{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.2835164835164834,
  "eval_steps": 500,
  "global_step": 195,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.4188497066497803,
      "learning_rate": 0.0,
      "loss": 2.4874,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.6966615915298462,
      "learning_rate": 4e-05,
      "loss": 2.6618,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.8571358919143677,
      "learning_rate": 8e-05,
      "loss": 2.8953,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.701550841331482,
      "learning_rate": 0.00012,
      "loss": 2.5134,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.3071422576904297,
      "learning_rate": 0.00016,
      "loss": 2.8063,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.2974326610565186,
      "learning_rate": 0.0002,
      "loss": 2.1778,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 3.3090689182281494,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.1984,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.5245072841644287,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.5319,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.8647416234016418,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.6248,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.0439573526382446,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.1487,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.1243475675582886,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.0713,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.6728630661964417,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.2753,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.4465005397796631,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0032,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.6374929547309875,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.9887,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5495445132255554,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.2954,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5156247019767761,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.1906,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.4463346004486084,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.9256,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.4280051290988922,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.1569,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.43795275688171387,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.9857,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.3561479449272156,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.2937,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.4115261137485504,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.0066,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3871329128742218,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.1393,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.33028116822242737,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.1698,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.2790043354034424,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.8708,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3371724486351013,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.8378,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.34898409247398376,
      "learning_rate": 0.00019113082039911309,
      "loss": 1.1172,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.33062544465065,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9484,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3693927824497223,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.0166,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3819218575954437,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.0723,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.36232468485832214,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.0513,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.40888673067092896,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.9645,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3149604797363281,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.9656,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.32306352257728577,
      "learning_rate": 0.00018802660753880268,
      "loss": 1.169,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.3461757004261017,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.0468,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.2818543612957001,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.8387,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.32426363229751587,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.9198,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.26946142315864563,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.898,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.26598164439201355,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.9514,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3692566156387329,
      "learning_rate": 0.0001853658536585366,
      "loss": 1.1016,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.311518132686615,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.9413,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.4243979752063751,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.9654,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3635575473308563,
      "learning_rate": 0.00018403547671840356,
      "loss": 1.0372,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.30182573199272156,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.8261,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.31842130422592163,
      "learning_rate": 0.00018314855875831487,
      "loss": 1.0436,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.3591977059841156,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.9513,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.24449662864208221,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.9533,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.30334410071372986,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.9391,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.2679116129875183,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.9557,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.30669721961021423,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.9968,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.28827592730522156,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.9107,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.29647353291511536,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.7813,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.2701469659805298,
      "learning_rate": 0.00017960088691796008,
      "loss": 1.0117,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.32161539793014526,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.9802,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2998199462890625,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.9743,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.2879527509212494,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.9694,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.2754303812980652,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.8067,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.26895761489868164,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.738,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.3064604699611664,
      "learning_rate": 0.000176940133037694,
      "loss": 1.1298,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.28680023550987244,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.8178,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.32110995054244995,
      "learning_rate": 0.00017605321507760532,
      "loss": 1.1707,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.2549216151237488,
      "learning_rate": 0.000175609756097561,
      "loss": 0.8178,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.37096455693244934,
      "learning_rate": 0.00017516629711751663,
      "loss": 1.0422,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.29533639550209045,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.8687,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.24831083416938782,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.7759,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.38010746240615845,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.8096,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3136991560459137,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.9047,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.3377384543418884,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.9734,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.3258354663848877,
      "learning_rate": 0.00017250554323725056,
      "loss": 1.1381,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.3756682574748993,
      "learning_rate": 0.00017206208425720623,
      "loss": 1.142,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.297951877117157,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.9006,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.2713771462440491,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.6848,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.24453136324882507,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.9149,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.3121640682220459,
      "learning_rate": 0.00017028824833702883,
      "loss": 1.0345,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.32448261976242065,
      "learning_rate": 0.0001698447893569845,
      "loss": 1.0006,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.3626672923564911,
      "learning_rate": 0.00016940133037694015,
      "loss": 1.1085,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.27186319231987,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.8483,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.2213844507932663,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.8223,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.2720603048801422,
      "learning_rate": 0.0001680709534368071,
      "loss": 1.0244,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.2589336335659027,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.9877,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.3112776577472687,
      "learning_rate": 0.00016718403547671842,
      "loss": 1.161,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.34570449590682983,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.998,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.28220993280410767,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.8724,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.27869945764541626,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.8547,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.2822398841381073,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.7578,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.31407874822616577,
      "learning_rate": 0.00016496674057649667,
      "loss": 1.0796,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.30678629875183105,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.775,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.27964624762535095,
      "learning_rate": 0.000164079822616408,
      "loss": 0.8569,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.33941248059272766,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.991,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.2756584584712982,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.9051,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.3098355531692505,
      "learning_rate": 0.00016274944567627495,
      "loss": 1.0437,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.28124678134918213,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.9356,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.5097110867500305,
      "learning_rate": 0.00016186252771618626,
      "loss": 1.1216,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.343028724193573,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.6632,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.33653372526168823,
      "learning_rate": 0.00016097560975609758,
      "loss": 1.0992,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.299843430519104,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.8637,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.36192506551742554,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.8398,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.2896318733692169,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.9076,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.3109341561794281,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.9252,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.2562720775604248,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.8724,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.3914013206958771,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.9987,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.317617267370224,
