{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.75,
  "eval_steps": 500,
  "global_step": 15750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.523809523809524e-05,
      "grad_norm": 5.334249496459961,
      "learning_rate": 0.0009599999757483602,
      "loss": 11.338590621948242,
      "step": 2
    },
    {
      "epoch": 0.00019047619047619048,
      "grad_norm": 4.912158489227295,
      "learning_rate": 0.0019199999514967203,
      "loss": 11.106103897094727,
      "step": 4
    },
    {
      "epoch": 0.00028571428571428574,
      "grad_norm": 3.8797929286956787,
      "learning_rate": 0.0028800000436604023,
      "loss": 10.584598541259766,
      "step": 6
    },
    {
      "epoch": 0.00038095238095238096,
      "grad_norm": 3.2725608348846436,
      "learning_rate": 0.0038399999029934406,
      "loss": 9.865562438964844,
      "step": 8
    },
    {
      "epoch": 0.0004761904761904762,
      "grad_norm": 2.6068851947784424,
      "learning_rate": 0.004800000227987766,
      "loss": 9.060608863830566,
      "step": 10
    },
    {
      "epoch": 0.0005714285714285715,
      "grad_norm": 1.7468725442886353,
      "learning_rate": 0.005760000087320805,
      "loss": 8.384103775024414,
      "step": 12
    },
    {
      "epoch": 0.0006666666666666666,
      "grad_norm": 1.3570023775100708,
      "learning_rate": 0.006719999946653843,
      "loss": 7.987142562866211,
      "step": 14
    },
    {
      "epoch": 0.0007619047619047619,
      "grad_norm": 1.487230658531189,
      "learning_rate": 0.007679999805986881,
      "loss": 7.8146653175354,
      "step": 16
    },
    {
      "epoch": 0.0008571428571428571,
      "grad_norm": 1.4034303426742554,
      "learning_rate": 0.008640000596642494,
      "loss": 7.720141410827637,
      "step": 18
    },
    {
      "epoch": 0.0009523809523809524,
      "grad_norm": 1.0685454607009888,
      "learning_rate": 0.009600000455975533,
      "loss": 7.585640907287598,
      "step": 20
    },
    {
      "epoch": 0.0010476190476190477,
      "grad_norm": 1.312131404876709,
      "learning_rate": 0.01056000031530857,
      "loss": 7.492856025695801,
      "step": 22
    },
    {
      "epoch": 0.001142857142857143,
      "grad_norm": 1.8928203582763672,
      "learning_rate": 0.01152000017464161,
      "loss": 7.4614338874816895,
      "step": 24
    },
    {
      "epoch": 0.001238095238095238,
      "grad_norm": 0.8378232717514038,
      "learning_rate": 0.012480000033974648,
      "loss": 7.34164571762085,
      "step": 26
    },
    {
      "epoch": 0.0013333333333333333,
      "grad_norm": 1.228731632232666,
      "learning_rate": 0.013439999893307686,
      "loss": 7.239810466766357,
      "step": 28
    },
    {
      "epoch": 0.0014285714285714286,
      "grad_norm": 1.876471757888794,
      "learning_rate": 0.014400000683963299,
      "loss": 7.2283172607421875,
      "step": 30
    },
    {
      "epoch": 0.0015238095238095239,
      "grad_norm": 1.8284523487091064,
      "learning_rate": 0.015359999611973763,
      "loss": 7.045976161956787,
      "step": 32
    },
    {
      "epoch": 0.0016190476190476191,
      "grad_norm": 1.139763593673706,
      "learning_rate": 0.0163199994713068,
      "loss": 6.928892612457275,
      "step": 34
    },
    {
      "epoch": 0.0017142857142857142,
      "grad_norm": 1.4842286109924316,
      "learning_rate": 0.01728000119328499,
      "loss": 6.857249736785889,
      "step": 36
    },
    {
      "epoch": 0.0018095238095238095,
      "grad_norm": 1.2160557508468628,
      "learning_rate": 0.018239999189972878,
      "loss": 6.804518699645996,
      "step": 38
    },
    {
      "epoch": 0.0019047619047619048,
      "grad_norm": 0.7941610217094421,
      "learning_rate": 0.019200000911951065,
      "loss": 6.6685380935668945,
      "step": 40
    },
    {
      "epoch": 0.002,
      "grad_norm": 1.1024287939071655,
      "learning_rate": 0.020159998908638954,
      "loss": 6.523946762084961,
      "step": 42
    },
    {
      "epoch": 0.0020952380952380953,
      "grad_norm": 1.01893150806427,
      "learning_rate": 0.02112000063061714,
      "loss": 6.507093906402588,
      "step": 44
    },
    {
      "epoch": 0.0021904761904761906,
      "grad_norm": 0.9222122430801392,
      "learning_rate": 0.02208000048995018,
      "loss": 6.462471008300781,
      "step": 46
    },
    {
      "epoch": 0.002285714285714286,
      "grad_norm": 0.9372642040252686,
      "learning_rate": 0.02304000034928322,
      "loss": 6.336216449737549,
      "step": 48
    },
    {
      "epoch": 0.002380952380952381,
      "grad_norm": 0.7343265414237976,
      "learning_rate": 0.024000000208616257,
      "loss": 6.313828468322754,
      "step": 50
    },
    {
      "epoch": 0.002476190476190476,
      "grad_norm": 0.7058768272399902,
      "learning_rate": 0.024000000208616257,
      "loss": 6.157600402832031,
      "step": 52
    },
    {
      "epoch": 0.0025714285714285713,
      "grad_norm": 0.6334480047225952,
      "learning_rate": 0.024000000208616257,
      "loss": 6.117180824279785,
      "step": 54
    },
    {
      "epoch": 0.0026666666666666666,
      "grad_norm": 0.6416035890579224,
      "learning_rate": 0.024000000208616257,
      "loss": 6.12557315826416,
      "step": 56
    },
    {
      "epoch": 0.002761904761904762,
      "grad_norm": 0.6256217956542969,
      "learning_rate": 0.024000000208616257,
      "loss": 5.993575096130371,
      "step": 58
    },
    {
      "epoch": 0.002857142857142857,
      "grad_norm": 0.6432225704193115,
      "learning_rate": 0.024000000208616257,
      "loss": 5.912439346313477,
      "step": 60
    },
    {
      "epoch": 0.0029523809523809524,
      "grad_norm": 0.697803258895874,
      "learning_rate": 0.024000000208616257,
      "loss": 5.949170112609863,
      "step": 62
    },
    {
      "epoch": 0.0030476190476190477,
      "grad_norm": 0.5313658118247986,
      "learning_rate": 0.024000000208616257,
      "loss": 5.836516380310059,
      "step": 64
    },
    {
      "epoch": 0.003142857142857143,
      "grad_norm": 0.6081739068031311,
      "learning_rate": 0.024000000208616257,
      "loss": 5.72202205657959,
      "step": 66
    },
    {
      "epoch": 0.0032380952380952383,
      "grad_norm": 0.6072482466697693,
      "learning_rate": 0.024000000208616257,
      "loss": 5.780881404876709,
      "step": 68
    },
    {
      "epoch": 0.0033333333333333335,
      "grad_norm": 0.53412264585495,
      "learning_rate": 0.024000000208616257,
      "loss": 5.725709915161133,
      "step": 70
    },
    {
      "epoch": 0.0034285714285714284,
      "grad_norm": 0.3784787356853485,
      "learning_rate": 0.024000000208616257,
      "loss": 5.686314582824707,
      "step": 72
    },
    {
      "epoch": 0.0035238095238095237,
      "grad_norm": 0.4787817597389221,
      "learning_rate": 0.024000000208616257,
      "loss": 5.597344398498535,
      "step": 74
    },
    {
      "epoch": 0.003619047619047619,
      "grad_norm": 0.40686413645744324,
      "learning_rate": 0.024000000208616257,
      "loss": 5.596353530883789,
      "step": 76
    },
    {
      "epoch": 0.0037142857142857142,
      "grad_norm": 0.5109027028083801,
      "learning_rate": 0.024000000208616257,
      "loss": 5.512279510498047,
      "step": 78
    },
    {
      "epoch": 0.0038095238095238095,
      "grad_norm": 0.3989114463329315,
      "learning_rate": 0.024000000208616257,
      "loss": 5.525890350341797,
      "step": 80
    },
    {
      "epoch": 0.003904761904761905,
      "grad_norm": 0.3629150688648224,
      "learning_rate": 0.024000000208616257,
      "loss": 5.484899520874023,
      "step": 82
    },
    {
      "epoch": 0.004,
      "grad_norm": 0.40528976917266846,
      "learning_rate": 0.024000000208616257,
      "loss": 5.402684688568115,
      "step": 84
    },
    {
      "epoch": 0.004095238095238095,
      "grad_norm": 0.44190651178359985,
      "learning_rate": 0.024000000208616257,
      "loss": 5.365906715393066,
      "step": 86
    },
    {
      "epoch": 0.004190476190476191,
      "grad_norm": 0.38514354825019836,
      "learning_rate": 0.024000000208616257,
      "loss": 5.36356258392334,
      "step": 88
    },
    {
      "epoch": 0.004285714285714286,
      "grad_norm": 0.37013643980026245,
      "learning_rate": 0.024000000208616257,
      "loss": 5.330933570861816,
      "step": 90
    },
    {
      "epoch": 0.004380952380952381,
      "grad_norm": 0.370812326669693,
      "learning_rate": 0.024000000208616257,
      "loss": 5.225103378295898,
      "step": 92
    },
    {
      "epoch": 0.0044761904761904765,
      "grad_norm": 0.32646599411964417,
      "learning_rate": 0.024000000208616257,
      "loss": 5.223209381103516,
      "step": 94
    },
    {
      "epoch": 0.004571428571428572,
      "grad_norm": 0.42137834429740906,
      "learning_rate": 0.024000000208616257,
      "loss": 5.143673419952393,
      "step": 96
    },
    {
      "epoch": 0.004666666666666667,
      "grad_norm": 0.34391850233078003,
      "learning_rate": 0.024000000208616257,
      "loss": 5.172023773193359,
      "step": 98
    },
    {
      "epoch": 0.004761904761904762,
      "grad_norm": 0.40263113379478455,
      "learning_rate": 0.024000000208616257,
      "loss": 5.13016414642334,
      "step": 100
    },
    {
      "epoch": 0.004857142857142857,
      "grad_norm": 0.3414495885372162,
      "learning_rate": 0.024000000208616257,
      "loss": 5.08735466003418,
      "step": 102
    },
    {
      "epoch": 0.004952380952380952,
      "grad_norm": 0.3308958113193512,
      "learning_rate": 0.024000000208616257,
      "loss": 4.9940595626831055,
      "step": 104
    },
    {
      "epoch": 0.005047619047619047,
      "grad_norm": 0.35891515016555786,
      "learning_rate": 0.024000000208616257,
      "loss": 5.052173614501953,
      "step": 106
    },
    {
      "epoch": 0.005142857142857143,
      "grad_norm": 0.3349107801914215,
      "learning_rate": 0.024000000208616257,
      "loss": 4.994757652282715,
      "step": 108
    },
    {
      "epoch": 0.005238095238095238,
      "grad_norm": 0.321865439414978,
      "learning_rate": 0.024000000208616257,
      "loss": 4.981725692749023,
      "step": 110
    },
    {
      "epoch": 0.005333333333333333,
      "grad_norm": 0.3503016233444214,
      "learning_rate": 0.024000000208616257,
      "loss": 4.932741165161133,
      "step": 112
    },
    {
      "epoch": 0.0054285714285714284,
      "grad_norm": 0.28275245428085327,
      "learning_rate": 0.024000000208616257,
      "loss": 4.885126113891602,
      "step": 114
    },
    {
      "epoch": 0.005523809523809524,
      "grad_norm": 0.2764172852039337,
      "learning_rate": 0.024000000208616257,
      "loss": 4.904468536376953,
      "step": 116
    },
    {
      "epoch": 0.005619047619047619,
      "grad_norm": 0.2603635787963867,
      "learning_rate": 0.024000000208616257,
      "loss": 4.8304901123046875,
      "step": 118
    },
    {
      "epoch": 0.005714285714285714,
      "grad_norm": 0.30044037103652954,
      "learning_rate": 0.024000000208616257,
      "loss": 4.82453727722168,
      "step": 120
    },
    {
      "epoch": 0.0058095238095238096,
      "grad_norm": 0.26797524094581604,
      "learning_rate": 0.024000000208616257,
      "loss": 4.775590896606445,
      "step": 122
    },
    {
      "epoch": 0.005904761904761905,
      "grad_norm": 0.22359897196292877,
      "learning_rate": 0.024000000208616257,
      "loss": 4.801427841186523,
      "step": 124
    },
    {
      "epoch": 0.006,
      "grad_norm": 0.22624699771404266,
      "learning_rate": 0.024000000208616257,
      "loss": 4.7194647789001465,
      "step": 126
    },
    {
      "epoch": 0.006095238095238095,
      "grad_norm": 0.25256356596946716,
      "learning_rate": 0.024000000208616257,
      "loss": 4.714766502380371,
      "step": 128
    },
    {
      "epoch": 0.006190476190476191,
      "grad_norm": 0.2946987450122833,
      "learning_rate": 0.024000000208616257,
      "loss": 4.684695720672607,
      "step": 130
    },
    {
      "epoch": 0.006285714285714286,
      "grad_norm": 0.23077909648418427,
      "learning_rate": 0.024000000208616257,
      "loss": 4.619433403015137,
      "step": 132
    },
    {
      "epoch": 0.006380952380952381,
      "grad_norm": 0.26244816184043884,
      "learning_rate": 0.024000000208616257,
      "loss": 4.630702972412109,
      "step": 134
    },
    {
      "epoch": 0.0064761904761904765,
      "grad_norm": 0.2738366723060608,
      "learning_rate": 0.024000000208616257,
      "loss": 4.590965270996094,
      "step": 136
    },
    {
      "epoch": 0.006571428571428572,
      "grad_norm": 0.2275918424129486,
      "learning_rate": 0.024000000208616257,
      "loss": 4.600028991699219,
      "step": 138
    },
    {
      "epoch": 0.006666666666666667,
      "grad_norm": 0.226734459400177,
      "learning_rate": 0.024000000208616257,
      "loss": 4.577237129211426,
      "step": 140
    },
    {
      "epoch": 0.0067619047619047615,
      "grad_norm": 0.23907658457756042,
      "learning_rate": 0.024000000208616257,
      "loss": 4.585365295410156,
      "step": 142
    },
    {
      "epoch": 0.006857142857142857,
      "grad_norm": 0.24208958446979523,
      "learning_rate": 0.024000000208616257,
      "loss": 4.519833564758301,
      "step": 144
    },
    {
      "epoch": 0.006952380952380952,
      "grad_norm": 0.22431696951389313,
      "learning_rate": 0.024000000208616257,
      "loss": 4.502078533172607,
      "step": 146
    },
    {
      "epoch": 0.007047619047619047,
      "grad_norm": 0.20942296087741852,
      "learning_rate": 0.024000000208616257,
      "loss": 4.443584442138672,
      "step": 148
    },
    {
      "epoch": 0.007142857142857143,
      "grad_norm": 0.1971714198589325,
      "learning_rate": 0.024000000208616257,
      "loss": 4.461605548858643,
      "step": 150
    },
    {
      "epoch": 0.007238095238095238,
      "grad_norm": 0.206486776471138,
      "learning_rate": 0.024000000208616257,
      "loss": 4.456093788146973,
      "step": 152
    },
    {
      "epoch": 0.007333333333333333,
      "grad_norm": 0.1869850605726242,
      "learning_rate": 0.024000000208616257,
      "loss": 4.357968330383301,
      "step": 154
    },
    {
      "epoch": 0.0074285714285714285,
      "grad_norm": 0.18810655176639557,
      "learning_rate": 0.024000000208616257,
      "loss": 4.3473358154296875,
      "step": 156
    },
    {
      "epoch": 0.007523809523809524,
      "grad_norm": 0.18723595142364502,
      "learning_rate": 0.024000000208616257,
      "loss": 4.243231773376465,
      "step": 158
    },
    {
      "epoch": 0.007619047619047619,
      "grad_norm": 0.22764718532562256,
      "learning_rate": 0.024000000208616257,
      "loss": 4.338347911834717,
      "step": 160
    },
    {
      "epoch": 0.007714285714285714,
      "grad_norm": 0.18891257047653198,
      "learning_rate": 0.024000000208616257,
      "loss": 4.256882667541504,
      "step": 162
    },
    {
      "epoch": 0.00780952380952381,
      "grad_norm": 0.18442027270793915,
      "learning_rate": 0.024000000208616257,
      "loss": 4.249155044555664,
      "step": 164
    },
    {
      "epoch": 0.007904761904761904,
      "grad_norm": 0.2203933149576187,
      "learning_rate": 0.024000000208616257,
      "loss": 4.244586944580078,
      "step": 166
    },
    {
      "epoch": 0.008,
      "grad_norm": 0.19718140363693237,
      "learning_rate": 0.024000000208616257,
      "loss": 4.2194719314575195,
      "step": 168
    },
    {
      "epoch": 0.008095238095238095,
      "grad_norm": 0.19148792326450348,
      "learning_rate": 0.024000000208616257,
      "loss": 4.12512731552124,
      "step": 170
    },
    {
      "epoch": 0.00819047619047619,
      "grad_norm": 0.2063865214586258,
      "learning_rate": 0.024000000208616257,
      "loss": 4.138655662536621,
      "step": 172
    },
    {
      "epoch": 0.008285714285714285,
      "grad_norm": 0.19589954614639282,
      "learning_rate": 0.024000000208616257,
      "loss": 4.122981548309326,
      "step": 174
    },
    {
      "epoch": 0.008380952380952381,
      "grad_norm": 0.17040422558784485,
      "learning_rate": 0.024000000208616257,
      "loss": 4.120534420013428,
      "step": 176
    },
    {
      "epoch": 0.008476190476190476,
      "grad_norm": 0.16039830446243286,
      "learning_rate": 0.024000000208616257,
      "loss": 4.031489372253418,
      "step": 178
    },
    {
      "epoch": 0.008571428571428572,
      "grad_norm": 0.17483080923557281,
      "learning_rate": 0.024000000208616257,
      "loss": 4.093786239624023,
      "step": 180
    },
    {
      "epoch": 0.008666666666666666,
      "grad_norm": 0.18141613900661469,
      "learning_rate": 0.024000000208616257,
      "loss": 4.060184478759766,
      "step": 182
    },
    {
      "epoch": 0.008761904761904762,
      "grad_norm": 0.20803888142108917,
      "learning_rate": 0.024000000208616257,
      "loss": 4.038195610046387,
      "step": 184
    },
    {
      "epoch": 0.008857142857142857,
      "grad_norm": 0.20504431426525116,
      "learning_rate": 0.024000000208616257,
      "loss": 4.010971546173096,
      "step": 186
    },
    {
      "epoch": 0.008952380952380953,
      "grad_norm": 0.2211029976606369,
      "learning_rate": 0.024000000208616257,
      "loss": 4.010530471801758,
      "step": 188
    },
    {
      "epoch": 0.009047619047619047,
      "grad_norm": 0.16161268949508667,
      "learning_rate": 0.024000000208616257,
      "loss": 3.956794261932373,
      "step": 190
    },
    {
      "epoch": 0.009142857142857144,
      "grad_norm": 0.17623260617256165,
      "learning_rate": 0.024000000208616257,
      "loss": 3.981397867202759,
      "step": 192
    },
    {
      "epoch": 0.009238095238095238,
      "grad_norm": 0.16728992760181427,
      "learning_rate": 0.024000000208616257,
      "loss": 3.931537628173828,
      "step": 194
    },
    {
      "epoch": 0.009333333333333334,
      "grad_norm": 0.14352665841579437,
      "learning_rate": 0.024000000208616257,
      "loss": 3.9382262229919434,
      "step": 196
    },
    {
      "epoch": 0.009428571428571429,
      "grad_norm": 0.17751771211624146,
      "learning_rate": 0.024000000208616257,
      "loss": 3.9443423748016357,
      "step": 198
    },
    {
      "epoch": 0.009523809523809525,
      "grad_norm": 0.18594537675380707,
      "learning_rate": 0.024000000208616257,
      "loss": 3.898176431655884,
      "step": 200
    },
    {
      "epoch": 0.009619047619047619,
      "grad_norm": 0.16507096588611603,
      "learning_rate": 0.024000000208616257,
      "loss": 3.8557991981506348,
      "step": 202
    },
    {
      "epoch": 0.009714285714285713,
      "grad_norm": 0.15689560770988464,
      "learning_rate": 0.024000000208616257,
      "loss": 3.8919527530670166,
      "step": 204
    },
    {
      "epoch": 0.00980952380952381,
      "grad_norm": 0.16706326603889465,
      "learning_rate": 0.024000000208616257,
      "loss": 3.8841633796691895,
      "step": 206
    },
    {
      "epoch": 0.009904761904761904,
      "grad_norm": 0.16349129378795624,
      "learning_rate": 0.024000000208616257,
      "loss": 3.871731758117676,
      "step": 208
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.15250366926193237,
      "learning_rate": 0.024000000208616257,
      "loss": 3.835054874420166,
      "step": 210
    },
    {
      "epoch": 0.010095238095238095,
      "grad_norm": 0.14798583090305328,
      "learning_rate": 0.024000000208616257,
      "loss": 3.8407793045043945,
      "step": 212
    },
    {
      "epoch": 0.01019047619047619,
      "grad_norm": 0.1303013116121292,
      "learning_rate": 0.024000000208616257,
      "loss": 3.8467090129852295,
      "step": 214
    },
    {
      "epoch": 0.010285714285714285,
      "grad_norm": 0.14930962026119232,
      "learning_rate": 0.024000000208616257,
      "loss": 3.826352596282959,
      "step": 216
    },
    {
      "epoch": 0.010380952380952381,
      "grad_norm": 0.13380160927772522,
      "learning_rate": 0.024000000208616257,
      "loss": 3.803123712539673,
      "step": 218
    },
    {
      "epoch": 0.010476190476190476,
      "grad_norm": 0.13185061514377594,
      "learning_rate": 0.024000000208616257,
      "loss": 3.764822483062744,
      "step": 220
    },
    {
      "epoch": 0.010571428571428572,
      "grad_norm": 0.13195107877254486,
      "learning_rate": 0.024000000208616257,
      "loss": 3.7949039936065674,
      "step": 222
    },
    {
      "epoch": 0.010666666666666666,
      "grad_norm": 0.13089139759540558,
      "learning_rate": 0.024000000208616257,
      "loss": 3.7087113857269287,
      "step": 224
    },
    {
      "epoch": 0.010761904761904762,
      "grad_norm": 0.13606908917427063,
      "learning_rate": 0.024000000208616257,
      "loss": 3.7712719440460205,
      "step": 226
    },
    {
      "epoch": 0.010857142857142857,
      "grad_norm": 0.1236468106508255,
      "learning_rate": 0.024000000208616257,
      "loss": 3.704202651977539,
      "step": 228
    },
    {
      "epoch": 0.010952380952380953,
      "grad_norm": 0.13038469851016998,
      "learning_rate": 0.024000000208616257,
      "loss": 3.735424518585205,
      "step": 230
    },
    {
      "epoch": 0.011047619047619047,
      "grad_norm": 0.13107383251190186,
      "learning_rate": 0.024000000208616257,
      "loss": 3.7293262481689453,
      "step": 232
    },
    {
      "epoch": 0.011142857142857144,
      "grad_norm": 0.12255515158176422,
      "learning_rate": 0.024000000208616257,
      "loss": 3.7370452880859375,
      "step": 234
    },
    {
      "epoch": 0.011238095238095238,
      "grad_norm": 0.12898030877113342,
      "learning_rate": 0.024000000208616257,
      "loss": 3.721784830093384,
      "step": 236
    },
    {
      "epoch": 0.011333333333333334,
      "grad_norm": 0.14469777047634125,
      "learning_rate": 0.024000000208616257,
      "loss": 3.7427377700805664,
      "step": 238
    },
    {
      "epoch": 0.011428571428571429,
      "grad_norm": 0.1504635214805603,
      "learning_rate": 0.024000000208616257,
      "loss": 3.6971869468688965,
      "step": 240
    },
    {
      "epoch": 0.011523809523809523,
      "grad_norm": 0.1295986771583557,
      "learning_rate": 0.024000000208616257,
      "loss": 3.7021772861480713,
      "step": 242
    },
    {
      "epoch": 0.011619047619047619,
      "grad_norm": 0.14498457312583923,
      "learning_rate": 0.024000000208616257,
      "loss": 3.689133405685425,
      "step": 244
    },
    {
      "epoch": 0.011714285714285714,
      "grad_norm": 0.15880340337753296,
      "learning_rate": 0.024000000208616257,
      "loss": 3.6457457542419434,
      "step": 246
    },
    {
      "epoch": 0.01180952380952381,
      "grad_norm": 0.12845812737941742,
      "learning_rate": 0.024000000208616257,
      "loss": 3.6668453216552734,
      "step": 248
    },
    {
      "epoch": 0.011904761904761904,
      "grad_norm": 0.11414748430252075,
      "learning_rate": 0.024000000208616257,
      "loss": 3.672318935394287,
      "step": 250
    },
    {
      "epoch": 0.012,
      "grad_norm": 0.10975576192140579,
      "learning_rate": 0.024000000208616257,
      "loss": 3.6713898181915283,
      "step": 252
    },
    {
      "epoch": 0.012095238095238095,
      "grad_norm": 0.11887271702289581,
      "learning_rate": 0.024000000208616257,
      "loss": 3.632063865661621,
      "step": 254
    },
    {
      "epoch": 0.01219047619047619,
      "grad_norm": 0.11623682081699371,
      "learning_rate": 0.024000000208616257,
      "loss": 3.6583919525146484,
      "step": 256
    },
    {
      "epoch": 0.012285714285714285,
      "grad_norm": 0.15844392776489258,
      "learning_rate": 0.024000000208616257,
      "loss": 3.615412712097168,
      "step": 258
    },
    {
      "epoch": 0.012380952380952381,
      "grad_norm": 0.1317964494228363,
      "learning_rate": 0.024000000208616257,
      "loss": 3.6437807083129883,
      "step": 260
    },
    {
      "epoch": 0.012476190476190476,
      "grad_norm": 0.14390750229358673,
      "learning_rate": 0.024000000208616257,
      "loss": 3.6259701251983643,
      "step": 262
    },
    {
      "epoch": 0.012571428571428572,
      "grad_norm": 0.1169910803437233,
      "learning_rate": 0.024000000208616257,
      "loss": 3.637897491455078,
      "step": 264
    },
    {
      "epoch": 0.012666666666666666,
      "grad_norm": 0.11459456384181976,
      "learning_rate": 0.024000000208616257,
      "loss": 3.611710786819458,
      "step": 266
    },
    {
      "epoch": 0.012761904761904763,
      "grad_norm": 0.11044281721115112,
      "learning_rate": 0.024000000208616257,
      "loss": 3.613513231277466,
      "step": 268
    },
    {
      "epoch": 0.012857142857142857,
      "grad_norm": 0.10898206382989883,
      "learning_rate": 0.024000000208616257,
      "loss": 3.593027353286743,
      "step": 270
    },
    {
      "epoch": 0.012952380952380953,
      "grad_norm": 0.1149030476808548,
      "learning_rate": 0.024000000208616257,
      "loss": 3.621788501739502,
      "step": 272
    },
    {
      "epoch": 0.013047619047619047,
      "grad_norm": 0.1170446127653122,
      "learning_rate": 0.024000000208616257,
      "loss": 3.610743999481201,
      "step": 274
    },
    {
      "epoch": 0.013142857142857144,
      "grad_norm": 0.13015896081924438,
      "learning_rate": 0.024000000208616257,
      "loss": 3.578035354614258,
      "step": 276
    },
    {
      "epoch": 0.013238095238095238,
      "grad_norm": 0.11585091799497604,
      "learning_rate": 0.024000000208616257,
      "loss": 3.5824408531188965,
      "step": 278
    },
    {
      "epoch": 0.013333333333333334,
      "grad_norm": 0.12804314494132996,
      "learning_rate": 0.024000000208616257,
      "loss": 3.546003818511963,
      "step": 280
    },
    {
      "epoch": 0.013428571428571429,
      "grad_norm": 0.12476787716150284,
      "learning_rate": 0.024000000208616257,
      "loss": 3.5286173820495605,
      "step": 282
    },
    {
      "epoch": 0.013523809523809523,
      "grad_norm": 0.1275377720594406,
      "learning_rate": 0.024000000208616257,
      "loss": 3.5649986267089844,
      "step": 284
    },
    {
      "epoch": 0.01361904761904762,
      "grad_norm": 0.1443047970533371,
      "learning_rate": 0.024000000208616257,
      "loss": 3.534911870956421,
      "step": 286
    },
    {
      "epoch": 0.013714285714285714,
      "grad_norm": 0.126201793551445,
      "learning_rate": 0.024000000208616257,
      "loss": 3.5897974967956543,
      "step": 288
    },
    {
      "epoch": 0.01380952380952381,
      "grad_norm": 0.14978854358196259,
      "learning_rate": 0.024000000208616257,
      "loss": 3.5548784732818604,
      "step": 290
    },
    {
      "epoch": 0.013904761904761904,
      "grad_norm": 0.12638816237449646,
      "learning_rate": 0.024000000208616257,
      "loss": 3.537980794906616,
      "step": 292
    },
    {
      "epoch": 0.014,
      "grad_norm": 0.12399981170892715,
      "learning_rate": 0.024000000208616257,
      "loss": 3.5440704822540283,
      "step": 294
    },
    {
      "epoch": 0.014095238095238095,
      "grad_norm": 0.13476406037807465,
      "learning_rate": 0.024000000208616257,
      "loss": 3.5361413955688477,
      "step": 296
    },
    {
      "epoch": 0.01419047619047619,
      "grad_norm": 0.11274745315313339,
      "learning_rate": 0.024000000208616257,
      "loss": 3.5662314891815186,
      "step": 298
    },
    {
      "epoch": 0.014285714285714285,
      "grad_norm": 0.10571589320898056,
      "learning_rate": 0.024000000208616257,
      "loss": 3.549699068069458,
      "step": 300
    },
    {
      "epoch": 0.014380952380952381,
      "grad_norm": 0.11887554079294205,
      "learning_rate": 0.024000000208616257,
      "loss": 3.5678656101226807,
      "step": 302
    },
    {
      "epoch": 0.014476190476190476,
      "grad_norm": 0.11401069164276123,
      "learning_rate": 0.024000000208616257,
      "loss": 3.5054450035095215,
      "step": 304
    },
    {
      "epoch": 0.014571428571428572,
      "grad_norm": 0.11524013429880142,
      "learning_rate": 0.024000000208616257,
      "loss": 3.521726369857788,
      "step": 306
    },
    {
      "epoch": 0.014666666666666666,
      "grad_norm": 0.11810661852359772,
      "learning_rate": 0.024000000208616257,
      "loss": 3.503756523132324,
      "step": 308
    },
    {
      "epoch": 0.014761904761904763,
      "grad_norm": 0.1283569484949112,
      "learning_rate": 0.024000000208616257,
      "loss": 3.505880355834961,
      "step": 310
    },
    {
      "epoch": 0.014857142857142857,
      "grad_norm": 0.10811018943786621,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4756155014038086,
      "step": 312
    },
    {
      "epoch": 0.014952380952380953,
      "grad_norm": 0.11082758754491806,
      "learning_rate": 0.024000000208616257,
      "loss": 3.496945858001709,
      "step": 314
    },
    {
      "epoch": 0.015047619047619048,
      "grad_norm": 0.11726303398609161,
      "learning_rate": 0.024000000208616257,
      "loss": 3.473219156265259,
      "step": 316
    },
    {
      "epoch": 0.015142857142857144,
      "grad_norm": 0.10839106887578964,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4745240211486816,
      "step": 318
    },
    {
      "epoch": 0.015238095238095238,
      "grad_norm": 0.1077137365937233,
      "learning_rate": 0.024000000208616257,
      "loss": 3.5088939666748047,
      "step": 320
    },
    {
      "epoch": 0.015333333333333332,
      "grad_norm": 0.12155335396528244,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4618678092956543,
      "step": 322
    },
    {
      "epoch": 0.015428571428571429,
      "grad_norm": 0.10906599462032318,
      "learning_rate": 0.024000000208616257,
      "loss": 3.5050854682922363,
      "step": 324
    },
    {
      "epoch": 0.015523809523809523,
      "grad_norm": 0.11417632550001144,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4578499794006348,
      "step": 326
    },
    {
      "epoch": 0.01561904761904762,
      "grad_norm": 0.09178224205970764,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4617133140563965,
      "step": 328
    },
    {
      "epoch": 0.015714285714285715,
      "grad_norm": 0.1029578447341919,
      "learning_rate": 0.024000000208616257,
      "loss": 3.473824977874756,
      "step": 330
    },
    {
      "epoch": 0.015809523809523808,
      "grad_norm": 0.10480651259422302,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4425692558288574,
      "step": 332
    },
    {
      "epoch": 0.015904761904761904,
      "grad_norm": 0.09576138854026794,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4444570541381836,
      "step": 334
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.10579310357570648,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4755492210388184,
      "step": 336
    },
    {
      "epoch": 0.016095238095238096,
      "grad_norm": 0.11131022870540619,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4358997344970703,
      "step": 338
    },
    {
      "epoch": 0.01619047619047619,
      "grad_norm": 0.11613092571496964,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4474031925201416,
      "step": 340
    },
    {
      "epoch": 0.016285714285714285,
      "grad_norm": 0.10332045704126358,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4534311294555664,
      "step": 342
    },
    {
      "epoch": 0.01638095238095238,
      "grad_norm": 0.10366816073656082,
      "learning_rate": 0.024000000208616257,
      "loss": 3.429917335510254,
      "step": 344
    },
    {
      "epoch": 0.016476190476190478,
      "grad_norm": 0.10107503831386566,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4414310455322266,
      "step": 346
    },
    {
      "epoch": 0.01657142857142857,
      "grad_norm": 0.10653431713581085,
      "learning_rate": 0.024000000208616257,
      "loss": 3.451590061187744,
      "step": 348
    },
    {
      "epoch": 0.016666666666666666,
      "grad_norm": 0.09354981780052185,
      "learning_rate": 0.024000000208616257,
      "loss": 3.47836971282959,
      "step": 350
    },
    {
      "epoch": 0.016761904761904763,
      "grad_norm": 0.10947000980377197,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4158945083618164,
      "step": 352
    },
    {
      "epoch": 0.01685714285714286,
      "grad_norm": 0.10842986404895782,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4518861770629883,
      "step": 354
    },
    {
      "epoch": 0.01695238095238095,
      "grad_norm": 0.09586591273546219,
      "learning_rate": 0.024000000208616257,
      "loss": 3.412656307220459,
      "step": 356
    },
    {
      "epoch": 0.017047619047619048,
      "grad_norm": 0.12009255588054657,
      "learning_rate": 0.024000000208616257,
      "loss": 3.439100742340088,
      "step": 358
    },
    {
      "epoch": 0.017142857142857144,
      "grad_norm": 0.12858207523822784,
      "learning_rate": 0.024000000208616257,
      "loss": 3.450693130493164,
      "step": 360
    },
    {
      "epoch": 0.017238095238095236,
      "grad_norm": 0.0911901518702507,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4140405654907227,
      "step": 362
    },
    {
      "epoch": 0.017333333333333333,
      "grad_norm": 0.09317584335803986,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4227757453918457,
      "step": 364
    },
    {
      "epoch": 0.01742857142857143,
      "grad_norm": 0.09875544905662537,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4036762714385986,
      "step": 366
    },
    {
      "epoch": 0.017523809523809525,
      "grad_norm": 0.09594345837831497,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4147934913635254,
      "step": 368
    },
    {
      "epoch": 0.017619047619047618,
      "grad_norm": 0.09612176567316055,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4124817848205566,
      "step": 370
    },
    {
      "epoch": 0.017714285714285714,
      "grad_norm": 0.11377938836812973,
      "learning_rate": 0.024000000208616257,
      "loss": 3.394390821456909,
      "step": 372
    },
    {
      "epoch": 0.01780952380952381,
      "grad_norm": 0.1012466698884964,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3811049461364746,
      "step": 374
    },
    {
      "epoch": 0.017904761904761906,
      "grad_norm": 0.10026443749666214,
      "learning_rate": 0.024000000208616257,
      "loss": 3.375251531600952,
      "step": 376
    },
    {
      "epoch": 0.018,
      "grad_norm": 0.09609606117010117,
      "learning_rate": 0.024000000208616257,
      "loss": 3.377617120742798,
      "step": 378
    },
    {
      "epoch": 0.018095238095238095,
      "grad_norm": 0.09122078120708466,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3962011337280273,
      "step": 380
    },
    {
      "epoch": 0.01819047619047619,
      "grad_norm": 0.10296985507011414,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4071035385131836,
      "step": 382
    },
    {
      "epoch": 0.018285714285714287,
      "grad_norm": 0.09579654037952423,
      "learning_rate": 0.024000000208616257,
      "loss": 3.4162230491638184,
      "step": 384
    },
    {
      "epoch": 0.01838095238095238,
      "grad_norm": 0.09958939999341965,
      "learning_rate": 0.024000000208616257,
      "loss": 3.399854898452759,
      "step": 386
    },
    {
      "epoch": 0.018476190476190476,
      "grad_norm": 0.10002212971448898,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3855652809143066,
      "step": 388
    },
    {
      "epoch": 0.018571428571428572,
      "grad_norm": 0.08823107928037643,
      "learning_rate": 0.024000000208616257,
      "loss": 3.378729820251465,
      "step": 390
    },
    {
      "epoch": 0.018666666666666668,
      "grad_norm": 0.09617450088262558,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3953237533569336,
      "step": 392
    },
    {
      "epoch": 0.01876190476190476,
      "grad_norm": 0.104954794049263,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3744618892669678,
      "step": 394
    },
    {
      "epoch": 0.018857142857142857,
      "grad_norm": 0.09269546717405319,
      "learning_rate": 0.024000000208616257,
      "loss": 3.368316173553467,
      "step": 396
    },
    {
      "epoch": 0.018952380952380953,
      "grad_norm": 0.11259199678897858,
      "learning_rate": 0.024000000208616257,
      "loss": 3.339540958404541,
      "step": 398
    },
    {
      "epoch": 0.01904761904761905,
      "grad_norm": 0.0991843044757843,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3897652626037598,
      "step": 400
    },
    {
      "epoch": 0.019142857142857142,
      "grad_norm": 0.0994994193315506,
      "learning_rate": 0.024000000208616257,
      "loss": 3.376940965652466,
      "step": 402
    },
    {
      "epoch": 0.019238095238095238,
      "grad_norm": 0.09660818427801132,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3687825202941895,
      "step": 404
    },
    {
      "epoch": 0.019333333333333334,
      "grad_norm": 0.0863373652100563,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3705267906188965,
      "step": 406
    },
    {
      "epoch": 0.019428571428571427,
      "grad_norm": 0.09684601426124573,
      "learning_rate": 0.024000000208616257,
      "loss": 3.375084638595581,
      "step": 408
    },
    {
      "epoch": 0.019523809523809523,
      "grad_norm": 0.10115697234869003,
      "learning_rate": 0.024000000208616257,
      "loss": 3.351313591003418,
      "step": 410
    },
    {
      "epoch": 0.01961904761904762,
      "grad_norm": 0.08989071846008301,
      "learning_rate": 0.024000000208616257,
      "loss": 3.356839179992676,
      "step": 412
    },
    {
      "epoch": 0.019714285714285715,
      "grad_norm": 0.0900016501545906,
      "learning_rate": 0.024000000208616257,
      "loss": 3.327641487121582,
      "step": 414
    },
    {
      "epoch": 0.019809523809523808,
      "grad_norm": 0.09114416688680649,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3325247764587402,
      "step": 416
    },
    {
      "epoch": 0.019904761904761904,
      "grad_norm": 0.10203016549348831,
      "learning_rate": 0.024000000208616257,
      "loss": 3.363564968109131,
      "step": 418
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.09062886983156204,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3132519721984863,
      "step": 420
    },
    {
      "epoch": 0.020095238095238097,
      "grad_norm": 0.10633069276809692,
      "learning_rate": 0.024000000208616257,
      "loss": 3.369839668273926,
      "step": 422
    },
    {
      "epoch": 0.02019047619047619,
      "grad_norm": 0.09011076390743256,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3549909591674805,
      "step": 424
    },
    {
      "epoch": 0.020285714285714285,
      "grad_norm": 0.10212909430265427,
      "learning_rate": 0.024000000208616257,
      "loss": 3.364309787750244,
      "step": 426
    },
    {
      "epoch": 0.02038095238095238,
      "grad_norm": 0.10170941799879074,
      "learning_rate": 0.024000000208616257,
      "loss": 3.338170051574707,
      "step": 428
    },
    {
      "epoch": 0.020476190476190478,
      "grad_norm": 0.08958912640810013,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3482747077941895,
      "step": 430
    },
    {
      "epoch": 0.02057142857142857,
      "grad_norm": 0.0949966311454773,
      "learning_rate": 0.024000000208616257,
      "loss": 3.358294725418091,
      "step": 432
    },
    {
      "epoch": 0.020666666666666667,
      "grad_norm": 0.0901513397693634,
      "learning_rate": 0.024000000208616257,
      "loss": 3.353799343109131,
      "step": 434
    },
    {
      "epoch": 0.020761904761904763,
      "grad_norm": 0.09647983312606812,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3723888397216797,
      "step": 436
    },
    {
      "epoch": 0.02085714285714286,
      "grad_norm": 0.09669607877731323,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3483431339263916,
      "step": 438
    },
    {
      "epoch": 0.02095238095238095,
      "grad_norm": 0.08591976016759872,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3569095134735107,
      "step": 440
    },
    {
      "epoch": 0.021047619047619048,
      "grad_norm": 0.08637959510087967,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3328800201416016,
      "step": 442
    },
    {
      "epoch": 0.021142857142857144,
      "grad_norm": 0.09086910635232925,
      "learning_rate": 0.024000000208616257,
      "loss": 3.332063913345337,
      "step": 444
    },
    {
      "epoch": 0.021238095238095236,
      "grad_norm": 0.08502456545829773,
      "learning_rate": 0.024000000208616257,
      "loss": 3.352468252182007,
      "step": 446
    },
    {
      "epoch": 0.021333333333333333,
      "grad_norm": 0.08834676444530487,
      "learning_rate": 0.024000000208616257,
      "loss": 3.353539228439331,
      "step": 448
    },
    {
      "epoch": 0.02142857142857143,
      "grad_norm": 0.09138694405555725,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3436567783355713,
      "step": 450
    },
    {
      "epoch": 0.021523809523809525,
      "grad_norm": 0.10472003370523453,
      "learning_rate": 0.024000000208616257,
      "loss": 3.327854633331299,
      "step": 452
    },
    {
      "epoch": 0.021619047619047618,
      "grad_norm": 0.09763047099113464,
      "learning_rate": 0.024000000208616257,
      "loss": 3.324946641921997,
      "step": 454
    },
    {
      "epoch": 0.021714285714285714,
      "grad_norm": 0.09421174228191376,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3445773124694824,
      "step": 456
    },
    {
      "epoch": 0.02180952380952381,
      "grad_norm": 0.09068513661623001,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3250272274017334,
      "step": 458
    },
    {
      "epoch": 0.021904761904761906,
      "grad_norm": 0.08916594833135605,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3360986709594727,
      "step": 460
    },
    {
      "epoch": 0.022,
      "grad_norm": 0.10518743097782135,
      "learning_rate": 0.024000000208616257,
      "loss": 3.339228630065918,
      "step": 462
    },
    {
      "epoch": 0.022095238095238095,
      "grad_norm": 0.08912716805934906,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3741464614868164,
      "step": 464
    },
    {
      "epoch": 0.02219047619047619,
      "grad_norm": 0.08554211258888245,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3536620140075684,
      "step": 466
    },
    {
      "epoch": 0.022285714285714287,
      "grad_norm": 0.09278947860002518,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2817907333374023,
      "step": 468
    },
    {
      "epoch": 0.02238095238095238,
      "grad_norm": 0.09330140799283981,
      "learning_rate": 0.024000000208616257,
      "loss": 3.340385913848877,
      "step": 470
    },
    {
      "epoch": 0.022476190476190476,
      "grad_norm": 0.08844682574272156,
      "learning_rate": 0.024000000208616257,
      "loss": 3.30399751663208,
      "step": 472
    },
    {
      "epoch": 0.022571428571428572,
      "grad_norm": 0.08637949079275131,
      "learning_rate": 0.024000000208616257,
      "loss": 3.316169261932373,
      "step": 474
    },
    {
      "epoch": 0.02266666666666667,
      "grad_norm": 0.0865374282002449,
      "learning_rate": 0.024000000208616257,
      "loss": 3.337653160095215,
      "step": 476
    },
    {
      "epoch": 0.02276190476190476,
      "grad_norm": 0.09139890968799591,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3410844802856445,
      "step": 478
    },
    {
      "epoch": 0.022857142857142857,
      "grad_norm": 0.09083344042301178,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3579235076904297,
      "step": 480
    },
    {
      "epoch": 0.022952380952380953,
      "grad_norm": 0.09038805216550827,
      "learning_rate": 0.024000000208616257,
      "loss": 3.313967704772949,
      "step": 482
    },
    {
      "epoch": 0.023047619047619046,
      "grad_norm": 0.08872606605291367,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3254542350769043,
      "step": 484
    },
    {
      "epoch": 0.023142857142857142,
      "grad_norm": 0.0929810181260109,
      "learning_rate": 0.024000000208616257,
      "loss": 3.325802803039551,
      "step": 486
    },
    {
      "epoch": 0.023238095238095238,
      "grad_norm": 0.09297630190849304,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3549675941467285,
      "step": 488
    },
    {
      "epoch": 0.023333333333333334,
      "grad_norm": 0.08241813629865646,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3219852447509766,
      "step": 490
    },
    {
      "epoch": 0.023428571428571427,
      "grad_norm": 0.09606776386499405,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3519091606140137,
      "step": 492
    },
    {
      "epoch": 0.023523809523809523,
      "grad_norm": 0.09051039069890976,
      "learning_rate": 0.024000000208616257,
      "loss": 3.303131103515625,
      "step": 494
    },
    {
      "epoch": 0.02361904761904762,
      "grad_norm": 0.09041043370962143,
      "learning_rate": 0.024000000208616257,
      "loss": 3.341622829437256,
      "step": 496
    },
    {
      "epoch": 0.023714285714285716,
      "grad_norm": 0.08397683501243591,
      "learning_rate": 0.024000000208616257,
      "loss": 3.28572678565979,
      "step": 498
    },
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 0.08695260435342789,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2822513580322266,
      "step": 500
    },
    {
      "epoch": 0.023904761904761904,
      "grad_norm": 0.09433641284704208,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3121323585510254,
      "step": 502
    },
    {
      "epoch": 0.024,
      "grad_norm": 0.08416978269815445,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3401541709899902,
      "step": 504
    },
    {
      "epoch": 0.024095238095238097,
      "grad_norm": 0.07843983173370361,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3193306922912598,
      "step": 506
    },
    {
      "epoch": 0.02419047619047619,
      "grad_norm": 0.08368676155805588,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3135461807250977,
      "step": 508
    },
    {
      "epoch": 0.024285714285714285,
      "grad_norm": 0.0851934403181076,
      "learning_rate": 0.024000000208616257,
      "loss": 3.314640998840332,
      "step": 510
    },
    {
      "epoch": 0.02438095238095238,
      "grad_norm": 0.08735057711601257,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3325018882751465,
