{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.876923076923077,
  "eval_steps": 500,
  "global_step": 285,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 0.8822625875473022,
      "learning_rate": 0.0,
      "loss": 2.9966,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.1069581508636475,
      "learning_rate": 4e-05,
      "loss": 2.9598,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 0.8758227229118347,
      "learning_rate": 8e-05,
      "loss": 2.5775,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.0401133298873901,
      "learning_rate": 0.00012,
      "loss": 2.6196,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.4041666984558105,
      "learning_rate": 0.00016,
      "loss": 3.1798,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 1.4210084676742554,
      "learning_rate": 0.0002,
      "loss": 2.0834,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.1845953464508057,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.3524,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.3485188484191895,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.616,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.0533819198608398,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2391,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.1041414737701416,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.0831,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.7204957604408264,
      "learning_rate": 0.00019778270509977829,
      "loss": 0.8896,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.7176511287689209,
      "learning_rate": 0.00019733924611973393,
      "loss": 0.8995,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.7679543495178223,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.7737,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.8583915829658508,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.8345,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5992399454116821,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.7105,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5483726859092712,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.7893,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.47341662645339966,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.8783,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.4923449456691742,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.5529,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.382350355386734,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.6698,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.43962135910987854,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.6906,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.6100013256072998,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.7102,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.4505807161331177,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.5965,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.420966774225235,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.8076,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.37792259454727173,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.4851,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.39667177200317383,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.7452,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.35318464040756226,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.7378,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.34349656105041504,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.6639,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.37496012449264526,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.5393,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.42517000436782837,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.6226,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.365597128868103,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.5503,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.4194570481777191,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.6564,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.400821328163147,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.7257,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.4243015646934509,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.5831,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.4274579584598541,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.6801,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.30914393067359924,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.4985,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.36418190598487854,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.506,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.5366491079330444,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.6998,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.40732792019844055,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.6035,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.41157761216163635,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.5741,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.49116623401641846,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.5644,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.43378788232803345,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.5459,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.43929198384284973,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.4644,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.40316739678382874,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.6401,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.41275328397750854,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.601,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.2872825264930725,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.4375,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.4530083239078522,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.7684,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.31746530532836914,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.5948,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.35115814208984375,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.6928,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.29176679253578186,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.5716,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.356320858001709,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.5595,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.33391836285591125,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.5823,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.35161083936691284,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.5482,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.31787368655204773,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.5471,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2908938527107239,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.5348,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.34024009108543396,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.4426,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.40695953369140625,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.5771,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.49275121092796326,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.544,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.4099092483520508,
      "learning_rate": 0.000176940133037694,
      "loss": 0.5028,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.31285232305526733,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.5137,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.414304256439209,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.4803,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.4016311466693878,
      "learning_rate": 0.000175609756097561,
      "loss": 0.5934,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.30074217915534973,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.461,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3320770859718323,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.5756,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.37848159670829773,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.6247,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3719041347503662,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.5425,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3609648644924164,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.484,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.32436180114746094,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.5081,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.33831897377967834,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.5861,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.26558148860931396,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.6159,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.32884278893470764,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.5497,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.34436213970184326,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.4994,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.3457243740558624,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.6952,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.310139536857605,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.5439,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.417996346950531,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.5534,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.35336464643478394,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.4557,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.3493141233921051,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.5587,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.38658949732780457,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.64,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.4228934049606323,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.7367,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.38229817152023315,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.5983,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.3111512362957001,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.601,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.3454195261001587,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.4988,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.3082880675792694,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.3354,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.3996518552303314,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.5782,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3453790843486786,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.604,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.3558626174926758,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.4868,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.3380248248577118,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.6232,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.3425062298774719,
      "learning_rate": 0.000164079822616408,
