{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9836867862969005,
  "eval_steps": 39,
  "global_step": 306,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0065252854812398045,
      "grad_norm": 0.23828125,
      "learning_rate": 2e-05,
      "loss": 1.3184,
      "step": 1
    },
    {
      "epoch": 0.0065252854812398045,
      "eval_loss": 1.3192611932754517,
      "eval_runtime": 235.1739,
      "eval_samples_per_second": 1.811,
      "eval_steps_per_second": 0.906,
      "step": 1
    },
    {
      "epoch": 0.013050570962479609,
      "grad_norm": 0.2373046875,
      "learning_rate": 4e-05,
      "loss": 1.3213,
      "step": 2
    },
    {
      "epoch": 0.01957585644371941,
      "grad_norm": 0.2373046875,
      "learning_rate": 6e-05,
      "loss": 1.3232,
      "step": 3
    },
    {
      "epoch": 0.026101141924959218,
      "grad_norm": 0.259765625,
      "learning_rate": 8e-05,
      "loss": 1.3418,
      "step": 4
    },
    {
      "epoch": 0.03262642740619902,
      "grad_norm": 0.275390625,
      "learning_rate": 0.0001,
      "loss": 1.2712,
      "step": 5
    },
    {
      "epoch": 0.03915171288743882,
      "grad_norm": 0.2412109375,
      "learning_rate": 0.00012,
      "loss": 1.2682,
      "step": 6
    },
    {
      "epoch": 0.04567699836867863,
      "grad_norm": 0.1015625,
      "learning_rate": 0.00014,
      "loss": 1.2672,
      "step": 7
    },
    {
      "epoch": 0.052202283849918436,
      "grad_norm": 0.44140625,
      "learning_rate": 0.00016,
      "loss": 1.2337,
      "step": 8
    },
    {
      "epoch": 0.05872756933115824,
      "grad_norm": 0.51171875,
      "learning_rate": 0.00018,
      "loss": 1.3138,
      "step": 9
    },
    {
      "epoch": 0.06525285481239804,
      "grad_norm": 0.326171875,
      "learning_rate": 0.0002,
      "loss": 1.238,
      "step": 10
    },
    {
      "epoch": 0.07177814029363784,
      "grad_norm": 0.138671875,
      "learning_rate": 0.0001999986383177335,
      "loss": 1.2244,
      "step": 11
    },
    {
      "epoch": 0.07830342577487764,
      "grad_norm": 0.07666015625,
      "learning_rate": 0.0001999945533080175,
      "loss": 1.1796,
      "step": 12
    },
    {
      "epoch": 0.08482871125611746,
      "grad_norm": 0.1171875,
      "learning_rate": 0.0001999877450821018,
      "loss": 1.1873,
      "step": 13
    },
    {
      "epoch": 0.09135399673735727,
      "grad_norm": 0.154296875,
      "learning_rate": 0.0001999782138253991,
      "loss": 1.1684,
      "step": 14
    },
    {
      "epoch": 0.09787928221859707,
      "grad_norm": 0.15625,
      "learning_rate": 0.00019996595979748037,
      "loss": 1.2122,
      "step": 15
    },
    {
      "epoch": 0.10440456769983687,
      "grad_norm": 0.12158203125,
      "learning_rate": 0.00019995098333206742,
      "loss": 1.1772,
      "step": 16
    },
    {
      "epoch": 0.11092985318107668,
      "grad_norm": 0.07958984375,
      "learning_rate": 0.00019993328483702393,
      "loss": 1.1742,
      "step": 17
    },
    {
      "epoch": 0.11745513866231648,
      "grad_norm": 0.09326171875,
      "learning_rate": 0.00019991286479434454,
      "loss": 1.1791,
      "step": 18
    },
    {
      "epoch": 0.12398042414355628,
      "grad_norm": 0.11474609375,
      "learning_rate": 0.00019988972376014142,
      "loss": 1.1651,
      "step": 19
    },
    {
      "epoch": 0.13050570962479607,
      "grad_norm": 0.1572265625,
      "learning_rate": 0.00019986386236462924,
      "loss": 1.1874,
      "step": 20
    },
    {
      "epoch": 0.1370309951060359,
      "grad_norm": 0.12255859375,
      "learning_rate": 0.00019983528131210812,
      "loss": 1.1371,
      "step": 21
    },
    {
      "epoch": 0.14355628058727568,
      "grad_norm": 0.08544921875,
      "learning_rate": 0.00019980398138094428,
      "loss": 1.1725,
      "step": 22
    },
    {
      "epoch": 0.1500815660685155,
      "grad_norm": 0.07763671875,
      "learning_rate": 0.00019976996342354898,
      "loss": 1.1264,
      "step": 23
    },
    {
      "epoch": 0.1566068515497553,
      "grad_norm": 0.078125,
      "learning_rate": 0.00019973322836635518,
      "loss": 1.091,
      "step": 24
    },
    {
      "epoch": 0.1631321370309951,
      "grad_norm": 0.09423828125,
      "learning_rate": 0.00019969377720979237,
      "loss": 1.1636,
      "step": 25
    },
    {
      "epoch": 0.16965742251223492,
      "grad_norm": 0.1044921875,
      "learning_rate": 0.00019965161102825945,
      "loss": 1.1472,
      "step": 26
    },
    {
      "epoch": 0.1761827079934747,
      "grad_norm": 0.0751953125,
      "learning_rate": 0.00019960673097009518,
      "loss": 1.1212,
      "step": 27
    },
    {
      "epoch": 0.18270799347471453,
      "grad_norm": 0.072265625,
      "learning_rate": 0.00019955913825754713,
      "loss": 1.1466,
      "step": 28
    },
    {
      "epoch": 0.18923327895595432,
      "grad_norm": 0.0693359375,
      "learning_rate": 0.0001995088341867384,
      "loss": 1.1235,
      "step": 29
    },
    {
      "epoch": 0.19575856443719414,
      "grad_norm": 0.06787109375,
      "learning_rate": 0.0001994558201276322,
      "loss": 1.1123,
      "step": 30
    },
    {
      "epoch": 0.20228384991843393,
      "grad_norm": 0.07177734375,
      "learning_rate": 0.0001994000975239946,
      "loss": 1.1459,
      "step": 31
    },
    {
      "epoch": 0.20880913539967375,
      "grad_norm": 0.07470703125,
      "learning_rate": 0.00019934166789335525,
      "loss": 1.1231,
      "step": 32
    },
    {
      "epoch": 0.21533442088091354,
      "grad_norm": 0.06689453125,
      "learning_rate": 0.00019928053282696596,
      "loss": 1.1153,
      "step": 33
    },
    {
      "epoch": 0.22185970636215335,
      "grad_norm": 0.078125,
      "learning_rate": 0.00019921669398975745,
      "loss": 1.0979,
      "step": 34
    },
    {
      "epoch": 0.22838499184339314,
      "grad_norm": 0.07421875,
      "learning_rate": 0.000199150153120294,
      "loss": 1.0667,
      "step": 35
    },
    {
      "epoch": 0.23491027732463296,
      "grad_norm": 0.06689453125,
      "learning_rate": 0.00019908091203072598,
      "loss": 1.1144,
      "step": 36
    },
    {
      "epoch": 0.24143556280587275,
      "grad_norm": 0.07080078125,
      "learning_rate": 0.00019900897260674073,
      "loss": 1.104,
      "step": 37
    },
    {
      "epoch": 0.24796084828711257,
      "grad_norm": 0.06689453125,
      "learning_rate": 0.00019893433680751103,
      "loss": 1.1016,
      "step": 38
    },
    {
      "epoch": 0.2544861337683524,
      "grad_norm": 0.07275390625,
