{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.778021978021978,
  "eval_steps": 500,
  "global_step": 270,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.6930128335952759,
      "learning_rate": 0.0,
      "loss": 2.928,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 2.0695436000823975,
      "learning_rate": 4e-05,
      "loss": 3.1113,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.7279797792434692,
      "learning_rate": 8e-05,
      "loss": 2.9342,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 2.2194223403930664,
      "learning_rate": 0.00012,
      "loss": 2.7118,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.230350971221924,
      "learning_rate": 0.00016,
      "loss": 2.7447,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 1.910759687423706,
      "learning_rate": 0.0002,
      "loss": 2.1327,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.5618112087249756,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.9556,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.9021365642547607,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.6424,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.286272644996643,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.4791,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.4115949869155884,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.377,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.145708441734314,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.2094,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.7020348310470581,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.0072,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5024922490119934,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0443,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5629758834838867,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.0639,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5546975135803223,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.314,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5420740842819214,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.0626,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.37482699751853943,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.1074,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.40214911103248596,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.9848,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.419202595949173,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.0753,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.33671835064888,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.0085,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.44745343923568726,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.9513,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.37639105319976807,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.1672,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.32556065917015076,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.9501,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.383694589138031,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.2319,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.37907055020332336,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.1092,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.41361159086227417,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.8801,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.35189583897590637,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9372,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3460371792316437,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.9824,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.2863202691078186,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.9519,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.35374775528907776,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.9488,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.33736664056777954,
      "learning_rate": 0.00018891352549889136,
      "loss": 1.003,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3823721408843994,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.9741,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.3287733197212219,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.7298,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.32600271701812744,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.9182,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.2565169036388397,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.9745,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.2968987822532654,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.9073,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3006089925765991,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.0081,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.33710068464279175,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.1097,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.303536057472229,
      "learning_rate": 0.0001853658536585366,
      "loss": 1.0739,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3171040117740631,
      "learning_rate": 0.00018492239467849224,
      "loss": 1.2348,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.22676604986190796,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.9608,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3190021812915802,
      "learning_rate": 0.00018403547671840356,
      "loss": 1.0562,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.32901304960250854,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.99,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.2709827721118927,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.9346,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.3040912449359894,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.9768,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.29077914357185364,
      "learning_rate": 0.00018226164079822616,
      "loss": 1.1089,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.28233659267425537,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.9453,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.3262775242328644,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.1054,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.279989093542099,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.9303,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.25710755586624146,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.9733,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.3231169581413269,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.0238,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.33115774393081665,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.9413,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.2491127848625183,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.8925,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.31202462315559387,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.8995,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.2637079954147339,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.8217,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.3263390064239502,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.0353,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.2859494090080261,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.9515,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.3218170404434204,
      "learning_rate": 0.000176940133037694,
      "loss": 0.9058,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.2746146023273468,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.9533,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.28438180685043335,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.7757,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.31144917011260986,
      "learning_rate": 0.000175609756097561,
      "loss": 0.9712,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.27892422676086426,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.8667,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3682326674461365,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.964,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.3652111887931824,
      "learning_rate": 0.00017427937915742792,
      "loss": 1.0425,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.36866724491119385,
      "learning_rate": 0.0001738359201773836,
      "loss": 1.0384,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3109075725078583,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.9583,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.35701784491539,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.9576,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.4238913059234619,
      "learning_rate": 0.00017250554323725056,
      "loss": 1.2114,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.31754815578460693,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.889,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3375859558582306,
      "learning_rate": 0.00017161862527716187,
      "loss": 1.0122,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.2911067008972168,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.8656,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.30369794368743896,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.9576,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.29462429881095886,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.9093,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.31118860840797424,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.9206,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.2751140892505646,
      "learning_rate": 0.00016940133037694015,
      "loss": 1.0311,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.2821599841117859,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.9317,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.33688560128211975,
      "learning_rate": 0.00016851441241685144,
      "loss": 1.1574,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.27711614966392517,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.8769,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.2877914607524872,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.7165,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.37430161237716675,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.9988,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.30598729848861694,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.9448,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.3497956693172455,
      "learning_rate": 0.00016629711751662974,
      "loss": 1.0439,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.275566041469574,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.9048,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.2594054639339447,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.8272,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.33042293787002563,
      "learning_rate": 0.00016496674057649667,
      "loss": 1.0435,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.31174999475479126,
      "learning_rate": 0.00016452328159645234,
      "loss": 1.0867,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.28217947483062744,
      "learning_rate": 0.000164079822616408,
      "loss": 0.8824,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.31404972076416016,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.1421,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.33777496218681335,
      "learning_rate": 0.0001631929046563193,
