{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.2,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008,
      "grad_norm": 0.09337692707777023,
      "learning_rate": 2e-05,
      "loss": 0.015294969081878662,
      "step": 1
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.07111852616071701,
      "learning_rate": 2e-05,
      "loss": 0.007340883836150169,
      "step": 2
    },
    {
      "epoch": 0.024,
      "grad_norm": 0.07195291668176651,
      "learning_rate": 2e-05,
      "loss": 0.0077208466827869415,
      "step": 3
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.09681837260723114,
      "learning_rate": 2e-05,
      "loss": 0.008473804220557213,
      "step": 4
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.06043309345841408,
      "learning_rate": 2e-05,
      "loss": 0.006642022170126438,
      "step": 5
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.05604363605380058,
      "learning_rate": 2e-05,
      "loss": 0.003878322197124362,
      "step": 6
    },
    {
      "epoch": 0.056,
      "grad_norm": 0.06847543269395828,
      "learning_rate": 2e-05,
      "loss": 0.011454813182353973,
      "step": 7
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.05413937568664551,
      "learning_rate": 2e-05,
      "loss": 0.005098872818052769,
      "step": 8
    },
    {
      "epoch": 0.072,
      "grad_norm": 0.04113985598087311,
      "learning_rate": 2e-05,
      "loss": 0.0072427294217050076,
      "step": 9
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.06007072329521179,
      "learning_rate": 2e-05,
      "loss": 0.005184551235288382,
      "step": 10
    },
    {
      "epoch": 0.088,
      "grad_norm": 0.05269957333803177,
      "learning_rate": 2e-05,
      "loss": 0.006402506493031979,
      "step": 11
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.07171762734651566,
      "learning_rate": 2e-05,
      "loss": 0.006807660683989525,
      "step": 12
    },
    {
      "epoch": 0.104,
      "grad_norm": 0.04405634105205536,
      "learning_rate": 2e-05,
      "loss": 0.0049944375641644,
      "step": 13
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.04304119199514389,
      "learning_rate": 2e-05,
      "loss": 0.005410908255726099,
      "step": 14
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.057690370827913284,
      "learning_rate": 2e-05,
      "loss": 0.007783032953739166,
      "step": 15
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.04541298747062683,
      "learning_rate": 2e-05,
      "loss": 0.004243949428200722,
      "step": 16
    },
    {
      "epoch": 0.136,
      "grad_norm": 0.06319569051265717,
      "learning_rate": 2e-05,
      "loss": 0.005336169619113207,
      "step": 17
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.03583596274256706,
      "learning_rate": 2e-05,
      "loss": 0.004895349964499474,
      "step": 18
    },
    {
      "epoch": 0.152,
      "grad_norm": 0.05986885726451874,
      "learning_rate": 2e-05,
      "loss": 0.006950004491955042,
      "step": 19
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.08991007506847382,
      "learning_rate": 2e-05,
      "loss": 0.00810159184038639,
      "step": 20
    },
    {
      "epoch": 0.168,
      "grad_norm": 0.05890341475605965,
      "learning_rate": 2e-05,
      "loss": 0.006250896491110325,
      "step": 21
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.04574795812368393,
      "learning_rate": 2e-05,
      "loss": 0.005519284401088953,
      "step": 22
    },
    {
      "epoch": 0.184,
      "grad_norm": 0.05631595849990845,
      "learning_rate": 2e-05,
      "loss": 0.00560405757278204,
      "step": 23
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.06935696303844452,
      "learning_rate": 2e-05,
      "loss": 0.00864097848534584,
      "step": 24
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.04360036551952362,
      "learning_rate": 2e-05,
      "loss": 0.003752000629901886,
      "step": 25
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.05469367280602455,
      "learning_rate": 2e-05,
      "loss": 0.0067576696164906025,
      "step": 26
    },
    {
      "epoch": 0.216,
      "grad_norm": 0.06384038180112839,
      "learning_rate": 2e-05,
      "loss": 0.004895553924143314,
      "step": 27
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.06384114921092987,
      "learning_rate": 2e-05,
      "loss": 0.005900057964026928,
      "step": 28
    },
    {
      "epoch": 0.232,
      "grad_norm": 0.0655912533402443,
      "learning_rate": 2e-05,
      "loss": 0.005855287425220013,
      "step": 29
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.04619958996772766,
      "learning_rate": 2e-05,
      "loss": 0.005466114729642868,
      "step": 30
    },
    {
      "epoch": 0.248,
      "grad_norm": 0.04525391384959221,
      "learning_rate": 2e-05,
      "loss": 0.004368640948086977,
      "step": 31
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.04429985210299492,
      "learning_rate": 2e-05,
      "loss": 0.005769067443907261,
      "step": 32
    },
    {
      "epoch": 0.264,
      "grad_norm": 0.03835798799991608,
      "learning_rate": 2e-05,
      "loss": 0.004946814849972725,
      "step": 33
    },
    {
      "epoch": 0.272,
      "grad_norm": 0.06351771950721741,
      "learning_rate": 2e-05,
      "loss": 0.005820239428430796,
      "step": 34
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.05175631865859032,
      "learning_rate": 2e-05,
      "loss": 0.007221951149404049,
      "step": 35
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.031039636582136154,
      "learning_rate": 2e-05,
      "loss": 0.0024754288606345654,
      "step": 36
    },
    {
      "epoch": 0.296,
      "grad_norm": 0.04708324000239372,
      "learning_rate": 2e-05,
      "loss": 0.002840370638296008,
      "step": 37
    },
    {
      "epoch": 0.304,
      "grad_norm": 0.06475556641817093,
      "learning_rate": 2e-05,
      "loss": 0.0077974689193069935,
      "step": 38
    },
    {
      "epoch": 0.312,
      "grad_norm": 0.048895902931690216,
      "learning_rate": 2e-05,
      "loss": 0.0040883091278374195,
      "step": 39
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.058496665209531784,
      "learning_rate": 2e-05,
      "loss": 0.004431126173585653,
      "step": 40
    },
    {
      "epoch": 0.328,
      "grad_norm": 0.0752127543091774,
      "learning_rate": 2e-05,
      "loss": 0.009588265791535378,
      "step": 41
    },
    {
      "epoch": 0.336,
      "grad_norm": 0.029396817088127136,
      "learning_rate": 2e-05,
      "loss": 0.004547424148768187,
      "step": 42
    },
    {
      "epoch": 0.344,
      "grad_norm": 0.10113711655139923,
      "learning_rate": 2e-05,
      "loss": 0.00836176797747612,
      "step": 43
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.04212963953614235,
      "learning_rate": 2e-05,
      "loss": 0.004907882306724787,
      "step": 44
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.02902965061366558,
      "learning_rate": 2e-05,
      "loss": 0.002945390995591879,
      "step": 45
    },
    {
      "epoch": 0.368,
      "grad_norm": 0.05033962428569794,
      "learning_rate": 2e-05,
      "loss": 0.005018638446927071,
      "step": 46
    },
    {
      "epoch": 0.376,
      "grad_norm": 0.034906402230262756,
      "learning_rate": 2e-05,
      "loss": 0.0026375213637948036,
      "step": 47
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.03871266171336174,
      "learning_rate": 2e-05,
      "loss": 0.004687938839197159,
      "step": 48
    },
    {
      "epoch": 0.392,
      "grad_norm": 0.040328506380319595,
      "learning_rate": 2e-05,
      "loss": 0.006280779838562012,
      "step": 49
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.04712209478020668,
      "learning_rate": 2e-05,
      "loss": 0.0031323714647442102,
      "step": 50
    },
    {
      "epoch": 0.408,
      "grad_norm": 0.045797791332006454,
