{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.764835164835165,
  "eval_steps": 500,
  "global_step": 420,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 5.459638595581055,
      "learning_rate": 0.0,
      "loss": 5.1572,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 4.408932209014893,
      "learning_rate": 4e-05,
      "loss": 4.941,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 5.487926959991455,
      "learning_rate": 8e-05,
      "loss": 5.5698,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 5.361940860748291,
      "learning_rate": 0.00012,
      "loss": 5.4254,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 5.856925010681152,
      "learning_rate": 0.00016,
      "loss": 4.9638,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 6.2031073570251465,
      "learning_rate": 0.0002,
      "loss": 4.1384,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 6.153454780578613,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.5665,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 2.060917615890503,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.335,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.5414468050003052,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2202,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 2.760967493057251,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.3177,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.4582066535949707,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.1973,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.800369918346405,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.1367,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.8436974287033081,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.2465,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.9210023283958435,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.0176,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.8066878318786621,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.9148,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.8594912886619568,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.0468,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.6237018704414368,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.0676,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.6330975294113159,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.9913,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.7443146705627441,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.8187,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.7366983890533447,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.1666,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.571020781993866,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.9126,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.6713335514068604,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.7393,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.5838486552238464,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.9377,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.6766859889030457,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.1663,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.6486108303070068,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.8836,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.6390822529792786,
      "learning_rate": 0.00019113082039911309,
      "loss": 1.0328,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.6051312685012817,
      "learning_rate": 0.00019068736141906876,
      "loss": 1.1173,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.539639949798584,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.8195,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.6244184970855713,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.9956,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.5312393307685852,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.9427,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.6213347911834717,
      "learning_rate": 0.00018891352549889136,
      "loss": 1.0347,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.5339341759681702,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.8984,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.5304893851280212,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.8964,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.6589417457580566,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.3518,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.6399314403533936,
      "learning_rate": 0.00018713968957871397,
      "loss": 1.1438,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.545724630355835,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.9772,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.5593492984771729,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.883,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.5673443078994751,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.9052,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.6377619504928589,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.9566,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.5556446313858032,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.8046,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.5751636624336243,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.9647,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.8823965191841125,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.914,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.4730704128742218,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.8514,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.527775764465332,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.8588,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 1.2125602960586548,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.9817,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.46695390343666077,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.7875,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.45550069212913513,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.7247,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.5238901972770691,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.788,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.5668091773986816,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.8173,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.5564643740653992,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.9231,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.4617767035961151,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.8297,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.47752270102500916,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.7544,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.535720705986023,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.9407,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.47505563497543335,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.8374,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.6126910448074341,
      "learning_rate": 0.00017827050997782707,
      "loss": 1.0878,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.5779691934585571,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.0181,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.5656658411026001,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.8647,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.5828663110733032,
