{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 456,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.6841859817504883,
      "learning_rate": 0.0,
      "loss": 2.6699,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.6275595426559448,
      "learning_rate": 4e-05,
      "loss": 2.8927,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.8733887672424316,
      "learning_rate": 8e-05,
      "loss": 2.892,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 2.217374324798584,
      "learning_rate": 0.00012,
      "loss": 3.1736,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.244591474533081,
      "learning_rate": 0.00016,
      "loss": 2.9009,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.151010036468506,
      "learning_rate": 0.0002,
      "loss": 2.9239,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.4616637229919434,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.6906,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.9495002031326294,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.3796,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.0036247968673706,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.4208,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.268955111503601,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.1932,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.9355878233909607,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.3019,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.6264943480491638,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.3045,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.48183032870292664,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0772,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.4918908178806305,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.1073,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.47716087102890015,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.0682,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5131794810295105,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.235,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.374526709318161,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.0192,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.42145562171936035,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.1169,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.3757359981536865,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.0849,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.39348798990249634,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.8945,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3551047742366791,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.8459,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.49977052211761475,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.1775,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.40330278873443604,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.045,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3608703315258026,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.1339,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3405609130859375,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.1932,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3685476779937744,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9513,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.3427353799343109,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9238,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.31721019744873047,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.9311,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.33064839243888855,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.9628,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.40480926632881165,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.0018,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.3145495355129242,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.7893,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3124920129776001,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.902,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.33218735456466675,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9481,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.29943299293518066,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.9887,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.2689051330089569,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.8745,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3515532910823822,
      "learning_rate": 0.00018669623059866964,
      "loss": 1.0236,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.4234579801559448,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.9152,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.23922260105609894,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.8792,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.33698251843452454,
      "learning_rate": 0.0001853658536585366,
      "loss": 1.0251,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3279472589492798,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.944,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3242871165275574,
      "learning_rate": 0.0001844789356984479,
      "loss": 1.0269,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.23830707371234894,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.7736,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.31032833456993103,
      "learning_rate": 0.0001835920177383592,
      "loss": 1.1615,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.34291455149650574,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.9362,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.3425392508506775,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.8127,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.3245941996574402,
      "learning_rate": 0.00018226164079822616,
      "loss": 1.0144,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.30251234769821167,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.7219,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.33010566234588623,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.1277,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.34598809480667114,
      "learning_rate": 0.00018093126385809312,
      "loss": 1.0634,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.29939746856689453,
      "learning_rate": 0.0001804878048780488,
      "loss": 1.0615,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.3273846209049225,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.0597,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.29587024450302124,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.9912,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3769407570362091,
      "learning_rate": 0.00017915742793791575,
      "loss": 1.1541,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.33768051862716675,
      "learning_rate": 0.0001787139689578714,
      "loss": 1.0642,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.34447458386421204,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.8971,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.21314434707164764,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.6039,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.31818050146102905,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.7694,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.31640103459358215,
      "learning_rate": 0.000176940133037694,
      "loss": 0.904,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.3352418839931488,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.949,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.2662431001663208,
      "learning_rate": 0.00017605321507760532,
      "loss": 1.0311,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.30483973026275635,
      "learning_rate": 0.000175609756097561,
      "loss": 1.0855,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.36452263593673706,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.8468,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.30326971411705017,