      "learning_rate": 0.0001988570066656417,
      "loss": 1.089,
      "step": 39
    },
    {
      "epoch": 0.2544861337683524,
      "eval_loss": 1.1131086349487305,
      "eval_runtime": 236.8764,
      "eval_samples_per_second": 1.798,
      "eval_steps_per_second": 0.899,
      "step": 39
    },
    {
      "epoch": 0.26101141924959215,
      "grad_norm": 0.078125,
      "learning_rate": 0.00019877698428711442,
      "loss": 1.1207,
      "step": 40
    },
    {
      "epoch": 0.26753670473083196,
      "grad_norm": 0.06982421875,
      "learning_rate": 0.00019869427185123027,
      "loss": 1.1376,
      "step": 41
    },
    {
      "epoch": 0.2740619902120718,
      "grad_norm": 0.06982421875,
      "learning_rate": 0.00019860887161055038,
      "loss": 1.1,
      "step": 42
    },
    {
      "epoch": 0.2805872756933116,
      "grad_norm": 0.080078125,
      "learning_rate": 0.00019852078589083466,
      "loss": 1.1185,
      "step": 43
    },
    {
      "epoch": 0.28711256117455136,
      "grad_norm": 0.0732421875,
      "learning_rate": 0.0001984300170909783,
      "loss": 1.1282,
      "step": 44
    },
    {
      "epoch": 0.2936378466557912,
      "grad_norm": 0.0654296875,
      "learning_rate": 0.00019833656768294662,
      "loss": 1.1505,
      "step": 45
    },
    {
      "epoch": 0.300163132137031,
      "grad_norm": 0.06689453125,
      "learning_rate": 0.0001982404402117077,
      "loss": 1.1102,
      "step": 46
    },
    {
      "epoch": 0.3066884176182708,
      "grad_norm": 0.0712890625,
      "learning_rate": 0.00019814163729516292,
      "loss": 1.1254,
      "step": 47
    },
    {
      "epoch": 0.3132137030995106,
      "grad_norm": 0.0673828125,
      "learning_rate": 0.0001980401616240759,
      "loss": 1.0934,
      "step": 48
    },
    {
      "epoch": 0.3197389885807504,
      "grad_norm": 0.06689453125,
      "learning_rate": 0.00019793601596199912,
      "loss": 1.0792,
      "step": 49
    },
    {
      "epoch": 0.3262642740619902,
      "grad_norm": 0.07177734375,
      "learning_rate": 0.00019782920314519856,
      "loss": 1.0936,
      "step": 50
    },
    {
      "epoch": 0.33278955954323003,
      "grad_norm": 0.06884765625,
      "learning_rate": 0.00019771972608257659,
      "loss": 1.0636,
      "step": 51
    },
    {
      "epoch": 0.33931484502446985,
      "grad_norm": 0.0673828125,
      "learning_rate": 0.00019760758775559274,
      "loss": 1.0693,
      "step": 52
    },
    {
      "epoch": 0.3458401305057096,
      "grad_norm": 0.06787109375,
      "learning_rate": 0.00019749279121818235,
      "loss": 1.0882,
      "step": 53
    },
    {
      "epoch": 0.3523654159869494,
      "grad_norm": 0.0703125,
      "learning_rate": 0.0001973753395966737,
      "loss": 1.1066,
      "step": 54
    },
    {
      "epoch": 0.35889070146818924,
      "grad_norm": 0.0712890625,
      "learning_rate": 0.00019725523608970255,
      "loss": 1.049,
      "step": 55
    },
    {
      "epoch": 0.36541598694942906,
      "grad_norm": 0.06982421875,
      "learning_rate": 0.00019713248396812524,
      "loss": 1.1083,
      "step": 56
    },
    {
      "epoch": 0.3719412724306688,
      "grad_norm": 0.072265625,
      "learning_rate": 0.00019700708657492948,
      "loss": 1.0854,
      "step": 57
    },
    {
      "epoch": 0.37846655791190864,
      "grad_norm": 0.07275390625,
      "learning_rate": 0.0001968790473251434,
      "loss": 1.0954,
      "step": 58
    },
    {
      "epoch": 0.38499184339314846,
      "grad_norm": 0.07373046875,
      "learning_rate": 0.00019674836970574254,
      "loss": 1.0833,
      "step": 59
    },
    {
      "epoch": 0.3915171288743883,
      "grad_norm": 0.07275390625,
      "learning_rate": 0.00019661505727555482,
      "loss": 1.0945,
      "step": 60
    },
    {
      "epoch": 0.39804241435562804,
      "grad_norm": 0.07080078125,
      "learning_rate": 0.0001964791136651637,
      "loss": 1.07,
      "step": 61
    },
    {
      "epoch": 0.40456769983686786,
      "grad_norm": 0.07177734375,
      "learning_rate": 0.00019634054257680923,
      "loss": 1.0998,
      "step": 62
    },
    {
      "epoch": 0.4110929853181077,
      "grad_norm": 0.0712890625,
      "learning_rate": 0.0001961993477842873,
      "loss": 1.0718,
      "step": 63
    },
    {
      "epoch": 0.4176182707993475,
      "grad_norm": 0.078125,
      "learning_rate": 0.0001960555331328468,
      "loss": 1.0285,
      "step": 64
    },
    {
      "epoch": 0.42414355628058725,
      "grad_norm": 0.08203125,
      "learning_rate": 0.00019590910253908494,
      "loss": 1.0836,
      "step": 65
    },
    {
      "epoch": 0.43066884176182707,
      "grad_norm": 0.076171875,
      "learning_rate": 0.0001957600599908406,
      "loss": 1.0836,
      "step": 66
    },
    {
      "epoch": 0.4371941272430669,
      "grad_norm": 0.07373046875,
      "learning_rate": 0.00019560840954708565,
      "loss": 1.0868,
      "step": 67
    },
    {
      "epoch": 0.4437194127243067,
      "grad_norm": 0.06884765625,
      "learning_rate": 0.0001954541553378145,
      "loss": 1.115,
      "step": 68
    },
    {
      "epoch": 0.45024469820554647,
      "grad_norm": 0.0703125,
      "learning_rate": 0.0001952973015639316,
      "loss": 1.047,
      "step": 69
    },
    {
      "epoch": 0.4567699836867863,
      "grad_norm": 0.07373046875,
      "learning_rate": 0.00019513785249713697,
      "loss": 1.0878,
      "step": 70
    },
    {
      "epoch": 0.4632952691680261,
      "grad_norm": 0.07275390625,
      "learning_rate": 0.00019497581247980992,
      "loss": 1.0547,
      "step": 71
    },
    {
      "epoch": 0.4698205546492659,
      "grad_norm": 0.0732421875,
      "learning_rate": 0.00019481118592489086,
      "loss": 1.0907,
      "step": 72
    },
    {
      "epoch": 0.4763458401305057,
      "grad_norm": 0.0703125,
      "learning_rate": 0.00019464397731576094,
      "loss": 1.053,
      "step": 73
    },
    {
      "epoch": 0.4828711256117455,
      "grad_norm": 0.07421875,
      "learning_rate": 0.00019447419120612017,
      "loss": 1.0768,
      "step": 74
    },
    {
      "epoch": 0.4893964110929853,
      "grad_norm": 0.0732421875,
      "learning_rate": 0.00019430183221986325,
      "loss": 1.0599,
      "step": 75
    },
    {
      "epoch": 0.49592169657422513,
      "grad_norm": 0.076171875,
      "learning_rate": 0.00019412690505095365,
      "loss": 1.0721,
      "step": 76
    },
    {
      "epoch": 0.5024469820554649,
      "grad_norm": 0.07666015625,
      "learning_rate": 0.00019394941446329583,
      "loss": 1.0802,
      "step": 77
    },
    {