      "learning_rate": 0.000176940133037694,
      "loss": 0.7128,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.5121160745620728,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.9738,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.621181309223175,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.808,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.5183335542678833,
      "learning_rate": 0.000175609756097561,
      "loss": 0.8703,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.6565868258476257,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.9312,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.6722279191017151,
      "learning_rate": 0.0001747228381374723,
      "loss": 1.0824,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.6071406006813049,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.891,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.513313889503479,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.742,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.5047631859779358,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.9423,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.5646599531173706,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.8566,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.5328014492988586,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.8397,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.6697370409965515,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.9044,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.7905986309051514,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.9489,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.5284698605537415,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.7049,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.5368447303771973,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.8274,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.5713925361633301,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.6653,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.5431435108184814,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.9738,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.5508645176887512,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.7946,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.5687035918235779,
      "learning_rate": 0.00016895787139689582,
      "loss": 1.1262,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.499746710062027,
      "learning_rate": 0.00016851441241685144,
      "loss": 1.0047,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.59474116563797,
      "learning_rate": 0.0001680709534368071,
      "loss": 1.1529,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.6204425096511841,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.8883,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.5115718245506287,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.8317,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.5380851030349731,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.9325,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.5884971618652344,
      "learning_rate": 0.00016629711751662974,
      "loss": 1.0196,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.6122893691062927,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.787,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.5914639830589294,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.928,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.6377210021018982,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.953,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.5960861444473267,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.8375,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.5654808282852173,
      "learning_rate": 0.000164079822616408,
      "loss": 0.7931,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.6073900461196899,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.0419,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.5416488647460938,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.8963,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.48589223623275757,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.8119,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.5589356422424316,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.9856,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.5352998375892639,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.7669,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.6389907002449036,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.7909,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.7931464314460754,
      "learning_rate": 0.00016097560975609758,
      "loss": 1.1146,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.6886119246482849,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.8083,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.5980899333953857,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.8838,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.6072768568992615,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.9462,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.5868003964424133,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.8632,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.7429962158203125,
      "learning_rate": 0.00015875831485587586,
      "loss": 1.1878,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.49301764369010925,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.86,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.4976905584335327,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.9493,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.5512967705726624,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.9698,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.5553017258644104,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.9741,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.5939576625823975,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.8432,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.576961100101471,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.7377,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.6039689779281616,
      "learning_rate": 0.00015565410199556542,
      "loss": 1.1159,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.650936484336853,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.8777,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.5367209315299988,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.9016,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.5427932143211365,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.7885,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.5590482950210571,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.831,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.6897863745689392,
      "learning_rate": 0.0001534368070953437,
