{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.8637362637362638,
  "eval_steps": 500,
  "global_step": 435,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.51781165599823,
      "learning_rate": 0.0,
      "loss": 2.6003,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.9261507987976074,
      "learning_rate": 4e-05,
      "loss": 2.9025,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.853804588317871,
      "learning_rate": 8e-05,
      "loss": 2.8561,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.526839256286621,
      "learning_rate": 0.00012,
      "loss": 2.2888,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.0907649993896484,
      "learning_rate": 0.00016,
      "loss": 2.6181,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.8383708000183105,
      "learning_rate": 0.0002,
      "loss": 2.5613,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 3.0531911849975586,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.8836,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.9199020862579346,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.3011,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.8820964694023132,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2175,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.2959258556365967,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.1792,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.0196328163146973,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.4126,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.6727527976036072,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.3123,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.6856306195259094,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.1368,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5775002241134644,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.2559,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5077104568481445,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.0962,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.4343227446079254,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.2124,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.38887736201286316,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.1039,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.3728462755680084,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.1092,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.4714427888393402,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.0643,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.37319809198379517,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.8982,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.43793997168540955,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.0853,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.35266539454460144,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.0757,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3485453128814697,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.0654,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.32909029722213745,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.9124,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.29112690687179565,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.998,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.34860149025917053,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9398,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.3410319685935974,
      "learning_rate": 0.00019068736141906876,
      "loss": 1.085,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.27022361755371094,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.8182,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.39027002453804016,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.0936,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3809190094470978,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.9669,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.2618960738182068,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.7325,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.31428655982017517,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.8969,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.3208927512168884,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9837,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.3479961156845093,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.9492,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.24484692513942719,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.8931,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.31913065910339355,
      "learning_rate": 0.00018669623059866964,
      "loss": 1.0286,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3971562087535858,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.1215,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.3638000190258026,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.9333,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.34042876958847046,
      "learning_rate": 0.0001853658536585366,
      "loss": 1.1182,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.35048097372055054,
      "learning_rate": 0.00018492239467849224,
      "loss": 1.0188,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3047362267971039,
      "learning_rate": 0.0001844789356984479,
      "loss": 1.1008,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.24302105605602264,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.8789,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.32716572284698486,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.8929,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.24855059385299683,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.7146,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.2590542137622833,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.9198,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.32804593443870544,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.895,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.3551070988178253,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.9866,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.2825017273426056,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.8555,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.2646731436252594,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.9711,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.33243000507354736,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.9449,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.385030061006546,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.9101,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.31159284710884094,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.8401,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.2921944558620453,
      "learning_rate": 0.00017915742793791575,
      "loss": 1.0733,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2874985337257385,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.8802,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.31257903575897217,
      "learning_rate": 0.00017827050997782707,
      "loss": 1.1215,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.2742151916027069,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.9605,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.32726484537124634,
      "learning_rate": 0.00017738359201773839,
      "loss": 1.0408,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.3544639050960541,
      "learning_rate": 0.000176940133037694,
      "loss": 1.0483,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.3291817009449005,
      "learning_rate": 0.00017649667405764967,