      "learning_rate": 0.0001747228381374723,
      "loss": 1.0586,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.24980409443378448,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.9535,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.4103758931159973,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.8719,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.39455509185791016,
      "learning_rate": 0.00017339246119733924,
      "loss": 1.2655,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.3029159605503082,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.9434,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.2612789273262024,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.9328,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.27301448583602905,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.8727,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3540093004703522,
      "learning_rate": 0.00017161862527716187,
      "loss": 1.0226,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.35511624813079834,
      "learning_rate": 0.00017117516629711752,
      "loss": 1.0837,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.30946084856987,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.955,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.27514076232910156,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8824,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.32071107625961304,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.9625,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.32895898818969727,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.8895,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.27520042657852173,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.8647,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.2894044816493988,
      "learning_rate": 0.00016851441241685144,
      "loss": 1.051,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.3063855767250061,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.9467,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.3323456048965454,
      "learning_rate": 0.00016762749445676275,
      "loss": 1.0092,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.2992066740989685,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.8565,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.35619041323661804,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.8428,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.31528913974761963,
      "learning_rate": 0.00016629711751662974,
      "loss": 1.0285,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.3301350474357605,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.8895,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.287077397108078,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.9325,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.3263772428035736,
      "learning_rate": 0.00016496674057649667,
      "loss": 1.0485,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.4456893503665924,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.9331,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.3191007971763611,
      "learning_rate": 0.000164079822616408,
      "loss": 1.151,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.30760490894317627,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.0333,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.29519811272621155,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.8138,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.2646964490413666,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.8292,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.28049373626708984,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.9276,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.3945385813713074,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.8175,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.3451618254184723,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.9411,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.25848403573036194,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.7706,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.29975318908691406,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.8506,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.2926693260669708,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.9974,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.2618350684642792,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.7716,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.2566186487674713,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.787,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.295584112405777,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.9429,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.3691546618938446,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.9469,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.33327218890190125,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.9988,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.35731151700019836,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.8776,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.37254080176353455,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.9446,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.3828260004520416,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.9977,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.3122965395450592,
      "learning_rate": 0.00015609756097560978,
      "loss": 1.042,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.29073771834373474,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.8936,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.2893447279930115,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.8716,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.32247859239578247,
      "learning_rate": 0.0001547671840354767,
      "loss": 1.0634,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.34692034125328064,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.9869,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.3532610833644867,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.9486,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.3133867681026459,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.9985,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.32353246212005615,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.8965,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.3264450132846832,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.9647,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.300886332988739,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.9389,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.3279182016849518,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.923,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.3101827800273895,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.9331,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.44228804111480713,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.9149,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.36783236265182495,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.9841,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.2897002398967743,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.8653,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.41255247592926025,
      "learning_rate": 0.00014944567627494458,
      "loss": 1.1311,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.3843879997730255,
      "learning_rate": 0.00014900221729490022,
      "loss": 1.0689,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.3691098093986511,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.9779,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.3556641638278961,
      "learning_rate": 0.00014811529933481154,
