{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.665934065934066,
  "eval_steps": 500,
  "global_step": 405,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.9395878314971924,
      "learning_rate": 0.0,
      "loss": 3.0255,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 2.0909342765808105,
      "learning_rate": 4e-05,
      "loss": 3.2722,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 2.2211079597473145,
      "learning_rate": 8e-05,
      "loss": 3.0812,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.576534390449524,
      "learning_rate": 0.00012,
      "loss": 2.3772,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.288299560546875,
      "learning_rate": 0.00016,
      "loss": 2.7816,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.0976123809814453,
      "learning_rate": 0.0002,
      "loss": 1.8456,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.893791437149048,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.9392,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.5747392177581787,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.2524,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.9431101083755493,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2513,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.4205081462860107,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.5582,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.0894768238067627,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.2454,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5371621251106262,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.1853,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5113345384597778,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0215,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5522609353065491,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.0844,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5567106604576111,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.28,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5977707505226135,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.3916,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.4428749680519104,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.0281,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.39748522639274597,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.9917,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.4602974057197571,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.9289,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.46893274784088135,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.0148,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3629504144191742,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.0688,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3591447174549103,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.1489,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.38264843821525574,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.0042,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.30332762002944946,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.0645,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.36956873536109924,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.8483,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.35823047161102295,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9212,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.31688058376312256,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.8109,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.34314897656440735,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.9747,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.39364388585090637,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.0013,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.30356618762016296,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.9765,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.34586668014526367,
      "learning_rate": 0.00018891352549889136,
      "loss": 1.0919,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.32317039370536804,
      "learning_rate": 0.00018847006651884703,
      "loss": 1.0067,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.44286298751831055,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9623,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.3818933367729187,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.0142,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.33253738284111023,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.8074,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3408537805080414,
      "learning_rate": 0.00018669623059866964,
      "loss": 1.0326,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.40733590722084045,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.0927,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.36787742376327515,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.0677,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3505491614341736,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.9553,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3779163062572479,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.921,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3095817565917969,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.8463,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3786693513393402,
      "learning_rate": 0.00018403547671840356,
      "loss": 1.0101,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.2848946750164032,
      "learning_rate": 0.0001835920177383592,
      "loss": 1.1081,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.2794632613658905,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.8742,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.33480748534202576,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.9947,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.37888801097869873,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.9493,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.39233142137527466,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.0789,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.2909736931324005,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.0518,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.2732703983783722,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.9017,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.30006876587867737,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.8561,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.34367501735687256,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.0616,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.2993384003639221,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.7779,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3281186819076538,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.7872,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2709483206272125,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.9384,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3327484428882599,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.9123,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.32308903336524963,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.0042,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.2704257369041443,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.9699,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.28141987323760986,