      "epoch": 0.5089722675367048,
      "grad_norm": 0.0771484375,
      "learning_rate": 0.00019376936529060554,
      "loss": 1.0475,
      "step": 78
    },
    {
      "epoch": 0.5089722675367048,
      "eval_loss": 1.0718731880187988,
      "eval_runtime": 236.7722,
      "eval_samples_per_second": 1.799,
      "eval_steps_per_second": 0.9,
      "step": 78
    },
    {
      "epoch": 0.5154975530179445,
      "grad_norm": 0.072265625,
      "learning_rate": 0.00019358676243627808,
      "loss": 1.0706,
      "step": 79
    },
    {
      "epoch": 0.5220228384991843,
      "grad_norm": 0.07568359375,
      "learning_rate": 0.0001934016108732548,
      "loss": 1.0679,
      "step": 80
    },
    {
      "epoch": 0.5285481239804242,
      "grad_norm": 0.08056640625,
      "learning_rate": 0.00019321391564388775,
      "loss": 1.044,
      "step": 81
    },
    {
      "epoch": 0.5350734094616639,
      "grad_norm": 0.078125,
      "learning_rate": 0.00019302368185980217,
      "loss": 1.0878,
      "step": 82
    },
    {
      "epoch": 0.5415986949429038,
      "grad_norm": 0.08447265625,
      "learning_rate": 0.00019283091470175754,
      "loss": 1.0469,
      "step": 83
    },
    {
      "epoch": 0.5481239804241436,
      "grad_norm": 0.07861328125,
      "learning_rate": 0.00019263561941950622,
      "loss": 1.0453,
      "step": 84
    },
    {
      "epoch": 0.5546492659053833,
      "grad_norm": 0.08154296875,
      "learning_rate": 0.00019243780133165067,
      "loss": 1.0677,
      "step": 85
    },
    {
      "epoch": 0.5611745513866232,
      "grad_norm": 0.08056640625,
      "learning_rate": 0.00019223746582549853,
      "loss": 1.0648,
      "step": 86
    },
    {
      "epoch": 0.567699836867863,
      "grad_norm": 0.083984375,
      "learning_rate": 0.00019203461835691594,
      "loss": 1.0891,
      "step": 87
    },
    {
      "epoch": 0.5742251223491027,
      "grad_norm": 0.08447265625,
      "learning_rate": 0.00019182926445017893,
      "loss": 1.0607,
      "step": 88
    },
    {
      "epoch": 0.5807504078303426,
      "grad_norm": 0.078125,
      "learning_rate": 0.00019162140969782292,
      "loss": 1.0241,
      "step": 89
    },
    {
      "epoch": 0.5872756933115824,
      "grad_norm": 0.08642578125,
      "learning_rate": 0.00019141105976049053,
      "loss": 1.0675,
      "step": 90
    },
    {
      "epoch": 0.5938009787928222,
      "grad_norm": 0.08642578125,
      "learning_rate": 0.00019119822036677738,
      "loss": 1.0538,
      "step": 91
    },
    {
      "epoch": 0.600326264274062,
      "grad_norm": 0.0751953125,
      "learning_rate": 0.000190982897313076,
      "loss": 1.0572,
      "step": 92
    },
    {
      "epoch": 0.6068515497553018,
      "grad_norm": 0.076171875,
      "learning_rate": 0.00019076509646341806,
      "loss": 1.0372,
      "step": 93
    },
    {
      "epoch": 0.6133768352365416,
      "grad_norm": 0.07861328125,
      "learning_rate": 0.00019054482374931467,
      "loss": 1.0693,
      "step": 94
    },
    {
      "epoch": 0.6199021207177814,
      "grad_norm": 0.07861328125,
      "learning_rate": 0.0001903220851695948,
      "loss": 1.0726,
      "step": 95
    },
    {
      "epoch": 0.6264274061990212,
      "grad_norm": 0.0791015625,
      "learning_rate": 0.0001900968867902419,
      "loss": 1.0543,
      "step": 96
    },
    {
      "epoch": 0.632952691680261,
      "grad_norm": 0.08447265625,
      "learning_rate": 0.00018986923474422884,
      "loss": 1.0577,
      "step": 97
    },
    {
      "epoch": 0.6394779771615008,
      "grad_norm": 0.08447265625,
      "learning_rate": 0.0001896391352313506,
      "loss": 1.0649,
      "step": 98
    },
    {
      "epoch": 0.6460032626427407,
      "grad_norm": 0.08056640625,
      "learning_rate": 0.0001894065945180558,
      "loss": 1.0828,
      "step": 99
    },
    {
      "epoch": 0.6525285481239804,
      "grad_norm": 0.07861328125,
      "learning_rate": 0.0001891716189372757,
      "loss": 1.0805,
      "step": 100
    },
    {
      "epoch": 0.6590538336052202,
      "grad_norm": 0.07861328125,
      "learning_rate": 0.0001889342148882519,
      "loss": 1.0158,
      "step": 101
    },
    {
      "epoch": 0.6655791190864601,
      "grad_norm": 0.08056640625,
      "learning_rate": 0.00018869438883636214,
      "loss": 1.0686,
      "step": 102
    },
    {
      "epoch": 0.6721044045676998,
      "grad_norm": 0.07958984375,
      "learning_rate": 0.000188452147312944,
      "loss": 1.0498,
      "step": 103
    },
    {
      "epoch": 0.6786296900489397,
      "grad_norm": 0.07861328125,
      "learning_rate": 0.0001882074969151172,
      "loss": 1.0783,
      "step": 104
    },
    {
      "epoch": 0.6851549755301795,
      "grad_norm": 0.08056640625,
      "learning_rate": 0.000187960444305604,
      "loss": 0.9942,
      "step": 105
    },
    {
      "epoch": 0.6916802610114192,
      "grad_norm": 0.0791015625,
      "learning_rate": 0.00018771099621254746,
      "loss": 1.0517,
      "step": 106
    },
    {
      "epoch": 0.6982055464926591,
      "grad_norm": 0.0810546875,
      "learning_rate": 0.0001874591594293285,
      "loss": 1.0619,
      "step": 107
    },
    {
      "epoch": 0.7047308319738989,
      "grad_norm": 0.08251953125,
      "learning_rate": 0.00018720494081438078,
      "loss": 1.0584,
      "step": 108
    },
    {
      "epoch": 0.7112561174551386,
      "grad_norm": 0.08740234375,
      "learning_rate": 0.00018694834729100386,
      "loss": 1.0466,
      "step": 109
    },
    {
      "epoch": 0.7177814029363785,
      "grad_norm": 0.08349609375,
      "learning_rate": 0.00018668938584717471,
      "loss": 1.0391,
      "step": 110
    },
    {
      "epoch": 0.7243066884176182,
      "grad_norm": 0.08251953125,
      "learning_rate": 0.00018642806353535754,
      "loss": 1.0331,
      "step": 111
    },
    {
      "epoch": 0.7308319738988581,
      "grad_norm": 0.0859375,
      "learning_rate": 0.00018616438747231148,
      "loss": 1.0671,
      "step": 112
    },
    {
      "epoch": 0.7373572593800979,
      "grad_norm": 0.087890625,
      "learning_rate": 0.00018589836483889687,
      "loss": 1.0525,
      "step": 113
    },
    {
      "epoch": 0.7438825448613376,
      "grad_norm": 0.08935546875,
      "learning_rate": 0.0001856300028798798,
      "loss": 1.0182,
      "step": 114
    },
    {
      "epoch": 0.7504078303425775,
      "grad_norm": 0.08349609375,
      "learning_rate": 0.00018535930890373466,
      "loss": 1.0566,
      "step": 115
    },
    {
      "epoch": 0.7569331158238173,
      "grad_norm": 0.080078125,
