{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.3824175824175824,
  "eval_steps": 500,
  "global_step": 210,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.80160653591156,
      "learning_rate": 0.0,
      "loss": 2.9328,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.7631034851074219,
      "learning_rate": 4e-05,
      "loss": 2.5632,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.979168176651001,
      "learning_rate": 8e-05,
      "loss": 2.8893,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.628666639328003,
      "learning_rate": 0.00012,
      "loss": 2.6316,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.1780693531036377,
      "learning_rate": 0.00016,
      "loss": 2.9097,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.302360773086548,
      "learning_rate": 0.0002,
      "loss": 2.1123,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.914445400238037,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.1906,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.5178985595703125,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.1279,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.929740846157074,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.3212,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.4806253910064697,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.3838,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.0875375270843506,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.2722,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5247994065284729,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.033,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.4811086654663086,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.1717,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.48578667640686035,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.0371,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5592583417892456,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.0944,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.4616752564907074,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.2038,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.35458147525787354,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.9475,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.4379289746284485,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.1557,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.47600260376930237,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.0279,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.41127586364746094,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.0024,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.4124883711338043,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.1145,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.46736782789230347,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.8806,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.41343656182289124,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.1182,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3253372013568878,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.2312,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.292022168636322,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.918,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3209899067878723,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9837,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.34899088740348816,
      "learning_rate": 0.00019068736141906876,
      "loss": 1.3112,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3487248420715332,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.9571,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3065617084503174,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.9281,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.2781093418598175,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.8696,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.39035555720329285,
      "learning_rate": 0.00018891352549889136,
      "loss": 1.0626,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.29400211572647095,
      "learning_rate": 0.00018847006651884703,
      "loss": 1.1782,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.3062567412853241,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9014,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.3487623929977417,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.9203,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3516588509082794,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.9392,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.31045418977737427,
      "learning_rate": 0.00018669623059866964,
      "loss": 1.0123,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.32259854674339294,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.0941,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.3016436696052551,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.8656,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3304094672203064,
      "learning_rate": 0.0001853658536585366,
      "loss": 1.0784,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.30421414971351624,
      "learning_rate": 0.00018492239467849224,
      "loss": 1.0333,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.34875184297561646,
      "learning_rate": 0.0001844789356984479,
      "loss": 1.0155,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3075156807899475,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.8472,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.33417773246765137,
      "learning_rate": 0.0001835920177383592,
      "loss": 1.132,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.26805588603019714,
      "learning_rate": 0.00018314855875831487,
      "loss": 1.0217,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.3158379793167114,
      "learning_rate": 0.00018270509977827052,
      "loss": 1.1234,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.24774910509586334,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.8902,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.31354963779449463,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.9622,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.26874473690986633,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.9882,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.3208855092525482,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.9669,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.29467493295669556,
      "learning_rate": 0.0001804878048780488,
      "loss": 1.0222,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.2658853232860565,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.7179,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.4095586836338043,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.9298,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3588062524795532,
      "learning_rate": 0.00017915742793791575,
      "loss": 1.2951,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.3221994936466217,
      "learning_rate": 0.0001787139689578714,
      "loss": 1.1634,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.33207544684410095,
      "learning_rate": 0.00017827050997782707,
      "loss": 1.0126,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.3135206401348114,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.8339,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.2858564555644989,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.8908,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.40534305572509766,
      "learning_rate": 0.000176940133037694,
      "loss": 0.9854,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.4386303722858429,
      "learning_rate": 0.00017649667405764967,
      "loss": 1.0455,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.3208898603916168,
      "learning_rate": 0.00017605321507760532,
      "loss": 1.029,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 1.0228146314620972,
      "learning_rate": 0.000175609756097561,
      "loss": 1.018,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3353184461593628,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.9225,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3532666265964508,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.8927,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.351450115442276,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.8763,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3587055802345276,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.9099,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.30922290682792664,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.9751,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.3808385133743286,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.9033,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.3210577368736267,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.9509,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.26781076192855835,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.7911,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3017228841781616,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.9287,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.2805789113044739,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.9327,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.27982276678085327,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.815,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.29375341534614563,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.9923,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3183509409427643,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.7957,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.38404369354248047,
      "learning_rate": 0.00016940133037694015,
      "loss": 1.01,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.3639436960220337,
      "learning_rate": 0.00016895787139689582,
      "loss": 1.0429,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.3531999886035919,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.8894,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.2900453805923462,
      "learning_rate": 0.0001680709534368071,
      "loss": 1.01,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.32503485679626465,
      "learning_rate": 0.00016762749445676275,
      "loss": 1.0691,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.33818212151527405,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.9772,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.3284465968608856,
      "learning_rate": 0.00016674057649667407,
      "loss": 1.1549,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.29464396834373474,
      "learning_rate": 0.00016629711751662974,
      "loss": 1.0735,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.27115604281425476,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.9209,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.4824427664279938,
      "learning_rate": 0.00016541019955654103,
      "loss": 1.0107,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.2313273847103119,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.7762,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.4009738266468048,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.9261,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.31743648648262024,
      "learning_rate": 0.000164079822616408,
      "loss": 1.0042,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.4018518030643463,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.0824,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.31311529874801636,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.8282,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.3358812630176544,
      "learning_rate": 0.00016274944567627495,
      "loss": 1.0986,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.33934324979782104,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.8888,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.29767975211143494,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.8761,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.3453633785247803,
      "learning_rate": 0.0001614190687361419,
      "loss": 1.0768,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.321541428565979,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.9561,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.35036543011665344,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.9255,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.29597529768943787,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.9833,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.40686383843421936,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.9489,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.33007949590682983,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.8745,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.39512237906455994,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.8482,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.3318308889865875,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.9927,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.27740347385406494,
      "learning_rate": 0.00015787139689578714,
      "loss": 1.0758,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.2783048152923584,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.8432,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.3250581920146942,
      "learning_rate": 0.00015698447893569846,
      "loss": 1.0842,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.41406434774398804,
      "learning_rate": 0.0001565410199556541,