      "learning_rate": 0.000176940133037694,
      "loss": 0.8826,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.35217514634132385,
      "learning_rate": 0.00017649667405764967,
      "loss": 1.0742,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.3242128789424896,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.8373,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.29047495126724243,
      "learning_rate": 0.000175609756097561,
      "loss": 0.885,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.30491581559181213,
      "learning_rate": 0.00017516629711751663,
      "loss": 1.0813,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.34017154574394226,
      "learning_rate": 0.0001747228381374723,
      "loss": 1.0067,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.2905332148075104,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.8561,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3342151343822479,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.9917,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.35391831398010254,
      "learning_rate": 0.00017339246119733924,
      "loss": 1.1116,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.34148970246315,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.9165,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.35057196021080017,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.9318,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.3118966221809387,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.9556,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.29268085956573486,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.8563,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3315921127796173,
      "learning_rate": 0.00017117516629711752,
      "loss": 1.1628,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.35345011949539185,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.944,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.2805996835231781,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8882,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.385016530752182,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.799,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.35097435116767883,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.9332,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.2864893674850464,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.8632,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.2386821061372757,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.9646,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.3139204978942871,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.9282,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.37618762254714966,
      "learning_rate": 0.00016762749445676275,
      "loss": 1.1463,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.3567148447036743,
      "learning_rate": 0.00016718403547671842,
      "loss": 1.2093,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.3268345594406128,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.8578,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.3362461030483246,
      "learning_rate": 0.00016629711751662974,
      "loss": 1.209,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.33477821946144104,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.9915,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.38696935772895813,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.8887,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.3261304199695587,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.9255,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.3052448034286499,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.9299,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.3229495584964752,
      "learning_rate": 0.000164079822616408,
      "loss": 0.874,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.34713301062583923,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.8682,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.32546767592430115,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.9824,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.2888805866241455,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.8598,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.32607126235961914,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.891,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.31503042578697205,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.9513,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.398336797952652,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.8821,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.32223382592201233,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.9786,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.33958667516708374,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.8952,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.2868139147758484,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.8921,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.34224361181259155,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.9362,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.30754712224006653,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.9801,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.2931382656097412,
      "learning_rate": 0.00015875831485587586,
      "loss": 1.1286,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.30773454904556274,
      "learning_rate": 0.0001583148558758315,
      "loss": 1.0438,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.3150854706764221,
      "learning_rate": 0.00015787139689578714,
      "loss": 1.1029,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.34101125597953796,
      "learning_rate": 0.0001574279379157428,
      "loss": 1.3197,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.301902174949646,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.9134,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.4397645592689514,
      "learning_rate": 0.0001565410199556541,
      "loss": 1.0168,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.30188363790512085,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.9051,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.28673937916755676,
      "learning_rate": 0.00015565410199556542,
      "loss": 1.0421,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.34226083755493164,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.8999,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.21212828159332275,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.6621,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.33283287286758423,
