{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4994054696789536,
  "eval_steps": 105,
  "global_step": 210,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0023781212841854932,
      "grad_norm": 32.74397118558861,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.9478,
      "step": 1
    },
    {
      "epoch": 0.0023781212841854932,
      "eval_loss": 3.373392343521118,
      "eval_runtime": 78.9756,
      "eval_samples_per_second": 8.091,
      "eval_steps_per_second": 1.013,
      "step": 1
    },
    {
      "epoch": 0.0047562425683709865,
      "grad_norm": 37.080911592721954,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 2.8264,
      "step": 2
    },
    {
      "epoch": 0.007134363852556481,
      "grad_norm": 31.107267997702266,
      "learning_rate": 1.5e-06,
      "loss": 2.9936,
      "step": 3
    },
    {
      "epoch": 0.009512485136741973,
      "grad_norm": 27.574905774161167,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.8944,
      "step": 4
    },
    {
      "epoch": 0.011890606420927468,
      "grad_norm": 13.643957484299273,
      "learning_rate": 2.5e-06,
      "loss": 2.7687,
      "step": 5
    },
    {
      "epoch": 0.014268727705112961,
      "grad_norm": 15.077028980653411,
      "learning_rate": 3e-06,
      "loss": 2.6623,
      "step": 6
    },
    {
      "epoch": 0.016646848989298454,
      "grad_norm": 14.569557474559408,
      "learning_rate": 3.5e-06,
      "loss": 2.9007,
      "step": 7
    },
    {
      "epoch": 0.019024970273483946,
      "grad_norm": 13.894984550517007,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.8359,
      "step": 8
    },
    {
      "epoch": 0.02140309155766944,
      "grad_norm": 13.546442233583257,
      "learning_rate": 4.5e-06,
      "loss": 2.7583,
      "step": 9
    },
    {
      "epoch": 0.023781212841854936,
      "grad_norm": 11.166476039936938,
      "learning_rate": 5e-06,
      "loss": 2.518,
      "step": 10
    },
    {
      "epoch": 0.026159334126040427,
      "grad_norm": 7.787448179397784,
      "learning_rate": 5.500000000000001e-06,
      "loss": 2.6494,
      "step": 11
    },
    {
      "epoch": 0.028537455410225922,
      "grad_norm": 4.72349822440695,
      "learning_rate": 6e-06,
      "loss": 2.4022,
      "step": 12
    },
    {
      "epoch": 0.030915576694411414,
      "grad_norm": 4.100722460414476,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 2.3933,
      "step": 13
    },
    {
      "epoch": 0.03329369797859691,
      "grad_norm": 4.193151112965372,
      "learning_rate": 7e-06,
      "loss": 2.5468,
      "step": 14
    },
    {
      "epoch": 0.0356718192627824,
      "grad_norm": 5.502246954578136,
      "learning_rate": 7.500000000000001e-06,
      "loss": 2.5126,
      "step": 15
    },
    {
      "epoch": 0.03804994054696789,
      "grad_norm": 5.716937946349337,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.6761,
      "step": 16
    },
    {
      "epoch": 0.04042806183115339,
      "grad_norm": 3.008867017303434,
      "learning_rate": 8.5e-06,
      "loss": 2.4264,
      "step": 17
    },
    {
      "epoch": 0.04280618311533888,
      "grad_norm": 3.6016120293217178,
      "learning_rate": 9e-06,
      "loss": 2.3836,
      "step": 18
    },
    {
      "epoch": 0.04518430439952437,
      "grad_norm": 2.1431386543975908,
      "learning_rate": 9.5e-06,
      "loss": 2.4879,
      "step": 19
    },
    {
      "epoch": 0.04756242568370987,
      "grad_norm": 3.838539096237921,
      "learning_rate": 1e-05,
      "loss": 2.4116,
      "step": 20
    },
    {
      "epoch": 0.04994054696789536,
      "grad_norm": 1.9119200890173822,
      "learning_rate": 1.0500000000000001e-05,
      "loss": 2.6716,
      "step": 21
    },
    {
      "epoch": 0.052318668252080855,
      "grad_norm": 2.0853737807318904,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 2.4523,
      "step": 22
    },
    {
      "epoch": 0.054696789536266346,
      "grad_norm": 1.6109539551135528,
      "learning_rate": 1.15e-05,
      "loss": 2.3086,
      "step": 23
    },
    {
      "epoch": 0.057074910820451845,
      "grad_norm": 2.575933824126331,
      "learning_rate": 1.2e-05,
      "loss": 2.5576,
      "step": 24
    },
    {
      "epoch": 0.059453032104637336,
      "grad_norm": 1.4827660467902501,
      "learning_rate": 1.25e-05,
      "loss": 2.264,
      "step": 25
    },
    {
      "epoch": 0.06183115338882283,
      "grad_norm": 2.1022593224903128,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 2.8781,
      "step": 26
    },
    {
      "epoch": 0.06420927467300833,