      "loss": 1.1011,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.2836039662361145,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.767,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.25027620792388916,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.7865,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.29174336791038513,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.8532,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.3475264012813568,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.8624,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.2773895561695099,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.9028,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.31629523634910583,
      "learning_rate": 0.00016053215077605322,
      "loss": 1.0586,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.39944446086883545,
      "learning_rate": 0.00016008869179600887,
      "loss": 1.0143,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.3276192247867584,
      "learning_rate": 0.00015964523281596454,
      "loss": 1.1036,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.2896903455257416,
      "learning_rate": 0.00015920177383592018,
      "loss": 1.0489,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.30382803082466125,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.972,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.3121547996997833,
      "learning_rate": 0.0001583148558758315,
      "loss": 1.0882,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.3023766577243805,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.7809,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.2780039608478546,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.8836,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.3332766592502594,
      "learning_rate": 0.00015698447893569846,
      "loss": 1.0694,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.29558783769607544,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.8415,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.5045173168182373,
      "learning_rate": 0.00015609756097560978,
      "loss": 1.118,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.3304552137851715,
      "learning_rate": 0.00015565410199556542,
      "loss": 1.0419,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.34461191296577454,
      "learning_rate": 0.00015521064301552106,
      "loss": 1.135,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.3275623619556427,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.8303,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.32883021235466003,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.9534,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.32757338881492615,
      "learning_rate": 0.00015388026607538802,
      "loss": 1.0292,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.27910470962524414,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.7889,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.37619730830192566,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.9531,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.31574106216430664,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.7694,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.34590858221054077,
      "learning_rate": 0.00015210643015521066,
      "loss": 1.1163,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.35482433438301086,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.7629,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.4208705425262451,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.9236,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.43589532375335693,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.9507,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.3324430286884308,
      "learning_rate": 0.0001503325942350333,
      "loss": 1.0232,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.31654858589172363,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.804,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.3578777313232422,
      "learning_rate": 0.00014944567627494458,
      "loss": 1.0838,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.34919649362564087,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.9546,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.38925492763519287,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.9944,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.3600817620754242,
      "learning_rate": 0.00014811529933481154,
      "loss": 1.031,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.27231305837631226,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.8119,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.36040836572647095,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.9111,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.32915768027305603,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.8508,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.36124947667121887,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.922,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.34751126170158386,
      "learning_rate": 0.0001458980044345898,
      "loss": 1.0451,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.3373923897743225,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.8848,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.2610858678817749,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.8306,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.35008230805397034,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.9276,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.28943729400634766,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.7841,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.3186952769756317,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.9654,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.3269159197807312,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.9193,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.3147454261779785,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.9692,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.2752673923969269,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.8861,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.3329693377017975,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.8469,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.3413521945476532,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.8924,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.31446534395217896,
      "learning_rate": 0.000141019955654102,
      "loss": 0.7786,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.3619074523448944,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.8564,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.3891836106777191,
      "learning_rate": 0.00014013303769401332,
      "loss": 1.1423,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.30770009756088257,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.8446,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.32106268405914307,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.7408,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.37367093563079834,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.9217,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.29945507645606995,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.9278,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.3027839660644531,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.9139,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.3183470666408539,
      "learning_rate": 0.00013747228381374724,
      "loss": 1.0583,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.4891042113304138,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.9839,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.3688880503177643,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.9675,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.3271139860153198,
      "learning_rate": 0.00013614190687361418,
      "loss": 1.0155,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.318075031042099,
      "learning_rate": 0.00013569844789356985,
      "loss": 1.0282,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5676755905151367,
      "learning_rate": 0.0001352549889135255,
      "loss": 1.1171,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.3654722273349762,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.6907,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.33860713243484497,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.8817,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.384088933467865,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.9015,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.3659598231315613,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.8327,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.36128368973731995,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.9936,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.34745991230010986,
      "learning_rate": 0.00013259423503325944,
      "loss": 1.1411,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.28069716691970825,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.7375,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.33490055799484253,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.8096,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.38482752442359924,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.9818,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.33197125792503357,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.7755,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.36582455039024353,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.8951,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.40773439407348633,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.9694,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.454887330532074,
      "learning_rate": 0.000129490022172949,
      "loss": 0.858,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.33256253600120544,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.8881,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.4032762050628662,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.8342,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.3344157934188843,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.9812,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.3543623089790344,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.8367,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.4186347424983978,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.9294,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.3853510022163391,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.9117,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.39438897371292114,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.7036,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.35599595308303833,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.7147,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.37087661027908325,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.971,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.41872212290763855,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.8938,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.43149900436401367,
      "learning_rate": 0.0001246119733924612,
      "loss": 1.0002,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.4324473440647125,
      "learning_rate": 0.00012416851441241685,