      "step": 512
    },
    {
      "epoch": 0.024476190476190478,
      "grad_norm": 0.08266250044107437,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2619757652282715,
      "step": 514
    },
    {
      "epoch": 0.02457142857142857,
      "grad_norm": 0.09488537162542343,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3159022331237793,
      "step": 516
    },
    {
      "epoch": 0.024666666666666667,
      "grad_norm": 0.08253837376832962,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2534141540527344,
      "step": 518
    },
    {
      "epoch": 0.024761904761904763,
      "grad_norm": 0.0889001190662384,
      "learning_rate": 0.024000000208616257,
      "loss": 3.312020778656006,
      "step": 520
    },
    {
      "epoch": 0.024857142857142855,
      "grad_norm": 0.09991835057735443,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3071937561035156,
      "step": 522
    },
    {
      "epoch": 0.02495238095238095,
      "grad_norm": 0.08465713262557983,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3195252418518066,
      "step": 524
    },
    {
      "epoch": 0.025047619047619048,
      "grad_norm": 0.08082892745733261,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3125452995300293,
      "step": 526
    },
    {
      "epoch": 0.025142857142857144,
      "grad_norm": 0.08431288599967957,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3238134384155273,
      "step": 528
    },
    {
      "epoch": 0.025238095238095237,
      "grad_norm": 0.0876336395740509,
      "learning_rate": 0.024000000208616257,
      "loss": 3.311713218688965,
      "step": 530
    },
    {
      "epoch": 0.025333333333333333,
      "grad_norm": 0.08943317085504532,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2971935272216797,
      "step": 532
    },
    {
      "epoch": 0.02542857142857143,
      "grad_norm": 0.08404400944709778,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2701122760772705,
      "step": 534
    },
    {
      "epoch": 0.025523809523809525,
      "grad_norm": 0.08375234156847,
      "learning_rate": 0.024000000208616257,
      "loss": 3.299881935119629,
      "step": 536
    },
    {
      "epoch": 0.025619047619047618,
      "grad_norm": 0.08366347849369049,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2689080238342285,
      "step": 538
    },
    {
      "epoch": 0.025714285714285714,
      "grad_norm": 0.0880344957113266,
      "learning_rate": 0.024000000208616257,
      "loss": 3.286287307739258,
      "step": 540
    },
    {
      "epoch": 0.02580952380952381,
      "grad_norm": 0.08554854989051819,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2822937965393066,
      "step": 542
    },
    {
      "epoch": 0.025904761904761906,
      "grad_norm": 0.09102355688810349,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3268446922302246,
      "step": 544
    },
    {
      "epoch": 0.026,
      "grad_norm": 0.08388399332761765,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2783405780792236,
      "step": 546
    },
    {
      "epoch": 0.026095238095238095,
      "grad_norm": 0.08136118203401566,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2847094535827637,
      "step": 548
    },
    {
      "epoch": 0.02619047619047619,
      "grad_norm": 0.08426133543252945,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2694313526153564,
      "step": 550
    },
    {
      "epoch": 0.026285714285714287,
      "grad_norm": 0.07826825976371765,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3067517280578613,
      "step": 552
    },
    {
      "epoch": 0.02638095238095238,
      "grad_norm": 0.07997143268585205,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2627696990966797,
      "step": 554
    },
    {
      "epoch": 0.026476190476190476,
      "grad_norm": 0.07255858182907104,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3173160552978516,
      "step": 556
    },
    {
      "epoch": 0.026571428571428572,
      "grad_norm": 0.07426390051841736,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2966771125793457,
      "step": 558
    },
    {
      "epoch": 0.02666666666666667,
      "grad_norm": 0.07563555985689163,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2874350547790527,
      "step": 560
    },
    {
      "epoch": 0.02676190476190476,
      "grad_norm": 0.07340831309556961,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3080782890319824,
      "step": 562
    },
    {
      "epoch": 0.026857142857142857,
      "grad_norm": 0.07890055328607559,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3063645362854004,
      "step": 564
    },
    {
      "epoch": 0.026952380952380953,
      "grad_norm": 0.07918807119131088,
      "learning_rate": 0.024000000208616257,
      "loss": 3.318636417388916,
      "step": 566
    },
    {
      "epoch": 0.027047619047619046,
      "grad_norm": 0.07477977126836777,
      "learning_rate": 0.024000000208616257,
      "loss": 3.3263745307922363,
      "step": 568
    },
    {
      "epoch": 0.027142857142857142,
      "grad_norm": 0.0745420902967453,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2653188705444336,
      "step": 570
    },
    {
      "epoch": 0.02723809523809524,
      "grad_norm": 0.07391494512557983,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2731356620788574,
      "step": 572
    },
    {
      "epoch": 0.027333333333333334,
      "grad_norm": 0.07435967773199081,
      "learning_rate": 0.024000000208616257,
      "loss": 3.299403667449951,
      "step": 574
    },
    {
      "epoch": 0.027428571428571427,
      "grad_norm": 0.07816862314939499,
      "learning_rate": 0.024000000208616257,
      "loss": 3.292506694793701,
      "step": 576
    },
    {
      "epoch": 0.027523809523809523,
      "grad_norm": 0.07465045899152756,
      "learning_rate": 0.024000000208616257,
      "loss": 3.303959846496582,
      "step": 578
    },
    {
      "epoch": 0.02761904761904762,
      "grad_norm": 0.08007777482271194,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2651515007019043,
      "step": 580
    },
    {
      "epoch": 0.027714285714285716,
      "grad_norm": 0.07768258452415466,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2572450637817383,
      "step": 582
    },
    {
      "epoch": 0.02780952380952381,
      "grad_norm": 0.07689087092876434,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2957043647766113,
      "step": 584
    },
    {
      "epoch": 0.027904761904761904,
      "grad_norm": 0.08504579216241837,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2990970611572266,
      "step": 586
    },
    {
      "epoch": 0.028,
      "grad_norm": 0.09150636196136475,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2734103202819824,
      "step": 588
    },
    {
      "epoch": 0.028095238095238097,
      "grad_norm": 0.08489084988832474,
      "learning_rate": 0.024000000208616257,
      "loss": 3.276306629180908,
      "step": 590
    },
    {
      "epoch": 0.02819047619047619,
      "grad_norm": 0.0749487578868866,
      "learning_rate": 0.024000000208616257,
      "loss": 3.284188747406006,
      "step": 592
    },
    {
      "epoch": 0.028285714285714286,
      "grad_norm": 0.07584529370069504,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2419469356536865,
      "step": 594
    },
    {
      "epoch": 0.02838095238095238,
      "grad_norm": 0.0757167637348175,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2719264030456543,
      "step": 596
    },
    {
      "epoch": 0.028476190476190478,
      "grad_norm": 0.08220788091421127,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2787561416625977,
      "step": 598
    },
    {
      "epoch": 0.02857142857142857,
      "grad_norm": 0.07616401463747025,
      "learning_rate": 0.024000000208616257,
      "loss": 3.251516819000244,
      "step": 600
    },
    {
      "epoch": 0.028666666666666667,
      "grad_norm": 0.0860067680478096,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2518413066864014,
      "step": 602
    },
    {
      "epoch": 0.028761904761904763,
      "grad_norm": 0.08446262776851654,
      "learning_rate": 0.024000000208616257,
      "loss": 3.27824330329895,
      "step": 604
    },
    {
      "epoch": 0.028857142857142856,
      "grad_norm": 0.07788730412721634,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2762060165405273,
      "step": 606
    },
    {
      "epoch": 0.02895238095238095,
      "grad_norm": 0.08228492736816406,
      "learning_rate": 0.024000000208616257,
      "loss": 3.271141767501831,
      "step": 608
    },
    {
      "epoch": 0.029047619047619048,
      "grad_norm": 0.08117784559726715,
      "learning_rate": 0.024000000208616257,
      "loss": 3.268932819366455,
      "step": 610
    },
    {
      "epoch": 0.029142857142857144,
      "grad_norm": 0.07280375808477402,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2373249530792236,
      "step": 612
    },
    {
      "epoch": 0.029238095238095237,
      "grad_norm": 0.07577385008335114,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2347710132598877,
      "step": 614
    },
    {
      "epoch": 0.029333333333333333,
      "grad_norm": 0.07516426593065262,
      "learning_rate": 0.024000000208616257,
      "loss": 3.262713670730591,
      "step": 616
    },
    {
      "epoch": 0.02942857142857143,
      "grad_norm": 0.08333681523799896,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2337334156036377,
      "step": 618
    },
    {
      "epoch": 0.029523809523809525,
      "grad_norm": 0.07921888679265976,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2889490127563477,
      "step": 620
    },
    {
      "epoch": 0.029619047619047618,
      "grad_norm": 0.076380155980587,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2540183067321777,
      "step": 622
    },
    {
      "epoch": 0.029714285714285714,
      "grad_norm": 0.07165036350488663,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2376198768615723,
      "step": 624
    },
    {
      "epoch": 0.02980952380952381,
      "grad_norm": 0.07230059057474136,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2197844982147217,
      "step": 626
    },
    {
      "epoch": 0.029904761904761906,
      "grad_norm": 0.07571039348840714,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2135324478149414,
      "step": 628
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.0722360759973526,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2413320541381836,
      "step": 630
    },
    {
      "epoch": 0.030095238095238095,
      "grad_norm": 0.0737529769539833,
      "learning_rate": 0.024000000208616257,
      "loss": 3.237673759460449,
      "step": 632
    },
    {
      "epoch": 0.03019047619047619,
      "grad_norm": 0.0708562508225441,
      "learning_rate": 0.024000000208616257,
      "loss": 3.239184856414795,
      "step": 634
    },
    {
      "epoch": 0.030285714285714287,
      "grad_norm": 0.07465169578790665,
      "learning_rate": 0.024000000208616257,
      "loss": 3.247126340866089,
      "step": 636
    },
    {
      "epoch": 0.03038095238095238,
      "grad_norm": 0.07865563780069351,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2413077354431152,
      "step": 638
    },
    {
      "epoch": 0.030476190476190476,
      "grad_norm": 0.07570512592792511,
      "learning_rate": 0.024000000208616257,
      "loss": 3.241866111755371,
      "step": 640
    },
    {
      "epoch": 0.030571428571428572,
      "grad_norm": 0.07566533982753754,
      "learning_rate": 0.024000000208616257,
      "loss": 3.230283737182617,
      "step": 642
    },
    {
      "epoch": 0.030666666666666665,
      "grad_norm": 0.07939726114273071,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2430949211120605,
      "step": 644
    },
    {
      "epoch": 0.03076190476190476,
      "grad_norm": 0.07281908392906189,
      "learning_rate": 0.024000000208616257,
      "loss": 3.235027551651001,
      "step": 646
    },
    {
      "epoch": 0.030857142857142857,
      "grad_norm": 0.07376979291439056,
      "learning_rate": 0.024000000208616257,
      "loss": 3.241706132888794,
      "step": 648
    },
    {
      "epoch": 0.030952380952380953,
      "grad_norm": 0.07461351901292801,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2333860397338867,
      "step": 650
    },
    {
      "epoch": 0.031047619047619046,
      "grad_norm": 0.07640799880027771,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2356271743774414,
      "step": 652
    },
    {
      "epoch": 0.031142857142857142,
      "grad_norm": 0.08132467418909073,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2246525287628174,
      "step": 654
    },
    {
      "epoch": 0.03123809523809524,
      "grad_norm": 0.08438136428594589,
      "learning_rate": 0.024000000208616257,
      "loss": 3.238943099975586,
      "step": 656
    },
    {
      "epoch": 0.03133333333333333,
      "grad_norm": 0.07416946440935135,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1642227172851562,
      "step": 658
    },
    {
      "epoch": 0.03142857142857143,
      "grad_norm": 0.07203076034784317,
      "learning_rate": 0.024000000208616257,
      "loss": 3.229591131210327,
      "step": 660
    },
    {
      "epoch": 0.03152380952380952,
      "grad_norm": 0.06781172007322311,
      "learning_rate": 0.024000000208616257,
      "loss": 3.228139877319336,
      "step": 662
    },
    {
      "epoch": 0.031619047619047616,
      "grad_norm": 0.07503106445074081,
      "learning_rate": 0.024000000208616257,
      "loss": 3.197584629058838,
      "step": 664
    },
    {
      "epoch": 0.031714285714285716,
      "grad_norm": 0.07130474597215652,
      "learning_rate": 0.024000000208616257,
      "loss": 3.203066110610962,
      "step": 666
    },
    {
      "epoch": 0.03180952380952381,
      "grad_norm": 0.0787835493683815,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2011899948120117,
      "step": 668
    },
    {
      "epoch": 0.03190476190476191,
      "grad_norm": 0.07815150171518326,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1930465698242188,
      "step": 670
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.07381319254636765,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1839358806610107,
      "step": 672
    },
    {
      "epoch": 0.03209523809523809,
      "grad_norm": 0.07276026159524918,
      "learning_rate": 0.024000000208616257,
      "loss": 3.239224433898926,
      "step": 674
    },
    {
      "epoch": 0.03219047619047619,
      "grad_norm": 0.07294740527868271,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2312121391296387,
      "step": 676
    },
    {
      "epoch": 0.032285714285714286,
      "grad_norm": 0.06824035942554474,
      "learning_rate": 0.024000000208616257,
      "loss": 3.180049419403076,
      "step": 678
    },
    {
      "epoch": 0.03238095238095238,
      "grad_norm": 0.06968836486339569,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2029576301574707,
      "step": 680
    },
    {
      "epoch": 0.03247619047619048,
      "grad_norm": 0.07547624409198761,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2137365341186523,
      "step": 682
    },
    {
      "epoch": 0.03257142857142857,
      "grad_norm": 0.07893373817205429,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2070488929748535,
      "step": 684
    },
    {
      "epoch": 0.03266666666666666,
      "grad_norm": 0.07199888676404953,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1975550651550293,
      "step": 686
    },
    {
      "epoch": 0.03276190476190476,
      "grad_norm": 0.07550406455993652,
      "learning_rate": 0.024000000208616257,
      "loss": 3.183717966079712,
      "step": 688
    },
    {
      "epoch": 0.032857142857142856,
      "grad_norm": 0.0771876648068428,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2129225730895996,
      "step": 690
    },
    {
      "epoch": 0.032952380952380955,
      "grad_norm": 0.0741945430636406,
      "learning_rate": 0.024000000208616257,
      "loss": 3.217057943344116,
      "step": 692
    },
    {
      "epoch": 0.03304761904761905,
      "grad_norm": 0.08009914308786392,
      "learning_rate": 0.024000000208616257,
      "loss": 3.176427125930786,
      "step": 694
    },
    {
      "epoch": 0.03314285714285714,
      "grad_norm": 0.07615108788013458,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1865429878234863,
      "step": 696
    },
    {
      "epoch": 0.03323809523809524,
      "grad_norm": 0.07548828423023224,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2012887001037598,
      "step": 698
    },
    {
      "epoch": 0.03333333333333333,
      "grad_norm": 0.07466068118810654,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1872074604034424,
      "step": 700
    },
    {
      "epoch": 0.033428571428571426,
      "grad_norm": 0.08404888212680817,
      "learning_rate": 0.024000000208616257,
      "loss": 3.212120532989502,
      "step": 702
    },
    {
      "epoch": 0.033523809523809525,
      "grad_norm": 0.08296217769384384,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1915016174316406,
      "step": 704
    },
    {
      "epoch": 0.03361904761904762,
      "grad_norm": 0.07982564717531204,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2320799827575684,
      "step": 706
    },
    {
      "epoch": 0.03371428571428572,
      "grad_norm": 0.0702260360121727,
      "learning_rate": 0.024000000208616257,
      "loss": 3.176420211791992,
      "step": 708
    },
    {
      "epoch": 0.03380952380952381,
      "grad_norm": 0.06436009705066681,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1648738384246826,
      "step": 710
    },
    {
      "epoch": 0.0339047619047619,
      "grad_norm": 0.06554312258958817,
      "learning_rate": 0.024000000208616257,
      "loss": 3.177537441253662,
      "step": 712
    },
    {
      "epoch": 0.034,
      "grad_norm": 0.0696633830666542,
      "learning_rate": 0.024000000208616257,
      "loss": 3.161865711212158,
      "step": 714
    },
    {
      "epoch": 0.034095238095238095,
      "grad_norm": 0.0706041231751442,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1790690422058105,
      "step": 716
    },
    {
      "epoch": 0.03419047619047619,
      "grad_norm": 0.06836401671171188,
      "learning_rate": 0.024000000208616257,
      "loss": 3.154026508331299,
      "step": 718
    },
    {
      "epoch": 0.03428571428571429,
      "grad_norm": 0.07681194692850113,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1468605995178223,
      "step": 720
    },
    {
      "epoch": 0.03438095238095238,
      "grad_norm": 0.07750710844993591,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1578662395477295,
      "step": 722
    },
    {
      "epoch": 0.03447619047619047,
      "grad_norm": 0.06742233037948608,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2457776069641113,
      "step": 724
    },
    {
      "epoch": 0.03457142857142857,
      "grad_norm": 0.06920700520277023,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1927900314331055,
      "step": 726
    },
    {
      "epoch": 0.034666666666666665,
      "grad_norm": 0.07110117375850677,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1812782287597656,
      "step": 728
    },
    {
      "epoch": 0.034761904761904765,
      "grad_norm": 0.08268111199140549,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1666388511657715,
      "step": 730
    },
    {
      "epoch": 0.03485714285714286,
      "grad_norm": 0.08110952377319336,
      "learning_rate": 0.024000000208616257,
      "loss": 3.2147364616394043,
      "step": 732
    },
    {
      "epoch": 0.03495238095238095,
      "grad_norm": 0.08320687711238861,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1722617149353027,
      "step": 734
    },
    {
      "epoch": 0.03504761904761905,
      "grad_norm": 0.0814925879240036,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1830286979675293,
      "step": 736
    },
    {
      "epoch": 0.03514285714285714,
      "grad_norm": 0.08159703016281128,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1796393394470215,
      "step": 738
    },
    {
      "epoch": 0.035238095238095235,
      "grad_norm": 0.06512708216905594,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1944589614868164,
      "step": 740
    },
    {
      "epoch": 0.035333333333333335,
      "grad_norm": 0.06749378144741058,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1454129219055176,
      "step": 742
    },
    {
      "epoch": 0.03542857142857143,
      "grad_norm": 0.07329411804676056,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1638593673706055,
      "step": 744
    },
    {
      "epoch": 0.03552380952380953,
      "grad_norm": 0.0763290598988533,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1893742084503174,
      "step": 746
    },
    {
      "epoch": 0.03561904761904762,
      "grad_norm": 0.07005666196346283,
      "learning_rate": 0.024000000208616257,
      "loss": 3.13489031791687,
      "step": 748
    },
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 0.06956160068511963,
      "learning_rate": 0.024000000208616257,
      "loss": 3.166025161743164,
      "step": 750
    },
    {
      "epoch": 0.03580952380952381,
      "grad_norm": 0.06571304053068161,
      "learning_rate": 0.024000000208616257,
      "loss": 3.156802177429199,
      "step": 752
    },
    {
      "epoch": 0.035904761904761905,
      "grad_norm": 0.07679462432861328,
      "learning_rate": 0.024000000208616257,
      "loss": 3.138455867767334,
      "step": 754
    },
    {
      "epoch": 0.036,
      "grad_norm": 0.07127557694911957,
      "learning_rate": 0.024000000208616257,
      "loss": 3.158381700515747,
      "step": 756
    },
    {
      "epoch": 0.0360952380952381,
      "grad_norm": 0.06858626753091812,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1413769721984863,
      "step": 758
    },
    {
      "epoch": 0.03619047619047619,
      "grad_norm": 0.06887949258089066,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1974706649780273,
      "step": 760
    },
    {
      "epoch": 0.03628571428571428,
      "grad_norm": 0.07180433720350266,
      "learning_rate": 0.024000000208616257,
      "loss": 3.142838954925537,
      "step": 762
    },
    {
      "epoch": 0.03638095238095238,
      "grad_norm": 0.07630762457847595,
      "learning_rate": 0.024000000208616257,
      "loss": 3.13484525680542,
      "step": 764
    },
    {
      "epoch": 0.036476190476190475,
      "grad_norm": 0.06539653986692429,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1610283851623535,
      "step": 766
    },
    {
      "epoch": 0.036571428571428574,
      "grad_norm": 0.06617697328329086,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1803746223449707,
      "step": 768
    },
    {
      "epoch": 0.03666666666666667,
      "grad_norm": 0.07375525683164597,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1807384490966797,
      "step": 770
    },
    {
      "epoch": 0.03676190476190476,
      "grad_norm": 0.06634707748889923,
      "learning_rate": 0.024000000208616257,
      "loss": 3.156447172164917,
      "step": 772
    },
    {
      "epoch": 0.03685714285714286,
      "grad_norm": 0.06482807546854019,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1762161254882812,
      "step": 774
    },
    {
      "epoch": 0.03695238095238095,
      "grad_norm": 0.06851062923669815,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1759800910949707,
      "step": 776
    },
    {
      "epoch": 0.037047619047619045,
      "grad_norm": 0.06895986944437027,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1339364051818848,
      "step": 778
    },
    {
      "epoch": 0.037142857142857144,
      "grad_norm": 0.07117994874715805,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1467373371124268,
      "step": 780
    },
    {
      "epoch": 0.03723809523809524,
      "grad_norm": 0.07626303285360336,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1602282524108887,
      "step": 782
    },
    {
      "epoch": 0.037333333333333336,
      "grad_norm": 0.06421144306659698,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1545724868774414,
      "step": 784
    },
    {
      "epoch": 0.03742857142857143,
      "grad_norm": 0.06410733610391617,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1749696731567383,
      "step": 786
    },
    {
      "epoch": 0.03752380952380952,
      "grad_norm": 0.06822361052036285,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1546266078948975,
      "step": 788
    },
    {
      "epoch": 0.03761904761904762,
      "grad_norm": 0.06876611709594727,
      "learning_rate": 0.024000000208616257,
      "loss": 3.137157917022705,
      "step": 790
    },
    {
      "epoch": 0.037714285714285714,
      "grad_norm": 0.06471683084964752,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1217448711395264,
      "step": 792
    },
    {
      "epoch": 0.03780952380952381,
      "grad_norm": 0.06299459934234619,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1454782485961914,
      "step": 794
    },
    {
      "epoch": 0.037904761904761906,
      "grad_norm": 0.06754894554615021,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1453404426574707,
      "step": 796
    },
    {
      "epoch": 0.038,
      "grad_norm": 0.07478955388069153,
      "learning_rate": 0.024000000208616257,
      "loss": 3.144214153289795,
      "step": 798
    },
    {
      "epoch": 0.0380952380952381,
      "grad_norm": 0.0659400150179863,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1132359504699707,
      "step": 800
    },
    {
      "epoch": 0.03819047619047619,
      "grad_norm": 0.06845249980688095,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1357860565185547,
      "step": 802
    },
    {
      "epoch": 0.038285714285714284,
      "grad_norm": 0.06860584020614624,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1594438552856445,
      "step": 804
    },
    {
      "epoch": 0.038380952380952384,
      "grad_norm": 0.07030051201581955,
      "learning_rate": 0.024000000208616257,
      "loss": 3.18593692779541,
      "step": 806
    },
    {
      "epoch": 0.038476190476190476,
      "grad_norm": 0.07023944705724716,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1356382369995117,
      "step": 808
    },
    {
      "epoch": 0.03857142857142857,
      "grad_norm": 0.08672435581684113,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1328818798065186,
      "step": 810
    },
    {
      "epoch": 0.03866666666666667,
      "grad_norm": 0.07612980157136917,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1412744522094727,
      "step": 812
    },
    {
      "epoch": 0.03876190476190476,
      "grad_norm": 0.0680103600025177,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1005563735961914,
      "step": 814
    },
    {
      "epoch": 0.038857142857142854,
      "grad_norm": 0.06437309831380844,
      "learning_rate": 0.024000000208616257,
      "loss": 3.131866455078125,
      "step": 816
    },
    {
      "epoch": 0.038952380952380954,
      "grad_norm": 0.0659368485212326,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1187214851379395,
      "step": 818
    },
    {
      "epoch": 0.039047619047619046,
      "grad_norm": 0.06681571900844574,
      "learning_rate": 0.024000000208616257,
      "loss": 3.119333267211914,
      "step": 820
    },
    {
      "epoch": 0.039142857142857146,
      "grad_norm": 0.0727713406085968,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1186232566833496,
      "step": 822
    },
    {
      "epoch": 0.03923809523809524,
      "grad_norm": 0.07257276028394699,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1727452278137207,
      "step": 824
    },
    {
      "epoch": 0.03933333333333333,
      "grad_norm": 0.06537605077028275,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1685996055603027,
      "step": 826
    },
    {
      "epoch": 0.03942857142857143,
      "grad_norm": 0.07205349206924438,
      "learning_rate": 0.024000000208616257,
      "loss": 3.126197338104248,
      "step": 828
    },
    {
      "epoch": 0.039523809523809524,
      "grad_norm": 0.07520736008882523,
      "learning_rate": 0.024000000208616257,
      "loss": 3.097465753555298,
      "step": 830
    },
    {
      "epoch": 0.039619047619047616,
      "grad_norm": 0.06576979160308838,
      "learning_rate": 0.024000000208616257,
      "loss": 3.123183488845825,
      "step": 832
    },
    {
      "epoch": 0.039714285714285716,
      "grad_norm": 0.07439937442541122,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1157078742980957,
      "step": 834
    },
    {
      "epoch": 0.03980952380952381,
      "grad_norm": 0.07092170417308807,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0969648361206055,
      "step": 836
    },
    {
      "epoch": 0.03990476190476191,
      "grad_norm": 0.06886891275644302,
      "learning_rate": 0.024000000208616257,
      "loss": 3.130530834197998,
      "step": 838
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.06731168925762177,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1135735511779785,
      "step": 840
    },
    {
      "epoch": 0.040095238095238094,
      "grad_norm": 0.06422185152769089,
      "learning_rate": 0.024000000208616257,
      "loss": 3.132582187652588,
      "step": 842
    },
    {
      "epoch": 0.04019047619047619,
      "grad_norm": 0.06998761743307114,
      "learning_rate": 0.024000000208616257,
      "loss": 3.117568016052246,
      "step": 844
    },
    {
      "epoch": 0.040285714285714286,
      "grad_norm": 0.06589635461568832,
      "learning_rate": 0.024000000208616257,
      "loss": 3.102053642272949,
      "step": 846
    },
    {
      "epoch": 0.04038095238095238,
      "grad_norm": 0.06501191854476929,
      "learning_rate": 0.024000000208616257,
      "loss": 3.120415687561035,
      "step": 848
    },
    {
      "epoch": 0.04047619047619048,
      "grad_norm": 0.06688158214092255,
      "learning_rate": 0.024000000208616257,
      "loss": 3.113985061645508,
      "step": 850
    },
    {
      "epoch": 0.04057142857142857,
      "grad_norm": 0.07136926054954529,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0967507362365723,
      "step": 852
    },
    {
      "epoch": 0.04066666666666666,
      "grad_norm": 0.07345432043075562,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0976791381835938,
      "step": 854
    },
    {
      "epoch": 0.04076190476190476,
      "grad_norm": 0.06671705096960068,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1271042823791504,
      "step": 856
    },
    {
      "epoch": 0.040857142857142856,
      "grad_norm": 0.0703168734908104,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1158695220947266,
      "step": 858
    },
    {
      "epoch": 0.040952380952380955,
      "grad_norm": 0.0657120868563652,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1168711185455322,
      "step": 860
    },
    {
      "epoch": 0.04104761904761905,
      "grad_norm": 0.06279563158750534,
      "learning_rate": 0.024000000208616257,
      "loss": 3.112147808074951,
      "step": 862
    },
    {
      "epoch": 0.04114285714285714,
      "grad_norm": 0.06903357058763504,
      "learning_rate": 0.024000000208616257,
      "loss": 3.130458354949951,
      "step": 864
    },
    {
      "epoch": 0.04123809523809524,
      "grad_norm": 0.07460320740938187,
      "learning_rate": 0.024000000208616257,
      "loss": 3.047708511352539,
      "step": 866
    },
    {
      "epoch": 0.04133333333333333,
      "grad_norm": 0.07181910425424576,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0596158504486084,
      "step": 868
    },
    {
      "epoch": 0.041428571428571426,
      "grad_norm": 0.062275804579257965,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0899834632873535,
      "step": 870
    },
    {
      "epoch": 0.041523809523809525,
      "grad_norm": 0.06110190227627754,
      "learning_rate": 0.024000000208616257,
      "loss": 3.121835708618164,
      "step": 872
    },
    {
      "epoch": 0.04161904761904762,
      "grad_norm": 0.062481507658958435,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1040072441101074,
      "step": 874
    },
    {
      "epoch": 0.04171428571428572,
      "grad_norm": 0.06465902179479599,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0803303718566895,
      "step": 876
    },
    {
      "epoch": 0.04180952380952381,
      "grad_norm": 0.06454935669898987,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0644068717956543,
      "step": 878
    },
    {
      "epoch": 0.0419047619047619,
      "grad_norm": 0.06235034391283989,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0754425525665283,
      "step": 880
    },
    {
      "epoch": 0.042,
      "grad_norm": 0.06558102369308472,
      "learning_rate": 0.024000000208616257,
      "loss": 3.095618724822998,
      "step": 882
    },
    {
      "epoch": 0.042095238095238095,
      "grad_norm": 0.06225241720676422,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0607080459594727,
      "step": 884
    },
    {
      "epoch": 0.04219047619047619,
      "grad_norm": 0.0613737627863884,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1157031059265137,
      "step": 886
    },
    {
      "epoch": 0.04228571428571429,
      "grad_norm": 0.061712831258773804,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0956549644470215,
      "step": 888
    },
    {
      "epoch": 0.04238095238095238,
      "grad_norm": 0.06462763249874115,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0844128131866455,
      "step": 890
    },
    {
      "epoch": 0.04247619047619047,
      "grad_norm": 0.0794723704457283,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0859038829803467,
      "step": 892
    },
    {
      "epoch": 0.04257142857142857,
      "grad_norm": 0.07729235291481018,
      "learning_rate": 0.024000000208616257,
      "loss": 3.072681427001953,
      "step": 894
    },
    {
      "epoch": 0.042666666666666665,
      "grad_norm": 0.07238233834505081,
      "learning_rate": 0.024000000208616257,
      "loss": 3.075396776199341,
      "step": 896
    },
    {
      "epoch": 0.042761904761904765,
      "grad_norm": 0.06877360492944717,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0765905380249023,
      "step": 898
    },
    {
      "epoch": 0.04285714285714286,
      "grad_norm": 0.07515493035316467,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0844407081604004,
      "step": 900
    },
    {
      "epoch": 0.04295238095238095,
      "grad_norm": 0.07547783106565475,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0706019401550293,
      "step": 902
    },
    {
      "epoch": 0.04304761904761905,
      "grad_norm": 0.06627517938613892,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0726070404052734,
      "step": 904
    },
    {
      "epoch": 0.04314285714285714,
      "grad_norm": 0.06536763906478882,
      "learning_rate": 0.024000000208616257,
      "loss": 3.087002992630005,
      "step": 906
    },
    {
      "epoch": 0.043238095238095235,
      "grad_norm": 0.07094710320234299,
      "learning_rate": 0.024000000208616257,
      "loss": 3.051009178161621,
      "step": 908
    },
    {
      "epoch": 0.043333333333333335,
      "grad_norm": 0.06429240852594376,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0804049968719482,
      "step": 910
    },
    {
      "epoch": 0.04342857142857143,
      "grad_norm": 0.06235828623175621,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0663909912109375,
      "step": 912
    },
    {
      "epoch": 0.04352380952380953,
      "grad_norm": 0.0697418674826622,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0646214485168457,
      "step": 914
    },
    {
      "epoch": 0.04361904761904762,
      "grad_norm": 0.06777344644069672,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0696520805358887,
      "step": 916
    },
    {
      "epoch": 0.04371428571428571,
      "grad_norm": 0.06729612499475479,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0770034790039062,
      "step": 918
    },
    {
      "epoch": 0.04380952380952381,
      "grad_norm": 0.0657837763428688,
      "learning_rate": 0.024000000208616257,
      "loss": 3.09183669090271,
      "step": 920
    },
    {
      "epoch": 0.043904761904761905,
      "grad_norm": 0.06455850601196289,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0763893127441406,
      "step": 922
    },
    {
      "epoch": 0.044,
      "grad_norm": 0.06527040153741837,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0549378395080566,
      "step": 924
    },
    {
      "epoch": 0.0440952380952381,
      "grad_norm": 0.06264866888523102,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1002461910247803,
      "step": 926
    },
    {
      "epoch": 0.04419047619047619,
      "grad_norm": 0.06643705070018768,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0791029930114746,
      "step": 928
    },
    {
      "epoch": 0.04428571428571428,
      "grad_norm": 0.06560289859771729,
      "learning_rate": 0.024000000208616257,
      "loss": 3.056124210357666,
      "step": 930
    },
    {
      "epoch": 0.04438095238095238,
      "grad_norm": 0.07225628942251205,
      "learning_rate": 0.024000000208616257,
      "loss": 3.077237606048584,
      "step": 932
    },
    {
      "epoch": 0.044476190476190475,
      "grad_norm": 0.0648811012506485,
      "learning_rate": 0.024000000208616257,
      "loss": 3.051553964614868,
      "step": 934
    },
    {
      "epoch": 0.044571428571428574,
      "grad_norm": 0.06221294030547142,
      "learning_rate": 0.024000000208616257,
      "loss": 3.065746307373047,
      "step": 936
    },
    {
      "epoch": 0.04466666666666667,
      "grad_norm": 0.06485804170370102,
      "learning_rate": 0.024000000208616257,
      "loss": 3.075626850128174,
      "step": 938
    },
    {
      "epoch": 0.04476190476190476,
      "grad_norm": 0.06684035807847977,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0684847831726074,
      "step": 940
    },
    {
      "epoch": 0.04485714285714286,
      "grad_norm": 0.06848568469285965,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0551886558532715,
      "step": 942
    },
    {
      "epoch": 0.04495238095238095,
      "grad_norm": 0.06428419798612595,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0681066513061523,
      "step": 944
    },
    {
      "epoch": 0.045047619047619045,
      "grad_norm": 0.06246276944875717,
      "learning_rate": 0.024000000208616257,
      "loss": 3.069855213165283,
      "step": 946
    },
    {
      "epoch": 0.045142857142857144,
      "grad_norm": 0.06441211700439453,
      "learning_rate": 0.024000000208616257,
      "loss": 3.076978921890259,
      "step": 948
    },
    {
      "epoch": 0.04523809523809524,
      "grad_norm": 0.060650404542684555,
      "learning_rate": 0.024000000208616257,
      "loss": 3.058931827545166,
      "step": 950
    },
    {
      "epoch": 0.04533333333333334,
      "grad_norm": 0.06274467706680298,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0689749717712402,
      "step": 952
    },
    {
      "epoch": 0.04542857142857143,
      "grad_norm": 0.062426384538412094,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9861903190612793,
      "step": 954
    },
    {
      "epoch": 0.04552380952380952,
      "grad_norm": 0.07028868794441223,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0526235103607178,
      "step": 956
    },
    {
      "epoch": 0.04561904761904762,
      "grad_norm": 0.08050168305635452,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0686590671539307,
      "step": 958
    },
    {
      "epoch": 0.045714285714285714,
      "grad_norm": 0.07005076855421066,
      "learning_rate": 0.024000000208616257,
      "loss": 3.067628860473633,
      "step": 960
    },
    {
      "epoch": 0.04580952380952381,
      "grad_norm": 0.05959608033299446,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0191359519958496,
      "step": 962
    },
    {
      "epoch": 0.04590476190476191,
      "grad_norm": 0.05864005535840988,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0680694580078125,
      "step": 964
    },
    {
      "epoch": 0.046,
      "grad_norm": 0.0645788311958313,
      "learning_rate": 0.024000000208616257,
      "loss": 3.074080467224121,
      "step": 966
    },
    {
      "epoch": 0.04609523809523809,
      "grad_norm": 0.06542934477329254,
      "learning_rate": 0.024000000208616257,
      "loss": 3.074032783508301,
      "step": 968
    },
    {
      "epoch": 0.04619047619047619,
      "grad_norm": 0.06495311111211777,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0810647010803223,
      "step": 970
    },
    {
      "epoch": 0.046285714285714284,
      "grad_norm": 0.06691587716341019,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0416259765625,
      "step": 972
    },
    {
      "epoch": 0.046380952380952384,
      "grad_norm": 0.06752321869134903,
      "learning_rate": 0.024000000208616257,
      "loss": 3.090067148208618,
      "step": 974
    },
    {
      "epoch": 0.046476190476190476,
      "grad_norm": 0.06306398659944534,
      "learning_rate": 0.024000000208616257,
      "loss": 3.052189826965332,
      "step": 976
    },
    {
      "epoch": 0.04657142857142857,
      "grad_norm": 0.06301634758710861,
      "learning_rate": 0.024000000208616257,
      "loss": 3.058084487915039,
      "step": 978
    },
    {
      "epoch": 0.04666666666666667,
      "grad_norm": 0.06827303022146225,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0563530921936035,
      "step": 980
    },
    {
      "epoch": 0.04676190476190476,
      "grad_norm": 0.06573956459760666,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0880050659179688,
      "step": 982
    },
    {
      "epoch": 0.046857142857142854,
      "grad_norm": 0.06142352148890495,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0661873817443848,
      "step": 984
    },
    {
      "epoch": 0.046952380952380954,
      "grad_norm": 0.06406045705080032,
      "learning_rate": 0.024000000208616257,
      "loss": 3.063352108001709,
      "step": 986
    },
    {
      "epoch": 0.047047619047619046,
      "grad_norm": 0.06274869292974472,
      "learning_rate": 0.024000000208616257,
      "loss": 3.055903196334839,
      "step": 988
    },
    {
      "epoch": 0.047142857142857146,
      "grad_norm": 0.05941158905625343,
      "learning_rate": 0.024000000208616257,
      "loss": 3.061056137084961,
      "step": 990
    },
    {
      "epoch": 0.04723809523809524,
      "grad_norm": 0.05682099983096123,
      "learning_rate": 0.024000000208616257,
      "loss": 3.079113006591797,
      "step": 992
    },
    {
      "epoch": 0.04733333333333333,
      "grad_norm": 0.05980977043509483,
      "learning_rate": 0.024000000208616257,
      "loss": 3.048689365386963,
      "step": 994
    },
    {
      "epoch": 0.04742857142857143,
      "grad_norm": 0.061439573764801025,
      "learning_rate": 0.024000000208616257,
      "loss": 3.06083607673645,
      "step": 996
    },
    {
      "epoch": 0.047523809523809524,
      "grad_norm": 0.06291661411523819,
      "learning_rate": 0.024000000208616257,
      "loss": 3.055856227874756,
      "step": 998
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 0.05849756672978401,
      "learning_rate": 0.024000000208616257,
      "loss": 3.024712562561035,
      "step": 1000
    },
    {
      "epoch": 0.047714285714285716,
      "grad_norm": 0.06354766339063644,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0479273796081543,
      "step": 1002
    },
    {
      "epoch": 0.04780952380952381,
      "grad_norm": 0.07189547270536423,
      "learning_rate": 0.024000000208616257,
      "loss": 3.037203311920166,
      "step": 1004
    },
    {
      "epoch": 0.0479047619047619,
      "grad_norm": 0.06168299913406372,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0696561336517334,
      "step": 1006
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.06008967384696007,
      "learning_rate": 0.024000000208616257,
      "loss": 3.03644061088562,
      "step": 1008
    },
    {
      "epoch": 0.048095238095238094,
      "grad_norm": 0.062147356569767,
      "learning_rate": 0.024000000208616257,
      "loss": 3.086516857147217,
      "step": 1010
    },
    {
      "epoch": 0.04819047619047619,
      "grad_norm": 0.0690990760922432,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0647566318511963,
      "step": 1012
    },
    {
      "epoch": 0.048285714285714286,
      "grad_norm": 0.06334016472101212,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0747222900390625,
      "step": 1014
    },
    {
      "epoch": 0.04838095238095238,
      "grad_norm": 0.06369421631097794,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0489585399627686,
      "step": 1016
    },
    {
      "epoch": 0.04847619047619048,
      "grad_norm": 0.05949234217405319,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0545129776000977,
      "step": 1018
    },
    {
      "epoch": 0.04857142857142857,
      "grad_norm": 0.06704841554164886,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0756356716156006,
      "step": 1020
    },
    {
      "epoch": 0.048666666666666664,
      "grad_norm": 0.0626104548573494,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0496630668640137,
      "step": 1022
    },
    {
      "epoch": 0.04876190476190476,
      "grad_norm": 0.06039304658770561,
      "learning_rate": 0.024000000208616257,
      "loss": 3.083125352859497,
      "step": 1024
    },
    {
      "epoch": 0.048857142857142856,
      "grad_norm": 0.06297505646944046,
      "learning_rate": 0.024000000208616257,
      "loss": 3.069502830505371,
      "step": 1026
    },
    {
      "epoch": 0.048952380952380956,
      "grad_norm": 0.06280398368835449,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0576858520507812,
      "step": 1028
    },
    {
      "epoch": 0.04904761904761905,
      "grad_norm": 0.0598304346203804,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0707099437713623,
      "step": 1030
    },
    {
      "epoch": 0.04914285714285714,
      "grad_norm": 0.062489185482263565,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0659570693969727,
      "step": 1032
    },
    {
      "epoch": 0.04923809523809524,
      "grad_norm": 0.06388653814792633,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0427517890930176,
      "step": 1034
    },
    {
      "epoch": 0.04933333333333333,
      "grad_norm": 0.06645842641592026,