      "loss": 1.0135,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.5914762020111084,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.881,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.8431822061538696,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.8999,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.5025018453598022,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.771,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.6190459728240967,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.8828,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.5529432892799377,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.7698,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.5121442675590515,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.8353,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.5955220460891724,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.6533,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.59442538022995,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.7851,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.5546603798866272,
      "learning_rate": 0.00014944567627494458,
      "loss": 1.1005,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.5451670289039612,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.7612,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.5197620391845703,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.837,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.5600094199180603,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.8021,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.6268289685249329,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.8966,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.5550496578216553,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.8343,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.6128094792366028,
      "learning_rate": 0.0001467849223946785,
      "loss": 1.1045,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.5269573926925659,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.7257,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.6352261304855347,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.7755,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.5489485263824463,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.7397,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.5395745038986206,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.7006,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.567113995552063,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.7323,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.5484573841094971,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.7767,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.5116643309593201,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.8164,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.5965120196342468,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.9261,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.619005560874939,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.8345,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.6372644305229187,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.8322,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.5704457759857178,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.7773,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.6067429184913635,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.9886,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.5782042145729065,
      "learning_rate": 0.000141019955654102,
      "loss": 0.8481,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.5294620990753174,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.8596,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.5170754194259644,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.8392,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.6627360582351685,
      "learning_rate": 0.00013968957871396897,
      "loss": 1.0295,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.5979954600334167,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.8471,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.5813125371932983,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.8533,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.6231347918510437,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.8619,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.5202571749687195,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.6541,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.5599802732467651,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.7213,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.5238470435142517,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.7997,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.6066797971725464,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.7616,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.5322993993759155,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.9426,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.5406814813613892,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.9232,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6926743984222412,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.7743,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.6528266668319702,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.8807,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.5777136087417603,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.749,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.5486526489257812,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.8516,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.5391802787780762,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.7205,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.5297644734382629,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.6941,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.5092700123786926,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.5409,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.5707080364227295,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.6905,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.606627881526947,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.7107,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.5382817387580872,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.7526,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.558792769908905,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.7253,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.5459743142127991,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.6518,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.5695344805717468,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.6852,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.6128743886947632,
      "learning_rate": 0.000129490022172949,
      "loss": 0.6762,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.6627138257026672,
      "learning_rate": 0.00012904656319290468,
