{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.1714285714285713,
  "eval_steps": 500,
  "global_step": 330,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.1175572872161865,
      "learning_rate": 0.0,
      "loss": 3.0744,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.2595356702804565,
      "learning_rate": 4e-05,
      "loss": 3.3519,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.1831451654434204,
      "learning_rate": 8e-05,
      "loss": 3.4142,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.1135042905807495,
      "learning_rate": 0.00012,
      "loss": 2.8473,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.6986281871795654,
      "learning_rate": 0.00016,
      "loss": 3.1145,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 1.8996844291687012,
      "learning_rate": 0.0002,
      "loss": 2.7206,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 1.654848337173462,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.6435,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.9960455894470215,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.6488,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.1452784538269043,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2791,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.9133374094963074,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.0621,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.7128933668136597,
      "learning_rate": 0.00019778270509977829,
      "loss": 0.8729,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.9738520383834839,
      "learning_rate": 0.00019733924611973393,
      "loss": 0.945,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 1.0968796014785767,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.9219,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.8448852300643921,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.7323,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.6533470153808594,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.7965,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5058298707008362,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.7675,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.5244030952453613,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.6938,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.5534260869026184,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.7475,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.49227115511894226,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.7782,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.6014466881752014,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.6281,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.46302980184555054,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.6085,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3817231357097626,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.4978,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.41959288716316223,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.7479,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.37861549854278564,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.5145,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.41947174072265625,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.6564,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.43568453192710876,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.7639,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.35360434651374817,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.7617,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.43759599328041077,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.6815,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3009309470653534,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.5048,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.37697890400886536,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.5197,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.36582183837890625,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.4953,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.4371263384819031,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.6357,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.35323941707611084,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.6407,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.4218985438346863,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.6067,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.4576883614063263,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.7649,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3939562737941742,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.7539,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3907439112663269,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.6574,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.34653839468955994,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.4845,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.30807438492774963,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.5046,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3422587811946869,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.642,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.4083802103996277,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.6177,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3902239203453064,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.6883,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.413637638092041,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.5178,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.3305671513080597,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.4925,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.3556175231933594,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.4991,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.3833027482032776,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.5837,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.34828928112983704,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.4893,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.4020296335220337,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.4792,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.47377222776412964,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.5776,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.47716471552848816,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.6295,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.4160218834877014,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.5249,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.3925120234489441,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.5979,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.451288104057312,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.7045,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.44237250089645386,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.6288,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.37273454666137695,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.5214,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.4249885380268097,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.6523,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.4397568702697754,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.7857,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.37436991930007935,
      "learning_rate": 0.000176940133037694,
      "loss": 0.5266,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.3295058310031891,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.5685,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.3959578275680542,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.4584,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.37387439608573914,
      "learning_rate": 0.000175609756097561,
      "loss": 0.5703,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.28911006450653076,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.4591,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.6077892184257507,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.7229,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.44933897256851196,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.4895,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.4583057463169098,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.5422,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.441131055355072,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.5039,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.37214893102645874,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.4451,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.37915486097335815,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.5498,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.43058085441589355,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.6258,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.4087371528148651,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.4304,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3702792525291443,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.5061,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.40271690487861633,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.5221,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.4654999077320099,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.5427,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.422850638628006,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.5003,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.35233739018440247,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.5353,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.3508605659008026,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.5011,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.35129278898239136,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.5396,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.4907684922218323,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.5464,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.3281923234462738,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.5209,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.444183349609375,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.7176,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.5929686427116394,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.6389,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.40402573347091675,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.4612,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.4387584626674652,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.4967,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3580304682254791,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.5834,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.5472170114517212,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.5454,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.4298936426639557,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.4903,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.428013414144516,