      "learning_rate": 0.024000000208616257,
      "loss": 3.052427291870117,
      "step": 1036
    },
    {
      "epoch": 0.049428571428571426,
      "grad_norm": 0.063435398042202,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0692105293273926,
      "step": 1038
    },
    {
      "epoch": 0.049523809523809526,
      "grad_norm": 0.06134660542011261,
      "learning_rate": 0.024000000208616257,
      "loss": 3.051891803741455,
      "step": 1040
    },
    {
      "epoch": 0.04961904761904762,
      "grad_norm": 0.05831262841820717,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0275063514709473,
      "step": 1042
    },
    {
      "epoch": 0.04971428571428571,
      "grad_norm": 0.06195816770195961,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0686089992523193,
      "step": 1044
    },
    {
      "epoch": 0.04980952380952381,
      "grad_norm": 0.06554307043552399,
      "learning_rate": 0.024000000208616257,
      "loss": 3.055507183074951,
      "step": 1046
    },
    {
      "epoch": 0.0499047619047619,
      "grad_norm": 0.0715007558465004,
      "learning_rate": 0.024000000208616257,
      "loss": 3.056023597717285,
      "step": 1048
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.07247067987918854,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0667905807495117,
      "step": 1050
    },
    {
      "epoch": 0.050095238095238095,
      "grad_norm": 0.06911437958478928,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0486268997192383,
      "step": 1052
    },
    {
      "epoch": 0.05019047619047619,
      "grad_norm": 0.06312612444162369,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0822343826293945,
      "step": 1054
    },
    {
      "epoch": 0.05028571428571429,
      "grad_norm": 0.059785693883895874,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0627212524414062,
      "step": 1056
    },
    {
      "epoch": 0.05038095238095238,
      "grad_norm": 0.059214379638433456,
      "learning_rate": 0.024000000208616257,
      "loss": 3.054945945739746,
      "step": 1058
    },
    {
      "epoch": 0.05047619047619047,
      "grad_norm": 0.05899949371814728,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0392608642578125,
      "step": 1060
    },
    {
      "epoch": 0.05057142857142857,
      "grad_norm": 0.058471690863370895,
      "learning_rate": 0.024000000208616257,
      "loss": 3.077596426010132,
      "step": 1062
    },
    {
      "epoch": 0.050666666666666665,
      "grad_norm": 0.058646995574235916,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0268001556396484,
      "step": 1064
    },
    {
      "epoch": 0.050761904761904765,
      "grad_norm": 0.05497264117002487,
      "learning_rate": 0.024000000208616257,
      "loss": 3.051115036010742,
      "step": 1066
    },
    {
      "epoch": 0.05085714285714286,
      "grad_norm": 0.06088046357035637,
      "learning_rate": 0.024000000208616257,
      "loss": 3.052265167236328,
      "step": 1068
    },
    {
      "epoch": 0.05095238095238095,
      "grad_norm": 0.05846144258975983,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0579476356506348,
      "step": 1070
    },
    {
      "epoch": 0.05104761904761905,
      "grad_norm": 0.05864694342017174,
      "learning_rate": 0.024000000208616257,
      "loss": 3.052201271057129,
      "step": 1072
    },
    {
      "epoch": 0.05114285714285714,
      "grad_norm": 0.060412462800741196,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0255303382873535,
      "step": 1074
    },
    {
      "epoch": 0.051238095238095235,
      "grad_norm": 0.057002849876880646,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0424985885620117,
      "step": 1076
    },
    {
      "epoch": 0.051333333333333335,
      "grad_norm": 0.05671170353889465,
      "learning_rate": 0.024000000208616257,
      "loss": 3.055744171142578,
      "step": 1078
    },
    {
      "epoch": 0.05142857142857143,
      "grad_norm": 0.05752897262573242,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0241496562957764,
      "step": 1080
    },
    {
      "epoch": 0.05152380952380953,
      "grad_norm": 0.05675262585282326,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0075736045837402,
      "step": 1082
    },
    {
      "epoch": 0.05161904761904762,
      "grad_norm": 0.05479305982589722,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0436277389526367,
      "step": 1084
    },
    {
      "epoch": 0.05171428571428571,
      "grad_norm": 0.058180734515190125,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0406651496887207,
      "step": 1086
    },
    {
      "epoch": 0.05180952380952381,
      "grad_norm": 0.05768230929970741,
      "learning_rate": 0.024000000208616257,
      "loss": 3.01808500289917,
      "step": 1088
    },
    {
      "epoch": 0.051904761904761905,
      "grad_norm": 0.060971699655056,
      "learning_rate": 0.024000000208616257,
      "loss": 3.039900779724121,
      "step": 1090
    },
    {
      "epoch": 0.052,
      "grad_norm": 0.05676783621311188,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0445547103881836,
      "step": 1092
    },
    {
      "epoch": 0.0520952380952381,
      "grad_norm": 0.05435581132769585,
      "learning_rate": 0.024000000208616257,
      "loss": 3.064800262451172,
      "step": 1094
    },
    {
      "epoch": 0.05219047619047619,
      "grad_norm": 0.0610000379383564,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0320749282836914,
      "step": 1096
    },
    {
      "epoch": 0.05228571428571428,
      "grad_norm": 0.06003008782863617,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0314271450042725,
      "step": 1098
    },
    {
      "epoch": 0.05238095238095238,
      "grad_norm": 0.061458759009838104,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0218610763549805,
      "step": 1100
    },
    {
      "epoch": 0.052476190476190475,
      "grad_norm": 0.06403152644634247,
      "learning_rate": 0.024000000208616257,
      "loss": 3.040764808654785,
      "step": 1102
    },
    {
      "epoch": 0.052571428571428575,
      "grad_norm": 0.059456296265125275,
      "learning_rate": 0.024000000208616257,
      "loss": 3.046827793121338,
      "step": 1104
    },
    {
      "epoch": 0.05266666666666667,
      "grad_norm": 0.059432171285152435,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0120744705200195,
      "step": 1106
    },
    {
      "epoch": 0.05276190476190476,
      "grad_norm": 0.06151725351810455,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0427212715148926,
      "step": 1108
    },
    {
      "epoch": 0.05285714285714286,
      "grad_norm": 0.05983575060963631,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0434534549713135,
      "step": 1110
    },
    {
      "epoch": 0.05295238095238095,
      "grad_norm": 0.060025084763765335,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0613644123077393,
      "step": 1112
    },
    {
      "epoch": 0.053047619047619045,
      "grad_norm": 0.061329133808612823,
      "learning_rate": 0.024000000208616257,
      "loss": 3.032843589782715,
      "step": 1114
    },
    {
      "epoch": 0.053142857142857144,
      "grad_norm": 0.061610158532857895,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0331790447235107,
      "step": 1116
    },
    {
      "epoch": 0.05323809523809524,
      "grad_norm": 0.058027368038892746,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0368051528930664,
      "step": 1118
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 0.05735352635383606,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0195162296295166,
      "step": 1120
    },
    {
      "epoch": 0.05342857142857143,
      "grad_norm": 0.059881627559661865,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0228123664855957,
      "step": 1122
    },
    {
      "epoch": 0.05352380952380952,
      "grad_norm": 0.06019507721066475,
      "learning_rate": 0.024000000208616257,
      "loss": 3.031332492828369,
      "step": 1124
    },
    {
      "epoch": 0.05361904761904762,
      "grad_norm": 0.057742681354284286,
      "learning_rate": 0.024000000208616257,
      "loss": 3.040836811065674,
      "step": 1126
    },
    {
      "epoch": 0.053714285714285714,
      "grad_norm": 0.057205189019441605,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0521864891052246,
      "step": 1128
    },
    {
      "epoch": 0.05380952380952381,
      "grad_norm": 0.056748729199171066,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0366411209106445,
      "step": 1130
    },
    {
      "epoch": 0.05390476190476191,
      "grad_norm": 0.06324241310358047,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0562472343444824,
      "step": 1132
    },
    {
      "epoch": 0.054,
      "grad_norm": 0.05621308088302612,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0535342693328857,
      "step": 1134
    },
    {
      "epoch": 0.05409523809523809,
      "grad_norm": 0.058671917766332626,
      "learning_rate": 0.024000000208616257,
      "loss": 3.067357063293457,
      "step": 1136
    },
    {
      "epoch": 0.05419047619047619,
      "grad_norm": 0.06093320995569229,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0442891120910645,
      "step": 1138
    },
    {
      "epoch": 0.054285714285714284,
      "grad_norm": 0.05917782336473465,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0462894439697266,
      "step": 1140
    },
    {
      "epoch": 0.054380952380952384,
      "grad_norm": 0.057291436940431595,
      "learning_rate": 0.024000000208616257,
      "loss": 3.056645393371582,
      "step": 1142
    },
    {
      "epoch": 0.05447619047619048,
      "grad_norm": 0.05575151368975639,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0238351821899414,
      "step": 1144
    },
    {
      "epoch": 0.05457142857142857,
      "grad_norm": 0.05863843113183975,
      "learning_rate": 0.024000000208616257,
      "loss": 3.063243865966797,
      "step": 1146
    },
    {
      "epoch": 0.05466666666666667,
      "grad_norm": 0.05625324323773384,
      "learning_rate": 0.024000000208616257,
      "loss": 3.039976119995117,
      "step": 1148
    },
    {
      "epoch": 0.05476190476190476,
      "grad_norm": 0.05849955230951309,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0391838550567627,
      "step": 1150
    },
    {
      "epoch": 0.054857142857142854,
      "grad_norm": 0.05602460354566574,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0444366931915283,
      "step": 1152
    },
    {
      "epoch": 0.054952380952380954,
      "grad_norm": 0.05626349151134491,
      "learning_rate": 0.024000000208616257,
      "loss": 3.027592658996582,
      "step": 1154
    },
    {
      "epoch": 0.05504761904761905,
      "grad_norm": 0.05983627960085869,
      "learning_rate": 0.024000000208616257,
      "loss": 3.005208730697632,
      "step": 1156
    },
    {
      "epoch": 0.055142857142857146,
      "grad_norm": 0.05669187009334564,
      "learning_rate": 0.024000000208616257,
      "loss": 3.072868824005127,
      "step": 1158
    },
    {
      "epoch": 0.05523809523809524,
      "grad_norm": 0.05603785812854767,
      "learning_rate": 0.024000000208616257,
      "loss": 3.041327953338623,
      "step": 1160
    },
    {
      "epoch": 0.05533333333333333,
      "grad_norm": 0.05536894500255585,
      "learning_rate": 0.024000000208616257,
      "loss": 3.039623737335205,
      "step": 1162
    },
    {
      "epoch": 0.05542857142857143,
      "grad_norm": 0.0583699569106102,
      "learning_rate": 0.024000000208616257,
      "loss": 3.108242988586426,
      "step": 1164
    },
    {
      "epoch": 0.055523809523809524,
      "grad_norm": 0.06629029661417007,
      "learning_rate": 0.024000000208616257,
      "loss": 3.043562650680542,
      "step": 1166
    },
    {
      "epoch": 0.05561904761904762,
      "grad_norm": 0.060873132199048996,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0665910243988037,
      "step": 1168
    },
    {
      "epoch": 0.055714285714285716,
      "grad_norm": 0.05814237892627716,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0411415100097656,
      "step": 1170
    },
    {
      "epoch": 0.05580952380952381,
      "grad_norm": 0.0546601228415966,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0361056327819824,
      "step": 1172
    },
    {
      "epoch": 0.0559047619047619,
      "grad_norm": 0.05922131985425949,
      "learning_rate": 0.024000000208616257,
      "loss": 3.010694980621338,
      "step": 1174
    },
    {
      "epoch": 0.056,
      "grad_norm": 0.061644259840250015,
      "learning_rate": 0.024000000208616257,
      "loss": 3.049976110458374,
      "step": 1176
    },
    {
      "epoch": 0.056095238095238094,
      "grad_norm": 0.06270940601825714,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1042864322662354,
      "step": 1178
    },
    {
      "epoch": 0.05619047619047619,
      "grad_norm": 0.05776225030422211,
      "learning_rate": 0.024000000208616257,
      "loss": 3.020934581756592,
      "step": 1180
    },
    {
      "epoch": 0.056285714285714286,
      "grad_norm": 0.05527959018945694,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0579333305358887,
      "step": 1182
    },
    {
      "epoch": 0.05638095238095238,
      "grad_norm": 0.05365069955587387,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0560717582702637,
      "step": 1184
    },
    {
      "epoch": 0.05647619047619048,
      "grad_norm": 0.0560082271695137,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0488715171813965,
      "step": 1186
    },
    {
      "epoch": 0.05657142857142857,
      "grad_norm": 0.05341020226478577,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0562081336975098,
      "step": 1188
    },
    {
      "epoch": 0.056666666666666664,
      "grad_norm": 0.05400562658905983,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0702807903289795,
      "step": 1190
    },
    {
      "epoch": 0.05676190476190476,
      "grad_norm": 0.056847184896469116,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0575225353240967,
      "step": 1192
    },
    {
      "epoch": 0.056857142857142856,
      "grad_norm": 0.0556766539812088,
      "learning_rate": 0.024000000208616257,
      "loss": 3.033548355102539,
      "step": 1194
    },
    {
      "epoch": 0.056952380952380956,
      "grad_norm": 0.06070096790790558,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0435214042663574,
      "step": 1196
    },
    {
      "epoch": 0.05704761904761905,
      "grad_norm": 0.05682795122265816,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0444326400756836,
      "step": 1198
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 0.05378428101539612,
      "learning_rate": 0.024000000208616257,
      "loss": 3.036590576171875,
      "step": 1200
    },
    {
      "epoch": 0.05723809523809524,
      "grad_norm": 0.06143005192279816,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0738346576690674,
      "step": 1202
    },
    {
      "epoch": 0.05733333333333333,
      "grad_norm": 0.0571569949388504,
      "learning_rate": 0.024000000208616257,
      "loss": 3.077674388885498,
      "step": 1204
    },
    {
      "epoch": 0.057428571428571426,
      "grad_norm": 0.05762338265776634,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0628223419189453,
      "step": 1206
    },
    {
      "epoch": 0.057523809523809526,
      "grad_norm": 0.057911910116672516,
      "learning_rate": 0.024000000208616257,
      "loss": 3.006883382797241,
      "step": 1208
    },
    {
      "epoch": 0.05761904761904762,
      "grad_norm": 0.061829276382923126,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0619115829467773,
      "step": 1210
    },
    {
      "epoch": 0.05771428571428571,
      "grad_norm": 0.0570538230240345,
      "learning_rate": 0.024000000208616257,
      "loss": 3.1065924167633057,
      "step": 1212
    },
    {
      "epoch": 0.05780952380952381,
      "grad_norm": 0.056189004331827164,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0566294193267822,
      "step": 1214
    },
    {
      "epoch": 0.0579047619047619,
      "grad_norm": 0.05829361826181412,
      "learning_rate": 0.024000000208616257,
      "loss": 3.059316873550415,
      "step": 1216
    },
    {
      "epoch": 0.058,
      "grad_norm": 0.05528026074171066,
      "learning_rate": 0.024000000208616257,
      "loss": 3.049365997314453,
      "step": 1218
    },
    {
      "epoch": 0.058095238095238096,
      "grad_norm": 0.05655008554458618,
      "learning_rate": 0.024000000208616257,
      "loss": 3.044992446899414,
      "step": 1220
    },
    {
      "epoch": 0.05819047619047619,
      "grad_norm": 0.057734113186597824,
      "learning_rate": 0.024000000208616257,
      "loss": 3.045952320098877,
      "step": 1222
    },
    {
      "epoch": 0.05828571428571429,
      "grad_norm": 0.05418461188673973,
      "learning_rate": 0.024000000208616257,
      "loss": 3.085960865020752,
      "step": 1224
    },
    {
      "epoch": 0.05838095238095238,
      "grad_norm": 0.055153876543045044,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0350441932678223,
      "step": 1226
    },
    {
      "epoch": 0.05847619047619047,
      "grad_norm": 0.05870424583554268,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0186948776245117,
      "step": 1228
    },
    {
      "epoch": 0.05857142857142857,
      "grad_norm": 0.05565826594829559,
      "learning_rate": 0.024000000208616257,
      "loss": 3.021219253540039,
      "step": 1230
    },
    {
      "epoch": 0.058666666666666666,
      "grad_norm": 0.05637678503990173,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0101027488708496,
      "step": 1232
    },
    {
      "epoch": 0.058761904761904765,
      "grad_norm": 0.055582012981176376,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0474114418029785,
      "step": 1234
    },
    {
      "epoch": 0.05885714285714286,
      "grad_norm": 0.05842011794447899,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0463523864746094,
      "step": 1236
    },
    {
      "epoch": 0.05895238095238095,
      "grad_norm": 0.05393781140446663,
      "learning_rate": 0.024000000208616257,
      "loss": 3.082899332046509,
      "step": 1238
    },
    {
      "epoch": 0.05904761904761905,
      "grad_norm": 0.05697547271847725,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0784435272216797,
      "step": 1240
    },
    {
      "epoch": 0.05914285714285714,
      "grad_norm": 0.05603957548737526,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0417168140411377,
      "step": 1242
    },
    {
      "epoch": 0.059238095238095236,
      "grad_norm": 0.05376940593123436,
      "learning_rate": 0.024000000208616257,
      "loss": 3.080162525177002,
      "step": 1244
    },
    {
      "epoch": 0.059333333333333335,
      "grad_norm": 0.055727291852235794,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0575337409973145,
      "step": 1246
    },
    {
      "epoch": 0.05942857142857143,
      "grad_norm": 0.05776844918727875,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0942487716674805,
      "step": 1248
    },
    {
      "epoch": 0.05952380952380952,
      "grad_norm": 0.058101195842027664,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0732483863830566,
      "step": 1250
    },
    {
      "epoch": 0.05961904761904762,
      "grad_norm": 0.057925995439291,
      "learning_rate": 0.024000000208616257,
      "loss": 3.083416223526001,
      "step": 1252
    },
    {
      "epoch": 0.05971428571428571,
      "grad_norm": 0.05579056590795517,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0561470985412598,
      "step": 1254
    },
    {
      "epoch": 0.05980952380952381,
      "grad_norm": 0.05993054807186127,
      "learning_rate": 0.024000000208616257,
      "loss": 3.070157527923584,
      "step": 1256
    },
    {
      "epoch": 0.059904761904761905,
      "grad_norm": 0.05810578912496567,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0744335651397705,
      "step": 1258
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.06029128283262253,
      "learning_rate": 0.024000000208616257,
      "loss": 3.095670700073242,
      "step": 1260
    },
    {
      "epoch": 0.0600952380952381,
      "grad_norm": 0.059252843260765076,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0702567100524902,
      "step": 1262
    },
    {
      "epoch": 0.06019047619047619,
      "grad_norm": 0.05639823153614998,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0671772956848145,
      "step": 1264
    },
    {
      "epoch": 0.06028571428571428,
      "grad_norm": 0.05523160472512245,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0249438285827637,
      "step": 1266
    },
    {
      "epoch": 0.06038095238095238,
      "grad_norm": 0.057453662157058716,
      "learning_rate": 0.024000000208616257,
      "loss": 3.087273120880127,
      "step": 1268
    },
    {
      "epoch": 0.060476190476190475,
      "grad_norm": 0.05788185074925423,
      "learning_rate": 0.024000000208616257,
      "loss": 3.055483818054199,
      "step": 1270
    },
    {
      "epoch": 0.060571428571428575,
      "grad_norm": 0.057222433388233185,
      "learning_rate": 0.024000000208616257,
      "loss": 3.052868366241455,
      "step": 1272
    },
    {
      "epoch": 0.06066666666666667,
      "grad_norm": 0.05606599524617195,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0848355293273926,
      "step": 1274
    },
    {
      "epoch": 0.06076190476190476,
      "grad_norm": 0.05571572855114937,
      "learning_rate": 0.024000000208616257,
      "loss": 3.067436695098877,
      "step": 1276
    },
    {
      "epoch": 0.06085714285714286,
      "grad_norm": 0.053575705736875534,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0775704383850098,
      "step": 1278
    },
    {
      "epoch": 0.06095238095238095,
      "grad_norm": 0.054226264357566833,
      "learning_rate": 0.024000000208616257,
      "loss": 3.060917615890503,
      "step": 1280
    },
    {
      "epoch": 0.061047619047619045,
      "grad_norm": 0.05277332291007042,
      "learning_rate": 0.024000000208616257,
      "loss": 3.083040714263916,
      "step": 1282
    },
    {
      "epoch": 0.061142857142857145,
      "grad_norm": 0.05427541211247444,
      "learning_rate": 0.024000000208616257,
      "loss": 3.027400016784668,
      "step": 1284
    },
    {
      "epoch": 0.06123809523809524,
      "grad_norm": 0.05363941565155983,
      "learning_rate": 0.024000000208616257,
      "loss": 3.037872314453125,
      "step": 1286
    },
    {
      "epoch": 0.06133333333333333,
      "grad_norm": 0.05484069511294365,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0488343238830566,
      "step": 1288
    },
    {
      "epoch": 0.06142857142857143,
      "grad_norm": 0.054410722106695175,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0742735862731934,
      "step": 1290
    },
    {
      "epoch": 0.06152380952380952,
      "grad_norm": 0.05448170006275177,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0772361755371094,
      "step": 1292
    },
    {
      "epoch": 0.06161904761904762,
      "grad_norm": 0.053643129765987396,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0718836784362793,
      "step": 1294
    },
    {
      "epoch": 0.061714285714285715,
      "grad_norm": 0.05717478692531586,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0542359352111816,
      "step": 1296
    },
    {
      "epoch": 0.06180952380952381,
      "grad_norm": 0.057955410331487656,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0606088638305664,
      "step": 1298
    },
    {
      "epoch": 0.06190476190476191,
      "grad_norm": 0.05767637863755226,
      "learning_rate": 0.024000000208616257,
      "loss": 3.06565523147583,
      "step": 1300
    },
    {
      "epoch": 0.062,
      "grad_norm": 0.05788761377334595,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0516304969787598,
      "step": 1302
    },
    {
      "epoch": 0.06209523809523809,
      "grad_norm": 0.05905814468860626,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0417261123657227,
      "step": 1304
    },
    {
      "epoch": 0.06219047619047619,
      "grad_norm": 0.05953981727361679,
      "learning_rate": 0.024000000208616257,
      "loss": 3.077012062072754,
      "step": 1306
    },
    {
      "epoch": 0.062285714285714285,
      "grad_norm": 0.05429840832948685,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0720133781433105,
      "step": 1308
    },
    {
      "epoch": 0.062380952380952384,
      "grad_norm": 0.05659131333231926,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0504961013793945,
      "step": 1310
    },
    {
      "epoch": 0.06247619047619048,
      "grad_norm": 0.05538174510002136,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0356507301330566,
      "step": 1312
    },
    {
      "epoch": 0.06257142857142857,
      "grad_norm": 0.056818198412656784,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0559210777282715,
      "step": 1314
    },
    {
      "epoch": 0.06266666666666666,
      "grad_norm": 0.05633227154612541,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0519261360168457,
      "step": 1316
    },
    {
      "epoch": 0.06276190476190477,
      "grad_norm": 0.052252065390348434,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0226268768310547,
      "step": 1318
    },
    {
      "epoch": 0.06285714285714286,
      "grad_norm": 0.05385222285985947,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0531070232391357,
      "step": 1320
    },
    {
      "epoch": 0.06295238095238095,
      "grad_norm": 0.0530044361948967,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0255513191223145,
      "step": 1322
    },
    {
      "epoch": 0.06304761904761905,
      "grad_norm": 0.05505853518843651,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0357465744018555,
      "step": 1324
    },
    {
      "epoch": 0.06314285714285714,
      "grad_norm": 0.0579497404396534,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0440921783447266,
      "step": 1326
    },
    {
      "epoch": 0.06323809523809523,
      "grad_norm": 0.057244379073381424,
      "learning_rate": 0.024000000208616257,
      "loss": 3.054093360900879,
      "step": 1328
    },
    {
      "epoch": 0.06333333333333334,
      "grad_norm": 0.05481645464897156,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0809664726257324,
      "step": 1330
    },
    {
      "epoch": 0.06342857142857143,
      "grad_norm": 0.059082359075546265,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0450377464294434,
      "step": 1332
    },
    {
      "epoch": 0.06352380952380952,
      "grad_norm": 0.054620563983917236,
      "learning_rate": 0.024000000208616257,
      "loss": 3.001835346221924,
      "step": 1334
    },
    {
      "epoch": 0.06361904761904762,
      "grad_norm": 0.0551108755171299,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0192904472351074,
      "step": 1336
    },
    {
      "epoch": 0.06371428571428571,
      "grad_norm": 0.05495007708668709,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9814538955688477,
      "step": 1338
    },
    {
      "epoch": 0.06380952380952382,
      "grad_norm": 0.060208629816770554,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0237491130828857,
      "step": 1340
    },
    {
      "epoch": 0.06390476190476191,
      "grad_norm": 0.05446393042802811,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0459742546081543,
      "step": 1342
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.051229387521743774,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0546300411224365,
      "step": 1344
    },
    {
      "epoch": 0.0640952380952381,
      "grad_norm": 0.053017016500234604,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0226893424987793,
      "step": 1346
    },
    {
      "epoch": 0.06419047619047619,
      "grad_norm": 0.05327665060758591,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9940989017486572,
      "step": 1348
    },
    {
      "epoch": 0.06428571428571428,
      "grad_norm": 0.05563163384795189,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0449414253234863,
      "step": 1350
    },
    {
      "epoch": 0.06438095238095239,
      "grad_norm": 0.055892862379550934,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0088772773742676,
      "step": 1352
    },
    {
      "epoch": 0.06447619047619048,
      "grad_norm": 0.05583472549915314,
      "learning_rate": 0.024000000208616257,
      "loss": 3.021486759185791,
      "step": 1354
    },
    {
      "epoch": 0.06457142857142857,
      "grad_norm": 0.056363992393016815,
      "learning_rate": 0.024000000208616257,
      "loss": 3.017400026321411,
      "step": 1356
    },
    {
      "epoch": 0.06466666666666666,
      "grad_norm": 0.05598435178399086,
      "learning_rate": 0.024000000208616257,
      "loss": 2.989924669265747,
      "step": 1358
    },
    {
      "epoch": 0.06476190476190476,
      "grad_norm": 0.05749648064374924,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0302414894104004,
      "step": 1360
    },
    {
      "epoch": 0.06485714285714286,
      "grad_norm": 0.05641870200634003,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0033111572265625,
      "step": 1362
    },
    {
      "epoch": 0.06495238095238096,
      "grad_norm": 0.0557023286819458,
      "learning_rate": 0.024000000208616257,
      "loss": 2.989525318145752,
      "step": 1364
    },
    {
      "epoch": 0.06504761904761905,
      "grad_norm": 0.054063040763139725,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9971821308135986,
      "step": 1366
    },
    {
      "epoch": 0.06514285714285714,
      "grad_norm": 0.050344355404376984,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0008978843688965,
      "step": 1368
    },
    {
      "epoch": 0.06523809523809523,
      "grad_norm": 0.05040469020605087,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0521326065063477,
      "step": 1370
    },
    {
      "epoch": 0.06533333333333333,
      "grad_norm": 0.056519217789173126,
      "learning_rate": 0.024000000208616257,
      "loss": 3.010171890258789,
      "step": 1372
    },
    {
      "epoch": 0.06542857142857143,
      "grad_norm": 0.05178011208772659,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9858317375183105,
      "step": 1374
    },
    {
      "epoch": 0.06552380952380953,
      "grad_norm": 0.05159865692257881,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0254664421081543,
      "step": 1376
    },
    {
      "epoch": 0.06561904761904762,
      "grad_norm": 0.05314699932932854,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0217387676239014,
      "step": 1378
    },
    {
      "epoch": 0.06571428571428571,
      "grad_norm": 0.051117151975631714,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9899749755859375,
      "step": 1380
    },
    {
      "epoch": 0.0658095238095238,
      "grad_norm": 0.05329446122050285,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9847571849823,
      "step": 1382
    },
    {
      "epoch": 0.06590476190476191,
      "grad_norm": 0.05318654328584671,
      "learning_rate": 0.024000000208616257,
      "loss": 3.02400541305542,
      "step": 1384
    },
    {
      "epoch": 0.066,
      "grad_norm": 0.05273803323507309,
      "learning_rate": 0.024000000208616257,
      "loss": 3.001965284347534,
      "step": 1386
    },
    {
      "epoch": 0.0660952380952381,
      "grad_norm": 0.059401653707027435,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0282540321350098,
      "step": 1388
    },
    {
      "epoch": 0.06619047619047619,
      "grad_norm": 0.05625959858298302,
      "learning_rate": 0.024000000208616257,
      "loss": 2.99084734916687,
      "step": 1390
    },
    {
      "epoch": 0.06628571428571428,
      "grad_norm": 0.055680051445961,
      "learning_rate": 0.024000000208616257,
      "loss": 3.02760648727417,
      "step": 1392
    },
    {
      "epoch": 0.06638095238095239,
      "grad_norm": 0.055258963257074356,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9963059425354004,
      "step": 1394
    },
    {
      "epoch": 0.06647619047619048,
      "grad_norm": 0.055165063589811325,
      "learning_rate": 0.024000000208616257,
      "loss": 2.993396282196045,
      "step": 1396
    },
    {
      "epoch": 0.06657142857142857,
      "grad_norm": 0.055666614323854446,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9779701232910156,
      "step": 1398
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 0.053545158356428146,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9770541191101074,
      "step": 1400
    },
    {
      "epoch": 0.06676190476190476,
      "grad_norm": 0.05078350007534027,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0418033599853516,
      "step": 1402
    },
    {
      "epoch": 0.06685714285714285,
      "grad_norm": 0.053147364407777786,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9669225215911865,
      "step": 1404
    },
    {
      "epoch": 0.06695238095238096,
      "grad_norm": 0.05339110642671585,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9853100776672363,
      "step": 1406
    },
    {
      "epoch": 0.06704761904761905,
      "grad_norm": 0.05479119345545769,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9432263374328613,
      "step": 1408
    },
    {
      "epoch": 0.06714285714285714,
      "grad_norm": 0.05539429932832718,
      "learning_rate": 0.024000000208616257,
      "loss": 2.995213508605957,
      "step": 1410
    },
    {
      "epoch": 0.06723809523809524,
      "grad_norm": 0.054930973798036575,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9972450733184814,
      "step": 1412
    },
    {
      "epoch": 0.06733333333333333,
      "grad_norm": 0.05108562484383583,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9776248931884766,
      "step": 1414
    },
    {
      "epoch": 0.06742857142857143,
      "grad_norm": 0.05199114978313446,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9937856197357178,
      "step": 1416
    },
    {
      "epoch": 0.06752380952380953,
      "grad_norm": 0.05385183170437813,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9960269927978516,
      "step": 1418
    },
    {
      "epoch": 0.06761904761904762,
      "grad_norm": 0.05764460563659668,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9696526527404785,
      "step": 1420
    },
    {
      "epoch": 0.06771428571428571,
      "grad_norm": 0.05284947156906128,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9612278938293457,
      "step": 1422
    },
    {
      "epoch": 0.0678095238095238,
      "grad_norm": 0.05444653704762459,
      "learning_rate": 0.024000000208616257,
      "loss": 2.998746871948242,
      "step": 1424
    },
    {
      "epoch": 0.0679047619047619,
      "grad_norm": 0.054537467658519745,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9729442596435547,
      "step": 1426
    },
    {
      "epoch": 0.068,
      "grad_norm": 0.05496001988649368,
      "learning_rate": 0.024000000208616257,
      "loss": 3.013942241668701,
      "step": 1428
    },
    {
      "epoch": 0.0680952380952381,
      "grad_norm": 0.05087234824895859,
      "learning_rate": 0.024000000208616257,
      "loss": 2.961179256439209,
      "step": 1430
    },
    {
      "epoch": 0.06819047619047619,
      "grad_norm": 0.05314084514975548,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9584856033325195,
      "step": 1432
    },
    {
      "epoch": 0.06828571428571428,
      "grad_norm": 0.05719631910324097,
      "learning_rate": 0.024000000208616257,
      "loss": 2.956432342529297,
      "step": 1434
    },
    {
      "epoch": 0.06838095238095238,
      "grad_norm": 0.05563769489526749,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0060951709747314,
      "step": 1436
    },
    {
      "epoch": 0.06847619047619048,
      "grad_norm": 0.053091928362846375,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9785847663879395,
      "step": 1438
    },
    {
      "epoch": 0.06857142857142857,
      "grad_norm": 0.051365599036216736,
      "learning_rate": 0.024000000208616257,
      "loss": 2.955984115600586,
      "step": 1440
    },
    {
      "epoch": 0.06866666666666667,
      "grad_norm": 0.051559120416641235,
      "learning_rate": 0.024000000208616257,
      "loss": 2.933061122894287,
      "step": 1442
    },
    {
      "epoch": 0.06876190476190476,
      "grad_norm": 0.05057550594210625,
      "learning_rate": 0.024000000208616257,
      "loss": 2.991905689239502,
      "step": 1444
    },
    {
      "epoch": 0.06885714285714285,
      "grad_norm": 0.05389087647199631,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9579153060913086,
      "step": 1446
    },
    {
      "epoch": 0.06895238095238095,
      "grad_norm": 0.05442383885383606,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9600930213928223,
      "step": 1448
    },
    {
      "epoch": 0.06904761904761905,
      "grad_norm": 0.05193992704153061,
      "learning_rate": 0.024000000208616257,
      "loss": 2.957550525665283,
      "step": 1450
    },
    {
      "epoch": 0.06914285714285714,
      "grad_norm": 0.05397174879908562,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9609909057617188,
      "step": 1452
    },
    {
      "epoch": 0.06923809523809524,
      "grad_norm": 0.05526004359126091,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9491891860961914,
      "step": 1454
    },
    {
      "epoch": 0.06933333333333333,
      "grad_norm": 0.052920784801244736,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9612784385681152,
      "step": 1456
    },
    {
      "epoch": 0.06942857142857142,
      "grad_norm": 0.05059688910841942,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9757425785064697,
      "step": 1458
    },
    {
      "epoch": 0.06952380952380953,
      "grad_norm": 0.0504024475812912,
      "learning_rate": 0.024000000208616257,
      "loss": 2.950127363204956,
      "step": 1460
    },
    {
      "epoch": 0.06961904761904762,
      "grad_norm": 0.050467055290937424,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9704010486602783,
      "step": 1462
    },
    {
      "epoch": 0.06971428571428571,
      "grad_norm": 0.0491148866713047,
      "learning_rate": 0.024000000208616257,
      "loss": 2.935638904571533,
      "step": 1464
    },
    {
      "epoch": 0.06980952380952381,
      "grad_norm": 0.05100981518626213,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9824423789978027,
      "step": 1466
    },
    {
      "epoch": 0.0699047619047619,
      "grad_norm": 0.051131974905729294,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9281482696533203,
      "step": 1468
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.05205634981393814,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9510130882263184,
      "step": 1470
    },
    {
      "epoch": 0.0700952380952381,
      "grad_norm": 0.05206327885389328,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9778635501861572,
      "step": 1472
    },
    {
      "epoch": 0.07019047619047619,
      "grad_norm": 0.049035921692848206,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9861538410186768,
      "step": 1474
    },
    {
      "epoch": 0.07028571428571428,
      "grad_norm": 0.04922155663371086,
      "learning_rate": 0.024000000208616257,
      "loss": 2.930302619934082,
      "step": 1476
    },
    {
      "epoch": 0.07038095238095238,
      "grad_norm": 0.05012796074151993,
      "learning_rate": 0.024000000208616257,
      "loss": 3.01483154296875,
      "step": 1478
    },
    {
      "epoch": 0.07047619047619047,
      "grad_norm": 0.05105793476104736,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9851787090301514,
      "step": 1480
    },
    {
      "epoch": 0.07057142857142858,
      "grad_norm": 0.05164980888366699,
      "learning_rate": 0.024000000208616257,
      "loss": 2.968639850616455,
      "step": 1482
    },
    {
      "epoch": 0.07066666666666667,
      "grad_norm": 0.05381036549806595,
      "learning_rate": 0.024000000208616257,
      "loss": 2.952967882156372,
      "step": 1484
    },
    {
      "epoch": 0.07076190476190476,
      "grad_norm": 0.05104340612888336,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9537272453308105,
      "step": 1486
    },
    {
      "epoch": 0.07085714285714285,
      "grad_norm": 0.05003172531723976,
      "learning_rate": 0.024000000208616257,
      "loss": 2.95678448677063,
      "step": 1488
    },
    {
      "epoch": 0.07095238095238095,
      "grad_norm": 0.053165435791015625,
      "learning_rate": 0.024000000208616257,
      "loss": 2.939756393432617,
      "step": 1490
    },
    {
      "epoch": 0.07104761904761905,
      "grad_norm": 0.05094069242477417,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9304466247558594,
      "step": 1492
    },
    {
      "epoch": 0.07114285714285715,
      "grad_norm": 0.05336402729153633,
      "learning_rate": 0.024000000208616257,
      "loss": 2.972684383392334,
      "step": 1494
    },
    {
      "epoch": 0.07123809523809524,
      "grad_norm": 0.05404333770275116,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9394259452819824,
      "step": 1496
    },
    {
      "epoch": 0.07133333333333333,
      "grad_norm": 0.05074213445186615,
      "learning_rate": 0.024000000208616257,
      "loss": 2.937626361846924,
      "step": 1498
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.05048748105764389,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9671759605407715,
      "step": 1500
    },
    {
      "epoch": 0.07152380952380952,
      "grad_norm": 0.05700121819972992,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9593100547790527,
      "step": 1502
    },
    {
      "epoch": 0.07161904761904762,
      "grad_norm": 0.05133889988064766,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9719390869140625,
      "step": 1504
    },
    {
      "epoch": 0.07171428571428572,
      "grad_norm": 0.04913727194070816,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9642999172210693,
      "step": 1506
    },
    {
      "epoch": 0.07180952380952381,
      "grad_norm": 0.05593148246407509,
      "learning_rate": 0.024000000208616257,
      "loss": 2.953390121459961,
      "step": 1508
    },
    {
      "epoch": 0.0719047619047619,
      "grad_norm": 0.054479822516441345,
      "learning_rate": 0.024000000208616257,
      "loss": 2.947855234146118,
      "step": 1510
    },
    {
      "epoch": 0.072,
      "grad_norm": 0.05125455930829048,
      "learning_rate": 0.024000000208616257,
      "loss": 2.955707311630249,
      "step": 1512
    },
    {
      "epoch": 0.0720952380952381,
      "grad_norm": 0.05141017958521843,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9809012413024902,
      "step": 1514
    },
    {
      "epoch": 0.0721904761904762,
      "grad_norm": 0.05110297352075577,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9538373947143555,
      "step": 1516
    },
    {
      "epoch": 0.07228571428571429,
      "grad_norm": 0.0498446561396122,
      "learning_rate": 0.024000000208616257,
      "loss": 2.986443519592285,
      "step": 1518
    },
    {
      "epoch": 0.07238095238095238,
      "grad_norm": 0.052777163684368134,
      "learning_rate": 0.024000000208616257,
      "loss": 2.954832077026367,
      "step": 1520
    },
    {
      "epoch": 0.07247619047619047,
      "grad_norm": 0.0540725402534008,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9536774158477783,
      "step": 1522
    },
    {
      "epoch": 0.07257142857142856,
      "grad_norm": 0.053248222917318344,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9774022102355957,
      "step": 1524
    },
    {
      "epoch": 0.07266666666666667,
      "grad_norm": 0.051604487001895905,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9838297367095947,
      "step": 1526
    },
    {
      "epoch": 0.07276190476190476,
      "grad_norm": 0.053434163331985474,
      "learning_rate": 0.024000000208616257,
      "loss": 2.934507369995117,
      "step": 1528
    },
    {
      "epoch": 0.07285714285714286,
      "grad_norm": 0.049254160374403,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9355716705322266,
      "step": 1530
    },
    {
      "epoch": 0.07295238095238095,
      "grad_norm": 0.04825703799724579,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9596667289733887,
      "step": 1532
    },
    {
      "epoch": 0.07304761904761904,
      "grad_norm": 0.051745690405368805,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9689760208129883,
      "step": 1534
    },
    {
      "epoch": 0.07314285714285715,
      "grad_norm": 0.055744338780641556,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9682819843292236,
      "step": 1536
    },
    {
      "epoch": 0.07323809523809524,
      "grad_norm": 0.04985868185758591,
      "learning_rate": 0.024000000208616257,
      "loss": 2.962550640106201,
      "step": 1538
    },
    {
      "epoch": 0.07333333333333333,
      "grad_norm": 0.050407350063323975,
      "learning_rate": 0.024000000208616257,
      "loss": 2.962275981903076,
      "step": 1540
    },
    {
      "epoch": 0.07342857142857143,
      "grad_norm": 0.05071704089641571,
      "learning_rate": 0.024000000208616257,
      "loss": 2.960676670074463,
      "step": 1542
    },
    {
      "epoch": 0.07352380952380952,
      "grad_norm": 0.05203435942530632,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9428985118865967,
      "step": 1544
    },
    {
      "epoch": 0.07361904761904763,
      "grad_norm": 0.05124904587864876,
      "learning_rate": 0.024000000208616257,
      "loss": 2.954646110534668,
      "step": 1546
    },
    {
      "epoch": 0.07371428571428572,
      "grad_norm": 0.0522538460791111,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9812703132629395,
      "step": 1548
    },
    {
      "epoch": 0.07380952380952381,
      "grad_norm": 0.051747582852840424,
      "learning_rate": 0.024000000208616257,
      "loss": 3.0026121139526367,
      "step": 1550
    },
    {
      "epoch": 0.0739047619047619,
      "grad_norm": 0.05250281095504761,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9918432235717773,
      "step": 1552
    },
    {
      "epoch": 0.074,
      "grad_norm": 0.05064147338271141,
      "learning_rate": 0.024000000208616257,
      "loss": 2.943103075027466,
      "step": 1554
    },
    {
      "epoch": 0.07409523809523809,
      "grad_norm": 0.050017327070236206,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9461660385131836,
