{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5802197802197804,
  "eval_steps": 500,
  "global_step": 240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.5843391418457031,
      "learning_rate": 0.0,
      "loss": 2.8156,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.8521391153335571,
      "learning_rate": 4e-05,
      "loss": 2.8825,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.772310495376587,
      "learning_rate": 8e-05,
      "loss": 3.0455,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.5936847925186157,
      "learning_rate": 0.00012,
      "loss": 2.3228,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.7163457870483398,
      "learning_rate": 0.00016,
      "loss": 2.4105,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 1.8210536241531372,
      "learning_rate": 0.0002,
      "loss": 1.9757,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.4785475730895996,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.9602,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.8151148557662964,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.5283,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.8721301555633545,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.1164,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.8999813199043274,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.3153,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.8793871998786926,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.5728,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.7212244868278503,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.4584,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5409421324729919,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.2519,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.44038522243499756,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.4694,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.35416823625564575,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.9877,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.4410957992076874,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.2377,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.39518073201179504,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.1182,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.4025755524635315,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.1645,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.3367070257663727,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.8772,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.3709753751754761,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.2793,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.40532636642456055,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.9308,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3041611313819885,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.1534,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.38191983103752136,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.9038,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.377227246761322,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.1424,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3673517107963562,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.2671,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.31700432300567627,
      "learning_rate": 0.00019113082039911309,
      "loss": 1.1441,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.3470500409603119,
      "learning_rate": 0.00019068736141906876,
      "loss": 1.1671,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.27670592069625854,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.14,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3592919409275055,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.3351,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.38518282771110535,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.2833,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.3708607852458954,
      "learning_rate": 0.00018891352549889136,
      "loss": 1.0154,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3055068850517273,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.9309,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.2933763563632965,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9721,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.34914690256118774,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.1341,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.31120434403419495,
      "learning_rate": 0.00018713968957871397,
      "loss": 1.1207,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.30122801661491394,
      "learning_rate": 0.00018669623059866964,
      "loss": 1.3361,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3731483519077301,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.0789,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.30212077498435974,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.3128,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3174402415752411,
      "learning_rate": 0.0001853658536585366,
      "loss": 1.0298,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.27389031648635864,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.7857,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.358776718378067,
      "learning_rate": 0.0001844789356984479,
      "loss": 1.0977,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.341391921043396,
      "learning_rate": 0.00018403547671840356,
      "loss": 1.1621,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.385212242603302,
      "learning_rate": 0.0001835920177383592,
      "loss": 1.1445,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.24659432470798492,
      "learning_rate": 0.00018314855875831487,
      "loss": 1.1188,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.2595515847206116,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.8302,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.3767276108264923,
      "learning_rate": 0.00018226164079822616,
      "loss": 1.6553,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.28310975432395935,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.1345,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.35903477668762207,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.7517,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.342821329832077,
      "learning_rate": 0.00018093126385809312,
      "loss": 1.0464,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.2808687090873718,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.9247,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.33112433552742004,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.0519,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.29903167486190796,
      "learning_rate": 0.00017960088691796008,
      "loss": 1.0643,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3124869465827942,
      "learning_rate": 0.00017915742793791575,
      "loss": 1.2023,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2661173939704895,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.8074,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3182145953178406,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.9457,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.3288654088973999,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.1957,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.2978874742984772,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.9535,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.3069325387477875,
      "learning_rate": 0.000176940133037694,
      "loss": 1.0443,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.31956231594085693,
      "learning_rate": 0.00017649667405764967,
      "loss": 1.2383,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.2928081154823303,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.9903,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.2808949947357178,
      "learning_rate": 0.000175609756097561,
      "loss": 1.0634,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3161472976207733,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.9278,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3816571533679962,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.9225,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.2767592966556549,
      "learning_rate": 0.00017427937915742792,
      "loss": 1.1057,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.323319673538208,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.9706,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.35678160190582275,
      "learning_rate": 0.00017339246119733924,
      "loss": 1.2009,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.311489462852478,
      "learning_rate": 0.0001729490022172949,
      "loss": 1.0323,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.3634609580039978,
      "learning_rate": 0.00017250554323725056,
      "loss": 1.0794,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.29051142930984497,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.9095,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.2702578604221344,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.9749,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.2855437695980072,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.8197,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.297456294298172,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.9567,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.24237467348575592,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8005,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.328037291765213,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.9423,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.2795104384422302,
      "learning_rate": 0.00016940133037694015,
      "loss": 1.0958,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.26989641785621643,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.8853,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.3442732095718384,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.8165,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.28731393814086914,
      "learning_rate": 0.0001680709534368071,
      "loss": 1.0472,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.29334571957588196,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.9369,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.3078097403049469,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.912,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.33694934844970703,