      "loss": 0.6562,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.31318148970603943,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.4692,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3718196153640747,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.7078,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.34966057538986206,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.5526,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.3773850202560425,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.6103,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.36322781443595886,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.5904,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.314194917678833,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.3933,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.4864939749240875,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.608,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.3643064498901367,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.5463,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.3837382197380066,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.6186,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.3626998960971832,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.5897,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.33142223954200745,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.717,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.45660701394081116,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.6902,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.3394142687320709,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.5096,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.34123778343200684,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.4695,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.30545035004615784,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.4207,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.4257568418979645,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.6606,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.39079609513282776,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.5924,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.33211061358451843,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.7863,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.35392093658447266,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.4304,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.32990017533302307,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.4925,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.3811289966106415,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.5385,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.3849605917930603,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.5486,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.33083489537239075,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.4275,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.303181916475296,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.462,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.2988913357257843,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.578,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.36678484082221985,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.6845,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.31926098465919495,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.4582,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.4101877510547638,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.5467,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.26495423913002014,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.5074,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.40077540278434753,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.5351,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.31428056955337524,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.5487,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.43033796548843384,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.5189,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.3554536998271942,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.6639,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.3810238838195801,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.4163,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.34163999557495117,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.4729,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.27072814106941223,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.5592,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.30819904804229736,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.6138,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.29901814460754395,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.5564,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.3798276484012604,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.5403,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.3513716459274292,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.4525,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.2955039441585541,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.3668,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.35771843791007996,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.4494,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.33378154039382935,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.5776,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.37778571248054504,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.5963,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.32039493322372437,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.5944,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.40721142292022705,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.6099,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.4036446511745453,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.5242,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.351977676153183,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.4968,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.38045594096183777,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.5281,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.38101157546043396,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.5149,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.3019929826259613,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.5552,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.3302483856678009,
      "learning_rate": 0.000141019955654102,
      "loss": 0.6418,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.4234539866447449,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.5229,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.2972713112831116,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.5551,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.27675893902778625,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.5109,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.2889951169490814,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.3672,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.2961999773979187,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.4137,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.3546917140483856,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.5216,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.37595945596694946,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.5289,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.3186666667461395,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.654,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.3383956253528595,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.5238,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.3210618495941162,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.5327,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.34825605154037476,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.4882,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.412462443113327,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.6217,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6325540542602539,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.5399,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.3650630712509155,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.4957,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.2766192853450775,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.6144,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.3141804039478302,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.4483,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.3264051079750061,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.5896,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.28167369961738586,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.5106,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.3362073600292206,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.4182,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.35224464535713196,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.4604,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.4684576988220215,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.6034,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.35625913739204407,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.4058,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.33301690220832825,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.4188,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.3223712742328644,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.2773,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.4068375825881958,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.4553,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.5154572129249573,
      "learning_rate": 0.000129490022172949,
      "loss": 0.5075,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.33299142122268677,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.4019,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.3969050347805023,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.4525,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.44202563166618347,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.4411,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.4070901870727539,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.4049,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.38326776027679443,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.4305,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.43944215774536133,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.4957,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.49736371636390686,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.5455,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.35538333654403687,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.3539,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.29923737049102783,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.4417,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.3308171331882477,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.4626,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.38174349069595337,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.4807,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.34894776344299316,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.4429,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.3939150273799896,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.4309,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.48942357301712036,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.4328,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.5319377183914185,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.4294,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.3328636586666107,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.3631,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.35425251722335815,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.404,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.3792189657688141,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.4512,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.416687548160553,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.4504,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.4108631908893585,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.4336,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.41201335191726685,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.4119,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.3686502277851105,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.3951,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.47153526544570923,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.455,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.4673938453197479,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.4357,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.40298277139663696,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.4293,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.43564698100090027,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.434,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.44750574231147766,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