      "loss": 1.0477,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.3571156859397888,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.9452,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.33297181129455566,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.7441,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.2841457426548004,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.8841,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.391421377658844,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.889,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.35912957787513733,
      "learning_rate": 0.0001458980044345898,
      "loss": 1.0445,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.37496209144592285,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.0471,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.33316782116889954,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.9412,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.3246273398399353,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.9455,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.3718457818031311,
      "learning_rate": 0.00014412416851441242,
      "loss": 1.0444,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.3045291602611542,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.9313,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.3263269364833832,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.8312,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.3347906768321991,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.9123,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.32112935185432434,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.9683,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.29835888743400574,
      "learning_rate": 0.0001419068736141907,
      "loss": 1.0371,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.3718062937259674,
      "learning_rate": 0.00014146341463414634,
      "loss": 1.0962,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.29746073484420776,
      "learning_rate": 0.000141019955654102,
      "loss": 0.8657,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.33095526695251465,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.978,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.32061001658439636,
      "learning_rate": 0.00014013303769401332,
      "loss": 1.093,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.3012893795967102,
      "learning_rate": 0.00013968957871396897,
      "loss": 1.0411,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.33352234959602356,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.9689,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.36238616704940796,
      "learning_rate": 0.00013880266075388026,
      "loss": 1.0306,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.4270712435245514,
      "learning_rate": 0.00013835920177383593,
      "loss": 1.0203,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.4066736400127411,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.9071,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.4059554934501648,
      "learning_rate": 0.00013747228381374724,
      "loss": 1.1377,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.3651235103607178,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.9876,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.3939873278141022,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.9291,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.33947116136550903,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.9669,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.35278114676475525,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.9525,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5010539293289185,
      "learning_rate": 0.0001352549889135255,
      "loss": 1.0112,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.2538866400718689,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.6762,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.3684784471988678,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.8804,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.267274409532547,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.7563,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.33515307307243347,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.984,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.3435611426830292,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.8114,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.3645172715187073,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.9691,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.2773774564266205,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.8315,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.3886251449584961,
      "learning_rate": 0.00013170731707317076,
      "loss": 1.0001,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.3205171823501587,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.8011,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.3026052415370941,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.7669,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.3828047811985016,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.8812,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.43710312247276306,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.8759,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.3432680368423462,
      "learning_rate": 0.000129490022172949,
      "loss": 1.0038,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.35332900285720825,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.8612,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.3179774284362793,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.7998,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.33912646770477295,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.8104,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.4001254141330719,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.8691,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.31761422753334045,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.8402,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.3527398407459259,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.8732,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.4132620096206665,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.9772,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.36580634117126465,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.9152,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.3979237675666809,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.8563,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.3673313856124878,
      "learning_rate": 0.00012505543237250553,
      "loss": 1.1258,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.339437872171402,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.8658,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.37196624279022217,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.8409,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.43718069791793823,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.9349,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.41652625799179077,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.8683,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.37911519408226013,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.735,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.42966213822364807,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.8693,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.3764631748199463,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.948,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.3970170319080353,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.8294,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.2853337526321411,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.6603,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.4285735785961151,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.7915,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.39039742946624756,
      "learning_rate": 0.00012017738359201774,
      "loss": 1.0193,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.46625036001205444,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.8404,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.41254904866218567,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.7741,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.48079437017440796,