      "loss": 1.0099,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.2948567271232605,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.7214,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.3465343713760376,
      "learning_rate": 0.000175609756097561,
      "loss": 0.8914,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.294916033744812,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.9002,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.2645125687122345,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.9807,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.26566192507743835,
      "learning_rate": 0.00017427937915742792,
      "loss": 1.0263,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3932898938655853,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.9964,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3968732953071594,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.905,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.2582176923751831,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.762,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.3497701585292816,
      "learning_rate": 0.00017250554323725056,
      "loss": 1.2204,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.21835869550704956,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.8432,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.4241009056568146,
      "learning_rate": 0.00017161862527716187,
      "loss": 1.1661,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.29903969168663025,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.9637,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.32923105359077454,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.9613,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.33389630913734436,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8119,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.2928239703178406,
      "learning_rate": 0.0001698447893569845,
      "loss": 1.1114,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.4275268316268921,
      "learning_rate": 0.00016940133037694015,
      "loss": 1.0924,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.252409964799881,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.9047,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.27643951773643494,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.9516,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.31490686535835266,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.9629,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.28956061601638794,
      "learning_rate": 0.00016762749445676275,
      "loss": 1.073,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.39840641617774963,
      "learning_rate": 0.00016718403547671842,
      "loss": 1.0587,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.3193679749965668,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.9033,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.29296162724494934,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.9926,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.25819483399391174,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.9406,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3168943226337433,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.8069,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.30880314111709595,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.872,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.3081277310848236,
      "learning_rate": 0.00016452328159645234,
      "loss": 1.0051,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.41150379180908203,
      "learning_rate": 0.000164079822616408,
      "loss": 0.9577,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.3497859239578247,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.9117,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.24770864844322205,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.8452,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.2897774875164032,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.9269,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.2963946759700775,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.883,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.35474881529808044,
      "learning_rate": 0.00016186252771618626,
      "loss": 1.0333,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.3128604292869568,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.8813,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.3175148069858551,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.9218,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.30592796206474304,
      "learning_rate": 0.00016053215077605322,
      "loss": 1.0093,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.30979204177856445,
      "learning_rate": 0.00016008869179600887,
      "loss": 1.1087,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.3170197010040283,
      "learning_rate": 0.00015964523281596454,
      "loss": 1.0377,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.34211069345474243,
      "learning_rate": 0.00015920177383592018,
      "loss": 1.1252,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.34838294982910156,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.9858,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.3975377082824707,
      "learning_rate": 0.0001583148558758315,
      "loss": 1.041,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.33024221658706665,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.9925,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.3557412922382355,
      "learning_rate": 0.0001574279379157428,
      "loss": 1.077,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.3489350378513336,
      "learning_rate": 0.00015698447893569846,
      "loss": 1.1104,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.3904794454574585,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.816,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.28544628620147705,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.8572,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.2343568354845047,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.8888,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.25775396823883057,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.7646,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.32354897260665894,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.8485,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.2608407735824585,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.8236,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.2987760603427887,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.9411,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.3875117599964142,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.8312,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.3331878185272217,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.94,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.36396199464797974,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.8921,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.2830229103565216,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.9608,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.27632445096969604,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.9802,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.3065943717956543,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.9039,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.27498388290405273,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.6538,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.29651233553886414,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.7523,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.34246179461479187,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.9063,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.2942260801792145,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.9174,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.35497164726257324,