      "learning_rate": 0.000164079822616408,
      "loss": 0.5407,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.4182053506374359,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.5558,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3617396652698517,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.4448,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.35693031549453735,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.5425,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.3613317012786865,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.4412,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.417049765586853,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.5735,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.43856459856033325,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.4225,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.47907739877700806,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.502,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.36149153113365173,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.4725,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.4654827117919922,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.5749,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.4263451397418976,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.5116,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.44888293743133545,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.5232,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.5640338659286499,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.7007,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.4415484070777893,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.3907,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.473460853099823,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.55,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.5150168538093567,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.5257,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.3559170365333557,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.4953,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.3546290099620819,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.5694,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.4086984395980835,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.4952,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.4047616422176361,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.4458,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.35968494415283203,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.4463,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.42160969972610474,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.5333,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.49412330985069275,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.6404,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.4050638675689697,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.5419,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.3907662034034729,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.5049,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.36140918731689453,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.4011,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.38780495524406433,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.5795,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 1.2969988584518433,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.5652,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.41087356209754944,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.5451,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.351934015750885,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.5072,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.3761547803878784,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.4851,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.38351503014564514,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.479,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.3756462037563324,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.4348,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.42825978994369507,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.6265,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.40038374066352844,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.4257,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.40185239911079407,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.4819,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.3839464485645294,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.4153,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.4148792624473572,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.5652,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.37263253331184387,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.619,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.4481087327003479,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.5542,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.39149171113967896,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.5478,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.3571181297302246,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.5864,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.3801731765270233,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.5381,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.3862723708152771,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.4461,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.36548087000846863,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.5404,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.3452293276786804,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.4019,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.3497912287712097,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.5098,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.35823172330856323,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.5005,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.4362906217575073,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.4726,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.38212844729423523,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.5083,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.40376564860343933,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.4904,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.38468191027641296,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.5085,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.4096522629261017,
      "learning_rate": 0.000141019955654102,
      "loss": 0.4871,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.4750652313232422,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.4523,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.3995967507362366,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.5426,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.3848707675933838,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.4811,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.36099928617477417,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.4182,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.47264882922172546,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.3971,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.41076722741127014,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.5617,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.2651715874671936,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.4181,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.3821229338645935,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.3827,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.3557185232639313,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.3979,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.37807080149650574,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.5276,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.3489227294921875,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.4667,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.4312669634819031,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.5085,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5447825193405151,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.4935,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.32439136505126953,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.3268,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.32710787653923035,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.4445,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.36168673634529114,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.4274,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.38555222749710083,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.4754,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.3598826229572296,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.3901,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.43716490268707275,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.3094,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.36829623579978943,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.4367,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.4934532642364502,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.3806,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.38397151231765747,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.3425,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.40905672311782837,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.5985,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.4286136031150818,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.4549,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.5130642652511597,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.4132,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.45624852180480957,
      "learning_rate": 0.000129490022172949,