      "loss": 1.0677,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.7332176566123962,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.8847,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.5791655778884888,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.746,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.6921065449714661,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.6869,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.5876157879829407,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.6389,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.6788483262062073,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.6412,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.5909616947174072,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.6374,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.6279222369194031,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.7105,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.5922663807868958,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.7109,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.7478090524673462,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.677,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.5965471863746643,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.7968,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.6833251714706421,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.8221,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.6009984016418457,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.5564,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.7059131264686584,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.9398,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.6330722570419312,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.6585,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.754753053188324,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.7682,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.6728742122650146,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.7416,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.646062970161438,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.7183,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.6689327955245972,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.7409,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.6284791231155396,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.7137,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.6613520383834839,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.7389,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.855766773223877,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.8416,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.7242646217346191,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.6823,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.7441504597663879,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.7099,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.6454845070838928,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.627,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.6478668451309204,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.5941,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.7972174882888794,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.7645,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.8269811868667603,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.7868,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.7218356728553772,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.6267,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.585889458656311,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.4764,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.7548837065696716,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.7732,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.7082198262214661,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.7557,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.8400455713272095,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.7135,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.6694929599761963,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.5674,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.8161136507987976,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.818,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.742396891117096,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.6762,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.779309868812561,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.964,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.6914857029914856,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.5703,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.6019184589385986,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.5698,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.7562709450721741,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.7521,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.8199368119239807,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.7424,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.6822022795677185,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.5055,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.8027207851409912,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.8313,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.7092612385749817,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.643,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.7525438070297241,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.7973,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 1.0159446001052856,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.8284,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.8263998627662659,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.7491,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.769382894039154,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.7362,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.7658213376998901,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.8199,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.7609794735908508,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.7025,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.7956355810165405,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.6499,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.8957807421684265,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.736,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.8372054696083069,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.6374,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.8443581461906433,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.6742,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.7275757789611816,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.5316,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.8710049986839294,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.7603,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.8214333057403564,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.8326,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.8082292079925537,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.7703,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.8103289008140564,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.7311,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.852648138999939,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.8244,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.8637315630912781,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.8219,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.7717117667198181,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.5702,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.7740812301635742,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.5709,