      "loss": 1.0454,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.426993727684021,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.8221,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.35376137495040894,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.7778,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.3335689306259155,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.7919,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.3972911238670349,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.8262,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.43739598989486694,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.8306,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.37755346298217773,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.6756,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.3913998603820801,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.781,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.37282794713974,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.8199,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.37491321563720703,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.8653,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.3359408974647522,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.7828,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.4867953658103943,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.8798,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.4904435873031616,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.791,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.32608407735824585,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.762,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.4891336262226105,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.9012,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.42415574193000793,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.8063,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.4244902431964874,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.8998,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.34502360224723816,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.6885,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.43045124411582947,
      "learning_rate": 0.00011618625277161863,
      "loss": 1.0175,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.4733395278453827,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.8021,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.48999080061912537,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.7043,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.45415598154067993,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.8804,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.4172290563583374,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.6526,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.4447998106479645,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.963,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.5015835165977478,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.9245,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.45346951484680176,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.9357,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.4470013380050659,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.946,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.4663847088813782,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.8789,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.5370610952377319,
      "learning_rate": 0.00011175166297117516,
      "loss": 1.0416,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.5041185617446899,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.9507,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.49543726444244385,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.798,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.30527275800704956,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.5458,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.4312393367290497,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.6798,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.4694804847240448,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.7815,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.4962475895881653,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.8366,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.4185539782047272,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.9254,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.4347681701183319,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.984,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.4761349856853485,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.7432,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.45826518535614014,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.9174,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.412378191947937,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.8497,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.5427189469337463,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.7651,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.5400201678276062,
      "learning_rate": 0.00010598669623059867,
      "loss": 1.1319,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.47205066680908203,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.8337,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.4242938756942749,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.8419,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.3807678520679474,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.7633,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.5604559779167175,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.9019,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.5625519752502441,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.9572,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.49393072724342346,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.8432,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.48364537954330444,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.8119,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.5197112560272217,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.845,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.5382224917411804,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.7792,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.4762476086616516,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.7739,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.4826640188694,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.9453,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.5029851198196411,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.8364,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.5529888272285461,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.8939,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.48370257019996643,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.7636,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.5642214417457581,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.7194,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.530613124370575,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.9193,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.48665669560432434,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.7856,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.4574538469314575,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.8276,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.5267653465270996,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.9417,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.5731924176216125,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.8228,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.5030391216278076,
      "learning_rate": 9.667405764966742e-05,
      "loss": 1.0216,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.517092227935791,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.9204,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.47126346826553345,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.7168,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.4682159125804901,
      "learning_rate": 9.534368070953438e-05,
      "loss": 0.742,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.43394774198532104,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.8273,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.5333678126335144,
      "learning_rate": 9.445676274944568e-05,
      "loss": 0.7077,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.498773455619812,
      "learning_rate": 9.401330376940134e-05,
      "loss": 0.8365,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.421216756105423,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.6706,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.4821241497993469,
      "learning_rate": 9.312638580931264e-05,
      "loss": 0.7564,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.4917333126068115,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.9009,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.44124066829681396,
      "learning_rate": 9.223946784922394e-05,
      "loss": 0.6905,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.43866556882858276,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.7102,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.4908434748649597,
      "learning_rate": 9.135254988913526e-05,
      "loss": 0.8377,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.5608130097389221,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.8236,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.5127186179161072,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.879,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.5649936199188232,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.7949,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.6240202784538269,
      "learning_rate": 8.957871396895788e-05,
      "loss": 0.8524,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.6061081886291504,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.8846,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.5024527907371521,
      "learning_rate": 8.869179600886919e-05,
      "loss": 0.9297,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.46925368905067444,
      "learning_rate": 8.824833702882484e-05,
      "loss": 0.7879,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.5068337321281433,
      "learning_rate": 8.78048780487805e-05,
      "loss": 0.7673,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.48550689220428467,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.9313,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.5283243060112,
      "learning_rate": 8.69179600886918e-05,
      "loss": 0.8819,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.54749995470047,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.8372,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.49284231662750244,
      "learning_rate": 8.603104212860311e-05,
      "loss": 0.8814,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.555268406867981,
      "learning_rate": 8.558758314855876e-05,
      "loss": 0.7835,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.555834949016571,
      "learning_rate": 8.514412416851442e-05,
      "loss": 0.8541,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.4698779284954071,
      "learning_rate": 8.470066518847007e-05,
      "loss": 0.8399,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.5328496694564819,
      "learning_rate": 8.425720620842572e-05,
      "loss": 0.8227,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.5266067981719971,
      "learning_rate": 8.381374722838138e-05,
      "loss": 0.8364,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.6609089970588684,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.7984,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.5935308933258057,
      "learning_rate": 8.292682926829268e-05,
      "loss": 0.8908,
      "step": 270
    }
  ],
  "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": 4.341694410655334e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}