{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.3692307692307693,
  "eval_steps": 500,
  "global_step": 360,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 2.040729522705078,
      "learning_rate": 0.0,
      "loss": 2.7683,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.5997058153152466,
      "learning_rate": 4e-05,
      "loss": 2.8974,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.4524474143981934,
      "learning_rate": 8e-05,
      "loss": 2.5688,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.9891413450241089,
      "learning_rate": 0.00012,
      "loss": 2.8694,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.8264071941375732,
      "learning_rate": 0.00016,
      "loss": 2.6132,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.4443397521972656,
      "learning_rate": 0.0002,
      "loss": 2.2173,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.0982062816619873,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.7622,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.6505112648010254,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.3387,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.010646939277649,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2799,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.153071641921997,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.1895,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.1261000633239746,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.2056,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.759114682674408,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.3029,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5342807769775391,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0965,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.4958232641220093,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.0701,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.3884180784225464,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.9401,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.4318467676639557,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.9828,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.3914318084716797,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.1001,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.3810254633426666,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.0365,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.35773465037345886,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.014,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.3865130543708801,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.8989,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.4047197699546814,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.1462,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3278495669364929,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.1252,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3710285425186157,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.2668,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3148868978023529,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.8434,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3265138864517212,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.768,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3631599247455597,
      "learning_rate": 0.00019113082039911309,
      "loss": 1.1749,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.27795249223709106,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9959,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3963681757450104,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.1824,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.2918461859226227,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.9414,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3593352437019348,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.0456,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.34449681639671326,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.8949,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3254448473453522,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.9376,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.41807615756988525,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9988,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.37100034952163696,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.8622,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3113406300544739,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.9483,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3257967233657837,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.9764,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.2937210202217102,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.7566,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.29698532819747925,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.825,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.27970588207244873,
      "learning_rate": 0.0001853658536585366,
      "loss": 1.0668,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.35342398285865784,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.9583,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3180616497993469,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.902,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.31773990392684937,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.822,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.3524340093135834,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.9059,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.29651206731796265,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.7724,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.34590038657188416,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.9302,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.2645731568336487,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.9153,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.23055709898471832,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.8608,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.2497446984052658,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.9208,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.2636415660381317,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.8463,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.26790788769721985,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.8621,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.421093612909317,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.9132,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.31024041771888733,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.9297,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.23121075332164764,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.6466,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.296550989151001,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.9569,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.2945939302444458,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.8977,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.3035891354084015,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.8298,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.3183322250843048,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.9327,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.29244929552078247,
      "learning_rate": 0.000176940133037694,
      "loss": 0.8703,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.2913990616798401,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.8028,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.2462514191865921,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.7429,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.2985650897026062,
      "learning_rate": 0.000175609756097561,
      "loss": 0.8638,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3608158230781555,
      "learning_rate": 0.00017516629711751663,
