{
  "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": 0.84739089012146,
      "learning_rate": 0.0,
      "loss": 2.5294,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.1141237020492554,
      "learning_rate": 4e-05,
      "loss": 2.971,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 0.9252207279205322,
      "learning_rate": 8e-05,
      "loss": 2.6577,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.0669474601745605,
      "learning_rate": 0.00012,
      "loss": 2.7327,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.2827067375183105,
      "learning_rate": 0.00016,
      "loss": 2.4985,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 1.535577654838562,
      "learning_rate": 0.0002,
      "loss": 2.2724,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 1.5054770708084106,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.7826,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.5897902250289917,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.577,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.276290774345398,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.3913,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.9067478775978088,
      "learning_rate": 0.00019822616407982261,
      "loss": 0.9285,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.8181219696998596,
      "learning_rate": 0.00019778270509977829,
      "loss": 0.9723,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.643192708492279,
      "learning_rate": 0.00019733924611973393,
      "loss": 0.7687,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.9791983962059021,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.8786,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.7479966282844543,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.7774,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.6947417259216309,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.6839,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5914806723594666,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.7237,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.42310217022895813,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.6851,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.47218093276023865,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.7273,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.46259188652038574,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.6595,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.5722907185554504,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.7801,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.4656625986099243,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.6497,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.4682161808013916,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.6736,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.39626696705818176,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.5796,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.47387194633483887,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.8255,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3779480755329132,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.644,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3660251498222351,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.5743,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.403241902589798,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.6733,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3720276951789856,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.6863,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.4944595694541931,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.7871,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3705757260322571,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.6641,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.35951438546180725,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.5976,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.4171309471130371,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.7118,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.4173280894756317,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.7252,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.2907676100730896,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.6107,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.37369343638420105,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.5882,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.35333916544914246,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.6614,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.40799376368522644,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.6075,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.3764449954032898,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.5884,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.50343257188797,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.6891,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.38306352496147156,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.5317,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.37110263109207153,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.7071,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.37663453817367554,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.5504,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.3508777916431427,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.519,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.4708102345466614,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.6746,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.3932710289955139,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.5773,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.37868738174438477,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.5822,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.42172908782958984,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.5933,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.35971713066101074,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.6116,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.4047083258628845,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.6457,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.339240700006485,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.5884,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.3325043320655823,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.4338,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.36758092045783997,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.5593,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.2999785244464874,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.5004,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.31713420152664185,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.4877,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.39375901222229004,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.5175,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.42274758219718933,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.6523,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.29750198125839233,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.4427,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.47597289085388184,
      "learning_rate": 0.000176940133037694,
      "loss": 0.6757,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.44186708331108093,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.6083,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.4179357588291168,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.5862,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.4003635048866272,
      "learning_rate": 0.000175609756097561,
      "loss": 0.5315,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3589266538619995,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.5633,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.35732004046440125,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.5134,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.3739253282546997,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.4672,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.353863000869751,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.5416,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3577174246311188,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.4495,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.43537166714668274,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.5697,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.43162912130355835,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.5175,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.3763505220413208,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.4518,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.47527551651000977,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.5243,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3973166346549988,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.6154,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.44812852144241333,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.6121,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.4196566343307495,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.5497,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.4730215072631836,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.5401,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.5152289867401123,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.6667,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.3725070655345917,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.5978,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.4534280598163605,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.4166,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.3526279926300049,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.4398,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.3633706569671631,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.5535,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.3769456446170807,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.5652,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.45618465542793274,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.4789,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.40748119354248047,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.5043,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.4052966833114624,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.4887,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.41316401958465576,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.4591,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.37975427508354187,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.5393,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.5379762053489685,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.7197,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.42292851209640503,
      "learning_rate": 0.000164079822616408,
      "loss": 0.5921,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.45978912711143494,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.5934,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.41444504261016846,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.4214,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.4473384618759155,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.6076,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.32551729679107666,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.6697,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.42840301990509033,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.4924,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.36419162154197693,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.5666,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.38450661301612854,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.6167,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.39747440814971924,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.5399,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.4632483422756195,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.5055,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.423412948846817,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.5487,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.43535298109054565,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.6215,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.496204674243927,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.7787,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.3512228727340698,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.4529,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.43772977590560913,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.6014,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.5691178441047668,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.6481,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.4727238416671753,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.5023,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.4905391335487366,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.5519,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.40309712290763855,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.4542,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.40239