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.9017543792724609,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.8741,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.7725918889045715,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.6267,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.7425467371940613,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.6667,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.9202691912651062,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.6306,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.8152969479560852,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.7289,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.8297674059867859,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.5967,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.8030088543891907,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.7101,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.7593726515769958,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.5981,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.8092892169952393,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.6515,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.8555645942687988,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.6816,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.8448258638381958,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.4817,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.8899918794631958,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.786,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.8702341914176941,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.6234,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.8521184325218201,
      "learning_rate": 9.534368070953438e-05,
      "loss": 0.6938,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.0372881889343262,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.746,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 1.0582796335220337,
      "learning_rate": 9.445676274944568e-05,
      "loss": 0.6569,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.9429578185081482,
      "learning_rate": 9.401330376940134e-05,
      "loss": 0.6382,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.8401104807853699,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.6009,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.8209211230278015,
      "learning_rate": 9.312638580931264e-05,
      "loss": 0.6816,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.8829045295715332,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.6105,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.9745340943336487,
      "learning_rate": 9.223946784922394e-05,
      "loss": 0.8103,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.8930656909942627,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.6681,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 1.0974589586257935,
      "learning_rate": 9.135254988913526e-05,
      "loss": 0.7878,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.9503677487373352,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.9269,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.8988383412361145,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.7827,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.8854551315307617,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.5983,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.9577869176864624,
      "learning_rate": 8.957871396895788e-05,
      "loss": 0.8595,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.8902473449707031,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.6507,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 1.065733790397644,
      "learning_rate": 8.869179600886919e-05,
      "loss": 0.7652,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.8974253535270691,
      "learning_rate": 8.824833702882484e-05,
      "loss": 0.7027,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.8265765905380249,
      "learning_rate": 8.78048780487805e-05,
      "loss": 0.5939,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.8332666158676147,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.6514,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.9671381711959839,
      "learning_rate": 8.69179600886918e-05,
      "loss": 0.6413,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.8843182325363159,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.6672,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.8019580841064453,
      "learning_rate": 8.603104212860311e-05,
      "loss": 0.7517,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.8459179401397705,
      "learning_rate": 8.558758314855876e-05,
      "loss": 0.6757,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.7577002644538879,
      "learning_rate": 8.514412416851442e-05,
      "loss": 0.593,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.822655200958252,
      "learning_rate": 8.470066518847007e-05,
      "loss": 0.6908,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 1.0421106815338135,
      "learning_rate": 8.425720620842572e-05,
      "loss": 0.7953,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.7431073188781738,
      "learning_rate": 8.381374722838138e-05,
      "loss": 0.5356,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.8398526906967163,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.716,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.9277116656303406,
      "learning_rate": 8.292682926829268e-05,
      "loss": 0.7265,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.7903785109519958,
      "learning_rate": 8.248337028824834e-05,
      "loss": 0.4978,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.8861078023910522,
      "learning_rate": 8.2039911308204e-05,
      "loss": 0.6493,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.9308344721794128,
      "learning_rate": 8.159645232815965e-05,
      "loss": 0.6134,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.8835091590881348,
      "learning_rate": 8.11529933481153e-05,
      "loss": 0.68,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.8292971253395081,
      "learning_rate": 8.070953436807095e-05,
      "loss": 0.7716,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.9011790752410889,
      "learning_rate": 8.026607538802661e-05,
      "loss": 0.7068,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 1.0252760648727417,
      "learning_rate": 7.982261640798227e-05,
      "loss": 0.7312,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.9704046845436096,
      "learning_rate": 7.937915742793793e-05,
      "loss": 0.5726,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.9528927803039551,
      "learning_rate": 7.893569844789357e-05,
      "loss": 0.7069,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.9962840676307678,
      "learning_rate": 7.849223946784923e-05,
      "loss": 0.6893,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 1.1115580797195435,
      "learning_rate": 7.804878048780489e-05,
      "loss": 0.8623,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.9611544013023376,
      "learning_rate": 7.760532150776053e-05,
      "loss": 0.6206,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.9705760478973389,
      "learning_rate": 7.716186252771619e-05,
      "loss": 0.8395,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.9322996139526367,