      "loss": 1.1919,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3318116366863251,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.9872,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.3617628216743469,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.9364,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.31744787096977234,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.9506,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3872555196285248,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.9261,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.39704272150993347,
      "learning_rate": 0.0001729490022172949,
      "loss": 1.0269,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.28049373626708984,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.9623,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.300989031791687,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.9126,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3367176055908203,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.9019,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.28371915221214294,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.9708,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.31290653347969055,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.9857,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.2825471758842468,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.7815,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.35956916213035583,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.9159,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.3377499580383301,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.9292,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.33395451307296753,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.876,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.28057777881622314,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.9677,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.2822154462337494,
      "learning_rate": 0.0001680709534368071,
      "loss": 1.0842,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.3324544429779053,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.8575,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.2870771884918213,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.7998,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.33145201206207275,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.9562,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.2959634065628052,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.7711,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.3113443851470947,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.8239,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3531242907047272,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.8348,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.3268181085586548,
      "learning_rate": 0.00016496674057649667,
      "loss": 1.0932,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.2966617941856384,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.8145,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.29501864314079285,
      "learning_rate": 0.000164079822616408,
      "loss": 0.9101,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.44777199625968933,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.0954,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.33370208740234375,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.9927,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.3485364019870758,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.9479,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.35214394330978394,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.868,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.38331282138824463,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.9928,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.2905575633049011,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.8042,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.3119705617427826,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.8735,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.34137290716171265,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.8623,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.3644528388977051,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.866,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.31675055623054504,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.9698,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.3355556130409241,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.9107,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.30216923356056213,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.9989,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.33366093039512634,
      "learning_rate": 0.0001583148558758315,
      "loss": 1.0218,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.31476911902427673,
      "learning_rate": 0.00015787139689578714,
      "loss": 1.0171,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.26105156540870667,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.8956,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.26974397897720337,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.8026,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.3336484432220459,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.8995,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.29841259121894836,
      "learning_rate": 0.00015609756097560978,
      "loss": 1.0647,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.2999913990497589,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.8008,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.3095431327819824,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.9433,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.27054646611213684,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.9113,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.2927210330963135,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.9312,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.29628896713256836,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.8605,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.3454248011112213,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.846,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.3357175290584564,
      "learning_rate": 0.00015299334811529934,
      "loss": 1.0185,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.29496240615844727,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.9517,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.2650928199291229,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.8111,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.396181583404541,
      "learning_rate": 0.0001516629711751663,
      "loss": 1.0588,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.3637149930000305,
      "learning_rate": 0.00015121951219512197,
      "loss": 1.1221,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.41569623351097107,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.9496,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.2925027310848236,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.9064,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.35358142852783203,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.9381,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.3887578845024109,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.9566,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.32111304998397827,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.8861,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.35338282585144043,
      "learning_rate": 0.0001485587583148559,
      "loss": 1.1087,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.3537110984325409,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.9158,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.34085920453071594,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.904,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.3360932171344757,
      "learning_rate": 0.00014722838137472282,