      "grad_norm": 2.756765764204405,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 2.5071,
      "step": 27
    },
    {
      "epoch": 0.06658739595719382,
      "grad_norm": 1.6249455774563617,
      "learning_rate": 1.4e-05,
      "loss": 2.5085,
      "step": 28
    },
    {
      "epoch": 0.06896551724137931,
      "grad_norm": 1.8653671914008603,
      "learning_rate": 1.45e-05,
      "loss": 2.4368,
      "step": 29
    },
    {
      "epoch": 0.0713436385255648,
      "grad_norm": 1.867632087572305,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 2.1204,
      "step": 30
    },
    {
      "epoch": 0.07372175980975029,
      "grad_norm": 1.2367329590346625,
      "learning_rate": 1.55e-05,
      "loss": 2.1118,
      "step": 31
    },
    {
      "epoch": 0.07609988109393578,
      "grad_norm": 1.5969207000997636,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.4747,
      "step": 32
    },
    {
      "epoch": 0.07847800237812129,
      "grad_norm": 1.5075133034220278,
      "learning_rate": 1.65e-05,
      "loss": 2.3349,
      "step": 33
    },
    {
      "epoch": 0.08085612366230678,
      "grad_norm": 1.4803692479229955,
      "learning_rate": 1.7e-05,
      "loss": 2.3915,
      "step": 34
    },
    {
      "epoch": 0.08323424494649227,
      "grad_norm": 2.692949771759104,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 2.6397,
      "step": 35
    },
    {
      "epoch": 0.08561236623067776,
      "grad_norm": 1.3636512770329847,
      "learning_rate": 1.8e-05,
      "loss": 2.2944,
      "step": 36
    },
    {
      "epoch": 0.08799048751486326,
      "grad_norm": 1.8310086696195464,
      "learning_rate": 1.8500000000000002e-05,
      "loss": 2.2614,
      "step": 37
    },
    {
      "epoch": 0.09036860879904875,
      "grad_norm": 1.7765027708264853,
      "learning_rate": 1.9e-05,
      "loss": 2.3579,
      "step": 38
    },
    {
      "epoch": 0.09274673008323424,
      "grad_norm": 1.4484769960901491,
      "learning_rate": 1.95e-05,
      "loss": 2.4548,
      "step": 39
    },
    {
      "epoch": 0.09512485136741974,
      "grad_norm": 3.1520205275209414,
      "learning_rate": 2e-05,
      "loss": 2.5208,
      "step": 40
    },
    {
      "epoch": 0.09750297265160524,
      "grad_norm": 1.5897739849482102,
      "learning_rate": 1.9999981652287733e-05,
      "loss": 2.4216,
      "step": 41
    },
    {
      "epoch": 0.09988109393579073,
      "grad_norm": 2.4520591326987495,
      "learning_rate": 1.999992660921826e-05,
      "loss": 2.2326,
      "step": 42
    },
    {
      "epoch": 0.10225921521997622,
      "grad_norm": 1.4817926319377914,
      "learning_rate": 1.999983487099356e-05,
      "loss": 2.541,
      "step": 43
    },
    {
      "epoch": 0.10463733650416171,
      "grad_norm": 2.4022755616863956,
      "learning_rate": 1.999970643795027e-05,
      "loss": 2.3645,
      "step": 44
    },
    {
      "epoch": 0.1070154577883472,
      "grad_norm": 2.476073007712477,
      "learning_rate": 1.9999541310559686e-05,
      "loss": 2.5051,
      "step": 45
    },
    {
      "epoch": 0.10939357907253269,
      "grad_norm": 3.428213096316913,
      "learning_rate": 1.9999339489427746e-05,
      "loss": 2.3605,
      "step": 46
    },
    {
      "epoch": 0.1117717003567182,
      "grad_norm": 2.464783346708793,
      "learning_rate": 1.9999100975295046e-05,
      "loss": 2.3785,
      "step": 47
    },
    {
      "epoch": 0.11414982164090369,
      "grad_norm": 2.0686444585541754,
      "learning_rate": 1.999882576903682e-05,
      "loss": 2.6035,
      "step": 48
    },
    {
      "epoch": 0.11652794292508918,
      "grad_norm": 2.30832669621963,
      "learning_rate": 1.9998513871662945e-05,
      "loss": 2.3982,
      "step": 49
    },
    {
      "epoch": 0.11890606420927467,
      "grad_norm": 1.7443884357427357,
      "learning_rate": 1.9998165284317944e-05,
      "loss": 2.2344,
      "step": 50
    },
    {
      "epoch": 0.12128418549346016,
      "grad_norm": 1.862498116501275,
      "learning_rate": 1.999778000828098e-05,
      "loss": 2.0631,
      "step": 51
    },
    {
      "epoch": 0.12366230677764566,
      "grad_norm": 1.3054707043181313,
      "learning_rate": 1.9997358044965833e-05,
      "loss": 2.4434,
      "step": 52
    },
    {
      "epoch": 0.12604042806183116,
      "grad_norm": 2.6645481874919583,
      "learning_rate": 1.9996899395920915e-05,
      "loss": 2.4647,
      "step": 53
    },
    {
      "epoch": 0.12841854934601665,
      "grad_norm": 1.6884769054479885,
      "learning_rate": 1.999640406282926e-05,
      "loss": 2.2864,