      "step": 1556
    },
    {
      "epoch": 0.0741904761904762,
      "grad_norm": 0.0501667857170105,
      "learning_rate": 0.024000000208616257,
      "loss": 2.940037727355957,
      "step": 1558
    },
    {
      "epoch": 0.07428571428571429,
      "grad_norm": 0.05168139189481735,
      "learning_rate": 0.024000000208616257,
      "loss": 2.998946189880371,
      "step": 1560
    },
    {
      "epoch": 0.07438095238095238,
      "grad_norm": 0.05031423270702362,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9820432662963867,
      "step": 1562
    },
    {
      "epoch": 0.07447619047619047,
      "grad_norm": 0.052343208342790604,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9335556030273438,
      "step": 1564
    },
    {
      "epoch": 0.07457142857142857,
      "grad_norm": 0.051272597163915634,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9939446449279785,
      "step": 1566
    },
    {
      "epoch": 0.07466666666666667,
      "grad_norm": 0.05321313440799713,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9433512687683105,
      "step": 1568
    },
    {
      "epoch": 0.07476190476190477,
      "grad_norm": 0.05056106299161911,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9906277656555176,
      "step": 1570
    },
    {
      "epoch": 0.07485714285714286,
      "grad_norm": 0.050753768533468246,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9522647857666016,
      "step": 1572
    },
    {
      "epoch": 0.07495238095238095,
      "grad_norm": 0.05238558351993561,
      "learning_rate": 0.024000000208616257,
      "loss": 2.999666213989258,
      "step": 1574
    },
    {
      "epoch": 0.07504761904761904,
      "grad_norm": 0.051249317824840546,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9436593055725098,
      "step": 1576
    },
    {
      "epoch": 0.07514285714285714,
      "grad_norm": 0.05173823982477188,
      "learning_rate": 0.024000000208616257,
      "loss": 2.944077253341675,
      "step": 1578
    },
    {
      "epoch": 0.07523809523809524,
      "grad_norm": 0.05483006313443184,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9531617164611816,
      "step": 1580
    },
    {
      "epoch": 0.07533333333333334,
      "grad_norm": 0.05134297534823418,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9907755851745605,
      "step": 1582
    },
    {
      "epoch": 0.07542857142857143,
      "grad_norm": 0.05116408318281174,
      "learning_rate": 0.024000000208616257,
      "loss": 2.972456932067871,
      "step": 1584
    },
    {
      "epoch": 0.07552380952380952,
      "grad_norm": 0.048827990889549255,
      "learning_rate": 0.024000000208616257,
      "loss": 2.974180221557617,
      "step": 1586
    },
    {
      "epoch": 0.07561904761904761,
      "grad_norm": 0.04789367690682411,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9835150241851807,
      "step": 1588
    },
    {
      "epoch": 0.07571428571428572,
      "grad_norm": 0.048732783645391464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9673824310302734,
      "step": 1590
    },
    {
      "epoch": 0.07580952380952381,
      "grad_norm": 0.0490325428545475,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9274425506591797,
      "step": 1592
    },
    {
      "epoch": 0.0759047619047619,
      "grad_norm": 0.05035490170121193,
      "learning_rate": 0.024000000208616257,
      "loss": 2.937790870666504,
      "step": 1594
    },
    {
      "epoch": 0.076,
      "grad_norm": 0.05031260848045349,
      "learning_rate": 0.024000000208616257,
      "loss": 2.949305295944214,
      "step": 1596
    },
    {
      "epoch": 0.07609523809523809,
      "grad_norm": 0.04958663508296013,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9433674812316895,
      "step": 1598
    },
    {
      "epoch": 0.0761904761904762,
      "grad_norm": 0.04890432581305504,
      "learning_rate": 0.024000000208616257,
      "loss": 2.948641777038574,
      "step": 1600
    },
    {
      "epoch": 0.07628571428571429,
      "grad_norm": 0.04723256826400757,
      "learning_rate": 0.024000000208616257,
      "loss": 2.945173501968384,
      "step": 1602
    },
    {
      "epoch": 0.07638095238095238,
      "grad_norm": 0.048460956662893295,
      "learning_rate": 0.024000000208616257,
      "loss": 2.957202911376953,
      "step": 1604
    },
    {
      "epoch": 0.07647619047619048,
      "grad_norm": 0.046563368290662766,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9298903942108154,
      "step": 1606
    },
    {
      "epoch": 0.07657142857142857,
      "grad_norm": 0.04844145104289055,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9221415519714355,
      "step": 1608
    },
    {
      "epoch": 0.07666666666666666,
      "grad_norm": 0.04702707380056381,
      "learning_rate": 0.024000000208616257,
      "loss": 2.956395149230957,
      "step": 1610
    },
    {
      "epoch": 0.07676190476190477,
      "grad_norm": 0.05915679782629013,
      "learning_rate": 0.024000000208616257,
      "loss": 2.980738639831543,
      "step": 1612
    },
    {
      "epoch": 0.07685714285714286,
      "grad_norm": 0.04919930174946785,
      "learning_rate": 0.024000000208616257,
      "loss": 2.985334634780884,
      "step": 1614
    },
    {
      "epoch": 0.07695238095238095,
      "grad_norm": 0.047026414424180984,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9819750785827637,
      "step": 1616
    },
    {
      "epoch": 0.07704761904761905,
      "grad_norm": 0.04929918423295021,
      "learning_rate": 0.024000000208616257,
      "loss": 2.999006748199463,
      "step": 1618
    },
    {
      "epoch": 0.07714285714285714,
      "grad_norm": 0.05256955698132515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9548728466033936,
      "step": 1620
    },
    {
      "epoch": 0.07723809523809524,
      "grad_norm": 0.05229438468813896,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9768104553222656,
      "step": 1622
    },
    {
      "epoch": 0.07733333333333334,
      "grad_norm": 0.051181722432374954,
      "learning_rate": 0.024000000208616257,
      "loss": 2.935715913772583,
      "step": 1624
    },
    {
      "epoch": 0.07742857142857143,
      "grad_norm": 0.05110138654708862,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9784393310546875,
      "step": 1626
    },
    {
      "epoch": 0.07752380952380952,
      "grad_norm": 0.05045212805271149,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9721415042877197,
      "step": 1628
    },
    {
      "epoch": 0.07761904761904762,
      "grad_norm": 0.05290203168988228,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9563779830932617,
      "step": 1630
    },
    {
      "epoch": 0.07771428571428571,
      "grad_norm": 0.05224497616291046,
      "learning_rate": 0.024000000208616257,
      "loss": 2.922201633453369,
      "step": 1632
    },
    {
      "epoch": 0.07780952380952381,
      "grad_norm": 0.05020322650671005,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9937567710876465,
      "step": 1634
    },
    {
      "epoch": 0.07790476190476191,
      "grad_norm": 0.05206846073269844,
      "learning_rate": 0.024000000208616257,
      "loss": 2.909306049346924,
      "step": 1636
    },
    {
      "epoch": 0.078,
      "grad_norm": 0.05338073521852493,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9420433044433594,
      "step": 1638
    },
    {
      "epoch": 0.07809523809523809,
      "grad_norm": 0.053326550871133804,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9714150428771973,
      "step": 1640
    },
    {
      "epoch": 0.07819047619047619,
      "grad_norm": 0.051709383726119995,
      "learning_rate": 0.024000000208616257,
      "loss": 2.926772117614746,
      "step": 1642
    },
    {
      "epoch": 0.07828571428571429,
      "grad_norm": 0.050150658935308456,
      "learning_rate": 0.024000000208616257,
      "loss": 2.928222417831421,
      "step": 1644
    },
    {
      "epoch": 0.07838095238095238,
      "grad_norm": 0.04807840287685394,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9870381355285645,
      "step": 1646
    },
    {
      "epoch": 0.07847619047619048,
      "grad_norm": 0.05002305284142494,
      "learning_rate": 0.024000000208616257,
      "loss": 2.914888381958008,
      "step": 1648
    },
    {
      "epoch": 0.07857142857142857,
      "grad_norm": 0.04878280311822891,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9488868713378906,
      "step": 1650
    },
    {
      "epoch": 0.07866666666666666,
      "grad_norm": 0.050738319754600525,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9476637840270996,
      "step": 1652
    },
    {
      "epoch": 0.07876190476190476,
      "grad_norm": 0.05335826054215431,
      "learning_rate": 0.024000000208616257,
      "loss": 2.95307993888855,
      "step": 1654
    },
    {
      "epoch": 0.07885714285714286,
      "grad_norm": 0.05299368500709534,
      "learning_rate": 0.024000000208616257,
      "loss": 2.946465015411377,
      "step": 1656
    },
    {
      "epoch": 0.07895238095238095,
      "grad_norm": 0.05228763446211815,
      "learning_rate": 0.024000000208616257,
      "loss": 2.938046455383301,
      "step": 1658
    },
    {
      "epoch": 0.07904761904761905,
      "grad_norm": 0.04993869364261627,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9637610912323,
      "step": 1660
    },
    {
      "epoch": 0.07914285714285714,
      "grad_norm": 0.05237402394413948,
      "learning_rate": 0.024000000208616257,
      "loss": 2.925386905670166,
      "step": 1662
    },
    {
      "epoch": 0.07923809523809523,
      "grad_norm": 0.05128273740410805,
      "learning_rate": 0.024000000208616257,
      "loss": 2.918161153793335,
      "step": 1664
    },
    {
      "epoch": 0.07933333333333334,
      "grad_norm": 0.049397796392440796,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9336977005004883,
      "step": 1666
    },
    {
      "epoch": 0.07942857142857143,
      "grad_norm": 0.04721633717417717,
      "learning_rate": 0.024000000208616257,
      "loss": 2.915818929672241,
      "step": 1668
    },
    {
      "epoch": 0.07952380952380952,
      "grad_norm": 0.046410493552684784,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9523985385894775,
      "step": 1670
    },
    {
      "epoch": 0.07961904761904762,
      "grad_norm": 0.047236282378435135,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9539542198181152,
      "step": 1672
    },
    {
      "epoch": 0.07971428571428571,
      "grad_norm": 0.048206545412540436,
      "learning_rate": 0.024000000208616257,
      "loss": 2.924769878387451,
      "step": 1674
    },
    {
      "epoch": 0.07980952380952382,
      "grad_norm": 0.04895470663905144,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9760706424713135,
      "step": 1676
    },
    {
      "epoch": 0.07990476190476191,
      "grad_norm": 0.0469241626560688,
      "learning_rate": 0.024000000208616257,
      "loss": 2.944624423980713,
      "step": 1678
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.05069416016340256,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9422690868377686,
      "step": 1680
    },
    {
      "epoch": 0.0800952380952381,
      "grad_norm": 0.047909315675497055,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9560680389404297,
      "step": 1682
    },
    {
      "epoch": 0.08019047619047619,
      "grad_norm": 0.049206990748643875,
      "learning_rate": 0.024000000208616257,
      "loss": 2.926823854446411,
      "step": 1684
    },
    {
      "epoch": 0.08028571428571428,
      "grad_norm": 0.049896325916051865,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9487195014953613,
      "step": 1686
    },
    {
      "epoch": 0.08038095238095239,
      "grad_norm": 0.04920772835612297,
      "learning_rate": 0.024000000208616257,
      "loss": 2.922633409500122,
      "step": 1688
    },
    {
      "epoch": 0.08047619047619048,
      "grad_norm": 0.047694407403469086,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9417123794555664,
      "step": 1690
    },
    {
      "epoch": 0.08057142857142857,
      "grad_norm": 0.046708762645721436,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9191548824310303,
      "step": 1692
    },
    {
      "epoch": 0.08066666666666666,
      "grad_norm": 0.0494520366191864,
      "learning_rate": 0.024000000208616257,
      "loss": 2.943769931793213,
      "step": 1694
    },
    {
      "epoch": 0.08076190476190476,
      "grad_norm": 0.0505329854786396,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9508543014526367,
      "step": 1696
    },
    {
      "epoch": 0.08085714285714286,
      "grad_norm": 0.05222766473889351,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9495925903320312,
      "step": 1698
    },
    {
      "epoch": 0.08095238095238096,
      "grad_norm": 0.05532173439860344,
      "learning_rate": 0.024000000208616257,
      "loss": 2.955954074859619,
      "step": 1700
    },
    {
      "epoch": 0.08104761904761905,
      "grad_norm": 0.05214424431324005,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9537296295166016,
      "step": 1702
    },
    {
      "epoch": 0.08114285714285714,
      "grad_norm": 0.05549017712473869,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9440126419067383,
      "step": 1704
    },
    {
      "epoch": 0.08123809523809523,
      "grad_norm": 0.048897478729486465,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9135632514953613,
      "step": 1706
    },
    {
      "epoch": 0.08133333333333333,
      "grad_norm": 0.05174533277750015,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8939993381500244,
      "step": 1708
    },
    {
      "epoch": 0.08142857142857143,
      "grad_norm": 0.049746595323085785,
      "learning_rate": 0.024000000208616257,
      "loss": 2.937708854675293,
      "step": 1710
    },
    {
      "epoch": 0.08152380952380953,
      "grad_norm": 0.04751712828874588,
      "learning_rate": 0.024000000208616257,
      "loss": 2.936490058898926,
      "step": 1712
    },
    {
      "epoch": 0.08161904761904762,
      "grad_norm": 0.047995757311582565,
      "learning_rate": 0.024000000208616257,
      "loss": 2.917097568511963,
      "step": 1714
    },
    {
      "epoch": 0.08171428571428571,
      "grad_norm": 0.04844076558947563,
      "learning_rate": 0.024000000208616257,
      "loss": 2.896604537963867,
      "step": 1716
    },
    {
      "epoch": 0.0818095238095238,
      "grad_norm": 0.0512847974896431,
      "learning_rate": 0.024000000208616257,
      "loss": 2.912191867828369,
      "step": 1718
    },
    {
      "epoch": 0.08190476190476191,
      "grad_norm": 0.050481829792261124,
      "learning_rate": 0.024000000208616257,
      "loss": 2.899132251739502,
      "step": 1720
    },
    {
      "epoch": 0.082,
      "grad_norm": 0.0465298555791378,
      "learning_rate": 0.024000000208616257,
      "loss": 2.910287857055664,
      "step": 1722
    },
    {
      "epoch": 0.0820952380952381,
      "grad_norm": 0.04769933223724365,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8746402263641357,
      "step": 1724
    },
    {
      "epoch": 0.08219047619047619,
      "grad_norm": 0.050012752413749695,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8983213901519775,
      "step": 1726
    },
    {
      "epoch": 0.08228571428571428,
      "grad_norm": 0.05396344140172005,
      "learning_rate": 0.024000000208616257,
      "loss": 2.904280185699463,
      "step": 1728
    },
    {
      "epoch": 0.08238095238095237,
      "grad_norm": 0.053190890699625015,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8818109035491943,
      "step": 1730
    },
    {
      "epoch": 0.08247619047619048,
      "grad_norm": 0.048120662569999695,
      "learning_rate": 0.024000000208616257,
      "loss": 2.924501657485962,
      "step": 1732
    },
    {
      "epoch": 0.08257142857142857,
      "grad_norm": 0.04883351922035217,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9433979988098145,
      "step": 1734
    },
    {
      "epoch": 0.08266666666666667,
      "grad_norm": 0.052017178386449814,
      "learning_rate": 0.024000000208616257,
      "loss": 2.884570837020874,
      "step": 1736
    },
    {
      "epoch": 0.08276190476190476,
      "grad_norm": 0.05285165458917618,
      "learning_rate": 0.024000000208616257,
      "loss": 2.916743278503418,
      "step": 1738
    },
    {
      "epoch": 0.08285714285714285,
      "grad_norm": 0.04843684285879135,
      "learning_rate": 0.024000000208616257,
      "loss": 2.929807662963867,
      "step": 1740
    },
    {
      "epoch": 0.08295238095238096,
      "grad_norm": 0.05033249780535698,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9302589893341064,
      "step": 1742
    },
    {
      "epoch": 0.08304761904761905,
      "grad_norm": 0.048141587525606155,
      "learning_rate": 0.024000000208616257,
      "loss": 2.923670530319214,
      "step": 1744
    },
    {
      "epoch": 0.08314285714285714,
      "grad_norm": 0.052375055849552155,
      "learning_rate": 0.024000000208616257,
      "loss": 2.912346124649048,
      "step": 1746
    },
    {
      "epoch": 0.08323809523809524,
      "grad_norm": 0.05359971523284912,
      "learning_rate": 0.024000000208616257,
      "loss": 2.933220386505127,
      "step": 1748
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.05416681990027428,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9013454914093018,
      "step": 1750
    },
    {
      "epoch": 0.08342857142857144,
      "grad_norm": 0.05477030947804451,
      "learning_rate": 0.024000000208616257,
      "loss": 2.954806327819824,
      "step": 1752
    },
    {
      "epoch": 0.08352380952380953,
      "grad_norm": 0.0504164844751358,
      "learning_rate": 0.024000000208616257,
      "loss": 2.901737928390503,
      "step": 1754
    },
    {
      "epoch": 0.08361904761904762,
      "grad_norm": 0.0505952462553978,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9503352642059326,
      "step": 1756
    },
    {
      "epoch": 0.08371428571428571,
      "grad_norm": 0.051258429884910583,
      "learning_rate": 0.024000000208616257,
      "loss": 2.922111988067627,
      "step": 1758
    },
    {
      "epoch": 0.0838095238095238,
      "grad_norm": 0.048889029771089554,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9323060512542725,
      "step": 1760
    },
    {
      "epoch": 0.0839047619047619,
      "grad_norm": 0.048582132905721664,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9029788970947266,
      "step": 1762
    },
    {
      "epoch": 0.084,
      "grad_norm": 0.05020999163389206,
      "learning_rate": 0.024000000208616257,
      "loss": 2.95003342628479,
      "step": 1764
    },
    {
      "epoch": 0.0840952380952381,
      "grad_norm": 0.050957951694726944,
      "learning_rate": 0.024000000208616257,
      "loss": 2.913956642150879,
      "step": 1766
    },
    {
      "epoch": 0.08419047619047619,
      "grad_norm": 0.04795093834400177,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9243288040161133,
      "step": 1768
    },
    {
      "epoch": 0.08428571428571428,
      "grad_norm": 0.048361022025346756,
      "learning_rate": 0.024000000208616257,
      "loss": 2.932157516479492,
      "step": 1770
    },
    {
      "epoch": 0.08438095238095238,
      "grad_norm": 0.04864426702260971,
      "learning_rate": 0.024000000208616257,
      "loss": 2.922715663909912,
      "step": 1772
    },
    {
      "epoch": 0.08447619047619048,
      "grad_norm": 0.04898499697446823,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9477601051330566,
      "step": 1774
    },
    {
      "epoch": 0.08457142857142858,
      "grad_norm": 0.0483531653881073,
      "learning_rate": 0.024000000208616257,
      "loss": 2.902346611022949,
      "step": 1776
    },
    {
      "epoch": 0.08466666666666667,
      "grad_norm": 0.05009257048368454,
      "learning_rate": 0.024000000208616257,
      "loss": 2.911827325820923,
      "step": 1778
    },
    {
      "epoch": 0.08476190476190476,
      "grad_norm": 0.04960031434893608,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9267053604125977,
      "step": 1780
    },
    {
      "epoch": 0.08485714285714285,
      "grad_norm": 0.04906485602259636,
      "learning_rate": 0.024000000208616257,
      "loss": 2.909885883331299,
      "step": 1782
    },
    {
      "epoch": 0.08495238095238095,
      "grad_norm": 0.044801630079746246,
      "learning_rate": 0.024000000208616257,
      "loss": 2.941408634185791,
      "step": 1784
    },
    {
      "epoch": 0.08504761904761905,
      "grad_norm": 0.045400481671094894,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9211926460266113,
      "step": 1786
    },
    {
      "epoch": 0.08514285714285715,
      "grad_norm": 0.04736117646098137,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9198503494262695,
      "step": 1788
    },
    {
      "epoch": 0.08523809523809524,
      "grad_norm": 0.04929405450820923,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9106826782226562,
      "step": 1790
    },
    {
      "epoch": 0.08533333333333333,
      "grad_norm": 0.0495775043964386,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9230260848999023,
      "step": 1792
    },
    {
      "epoch": 0.08542857142857142,
      "grad_norm": 0.04621453955769539,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9366226196289062,
      "step": 1794
    },
    {
      "epoch": 0.08552380952380953,
      "grad_norm": 0.04935209080576897,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9170100688934326,
      "step": 1796
    },
    {
      "epoch": 0.08561904761904762,
      "grad_norm": 0.04880139231681824,
      "learning_rate": 0.024000000208616257,
      "loss": 2.925306797027588,
      "step": 1798
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.04902074486017227,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9086456298828125,
      "step": 1800
    },
    {
      "epoch": 0.08580952380952381,
      "grad_norm": 0.04751172289252281,
      "learning_rate": 0.024000000208616257,
      "loss": 2.926955461502075,
      "step": 1802
    },
    {
      "epoch": 0.0859047619047619,
      "grad_norm": 0.05038060247898102,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9027867317199707,
      "step": 1804
    },
    {
      "epoch": 0.086,
      "grad_norm": 0.04624738171696663,
      "learning_rate": 0.024000000208616257,
      "loss": 2.916271686553955,
      "step": 1806
    },
    {
      "epoch": 0.0860952380952381,
      "grad_norm": 0.04678872600197792,
      "learning_rate": 0.024000000208616257,
      "loss": 2.876336097717285,
      "step": 1808
    },
    {
      "epoch": 0.08619047619047619,
      "grad_norm": 0.050623569637537,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8829941749572754,
      "step": 1810
    },
    {
      "epoch": 0.08628571428571429,
      "grad_norm": 0.052835430949926376,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9349863529205322,
      "step": 1812
    },
    {
      "epoch": 0.08638095238095238,
      "grad_norm": 0.05240755155682564,
      "learning_rate": 0.024000000208616257,
      "loss": 2.871344566345215,
      "step": 1814
    },
    {
      "epoch": 0.08647619047619047,
      "grad_norm": 0.048297155648469925,
      "learning_rate": 0.024000000208616257,
      "loss": 2.902907371520996,
      "step": 1816
    },
    {
      "epoch": 0.08657142857142858,
      "grad_norm": 0.04735265299677849,
      "learning_rate": 0.024000000208616257,
      "loss": 2.919884204864502,
      "step": 1818
    },
    {
      "epoch": 0.08666666666666667,
      "grad_norm": 0.04946067929267883,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9102816581726074,
      "step": 1820
    },
    {
      "epoch": 0.08676190476190476,
      "grad_norm": 0.05052957683801651,
      "learning_rate": 0.024000000208616257,
      "loss": 2.899509906768799,
      "step": 1822
    },
    {
      "epoch": 0.08685714285714285,
      "grad_norm": 0.047798264771699905,
      "learning_rate": 0.024000000208616257,
      "loss": 2.944962501525879,
      "step": 1824
    },
    {
      "epoch": 0.08695238095238095,
      "grad_norm": 0.04692132771015167,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9210376739501953,
      "step": 1826
    },
    {
      "epoch": 0.08704761904761905,
      "grad_norm": 0.04988217353820801,
      "learning_rate": 0.024000000208616257,
      "loss": 2.895080804824829,
      "step": 1828
    },
    {
      "epoch": 0.08714285714285715,
      "grad_norm": 0.04940056800842285,
      "learning_rate": 0.024000000208616257,
      "loss": 2.910677909851074,
      "step": 1830
    },
    {
      "epoch": 0.08723809523809524,
      "grad_norm": 0.04905298352241516,
      "learning_rate": 0.024000000208616257,
      "loss": 2.87399959564209,
      "step": 1832
    },
    {
      "epoch": 0.08733333333333333,
      "grad_norm": 0.04785619303584099,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9453775882720947,
      "step": 1834
    },
    {
      "epoch": 0.08742857142857142,
      "grad_norm": 0.04924243688583374,
      "learning_rate": 0.024000000208616257,
      "loss": 2.871040105819702,
      "step": 1836
    },
    {
      "epoch": 0.08752380952380952,
      "grad_norm": 0.047585658729076385,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9043450355529785,
      "step": 1838
    },
    {
      "epoch": 0.08761904761904762,
      "grad_norm": 0.051190439611673355,
      "learning_rate": 0.024000000208616257,
      "loss": 2.921894073486328,
      "step": 1840
    },
    {
      "epoch": 0.08771428571428572,
      "grad_norm": 0.0523282065987587,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9013051986694336,
      "step": 1842
    },
    {
      "epoch": 0.08780952380952381,
      "grad_norm": 0.04741648957133293,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8834471702575684,
      "step": 1844
    },
    {
      "epoch": 0.0879047619047619,
      "grad_norm": 0.04696672037243843,
      "learning_rate": 0.024000000208616257,
      "loss": 2.919973373413086,
      "step": 1846
    },
    {
      "epoch": 0.088,
      "grad_norm": 0.04543508216738701,
      "learning_rate": 0.024000000208616257,
      "loss": 2.90704345703125,
      "step": 1848
    },
    {
      "epoch": 0.0880952380952381,
      "grad_norm": 0.045827776193618774,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8946852684020996,
      "step": 1850
    },
    {
      "epoch": 0.0881904761904762,
      "grad_norm": 0.0484558567404747,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8845162391662598,
      "step": 1852
    },
    {
      "epoch": 0.08828571428571429,
      "grad_norm": 0.04969274252653122,
      "learning_rate": 0.024000000208616257,
      "loss": 2.896610736846924,
      "step": 1854
    },
    {
      "epoch": 0.08838095238095238,
      "grad_norm": 0.047750845551490784,
      "learning_rate": 0.024000000208616257,
      "loss": 2.925387144088745,
      "step": 1856
    },
    {
      "epoch": 0.08847619047619047,
      "grad_norm": 0.04754344001412392,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9030370712280273,
      "step": 1858
    },
    {
      "epoch": 0.08857142857142856,
      "grad_norm": 0.04745683819055557,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8768744468688965,
      "step": 1860
    },
    {
      "epoch": 0.08866666666666667,
      "grad_norm": 0.04529402777552605,
      "learning_rate": 0.024000000208616257,
      "loss": 2.937650680541992,
      "step": 1862
    },
    {
      "epoch": 0.08876190476190476,
      "grad_norm": 0.045453060418367386,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9259190559387207,
      "step": 1864
    },
    {
      "epoch": 0.08885714285714286,
      "grad_norm": 0.051195286214351654,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8839707374572754,
      "step": 1866
    },
    {
      "epoch": 0.08895238095238095,
      "grad_norm": 0.051619917154312134,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8866395950317383,
      "step": 1868
    },
    {
      "epoch": 0.08904761904761904,
      "grad_norm": 0.053829122334718704,
      "learning_rate": 0.024000000208616257,
      "loss": 2.892927408218384,
      "step": 1870
    },
    {
      "epoch": 0.08914285714285715,
      "grad_norm": 0.047841109335422516,
      "learning_rate": 0.024000000208616257,
      "loss": 2.894252300262451,
      "step": 1872
    },
    {
      "epoch": 0.08923809523809524,
      "grad_norm": 0.046796709299087524,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8708386421203613,
      "step": 1874
    },
    {
      "epoch": 0.08933333333333333,
      "grad_norm": 0.052024565637111664,
      "learning_rate": 0.024000000208616257,
      "loss": 2.859463930130005,
      "step": 1876
    },
    {
      "epoch": 0.08942857142857143,
      "grad_norm": 0.04834221675992012,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8736495971679688,
      "step": 1878
    },
    {
      "epoch": 0.08952380952380952,
      "grad_norm": 0.04942356422543526,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8546204566955566,
      "step": 1880
    },
    {
      "epoch": 0.08961904761904763,
      "grad_norm": 0.050201307982206345,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8966493606567383,
      "step": 1882
    },
    {
      "epoch": 0.08971428571428572,
      "grad_norm": 0.04961952194571495,
      "learning_rate": 0.024000000208616257,
      "loss": 2.832888603210449,
      "step": 1884
    },
    {
      "epoch": 0.08980952380952381,
      "grad_norm": 0.04845400154590607,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9102015495300293,
      "step": 1886
    },
    {
      "epoch": 0.0899047619047619,
      "grad_norm": 0.04760521650314331,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8759899139404297,
      "step": 1888
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.04865095764398575,
      "learning_rate": 0.024000000208616257,
      "loss": 2.873173713684082,
      "step": 1890
    },
    {
      "epoch": 0.09009523809523809,
      "grad_norm": 0.04782674461603165,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8944315910339355,
      "step": 1892
    },
    {
      "epoch": 0.0901904761904762,
      "grad_norm": 0.04953862726688385,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8837642669677734,
      "step": 1894
    },
    {
      "epoch": 0.09028571428571429,
      "grad_norm": 0.04587021842598915,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8647146224975586,
      "step": 1896
    },
    {
      "epoch": 0.09038095238095238,
      "grad_norm": 0.04698994755744934,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8609018325805664,
      "step": 1898
    },
    {
      "epoch": 0.09047619047619047,
      "grad_norm": 0.05049850419163704,
      "learning_rate": 0.024000000208616257,
      "loss": 2.864516496658325,
      "step": 1900
    },
    {
      "epoch": 0.09057142857142857,
      "grad_norm": 0.046002715826034546,
      "learning_rate": 0.024000000208616257,
      "loss": 2.866804838180542,
      "step": 1902
    },
    {
      "epoch": 0.09066666666666667,
      "grad_norm": 0.04630015045404434,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8910927772521973,
      "step": 1904
    },
    {
      "epoch": 0.09076190476190477,
      "grad_norm": 0.04620473086833954,
      "learning_rate": 0.024000000208616257,
      "loss": 2.885674238204956,
      "step": 1906
    },
    {
      "epoch": 0.09085714285714286,
      "grad_norm": 0.04824550077319145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8710174560546875,
      "step": 1908
    },
    {
      "epoch": 0.09095238095238095,
      "grad_norm": 0.04841945692896843,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8912553787231445,
      "step": 1910
    },
    {
      "epoch": 0.09104761904761904,
      "grad_norm": 0.049596238881349564,
      "learning_rate": 0.024000000208616257,
      "loss": 2.852769613265991,
      "step": 1912
    },
    {
      "epoch": 0.09114285714285714,
      "grad_norm": 0.04636437073349953,
      "learning_rate": 0.024000000208616257,
      "loss": 2.839388370513916,
      "step": 1914
    },
    {
      "epoch": 0.09123809523809524,
      "grad_norm": 0.04494453966617584,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9251198768615723,
      "step": 1916
    },
    {
      "epoch": 0.09133333333333334,
      "grad_norm": 0.04819165915250778,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8807997703552246,
      "step": 1918
    },
    {
      "epoch": 0.09142857142857143,
      "grad_norm": 0.044840097427368164,
      "learning_rate": 0.024000000208616257,
      "loss": 2.865434169769287,
      "step": 1920
    },
    {
      "epoch": 0.09152380952380952,
      "grad_norm": 0.04443307965993881,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8829140663146973,
      "step": 1922
    },
    {
      "epoch": 0.09161904761904761,
      "grad_norm": 0.04454384371638298,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8671813011169434,
      "step": 1924
    },
    {
      "epoch": 0.09171428571428572,
      "grad_norm": 0.04788820818066597,
      "learning_rate": 0.024000000208616257,
      "loss": 2.9038796424865723,
      "step": 1926
    },
    {
      "epoch": 0.09180952380952381,
      "grad_norm": 0.0465865395963192,
      "learning_rate": 0.024000000208616257,
      "loss": 2.866696834564209,
      "step": 1928
    },
    {
      "epoch": 0.0919047619047619,
      "grad_norm": 0.047647133469581604,
      "learning_rate": 0.024000000208616257,
      "loss": 2.885589599609375,
      "step": 1930
    },
    {
      "epoch": 0.092,
      "grad_norm": 0.04957328736782074,
      "learning_rate": 0.024000000208616257,
      "loss": 2.88862943649292,
      "step": 1932
    },
    {
      "epoch": 0.09209523809523809,
      "grad_norm": 0.048244498670101166,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8736824989318848,
      "step": 1934
    },
    {
      "epoch": 0.09219047619047618,
      "grad_norm": 0.04724639281630516,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8921637535095215,
      "step": 1936
    },
    {
      "epoch": 0.09228571428571429,
      "grad_norm": 0.04675273224711418,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8413829803466797,
      "step": 1938
    },
    {
      "epoch": 0.09238095238095238,
      "grad_norm": 0.04670845717191696,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8642895221710205,
      "step": 1940
    },
    {
      "epoch": 0.09247619047619048,
      "grad_norm": 0.04450660198926926,
      "learning_rate": 0.024000000208616257,
      "loss": 2.878390312194824,
      "step": 1942
    },
    {
      "epoch": 0.09257142857142857,
      "grad_norm": 0.04861907660961151,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8296988010406494,
      "step": 1944
    },
    {
      "epoch": 0.09266666666666666,
      "grad_norm": 0.04889195039868355,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8825531005859375,
      "step": 1946
    },
    {
      "epoch": 0.09276190476190477,
      "grad_norm": 0.04825654625892639,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8327250480651855,
      "step": 1948
    },
    {
      "epoch": 0.09285714285714286,
      "grad_norm": 0.04776325449347496,
      "learning_rate": 0.024000000208616257,
      "loss": 2.858691692352295,
      "step": 1950
    },
    {
      "epoch": 0.09295238095238095,
      "grad_norm": 0.047096576541662216,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8326539993286133,
      "step": 1952
    },
    {
      "epoch": 0.09304761904761905,
      "grad_norm": 0.05279967933893204,
      "learning_rate": 0.024000000208616257,
      "loss": 2.842270851135254,
      "step": 1954
    },
    {
      "epoch": 0.09314285714285714,
      "grad_norm": 0.048733871430158615,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8517894744873047,
      "step": 1956
    },
    {
      "epoch": 0.09323809523809524,
      "grad_norm": 0.04669317230582237,
      "learning_rate": 0.024000000208616257,
      "loss": 2.853306293487549,
      "step": 1958
    },
    {
      "epoch": 0.09333333333333334,
      "grad_norm": 0.04687914624810219,
      "learning_rate": 0.024000000208616257,
      "loss": 2.845712661743164,
      "step": 1960
    },
    {
      "epoch": 0.09342857142857143,
      "grad_norm": 0.04500582441687584,
      "learning_rate": 0.024000000208616257,
      "loss": 2.856719732284546,
      "step": 1962
    },
    {
      "epoch": 0.09352380952380952,
      "grad_norm": 0.04837122559547424,
      "learning_rate": 0.024000000208616257,
      "loss": 2.832679271697998,
      "step": 1964
    },
    {
      "epoch": 0.09361904761904762,
      "grad_norm": 0.04894803836941719,
      "learning_rate": 0.024000000208616257,
      "loss": 2.845010757446289,
      "step": 1966
    },
    {
      "epoch": 0.09371428571428571,
      "grad_norm": 0.04745759442448616,
      "learning_rate": 0.024000000208616257,
      "loss": 2.874016523361206,
      "step": 1968
    },
    {
      "epoch": 0.09380952380952381,
      "grad_norm": 0.04585672914981842,
      "learning_rate": 0.024000000208616257,
      "loss": 2.846766471862793,
      "step": 1970
    },
    {
      "epoch": 0.09390476190476191,
      "grad_norm": 0.046256132423877716,
      "learning_rate": 0.024000000208616257,
      "loss": 2.819000720977783,
      "step": 1972
    },
    {
      "epoch": 0.094,
      "grad_norm": 0.045277297496795654,
      "learning_rate": 0.024000000208616257,
      "loss": 2.849764823913574,
      "step": 1974
    },
    {
      "epoch": 0.09409523809523809,
      "grad_norm": 0.04414394870400429,
      "learning_rate": 0.024000000208616257,
      "loss": 2.862924337387085,
      "step": 1976
    },
    {
      "epoch": 0.09419047619047619,
      "grad_norm": 0.04697718471288681,
      "learning_rate": 0.024000000208616257,
      "loss": 2.849367141723633,
      "step": 1978
    },
    {
      "epoch": 0.09428571428571429,
      "grad_norm": 0.04767430201172829,
      "learning_rate": 0.024000000208616257,
      "loss": 2.871857166290283,
      "step": 1980
    },
    {
      "epoch": 0.09438095238095238,
      "grad_norm": 0.049441032111644745,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8404994010925293,
      "step": 1982
    },
    {
      "epoch": 0.09447619047619048,
      "grad_norm": 0.04973596706986427,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8469762802124023,
      "step": 1984
    },
    {
      "epoch": 0.09457142857142857,
      "grad_norm": 0.04772248491644859,
      "learning_rate": 0.024000000208616257,
      "loss": 2.859570026397705,
      "step": 1986
    },
    {
      "epoch": 0.09466666666666666,
      "grad_norm": 0.04859307035803795,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8513991832733154,
      "step": 1988
    },
    {
      "epoch": 0.09476190476190476,
      "grad_norm": 0.04829339683055878,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8382010459899902,
      "step": 1990
    },
    {
      "epoch": 0.09485714285714286,
      "grad_norm": 0.049595948308706284,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8291382789611816,
      "step": 1992
    },
    {
      "epoch": 0.09495238095238095,
      "grad_norm": 0.04629486799240112,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8208744525909424,
      "step": 1994
    },
    {
      "epoch": 0.09504761904761905,
      "grad_norm": 0.0447094589471817,
      "learning_rate": 0.024000000208616257,
      "loss": 2.833498477935791,
      "step": 1996
    },
    {
      "epoch": 0.09514285714285714,
      "grad_norm": 0.04580864682793617,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8686211109161377,
      "step": 1998
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.0470288023352623,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8630638122558594,
      "step": 2000
    },
    {
      "epoch": 0.09533333333333334,
      "grad_norm": 0.04554036259651184,
      "learning_rate": 0.024000000208616257,
      "loss": 2.831763744354248,
      "step": 2002
    },
    {
      "epoch": 0.09542857142857143,
      "grad_norm": 0.04663560166954994,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8406424522399902,
      "step": 2004
    },
    {
      "epoch": 0.09552380952380952,
      "grad_norm": 0.04670238122344017,
      "learning_rate": 0.024000000208616257,
      "loss": 2.858717441558838,
      "step": 2006
    },
    {
      "epoch": 0.09561904761904762,
      "grad_norm": 0.04544892907142639,
      "learning_rate": 0.024000000208616257,
      "loss": 2.846251964569092,
      "step": 2008
    },
    {
      "epoch": 0.09571428571428571,
      "grad_norm": 0.04494383558630943,
      "learning_rate": 0.024000000208616257,
      "loss": 2.836210250854492,
      "step": 2010
    },
    {
      "epoch": 0.0958095238095238,
      "grad_norm": 0.04496229439973831,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8258056640625,
      "step": 2012
    },
    {
      "epoch": 0.09590476190476191,
      "grad_norm": 0.04366561397910118,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8283958435058594,
      "step": 2014
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.043547749519348145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8297252655029297,
      "step": 2016
    },
    {
      "epoch": 0.0960952380952381,
      "grad_norm": 0.04916880652308464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.85078763961792,
      "step": 2018
    },
    {
      "epoch": 0.09619047619047619,
      "grad_norm": 0.04956594109535217,
      "learning_rate": 0.024000000208616257,
      "loss": 2.856487274169922,
      "step": 2020
    },
    {
      "epoch": 0.09628571428571428,
      "grad_norm": 0.04618437588214874,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8403139114379883,
      "step": 2022
    },
    {
      "epoch": 0.09638095238095239,
      "grad_norm": 0.04574640840291977,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8448681831359863,
      "step": 2024
    },
    {
      "epoch": 0.09647619047619048,
      "grad_norm": 0.04415767267346382,
      "learning_rate": 0.024000000208616257,
      "loss": 2.883380174636841,
      "step": 2026
    },
    {
      "epoch": 0.09657142857142857,
      "grad_norm": 0.04504362866282463,
      "learning_rate": 0.024000000208616257,
      "loss": 2.848153591156006,
      "step": 2028
    },
    {
      "epoch": 0.09666666666666666,
      "grad_norm": 0.043912649154663086,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8664803504943848,
      "step": 2030
    },
    {
      "epoch": 0.09676190476190476,
      "grad_norm": 0.04732342064380646,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8426120281219482,
      "step": 2032
    },
    {
      "epoch": 0.09685714285714286,
      "grad_norm": 0.043381985276937485,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8614749908447266,
      "step": 2034
    },
    {
      "epoch": 0.09695238095238096,
      "grad_norm": 0.043311990797519684,
      "learning_rate": 0.024000000208616257,
      "loss": 2.890892505645752,
      "step": 2036
    },
    {
      "epoch": 0.09704761904761905,
      "grad_norm": 0.04673368111252785,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8286983966827393,
      "step": 2038
    },
    {
      "epoch": 0.09714285714285714,
      "grad_norm": 0.04454313963651657,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8314905166625977,
      "step": 2040
    },
    {
      "epoch": 0.09723809523809523,
      "grad_norm": 0.046734172850847244,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8361523151397705,
      "step": 2042
    },
    {
      "epoch": 0.09733333333333333,
      "grad_norm": 0.04624871164560318,
      "learning_rate": 0.024000000208616257,
      "loss": 2.842376232147217,
      "step": 2044
    },
    {
      "epoch": 0.09742857142857143,
      "grad_norm": 0.04599558562040329,
      "learning_rate": 0.024000000208616257,
      "loss": 2.844224452972412,
      "step": 2046
    },
    {
      "epoch": 0.09752380952380953,
      "grad_norm": 0.04524260014295578,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8610355854034424,
      "step": 2048
    },
    {
      "epoch": 0.09761904761904762,
      "grad_norm": 0.043864425271749496,
      "learning_rate": 0.024000000208616257,
      "loss": 2.830440044403076,
      "step": 2050
    },
    {
      "epoch": 0.09771428571428571,
      "grad_norm": 0.04593706876039505,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8175859451293945,
      "step": 2052
    },
    {
      "epoch": 0.0978095238095238,
      "grad_norm": 0.045440398156642914,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8330068588256836,
      "step": 2054
    },
    {
      "epoch": 0.09790476190476191,
      "grad_norm": 0.047161512076854706,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8572006225585938,
      "step": 2056
    },
    {
      "epoch": 0.098,
      "grad_norm": 0.04605802148580551,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8463287353515625,
      "step": 2058
    },
    {
      "epoch": 0.0980952380952381,
      "grad_norm": 0.045254629105329514,
      "learning_rate": 0.024000000208616257,
      "loss": 2.840179681777954,
      "step": 2060
    },
    {
      "epoch": 0.09819047619047619,
      "grad_norm": 0.05186774581670761,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8254218101501465,
      "step": 2062
    },
    {
      "epoch": 0.09828571428571428,
      "grad_norm": 0.04939455911517143,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8321309089660645,
      "step": 2064
    },
    {
      "epoch": 0.09838095238095237,
      "grad_norm": 0.05161518603563309,
      "learning_rate": 0.024000000208616257,
      "loss": 2.884840965270996,
      "step": 2066
    },
    {
      "epoch": 0.09847619047619048,
      "grad_norm": 0.05238473787903786,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8062829971313477,
      "step": 2068
    },
    {
      "epoch": 0.09857142857142857,
      "grad_norm": 0.047204844653606415,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8672332763671875,
      "step": 2070
    },
    {
      "epoch": 0.09866666666666667,
      "grad_norm": 0.04796832054853439,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8585565090179443,
      "step": 2072
    },
    {
      "epoch": 0.09876190476190476,
      "grad_norm": 0.044070784002542496,
      "learning_rate": 0.024000000208616257,
      "loss": 2.840139389038086,
      "step": 2074
    },
    {