      "learning_rate": 0.00015787139689578714,
      "loss": 1.017,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.3310759961605072,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.8552,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.2968403398990631,
      "learning_rate": 0.00015698447893569846,
      "loss": 1.1474,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.2752165198326111,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.6691,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.40840086340904236,
      "learning_rate": 0.00015609756097560978,
      "loss": 1.0522,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.28805288672447205,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.9381,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.358764111995697,
      "learning_rate": 0.00015521064301552106,
      "loss": 1.0337,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.293722927570343,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.8568,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.319948673248291,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.9235,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.26046696305274963,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.8753,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.36574044823646545,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.9953,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.3562886118888855,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.8283,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.3408907651901245,
      "learning_rate": 0.00015254988913525498,
      "loss": 1.006,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.236922949552536,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.6945,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.3720478117465973,
      "learning_rate": 0.0001516629711751663,
      "loss": 1.0167,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.3175780475139618,
      "learning_rate": 0.00015121951219512197,
      "loss": 1.0183,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.3172849416732788,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.927,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.3909221589565277,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.9408,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.4135044813156128,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.9369,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.2699657082557678,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.9792,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.4099826514720917,
      "learning_rate": 0.00014900221729490022,
      "loss": 1.0243,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.28967276215553284,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.8743,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.32177120447158813,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.9133,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.37054261565208435,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.952,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.34513619542121887,
      "learning_rate": 0.00014722838137472282,
      "loss": 1.0085,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.29551732540130615,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.8977,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.4093962013721466,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.9383,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.2644466459751129,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.843,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.3149050772190094,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.8665,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.3474298417568207,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.8853,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.3462107181549072,
      "learning_rate": 0.00014456762749445675,
      "loss": 1.0915,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.30180296301841736,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.8373,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.4664198160171509,
      "learning_rate": 0.00014368070953436806,
      "loss": 1.0105,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.32542654871940613,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.9814,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.30870160460472107,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.8312,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.3272714912891388,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.9501,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.3464250862598419,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.8797,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.28544020652770996,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.9209,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.37120968103408813,
      "learning_rate": 0.000141019955654102,
      "loss": 0.8606,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.36657431721687317,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.9432,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.3297801613807678,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.9244,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.4274684190750122,
      "learning_rate": 0.00013968957871396897,
      "loss": 1.0372,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.32689639925956726,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.8632,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.30232951045036316,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.85,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.31909507513046265,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.9114,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.2917619049549103,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.841,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.4549616575241089,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.8867,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.2622043192386627,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.7721,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.35712870955467224,
      "learning_rate": 0.00013658536585365856,
      "loss": 1.0232,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.28602007031440735,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.7084,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.3272465765476227,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.7709,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.42405179142951965,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.8953,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.33868545293807983,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.7551,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.24465341866016388,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.7176,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.3249797821044922,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.9171,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.3447222411632538,
      "learning_rate": 0.00013348115299334812,
      "loss": 1.0605,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.31464534997940063,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.8846,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.3179872930049896,
      "learning_rate": 0.00013259423503325944,
      "loss": 1.0206,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.282023161649704,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.771,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.4420493245124817,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.7757,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.34315261244773865,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.7939,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.35199642181396484,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.9921,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.32300400733947754,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.9032,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.37724098563194275,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.8255,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.35990023612976074,
      "learning_rate": 0.000129490022172949,
      "loss": 0.8228,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.3496895730495453,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.7755,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.330461323261261,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.7604,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.2884053587913513,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.7073,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.38278475403785706,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.8768,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.414743036031723,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.6892,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.3273482918739319,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.8501,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.3307011127471924,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.7632,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.34743618965148926,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.7053,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.36164161562919617,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.9086,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.360045462846756,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.9171,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.3618490695953369,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.7441,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.44415420293807983,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.7584,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.33986684679985046,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.7676,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.46253499388694763,
      "learning_rate": 0.00012328159645232816,
      "loss": 1.0549,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.3851480782032013,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.7829,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.3774937391281128,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.8041,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.3441581130027771,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.7361,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.348701149225235,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.9374,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.3302812874317169,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.784,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.3508409261703491,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.8263,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.38347405195236206,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.9951,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.45356741547584534,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.8438,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.38501477241516113,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.7814,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.377353310585022,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.8967,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.4473981559276581,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.9326,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.5064100623130798,
      "learning_rate": 0.00011796008869179602,
      "loss": 1.0365,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.33430564403533936,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.7788,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.4263209104537964,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.7154,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.45719534158706665,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.7693,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.39407414197921753,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.7418,
      "step": 195
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.18013683572736e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}