062905311584,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.5088,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.562965989112854,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.5095,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.48890256881713867,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.5086,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.4647333025932312,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.476,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.42808303236961365,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.4981,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.4905294179916382,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.4566,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.4641740024089813,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.5761,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.39417940378189087,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.5467,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.4153878688812256,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.4341,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.44727814197540283,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.4887,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.5372669100761414,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.5441,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.3450123965740204,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.5653,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.46070244908332825,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.5678,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.42381054162979126,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.543,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.39341410994529724,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.4895,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.38430294394493103,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.4799,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.4222980737686157,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.5264,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.48887255787849426,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.6112,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.45318329334259033,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.4812,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.32094570994377136,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.4489,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.4471578299999237,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.5269,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.3956528306007385,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.5281,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.3894623816013336,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.5716,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.4060910642147064,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.4315,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.3835338354110718,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.5042,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.4795628786087036,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.5591,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.3402988612651825,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.5218,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.3220534324645996,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.4015,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.41338276863098145,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.6331,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.45399585366249084,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.5927,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.3963128924369812,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.5489,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.3956300616264343,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.5707,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.39705580472946167,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.5019,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.41356807947158813,
      "learning_rate": 0.000141019955654102,
      "loss": 0.6957,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.4428199231624603,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.7367,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.4398159384727478,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.5386,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.49111294746398926,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.4737,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.37492799758911133,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.445,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.4115169942378998,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.4426,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.3737935423851013,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.3545,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.5006787776947021,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.5994,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.46611273288726807,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.5028,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.3841986656188965,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.4176,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.383601576089859,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.4983,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.34659916162490845,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.4067,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.37530845403671265,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.5751,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.7831601500511169,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.7483,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.3889882564544678,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.4935,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.39255622029304504,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.4804,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.3336627781391144,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.3969,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.38084396719932556,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.4958,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.4367420971393585,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.4464,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.4804650843143463,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.4755,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.33974507451057434,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.3565,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.4648623466491699,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.4782,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.39252355694770813,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.4432,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.35544973611831665,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.484,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.4241635799407959,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.3667,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.34874269366264343,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.4507,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.4336688816547394,
      "learning_rate": 0.000129490022172949,
      "loss": 0.3597,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.4772028923034668,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.409,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.4917652904987335,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.3847,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.491860955953598,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.3454,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.5038275718688965,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.4184,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.45596447587013245,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.4056,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.6608575582504272,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.3922,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.40797296166419983,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.4701,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.5078899264335632,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.5479,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.360521137714386,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.4832,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.4067363440990448,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.3985,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.35195401310920715,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.3724,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.4969233274459839,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.4568,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.4823935925960541,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.4006,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.4239618480205536,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.4285,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.5152596235275269,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.4873,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.36399662494659424,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.2889,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.5911298990249634,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.4922,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.5763875842094421,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.4863,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.5428652167320251,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.472,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.5004507899284363,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.443,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.5332474708557129,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.5491,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.43450143933296204,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.4009,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.6134043335914612,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.4698,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.5153659582138062,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.347,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.402942955493927,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.3554,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.4387974143028259,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.4331,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.4739099442958832,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.4111,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.5378749966621399,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.4155,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.5006451606750488,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.3644,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.524803102016449,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.3548,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.5319029092788696,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.3478,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.5924810171127319,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.4756,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.592688798904419,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.362,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.523607075214386,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.4958,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.5575888156890869,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.3407,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.5454251170158386,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.3894,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.6361061930656433,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.447,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.6461852788925171,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.4256,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.6373979449272156,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.3192,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.5404419898986816,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.484,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.539198637008667,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.4868,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.547508716583252,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.4648,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.4799720048904419,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.4327,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.6750230193138123,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.4259,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.5118879675865173,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.4174,
      "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": 8.955983548689408e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}