      "loss": 1.0646,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.37404346466064453,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.9414,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.4108354449272156,
      "learning_rate": 0.00014634146341463414,
      "loss": 1.2007,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.2696903944015503,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.8779,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.323378324508667,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.0581,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.2431671917438507,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.8635,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.3379897475242615,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.9279,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.3065502643585205,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.8243,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.46185189485549927,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.8997,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.3813929557800293,
      "learning_rate": 0.00014323725055432373,
      "loss": 1.1088,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.27054256200790405,
      "learning_rate": 0.00014279379157427938,
      "loss": 1.0085,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.3499416708946228,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.9426,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.3143306374549866,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.9715,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.3015587329864502,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.9488,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.34380462765693665,
      "learning_rate": 0.000141019955654102,
      "loss": 0.8785,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.44090035557746887,
      "learning_rate": 0.00014057649667405765,
      "loss": 1.0484,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.39180663228034973,
      "learning_rate": 0.00014013303769401332,
      "loss": 1.2142,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.2903823256492615,
      "learning_rate": 0.00013968957871396897,
      "loss": 1.1199,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.301432341337204,
      "learning_rate": 0.00013924611973392464,
      "loss": 1.031,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.3448426127433777,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.8118,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.39949119091033936,
      "learning_rate": 0.00013835920177383593,
      "loss": 1.0262,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.3494434356689453,
      "learning_rate": 0.00013791574279379157,
      "loss": 1.0085,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.37902480363845825,
      "learning_rate": 0.00013747228381374724,
      "loss": 1.1039,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.36213400959968567,
      "learning_rate": 0.0001370288248337029,
      "loss": 1.0547,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.2966698408126831,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.9102,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.40465399622917175,
      "learning_rate": 0.00013614190687361418,
      "loss": 1.1571,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.2752663493156433,
      "learning_rate": 0.00013569844789356985,
      "loss": 1.0154,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.49627214670181274,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.7374,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.33316904306411743,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.9571,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.3286375403404236,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.7735,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.3124527037143707,
      "learning_rate": 0.00013392461197339248,
      "loss": 1.0182,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.27000507712364197,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.7302,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.33546531200408936,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.7168,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.32710471749305725,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.7415,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.3367829918861389,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.7639,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.3086932897567749,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.9011,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.3069556951522827,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.8736,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.38524317741394043,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.9046,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.368782103061676,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.8038,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.38482290506362915,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.9006,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.35978007316589355,
      "learning_rate": 0.000129490022172949,
      "loss": 0.9857,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.41065138578414917,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.8954,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.3142144978046417,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.8195,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.31044167280197144,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.664,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.40812182426452637,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.7827,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.3895621597766876,
      "learning_rate": 0.00012727272727272728,
      "loss": 1.0224,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.3680282533168793,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.9538,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.3892245292663574,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.8286,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.3541584312915802,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.8304,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.40991920232772827,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.8447,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.3959386348724365,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.9693,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.42273956537246704,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.8459,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.3517262637615204,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.7026,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.39490169286727905,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.7876,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.322983980178833,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.7934,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.37467533349990845,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.8366,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.4527815282344818,
      "learning_rate": 0.00012239467849223948,
      "loss": 1.1189,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.3937065005302429,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.763,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.4277024269104004,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.9977,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.3426341116428375,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.7202,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.47265154123306274,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.982,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.35672813653945923,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.6974,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.3976980447769165,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.9709,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.4389066696166992,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.8037,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.3946899175643921,