      "learning_rate": 0.00018508629028244519,
      "loss": 1.0316,
      "step": 116
    },
    {
      "epoch": 0.763458401305057,
      "grad_norm": 0.09033203125,
      "learning_rate": 0.0001848109544513037,
      "loss": 1.0362,
      "step": 117
    },
    {
      "epoch": 0.763458401305057,
      "eval_loss": 1.0525188446044922,
      "eval_runtime": 236.6432,
      "eval_samples_per_second": 1.8,
      "eval_steps_per_second": 0.9,
      "step": 117
    },
    {
      "epoch": 0.7699836867862969,
      "grad_norm": 0.08544921875,
      "learning_rate": 0.00018453330890870855,
      "loss": 1.0141,
      "step": 118
    },
    {
      "epoch": 0.7765089722675367,
      "grad_norm": 0.08203125,
      "learning_rate": 0.00018425336121596,
      "loss": 1.0464,
      "step": 119
    },
    {
      "epoch": 0.7830342577487766,
      "grad_norm": 0.0830078125,
      "learning_rate": 0.00018397111899705419,
      "loss": 1.0278,
      "step": 120
    },
    {
      "epoch": 0.7895595432300163,
      "grad_norm": 0.080078125,
      "learning_rate": 0.00018368658993847566,
      "loss": 1.0439,
      "step": 121
    },
    {
      "epoch": 0.7960848287112561,
      "grad_norm": 0.08251953125,
      "learning_rate": 0.0001833997817889878,
      "loss": 1.053,
      "step": 122
    },
    {
      "epoch": 0.802610114192496,
      "grad_norm": 0.08642578125,
      "learning_rate": 0.0001831107023594221,
      "loss": 1.0447,
      "step": 123
    },
    {
      "epoch": 0.8091353996737357,
      "grad_norm": 0.08349609375,
      "learning_rate": 0.00018281935952246518,
      "loss": 1.0347,
      "step": 124
    },
    {
      "epoch": 0.8156606851549756,
      "grad_norm": 0.0810546875,
      "learning_rate": 0.00018252576121244456,
      "loss": 1.0628,
      "step": 125
    },
    {
      "epoch": 0.8221859706362153,
      "grad_norm": 0.08056640625,
      "learning_rate": 0.00018222991542511246,
      "loss": 1.0112,
      "step": 126
    },
    {
      "epoch": 0.8287112561174551,
      "grad_norm": 0.08984375,
      "learning_rate": 0.0001819318302174281,
      "loss": 1.0657,
      "step": 127
    },
    {
      "epoch": 0.835236541598695,
      "grad_norm": 0.08837890625,
      "learning_rate": 0.00018163151370733838,
      "loss": 1.0936,
      "step": 128
    },
    {
      "epoch": 0.8417618270799347,
      "grad_norm": 0.0869140625,
      "learning_rate": 0.00018132897407355657,
      "loss": 1.0519,
      "step": 129
    },
    {
      "epoch": 0.8482871125611745,
      "grad_norm": 0.08447265625,
      "learning_rate": 0.00018102421955533974,
      "loss": 1.018,
      "step": 130
    },
    {
      "epoch": 0.8548123980424144,
      "grad_norm": 0.08349609375,
      "learning_rate": 0.00018071725845226436,
      "loss": 0.9982,
      "step": 131
    },
    {
      "epoch": 0.8613376835236541,
      "grad_norm": 0.0966796875,
      "learning_rate": 0.0001804080991240003,
      "loss": 1.0522,
      "step": 132
    },
    {
      "epoch": 0.867862969004894,
      "grad_norm": 0.0830078125,
      "learning_rate": 0.000180096749990083,
      "loss": 1.0149,
      "step": 133
    },
    {
      "epoch": 0.8743882544861338,
      "grad_norm": 0.0810546875,
      "learning_rate": 0.00017978321952968434,
      "loss": 1.0096,
      "step": 134
    },
    {
      "epoch": 0.8809135399673735,
      "grad_norm": 0.09765625,
      "learning_rate": 0.00017946751628138174,
      "loss": 1.0551,
      "step": 135
    },
    {
      "epoch": 0.8874388254486134,
      "grad_norm": 0.083984375,
      "learning_rate": 0.00017914964884292544,
      "loss": 1.0384,
      "step": 136
    },
    {
      "epoch": 0.8939641109298532,
      "grad_norm": 0.09326171875,
      "learning_rate": 0.0001788296258710045,
      "loss": 1.0341,
      "step": 137
    },
    {
      "epoch": 0.9004893964110929,
      "grad_norm": 0.0859375,
      "learning_rate": 0.0001785074560810111,
      "loss": 1.0162,
      "step": 138
    },
    {
      "epoch": 0.9070146818923328,
      "grad_norm": 0.0849609375,
      "learning_rate": 0.000178183148246803,
      "loss": 1.0332,
      "step": 139
    },
    {
      "epoch": 0.9135399673735726,
      "grad_norm": 0.08251953125,
      "learning_rate": 0.00017785671120046473,
      "loss": 1.0219,
      "step": 140
    },
    {
      "epoch": 0.9200652528548124,
      "grad_norm": 0.080078125,
      "learning_rate": 0.00017752815383206705,
      "loss": 1.0557,
      "step": 141
    },
    {
      "epoch": 0.9265905383360522,
      "grad_norm": 0.0849609375,
      "learning_rate": 0.0001771974850894248,
      "loss": 1.075,
      "step": 142
    },
    {
      "epoch": 0.933115823817292,
      "grad_norm": 0.087890625,
      "learning_rate": 0.0001768647139778532,
      "loss": 1.0458,
      "step": 143
    },
    {
      "epoch": 0.9396411092985318,
      "grad_norm": 0.0830078125,
      "learning_rate": 0.00017652984955992277,
      "loss": 1.054,
      "step": 144
    },
    {
      "epoch": 0.9461663947797716,
      "grad_norm": 0.08154296875,
      "learning_rate": 0.0001761929009552122,
      "loss": 1.0297,
      "step": 145
    },
    {
      "epoch": 0.9526916802610114,
      "grad_norm": 0.0849609375,
      "learning_rate": 0.00017585387734006034,
      "loss": 1.0299,
      "step": 146
    },
    {
      "epoch": 0.9592169657422512,
      "grad_norm": 0.0810546875,
      "learning_rate": 0.00017551278794731607,
      "loss": 1.0578,
      "step": 147
    },
    {
      "epoch": 0.965742251223491,
      "grad_norm": 0.0859375,
      "learning_rate": 0.00017516964206608696,
      "loss": 1.0362,
      "step": 148
    },
    {
      "epoch": 0.9722675367047309,
      "grad_norm": 0.09130859375,
      "learning_rate": 0.00017482444904148617,
      "loss": 1.0356,
      "step": 149
    },
    {
      "epoch": 0.9787928221859706,
      "grad_norm": 0.0869140625,
      "learning_rate": 0.0001744772182743782,
      "loss": 1.038,
      "step": 150
    },
    {
      "epoch": 0.9853181076672104,
      "grad_norm": 0.0859375,
      "learning_rate": 0.00017412795922112253,
      "loss": 1.0445,
      "step": 151
    },
    {
      "epoch": 0.9918433931484503,
      "grad_norm": 0.08544921875,
      "learning_rate": 0.0001737766813933164,
      "loss": 1.0524,
      "step": 152
    },
    {
      "epoch": 0.99836867862969,
      "grad_norm": 0.08837890625,
      "learning_rate": 0.00017342339435753553,
      "loss": 1.0517,
      "step": 153
    },
    {
      "epoch": 1.0048939641109298,
      "grad_norm": 0.083984375,
      "learning_rate": 0.00017306810773507376,
      "loss": 1.0033,
