{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.985148514851485,
  "eval_steps": 500,
  "global_step": 201,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01485148514851485,
      "grad_norm": 6.48456557234758,
      "learning_rate": 4.7619047619047623e-07,
      "loss": 1.1703,
      "step": 1
    },
    {
      "epoch": 0.0297029702970297,
      "grad_norm": 6.594689369570434,
      "learning_rate": 9.523809523809525e-07,
      "loss": 1.1918,
      "step": 2
    },
    {
      "epoch": 0.04455445544554455,
      "grad_norm": 6.23293374565609,
      "learning_rate": 1.4285714285714286e-06,
      "loss": 1.1576,
      "step": 3
    },
    {
      "epoch": 0.0594059405940594,
      "grad_norm": 6.401466218218343,
      "learning_rate": 1.904761904761905e-06,
      "loss": 1.2099,
      "step": 4
    },
    {
      "epoch": 0.07425742574257425,
      "grad_norm": 5.7694144179716,
      "learning_rate": 2.380952380952381e-06,
      "loss": 1.1447,
      "step": 5
    },
    {
      "epoch": 0.0891089108910891,
      "grad_norm": 4.584773158856208,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 1.1128,
      "step": 6
    },
    {
      "epoch": 0.10396039603960396,
      "grad_norm": 4.408264566567633,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.1444,
      "step": 7
    },
    {
      "epoch": 0.1188118811881188,
      "grad_norm": 2.6961190293519213,
      "learning_rate": 3.80952380952381e-06,
      "loss": 1.0333,
      "step": 8
    },
    {
      "epoch": 0.13366336633663367,
      "grad_norm": 2.366910263126932,
      "learning_rate": 4.2857142857142855e-06,
      "loss": 1.039,
      "step": 9
    },
    {
      "epoch": 0.1485148514851485,
      "grad_norm": 3.6999770055634555,
      "learning_rate": 4.761904761904762e-06,
      "loss": 1.0171,
      "step": 10
    },
    {
      "epoch": 0.16336633663366337,
      "grad_norm": 3.894316339063172,
      "learning_rate": 5.2380952380952384e-06,
      "loss": 1.0232,
      "step": 11
    },
    {
      "epoch": 0.1782178217821782,
      "grad_norm": 3.8249399482892703,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 1.0875,
      "step": 12
    },
    {
      "epoch": 0.19306930693069307,
      "grad_norm": 3.0670108504304334,
      "learning_rate": 6.1904761904761914e-06,
      "loss": 1.0108,
      "step": 13
    },
    {
      "epoch": 0.2079207920792079,
      "grad_norm": 2.6030053112293676,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.9857,
      "step": 14
    },
    {
      "epoch": 0.22277227722772278,
      "grad_norm": 2.370576635506437,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 0.9728,
      "step": 15
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 2.3399338429829615,
      "learning_rate": 7.61904761904762e-06,
      "loss": 0.9694,
      "step": 16
    },
    {
      "epoch": 0.2524752475247525,
      "grad_norm": 1.8311702968068935,
      "learning_rate": 8.095238095238097e-06,
      "loss": 0.934,
      "step": 17
    },
    {
      "epoch": 0.26732673267326734,
      "grad_norm": 1.4308728197686567,
      "learning_rate": 8.571428571428571e-06,
      "loss": 0.9175,
      "step": 18
    },
    {
      "epoch": 0.28217821782178215,
      "grad_norm": 1.5620018816986423,
      "learning_rate": 9.047619047619049e-06,
      "loss": 0.9595,
      "step": 19
    },
    {
      "epoch": 0.297029702970297,
      "grad_norm": 1.4122378912732825,
      "learning_rate": 9.523809523809525e-06,
      "loss": 0.9082,
      "step": 20
    },
    {
      "epoch": 0.3118811881188119,
      "grad_norm": 1.2544223318659375,
      "learning_rate": 1e-05,
      "loss": 0.8293,
      "step": 21
    },
    {
      "epoch": 0.32673267326732675,
      "grad_norm": 1.0621864931131515,
      "learning_rate": 9.999238475781957e-06,
      "loss": 0.8615,
      "step": 22
    },
    {
      "epoch": 0.3415841584158416,
      "grad_norm": 1.067756678297183,
      "learning_rate": 9.99695413509548e-06,
      "loss": 0.8963,
      "step": 23
    },
    {
      "epoch": 0.3564356435643564,
      "grad_norm": 1.1625635155258327,
      "learning_rate": 9.993147673772869e-06,
      "loss": 0.875,
      "step": 24
    },
    {
      "epoch": 0.3712871287128713,
      "grad_norm": 0.9411109178322155,
      "learning_rate": 9.987820251299121e-06,
      "loss": 0.8488,
      "step": 25
    },
    {