      "learning_rate": 2e-05,
      "loss": 0.004443546291440725,
      "step": 51
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.06185959652066231,
      "learning_rate": 2e-05,
      "loss": 0.008573911152780056,
      "step": 52
    },
    {
      "epoch": 0.424,
      "grad_norm": 0.059398140758275986,
      "learning_rate": 2e-05,
      "loss": 0.00942009873688221,
      "step": 53
    },
    {
      "epoch": 0.432,
      "grad_norm": 0.07633177191019058,
      "learning_rate": 2e-05,
      "loss": 0.009616912342607975,
      "step": 54
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.053814005106687546,
      "learning_rate": 2e-05,
      "loss": 0.007603101897984743,
      "step": 55
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.05707194656133652,
      "learning_rate": 2e-05,
      "loss": 0.005355853587388992,
      "step": 56
    },
    {
      "epoch": 0.456,
      "grad_norm": 0.04392722621560097,
      "learning_rate": 2e-05,
      "loss": 0.003092748112976551,
      "step": 57
    },
    {
      "epoch": 0.464,
      "grad_norm": 0.027375129982829094,
      "learning_rate": 2e-05,
      "loss": 0.003245085943490267,
      "step": 58
    },
    {
      "epoch": 0.472,
      "grad_norm": 0.05855637416243553,
      "learning_rate": 2e-05,
      "loss": 0.006621942389756441,
      "step": 59
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.040302883833646774,
      "learning_rate": 2e-05,
      "loss": 0.004884965717792511,
      "step": 60
    },
    {
      "epoch": 0.488,
      "grad_norm": 0.038790635764598846,
      "learning_rate": 2e-05,
      "loss": 0.0041805170476436615,
      "step": 61
    },
    {
      "epoch": 0.496,
      "grad_norm": 0.059503670781850815,
      "learning_rate": 2e-05,
      "loss": 0.0071491943672299385,
      "step": 62
    },
    {
      "epoch": 0.504,
      "grad_norm": 0.059957440942525864,
      "learning_rate": 2e-05,
      "loss": 0.006595572456717491,
      "step": 63
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.05570148676633835,
      "learning_rate": 2e-05,
      "loss": 0.007463263813406229,
      "step": 64
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.056187067180871964,
      "learning_rate": 2e-05,
      "loss": 0.004543005023151636,
      "step": 65
    },
    {
      "epoch": 0.528,
      "grad_norm": 0.04404418170452118,
      "learning_rate": 2e-05,
      "loss": 0.006366059184074402,
      "step": 66
    },
    {
      "epoch": 0.536,
      "grad_norm": 0.049447719007730484,
      "learning_rate": 2e-05,
      "loss": 0.006581606809049845,
      "step": 67
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.03419354185461998,
      "learning_rate": 2e-05,
      "loss": 0.0035948362201452255,
      "step": 68
    },
    {
      "epoch": 0.552,
      "grad_norm": 0.05780700221657753,
      "learning_rate": 2e-05,
      "loss": 0.005125825759023428,
      "step": 69
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.06544717401266098,
      "learning_rate": 2e-05,
      "loss": 0.006060135085135698,
      "step": 70
    },
    {
      "epoch": 0.568,
      "grad_norm": 0.04413054138422012,
      "learning_rate": 2e-05,
      "loss": 0.003213978838175535,
      "step": 71
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.039240192621946335,
      "learning_rate": 2e-05,
      "loss": 0.004292209167033434,
      "step": 72
    },
    {
      "epoch": 0.584,
      "grad_norm": 0.060329239815473557,
      "learning_rate": 2e-05,
      "loss": 0.006161934696137905,
      "step": 73
    },
    {
      "epoch": 0.592,
      "grad_norm": 0.06489120423793793,
      "learning_rate": 2e-05,
      "loss": 0.0032440992072224617,
      "step": 74
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.04400647059082985,
      "learning_rate": 2e-05,
      "loss": 0.004546411335468292,
      "step": 75
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.046490587294101715,
      "learning_rate": 2e-05,
      "loss": 0.00506614800542593,
      "step": 76
    },
    {
      "epoch": 0.616,
      "grad_norm": 0.03474031388759613,
      "learning_rate": 2e-05,
      "loss": 0.003143966430798173,
      "step": 77
    },
    {
      "epoch": 0.624,
      "grad_norm": 0.04975699633359909,
      "learning_rate": 2e-05,
      "loss": 0.004066984634846449,
      "step": 78
    },
    {
      "epoch": 0.632,
      "grad_norm": 0.06441677361726761,
      "learning_rate": 2e-05,
      "loss": 0.007056248374283314,
      "step": 79
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.05794770270586014,
      "learning_rate": 2e-05,
      "loss": 0.0037886211648583412,
      "step": 80
    },
    {
      "epoch": 0.648,
      "grad_norm": 0.06725575029850006,
      "learning_rate": 2e-05,
      "loss": 0.005529267713427544,
      "step": 81
    },
    {
      "epoch": 0.656,
      "grad_norm": 0.05235245078802109,
      "learning_rate": 2e-05,
      "loss": 0.0031472702976316214,
      "step": 82
    },
    {
      "epoch": 0.664,
      "grad_norm": 0.0473208874464035,
      "learning_rate": 2e-05,
      "loss": 0.004731162916868925,
      "step": 83
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.05135403573513031,
      "learning_rate": 2e-05,
      "loss": 0.005146307405084372,
      "step": 84
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.04229608178138733,
      "learning_rate": 2e-05,
      "loss": 0.004758044611662626,
      "step": 85
    },
    {
      "epoch": 0.688,
      "grad_norm": 0.04035644605755806,
      "learning_rate": 2e-05,
      "loss": 0.0043296488001942635,
      "step": 86
    },
    {
      "epoch": 0.696,
      "grad_norm": 0.060147274285554886,
      "learning_rate": 2e-05,
      "loss": 0.008551320061087608,
      "step": 87
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.0395248718559742,
      "learning_rate": 2e-05,
      "loss": 0.0024903551675379276,
      "step": 88
    },
    {
      "epoch": 0.712,
      "grad_norm": 0.071822389960289,
      "learning_rate": 2e-05,
      "loss": 0.008494703099131584,
      "step": 89
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.058960266411304474,
      "learning_rate": 2e-05,
      "loss": 0.006603310350328684,
      "step": 90
    },
    {
      "epoch": 0.728,
      "grad_norm": 0.05052534490823746,
      "learning_rate": 2e-05,
      "loss": 0.0058289458975195885,
      "step": 91
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.049510154873132706,
      "learning_rate": 2e-05,
      "loss": 0.003644926007837057,
      "step": 92
    },
    {
      "epoch": 0.744,
      "grad_norm": 0.0739966556429863,
      "learning_rate": 2e-05,
      "loss": 0.0028007840737700462,
      "step": 93
    },
    {
      "epoch": 0.752,
      "grad_norm": 0.07646612823009491,
      "learning_rate": 2e-05,
      "loss": 0.010534452274441719,
      "step": 94
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.05939766764640808,
      "learning_rate": 2e-05,
      "loss": 0.004194422625005245,
      "step": 95
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.049664683640003204,
      "learning_rate": 2e-05,
      "loss": 0.003597400849685073,
      "step": 96
    },
    {
      "epoch": 0.776,
      "grad_norm": 0.13988253474235535,
      "learning_rate": 2e-05,
      "loss": 0.006600011605769396,
      "step": 97
    },
    {
      "epoch": 0.784,
      "grad_norm": 0.06141381338238716,
      "learning_rate": 2e-05,
      "loss": 0.004176464397460222,
      "step": 98
    },
    {
      "epoch": 0.792,
      "grad_norm": 0.040125612169504166,
      "learning_rate": 2e-05,
      "loss": 0.0029954789206385612,
      "step": 99
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.05379870533943176,
      "learning_rate": 2e-05,
      "loss": 0.005120614543557167,
      "step": 100
    },
    {
      "epoch": 0.808,
      "grad_norm": 0.04878966137766838,
      "learning_rate": 2e-05,
      "loss": 0.0049518863670527935,
      "step": 101
    },
    {
      "epoch": 0.816,