      "learning_rate": 0.00014900221729490022,
      "loss": 1.061,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.31248870491981506,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.5611,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.3703018128871918,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.994,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.30003687739372253,
      "learning_rate": 0.0001476718403547672,
      "loss": 1.0005,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.3337390720844269,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.9926,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.3595570921897888,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.9224,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.32574501633644104,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.925,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.3348236382007599,
      "learning_rate": 0.0001458980044345898,
      "loss": 1.0227,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.4262445569038391,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.1669,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.2437465935945511,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.9765,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.2993992865085602,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.9402,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.31676241755485535,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.7698,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.3266180753707886,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.9382,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.5359867811203003,
      "learning_rate": 0.00014323725055432373,
      "loss": 1.1008,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.3537139892578125,
      "learning_rate": 0.00014279379157427938,
      "loss": 1.0479,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.29332348704338074,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.7726,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.26056739687919617,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.8899,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.3328043222427368,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.8826,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.318121075630188,
      "learning_rate": 0.000141019955654102,
      "loss": 1.0313,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.27776262164115906,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.8429,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.41019654273986816,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.7596,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.44149407744407654,
      "learning_rate": 0.00013968957871396897,
      "loss": 1.0933,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.3452533781528473,
      "learning_rate": 0.00013924611973392464,
      "loss": 1.092,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.4055083990097046,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.8477,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.29458796977996826,
      "learning_rate": 0.00013835920177383593,
      "loss": 1.0863,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.3553215265274048,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.841,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.2607809603214264,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.8665,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.3363148868083954,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.9835,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.3593413233757019,
      "learning_rate": 0.00013658536585365856,
      "loss": 1.0942,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.3413514196872711,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.7658,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.3798319399356842,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.9531,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5191491842269897,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.895,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.29708221554756165,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.8409,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.3404264748096466,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.8998,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.2907215654850006,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.791,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.3138722777366638,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.7115,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.2748890519142151,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.7963,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.3424566090106964,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.917,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.4405767023563385,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.9621,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.3384034037590027,
      "learning_rate": 0.00013170731707317076,
      "loss": 1.0064,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.33156687021255493,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.9567,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.5067695379257202,
      "learning_rate": 0.00013082039911308205,
      "loss": 1.1466,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.31624114513397217,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.8416,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.3610425591468811,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.8084,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.35755568742752075,
      "learning_rate": 0.000129490022172949,
      "loss": 0.9263,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.35494673252105713,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.8468,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.31086811423301697,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.8116,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.4692591726779938,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.7696,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.41669943928718567,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.8848,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.32662615180015564,
      "learning_rate": 0.00012727272727272728,
      "loss": 1.0124,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.37332552671432495,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.9621,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.3247275650501251,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.6283,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.3729154169559479,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.7774,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.34493041038513184,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.8906,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.40263891220092773,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.9097,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.33932220935821533,
      "learning_rate": 0.0001246119733924612,