      "learning_rate": 0.00011884700665188471,
      "loss": 1.0088,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.44508126378059387,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.8487,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.388470858335495,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.9337,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.4118698835372925,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.8203,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.39014217257499695,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.9304,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.3931826949119568,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.8272,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.46026092767715454,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.814,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.3287672996520996,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.8193,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.43756914138793945,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.7961,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.3982744514942169,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.7334,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.514826774597168,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.9054,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.4161317050457001,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.8591,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.4838102459907532,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.812,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.5108524560928345,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.8598,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.4338836967945099,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.83,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.4803040623664856,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.74,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.5522419214248657,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.8982,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.4007526636123657,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.8945,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.44590815901756287,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.8946,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.45139092206954956,
      "learning_rate": 0.00011042128603104213,
      "loss": 1.0059,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.42539849877357483,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.8158,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.49731504917144775,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.9491,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.568740725517273,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.9356,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.4906386733055115,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.9204,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.4245906174182892,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.7317,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.5111746788024902,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.7949,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.49368029832839966,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.9795,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.5272615551948547,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.8617,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.5284165740013123,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.6614,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.4840940535068512,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.9969,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.483829140663147,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.7523,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.5638898611068726,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.8715,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.44715312123298645,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.8173,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.5283309817314148,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.8887,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.4485217034816742,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.8962,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.4839077591896057,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.7892,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.4501904249191284,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.9471,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.5451169610023499,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.8172,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.5381113290786743,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.8384,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.5011449456214905,
      "learning_rate": 0.00010155210643015522,
      "loss": 1.0465,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.5088122487068176,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.8004,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.44216015934944153,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.8387,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.3692184090614319,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.8306,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.5074309706687927,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.9678,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.46052587032318115,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.9005,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.4800049066543579,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.7707,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.4891799986362457,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.8048,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.42039352655410767,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.8295,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.5204365253448486,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.8587,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.5300447940826416,
      "learning_rate": 9.711751662971176e-05,
      "loss": 1.0995,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.5329034328460693,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.81,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.43644365668296814,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.5908,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.574343740940094,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.9352,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.5560671091079712,
      "learning_rate": 9.534368070953438e-05,
      "loss": 0.9341,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.5033860802650452,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.7887,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.49761322140693665,
      "learning_rate": 9.445676274944568e-05,
      "loss": 0.7546,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.5591793656349182,
      "learning_rate": 9.401330376940134e-05,
      "loss": 1.0192,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.4839686453342438,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.7672,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.467282235622406,
      "learning_rate": 9.312638580931264e-05,
      "loss": 0.6839,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.4524802267551422,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.6728,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.46149277687072754,
      "learning_rate": 9.223946784922394e-05,
      "loss": 0.8344,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.5137358903884888,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.7649,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.523654580116272,
      "learning_rate": 9.135254988913526e-05,