      "step": 154
    },
    {
      "epoch": 1.0114192495921697,
      "grad_norm": 0.09033203125,
      "learning_rate": 0.00017271083120168102,
      "loss": 1.0477,
      "step": 155
    },
    {
      "epoch": 1.0048939641109298,
      "grad_norm": 0.13671875,
      "learning_rate": 0.00017235157448729967,
      "loss": 1.0619,
      "step": 156
    },
    {
      "epoch": 1.0048939641109298,
      "eval_loss": 1.0388679504394531,
      "eval_runtime": 236.7713,
      "eval_samples_per_second": 1.799,
      "eval_steps_per_second": 0.9,
      "step": 156
    },
    {
      "epoch": 1.0114192495921697,
      "grad_norm": 0.08740234375,
      "learning_rate": 0.0001719903473757996,
      "loss": 1.0131,
      "step": 157
    },
    {
      "epoch": 1.0179445350734095,
      "grad_norm": 0.0927734375,
      "learning_rate": 0.0001716271597047119,
      "loss": 0.9966,
      "step": 158
    },
    {
      "epoch": 1.0244698205546492,
      "grad_norm": 0.0947265625,
      "learning_rate": 0.0001712620213649608,
      "loss": 0.9817,
      "step": 159
    },
    {
      "epoch": 1.030995106035889,
      "grad_norm": 0.0888671875,
      "learning_rate": 0.00017089494230059432,
      "loss": 1.0036,
      "step": 160
    },
    {
      "epoch": 1.037520391517129,
      "grad_norm": 0.09716796875,
      "learning_rate": 0.0001705259325085135,
      "loss": 1.0318,
      "step": 161
    },
    {
      "epoch": 1.0440456769983686,
      "grad_norm": 0.09814453125,
      "learning_rate": 0.00017015500203820022,
      "loss": 1.0106,
      "step": 162
    },
    {
      "epoch": 1.0505709624796085,
      "grad_norm": 0.09521484375,
      "learning_rate": 0.0001697821609914432,
      "loss": 1.0178,
      "step": 163
    },
    {
      "epoch": 1.0570962479608483,
      "grad_norm": 0.09033203125,
      "learning_rate": 0.0001694074195220634,
      "loss": 0.9909,
      "step": 164
    },
    {
      "epoch": 1.0636215334420882,
      "grad_norm": 0.08740234375,
      "learning_rate": 0.000169030787835637,
      "loss": 0.9916,
      "step": 165
    },
    {
      "epoch": 1.0701468189233279,
      "grad_norm": 0.09130859375,
      "learning_rate": 0.00016865227618921788,
      "loss": 1.0101,
      "step": 166
    },
    {
      "epoch": 1.0766721044045677,
      "grad_norm": 0.0908203125,
      "learning_rate": 0.00016827189489105788,
      "loss": 0.9966,
      "step": 167
    },
    {
      "epoch": 1.0831973898858076,
      "grad_norm": 0.09521484375,
      "learning_rate": 0.00016788965430032638,
      "loss": 1.0048,
      "step": 168
    },
    {
      "epoch": 1.0897226753670473,
      "grad_norm": 0.09521484375,
      "learning_rate": 0.00016750556482682805,
      "loss": 1.0074,
      "step": 169
    },
    {
      "epoch": 1.0962479608482871,
      "grad_norm": 0.08935546875,
      "learning_rate": 0.00016711963693071943,
      "loss": 0.9762,
      "step": 170
    },
    {
      "epoch": 1.102773246329527,
      "grad_norm": 0.09619140625,
      "learning_rate": 0.00016673188112222394,
      "loss": 1.0044,
      "step": 171
    },
    {
      "epoch": 1.1092985318107667,
      "grad_norm": 0.091796875,
      "learning_rate": 0.00016634230796134576,
      "loss": 0.9972,
      "step": 172
    },
    {
      "epoch": 1.1158238172920065,
      "grad_norm": 0.09228515625,
      "learning_rate": 0.0001659509280575821,
      "loss": 1.0308,
      "step": 173
    },
    {
      "epoch": 1.1223491027732464,
      "grad_norm": 0.0927734375,
      "learning_rate": 0.0001655577520696346,
      "loss": 0.996,
      "step": 174
    },
    {
      "epoch": 1.128874388254486,
      "grad_norm": 0.0947265625,
      "learning_rate": 0.00016516279070511854,
      "loss": 0.9671,
      "step": 175
    },
    {
      "epoch": 1.135399673735726,
      "grad_norm": 0.09228515625,
      "learning_rate": 0.00016476605472027172,
      "loss": 1.0121,
      "step": 176
    },
    {
      "epoch": 1.1419249592169658,
      "grad_norm": 0.0927734375,
      "learning_rate": 0.00016436755491966115,
      "loss": 1.0132,
      "step": 177
    },
    {
      "epoch": 1.1484502446982057,
      "grad_norm": 0.09375,
      "learning_rate": 0.00016396730215588915,
      "loss": 1.0146,
      "step": 178
    },
    {
      "epoch": 1.1549755301794453,
      "grad_norm": 0.09521484375,
      "learning_rate": 0.0001635653073292975,
      "loss": 0.9911,
      "step": 179
    },
    {
      "epoch": 1.1615008156606852,
      "grad_norm": 0.09716796875,
      "learning_rate": 0.0001631615813876707,
      "loss": 1.0125,
      "step": 180
    },
    {
      "epoch": 1.1680261011419248,
      "grad_norm": 0.09521484375,
      "learning_rate": 0.0001627561353259379,
      "loss": 1.0162,
      "step": 181
    },
    {
      "epoch": 1.1745513866231647,
      "grad_norm": 0.09716796875,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.995,
      "step": 182
    },
    {
      "epoch": 1.1810766721044046,
      "grad_norm": 0.09326171875,
      "learning_rate": 0.00016194012705579572,
      "loss": 0.9839,
      "step": 183
    },
    {
      "epoch": 1.1876019575856445,
      "grad_norm": 0.09716796875,
      "learning_rate": 0.00016152958707026614,
      "loss": 1.0107,
      "step": 184
    },
    {
      "epoch": 1.1941272430668841,
      "grad_norm": 0.09326171875,
      "learning_rate": 0.00016111737140978494,
      "loss": 0.9715,
      "step": 185
    },
    {
      "epoch": 1.200652528548124,
      "grad_norm": 0.09326171875,
      "learning_rate": 0.00016070349130048724,
      "loss": 0.9751,
      "step": 186
    },
    {
      "epoch": 1.2071778140293639,
      "grad_norm": 0.09375,
      "learning_rate": 0.00016028795801383718,
      "loss": 0.9845,
      "step": 187
    },
    {
      "epoch": 1.2137030995106035,
      "grad_norm": 0.10302734375,
      "learning_rate": 0.0001598707828663209,
      "loss": 0.9604,
      "step": 188
    },
    {
      "epoch": 1.2202283849918434,
      "grad_norm": 0.09765625,
      "learning_rate": 0.00015945197721913833,
      "loss": 0.9715,
      "step": 189
    },
    {
      "epoch": 1.2267536704730833,
      "grad_norm": 0.0966796875,
      "learning_rate": 0.00015903155247789404,
      "loss": 1.0156,
      "step": 190
    },
    {
      "epoch": 1.233278955954323,
      "grad_norm": 0.09814453125,
      "learning_rate": 0.00015860952009228625,
      "loss": 1.0044,
      "step": 191
    },
    {
      "epoch": 1.2398042414355628,
      "grad_norm": 0.099609375,
      "learning_rate": 0.0001581858915557953,
      "loss": 0.9849,
      "step": 192
    },
    {
      "epoch": 1.2463295269168027,