      "grad_norm": 0.0832071602344513,
      "learning_rate": 2e-05,
      "loss": 0.003636852605268359,
      "step": 102
    },
    {
      "epoch": 0.824,
      "grad_norm": 0.1109263077378273,
      "learning_rate": 2e-05,
      "loss": 0.011921115219593048,
      "step": 103
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.037266287952661514,
      "learning_rate": 2e-05,
      "loss": 0.002762642689049244,
      "step": 104
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.044354166835546494,
      "learning_rate": 2e-05,
      "loss": 0.004988430067896843,
      "step": 105
    },
    {
      "epoch": 0.848,
      "grad_norm": 0.03570897877216339,
      "learning_rate": 2e-05,
      "loss": 0.002259196015074849,
      "step": 106
    },
    {
      "epoch": 0.856,
      "grad_norm": 0.059259530156850815,
      "learning_rate": 2e-05,
      "loss": 0.006721946410834789,
      "step": 107
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.05184999480843544,
      "learning_rate": 2e-05,
      "loss": 0.005531419534236193,
      "step": 108
    },
    {
      "epoch": 0.872,
      "grad_norm": 0.08037418127059937,
      "learning_rate": 2e-05,
      "loss": 0.006799847353249788,
      "step": 109
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.039056453853845596,
      "learning_rate": 2e-05,
      "loss": 0.00481954962015152,
      "step": 110
    },
    {
      "epoch": 0.888,
      "grad_norm": 0.05626671388745308,
      "learning_rate": 2e-05,
      "loss": 0.0032779546454548836,
      "step": 111
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.05177405849099159,
      "learning_rate": 2e-05,
      "loss": 0.004294276237487793,
      "step": 112
    },
    {
      "epoch": 0.904,
      "grad_norm": 0.029522892087697983,
      "learning_rate": 2e-05,
      "loss": 0.0030598388984799385,
      "step": 113
    },
    {
      "epoch": 0.912,
      "grad_norm": 0.05130866542458534,
      "learning_rate": 2e-05,
      "loss": 0.005800556857138872,
      "step": 114
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.021749891340732574,
      "learning_rate": 2e-05,
      "loss": 0.001492157345637679,
      "step": 115
    },
    {
      "epoch": 0.928,
      "grad_norm": 0.0728369727730751,
      "learning_rate": 2e-05,
      "loss": 0.008168019354343414,
      "step": 116
    },
    {
      "epoch": 0.936,
      "grad_norm": 0.051655277609825134,
      "learning_rate": 2e-05,
      "loss": 0.004517991095781326,
      "step": 117
    },
    {
      "epoch": 0.944,
      "grad_norm": 0.028527911752462387,
      "learning_rate": 2e-05,
      "loss": 0.004356182646006346,
      "step": 118
    },
    {
      "epoch": 0.952,
      "grad_norm": 0.04092099890112877,
      "learning_rate": 2e-05,
      "loss": 0.0035778400488197803,
      "step": 119
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.06751365959644318,
      "learning_rate": 2e-05,
      "loss": 0.006765933241695166,
      "step": 120
    },
    {
      "epoch": 0.968,
      "grad_norm": 0.06141749769449234,
      "learning_rate": 2e-05,
      "loss": 0.010381967760622501,
      "step": 121
    },
    {
      "epoch": 0.976,
      "grad_norm": 0.0584125854074955,
      "learning_rate": 2e-05,
      "loss": 0.0059956214390695095,
      "step": 122
    },
    {
      "epoch": 0.984,
      "grad_norm": 0.06699343770742416,
      "learning_rate": 2e-05,
      "loss": 0.006007581949234009,
      "step": 123
    },
    {
      "epoch": 0.992,
      "grad_norm": 0.04457642510533333,
      "learning_rate": 2e-05,
      "loss": 0.00433978158980608,
      "step": 124
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.0724361315369606,
      "learning_rate": 2e-05,
      "loss": 0.009294194169342518,
      "step": 125
    },
    {
      "epoch": 1.008,
      "grad_norm": 0.041911620646715164,
      "learning_rate": 2e-05,
      "loss": 0.0031240973621606827,
      "step": 126
    },
    {
      "epoch": 1.016,
      "grad_norm": 0.03944513201713562,
      "learning_rate": 2e-05,
      "loss": 0.005666844546794891,
      "step": 127
    },
    {
      "epoch": 1.024,
      "grad_norm": 0.024236207827925682,
      "learning_rate": 2e-05,
      "loss": 0.002599143423140049,
      "step": 128
    },
    {
      "epoch": 1.032,
      "grad_norm": 0.02648847922682762,
      "learning_rate": 2e-05,
      "loss": 0.002489139325916767,
      "step": 129
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.03522297367453575,
      "learning_rate": 2e-05,
      "loss": 0.0031560207717120647,
      "step": 130
    },
    {
      "epoch": 1.048,
      "grad_norm": 0.03963733837008476,
      "learning_rate": 2e-05,
      "loss": 0.002944512525573373,
      "step": 131
    },
    {
      "epoch": 1.056,
      "grad_norm": 0.043245717883110046,
      "learning_rate": 2e-05,
      "loss": 0.005929629784077406,
      "step": 132
    },
    {
      "epoch": 1.064,
      "grad_norm": 0.04024028778076172,
      "learning_rate": 2e-05,
      "loss": 0.0028088355902582407,
      "step": 133
    },
    {
      "epoch": 1.072,
      "grad_norm": 0.03739921376109123,
      "learning_rate": 2e-05,
      "loss": 0.0025795348919928074,
      "step": 134
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.053612496703863144,
      "learning_rate": 2e-05,
      "loss": 0.0051528215408325195,
      "step": 135
    },
    {
      "epoch": 1.088,
      "grad_norm": 0.03874121978878975,
      "learning_rate": 2e-05,
      "loss": 0.0029356672894209623,
      "step": 136
    },
    {
      "epoch": 1.096,
      "grad_norm": 0.04209478199481964,
      "learning_rate": 2e-05,
      "loss": 0.004753364250063896,
      "step": 137
    },
    {
      "epoch": 1.104,
      "grad_norm": 0.032321907579898834,
      "learning_rate": 2e-05,
      "loss": 0.002570532029494643,
      "step": 138
    },
    {
      "epoch": 1.112,
      "grad_norm": 0.03770575299859047,
      "learning_rate": 2e-05,
      "loss": 0.0032067985739558935,
      "step": 139
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.042145032435655594,
      "learning_rate": 2e-05,
      "loss": 0.004715348593890667,
      "step": 140
    },
    {
      "epoch": 1.1280000000000001,
      "grad_norm": 0.04259483888745308,
      "learning_rate": 2e-05,
      "loss": 0.0040532853454351425,
      "step": 141
    },
    {
      "epoch": 1.1360000000000001,
      "grad_norm": 0.04432355985045433,
      "learning_rate": 2e-05,
      "loss": 0.004878481850028038,
      "step": 142
    },
    {
      "epoch": 1.144,
      "grad_norm": 0.04144922271370888,
      "learning_rate": 2e-05,
      "loss": 0.0035966027062386274,
      "step": 143
    },
    {
      "epoch": 1.152,
      "grad_norm": 0.034188415855169296,
      "learning_rate": 2e-05,
      "loss": 0.0035179737024009228,
      "step": 144
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.04314472898840904,
      "learning_rate": 2e-05,
      "loss": 0.00275869807228446,
      "step": 145
    },
    {
      "epoch": 1.168,
      "grad_norm": 0.03345927596092224,
      "learning_rate": 2e-05,
      "loss": 0.004454055335372686,
      "step": 146
    },
    {
      "epoch": 1.176,
      "grad_norm": 0.032709989696741104,
      "learning_rate": 2e-05,
      "loss": 0.002561516361311078,
      "step": 147
    },
    {
      "epoch": 1.184,
      "grad_norm": 0.037629563361406326,
      "learning_rate": 2e-05,
      "loss": 0.002726494800299406,
      "step": 148
    },
    {
      "epoch": 1.192,
      "grad_norm": 0.03565853834152222,
      "learning_rate": 2e-05,
      "loss": 0.005714224185794592,
      "step": 149
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.04101553559303284,
      "learning_rate": 2e-05,
      "loss": 0.00477135693654418,
      "step": 150
    },
    {
      "epoch": 1.208,
      "grad_norm": 0.02103736251592636,
      "learning_rate": 2e-05,
      "loss": 0.00214054505340755,
      "step": 151
    },
    {
      "epoch": 1.216,
      "grad_norm": 0.038353558629751205,