      "loss": 1.0619,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.4906759262084961,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.8555,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.34933722019195557,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.7188,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.3895803987979889,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.8163,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.37271687388420105,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.8583,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.37537920475006104,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.9301,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.43662625551223755,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.9643,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.4180794060230255,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.819,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.4734267294406891,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.8844,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.4149094820022583,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.7993,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.39257511496543884,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.8444,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.4501616954803467,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.9523,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.4055061340332031,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.8141,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.3888970613479614,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.7335,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.3809174597263336,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.9792,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.4059563875198364,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.8623,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.40468695759773254,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.9576,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.4100147485733032,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.83,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.3891144394874573,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.817,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.46983179450035095,
      "learning_rate": 0.00011618625277161863,
      "loss": 1.0129,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.40355440974235535,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.8589,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.45564204454421997,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.9284,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.4047411382198334,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.8623,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.47230207920074463,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.9353,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.33869704604148865,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.7763,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.41405606269836426,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.7396,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.417321115732193,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.7828,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.43744906783103943,
      "learning_rate": 0.00011263858093126387,
      "loss": 1.0282,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.45967185497283936,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.775,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.3601992726325989,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.786,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.4809643626213074,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.8693,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.4741341471672058,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.8719,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.36272764205932617,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.6556,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.44228801131248474,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.9628,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.3871653974056244,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.6797,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.41632112860679626,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.815,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.502764880657196,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.846,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.42912641167640686,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.7621,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.4650607407093048,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.7421,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.4582888185977936,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.7818,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.48180267214775085,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.8138,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.511580765247345,
      "learning_rate": 0.00010643015521064301,
      "loss": 1.1168,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.45081284642219543,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.9058,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.5508686304092407,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.9215,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.5153694748878479,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.6763,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.37435415387153625,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.7935,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.5131158232688904,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.7725,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.4943814277648926,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.8125,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.5116263031959534,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.8158,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.4587961435317993,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.8219,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.553566575050354,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.9088,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.48576125502586365,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.9392,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.5061334371566772,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.7208,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.4555932879447937,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.8382,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.46783602237701416,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.7965,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.49874311685562134,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.6752,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.5444801449775696,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.8343,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.5175329446792603,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.8578,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.5829601287841797,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.8519,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.43729230761528015,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.7164,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.571960985660553,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.9142,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.4475269913673401,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.8157,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.480765163898468,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.8811,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.5030956268310547,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.8106,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.40986260771751404,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.7308,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.5326623320579529,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.8044,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.57526695728302,