      "epoch": 0.09885714285714285,
      "grad_norm": 0.042820632457733154,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8405439853668213,
      "step": 2076
    },
    {
      "epoch": 0.09895238095238096,
      "grad_norm": 0.0434587337076664,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8412208557128906,
      "step": 2078
    },
    {
      "epoch": 0.09904761904761905,
      "grad_norm": 0.04619544371962547,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8065357208251953,
      "step": 2080
    },
    {
      "epoch": 0.09914285714285714,
      "grad_norm": 0.044262588024139404,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8465912342071533,
      "step": 2082
    },
    {
      "epoch": 0.09923809523809524,
      "grad_norm": 0.04671461880207062,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8558590412139893,
      "step": 2084
    },
    {
      "epoch": 0.09933333333333333,
      "grad_norm": 0.04726586118340492,
      "learning_rate": 0.024000000208616257,
      "loss": 2.802800416946411,
      "step": 2086
    },
    {
      "epoch": 0.09942857142857142,
      "grad_norm": 0.04587564617395401,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8421497344970703,
      "step": 2088
    },
    {
      "epoch": 0.09952380952380953,
      "grad_norm": 0.04731918126344681,
      "learning_rate": 0.024000000208616257,
      "loss": 2.869065046310425,
      "step": 2090
    },
    {
      "epoch": 0.09961904761904762,
      "grad_norm": 0.045317549258470535,
      "learning_rate": 0.024000000208616257,
      "loss": 2.830443859100342,
      "step": 2092
    },
    {
      "epoch": 0.09971428571428571,
      "grad_norm": 0.04637543484568596,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8099091053009033,
      "step": 2094
    },
    {
      "epoch": 0.0998095238095238,
      "grad_norm": 0.048281311988830566,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8163256645202637,
      "step": 2096
    },
    {
      "epoch": 0.0999047619047619,
      "grad_norm": 0.045609377324581146,
      "learning_rate": 0.024000000208616257,
      "loss": 2.84521746635437,
      "step": 2098
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.04590599238872528,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8496956825256348,
      "step": 2100
    },
    {
      "epoch": 0.1000952380952381,
      "grad_norm": 0.046635743230581284,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8566818237304688,
      "step": 2102
    },
    {
      "epoch": 0.10019047619047619,
      "grad_norm": 0.044828761368989944,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8403878211975098,
      "step": 2104
    },
    {
      "epoch": 0.10028571428571428,
      "grad_norm": 0.04601656273007393,
      "learning_rate": 0.024000000208616257,
      "loss": 2.872518539428711,
      "step": 2106
    },
    {
      "epoch": 0.10038095238095238,
      "grad_norm": 0.045710448175668716,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8315157890319824,
      "step": 2108
    },
    {
      "epoch": 0.10047619047619048,
      "grad_norm": 0.04519449919462204,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8540096282958984,
      "step": 2110
    },
    {
      "epoch": 0.10057142857142858,
      "grad_norm": 0.04472912847995758,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8516390323638916,
      "step": 2112
    },
    {
      "epoch": 0.10066666666666667,
      "grad_norm": 0.04309597238898277,
      "learning_rate": 0.024000000208616257,
      "loss": 2.856410026550293,
      "step": 2114
    },
    {
      "epoch": 0.10076190476190476,
      "grad_norm": 0.04461464658379555,
      "learning_rate": 0.024000000208616257,
      "loss": 2.86624813079834,
      "step": 2116
    },
    {
      "epoch": 0.10085714285714285,
      "grad_norm": 0.048866286873817444,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7971999645233154,
      "step": 2118
    },
    {
      "epoch": 0.10095238095238095,
      "grad_norm": 0.05240330845117569,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8426027297973633,
      "step": 2120
    },
    {
      "epoch": 0.10104761904761905,
      "grad_norm": 0.04889432713389397,
      "learning_rate": 0.024000000208616257,
      "loss": 2.835803508758545,
      "step": 2122
    },
    {
      "epoch": 0.10114285714285715,
      "grad_norm": 0.04586942866444588,
      "learning_rate": 0.024000000208616257,
      "loss": 2.858893394470215,
      "step": 2124
    },
    {
      "epoch": 0.10123809523809524,
      "grad_norm": 0.04378058388829231,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8306028842926025,
      "step": 2126
    },
    {
      "epoch": 0.10133333333333333,
      "grad_norm": 0.04321957007050514,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8214197158813477,
      "step": 2128
    },
    {
      "epoch": 0.10142857142857142,
      "grad_norm": 0.04393071308732033,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8262834548950195,
      "step": 2130
    },
    {
      "epoch": 0.10152380952380953,
      "grad_norm": 0.04210207611322403,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8061437606811523,
      "step": 2132
    },
    {
      "epoch": 0.10161904761904762,
      "grad_norm": 0.04229958355426788,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8295655250549316,
      "step": 2134
    },
    {
      "epoch": 0.10171428571428572,
      "grad_norm": 0.04320858418941498,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8149302005767822,
      "step": 2136
    },
    {
      "epoch": 0.10180952380952381,
      "grad_norm": 0.04470789432525635,
      "learning_rate": 0.024000000208616257,
      "loss": 2.808070659637451,
      "step": 2138
    },
    {
      "epoch": 0.1019047619047619,
      "grad_norm": 0.04178925231099129,
      "learning_rate": 0.024000000208616257,
      "loss": 2.797851800918579,
      "step": 2140
    },
    {
      "epoch": 0.102,
      "grad_norm": 0.04365589842200279,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7991480827331543,
      "step": 2142
    },
    {
      "epoch": 0.1020952380952381,
      "grad_norm": 0.043695636093616486,
      "learning_rate": 0.024000000208616257,
      "loss": 2.855901002883911,
      "step": 2144
    },
    {
      "epoch": 0.10219047619047619,
      "grad_norm": 0.045504696667194366,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8165531158447266,
      "step": 2146
    },
    {
      "epoch": 0.10228571428571429,
      "grad_norm": 0.047187674790620804,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8199291229248047,
      "step": 2148
    },
    {
      "epoch": 0.10238095238095238,
      "grad_norm": 0.043682459741830826,
      "learning_rate": 0.024000000208616257,
      "loss": 2.839977264404297,
      "step": 2150
    },
    {
      "epoch": 0.10247619047619047,
      "grad_norm": 0.04365682229399681,
      "learning_rate": 0.024000000208616257,
      "loss": 2.826511859893799,
      "step": 2152
    },
    {
      "epoch": 0.10257142857142858,
      "grad_norm": 0.04749247059226036,
      "learning_rate": 0.024000000208616257,
      "loss": 2.843919277191162,
      "step": 2154
    },
    {
      "epoch": 0.10266666666666667,
      "grad_norm": 0.04342002049088478,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8201985359191895,
      "step": 2156
    },
    {
      "epoch": 0.10276190476190476,
      "grad_norm": 0.04460325092077255,
      "learning_rate": 0.024000000208616257,
      "loss": 2.821110725402832,
      "step": 2158
    },
    {
      "epoch": 0.10285714285714286,
      "grad_norm": 0.04470650479197502,
      "learning_rate": 0.024000000208616257,
      "loss": 2.858128547668457,
      "step": 2160
    },
    {
      "epoch": 0.10295238095238095,
      "grad_norm": 0.04588766768574715,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8228402137756348,
      "step": 2162
    },
    {
      "epoch": 0.10304761904761905,
      "grad_norm": 0.0480223074555397,
      "learning_rate": 0.024000000208616257,
      "loss": 2.832181215286255,
      "step": 2164
    },
    {
      "epoch": 0.10314285714285715,
      "grad_norm": 0.04655365273356438,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8186793327331543,
      "step": 2166
    },
    {
      "epoch": 0.10323809523809524,
      "grad_norm": 0.045809727162122726,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8475966453552246,
      "step": 2168
    },
    {
      "epoch": 0.10333333333333333,
      "grad_norm": 0.043699879199266434,
      "learning_rate": 0.024000000208616257,
      "loss": 2.841308355331421,
      "step": 2170
    },
    {
      "epoch": 0.10342857142857143,
      "grad_norm": 0.0426674485206604,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8552589416503906,
      "step": 2172
    },
    {
      "epoch": 0.10352380952380952,
      "grad_norm": 0.04381323233246803,
      "learning_rate": 0.024000000208616257,
      "loss": 2.80580735206604,
      "step": 2174
    },
    {
      "epoch": 0.10361904761904762,
      "grad_norm": 0.04523113742470741,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8417515754699707,
      "step": 2176
    },
    {
      "epoch": 0.10371428571428572,
      "grad_norm": 0.052583128213882446,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7783849239349365,
      "step": 2178
    },
    {
      "epoch": 0.10380952380952381,
      "grad_norm": 0.04889420047402382,
      "learning_rate": 0.024000000208616257,
      "loss": 2.85310435295105,
      "step": 2180
    },
    {
      "epoch": 0.1039047619047619,
      "grad_norm": 0.05313193425536156,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8446478843688965,
      "step": 2182
    },
    {
      "epoch": 0.104,
      "grad_norm": 0.052939850836992264,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8644540309906006,
      "step": 2184
    },
    {
      "epoch": 0.1040952380952381,
      "grad_norm": 0.04608689248561859,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8259527683258057,
      "step": 2186
    },
    {
      "epoch": 0.1041904761904762,
      "grad_norm": 0.04213324561715126,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8431973457336426,
      "step": 2188
    },
    {
      "epoch": 0.10428571428571429,
      "grad_norm": 0.046848978847265244,
      "learning_rate": 0.024000000208616257,
      "loss": 2.795813798904419,
      "step": 2190
    },
    {
      "epoch": 0.10438095238095238,
      "grad_norm": 0.04308215528726578,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7969753742218018,
      "step": 2192
    },
    {
      "epoch": 0.10447619047619047,
      "grad_norm": 0.043003957718610764,
      "learning_rate": 0.024000000208616257,
      "loss": 2.825375556945801,
      "step": 2194
    },
    {
      "epoch": 0.10457142857142857,
      "grad_norm": 0.046162862330675125,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8525490760803223,
      "step": 2196
    },
    {
      "epoch": 0.10466666666666667,
      "grad_norm": 0.04360783100128174,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8352913856506348,
      "step": 2198
    },
    {
      "epoch": 0.10476190476190476,
      "grad_norm": 0.04429905116558075,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8292059898376465,
      "step": 2200
    },
    {
      "epoch": 0.10485714285714286,
      "grad_norm": 0.048310477286577225,
      "learning_rate": 0.024000000208616257,
      "loss": 2.840420722961426,
      "step": 2202
    },
    {
      "epoch": 0.10495238095238095,
      "grad_norm": 0.05058959126472473,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8292698860168457,
      "step": 2204
    },
    {
      "epoch": 0.10504761904761904,
      "grad_norm": 0.047456055879592896,
      "learning_rate": 0.024000000208616257,
      "loss": 2.841060161590576,
      "step": 2206
    },
    {
      "epoch": 0.10514285714285715,
      "grad_norm": 0.043398693203926086,
      "learning_rate": 0.024000000208616257,
      "loss": 2.842210292816162,
      "step": 2208
    },
    {
      "epoch": 0.10523809523809524,
      "grad_norm": 0.04361608251929283,
      "learning_rate": 0.024000000208616257,
      "loss": 2.809234142303467,
      "step": 2210
    },
    {
      "epoch": 0.10533333333333333,
      "grad_norm": 0.04360458254814148,
      "learning_rate": 0.024000000208616257,
      "loss": 2.816373348236084,
      "step": 2212
    },
    {
      "epoch": 0.10542857142857143,
      "grad_norm": 0.042638182640075684,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8265433311462402,
      "step": 2214
    },
    {
      "epoch": 0.10552380952380952,
      "grad_norm": 0.04298174008727074,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8274474143981934,
      "step": 2216
    },
    {
      "epoch": 0.10561904761904761,
      "grad_norm": 0.04192093759775162,
      "learning_rate": 0.024000000208616257,
      "loss": 2.806565046310425,
      "step": 2218
    },
    {
      "epoch": 0.10571428571428572,
      "grad_norm": 0.0414656400680542,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8038058280944824,
      "step": 2220
    },
    {
      "epoch": 0.10580952380952381,
      "grad_norm": 0.043800484389066696,
      "learning_rate": 0.024000000208616257,
      "loss": 2.808396339416504,
      "step": 2222
    },
    {
      "epoch": 0.1059047619047619,
      "grad_norm": 0.0428471602499485,
      "learning_rate": 0.024000000208616257,
      "loss": 2.834014892578125,
      "step": 2224
    },
    {
      "epoch": 0.106,
      "grad_norm": 0.04332656040787697,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8288464546203613,
      "step": 2226
    },
    {
      "epoch": 0.10609523809523809,
      "grad_norm": 0.04396739974617958,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8604636192321777,
      "step": 2228
    },
    {
      "epoch": 0.1061904761904762,
      "grad_norm": 0.044309601187705994,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8745779991149902,
      "step": 2230
    },
    {
      "epoch": 0.10628571428571429,
      "grad_norm": 0.04606819897890091,
      "learning_rate": 0.024000000208616257,
      "loss": 2.85555362701416,
      "step": 2232
    },
    {
      "epoch": 0.10638095238095238,
      "grad_norm": 0.04263854771852493,
      "learning_rate": 0.024000000208616257,
      "loss": 2.819735050201416,
      "step": 2234
    },
    {
      "epoch": 0.10647619047619047,
      "grad_norm": 0.04349078610539436,
      "learning_rate": 0.024000000208616257,
      "loss": 2.82175874710083,
      "step": 2236
    },
    {
      "epoch": 0.10657142857142857,
      "grad_norm": 0.042073123157024384,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8130078315734863,
      "step": 2238
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 0.041954439133405685,
      "learning_rate": 0.024000000208616257,
      "loss": 2.801999807357788,
      "step": 2240
    },
    {
      "epoch": 0.10676190476190477,
      "grad_norm": 0.04304694011807442,
      "learning_rate": 0.024000000208616257,
      "loss": 2.821308135986328,
      "step": 2242
    },
    {
      "epoch": 0.10685714285714286,
      "grad_norm": 0.04589733108878136,
      "learning_rate": 0.024000000208616257,
      "loss": 2.827450752258301,
      "step": 2244
    },
    {
      "epoch": 0.10695238095238095,
      "grad_norm": 0.04315415769815445,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8696911334991455,
      "step": 2246
    },
    {
      "epoch": 0.10704761904761904,
      "grad_norm": 0.04247879236936569,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8103904724121094,
      "step": 2248
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 0.04258597642183304,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8390116691589355,
      "step": 2250
    },
    {
      "epoch": 0.10723809523809524,
      "grad_norm": 0.04168941453099251,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8837156295776367,
      "step": 2252
    },
    {
      "epoch": 0.10733333333333334,
      "grad_norm": 0.04468107596039772,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8262386322021484,
      "step": 2254
    },
    {
      "epoch": 0.10742857142857143,
      "grad_norm": 0.04520596191287041,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8208703994750977,
      "step": 2256
    },
    {
      "epoch": 0.10752380952380952,
      "grad_norm": 0.04420165345072746,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8371129035949707,
      "step": 2258
    },
    {
      "epoch": 0.10761904761904761,
      "grad_norm": 0.04187846928834915,
      "learning_rate": 0.024000000208616257,
      "loss": 2.824359178543091,
      "step": 2260
    },
    {
      "epoch": 0.10771428571428572,
      "grad_norm": 0.04211211949586868,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8429744243621826,
      "step": 2262
    },
    {
      "epoch": 0.10780952380952381,
      "grad_norm": 0.04149043187499046,
      "learning_rate": 0.024000000208616257,
      "loss": 2.860873222351074,
      "step": 2264
    },
    {
      "epoch": 0.1079047619047619,
      "grad_norm": 0.04406444728374481,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8222906589508057,
      "step": 2266
    },
    {
      "epoch": 0.108,
      "grad_norm": 0.042441558092832565,
      "learning_rate": 0.024000000208616257,
      "loss": 2.81638240814209,
      "step": 2268
    },
    {
      "epoch": 0.10809523809523809,
      "grad_norm": 0.0443294420838356,
      "learning_rate": 0.024000000208616257,
      "loss": 2.847189426422119,
      "step": 2270
    },
    {
      "epoch": 0.10819047619047618,
      "grad_norm": 0.04300334304571152,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8115720748901367,
      "step": 2272
    },
    {
      "epoch": 0.10828571428571429,
      "grad_norm": 0.04425588250160217,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8434369564056396,
      "step": 2274
    },
    {
      "epoch": 0.10838095238095238,
      "grad_norm": 0.04260528087615967,
      "learning_rate": 0.024000000208616257,
      "loss": 2.853005886077881,
      "step": 2276
    },
    {
      "epoch": 0.10847619047619048,
      "grad_norm": 0.04244031757116318,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8413069248199463,
      "step": 2278
    },
    {
      "epoch": 0.10857142857142857,
      "grad_norm": 0.04342708736658096,
      "learning_rate": 0.024000000208616257,
      "loss": 2.832235813140869,
      "step": 2280
    },
    {
      "epoch": 0.10866666666666666,
      "grad_norm": 0.04550527036190033,
      "learning_rate": 0.024000000208616257,
      "loss": 2.81189227104187,
      "step": 2282
    },
    {
      "epoch": 0.10876190476190477,
      "grad_norm": 0.04587160423398018,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8236989974975586,
      "step": 2284
    },
    {
      "epoch": 0.10885714285714286,
      "grad_norm": 0.04425467178225517,
      "learning_rate": 0.024000000208616257,
      "loss": 2.818662643432617,
      "step": 2286
    },
    {
      "epoch": 0.10895238095238095,
      "grad_norm": 0.04258762300014496,
      "learning_rate": 0.024000000208616257,
      "loss": 2.874483823776245,
      "step": 2288
    },
    {
      "epoch": 0.10904761904761905,
      "grad_norm": 0.04587321728467941,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8553757667541504,
      "step": 2290
    },
    {
      "epoch": 0.10914285714285714,
      "grad_norm": 0.0433911494910717,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8366546630859375,
      "step": 2292
    },
    {
      "epoch": 0.10923809523809523,
      "grad_norm": 0.043584879487752914,
      "learning_rate": 0.024000000208616257,
      "loss": 2.836789608001709,
      "step": 2294
    },
    {
      "epoch": 0.10933333333333334,
      "grad_norm": 0.044756993651390076,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8138184547424316,
      "step": 2296
    },
    {
      "epoch": 0.10942857142857143,
      "grad_norm": 0.053319793194532394,
      "learning_rate": 0.024000000208616257,
      "loss": 2.867032527923584,
      "step": 2298
    },
    {
      "epoch": 0.10952380952380952,
      "grad_norm": 0.04646826535463333,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8240857124328613,
      "step": 2300
    },
    {
      "epoch": 0.10961904761904762,
      "grad_norm": 0.04508837312459946,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8072800636291504,
      "step": 2302
    },
    {
      "epoch": 0.10971428571428571,
      "grad_norm": 0.04732076823711395,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8292336463928223,
      "step": 2304
    },
    {
      "epoch": 0.10980952380952382,
      "grad_norm": 0.043903470039367676,
      "learning_rate": 0.024000000208616257,
      "loss": 2.854513645172119,
      "step": 2306
    },
    {
      "epoch": 0.10990476190476191,
      "grad_norm": 0.042101193219423294,
      "learning_rate": 0.024000000208616257,
      "loss": 2.788601875305176,
      "step": 2308
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.043917782604694366,
      "learning_rate": 0.024000000208616257,
      "loss": 2.845720052719116,
      "step": 2310
    },
    {
      "epoch": 0.1100952380952381,
      "grad_norm": 0.042219050228595734,
      "learning_rate": 0.024000000208616257,
      "loss": 2.866366147994995,
      "step": 2312
    },
    {
      "epoch": 0.11019047619047619,
      "grad_norm": 0.04372352361679077,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8299593925476074,
      "step": 2314
    },
    {
      "epoch": 0.11028571428571429,
      "grad_norm": 0.044427335262298584,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8645622730255127,
      "step": 2316
    },
    {
      "epoch": 0.11038095238095239,
      "grad_norm": 0.041419245302677155,
      "learning_rate": 0.024000000208616257,
      "loss": 2.830963134765625,
      "step": 2318
    },
    {
      "epoch": 0.11047619047619048,
      "grad_norm": 0.04397374019026756,
      "learning_rate": 0.024000000208616257,
      "loss": 2.849337577819824,
      "step": 2320
    },
    {
      "epoch": 0.11057142857142857,
      "grad_norm": 0.04290112480521202,
      "learning_rate": 0.024000000208616257,
      "loss": 2.805194854736328,
      "step": 2322
    },
    {
      "epoch": 0.11066666666666666,
      "grad_norm": 0.04386370629072189,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8648576736450195,
      "step": 2324
    },
    {
      "epoch": 0.11076190476190476,
      "grad_norm": 0.0430656298995018,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8540968894958496,
      "step": 2326
    },
    {
      "epoch": 0.11085714285714286,
      "grad_norm": 0.04284806549549103,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8408892154693604,
      "step": 2328
    },
    {
      "epoch": 0.11095238095238096,
      "grad_norm": 0.043848469853401184,
      "learning_rate": 0.024000000208616257,
      "loss": 2.847029209136963,
      "step": 2330
    },
    {
      "epoch": 0.11104761904761905,
      "grad_norm": 0.04454044625163078,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8233251571655273,
      "step": 2332
    },
    {
      "epoch": 0.11114285714285714,
      "grad_norm": 0.04285981133580208,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7999281883239746,
      "step": 2334
    },
    {
      "epoch": 0.11123809523809523,
      "grad_norm": 0.04382999986410141,
      "learning_rate": 0.024000000208616257,
      "loss": 2.864316701889038,
      "step": 2336
    },
    {
      "epoch": 0.11133333333333334,
      "grad_norm": 0.04272577166557312,
      "learning_rate": 0.024000000208616257,
      "loss": 2.853971481323242,
      "step": 2338
    },
    {
      "epoch": 0.11142857142857143,
      "grad_norm": 0.041428983211517334,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8278865814208984,
      "step": 2340
    },
    {
      "epoch": 0.11152380952380953,
      "grad_norm": 0.0410514697432518,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8294973373413086,
      "step": 2342
    },
    {
      "epoch": 0.11161904761904762,
      "grad_norm": 0.04077216982841492,
      "learning_rate": 0.024000000208616257,
      "loss": 2.831887722015381,
      "step": 2344
    },
    {
      "epoch": 0.11171428571428571,
      "grad_norm": 0.04132991284132004,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8307251930236816,
      "step": 2346
    },
    {
      "epoch": 0.1118095238095238,
      "grad_norm": 0.042733702808618546,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8326148986816406,
      "step": 2348
    },
    {
      "epoch": 0.11190476190476191,
      "grad_norm": 0.04239274933934212,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8187685012817383,
      "step": 2350
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.04121135547757149,
      "learning_rate": 0.024000000208616257,
      "loss": 2.842602252960205,
      "step": 2352
    },
    {
      "epoch": 0.1120952380952381,
      "grad_norm": 0.041925784200429916,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8838212490081787,
      "step": 2354
    },
    {
      "epoch": 0.11219047619047619,
      "grad_norm": 0.0406259223818779,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8404972553253174,
      "step": 2356
    },
    {
      "epoch": 0.11228571428571428,
      "grad_norm": 0.042709410190582275,
      "learning_rate": 0.024000000208616257,
      "loss": 2.829044818878174,
      "step": 2358
    },
    {
      "epoch": 0.11238095238095239,
      "grad_norm": 0.045218441635370255,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8299612998962402,
      "step": 2360
    },
    {
      "epoch": 0.11247619047619048,
      "grad_norm": 0.046516768634319305,
      "learning_rate": 0.024000000208616257,
      "loss": 2.838028907775879,
      "step": 2362
    },
    {
      "epoch": 0.11257142857142857,
      "grad_norm": 0.044673603028059006,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8082804679870605,
      "step": 2364
    },
    {
      "epoch": 0.11266666666666666,
      "grad_norm": 0.04215879738330841,
      "learning_rate": 0.024000000208616257,
      "loss": 2.861239433288574,
      "step": 2366
    },
    {
      "epoch": 0.11276190476190476,
      "grad_norm": 0.04143514111638069,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8396496772766113,
      "step": 2368
    },
    {
      "epoch": 0.11285714285714285,
      "grad_norm": 0.0444062314927578,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8599491119384766,
      "step": 2370
    },
    {
      "epoch": 0.11295238095238096,
      "grad_norm": 0.0436428003013134,
      "learning_rate": 0.024000000208616257,
      "loss": 2.797435998916626,
      "step": 2372
    },
    {
      "epoch": 0.11304761904761905,
      "grad_norm": 0.0428193137049675,
      "learning_rate": 0.024000000208616257,
      "loss": 2.868582010269165,
      "step": 2374
    },
    {
      "epoch": 0.11314285714285714,
      "grad_norm": 0.04292425885796547,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8202855587005615,
      "step": 2376
    },
    {
      "epoch": 0.11323809523809523,
      "grad_norm": 0.044168662279844284,
      "learning_rate": 0.024000000208616257,
      "loss": 2.811751365661621,
      "step": 2378
    },
    {
      "epoch": 0.11333333333333333,
      "grad_norm": 0.04495973140001297,
      "learning_rate": 0.024000000208616257,
      "loss": 2.848576068878174,
      "step": 2380
    },
    {
      "epoch": 0.11342857142857143,
      "grad_norm": 0.04679540917277336,
      "learning_rate": 0.024000000208616257,
      "loss": 2.863935947418213,
      "step": 2382
    },
    {
      "epoch": 0.11352380952380953,
      "grad_norm": 0.04426640272140503,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8212890625,
      "step": 2384
    },
    {
      "epoch": 0.11361904761904762,
      "grad_norm": 0.043218426406383514,
      "learning_rate": 0.024000000208616257,
      "loss": 2.833470582962036,
      "step": 2386
    },
    {
      "epoch": 0.11371428571428571,
      "grad_norm": 0.04432336613535881,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8554797172546387,
      "step": 2388
    },
    {
      "epoch": 0.1138095238095238,
      "grad_norm": 0.042223673313856125,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8440189361572266,
      "step": 2390
    },
    {
      "epoch": 0.11390476190476191,
      "grad_norm": 0.04422670975327492,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8496994972229004,
      "step": 2392
    },
    {
      "epoch": 0.114,
      "grad_norm": 0.040997084230184555,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8587260246276855,
      "step": 2394
    },
    {
      "epoch": 0.1140952380952381,
      "grad_norm": 0.04322665557265282,
      "learning_rate": 0.024000000208616257,
      "loss": 2.840376377105713,
      "step": 2396
    },
    {
      "epoch": 0.11419047619047619,
      "grad_norm": 0.04394073411822319,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8482980728149414,
      "step": 2398
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.040876634418964386,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8109383583068848,
      "step": 2400
    },
    {
      "epoch": 0.11438095238095237,
      "grad_norm": 0.043771810829639435,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8027424812316895,
      "step": 2402
    },
    {
      "epoch": 0.11447619047619048,
      "grad_norm": 0.043264951556921005,
      "learning_rate": 0.024000000208616257,
      "loss": 2.817607879638672,
      "step": 2404
    },
    {
      "epoch": 0.11457142857142857,
      "grad_norm": 0.04173532500863075,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8312740325927734,
      "step": 2406
    },
    {
      "epoch": 0.11466666666666667,
      "grad_norm": 0.04291177913546562,
      "learning_rate": 0.024000000208616257,
      "loss": 2.816741943359375,
      "step": 2408
    },
    {
      "epoch": 0.11476190476190476,
      "grad_norm": 0.04172365739941597,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8402504920959473,
      "step": 2410
    },
    {
      "epoch": 0.11485714285714285,
      "grad_norm": 0.04213319718837738,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8233413696289062,
      "step": 2412
    },
    {
      "epoch": 0.11495238095238096,
      "grad_norm": 0.044634535908699036,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8353424072265625,
      "step": 2414
    },
    {
      "epoch": 0.11504761904761905,
      "grad_norm": 0.04112102463841438,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8723654747009277,
      "step": 2416
    },
    {
      "epoch": 0.11514285714285714,
      "grad_norm": 0.04054361209273338,
      "learning_rate": 0.024000000208616257,
      "loss": 2.793976306915283,
      "step": 2418
    },
    {
      "epoch": 0.11523809523809524,
      "grad_norm": 0.042160842567682266,
      "learning_rate": 0.024000000208616257,
      "loss": 2.843012571334839,
      "step": 2420
    },
    {
      "epoch": 0.11533333333333333,
      "grad_norm": 0.04311958700418472,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8622488975524902,
      "step": 2422
    },
    {
      "epoch": 0.11542857142857142,
      "grad_norm": 0.0469115674495697,
      "learning_rate": 0.024000000208616257,
      "loss": 2.834247350692749,
      "step": 2424
    },
    {
      "epoch": 0.11552380952380953,
      "grad_norm": 0.043748702853918076,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8269705772399902,
      "step": 2426
    },
    {
      "epoch": 0.11561904761904762,
      "grad_norm": 0.042724478989839554,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8371024131774902,
      "step": 2428
    },
    {
      "epoch": 0.11571428571428571,
      "grad_norm": 0.04362207278609276,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8114664554595947,
      "step": 2430
    },
    {
      "epoch": 0.1158095238095238,
      "grad_norm": 0.04225478321313858,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8217904567718506,
      "step": 2432
    },
    {
      "epoch": 0.1159047619047619,
      "grad_norm": 0.04482317715883255,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7999391555786133,
      "step": 2434
    },
    {
      "epoch": 0.116,
      "grad_norm": 0.043676137924194336,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8291964530944824,
      "step": 2436
    },
    {
      "epoch": 0.1160952380952381,
      "grad_norm": 0.042820390313863754,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8213815689086914,
      "step": 2438
    },
    {
      "epoch": 0.11619047619047619,
      "grad_norm": 0.04170040413737297,
      "learning_rate": 0.024000000208616257,
      "loss": 2.857628345489502,
      "step": 2440
    },
    {
      "epoch": 0.11628571428571428,
      "grad_norm": 0.0409671850502491,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8355746269226074,
      "step": 2442
    },
    {
      "epoch": 0.11638095238095238,
      "grad_norm": 0.042207904160022736,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8353703022003174,
      "step": 2444
    },
    {
      "epoch": 0.11647619047619047,
      "grad_norm": 0.042373593896627426,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8219804763793945,
      "step": 2446
    },
    {
      "epoch": 0.11657142857142858,
      "grad_norm": 0.04138309881091118,
      "learning_rate": 0.024000000208616257,
      "loss": 2.855465888977051,
      "step": 2448
    },
    {
      "epoch": 0.11666666666666667,
      "grad_norm": 0.042857978492975235,
      "learning_rate": 0.024000000208616257,
      "loss": 2.846458911895752,
      "step": 2450
    },
    {
      "epoch": 0.11676190476190476,
      "grad_norm": 0.04180941358208656,
      "learning_rate": 0.024000000208616257,
      "loss": 2.831083059310913,
      "step": 2452
    },
    {
      "epoch": 0.11685714285714285,
      "grad_norm": 0.041938502341508865,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8106977939605713,
      "step": 2454
    },
    {
      "epoch": 0.11695238095238095,
      "grad_norm": 0.04620752111077309,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8303287029266357,
      "step": 2456
    },
    {
      "epoch": 0.11704761904761905,
      "grad_norm": 0.04594069719314575,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8401880264282227,
      "step": 2458
    },
    {
      "epoch": 0.11714285714285715,
      "grad_norm": 0.04343053698539734,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8270816802978516,
      "step": 2460
    },
    {
      "epoch": 0.11723809523809524,
      "grad_norm": 0.04365908354520798,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8401761054992676,
      "step": 2462
    },
    {
      "epoch": 0.11733333333333333,
      "grad_norm": 0.0409209243953228,
      "learning_rate": 0.024000000208616257,
      "loss": 2.824024200439453,
      "step": 2464
    },
    {
      "epoch": 0.11742857142857142,
      "grad_norm": 0.0426412895321846,
      "learning_rate": 0.024000000208616257,
      "loss": 2.83526611328125,
      "step": 2466
    },
    {
      "epoch": 0.11752380952380953,
      "grad_norm": 0.041445523500442505,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8397469520568848,
      "step": 2468
    },
    {
      "epoch": 0.11761904761904762,
      "grad_norm": 0.04184895008802414,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8130381107330322,
      "step": 2470
    },
    {
      "epoch": 0.11771428571428572,
      "grad_norm": 0.0399913527071476,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8357410430908203,
      "step": 2472
    },
    {
      "epoch": 0.11780952380952381,
      "grad_norm": 0.040286775678396225,
      "learning_rate": 0.024000000208616257,
      "loss": 2.872114896774292,
      "step": 2474
    },
    {
      "epoch": 0.1179047619047619,
      "grad_norm": 0.04195312783122063,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8432769775390625,
      "step": 2476
    },
    {
      "epoch": 0.118,
      "grad_norm": 0.0407257042825222,
      "learning_rate": 0.024000000208616257,
      "loss": 2.821531295776367,
      "step": 2478
    },
    {
      "epoch": 0.1180952380952381,
      "grad_norm": 0.043279532343149185,
      "learning_rate": 0.024000000208616257,
      "loss": 2.832317352294922,
      "step": 2480
    },
    {
      "epoch": 0.11819047619047619,
      "grad_norm": 0.04548255726695061,
      "learning_rate": 0.024000000208616257,
      "loss": 2.841709613800049,
      "step": 2482
    },
    {
      "epoch": 0.11828571428571429,
      "grad_norm": 0.04240364208817482,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8658716678619385,
      "step": 2484
    },
    {
      "epoch": 0.11838095238095238,
      "grad_norm": 0.04236829653382301,
      "learning_rate": 0.024000000208616257,
      "loss": 2.850191116333008,
      "step": 2486
    },
    {
      "epoch": 0.11847619047619047,
      "grad_norm": 0.04410003125667572,
      "learning_rate": 0.024000000208616257,
      "loss": 2.831181764602661,
      "step": 2488
    },
    {
      "epoch": 0.11857142857142858,
      "grad_norm": 0.04144475236535072,
      "learning_rate": 0.024000000208616257,
      "loss": 2.818572521209717,
      "step": 2490
    },
    {
      "epoch": 0.11866666666666667,
      "grad_norm": 0.04223351553082466,
      "learning_rate": 0.024000000208616257,
      "loss": 2.822672128677368,
      "step": 2492
    },
    {
      "epoch": 0.11876190476190476,
      "grad_norm": 0.04332510009407997,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8019838333129883,
      "step": 2494
    },
    {
      "epoch": 0.11885714285714286,
      "grad_norm": 0.04312538355588913,
      "learning_rate": 0.024000000208616257,
      "loss": 2.812119960784912,
      "step": 2496
    },
    {
      "epoch": 0.11895238095238095,
      "grad_norm": 0.042870163917541504,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8283934593200684,
      "step": 2498
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 0.04303615912795067,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8259434700012207,
      "step": 2500
    },
    {
      "epoch": 0.11914285714285715,
      "grad_norm": 0.04287268593907356,
      "learning_rate": 0.024000000208616257,
      "loss": 2.791656970977783,
      "step": 2502
    },
    {
      "epoch": 0.11923809523809524,
      "grad_norm": 0.044576600193977356,
      "learning_rate": 0.024000000208616257,
      "loss": 2.809335708618164,
      "step": 2504
    },
    {
      "epoch": 0.11933333333333333,
      "grad_norm": 0.04174851253628731,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8525495529174805,
      "step": 2506
    },
    {
      "epoch": 0.11942857142857143,
      "grad_norm": 0.043079923838377,
      "learning_rate": 0.024000000208616257,
      "loss": 2.826742172241211,
      "step": 2508
    },
    {
      "epoch": 0.11952380952380952,
      "grad_norm": 0.04116980358958244,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8250632286071777,
      "step": 2510
    },
    {
      "epoch": 0.11961904761904762,
      "grad_norm": 0.04109499230980873,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8161730766296387,
      "step": 2512
    },
    {
      "epoch": 0.11971428571428572,
      "grad_norm": 0.04191192239522934,
      "learning_rate": 0.024000000208616257,
      "loss": 2.824246883392334,
      "step": 2514
    },
    {
      "epoch": 0.11980952380952381,
      "grad_norm": 0.04260021075606346,
      "learning_rate": 0.024000000208616257,
      "loss": 2.805546283721924,
      "step": 2516
    },
    {
      "epoch": 0.1199047619047619,
      "grad_norm": 0.039424169808626175,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8421409130096436,
      "step": 2518
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.03969598561525345,
      "learning_rate": 0.024000000208616257,
      "loss": 2.837010383605957,
      "step": 2520
    },
    {
      "epoch": 0.1200952380952381,
      "grad_norm": 0.042548663914203644,
      "learning_rate": 0.024000000208616257,
      "loss": 2.797226905822754,
      "step": 2522
    },
    {
      "epoch": 0.1201904761904762,
      "grad_norm": 0.04068288207054138,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8313212394714355,
      "step": 2524
    },
    {
      "epoch": 0.12028571428571429,
      "grad_norm": 0.040572330355644226,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8244404792785645,
      "step": 2526
    },
    {
      "epoch": 0.12038095238095238,
      "grad_norm": 0.04358648136258125,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8327105045318604,
      "step": 2528
    },
    {
      "epoch": 0.12047619047619047,
      "grad_norm": 0.040242988616228104,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8164312839508057,
      "step": 2530
    },
    {
      "epoch": 0.12057142857142857,
      "grad_norm": 0.041757237166166306,
      "learning_rate": 0.024000000208616257,
      "loss": 2.839569330215454,
      "step": 2532
    },
    {
      "epoch": 0.12066666666666667,
      "grad_norm": 0.04144726321101189,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8269295692443848,
      "step": 2534
    },
    {
      "epoch": 0.12076190476190476,
      "grad_norm": 0.041154976934194565,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7893707752227783,
      "step": 2536
    },
    {
      "epoch": 0.12085714285714286,
      "grad_norm": 0.041517194360494614,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8037023544311523,
      "step": 2538
    },
    {
      "epoch": 0.12095238095238095,
      "grad_norm": 0.041037652641534805,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7912702560424805,
      "step": 2540
    },
    {
      "epoch": 0.12104761904761904,
      "grad_norm": 0.04032597318291664,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8323111534118652,
      "step": 2542
    },
    {
      "epoch": 0.12114285714285715,
      "grad_norm": 0.04222707450389862,
      "learning_rate": 0.024000000208616257,
      "loss": 2.840578317642212,
      "step": 2544
    },
    {
      "epoch": 0.12123809523809524,
      "grad_norm": 0.04219461604952812,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8192298412323,
      "step": 2546
    },
    {
      "epoch": 0.12133333333333333,
      "grad_norm": 0.04300006479024887,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8006722927093506,
      "step": 2548
    },
    {
      "epoch": 0.12142857142857143,
      "grad_norm": 0.040970053523778915,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8169565200805664,
      "step": 2550
    },
    {
      "epoch": 0.12152380952380952,
      "grad_norm": 0.04170817509293556,
      "learning_rate": 0.024000000208616257,
      "loss": 2.795762062072754,
      "step": 2552
    },
    {
      "epoch": 0.12161904761904761,
      "grad_norm": 0.039905671030282974,
      "learning_rate": 0.024000000208616257,
      "loss": 2.812732458114624,
      "step": 2554
    },
    {
      "epoch": 0.12171428571428572,
      "grad_norm": 0.04187404736876488,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8021366596221924,
      "step": 2556
    },
    {
      "epoch": 0.12180952380952381,
      "grad_norm": 0.041201017796993256,
      "learning_rate": 0.024000000208616257,
      "loss": 2.834861993789673,
      "step": 2558
    },
    {
      "epoch": 0.1219047619047619,
      "grad_norm": 0.04161055386066437,
      "learning_rate": 0.024000000208616257,
      "loss": 2.827259063720703,
      "step": 2560
    },
    {
      "epoch": 0.122,
      "grad_norm": 0.04024839773774147,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7820394039154053,
      "step": 2562
    },
    {
      "epoch": 0.12209523809523809,
      "grad_norm": 0.042443837970495224,
      "learning_rate": 0.024000000208616257,
      "loss": 2.809875965118408,
      "step": 2564
    },
    {
      "epoch": 0.1221904761904762,
      "grad_norm": 0.04276329278945923,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7907843589782715,
      "step": 2566
    },
    {
      "epoch": 0.12228571428571429,
      "grad_norm": 0.041821978986263275,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8167150020599365,
      "step": 2568
    },
    {
      "epoch": 0.12238095238095238,
      "grad_norm": 0.04059464484453201,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8164660930633545,
      "step": 2570
    },
    {
      "epoch": 0.12247619047619047,
      "grad_norm": 0.042192861437797546,
      "learning_rate": 0.024000000208616257,
      "loss": 2.813122272491455,
      "step": 2572
    },
    {
      "epoch": 0.12257142857142857,
      "grad_norm": 0.04232925549149513,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7901129722595215,
      "step": 2574
    },
    {
      "epoch": 0.12266666666666666,
      "grad_norm": 0.04282986372709274,
      "learning_rate": 0.024000000208616257,
      "loss": 2.780177116394043,
      "step": 2576
    },
    {
      "epoch": 0.12276190476190477,
      "grad_norm": 0.03994080424308777,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7782464027404785,
      "step": 2578
    },
    {
      "epoch": 0.12285714285714286,
      "grad_norm": 0.040026143193244934,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7961816787719727,
      "step": 2580
    },
    {
      "epoch": 0.12295238095238095,
      "grad_norm": 0.04466131329536438,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7859439849853516,
      "step": 2582
    },
    {
      "epoch": 0.12304761904761904,
      "grad_norm": 0.04065300151705742,
      "learning_rate": 0.024000000208616257,
      "loss": 2.821704149246216,
      "step": 2584
    },
    {
      "epoch": 0.12314285714285714,
      "grad_norm": 0.041388481855392456,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8279848098754883,
      "step": 2586
    },
    {
      "epoch": 0.12323809523809524,
      "grad_norm": 0.03929205983877182,
      "learning_rate": 0.024000000208616257,
      "loss": 2.77022123336792,
      "step": 2588
    },
    {
      "epoch": 0.12333333333333334,
      "grad_norm": 0.041244663298130035,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7936577796936035,
      "step": 2590
    },
    {
      "epoch": 0.12342857142857143,
      "grad_norm": 0.041991300880908966,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7876901626586914,
      "step": 2592
    },
    {
      "epoch": 0.12352380952380952,
      "grad_norm": 0.041687339544296265,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7761549949645996,
      "step": 2594
    },
    {
      "epoch": 0.12361904761904761,