      "loss": 0.458,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.39248326420783997,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.3959,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.4087737202644348,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.298,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.3303489685058594,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.3373,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.40938934683799744,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.3451,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.4682055115699768,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.4516,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.4584009647369385,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.4645,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.372245728969574,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.312,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.37105751037597656,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.359,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.46969908475875854,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.403,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.44157159328460693,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.5257,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.4284711480140686,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.35,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.5392049551010132,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.4616,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.44538211822509766,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.3029,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.397977352142334,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.4254,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.47894006967544556,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.3971,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.4622189998626709,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.416,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.4657520353794098,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.412,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.40158042311668396,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.3782,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.5625936388969421,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.3868,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.6642662286758423,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.5048,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.481275349855423,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.3754,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.5356916785240173,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.4276,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.4984596073627472,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.4334,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.43002745509147644,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.3791,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.47355565428733826,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.4529,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.43340304493904114,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.3329,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.43819621205329895,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.3533,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.4530319571495056,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.344,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.44500353932380676,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.365,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.5287085175514221,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.4125,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.5646275877952576,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.3593,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.4645012319087982,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.3502,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.5080211758613586,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.4507,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.41564974188804626,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.3555,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.5530214905738831,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.4125,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.44988399744033813,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.491,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.5231350064277649,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.4134,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.5113458037376404,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.4081,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.6865445375442505,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.3838,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.48441004753112793,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.3904,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.4840584695339203,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.3864,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.44177472591400146,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.368,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.501458466053009,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.3655,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.47747597098350525,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.3568,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.6014925241470337,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.4423,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.5459688305854797,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.3745,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.5288100242614746,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.388,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.5560075640678406,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.4398,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.5840931534767151,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.3618,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.5484616160392761,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.3555,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.593464195728302,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.4097,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.7812267541885376,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.4228,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.7217245101928711,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.4135,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.547836184501648,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.4514,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.4315856993198395,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.3474,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.6103102564811707,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.3661,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.6544564366340637,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.3761,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.531951367855072,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.4533,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.6299111843109131,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.3715,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.609921932220459,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.4477,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.6111509799957275,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.5078,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.5808625221252441,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.4138,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.6177905797958374,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.3766,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.6424322724342346,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.3628,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.6043084859848022,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.3328,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.6308062076568604,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.3428,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.63124018907547,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.3397,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.6130645275115967,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.4183,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.6135052442550659,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.4458,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.5835489630699158,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.3602,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.643936812877655,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.4288,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.6135910749435425,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.3893,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.7730970978736877,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.3779,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.6241534948348999,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.3498,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.6003444194793701,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.3269,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.5080982446670532,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.424,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.5332189798355103,
      "learning_rate": 9.534368070953438e-05,
      "loss": 0.3855,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.6306498050689697,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.3687,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.6601876020431519,
      "learning_rate": 9.445676274944568e-05,
      "loss": 0.3918,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.5683952569961548,
      "learning_rate": 9.401330376940134e-05,
      "loss": 0.3671,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.5387312769889832,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.3399,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.5436490178108215,
      "learning_rate": 9.312638580931264e-05,
      "loss": 0.3882,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.6847561597824097,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.3846,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.5701587796211243,
      "learning_rate": 9.223946784922394e-05,
      "loss": 0.3969,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.6424371004104614,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.5884,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.7478569746017456,
      "learning_rate": 9.135254988913526e-05,
      "loss": 0.4742,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.7700985074043274,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.4526,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.6621297001838684,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.4101,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.5570635199546814,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.3561,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.5587785243988037,