      "learning_rate": 9.534368070953438e-05,
      "loss": 1.0453,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.4797089099884033,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.883,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.44899997115135193,
      "learning_rate": 9.445676274944568e-05,
      "loss": 0.8558,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.42102983593940735,
      "learning_rate": 9.401330376940134e-05,
      "loss": 0.6533,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.43832311034202576,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.6702,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.5539906620979309,
      "learning_rate": 9.312638580931264e-05,
      "loss": 0.8937,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.4885682761669159,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.6732,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.45122894644737244,
      "learning_rate": 9.223946784922394e-05,
      "loss": 0.7181,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.5054178237915039,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.7449,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.5053577423095703,
      "learning_rate": 9.135254988913526e-05,
      "loss": 0.9046,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.5948387980461121,
      "learning_rate": 9.090909090909092e-05,
      "loss": 1.0525,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.4533322751522064,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.7566,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.4726763665676117,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.9861,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.5025450587272644,
      "learning_rate": 8.957871396895788e-05,
      "loss": 0.8539,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.5008198022842407,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.9187,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.4883393943309784,
      "learning_rate": 8.869179600886919e-05,
      "loss": 0.8739,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.4469898045063019,
      "learning_rate": 8.824833702882484e-05,
      "loss": 0.7624,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.5065831542015076,
      "learning_rate": 8.78048780487805e-05,
      "loss": 0.7105,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.4368380904197693,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.8694,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.48139819502830505,
      "learning_rate": 8.69179600886918e-05,
      "loss": 0.7769,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.5313706994056702,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.8651,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.4431131184101105,
      "learning_rate": 8.603104212860311e-05,
      "loss": 0.762,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.538593053817749,
      "learning_rate": 8.558758314855876e-05,
      "loss": 0.8551,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.503423810005188,
      "learning_rate": 8.514412416851442e-05,
      "loss": 0.8014,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.3678390383720398,
      "learning_rate": 8.470066518847007e-05,
      "loss": 0.8271,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.5572373270988464,
      "learning_rate": 8.425720620842572e-05,
      "loss": 0.8267,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.5745418667793274,
      "learning_rate": 8.381374722838138e-05,
      "loss": 0.9133,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.5345473289489746,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.7464,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.525519609451294,
      "learning_rate": 8.292682926829268e-05,
      "loss": 1.026,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.5444814562797546,
      "learning_rate": 8.248337028824834e-05,
      "loss": 0.8921,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.47043466567993164,
      "learning_rate": 8.2039911308204e-05,
      "loss": 0.7557,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.566632866859436,
      "learning_rate": 8.159645232815965e-05,
      "loss": 0.925,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.494680792093277,
      "learning_rate": 8.11529933481153e-05,
      "loss": 0.8849,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.47679436206817627,
      "learning_rate": 8.070953436807095e-05,
      "loss": 0.9188,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.5667601227760315,
      "learning_rate": 8.026607538802661e-05,
      "loss": 0.7701,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.523406982421875,
      "learning_rate": 7.982261640798227e-05,
      "loss": 1.0115,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.5772580504417419,
      "learning_rate": 7.937915742793793e-05,
      "loss": 0.9229,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.5381619930267334,
      "learning_rate": 7.893569844789357e-05,
      "loss": 0.7686,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.5690406560897827,
      "learning_rate": 7.849223946784923e-05,
      "loss": 0.9865,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.5080500841140747,
      "learning_rate": 7.804878048780489e-05,
      "loss": 0.8298,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.4479190409183502,
      "learning_rate": 7.760532150776053e-05,
      "loss": 0.7265,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.47274479269981384,
      "learning_rate": 7.716186252771619e-05,
      "loss": 0.7823,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.5814086198806763,
      "learning_rate": 7.671840354767185e-05,
      "loss": 0.9834,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.5235365629196167,
      "learning_rate": 7.627494456762749e-05,
      "loss": 0.6929,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.5357524752616882,
      "learning_rate": 7.583148558758315e-05,
      "loss": 0.9684,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.48358154296875,
      "learning_rate": 7.538802660753881e-05,
      "loss": 0.7867,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.5202826857566833,
      "learning_rate": 7.494456762749445e-05,
      "loss": 0.8325,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.5686357021331787,
      "learning_rate": 7.450110864745011e-05,
      "loss": 0.833,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.533931314945221,
      "learning_rate": 7.405764966740577e-05,
      "loss": 0.8363,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.45171716809272766,
      "learning_rate": 7.361419068736141e-05,
      "loss": 0.7921,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.6389825344085693,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.9351,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.5065105557441711,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.8063,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.5711171627044678,
      "learning_rate": 7.228381374722837e-05,
      "loss": 0.9136,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.6816263794898987,