      "grad_norm": 0.09619140625,
      "learning_rate": 0.0001577606784053705,
      "loss": 1.0007,
      "step": 193
    },
    {
      "epoch": 1.2528548123980423,
      "grad_norm": 0.0947265625,
      "learning_rate": 0.00015733389222111592,
      "loss": 0.9682,
      "step": 194
    },
    {
      "epoch": 1.2593800978792822,
      "grad_norm": 0.0966796875,
      "learning_rate": 0.00015690554462597522,
      "loss": 1.0165,
      "step": 195
    },
    {
      "epoch": 1.2593800978792822,
      "eval_loss": 1.0322120189666748,
      "eval_runtime": 236.6694,
      "eval_samples_per_second": 1.8,
      "eval_steps_per_second": 0.9,
      "step": 195
    },
    {
      "epoch": 1.265905383360522,
      "grad_norm": 0.1005859375,
      "learning_rate": 0.00015647564728541485,
      "loss": 1.0376,
      "step": 196
    },
    {
      "epoch": 1.272430668841762,
      "grad_norm": 0.09619140625,
      "learning_rate": 0.0001560442119071065,
      "loss": 1.0066,
      "step": 197
    },
    {
      "epoch": 1.2789559543230016,
      "grad_norm": 0.095703125,
      "learning_rate": 0.00015561125024060826,
      "loss": 0.9872,
      "step": 198
    },
    {
      "epoch": 1.2854812398042414,
      "grad_norm": 0.0966796875,
      "learning_rate": 0.0001551767740770446,
      "loss": 1.0079,
      "step": 199
    },
    {
      "epoch": 1.2920065252854813,
      "grad_norm": 0.09765625,
      "learning_rate": 0.00015474079524878525,
      "loss": 0.9865,
      "step": 200
    },
    {
      "epoch": 1.298531810766721,
      "grad_norm": 0.09423828125,
      "learning_rate": 0.000154303325629123,
      "loss": 0.9747,
      "step": 201
    },
    {
      "epoch": 1.3050570962479608,
      "grad_norm": 0.09814453125,
      "learning_rate": 0.0001538643771319503,
      "loss": 1.0119,
      "step": 202
    },
    {
      "epoch": 1.3115823817292007,
      "grad_norm": 0.095703125,
      "learning_rate": 0.00015342396171143488,
      "loss": 0.9815,
      "step": 203
    },
    {
      "epoch": 1.3181076672104406,
      "grad_norm": 0.09912109375,
      "learning_rate": 0.00015298209136169403,
      "loss": 0.9772,
      "step": 204
    },
    {
      "epoch": 1.3246329526916802,
      "grad_norm": 0.095703125,
      "learning_rate": 0.00015253877811646817,
      "loss": 0.9804,
      "step": 205
    },
    {
      "epoch": 1.3311582381729201,
      "grad_norm": 0.09716796875,
      "learning_rate": 0.00015209403404879303,
      "loss": 0.9457,
      "step": 206
    },
    {
      "epoch": 1.3376835236541598,
      "grad_norm": 0.1005859375,
      "learning_rate": 0.0001516478712706708,
      "loss": 0.9951,
      "step": 207
    },
    {
      "epoch": 1.3442088091353996,
      "grad_norm": 0.09521484375,
      "learning_rate": 0.00015120030193274027,
      "loss": 1.0085,
      "step": 208
    },
    {
      "epoch": 1.3507340946166395,
      "grad_norm": 0.09619140625,
      "learning_rate": 0.00015075133822394613,
      "loss": 1.0105,
      "step": 209
    },
    {
      "epoch": 1.3572593800978794,
      "grad_norm": 0.1025390625,
      "learning_rate": 0.00015030099237120674,
      "loss": 1.005,
      "step": 210
    },
    {
      "epoch": 1.363784665579119,
      "grad_norm": 0.0986328125,
      "learning_rate": 0.00014984927663908137,
      "loss": 0.9703,
      "step": 211
    },
    {
      "epoch": 1.370309951060359,
      "grad_norm": 0.0947265625,
      "learning_rate": 0.00014939620332943604,
      "loss": 0.9747,
      "step": 212
    },
    {
      "epoch": 1.3768352365415986,
      "grad_norm": 0.09716796875,
      "learning_rate": 0.00014894178478110857,
      "loss": 0.9785,
      "step": 213
    },
    {
      "epoch": 1.3833605220228384,
      "grad_norm": 0.09814453125,
      "learning_rate": 0.00014848603336957251,
      "loss": 1.0329,
      "step": 214
    },
    {
      "epoch": 1.3898858075040783,
      "grad_norm": 0.09423828125,
      "learning_rate": 0.00014802896150660022,
      "loss": 0.9429,
      "step": 215
    },
    {
      "epoch": 1.3964110929853182,
      "grad_norm": 0.099609375,
      "learning_rate": 0.00014757058163992464,
      "loss": 0.9578,
      "step": 216
    },
    {
      "epoch": 1.4029363784665578,
      "grad_norm": 0.1025390625,
      "learning_rate": 0.00014711090625290057,
      "loss": 1.0216,
      "step": 217
    },
    {
      "epoch": 1.4094616639477977,
      "grad_norm": 0.10986328125,
      "learning_rate": 0.0001466499478641644,
      "loss": 0.9792,
      "step": 218
    },
    {
      "epoch": 1.4159869494290376,
      "grad_norm": 0.095703125,
      "learning_rate": 0.00014618771902729342,
      "loss": 1.0001,
      "step": 219
    },
    {
      "epoch": 1.4225122349102772,
      "grad_norm": 0.1044921875,
      "learning_rate": 0.00014572423233046386,
      "loss": 1.0057,
      "step": 220
    },
    {
      "epoch": 1.429037520391517,
      "grad_norm": 0.09912109375,
      "learning_rate": 0.000145259500396108,
      "loss": 0.9698,
      "step": 221
    },
    {
      "epoch": 1.435562805872757,
      "grad_norm": 0.09814453125,
      "learning_rate": 0.00014479353588057052,
      "loss": 0.9533,
      "step": 222
    },
    {
      "epoch": 1.4420880913539968,
      "grad_norm": 0.103515625,
      "learning_rate": 0.00014432635147376376,
      "loss": 0.9686,
      "step": 223
    },
    {
      "epoch": 1.4486133768352365,
      "grad_norm": 0.0986328125,
      "learning_rate": 0.00014385795989882221,
      "loss": 1.0278,
      "step": 224
    },
    {
      "epoch": 1.4551386623164764,
      "grad_norm": 0.103515625,
      "learning_rate": 0.00014338837391175582,
      "loss": 1.0013,
      "step": 225
    },
    {
      "epoch": 1.461663947797716,
      "grad_norm": 0.10400390625,
      "learning_rate": 0.00014291760630110288,
      "loss": 1.0053,
      "step": 226
    },
    {
      "epoch": 1.468189233278956,
      "grad_norm": 0.10302734375,
      "learning_rate": 0.00014244566988758152,
      "loss": 1.0216,
      "step": 227
    },
    {
      "epoch": 1.4747145187601958,
      "grad_norm": 0.09912109375,
      "learning_rate": 0.0001419725775237406,
      "loss": 0.992,
      "step": 228
    },
    {
      "epoch": 1.4812398042414356,
      "grad_norm": 0.099609375,
      "learning_rate": 0.00014149834209360986,
      "loss": 1.0053,
      "step": 229
    },
    {
      "epoch": 1.4877650897226753,
      "grad_norm": 0.103515625,
      "learning_rate": 0.0001410229765123487,
      "loss": 0.9948,
      "step": 230
    },
    {
      "epoch": 1.4942903752039152,
      "grad_norm": 0.09912109375,