      "learning_rate": 0.00016674057649667407,
      "loss": 1.1832,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.27495941519737244,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.9264,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.3295109272003174,
      "learning_rate": 0.00016585365853658536,
      "loss": 1.1884,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.30429670214653015,
      "learning_rate": 0.00016541019955654103,
      "loss": 1.2774,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.28503450751304626,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.8402,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.38091132044792175,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.9921,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.33023545145988464,
      "learning_rate": 0.000164079822616408,
      "loss": 1.168,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.28644034266471863,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.048,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.2850220501422882,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.8613,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.27724236249923706,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.9522,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.28526735305786133,
      "learning_rate": 0.0001623059866962306,
      "loss": 1.0575,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.3300544321537018,
      "learning_rate": 0.00016186252771618626,
      "loss": 1.1596,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.3302018642425537,
      "learning_rate": 0.0001614190687361419,
      "loss": 1.1164,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.34805142879486084,
      "learning_rate": 0.00016097560975609758,
      "loss": 1.1106,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.36664891242980957,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.9729,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.29839083552360535,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.86,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.40213289856910706,
      "learning_rate": 0.00015964523281596454,
      "loss": 1.1324,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.2544693648815155,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.9688,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.2986075282096863,
      "learning_rate": 0.00015875831485587586,
      "loss": 1.1061,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.37222951650619507,
      "learning_rate": 0.0001583148558758315,
      "loss": 1.1107,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.2792779505252838,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.992,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.2820577621459961,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.8408,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.31690841913223267,
      "learning_rate": 0.00015698447893569846,
      "loss": 1.2549,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.2861771285533905,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.9154,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.26935121417045593,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.8391,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.35693269968032837,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.8458,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.28164708614349365,
      "learning_rate": 0.00015521064301552106,
      "loss": 1.0945,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.3093002438545227,
      "learning_rate": 0.0001547671840354767,
      "loss": 1.0787,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.3896459639072418,
      "learning_rate": 0.00015432372505543238,
      "loss": 1.0757,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.34897807240486145,
      "learning_rate": 0.00015388026607538802,
      "loss": 1.0409,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.36673831939697266,
      "learning_rate": 0.0001534368070953437,
      "loss": 1.0385,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.4313843548297882,
      "learning_rate": 0.00015299334811529934,
      "loss": 1.0996,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.29618099331855774,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.9261,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.31989842653274536,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.9106,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.3386354446411133,
      "learning_rate": 0.0001516629711751663,
      "loss": 1.2015,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.3514902591705322,
      "learning_rate": 0.00015121951219512197,
      "loss": 1.3507,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.27930814027786255,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.9667,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.3235801160335541,
      "learning_rate": 0.0001503325942350333,
      "loss": 1.1243,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.2760171890258789,
      "learning_rate": 0.0001498891352549889,
      "loss": 1.063,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.2974321246147156,
      "learning_rate": 0.00014944567627494458,
      "loss": 1.0874,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.3042125403881073,
      "learning_rate": 0.00014900221729490022,
      "loss": 1.0485,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.2973671555519104,
      "learning_rate": 0.0001485587583148559,
      "loss": 1.0581,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.4362548887729645,
      "learning_rate": 0.00014811529933481154,
      "loss": 1.0736,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.31430351734161377,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.9575,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.31971320509910583,
      "learning_rate": 0.00014722838137472282,
      "loss": 1.06,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.28114503622055054,
      "learning_rate": 0.0001467849223946785,
      "loss": 1.2639,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.2903381586074829,
      "learning_rate": 0.00014634146341463414,
      "loss": 1.0742,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.3863905966281891,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.9379,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.30715394020080566,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.8741,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.3623356223106384,
      "learning_rate": 0.00014501108647450113,
      "loss": 1.0023,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.3077038824558258,
      "learning_rate": 0.00014456762749445675,
      "loss": 1.1705,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.2857320308685303,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.989,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.4221183657646179,
      "learning_rate": 0.00014368070953436806,
      "loss": 1.1737,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.26992401480674744,
      "learning_rate": 0.00014323725055432373,
      "loss": 1.1065,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.2924363315105438,
      "learning_rate": 0.00014279379157427938,
      "loss": 1.1701,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.29272526502609253,
      "learning_rate": 0.00014235033259423505,
      "loss": 1.0431,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.35805362462997437,
      "learning_rate": 0.0001419068736141907,
      "loss": 1.0048,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.3064621388912201,
      "learning_rate": 0.00014146341463414634,
      "loss": 1.0563,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.2745743989944458,
      "learning_rate": 0.000141019955654102,
      "loss": 0.8093,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.2574104368686676,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.8897,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.3551047742366791,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.9551,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.31768593192100525,
      "learning_rate": 0.00013968957871396897,
      "loss": 1.0787,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.3659076392650604,
      "learning_rate": 0.00013924611973392464,
      "loss": 1.0164,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.33559244871139526,
      "learning_rate": 0.00013880266075388026,
      "loss": 1.0276,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.3228370249271393,
      "learning_rate": 0.00013835920177383593,
      "loss": 1.2313,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.2789573073387146,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.8152,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.324306845664978,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.9888,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.307303249835968,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.9933,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.29327502846717834,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.9589,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.33833250403404236,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.9858,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.2873021364212036,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.9503,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.38166123628616333,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.9859,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.3040919005870819,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.9403,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.3346724212169647,
      "learning_rate": 0.0001343680709534368,
      "loss": 1.3198,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.2888737916946411,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.9449,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.24763283133506775,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.845,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.35276684165000916,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.8571,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.3068442642688751,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.9584,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.2783297896385193,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.8542,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.30835285782814026,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.8036,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.32938769459724426,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.701,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.42673012614250183,