      "learning_rate": 7.184035476718403e-05,
      "loss": 0.9611,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.48403802514076233,
      "learning_rate": 7.139689578713969e-05,
      "loss": 0.7395,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.5887596607208252,
      "learning_rate": 7.095343680709535e-05,
      "loss": 0.7536,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.5480006337165833,
      "learning_rate": 7.0509977827051e-05,
      "loss": 0.7983,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.5043086409568787,
      "learning_rate": 7.006651884700666e-05,
      "loss": 0.6189,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.5580520033836365,
      "learning_rate": 6.962305986696232e-05,
      "loss": 0.8428,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.5937092304229736,
      "learning_rate": 6.917960088691796e-05,
      "loss": 0.8885,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.5315391421318054,
      "learning_rate": 6.873614190687362e-05,
      "loss": 0.6616,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.6503174304962158,
      "learning_rate": 6.829268292682928e-05,
      "loss": 0.8987,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6370692849159241,
      "learning_rate": 6.784922394678492e-05,
      "loss": 0.8457,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.5143169164657593,
      "learning_rate": 6.740576496674058e-05,
      "loss": 0.9098,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.47951698303222656,
      "learning_rate": 6.696230598669624e-05,
      "loss": 0.8517,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.5648759603500366,
      "learning_rate": 6.651884700665188e-05,
      "loss": 0.6878,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.5876017808914185,
      "learning_rate": 6.607538802660754e-05,
      "loss": 0.7088,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.5554363131523132,
      "learning_rate": 6.56319290465632e-05,
      "loss": 0.8193,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.4989209771156311,
      "learning_rate": 6.518847006651884e-05,
      "loss": 0.766,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.5161620378494263,
      "learning_rate": 6.47450110864745e-05,
      "loss": 0.6272,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.5355135798454285,
      "learning_rate": 6.430155210643016e-05,
      "loss": 0.7108,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.5928871631622314,
      "learning_rate": 6.38580931263858e-05,
      "loss": 0.7783,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.569097101688385,
      "learning_rate": 6.341463414634146e-05,
      "loss": 0.8424,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.5363989472389221,
      "learning_rate": 6.297117516629712e-05,
      "loss": 0.7,
      "step": 315
    },
    {
      "epoch": 2.0791208791208793,
      "grad_norm": 0.607695460319519,
      "learning_rate": 6.252771618625277e-05,
      "loss": 0.7568,
      "step": 316
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.5872042775154114,
      "learning_rate": 6.208425720620842e-05,
      "loss": 0.7658,
      "step": 317
    },
    {
      "epoch": 2.0923076923076924,
      "grad_norm": 0.6008285880088806,
      "learning_rate": 6.164079822616408e-05,
      "loss": 0.7884,
      "step": 318
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.5304933190345764,
      "learning_rate": 6.119733924611974e-05,
      "loss": 0.8699,
      "step": 319
    },
    {
      "epoch": 2.1054945054945056,
      "grad_norm": 0.5592557191848755,
      "learning_rate": 6.075388026607539e-05,
      "loss": 0.8035,
      "step": 320
    },
    {
      "epoch": 2.112087912087912,
      "grad_norm": 0.492391973733902,
      "learning_rate": 6.031042128603105e-05,
      "loss": 0.7113,
      "step": 321
    },
    {
      "epoch": 2.1186813186813187,
      "grad_norm": 0.6822896003723145,
      "learning_rate": 5.98669623059867e-05,
      "loss": 0.6485,
      "step": 322
    },
    {
      "epoch": 2.1252747252747253,
      "grad_norm": 0.6155532002449036,
      "learning_rate": 5.942350332594236e-05,
      "loss": 0.6807,
      "step": 323
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.5636239051818848,
      "learning_rate": 5.898004434589801e-05,
      "loss": 0.6834,
      "step": 324
    },
    {
      "epoch": 2.1384615384615384,
      "grad_norm": 0.6690635681152344,
      "learning_rate": 5.853658536585366e-05,
      "loss": 0.7031,
      "step": 325
    },
    {
      "epoch": 2.145054945054945,
      "grad_norm": 0.6629694104194641,
      "learning_rate": 5.809312638580932e-05,
      "loss": 0.6945,
      "step": 326
    },
    {
      "epoch": 2.1516483516483516,
      "grad_norm": 0.5748483538627625,
      "learning_rate": 5.7649667405764975e-05,
      "loss": 0.6662,
      "step": 327
    },
    {
      "epoch": 2.158241758241758,
      "grad_norm": 0.7516551613807678,
      "learning_rate": 5.720620842572062e-05,
      "loss": 0.6819,
      "step": 328
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 0.5038599967956543,
      "learning_rate": 5.676274944567628e-05,
      "loss": 0.7335,
      "step": 329
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.8228599429130554,
      "learning_rate": 5.6319290465631935e-05,
      "loss": 0.7881,
      "step": 330
    },
    {
      "epoch": 2.178021978021978,
      "grad_norm": 0.6872739195823669,
      "learning_rate": 5.587583148558758e-05,
      "loss": 0.7179,
      "step": 331
    },
    {
      "epoch": 2.184615384615385,
      "grad_norm": 0.5808748602867126,
      "learning_rate": 5.543237250554324e-05,
      "loss": 0.5949,
      "step": 332
    },
    {
      "epoch": 2.1912087912087914,
      "grad_norm": 0.7332891225814819,
      "learning_rate": 5.4988913525498895e-05,
      "loss": 0.7676,
      "step": 333
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.6026077270507812,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.6923,
      "step": 334
    },
    {
      "epoch": 2.2043956043956046,
      "grad_norm": 0.5872125029563904,
      "learning_rate": 5.4101995565410204e-05,
      "loss": 0.8292,
      "step": 335
    },
    {
      "epoch": 2.210989010989011,
      "grad_norm": 0.6865414977073669,
      "learning_rate": 5.365853658536586e-05,
      "loss": 0.6795,
      "step": 336
    },
    {
      "epoch": 2.2175824175824177,
      "grad_norm": 0.6352996826171875,
      "learning_rate": 5.3215077605321506e-05,
      "loss": 0.8914,
      "step": 337
    },
    {
      "epoch": 2.2241758241758243,
      "grad_norm": 0.7429395914077759,
      "learning_rate": 5.2771618625277164e-05,
      "loss": 0.8398,
      "step": 338
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.7131506204605103,
      "learning_rate": 5.232815964523282e-05,
      "loss": 0.8123,
      "step": 339
    },
    {
      "epoch": 2.2373626373626374,
      "grad_norm": 0.5287996530532837,
      "learning_rate": 5.1884700665188466e-05,
      "loss": 0.7368,
      "step": 340
    },
    {
      "epoch": 2.243956043956044,
      "grad_norm": 0.5643261671066284,
      "learning_rate": 5.1441241685144124e-05,
      "loss": 0.7502,
      "step": 341
    },
    {
      "epoch": 2.2505494505494505,
      "grad_norm": 0.6251582503318787,
      "learning_rate": 5.099778270509978e-05,
      "loss": 0.6688,
      "step": 342
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 0.7469930648803711,
      "learning_rate": 5.0554323725055433e-05,
      "loss": 0.6385,
      "step": 343
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 0.5672867894172668,
      "learning_rate": 5.011086474501109e-05,
      "loss": 0.6453,
      "step": 344
    },
    {
      "epoch": 2.2703296703296703,
      "grad_norm": 0.584135115146637,