      "learning_rate": 7.671840354767185e-05,
      "loss": 0.7347,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.9395545721054077,
      "learning_rate": 7.627494456762749e-05,
      "loss": 0.5986,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.8874136805534363,
      "learning_rate": 7.583148558758315e-05,
      "loss": 0.6516,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.9556251168251038,
      "learning_rate": 7.538802660753881e-05,
      "loss": 0.6359,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 1.0586069822311401,
      "learning_rate": 7.494456762749445e-05,
      "loss": 0.661,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 1.0538480281829834,
      "learning_rate": 7.450110864745011e-05,
      "loss": 0.9867,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.9686607718467712,
      "learning_rate": 7.405764966740577e-05,
      "loss": 0.6205,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 1.0474941730499268,
      "learning_rate": 7.361419068736141e-05,
      "loss": 0.6991,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.9035308361053467,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.6355,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.9009690880775452,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.6596,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.9220340251922607,
      "learning_rate": 7.228381374722837e-05,
      "loss": 0.5769,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 1.2096954584121704,
      "learning_rate": 7.184035476718403e-05,
      "loss": 0.6472,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 1.0383412837982178,
      "learning_rate": 7.139689578713969e-05,
      "loss": 0.8429,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 1.0365651845932007,
      "learning_rate": 7.095343680709535e-05,
      "loss": 0.7559,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.9036271572113037,
      "learning_rate": 7.0509977827051e-05,
      "loss": 0.8031,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.9713782668113708,
      "learning_rate": 7.006651884700666e-05,
      "loss": 0.7141,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 1.0330990552902222,
      "learning_rate": 6.962305986696232e-05,
      "loss": 0.7031,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 1.1108256578445435,
      "learning_rate": 6.917960088691796e-05,
      "loss": 0.7687,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.9213413596153259,
      "learning_rate": 6.873614190687362e-05,
      "loss": 0.673,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.8675325512886047,
      "learning_rate": 6.829268292682928e-05,
      "loss": 0.5652,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3265252113342285,
      "learning_rate": 6.784922394678492e-05,
      "loss": 0.7176,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.7013648748397827,
      "learning_rate": 6.740576496674058e-05,
      "loss": 0.4275,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.7365581393241882,
      "learning_rate": 6.696230598669624e-05,
      "loss": 0.5457,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.7674388885498047,
      "learning_rate": 6.651884700665188e-05,
      "loss": 0.3907,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.8511399030685425,
      "learning_rate": 6.607538802660754e-05,
      "loss": 0.647,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.9699122905731201,
      "learning_rate": 6.56319290465632e-05,
      "loss": 0.4183,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.8858424425125122,
      "learning_rate": 6.518847006651884e-05,
      "loss": 0.5119,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.8715095520019531,
      "learning_rate": 6.47450110864745e-05,
      "loss": 0.5206,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.8098522424697876,
      "learning_rate": 6.430155210643016e-05,
      "loss": 0.4741,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.8343369364738464,
      "learning_rate": 6.38580931263858e-05,
      "loss": 0.5165,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.9550448656082153,
      "learning_rate": 6.341463414634146e-05,
      "loss": 0.6236,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.9624354243278503,
      "learning_rate": 6.297117516629712e-05,
      "loss": 0.4922,
      "step": 315
    },
    {
      "epoch": 2.0791208791208793,
      "grad_norm": 0.8983634114265442,
      "learning_rate": 6.252771618625277e-05,
      "loss": 0.4947,
      "step": 316
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.9442097544670105,
      "learning_rate": 6.208425720620842e-05,
      "loss": 0.4931,
      "step": 317
    },
    {
      "epoch": 2.0923076923076924,
      "grad_norm": 0.9355817437171936,
      "learning_rate": 6.164079822616408e-05,
      "loss": 0.5792,
      "step": 318
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.8248960971832275,
      "learning_rate": 6.119733924611974e-05,
      "loss": 0.4732,
      "step": 319
    },
    {
      "epoch": 2.1054945054945056,
      "grad_norm": 0.880276620388031,
      "learning_rate": 6.075388026607539e-05,
      "loss": 0.4319,
      "step": 320
    },
    {
      "epoch": 2.112087912087912,
      "grad_norm": 0.9394314885139465,
      "learning_rate": 6.031042128603105e-05,
      "loss": 0.5381,
      "step": 321
    },
    {
      "epoch": 2.1186813186813187,
      "grad_norm": 0.9725684523582458,
      "learning_rate": 5.98669623059867e-05,
      "loss": 0.5354,
      "step": 322
    },
    {
      "epoch": 2.1252747252747253,
      "grad_norm": 1.1816222667694092,
      "learning_rate": 5.942350332594236e-05,
      "loss": 0.7806,
      "step": 323
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.9629228115081787,
      "learning_rate": 5.898004434589801e-05,
      "loss": 0.4421,
      "step": 324
    },
    {
      "epoch": 2.1384615384615384,
      "grad_norm": 1.012334942817688,
      "learning_rate": 5.853658536585366e-05,
      "loss": 0.6238,
      "step": 325
    },
    {
      "epoch": 2.145054945054945,
      "grad_norm": 1.0071128606796265,
      "learning_rate": 5.809312638580932e-05,
      "loss": 0.5277,
      "step": 326
    },
    {
      "epoch": 2.1516483516483516,
      "grad_norm": 0.9645769596099854,
      "learning_rate": 5.7649667405764975e-05,
      "loss": 0.3975,
      "step": 327
    },
    {
      "epoch": 2.158241758241758,
      "grad_norm": 0.990266740322113,
      "learning_rate": 5.720620842572062e-05,
      "loss": 0.5537,
      "step": 328
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 1.1952433586120605,
      "learning_rate": 5.676274944567628e-05,
      "loss": 0.5922,
      "step": 329
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.9839120507240295,
      "learning_rate": 5.6319290465631935e-05,
      "loss": 0.4744,
      "step": 330
    },
    {
      "epoch": 2.178021978021978,
      "grad_norm": 1.1202560663223267,
      "learning_rate": 5.587583148558758e-05,
      "loss": 0.6021,
      "step": 331
    },
    {
      "epoch": 2.184615384615385,
      "grad_norm": 1.017528772354126,
      "learning_rate": 5.543237250554324e-05,
      "loss": 0.4286,
      "step": 332
    },
    {
      "epoch": 2.1912087912087914,
      "grad_norm": 1.167262315750122,
      "learning_rate": 5.4988913525498895e-05,
      "loss": 0.605,
      "step": 333