      "loss": 0.795,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.45009148120880127,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.7484,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.5043858289718628,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.6702,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.40968772768974304,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.697,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.43491634726524353,
      "learning_rate": 8.957871396895788e-05,
      "loss": 0.5821,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.5302298665046692,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.8566,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.5804020166397095,
      "learning_rate": 8.869179600886919e-05,
      "loss": 0.8176,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.5115612745285034,
      "learning_rate": 8.824833702882484e-05,
      "loss": 0.824,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.5702483654022217,
      "learning_rate": 8.78048780487805e-05,
      "loss": 0.7843,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.5767391324043274,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.7592,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.4662434160709381,
      "learning_rate": 8.69179600886918e-05,
      "loss": 0.905,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.5669234991073608,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.8368,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.5055147409439087,
      "learning_rate": 8.603104212860311e-05,
      "loss": 0.9178,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.5356152653694153,
      "learning_rate": 8.558758314855876e-05,
      "loss": 0.7078,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.5189350843429565,
      "learning_rate": 8.514412416851442e-05,
      "loss": 0.9262,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.4941180646419525,
      "learning_rate": 8.470066518847007e-05,
      "loss": 0.7839,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.519519031047821,
      "learning_rate": 8.425720620842572e-05,
      "loss": 0.7491,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.5200636982917786,
      "learning_rate": 8.381374722838138e-05,
      "loss": 0.8273,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.511701762676239,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.7722,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.5713851451873779,
      "learning_rate": 8.292682926829268e-05,
      "loss": 0.823,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.588949978351593,
      "learning_rate": 8.248337028824834e-05,
      "loss": 0.8404,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.527821958065033,
      "learning_rate": 8.2039911308204e-05,
      "loss": 0.8841,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.592380166053772,
      "learning_rate": 8.159645232815965e-05,
      "loss": 0.8181,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.39086422324180603,
      "learning_rate": 8.11529933481153e-05,
      "loss": 0.7187,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.6602182388305664,
      "learning_rate": 8.070953436807095e-05,
      "loss": 0.872,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.5376669764518738,
      "learning_rate": 8.026607538802661e-05,
      "loss": 0.7066,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.5320796966552734,
      "learning_rate": 7.982261640798227e-05,
      "loss": 0.8113,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.4373811185359955,
      "learning_rate": 7.937915742793793e-05,
      "loss": 0.7399,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.5380655527114868,
      "learning_rate": 7.893569844789357e-05,
      "loss": 0.8473,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.541419267654419,
      "learning_rate": 7.849223946784923e-05,
      "loss": 0.8342,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.5031387209892273,
      "learning_rate": 7.804878048780489e-05,
      "loss": 0.781,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.4829193949699402,
      "learning_rate": 7.760532150776053e-05,
      "loss": 0.6815,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.6294733881950378,
      "learning_rate": 7.716186252771619e-05,
      "loss": 0.9334,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.4638768434524536,
      "learning_rate": 7.671840354767185e-05,
      "loss": 0.8422,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.4632713794708252,
      "learning_rate": 7.627494456762749e-05,
      "loss": 0.7666,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.49210992455482483,
      "learning_rate": 7.583148558758315e-05,
      "loss": 0.7339,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.5478222370147705,
      "learning_rate": 7.538802660753881e-05,
      "loss": 0.7423,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.5831414461135864,
      "learning_rate": 7.494456762749445e-05,
      "loss": 0.8497,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.5755442976951599,
      "learning_rate": 7.450110864745011e-05,
      "loss": 0.893,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.5306404232978821,
      "learning_rate": 7.405764966740577e-05,
      "loss": 0.8555,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.42399412393569946,
      "learning_rate": 7.361419068736141e-05,
      "loss": 0.7863,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.5433387160301208,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.8765,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.49213698506355286,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.7955,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.5636268854141235,
      "learning_rate": 7.228381374722837e-05,
      "loss": 0.734,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.593161404132843,
      "learning_rate": 7.184035476718403e-05,
      "loss": 0.8935,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.5714583396911621,
      "learning_rate": 7.139689578713969e-05,
      "loss": 0.8479,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.5962339639663696,
      "learning_rate": 7.095343680709535e-05,
      "loss": 0.9025,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.4530405104160309,
      "learning_rate": 7.0509977827051e-05,
      "loss": 0.8319,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.5993704795837402,
      "learning_rate": 7.006651884700666e-05,
      "loss": 0.8184,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.5871928334236145,
      "learning_rate": 6.962305986696232e-05,
      "loss": 0.7105,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.6520583033561707,
      "learning_rate": 6.917960088691796e-05,
      "loss": 0.6998,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.5593491792678833,
      "learning_rate": 6.873614190687362e-05,
      "loss": 0.9902,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.6667995452880859,
      "learning_rate": 6.829268292682928e-05,
      "loss": 0.9119,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7744415402412415,
      "learning_rate": 6.784922394678492e-05,
      "loss": 1.0563,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.5271946787834167,
      "learning_rate": 6.740576496674058e-05,
      "loss": 0.6821,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.4657348692417145,
      "learning_rate": 6.696230598669624e-05,
      "loss": 0.7078,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.5532839894294739,
      "learning_rate": 6.651884700665188e-05,
      "loss": 0.9029,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.5572279095649719,
      "learning_rate": 6.607538802660754e-05,
      "loss": 0.6561,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.5306766033172607,
      "learning_rate": 6.56319290465632e-05,
      "loss": 0.814,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.6224051713943481,
      "learning_rate": 6.518847006651884e-05,
      "loss": 0.8239,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.5042083859443665,
      "learning_rate": 6.47450110864745e-05,
      "loss": 0.6035,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.4926060140132904,