      "learning_rate": 0.00013082039911308205,
      "loss": 1.1817,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.37019211053848267,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.9628,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.3247932493686676,
      "learning_rate": 0.00012993348115299336,
      "loss": 1.1035,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.31072118878364563,
      "learning_rate": 0.000129490022172949,
      "loss": 1.0836,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.3443380892276764,
      "learning_rate": 0.00012904656319290468,
      "loss": 1.0268,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.39338764548301697,
      "learning_rate": 0.00012860310421286032,
      "loss": 1.2012,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.3188355267047882,
      "learning_rate": 0.00012815964523281597,
      "loss": 1.073,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.390495628118515,
      "learning_rate": 0.0001277161862527716,
      "loss": 1.0057,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.38059771060943604,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.8281,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.3839198648929596,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.9558,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.3393332064151764,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.9078,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.34839192032814026,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.876,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.36449167132377625,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.8704,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.40781110525131226,
      "learning_rate": 0.00012505543237250553,
      "loss": 1.0215,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.3179631233215332,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.7361,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.44013991951942444,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.9469,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.3477267920970917,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.995,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.3559893071651459,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.9047,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.47691860795021057,
      "learning_rate": 0.0001228381374722838,
      "loss": 1.0441,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.31850194931030273,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.8703,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.45557940006256104,
      "learning_rate": 0.00012195121951219512,
      "loss": 1.1753,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.3637930750846863,
      "learning_rate": 0.00012150776053215078,
      "loss": 1.151,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.43823617696762085,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.8979,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.3514891266822815,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.9443,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.3895740211009979,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.972,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.3714885115623474,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.8454,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.47325366735458374,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.8913,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.37345072627067566,
      "learning_rate": 0.00011884700665188471,
      "loss": 1.1981,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.4246751666069031,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.8321,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.49544385075569153,
      "learning_rate": 0.00011796008869179602,
      "loss": 1.0758,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.5096224546432495,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.81,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.4344899654388428,
      "learning_rate": 0.00011707317073170732,
      "loss": 1.0509,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.43887391686439514,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.9858,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.47227200865745544,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.9425,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.44675981998443604,
      "learning_rate": 0.00011574279379157429,
      "loss": 1.0873,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.3999116122722626,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.9234,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.4873921871185303,
      "learning_rate": 0.00011485587583148558,
      "loss": 1.3982,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.5263328552246094,
      "learning_rate": 0.00011441241685144124,
      "loss": 1.1196,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.41891786456108093,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.9244,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.3824903666973114,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.8249,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.3771800100803375,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.7892,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.45261913537979126,
      "learning_rate": 0.00011263858093126387,
      "loss": 1.0867,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.421709805727005,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.8096,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.5280342698097229,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.7606,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.38911956548690796,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.7891,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.47260016202926636,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.9646,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.479998916387558,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.7267,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.476073682308197,
      "learning_rate": 0.00010997782705099779,
      "loss": 1.0749,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.45205914974212646,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.9639,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.44608914852142334,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.9021,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.46160390973091125,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.9141,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.4132397174835205,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.9648,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.4495893716812134,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.9116,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.4337720572948456,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.694,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.5669428110122681,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.8486,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.41822999715805054,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.8772,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.49358034133911133,
      "learning_rate": 0.00010598669623059867,
      "loss": 1.2407,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.5223171710968018,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.8801,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.4524052143096924,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.7871,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.4000990092754364,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.8886,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.5052671432495117,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.8672,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.4210032820701599,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.8045,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.4130396246910095,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.7502,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.4363018274307251,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.7552,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.568086564540863,
      "learning_rate": 0.0001024390243902439,
      "loss": 1.1268,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.43064337968826294,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.855,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.46825194358825684,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.9004,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.42373931407928467,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.9398,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.5816337466239929,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.9807,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.5260667204856873,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.9639,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.3763827085494995,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.7729,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.4962773323059082,
      "learning_rate": 9.933481152993348e-05,
      "loss": 1.0272,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.5261977314949036,
      "learning_rate": 9.889135254988914e-05,
      "loss": 1.0381,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.5453608632087708,
      "learning_rate": 9.84478935698448e-05,
      "loss": 1.0068,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.5260674953460693,
      "learning_rate": 9.800443458980046e-05,
      "loss": 1.24,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.4607008397579193,
      "learning_rate": 9.75609756097561e-05,
      "loss": 1.136,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.48102492094039917,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.9013,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.55854731798172,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.9384,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.4186471402645111,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.804,
      "step": 240
    }
  ],
  "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": 4.23792275779584e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}