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.9748615026473999,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.4101,
      "step": 334
    },
    {
      "epoch": 2.2043956043956046,
      "grad_norm": 0.9268114566802979,
      "learning_rate": 5.4101995565410204e-05,
      "loss": 0.4115,
      "step": 335
    },
    {
      "epoch": 2.210989010989011,
      "grad_norm": 1.0468456745147705,
      "learning_rate": 5.365853658536586e-05,
      "loss": 0.4421,
      "step": 336
    },
    {
      "epoch": 2.2175824175824177,
      "grad_norm": 1.1049137115478516,
      "learning_rate": 5.3215077605321506e-05,
      "loss": 0.6606,
      "step": 337
    },
    {
      "epoch": 2.2241758241758243,
      "grad_norm": 1.1637773513793945,
      "learning_rate": 5.2771618625277164e-05,
      "loss": 0.4775,
      "step": 338
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 1.1783384084701538,
      "learning_rate": 5.232815964523282e-05,
      "loss": 0.722,
      "step": 339
    },
    {
      "epoch": 2.2373626373626374,
      "grad_norm": 1.0153567790985107,
      "learning_rate": 5.1884700665188466e-05,
      "loss": 0.331,
      "step": 340
    },
    {
      "epoch": 2.243956043956044,
      "grad_norm": 0.9955103397369385,
      "learning_rate": 5.1441241685144124e-05,
      "loss": 0.39,
      "step": 341
    },
    {
      "epoch": 2.2505494505494505,
      "grad_norm": 1.1367878913879395,
      "learning_rate": 5.099778270509978e-05,
      "loss": 0.4492,
      "step": 342
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 1.0891565084457397,
      "learning_rate": 5.0554323725055433e-05,
      "loss": 0.5591,
      "step": 343
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 1.0645451545715332,
      "learning_rate": 5.011086474501109e-05,
      "loss": 0.4606,
      "step": 344
    },
    {
      "epoch": 2.2703296703296703,
      "grad_norm": 1.0706084966659546,
      "learning_rate": 4.966740576496674e-05,
      "loss": 0.578,
      "step": 345
    },
    {
      "epoch": 2.276923076923077,
      "grad_norm": 1.4060033559799194,
      "learning_rate": 4.92239467849224e-05,
      "loss": 0.665,
      "step": 346
    },
    {
      "epoch": 2.2835164835164834,
      "grad_norm": 1.0793073177337646,
      "learning_rate": 4.878048780487805e-05,
      "loss": 0.4808,
      "step": 347
    },
    {
      "epoch": 2.29010989010989,
      "grad_norm": 1.1167839765548706,
      "learning_rate": 4.833702882483371e-05,
      "loss": 0.406,
      "step": 348
    },
    {
      "epoch": 2.2967032967032965,
      "grad_norm": 1.1641631126403809,
      "learning_rate": 4.789356984478936e-05,
      "loss": 0.5406,
      "step": 349
    },
    {
      "epoch": 2.303296703296703,
      "grad_norm": 1.3084074258804321,
      "learning_rate": 4.745011086474501e-05,
      "loss": 0.5515,
      "step": 350
    },
    {
      "epoch": 2.3098901098901097,
      "grad_norm": 1.0858845710754395,
      "learning_rate": 4.700665188470067e-05,
      "loss": 0.4278,
      "step": 351
    },
    {
      "epoch": 2.3164835164835162,
      "grad_norm": 1.1119556427001953,
      "learning_rate": 4.656319290465632e-05,
      "loss": 0.3731,
      "step": 352
    },
    {
      "epoch": 2.3230769230769233,
      "grad_norm": 1.2518242597579956,
      "learning_rate": 4.611973392461197e-05,
      "loss": 0.5989,
      "step": 353
    },
    {
      "epoch": 2.32967032967033,
      "grad_norm": 1.1492260694503784,
      "learning_rate": 4.567627494456763e-05,
      "loss": 0.5067,
      "step": 354
    },
    {
      "epoch": 2.3362637362637364,
      "grad_norm": 1.073535442352295,
      "learning_rate": 4.523281596452328e-05,
      "loss": 0.3709,
      "step": 355
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 1.0503990650177002,
      "learning_rate": 4.478935698447894e-05,
      "loss": 0.4163,
      "step": 356
    },
    {
      "epoch": 2.3494505494505495,
      "grad_norm": 1.1108131408691406,
      "learning_rate": 4.4345898004434597e-05,
      "loss": 0.4148,
      "step": 357
    },
    {
      "epoch": 2.356043956043956,
      "grad_norm": 1.2125322818756104,
      "learning_rate": 4.390243902439025e-05,
      "loss": 0.5726,
      "step": 358
    },
    {
      "epoch": 2.3626373626373627,
      "grad_norm": 1.170358657836914,
      "learning_rate": 4.34589800443459e-05,
      "loss": 0.4314,
      "step": 359
    },
    {
      "epoch": 2.3692307692307693,
      "grad_norm": 1.1968660354614258,
      "learning_rate": 4.301552106430156e-05,
      "loss": 0.4125,
      "step": 360
    },
    {
      "epoch": 2.375824175824176,
      "grad_norm": 1.2067203521728516,
      "learning_rate": 4.257206208425721e-05,
      "loss": 0.6275,
      "step": 361
    },
    {
      "epoch": 2.3824175824175824,
      "grad_norm": 1.3774431943893433,
      "learning_rate": 4.212860310421286e-05,
      "loss": 0.6278,
      "step": 362
    },
    {
      "epoch": 2.389010989010989,
      "grad_norm": 1.3856054544448853,
      "learning_rate": 4.168514412416852e-05,
      "loss": 0.5777,
      "step": 363
    },
    {
      "epoch": 2.3956043956043955,
      "grad_norm": 1.2358636856079102,
      "learning_rate": 4.124168514412417e-05,
      "loss": 0.5083,
      "step": 364
    },
    {
      "epoch": 2.402197802197802,
      "grad_norm": 1.1643177270889282,
      "learning_rate": 4.0798226164079826e-05,
      "loss": 0.3712,
      "step": 365
    },
    {
      "epoch": 2.4087912087912087,
      "grad_norm": 1.186922550201416,
      "learning_rate": 4.035476718403548e-05,
      "loss": 0.4798,
      "step": 366
    },
    {
      "epoch": 2.4153846153846152,
      "grad_norm": 1.1686656475067139,
      "learning_rate": 3.9911308203991135e-05,
      "loss": 0.4015,
      "step": 367
    },
    {
      "epoch": 2.421978021978022,
      "grad_norm": 1.2546952962875366,
      "learning_rate": 3.9467849223946786e-05,
      "loss": 0.3787,
      "step": 368
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 1.0189659595489502,
      "learning_rate": 3.9024390243902444e-05,
      "loss": 0.3936,
      "step": 369
    },
    {
      "epoch": 2.4351648351648354,
      "grad_norm": 1.2587424516677856,
      "learning_rate": 3.8580931263858095e-05,
      "loss": 0.4116,
      "step": 370
    },
    {
      "epoch": 2.441758241758242,
      "grad_norm": 1.1861242055892944,
      "learning_rate": 3.8137472283813746e-05,
      "loss": 0.4552,
      "step": 371
    },
    {
      "epoch": 2.4483516483516485,
      "grad_norm": 1.3117057085037231,
      "learning_rate": 3.7694013303769404e-05,
      "loss": 0.4947,
      "step": 372
    },
    {
      "epoch": 2.454945054945055,
      "grad_norm": 1.2183837890625,
      "learning_rate": 3.7250554323725055e-05,
      "loss": 0.515,
      "step": 373
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 1.0376622676849365,
      "learning_rate": 3.6807095343680706e-05,
      "loss": 0.3311,
      "step": 374
    },
    {
      "epoch": 2.4681318681318682,
      "grad_norm": 1.1530171632766724,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.4543,
      "step": 375
    },
    {
      "epoch": 2.474725274725275,
      "grad_norm": 1.1159075498580933,
      "learning_rate": 3.5920177383592015e-05,
      "loss": 0.4161,
      "step": 376
    },
    {
      "epoch": 2.4813186813186814,
      "grad_norm": 1.0483793020248413,
      "learning_rate": 3.547671840354767e-05,
      "loss": 0.3893,
      "step": 377
    },
    {
      "epoch": 2.487912087912088,