      "learning_rate": 0.00014054649372589482,
      "loss": 0.9717,
      "step": 231
    },
    {
      "epoch": 1.5008156606851548,
      "grad_norm": 0.0986328125,
      "learning_rate": 0.00014006890671061143,
      "loss": 0.9805,
      "step": 232
    },
    {
      "epoch": 1.5073409461663947,
      "grad_norm": 0.10400390625,
      "learning_rate": 0.00013959022847293391,
      "loss": 0.9826,
      "step": 233
    },
    {
      "epoch": 1.5138662316476346,
      "grad_norm": 0.09765625,
      "learning_rate": 0.0001391104720490156,
      "loss": 0.9394,
      "step": 234
    },
    {
      "epoch": 1.5138662316476346,
      "eval_loss": 1.0245814323425293,
      "eval_runtime": 236.6376,
      "eval_samples_per_second": 1.8,
      "eval_steps_per_second": 0.9,
      "step": 234
    },
    {
      "epoch": 1.5203915171288744,
      "grad_norm": 0.10107421875,
      "learning_rate": 0.0001386296505043728,
      "loss": 0.9857,
      "step": 235
    },
    {
      "epoch": 1.5269168026101143,
      "grad_norm": 0.099609375,
      "learning_rate": 0.000138147776933529,
      "loss": 0.997,
      "step": 236
    },
    {
      "epoch": 1.533442088091354,
      "grad_norm": 0.107421875,
      "learning_rate": 0.00013766486445965795,
      "loss": 0.9927,
      "step": 237
    },
    {
      "epoch": 1.5399673735725938,
      "grad_norm": 0.095703125,
      "learning_rate": 0.00013718092623422686,
      "loss": 0.9745,
      "step": 238
    },
    {
      "epoch": 1.5464926590538335,
      "grad_norm": 0.1005859375,
      "learning_rate": 0.00013669597543663762,
      "loss": 0.9842,
      "step": 239
    },
    {
      "epoch": 1.5530179445350734,
      "grad_norm": 0.099609375,
      "learning_rate": 0.00013621002527386834,
      "loss": 1.0102,
      "step": 240
    },
    {
      "epoch": 1.5595432300163132,
      "grad_norm": 0.1015625,
      "learning_rate": 0.0001357230889801133,
      "loss": 0.9389,
      "step": 241
    },
    {
      "epoch": 1.566068515497553,
      "grad_norm": 0.099609375,
      "learning_rate": 0.00013523517981642286,
      "loss": 1.0044,
      "step": 242
    },
    {
      "epoch": 1.572593800978793,
      "grad_norm": 0.09716796875,
      "learning_rate": 0.0001347463110703422,
      "loss": 0.9698,
      "step": 243
    },
    {
      "epoch": 1.5791190864600326,
      "grad_norm": 0.1015625,
      "learning_rate": 0.00013425649605554928,
      "loss": 0.9858,
      "step": 244
    },
    {
      "epoch": 1.5856443719412723,
      "grad_norm": 0.1396484375,
      "learning_rate": 0.00013376574811149253,
      "loss": 0.9513,
      "step": 245
    },
    {
      "epoch": 1.5921696574225122,
      "grad_norm": 0.10009765625,
      "learning_rate": 0.00013327408060302738,
      "loss": 0.9943,
      "step": 246
    },
    {
      "epoch": 1.598694942903752,
      "grad_norm": 0.0986328125,
      "learning_rate": 0.00013278150692005243,
      "loss": 0.9933,
      "step": 247
    },
    {
      "epoch": 1.605220228384992,
      "grad_norm": 0.1005859375,
      "learning_rate": 0.00013228804047714463,
      "loss": 0.9865,
      "step": 248
    },
    {
      "epoch": 1.6117455138662318,
      "grad_norm": 0.09716796875,
      "learning_rate": 0.00013179369471319404,
      "loss": 0.9466,
      "step": 249
    },
    {
      "epoch": 1.6182707993474714,
      "grad_norm": 0.0986328125,
      "learning_rate": 0.0001312984830910379,
      "loss": 0.9684,
      "step": 250
    },
    {
      "epoch": 1.6247960848287113,
      "grad_norm": 0.10205078125,
      "learning_rate": 0.00013080241909709387,
      "loss": 1.004,
      "step": 251
    },
    {
      "epoch": 1.631321370309951,
      "grad_norm": 0.10400390625,
      "learning_rate": 0.00013030551624099287,
      "loss": 0.9964,
      "step": 252
    },
    {
      "epoch": 1.6378466557911908,
      "grad_norm": 0.10888671875,
      "learning_rate": 0.000129807788055211,
      "loss": 0.9745,
      "step": 253
    },
    {
      "epoch": 1.6443719412724307,
      "grad_norm": 0.1044921875,
      "learning_rate": 0.00012930924809470115,
      "loss": 1.0074,
      "step": 254
    },
    {
      "epoch": 1.6508972267536706,
      "grad_norm": 0.1064453125,
      "learning_rate": 0.00012880990993652377,
      "loss": 0.9842,
      "step": 255
    },
    {
      "epoch": 1.6574225122349104,
      "grad_norm": 0.1025390625,
      "learning_rate": 0.00012830978717947718,
      "loss": 0.9699,
      "step": 256
    },
    {
      "epoch": 1.66394779771615,
      "grad_norm": 0.10009765625,
      "learning_rate": 0.00012780889344372718,
      "loss": 0.9892,
      "step": 257
    },
    {
      "epoch": 1.6704730831973897,
      "grad_norm": 0.1025390625,
      "learning_rate": 0.00012730724237043615,
      "loss": 0.9804,
      "step": 258
    },
    {
      "epoch": 1.6769983686786296,
      "grad_norm": 0.09814453125,
      "learning_rate": 0.0001268048476213914,
      "loss": 0.9873,
      "step": 259
    },
    {
      "epoch": 1.6835236541598695,
      "grad_norm": 0.09765625,
      "learning_rate": 0.0001263017228786334,
      "loss": 0.9737,
      "step": 260
    },
    {
      "epoch": 1.6900489396411094,
      "grad_norm": 0.10107421875,
      "learning_rate": 0.00012579788184408295,
      "loss": 1.0064,
      "step": 261
    },
    {
      "epoch": 1.6965742251223492,
      "grad_norm": 0.10888671875,
      "learning_rate": 0.00012529333823916807,
      "loss": 0.9745,
      "step": 262
    },
    {
      "epoch": 1.7030995106035889,
      "grad_norm": 0.1005859375,
      "learning_rate": 0.0001247881058044504,
      "loss": 0.9988,
      "step": 263
    },
    {
      "epoch": 1.7096247960848288,
      "grad_norm": 0.10595703125,
      "learning_rate": 0.00012428219829925083,
      "loss": 1.0021,
      "step": 264
    },
    {
      "epoch": 1.7161500815660684,
      "grad_norm": 0.09814453125,
      "learning_rate": 0.00012377562950127493,
      "loss": 0.9681,
      "step": 265
    },
    {
      "epoch": 1.7226753670473083,
      "grad_norm": 0.107421875,
      "learning_rate": 0.00012326841320623767,
      "loss": 0.9968,
      "step": 266
    },
    {
      "epoch": 1.7292006525285482,
      "grad_norm": 0.10791015625,
      "learning_rate": 0.00012276056322748778,
      "loss": 1.0235,
      "step": 267
    },
    {
      "epoch": 1.735725938009788,
      "grad_norm": 0.10498046875,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.977,
      "step": 268
    },
    {
      "epoch": 1.7422512234910277,
      "grad_norm": 0.10302734375,
      "learning_rate": 0.00012174301755815571,
      "loss": 1.0021,
      "step": 269