      "step": 54
    },
    {
      "epoch": 0.13079667063020214,
      "grad_norm": 2.281038989939936,
      "learning_rate": 1.9995872047508516e-05,
      "loss": 2.2999,
      "step": 55
    },
    {
      "epoch": 0.13317479191438764,
      "grad_norm": 1.8457967068582515,
      "learning_rate": 1.9995303351910934e-05,
      "loss": 2.5117,
      "step": 56
    },
    {
      "epoch": 0.13555291319857313,
      "grad_norm": 1.593901860141829,
      "learning_rate": 1.9994697978123363e-05,
      "loss": 2.1696,
      "step": 57
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": 2.168613470386471,
      "learning_rate": 1.9994055928367256e-05,
      "loss": 2.6852,
      "step": 58
    },
    {
      "epoch": 0.1403091557669441,
      "grad_norm": 1.5398971278043392,
      "learning_rate": 1.999337720499863e-05,
      "loss": 2.396,
      "step": 59
    },
    {
      "epoch": 0.1426872770511296,
      "grad_norm": 1.7618365641290346,
      "learning_rate": 1.99926618105081e-05,
      "loss": 2.047,
      "step": 60
    },
    {
      "epoch": 0.1450653983353151,
      "grad_norm": 1.3935889380673343,
      "learning_rate": 1.9991909747520835e-05,
      "loss": 2.1071,
      "step": 61
    },
    {
      "epoch": 0.14744351961950058,
      "grad_norm": 1.3063537354837544,
      "learning_rate": 1.999112101879656e-05,
      "loss": 2.3992,
      "step": 62
    },
    {
      "epoch": 0.14982164090368608,
      "grad_norm": 1.025531260937785,
      "learning_rate": 1.9990295627229544e-05,
      "loss": 2.4764,
      "step": 63
    },
    {
      "epoch": 0.15219976218787157,
      "grad_norm": 1.0662434476421614,
      "learning_rate": 1.99894335758486e-05,
      "loss": 2.0608,
      "step": 64
    },
    {
      "epoch": 0.1545778834720571,
      "grad_norm": 1.335312659171346,
      "learning_rate": 1.9988534867817065e-05,
      "loss": 2.0345,
      "step": 65
    },
    {
      "epoch": 0.15695600475624258,
      "grad_norm": 1.7866360477276542,
      "learning_rate": 1.9987599506432785e-05,
      "loss": 2.4781,
      "step": 66
    },
    {
      "epoch": 0.15933412604042807,
      "grad_norm": 1.3661388854405736,
      "learning_rate": 1.9986627495128105e-05,
      "loss": 2.3895,
      "step": 67
    },
    {
      "epoch": 0.16171224732461356,
      "grad_norm": 1.69413799763372,
      "learning_rate": 1.9985618837469864e-05,
      "loss": 2.415,
      "step": 68
    },
    {
      "epoch": 0.16409036860879905,
      "grad_norm": 1.6458921632697698,
      "learning_rate": 1.998457353715938e-05,
      "loss": 2.4017,
      "step": 69
    },
    {
      "epoch": 0.16646848989298454,
      "grad_norm": 1.705150979387567,
      "learning_rate": 1.998349159803241e-05,
      "loss": 2.317,
      "step": 70
    },
    {
      "epoch": 0.16884661117717004,
      "grad_norm": 1.4786622132550975,
      "learning_rate": 1.9982373024059195e-05,
      "loss": 2.4046,
      "step": 71
    },
    {
      "epoch": 0.17122473246135553,
      "grad_norm": 1.1257378401253821,
      "learning_rate": 1.998121781934438e-05,
      "loss": 2.196,
      "step": 72
    },
    {
      "epoch": 0.17360285374554102,
      "grad_norm": 1.2450243917414825,
      "learning_rate": 1.9980025988127037e-05,
      "loss": 2.1235,
      "step": 73
    },
    {
      "epoch": 0.1759809750297265,
      "grad_norm": 1.2574977788035384,
      "learning_rate": 1.9978797534780646e-05,
      "loss": 2.4466,
      "step": 74
    },
    {
      "epoch": 0.178359096313912,
      "grad_norm": 1.390309850165232,
      "learning_rate": 1.9977532463813064e-05,
      "loss": 2.4469,
      "step": 75
    },
    {
      "epoch": 0.1807372175980975,
      "grad_norm": 1.2146735833909619,
      "learning_rate": 1.9976230779866527e-05,
      "loss": 2.3705,
      "step": 76
    },
    {
      "epoch": 0.18311533888228299,
      "grad_norm": 1.26356031715395,
      "learning_rate": 1.9974892487717613e-05,
      "loss": 2.4926,
      "step": 77
    },
    {
      "epoch": 0.18549346016646848,
      "grad_norm": 1.3934309027656608,
      "learning_rate": 1.997351759227725e-05,
      "loss": 2.47,
      "step": 78
    },
    {
      "epoch": 0.187871581450654,
      "grad_norm": 1.129998342751621,
      "learning_rate": 1.9972106098590665e-05,
      "loss": 2.3718,
      "step": 79
    },
    {
      "epoch": 0.1902497027348395,
      "grad_norm": 1.3957720808228478,
      "learning_rate": 1.9970658011837404e-05,
      "loss": 2.2057,
      "step": 80
    },
    {
      "epoch": 0.19262782401902498,
      "grad_norm": 1.5835508346410572,
      "learning_rate": 1.9969173337331283e-05,