      "epoch": 0.38613861386138615,
      "grad_norm": 0.8920662981646181,
      "learning_rate": 9.980973490458728e-06,
      "loss": 0.8838,
      "step": 26
    },
    {
      "epoch": 0.400990099009901,
      "grad_norm": 0.9110888685882579,
      "learning_rate": 9.972609476841368e-06,
      "loss": 0.8299,
      "step": 27
    },
    {
      "epoch": 0.4158415841584158,
      "grad_norm": 0.8423480290666405,
      "learning_rate": 9.962730758206612e-06,
      "loss": 0.866,
      "step": 28
    },
    {
      "epoch": 0.4306930693069307,
      "grad_norm": 0.8825677961798845,
      "learning_rate": 9.951340343707852e-06,
      "loss": 0.8509,
      "step": 29
    },
    {
      "epoch": 0.44554455445544555,
      "grad_norm": 0.7581834656729458,
      "learning_rate": 9.938441702975689e-06,
      "loss": 0.8288,
      "step": 30
    },
    {
      "epoch": 0.4603960396039604,
      "grad_norm": 1.055473120057636,
      "learning_rate": 9.924038765061042e-06,
      "loss": 0.838,
      "step": 31
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 0.7922082592771019,
      "learning_rate": 9.908135917238321e-06,
      "loss": 0.8609,
      "step": 32
    },
    {
      "epoch": 0.4900990099009901,
      "grad_norm": 0.754302150819188,
      "learning_rate": 9.890738003669029e-06,
      "loss": 0.8583,
      "step": 33
    },
    {
      "epoch": 0.504950495049505,
      "grad_norm": 1.0626447047968044,
      "learning_rate": 9.871850323926178e-06,
      "loss": 0.7944,
      "step": 34
    },
    {
      "epoch": 0.5198019801980198,
      "grad_norm": 0.8923345386621004,
      "learning_rate": 9.851478631379982e-06,
      "loss": 0.8975,
      "step": 35
    },
    {
      "epoch": 0.5346534653465347,
      "grad_norm": 0.7366372348142536,
      "learning_rate": 9.829629131445342e-06,
      "loss": 0.8676,
      "step": 36
    },
    {
      "epoch": 0.5495049504950495,
      "grad_norm": 1.2738146882781316,
      "learning_rate": 9.806308479691595e-06,
      "loss": 0.8975,
      "step": 37
    },
    {
      "epoch": 0.5643564356435643,
      "grad_norm": 0.8592154350621992,
      "learning_rate": 9.781523779815178e-06,
      "loss": 0.8207,
      "step": 38
    },
    {
      "epoch": 0.5792079207920792,
      "grad_norm": 0.7049611640819059,
      "learning_rate": 9.755282581475769e-06,
      "loss": 0.8416,
      "step": 39
    },
    {
      "epoch": 0.594059405940594,
      "grad_norm": 0.8172609258295951,
      "learning_rate": 9.727592877996585e-06,
      "loss": 0.9003,
      "step": 40
    },
    {
      "epoch": 0.6089108910891089,
      "grad_norm": 0.943383839148404,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.8279,
      "step": 41
    },
    {
      "epoch": 0.6237623762376238,
      "grad_norm": 0.8200827897891733,
      "learning_rate": 9.667902132486009e-06,
      "loss": 0.8252,
      "step": 42
    },
    {
      "epoch": 0.6386138613861386,
      "grad_norm": 0.750459606762128,
      "learning_rate": 9.635919272833938e-06,
      "loss": 0.8417,
      "step": 43
    },
    {
      "epoch": 0.6534653465346535,
      "grad_norm": 0.8256180076390092,
      "learning_rate": 9.602524267262202e-06,
      "loss": 0.8068,
      "step": 44
    },
    {
      "epoch": 0.6683168316831684,
      "grad_norm": 0.7362971479000804,
      "learning_rate": 9.567727288213005e-06,
      "loss": 0.8116,
      "step": 45
    },
    {
      "epoch": 0.6831683168316832,
      "grad_norm": 0.6611484879378139,
      "learning_rate": 9.531538935183252e-06,
      "loss": 0.8049,
      "step": 46
    },
    {
      "epoch": 0.698019801980198,
      "grad_norm": 0.6483590920807921,
      "learning_rate": 9.493970231495836e-06,
      "loss": 0.8158,
      "step": 47
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 0.6499715006108466,
      "learning_rate": 9.45503262094184e-06,
      "loss": 0.7963,
      "step": 48
    },
    {
      "epoch": 0.7277227722772277,
      "grad_norm": 0.6445318374705665,
      "learning_rate": 9.414737964294636e-06,
      "loss": 0.8372,
      "step": 49
    },
    {
      "epoch": 0.7425742574257426,
      "grad_norm": 0.6749851299246947,
      "learning_rate": 9.37309853569698e-06,
      "loss": 0.7974,
      "step": 50
    },
    {
      "epoch": 0.7574257425742574,
      "grad_norm": 0.6430920805349686,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.797,