      "grad_norm": 1.1418009996414185,
      "learning_rate": 3.503325942350333e-05,
      "loss": 0.4197,
      "step": 378
    },
    {
      "epoch": 2.4945054945054945,
      "grad_norm": 1.148313045501709,
      "learning_rate": 3.458980044345898e-05,
      "loss": 0.459,
      "step": 379
    },
    {
      "epoch": 2.501098901098901,
      "grad_norm": 1.1676642894744873,
      "learning_rate": 3.414634146341464e-05,
      "loss": 0.5307,
      "step": 380
    },
    {
      "epoch": 2.5076923076923077,
      "grad_norm": 1.2005789279937744,
      "learning_rate": 3.370288248337029e-05,
      "loss": 0.5095,
      "step": 381
    },
    {
      "epoch": 2.5142857142857142,
      "grad_norm": 1.2387758493423462,
      "learning_rate": 3.325942350332594e-05,
      "loss": 0.5335,
      "step": 382
    },
    {
      "epoch": 2.520879120879121,
      "grad_norm": 1.0163699388504028,
      "learning_rate": 3.28159645232816e-05,
      "loss": 0.3154,
      "step": 383
    },
    {
      "epoch": 2.5274725274725274,
      "grad_norm": 1.137412667274475,
      "learning_rate": 3.237250554323725e-05,
      "loss": 0.5007,
      "step": 384
    },
    {
      "epoch": 2.534065934065934,
      "grad_norm": 1.3869373798370361,
      "learning_rate": 3.19290465631929e-05,
      "loss": 0.5978,
      "step": 385
    },
    {
      "epoch": 2.5406593406593405,
      "grad_norm": 1.3165379762649536,
      "learning_rate": 3.148558758314856e-05,
      "loss": 0.64,
      "step": 386
    },
    {
      "epoch": 2.547252747252747,
      "grad_norm": 1.1474852561950684,
      "learning_rate": 3.104212860310421e-05,
      "loss": 0.4118,
      "step": 387
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 1.257961630821228,
      "learning_rate": 3.059866962305987e-05,
      "loss": 0.4638,
      "step": 388
    },
    {
      "epoch": 2.5604395604395602,
      "grad_norm": 1.3257153034210205,
      "learning_rate": 3.0155210643015524e-05,
      "loss": 0.4878,
      "step": 389
    },
    {
      "epoch": 2.567032967032967,
      "grad_norm": 1.2379809617996216,
      "learning_rate": 2.971175166297118e-05,
      "loss": 0.3795,
      "step": 390
    },
    {
      "epoch": 2.5736263736263734,
      "grad_norm": 1.193955421447754,
      "learning_rate": 2.926829268292683e-05,
      "loss": 0.6152,
      "step": 391
    },
    {
      "epoch": 2.5802197802197804,
      "grad_norm": 1.389012336730957,
      "learning_rate": 2.8824833702882487e-05,
      "loss": 0.5685,
      "step": 392
    },
    {
      "epoch": 2.586813186813187,
      "grad_norm": 1.4353406429290771,
      "learning_rate": 2.838137472283814e-05,
      "loss": 0.6191,
      "step": 393
    },
    {
      "epoch": 2.5934065934065935,
      "grad_norm": 1.3055601119995117,
      "learning_rate": 2.793791574279379e-05,
      "loss": 0.454,
      "step": 394
    },
    {
      "epoch": 2.6,
      "grad_norm": 1.104642391204834,
      "learning_rate": 2.7494456762749448e-05,
      "loss": 0.4526,
      "step": 395
    },
    {
      "epoch": 2.6065934065934067,
      "grad_norm": 1.250524640083313,
      "learning_rate": 2.7050997782705102e-05,
      "loss": 0.4507,
      "step": 396
    },
    {
      "epoch": 2.6131868131868132,
      "grad_norm": 1.1721676588058472,
      "learning_rate": 2.6607538802660753e-05,
      "loss": 0.6279,
      "step": 397
    },
    {
      "epoch": 2.61978021978022,
      "grad_norm": 1.151241421699524,
      "learning_rate": 2.616407982261641e-05,
      "loss": 0.4111,
      "step": 398
    },
    {
      "epoch": 2.6263736263736264,
      "grad_norm": 1.2725980281829834,
      "learning_rate": 2.5720620842572062e-05,
      "loss": 0.4918,
      "step": 399
    },
    {
      "epoch": 2.632967032967033,
      "grad_norm": 1.1727885007858276,
      "learning_rate": 2.5277161862527717e-05,
      "loss": 0.3993,
      "step": 400
    },
    {
      "epoch": 2.6395604395604395,
      "grad_norm": 1.2473317384719849,
      "learning_rate": 2.483370288248337e-05,
      "loss": 0.6908,
      "step": 401
    },
    {
      "epoch": 2.646153846153846,
      "grad_norm": 1.2084693908691406,
      "learning_rate": 2.4390243902439026e-05,
      "loss": 0.4312,
      "step": 402
    },
    {
      "epoch": 2.6527472527472526,
      "grad_norm": 1.2712416648864746,
      "learning_rate": 2.394678492239468e-05,
      "loss": 0.5147,
      "step": 403
    },
    {
      "epoch": 2.659340659340659,
      "grad_norm": 1.304729700088501,
      "learning_rate": 2.3503325942350335e-05,
      "loss": 0.5742,
      "step": 404
    },
    {
      "epoch": 2.665934065934066,
      "grad_norm": 1.1358871459960938,
      "learning_rate": 2.3059866962305986e-05,
      "loss": 0.405,
      "step": 405
    },
    {
      "epoch": 2.672527472527473,
      "grad_norm": 1.4427748918533325,
      "learning_rate": 2.261640798226164e-05,
      "loss": 0.5304,
      "step": 406
    },
    {
      "epoch": 2.6791208791208794,
      "grad_norm": 1.356003761291504,
      "learning_rate": 2.2172949002217298e-05,
      "loss": 0.4849,
      "step": 407
    },
    {
      "epoch": 2.685714285714286,
      "grad_norm": 1.0818793773651123,
      "learning_rate": 2.172949002217295e-05,
      "loss": 0.3474,
      "step": 408
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 1.2190459966659546,
      "learning_rate": 2.1286031042128604e-05,
      "loss": 0.4004,
      "step": 409
    },
    {
      "epoch": 2.698901098901099,
      "grad_norm": 1.2626338005065918,
      "learning_rate": 2.084257206208426e-05,
      "loss": 0.5191,
      "step": 410
    },
    {
      "epoch": 2.7054945054945057,
      "grad_norm": 1.2770973443984985,
      "learning_rate": 2.0399113082039913e-05,
      "loss": 0.5452,
      "step": 411
    },
    {
      "epoch": 2.7120879120879122,
      "grad_norm": 1.1388674974441528,
      "learning_rate": 1.9955654101995567e-05,
      "loss": 0.3899,
      "step": 412
    },
    {
      "epoch": 2.718681318681319,
      "grad_norm": 1.2490386962890625,
      "learning_rate": 1.9512195121951222e-05,
      "loss": 0.5189,
      "step": 413
    },
    {
      "epoch": 2.7252747252747254,
      "grad_norm": 1.0870662927627563,
      "learning_rate": 1.9068736141906873e-05,
      "loss": 0.3899,
      "step": 414
    },
    {
      "epoch": 2.731868131868132,
      "grad_norm": 1.2912698984146118,
      "learning_rate": 1.8625277161862528e-05,
      "loss": 0.5787,
      "step": 415
    },
    {
      "epoch": 2.7384615384615385,
      "grad_norm": 1.2180625200271606,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.7846,
      "step": 416
    },
    {
      "epoch": 2.745054945054945,
      "grad_norm": 1.2585035562515259,
      "learning_rate": 1.7738359201773837e-05,
      "loss": 0.5965,
      "step": 417
    },
    {
      "epoch": 2.7516483516483516,
      "grad_norm": 1.2611061334609985,
      "learning_rate": 1.729490022172949e-05,
      "loss": 0.4222,
      "step": 418
    },
    {
      "epoch": 2.758241758241758,
      "grad_norm": 1.2865656614303589,
      "learning_rate": 1.6851441241685146e-05,
      "loss": 0.4435,
      "step": 419
    },
    {
      "epoch": 2.764835164835165,
      "grad_norm": 1.2082082033157349,
      "learning_rate": 1.64079822616408e-05,
      "loss": 0.538,
      "step": 420
    }
  ],
  "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": 4.371893909992243e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}