      "learning_rate": 8.957871396895788e-05,
      "loss": 0.3704,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.536127507686615,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.3782,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.7835214138031006,
      "learning_rate": 8.869179600886919e-05,
      "loss": 0.4355,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.6151403784751892,
      "learning_rate": 8.824833702882484e-05,
      "loss": 0.4165,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.642164945602417,
      "learning_rate": 8.78048780487805e-05,
      "loss": 0.341,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.6211482286453247,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.3711,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.5878557562828064,
      "learning_rate": 8.69179600886918e-05,
      "loss": 0.4751,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.5607050657272339,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.3138,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.5980952978134155,
      "learning_rate": 8.603104212860311e-05,
      "loss": 0.376,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.538848876953125,
      "learning_rate": 8.558758314855876e-05,
      "loss": 0.3729,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.6324768662452698,
      "learning_rate": 8.514412416851442e-05,
      "loss": 0.3589,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.6783068180084229,
      "learning_rate": 8.470066518847007e-05,
      "loss": 0.4309,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.5527329444885254,
      "learning_rate": 8.425720620842572e-05,
      "loss": 0.3766,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.6501910090446472,
      "learning_rate": 8.381374722838138e-05,
      "loss": 0.5597,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.7451267242431641,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.4383,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.5386755466461182,
      "learning_rate": 8.292682926829268e-05,
      "loss": 0.3546,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.5901831984519958,
      "learning_rate": 8.248337028824834e-05,
      "loss": 0.3724,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.6270937919616699,
      "learning_rate": 8.2039911308204e-05,
      "loss": 0.2934,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.6454430222511292,
      "learning_rate": 8.159645232815965e-05,
      "loss": 0.4119,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.6793332695960999,
      "learning_rate": 8.11529933481153e-05,
      "loss": 0.4462,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.6240165829658508,
      "learning_rate": 8.070953436807095e-05,
      "loss": 0.4505,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.6699845194816589,
      "learning_rate": 8.026607538802661e-05,
      "loss": 0.3936,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.7052980661392212,
      "learning_rate": 7.982261640798227e-05,
      "loss": 0.3686,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.6768690347671509,
      "learning_rate": 7.937915742793793e-05,
      "loss": 0.3587,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.6286340355873108,
      "learning_rate": 7.893569844789357e-05,
      "loss": 0.4788,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.7440539002418518,
      "learning_rate": 7.849223946784923e-05,
      "loss": 0.3866,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.5840330719947815,
      "learning_rate": 7.804878048780489e-05,
      "loss": 0.4327,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.5658918023109436,
      "learning_rate": 7.760532150776053e-05,
      "loss": 0.29,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.5715025067329407,
      "learning_rate": 7.716186252771619e-05,
      "loss": 0.3226,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.7134278416633606,
      "learning_rate": 7.671840354767185e-05,
      "loss": 0.4735,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.5608999133110046,
      "learning_rate": 7.627494456762749e-05,
      "loss": 0.3853,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.591826856136322,
      "learning_rate": 7.583148558758315e-05,
      "loss": 0.3287,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.6222074627876282,
      "learning_rate": 7.538802660753881e-05,
      "loss": 0.3492,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.6133440136909485,
      "learning_rate": 7.494456762749445e-05,
      "loss": 0.3292,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.5629295110702515,
      "learning_rate": 7.450110864745011e-05,
      "loss": 0.396,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.6393409967422485,
      "learning_rate": 7.405764966740577e-05,
      "loss": 0.3658,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.59514319896698,
      "learning_rate": 7.361419068736141e-05,
      "loss": 0.3462,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.559347927570343,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.274,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.6032190322875977,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.5212,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.6341789364814758,
      "learning_rate": 7.228381374722837e-05,
      "loss": 0.4197,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.6444764733314514,
      "learning_rate": 7.184035476718403e-05,
      "loss": 0.3578,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.6167255640029907,
      "learning_rate": 7.139689578713969e-05,
      "loss": 0.4272,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.6650995016098022,
      "learning_rate": 7.095343680709535e-05,
      "loss": 0.3834,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.6289847493171692,
      "learning_rate": 7.0509977827051e-05,
      "loss": 0.3697,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.6074461936950684,
      "learning_rate": 7.006651884700666e-05,
      "loss": 0.3731,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.5654978156089783,
      "learning_rate": 6.962305986696232e-05,
      "loss": 0.3075,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.6505368947982788,
      "learning_rate": 6.917960088691796e-05,
      "loss": 0.4137,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.5887136459350586,
      "learning_rate": 6.873614190687362e-05,
      "loss": 0.3306,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.5790920257568359,
      "learning_rate": 6.829268292682928e-05,
      "loss": 0.3979,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8983719944953918,
      "learning_rate": 6.784922394678492e-05,
      "loss": 0.4503,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.5194648504257202,
      "learning_rate": 6.740576496674058e-05,
      "loss": 0.3181,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.4476855397224426,
      "learning_rate": 6.696230598669624e-05,
      "loss": 0.1954,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.5169367790222168,
      "learning_rate": 6.651884700665188e-05,
      "loss": 0.2893,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.5720203518867493,
      "learning_rate": 6.607538802660754e-05,
      "loss": 0.305,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.46126630902290344,
      "learning_rate": 6.56319290465632e-05,
      "loss": 0.2755,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.49057164788246155,
      "learning_rate": 6.518847006651884e-05,
      "loss": 0.2742,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.5442298650741577,
      "learning_rate": 6.47450110864745e-05,
      "loss": 0.2893,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.6755426526069641,
      "learning_rate": 6.430155210643016e-05,
      "loss": 0.3275,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.592153787612915,
      "learning_rate": 6.38580931263858e-05,
      "loss": 0.2714,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.42081865668296814,
      "learning_rate": 6.341463414634146e-05,
      "loss": 0.2378,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.5356279015541077,
      "learning_rate": 6.297117516629712e-05,
      "loss": 0.1549,
      "step": 315
    },
    {
      "epoch": 2.0791208791208793,
      "grad_norm": 0.6697273254394531,
      "learning_rate": 6.252771618625277e-05,
      "loss": 0.337,
      "step": 316
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.5769929885864258,
      "learning_rate": 6.208425720620842e-05,
      "loss": 0.2079,
      "step": 317
    },
    {
      "epoch": 2.0923076923076924,
      "grad_norm": 0.5834750533103943,
      "learning_rate": 6.164079822616408e-05,
      "loss": 0.308,
      "step": 318
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.505768358707428,
      "learning_rate": 6.119733924611974e-05,
      "loss": 0.1968,
      "step": 319
    },
    {
      "epoch": 2.1054945054945056,
      "grad_norm": 0.6112735271453857,
      "learning_rate": 6.075388026607539e-05,
      "loss": 0.2804,
      "step": 320
    },
    {
      "epoch": 2.112087912087912,
      "grad_norm": 0.6500109434127808,
      "learning_rate": 6.031042128603105e-05,
      "loss": 0.2308,
      "step": 321
    },
    {
      "epoch": 2.1186813186813187,
      "grad_norm": 0.6243614554405212,
      "learning_rate": 5.98669623059867e-05,
      "loss": 0.2483,
      "step": 322
    },
    {
      "epoch": 2.1252747252747253,
      "grad_norm": 0.70741206407547,
      "learning_rate": 5.942350332594236e-05,
      "loss": 0.3121,
      "step": 323
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.6219747066497803,
      "learning_rate": 5.898004434589801e-05,
      "loss": 0.3055,
      "step": 324
    },
    {
      "epoch": 2.1384615384615384,
      "grad_norm": 0.6348203420639038,
      "learning_rate": 5.853658536585366e-05,
      "loss": 0.2511,
      "step": 325
    },
    {
      "epoch": 2.145054945054945,
      "grad_norm": 0.661316454410553,
      "learning_rate": 5.809312638580932e-05,
      "loss": 0.2411,
      "step": 326
    },
    {
      "epoch": 2.1516483516483516,
      "grad_norm": 0.6025199294090271,
      "learning_rate": 5.7649667405764975e-05,
      "loss": 0.217,
      "step": 327
    },
    {
      "epoch": 2.158241758241758,
      "grad_norm": 0.5600637793540955,
      "learning_rate": 5.720620842572062e-05,
      "loss": 0.217,
      "step": 328
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 0.6027415990829468,
      "learning_rate": 5.676274944567628e-05,
      "loss": 0.2732,
      "step": 329
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.5948612689971924,
      "learning_rate": 5.6319290465631935e-05,
      "loss": 0.2324,
      "step": 330
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3648771382748365e+17,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}