      "learning_rate": 0.00011884700665188471,
      "loss": 1.1514,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.5543079972267151,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.7679,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.45669472217559814,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.7384,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.556228756904602,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.9383,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.4771917462348938,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.8347,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.4172128736972809,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.852,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.4745047092437744,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.7344,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.46971040964126587,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.7481,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.46286725997924805,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.9246,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.4090142250061035,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.6622,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.4914513826370239,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.8372,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.47185248136520386,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.9582,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.5578212141990662,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.9445,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.47764039039611816,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.6539,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.4880480170249939,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.9413,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.5571289658546448,
      "learning_rate": 0.00011219512195121953,
      "loss": 1.0213,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.4747670590877533,
      "learning_rate": 0.00011175166297117516,
      "loss": 1.0307,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.5119542479515076,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.9872,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.40573716163635254,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.6651,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.38423505425453186,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.74,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.4716280996799469,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.8101,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.4662966728210449,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.8128,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.42522603273391724,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.8355,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.49166983366012573,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.6476,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.5308767557144165,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.8645,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.4998355507850647,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.8771,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.3976370692253113,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.764,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.4535082280635834,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.8562,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.5187000632286072,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.8502,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.5293376445770264,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.7147,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.5078467726707458,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.7802,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.46534693241119385,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.6928,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.4834364652633667,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.6597,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.5952091813087463,
      "learning_rate": 0.0001042128603104213,
      "loss": 1.0831,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.4789791405200958,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.8416,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.5206921100616455,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.7999,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.4702036678791046,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.8255,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.5501304268836975,
      "learning_rate": 0.0001024390243902439,
      "loss": 1.0623,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.5646650195121765,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.871,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.542455792427063,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.9041,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.5931452512741089,
      "learning_rate": 0.00010110864745011087,
      "loss": 1.0304,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.5497051477432251,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.8133,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.48107224702835083,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.8898,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.4992772936820984,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.8703,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.44935235381126404,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.7752,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.41368263959884644,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.8511,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.47118479013442993,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.8943,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.5319402813911438,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.8189,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.44167274236679077,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.8111,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.5065480470657349,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.8791,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.5863763093948364,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.8939,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.45883458852767944,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.7217,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.5509287118911743,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.9164,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.4993155002593994,
      "learning_rate": 9.534368070953438e-05,
      "loss": 0.8379,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.4131239652633667,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.7053,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.4165731966495514,
      "learning_rate": 9.445676274944568e-05,
      "loss": 0.9222,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.5763219594955444,
      "learning_rate": 9.401330376940134e-05,
      "loss": 0.8772,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.5291178226470947,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.8295,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.507473349571228,
      "learning_rate": 9.312638580931264e-05,
      "loss": 0.808,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.4162127375602722,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.6283,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.4975997507572174,
      "learning_rate": 9.223946784922394e-05,
      "loss": 0.8479,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.5329369902610779,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.6518,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.4321173131465912,