      "learning_rate": 6.430155210643016e-05,
      "loss": 0.8085,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.4982396066188812,
      "learning_rate": 6.38580931263858e-05,
      "loss": 0.6385,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.5828055739402771,
      "learning_rate": 6.341463414634146e-05,
      "loss": 0.7955,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.5451907515525818,
      "learning_rate": 6.297117516629712e-05,
      "loss": 0.6795,
      "step": 315
    },
    {
      "epoch": 2.0791208791208793,
      "grad_norm": 0.6262648701667786,
      "learning_rate": 6.252771618625277e-05,
      "loss": 0.7155,
      "step": 316
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.5633311867713928,
      "learning_rate": 6.208425720620842e-05,
      "loss": 0.5825,
      "step": 317
    },
    {
      "epoch": 2.0923076923076924,
      "grad_norm": 0.7124677896499634,
      "learning_rate": 6.164079822616408e-05,
      "loss": 0.6798,
      "step": 318
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.5539960861206055,
      "learning_rate": 6.119733924611974e-05,
      "loss": 0.7498,
      "step": 319
    },
    {
      "epoch": 2.1054945054945056,
      "grad_norm": 0.6102056503295898,
      "learning_rate": 6.075388026607539e-05,
      "loss": 0.7747,
      "step": 320
    },
    {
      "epoch": 2.112087912087912,
      "grad_norm": 0.556080162525177,
      "learning_rate": 6.031042128603105e-05,
      "loss": 0.8299,
      "step": 321
    },
    {
      "epoch": 2.1186813186813187,
      "grad_norm": 0.5393229126930237,
      "learning_rate": 5.98669623059867e-05,
      "loss": 0.7723,
      "step": 322
    },
    {
      "epoch": 2.1252747252747253,
      "grad_norm": 0.6829695701599121,
      "learning_rate": 5.942350332594236e-05,
      "loss": 0.7062,
      "step": 323
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.6692259907722473,
      "learning_rate": 5.898004434589801e-05,
      "loss": 0.7688,
      "step": 324
    },
    {
      "epoch": 2.1384615384615384,
      "grad_norm": 0.6317521333694458,
      "learning_rate": 5.853658536585366e-05,
      "loss": 0.6287,
      "step": 325
    },
    {
      "epoch": 2.145054945054945,
      "grad_norm": 0.549068033695221,
      "learning_rate": 5.809312638580932e-05,
      "loss": 0.9385,
      "step": 326
    },
    {
      "epoch": 2.1516483516483516,
      "grad_norm": 0.6179473400115967,
      "learning_rate": 5.7649667405764975e-05,
      "loss": 0.6953,
      "step": 327
    },
    {
      "epoch": 2.158241758241758,
      "grad_norm": 0.7025701403617859,
      "learning_rate": 5.720620842572062e-05,
      "loss": 0.7022,
      "step": 328
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 0.6069876551628113,
      "learning_rate": 5.676274944567628e-05,
      "loss": 0.7019,
      "step": 329
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.6731175780296326,
      "learning_rate": 5.6319290465631935e-05,
      "loss": 0.6305,
      "step": 330
    },
    {
      "epoch": 2.178021978021978,
      "grad_norm": 0.6524785757064819,
      "learning_rate": 5.587583148558758e-05,
      "loss": 0.6279,
      "step": 331
    },
    {
      "epoch": 2.184615384615385,
      "grad_norm": 0.6665555238723755,
      "learning_rate": 5.543237250554324e-05,
      "loss": 0.7597,
      "step": 332
    },
    {
      "epoch": 2.1912087912087914,
      "grad_norm": 0.6152045130729675,
      "learning_rate": 5.4988913525498895e-05,
      "loss": 0.7998,
      "step": 333
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.6133410334587097,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.6094,
      "step": 334
    },
    {
      "epoch": 2.2043956043956046,
      "grad_norm": 0.6700759530067444,
      "learning_rate": 5.4101995565410204e-05,
      "loss": 0.592,
      "step": 335
    },
    {
      "epoch": 2.210989010989011,
      "grad_norm": 0.6468697190284729,
      "learning_rate": 5.365853658536586e-05,
      "loss": 0.6456,
      "step": 336
    },
    {
      "epoch": 2.2175824175824177,
      "grad_norm": 0.6270462274551392,
      "learning_rate": 5.3215077605321506e-05,
      "loss": 0.5772,
      "step": 337
    },
    {
      "epoch": 2.2241758241758243,
      "grad_norm": 0.728397786617279,
      "learning_rate": 5.2771618625277164e-05,
      "loss": 0.7453,
      "step": 338
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.5902977585792542,
      "learning_rate": 5.232815964523282e-05,
      "loss": 0.5289,
      "step": 339
    },
    {
      "epoch": 2.2373626373626374,
      "grad_norm": 0.6009433269500732,
      "learning_rate": 5.1884700665188466e-05,
      "loss": 0.7279,
      "step": 340
    },
    {
      "epoch": 2.243956043956044,
      "grad_norm": 0.612016499042511,
      "learning_rate": 5.1441241685144124e-05,
      "loss": 0.7611,
      "step": 341
    },
    {
      "epoch": 2.2505494505494505,
      "grad_norm": 0.6445833444595337,
      "learning_rate": 5.099778270509978e-05,
      "loss": 0.654,
      "step": 342
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 0.6202147603034973,
      "learning_rate": 5.0554323725055433e-05,
      "loss": 0.6461,
      "step": 343
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 0.6622617840766907,
      "learning_rate": 5.011086474501109e-05,
      "loss": 0.6796,
      "step": 344
    },
    {
      "epoch": 2.2703296703296703,
      "grad_norm": 0.7441677451133728,
      "learning_rate": 4.966740576496674e-05,
      "loss": 0.9157,
      "step": 345
    },
    {
      "epoch": 2.276923076923077,
      "grad_norm": 0.6095447540283203,
      "learning_rate": 4.92239467849224e-05,
      "loss": 0.6173,
      "step": 346
    },
    {
      "epoch": 2.2835164835164834,
      "grad_norm": 0.5934126377105713,
      "learning_rate": 4.878048780487805e-05,
      "loss": 0.5257,
      "step": 347
    },
    {
      "epoch": 2.29010989010989,
      "grad_norm": 0.6706028580665588,
      "learning_rate": 4.833702882483371e-05,
      "loss": 0.7482,
      "step": 348
    },
    {
      "epoch": 2.2967032967032965,
      "grad_norm": 0.5668266415596008,
      "learning_rate": 4.789356984478936e-05,
      "loss": 0.8187,
      "step": 349
    },
    {
      "epoch": 2.303296703296703,
      "grad_norm": 0.6261492967605591,
      "learning_rate": 4.745011086474501e-05,
      "loss": 0.6418,
      "step": 350
    },
    {
      "epoch": 2.3098901098901097,
      "grad_norm": 0.5984154939651489,
      "learning_rate": 4.700665188470067e-05,
      "loss": 0.5466,
      "step": 351
    },
    {
      "epoch": 2.3164835164835162,
      "grad_norm": 0.5237962603569031,
      "learning_rate": 4.656319290465632e-05,
      "loss": 0.8473,
      "step": 352
    },
    {
      "epoch": 2.3230769230769233,
      "grad_norm": 0.6905950903892517,
      "learning_rate": 4.611973392461197e-05,
      "loss": 0.7192,
      "step": 353
    },
    {
      "epoch": 2.32967032967033,
      "grad_norm": 0.5511868000030518,
      "learning_rate": 4.567627494456763e-05,
      "loss": 0.5465,
      "step": 354
    },
    {
      "epoch": 2.3362637362637364,
      "grad_norm": 0.6822977066040039,
      "learning_rate": 4.523281596452328e-05,
      "loss": 0.7271,
      "step": 355
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 0.709517240524292,
      "learning_rate": 4.478935698447894e-05,
      "loss": 1.0472,
      "step": 356
    },
    {
      "epoch": 2.3494505494505495,
      "grad_norm": 0.5151809453964233,
      "learning_rate": 4.4345898004434597e-05,
      "loss": 0.6928,
      "step": 357
    },
    {
      "epoch": 2.356043956043956,
      "grad_norm": 0.6557967662811279,
      "learning_rate": 4.390243902439025e-05,
      "loss": 0.6978,
      "step": 358
    },
    {
      "epoch": 2.3626373626373627,
      "grad_norm": 0.5282977223396301,
      "learning_rate": 4.34589800443459e-05,
      "loss": 0.4567,
      "step": 359
    },
    {
      "epoch": 2.3692307692307693,
      "grad_norm": 0.8173336982727051,
      "learning_rate": 4.301552106430156e-05,
      "loss": 0.8292,
      "step": 360
    }
  ],
  "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": 5.884018092952781e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}