      "grad_norm": 0.04078041762113571,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7935638427734375,
      "step": 2596
    },
    {
      "epoch": 0.12371428571428572,
      "grad_norm": 0.041737768799066544,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7783260345458984,
      "step": 2598
    },
    {
      "epoch": 0.12380952380952381,
      "grad_norm": 0.04125306010246277,
      "learning_rate": 0.024000000208616257,
      "loss": 2.76729154586792,
      "step": 2600
    },
    {
      "epoch": 0.1239047619047619,
      "grad_norm": 0.04213384911417961,
      "learning_rate": 0.024000000208616257,
      "loss": 2.78336238861084,
      "step": 2602
    },
    {
      "epoch": 0.124,
      "grad_norm": 0.042800646275281906,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8083114624023438,
      "step": 2604
    },
    {
      "epoch": 0.12409523809523809,
      "grad_norm": 0.03879621624946594,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7956390380859375,
      "step": 2606
    },
    {
      "epoch": 0.12419047619047618,
      "grad_norm": 0.03873562812805176,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7316794395446777,
      "step": 2608
    },
    {
      "epoch": 0.12428571428571429,
      "grad_norm": 0.0406021811068058,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8145947456359863,
      "step": 2610
    },
    {
      "epoch": 0.12438095238095238,
      "grad_norm": 0.040496669709682465,
      "learning_rate": 0.024000000208616257,
      "loss": 2.78377628326416,
      "step": 2612
    },
    {
      "epoch": 0.12447619047619048,
      "grad_norm": 0.041629184037446976,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7749762535095215,
      "step": 2614
    },
    {
      "epoch": 0.12457142857142857,
      "grad_norm": 0.04244022071361542,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8054652214050293,
      "step": 2616
    },
    {
      "epoch": 0.12466666666666666,
      "grad_norm": 0.04082432761788368,
      "learning_rate": 0.024000000208616257,
      "loss": 2.776865005493164,
      "step": 2618
    },
    {
      "epoch": 0.12476190476190477,
      "grad_norm": 0.04231296852231026,
      "learning_rate": 0.024000000208616257,
      "loss": 2.777987003326416,
      "step": 2620
    },
    {
      "epoch": 0.12485714285714286,
      "grad_norm": 0.041969235986471176,
      "learning_rate": 0.024000000208616257,
      "loss": 2.788653612136841,
      "step": 2622
    },
    {
      "epoch": 0.12495238095238095,
      "grad_norm": 0.04375968873500824,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7525391578674316,
      "step": 2624
    },
    {
      "epoch": 0.12504761904761905,
      "grad_norm": 0.04146707430481911,
      "learning_rate": 0.024000000208616257,
      "loss": 2.781435251235962,
      "step": 2626
    },
    {
      "epoch": 0.12514285714285714,
      "grad_norm": 0.04309874027967453,
      "learning_rate": 0.024000000208616257,
      "loss": 2.775402307510376,
      "step": 2628
    },
    {
      "epoch": 0.12523809523809523,
      "grad_norm": 0.04354269802570343,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7576117515563965,
      "step": 2630
    },
    {
      "epoch": 0.12533333333333332,
      "grad_norm": 0.04040273651480675,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7722115516662598,
      "step": 2632
    },
    {
      "epoch": 0.12542857142857142,
      "grad_norm": 0.04038441553711891,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7637338638305664,
      "step": 2634
    },
    {
      "epoch": 0.12552380952380954,
      "grad_norm": 0.041502632200717926,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7595763206481934,
      "step": 2636
    },
    {
      "epoch": 0.12561904761904763,
      "grad_norm": 0.04005318135023117,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7612314224243164,
      "step": 2638
    },
    {
      "epoch": 0.12571428571428572,
      "grad_norm": 0.039453305304050446,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7850496768951416,
      "step": 2640
    },
    {
      "epoch": 0.12580952380952382,
      "grad_norm": 0.038929879665374756,
      "learning_rate": 0.024000000208616257,
      "loss": 2.764094352722168,
      "step": 2642
    },
    {
      "epoch": 0.1259047619047619,
      "grad_norm": 0.04150986298918724,
      "learning_rate": 0.024000000208616257,
      "loss": 2.782787561416626,
      "step": 2644
    },
    {
      "epoch": 0.126,
      "grad_norm": 0.041197072714567184,
      "learning_rate": 0.024000000208616257,
      "loss": 2.784712314605713,
      "step": 2646
    },
    {
      "epoch": 0.1260952380952381,
      "grad_norm": 0.04141385853290558,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7543816566467285,
      "step": 2648
    },
    {
      "epoch": 0.1261904761904762,
      "grad_norm": 0.039842285215854645,
      "learning_rate": 0.024000000208616257,
      "loss": 2.731278419494629,
      "step": 2650
    },
    {
      "epoch": 0.12628571428571428,
      "grad_norm": 0.04048708826303482,
      "learning_rate": 0.024000000208616257,
      "loss": 2.766152858734131,
      "step": 2652
    },
    {
      "epoch": 0.12638095238095237,
      "grad_norm": 0.041250403970479965,
      "learning_rate": 0.024000000208616257,
      "loss": 2.781827926635742,
      "step": 2654
    },
    {
      "epoch": 0.12647619047619046,
      "grad_norm": 0.042609550058841705,
      "learning_rate": 0.024000000208616257,
      "loss": 2.741605043411255,
      "step": 2656
    },
    {
      "epoch": 0.12657142857142858,
      "grad_norm": 0.0402979776263237,
      "learning_rate": 0.024000000208616257,
      "loss": 2.748196601867676,
      "step": 2658
    },
    {
      "epoch": 0.12666666666666668,
      "grad_norm": 0.04009581729769707,
      "learning_rate": 0.024000000208616257,
      "loss": 2.760648250579834,
      "step": 2660
    },
    {
      "epoch": 0.12676190476190477,
      "grad_norm": 0.043276235461235046,
      "learning_rate": 0.024000000208616257,
      "loss": 2.757265567779541,
      "step": 2662
    },
    {
      "epoch": 0.12685714285714286,
      "grad_norm": 0.04315818473696709,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7829556465148926,
      "step": 2664
    },
    {
      "epoch": 0.12695238095238096,
      "grad_norm": 0.04265585541725159,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7123332023620605,
      "step": 2666
    },
    {
      "epoch": 0.12704761904761905,
      "grad_norm": 0.040915347635746,
      "learning_rate": 0.024000000208616257,
      "loss": 2.8020167350769043,
      "step": 2668
    },
    {
      "epoch": 0.12714285714285714,
      "grad_norm": 0.041975103318691254,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7441067695617676,
      "step": 2670
    },
    {
      "epoch": 0.12723809523809523,
      "grad_norm": 0.03998507186770439,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7499043941497803,
      "step": 2672
    },
    {
      "epoch": 0.12733333333333333,
      "grad_norm": 0.041279714554548264,
      "learning_rate": 0.024000000208616257,
      "loss": 2.751216411590576,
      "step": 2674
    },
    {
      "epoch": 0.12742857142857142,
      "grad_norm": 0.0403459332883358,
      "learning_rate": 0.024000000208616257,
      "loss": 2.767371654510498,
      "step": 2676
    },
    {
      "epoch": 0.1275238095238095,
      "grad_norm": 0.042274292558431625,
      "learning_rate": 0.024000000208616257,
      "loss": 2.769853115081787,
      "step": 2678
    },
    {
      "epoch": 0.12761904761904763,
      "grad_norm": 0.04127549007534981,
      "learning_rate": 0.024000000208616257,
      "loss": 2.754101514816284,
      "step": 2680
    },
    {
      "epoch": 0.12771428571428572,
      "grad_norm": 0.04110479727387428,
      "learning_rate": 0.024000000208616257,
      "loss": 2.741021156311035,
      "step": 2682
    },
    {
      "epoch": 0.12780952380952382,
      "grad_norm": 0.0406893752515316,
      "learning_rate": 0.024000000208616257,
      "loss": 2.746716260910034,
      "step": 2684
    },
    {
      "epoch": 0.1279047619047619,
      "grad_norm": 0.04102560132741928,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7289562225341797,
      "step": 2686
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.04158696159720421,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7459311485290527,
      "step": 2688
    },
    {
      "epoch": 0.1280952380952381,
      "grad_norm": 0.042834073305130005,
      "learning_rate": 0.024000000208616257,
      "loss": 2.763381004333496,
      "step": 2690
    },
    {
      "epoch": 0.1281904761904762,
      "grad_norm": 0.041532251983881,
      "learning_rate": 0.024000000208616257,
      "loss": 2.751598834991455,
      "step": 2692
    },
    {
      "epoch": 0.12828571428571428,
      "grad_norm": 0.04195414483547211,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7412872314453125,
      "step": 2694
    },
    {
      "epoch": 0.12838095238095237,
      "grad_norm": 0.039019301533699036,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7190961837768555,
      "step": 2696
    },
    {
      "epoch": 0.12847619047619047,
      "grad_norm": 0.03896051272749901,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7399709224700928,
      "step": 2698
    },
    {
      "epoch": 0.12857142857142856,
      "grad_norm": 0.03877197206020355,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7395057678222656,
      "step": 2700
    },
    {
      "epoch": 0.12866666666666668,
      "grad_norm": 0.03895197808742523,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7800097465515137,
      "step": 2702
    },
    {
      "epoch": 0.12876190476190477,
      "grad_norm": 0.04356874153017998,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7174572944641113,
      "step": 2704
    },
    {
      "epoch": 0.12885714285714286,
      "grad_norm": 0.04686201363801956,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7435009479522705,
      "step": 2706
    },
    {
      "epoch": 0.12895238095238096,
      "grad_norm": 0.04456666484475136,
      "learning_rate": 0.024000000208616257,
      "loss": 2.704989433288574,
      "step": 2708
    },
    {
      "epoch": 0.12904761904761905,
      "grad_norm": 0.04123445600271225,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7305989265441895,
      "step": 2710
    },
    {
      "epoch": 0.12914285714285714,
      "grad_norm": 0.04179234802722931,
      "learning_rate": 0.024000000208616257,
      "loss": 2.701507568359375,
      "step": 2712
    },
    {
      "epoch": 0.12923809523809524,
      "grad_norm": 0.046446118503808975,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7445578575134277,
      "step": 2714
    },
    {
      "epoch": 0.12933333333333333,
      "grad_norm": 0.04205678030848503,
      "learning_rate": 0.024000000208616257,
      "loss": 2.752220630645752,
      "step": 2716
    },
    {
      "epoch": 0.12942857142857142,
      "grad_norm": 0.043627865612506866,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7344448566436768,
      "step": 2718
    },
    {
      "epoch": 0.1295238095238095,
      "grad_norm": 0.04053850099444389,
      "learning_rate": 0.024000000208616257,
      "loss": 2.705702304840088,
      "step": 2720
    },
    {
      "epoch": 0.1296190476190476,
      "grad_norm": 0.044023171067237854,
      "learning_rate": 0.024000000208616257,
      "loss": 2.684936046600342,
      "step": 2722
    },
    {
      "epoch": 0.12971428571428573,
      "grad_norm": 0.044807326048612595,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6965909004211426,
      "step": 2724
    },
    {
      "epoch": 0.12980952380952382,
      "grad_norm": 0.040259864181280136,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7287659645080566,
      "step": 2726
    },
    {
      "epoch": 0.1299047619047619,
      "grad_norm": 0.043028708547353745,
      "learning_rate": 0.024000000208616257,
      "loss": 2.721649408340454,
      "step": 2728
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.04136021062731743,
      "learning_rate": 0.024000000208616257,
      "loss": 2.750351905822754,
      "step": 2730
    },
    {
      "epoch": 0.1300952380952381,
      "grad_norm": 0.04291125014424324,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7114293575286865,
      "step": 2732
    },
    {
      "epoch": 0.1301904761904762,
      "grad_norm": 0.04283392056822777,
      "learning_rate": 0.024000000208616257,
      "loss": 2.729598045349121,
      "step": 2734
    },
    {
      "epoch": 0.13028571428571428,
      "grad_norm": 0.0435488261282444,
      "learning_rate": 0.024000000208616257,
      "loss": 2.727576732635498,
      "step": 2736
    },
    {
      "epoch": 0.13038095238095238,
      "grad_norm": 0.04185225069522858,
      "learning_rate": 0.024000000208616257,
      "loss": 2.706106185913086,
      "step": 2738
    },
    {
      "epoch": 0.13047619047619047,
      "grad_norm": 0.04038235917687416,
      "learning_rate": 0.024000000208616257,
      "loss": 2.700671672821045,
      "step": 2740
    },
    {
      "epoch": 0.13057142857142856,
      "grad_norm": 0.040698155760765076,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7165868282318115,
      "step": 2742
    },
    {
      "epoch": 0.13066666666666665,
      "grad_norm": 0.04006931558251381,
      "learning_rate": 0.024000000208616257,
      "loss": 2.72568416595459,
      "step": 2744
    },
    {
      "epoch": 0.13076190476190477,
      "grad_norm": 0.040233563631772995,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7146434783935547,
      "step": 2746
    },
    {
      "epoch": 0.13085714285714287,
      "grad_norm": 0.038959018886089325,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7292914390563965,
      "step": 2748
    },
    {
      "epoch": 0.13095238095238096,
      "grad_norm": 0.03924540802836418,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7347793579101562,
      "step": 2750
    },
    {
      "epoch": 0.13104761904761905,
      "grad_norm": 0.04025218263268471,
      "learning_rate": 0.024000000208616257,
      "loss": 2.740389585494995,
      "step": 2752
    },
    {
      "epoch": 0.13114285714285714,
      "grad_norm": 0.0399710014462471,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7149949073791504,
      "step": 2754
    },
    {
      "epoch": 0.13123809523809524,
      "grad_norm": 0.04009760543704033,
      "learning_rate": 0.024000000208616257,
      "loss": 2.700632095336914,
      "step": 2756
    },
    {
      "epoch": 0.13133333333333333,
      "grad_norm": 0.041127242147922516,
      "learning_rate": 0.024000000208616257,
      "loss": 2.711601734161377,
      "step": 2758
    },
    {
      "epoch": 0.13142857142857142,
      "grad_norm": 0.04018864408135414,
      "learning_rate": 0.024000000208616257,
      "loss": 2.711930751800537,
      "step": 2760
    },
    {
      "epoch": 0.13152380952380952,
      "grad_norm": 0.0410848967730999,
      "learning_rate": 0.024000000208616257,
      "loss": 2.701314926147461,
      "step": 2762
    },
    {
      "epoch": 0.1316190476190476,
      "grad_norm": 0.04037822410464287,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7267751693725586,
      "step": 2764
    },
    {
      "epoch": 0.1317142857142857,
      "grad_norm": 0.043315108865499496,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7330355644226074,
      "step": 2766
    },
    {
      "epoch": 0.13180952380952382,
      "grad_norm": 0.04093198478221893,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7466533184051514,
      "step": 2768
    },
    {
      "epoch": 0.1319047619047619,
      "grad_norm": 0.04278977960348129,
      "learning_rate": 0.024000000208616257,
      "loss": 2.681534767150879,
      "step": 2770
    },
    {
      "epoch": 0.132,
      "grad_norm": 0.041052766144275665,
      "learning_rate": 0.024000000208616257,
      "loss": 2.683458089828491,
      "step": 2772
    },
    {
      "epoch": 0.1320952380952381,
      "grad_norm": 0.04038380831480026,
      "learning_rate": 0.024000000208616257,
      "loss": 2.694136619567871,
      "step": 2774
    },
    {
      "epoch": 0.1321904761904762,
      "grad_norm": 0.042045921087265015,
      "learning_rate": 0.024000000208616257,
      "loss": 2.678288698196411,
      "step": 2776
    },
    {
      "epoch": 0.13228571428571428,
      "grad_norm": 0.038873106241226196,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6905155181884766,
      "step": 2778
    },
    {
      "epoch": 0.13238095238095238,
      "grad_norm": 0.041868433356285095,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6793131828308105,
      "step": 2780
    },
    {
      "epoch": 0.13247619047619047,
      "grad_norm": 0.045103613287210464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6974549293518066,
      "step": 2782
    },
    {
      "epoch": 0.13257142857142856,
      "grad_norm": 0.04083101451396942,
      "learning_rate": 0.024000000208616257,
      "loss": 2.681457042694092,
      "step": 2784
    },
    {
      "epoch": 0.13266666666666665,
      "grad_norm": 0.0389193557202816,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6764352321624756,
      "step": 2786
    },
    {
      "epoch": 0.13276190476190478,
      "grad_norm": 0.04059649631381035,
      "learning_rate": 0.024000000208616257,
      "loss": 2.701692581176758,
      "step": 2788
    },
    {
      "epoch": 0.13285714285714287,
      "grad_norm": 0.046153724193573,
      "learning_rate": 0.024000000208616257,
      "loss": 2.681943416595459,
      "step": 2790
    },
    {
      "epoch": 0.13295238095238096,
      "grad_norm": 0.04838388413190842,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6785736083984375,
      "step": 2792
    },
    {
      "epoch": 0.13304761904761905,
      "grad_norm": 0.047838062047958374,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6886205673217773,
      "step": 2794
    },
    {
      "epoch": 0.13314285714285715,
      "grad_norm": 0.04280884563922882,
      "learning_rate": 0.024000000208616257,
      "loss": 2.695260524749756,
      "step": 2796
    },
    {
      "epoch": 0.13323809523809524,
      "grad_norm": 0.039508454501628876,
      "learning_rate": 0.024000000208616257,
      "loss": 2.654273509979248,
      "step": 2798
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.039450373500585556,
      "learning_rate": 0.024000000208616257,
      "loss": 2.680516242980957,
      "step": 2800
    },
    {
      "epoch": 0.13342857142857142,
      "grad_norm": 0.039599716663360596,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6453986167907715,
      "step": 2802
    },
    {
      "epoch": 0.13352380952380952,
      "grad_norm": 0.04147465154528618,
      "learning_rate": 0.024000000208616257,
      "loss": 2.677910804748535,
      "step": 2804
    },
    {
      "epoch": 0.1336190476190476,
      "grad_norm": 0.03976032882928848,
      "learning_rate": 0.024000000208616257,
      "loss": 2.699850082397461,
      "step": 2806
    },
    {
      "epoch": 0.1337142857142857,
      "grad_norm": 0.039951391518116,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6960697174072266,
      "step": 2808
    },
    {
      "epoch": 0.13380952380952382,
      "grad_norm": 0.04114368185400963,
      "learning_rate": 0.024000000208616257,
      "loss": 2.692931652069092,
      "step": 2810
    },
    {
      "epoch": 0.13390476190476192,
      "grad_norm": 0.040496353060007095,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6931886672973633,
      "step": 2812
    },
    {
      "epoch": 0.134,
      "grad_norm": 0.04267456382513046,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6665735244750977,
      "step": 2814
    },
    {
      "epoch": 0.1340952380952381,
      "grad_norm": 0.0385521799325943,
      "learning_rate": 0.024000000208616257,
      "loss": 2.64929461479187,
      "step": 2816
    },
    {
      "epoch": 0.1341904761904762,
      "grad_norm": 0.04104091599583626,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6566340923309326,
      "step": 2818
    },
    {
      "epoch": 0.13428571428571429,
      "grad_norm": 0.03943803161382675,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6731624603271484,
      "step": 2820
    },
    {
      "epoch": 0.13438095238095238,
      "grad_norm": 0.03935855254530907,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6837475299835205,
      "step": 2822
    },
    {
      "epoch": 0.13447619047619047,
      "grad_norm": 0.03910178691148758,
      "learning_rate": 0.024000000208616257,
      "loss": 2.7134106159210205,
      "step": 2824
    },
    {
      "epoch": 0.13457142857142856,
      "grad_norm": 0.039158161729574203,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6557364463806152,
      "step": 2826
    },
    {
      "epoch": 0.13466666666666666,
      "grad_norm": 0.03954636678099632,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6745145320892334,
      "step": 2828
    },
    {
      "epoch": 0.13476190476190475,
      "grad_norm": 0.03995664045214653,
      "learning_rate": 0.024000000208616257,
      "loss": 2.657139301300049,
      "step": 2830
    },
    {
      "epoch": 0.13485714285714287,
      "grad_norm": 0.04067015275359154,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6779978275299072,
      "step": 2832
    },
    {
      "epoch": 0.13495238095238096,
      "grad_norm": 0.04139202833175659,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6835622787475586,
      "step": 2834
    },
    {
      "epoch": 0.13504761904761906,
      "grad_norm": 0.039104025810956955,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6859207153320312,
      "step": 2836
    },
    {
      "epoch": 0.13514285714285715,
      "grad_norm": 0.04216964170336723,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6594200134277344,
      "step": 2838
    },
    {
      "epoch": 0.13523809523809524,
      "grad_norm": 0.040267135947942734,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6702561378479004,
      "step": 2840
    },
    {
      "epoch": 0.13533333333333333,
      "grad_norm": 0.04384255036711693,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6731019020080566,
      "step": 2842
    },
    {
      "epoch": 0.13542857142857143,
      "grad_norm": 0.04294711723923683,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6381993293762207,
      "step": 2844
    },
    {
      "epoch": 0.13552380952380952,
      "grad_norm": 0.03817366063594818,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6678214073181152,
      "step": 2846
    },
    {
      "epoch": 0.1356190476190476,
      "grad_norm": 0.038679130375385284,
      "learning_rate": 0.024000000208616257,
      "loss": 2.63529372215271,
      "step": 2848
    },
    {
      "epoch": 0.1357142857142857,
      "grad_norm": 0.03927658125758171,
      "learning_rate": 0.024000000208616257,
      "loss": 2.660576105117798,
      "step": 2850
    },
    {
      "epoch": 0.1358095238095238,
      "grad_norm": 0.03971083462238312,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6827425956726074,
      "step": 2852
    },
    {
      "epoch": 0.13590476190476192,
      "grad_norm": 0.03896373137831688,
      "learning_rate": 0.024000000208616257,
      "loss": 2.684269905090332,
      "step": 2854
    },
    {
      "epoch": 0.136,
      "grad_norm": 0.0378166139125824,
      "learning_rate": 0.024000000208616257,
      "loss": 2.636542797088623,
      "step": 2856
    },
    {
      "epoch": 0.1360952380952381,
      "grad_norm": 0.03954099491238594,
      "learning_rate": 0.024000000208616257,
      "loss": 2.673189163208008,
      "step": 2858
    },
    {
      "epoch": 0.1361904761904762,
      "grad_norm": 0.03805512189865112,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6681418418884277,
      "step": 2860
    },
    {
      "epoch": 0.1362857142857143,
      "grad_norm": 0.03844426944851875,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6852381229400635,
      "step": 2862
    },
    {
      "epoch": 0.13638095238095238,
      "grad_norm": 0.03839988633990288,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6407852172851562,
      "step": 2864
    },
    {
      "epoch": 0.13647619047619047,
      "grad_norm": 0.03929746896028519,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6381001472473145,
      "step": 2866
    },
    {
      "epoch": 0.13657142857142857,
      "grad_norm": 0.03905761241912842,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6717286109924316,
      "step": 2868
    },
    {
      "epoch": 0.13666666666666666,
      "grad_norm": 0.04006391763687134,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6785085201263428,
      "step": 2870
    },
    {
      "epoch": 0.13676190476190475,
      "grad_norm": 0.03996339812874794,
      "learning_rate": 0.024000000208616257,
      "loss": 2.678069829940796,
      "step": 2872
    },
    {
      "epoch": 0.13685714285714284,
      "grad_norm": 0.03989030048251152,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6422157287597656,
      "step": 2874
    },
    {
      "epoch": 0.13695238095238096,
      "grad_norm": 0.04217144474387169,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6668789386749268,
      "step": 2876
    },
    {
      "epoch": 0.13704761904761906,
      "grad_norm": 0.040372416377067566,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6651957035064697,
      "step": 2878
    },
    {
      "epoch": 0.13714285714285715,
      "grad_norm": 0.03993074968457222,
      "learning_rate": 0.024000000208616257,
      "loss": 2.662209987640381,
      "step": 2880
    },
    {
      "epoch": 0.13723809523809524,
      "grad_norm": 0.03925129026174545,
      "learning_rate": 0.024000000208616257,
      "loss": 2.682891607284546,
      "step": 2882
    },
    {
      "epoch": 0.13733333333333334,
      "grad_norm": 0.038872480392456055,
      "learning_rate": 0.024000000208616257,
      "loss": 2.673384189605713,
      "step": 2884
    },
    {
      "epoch": 0.13742857142857143,
      "grad_norm": 0.03834608569741249,
      "learning_rate": 0.024000000208616257,
      "loss": 2.672583818435669,
      "step": 2886
    },
    {
      "epoch": 0.13752380952380952,
      "grad_norm": 0.04069787636399269,
      "learning_rate": 0.024000000208616257,
      "loss": 2.641012668609619,
      "step": 2888
    },
    {
      "epoch": 0.1376190476190476,
      "grad_norm": 0.03847348690032959,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6502671241760254,
      "step": 2890
    },
    {
      "epoch": 0.1377142857142857,
      "grad_norm": 0.04134195297956467,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6393933296203613,
      "step": 2892
    },
    {
      "epoch": 0.1378095238095238,
      "grad_norm": 0.04047824442386627,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6315436363220215,
      "step": 2894
    },
    {
      "epoch": 0.1379047619047619,
      "grad_norm": 0.04260635003447533,
      "learning_rate": 0.024000000208616257,
      "loss": 2.647691011428833,
      "step": 2896
    },
    {
      "epoch": 0.138,
      "grad_norm": 0.0376734621822834,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6929445266723633,
      "step": 2898
    },
    {
      "epoch": 0.1380952380952381,
      "grad_norm": 0.03964005038142204,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6126708984375,
      "step": 2900
    },
    {
      "epoch": 0.1381904761904762,
      "grad_norm": 0.03940735384821892,
      "learning_rate": 0.024000000208616257,
      "loss": 2.630216598510742,
      "step": 2902
    },
    {
      "epoch": 0.1382857142857143,
      "grad_norm": 0.04031897708773613,
      "learning_rate": 0.024000000208616257,
      "loss": 2.653235673904419,
      "step": 2904
    },
    {
      "epoch": 0.13838095238095238,
      "grad_norm": 0.038918230682611465,
      "learning_rate": 0.024000000208616257,
      "loss": 2.620633602142334,
      "step": 2906
    },
    {
      "epoch": 0.13847619047619047,
      "grad_norm": 0.03889259323477745,
      "learning_rate": 0.024000000208616257,
      "loss": 2.659282684326172,
      "step": 2908
    },
    {
      "epoch": 0.13857142857142857,
      "grad_norm": 0.03944620490074158,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6663565635681152,
      "step": 2910
    },
    {
      "epoch": 0.13866666666666666,
      "grad_norm": 0.04059228673577309,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6467175483703613,
      "step": 2912
    },
    {
      "epoch": 0.13876190476190475,
      "grad_norm": 0.04343913495540619,
      "learning_rate": 0.024000000208616257,
      "loss": 2.622924327850342,
      "step": 2914
    },
    {
      "epoch": 0.13885714285714285,
      "grad_norm": 0.043369874358177185,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6712074279785156,
      "step": 2916
    },
    {
      "epoch": 0.13895238095238097,
      "grad_norm": 0.042386528104543686,
      "learning_rate": 0.024000000208616257,
      "loss": 2.643153190612793,
      "step": 2918
    },
    {
      "epoch": 0.13904761904761906,
      "grad_norm": 0.03954014927148819,
      "learning_rate": 0.024000000208616257,
      "loss": 2.619866371154785,
      "step": 2920
    },
    {
      "epoch": 0.13914285714285715,
      "grad_norm": 0.03807791694998741,
      "learning_rate": 0.024000000208616257,
      "loss": 2.651921510696411,
      "step": 2922
    },
    {
      "epoch": 0.13923809523809524,
      "grad_norm": 0.039258792996406555,
      "learning_rate": 0.024000000208616257,
      "loss": 2.645901679992676,
      "step": 2924
    },
    {
      "epoch": 0.13933333333333334,
      "grad_norm": 0.041380736976861954,
      "learning_rate": 0.024000000208616257,
      "loss": 2.648244857788086,
      "step": 2926
    },
    {
      "epoch": 0.13942857142857143,
      "grad_norm": 0.04004960507154465,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6421947479248047,
      "step": 2928
    },
    {
      "epoch": 0.13952380952380952,
      "grad_norm": 0.04143644496798515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.645738124847412,
      "step": 2930
    },
    {
      "epoch": 0.13961904761904761,
      "grad_norm": 0.04151866212487221,
      "learning_rate": 0.024000000208616257,
      "loss": 2.650439500808716,
      "step": 2932
    },
    {
      "epoch": 0.1397142857142857,
      "grad_norm": 0.041612230241298676,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6533665657043457,
      "step": 2934
    },
    {
      "epoch": 0.1398095238095238,
      "grad_norm": 0.04194706305861473,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6263740062713623,
      "step": 2936
    },
    {
      "epoch": 0.1399047619047619,
      "grad_norm": 0.039910729974508286,
      "learning_rate": 0.024000000208616257,
      "loss": 2.656196117401123,
      "step": 2938
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.04038766399025917,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6485226154327393,
      "step": 2940
    },
    {
      "epoch": 0.1400952380952381,
      "grad_norm": 0.04211939871311188,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6276211738586426,
      "step": 2942
    },
    {
      "epoch": 0.1401904761904762,
      "grad_norm": 0.04193573445081711,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6352179050445557,
      "step": 2944
    },
    {
      "epoch": 0.1402857142857143,
      "grad_norm": 0.039469823241233826,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6432840824127197,
      "step": 2946
    },
    {
      "epoch": 0.14038095238095238,
      "grad_norm": 0.038907259702682495,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6459147930145264,
      "step": 2948
    },
    {
      "epoch": 0.14047619047619048,
      "grad_norm": 0.03937728330492973,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5971879959106445,
      "step": 2950
    },
    {
      "epoch": 0.14057142857142857,
      "grad_norm": 0.040734078735113144,
      "learning_rate": 0.024000000208616257,
      "loss": 2.638200044631958,
      "step": 2952
    },
    {
      "epoch": 0.14066666666666666,
      "grad_norm": 0.03872331976890564,
      "learning_rate": 0.024000000208616257,
      "loss": 2.612642526626587,
      "step": 2954
    },
    {
      "epoch": 0.14076190476190475,
      "grad_norm": 0.03724416345357895,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6762888431549072,
      "step": 2956
    },
    {
      "epoch": 0.14085714285714285,
      "grad_norm": 0.04200783744454384,
      "learning_rate": 0.024000000208616257,
      "loss": 2.626366138458252,
      "step": 2958
    },
    {
      "epoch": 0.14095238095238094,
      "grad_norm": 0.04264798015356064,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6504194736480713,
      "step": 2960
    },
    {
      "epoch": 0.14104761904761906,
      "grad_norm": 0.04076986014842987,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6391167640686035,
      "step": 2962
    },
    {
      "epoch": 0.14114285714285715,
      "grad_norm": 0.03790652006864548,
      "learning_rate": 0.024000000208616257,
      "loss": 2.639674425125122,
      "step": 2964
    },
    {
      "epoch": 0.14123809523809525,
      "grad_norm": 0.0388825498521328,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6171326637268066,
      "step": 2966
    },
    {
      "epoch": 0.14133333333333334,
      "grad_norm": 0.03782769665122032,
      "learning_rate": 0.024000000208616257,
      "loss": 2.616725444793701,
      "step": 2968
    },
    {
      "epoch": 0.14142857142857143,
      "grad_norm": 0.037182100117206573,
      "learning_rate": 0.024000000208616257,
      "loss": 2.626232147216797,
      "step": 2970
    },
    {
      "epoch": 0.14152380952380952,
      "grad_norm": 0.039799291640520096,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6755733489990234,
      "step": 2972
    },
    {
      "epoch": 0.14161904761904762,
      "grad_norm": 0.039296701550483704,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6368651390075684,
      "step": 2974
    },
    {
      "epoch": 0.1417142857142857,
      "grad_norm": 0.038548558950424194,
      "learning_rate": 0.024000000208616257,
      "loss": 2.615267038345337,
      "step": 2976
    },
    {
      "epoch": 0.1418095238095238,
      "grad_norm": 0.039839159697294235,
      "learning_rate": 0.024000000208616257,
      "loss": 2.587344169616699,
      "step": 2978
    },
    {
      "epoch": 0.1419047619047619,
      "grad_norm": 0.03981087729334831,
      "learning_rate": 0.024000000208616257,
      "loss": 2.61289644241333,
      "step": 2980
    },
    {
      "epoch": 0.142,
      "grad_norm": 0.04115326702594757,
      "learning_rate": 0.024000000208616257,
      "loss": 2.649667739868164,
      "step": 2982
    },
    {
      "epoch": 0.1420952380952381,
      "grad_norm": 0.04393702372908592,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6150436401367188,
      "step": 2984
    },
    {
      "epoch": 0.1421904761904762,
      "grad_norm": 0.04394924268126488,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6212427616119385,
      "step": 2986
    },
    {
      "epoch": 0.1422857142857143,
      "grad_norm": 0.04177684336900711,
      "learning_rate": 0.024000000208616257,
      "loss": 2.618621349334717,
      "step": 2988
    },
    {
      "epoch": 0.14238095238095239,
      "grad_norm": 0.04122864454984665,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5652880668640137,
      "step": 2990
    },
    {
      "epoch": 0.14247619047619048,
      "grad_norm": 0.03842271491885185,
      "learning_rate": 0.024000000208616257,
      "loss": 2.621561050415039,
      "step": 2992
    },
    {
      "epoch": 0.14257142857142857,
      "grad_norm": 0.04010410234332085,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5930819511413574,
      "step": 2994
    },
    {
      "epoch": 0.14266666666666666,
      "grad_norm": 0.04060627147555351,
      "learning_rate": 0.024000000208616257,
      "loss": 2.620056629180908,
      "step": 2996
    },
    {
      "epoch": 0.14276190476190476,
      "grad_norm": 0.039582088589668274,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5957489013671875,
      "step": 2998
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.039420194923877716,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6166863441467285,
      "step": 3000
    },
    {
      "epoch": 0.14295238095238094,
      "grad_norm": 0.0392138808965683,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6371893882751465,
      "step": 3002
    },
    {
      "epoch": 0.14304761904761903,
      "grad_norm": 0.04179920628666878,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6331734657287598,
      "step": 3004
    },
    {
      "epoch": 0.14314285714285716,
      "grad_norm": 0.03786275535821915,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6294808387756348,
      "step": 3006
    },
    {
      "epoch": 0.14323809523809525,
      "grad_norm": 0.0388900563120842,
      "learning_rate": 0.024000000208616257,
      "loss": 2.613710880279541,
      "step": 3008
    },
    {
      "epoch": 0.14333333333333334,
      "grad_norm": 0.03854822367429733,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6088547706604004,
      "step": 3010
    },
    {
      "epoch": 0.14342857142857143,
      "grad_norm": 0.0364716500043869,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5984854698181152,
      "step": 3012
    },
    {
      "epoch": 0.14352380952380953,
      "grad_norm": 0.039459437131881714,
      "learning_rate": 0.024000000208616257,
      "loss": 2.584599018096924,
      "step": 3014
    },
    {
      "epoch": 0.14361904761904762,
      "grad_norm": 0.037484150379896164,
      "learning_rate": 0.024000000208616257,
      "loss": 2.632702112197876,
      "step": 3016
    },
    {
      "epoch": 0.1437142857142857,
      "grad_norm": 0.039724864065647125,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6238274574279785,
      "step": 3018
    },
    {
      "epoch": 0.1438095238095238,
      "grad_norm": 0.03902710974216461,
      "learning_rate": 0.024000000208616257,
      "loss": 2.618647813796997,
      "step": 3020
    },
    {
      "epoch": 0.1439047619047619,
      "grad_norm": 0.040613505989313126,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5997371673583984,
      "step": 3022
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.03852438926696777,
      "learning_rate": 0.024000000208616257,
      "loss": 2.616363048553467,
      "step": 3024
    },
    {
      "epoch": 0.14409523809523808,
      "grad_norm": 0.04180524870753288,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6243410110473633,
      "step": 3026
    },
    {
      "epoch": 0.1441904761904762,
      "grad_norm": 0.04116296023130417,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6090919971466064,
      "step": 3028
    },
    {
      "epoch": 0.1442857142857143,
      "grad_norm": 0.03752176836133003,
      "learning_rate": 0.024000000208616257,
      "loss": 2.594334363937378,
      "step": 3030
    },
    {
      "epoch": 0.1443809523809524,
      "grad_norm": 0.03882811591029167,
      "learning_rate": 0.024000000208616257,
      "loss": 2.585858106613159,
      "step": 3032
    },
    {
      "epoch": 0.14447619047619048,
      "grad_norm": 0.03914063051342964,
      "learning_rate": 0.024000000208616257,
      "loss": 2.626927375793457,
      "step": 3034
    },
    {
      "epoch": 0.14457142857142857,
      "grad_norm": 0.03666650503873825,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6382594108581543,
      "step": 3036
    },
    {
      "epoch": 0.14466666666666667,
      "grad_norm": 0.03868306800723076,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6070427894592285,
      "step": 3038
    },
    {
      "epoch": 0.14476190476190476,
      "grad_norm": 0.0413958914577961,
      "learning_rate": 0.024000000208616257,
      "loss": 2.602046489715576,
      "step": 3040
    },
    {
      "epoch": 0.14485714285714285,
      "grad_norm": 0.039238203316926956,
      "learning_rate": 0.024000000208616257,
      "loss": 2.598741054534912,
      "step": 3042
    },
    {
      "epoch": 0.14495238095238094,
      "grad_norm": 0.03756674751639366,
      "learning_rate": 0.024000000208616257,
      "loss": 2.59173583984375,
      "step": 3044
    },
    {
      "epoch": 0.14504761904761904,
      "grad_norm": 0.038962580263614655,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6036300659179688,
      "step": 3046
    },
    {
      "epoch": 0.14514285714285713,
      "grad_norm": 0.04044633358716965,
      "learning_rate": 0.024000000208616257,
      "loss": 2.623006820678711,
      "step": 3048
    },
    {
      "epoch": 0.14523809523809525,
      "grad_norm": 0.04012296721339226,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5926878452301025,
      "step": 3050
    },
    {
      "epoch": 0.14533333333333334,
      "grad_norm": 0.040498752146959305,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5605766773223877,
      "step": 3052
    },
    {
      "epoch": 0.14542857142857143,
      "grad_norm": 0.03759801387786865,
      "learning_rate": 0.024000000208616257,
      "loss": 2.599566698074341,
      "step": 3054
    },
    {
      "epoch": 0.14552380952380953,
      "grad_norm": 0.03971228748559952,
      "learning_rate": 0.024000000208616257,
      "loss": 2.620002269744873,
      "step": 3056
    },
    {
      "epoch": 0.14561904761904762,
      "grad_norm": 0.04205906391143799,
      "learning_rate": 0.024000000208616257,
      "loss": 2.611114025115967,
      "step": 3058
    },
    {
      "epoch": 0.1457142857142857,
      "grad_norm": 0.03935784474015236,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5592851638793945,
      "step": 3060
    },
    {
      "epoch": 0.1458095238095238,
      "grad_norm": 0.03973614051938057,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5818920135498047,
      "step": 3062
    },
    {
      "epoch": 0.1459047619047619,
      "grad_norm": 0.040794964879751205,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5968682765960693,
      "step": 3064
    },
    {
      "epoch": 0.146,
      "grad_norm": 0.03733645752072334,
      "learning_rate": 0.024000000208616257,
      "loss": 2.625763177871704,
      "step": 3066
    },
    {
      "epoch": 0.14609523809523808,
      "grad_norm": 0.03931474685668945,
      "learning_rate": 0.024000000208616257,
      "loss": 2.51363468170166,
      "step": 3068
    },
    {
      "epoch": 0.1461904761904762,
      "grad_norm": 0.040074340999126434,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6052005290985107,
      "step": 3070
    },
    {
      "epoch": 0.1462857142857143,
      "grad_norm": 0.04078330099582672,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5466160774230957,
      "step": 3072
    },
    {
      "epoch": 0.1463809523809524,
      "grad_norm": 0.03887728601694107,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5743465423583984,
      "step": 3074
    },
    {
      "epoch": 0.14647619047619048,
      "grad_norm": 0.03921743854880333,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5866732597351074,
      "step": 3076
    },
    {
      "epoch": 0.14657142857142857,
      "grad_norm": 0.04153836518526077,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5911436080932617,
      "step": 3078
    },
    {
      "epoch": 0.14666666666666667,
      "grad_norm": 0.03965853527188301,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6014280319213867,
      "step": 3080
    },
    {
      "epoch": 0.14676190476190476,
      "grad_norm": 0.037431709468364716,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5915699005126953,
      "step": 3082
    },
    {
      "epoch": 0.14685714285714285,
      "grad_norm": 0.0392446368932724,
      "learning_rate": 0.024000000208616257,
      "loss": 2.604689598083496,
      "step": 3084
    },
    {
      "epoch": 0.14695238095238095,
      "grad_norm": 0.03892185166478157,
      "learning_rate": 0.024000000208616257,
      "loss": 2.568957805633545,
      "step": 3086
    },
    {
      "epoch": 0.14704761904761904,
      "grad_norm": 0.041385602205991745,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5749292373657227,
      "step": 3088
    },
    {
      "epoch": 0.14714285714285713,
      "grad_norm": 0.0402534157037735,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5953779220581055,
      "step": 3090
    },
    {
      "epoch": 0.14723809523809525,
      "grad_norm": 0.037617940455675125,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5967750549316406,
      "step": 3092
    },
    {
      "epoch": 0.14733333333333334,
      "grad_norm": 0.03831905871629715,
      "learning_rate": 0.024000000208616257,
      "loss": 2.588866949081421,
      "step": 3094
    },
    {
      "epoch": 0.14742857142857144,
      "grad_norm": 0.03952209651470184,
      "learning_rate": 0.024000000208616257,
      "loss": 2.605015754699707,
      "step": 3096
    },
    {
      "epoch": 0.14752380952380953,
      "grad_norm": 0.038520801812410355,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5526885986328125,
      "step": 3098
    },
    {
      "epoch": 0.14761904761904762,
      "grad_norm": 0.044651009142398834,
      "learning_rate": 0.024000000208616257,
      "loss": 2.543869972229004,
      "step": 3100
    },
    {
      "epoch": 0.14771428571428571,
      "grad_norm": 0.04143275320529938,
      "learning_rate": 0.024000000208616257,
      "loss": 2.594620943069458,
      "step": 3102
    },
    {
      "epoch": 0.1478095238095238,
      "grad_norm": 0.03888707235455513,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5858654975891113,
      "step": 3104
    },
    {
      "epoch": 0.1479047619047619,
      "grad_norm": 0.0392955057322979,
      "learning_rate": 0.024000000208616257,
      "loss": 2.603306293487549,
      "step": 3106
    },
    {
      "epoch": 0.148,
      "grad_norm": 0.03902548551559448,
      "learning_rate": 0.024000000208616257,
      "loss": 2.582852363586426,
      "step": 3108
    },
    {
      "epoch": 0.14809523809523809,
      "grad_norm": 0.03929935023188591,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5718345642089844,
      "step": 3110
    },
    {
      "epoch": 0.14819047619047618,
      "grad_norm": 0.03979219123721123,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5792267322540283,
      "step": 3112
    },
    {
      "epoch": 0.1482857142857143,
      "grad_norm": 0.04326530918478966,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5757691860198975,
      "step": 3114
