974477,
      "loss": 0.3821,
      "num_input_tokens_seen": 793400,
      "step": 328,
      "train_runtime": 2694.3655,
      "train_tokens_per_second": 294.466
    },
    {
      "epoch": 2.653225806451613,
      "grad_norm": 0.569644033908844,
      "learning_rate": 0.00016828763982091826,
      "loss": 0.4001,
      "num_input_tokens_seen": 795767,
      "step": 329,
      "train_runtime": 2701.9131,
      "train_tokens_per_second": 294.52
    },
    {
      "epoch": 2.661290322580645,
      "grad_norm": 0.5384069681167603,
      "learning_rate": 0.00016810158587867973,
      "loss": 0.363,
      "num_input_tokens_seen": 798156,
      "step": 330,
      "train_runtime": 2709.485,
      "train_tokens_per_second": 294.578
    },
    {
      "epoch": 2.661290322580645,
      "eval_loss": 0.5271878838539124,
      "eval_runtime": 17.1438,
      "eval_samples_per_second": 3.033,
      "eval_steps_per_second": 1.517,
      "num_input_tokens_seen": 798156,
      "step": 330
    },
    {
      "epoch": 2.6693548387096775,
      "grad_norm": 0.5838504433631897,
      "learning_rate": 0.00016791509125696816,
      "loss": 0.3768,
      "num_input_tokens_seen": 800529,
      "step": 331,
      "train_runtime": 2734.6267,
      "train_tokens_per_second": 292.738
    },
    {
      "epoch": 2.6774193548387095,
      "grad_norm": 0.6681272983551025,
      "learning_rate": 0.00016772815716257412,
      "loss": 0.4815,
      "num_input_tokens_seen": 803033,
      "step": 332,
      "train_runtime": 2742.5363,
      "train_tokens_per_second": 292.807
    },
    {
      "epoch": 2.685483870967742,
      "grad_norm": 0.6045708060264587,
      "learning_rate": 0.00016754078480513197,
      "loss": 0.4308,
      "num_input_tokens_seen": 805467,
      "step": 333,
      "train_runtime": 2750.2472,
      "train_tokens_per_second": 292.871
    },
    {
      "epoch": 2.693548387096774,
      "grad_norm": 0.49178603291511536,
      "learning_rate": 0.00016735297539711204,
      "loss": 0.3579,
      "num_input_tokens_seen": 807830,
      "step": 334,
      "train_runtime": 2757.6998,
      "train_tokens_per_second": 292.936
    },
    {
      "epoch": 2.7016129032258065,
      "grad_norm": 0.6021568179130554,
      "learning_rate": 0.00016716473015381276,
      "loss": 0.5022,
      "num_input_tokens_seen": 810267,
      "step": 335,
      "train_runtime": 2765.4392,
      "train_tokens_per_second": 292.998
    },
    {
      "epoch": 2.709677419354839,
      "grad_norm": 0.642227292060852,
      "learning_rate": 0.0001669760502933528,
      "loss": 0.4935,
      "num_input_tokens_seen": 812742,
      "step": 336,
      "train_runtime": 2773.2451,
      "train_tokens_per_second": 293.065
    },
    {
      "epoch": 2.717741935483871,
      "grad_norm": 0.689476490020752,
      "learning_rate": 0.00016678693703666325,
      "loss": 0.4519,
      "num_input_tokens_seen": 815204,
      "step": 337,
      "train_runtime": 2780.9789,
      "train_tokens_per_second": 293.136
    },
    {
      "epoch": 2.725806451612903,
      "grad_norm": 0.639265775680542,
      "learning_rate": 0.00016659739160747967,
      "loss": 0.4412,
      "num_input_tokens_seen": 817573,
      "step": 338,
      "train_runtime": 2788.5484,
      "train_tokens_per_second": 293.189
    },
    {
      "epoch": 2.7338709677419355,
      "grad_norm": 0.5716695785522461,
      "learning_rate": 0.00016640741523233407,
      "loss": 0.3793,
      "num_input_tokens_seen": 819936,
      "step": 339,
      "train_runtime": 2796.0411,
      "train_tokens_per_second": 293.249
    },
    {
      "epoch": 2.741935483870968,
      "grad_norm": 0.604978084564209,
      "learning_rate": 0.00016621700914054718,
      "loss": 0.4706,
      "num_input_tokens_seen": 822393,
      "step": 340,
      "train_runtime": 2803.8011,
      "train_tokens_per_second": 293.314
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.5651271343231201,
      "learning_rate": 0.00016602617456422034,
      "loss": 0.4308,
      "num_input_tokens_seen": 824807,
      "step": 341,
      "train_runtime": 2811.4387,
      "train_tokens_per_second": 293.375
    },
    {
      "epoch": 2.758064516129032,
      "grad_norm": 0.6630417108535767,
      "learning_rate": 0.00016583491273822765,
      "loss": 0.457,
      "num_input_tokens_seen": 827252,
      "step": 342,
      "train_runtime": 2819.1309,
      "train_tokens_per_second": 293.442
    },
    {
      "epoch": 2.7661290322580645,
      "grad_norm": 0.6293765306472778,
      "learning_rate": 0.00016564322490020776,
      "loss": 0.4465,
      "num_input_tokens_seen": 829666,
      "step": 343,
      "train_runtime": 2826.7387,
      "train_tokens_per_second": 293.506
    },
    {
      "epoch": 2.774193548387097,
      "grad_norm": 0.5662552714347839,
      "learning_rate": 0.00016545111229055614,
      "loss": 0.4357,
      "num_input_tokens_seen": 832061,
      "step": 344,
      "train_runtime": 2834.3219,
      "train_tokens_per_second": 293.566
    },
    {
      "epoch": 2.782258064516129,