      "step": 51
    },
    {
      "epoch": 0.7722772277227723,
      "grad_norm": 0.7122774157069339,
      "learning_rate": 9.285836503510562e-06,
      "loss": 0.8178,
      "step": 52
    },
    {
      "epoch": 0.7871287128712872,
      "grad_norm": 0.6222782441453497,
      "learning_rate": 9.24024048078213e-06,
      "loss": 0.8286,
      "step": 53
    },
    {
      "epoch": 0.801980198019802,
      "grad_norm": 0.6774898848973883,
      "learning_rate": 9.193352839727122e-06,
      "loss": 0.8199,
      "step": 54
    },
    {
      "epoch": 0.8168316831683168,
      "grad_norm": 0.6685577033399003,
      "learning_rate": 9.145187862775208e-06,
      "loss": 0.8325,
      "step": 55
    },
    {
      "epoch": 0.8316831683168316,
      "grad_norm": 0.6954610466193606,
      "learning_rate": 9.09576022144496e-06,
      "loss": 0.7876,
      "step": 56
    },
    {
      "epoch": 0.8465346534653465,
      "grad_norm": 0.6717917465533401,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.7889,
      "step": 57
    },
    {
      "epoch": 0.8613861386138614,
      "grad_norm": 0.6710948817812145,
      "learning_rate": 8.993177550236464e-06,
      "loss": 0.819,
      "step": 58
    },
    {
      "epoch": 0.8762376237623762,
      "grad_norm": 0.6677437938362905,
      "learning_rate": 8.94005376803361e-06,
      "loss": 0.815,
      "step": 59
    },
    {
      "epoch": 0.8910891089108911,
      "grad_norm": 0.6333145369648289,
      "learning_rate": 8.885729807284855e-06,
      "loss": 0.8033,
      "step": 60
    },
    {
      "epoch": 0.905940594059406,
      "grad_norm": 0.810414558269581,
      "learning_rate": 8.83022221559489e-06,
      "loss": 0.8495,
      "step": 61
    },
    {
      "epoch": 0.9207920792079208,
      "grad_norm": 0.8092632573192287,
      "learning_rate": 8.773547901113862e-06,
      "loss": 0.7934,
      "step": 62
    },
    {
      "epoch": 0.9356435643564357,
      "grad_norm": 0.6595329129270622,
      "learning_rate": 8.715724127386971e-06,
      "loss": 0.8037,
      "step": 63
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 0.8763924940559503,
      "learning_rate": 8.656768508095853e-06,
      "loss": 0.8148,
      "step": 64
    },
    {
      "epoch": 0.9653465346534653,
      "grad_norm": 0.7170557641262976,
      "learning_rate": 8.596699001693257e-06,
      "loss": 0.8634,
      "step": 65
    },
    {
      "epoch": 0.9801980198019802,
      "grad_norm": 0.7120219047413958,
      "learning_rate": 8.535533905932739e-06,
      "loss": 0.8066,
      "step": 66
    },
    {
      "epoch": 0.995049504950495,
      "grad_norm": 0.7743156368261691,
      "learning_rate": 8.473291852294986e-06,
      "loss": 0.7911,
      "step": 67
    },
    {
      "epoch": 1.00990099009901,
      "grad_norm": 1.3350443160879135,
      "learning_rate": 8.409991800312493e-06,
      "loss": 1.252,
      "step": 68
    },
    {
      "epoch": 1.0247524752475248,
      "grad_norm": 0.7990302178349659,
      "learning_rate": 8.345653031794292e-06,
      "loss": 0.8425,
      "step": 69
    },
    {
      "epoch": 1.0396039603960396,
      "grad_norm": 0.6239804634649714,
      "learning_rate": 8.280295144952537e-06,
      "loss": 0.6491,
      "step": 70
    },
    {
      "epoch": 1.0544554455445545,
      "grad_norm": 0.6694927788559727,
      "learning_rate": 8.213938048432697e-06,
      "loss": 0.7202,
      "step": 71
    },
    {
      "epoch": 1.0693069306930694,
      "grad_norm": 0.7432686527943043,
      "learning_rate": 8.146601955249187e-06,
      "loss": 0.741,
      "step": 72
    },
    {
      "epoch": 1.0841584158415842,
      "grad_norm": 0.6416160685114952,
      "learning_rate": 8.078307376628292e-06,
      "loss": 0.8075,
      "step": 73
    },
    {
      "epoch": 1.099009900990099,
      "grad_norm": 0.698781285729984,
      "learning_rate": 8.009075115760243e-06,
      "loss": 0.6919,
      "step": 74
    },
    {
      "epoch": 1.113861386138614,
      "grad_norm": 0.6958006649391136,
      "learning_rate": 7.938926261462366e-06,
      "loss": 0.6921,
      "step": 75
    },
    {
      "epoch": 1.1287128712871288,
      "grad_norm": 0.6237956171364151,
      "learning_rate": 7.86788218175523e-06,
      "loss": 0.7287,
      "step": 76
    },
    {
      "epoch": 1.1435643564356435,