      "learning_rate": 4.966740576496674e-05,
      "loss": 0.6946,
      "step": 345
    },
    {
      "epoch": 2.276923076923077,
      "grad_norm": 0.6762666702270508,
      "learning_rate": 4.92239467849224e-05,
      "loss": 0.587,
      "step": 346
    },
    {
      "epoch": 2.2835164835164834,
      "grad_norm": 0.6489875316619873,
      "learning_rate": 4.878048780487805e-05,
      "loss": 0.6775,
      "step": 347
    },
    {
      "epoch": 2.29010989010989,
      "grad_norm": 0.5669387578964233,
      "learning_rate": 4.833702882483371e-05,
      "loss": 0.7281,
      "step": 348
    },
    {
      "epoch": 2.2967032967032965,
      "grad_norm": 0.6522759795188904,
      "learning_rate": 4.789356984478936e-05,
      "loss": 0.57,
      "step": 349
    },
    {
      "epoch": 2.303296703296703,
      "grad_norm": 0.5774281024932861,
      "learning_rate": 4.745011086474501e-05,
      "loss": 0.6345,
      "step": 350
    },
    {
      "epoch": 2.3098901098901097,
      "grad_norm": 0.720676600933075,
      "learning_rate": 4.700665188470067e-05,
      "loss": 0.6763,
      "step": 351
    },
    {
      "epoch": 2.3164835164835162,
      "grad_norm": 0.4796013832092285,
      "learning_rate": 4.656319290465632e-05,
      "loss": 0.6514,
      "step": 352
    },
    {
      "epoch": 2.3230769230769233,
      "grad_norm": 0.6652957201004028,
      "learning_rate": 4.611973392461197e-05,
      "loss": 0.6947,
      "step": 353
    },
    {
      "epoch": 2.32967032967033,
      "grad_norm": 0.6702308654785156,
      "learning_rate": 4.567627494456763e-05,
      "loss": 0.7393,
      "step": 354
    },
    {
      "epoch": 2.3362637362637364,
      "grad_norm": 0.7704075574874878,
      "learning_rate": 4.523281596452328e-05,
      "loss": 0.7915,
      "step": 355
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 0.6327314972877502,
      "learning_rate": 4.478935698447894e-05,
      "loss": 0.6167,
      "step": 356
    },
    {
      "epoch": 2.3494505494505495,
      "grad_norm": 0.7284319400787354,
      "learning_rate": 4.4345898004434597e-05,
      "loss": 0.6293,
      "step": 357
    },
    {
      "epoch": 2.356043956043956,
      "grad_norm": 0.7199291586875916,
      "learning_rate": 4.390243902439025e-05,
      "loss": 0.7445,
      "step": 358
    },
    {
      "epoch": 2.3626373626373627,
      "grad_norm": 0.5351080894470215,
      "learning_rate": 4.34589800443459e-05,
      "loss": 0.7684,
      "step": 359
    },
    {
      "epoch": 2.3692307692307693,
      "grad_norm": 0.7263058423995972,
      "learning_rate": 4.301552106430156e-05,
      "loss": 0.6329,
      "step": 360
    },
    {
      "epoch": 2.375824175824176,
      "grad_norm": 0.6704328656196594,
      "learning_rate": 4.257206208425721e-05,
      "loss": 0.596,
      "step": 361
    },
    {
      "epoch": 2.3824175824175824,
      "grad_norm": 0.7016993761062622,
      "learning_rate": 4.212860310421286e-05,
      "loss": 1.0046,
      "step": 362
    },
    {
      "epoch": 2.389010989010989,
      "grad_norm": 0.722292959690094,
      "learning_rate": 4.168514412416852e-05,
      "loss": 0.6854,
      "step": 363
    },
    {
      "epoch": 2.3956043956043955,
      "grad_norm": 0.7929955720901489,
      "learning_rate": 4.124168514412417e-05,
      "loss": 0.9605,
      "step": 364
    },
    {
      "epoch": 2.402197802197802,
      "grad_norm": 0.8917398452758789,
      "learning_rate": 4.0798226164079826e-05,
      "loss": 0.6794,
      "step": 365
    },
    {
      "epoch": 2.4087912087912087,
      "grad_norm": 0.4652984142303467,
      "learning_rate": 4.035476718403548e-05,
      "loss": 0.5124,
      "step": 366
    },
    {
      "epoch": 2.4153846153846152,
      "grad_norm": 0.7584043741226196,
      "learning_rate": 3.9911308203991135e-05,
      "loss": 0.7153,
      "step": 367
    },
    {
      "epoch": 2.421978021978022,
      "grad_norm": 0.5517014861106873,
      "learning_rate": 3.9467849223946786e-05,
      "loss": 0.7481,
      "step": 368
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.7552153468132019,
      "learning_rate": 3.9024390243902444e-05,
      "loss": 0.8698,
      "step": 369
    },
    {
      "epoch": 2.4351648351648354,
      "grad_norm": 0.6394533514976501,
      "learning_rate": 3.8580931263858095e-05,
      "loss": 0.7458,
      "step": 370
    },
    {
      "epoch": 2.441758241758242,
      "grad_norm": 0.661910891532898,
      "learning_rate": 3.8137472283813746e-05,
      "loss": 0.7112,
      "step": 371
    },
    {
      "epoch": 2.4483516483516485,
      "grad_norm": 0.7396936416625977,
      "learning_rate": 3.7694013303769404e-05,
      "loss": 0.7334,
      "step": 372
    },
    {
      "epoch": 2.454945054945055,
      "grad_norm": 0.6523051261901855,
      "learning_rate": 3.7250554323725055e-05,
      "loss": 0.7392,
      "step": 373
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.7784618139266968,
      "learning_rate": 3.6807095343680706e-05,
      "loss": 0.5736,
      "step": 374
    },
    {
      "epoch": 2.4681318681318682,
      "grad_norm": 0.7373549938201904,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.6267,
      "step": 375
    },
    {
      "epoch": 2.474725274725275,
      "grad_norm": 0.8192687630653381,
      "learning_rate": 3.5920177383592015e-05,
      "loss": 0.8399,
      "step": 376
    },
    {
      "epoch": 2.4813186813186814,
      "grad_norm": 0.7324414253234863,
      "learning_rate": 3.547671840354767e-05,
      "loss": 0.7683,
      "step": 377
    },
    {
      "epoch": 2.487912087912088,
      "grad_norm": 0.907971978187561,
      "learning_rate": 3.503325942350333e-05,
      "loss": 0.9629,
      "step": 378
    },
    {
      "epoch": 2.4945054945054945,
      "grad_norm": 0.6732437014579773,
      "learning_rate": 3.458980044345898e-05,
      "loss": 0.588,
      "step": 379
    },
    {
      "epoch": 2.501098901098901,
      "grad_norm": 0.6966331601142883,
      "learning_rate": 3.414634146341464e-05,
      "loss": 0.6595,
      "step": 380
    },
    {
      "epoch": 2.5076923076923077,
      "grad_norm": 0.6771131157875061,
      "learning_rate": 3.370288248337029e-05,
      "loss": 0.6247,
      "step": 381
    },
    {
      "epoch": 2.5142857142857142,
      "grad_norm": 0.6766157150268555,
      "learning_rate": 3.325942350332594e-05,
      "loss": 0.8854,
      "step": 382
    },
    {
      "epoch": 2.520879120879121,
      "grad_norm": 0.7659056186676025,
      "learning_rate": 3.28159645232816e-05,
      "loss": 0.6436,
      "step": 383
    },
    {
      "epoch": 2.5274725274725274,
      "grad_norm": 0.6654849648475647,
      "learning_rate": 3.237250554323725e-05,
      "loss": 0.7231,
      "step": 384
    },
    {
      "epoch": 2.534065934065934,
      "grad_norm": 0.7134755849838257,
      "learning_rate": 3.19290465631929e-05,
      "loss": 0.573,
      "step": 385
    },
    {
      "epoch": 2.5406593406593405,
      "grad_norm": 0.6731679439544678,
      "learning_rate": 3.148558758314856e-05,
      "loss": 0.6813,
      "step": 386
    },
    {
      "epoch": 2.547252747252747,
      "grad_norm": 0.7563791275024414,
      "learning_rate": 3.104212860310421e-05,
      "loss": 0.7826,
      "step": 387
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.7487744688987732,
      "learning_rate": 3.059866962305987e-05,
      "loss": 0.6419,
      "step": 388
    },
    {
      "epoch": 2.5604395604395602,
      "grad_norm": 0.6904215216636658,
      "learning_rate": 3.0155210643015524e-05,
      "loss": 0.7418,
      "step": 389
    },
    {
      "epoch": 2.567032967032967,
      "grad_norm": 0.7288605570793152,
      "learning_rate": 2.971175166297118e-05,
      "loss": 0.7719,
      "step": 390
    },
    {
      "epoch": 2.5736263736263734,