      "loss": 1.1273,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.3118138313293457,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.7922,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.30124473571777344,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.9999,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.39211058616638184,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.8776,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.27413809299468994,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.8893,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.34604713320732117,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.8873,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.3172498345375061,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.838,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.36244919896125793,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.9934,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.2877050042152405,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.8643,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.33848118782043457,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.8918,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.3151146173477173,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.8461,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.3527005612850189,
      "learning_rate": 0.0001516629711751663,
      "loss": 1.0163,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.35679927468299866,
      "learning_rate": 0.00015121951219512197,
      "loss": 1.0204,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.30327364802360535,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.8969,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.36506813764572144,
      "learning_rate": 0.0001503325942350333,
      "loss": 1.0288,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.3919162154197693,
      "learning_rate": 0.0001498891352549889,
      "loss": 1.0183,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.3326948583126068,
      "learning_rate": 0.00014944567627494458,
      "loss": 1.0916,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.35894864797592163,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.914,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.2828134596347809,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.8214,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.2736477851867676,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.7242,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.33269619941711426,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.9283,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.3049944043159485,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.9345,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.2589491903781891,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.8777,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.3275723159313202,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.887,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.3315989673137665,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.997,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.39565399289131165,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.9566,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.33553048968315125,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.9301,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.3543066680431366,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.8064,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.30633488297462463,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.7978,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.35713377594947815,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.8389,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.3552398383617401,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.955,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.27409443259239197,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.6737,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.2564390301704407,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.7739,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.44198542833328247,
      "learning_rate": 0.0001419068736141907,
      "loss": 1.0518,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.3410949110984802,
      "learning_rate": 0.00014146341463414634,
      "loss": 1.1424,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.282086044549942,
      "learning_rate": 0.000141019955654102,
      "loss": 0.9633,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.31943991780281067,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.7823,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.37289759516716003,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.9284,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.3795759081840515,
      "learning_rate": 0.00013968957871396897,
      "loss": 1.0047,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.3668331801891327,
      "learning_rate": 0.00013924611973392464,
      "loss": 1.295,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.33693453669548035,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.951,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.32185056805610657,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.9373,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.33747026324272156,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.9877,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.3621857166290283,
      "learning_rate": 0.00013747228381374724,
      "loss": 1.0127,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.4637271463871002,
      "learning_rate": 0.0001370288248337029,
      "loss": 1.0362,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.3329949676990509,
      "learning_rate": 0.00013658536585365856,
      "loss": 1.0029,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.30521491169929504,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.94,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.39264100790023804,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.9168,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.671869695186615,
      "learning_rate": 0.0001352549889135255,
      "loss": 1.1048,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.2927721440792084,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.9166,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.387698769569397,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.8232,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.37951597571372986,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.9917,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.3240644335746765,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.9765,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.34418824315071106,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.9116,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.2417616844177246,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.6363,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.3096141219139099,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.8797,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.29916486144065857,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.7378,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.460305392742157,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.8265,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.3416884243488312,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.9072,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.33094775676727295,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.8692,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.34467509388923645,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.8256,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.3599700629711151,
      "learning_rate": 0.000129490022172949,
      "loss": 0.8399,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.38290295004844666,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.8801,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.3479115068912506,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.8513,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.4579565227031708,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.9113,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.4047691524028778,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.915,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.396960973739624,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.8687,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.4195733070373535,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.9494,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.3728105425834656,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.7637,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.3100377023220062,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.6897,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.32927340269088745,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.9149,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.42513713240623474,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.9242,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.3596545159816742,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.9459,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.34985214471817017,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.803,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.3914942741394043,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.8478,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.34107282757759094,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.8418,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.3705905079841614,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.8819,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.44214513897895813,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.9238,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.3772227168083191,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.9887,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.411452054977417,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.7212,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.5291978716850281,
      "learning_rate": 0.00012106430155210644,
      "loss": 1.148,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.45357951521873474,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.9959,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.36383458971977234,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.9581,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.440993070602417,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.8574,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.33490514755249023,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.8063,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.38672971725463867,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.8699,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.39427709579467773,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.856,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.5170843601226807,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.8792,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.3649735748767853,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.8092,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.44831663370132446,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.9371,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.4926474690437317,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.9969,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.4347097873687744,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.7737,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.46267786622047424,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.949,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.4386684000492096,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.869,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.4944095015525818,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.9093,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.483806312084198,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.8142,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.4529300034046173,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.8476,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.4150141179561615,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.7587,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.41961854696273804,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.838,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.46653783321380615,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.9107,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.4648878574371338,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.8256,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.5138787627220154,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.8924,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.4668973982334137,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.9472,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.44494184851646423,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.8189,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.5250690579414368,
      "learning_rate": 0.00011042128603104213,
      "loss": 1.0464,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.42257294058799744,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.9341,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.41006898880004883,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.8225,
      "step": 210
    }
  ],
  "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": 3.351588710080512e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}