      "learning_rate": 9.135254988913526e-05,
      "loss": 0.7536,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.6066352128982544,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.8153,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.47606831789016724,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.9168,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.5018001198768616,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.811,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.6833066344261169,
      "learning_rate": 8.957871396895788e-05,
      "loss": 0.8655,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.5936504602432251,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.9015,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.5161994695663452,
      "learning_rate": 8.869179600886919e-05,
      "loss": 0.8588,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.49730348587036133,
      "learning_rate": 8.824833702882484e-05,
      "loss": 0.7663,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.5727002024650574,
      "learning_rate": 8.78048780487805e-05,
      "loss": 0.8673,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.6194294691085815,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.808,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.5998407006263733,
      "learning_rate": 8.69179600886918e-05,
      "loss": 0.851,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.5524242520332336,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.8411,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.5222271084785461,
      "learning_rate": 8.603104212860311e-05,
      "loss": 0.7936,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.5839205980300903,
      "learning_rate": 8.558758314855876e-05,
      "loss": 0.8758,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.577774703502655,
      "learning_rate": 8.514412416851442e-05,
      "loss": 1.0402,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.6118867993354797,
      "learning_rate": 8.470066518847007e-05,
      "loss": 0.9276,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.5915772318840027,
      "learning_rate": 8.425720620842572e-05,
      "loss": 1.1303,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.5170447826385498,
      "learning_rate": 8.381374722838138e-05,
      "loss": 0.7716,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.5245774388313293,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.8803,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.6484259366989136,
      "learning_rate": 8.292682926829268e-05,
      "loss": 0.8278,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.5212241411209106,
      "learning_rate": 8.248337028824834e-05,
      "loss": 0.8735,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.577881395816803,
      "learning_rate": 8.2039911308204e-05,
      "loss": 0.9273,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.5476526021957397,
      "learning_rate": 8.159645232815965e-05,
      "loss": 0.9239,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.5820876955986023,
      "learning_rate": 8.11529933481153e-05,
      "loss": 1.0303,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.48912057280540466,
      "learning_rate": 8.070953436807095e-05,
      "loss": 0.7747,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.541632890701294,
      "learning_rate": 8.026607538802661e-05,
      "loss": 0.8395,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.5873585939407349,
      "learning_rate": 7.982261640798227e-05,
      "loss": 0.727,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.7092168927192688,
      "learning_rate": 7.937915742793793e-05,
      "loss": 0.9269,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.5426027178764343,
      "learning_rate": 7.893569844789357e-05,
      "loss": 0.8585,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.5484429597854614,
      "learning_rate": 7.849223946784923e-05,
      "loss": 0.9635,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.6468372344970703,
      "learning_rate": 7.804878048780489e-05,
      "loss": 1.0519,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.4692719280719757,
      "learning_rate": 7.760532150776053e-05,
      "loss": 0.8352,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.6469602584838867,
      "learning_rate": 7.716186252771619e-05,
      "loss": 0.9104,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.594027042388916,
      "learning_rate": 7.671840354767185e-05,
      "loss": 0.6812,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.4868098497390747,
      "learning_rate": 7.627494456762749e-05,
      "loss": 1.0022,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.5563430786132812,
      "learning_rate": 7.583148558758315e-05,
      "loss": 0.9412,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.5918856859207153,
      "learning_rate": 7.538802660753881e-05,
      "loss": 0.845,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.5524916648864746,
      "learning_rate": 7.494456762749445e-05,
      "loss": 0.8499,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.541551411151886,
      "learning_rate": 7.450110864745011e-05,
      "loss": 0.8657,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.6338327527046204,
      "learning_rate": 7.405764966740577e-05,
      "loss": 1.0029,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.5365959405899048,
      "learning_rate": 7.361419068736141e-05,
      "loss": 0.6254,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.5960354208946228,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.6994,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.5497714877128601,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.9413,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.5866880416870117,
      "learning_rate": 7.228381374722837e-05,
      "loss": 0.7285,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.5962703227996826,
      "learning_rate": 7.184035476718403e-05,
      "loss": 0.788,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.616629421710968,
      "learning_rate": 7.139689578713969e-05,
      "loss": 0.8497,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.613470733165741,
      "learning_rate": 7.095343680709535e-05,
      "loss": 0.9057,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.5836480259895325,
      "learning_rate": 7.0509977827051e-05,
      "loss": 0.8022,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.5487856864929199,
      "learning_rate": 7.006651884700666e-05,
      "loss": 0.6869,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.5918538570404053,
      "learning_rate": 6.962305986696232e-05,
      "loss": 0.8037,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.7227702140808105,
      "learning_rate": 6.917960088691796e-05,
      "loss": 0.7954,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.6393794417381287,
      "learning_rate": 6.873614190687362e-05,
      "loss": 0.8259,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.5841372013092041,
      "learning_rate": 6.829268292682928e-05,
      "loss": 0.8979,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7825490236282349,
      "learning_rate": 6.784922394678492e-05,
      "loss": 0.8309,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.5685052275657654,
      "learning_rate": 6.740576496674058e-05,
      "loss": 0.709,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.5786356329917908,
      "learning_rate": 6.696230598669624e-05,
      "loss": 0.8484,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.4731592833995819,
      "learning_rate": 6.651884700665188e-05,
      "loss": 0.7188,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.6482547521591187,
      "learning_rate": 6.607538802660754e-05,
      "loss": 0.7232,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.5470800399780273,
      "learning_rate": 6.56319290465632e-05,
      "loss": 0.9522,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.5904238224029541,
      "learning_rate": 6.518847006651884e-05,
      "loss": 0.803,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.5274516344070435,