      "loss": 2.2551,
      "step": 81
    },
    {
      "epoch": 0.19500594530321047,
      "grad_norm": 1.0726363834452401,
      "learning_rate": 1.996765208052037e-05,
      "loss": 1.9962,
      "step": 82
    },
    {
      "epoch": 0.19738406658739596,
      "grad_norm": 1.5380248440103288,
      "learning_rate": 1.9966094246986983e-05,
      "loss": 2.1986,
      "step": 83
    },
    {
      "epoch": 0.19976218787158145,
      "grad_norm": 1.2953387209833067,
      "learning_rate": 1.9964499842447665e-05,
      "loss": 2.5842,
      "step": 84
    },
    {
      "epoch": 0.20214030915576695,
      "grad_norm": 1.0712033116668103,
      "learning_rate": 1.9962868872753144e-05,
      "loss": 2.1298,
      "step": 85
    },
    {
      "epoch": 0.20451843043995244,
      "grad_norm": 1.095761902776689,
      "learning_rate": 1.996120134388834e-05,
      "loss": 2.3641,
      "step": 86
    },
    {
      "epoch": 0.20689655172413793,
      "grad_norm": 1.186679631328553,
      "learning_rate": 1.995949726197231e-05,
      "loss": 2.4801,
      "step": 87
    },
    {
      "epoch": 0.20927467300832342,
      "grad_norm": 1.1887498108170933,
      "learning_rate": 1.9957756633258264e-05,
      "loss": 2.2866,
      "step": 88
    },
    {
      "epoch": 0.2116527942925089,
      "grad_norm": 1.0909023774872124,
      "learning_rate": 1.9955979464133515e-05,
      "loss": 2.2916,
      "step": 89
    },
    {
      "epoch": 0.2140309155766944,
      "grad_norm": 1.1077175360558418,
      "learning_rate": 1.995416576111945e-05,
      "loss": 2.1077,
      "step": 90
    },
    {
      "epoch": 0.2164090368608799,
      "grad_norm": 1.1526064687436712,
      "learning_rate": 1.9952315530871537e-05,
      "loss": 2.2723,
      "step": 91
    },
    {
      "epoch": 0.21878715814506539,
      "grad_norm": 1.1818210038912647,
      "learning_rate": 1.9950428780179274e-05,
      "loss": 2.2338,
      "step": 92
    },
    {
      "epoch": 0.2211652794292509,
      "grad_norm": 1.164942154271255,
      "learning_rate": 1.994850551596617e-05,
      "loss": 2.3817,
      "step": 93
    },
    {
      "epoch": 0.2235434007134364,
      "grad_norm": 1.339398993177121,
      "learning_rate": 1.9946545745289727e-05,
      "loss": 2.5508,
      "step": 94
    },
    {
      "epoch": 0.2259215219976219,
      "grad_norm": 1.3267763052855093,
      "learning_rate": 1.9944549475341404e-05,
      "loss": 2.247,
      "step": 95
    },
    {
      "epoch": 0.22829964328180738,
      "grad_norm": 1.1953250811556597,
      "learning_rate": 1.99425167134466e-05,
      "loss": 2.3373,
      "step": 96
    },
    {
      "epoch": 0.23067776456599287,
      "grad_norm": 1.4321452409301854,
      "learning_rate": 1.9940447467064624e-05,
      "loss": 2.4776,
      "step": 97
    },
    {
      "epoch": 0.23305588585017836,
      "grad_norm": 1.0224444212683161,
      "learning_rate": 1.9938341743788658e-05,
      "loss": 2.1837,
      "step": 98
    },
    {
      "epoch": 0.23543400713436385,
      "grad_norm": 1.0977574950238398,
      "learning_rate": 1.9936199551345744e-05,
      "loss": 2.1478,
      "step": 99
    },
    {
      "epoch": 0.23781212841854935,
      "grad_norm": 1.0660069054078747,
      "learning_rate": 1.9934020897596752e-05,
      "loss": 2.2816,
      "step": 100
    },
    {
      "epoch": 0.24019024970273484,
      "grad_norm": 1.0312993672336248,
      "learning_rate": 1.9931805790536342e-05,
      "loss": 2.2468,
      "step": 101
    },
    {
      "epoch": 0.24256837098692033,
      "grad_norm": 1.1278898252066067,
      "learning_rate": 1.9929554238292944e-05,
      "loss": 2.0526,
      "step": 102
    },
    {
      "epoch": 0.24494649227110582,
      "grad_norm": 1.288343002944789,
      "learning_rate": 1.992726624912872e-05,
      "loss": 2.512,
      "step": 103
    },
    {
      "epoch": 0.2473246135552913,
      "grad_norm": 1.1840020386119305,
      "learning_rate": 1.992494183143955e-05,
      "loss": 2.6356,
      "step": 104
    },
    {
      "epoch": 0.2497027348394768,
      "grad_norm": 1.1014678408276726,
      "learning_rate": 1.9922580993754985e-05,
      "loss": 2.3521,
      "step": 105
    },
    {
      "epoch": 0.2497027348394768,
      "eval_loss": 2.5365779399871826,
      "eval_runtime": 66.0796,
      "eval_samples_per_second": 9.67,
      "eval_steps_per_second": 1.211,
      "step": 105
    },
    {
      "epoch": 0.2520808561236623,
      "grad_norm": 0.9957844757920508,
      "learning_rate": 1.9920183744738208e-05,
      "loss": 2.355,
      "step": 106
    },
    {