      "grad_norm": 0.5797594785690308,
      "learning_rate": 2.926829268292683e-05,
      "loss": 0.7815,
      "step": 391
    },
    {
      "epoch": 2.5802197802197804,
      "grad_norm": 0.8103426694869995,
      "learning_rate": 2.8824833702882487e-05,
      "loss": 0.6919,
      "step": 392
    },
    {
      "epoch": 2.586813186813187,
      "grad_norm": 0.714779794216156,
      "learning_rate": 2.838137472283814e-05,
      "loss": 0.7404,
      "step": 393
    },
    {
      "epoch": 2.5934065934065935,
      "grad_norm": 0.5625683665275574,
      "learning_rate": 2.793791574279379e-05,
      "loss": 0.7562,
      "step": 394
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.6392197608947754,
      "learning_rate": 2.7494456762749448e-05,
      "loss": 0.6178,
      "step": 395
    },
    {
      "epoch": 2.6065934065934067,
      "grad_norm": 0.9186407327651978,
      "learning_rate": 2.7050997782705102e-05,
      "loss": 0.7735,
      "step": 396
    },
    {
      "epoch": 2.6131868131868132,
      "grad_norm": 0.572242259979248,
      "learning_rate": 2.6607538802660753e-05,
      "loss": 0.7501,
      "step": 397
    },
    {
      "epoch": 2.61978021978022,
      "grad_norm": 0.6298501491546631,
      "learning_rate": 2.616407982261641e-05,
      "loss": 0.5643,
      "step": 398
    },
    {
      "epoch": 2.6263736263736264,
      "grad_norm": 0.8339748978614807,
      "learning_rate": 2.5720620842572062e-05,
      "loss": 0.7123,
      "step": 399
    },
    {
      "epoch": 2.632967032967033,
      "grad_norm": 0.8724586963653564,
      "learning_rate": 2.5277161862527717e-05,
      "loss": 0.7366,
      "step": 400
    },
    {
      "epoch": 2.6395604395604395,
      "grad_norm": 0.693099319934845,
      "learning_rate": 2.483370288248337e-05,
      "loss": 0.6845,
      "step": 401
    },
    {
      "epoch": 2.646153846153846,
      "grad_norm": 0.6929130554199219,
      "learning_rate": 2.4390243902439026e-05,
      "loss": 0.6127,
      "step": 402
    },
    {
      "epoch": 2.6527472527472526,
      "grad_norm": 0.7349172830581665,
      "learning_rate": 2.394678492239468e-05,
      "loss": 0.6801,
      "step": 403
    },
    {
      "epoch": 2.659340659340659,
      "grad_norm": 0.6877846121788025,
      "learning_rate": 2.3503325942350335e-05,
      "loss": 0.664,
      "step": 404
    },
    {
      "epoch": 2.665934065934066,
      "grad_norm": 0.7427359819412231,
      "learning_rate": 2.3059866962305986e-05,
      "loss": 0.6309,
      "step": 405
    },
    {
      "epoch": 2.672527472527473,
      "grad_norm": 0.6666280031204224,
      "learning_rate": 2.261640798226164e-05,
      "loss": 0.6183,
      "step": 406
    },
    {
      "epoch": 2.6791208791208794,
      "grad_norm": 0.7280635237693787,
      "learning_rate": 2.2172949002217298e-05,
      "loss": 0.6038,
      "step": 407
    },
    {
      "epoch": 2.685714285714286,
      "grad_norm": 0.7868024110794067,
      "learning_rate": 2.172949002217295e-05,
      "loss": 0.608,
      "step": 408
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.7681790590286255,
      "learning_rate": 2.1286031042128604e-05,
      "loss": 0.7647,
      "step": 409
    },
    {
      "epoch": 2.698901098901099,
      "grad_norm": 0.8302758932113647,
      "learning_rate": 2.084257206208426e-05,
      "loss": 0.914,
      "step": 410
    },
    {
      "epoch": 2.7054945054945057,
      "grad_norm": 0.7847422361373901,
      "learning_rate": 2.0399113082039913e-05,
      "loss": 0.802,
      "step": 411
    },
    {
      "epoch": 2.7120879120879122,
      "grad_norm": 0.776107907295227,
      "learning_rate": 1.9955654101995567e-05,
      "loss": 0.6332,
      "step": 412
    },
    {
      "epoch": 2.718681318681319,
      "grad_norm": 0.6751231551170349,
      "learning_rate": 1.9512195121951222e-05,
      "loss": 0.6908,
      "step": 413
    },
    {
      "epoch": 2.7252747252747254,
      "grad_norm": 0.8515974283218384,
      "learning_rate": 1.9068736141906873e-05,
      "loss": 0.7406,
      "step": 414
    },
    {
      "epoch": 2.731868131868132,
      "grad_norm": 0.7073973417282104,
      "learning_rate": 1.8625277161862528e-05,
      "loss": 0.7198,
      "step": 415
    },
    {
      "epoch": 2.7384615384615385,
      "grad_norm": 0.7655714154243469,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.6899,
      "step": 416
    },
    {
      "epoch": 2.745054945054945,
      "grad_norm": 0.7215205430984497,
      "learning_rate": 1.7738359201773837e-05,
      "loss": 0.7481,
      "step": 417
    },
    {
      "epoch": 2.7516483516483516,
      "grad_norm": 0.7629061937332153,
      "learning_rate": 1.729490022172949e-05,
      "loss": 0.6773,
      "step": 418
    },
    {
      "epoch": 2.758241758241758,
      "grad_norm": 0.6971875429153442,
      "learning_rate": 1.6851441241685146e-05,
      "loss": 0.6815,
      "step": 419
    },
    {
      "epoch": 2.764835164835165,
      "grad_norm": 0.7901301980018616,
      "learning_rate": 1.64079822616408e-05,
      "loss": 0.7546,
      "step": 420
    },
    {
      "epoch": 2.7714285714285714,
      "grad_norm": 0.6483908891677856,
      "learning_rate": 1.596452328159645e-05,
      "loss": 0.7048,
      "step": 421
    },
    {
      "epoch": 2.778021978021978,
      "grad_norm": 0.6222918629646301,
      "learning_rate": 1.5521064301552106e-05,
      "loss": 0.6491,
      "step": 422
    },
    {
      "epoch": 2.7846153846153845,
      "grad_norm": 0.6823261976242065,
      "learning_rate": 1.5077605321507762e-05,
      "loss": 0.6392,
      "step": 423
    },
    {
      "epoch": 2.791208791208791,
      "grad_norm": 0.6872479915618896,
      "learning_rate": 1.4634146341463415e-05,
      "loss": 0.5097,
      "step": 424
    },
    {
      "epoch": 2.7978021978021976,
      "grad_norm": 0.8053719401359558,
      "learning_rate": 1.419068736141907e-05,
      "loss": 0.7446,
      "step": 425
    },
    {
      "epoch": 2.804395604395604,
      "grad_norm": 0.6089292764663696,
      "learning_rate": 1.3747228381374724e-05,
      "loss": 0.6298,
      "step": 426
    },
    {
      "epoch": 2.8109890109890108,
      "grad_norm": 0.7660013437271118,
      "learning_rate": 1.3303769401330377e-05,
      "loss": 0.7539,
      "step": 427
    },
    {
      "epoch": 2.8175824175824173,
      "grad_norm": 0.8113587498664856,
      "learning_rate": 1.2860310421286031e-05,
      "loss": 0.7012,
      "step": 428
    },
    {
      "epoch": 2.824175824175824,
      "grad_norm": 0.6702430844306946,
      "learning_rate": 1.2416851441241686e-05,
      "loss": 0.5604,
      "step": 429
    },
    {
      "epoch": 2.830769230769231,
      "grad_norm": 0.7777356505393982,
      "learning_rate": 1.197339246119734e-05,
      "loss": 0.7934,
      "step": 430
    },
    {
      "epoch": 2.8373626373626375,
      "grad_norm": 0.7599412798881531,
      "learning_rate": 1.1529933481152993e-05,
      "loss": 0.9968,
      "step": 431
    },
    {
      "epoch": 2.843956043956044,
      "grad_norm": 0.7208889126777649,
      "learning_rate": 1.1086474501108649e-05,
      "loss": 0.6124,
      "step": 432
    },
    {
      "epoch": 2.8505494505494506,
      "grad_norm": 0.7946403622627258,
      "learning_rate": 1.0643015521064302e-05,
      "loss": 0.6152,
      "step": 433
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.7154289484024048,
      "learning_rate": 1.0199556541019956e-05,
      "loss": 0.7079,
      "step": 434
    },
    {
      "epoch": 2.8637362637362638,
      "grad_norm": 0.7349156141281128,
      "learning_rate": 9.756097560975611e-06,
      "loss": 0.5527,
      "step": 435
    }
  ],
  "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": 7.119737014606234e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}