      "learning_rate": 6.47450110864745e-05,
      "loss": 0.6923,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.5509029030799866,
      "learning_rate": 6.430155210643016e-05,
      "loss": 0.6866,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.5738897323608398,
      "learning_rate": 6.38580931263858e-05,
      "loss": 0.8263,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.5509968400001526,
      "learning_rate": 6.341463414634146e-05,
      "loss": 0.6072,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.5100750923156738,
      "learning_rate": 6.297117516629712e-05,
      "loss": 0.852,
      "step": 315
    },
    {
      "epoch": 2.0791208791208793,
      "grad_norm": 0.6671582460403442,
      "learning_rate": 6.252771618625277e-05,
      "loss": 0.7113,
      "step": 316
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.6658451557159424,
      "learning_rate": 6.208425720620842e-05,
      "loss": 0.8057,
      "step": 317
    },
    {
      "epoch": 2.0923076923076924,
      "grad_norm": 0.5679474472999573,
      "learning_rate": 6.164079822616408e-05,
      "loss": 0.7034,
      "step": 318
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.6358360648155212,
      "learning_rate": 6.119733924611974e-05,
      "loss": 0.7532,
      "step": 319
    },
    {
      "epoch": 2.1054945054945056,
      "grad_norm": 0.6937404870986938,
      "learning_rate": 6.075388026607539e-05,
      "loss": 0.6632,
      "step": 320
    },
    {
      "epoch": 2.112087912087912,
      "grad_norm": 0.47931885719299316,
      "learning_rate": 6.031042128603105e-05,
      "loss": 0.6697,
      "step": 321
    },
    {
      "epoch": 2.1186813186813187,
      "grad_norm": 0.6942909359931946,
      "learning_rate": 5.98669623059867e-05,
      "loss": 1.0084,
      "step": 322
    },
    {
      "epoch": 2.1252747252747253,
      "grad_norm": 0.5924917459487915,
      "learning_rate": 5.942350332594236e-05,
      "loss": 0.6472,
      "step": 323
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.532040536403656,
      "learning_rate": 5.898004434589801e-05,
      "loss": 0.8315,
      "step": 324
    },
    {
      "epoch": 2.1384615384615384,
      "grad_norm": 0.6012279391288757,
      "learning_rate": 5.853658536585366e-05,
      "loss": 0.6481,
      "step": 325
    },
    {
      "epoch": 2.145054945054945,
      "grad_norm": 0.6135839819908142,
      "learning_rate": 5.809312638580932e-05,
      "loss": 0.6477,
      "step": 326
    },
    {
      "epoch": 2.1516483516483516,
      "grad_norm": 0.6669001579284668,
      "learning_rate": 5.7649667405764975e-05,
      "loss": 0.7532,
      "step": 327
    },
    {
      "epoch": 2.158241758241758,
      "grad_norm": 0.6428529024124146,
      "learning_rate": 5.720620842572062e-05,
      "loss": 0.9126,
      "step": 328
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 0.64589923620224,
      "learning_rate": 5.676274944567628e-05,
      "loss": 0.6859,
      "step": 329
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.6041516661643982,
      "learning_rate": 5.6319290465631935e-05,
      "loss": 0.908,
      "step": 330
    },
    {
      "epoch": 2.178021978021978,
      "grad_norm": 0.552687406539917,
      "learning_rate": 5.587583148558758e-05,
      "loss": 0.6188,
      "step": 331
    },
    {
      "epoch": 2.184615384615385,
      "grad_norm": 0.6779181361198425,
      "learning_rate": 5.543237250554324e-05,
      "loss": 0.6414,
      "step": 332
    },
    {
      "epoch": 2.1912087912087914,
      "grad_norm": 0.5852479338645935,
      "learning_rate": 5.4988913525498895e-05,
      "loss": 0.6191,
      "step": 333
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.7304171919822693,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.7,
      "step": 334
    },
    {
      "epoch": 2.2043956043956046,
      "grad_norm": 0.6762036085128784,
      "learning_rate": 5.4101995565410204e-05,
      "loss": 0.5885,
      "step": 335
    },
    {
      "epoch": 2.210989010989011,
      "grad_norm": 0.6312422156333923,
      "learning_rate": 5.365853658536586e-05,
      "loss": 0.6448,
      "step": 336
    },
    {
      "epoch": 2.2175824175824177,
      "grad_norm": 0.6550151705741882,
      "learning_rate": 5.3215077605321506e-05,
      "loss": 0.6527,
      "step": 337
    },
    {
      "epoch": 2.2241758241758243,
      "grad_norm": 0.7031694650650024,
      "learning_rate": 5.2771618625277164e-05,
      "loss": 0.7288,
      "step": 338
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.620998203754425,
      "learning_rate": 5.232815964523282e-05,
      "loss": 0.5984,
      "step": 339
    },
    {
      "epoch": 2.2373626373626374,
      "grad_norm": 0.5582302212715149,
      "learning_rate": 5.1884700665188466e-05,
      "loss": 0.7688,
      "step": 340
    },
    {
      "epoch": 2.243956043956044,
      "grad_norm": 0.6201855540275574,
      "learning_rate": 5.1441241685144124e-05,
      "loss": 0.5735,
      "step": 341
    },
    {
      "epoch": 2.2505494505494505,
      "grad_norm": 0.7676466703414917,
      "learning_rate": 5.099778270509978e-05,
      "loss": 0.7353,
      "step": 342
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 0.7455613017082214,
      "learning_rate": 5.0554323725055433e-05,
      "loss": 0.9078,
      "step": 343
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 0.5493049025535583,
      "learning_rate": 5.011086474501109e-05,
      "loss": 0.6517,
      "step": 344
    },
    {
      "epoch": 2.2703296703296703,
      "grad_norm": 0.6080396175384521,
      "learning_rate": 4.966740576496674e-05,
      "loss": 0.7406,
      "step": 345
    },
    {
      "epoch": 2.276923076923077,
      "grad_norm": 0.6395838260650635,
      "learning_rate": 4.92239467849224e-05,
      "loss": 0.7122,
      "step": 346
    },
    {
      "epoch": 2.2835164835164834,
      "grad_norm": 0.6702880859375,
      "learning_rate": 4.878048780487805e-05,
      "loss": 0.7031,
      "step": 347
    },
    {
      "epoch": 2.29010989010989,
      "grad_norm": 0.5909764766693115,
      "learning_rate": 4.833702882483371e-05,
      "loss": 0.6669,
      "step": 348
    },
    {
      "epoch": 2.2967032967032965,
      "grad_norm": 0.5091834664344788,
      "learning_rate": 4.789356984478936e-05,
      "loss": 0.6907,
      "step": 349
    },
    {
      "epoch": 2.303296703296703,
      "grad_norm": 0.7072070837020874,
      "learning_rate": 4.745011086474501e-05,
      "loss": 0.8011,
      "step": 350
    },
    {
      "epoch": 2.3098901098901097,
      "grad_norm": 0.702075719833374,
      "learning_rate": 4.700665188470067e-05,
      "loss": 0.5269,
      "step": 351
    },
    {
      "epoch": 2.3164835164835162,
      "grad_norm": 0.6924239993095398,
      "learning_rate": 4.656319290465632e-05,
      "loss": 0.6825,
      "step": 352
    },
    {
      "epoch": 2.3230769230769233,
      "grad_norm": 0.6713880300521851,
      "learning_rate": 4.611973392461197e-05,
      "loss": 0.7271,
      "step": 353
    },
    {
      "epoch": 2.32967032967033,
      "grad_norm": 0.6753330230712891,
      "learning_rate": 4.567627494456763e-05,
      "loss": 0.7771,
      "step": 354
    },
    {
      "epoch": 2.3362637362637364,
      "grad_norm": 0.6170812249183655,
      "learning_rate": 4.523281596452328e-05,
      "loss": 0.7376,
      "step": 355
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 0.7448060512542725,
      "learning_rate": 4.478935698447894e-05,
      "loss": 0.7493,
      "step": 356
    },
    {
      "epoch": 2.3494505494505495,
      "grad_norm": 0.6544110774993896,
      "learning_rate": 4.4345898004434597e-05,
      "loss": 0.6951,
      "step": 357
    },
    {
      "epoch": 2.356043956043956,
      "grad_norm": 0.7350860834121704,
      "learning_rate": 4.390243902439025e-05,
      "loss": 0.6625,
      "step": 358
    },
    {
      "epoch": 2.3626373626373627,
      "grad_norm": 0.7889458537101746,
      "learning_rate": 4.34589800443459e-05,
      "loss": 0.6804,
      "step": 359
    },
    {
      "epoch": 2.3692307692307693,
      "grad_norm": 0.6763615608215332,
      "learning_rate": 4.301552106430156e-05,
      "loss": 0.7241,
      "step": 360
    },
    {