      "grad_norm": 0.7252061300181446,
      "learning_rate": 7.795964517353734e-06,
      "loss": 0.8264,
      "step": 77
    },
    {
      "epoch": 1.1584158415841583,
      "grad_norm": 0.674352802334064,
      "learning_rate": 7.723195175075136e-06,
      "loss": 0.6763,
      "step": 78
    },
    {
      "epoch": 1.1732673267326732,
      "grad_norm": 0.6546358450685043,
      "learning_rate": 7.649596321166024e-06,
      "loss": 0.7588,
      "step": 79
    },
    {
      "epoch": 1.188118811881188,
      "grad_norm": 0.6479565965693698,
      "learning_rate": 7.575190374550272e-06,
      "loss": 0.7277,
      "step": 80
    },
    {
      "epoch": 1.202970297029703,
      "grad_norm": 0.6626458405633724,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.7174,
      "step": 81
    },
    {
      "epoch": 1.2178217821782178,
      "grad_norm": 0.6756782160293404,
      "learning_rate": 7.424048101231687e-06,
      "loss": 0.7548,
      "step": 82
    },
    {
      "epoch": 1.2326732673267327,
      "grad_norm": 0.808652221633845,
      "learning_rate": 7.347357813929455e-06,
      "loss": 0.7933,
      "step": 83
    },
    {
      "epoch": 1.2475247524752475,
      "grad_norm": 0.573811498550998,
      "learning_rate": 7.269952498697734e-06,
      "loss": 0.6931,
      "step": 84
    },
    {
      "epoch": 1.2623762376237624,
      "grad_norm": 0.646918318906572,
      "learning_rate": 7.191855733945388e-06,
      "loss": 0.7785,
      "step": 85
    },
    {
      "epoch": 1.2772277227722773,
      "grad_norm": 0.5958671013573899,
      "learning_rate": 7.113091308703498e-06,
      "loss": 0.709,
      "step": 86
    },
    {
      "epoch": 1.2920792079207921,
      "grad_norm": 0.7165583961725527,
      "learning_rate": 7.033683215379002e-06,
      "loss": 0.6866,
      "step": 87
    },
    {
      "epoch": 1.306930693069307,
      "grad_norm": 0.8848970604430635,
      "learning_rate": 6.953655642446368e-06,
      "loss": 0.7576,
      "step": 88
    },
    {
      "epoch": 1.3217821782178218,
      "grad_norm": 0.6315927520470037,
      "learning_rate": 6.873032967079562e-06,
      "loss": 0.7615,
      "step": 89
    },
    {
      "epoch": 1.3366336633663367,
      "grad_norm": 0.6472208368826241,
      "learning_rate": 6.7918397477265e-06,
      "loss": 0.7158,
      "step": 90
    },
    {
      "epoch": 1.3514851485148514,
      "grad_norm": 0.8136088626747461,
      "learning_rate": 6.710100716628345e-06,
      "loss": 0.8109,
      "step": 91
    },
    {
      "epoch": 1.3663366336633662,
      "grad_norm": 0.6789106969356933,
      "learning_rate": 6.627840772285784e-06,
      "loss": 0.6553,
      "step": 92
    },
    {
      "epoch": 1.381188118811881,
      "grad_norm": 0.6684192399196682,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.7604,
      "step": 93
    },
    {
      "epoch": 1.396039603960396,
      "grad_norm": 0.6470872320361255,
      "learning_rate": 6.461858523613684e-06,
      "loss": 0.7548,
      "step": 94
    },
    {
      "epoch": 1.4108910891089108,
      "grad_norm": 0.6486567165728302,
      "learning_rate": 6.378186779084996e-06,
      "loss": 0.7484,
      "step": 95
    },
    {
      "epoch": 1.4257425742574257,
      "grad_norm": 0.8461471561359525,
      "learning_rate": 6.294095225512604e-06,
      "loss": 0.7523,
      "step": 96
    },
    {
      "epoch": 1.4405940594059405,
      "grad_norm": 0.6814439448544345,
      "learning_rate": 6.209609477998339e-06,
      "loss": 0.7334,
      "step": 97
    },
    {
      "epoch": 1.4554455445544554,
      "grad_norm": 0.5328496145736351,
      "learning_rate": 6.124755271719326e-06,
      "loss": 0.6584,
      "step": 98
    },
    {
      "epoch": 1.4702970297029703,
      "grad_norm": 0.680813767822209,
      "learning_rate": 6.039558454088796e-06,
      "loss": 0.8677,
      "step": 99
    },
    {
      "epoch": 1.4851485148514851,
      "grad_norm": 0.7359886080900357,
      "learning_rate": 5.954044976882725e-06,
      "loss": 0.7591,
      "step": 100
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.6483808901598864,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 0.7024,
      "step": 101
    },
    {
      "epoch": 1.5148514851485149,
      "grad_norm": 0.573259352808237,
      "learning_rate": 5.782172325201155e-06,
      "loss": 0.7647,
      "step": 102
    },
    {