    },
    {
      "epoch": 0.1483809523809524,
      "grad_norm": 0.039412934333086014,
      "learning_rate": 0.024000000208616257,
      "loss": 2.580282211303711,
      "step": 3116
    },
    {
      "epoch": 0.14847619047619048,
      "grad_norm": 0.04083528369665146,
      "learning_rate": 0.024000000208616257,
      "loss": 2.553467273712158,
      "step": 3118
    },
    {
      "epoch": 0.14857142857142858,
      "grad_norm": 0.03762682527303696,
      "learning_rate": 0.024000000208616257,
      "loss": 2.534761428833008,
      "step": 3120
    },
    {
      "epoch": 0.14866666666666667,
      "grad_norm": 0.038149431347846985,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5883092880249023,
      "step": 3122
    },
    {
      "epoch": 0.14876190476190476,
      "grad_norm": 0.03791528940200806,
      "learning_rate": 0.024000000208616257,
      "loss": 2.566225528717041,
      "step": 3124
    },
    {
      "epoch": 0.14885714285714285,
      "grad_norm": 0.03986047953367233,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5850725173950195,
      "step": 3126
    },
    {
      "epoch": 0.14895238095238095,
      "grad_norm": 0.04199884086847305,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6232714653015137,
      "step": 3128
    },
    {
      "epoch": 0.14904761904761904,
      "grad_norm": 0.03842385113239288,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6126813888549805,
      "step": 3130
    },
    {
      "epoch": 0.14914285714285713,
      "grad_norm": 0.03708665072917938,
      "learning_rate": 0.024000000208616257,
      "loss": 2.585184097290039,
      "step": 3132
    },
    {
      "epoch": 0.14923809523809523,
      "grad_norm": 0.03876678645610809,
      "learning_rate": 0.024000000208616257,
      "loss": 2.552013874053955,
      "step": 3134
    },
    {
      "epoch": 0.14933333333333335,
      "grad_norm": 0.03801149129867554,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5810422897338867,
      "step": 3136
    },
    {
      "epoch": 0.14942857142857144,
      "grad_norm": 0.039441123604774475,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5559239387512207,
      "step": 3138
    },
    {
      "epoch": 0.14952380952380953,
      "grad_norm": 0.038277365267276764,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5387797355651855,
      "step": 3140
    },
    {
      "epoch": 0.14961904761904762,
      "grad_norm": 0.038119617849588394,
      "learning_rate": 0.024000000208616257,
      "loss": 2.577263355255127,
      "step": 3142
    },
    {
      "epoch": 0.14971428571428572,
      "grad_norm": 0.041055046021938324,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5733118057250977,
      "step": 3144
    },
    {
      "epoch": 0.1498095238095238,
      "grad_norm": 0.037505995482206345,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5887436866760254,
      "step": 3146
    },
    {
      "epoch": 0.1499047619047619,
      "grad_norm": 0.03691397234797478,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5488247871398926,
      "step": 3148
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.04056220501661301,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5925769805908203,
      "step": 3150
    },
    {
      "epoch": 0.1500952380952381,
      "grad_norm": 0.03678319975733757,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5800743103027344,
      "step": 3152
    },
    {
      "epoch": 0.15019047619047618,
      "grad_norm": 0.038794394582509995,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5886306762695312,
      "step": 3154
    },
    {
      "epoch": 0.15028571428571427,
      "grad_norm": 0.03914694860577583,
      "learning_rate": 0.024000000208616257,
      "loss": 2.55511474609375,
      "step": 3156
    },
    {
      "epoch": 0.1503809523809524,
      "grad_norm": 0.03604903444647789,
      "learning_rate": 0.024000000208616257,
      "loss": 2.61460542678833,
      "step": 3158
    },
    {
      "epoch": 0.15047619047619049,
      "grad_norm": 0.03647039085626602,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5767784118652344,
      "step": 3160
    },
    {
      "epoch": 0.15057142857142858,
      "grad_norm": 0.03931108117103577,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5687875747680664,
      "step": 3162
    },
    {
      "epoch": 0.15066666666666667,
      "grad_norm": 0.041386935859918594,
      "learning_rate": 0.024000000208616257,
      "loss": 2.585418939590454,
      "step": 3164
    },
    {
      "epoch": 0.15076190476190476,
      "grad_norm": 0.04378081485629082,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5867645740509033,
      "step": 3166
    },
    {
      "epoch": 0.15085714285714286,
      "grad_norm": 0.040701672434806824,
      "learning_rate": 0.024000000208616257,
      "loss": 2.597322463989258,
      "step": 3168
    },
    {
      "epoch": 0.15095238095238095,
      "grad_norm": 0.04305503889918327,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5856833457946777,
      "step": 3170
    },
    {
      "epoch": 0.15104761904761904,
      "grad_norm": 0.04334327206015587,
      "learning_rate": 0.024000000208616257,
      "loss": 2.605402946472168,
      "step": 3172
    },
    {
      "epoch": 0.15114285714285713,
      "grad_norm": 0.037112362682819366,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5597732067108154,
      "step": 3174
    },
    {
      "epoch": 0.15123809523809523,
      "grad_norm": 0.03670288994908333,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5482399463653564,
      "step": 3176
    },
    {
      "epoch": 0.15133333333333332,
      "grad_norm": 0.038057245314121246,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5790276527404785,
      "step": 3178
    },
    {
      "epoch": 0.15142857142857144,
      "grad_norm": 0.03869212418794632,
      "learning_rate": 0.024000000208616257,
      "loss": 2.577225685119629,
      "step": 3180
    },
    {
      "epoch": 0.15152380952380953,
      "grad_norm": 0.03775709122419357,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5725831985473633,
      "step": 3182
    },
    {
      "epoch": 0.15161904761904763,
      "grad_norm": 0.03987998142838478,
      "learning_rate": 0.024000000208616257,
      "loss": 2.565498113632202,
      "step": 3184
    },
    {
      "epoch": 0.15171428571428572,
      "grad_norm": 0.0386643260717392,
      "learning_rate": 0.024000000208616257,
      "loss": 2.590784788131714,
      "step": 3186
    },
    {
      "epoch": 0.1518095238095238,
      "grad_norm": 0.038236502557992935,
      "learning_rate": 0.024000000208616257,
      "loss": 2.566640853881836,
      "step": 3188
    },
    {
      "epoch": 0.1519047619047619,
      "grad_norm": 0.0382254496216774,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5823230743408203,
      "step": 3190
    },
    {
      "epoch": 0.152,
      "grad_norm": 0.036894697695970535,
      "learning_rate": 0.024000000208616257,
      "loss": 2.580209732055664,
      "step": 3192
    },
    {
      "epoch": 0.1520952380952381,
      "grad_norm": 0.037333033978939056,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5808792114257812,
      "step": 3194
    },
    {
      "epoch": 0.15219047619047618,
      "grad_norm": 0.0369417741894722,
      "learning_rate": 0.024000000208616257,
      "loss": 2.594463348388672,
      "step": 3196
    },
    {
      "epoch": 0.15228571428571427,
      "grad_norm": 0.038168661296367645,
      "learning_rate": 0.024000000208616257,
      "loss": 2.546644449234009,
      "step": 3198
    },
    {
      "epoch": 0.1523809523809524,
      "grad_norm": 0.03916992247104645,
      "learning_rate": 0.024000000208616257,
      "loss": 2.580228328704834,
      "step": 3200
    },
    {
      "epoch": 0.1524761904761905,
      "grad_norm": 0.03850780427455902,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6106181144714355,
      "step": 3202
    },
    {
      "epoch": 0.15257142857142858,
      "grad_norm": 0.042017631232738495,
      "learning_rate": 0.024000000208616257,
      "loss": 2.614043712615967,
      "step": 3204
    },
    {
      "epoch": 0.15266666666666667,
      "grad_norm": 0.04434071108698845,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5827531814575195,
      "step": 3206
    },
    {
      "epoch": 0.15276190476190477,
      "grad_norm": 0.04001621901988983,
      "learning_rate": 0.024000000208616257,
      "loss": 2.578305244445801,
      "step": 3208
    },
    {
      "epoch": 0.15285714285714286,
      "grad_norm": 0.0393667109310627,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5966637134552,
      "step": 3210
    },
    {
      "epoch": 0.15295238095238095,
      "grad_norm": 0.037795938551425934,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5951523780822754,
      "step": 3212
    },
    {
      "epoch": 0.15304761904761904,
      "grad_norm": 0.03728668391704559,
      "learning_rate": 0.024000000208616257,
      "loss": 2.563171863555908,
      "step": 3214
    },
    {
      "epoch": 0.15314285714285714,
      "grad_norm": 0.037700019776821136,
      "learning_rate": 0.024000000208616257,
      "loss": 2.580166816711426,
      "step": 3216
    },
    {
      "epoch": 0.15323809523809523,
      "grad_norm": 0.03840586915612221,
      "learning_rate": 0.024000000208616257,
      "loss": 2.576883316040039,
      "step": 3218
    },
    {
      "epoch": 0.15333333333333332,
      "grad_norm": 0.03821544721722603,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6196446418762207,
      "step": 3220
    },
    {
      "epoch": 0.15342857142857144,
      "grad_norm": 0.039689864963293076,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5961766242980957,
      "step": 3222
    },
    {
      "epoch": 0.15352380952380953,
      "grad_norm": 0.037422940135002136,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5739245414733887,
      "step": 3224
    },
    {
      "epoch": 0.15361904761904763,
      "grad_norm": 0.03687533363699913,
      "learning_rate": 0.024000000208616257,
      "loss": 2.525033950805664,
      "step": 3226
    },
    {
      "epoch": 0.15371428571428572,
      "grad_norm": 0.03645416349172592,
      "learning_rate": 0.024000000208616257,
      "loss": 2.620124101638794,
      "step": 3228
    },
    {
      "epoch": 0.1538095238095238,
      "grad_norm": 0.03717149421572685,
      "learning_rate": 0.024000000208616257,
      "loss": 2.567460775375366,
      "step": 3230
    },
    {
      "epoch": 0.1539047619047619,
      "grad_norm": 0.03783761337399483,
      "learning_rate": 0.024000000208616257,
      "loss": 2.573657751083374,
      "step": 3232
    },
    {
      "epoch": 0.154,
      "grad_norm": 0.04119350388646126,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5738677978515625,
      "step": 3234
    },
    {
      "epoch": 0.1540952380952381,
      "grad_norm": 0.039168305695056915,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5970513820648193,
      "step": 3236
    },
    {
      "epoch": 0.15419047619047618,
      "grad_norm": 0.03738267347216606,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5702152252197266,
      "step": 3238
    },
    {
      "epoch": 0.15428571428571428,
      "grad_norm": 0.03730668127536774,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5735793113708496,
      "step": 3240
    },
    {
      "epoch": 0.15438095238095237,
      "grad_norm": 0.037182196974754333,
      "learning_rate": 0.024000000208616257,
      "loss": 2.558875560760498,
      "step": 3242
    },
    {
      "epoch": 0.1544761904761905,
      "grad_norm": 0.03875721991062164,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5722126960754395,
      "step": 3244
    },
    {
      "epoch": 0.15457142857142858,
      "grad_norm": 0.03913908824324608,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5881104469299316,
      "step": 3246
    },
    {
      "epoch": 0.15466666666666667,
      "grad_norm": 0.04028948396444321,
      "learning_rate": 0.024000000208616257,
      "loss": 2.551118850708008,
      "step": 3248
    },
    {
      "epoch": 0.15476190476190477,
      "grad_norm": 0.03996875882148743,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5976433753967285,
      "step": 3250
    },
    {
      "epoch": 0.15485714285714286,
      "grad_norm": 0.038361094892024994,
      "learning_rate": 0.024000000208616257,
      "loss": 2.598240852355957,
      "step": 3252
    },
    {
      "epoch": 0.15495238095238095,
      "grad_norm": 0.037602052092552185,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5746068954467773,
      "step": 3254
    },
    {
      "epoch": 0.15504761904761905,
      "grad_norm": 0.0370112843811512,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5632176399230957,
      "step": 3256
    },
    {
      "epoch": 0.15514285714285714,
      "grad_norm": 0.0365217961370945,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5950515270233154,
      "step": 3258
    },
    {
      "epoch": 0.15523809523809523,
      "grad_norm": 0.0372806079685688,
      "learning_rate": 0.024000000208616257,
      "loss": 2.571918487548828,
      "step": 3260
    },
    {
      "epoch": 0.15533333333333332,
      "grad_norm": 0.03837936744093895,
      "learning_rate": 0.024000000208616257,
      "loss": 2.55275821685791,
      "step": 3262
    },
    {
      "epoch": 0.15542857142857142,
      "grad_norm": 0.03752235695719719,
      "learning_rate": 0.024000000208616257,
      "loss": 2.572844982147217,
      "step": 3264
    },
    {
      "epoch": 0.15552380952380954,
      "grad_norm": 0.035989515483379364,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5604236125946045,
      "step": 3266
    },
    {
      "epoch": 0.15561904761904763,
      "grad_norm": 0.03745793551206589,
      "learning_rate": 0.024000000208616257,
      "loss": 2.56016206741333,
      "step": 3268
    },
    {
      "epoch": 0.15571428571428572,
      "grad_norm": 0.03846251219511032,
      "learning_rate": 0.024000000208616257,
      "loss": 2.582350254058838,
      "step": 3270
    },
    {
      "epoch": 0.15580952380952381,
      "grad_norm": 0.03891860321164131,
      "learning_rate": 0.024000000208616257,
      "loss": 2.590451240539551,
      "step": 3272
    },
    {
      "epoch": 0.1559047619047619,
      "grad_norm": 0.04092872887849808,
      "learning_rate": 0.024000000208616257,
      "loss": 2.572413921356201,
      "step": 3274
    },
    {
      "epoch": 0.156,
      "grad_norm": 0.038720179349184036,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5542426109313965,
      "step": 3276
    },
    {
      "epoch": 0.1560952380952381,
      "grad_norm": 0.03598913922905922,
      "learning_rate": 0.024000000208616257,
      "loss": 2.568225383758545,
      "step": 3278
    },
    {
      "epoch": 0.15619047619047619,
      "grad_norm": 0.03866675868630409,
      "learning_rate": 0.024000000208616257,
      "loss": 2.590632438659668,
      "step": 3280
    },
    {
      "epoch": 0.15628571428571428,
      "grad_norm": 0.03821682929992676,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5663301944732666,
      "step": 3282
    },
    {
      "epoch": 0.15638095238095237,
      "grad_norm": 0.03708387166261673,
      "learning_rate": 0.024000000208616257,
      "loss": 2.605644702911377,
      "step": 3284
    },
    {
      "epoch": 0.15647619047619046,
      "grad_norm": 0.03740717098116875,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5546374320983887,
      "step": 3286
    },
    {
      "epoch": 0.15657142857142858,
      "grad_norm": 0.03694584220647812,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5737366676330566,
      "step": 3288
    },
    {
      "epoch": 0.15666666666666668,
      "grad_norm": 0.037131596356630325,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5772480964660645,
      "step": 3290
    },
    {
      "epoch": 0.15676190476190477,
      "grad_norm": 0.04232798516750336,
      "learning_rate": 0.024000000208616257,
      "loss": 2.61156964302063,
      "step": 3292
    },
    {
      "epoch": 0.15685714285714286,
      "grad_norm": 0.04268529266119003,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5639820098876953,
      "step": 3294
    },
    {
      "epoch": 0.15695238095238095,
      "grad_norm": 0.03777864947915077,
      "learning_rate": 0.024000000208616257,
      "loss": 2.588480234146118,
      "step": 3296
    },
    {
      "epoch": 0.15704761904761905,
      "grad_norm": 0.03795722499489784,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5941028594970703,
      "step": 3298
    },
    {
      "epoch": 0.15714285714285714,
      "grad_norm": 0.03813173994421959,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5907163619995117,
      "step": 3300
    },
    {
      "epoch": 0.15723809523809523,
      "grad_norm": 0.03773348033428192,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5863349437713623,
      "step": 3302
    },
    {
      "epoch": 0.15733333333333333,
      "grad_norm": 0.04404408112168312,
      "learning_rate": 0.024000000208616257,
      "loss": 2.568857431411743,
      "step": 3304
    },
    {
      "epoch": 0.15742857142857142,
      "grad_norm": 0.04126882180571556,
      "learning_rate": 0.024000000208616257,
      "loss": 2.581489086151123,
      "step": 3306
    },
    {
      "epoch": 0.1575238095238095,
      "grad_norm": 0.042286887764930725,
      "learning_rate": 0.024000000208616257,
      "loss": 2.573014736175537,
      "step": 3308
    },
    {
      "epoch": 0.15761904761904763,
      "grad_norm": 0.03711560741066933,
      "learning_rate": 0.024000000208616257,
      "loss": 2.582048177719116,
      "step": 3310
    },
    {
      "epoch": 0.15771428571428572,
      "grad_norm": 0.03571171313524246,
      "learning_rate": 0.024000000208616257,
      "loss": 2.603975772857666,
      "step": 3312
    },
    {
      "epoch": 0.15780952380952382,
      "grad_norm": 0.03919314220547676,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5679986476898193,
      "step": 3314
    },
    {
      "epoch": 0.1579047619047619,
      "grad_norm": 0.036842912435531616,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6092076301574707,
      "step": 3316
    },
    {
      "epoch": 0.158,
      "grad_norm": 0.03792094066739082,
      "learning_rate": 0.024000000208616257,
      "loss": 2.578662157058716,
      "step": 3318
    },
    {
      "epoch": 0.1580952380952381,
      "grad_norm": 0.03942570835351944,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5927019119262695,
      "step": 3320
    },
    {
      "epoch": 0.1581904761904762,
      "grad_norm": 0.03766052797436714,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5704047679901123,
      "step": 3322
    },
    {
      "epoch": 0.15828571428571428,
      "grad_norm": 0.03880709782242775,
      "learning_rate": 0.024000000208616257,
      "loss": 2.56284761428833,
      "step": 3324
    },
    {
      "epoch": 0.15838095238095237,
      "grad_norm": 0.04064824432134628,
      "learning_rate": 0.024000000208616257,
      "loss": 2.611527442932129,
      "step": 3326
    },
    {
      "epoch": 0.15847619047619046,
      "grad_norm": 0.038762081414461136,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5870156288146973,
      "step": 3328
    },
    {
      "epoch": 0.15857142857142856,
      "grad_norm": 0.039282746613025665,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5951757431030273,
      "step": 3330
    },
    {
      "epoch": 0.15866666666666668,
      "grad_norm": 0.037641312927007675,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6158976554870605,
      "step": 3332
    },
    {
      "epoch": 0.15876190476190477,
      "grad_norm": 0.03574880585074425,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6234731674194336,
      "step": 3334
    },
    {
      "epoch": 0.15885714285714286,
      "grad_norm": 0.03838929533958435,
      "learning_rate": 0.024000000208616257,
      "loss": 2.608250379562378,
      "step": 3336
    },
    {
      "epoch": 0.15895238095238096,
      "grad_norm": 0.03741077333688736,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5765843391418457,
      "step": 3338
    },
    {
      "epoch": 0.15904761904761905,
      "grad_norm": 0.03563082963228226,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5831308364868164,
      "step": 3340
    },
    {
      "epoch": 0.15914285714285714,
      "grad_norm": 0.03876076638698578,
      "learning_rate": 0.024000000208616257,
      "loss": 2.597890853881836,
      "step": 3342
    },
    {
      "epoch": 0.15923809523809523,
      "grad_norm": 0.03783737123012543,
      "learning_rate": 0.024000000208616257,
      "loss": 2.559938430786133,
      "step": 3344
    },
    {
      "epoch": 0.15933333333333333,
      "grad_norm": 0.03706531226634979,
      "learning_rate": 0.024000000208616257,
      "loss": 2.567854881286621,
      "step": 3346
    },
    {
      "epoch": 0.15942857142857142,
      "grad_norm": 0.03845203295350075,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5791778564453125,
      "step": 3348
    },
    {
      "epoch": 0.1595238095238095,
      "grad_norm": 0.04361313208937645,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6156740188598633,
      "step": 3350
    },
    {
      "epoch": 0.15961904761904763,
      "grad_norm": 0.04642040655016899,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5656566619873047,
      "step": 3352
    },
    {
      "epoch": 0.15971428571428573,
      "grad_norm": 0.04452825337648392,
      "learning_rate": 0.024000000208616257,
      "loss": 2.586824417114258,
      "step": 3354
    },
    {
      "epoch": 0.15980952380952382,
      "grad_norm": 0.041569784283638,
      "learning_rate": 0.024000000208616257,
      "loss": 2.585782051086426,
      "step": 3356
    },
    {
      "epoch": 0.1599047619047619,
      "grad_norm": 0.03729706257581711,
      "learning_rate": 0.024000000208616257,
      "loss": 2.58206844329834,
      "step": 3358
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.03959599882364273,
      "learning_rate": 0.024000000208616257,
      "loss": 2.588587760925293,
      "step": 3360
    },
    {
      "epoch": 0.1600952380952381,
      "grad_norm": 0.03998541459441185,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5446887016296387,
      "step": 3362
    },
    {
      "epoch": 0.1601904761904762,
      "grad_norm": 0.03791630268096924,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6077332496643066,
      "step": 3364
    },
    {
      "epoch": 0.16028571428571428,
      "grad_norm": 0.03891317918896675,
      "learning_rate": 0.024000000208616257,
      "loss": 2.595003604888916,
      "step": 3366
    },
    {
      "epoch": 0.16038095238095237,
      "grad_norm": 0.04127093404531479,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5455398559570312,
      "step": 3368
    },
    {
      "epoch": 0.16047619047619047,
      "grad_norm": 0.037817683070898056,
      "learning_rate": 0.024000000208616257,
      "loss": 2.547694683074951,
      "step": 3370
    },
    {
      "epoch": 0.16057142857142856,
      "grad_norm": 0.03817488253116608,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5833773612976074,
      "step": 3372
    },
    {
      "epoch": 0.16066666666666668,
      "grad_norm": 0.03723282739520073,
      "learning_rate": 0.024000000208616257,
      "loss": 2.556349277496338,
      "step": 3374
    },
    {
      "epoch": 0.16076190476190477,
      "grad_norm": 0.0383579395711422,
      "learning_rate": 0.024000000208616257,
      "loss": 2.566047191619873,
      "step": 3376
    },
    {
      "epoch": 0.16085714285714287,
      "grad_norm": 0.03786962479352951,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5930604934692383,
      "step": 3378
    },
    {
      "epoch": 0.16095238095238096,
      "grad_norm": 0.04001046344637871,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5613529682159424,
      "step": 3380
    },
    {
      "epoch": 0.16104761904761905,
      "grad_norm": 0.04066681116819382,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5888655185699463,
      "step": 3382
    },
    {
      "epoch": 0.16114285714285714,
      "grad_norm": 0.041851963847875595,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5783705711364746,
      "step": 3384
    },
    {
      "epoch": 0.16123809523809524,
      "grad_norm": 0.03625408187508583,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5725550651550293,
      "step": 3386
    },
    {
      "epoch": 0.16133333333333333,
      "grad_norm": 0.038086891174316406,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5870871543884277,
      "step": 3388
    },
    {
      "epoch": 0.16142857142857142,
      "grad_norm": 0.03563603386282921,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5637826919555664,
      "step": 3390
    },
    {
      "epoch": 0.16152380952380951,
      "grad_norm": 0.03612935543060303,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5814735889434814,
      "step": 3392
    },
    {
      "epoch": 0.1616190476190476,
      "grad_norm": 0.03616178408265114,
      "learning_rate": 0.024000000208616257,
      "loss": 2.643418312072754,
      "step": 3394
    },
    {
      "epoch": 0.16171428571428573,
      "grad_norm": 0.03612351790070534,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5679268836975098,
      "step": 3396
    },
    {
      "epoch": 0.16180952380952382,
      "grad_norm": 0.03698921948671341,
      "learning_rate": 0.024000000208616257,
      "loss": 2.603511333465576,
      "step": 3398
    },
    {
      "epoch": 0.1619047619047619,
      "grad_norm": 0.04109130799770355,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6019320487976074,
      "step": 3400
    },
    {
      "epoch": 0.162,
      "grad_norm": 0.038623981177806854,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6113646030426025,
      "step": 3402
    },
    {
      "epoch": 0.1620952380952381,
      "grad_norm": 0.03660590574145317,
      "learning_rate": 0.024000000208616257,
      "loss": 2.588685989379883,
      "step": 3404
    },
    {
      "epoch": 0.1621904761904762,
      "grad_norm": 0.03793664649128914,
      "learning_rate": 0.024000000208616257,
      "loss": 2.55141544342041,
      "step": 3406
    },
    {
      "epoch": 0.16228571428571428,
      "grad_norm": 0.035847485065460205,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5615460872650146,
      "step": 3408
    },
    {
      "epoch": 0.16238095238095238,
      "grad_norm": 0.03646889701485634,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6155221462249756,
      "step": 3410
    },
    {
      "epoch": 0.16247619047619047,
      "grad_norm": 0.036390095949172974,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6109771728515625,
      "step": 3412
    },
    {
      "epoch": 0.16257142857142856,
      "grad_norm": 0.03707512468099594,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5646607875823975,
      "step": 3414
    },
    {
      "epoch": 0.16266666666666665,
      "grad_norm": 0.03661083057522774,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6156845092773438,
      "step": 3416
    },
    {
      "epoch": 0.16276190476190477,
      "grad_norm": 0.03813346102833748,
      "learning_rate": 0.024000000208616257,
      "loss": 2.630807399749756,
      "step": 3418
    },
    {
      "epoch": 0.16285714285714287,
      "grad_norm": 0.03798035904765129,
      "learning_rate": 0.024000000208616257,
      "loss": 2.56135892868042,
      "step": 3420
    },
    {
      "epoch": 0.16295238095238096,
      "grad_norm": 0.03608660399913788,
      "learning_rate": 0.024000000208616257,
      "loss": 2.609961748123169,
      "step": 3422
    },
    {
      "epoch": 0.16304761904761905,
      "grad_norm": 0.0365324430167675,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5857741832733154,
      "step": 3424
    },
    {
      "epoch": 0.16314285714285715,
      "grad_norm": 0.03628375753760338,
      "learning_rate": 0.024000000208616257,
      "loss": 2.600064754486084,
      "step": 3426
    },
    {
      "epoch": 0.16323809523809524,
      "grad_norm": 0.0378803126513958,
      "learning_rate": 0.024000000208616257,
      "loss": 2.570301055908203,
      "step": 3428
    },
    {
      "epoch": 0.16333333333333333,
      "grad_norm": 0.03707236424088478,
      "learning_rate": 0.024000000208616257,
      "loss": 2.585999011993408,
      "step": 3430
    },
    {
      "epoch": 0.16342857142857142,
      "grad_norm": 0.036202870309352875,
      "learning_rate": 0.024000000208616257,
      "loss": 2.579110622406006,
      "step": 3432
    },
    {
      "epoch": 0.16352380952380952,
      "grad_norm": 0.037235550582408905,
      "learning_rate": 0.024000000208616257,
      "loss": 2.587153196334839,
      "step": 3434
    },
    {
      "epoch": 0.1636190476190476,
      "grad_norm": 0.03785668686032295,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6179275512695312,
      "step": 3436
    },
    {
      "epoch": 0.1637142857142857,
      "grad_norm": 0.03860275819897652,
      "learning_rate": 0.024000000208616257,
      "loss": 2.570878505706787,
      "step": 3438
    },
    {
      "epoch": 0.16380952380952382,
      "grad_norm": 0.04103758558630943,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5863447189331055,
      "step": 3440
    },
    {
      "epoch": 0.16390476190476191,
      "grad_norm": 0.03937200456857681,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6026244163513184,
      "step": 3442
    },
    {
      "epoch": 0.164,
      "grad_norm": 0.037641383707523346,
      "learning_rate": 0.024000000208616257,
      "loss": 2.596400260925293,
      "step": 3444
    },
    {
      "epoch": 0.1640952380952381,
      "grad_norm": 0.04015339910984039,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5868072509765625,
      "step": 3446
    },
    {
      "epoch": 0.1641904761904762,
      "grad_norm": 0.03847150877118111,
      "learning_rate": 0.024000000208616257,
      "loss": 2.572628974914551,
      "step": 3448
    },
    {
      "epoch": 0.16428571428571428,
      "grad_norm": 0.036505747586488724,
      "learning_rate": 0.024000000208616257,
      "loss": 2.576861619949341,
      "step": 3450
    },
    {
      "epoch": 0.16438095238095238,
      "grad_norm": 0.03616289421916008,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5881576538085938,
      "step": 3452
    },
    {
      "epoch": 0.16447619047619047,
      "grad_norm": 0.036689721047878265,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5626728534698486,
      "step": 3454
    },
    {
      "epoch": 0.16457142857142856,
      "grad_norm": 0.03737341985106468,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6060287952423096,
      "step": 3456
    },
    {
      "epoch": 0.16466666666666666,
      "grad_norm": 0.03589243441820145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6014389991760254,
      "step": 3458
    },
    {
      "epoch": 0.16476190476190475,
      "grad_norm": 0.038638778030872345,
      "learning_rate": 0.024000000208616257,
      "loss": 2.604635715484619,
      "step": 3460
    },
    {
      "epoch": 0.16485714285714287,
      "grad_norm": 0.03649429604411125,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5763425827026367,
      "step": 3462
    },
    {
      "epoch": 0.16495238095238096,
      "grad_norm": 0.03698647394776344,
      "learning_rate": 0.024000000208616257,
      "loss": 2.579378366470337,
      "step": 3464
    },
    {
      "epoch": 0.16504761904761905,
      "grad_norm": 0.03638838976621628,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5946621894836426,
      "step": 3466
    },
    {
      "epoch": 0.16514285714285715,
      "grad_norm": 0.03810504451394081,
      "learning_rate": 0.024000000208616257,
      "loss": 2.568978786468506,
      "step": 3468
    },
    {
      "epoch": 0.16523809523809524,
      "grad_norm": 0.03943786025047302,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6168923377990723,
      "step": 3470
    },
    {
      "epoch": 0.16533333333333333,
      "grad_norm": 0.03832157328724861,
      "learning_rate": 0.024000000208616257,
      "loss": 2.580315113067627,
      "step": 3472
    },
    {
      "epoch": 0.16542857142857142,
      "grad_norm": 0.03782135620713234,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5799312591552734,
      "step": 3474
    },
    {
      "epoch": 0.16552380952380952,
      "grad_norm": 0.03735024109482765,
      "learning_rate": 0.024000000208616257,
      "loss": 2.595348834991455,
      "step": 3476
    },
    {
      "epoch": 0.1656190476190476,
      "grad_norm": 0.03641368821263313,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6049492359161377,
      "step": 3478
    },
    {
      "epoch": 0.1657142857142857,
      "grad_norm": 0.03679990768432617,
      "learning_rate": 0.024000000208616257,
      "loss": 2.573033571243286,
      "step": 3480
    },
    {
      "epoch": 0.16580952380952382,
      "grad_norm": 0.03874284774065018,
      "learning_rate": 0.024000000208616257,
      "loss": 2.623642921447754,
      "step": 3482
    },
    {
      "epoch": 0.16590476190476192,
      "grad_norm": 0.038069549947977066,
      "learning_rate": 0.024000000208616257,
      "loss": 2.613168716430664,
      "step": 3484
    },
    {
      "epoch": 0.166,
      "grad_norm": 0.03733432665467262,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6016125679016113,
      "step": 3486
    },
    {
      "epoch": 0.1660952380952381,
      "grad_norm": 0.03669515252113342,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5759811401367188,
      "step": 3488
    },
    {
      "epoch": 0.1661904761904762,
      "grad_norm": 0.03785407543182373,
      "learning_rate": 0.024000000208616257,
      "loss": 2.588169574737549,
      "step": 3490
    },
    {
      "epoch": 0.1662857142857143,
      "grad_norm": 0.03908075764775276,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5397157669067383,
      "step": 3492
    },
    {
      "epoch": 0.16638095238095238,
      "grad_norm": 0.03804094344377518,
      "learning_rate": 0.024000000208616257,
      "loss": 2.591651678085327,
      "step": 3494
    },
    {
      "epoch": 0.16647619047619047,
      "grad_norm": 0.038932785391807556,
      "learning_rate": 0.024000000208616257,
      "loss": 2.585786819458008,
      "step": 3496
    },
    {
      "epoch": 0.16657142857142856,
      "grad_norm": 0.03837302699685097,
      "learning_rate": 0.024000000208616257,
      "loss": 2.570621967315674,
      "step": 3498
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.03775116801261902,
      "learning_rate": 0.024000000208616257,
      "loss": 2.593334913253784,
      "step": 3500
    },
    {
      "epoch": 0.16676190476190475,
      "grad_norm": 0.03727610781788826,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6168670654296875,
      "step": 3502
    },
    {
      "epoch": 0.16685714285714287,
      "grad_norm": 0.03580665588378906,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5962228775024414,
      "step": 3504
    },
    {
      "epoch": 0.16695238095238096,
      "grad_norm": 0.034754037857055664,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6312170028686523,
      "step": 3506
    },
    {
      "epoch": 0.16704761904761906,
      "grad_norm": 0.0368194580078125,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5954651832580566,
      "step": 3508
    },
    {
      "epoch": 0.16714285714285715,
      "grad_norm": 0.034947820007801056,
      "learning_rate": 0.024000000208616257,
      "loss": 2.591233968734741,
      "step": 3510
    },
    {
      "epoch": 0.16723809523809524,
      "grad_norm": 0.035841718316078186,
      "learning_rate": 0.024000000208616257,
      "loss": 2.613448143005371,
      "step": 3512
    },
    {
      "epoch": 0.16733333333333333,
      "grad_norm": 0.037476133555173874,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5873382091522217,
      "step": 3514
    },
    {
      "epoch": 0.16742857142857143,
      "grad_norm": 0.036380741745233536,
      "learning_rate": 0.024000000208616257,
      "loss": 2.570094347000122,
      "step": 3516
    },
    {
      "epoch": 0.16752380952380952,
      "grad_norm": 0.03665466979146004,
      "learning_rate": 0.024000000208616257,
      "loss": 2.573232650756836,
      "step": 3518
    },
    {
      "epoch": 0.1676190476190476,
      "grad_norm": 0.035988084971904755,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5923912525177,
      "step": 3520
    },
    {
      "epoch": 0.1677142857142857,
      "grad_norm": 0.036385707557201385,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6142523288726807,
      "step": 3522
    },
    {
      "epoch": 0.1678095238095238,
      "grad_norm": 0.036231014877557755,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6069140434265137,
      "step": 3524
    },
    {
      "epoch": 0.16790476190476192,
      "grad_norm": 0.036921292543411255,
      "learning_rate": 0.024000000208616257,
      "loss": 2.623587131500244,
      "step": 3526
    },
    {
      "epoch": 0.168,
      "grad_norm": 0.04018191993236542,
      "learning_rate": 0.024000000208616257,
      "loss": 2.580695152282715,
      "step": 3528
    },
    {
      "epoch": 0.1680952380952381,
      "grad_norm": 0.03644008934497833,
      "learning_rate": 0.024000000208616257,
      "loss": 2.614800453186035,
      "step": 3530
    },
    {
      "epoch": 0.1681904761904762,
      "grad_norm": 0.03673102706670761,
      "learning_rate": 0.024000000208616257,
      "loss": 2.535187244415283,
      "step": 3532
    },
    {
      "epoch": 0.1682857142857143,
      "grad_norm": 0.037223439663648605,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5671334266662598,
      "step": 3534
    },
    {
      "epoch": 0.16838095238095238,
      "grad_norm": 0.036864832043647766,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6305367946624756,
      "step": 3536
    },
    {
      "epoch": 0.16847619047619047,
      "grad_norm": 0.03546323627233505,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5995192527770996,
      "step": 3538
    },
    {
      "epoch": 0.16857142857142857,
      "grad_norm": 0.04027576372027397,
      "learning_rate": 0.024000000208616257,
      "loss": 2.650289297103882,
      "step": 3540
    },
    {
      "epoch": 0.16866666666666666,
      "grad_norm": 0.03582875058054924,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5953903198242188,
      "step": 3542
    },
    {
      "epoch": 0.16876190476190475,
      "grad_norm": 0.03773697838187218,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6257529258728027,
      "step": 3544
    },
    {
      "epoch": 0.16885714285714284,
      "grad_norm": 0.03596377372741699,
      "learning_rate": 0.024000000208616257,
      "loss": 2.58420729637146,
      "step": 3546
    },
    {
      "epoch": 0.16895238095238096,
      "grad_norm": 0.0364086851477623,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5527148246765137,
      "step": 3548
    },
    {
      "epoch": 0.16904761904761906,
      "grad_norm": 0.037436917424201965,
      "learning_rate": 0.024000000208616257,
      "loss": 2.574831962585449,
      "step": 3550
    },
    {
      "epoch": 0.16914285714285715,
      "grad_norm": 0.039463888853788376,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5630855560302734,
      "step": 3552
    },
    {
      "epoch": 0.16923809523809524,
      "grad_norm": 0.037678178399801254,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5879950523376465,
      "step": 3554
    },
    {
      "epoch": 0.16933333333333334,
      "grad_norm": 0.03604988381266594,
      "learning_rate": 0.024000000208616257,
      "loss": 2.573836326599121,
      "step": 3556
    },
    {
      "epoch": 0.16942857142857143,
      "grad_norm": 0.03617486730217934,
      "learning_rate": 0.024000000208616257,
      "loss": 2.557751178741455,
      "step": 3558
    },
    {
      "epoch": 0.16952380952380952,
      "grad_norm": 0.038458410650491714,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5980172157287598,
      "step": 3560
    },
    {
      "epoch": 0.1696190476190476,
      "grad_norm": 0.03551517426967621,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6071441173553467,
      "step": 3562
    },
    {
      "epoch": 0.1697142857142857,
      "grad_norm": 0.03787603974342346,
      "learning_rate": 0.024000000208616257,
      "loss": 2.568479537963867,
      "step": 3564
    },
    {
      "epoch": 0.1698095238095238,
      "grad_norm": 0.03516482189297676,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6213905811309814,
      "step": 3566
    },
    {
      "epoch": 0.1699047619047619,
      "grad_norm": 0.03558916971087456,
      "learning_rate": 0.024000000208616257,
      "loss": 2.621114730834961,
      "step": 3568
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.035932037979364395,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5882320404052734,
      "step": 3570
    },
    {
      "epoch": 0.1700952380952381,
      "grad_norm": 0.03620745614171028,
      "learning_rate": 0.024000000208616257,
      "loss": 2.582932472229004,
      "step": 3572
    },
    {
      "epoch": 0.1701904761904762,
      "grad_norm": 0.038171831518411636,
      "learning_rate": 0.024000000208616257,
      "loss": 2.56256103515625,
      "step": 3574
    },
    {
      "epoch": 0.1702857142857143,
      "grad_norm": 0.035574108362197876,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5865225791931152,
      "step": 3576
    },
    {
      "epoch": 0.17038095238095238,
      "grad_norm": 0.035827990621328354,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5876071453094482,
      "step": 3578
    },
    {
      "epoch": 0.17047619047619048,
      "grad_norm": 0.03737903758883476,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5964996814727783,
      "step": 3580
    },
    {
      "epoch": 0.17057142857142857,
      "grad_norm": 0.03777303174138069,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5624570846557617,
      "step": 3582
    },
    {
      "epoch": 0.17066666666666666,
      "grad_norm": 0.03596317768096924,
      "learning_rate": 0.024000000208616257,
      "loss": 2.584359884262085,
      "step": 3584
    },
    {
      "epoch": 0.17076190476190475,
      "grad_norm": 0.037259310483932495,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6028850078582764,
      "step": 3586
    },
    {
      "epoch": 0.17085714285714285,
      "grad_norm": 0.035102687776088715,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5666756629943848,
      "step": 3588
    },
    {
      "epoch": 0.17095238095238094,
      "grad_norm": 0.035649124532938004,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5990047454833984,
      "step": 3590
    },
    {
      "epoch": 0.17104761904761906,
      "grad_norm": 0.03729894012212753,
      "learning_rate": 0.024000000208616257,
      "loss": 2.582552909851074,
      "step": 3592
    },
    {
      "epoch": 0.17114285714285715,
      "grad_norm": 0.03548767417669296,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5466384887695312,
      "step": 3594
    },
    {
      "epoch": 0.17123809523809524,
      "grad_norm": 0.03531584143638611,
      "learning_rate": 0.024000000208616257,
      "loss": 2.617431402206421,
      "step": 3596
    },
    {
      "epoch": 0.17133333333333334,
      "grad_norm": 0.03597282990813255,
      "learning_rate": 0.024000000208616257,
      "loss": 2.599491596221924,
      "step": 3598
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.03751680627465248,
      "learning_rate": 0.024000000208616257,
      "loss": 2.584411144256592,
      "step": 3600
    },
    {
      "epoch": 0.17152380952380952,
      "grad_norm": 0.037576835602521896,
      "learning_rate": 0.024000000208616257,
      "loss": 2.560194492340088,
      "step": 3602
    },
    {
      "epoch": 0.17161904761904762,
      "grad_norm": 0.03712962940335274,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6017680168151855,
      "step": 3604
    },
    {
      "epoch": 0.1717142857142857,
      "grad_norm": 0.037960439920425415,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5726912021636963,
      "step": 3606
    },
    {
      "epoch": 0.1718095238095238,
      "grad_norm": 0.03876996412873268,
      "learning_rate": 0.024000000208616257,
      "loss": 2.561384677886963,
      "step": 3608
    },
    {
      "epoch": 0.1719047619047619,
      "grad_norm": 0.03482695296406746,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5985355377197266,
      "step": 3610
    },
    {
      "epoch": 0.172,
      "grad_norm": 0.035959262400865555,
      "learning_rate": 0.024000000208616257,
      "loss": 2.581573009490967,
      "step": 3612
    },
    {
      "epoch": 0.1720952380952381,
      "grad_norm": 0.03593228757381439,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5873074531555176,
      "step": 3614
    },
    {
      "epoch": 0.1721904761904762,
      "grad_norm": 0.03638030216097832,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5881476402282715,
      "step": 3616
    },
    {
      "epoch": 0.1722857142857143,
      "grad_norm": 0.03616824746131897,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6094048023223877,
      "step": 3618
    },
    {
      "epoch": 0.17238095238095238,
      "grad_norm": 0.03731926903128624,
      "learning_rate": 0.024000000208616257,
      "loss": 2.612442970275879,
      "step": 3620
    },
    {
      "epoch": 0.17247619047619048,
      "grad_norm": 0.03471209853887558,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5927488803863525,
      "step": 3622
    },
    {
      "epoch": 0.17257142857142857,
      "grad_norm": 0.03509154170751572,
      "learning_rate": 0.024000000208616257,
      "loss": 2.60040283203125,
      "step": 3624
    },
    {
      "epoch": 0.17266666666666666,
      "grad_norm": 0.03731885552406311,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5951595306396484,
      "step": 3626
    },
    {
      "epoch": 0.17276190476190476,
      "grad_norm": 0.036898862570524216,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5682528018951416,
      "step": 3628
    },
    {
      "epoch": 0.17285714285714285,
      "grad_norm": 0.03588828071951866,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5972023010253906,
      "step": 3630
    },
    {
      "epoch": 0.17295238095238094,
      "grad_norm": 0.034947700798511505,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5906033515930176,
      "step": 3632
    },
    {
      "epoch": 0.17304761904761906,
      "grad_norm": 0.035763490945100784,
      "learning_rate": 0.024000000208616257,