      "epoch": 0.2544589774078478,
      "grad_norm": 1.0070598447313825,
      "learning_rate": 1.9917750093186036e-05,
      "loss": 2.1747,
      "step": 107
    },
    {
      "epoch": 0.2568370986920333,
      "grad_norm": 1.2463453868295562,
      "learning_rate": 1.9915280048028853e-05,
      "loss": 2.4131,
      "step": 108
    },
    {
      "epoch": 0.25921521997621877,
      "grad_norm": 1.158558292534161,
      "learning_rate": 1.9912773618330595e-05,
      "loss": 2.4527,
      "step": 109
    },
    {
      "epoch": 0.2615933412604043,
      "grad_norm": 1.1875643459332377,
      "learning_rate": 1.9910230813288713e-05,
      "loss": 2.1523,
      "step": 110
    },
    {
      "epoch": 0.26397146254458975,
      "grad_norm": 0.892269173897758,
      "learning_rate": 1.9907651642234138e-05,
      "loss": 1.9606,
      "step": 111
    },
    {
      "epoch": 0.26634958382877527,
      "grad_norm": 1.181952902180908,
      "learning_rate": 1.9905036114631247e-05,
      "loss": 2.3201,
      "step": 112
    },
    {
      "epoch": 0.26872770511296074,
      "grad_norm": 0.9689153704257877,
      "learning_rate": 1.990238424007783e-05,
      "loss": 2.2329,
      "step": 113
    },
    {
      "epoch": 0.27110582639714625,
      "grad_norm": 1.3665918769424286,
      "learning_rate": 1.989969602830505e-05,
      "loss": 2.2387,
      "step": 114
    },
    {
      "epoch": 0.2734839476813318,
      "grad_norm": 1.0478434719151144,
      "learning_rate": 1.9896971489177417e-05,
      "loss": 2.2798,
      "step": 115
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": 1.5752154316391798,
      "learning_rate": 1.9894210632692745e-05,
      "loss": 2.201,
      "step": 116
    },
    {
      "epoch": 0.27824019024970276,
      "grad_norm": 1.0264277011384757,
      "learning_rate": 1.9891413468982112e-05,
      "loss": 2.2756,
      "step": 117
    },
    {
      "epoch": 0.2806183115338882,
      "grad_norm": 1.1750703393359614,
      "learning_rate": 1.988858000830983e-05,
      "loss": 2.1907,
      "step": 118
    },
    {
      "epoch": 0.28299643281807374,
      "grad_norm": 0.9456957190962577,
      "learning_rate": 1.9885710261073402e-05,
      "loss": 2.2993,
      "step": 119
    },
    {
      "epoch": 0.2853745541022592,
      "grad_norm": 1.37591692336223,
      "learning_rate": 1.9882804237803487e-05,
      "loss": 2.0751,
      "step": 120
    },
    {
      "epoch": 0.2877526753864447,
      "grad_norm": 0.991181263305241,
      "learning_rate": 1.9879861949163863e-05,
      "loss": 2.1946,
      "step": 121
    },
    {
      "epoch": 0.2901307966706302,
      "grad_norm": 1.2826616603092615,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 2.3084,
      "step": 122
    },
    {
      "epoch": 0.2925089179548157,
      "grad_norm": 1.3162982027829009,
      "learning_rate": 1.987386861909593e-05,
      "loss": 2.294,
      "step": 123
    },
    {
      "epoch": 0.29488703923900117,
      "grad_norm": 1.086311999313279,
      "learning_rate": 1.98708175996604e-05,
      "loss": 2.3025,
      "step": 124
    },
    {
      "epoch": 0.2972651605231867,
      "grad_norm": 1.10683170372015,
      "learning_rate": 1.986773035884064e-05,
      "loss": 2.3447,
      "step": 125
    },
    {
      "epoch": 0.29964328180737215,
      "grad_norm": 1.090568761480393,
      "learning_rate": 1.9864606907965407e-05,
      "loss": 2.4104,
      "step": 126
    },
    {
      "epoch": 0.30202140309155767,
      "grad_norm": 1.4024759238343605,
      "learning_rate": 1.986144725849634e-05,
      "loss": 2.298,
      "step": 127
    },
    {
      "epoch": 0.30439952437574314,
      "grad_norm": 0.9324914520062791,
      "learning_rate": 1.9858251422027903e-05,
      "loss": 2.1123,
      "step": 128
    },
    {
      "epoch": 0.30677764565992865,
      "grad_norm": 1.3818136151492852,
      "learning_rate": 1.9855019410287355e-05,
      "loss": 2.2786,
      "step": 129
    },
    {
      "epoch": 0.3091557669441142,
      "grad_norm": 0.9879756737720099,
      "learning_rate": 1.98517512351347e-05,
      "loss": 2.2735,
      "step": 130
    },
    {
      "epoch": 0.31153388822829964,
      "grad_norm": 1.4107106057474024,
      "learning_rate": 1.9848446908562647e-05,
      "loss": 2.2421,
      "step": 131
    },
    {
      "epoch": 0.31391200951248516,
      "grad_norm": 0.978862094447652,
      "learning_rate": 1.9845106442696563e-05,
      "loss": 2.4152,
      "step": 132
    },
    {
      "epoch": 0.3162901307966706,
      "grad_norm": 1.3714074038447606,
      "learning_rate": 1.9841729849794427e-05,