      "grad_norm": 0.6861712336540222,
      "learning_rate": 0.00016525857615241687,
      "loss": 0.4776,
      "num_input_tokens_seen": 834532,
      "step": 345,
      "train_runtime": 2842.1306,
      "train_tokens_per_second": 293.629
    },
    {
      "epoch": 2.790322580645161,
      "grad_norm": 0.6480405330657959,
      "learning_rate": 0.00016506561773167464,
      "loss": 0.486,
      "num_input_tokens_seen": 837118,
      "step": 346,
      "train_runtime": 2850.1336,
      "train_tokens_per_second": 293.712
    },
    {
      "epoch": 2.7983870967741935,
      "grad_norm": 0.6150621771812439,
      "learning_rate": 0.00016487223827694672,
      "loss": 0.5001,
      "num_input_tokens_seen": 839620,
      "step": 347,
      "train_runtime": 2857.9459,
      "train_tokens_per_second": 293.784
    },
    {
      "epoch": 2.806451612903226,
      "grad_norm": 0.572364091873169,
      "learning_rate": 0.00016467843903957485,
      "loss": 0.4115,
      "num_input_tokens_seen": 842039,
      "step": 348,
      "train_runtime": 2865.4869,
      "train_tokens_per_second": 293.855
    },
    {
      "epoch": 2.814516129032258,
      "grad_norm": 0.5200697183609009,
      "learning_rate": 0.00016448422127361706,
      "loss": 0.3682,
      "num_input_tokens_seen": 844368,
      "step": 349,
      "train_runtime": 2872.8812,
      "train_tokens_per_second": 293.91
    },
    {
      "epoch": 2.8225806451612905,
      "grad_norm": 0.5125967264175415,
      "learning_rate": 0.00016428958623583982,
      "loss": 0.3246,
      "num_input_tokens_seen": 846670,
      "step": 350,
      "train_runtime": 2880.3239,
      "train_tokens_per_second": 293.95
    },
    {
      "epoch": 2.8306451612903225,
      "grad_norm": 0.5699242949485779,
      "learning_rate": 0.0001640945351857096,
      "loss": 0.4146,
      "num_input_tokens_seen": 849140,
      "step": 351,
      "train_runtime": 2888.0519,
      "train_tokens_per_second": 294.018
    },
    {
      "epoch": 2.838709677419355,
      "grad_norm": 0.5335444808006287,
      "learning_rate": 0.0001638990693853848,
      "loss": 0.3411,
      "num_input_tokens_seen": 851497,
      "step": 352,
      "train_runtime": 2895.5376,
      "train_tokens_per_second": 294.072
    },
    {
      "epoch": 2.846774193548387,
      "grad_norm": 0.5370481014251709,
      "learning_rate": 0.00016370319009970777,
      "loss": 0.3241,
      "num_input_tokens_seen": 853782,
      "step": 353,
      "train_runtime": 2902.8145,
      "train_tokens_per_second": 294.122
    },
    {
      "epoch": 2.8548387096774195,
      "grad_norm": 0.6068407893180847,
      "learning_rate": 0.0001635068985961965,
      "loss": 0.4412,
      "num_input_tokens_seen": 856228,
      "step": 354,
      "train_runtime": 2910.5006,
      "train_tokens_per_second": 294.186
    },
    {
      "epoch": 2.8629032258064515,
      "grad_norm": 0.5907058119773865,
      "learning_rate": 0.00016331019614503623,
      "loss": 0.4894,
      "num_input_tokens_seen": 858707,
      "step": 355,
      "train_runtime": 2918.2897,
      "train_tokens_per_second": 294.25
    },
    {
      "epoch": 2.870967741935484,
      "grad_norm": 0.6342933773994446,
      "learning_rate": 0.00016311308401907153,
      "loss": 0.4909,
      "num_input_tokens_seen": 861182,
      "step": 356,
      "train_runtime": 2926.0784,
      "train_tokens_per_second": 294.313
    },
    {
      "epoch": 2.879032258064516,
      "grad_norm": 0.5832836031913757,
      "learning_rate": 0.00016291556349379795,
      "loss": 0.4421,
      "num_input_tokens_seen": 863637,
      "step": 357,
      "train_runtime": 2933.8375,
      "train_tokens_per_second": 294.371
    },
    {
      "epoch": 2.8870967741935485,
      "grad_norm": 0.6093757152557373,
      "learning_rate": 0.0001627176358473537,
      "loss": 0.4871,
      "num_input_tokens_seen": 866076,
      "step": 358,
      "train_runtime": 2941.5666,
      "train_tokens_per_second": 294.427
    },
    {
      "epoch": 2.8951612903225805,
      "grad_norm": 0.5512157082557678,
      "learning_rate": 0.0001625193023605115,
      "loss": 0.379,
      "num_input_tokens_seen": 868405,
      "step": 359,
      "train_runtime": 2948.977,
      "train_tokens_per_second": 294.477
    },
    {
      "epoch": 2.903225806451613,
      "grad_norm": 0.540212869644165,
      "learning_rate": 0.00016232056431667017,
      "loss": 0.4007,
      "num_input_tokens_seen": 870779,
      "step": 360,
      "train_runtime": 2956.4862,
      "train_tokens_per_second": 294.532
    },
    {
      "epoch": 2.903225806451613,
      "eval_loss": 0.5227369070053101,
      "eval_runtime": 17.1651,
      "eval_samples_per_second": 3.029,
      "eval_steps_per_second": 1.515,
      "num_input_tokens_seen": 870779,
      "step": 360
    }
  ],
  "logging_steps": 1,
  "max_steps": 1240,
  "num_input_tokens_seen": 870779,
  "num_train_epochs": 10,
  "save_steps": 30,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.92211345087744e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}