      "learning_rate": 2e-05,
      "loss": 0.0023091635666787624,
      "step": 152
    },
    {
      "epoch": 1.224,
      "grad_norm": 0.03039981611073017,
      "learning_rate": 2e-05,
      "loss": 0.002429583575576544,
      "step": 153
    },
    {
      "epoch": 1.232,
      "grad_norm": 0.038060858845710754,
      "learning_rate": 2e-05,
      "loss": 0.0024876513052731752,
      "step": 154
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.10335491597652435,
      "learning_rate": 2e-05,
      "loss": 0.0025280544068664312,
      "step": 155
    },
    {
      "epoch": 1.248,
      "grad_norm": 0.040877990424633026,
      "learning_rate": 2e-05,
      "loss": 0.004313280805945396,
      "step": 156
    },
    {
      "epoch": 1.256,
      "grad_norm": 0.05562249571084976,
      "learning_rate": 2e-05,
      "loss": 0.0048119621351361275,
      "step": 157
    },
    {
      "epoch": 1.264,
      "grad_norm": 0.05108984187245369,
      "learning_rate": 2e-05,
      "loss": 0.00518863694742322,
      "step": 158
    },
    {
      "epoch": 1.272,
      "grad_norm": 0.05357106775045395,
      "learning_rate": 2e-05,
      "loss": 0.0024496042169630527,
      "step": 159
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.037901945412158966,
      "learning_rate": 2e-05,
      "loss": 0.002475207205861807,
      "step": 160
    },
    {
      "epoch": 1.288,
      "grad_norm": 0.0420001782476902,
      "learning_rate": 2e-05,
      "loss": 0.0058222366496920586,
      "step": 161
    },
    {
      "epoch": 1.296,
      "grad_norm": 0.05443611368536949,
      "learning_rate": 2e-05,
      "loss": 0.0052161430940032005,
      "step": 162
    },
    {
      "epoch": 1.304,
      "grad_norm": 0.05211922898888588,
      "learning_rate": 2e-05,
      "loss": 0.004603986628353596,
      "step": 163
    },
    {
      "epoch": 1.312,
      "grad_norm": 0.04726783558726311,
      "learning_rate": 2e-05,
      "loss": 0.004252967424690723,
      "step": 164
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.07070634514093399,
      "learning_rate": 2e-05,
      "loss": 0.006596374791115522,
      "step": 165
    },
    {
      "epoch": 1.328,
      "grad_norm": 0.05988767370581627,
      "learning_rate": 2e-05,
      "loss": 0.006062244065105915,
      "step": 166
    },
    {
      "epoch": 1.336,
      "grad_norm": 0.06943166255950928,
      "learning_rate": 2e-05,
      "loss": 0.007745644543319941,
      "step": 167
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 0.03787314146757126,
      "learning_rate": 2e-05,
      "loss": 0.003922807518392801,
      "step": 168
    },
    {
      "epoch": 1.3519999999999999,
      "grad_norm": 0.02878367155790329,
      "learning_rate": 2e-05,
      "loss": 0.0019241905538365245,
      "step": 169
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.05218566954135895,
      "learning_rate": 2e-05,
      "loss": 0.0058232140727341175,
      "step": 170
    },
    {
      "epoch": 1.3679999999999999,
      "grad_norm": 0.06744556874036789,
      "learning_rate": 2e-05,
      "loss": 0.004936105106025934,
      "step": 171
    },
    {
      "epoch": 1.376,
      "grad_norm": 0.04349220544099808,
      "learning_rate": 2e-05,
      "loss": 0.003136698855087161,
      "step": 172
    },
    {
      "epoch": 1.384,
      "grad_norm": 0.046757787466049194,
      "learning_rate": 2e-05,
      "loss": 0.004662223160266876,
      "step": 173
    },
    {
      "epoch": 1.392,
      "grad_norm": 0.03483404964208603,
      "learning_rate": 2e-05,
      "loss": 0.007330790627747774,
      "step": 174
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.050741445273160934,
      "learning_rate": 2e-05,
      "loss": 0.005321471951901913,
      "step": 175
    },
    {
      "epoch": 1.408,
      "grad_norm": 0.06053789332509041,
      "learning_rate": 2e-05,
      "loss": 0.007614850997924805,
      "step": 176
    },
    {
      "epoch": 1.416,
      "grad_norm": 0.045350395143032074,
      "learning_rate": 2e-05,
      "loss": 0.003982958849519491,
      "step": 177
    },
    {
      "epoch": 1.424,
      "grad_norm": 0.04105447977781296,
      "learning_rate": 2e-05,
      "loss": 0.0032091487664729357,
      "step": 178
    },
    {
      "epoch": 1.432,
      "grad_norm": 0.03485438972711563,
      "learning_rate": 2e-05,
      "loss": 0.0034181310329586267,
      "step": 179
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.0427364781498909,
      "learning_rate": 2e-05,
      "loss": 0.005363878328353167,
      "step": 180
    },
    {
      "epoch": 1.448,
      "grad_norm": 0.031005240976810455,
      "learning_rate": 2e-05,
      "loss": 0.003898187540471554,
      "step": 181
    },
    {
      "epoch": 1.456,
      "grad_norm": 0.030742423608899117,
      "learning_rate": 2e-05,
      "loss": 0.0026354389265179634,
      "step": 182
    },
    {
      "epoch": 1.464,
      "grad_norm": 0.04213688522577286,
      "learning_rate": 2e-05,
      "loss": 0.003235624171793461,
      "step": 183
    },
    {
      "epoch": 1.472,
      "grad_norm": 0.06017177179455757,
      "learning_rate": 2e-05,
      "loss": 0.004921246785670519,
      "step": 184
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.05274427682161331,
      "learning_rate": 2e-05,
      "loss": 0.006431959569454193,
      "step": 185
    },
    {
      "epoch": 1.488,
      "grad_norm": 0.03465743735432625,
      "learning_rate": 2e-05,
      "loss": 0.0017982947174459696,
      "step": 186
    },
    {
      "epoch": 1.496,
      "grad_norm": 0.031407665461301804,
      "learning_rate": 2e-05,
      "loss": 0.002308888593688607,
      "step": 187
    },
    {
      "epoch": 1.504,
      "grad_norm": 0.04751557856798172,
      "learning_rate": 2e-05,
      "loss": 0.0022526727989315987,
      "step": 188
    },
    {
      "epoch": 1.512,
      "grad_norm": 0.03473098948597908,
      "learning_rate": 2e-05,
      "loss": 0.0023300114553421736,
      "step": 189
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.02745967172086239,
      "learning_rate": 2e-05,
      "loss": 0.002407602034509182,
      "step": 190
    },
    {
      "epoch": 1.528,
      "grad_norm": 0.05958602949976921,
      "learning_rate": 2e-05,
      "loss": 0.007107679732143879,
      "step": 191
    },
    {
      "epoch": 1.536,
      "grad_norm": 0.05794493481516838,
      "learning_rate": 2e-05,
      "loss": 0.006767779588699341,
      "step": 192
    },
    {
      "epoch": 1.544,
      "grad_norm": 0.037513379007577896,
      "learning_rate": 2e-05,
      "loss": 0.003455360187217593,
      "step": 193
    },
    {
      "epoch": 1.552,
      "grad_norm": 0.03977490961551666,
      "learning_rate": 2e-05,
      "loss": 0.004349147900938988,
      "step": 194
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.03297000005841255,
      "learning_rate": 2e-05,
      "loss": 0.004090302158147097,
      "step": 195
    },
    {
      "epoch": 1.568,
      "grad_norm": 0.03089851886034012,
      "learning_rate": 2e-05,
      "loss": 0.0032683194149285555,
      "step": 196
    },
    {
      "epoch": 1.576,
      "grad_norm": 0.03224420174956322,
      "learning_rate": 2e-05,
      "loss": 0.0024244794622063637,
      "step": 197
    },
    {
      "epoch": 1.584,
      "grad_norm": 0.030442802235484123,
      "learning_rate": 2e-05,
      "loss": 0.0014301001792773604,
      "step": 198
    },
    {
      "epoch": 1.592,
      "grad_norm": 0.05126398056745529,
      "learning_rate": 2e-05,
      "loss": 0.0027298659551888704,
      "step": 199
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.05423342436552048,
      "learning_rate": 2e-05,
      "loss": 0.006995318457484245,
      "step": 200
    },
    {
      "epoch": 1.608,
      "grad_norm": 0.02536446414887905,
      "learning_rate": 2e-05,
      "loss": 0.0029984633438289165,
      "step": 201
    },
    {
      "epoch": 1.616,
      "grad_norm": 0.03072509542107582,