      "loss": 2.4567,
      "step": 133
    },
    {
      "epoch": 0.31866825208085614,
      "grad_norm": 1.030641093673837,
      "learning_rate": 1.983831714224679e-05,
      "loss": 2.3015,
      "step": 134
    },
    {
      "epoch": 0.3210463733650416,
      "grad_norm": 1.1744699755999302,
      "learning_rate": 1.9834868332576727e-05,
      "loss": 2.2878,
      "step": 135
    },
    {
      "epoch": 0.3234244946492271,
      "grad_norm": 0.9733999816490441,
      "learning_rate": 1.9831383433439798e-05,
      "loss": 2.1571,
      "step": 136
    },
    {
      "epoch": 0.3258026159334126,
      "grad_norm": 1.0470367999253474,
      "learning_rate": 1.982786245762398e-05,
      "loss": 2.0943,
      "step": 137
    },
    {
      "epoch": 0.3281807372175981,
      "grad_norm": 1.0748276455064096,
      "learning_rate": 1.9824305418049645e-05,
      "loss": 2.4156,
      "step": 138
    },
    {
      "epoch": 0.33055885850178357,
      "grad_norm": 1.0220509349947084,
      "learning_rate": 1.9820712327769503e-05,
      "loss": 2.1898,
      "step": 139
    },
    {
      "epoch": 0.3329369797859691,
      "grad_norm": 0.9811166423920332,
      "learning_rate": 1.9817083199968552e-05,
      "loss": 2.3449,
      "step": 140
    },
    {
      "epoch": 0.33531510107015455,
      "grad_norm": 1.0664757695722766,
      "learning_rate": 1.9813418047964025e-05,
      "loss": 2.1514,
      "step": 141
    },
    {
      "epoch": 0.3376932223543401,
      "grad_norm": 1.1228830278366924,
      "learning_rate": 1.9809716885205363e-05,
      "loss": 2.3371,
      "step": 142
    },
    {
      "epoch": 0.3400713436385256,
      "grad_norm": 1.0703957613617774,
      "learning_rate": 1.980597972527413e-05,
      "loss": 2.2577,
      "step": 143
    },
    {
      "epoch": 0.34244946492271106,
      "grad_norm": 0.9971842999532138,
      "learning_rate": 1.9802206581883992e-05,
      "loss": 2.2048,
      "step": 144
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 0.9969712850303254,
      "learning_rate": 1.979839746888067e-05,
      "loss": 2.1725,
      "step": 145
    },
    {
      "epoch": 0.34720570749108204,
      "grad_norm": 0.9782490093980141,
      "learning_rate": 1.979455240024186e-05,
      "loss": 2.1598,
      "step": 146
    },
    {
      "epoch": 0.34958382877526756,
      "grad_norm": 1.1595035293528873,
      "learning_rate": 1.97906713900772e-05,
      "loss": 2.1812,
      "step": 147
    },
    {
      "epoch": 0.351961950059453,
      "grad_norm": 1.0488323565717943,
      "learning_rate": 1.9786754452628226e-05,
      "loss": 2.126,
      "step": 148
    },
    {
      "epoch": 0.35434007134363854,
      "grad_norm": 1.0236205683546673,
      "learning_rate": 1.9782801602268306e-05,
      "loss": 1.9399,
      "step": 149
    },
    {
      "epoch": 0.356718192627824,
      "grad_norm": 0.983049547537296,
      "learning_rate": 1.9778812853502592e-05,
      "loss": 2.0336,
      "step": 150
    },
    {
      "epoch": 0.3590963139120095,
      "grad_norm": 1.0856474713800959,
      "learning_rate": 1.9774788220967968e-05,
      "loss": 2.2103,
      "step": 151
    },
    {
      "epoch": 0.361474435196195,
      "grad_norm": 1.098143269144179,
      "learning_rate": 1.9770727719432994e-05,
      "loss": 2.1425,
      "step": 152
    },
    {
      "epoch": 0.3638525564803805,
      "grad_norm": 1.1908904777112574,
      "learning_rate": 1.9766631363797852e-05,
      "loss": 2.2516,
      "step": 153
    },
    {
      "epoch": 0.36623067776456597,
      "grad_norm": 1.1823343263781934,
      "learning_rate": 1.9762499169094288e-05,
      "loss": 2.0991,
      "step": 154
    },
    {
      "epoch": 0.3686087990487515,
      "grad_norm": 1.1543274307271654,
      "learning_rate": 1.9758331150485576e-05,
      "loss": 2.2917,
      "step": 155
    },
    {
      "epoch": 0.37098692033293695,
      "grad_norm": 1.1828452156246019,
      "learning_rate": 1.9754127323266426e-05,
      "loss": 2.3577,
      "step": 156
    },
    {
      "epoch": 0.3733650416171225,
      "grad_norm": 1.2458434785978698,
      "learning_rate": 1.9749887702862972e-05,
      "loss": 2.2291,
      "step": 157
    },
    {
      "epoch": 0.375743162901308,
      "grad_norm": 1.0632348458757013,
      "learning_rate": 1.9745612304832672e-05,
      "loss": 2.495,
      "step": 158
    },
    {
      "epoch": 0.37812128418549346,
      "grad_norm": 1.2413557275846534,
      "learning_rate": 1.9741301144864284e-05,
      "loss": 2.3006,
      "step": 159
    },
    {
      "epoch": 0.380499405469679,
      "grad_norm": 1.068837985332943,