      "epoch": 1.5297029702970297,
      "grad_norm": 0.620232903115091,
      "learning_rate": 5.695865504800328e-06,
      "loss": 0.746,
      "step": 103
    },
    {
      "epoch": 1.5445544554455446,
      "grad_norm": 0.6008704350145148,
      "learning_rate": 5.609346717025738e-06,
      "loss": 0.7653,
      "step": 104
    },
    {
      "epoch": 1.5594059405940595,
      "grad_norm": 0.6651231967169247,
      "learning_rate": 5.522642316338268e-06,
      "loss": 0.7284,
      "step": 105
    },
    {
      "epoch": 1.5742574257425743,
      "grad_norm": 0.6508987525775917,
      "learning_rate": 5.435778713738292e-06,
      "loss": 0.7081,
      "step": 106
    },
    {
      "epoch": 1.5891089108910892,
      "grad_norm": 0.6668715575162661,
      "learning_rate": 5.348782368720627e-06,
      "loss": 0.7653,
      "step": 107
    },
    {
      "epoch": 1.603960396039604,
      "grad_norm": 0.5993279825702773,
      "learning_rate": 5.2616797812147205e-06,
      "loss": 0.6936,
      "step": 108
    },
    {
      "epoch": 1.618811881188119,
      "grad_norm": 0.6642916869660335,
      "learning_rate": 5.174497483512506e-06,
      "loss": 0.6781,
      "step": 109
    },
    {
      "epoch": 1.6336633663366338,
      "grad_norm": 0.666238358663729,
      "learning_rate": 5.087262032186418e-06,
      "loss": 0.7442,
      "step": 110
    },
    {
      "epoch": 1.6485148514851486,
      "grad_norm": 0.5597421651434128,
      "learning_rate": 5e-06,
      "loss": 0.781,
      "step": 111
    },
    {
      "epoch": 1.6633663366336635,
      "grad_norm": 0.5707641758576157,
      "learning_rate": 4.9127379678135825e-06,
      "loss": 0.6567,
      "step": 112
    },
    {
      "epoch": 1.6782178217821784,
      "grad_norm": 0.7209030283118137,
      "learning_rate": 4.825502516487497e-06,
      "loss": 0.8752,
      "step": 113
    },
    {
      "epoch": 1.693069306930693,
      "grad_norm": 0.6674679363110967,
      "learning_rate": 4.738320218785281e-06,
      "loss": 0.6735,
      "step": 114
    },
    {
      "epoch": 1.7079207920792079,
      "grad_norm": 0.5604986801350424,
      "learning_rate": 4.651217631279374e-06,
      "loss": 0.6056,
      "step": 115
    },
    {
      "epoch": 1.7227722772277227,
      "grad_norm": 0.6669131750643947,
      "learning_rate": 4.564221286261709e-06,
      "loss": 0.7485,
      "step": 116
    },
    {
      "epoch": 1.7376237623762376,
      "grad_norm": 0.64731110152955,
      "learning_rate": 4.477357683661734e-06,
      "loss": 0.7505,
      "step": 117
    },
    {
      "epoch": 1.7524752475247525,
      "grad_norm": 0.6087298446862004,
      "learning_rate": 4.390653282974264e-06,
      "loss": 0.7236,
      "step": 118
    },
    {
      "epoch": 1.7673267326732673,
      "grad_norm": 0.605354758035472,
      "learning_rate": 4.304134495199675e-06,
      "loss": 0.7576,
      "step": 119
    },
    {
      "epoch": 1.7821782178217822,
      "grad_norm": 0.592121550404726,
      "learning_rate": 4.217827674798845e-06,
      "loss": 0.6612,
      "step": 120
    },
    {
      "epoch": 1.797029702970297,
      "grad_norm": 0.583998747608208,
      "learning_rate": 4.131759111665349e-06,
      "loss": 0.8031,
      "step": 121
    },
    {
      "epoch": 1.811881188118812,
      "grad_norm": 0.5401381825177095,
      "learning_rate": 4.045955023117276e-06,
      "loss": 0.7083,
      "step": 122
    },
    {
      "epoch": 1.8267326732673266,
      "grad_norm": 0.5505024887448378,
      "learning_rate": 3.960441545911205e-06,
      "loss": 0.6603,
      "step": 123
    },
    {
      "epoch": 1.8415841584158414,
      "grad_norm": 0.5807490002016577,
      "learning_rate": 3.875244728280676e-06,
      "loss": 0.7428,
      "step": 124
    },
    {
      "epoch": 1.8564356435643563,
      "grad_norm": 0.5775296918472558,
      "learning_rate": 3.790390522001662e-06,
      "loss": 0.7071,
      "step": 125
    },
    {
      "epoch": 1.8712871287128712,
      "grad_norm": 0.5618797996455542,
      "learning_rate": 3.705904774487396e-06,
      "loss": 0.7738,
      "step": 126
    },
    {
      "epoch": 1.886138613861386,
      "grad_norm": 0.5612544221604727,
      "learning_rate": 3.6218132209150047e-06,
      "loss": 0.7353,
      "step": 127
    },
    {
      "epoch": 1.900990099009901,
      "grad_norm": 0.5269006078917019,