      "learning_rate": 2e-05,
      "loss": 0.0033400985412299633,
      "step": 202
    },
    {
      "epoch": 1.624,
      "grad_norm": 0.055368877947330475,
      "learning_rate": 2e-05,
      "loss": 0.004085185006260872,
      "step": 203
    },
    {
      "epoch": 1.6320000000000001,
      "grad_norm": 0.03939943388104439,
      "learning_rate": 2e-05,
      "loss": 0.003322000615298748,
      "step": 204
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.044486552476882935,
      "learning_rate": 2e-05,
      "loss": 0.002586575224995613,
      "step": 205
    },
    {
      "epoch": 1.6480000000000001,
      "grad_norm": 0.05059683322906494,
      "learning_rate": 2e-05,
      "loss": 0.010476172901690006,
      "step": 206
    },
    {
      "epoch": 1.6560000000000001,
      "grad_norm": 0.04618003964424133,
      "learning_rate": 2e-05,
      "loss": 0.004687571432441473,
      "step": 207
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 0.03308900445699692,
      "learning_rate": 2e-05,
      "loss": 0.004028619267046452,
      "step": 208
    },
    {
      "epoch": 1.6720000000000002,
      "grad_norm": 0.038209252059459686,
      "learning_rate": 2e-05,
      "loss": 0.0027929157949984074,
      "step": 209
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.034491200000047684,
      "learning_rate": 2e-05,
      "loss": 0.001778338453732431,
      "step": 210
    },
    {
      "epoch": 1.688,
      "grad_norm": 0.07821262627840042,
      "learning_rate": 2e-05,
      "loss": 0.005375068634748459,
      "step": 211
    },
    {
      "epoch": 1.696,
      "grad_norm": 0.04657049477100372,
      "learning_rate": 2e-05,
      "loss": 0.003136474872007966,
      "step": 212
    },
    {
      "epoch": 1.704,
      "grad_norm": 0.05357731506228447,
      "learning_rate": 2e-05,
      "loss": 0.006239030975848436,
      "step": 213
    },
    {
      "epoch": 1.712,
      "grad_norm": 0.04918161407113075,
      "learning_rate": 2e-05,
      "loss": 0.004385227337479591,
      "step": 214
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.04051123186945915,
      "learning_rate": 2e-05,
      "loss": 0.0024626629892736673,
      "step": 215
    },
    {
      "epoch": 1.728,
      "grad_norm": 0.034734904766082764,
      "learning_rate": 2e-05,
      "loss": 0.0024731624871492386,
      "step": 216
    },
    {
      "epoch": 1.736,
      "grad_norm": 0.06079041212797165,
      "learning_rate": 2e-05,
      "loss": 0.004821632523089647,
      "step": 217
    },
    {
      "epoch": 1.744,
      "grad_norm": 0.04052048176527023,
      "learning_rate": 2e-05,
      "loss": 0.003583197481930256,
      "step": 218
    },
    {
      "epoch": 1.752,
      "grad_norm": 0.03803209960460663,
      "learning_rate": 2e-05,
      "loss": 0.0032860925421118736,
      "step": 219
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.03718697279691696,
      "learning_rate": 2e-05,
      "loss": 0.0028506568633019924,
      "step": 220
    },
    {
      "epoch": 1.768,
      "grad_norm": 0.020328527316451073,
      "learning_rate": 2e-05,
      "loss": 0.0030127556528896093,
      "step": 221
    },
    {
      "epoch": 1.776,
      "grad_norm": 0.03647777810692787,
      "learning_rate": 2e-05,
      "loss": 0.0029757029842585325,
      "step": 222
    },
    {
      "epoch": 1.784,
      "grad_norm": 0.03103819489479065,
      "learning_rate": 2e-05,
      "loss": 0.002474813023582101,
      "step": 223
    },
    {
      "epoch": 1.792,
      "grad_norm": 0.031560298055410385,
      "learning_rate": 2e-05,
      "loss": 0.002314931945875287,
      "step": 224
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.03549206256866455,
      "learning_rate": 2e-05,
      "loss": 0.0032754004932940006,
      "step": 225
    },
    {
      "epoch": 1.808,
      "grad_norm": 0.03429936245083809,
      "learning_rate": 2e-05,
      "loss": 0.003921601455658674,
      "step": 226
    },
    {
      "epoch": 1.8159999999999998,
      "grad_norm": 0.06855639815330505,
      "learning_rate": 2e-05,
      "loss": 0.006101913750171661,
      "step": 227
    },
    {
      "epoch": 1.8239999999999998,
      "grad_norm": 0.08064403384923935,
      "learning_rate": 2e-05,
      "loss": 0.004588215611875057,
      "step": 228
    },
    {
      "epoch": 1.8319999999999999,
      "grad_norm": 0.03363880142569542,
      "learning_rate": 2e-05,
      "loss": 0.001759383245371282,
      "step": 229
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.04351300746202469,
      "learning_rate": 2e-05,
      "loss": 0.0032918578945100307,
      "step": 230
    },
    {
      "epoch": 1.8479999999999999,
      "grad_norm": 0.024159353226423264,
      "learning_rate": 2e-05,
      "loss": 0.0019000337924808264,
      "step": 231
    },
    {
      "epoch": 1.8559999999999999,
      "grad_norm": 0.04056349769234657,
      "learning_rate": 2e-05,
      "loss": 0.003138928906992078,
      "step": 232
    },
    {
      "epoch": 1.8639999999999999,
      "grad_norm": 0.026023566722869873,
      "learning_rate": 2e-05,
      "loss": 0.0033341734670102596,
      "step": 233
    },
    {
      "epoch": 1.8719999999999999,
      "grad_norm": 0.06581102311611176,
      "learning_rate": 2e-05,
      "loss": 0.0065653664059937,
      "step": 234
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.04903842508792877,
      "learning_rate": 2e-05,
      "loss": 0.005071278661489487,
      "step": 235
    },
    {
      "epoch": 1.888,
      "grad_norm": 0.09484432637691498,
      "learning_rate": 2e-05,
      "loss": 0.0026917962823063135,
      "step": 236
    },
    {
      "epoch": 1.896,
      "grad_norm": 0.029802817851305008,
      "learning_rate": 2e-05,
      "loss": 0.0020737922750413418,
      "step": 237
    },
    {
      "epoch": 1.904,
      "grad_norm": 0.030020302161574364,
      "learning_rate": 2e-05,
      "loss": 0.001601328724063933,
      "step": 238
    },
    {
      "epoch": 1.912,
      "grad_norm": 0.023855257779359818,
      "learning_rate": 2e-05,
      "loss": 0.002171756699681282,
      "step": 239
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.04743681848049164,
      "learning_rate": 2e-05,
      "loss": 0.005675522144883871,
      "step": 240
    },
    {
      "epoch": 1.928,
      "grad_norm": 0.05006203055381775,
      "learning_rate": 2e-05,
      "loss": 0.005861939862370491,
      "step": 241
    },
    {
      "epoch": 1.936,
      "grad_norm": 0.04128265008330345,
      "learning_rate": 2e-05,
      "loss": 0.005003426223993301,
      "step": 242
    },
    {
      "epoch": 1.944,
      "grad_norm": 0.06207670643925667,
      "learning_rate": 2e-05,
      "loss": 0.004483950790017843,
      "step": 243
    },
    {
      "epoch": 1.952,
      "grad_norm": 0.07824505865573883,
      "learning_rate": 2e-05,
      "loss": 0.004859112203121185,
      "step": 244
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.04579395800828934,
      "learning_rate": 2e-05,
      "loss": 0.004692354239523411,
      "step": 245
    },
    {
      "epoch": 1.968,
      "grad_norm": 0.04180062189698219,
      "learning_rate": 2e-05,
      "loss": 0.00455811619758606,
      "step": 246
    },
    {
      "epoch": 1.976,
      "grad_norm": 0.03964953497052193,
      "learning_rate": 2e-05,
      "loss": 0.0028610117733478546,
      "step": 247
    },
    {
      "epoch": 1.984,
      "grad_norm": 0.03513772413134575,
      "learning_rate": 2e-05,
      "loss": 0.0025510897394269705,
      "step": 248
    },
    {
      "epoch": 1.992,
      "grad_norm": 0.030972128733992577,
      "learning_rate": 2e-05,
      "loss": 0.00266153528355062,
      "step": 249
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.06495940685272217,
      "learning_rate": 2e-05,
      "loss": 0.005316338501870632,
      "step": 250
    },
    {
      "epoch": 2.008,
      "grad_norm": 0.03911746293306351,
      "learning_rate": 2e-05,
      "loss": 0.003454022342339158,