      "learning_rate": 1.9736954238777793e-05,
      "loss": 2.2228,
      "step": 160
    },
    {
      "epoch": 0.38287752675386444,
      "grad_norm": 1.181973772137545,
      "learning_rate": 1.9732571602524353e-05,
      "loss": 2.3419,
      "step": 161
    },
    {
      "epoch": 0.38525564803804996,
      "grad_norm": 0.9361759344356807,
      "learning_rate": 1.972815325218624e-05,
      "loss": 2.2727,
      "step": 162
    },
    {
      "epoch": 0.3876337693222354,
      "grad_norm": 1.2300672941710984,
      "learning_rate": 1.9723699203976768e-05,
      "loss": 2.3947,
      "step": 163
    },
    {
      "epoch": 0.39001189060642094,
      "grad_norm": 0.9647921025871186,
      "learning_rate": 1.9719209474240263e-05,
      "loss": 1.8388,
      "step": 164
    },
    {
      "epoch": 0.3923900118906064,
      "grad_norm": 1.1390311715526416,
      "learning_rate": 1.971468407945198e-05,
      "loss": 2.4054,
      "step": 165
    },
    {
      "epoch": 0.3947681331747919,
      "grad_norm": 0.9830051867519547,
      "learning_rate": 1.9710123036218044e-05,
      "loss": 2.0355,
      "step": 166
    },
    {
      "epoch": 0.3971462544589774,
      "grad_norm": 1.1244517585073737,
      "learning_rate": 1.97055263612754e-05,
      "loss": 2.0188,
      "step": 167
    },
    {
      "epoch": 0.3995243757431629,
      "grad_norm": 1.0256020852263494,
      "learning_rate": 1.9700894071491736e-05,
      "loss": 2.0774,
      "step": 168
    },
    {
      "epoch": 0.40190249702734837,
      "grad_norm": 1.011023720252716,
      "learning_rate": 1.9696226183865436e-05,
      "loss": 2.2592,
      "step": 169
    },
    {
      "epoch": 0.4042806183115339,
      "grad_norm": 1.046975898884085,
      "learning_rate": 1.969152271552552e-05,
      "loss": 2.1791,
      "step": 170
    },
    {
      "epoch": 0.40665873959571935,
      "grad_norm": 1.1800984480399852,
      "learning_rate": 1.9686783683731557e-05,
      "loss": 2.3941,
      "step": 171
    },
    {
      "epoch": 0.4090368608799049,
      "grad_norm": 1.2459882622321672,
      "learning_rate": 1.9682009105873633e-05,
      "loss": 2.1522,
      "step": 172
    },
    {
      "epoch": 0.4114149821640904,
      "grad_norm": 1.0732133381850257,
      "learning_rate": 1.9677198999472257e-05,
      "loss": 2.1233,
      "step": 173
    },
    {
      "epoch": 0.41379310344827586,
      "grad_norm": 1.2405484917580802,
      "learning_rate": 1.967235338217832e-05,
      "loss": 2.3016,
      "step": 174
    },
    {
      "epoch": 0.4161712247324614,
      "grad_norm": 1.0759940201219593,
      "learning_rate": 1.9667472271773026e-05,
      "loss": 2.2947,
      "step": 175
    },
    {
      "epoch": 0.41854934601664684,
      "grad_norm": 1.2008734320661734,
      "learning_rate": 1.9662555686167808e-05,
      "loss": 2.2155,
      "step": 176
    },
    {
      "epoch": 0.42092746730083236,
      "grad_norm": 0.9303619935178572,
      "learning_rate": 1.965760364340429e-05,
      "loss": 2.1234,
      "step": 177
    },
    {
      "epoch": 0.4233055885850178,
      "grad_norm": 1.3884826767438652,
      "learning_rate": 1.9652616161654204e-05,
      "loss": 2.2539,
      "step": 178
    },
    {
      "epoch": 0.42568370986920334,
      "grad_norm": 0.9947187673832885,
      "learning_rate": 1.9647593259219328e-05,
      "loss": 2.2052,
      "step": 179
    },
    {
      "epoch": 0.4280618311533888,
      "grad_norm": 1.4655922792083054,
      "learning_rate": 1.964253495453141e-05,
      "loss": 2.1552,
      "step": 180
    },
    {
      "epoch": 0.4304399524375743,
      "grad_norm": 1.1481294188693778,
      "learning_rate": 1.963744126615212e-05,
      "loss": 2.3942,
      "step": 181
    },
    {
      "epoch": 0.4328180737217598,
      "grad_norm": 1.239760521409481,
      "learning_rate": 1.9632312212772956e-05,
      "loss": 2.3091,
      "step": 182
    },
    {
      "epoch": 0.4351961950059453,
      "grad_norm": 1.0524654460411744,
      "learning_rate": 1.9627147813215207e-05,
      "loss": 2.302,
      "step": 183
    },
    {
      "epoch": 0.43757431629013077,
      "grad_norm": 1.0231645108607732,
      "learning_rate": 1.9621948086429847e-05,
      "loss": 2.2334,
      "step": 184
    },
    {
      "epoch": 0.4399524375743163,
      "grad_norm": 1.0600582051447691,
      "learning_rate": 1.9616713051497496e-05,
      "loss": 2.2044,
      "step": 185
    },
    {
      "epoch": 0.4423305588585018,
      "grad_norm": 1.0861978175484295,
      "learning_rate": 1.9611442727628344e-05,
      "loss": 2.3267,
      "step": 186