      "learning_rate": 3.538141476386317e-06,
      "loss": 0.7185,
      "step": 128
    },
    {
      "epoch": 1.9158415841584158,
      "grad_norm": 0.5442468804329766,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.696,
      "step": 129
    },
    {
      "epoch": 1.9306930693069306,
      "grad_norm": 0.5960660751056697,
      "learning_rate": 3.372159227714218e-06,
      "loss": 0.7649,
      "step": 130
    },
    {
      "epoch": 1.9455445544554455,
      "grad_norm": 0.4969333687228696,
      "learning_rate": 3.289899283371657e-06,
      "loss": 0.7024,
      "step": 131
    },
    {
      "epoch": 1.9603960396039604,
      "grad_norm": 0.5553043936209708,
      "learning_rate": 3.2081602522734987e-06,
      "loss": 0.823,
      "step": 132
    },
    {
      "epoch": 1.9752475247524752,
      "grad_norm": 0.5681040781939833,
      "learning_rate": 3.12696703292044e-06,
      "loss": 0.7705,
      "step": 133
    },
    {
      "epoch": 1.99009900990099,
      "grad_norm": 0.6009985220517085,
      "learning_rate": 3.0463443575536324e-06,
      "loss": 0.7319,
      "step": 134
    },
    {
      "epoch": 2.004950495049505,
      "grad_norm": 1.2209353424526557,
      "learning_rate": 2.966316784621e-06,
      "loss": 0.9991,
      "step": 135
    },
    {
      "epoch": 2.01980198019802,
      "grad_norm": 0.6663865953806991,
      "learning_rate": 2.886908691296504e-06,
      "loss": 0.7344,
      "step": 136
    },
    {
      "epoch": 2.0346534653465347,
      "grad_norm": 0.6515234599013568,
      "learning_rate": 2.8081442660546126e-06,
      "loss": 0.6747,
      "step": 137
    },
    {
      "epoch": 2.0495049504950495,
      "grad_norm": 0.5730091194025813,
      "learning_rate": 2.7300475013022666e-06,
      "loss": 0.603,
      "step": 138
    },
    {
      "epoch": 2.0643564356435644,
      "grad_norm": 0.5406638850651563,
      "learning_rate": 2.6526421860705474e-06,
      "loss": 0.7451,
      "step": 139
    },
    {
      "epoch": 2.0792079207920793,
      "grad_norm": 0.5841557122529807,
      "learning_rate": 2.5759518987683154e-06,
      "loss": 0.7037,
      "step": 140
    },
    {
      "epoch": 2.094059405940594,
      "grad_norm": 0.5894024920902818,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.6763,
      "step": 141
    },
    {
      "epoch": 2.108910891089109,
      "grad_norm": 0.6174804381821258,
      "learning_rate": 2.424809625449729e-06,
      "loss": 0.6384,
      "step": 142
    },
    {
      "epoch": 2.123762376237624,
      "grad_norm": 0.6119987306390974,
      "learning_rate": 2.3504036788339763e-06,
      "loss": 0.7545,
      "step": 143
    },
    {
      "epoch": 2.1386138613861387,
      "grad_norm": 0.5006999182134887,
      "learning_rate": 2.2768048249248648e-06,
      "loss": 0.5474,
      "step": 144
    },
    {
      "epoch": 2.1534653465346536,
      "grad_norm": 0.5375559180884052,
      "learning_rate": 2.204035482646267e-06,
      "loss": 0.6522,
      "step": 145
    },
    {
      "epoch": 2.1683168316831685,
      "grad_norm": 0.5708691567653545,
      "learning_rate": 2.132117818244771e-06,
      "loss": 0.6746,
      "step": 146
    },
    {
      "epoch": 2.1831683168316833,
      "grad_norm": 0.5360011345721072,
      "learning_rate": 2.061073738537635e-06,
      "loss": 0.6705,
      "step": 147
    },
    {
      "epoch": 2.198019801980198,
      "grad_norm": 0.6053709432824774,
      "learning_rate": 1.990924884239758e-06,
      "loss": 0.7101,
      "step": 148
    },
    {
      "epoch": 2.212871287128713,
      "grad_norm": 0.5531801803062121,
      "learning_rate": 1.9216926233717087e-06,
      "loss": 0.6503,
      "step": 149
    },
    {
      "epoch": 2.227722772277228,
      "grad_norm": 0.5761743172160733,
      "learning_rate": 1.8533980447508138e-06,
      "loss": 0.6597,
      "step": 150
    },
    {
      "epoch": 2.2425742574257423,
      "grad_norm": 0.5920189276988723,
      "learning_rate": 1.7860619515673034e-06,
      "loss": 0.7937,
      "step": 151
    },
    {
      "epoch": 2.2574257425742577,
      "grad_norm": 0.4711557273037673,
      "learning_rate": 1.7197048550474643e-06,
      "loss": 0.574,
      "step": 152
    },
    {
      "epoch": 2.272277227722772,
      "grad_norm": 0.5323981360953441,
      "learning_rate": 1.6543469682057105e-06,
      "loss": 0.6766,