      "learning_rate": 0.00015432372505543238,
      "loss": 1.0817,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.3267793357372284,
      "learning_rate": 0.00015388026607538802,
      "loss": 1.0826,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.33544689416885376,
      "learning_rate": 0.0001534368070953437,
      "loss": 1.043,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.2979942858219147,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.9555,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.29721397161483765,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.7911,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.23252011835575104,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.7186,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.3264557719230652,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.9136,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.3115456700325012,
      "learning_rate": 0.00015121951219512197,
      "loss": 1.0437,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.3569914996623993,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.9559,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.3666040301322937,
      "learning_rate": 0.0001503325942350333,
      "loss": 1.0863,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.44128793478012085,
      "learning_rate": 0.0001498891352549889,
      "loss": 1.0112,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.24702684581279755,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.7882,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.32932835817337036,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.8732,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.2903375029563904,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.9835,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.3277665376663208,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.9524,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.3548404276371002,
      "learning_rate": 0.0001476718403547672,
      "loss": 1.0401,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.3156849145889282,
      "learning_rate": 0.00014722838137472282,
      "loss": 1.0754,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.37477758526802063,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.9014,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.3087361752986908,
      "learning_rate": 0.00014634146341463414,
      "loss": 1.08,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.2732657492160797,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.8144,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.29096436500549316,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.8827,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.29380616545677185,
      "learning_rate": 0.00014501108647450113,
      "loss": 1.0531,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.31562578678131104,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.8875,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.35802748799324036,
      "learning_rate": 0.00014412416851441242,
      "loss": 1.0098,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.32378309965133667,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.8362,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.311889111995697,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.9096,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.3975204825401306,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.826,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.2858659625053406,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.8492,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.4061797261238098,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.9427,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.3105581998825073,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.9379,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.3545703589916229,
      "learning_rate": 0.000141019955654102,
      "loss": 0.9037,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.290799617767334,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.7515,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.3229195177555084,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.9423,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.38070327043533325,
      "learning_rate": 0.00013968957871396897,
      "loss": 1.0264,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.3201819062232971,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.8616,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.28324103355407715,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.9933,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.3484077453613281,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.9151,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.3093436062335968,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.8514,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.2318611741065979,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.7289,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.4191138744354248,
      "learning_rate": 0.0001370288248337029,
      "loss": 1.0423,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.29127630591392517,
      "learning_rate": 0.00013658536585365856,
      "loss": 1.0706,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.3293207585811615,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.846,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.32789573073387146,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.8972,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.35556045174598694,
      "learning_rate": 0.0001352549889135255,
      "loss": 1.0373,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.2797600030899048,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.8272,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.27939650416374207,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.7378,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.3140670955181122,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.873,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.3043338358402252,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.728,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.23797346651554108,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.8907,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.3470970094203949,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.9333,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.36303016543388367,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.7435,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.3077246844768524,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.7731,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.31969889998435974,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.8777,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.3754861056804657,
      "learning_rate": 0.00013082039911308205,