      "step": 251
    },
    {
      "epoch": 2.016,
      "grad_norm": 0.03907843679189682,
      "learning_rate": 2e-05,
      "loss": 0.002617109566926956,
      "step": 252
    },
    {
      "epoch": 2.024,
      "grad_norm": 0.0325784757733345,
      "learning_rate": 2e-05,
      "loss": 0.003027692437171936,
      "step": 253
    },
    {
      "epoch": 2.032,
      "grad_norm": 0.04280916228890419,
      "learning_rate": 2e-05,
      "loss": 0.003725123591721058,
      "step": 254
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.03285227715969086,
      "learning_rate": 2e-05,
      "loss": 0.002418406307697296,
      "step": 255
    },
    {
      "epoch": 2.048,
      "grad_norm": 0.04505843669176102,
      "learning_rate": 2e-05,
      "loss": 0.0030923697631806135,
      "step": 256
    },
    {
      "epoch": 2.056,
      "grad_norm": 0.02693861722946167,
      "learning_rate": 2e-05,
      "loss": 0.0029823114164173603,
      "step": 257
    },
    {
      "epoch": 2.064,
      "grad_norm": 0.03501451015472412,
      "learning_rate": 2e-05,
      "loss": 0.0022289499174803495,
      "step": 258
    },
    {
      "epoch": 2.072,
      "grad_norm": 0.04407954588532448,
      "learning_rate": 2e-05,
      "loss": 0.005173118785023689,
      "step": 259
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.03353921324014664,
      "learning_rate": 2e-05,
      "loss": 0.003529382636770606,
      "step": 260
    },
    {
      "epoch": 2.088,
      "grad_norm": 0.03029395453631878,
      "learning_rate": 2e-05,
      "loss": 0.0025696109514683485,
      "step": 261
    },
    {
      "epoch": 2.096,
      "grad_norm": 0.043411292135715485,
      "learning_rate": 2e-05,
      "loss": 0.0032275894191116095,
      "step": 262
    },
    {
      "epoch": 2.104,
      "grad_norm": 0.025156555697321892,
      "learning_rate": 2e-05,
      "loss": 0.0019941977225244045,
      "step": 263
    },
    {
      "epoch": 2.112,
      "grad_norm": 0.05474105849862099,
      "learning_rate": 2e-05,
      "loss": 0.006130381021648645,
      "step": 264
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.026152821257710457,
      "learning_rate": 2e-05,
      "loss": 0.0037242607213556767,
      "step": 265
    },
    {
      "epoch": 2.128,
      "grad_norm": 0.04658479988574982,
      "learning_rate": 2e-05,
      "loss": 0.0027500735595822334,
      "step": 266
    },
    {
      "epoch": 2.136,
      "grad_norm": 0.04310692846775055,
      "learning_rate": 2e-05,
      "loss": 0.0021111357491463423,
      "step": 267
    },
    {
      "epoch": 2.144,
      "grad_norm": 0.03860605135560036,
      "learning_rate": 2e-05,
      "loss": 0.004491395782679319,
      "step": 268
    },
    {
      "epoch": 2.152,
      "grad_norm": 0.019513150677084923,
      "learning_rate": 2e-05,
      "loss": 0.0019580726511776447,
      "step": 269
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.03170303627848625,
      "learning_rate": 2e-05,
      "loss": 0.001965203322470188,
      "step": 270
    },
    {
      "epoch": 2.168,
      "grad_norm": 0.02094845101237297,
      "learning_rate": 2e-05,
      "loss": 0.001287441118620336,
      "step": 271
    },
    {
      "epoch": 2.176,
      "grad_norm": 0.03304935246706009,
      "learning_rate": 2e-05,
      "loss": 0.0032492834143340588,
      "step": 272
    },
    {
      "epoch": 2.184,
      "grad_norm": 0.03120725229382515,
      "learning_rate": 2e-05,
      "loss": 0.0029026831034570932,
      "step": 273
    },
    {
      "epoch": 2.192,
      "grad_norm": 0.03816477581858635,
      "learning_rate": 2e-05,
      "loss": 0.0024198577739298344,
      "step": 274
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.039687663316726685,
      "learning_rate": 2e-05,
      "loss": 0.0031529159750789404,
      "step": 275
    },
    {
      "epoch": 2.208,
      "grad_norm": 0.026106711477041245,
      "learning_rate": 2e-05,
      "loss": 0.002224068157374859,
      "step": 276
    },
    {
      "epoch": 2.216,
      "grad_norm": 0.027437372133135796,
      "learning_rate": 2e-05,
      "loss": 0.0014647672651335597,
      "step": 277
    },
    {
      "epoch": 2.224,
      "grad_norm": 0.05910545587539673,
      "learning_rate": 2e-05,
      "loss": 0.00243214494548738,
      "step": 278
    },
    {
      "epoch": 2.232,
      "grad_norm": 0.02404620312154293,
      "learning_rate": 2e-05,
      "loss": 0.00222192844375968,
      "step": 279
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.03369680047035217,
      "learning_rate": 2e-05,
      "loss": 0.001881018397398293,
      "step": 280
    },
    {
      "epoch": 2.248,
      "grad_norm": 0.039129581302404404,
      "learning_rate": 2e-05,
      "loss": 0.0031921733170747757,
      "step": 281
    },
    {
      "epoch": 2.2560000000000002,
      "grad_norm": 0.026752755045890808,
      "learning_rate": 2e-05,
      "loss": 0.0027538840658962727,
      "step": 282
    },
    {
      "epoch": 2.2640000000000002,
      "grad_norm": 0.07003916054964066,
      "learning_rate": 2e-05,
      "loss": 0.005947021301835775,
      "step": 283
    },
    {
      "epoch": 2.2720000000000002,
      "grad_norm": 0.031368181109428406,
      "learning_rate": 2e-05,
      "loss": 0.0035742626059800386,
      "step": 284
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 0.027074171230196953,
      "learning_rate": 2e-05,
      "loss": 0.0021643084473907948,
      "step": 285
    },
    {
      "epoch": 2.288,
      "grad_norm": 0.023025641217827797,
      "learning_rate": 2e-05,
      "loss": 0.0017899582162499428,
      "step": 286
    },
    {
      "epoch": 2.296,
      "grad_norm": 0.03725794330239296,
      "learning_rate": 2e-05,
      "loss": 0.0034590037539601326,
      "step": 287
    },
    {
      "epoch": 2.304,
      "grad_norm": 0.04669518023729324,
      "learning_rate": 2e-05,
      "loss": 0.003809502115473151,
      "step": 288
    },
    {
      "epoch": 2.312,
      "grad_norm": 0.031050648540258408,
      "learning_rate": 2e-05,
      "loss": 0.003041312098503113,
      "step": 289
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.03626548871397972,
      "learning_rate": 2e-05,
      "loss": 0.0024002999998629093,
      "step": 290
    },
    {
      "epoch": 2.328,
      "grad_norm": 0.06315096467733383,
      "learning_rate": 2e-05,
      "loss": 0.006624164525419474,
      "step": 291
    },
    {
      "epoch": 2.336,
      "grad_norm": 0.04203896224498749,
      "learning_rate": 2e-05,
      "loss": 0.0019566724076867104,
      "step": 292
    },
    {
      "epoch": 2.344,
      "grad_norm": 0.04634423181414604,
      "learning_rate": 2e-05,
      "loss": 0.0032502529211342335,
      "step": 293
    },
    {
      "epoch": 2.352,
      "grad_norm": 0.04237474128603935,
      "learning_rate": 2e-05,
      "loss": 0.0031427519861608744,
      "step": 294
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.04034377261996269,
      "learning_rate": 2e-05,
      "loss": 0.00422636279836297,
      "step": 295
    },
    {
      "epoch": 2.368,
      "grad_norm": 0.044460564851760864,
      "learning_rate": 2e-05,
      "loss": 0.0028524911031126976,
      "step": 296
    },
    {
      "epoch": 2.376,
      "grad_norm": 0.0697890892624855,
      "learning_rate": 2e-05,
      "loss": 0.0036988966166973114,
      "step": 297
    },
    {
      "epoch": 2.384,
      "grad_norm": 0.04324623942375183,
      "learning_rate": 2e-05,
      "loss": 0.0037890365347266197,
      "step": 298
    },
    {
      "epoch": 2.392,
      "grad_norm": 0.02138633094727993,
      "learning_rate": 2e-05,
      "loss": 0.0021952460519969463,
      "step": 299
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.03607005998492241,
      "learning_rate": 2e-05,
      "loss": 0.002349622081965208,
      "step": 300
    },
    {
      "epoch": 2.408,
      "grad_norm": 0.039072196930646896,
      "learning_rate": 2e-05,
      "loss": 0.0035770011600106955,