      "step": 153
    },
    {
      "epoch": 2.287128712871287,
      "grad_norm": 0.5677075588486846,
      "learning_rate": 1.5900081996875083e-06,
      "loss": 0.7836,
      "step": 154
    },
    {
      "epoch": 2.301980198019802,
      "grad_norm": 0.495711192365763,
      "learning_rate": 1.5267081477050132e-06,
      "loss": 0.5805,
      "step": 155
    },
    {
      "epoch": 2.3168316831683167,
      "grad_norm": 0.5019129834363211,
      "learning_rate": 1.4644660940672628e-06,
      "loss": 0.6805,
      "step": 156
    },
    {
      "epoch": 2.3316831683168315,
      "grad_norm": 0.5924600811693187,
      "learning_rate": 1.4033009983067454e-06,
      "loss": 0.6958,
      "step": 157
    },
    {
      "epoch": 2.3465346534653464,
      "grad_norm": 0.5679498872247285,
      "learning_rate": 1.3432314919041478e-06,
      "loss": 0.7157,
      "step": 158
    },
    {
      "epoch": 2.3613861386138613,
      "grad_norm": 0.5378653771399984,
      "learning_rate": 1.2842758726130283e-06,
      "loss": 0.6421,
      "step": 159
    },
    {
      "epoch": 2.376237623762376,
      "grad_norm": 0.5716411245552344,
      "learning_rate": 1.22645209888614e-06,
      "loss": 0.7546,
      "step": 160
    },
    {
      "epoch": 2.391089108910891,
      "grad_norm": 0.5031816053120705,
      "learning_rate": 1.1697777844051105e-06,
      "loss": 0.7018,
      "step": 161
    },
    {
      "epoch": 2.405940594059406,
      "grad_norm": 0.46660397121098096,
      "learning_rate": 1.1142701927151456e-06,
      "loss": 0.639,
      "step": 162
    },
    {
      "epoch": 2.4207920792079207,
      "grad_norm": 0.5135926843254873,
      "learning_rate": 1.0599462319663906e-06,
      "loss": 0.7345,
      "step": 163
    },
    {
      "epoch": 2.4356435643564356,
      "grad_norm": 0.5145225601719905,
      "learning_rate": 1.006822449763537e-06,
      "loss": 0.6413,
      "step": 164
    },
    {
      "epoch": 2.4504950495049505,
      "grad_norm": 0.4781710026536871,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.6647,
      "step": 165
    },
    {
      "epoch": 2.4653465346534653,
      "grad_norm": 0.48799619696609925,
      "learning_rate": 9.042397785550405e-07,
      "loss": 0.7179,
      "step": 166
    },
    {
      "epoch": 2.48019801980198,
      "grad_norm": 0.488756423169197,
      "learning_rate": 8.54812137224792e-07,
      "loss": 0.6727,
      "step": 167
    },
    {
      "epoch": 2.495049504950495,
      "grad_norm": 0.47225504186982886,
      "learning_rate": 8.066471602728804e-07,
      "loss": 0.7016,
      "step": 168
    },
    {
      "epoch": 2.50990099009901,
      "grad_norm": 0.4884739098762309,
      "learning_rate": 7.597595192178702e-07,
      "loss": 0.7249,
      "step": 169
    },
    {
      "epoch": 2.5247524752475248,
      "grad_norm": 0.470588495873427,
      "learning_rate": 7.141634964894389e-07,
      "loss": 0.6672,
      "step": 170
    },
    {
      "epoch": 2.5396039603960396,
      "grad_norm": 0.4673487289438152,
      "learning_rate": 6.698729810778065e-07,
      "loss": 0.6774,
      "step": 171
    },
    {
      "epoch": 2.5544554455445545,
      "grad_norm": 0.4635764685120432,
      "learning_rate": 6.269014643030214e-07,
      "loss": 0.679,
      "step": 172
    },
    {
      "epoch": 2.5693069306930694,
      "grad_norm": 0.4956166674866954,
      "learning_rate": 5.852620357053651e-07,
      "loss": 0.6947,
      "step": 173
    },
    {
      "epoch": 2.5841584158415842,
      "grad_norm": 0.4817833751685946,
      "learning_rate": 5.449673790581611e-07,
      "loss": 0.6292,
      "step": 174
    },
    {
      "epoch": 2.599009900990099,
      "grad_norm": 0.5033414960012568,
      "learning_rate": 5.06029768504166e-07,
      "loss": 0.6521,
      "step": 175
    },
    {
      "epoch": 2.613861386138614,
      "grad_norm": 0.4826152038387741,
      "learning_rate": 4.6846106481675035e-07,
      "loss": 0.6345,
      "step": 176
    },
    {
      "epoch": 2.628712871287129,
      "grad_norm": 0.5148110561313826,
      "learning_rate": 4.322727117869951e-07,
      "loss": 0.7187,
      "step": 177
    },
    {
      "epoch": 2.6435643564356437,
      "grad_norm": 0.520468554829645,
      "learning_rate": 3.9747573273779816e-07,
      "loss": 0.6922,
      "step": 178
    },
    {
      "epoch": 2.6584158415841586,