      "loss": 1.098,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.29991087317466736,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.7567,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.3924933075904846,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.8253,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.3110440969467163,
      "learning_rate": 0.000129490022172949,
      "loss": 0.9294,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.477671355009079,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.9962,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.36420226097106934,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.8716,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.3950567841529846,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.6489,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.49215519428253174,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.8981,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.3717999756336212,
      "learning_rate": 0.00012727272727272728,
      "loss": 1.0126,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.32597070932388306,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.8131,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.3318406939506531,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.9198,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.4110514223575592,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.9242,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.3442305326461792,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.9842,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.40250134468078613,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.8919,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.3540174067020416,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.8814,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.4426930844783783,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.6934,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.3581725060939789,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.688,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.36629343032836914,
      "learning_rate": 0.00012328159645232816,
      "loss": 1.0895,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.31905603408813477,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.7644,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.4829590916633606,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.9648,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.4999721050262451,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.9346,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.41763952374458313,
      "learning_rate": 0.00012150776053215078,
      "loss": 1.1056,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.44277045130729675,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.7115,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.4127918779850006,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.956,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.41196775436401367,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.7456,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.4418405294418335,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.7181,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.3636420667171478,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.7889,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.33504438400268555,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.803,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.4142894446849823,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.7199,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.3721012771129608,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.7348,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.37692737579345703,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.784,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.4766246974468231,
      "learning_rate": 0.00011707317073170732,
      "loss": 1.0523,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.46161097288131714,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.8963,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.4499531388282776,
      "learning_rate": 0.00011618625277161863,
      "loss": 1.0331,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.3586902320384979,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.7852,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.40511220693588257,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.6751,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.4008190631866455,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.8498,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.4688575863838196,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.8175,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.4465175271034241,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.8179,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.4759213328361511,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.9403,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.4219147562980652,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.8712,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.4653088450431824,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.8987,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.4490373730659485,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.8106,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.4661843776702881,
      "learning_rate": 0.00011175166297117516,
      "loss": 1.0719,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.4243968427181244,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.818,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.4328853487968445,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.9956,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.5500715970993042,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.8236,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.41231441497802734,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.8938,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.47281545400619507,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.9136,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.49459365010261536,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.8019,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.5188332200050354,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.8719,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.5467557907104492,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.9006,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.3676692247390747,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.7469,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.4746938943862915,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.9304,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.5462958216667175,
      "learning_rate": 0.00010687361419068738,
      "loss": 1.1248,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.43692275881767273,
      "learning_rate": 0.00010643015521064301,