    },
    {
      "epoch": 0.4447086801426873,
      "grad_norm": 1.0122924353396487,
      "learning_rate": 1.960613713416206e-05,
      "loss": 2.2327,
      "step": 187
    },
    {
      "epoch": 0.4470868014268728,
      "grad_norm": 1.1275635495135592,
      "learning_rate": 1.9600796290567747e-05,
      "loss": 2.2474,
      "step": 188
    },
    {
      "epoch": 0.44946492271105826,
      "grad_norm": 1.0778906611663819,
      "learning_rate": 1.9595420216443864e-05,
      "loss": 2.2777,
      "step": 189
    },
    {
      "epoch": 0.4518430439952438,
      "grad_norm": 1.0593499669893551,
      "learning_rate": 1.9590008931518133e-05,
      "loss": 2.4937,
      "step": 190
    },
    {
      "epoch": 0.45422116527942924,
      "grad_norm": 1.0887914371115388,
      "learning_rate": 1.9584562455647494e-05,
      "loss": 2.2577,
      "step": 191
    },
    {
      "epoch": 0.45659928656361476,
      "grad_norm": 1.0280779311785984,
      "learning_rate": 1.9579080808818035e-05,
      "loss": 2.2352,
      "step": 192
    },
    {
      "epoch": 0.4589774078478002,
      "grad_norm": 1.1201705856067985,
      "learning_rate": 1.9573564011144873e-05,
      "loss": 2.1482,
      "step": 193
    },
    {
      "epoch": 0.46135552913198574,
      "grad_norm": 1.0039435227655624,
      "learning_rate": 1.9568012082872148e-05,
      "loss": 2.1069,
      "step": 194
    },
    {
      "epoch": 0.4637336504161712,
      "grad_norm": 1.0523831000821406,
      "learning_rate": 1.9562425044372884e-05,
      "loss": 1.9268,
      "step": 195
    },
    {
      "epoch": 0.4661117717003567,
      "grad_norm": 1.0635880350342213,
      "learning_rate": 1.9556802916148963e-05,
      "loss": 2.2722,
      "step": 196
    },
    {
      "epoch": 0.4684898929845422,
      "grad_norm": 2.4351848601787287,
      "learning_rate": 1.955114571883102e-05,
      "loss": 2.1402,
      "step": 197
    },
    {
      "epoch": 0.4708680142687277,
      "grad_norm": 1.2199308274597462,
      "learning_rate": 1.9545453473178384e-05,
      "loss": 2.2599,
      "step": 198
    },
    {
      "epoch": 0.47324613555291317,
      "grad_norm": 0.9936114796299212,
      "learning_rate": 1.9539726200078987e-05,
      "loss": 2.0662,
      "step": 199
    },
    {
      "epoch": 0.4756242568370987,
      "grad_norm": 1.0692703333507547,
      "learning_rate": 1.9533963920549307e-05,
      "loss": 2.3739,
      "step": 200
    },
    {
      "epoch": 0.4780023781212842,
      "grad_norm": 1.0406002686664542,
      "learning_rate": 1.9528166655734267e-05,
      "loss": 2.3611,
      "step": 201
    },
    {
      "epoch": 0.4803804994054697,
      "grad_norm": 1.9375905536343168,
      "learning_rate": 1.9522334426907185e-05,
      "loss": 2.0971,
      "step": 202
    },
    {
      "epoch": 0.4827586206896552,
      "grad_norm": 1.024548704059581,
      "learning_rate": 1.951646725546966e-05,
      "loss": 2.2498,
      "step": 203
    },
    {
      "epoch": 0.48513674197384066,
      "grad_norm": 1.0033895284405978,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 2.299,
      "step": 204
    },
    {
      "epoch": 0.4875148632580262,
      "grad_norm": 1.541631519071697,
      "learning_rate": 1.950462817101079e-05,
      "loss": 2.4076,
      "step": 205
    },
    {
      "epoch": 0.48989298454221164,
      "grad_norm": 0.9499702987331401,
      "learning_rate": 1.9498656301433466e-05,
      "loss": 2.0754,
      "step": 206
    },
    {
      "epoch": 0.49227110582639716,
      "grad_norm": 1.099383371761328,
      "learning_rate": 1.9492649576133594e-05,
      "loss": 2.2514,
      "step": 207
    },
    {
      "epoch": 0.4946492271105826,
      "grad_norm": 0.9296431838496088,
      "learning_rate": 1.94866080171531e-05,
      "loss": 2.2308,
      "step": 208
    },
    {
      "epoch": 0.49702734839476814,
      "grad_norm": 4.140796209905845,
      "learning_rate": 1.9480531646661753e-05,
      "loss": 2.4388,
      "step": 209
    },
    {
      "epoch": 0.4994054696789536,
      "grad_norm": 1.011142238194789,
      "learning_rate": 1.9474420486957045e-05,
      "loss": 2.2414,
      "step": 210
    },
    {
      "epoch": 0.4994054696789536,
      "eval_loss": 2.49302339553833,
      "eval_runtime": 65.8636,
      "eval_samples_per_second": 9.702,
      "eval_steps_per_second": 1.215,
      "step": 210
    }
  ],
  "logging_steps": 1,
  "max_steps": 1680,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 210,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3027116576669696e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}