{
  "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": 4.417632102966309,
      "learning_rate": 0.0,
      "loss": 4.6066,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 3.824070453643799,
      "learning_rate": 4e-05,
      "loss": 4.5809,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 4.764647960662842,
      "learning_rate": 8e-05,
      "loss": 4.8428,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 5.026129722595215,
      "learning_rate": 0.00012,
      "loss": 5.3246,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 5.568634033203125,
      "learning_rate": 0.00016,
      "loss": 5.0766,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 7.791904926300049,
      "learning_rate": 0.0002,
      "loss": 4.4789,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 5.971574306488037,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.7773,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 3.3475728034973145,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.6269,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 2.5669748783111572,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.6002,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 2.079508066177368,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.561,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.5781028270721436,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.188,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.8474287390708923,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.1719,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.7965599894523621,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0825,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.67277592420578,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.991,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.7163275480270386,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.1508,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.8085870146751404,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.2109,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.7520304322242737,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.0903,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.680241048336029,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.9543,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.8143166303634644,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.2347,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.7142716646194458,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.0114,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.5970592498779297,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.0567,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.7442165017127991,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.8508,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.6935762763023376,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.089,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.6430759429931641,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.7555,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.610454261302948,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.0817,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.6211035847663879,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9037,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.6100361943244934,
      "learning_rate": 0.00019068736141906876,
      "loss": 1.0705,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.5219504237174988,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.8251,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.5593066811561584,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.0416,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.5467231273651123,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.9379,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.8338480591773987,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.8073,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.6652135848999023,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.959,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.6371573805809021,
      "learning_rate": 0.00018802660753880268,
      "loss": 1.0453,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.5541828274726868,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.8059,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.6239511966705322,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.9681,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.6381208896636963,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.8827,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.5363917946815491,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.989,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.6242470741271973,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.6724,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.531095027923584,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.7495,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.6587176322937012,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.9717,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.5573552250862122,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.9977,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.6289750933647156,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.9671,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.5671831965446472,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.8712,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.603140115737915,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.9699,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.5726262927055359,
      "learning_rate": 0.00018270509977827052,
      "loss": 1.073,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.57386714220047,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.9159,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.5615765452384949,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.0575,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.47419869899749756,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.8356,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.5028887987136841,
      "learning_rate": 0.00018093126385809312,
      "loss": 1.0313,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.5023750066757202,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.8376,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.4543537199497223,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.7145,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.4374978244304657,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.7464,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.47209376096725464,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.9299,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.5425230264663696,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.8528,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.5343915820121765,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.7878,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.5154897570610046,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.8451,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.48188620805740356,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.9204,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.42773884534835815,
      "learning_rate": 0.000176940133037694,
      "loss": 0.7443,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.6305500268936157,
      "learning_rate": 0.00017649667405764967,
      "loss": 1.0036,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.571887731552124,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.8989,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.5789161324501038,
      "learning_rate": 0.000175609756097561,
      "loss": 0.9057,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.5388776063919067,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.9811,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.5069330334663391,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.8072,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.6007671356201172,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.9287,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.5581125020980835,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.9263,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.6751324534416199,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.8119,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.4773782789707184,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.6753,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.6136070489883423,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.8526,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.6497328281402588,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.7758,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.6036306023597717,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.941,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.5378339290618896,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.9566,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.4954136908054352,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.9078,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.5501747727394104,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8474,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.5908843874931335,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.9218,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.4488467574119568,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.8638,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.5528292059898376,
      "learning_rate": 0.00016895787139689582,
      "loss": 1.1412,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.4880754351615906,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.7314,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.5529576539993286,
      "learning_rate": 0.0001680709534368071,
      "loss": 1.0243,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.5193362832069397,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.9398,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.5076447129249573,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.6084,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.5762174129486084,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.9232,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.5628107786178589,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.9185,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.5657719969749451,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.8769,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.676673173904419,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.9929,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.5039803981781006,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.88,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.5343524217605591,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.7667,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.6614826917648315,
      "learning_rate": 0.000164079822616408,
      "loss": 0.7338,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.6496767997741699,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.0196,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.5414061546325684,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.9439,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.5283159017562866,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.6371,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.6610089540481567,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.9329,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.6365460157394409,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.888,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.5431596636772156,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.6909,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.6583664417266846,
      "learning_rate": 0.00016097560975609758,
      "loss": 1.0547,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.7014925479888916,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.9537,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.5222604870796204,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.797,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.5794833898544312,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.7284,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.5662128329277039,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.815,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.5566934943199158,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.7433,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.6824548244476318,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.8538,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.506364643573761,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.8519,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.531067430973053,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.811,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.5699226260185242,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.9107,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.6745486855506897,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.9513,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.5856108665466309,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.87,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.5589944124221802,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.9231,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.5654696226119995,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.9256,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.6465855836868286,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.8539,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.6349661350250244,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.9793,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.5383194088935852,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.8916,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.5718663930892944,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.9586,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.5511415600776672,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.876,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.5277529358863831,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.9305,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.5491341352462769,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.869,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.5900211334228516,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.9411,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.5197898149490356,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.8905,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.511114239692688,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.8522,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.5591258406639099,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.8849,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.49140432476997375,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.8749,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.5272778272628784,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.7527,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.5844745635986328,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.9937,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.5546406507492065,