      "loss": 1.0437,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.4930446743965149,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.979,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.42187803983688354,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.8182,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.5209100246429443,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.8033,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.47799891233444214,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.8344,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.4318145215511322,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.813,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.6414012908935547,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.9778,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.44472914934158325,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.8879,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.4827914834022522,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.8394,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.46199890971183777,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.941,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.5035198330879211,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.8193,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.4342774748802185,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.707,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.46749448776245117,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.927,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.4692822992801666,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.8456,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.36757326126098633,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.7205,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.4106445610523224,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.7479,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.42066770792007446,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.6994,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.5228074789047241,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.8563,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.43481704592704773,
      "learning_rate": 9.84478935698448e-05,
      "loss": 1.0424,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.44934388995170593,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.9017,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.5142791867256165,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.9222,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.48339542746543884,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.8272,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.49565625190734863,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.8425,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.390887975692749,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.7891,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.5517682433128357,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.8543,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.41703271865844727,
      "learning_rate": 9.534368070953438e-05,
      "loss": 0.7458,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.4884392023086548,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.931,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.4803483188152313,
      "learning_rate": 9.445676274944568e-05,
      "loss": 1.036,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.44105175137519836,
      "learning_rate": 9.401330376940134e-05,
      "loss": 0.889,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.5469719767570496,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.9203,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.5460917949676514,
      "learning_rate": 9.312638580931264e-05,
      "loss": 0.976,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.5596751570701599,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.8109,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.48213839530944824,
      "learning_rate": 9.223946784922394e-05,
      "loss": 0.6856,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.5236599445343018,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.8165,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.40055152773857117,
      "learning_rate": 9.135254988913526e-05,
      "loss": 0.6546,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.4437563717365265,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.6952,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.4342647194862366,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.7428,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.4418627619743347,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.7247,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.5011357665061951,
      "learning_rate": 8.957871396895788e-05,
      "loss": 0.9412,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.49515554308891296,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.9058,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.5808390378952026,
      "learning_rate": 8.869179600886919e-05,
      "loss": 1.0236,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.5184139013290405,
      "learning_rate": 8.824833702882484e-05,
      "loss": 0.8296,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.47297316789627075,
      "learning_rate": 8.78048780487805e-05,
      "loss": 0.7259,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.5300582647323608,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.6836,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.47751402854919434,
      "learning_rate": 8.69179600886918e-05,
      "loss": 0.7184,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.4832569360733032,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.7895,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.5803284645080566,
      "learning_rate": 8.603104212860311e-05,
      "loss": 1.0191,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.5501025319099426,
      "learning_rate": 8.558758314855876e-05,
      "loss": 0.741,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.5096864700317383,
      "learning_rate": 8.514412416851442e-05,
      "loss": 0.7416,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.5164092779159546,
      "learning_rate": 8.470066518847007e-05,
      "loss": 0.7942,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.5029067993164062,
      "learning_rate": 8.425720620842572e-05,
      "loss": 0.7648,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.5849440097808838,
      "learning_rate": 8.381374722838138e-05,
      "loss": 0.805,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.49502384662628174,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.9628,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.45415806770324707,
      "learning_rate": 8.292682926829268e-05,
      "loss": 0.7339,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.5368886590003967,
      "learning_rate": 8.248337028824834e-05,