      "epoch": 2.375824175824176,
      "grad_norm": 0.6661113500595093,
      "learning_rate": 4.257206208425721e-05,
      "loss": 0.6344,
      "step": 361
    },
    {
      "epoch": 2.3824175824175824,
      "grad_norm": 0.6395899653434753,
      "learning_rate": 4.212860310421286e-05,
      "loss": 0.7035,
      "step": 362
    },
    {
      "epoch": 2.389010989010989,
      "grad_norm": 0.70926433801651,
      "learning_rate": 4.168514412416852e-05,
      "loss": 0.6911,
      "step": 363
    },
    {
      "epoch": 2.3956043956043955,
      "grad_norm": 0.7031586766242981,
      "learning_rate": 4.124168514412417e-05,
      "loss": 0.6396,
      "step": 364
    },
    {
      "epoch": 2.402197802197802,
      "grad_norm": 0.7465059757232666,
      "learning_rate": 4.0798226164079826e-05,
      "loss": 0.6855,
      "step": 365
    },
    {
      "epoch": 2.4087912087912087,
      "grad_norm": 0.6353744268417358,
      "learning_rate": 4.035476718403548e-05,
      "loss": 0.6171,
      "step": 366
    },
    {
      "epoch": 2.4153846153846152,
      "grad_norm": 0.8016171455383301,
      "learning_rate": 3.9911308203991135e-05,
      "loss": 0.7606,
      "step": 367
    },
    {
      "epoch": 2.421978021978022,
      "grad_norm": 0.784881055355072,
      "learning_rate": 3.9467849223946786e-05,
      "loss": 0.6869,
      "step": 368
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.6462741494178772,
      "learning_rate": 3.9024390243902444e-05,
      "loss": 0.8102,
      "step": 369
    },
    {
      "epoch": 2.4351648351648354,
      "grad_norm": 0.5711301565170288,
      "learning_rate": 3.8580931263858095e-05,
      "loss": 0.5324,
      "step": 370
    },
    {
      "epoch": 2.441758241758242,
      "grad_norm": 0.6320512890815735,
      "learning_rate": 3.8137472283813746e-05,
      "loss": 0.6641,
      "step": 371
    },
    {
      "epoch": 2.4483516483516485,
      "grad_norm": 0.7693648934364319,
      "learning_rate": 3.7694013303769404e-05,
      "loss": 0.6079,
      "step": 372
    },
    {
      "epoch": 2.454945054945055,
      "grad_norm": 0.8172374963760376,
      "learning_rate": 3.7250554323725055e-05,
      "loss": 0.7527,
      "step": 373
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.7397374510765076,
      "learning_rate": 3.6807095343680706e-05,
      "loss": 0.6333,
      "step": 374
    },
    {
      "epoch": 2.4681318681318682,
      "grad_norm": 0.8138644099235535,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.7601,
      "step": 375
    },
    {
      "epoch": 2.474725274725275,
      "grad_norm": 0.6327239274978638,
      "learning_rate": 3.5920177383592015e-05,
      "loss": 0.7645,
      "step": 376
    },
    {
      "epoch": 2.4813186813186814,
      "grad_norm": 0.7217437028884888,
      "learning_rate": 3.547671840354767e-05,
      "loss": 0.8038,
      "step": 377
    },
    {
      "epoch": 2.487912087912088,
      "grad_norm": 0.7933579683303833,
      "learning_rate": 3.503325942350333e-05,
      "loss": 0.6671,
      "step": 378
    },
    {
      "epoch": 2.4945054945054945,
      "grad_norm": 0.7541384696960449,
      "learning_rate": 3.458980044345898e-05,
      "loss": 0.9523,
      "step": 379
    },
    {
      "epoch": 2.501098901098901,
      "grad_norm": 0.7814949154853821,
      "learning_rate": 3.414634146341464e-05,
      "loss": 0.7198,
      "step": 380
    },
    {
      "epoch": 2.5076923076923077,
      "grad_norm": 0.6220209002494812,
      "learning_rate": 3.370288248337029e-05,
      "loss": 0.6605,
      "step": 381
    },
    {
      "epoch": 2.5142857142857142,
      "grad_norm": 0.685131311416626,
      "learning_rate": 3.325942350332594e-05,
      "loss": 0.7541,
      "step": 382
    },
    {
      "epoch": 2.520879120879121,
      "grad_norm": 0.7568516135215759,
      "learning_rate": 3.28159645232816e-05,
      "loss": 0.7863,
      "step": 383
    },
    {
      "epoch": 2.5274725274725274,
      "grad_norm": 0.6581229567527771,
      "learning_rate": 3.237250554323725e-05,
      "loss": 0.5697,
      "step": 384
    },
    {
      "epoch": 2.534065934065934,
      "grad_norm": 0.8438876271247864,
      "learning_rate": 3.19290465631929e-05,
      "loss": 0.6762,
      "step": 385
    },
    {
      "epoch": 2.5406593406593405,
      "grad_norm": 0.7171187400817871,
      "learning_rate": 3.148558758314856e-05,
      "loss": 0.6587,
      "step": 386
    },
    {
      "epoch": 2.547252747252747,
      "grad_norm": 0.9332005977630615,
      "learning_rate": 3.104212860310421e-05,
      "loss": 0.7198,
      "step": 387
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.6284078359603882,
      "learning_rate": 3.059866962305987e-05,
      "loss": 0.5409,
      "step": 388
    },
    {
      "epoch": 2.5604395604395602,
      "grad_norm": 0.7558589577674866,
      "learning_rate": 3.0155210643015524e-05,
      "loss": 0.6611,
      "step": 389
    },
    {
      "epoch": 2.567032967032967,
      "grad_norm": 0.6738210320472717,
      "learning_rate": 2.971175166297118e-05,
      "loss": 0.6401,
      "step": 390
    },
    {
      "epoch": 2.5736263736263734,
      "grad_norm": 0.786262035369873,
      "learning_rate": 2.926829268292683e-05,
      "loss": 0.8352,
      "step": 391
    },
    {
      "epoch": 2.5802197802197804,
      "grad_norm": 0.6770197153091431,
      "learning_rate": 2.8824833702882487e-05,
      "loss": 0.6461,
      "step": 392
    },
    {
      "epoch": 2.586813186813187,
      "grad_norm": 0.722463071346283,
      "learning_rate": 2.838137472283814e-05,
      "loss": 0.7517,
      "step": 393
    },
    {
      "epoch": 2.5934065934065935,
      "grad_norm": 0.7087572813034058,
      "learning_rate": 2.793791574279379e-05,
      "loss": 0.7233,
      "step": 394
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.7239299416542053,
      "learning_rate": 2.7494456762749448e-05,
      "loss": 0.7679,
      "step": 395
    },
    {
      "epoch": 2.6065934065934067,
      "grad_norm": 0.7487732768058777,
      "learning_rate": 2.7050997782705102e-05,
      "loss": 0.638,
      "step": 396
    },
    {
      "epoch": 2.6131868131868132,
      "grad_norm": 0.630548357963562,
      "learning_rate": 2.6607538802660753e-05,
      "loss": 0.6437,
      "step": 397
    },
    {
      "epoch": 2.61978021978022,
      "grad_norm": 0.8996042013168335,
      "learning_rate": 2.616407982261641e-05,
      "loss": 0.7235,
      "step": 398
    },
    {
      "epoch": 2.6263736263736264,
      "grad_norm": 0.763251781463623,
      "learning_rate": 2.5720620842572062e-05,
      "loss": 0.5538,
      "step": 399
    },
    {
      "epoch": 2.632967032967033,
      "grad_norm": 0.8038184642791748,
      "learning_rate": 2.5277161862527717e-05,
      "loss": 0.7393,
      "step": 400
    },
    {
      "epoch": 2.6395604395604395,
      "grad_norm": 0.7436783909797668,
      "learning_rate": 2.483370288248337e-05,
      "loss": 0.7469,
      "step": 401
    },
    {
      "epoch": 2.646153846153846,
      "grad_norm": 0.7970079779624939,
      "learning_rate": 2.4390243902439026e-05,
      "loss": 0.6996,
      "step": 402
    },
    {
      "epoch": 2.6527472527472526,
      "grad_norm": 0.7553936243057251,
      "learning_rate": 2.394678492239468e-05,
      "loss": 0.7128,
      "step": 403
    },
    {
      "epoch": 2.659340659340659,
      "grad_norm": 0.7488527297973633,
      "learning_rate": 2.3503325942350335e-05,
      "loss": 0.7773,
      "step": 404
    },
    {
      "epoch": 2.665934065934066,
      "grad_norm": 0.7663573026657104,
      "learning_rate": 2.3059866962305986e-05,
      "loss": 0.6359,
      "step": 405
    },
    {
      "epoch": 2.672527472527473,
      "grad_norm": 0.6952940225601196,
      "learning_rate": 2.261640798226164e-05,
      "loss": 0.879,
      "step": 406
    },
    {
      "epoch": 2.6791208791208794,
      "grad_norm": 0.6013821363449097,
      "learning_rate": 2.2172949002217298e-05,
      "loss": 0.598,
      "step": 407
    },
    {
      "epoch": 2.685714285714286,
      "grad_norm": 0.7694355845451355,
      "learning_rate": 2.172949002217295e-05,
      "loss": 0.854,
      "step": 408
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.7486814260482788,