    },
    {
      "epoch": 1.7487765089722676,
      "grad_norm": 0.09716796875,
      "learning_rate": 0.0001212333495790514,
      "loss": 0.9781,
      "step": 270
    },
    {
      "epoch": 1.7553017944535072,
      "grad_norm": 0.10546875,
      "learning_rate": 0.00012072310333843544,
      "loss": 0.9901,
      "step": 271
    },
    {
      "epoch": 1.761827079934747,
      "grad_norm": 0.10205078125,
      "learning_rate": 0.00012021229273217302,
      "loss": 0.9675,
      "step": 272
    },
    {
      "epoch": 1.768352365415987,
      "grad_norm": 0.10546875,
      "learning_rate": 0.00011970093167149905,
      "loss": 0.999,
      "step": 273
    },
    {
      "epoch": 1.768352365415987,
      "eval_loss": 1.0181984901428223,
      "eval_runtime": 236.6668,
      "eval_samples_per_second": 1.8,
      "eval_steps_per_second": 0.9,
      "step": 273
    },
    {
      "epoch": 1.7748776508972268,
      "grad_norm": 0.1005859375,
      "learning_rate": 0.00011918903408263924,
      "loss": 0.9798,
      "step": 274
    },
    {
      "epoch": 1.7814029363784667,
      "grad_norm": 0.103515625,
      "learning_rate": 0.000118676613906431,
      "loss": 0.9826,
      "step": 275
    },
    {
      "epoch": 1.7879282218597063,
      "grad_norm": 0.0986328125,
      "learning_rate": 0.00011816368509794364,
      "loss": 0.9781,
      "step": 276
    },
    {
      "epoch": 1.7944535073409462,
      "grad_norm": 0.099609375,
      "learning_rate": 0.00011765026162609847,
      "loss": 0.9811,
      "step": 277
    },
    {
      "epoch": 1.8009787928221859,
      "grad_norm": 0.10498046875,
      "learning_rate": 0.00011713635747328818,
      "loss": 0.9859,
      "step": 278
    },
    {
      "epoch": 1.8075040783034257,
      "grad_norm": 0.10107421875,
      "learning_rate": 0.00011662198663499619,
      "loss": 0.9644,
      "step": 279
    },
    {
      "epoch": 1.8140293637846656,
      "grad_norm": 0.1025390625,
      "learning_rate": 0.0001161071631194155,
      "loss": 0.9931,
      "step": 280
    },
    {
      "epoch": 1.8205546492659055,
      "grad_norm": 0.09716796875,
      "learning_rate": 0.00011559190094706714,
      "loss": 1.0061,
      "step": 281
    },
    {
      "epoch": 1.8270799347471451,
      "grad_norm": 0.1015625,
      "learning_rate": 0.00011507621415041837,
      "loss": 0.9511,
      "step": 282
    },
    {
      "epoch": 1.833605220228385,
      "grad_norm": 0.10888671875,
      "learning_rate": 0.00011456011677350051,
      "loss": 0.9875,
      "step": 283
    },
    {
      "epoch": 1.8401305057096247,
      "grad_norm": 0.099609375,
      "learning_rate": 0.00011404362287152646,
      "loss": 0.9577,
      "step": 284
    },
    {
      "epoch": 1.8466557911908645,
      "grad_norm": 0.10205078125,
      "learning_rate": 0.00011352674651050796,
      "loss": 1.0018,
      "step": 285
    },
    {
      "epoch": 1.8531810766721044,
      "grad_norm": 0.1025390625,
      "learning_rate": 0.00011300950176687255,
      "loss": 0.9738,
      "step": 286
    },
    {
      "epoch": 1.8597063621533443,
      "grad_norm": 0.10009765625,
      "learning_rate": 0.00011249190272708008,
      "loss": 0.9635,
      "step": 287
    },
    {
      "epoch": 1.8662316476345842,
      "grad_norm": 0.10302734375,
      "learning_rate": 0.00011197396348723923,
      "loss": 0.9783,
      "step": 288
    },
    {
      "epoch": 1.8727569331158238,
      "grad_norm": 0.1123046875,
      "learning_rate": 0.0001114556981527236,
      "loss": 0.9895,
      "step": 289
    },
    {
      "epoch": 1.8792822185970635,
      "grad_norm": 0.10009765625,
      "learning_rate": 0.00011093712083778746,
      "loss": 0.9993,
      "step": 290
    },
    {
      "epoch": 1.8858075040783033,
      "grad_norm": 0.1123046875,
      "learning_rate": 0.00011041824566518146,
      "loss": 0.9842,
      "step": 291
    },
    {
      "epoch": 1.8923327895595432,
      "grad_norm": 0.10498046875,
      "learning_rate": 0.00010989908676576807,
      "loss": 0.9693,
      "step": 292
    },
    {
      "epoch": 1.898858075040783,
      "grad_norm": 0.0986328125,
      "learning_rate": 0.00010937965827813661,
      "loss": 0.9838,
      "step": 293
    },
    {
      "epoch": 1.905383360522023,
      "grad_norm": 0.1064453125,
      "learning_rate": 0.00010885997434821831,
      "loss": 0.9992,
      "step": 294
    },
    {
      "epoch": 1.9119086460032626,
      "grad_norm": 0.09912109375,
      "learning_rate": 0.00010834004912890092,
      "loss": 1.0066,
      "step": 295
    },
    {
      "epoch": 1.9184339314845025,
      "grad_norm": 0.10009765625,
      "learning_rate": 0.00010781989677964355,
      "loss": 0.9737,
      "step": 296
    },
    {
      "epoch": 1.9249592169657421,
      "grad_norm": 0.10546875,
      "learning_rate": 0.00010729953146609076,
      "loss": 0.9913,
      "step": 297
    },
    {
      "epoch": 1.931484502446982,
      "grad_norm": 0.10546875,
      "learning_rate": 0.00010677896735968693,
      "loss": 0.9835,
      "step": 298
    },
    {
      "epoch": 1.9380097879282219,
      "grad_norm": 0.1015625,
      "learning_rate": 0.00010625821863729036,
      "loss": 0.967,
      "step": 299
    },
    {
      "epoch": 1.9445350734094617,
      "grad_norm": 0.1015625,
      "learning_rate": 0.00010573729948078699,
      "loss": 0.9724,
      "step": 300
    },
    {
      "epoch": 1.9510603588907016,
      "grad_norm": 0.1005859375,
      "learning_rate": 0.00010521622407670439,
      "loss": 0.9732,
      "step": 301
    },
    {
      "epoch": 1.9575856443719413,
      "grad_norm": 0.1005859375,
      "learning_rate": 0.00010469500661582536,
      "loss": 1.0138,
      "step": 302
    },
    {
      "epoch": 1.964110929853181,
      "grad_norm": 0.1015625,
      "learning_rate": 0.00010417366129280133,
      "loss": 0.9903,
      "step": 303
    },
    {
      "epoch": 1.9706362153344208,
      "grad_norm": 0.099609375,
      "learning_rate": 0.0001036522023057659,
      "loss": 0.962,
      "step": 304
    },
    {
      "epoch": 1.9771615008156607,
      "grad_norm": 0.10302734375,
      "learning_rate": 0.00010313064385594822,
      "loss": 0.9793,
      "step": 305
    },
    {
      "epoch": 1.9836867862969005,
      "grad_norm": 0.103515625,
      "learning_rate": 0.0001026090001472861,
      "loss": 0.975,
      "step": 306
    }
  ],
  "logging_steps": 1,
  "max_steps": 612,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 153,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.127437882233979e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}