      "loss": 0.9911,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.529861330986023,
      "learning_rate": 8.2039911308204e-05,
      "loss": 0.7876,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.513733446598053,
      "learning_rate": 8.159645232815965e-05,
      "loss": 1.1312,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.5079568028450012,
      "learning_rate": 8.11529933481153e-05,
      "loss": 0.8613,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.48034361004829407,
      "learning_rate": 8.070953436807095e-05,
      "loss": 0.7719,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.5376922488212585,
      "learning_rate": 8.026607538802661e-05,
      "loss": 0.8119,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.589343249797821,
      "learning_rate": 7.982261640798227e-05,
      "loss": 0.9578,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.5273095965385437,
      "learning_rate": 7.937915742793793e-05,
      "loss": 0.8297,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.502260684967041,
      "learning_rate": 7.893569844789357e-05,
      "loss": 0.6974,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.5073599815368652,
      "learning_rate": 7.849223946784923e-05,
      "loss": 0.7095,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.5632908940315247,
      "learning_rate": 7.804878048780489e-05,
      "loss": 0.9438,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.5251880884170532,
      "learning_rate": 7.760532150776053e-05,
      "loss": 0.949,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.5640299916267395,
      "learning_rate": 7.716186252771619e-05,
      "loss": 0.8046,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.49976682662963867,
      "learning_rate": 7.671840354767185e-05,
      "loss": 0.778,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.5423333048820496,
      "learning_rate": 7.627494456762749e-05,
      "loss": 0.8147,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.5639551281929016,
      "learning_rate": 7.583148558758315e-05,
      "loss": 0.8837,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.4970256984233856,
      "learning_rate": 7.538802660753881e-05,
      "loss": 0.9495,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.4052160680294037,
      "learning_rate": 7.494456762749445e-05,
      "loss": 0.6844,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.4919658899307251,
      "learning_rate": 7.450110864745011e-05,
      "loss": 0.8857,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.4641786515712738,
      "learning_rate": 7.405764966740577e-05,
      "loss": 0.815,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.5832872986793518,
      "learning_rate": 7.361419068736141e-05,
      "loss": 0.7842,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.3834581673145294,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.5282,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.4863778054714203,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.6842,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.575855553150177,
      "learning_rate": 7.228381374722837e-05,
      "loss": 0.9846,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.5367918610572815,
      "learning_rate": 7.184035476718403e-05,
      "loss": 1.0408,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.5040566921234131,
      "learning_rate": 7.139689578713969e-05,
      "loss": 0.6592,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.4711240530014038,
      "learning_rate": 7.095343680709535e-05,
      "loss": 0.9054,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.5903924703598022,
      "learning_rate": 7.0509977827051e-05,
      "loss": 0.8764,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.5957019925117493,
      "learning_rate": 7.006651884700666e-05,
      "loss": 0.7864,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.6509841084480286,
      "learning_rate": 6.962305986696232e-05,
      "loss": 0.7532,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.4982222616672516,
      "learning_rate": 6.917960088691796e-05,
      "loss": 0.7904,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.563316285610199,
      "learning_rate": 6.873614190687362e-05,
      "loss": 0.8885,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.5464620590209961,
      "learning_rate": 6.829268292682928e-05,
      "loss": 0.8877,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8567683696746826,
      "learning_rate": 6.784922394678492e-05,
      "loss": 0.9257,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.45511293411254883,
      "learning_rate": 6.740576496674058e-05,
      "loss": 0.698,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.47419172525405884,
      "learning_rate": 6.696230598669624e-05,
      "loss": 0.6498,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.6667678356170654,
      "learning_rate": 6.651884700665188e-05,
      "loss": 0.978,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.5207124352455139,
      "learning_rate": 6.607538802660754e-05,
      "loss": 0.7804,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.4693681001663208,
      "learning_rate": 6.56319290465632e-05,
      "loss": 0.7096,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.5330842733383179,
      "learning_rate": 6.518847006651884e-05,
      "loss": 0.7121,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.5207657814025879,
      "learning_rate": 6.47450110864745e-05,
      "loss": 0.7342,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.5335293412208557,
      "learning_rate": 6.430155210643016e-05,
      "loss": 0.9512,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.5108652114868164,
      "learning_rate": 6.38580931263858e-05,
      "loss": 0.6952,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.485659658908844,
      "learning_rate": 6.341463414634146e-05,
      "loss": 0.7233,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.5744603276252747,
      "learning_rate": 6.297117516629712e-05,
      "loss": 0.8062,
      "step": 315
    },
    {
      "epoch": 2.0791208791208793,
      "grad_norm": 0.5345110893249512,
      "learning_rate": 6.252771618625277e-05,
      "loss": 0.7331,
      "step": 316
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.5660931468009949,
      "learning_rate": 6.208425720620842e-05,
      "loss": 0.7182,
      "step": 317
    },
    {
      "epoch": 2.0923076923076924,
      "grad_norm": 0.49297404289245605,
      "learning_rate": 6.164079822616408e-05,
      "loss": 0.6392,
      "step": 318
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.5957148671150208,
      "learning_rate": 6.119733924611974e-05,
      "loss": 1.067,
      "step": 319
    },
    {
      "epoch": 2.1054945054945056,
      "grad_norm": 0.539794385433197,
      "learning_rate": 6.075388026607539e-05,
      "loss": 0.6238,
      "step": 320
    },
    {
      "epoch": 2.112087912087912,
      "grad_norm": 0.5558685064315796,
      "learning_rate": 6.031042128603105e-05,
      "loss": 0.8062,
      "step": 321
    },
    {
      "epoch": 2.1186813186813187,
      "grad_norm": 0.5184114575386047,