.3933,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.5415198802947998,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.4578,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.4987425208091736,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.4109,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.579964280128479,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.396,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.6114839911460876,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.44,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.4714261591434479,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.4098,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.49813345074653625,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.5045,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.4932178258895874,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.4602,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.4815492331981659,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.4181,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.4283634424209595,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.5605,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.46324557065963745,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.3578,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.42129576206207275,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.3835,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.4637790024280548,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.4301,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.5327193140983582,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.4513,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.4558172821998596,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.4109,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.4329102635383606,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.3697,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.4930408000946045,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.4739,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.5058344602584839,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.541,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.42406877875328064,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.3786,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.48256126046180725,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.4806,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.529173731803894,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.5057,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.4997231960296631,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.3187,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.4941723644733429,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.4603,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.4805285632610321,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.3938,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.5577730536460876,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.368,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.5277256369590759,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.3752,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.496021032333374,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.3712,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.5099887847900391,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.4704,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.5312814116477966,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.348,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.4135531187057495,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.306,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.5146408081054688,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.3516,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.48959842324256897,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.3406,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.545744776725769,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.4795,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.5879824161529541,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.5289,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.6025318503379822,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.4185,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.46608248353004456,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.5053,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.5988180041313171,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.4033,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.4750719368457794,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.4748,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.49902719259262085,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.5969,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.5788288712501526,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.4318,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.5285109281539917,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.4796,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.4660860300064087,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.4147,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.5929581522941589,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.4935,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.5364082455635071,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.3583,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.6131191849708557,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.369,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.503869354724884,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.3881,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.5946326851844788,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.4273,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.5515992641448975,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.4354,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.538718044757843,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.4558,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.44571653008461,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.3915,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.5191220045089722,
      "learning_rate": 9.534368070953438e-05,
      "loss": 0.3591,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.5218830704689026,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.4483,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.5036188960075378,
      "learning_rate": 9.445676274944568e-05,
      "loss": 0.6159,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.49172458052635193,
      "learning_rate": 9.401330376940134e-05,
      "loss": 0.425,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.4049654006958008,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.501,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.48181113600730896,
      "learning_rate": 9.312638580931264e-05,
      "loss": 0.4471,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.5784696340560913,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.4712,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.5212926268577576,
      "learning_rate": 9.223946784922394e-05,
      "loss": 0.4304,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.5462768077850342,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.4135,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.41660547256469727,
      "learning_rate": 9.135254988913526e-05,
      "loss": 0.3191,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.5723269581794739,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.4253,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.4400235414505005,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.4311,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.5459662079811096,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.6107,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.719912588596344,
      "learning_rate": 8.957871396895788e-05,
      "loss": 0.4939,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.4602455496788025,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.4916,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.5616287589073181,
      "learning_rate": 8.869179600886919e-05,
      "loss": 0.4083,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.4645906984806061,
      "learning_rate": 8.824833702882484e-05,
      "loss": 0.3071,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.5330123901367188,
      "learning_rate": 8.78048780487805e-05,
      "loss": 0.3892,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.5268498063087463,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.61,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.4113461673259735,
      "learning_rate": 8.69179600886918e-05,
      "loss": 0.4738,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.5210222005844116,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.6632,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.6917738914489746,
      "learning_rate": 8.603104212860311e-05,
      "loss": 0.521,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.7001894116401672,
      "learning_rate": 8.558758314855876e-05,
      "loss": 0.4697,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.5656400918960571,
      "learning_rate": 8.514412416851442e-05,
      "loss": 0.3555,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.5176607370376587,
      "learning_rate": 8.470066518847007e-05,
      "loss": 0.419,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.6026767492294312,
      "learning_rate": 8.425720620842572e-05,
      "loss": 0.5455,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.6642753481864929,
      "learning_rate": 8.381374722838138e-05,
      "loss": 0.4938,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.46746525168418884,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.3544,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.47409144043922424,
      "learning_rate": 8.292682926829268e-05,
      "loss": 0.3393,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.4800575077533722,
      "learning_rate": 8.248337028824834e-05,
      "loss": 0.3919,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.5261036157608032,
      "learning_rate": 8.2039911308204e-05,
      "loss": 0.4047,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.5329307913780212,
      "learning_rate": 8.159645232815965e-05,
      "loss": 0.4349,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.6579233407974243,
      "learning_rate": 8.11529933481153e-05,
      "loss": 0.4237,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.6298967003822327,
      "learning_rate": 8.070953436807095e-05,
      "loss": 0.4848,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.668007493019104,
      "learning_rate": 8.026607538802661e-05,
      "loss": 0.4544,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.4833114743232727,
      "learning_rate": 7.982261640798227e-05,
      "loss": 0.486,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.5540068745613098,
      "learning_rate": 7.937915742793793e-05,
      "loss": 0.4871,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.5998792052268982,
      "learning_rate": 7.893569844789357e-05,
      "loss": 0.3854,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.5703440308570862,
      "learning_rate": 7.849223946784923e-05,
      "loss": 0.4145,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.6737166047096252,
      "learning_rate": 7.804878048780489e-05,
      "loss": 0.3808,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.6339266896247864,
      "learning_rate": 7.760532150776053e-05,
      "loss": 0.4302,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.5843977332115173,
      "learning_rate": 7.716186252771619e-05,
      "loss": 0.5419,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.6321794986724854,
      "learning_rate": 7.671840354767185e-05,
      "loss": 0.3533,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.6108585596084595,
      "learning_rate": 7.627494456762749e-05,
      "loss": 0.4716,
      "step": 285
    }
  ],
  "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": 1.2512186373683405e+17,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}