      "learning_rate": 2.1286031042128604e-05,
      "loss": 0.7093,
      "step": 409
    },
    {
      "epoch": 2.698901098901099,
      "grad_norm": 0.6668494939804077,
      "learning_rate": 2.084257206208426e-05,
      "loss": 0.7629,
      "step": 410
    },
    {
      "epoch": 2.7054945054945057,
      "grad_norm": 0.706438422203064,
      "learning_rate": 2.0399113082039913e-05,
      "loss": 0.6943,
      "step": 411
    },
    {
      "epoch": 2.7120879120879122,
      "grad_norm": 0.6633951663970947,
      "learning_rate": 1.9955654101995567e-05,
      "loss": 0.6563,
      "step": 412
    },
    {
      "epoch": 2.718681318681319,
      "grad_norm": 0.664840579032898,
      "learning_rate": 1.9512195121951222e-05,
      "loss": 0.5498,
      "step": 413
    },
    {
      "epoch": 2.7252747252747254,
      "grad_norm": 0.8504260778427124,
      "learning_rate": 1.9068736141906873e-05,
      "loss": 0.6875,
      "step": 414
    },
    {
      "epoch": 2.731868131868132,
      "grad_norm": 0.7241292595863342,
      "learning_rate": 1.8625277161862528e-05,
      "loss": 0.508,
      "step": 415
    },
    {
      "epoch": 2.7384615384615385,
      "grad_norm": 0.7645629644393921,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.5937,
      "step": 416
    },
    {
      "epoch": 2.745054945054945,
      "grad_norm": 0.7027500867843628,
      "learning_rate": 1.7738359201773837e-05,
      "loss": 0.5801,
      "step": 417
    },
    {
      "epoch": 2.7516483516483516,
      "grad_norm": 0.7785950303077698,
      "learning_rate": 1.729490022172949e-05,
      "loss": 0.7956,
      "step": 418
    },
    {
      "epoch": 2.758241758241758,
      "grad_norm": 0.7324172258377075,
      "learning_rate": 1.6851441241685146e-05,
      "loss": 0.8372,
      "step": 419
    },
    {
      "epoch": 2.764835164835165,
      "grad_norm": 0.8848752975463867,
      "learning_rate": 1.64079822616408e-05,
      "loss": 0.8474,
      "step": 420
    },
    {
      "epoch": 2.7714285714285714,
      "grad_norm": 0.8081530928611755,
      "learning_rate": 1.596452328159645e-05,
      "loss": 0.5454,
      "step": 421
    },
    {
      "epoch": 2.778021978021978,
      "grad_norm": 0.7642038464546204,
      "learning_rate": 1.5521064301552106e-05,
      "loss": 0.7693,
      "step": 422
    },
    {
      "epoch": 2.7846153846153845,
      "grad_norm": 0.7476908564567566,
      "learning_rate": 1.5077605321507762e-05,
      "loss": 0.643,
      "step": 423
    },
    {
      "epoch": 2.791208791208791,
      "grad_norm": 0.9479872584342957,
      "learning_rate": 1.4634146341463415e-05,
      "loss": 0.7529,
      "step": 424
    },
    {
      "epoch": 2.7978021978021976,
      "grad_norm": 0.7706624865531921,
      "learning_rate": 1.419068736141907e-05,
      "loss": 0.7234,
      "step": 425
    },
    {
      "epoch": 2.804395604395604,
      "grad_norm": 0.6908024549484253,
      "learning_rate": 1.3747228381374724e-05,
      "loss": 0.6922,
      "step": 426
    },
    {
      "epoch": 2.8109890109890108,
      "grad_norm": 0.7798461318016052,
      "learning_rate": 1.3303769401330377e-05,
      "loss": 0.642,
      "step": 427
    },
    {
      "epoch": 2.8175824175824173,
      "grad_norm": 0.7532527446746826,
      "learning_rate": 1.2860310421286031e-05,
      "loss": 0.6947,
      "step": 428
    },
    {
      "epoch": 2.824175824175824,
      "grad_norm": 0.7854769825935364,
      "learning_rate": 1.2416851441241686e-05,
      "loss": 0.719,
      "step": 429
    },
    {
      "epoch": 2.830769230769231,
      "grad_norm": 0.8277010321617126,
      "learning_rate": 1.197339246119734e-05,
      "loss": 0.6469,
      "step": 430
    },
    {
      "epoch": 2.8373626373626375,
      "grad_norm": 0.8104733824729919,
      "learning_rate": 1.1529933481152993e-05,
      "loss": 0.9231,
      "step": 431
    },
    {
      "epoch": 2.843956043956044,
      "grad_norm": 0.8771021366119385,
      "learning_rate": 1.1086474501108649e-05,
      "loss": 0.888,
      "step": 432
    },
    {
      "epoch": 2.8505494505494506,
      "grad_norm": 0.8072786331176758,
      "learning_rate": 1.0643015521064302e-05,
      "loss": 0.8411,
      "step": 433
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.8028353452682495,
      "learning_rate": 1.0199556541019956e-05,
      "loss": 0.669,
      "step": 434
    },
    {
      "epoch": 2.8637362637362638,
      "grad_norm": 0.7101897597312927,
      "learning_rate": 9.756097560975611e-06,
      "loss": 0.7392,
      "step": 435
    },
    {
      "epoch": 2.8703296703296703,
      "grad_norm": 0.8531978726387024,
      "learning_rate": 9.312638580931264e-06,
      "loss": 0.6862,
      "step": 436
    },
    {
      "epoch": 2.876923076923077,
      "grad_norm": 0.7238748073577881,
      "learning_rate": 8.869179600886918e-06,
      "loss": 0.7778,
      "step": 437
    },
    {
      "epoch": 2.8835164835164835,
      "grad_norm": 0.6305073499679565,
      "learning_rate": 8.425720620842573e-06,
      "loss": 0.5993,
      "step": 438
    },
    {
      "epoch": 2.89010989010989,
      "grad_norm": 0.7523983716964722,
      "learning_rate": 7.982261640798226e-06,
      "loss": 0.7169,
      "step": 439
    },
    {
      "epoch": 2.8967032967032966,
      "grad_norm": 0.8070085644721985,
      "learning_rate": 7.538802660753881e-06,
      "loss": 0.647,
      "step": 440
    },
    {
      "epoch": 2.903296703296703,
      "grad_norm": 0.8163391351699829,
      "learning_rate": 7.095343680709535e-06,
      "loss": 0.8444,
      "step": 441
    },
    {
      "epoch": 2.9098901098901098,
      "grad_norm": 0.8550701141357422,
      "learning_rate": 6.651884700665188e-06,
      "loss": 0.7054,
      "step": 442
    },
    {
      "epoch": 2.9164835164835163,
      "grad_norm": 0.7117502689361572,
      "learning_rate": 6.208425720620843e-06,
      "loss": 0.7274,
      "step": 443
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.7004100680351257,
      "learning_rate": 5.7649667405764965e-06,
      "loss": 0.702,
      "step": 444
    },
    {
      "epoch": 2.92967032967033,
      "grad_norm": 0.8559068441390991,
      "learning_rate": 5.321507760532151e-06,
      "loss": 0.7084,
      "step": 445
    },
    {
      "epoch": 2.9362637362637365,
      "grad_norm": 0.8398165106773376,
      "learning_rate": 4.8780487804878055e-06,
      "loss": 0.7081,
      "step": 446
    },
    {
      "epoch": 2.942857142857143,
      "grad_norm": 0.7549614310264587,
      "learning_rate": 4.434589800443459e-06,
      "loss": 0.724,
      "step": 447
    },
    {
      "epoch": 2.9494505494505496,
      "grad_norm": 0.7334049940109253,
      "learning_rate": 3.991130820399113e-06,
      "loss": 0.7953,
      "step": 448
    },
    {
      "epoch": 2.956043956043956,
      "grad_norm": 0.783241868019104,
      "learning_rate": 3.5476718403547673e-06,
      "loss": 0.6381,
      "step": 449
    },
    {
      "epoch": 2.9626373626373628,
      "grad_norm": 0.7294999361038208,
      "learning_rate": 3.1042128603104214e-06,
      "loss": 0.7779,
      "step": 450
    },
    {
      "epoch": 2.9692307692307693,
      "grad_norm": 0.8634478449821472,
      "learning_rate": 2.6607538802660755e-06,
      "loss": 0.8365,
      "step": 451
    },
    {
      "epoch": 2.975824175824176,
      "grad_norm": 0.8616492748260498,
      "learning_rate": 2.2172949002217296e-06,
      "loss": 0.6381,
      "step": 452
    },
    {
      "epoch": 2.9824175824175825,
      "grad_norm": 0.850271999835968,
      "learning_rate": 1.7738359201773837e-06,
      "loss": 0.8601,
      "step": 453
    },
    {
      "epoch": 2.989010989010989,
      "grad_norm": 0.6399109959602356,
      "learning_rate": 1.3303769401330377e-06,
      "loss": 0.5496,
      "step": 454
    },
    {
      "epoch": 2.9956043956043956,
      "grad_norm": 0.8177953958511353,
      "learning_rate": 8.869179600886918e-07,
      "loss": 0.8417,
      "step": 455
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7678176760673523,
      "learning_rate": 4.434589800443459e-07,
      "loss": 0.6693,
      "step": 456
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.291356273392026e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}