      "learning_rate": 5.98669623059867e-05,
      "loss": 0.7436,
      "step": 322
    },
    {
      "epoch": 2.1252747252747253,
      "grad_norm": 0.6513444185256958,
      "learning_rate": 5.942350332594236e-05,
      "loss": 0.74,
      "step": 323
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.5181543231010437,
      "learning_rate": 5.898004434589801e-05,
      "loss": 0.7075,
      "step": 324
    },
    {
      "epoch": 2.1384615384615384,
      "grad_norm": 0.6252086162567139,
      "learning_rate": 5.853658536585366e-05,
      "loss": 0.7187,
      "step": 325
    },
    {
      "epoch": 2.145054945054945,
      "grad_norm": 0.6153728365898132,
      "learning_rate": 5.809312638580932e-05,
      "loss": 0.9944,
      "step": 326
    },
    {
      "epoch": 2.1516483516483516,
      "grad_norm": 0.6015222668647766,
      "learning_rate": 5.7649667405764975e-05,
      "loss": 0.7169,
      "step": 327
    },
    {
      "epoch": 2.158241758241758,
      "grad_norm": 0.5064176917076111,
      "learning_rate": 5.720620842572062e-05,
      "loss": 0.6265,
      "step": 328
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 0.5567384362220764,
      "learning_rate": 5.676274944567628e-05,
      "loss": 0.7683,
      "step": 329
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.548378050327301,
      "learning_rate": 5.6319290465631935e-05,
      "loss": 0.8012,
      "step": 330
    },
    {
      "epoch": 2.178021978021978,
      "grad_norm": 0.5442594885826111,
      "learning_rate": 5.587583148558758e-05,
      "loss": 0.5863,
      "step": 331
    },
    {
      "epoch": 2.184615384615385,
      "grad_norm": 0.7566731572151184,
      "learning_rate": 5.543237250554324e-05,
      "loss": 0.7232,
      "step": 332
    },
    {
      "epoch": 2.1912087912087914,
      "grad_norm": 0.5859387516975403,
      "learning_rate": 5.4988913525498895e-05,
      "loss": 0.7633,
      "step": 333
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.504564106464386,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.5644,
      "step": 334
    },
    {
      "epoch": 2.2043956043956046,
      "grad_norm": 0.6888545751571655,
      "learning_rate": 5.4101995565410204e-05,
      "loss": 0.6819,
      "step": 335
    },
    {
      "epoch": 2.210989010989011,
      "grad_norm": 0.7069364190101624,
      "learning_rate": 5.365853658536586e-05,
      "loss": 0.8596,
      "step": 336
    },
    {
      "epoch": 2.2175824175824177,
      "grad_norm": 0.5506071448326111,
      "learning_rate": 5.3215077605321506e-05,
      "loss": 0.5828,
      "step": 337
    },
    {
      "epoch": 2.2241758241758243,
      "grad_norm": 0.6472330689430237,
      "learning_rate": 5.2771618625277164e-05,
      "loss": 0.8585,
      "step": 338
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.5552042126655579,
      "learning_rate": 5.232815964523282e-05,
      "loss": 0.6064,
      "step": 339
    },
    {
      "epoch": 2.2373626373626374,
      "grad_norm": 0.5830889940261841,
      "learning_rate": 5.1884700665188466e-05,
      "loss": 0.6525,
      "step": 340
    },
    {
      "epoch": 2.243956043956044,
      "grad_norm": 0.6821195483207703,
      "learning_rate": 5.1441241685144124e-05,
      "loss": 0.7399,
      "step": 341
    },
    {
      "epoch": 2.2505494505494505,
      "grad_norm": 0.6324757933616638,
      "learning_rate": 5.099778270509978e-05,
      "loss": 0.7071,
      "step": 342
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 0.6676268577575684,
      "learning_rate": 5.0554323725055433e-05,
      "loss": 0.736,
      "step": 343
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 0.7146083116531372,
      "learning_rate": 5.011086474501109e-05,
      "loss": 0.9265,
      "step": 344
    },
    {
      "epoch": 2.2703296703296703,
      "grad_norm": 0.6000850200653076,
      "learning_rate": 4.966740576496674e-05,
      "loss": 0.5441,
      "step": 345
    },
    {
      "epoch": 2.276923076923077,
      "grad_norm": 0.6654199361801147,
      "learning_rate": 4.92239467849224e-05,
      "loss": 0.8367,
      "step": 346
    },
    {
      "epoch": 2.2835164835164834,
      "grad_norm": 0.714779794216156,
      "learning_rate": 4.878048780487805e-05,
      "loss": 0.7301,
      "step": 347
    },
    {
      "epoch": 2.29010989010989,
      "grad_norm": 0.7316946387290955,
      "learning_rate": 4.833702882483371e-05,
      "loss": 0.7866,
      "step": 348
    },
    {
      "epoch": 2.2967032967032965,
      "grad_norm": 0.6614524126052856,
      "learning_rate": 4.789356984478936e-05,
      "loss": 0.7718,
      "step": 349
    },
    {
      "epoch": 2.303296703296703,
      "grad_norm": 0.6145124435424805,
      "learning_rate": 4.745011086474501e-05,
      "loss": 0.745,
      "step": 350
    },
    {
      "epoch": 2.3098901098901097,
      "grad_norm": 0.7498903274536133,
      "learning_rate": 4.700665188470067e-05,
      "loss": 0.8381,
      "step": 351
    },
    {
      "epoch": 2.3164835164835162,
      "grad_norm": 0.6393078565597534,
      "learning_rate": 4.656319290465632e-05,
      "loss": 0.6785,
      "step": 352
    },
    {
      "epoch": 2.3230769230769233,
      "grad_norm": 0.5282366871833801,
      "learning_rate": 4.611973392461197e-05,
      "loss": 0.6147,
      "step": 353
    },
    {
      "epoch": 2.32967032967033,
      "grad_norm": 0.6980156302452087,
      "learning_rate": 4.567627494456763e-05,
      "loss": 0.7648,
      "step": 354
    },
    {
      "epoch": 2.3362637362637364,
      "grad_norm": 0.6875157952308655,
      "learning_rate": 4.523281596452328e-05,
      "loss": 0.693,
      "step": 355
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 0.7353724837303162,
      "learning_rate": 4.478935698447894e-05,
      "loss": 0.6795,
      "step": 356
    },
    {
      "epoch": 2.3494505494505495,
      "grad_norm": 0.6802405714988708,
      "learning_rate": 4.4345898004434597e-05,
      "loss": 0.6426,
      "step": 357
    },
    {
      "epoch": 2.356043956043956,
      "grad_norm": 0.7008536458015442,
      "learning_rate": 4.390243902439025e-05,
      "loss": 0.5644,
      "step": 358
    },
    {
      "epoch": 2.3626373626373627,
      "grad_norm": 0.6939390301704407,
      "learning_rate": 4.34589800443459e-05,
      "loss": 0.8114,
      "step": 359
    },
    {
      "epoch": 2.3692307692307693,
      "grad_norm": 0.6811842918395996,
      "learning_rate": 4.301552106430156e-05,
      "loss": 0.7944,
      "step": 360
    },
    {
      "epoch": 2.375824175824176,
      "grad_norm": 0.551972508430481,
      "learning_rate": 4.257206208425721e-05,
      "loss": 0.7149,
      "step": 361
    },
    {
      "epoch": 2.3824175824175824,
      "grad_norm": 0.6565220355987549,
      "learning_rate": 4.212860310421286e-05,
      "loss": 0.7307,
      "step": 362
    },
    {
      "epoch": 2.389010989010989,
      "grad_norm": 0.6757850050926208,
      "learning_rate": 4.168514412416852e-05,
      "loss": 0.7072,
      "step": 363
    },
    {
      "epoch": 2.3956043956043955,
      "grad_norm": 0.7067420482635498,
      "learning_rate": 4.124168514412417e-05,