      "grad_norm": 0.48040006877742775,
      "learning_rate": 3.6408072716606346e-07,
      "loss": 0.6394,
      "step": 179
    },
    {
      "epoch": 2.6732673267326734,
      "grad_norm": 0.49771916703934643,
      "learning_rate": 3.320978675139919e-07,
      "loss": 0.6555,
      "step": 180
    },
    {
      "epoch": 2.6881188118811883,
      "grad_norm": 0.4985224870159162,
      "learning_rate": 3.015368960704584e-07,
      "loss": 0.6621,
      "step": 181
    },
    {
      "epoch": 2.7029702970297027,
      "grad_norm": 0.5032558199370275,
      "learning_rate": 2.724071220034158e-07,
      "loss": 0.7285,
      "step": 182
    },
    {
      "epoch": 2.717821782178218,
      "grad_norm": 0.4881972665265835,
      "learning_rate": 2.447174185242324e-07,
      "loss": 0.6426,
      "step": 183
    },
    {
      "epoch": 2.7326732673267324,
      "grad_norm": 0.4828031422366926,
      "learning_rate": 2.1847622018482283e-07,
      "loss": 0.6782,
      "step": 184
    },
    {
      "epoch": 2.7475247524752477,
      "grad_norm": 0.47484851901453023,
      "learning_rate": 1.9369152030840553e-07,
      "loss": 0.6326,
      "step": 185
    },
    {
      "epoch": 2.762376237623762,
      "grad_norm": 0.5311388807144789,
      "learning_rate": 1.7037086855465902e-07,
      "loss": 0.7419,
      "step": 186
    },
    {
      "epoch": 2.7772277227722775,
      "grad_norm": 0.4614470612824122,
      "learning_rate": 1.4852136862001766e-07,
      "loss": 0.6123,
      "step": 187
    },
    {
      "epoch": 2.792079207920792,
      "grad_norm": 0.48962299396889825,
      "learning_rate": 1.2814967607382433e-07,
      "loss": 0.7775,
      "step": 188
    },
    {
      "epoch": 2.806930693069307,
      "grad_norm": 0.5121698180749854,
      "learning_rate": 1.0926199633097156e-07,
      "loss": 0.6253,
      "step": 189
    },
    {
      "epoch": 2.8217821782178216,
      "grad_norm": 0.5454806153588347,
      "learning_rate": 9.186408276168012e-08,
      "loss": 0.6817,
      "step": 190
    },
    {
      "epoch": 2.8366336633663365,
      "grad_norm": 0.47926294627215255,
      "learning_rate": 7.59612349389599e-08,
      "loss": 0.6702,
      "step": 191
    },
    {
      "epoch": 2.8514851485148514,
      "grad_norm": 0.488962969794833,
      "learning_rate": 6.15582970243117e-08,
      "loss": 0.6687,
      "step": 192
    },
    {
      "epoch": 2.866336633663366,
      "grad_norm": 0.5042360939591695,
      "learning_rate": 4.865965629214819e-08,
      "loss": 0.6828,
      "step": 193
    },
    {
      "epoch": 2.881188118811881,
      "grad_norm": 0.4737639717650882,
      "learning_rate": 3.726924179339009e-08,
      "loss": 0.6109,
      "step": 194
    },
    {
      "epoch": 2.896039603960396,
      "grad_norm": 0.5367048842660397,
      "learning_rate": 2.7390523158633552e-08,
      "loss": 0.6467,
      "step": 195
    },
    {
      "epoch": 2.910891089108911,
      "grad_norm": 0.5043896642226987,
      "learning_rate": 1.9026509541272276e-08,
      "loss": 0.7169,
      "step": 196
    },
    {
      "epoch": 2.9257425742574257,
      "grad_norm": 0.4791625292476249,
      "learning_rate": 1.2179748700879013e-08,
      "loss": 0.7351,
      "step": 197
    },
    {
      "epoch": 2.9405940594059405,
      "grad_norm": 0.5102082840215327,
      "learning_rate": 6.852326227130835e-09,
      "loss": 0.6391,
      "step": 198
    },
    {
      "epoch": 2.9554455445544554,
      "grad_norm": 0.4865097004583583,
      "learning_rate": 3.0458649045211897e-09,
      "loss": 0.6674,
      "step": 199
    },
    {
      "epoch": 2.9702970297029703,
      "grad_norm": 0.5133741423875121,
      "learning_rate": 7.615242180436521e-10,
      "loss": 0.7427,
      "step": 200
    },
    {
      "epoch": 2.985148514851485,
      "grad_norm": 0.4923182359179608,
      "learning_rate": 0.0,
      "loss": 0.595,
      "step": 201
    },
    {
      "epoch": 2.985148514851485,
      "step": 201,
      "total_flos": 138721009057792.0,
      "train_loss": 0.7744821606583856,
      "train_runtime": 2765.7022,
      "train_samples_per_second": 6.994,
      "train_steps_per_second": 0.073
    }
  ],
  "logging_steps": 1,
  "max_steps": 201,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 138721009057792.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}