      "step": 301
    },
    {
      "epoch": 2.416,
      "grad_norm": 0.02861890196800232,
      "learning_rate": 2e-05,
      "loss": 0.002283460693433881,
      "step": 302
    },
    {
      "epoch": 2.424,
      "grad_norm": 0.035563308745622635,
      "learning_rate": 2e-05,
      "loss": 0.0026536290533840656,
      "step": 303
    },
    {
      "epoch": 2.432,
      "grad_norm": 0.03916006535291672,
      "learning_rate": 2e-05,
      "loss": 0.003950632177293301,
      "step": 304
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.039335884153842926,
      "learning_rate": 2e-05,
      "loss": 0.003372431267052889,
      "step": 305
    },
    {
      "epoch": 2.448,
      "grad_norm": 0.045527540147304535,
      "learning_rate": 2e-05,
      "loss": 0.0030923227313905954,
      "step": 306
    },
    {
      "epoch": 2.456,
      "grad_norm": 0.04456671327352524,
      "learning_rate": 2e-05,
      "loss": 0.004458888433873653,
      "step": 307
    },
    {
      "epoch": 2.464,
      "grad_norm": 0.03560574725270271,
      "learning_rate": 2e-05,
      "loss": 0.003171511460095644,
      "step": 308
    },
    {
      "epoch": 2.472,
      "grad_norm": 0.036603160202503204,
      "learning_rate": 2e-05,
      "loss": 0.0028585128020495176,
      "step": 309
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.03335639089345932,
      "learning_rate": 2e-05,
      "loss": 0.0023816449102014303,
      "step": 310
    },
    {
      "epoch": 2.488,
      "grad_norm": 0.030154302716255188,
      "learning_rate": 2e-05,
      "loss": 0.00486906711012125,
      "step": 311
    },
    {
      "epoch": 2.496,
      "grad_norm": 0.040795303881168365,
      "learning_rate": 2e-05,
      "loss": 0.003139256499707699,
      "step": 312
    },
    {
      "epoch": 2.504,
      "grad_norm": 0.04953761771321297,
      "learning_rate": 2e-05,
      "loss": 0.0039007822051644325,
      "step": 313
    },
    {
      "epoch": 2.512,
      "grad_norm": 0.12026029080152512,
      "learning_rate": 2e-05,
      "loss": 0.0038295963313430548,
      "step": 314
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.057940348982810974,
      "learning_rate": 2e-05,
      "loss": 0.0033367923460900784,
      "step": 315
    },
    {
      "epoch": 2.528,
      "grad_norm": 0.028937026858329773,
      "learning_rate": 2e-05,
      "loss": 0.001545312232337892,
      "step": 316
    },
    {
      "epoch": 2.536,
      "grad_norm": 0.03167141228914261,
      "learning_rate": 2e-05,
      "loss": 0.0028309039771556854,
      "step": 317
    },
    {
      "epoch": 2.544,
      "grad_norm": 0.04004928842186928,
      "learning_rate": 2e-05,
      "loss": 0.002698655240237713,
      "step": 318
    },
    {
      "epoch": 2.552,
      "grad_norm": 0.02045566588640213,
      "learning_rate": 2e-05,
      "loss": 0.0012601229827851057,
      "step": 319
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.03342553600668907,
      "learning_rate": 2e-05,
      "loss": 0.001859499723650515,
      "step": 320
    },
    {
      "epoch": 2.568,
      "grad_norm": 0.025396211072802544,
      "learning_rate": 2e-05,
      "loss": 0.0020996080711483955,
      "step": 321
    },
    {
      "epoch": 2.576,
      "grad_norm": 0.03771315887570381,
      "learning_rate": 2e-05,
      "loss": 0.005717152263969183,
      "step": 322
    },
    {
      "epoch": 2.584,
      "grad_norm": 0.02477932535111904,
      "learning_rate": 2e-05,
      "loss": 0.0024716444313526154,
      "step": 323
    },
    {
      "epoch": 2.592,
      "grad_norm": 0.031247377395629883,
      "learning_rate": 2e-05,
      "loss": 0.00390324997715652,
      "step": 324
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.04134252667427063,
      "learning_rate": 2e-05,
      "loss": 0.003920188173651695,
      "step": 325
    },
    {
      "epoch": 2.608,
      "grad_norm": 0.02774622291326523,
      "learning_rate": 2e-05,
      "loss": 0.0022154548205435276,
      "step": 326
    },
    {
      "epoch": 2.616,
      "grad_norm": 0.03957367688417435,
      "learning_rate": 2e-05,
      "loss": 0.0023058855440467596,
      "step": 327
    },
    {
      "epoch": 2.624,
      "grad_norm": 0.04483708739280701,
      "learning_rate": 2e-05,
      "loss": 0.002552008954808116,
      "step": 328
    },
    {
      "epoch": 2.632,
      "grad_norm": 0.02093776874244213,
      "learning_rate": 2e-05,
      "loss": 0.0027019393164664507,
      "step": 329
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.06742503494024277,
      "learning_rate": 2e-05,
      "loss": 0.008755444549024105,
      "step": 330
    },
    {
      "epoch": 2.648,
      "grad_norm": 0.038483329117298126,
      "learning_rate": 2e-05,
      "loss": 0.0028858440928161144,
      "step": 331
    },
    {
      "epoch": 2.656,
      "grad_norm": 0.0329829640686512,
      "learning_rate": 2e-05,
      "loss": 0.0024300175718963146,
      "step": 332
    },
    {
      "epoch": 2.664,
      "grad_norm": 0.051471542567014694,
      "learning_rate": 2e-05,
      "loss": 0.003998158499598503,
      "step": 333
    },
    {
      "epoch": 2.672,
      "grad_norm": 0.04422187805175781,
      "learning_rate": 2e-05,
      "loss": 0.004651157651096582,
      "step": 334
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.02528465911746025,
      "learning_rate": 2e-05,
      "loss": 0.0021933559328317642,
      "step": 335
    },
    {
      "epoch": 2.6879999999999997,
      "grad_norm": 0.030596323311328888,
      "learning_rate": 2e-05,
      "loss": 0.003947809804230928,
      "step": 336
    },
    {
      "epoch": 2.6959999999999997,
      "grad_norm": 0.04210244491696358,
      "learning_rate": 2e-05,
      "loss": 0.003154753241688013,
      "step": 337
    },
    {
      "epoch": 2.7039999999999997,
      "grad_norm": 0.06121843308210373,
      "learning_rate": 2e-05,
      "loss": 0.0029088810551911592,
      "step": 338
    },
    {
      "epoch": 2.7119999999999997,
      "grad_norm": 0.03322814777493477,
      "learning_rate": 2e-05,
      "loss": 0.0026830481365323067,
      "step": 339
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.03890882432460785,
      "learning_rate": 2e-05,
      "loss": 0.002993557136505842,
      "step": 340
    },
    {
      "epoch": 2.7279999999999998,
      "grad_norm": 0.03936028108000755,
      "learning_rate": 2e-05,
      "loss": 0.0023103575222194195,
      "step": 341
    },
    {
      "epoch": 2.7359999999999998,
      "grad_norm": 0.03645415976643562,
      "learning_rate": 2e-05,
      "loss": 0.0036545468028634787,
      "step": 342
    },
    {
      "epoch": 2.7439999999999998,
      "grad_norm": 0.04062900319695473,
      "learning_rate": 2e-05,
      "loss": 0.0036479239352047443,
      "step": 343
    },
    {
      "epoch": 2.752,
      "grad_norm": 0.049033768475055695,
      "learning_rate": 2e-05,
      "loss": 0.0034971858840435743,
      "step": 344
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.03926759585738182,
      "learning_rate": 2e-05,
      "loss": 0.0031690222676843405,
      "step": 345
    },
    {
      "epoch": 2.768,
      "grad_norm": 0.06413634121417999,
      "learning_rate": 2e-05,
      "loss": 0.004980374127626419,
      "step": 346
    },
    {
      "epoch": 2.776,
      "grad_norm": 0.04801516979932785,
      "learning_rate": 2e-05,
      "loss": 0.0037698009982705116,
      "step": 347
    },
    {
      "epoch": 2.784,
      "grad_norm": 0.03702208027243614,
      "learning_rate": 2e-05,
      "loss": 0.001877334201708436,
      "step": 348
    },
    {
      "epoch": 2.792,
      "grad_norm": 0.03120242804288864,
      "learning_rate": 2e-05,
      "loss": 0.0022658274974673986,
      "step": 349
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.048766590654850006,
      "learning_rate": 2e-05,
      "loss": 0.00202578236348927,
      "step": 350
    },
    {
      "epoch": 2.808,
      "grad_norm": 0.029100535437464714,