      "loss": 0.7373,
      "step": 364
    },
    {
      "epoch": 2.402197802197802,
      "grad_norm": 0.7561600804328918,
      "learning_rate": 4.0798226164079826e-05,
      "loss": 0.784,
      "step": 365
    },
    {
      "epoch": 2.4087912087912087,
      "grad_norm": 0.5724413394927979,
      "learning_rate": 4.035476718403548e-05,
      "loss": 0.6469,
      "step": 366
    },
    {
      "epoch": 2.4153846153846152,
      "grad_norm": 0.7691506743431091,
      "learning_rate": 3.9911308203991135e-05,
      "loss": 0.7677,
      "step": 367
    },
    {
      "epoch": 2.421978021978022,
      "grad_norm": 0.6724645495414734,
      "learning_rate": 3.9467849223946786e-05,
      "loss": 0.757,
      "step": 368
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.647789478302002,
      "learning_rate": 3.9024390243902444e-05,
      "loss": 0.7208,
      "step": 369
    },
    {
      "epoch": 2.4351648351648354,
      "grad_norm": 0.6674468517303467,
      "learning_rate": 3.8580931263858095e-05,
      "loss": 0.6829,
      "step": 370
    },
    {
      "epoch": 2.441758241758242,
      "grad_norm": 0.591004490852356,
      "learning_rate": 3.8137472283813746e-05,
      "loss": 0.5481,
      "step": 371
    },
    {
      "epoch": 2.4483516483516485,
      "grad_norm": 0.6257899403572083,
      "learning_rate": 3.7694013303769404e-05,
      "loss": 0.6607,
      "step": 372
    },
    {
      "epoch": 2.454945054945055,
      "grad_norm": 0.7829266786575317,
      "learning_rate": 3.7250554323725055e-05,
      "loss": 0.7234,
      "step": 373
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.7276508212089539,
      "learning_rate": 3.6807095343680706e-05,
      "loss": 0.6582,
      "step": 374
    },
    {
      "epoch": 2.4681318681318682,
      "grad_norm": 0.6682559847831726,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.5733,
      "step": 375
    },
    {
      "epoch": 2.474725274725275,
      "grad_norm": 0.6348960995674133,
      "learning_rate": 3.5920177383592015e-05,
      "loss": 0.7829,
      "step": 376
    },
    {
      "epoch": 2.4813186813186814,
      "grad_norm": 0.6563917398452759,
      "learning_rate": 3.547671840354767e-05,
      "loss": 0.6444,
      "step": 377
    },
    {
      "epoch": 2.487912087912088,
      "grad_norm": 0.5655530691146851,
      "learning_rate": 3.503325942350333e-05,
      "loss": 0.7123,
      "step": 378
    },
    {
      "epoch": 2.4945054945054945,
      "grad_norm": 0.7483373880386353,
      "learning_rate": 3.458980044345898e-05,
      "loss": 0.7843,
      "step": 379
    },
    {
      "epoch": 2.501098901098901,
      "grad_norm": 0.6387296915054321,
      "learning_rate": 3.414634146341464e-05,
      "loss": 0.7239,
      "step": 380
    },
    {
      "epoch": 2.5076923076923077,
      "grad_norm": 0.6491879224777222,
      "learning_rate": 3.370288248337029e-05,
      "loss": 0.7298,
      "step": 381
    },
    {
      "epoch": 2.5142857142857142,
      "grad_norm": 0.6527333855628967,
      "learning_rate": 3.325942350332594e-05,
      "loss": 0.7032,
      "step": 382
    },
    {
      "epoch": 2.520879120879121,
      "grad_norm": 0.6915631294250488,
      "learning_rate": 3.28159645232816e-05,
      "loss": 0.6905,
      "step": 383
    },
    {
      "epoch": 2.5274725274725274,
      "grad_norm": 0.6882393956184387,
      "learning_rate": 3.237250554323725e-05,
      "loss": 0.7064,
      "step": 384
    },
    {
      "epoch": 2.534065934065934,
      "grad_norm": 0.6833249926567078,
      "learning_rate": 3.19290465631929e-05,
      "loss": 0.5496,
      "step": 385
    },
    {
      "epoch": 2.5406593406593405,
      "grad_norm": 0.7481502890586853,
      "learning_rate": 3.148558758314856e-05,
      "loss": 0.8646,
      "step": 386
    },
    {
      "epoch": 2.547252747252747,
      "grad_norm": 0.8310028910636902,
      "learning_rate": 3.104212860310421e-05,
      "loss": 0.8396,
      "step": 387
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.6542199850082397,
      "learning_rate": 3.059866962305987e-05,
      "loss": 0.6012,
      "step": 388
    },
    {
      "epoch": 2.5604395604395602,
      "grad_norm": 0.75499027967453,
      "learning_rate": 3.0155210643015524e-05,
      "loss": 0.8653,
      "step": 389
    },
    {
      "epoch": 2.567032967032967,
      "grad_norm": 0.7438053488731384,
      "learning_rate": 2.971175166297118e-05,
      "loss": 0.683,
      "step": 390
    },
    {
      "epoch": 2.5736263736263734,
      "grad_norm": 0.568401038646698,
      "learning_rate": 2.926829268292683e-05,
      "loss": 0.6334,
      "step": 391
    },
    {
      "epoch": 2.5802197802197804,
      "grad_norm": 0.7895120978355408,
      "learning_rate": 2.8824833702882487e-05,
      "loss": 0.7045,
      "step": 392
    },
    {
      "epoch": 2.586813186813187,
      "grad_norm": 0.8546737432479858,
      "learning_rate": 2.838137472283814e-05,
      "loss": 0.7115,
      "step": 393
    },
    {
      "epoch": 2.5934065934065935,
      "grad_norm": 0.7335292100906372,
      "learning_rate": 2.793791574279379e-05,
      "loss": 0.6363,
      "step": 394
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.7299824953079224,
      "learning_rate": 2.7494456762749448e-05,
      "loss": 0.77,
      "step": 395
    },
    {
      "epoch": 2.6065934065934067,
      "grad_norm": 0.7404250502586365,
      "learning_rate": 2.7050997782705102e-05,
      "loss": 0.7626,
      "step": 396
    },
    {
      "epoch": 2.6131868131868132,
      "grad_norm": 0.8042293787002563,
      "learning_rate": 2.6607538802660753e-05,
      "loss": 0.7682,
      "step": 397
    },
    {
      "epoch": 2.61978021978022,
      "grad_norm": 0.7943377494812012,
      "learning_rate": 2.616407982261641e-05,
      "loss": 0.7315,
      "step": 398
    },
    {
      "epoch": 2.6263736263736264,
      "grad_norm": 0.739908754825592,
      "learning_rate": 2.5720620842572062e-05,
      "loss": 0.6584,
      "step": 399
    },
    {
      "epoch": 2.632967032967033,
      "grad_norm": 0.594794750213623,
      "learning_rate": 2.5277161862527717e-05,
      "loss": 0.7116,
      "step": 400
    },
    {
      "epoch": 2.6395604395604395,
      "grad_norm": 0.7867955565452576,
      "learning_rate": 2.483370288248337e-05,
      "loss": 0.7911,
      "step": 401
    },
    {
      "epoch": 2.646153846153846,
      "grad_norm": 0.6884506940841675,
      "learning_rate": 2.4390243902439026e-05,
      "loss": 0.6677,
      "step": 402
    },
    {
      "epoch": 2.6527472527472526,
      "grad_norm": 0.7823262214660645,
      "learning_rate": 2.394678492239468e-05,
      "loss": 0.7569,
      "step": 403
    },
    {
      "epoch": 2.659340659340659,
      "grad_norm": 0.6857930421829224,
      "learning_rate": 2.3503325942350335e-05,
      "loss": 0.7542,
      "step": 404
    },
    {
      "epoch": 2.665934065934066,
      "grad_norm": 0.5742538571357727,
      "learning_rate": 2.3059866962305986e-05,
      "loss": 0.6784,
      "step": 405
    }
  ],
  "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": 6.718329059003597e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}