      "learning_rate": 0.0001485587583148559,
      "loss": 1.0046,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.5028824210166931,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.8752,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.4766760766506195,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.6806,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.5514656901359558,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.896,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.6014825701713562,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.8438,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.5003427863121033,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.894,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.5340179204940796,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.7952,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.5958055257797241,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.8895,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.663881778717041,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.9227,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.7118547558784485,
      "learning_rate": 0.00014456762749445675,
      "loss": 1.2685,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.6181128025054932,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.9934,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.5530040264129639,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.6678,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.5773662328720093,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.7822,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.6204919219017029,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.8531,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.5235987901687622,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.9034,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.5405385494232178,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.8628,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.5767109394073486,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.9248,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.6193376779556274,
      "learning_rate": 0.000141019955654102,
      "loss": 0.9899,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.5930230617523193,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.9528,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.6145725846290588,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.8576,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.5589808821678162,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.6813,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.5464595556259155,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.8162,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.5102654695510864,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.6105,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.6438682675361633,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.8576,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.7712976932525635,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.932,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.6082596778869629,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.9235,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.5627255439758301,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.7996,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.5708767175674438,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.6233,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.5511801838874817,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.7211,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.5675956010818481,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.7203,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.841576099395752,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.7334,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.6041272878646851,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.7238,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.48842668533325195,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.8418,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.5356717705726624,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.6318,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.5651488304138184,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.6607,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.5447269082069397,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.7638,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.5723810195922852,
      "learning_rate": 0.00013259423503325944,
      "loss": 1.0065,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.5228806734085083,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.6397,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.5963119268417358,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.91,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.5306135416030884,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.7778,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.5146408677101135,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.7719,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.5158949494361877,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.7203,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.5516198873519897,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.4801,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.5656818747520447,
      "learning_rate": 0.000129490022172949,
      "loss": 0.6675,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.5386690497398376,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.7166,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.5922750234603882,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.6271,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.5892629623413086,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.614,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.5477419495582581,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.6421,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.6130991578102112,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.6938,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.7019168734550476,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.8087,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.6180416941642761,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.7819,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.6685227751731873,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.7466,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.5855250358581543,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.5945,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.582728385925293,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.8723,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.6902685761451721,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.5879,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.6733485460281372,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.6244,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.6403049826622009,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.7442,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.6300265789031982,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.7412,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.5773813724517822,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.6802,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.64751136302948,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.7256,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.6257942318916321,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.6448,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.6436994075775146,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.8134,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.7222681641578674,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.8496,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.5950624942779541,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.601,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.7700217962265015,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.9038,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.698784351348877,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.6952,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.803534984588623,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.5598,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.810663104057312,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.8977,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.7135093212127686,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.7501,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.9062169790267944,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.7618,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.6200124025344849,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.6832,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.7953326106071472,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.7149,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.7229250073432922,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.6501,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.7693234086036682,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.7875,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 1.03544020652771,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.9469,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.7549523115158081,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.5158,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.6752796173095703,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.6001,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.7703771591186523,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.711,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.7333843111991882,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.7516,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.7859432101249695,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.9336,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.77800053358078,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.8772,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.8271440267562866,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.6986,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.6502723693847656,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.4378,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.8076328635215759,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.6504,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.8068559765815735,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.6608,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.7107000350952148,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.6953,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.7289706468582153,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.6603,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.8543151617050171,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.8272,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.748634934425354,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.681,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.6797105073928833,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.5805,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.9264088869094849,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.6196,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.8796908259391785,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.8333,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.7682700157165527,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.6805,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.7117056250572205,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.5846,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.8295667171478271,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.563,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.7516017556190491,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.6103,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.7708144187927246,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.706,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.7590659260749817,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.756,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.8152827024459839,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.6396,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.8612132668495178,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.614,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.8408886194229126,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.741,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.7959259748458862,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.7306,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.8105316162109375,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.7496,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.7634991407394409,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.4973,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.86619633436203,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.6977,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.9370027780532837,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.9136,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.8094936013221741,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.6651,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.9540297985076904,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.76,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.9854940176010132,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.8393,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.8038029074668884,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.709,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.8540597558021545,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.6907,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.7940883040428162,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.7181,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.799118161201477,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.6442,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.7642391920089722,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.7556,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.7873114347457886,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.7719,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.7426925301551819,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.5357,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.8319903612136841,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.7869,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.868106484413147,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.6447,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.7776063084602356,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.6502,
      "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": 2.504459444178125e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}