      "learning_rate": 2e-05,
      "loss": 0.004179732408374548,
      "step": 351
    },
    {
      "epoch": 2.816,
      "grad_norm": 0.04512881860136986,
      "learning_rate": 2e-05,
      "loss": 0.002607448725029826,
      "step": 352
    },
    {
      "epoch": 2.824,
      "grad_norm": 0.07799641042947769,
      "learning_rate": 2e-05,
      "loss": 0.004347057081758976,
      "step": 353
    },
    {
      "epoch": 2.832,
      "grad_norm": 0.04792260378599167,
      "learning_rate": 2e-05,
      "loss": 0.003629413666203618,
      "step": 354
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.11515104025602341,
      "learning_rate": 2e-05,
      "loss": 0.006446151994168758,
      "step": 355
    },
    {
      "epoch": 2.848,
      "grad_norm": 0.023408330976963043,
      "learning_rate": 2e-05,
      "loss": 0.0017018368234857917,
      "step": 356
    },
    {
      "epoch": 2.856,
      "grad_norm": 0.03008626215159893,
      "learning_rate": 2e-05,
      "loss": 0.002287666779011488,
      "step": 357
    },
    {
      "epoch": 2.864,
      "grad_norm": 0.03706612437963486,
      "learning_rate": 2e-05,
      "loss": 0.0028982325457036495,
      "step": 358
    },
    {
      "epoch": 2.872,
      "grad_norm": 0.020318036898970604,
      "learning_rate": 2e-05,
      "loss": 0.0018703520763665438,
      "step": 359
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.06123220548033714,
      "learning_rate": 2e-05,
      "loss": 0.0029717511497437954,
      "step": 360
    },
    {
      "epoch": 2.888,
      "grad_norm": 0.055422086268663406,
      "learning_rate": 2e-05,
      "loss": 0.004031006712466478,
      "step": 361
    },
    {
      "epoch": 2.896,
      "grad_norm": 0.036786146461963654,
      "learning_rate": 2e-05,
      "loss": 0.003937885165214539,
      "step": 362
    },
    {
      "epoch": 2.904,
      "grad_norm": 0.038341671228408813,
      "learning_rate": 2e-05,
      "loss": 0.002436596667394042,
      "step": 363
    },
    {
      "epoch": 2.912,
      "grad_norm": 0.03609547019004822,
      "learning_rate": 2e-05,
      "loss": 0.004547444172203541,
      "step": 364
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.06485926359891891,
      "learning_rate": 2e-05,
      "loss": 0.003946429584175348,
      "step": 365
    },
    {
      "epoch": 2.928,
      "grad_norm": 0.04949840530753136,
      "learning_rate": 2e-05,
      "loss": 0.00502239353954792,
      "step": 366
    },
    {
      "epoch": 2.936,
      "grad_norm": 0.0354098416864872,
      "learning_rate": 2e-05,
      "loss": 0.002601196290925145,
      "step": 367
    },
    {
      "epoch": 2.944,
      "grad_norm": 0.025988208130002022,
      "learning_rate": 2e-05,
      "loss": 0.0036114591639488935,
      "step": 368
    },
    {
      "epoch": 2.952,
      "grad_norm": 0.034603431820869446,
      "learning_rate": 2e-05,
      "loss": 0.0026605837047100067,
      "step": 369
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.045072562992572784,
      "learning_rate": 2e-05,
      "loss": 0.002992109628394246,
      "step": 370
    },
    {
      "epoch": 2.968,
      "grad_norm": 0.07029342651367188,
      "learning_rate": 2e-05,
      "loss": 0.004379983991384506,
      "step": 371
    },
    {
      "epoch": 2.976,
      "grad_norm": 0.013431387022137642,
      "learning_rate": 2e-05,
      "loss": 0.0030165393836796284,
      "step": 372
    },
    {
      "epoch": 2.984,
      "grad_norm": 0.046111706644296646,
      "learning_rate": 2e-05,
      "loss": 0.0029378868639469147,
      "step": 373
    },
    {
      "epoch": 2.992,
      "grad_norm": 0.05583514645695686,
      "learning_rate": 2e-05,
      "loss": 0.0040816557593643665,
      "step": 374
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.03255736827850342,
      "learning_rate": 2e-05,
      "loss": 0.0035074178595095873,
      "step": 375
    },
    {
      "epoch": 3.008,
      "grad_norm": 0.03124692291021347,
      "learning_rate": 2e-05,
      "loss": 0.0031269516330212355,
      "step": 376
    },
    {
      "epoch": 3.016,
      "grad_norm": 0.05301191285252571,
      "learning_rate": 2e-05,
      "loss": 0.004872915334999561,
      "step": 377
    },
    {
      "epoch": 3.024,
      "grad_norm": 0.037463486194610596,
      "learning_rate": 2e-05,
      "loss": 0.0030003672000020742,
      "step": 378
    },
    {
      "epoch": 3.032,
      "grad_norm": 0.03362922742962837,
      "learning_rate": 2e-05,
      "loss": 0.0018557708244770765,
      "step": 379
    },
    {
      "epoch": 3.04,
      "grad_norm": 0.042213547974824905,
      "learning_rate": 2e-05,
      "loss": 0.0038657563272863626,
      "step": 380
    },
    {
      "epoch": 3.048,
      "grad_norm": 0.020529089495539665,
      "learning_rate": 2e-05,
      "loss": 0.0015072536189109087,
      "step": 381
    },
    {
      "epoch": 3.056,
      "grad_norm": 0.07512009888887405,
      "learning_rate": 2e-05,
      "loss": 0.004759274888783693,
      "step": 382
    },
    {
      "epoch": 3.064,
      "grad_norm": 0.03783705085515976,
      "learning_rate": 2e-05,
      "loss": 0.0032726821955293417,
      "step": 383
    },
    {
      "epoch": 3.072,
      "grad_norm": 0.04495864734053612,
      "learning_rate": 2e-05,
      "loss": 0.003068119753152132,
      "step": 384
    },
    {
      "epoch": 3.08,
      "grad_norm": 0.03879435732960701,
      "learning_rate": 2e-05,
      "loss": 0.0027257727924734354,
      "step": 385
    },
    {
      "epoch": 3.088,
      "grad_norm": 0.049851685762405396,
      "learning_rate": 2e-05,
      "loss": 0.004501521587371826,
      "step": 386
    },
    {
      "epoch": 3.096,
      "grad_norm": 0.037314675748348236,
      "learning_rate": 2e-05,
      "loss": 0.0031016827560961246,
      "step": 387
    },
    {
      "epoch": 3.104,
      "grad_norm": 0.032761648297309875,
      "learning_rate": 2e-05,
      "loss": 0.0029233950190246105,
      "step": 388
    },
    {
      "epoch": 3.112,
      "grad_norm": 0.0324791744351387,
      "learning_rate": 2e-05,
      "loss": 0.0026512390468269587,
      "step": 389
    },
    {
      "epoch": 3.12,
      "grad_norm": 0.03452916815876961,
      "learning_rate": 2e-05,
      "loss": 0.003484592540189624,
      "step": 390
    },
    {
      "epoch": 3.128,
      "grad_norm": 0.04120925813913345,
      "learning_rate": 2e-05,
      "loss": 0.0027602710761129856,
      "step": 391
    },
    {
      "epoch": 3.136,
      "grad_norm": 0.03730145841836929,
      "learning_rate": 2e-05,
      "loss": 0.003531615249812603,
      "step": 392
    },
    {
      "epoch": 3.144,
      "grad_norm": 0.03210754320025444,
      "learning_rate": 2e-05,
      "loss": 0.0023888859432190657,
      "step": 393
    },
    {
      "epoch": 3.152,
      "grad_norm": 0.036783989518880844,
      "learning_rate": 2e-05,
      "loss": 0.0027839350514113903,
      "step": 394
    },
    {
      "epoch": 3.16,
      "grad_norm": 0.03480631858110428,
      "learning_rate": 2e-05,
      "loss": 0.0027098648715764284,
      "step": 395
    },
    {
      "epoch": 3.168,
      "grad_norm": 0.03560803085565567,
      "learning_rate": 2e-05,
      "loss": 0.003286743303760886,
      "step": 396
    },
    {
      "epoch": 3.176,
      "grad_norm": 0.02866840735077858,
      "learning_rate": 2e-05,
      "loss": 0.0024349656887352467,
      "step": 397
    },
    {
      "epoch": 3.184,
      "grad_norm": 0.025658991187810898,
      "learning_rate": 2e-05,
      "loss": 0.0043978262692689896,
      "step": 398
    },
    {
      "epoch": 3.192,
      "grad_norm": 0.030603215098381042,
      "learning_rate": 2e-05,
      "loss": 0.0023162788711488247,
      "step": 399
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.05031350627541542,
      "learning_rate": 2e-05,
      "loss": 0.0037095744628459215,
      "step": 400
    }
  ],
  "logging_steps": 1,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}