      "loss": 2.56508731842041,
      "step": 3634
    },
    {
      "epoch": 0.17314285714285715,
      "grad_norm": 0.036852627992630005,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5908162593841553,
      "step": 3636
    },
    {
      "epoch": 0.17323809523809525,
      "grad_norm": 0.035351671278476715,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5650949478149414,
      "step": 3638
    },
    {
      "epoch": 0.17333333333333334,
      "grad_norm": 0.03427856042981148,
      "learning_rate": 0.024000000208616257,
      "loss": 2.598670482635498,
      "step": 3640
    },
    {
      "epoch": 0.17342857142857143,
      "grad_norm": 0.03623297065496445,
      "learning_rate": 0.024000000208616257,
      "loss": 2.58864426612854,
      "step": 3642
    },
    {
      "epoch": 0.17352380952380952,
      "grad_norm": 0.03480357676744461,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5817041397094727,
      "step": 3644
    },
    {
      "epoch": 0.17361904761904762,
      "grad_norm": 0.03777971491217613,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5737428665161133,
      "step": 3646
    },
    {
      "epoch": 0.1737142857142857,
      "grad_norm": 0.03651659935712814,
      "learning_rate": 0.024000000208616257,
      "loss": 2.543006420135498,
      "step": 3648
    },
    {
      "epoch": 0.1738095238095238,
      "grad_norm": 0.036921169608831406,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5738234519958496,
      "step": 3650
    },
    {
      "epoch": 0.1739047619047619,
      "grad_norm": 0.036098722368478775,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6204605102539062,
      "step": 3652
    },
    {
      "epoch": 0.174,
      "grad_norm": 0.036098141223192215,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6146445274353027,
      "step": 3654
    },
    {
      "epoch": 0.1740952380952381,
      "grad_norm": 0.035169582813978195,
      "learning_rate": 0.024000000208616257,
      "loss": 2.592545986175537,
      "step": 3656
    },
    {
      "epoch": 0.1741904761904762,
      "grad_norm": 0.03683904558420181,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6085023880004883,
      "step": 3658
    },
    {
      "epoch": 0.1742857142857143,
      "grad_norm": 0.03676556050777435,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5953969955444336,
      "step": 3660
    },
    {
      "epoch": 0.1743809523809524,
      "grad_norm": 0.03526705875992775,
      "learning_rate": 0.024000000208616257,
      "loss": 2.55515193939209,
      "step": 3662
    },
    {
      "epoch": 0.17447619047619048,
      "grad_norm": 0.03612072765827179,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5799527168273926,
      "step": 3664
    },
    {
      "epoch": 0.17457142857142857,
      "grad_norm": 0.03832464665174484,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6143224239349365,
      "step": 3666
    },
    {
      "epoch": 0.17466666666666666,
      "grad_norm": 0.03806809335947037,
      "learning_rate": 0.024000000208616257,
      "loss": 2.594058036804199,
      "step": 3668
    },
    {
      "epoch": 0.17476190476190476,
      "grad_norm": 0.03448909893631935,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5650601387023926,
      "step": 3670
    },
    {
      "epoch": 0.17485714285714285,
      "grad_norm": 0.036144960671663284,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5896992683410645,
      "step": 3672
    },
    {
      "epoch": 0.17495238095238094,
      "grad_norm": 0.034775134176015854,
      "learning_rate": 0.024000000208616257,
      "loss": 2.628300189971924,
      "step": 3674
    },
    {
      "epoch": 0.17504761904761904,
      "grad_norm": 0.03409407660365105,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5680503845214844,
      "step": 3676
    },
    {
      "epoch": 0.17514285714285716,
      "grad_norm": 0.0348866805434227,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5674936771392822,
      "step": 3678
    },
    {
      "epoch": 0.17523809523809525,
      "grad_norm": 0.037791550159454346,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5739011764526367,
      "step": 3680
    },
    {
      "epoch": 0.17533333333333334,
      "grad_norm": 0.03485983610153198,
      "learning_rate": 0.024000000208616257,
      "loss": 2.568359851837158,
      "step": 3682
    },
    {
      "epoch": 0.17542857142857143,
      "grad_norm": 0.03463426232337952,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5831427574157715,
      "step": 3684
    },
    {
      "epoch": 0.17552380952380953,
      "grad_norm": 0.036229364573955536,
      "learning_rate": 0.024000000208616257,
      "loss": 2.603055000305176,
      "step": 3686
    },
    {
      "epoch": 0.17561904761904762,
      "grad_norm": 0.03655305504798889,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5906405448913574,
      "step": 3688
    },
    {
      "epoch": 0.1757142857142857,
      "grad_norm": 0.036985304206609726,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5781192779541016,
      "step": 3690
    },
    {
      "epoch": 0.1758095238095238,
      "grad_norm": 0.03758997470140457,
      "learning_rate": 0.024000000208616257,
      "loss": 2.603226900100708,
      "step": 3692
    },
    {
      "epoch": 0.1759047619047619,
      "grad_norm": 0.03595545142889023,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5879788398742676,
      "step": 3694
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.035379160195589066,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5790154933929443,
      "step": 3696
    },
    {
      "epoch": 0.17609523809523808,
      "grad_norm": 0.03553472086787224,
      "learning_rate": 0.024000000208616257,
      "loss": 2.606894016265869,
      "step": 3698
    },
    {
      "epoch": 0.1761904761904762,
      "grad_norm": 0.0357932411134243,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6251816749572754,
      "step": 3700
    },
    {
      "epoch": 0.1762857142857143,
      "grad_norm": 0.03533565625548363,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5976457595825195,
      "step": 3702
    },
    {
      "epoch": 0.1763809523809524,
      "grad_norm": 0.03477932885289192,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5823850631713867,
      "step": 3704
    },
    {
      "epoch": 0.17647619047619048,
      "grad_norm": 0.03873877972364426,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6059117317199707,
      "step": 3706
    },
    {
      "epoch": 0.17657142857142857,
      "grad_norm": 0.03577069938182831,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5611815452575684,
      "step": 3708
    },
    {
      "epoch": 0.17666666666666667,
      "grad_norm": 0.03615465387701988,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5618643760681152,
      "step": 3710
    },
    {
      "epoch": 0.17676190476190476,
      "grad_norm": 0.03739304468035698,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5999016761779785,
      "step": 3712
    },
    {
      "epoch": 0.17685714285714285,
      "grad_norm": 0.03572199493646622,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6072468757629395,
      "step": 3714
    },
    {
      "epoch": 0.17695238095238094,
      "grad_norm": 0.035238515585660934,
      "learning_rate": 0.024000000208616257,
      "loss": 2.58591628074646,
      "step": 3716
    },
    {
      "epoch": 0.17704761904761904,
      "grad_norm": 0.03499443456530571,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6075985431671143,
      "step": 3718
    },
    {
      "epoch": 0.17714285714285713,
      "grad_norm": 0.03582942485809326,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5918827056884766,
      "step": 3720
    },
    {
      "epoch": 0.17723809523809525,
      "grad_norm": 0.036836907267570496,
      "learning_rate": 0.024000000208616257,
      "loss": 2.571028709411621,
      "step": 3722
    },
    {
      "epoch": 0.17733333333333334,
      "grad_norm": 0.03630765527486801,
      "learning_rate": 0.024000000208616257,
      "loss": 2.580092430114746,
      "step": 3724
    },
    {
      "epoch": 0.17742857142857144,
      "grad_norm": 0.036366358399391174,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5743050575256348,
      "step": 3726
    },
    {
      "epoch": 0.17752380952380953,
      "grad_norm": 0.03660175949335098,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6147756576538086,
      "step": 3728
    },
    {
      "epoch": 0.17761904761904762,
      "grad_norm": 0.03643450886011124,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5741405487060547,
      "step": 3730
    },
    {
      "epoch": 0.1777142857142857,
      "grad_norm": 0.03450893983244896,
      "learning_rate": 0.024000000208616257,
      "loss": 2.594085216522217,
      "step": 3732
    },
    {
      "epoch": 0.1778095238095238,
      "grad_norm": 0.03618762642145157,
      "learning_rate": 0.024000000208616257,
      "loss": 2.598489284515381,
      "step": 3734
    },
    {
      "epoch": 0.1779047619047619,
      "grad_norm": 0.03568660095334053,
      "learning_rate": 0.024000000208616257,
      "loss": 2.557643413543701,
      "step": 3736
    },
    {
      "epoch": 0.178,
      "grad_norm": 0.0356903150677681,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5890588760375977,
      "step": 3738
    },
    {
      "epoch": 0.17809523809523808,
      "grad_norm": 0.03534645959734917,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6087589263916016,
      "step": 3740
    },
    {
      "epoch": 0.17819047619047618,
      "grad_norm": 0.03678276017308235,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6069393157958984,
      "step": 3742
    },
    {
      "epoch": 0.1782857142857143,
      "grad_norm": 0.03761300444602966,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5609617233276367,
      "step": 3744
    },
    {
      "epoch": 0.1783809523809524,
      "grad_norm": 0.036356858909130096,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5791022777557373,
      "step": 3746
    },
    {
      "epoch": 0.17847619047619048,
      "grad_norm": 0.03677915781736374,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5832128524780273,
      "step": 3748
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 0.03632054477930069,
      "learning_rate": 0.024000000208616257,
      "loss": 2.521916389465332,
      "step": 3750
    },
    {
      "epoch": 0.17866666666666667,
      "grad_norm": 0.03682326152920723,
      "learning_rate": 0.024000000208616257,
      "loss": 2.597667932510376,
      "step": 3752
    },
    {
      "epoch": 0.17876190476190476,
      "grad_norm": 0.035291146486997604,
      "learning_rate": 0.024000000208616257,
      "loss": 2.575679302215576,
      "step": 3754
    },
    {
      "epoch": 0.17885714285714285,
      "grad_norm": 0.03844251483678818,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5977742671966553,
      "step": 3756
    },
    {
      "epoch": 0.17895238095238095,
      "grad_norm": 0.040382757782936096,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5831048488616943,
      "step": 3758
    },
    {
      "epoch": 0.17904761904761904,
      "grad_norm": 0.0340469628572464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5819618701934814,
      "step": 3760
    },
    {
      "epoch": 0.17914285714285713,
      "grad_norm": 0.0377904511988163,
      "learning_rate": 0.024000000208616257,
      "loss": 2.579611301422119,
      "step": 3762
    },
    {
      "epoch": 0.17923809523809525,
      "grad_norm": 0.034769341349601746,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5916800498962402,
      "step": 3764
    },
    {
      "epoch": 0.17933333333333334,
      "grad_norm": 0.036123327910900116,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5613017082214355,
      "step": 3766
    },
    {
      "epoch": 0.17942857142857144,
      "grad_norm": 0.036977894604206085,
      "learning_rate": 0.024000000208616257,
      "loss": 2.586777687072754,
      "step": 3768
    },
    {
      "epoch": 0.17952380952380953,
      "grad_norm": 0.03416622430086136,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5695276260375977,
      "step": 3770
    },
    {
      "epoch": 0.17961904761904762,
      "grad_norm": 0.03839719295501709,
      "learning_rate": 0.024000000208616257,
      "loss": 2.591599702835083,
      "step": 3772
    },
    {
      "epoch": 0.17971428571428572,
      "grad_norm": 0.03493225574493408,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6083011627197266,
      "step": 3774
    },
    {
      "epoch": 0.1798095238095238,
      "grad_norm": 0.03486818075180054,
      "learning_rate": 0.024000000208616257,
      "loss": 2.565929412841797,
      "step": 3776
    },
    {
      "epoch": 0.1799047619047619,
      "grad_norm": 0.03632477670907974,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5991621017456055,
      "step": 3778
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.03698736056685448,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6066994667053223,
      "step": 3780
    },
    {
      "epoch": 0.18009523809523809,
      "grad_norm": 0.036889299750328064,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5794386863708496,
      "step": 3782
    },
    {
      "epoch": 0.18019047619047618,
      "grad_norm": 0.03622773289680481,
      "learning_rate": 0.024000000208616257,
      "loss": 2.553499698638916,
      "step": 3784
    },
    {
      "epoch": 0.1802857142857143,
      "grad_norm": 0.03733193501830101,
      "learning_rate": 0.024000000208616257,
      "loss": 2.570643186569214,
      "step": 3786
    },
    {
      "epoch": 0.1803809523809524,
      "grad_norm": 0.03909533843398094,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5848593711853027,
      "step": 3788
    },
    {
      "epoch": 0.18047619047619048,
      "grad_norm": 0.04251650348305702,
      "learning_rate": 0.024000000208616257,
      "loss": 2.589991569519043,
      "step": 3790
    },
    {
      "epoch": 0.18057142857142858,
      "grad_norm": 0.0425642728805542,
      "learning_rate": 0.024000000208616257,
      "loss": 2.569910764694214,
      "step": 3792
    },
    {
      "epoch": 0.18066666666666667,
      "grad_norm": 0.040211379528045654,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5878047943115234,
      "step": 3794
    },
    {
      "epoch": 0.18076190476190476,
      "grad_norm": 0.03971543163061142,
      "learning_rate": 0.024000000208616257,
      "loss": 2.596428394317627,
      "step": 3796
    },
    {
      "epoch": 0.18085714285714286,
      "grad_norm": 0.03757985681295395,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5731163024902344,
      "step": 3798
    },
    {
      "epoch": 0.18095238095238095,
      "grad_norm": 0.039098531007766724,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6045825481414795,
      "step": 3800
    },
    {
      "epoch": 0.18104761904761904,
      "grad_norm": 0.03863958269357681,
      "learning_rate": 0.024000000208616257,
      "loss": 2.559603452682495,
      "step": 3802
    },
    {
      "epoch": 0.18114285714285713,
      "grad_norm": 0.03727087005972862,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5800206661224365,
      "step": 3804
    },
    {
      "epoch": 0.18123809523809523,
      "grad_norm": 0.035311002284288406,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5937516689300537,
      "step": 3806
    },
    {
      "epoch": 0.18133333333333335,
      "grad_norm": 0.03637601435184479,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5942938327789307,
      "step": 3808
    },
    {
      "epoch": 0.18142857142857144,
      "grad_norm": 0.03690359368920326,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5750186443328857,
      "step": 3810
    },
    {
      "epoch": 0.18152380952380953,
      "grad_norm": 0.035629723221063614,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5644125938415527,
      "step": 3812
    },
    {
      "epoch": 0.18161904761904762,
      "grad_norm": 0.03920522704720497,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5680899620056152,
      "step": 3814
    },
    {
      "epoch": 0.18171428571428572,
      "grad_norm": 0.03598304092884064,
      "learning_rate": 0.024000000208616257,
      "loss": 2.571955680847168,
      "step": 3816
    },
    {
      "epoch": 0.1818095238095238,
      "grad_norm": 0.03703358769416809,
      "learning_rate": 0.024000000208616257,
      "loss": 2.559556245803833,
      "step": 3818
    },
    {
      "epoch": 0.1819047619047619,
      "grad_norm": 0.0338224396109581,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5974698066711426,
      "step": 3820
    },
    {
      "epoch": 0.182,
      "grad_norm": 0.03628638759255409,
      "learning_rate": 0.024000000208616257,
      "loss": 2.565671443939209,
      "step": 3822
    },
    {
      "epoch": 0.1820952380952381,
      "grad_norm": 0.03563361242413521,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5843684673309326,
      "step": 3824
    },
    {
      "epoch": 0.18219047619047618,
      "grad_norm": 0.035930778831243515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5907411575317383,
      "step": 3826
    },
    {
      "epoch": 0.18228571428571427,
      "grad_norm": 0.03542965650558472,
      "learning_rate": 0.024000000208616257,
      "loss": 2.582669734954834,
      "step": 3828
    },
    {
      "epoch": 0.1823809523809524,
      "grad_norm": 0.0352163128554821,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5982015132904053,
      "step": 3830
    },
    {
      "epoch": 0.1824761904761905,
      "grad_norm": 0.03489324077963829,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5717952251434326,
      "step": 3832
    },
    {
      "epoch": 0.18257142857142858,
      "grad_norm": 0.03707144036889076,
      "learning_rate": 0.024000000208616257,
      "loss": 2.553835391998291,
      "step": 3834
    },
    {
      "epoch": 0.18266666666666667,
      "grad_norm": 0.03687654435634613,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5953707695007324,
      "step": 3836
    },
    {
      "epoch": 0.18276190476190476,
      "grad_norm": 0.034177061170339584,
      "learning_rate": 0.024000000208616257,
      "loss": 2.579918384552002,
      "step": 3838
    },
    {
      "epoch": 0.18285714285714286,
      "grad_norm": 0.03682340681552887,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5847606658935547,
      "step": 3840
    },
    {
      "epoch": 0.18295238095238095,
      "grad_norm": 0.03682130202651024,
      "learning_rate": 0.024000000208616257,
      "loss": 2.570807456970215,
      "step": 3842
    },
    {
      "epoch": 0.18304761904761904,
      "grad_norm": 0.03474225476384163,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5558857917785645,
      "step": 3844
    },
    {
      "epoch": 0.18314285714285714,
      "grad_norm": 0.03462562710046768,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5621089935302734,
      "step": 3846
    },
    {
      "epoch": 0.18323809523809523,
      "grad_norm": 0.035473935306072235,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5694785118103027,
      "step": 3848
    },
    {
      "epoch": 0.18333333333333332,
      "grad_norm": 0.03322350233793259,
      "learning_rate": 0.024000000208616257,
      "loss": 2.551501750946045,
      "step": 3850
    },
    {
      "epoch": 0.18342857142857144,
      "grad_norm": 0.03443906456232071,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5708844661712646,
      "step": 3852
    },
    {
      "epoch": 0.18352380952380953,
      "grad_norm": 0.0343591645359993,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6071577072143555,
      "step": 3854
    },
    {
      "epoch": 0.18361904761904763,
      "grad_norm": 0.03414541110396385,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5749268531799316,
      "step": 3856
    },
    {
      "epoch": 0.18371428571428572,
      "grad_norm": 0.035436782985925674,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5797038078308105,
      "step": 3858
    },
    {
      "epoch": 0.1838095238095238,
      "grad_norm": 0.035962190479040146,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6006264686584473,
      "step": 3860
    },
    {
      "epoch": 0.1839047619047619,
      "grad_norm": 0.034405361860990524,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5177998542785645,
      "step": 3862
    },
    {
      "epoch": 0.184,
      "grad_norm": 0.03483660891652107,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5903868675231934,
      "step": 3864
    },
    {
      "epoch": 0.1840952380952381,
      "grad_norm": 0.036718521267175674,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5736422538757324,
      "step": 3866
    },
    {
      "epoch": 0.18419047619047618,
      "grad_norm": 0.03834947943687439,
      "learning_rate": 0.024000000208616257,
      "loss": 2.583667755126953,
      "step": 3868
    },
    {
      "epoch": 0.18428571428571427,
      "grad_norm": 0.033917441964149475,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5368809700012207,
      "step": 3870
    },
    {
      "epoch": 0.18438095238095237,
      "grad_norm": 0.034085649996995926,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5599677562713623,
      "step": 3872
    },
    {
      "epoch": 0.1844761904761905,
      "grad_norm": 0.03609776869416237,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5669021606445312,
      "step": 3874
    },
    {
      "epoch": 0.18457142857142858,
      "grad_norm": 0.03386789187788963,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6025452613830566,
      "step": 3876
    },
    {
      "epoch": 0.18466666666666667,
      "grad_norm": 0.03945763036608696,
      "learning_rate": 0.024000000208616257,
      "loss": 2.538090229034424,
      "step": 3878
    },
    {
      "epoch": 0.18476190476190477,
      "grad_norm": 0.03828416392207146,
      "learning_rate": 0.024000000208616257,
      "loss": 2.547985076904297,
      "step": 3880
    },
    {
      "epoch": 0.18485714285714286,
      "grad_norm": 0.03782835230231285,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5466725826263428,
      "step": 3882
    },
    {
      "epoch": 0.18495238095238095,
      "grad_norm": 0.037058766931295395,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5865139961242676,
      "step": 3884
    },
    {
      "epoch": 0.18504761904761904,
      "grad_norm": 0.03750511631369591,
      "learning_rate": 0.024000000208616257,
      "loss": 2.59661865234375,
      "step": 3886
    },
    {
      "epoch": 0.18514285714285714,
      "grad_norm": 0.03587372228503227,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5522284507751465,
      "step": 3888
    },
    {
      "epoch": 0.18523809523809523,
      "grad_norm": 0.036680918186903,
      "learning_rate": 0.024000000208616257,
      "loss": 2.540776252746582,
      "step": 3890
    },
    {
      "epoch": 0.18533333333333332,
      "grad_norm": 0.03604034706950188,
      "learning_rate": 0.024000000208616257,
      "loss": 2.556938409805298,
      "step": 3892
    },
    {
      "epoch": 0.18542857142857141,
      "grad_norm": 0.03424551710486412,
      "learning_rate": 0.024000000208616257,
      "loss": 2.572035312652588,
      "step": 3894
    },
    {
      "epoch": 0.18552380952380954,
      "grad_norm": 0.03640477731823921,
      "learning_rate": 0.024000000208616257,
      "loss": 2.543801784515381,
      "step": 3896
    },
    {
      "epoch": 0.18561904761904763,
      "grad_norm": 0.035998739302158356,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5703468322753906,
      "step": 3898
    },
    {
      "epoch": 0.18571428571428572,
      "grad_norm": 0.03624982014298439,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5546584129333496,
      "step": 3900
    },
    {
      "epoch": 0.1858095238095238,
      "grad_norm": 0.03669844940304756,
      "learning_rate": 0.024000000208616257,
      "loss": 2.579784393310547,
      "step": 3902
    },
    {
      "epoch": 0.1859047619047619,
      "grad_norm": 0.036059655249118805,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5795562267303467,
      "step": 3904
    },
    {
      "epoch": 0.186,
      "grad_norm": 0.036286402493715286,
      "learning_rate": 0.024000000208616257,
      "loss": 2.603867769241333,
      "step": 3906
    },
    {
      "epoch": 0.1860952380952381,
      "grad_norm": 0.03371820226311684,
      "learning_rate": 0.024000000208616257,
      "loss": 2.594308376312256,
      "step": 3908
    },
    {
      "epoch": 0.18619047619047618,
      "grad_norm": 0.035554610192775726,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5368824005126953,
      "step": 3910
    },
    {
      "epoch": 0.18628571428571428,
      "grad_norm": 0.035783551633358,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5571463108062744,
      "step": 3912
    },
    {
      "epoch": 0.18638095238095237,
      "grad_norm": 0.03562548756599426,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5841615200042725,
      "step": 3914
    },
    {
      "epoch": 0.1864761904761905,
      "grad_norm": 0.0368603952229023,
      "learning_rate": 0.024000000208616257,
      "loss": 2.594428062438965,
      "step": 3916
    },
    {
      "epoch": 0.18657142857142858,
      "grad_norm": 0.03434215858578682,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5495433807373047,
      "step": 3918
    },
    {
      "epoch": 0.18666666666666668,
      "grad_norm": 0.03743297606706619,
      "learning_rate": 0.024000000208616257,
      "loss": 2.569371223449707,
      "step": 3920
    },
    {
      "epoch": 0.18676190476190477,
      "grad_norm": 0.03600861504673958,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5812363624572754,
      "step": 3922
    },
    {
      "epoch": 0.18685714285714286,
      "grad_norm": 0.034476861357688904,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5817108154296875,
      "step": 3924
    },
    {
      "epoch": 0.18695238095238095,
      "grad_norm": 0.03442566469311714,
      "learning_rate": 0.024000000208616257,
      "loss": 2.580728530883789,
      "step": 3926
    },
    {
      "epoch": 0.18704761904761905,
      "grad_norm": 0.03582291677594185,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5501585006713867,
      "step": 3928
    },
    {
      "epoch": 0.18714285714285714,
      "grad_norm": 0.03480437025427818,
      "learning_rate": 0.024000000208616257,
      "loss": 2.563168525695801,
      "step": 3930
    },
    {
      "epoch": 0.18723809523809523,
      "grad_norm": 0.033831916749477386,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5686159133911133,
      "step": 3932
    },
    {
      "epoch": 0.18733333333333332,
      "grad_norm": 0.03668172284960747,
      "learning_rate": 0.024000000208616257,
      "loss": 2.567789077758789,
      "step": 3934
    },
    {
      "epoch": 0.18742857142857142,
      "grad_norm": 0.0369279719889164,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5745060443878174,
      "step": 3936
    },
    {
      "epoch": 0.18752380952380954,
      "grad_norm": 0.03529951348900795,
      "learning_rate": 0.024000000208616257,
      "loss": 2.566387176513672,
      "step": 3938
    },
    {
      "epoch": 0.18761904761904763,
      "grad_norm": 0.037536926567554474,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5819735527038574,
      "step": 3940
    },
    {
      "epoch": 0.18771428571428572,
      "grad_norm": 0.03803282603621483,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5803279876708984,
      "step": 3942
    },
    {
      "epoch": 0.18780952380952382,
      "grad_norm": 0.03888283297419548,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5800604820251465,
      "step": 3944
    },
    {
      "epoch": 0.1879047619047619,
      "grad_norm": 0.03653387352824211,
      "learning_rate": 0.024000000208616257,
      "loss": 2.602646589279175,
      "step": 3946
    },
    {
      "epoch": 0.188,
      "grad_norm": 0.03531850874423981,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5851640701293945,
      "step": 3948
    },
    {
      "epoch": 0.1880952380952381,
      "grad_norm": 0.03786034137010574,
      "learning_rate": 0.024000000208616257,
      "loss": 2.558778762817383,
      "step": 3950
    },
    {
      "epoch": 0.18819047619047619,
      "grad_norm": 0.036380134522914886,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5725481510162354,
      "step": 3952
    },
    {
      "epoch": 0.18828571428571428,
      "grad_norm": 0.03544646501541138,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6077680587768555,
      "step": 3954
    },
    {
      "epoch": 0.18838095238095237,
      "grad_norm": 0.03478200361132622,
      "learning_rate": 0.024000000208616257,
      "loss": 2.595104217529297,
      "step": 3956
    },
    {
      "epoch": 0.18847619047619046,
      "grad_norm": 0.03539995476603508,
      "learning_rate": 0.024000000208616257,
      "loss": 2.567141056060791,
      "step": 3958
    },
    {
      "epoch": 0.18857142857142858,
      "grad_norm": 0.03709389269351959,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5832438468933105,
      "step": 3960
    },
    {
      "epoch": 0.18866666666666668,
      "grad_norm": 0.03470085188746452,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5676064491271973,
      "step": 3962
    },
    {
      "epoch": 0.18876190476190477,
      "grad_norm": 0.03516855090856552,
      "learning_rate": 0.024000000208616257,
      "loss": 2.569812059402466,
      "step": 3964
    },
    {
      "epoch": 0.18885714285714286,
      "grad_norm": 0.0350259393453598,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6041622161865234,
      "step": 3966
    },
    {
      "epoch": 0.18895238095238095,
      "grad_norm": 0.034796375781297684,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5570831298828125,
      "step": 3968
    },
    {
      "epoch": 0.18904761904761905,
      "grad_norm": 0.034140463918447495,
      "learning_rate": 0.024000000208616257,
      "loss": 2.583599090576172,
      "step": 3970
    },
    {
      "epoch": 0.18914285714285714,
      "grad_norm": 0.03554283455014229,
      "learning_rate": 0.024000000208616257,
      "loss": 2.584758758544922,
      "step": 3972
    },
    {
      "epoch": 0.18923809523809523,
      "grad_norm": 0.03525828942656517,
      "learning_rate": 0.024000000208616257,
      "loss": 2.594377040863037,
      "step": 3974
    },
    {
      "epoch": 0.18933333333333333,
      "grad_norm": 0.03587576374411583,
      "learning_rate": 0.024000000208616257,
      "loss": 2.588909387588501,
      "step": 3976
    },
    {
      "epoch": 0.18942857142857142,
      "grad_norm": 0.03541038930416107,
      "learning_rate": 0.024000000208616257,
      "loss": 2.552457094192505,
      "step": 3978
    },
    {
      "epoch": 0.1895238095238095,
      "grad_norm": 0.03540955111384392,
      "learning_rate": 0.024000000208616257,
      "loss": 2.597123861312866,
      "step": 3980
    },
    {
      "epoch": 0.18961904761904763,
      "grad_norm": 0.03591640293598175,
      "learning_rate": 0.024000000208616257,
      "loss": 2.558781385421753,
      "step": 3982
    },
    {
      "epoch": 0.18971428571428572,
      "grad_norm": 0.03546721115708351,
      "learning_rate": 0.024000000208616257,
      "loss": 2.58347225189209,
      "step": 3984
    },
    {
      "epoch": 0.18980952380952382,
      "grad_norm": 0.035707972943782806,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5495967864990234,
      "step": 3986
    },
    {
      "epoch": 0.1899047619047619,
      "grad_norm": 0.038125958293676376,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5839104652404785,
      "step": 3988
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.03766465559601784,
      "learning_rate": 0.024000000208616257,
      "loss": 2.590101718902588,
      "step": 3990
    },
    {
      "epoch": 0.1900952380952381,
      "grad_norm": 0.03524955362081528,
      "learning_rate": 0.024000000208616257,
      "loss": 2.583113670349121,
      "step": 3992
    },
    {
      "epoch": 0.1901904761904762,
      "grad_norm": 0.03453271836042404,
      "learning_rate": 0.024000000208616257,
      "loss": 2.587566375732422,
      "step": 3994
    },
    {
      "epoch": 0.19028571428571428,
      "grad_norm": 0.0349983349442482,
      "learning_rate": 0.024000000208616257,
      "loss": 2.603372097015381,
      "step": 3996
    },
    {
      "epoch": 0.19038095238095237,
      "grad_norm": 0.033327214419841766,
      "learning_rate": 0.024000000208616257,
      "loss": 2.572134494781494,
      "step": 3998
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.0345207080245018,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5726029872894287,
      "step": 4000
    },
    {
      "epoch": 0.19057142857142856,
      "grad_norm": 0.035919249057769775,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5764451026916504,
      "step": 4002
    },
    {
      "epoch": 0.19066666666666668,
      "grad_norm": 0.03498078137636185,
      "learning_rate": 0.024000000208616257,
      "loss": 2.543534278869629,
      "step": 4004
    },
    {
      "epoch": 0.19076190476190477,
      "grad_norm": 0.03415418416261673,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5808145999908447,
      "step": 4006
    },
    {
      "epoch": 0.19085714285714286,
      "grad_norm": 0.04000689834356308,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5693047046661377,
      "step": 4008
    },
    {
      "epoch": 0.19095238095238096,
      "grad_norm": 0.034647099673748016,
      "learning_rate": 0.024000000208616257,
      "loss": 2.572798490524292,
      "step": 4010
    },
    {
      "epoch": 0.19104761904761905,
      "grad_norm": 0.035181835293769836,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5400123596191406,
      "step": 4012
    },
    {
      "epoch": 0.19114285714285714,
      "grad_norm": 0.0367269292473793,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5885791778564453,
      "step": 4014
    },
    {
      "epoch": 0.19123809523809523,
      "grad_norm": 0.035066112875938416,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5827269554138184,
      "step": 4016
    },
    {
      "epoch": 0.19133333333333333,
      "grad_norm": 0.036599427461624146,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5676329135894775,
      "step": 4018
    },
    {
      "epoch": 0.19142857142857142,
      "grad_norm": 0.03744552657008171,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5834617614746094,
      "step": 4020
    },
    {
      "epoch": 0.1915238095238095,
      "grad_norm": 0.03463251143693924,
      "learning_rate": 0.024000000208616257,
      "loss": 2.55588960647583,
      "step": 4022
    },
    {
      "epoch": 0.1916190476190476,
      "grad_norm": 0.036631837487220764,
      "learning_rate": 0.024000000208616257,
      "loss": 2.587717056274414,
      "step": 4024
    },
    {
      "epoch": 0.19171428571428573,
      "grad_norm": 0.035280242562294006,
      "learning_rate": 0.024000000208616257,
      "loss": 2.59883189201355,
      "step": 4026
    },
    {
      "epoch": 0.19180952380952382,
      "grad_norm": 0.03398521989583969,
      "learning_rate": 0.024000000208616257,
      "loss": 2.586668014526367,
      "step": 4028
    },
    {
      "epoch": 0.1919047619047619,
      "grad_norm": 0.03478521481156349,
      "learning_rate": 0.024000000208616257,
      "loss": 2.602464199066162,
      "step": 4030
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.03603247180581093,
      "learning_rate": 0.024000000208616257,
      "loss": 2.59920072555542,
      "step": 4032
    },
    {
      "epoch": 0.1920952380952381,
      "grad_norm": 0.0360339991748333,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6083576679229736,
      "step": 4034
    },
    {
      "epoch": 0.1921904761904762,
      "grad_norm": 0.03687717765569687,
      "learning_rate": 0.024000000208616257,
      "loss": 2.574791431427002,
      "step": 4036
    },
    {
      "epoch": 0.19228571428571428,
      "grad_norm": 0.03439399600028992,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5542335510253906,
      "step": 4038
    },
    {
      "epoch": 0.19238095238095237,
      "grad_norm": 0.035350337624549866,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5740103721618652,
      "step": 4040
    },
    {
      "epoch": 0.19247619047619047,
      "grad_norm": 0.03419196233153343,
      "learning_rate": 0.024000000208616257,
      "loss": 2.593364715576172,
      "step": 4042
    },
    {
      "epoch": 0.19257142857142856,
      "grad_norm": 0.034745100885629654,
      "learning_rate": 0.024000000208616257,
      "loss": 2.583347797393799,
      "step": 4044
    },
    {
      "epoch": 0.19266666666666668,
      "grad_norm": 0.034512653946876526,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5642800331115723,
      "step": 4046
    },
    {
      "epoch": 0.19276190476190477,
      "grad_norm": 0.035629257559776306,
      "learning_rate": 0.024000000208616257,
      "loss": 2.574430227279663,
      "step": 4048
    },
    {
      "epoch": 0.19285714285714287,
      "grad_norm": 0.03505939990282059,
      "learning_rate": 0.024000000208616257,
      "loss": 2.589724063873291,
      "step": 4050
    },
    {
      "epoch": 0.19295238095238096,
      "grad_norm": 0.034282706677913666,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5716278553009033,
      "step": 4052
    },
    {
      "epoch": 0.19304761904761905,
      "grad_norm": 0.03433636203408241,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5909717082977295,
      "step": 4054
    },
    {
      "epoch": 0.19314285714285714,
      "grad_norm": 0.033141255378723145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.586576223373413,
      "step": 4056
    },
    {
      "epoch": 0.19323809523809524,
      "grad_norm": 0.03318466618657112,
      "learning_rate": 0.024000000208616257,
      "loss": 2.582129716873169,
      "step": 4058
    },
    {
      "epoch": 0.19333333333333333,
      "grad_norm": 0.03590330109000206,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5722076892852783,
      "step": 4060
    },
    {
      "epoch": 0.19342857142857142,
      "grad_norm": 0.034424442797899246,
      "learning_rate": 0.024000000208616257,
      "loss": 2.619863271713257,
      "step": 4062
    },
    {
      "epoch": 0.19352380952380951,
      "grad_norm": 0.03711072355508804,
      "learning_rate": 0.024000000208616257,
      "loss": 2.568904399871826,
      "step": 4064
    },
    {
      "epoch": 0.1936190476190476,
      "grad_norm": 0.039717428386211395,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5601108074188232,
      "step": 4066
    },
    {
      "epoch": 0.19371428571428573,
      "grad_norm": 0.037900879979133606,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5636086463928223,
      "step": 4068
    },
    {
      "epoch": 0.19380952380952382,
      "grad_norm": 0.03543683513998985,
      "learning_rate": 0.024000000208616257,
      "loss": 2.563335418701172,
      "step": 4070
    },
    {
      "epoch": 0.1939047619047619,
      "grad_norm": 0.036185432225465775,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5899839401245117,
      "step": 4072
    },
    {
      "epoch": 0.194,
      "grad_norm": 0.03377417474985123,
      "learning_rate": 0.024000000208616257,
      "loss": 2.566890001296997,
      "step": 4074
    },
    {
      "epoch": 0.1940952380952381,
      "grad_norm": 0.03569241240620613,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6012792587280273,
      "step": 4076
    },
    {
      "epoch": 0.1941904761904762,
      "grad_norm": 0.035121772438287735,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5599584579467773,
      "step": 4078
    },
    {
      "epoch": 0.19428571428571428,
      "grad_norm": 0.035765938460826874,
      "learning_rate": 0.024000000208616257,
      "loss": 2.574533462524414,
      "step": 4080
    },
    {
      "epoch": 0.19438095238095238,
      "grad_norm": 0.03651375323534012,
      "learning_rate": 0.024000000208616257,
      "loss": 2.575179100036621,
      "step": 4082
    },
    {
      "epoch": 0.19447619047619047,
      "grad_norm": 0.032939594238996506,
      "learning_rate": 0.024000000208616257,
      "loss": 2.565250873565674,
      "step": 4084
    },
    {
      "epoch": 0.19457142857142856,
      "grad_norm": 0.033757809549570084,
      "learning_rate": 0.024000000208616257,
      "loss": 2.564136266708374,
      "step": 4086
    },
    {
      "epoch": 0.19466666666666665,
      "grad_norm": 0.036203041672706604,
      "learning_rate": 0.024000000208616257,
      "loss": 2.574443817138672,
      "step": 4088
    },
    {
      "epoch": 0.19476190476190477,
      "grad_norm": 0.0338924378156662,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5327677726745605,
      "step": 4090
    },
    {
      "epoch": 0.19485714285714287,
      "grad_norm": 0.03631781414151192,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5588722229003906,
      "step": 4092
    },
    {
      "epoch": 0.19495238095238096,
      "grad_norm": 0.03682277351617813,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5773253440856934,
      "step": 4094
    },
    {
      "epoch": 0.19504761904761905,
      "grad_norm": 0.03771039471030235,
      "learning_rate": 0.024000000208616257,
      "loss": 2.6134185791015625,
      "step": 4096
    },
    {
      "epoch": 0.19514285714285715,
      "grad_norm": 0.043583620339632034,
      "learning_rate": 0.024000000208616257,
      "loss": 2.573237180709839,
      "step": 4098
    },
    {
      "epoch": 0.19523809523809524,
      "grad_norm": 0.038749683648347855,
      "learning_rate": 0.024000000208616257,
      "loss": 2.582487106323242,
      "step": 4100
    },
    {
      "epoch": 0.19533333333333333,
      "grad_norm": 0.04303133487701416,
      "learning_rate": 0.024000000208616257,
      "loss": 2.594564437866211,
      "step": 4102
    },
    {
      "epoch": 0.19542857142857142,
      "grad_norm": 0.04366550222039223,
      "learning_rate": 0.024000000208616257,
      "loss": 2.602062463760376,
      "step": 4104
    },
    {
      "epoch": 0.19552380952380952,
      "grad_norm": 0.03739605098962784,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5859251022338867,
      "step": 4106
    },
    {
      "epoch": 0.1956190476190476,
      "grad_norm": 0.04063514992594719,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5562491416931152,
      "step": 4108
    },
    {
      "epoch": 0.1957142857142857,
      "grad_norm": 0.0402587428689003,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5946474075317383,
      "step": 4110
    },
    {
      "epoch": 0.19580952380952382,
      "grad_norm": 0.03707674890756607,
      "learning_rate": 0.024000000208616257,
      "loss": 2.563938617706299,
      "step": 4112
    },
    {
      "epoch": 0.19590476190476191,
      "grad_norm": 0.0363638699054718,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5415945053100586,
      "step": 4114
    },
    {
      "epoch": 0.196,
      "grad_norm": 0.033633146435022354,
      "learning_rate": 0.024000000208616257,
      "loss": 2.539292812347412,
      "step": 4116
    },
    {
      "epoch": 0.1960952380952381,
      "grad_norm": 0.032996051013469696,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5668439865112305,
      "step": 4118
    },
    {
      "epoch": 0.1961904761904762,
      "grad_norm": 0.03551589325070381,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5800704956054688,
      "step": 4120
    },
    {
      "epoch": 0.19628571428571429,
      "grad_norm": 0.03535579517483711,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5717945098876953,
      "step": 4122
    },
    {
      "epoch": 0.19638095238095238,
      "grad_norm": 0.0339796207845211,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5824027061462402,
      "step": 4124
    },
    {
      "epoch": 0.19647619047619047,
      "grad_norm": 0.03379741683602333,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5625414848327637,
      "step": 4126
    },
    {
      "epoch": 0.19657142857142856,
      "grad_norm": 0.03496759012341499,
      "learning_rate": 0.024000000208616257,
      "loss": 2.598557472229004,
      "step": 4128
    },
    {
      "epoch": 0.19666666666666666,
      "grad_norm": 0.034331172704696655,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5762972831726074,
      "step": 4130
    },
    {
      "epoch": 0.19676190476190475,
      "grad_norm": 0.034758783876895905,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5428030490875244,
      "step": 4132
    },
    {
      "epoch": 0.19685714285714287,
      "grad_norm": 0.0341840460896492,
      "learning_rate": 0.024000000208616257,
      "loss": 2.575894832611084,
      "step": 4134
    },
    {
      "epoch": 0.19695238095238096,
      "grad_norm": 0.03939260542392731,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5734972953796387,
      "step": 4136
    },
    {
      "epoch": 0.19704761904761905,
      "grad_norm": 0.03350234031677246,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5522074699401855,
      "step": 4138
    },
    {
      "epoch": 0.19714285714285715,
      "grad_norm": 0.033600788563489914,
      "learning_rate": 0.024000000208616257,
      "loss": 2.564110279083252,
      "step": 4140
    },
    {
      "epoch": 0.19723809523809524,
      "grad_norm": 0.03416472300887108,
      "learning_rate": 0.024000000208616257,
      "loss": 2.552288055419922,
      "step": 4142
    },
    {
      "epoch": 0.19733333333333333,
      "grad_norm": 0.035980742424726486,
      "learning_rate": 0.024000000208616257,
      "loss": 2.572021961212158,
      "step": 4144
    },
    {
      "epoch": 0.19742857142857143,
      "grad_norm": 0.035461146384477615,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5526280403137207,
      "step": 4146
    },
    {
      "epoch": 0.19752380952380952,
      "grad_norm": 0.03308216109871864,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5377674102783203,
      "step": 4148
    },
    {
      "epoch": 0.1976190476190476,
      "grad_norm": 0.03606276586651802,
      "learning_rate": 0.024000000208616257,
      "loss": 2.578195571899414,
      "step": 4150
    },
    {
      "epoch": 0.1977142857142857,
      "grad_norm": 0.034640081226825714,
      "learning_rate": 0.024000000208616257,
      "loss": 2.566316604614258,
      "step": 4152
    },
    {
      "epoch": 0.1978095238095238,
      "grad_norm": 0.03637755662202835,
      "learning_rate": 0.024000000208616257,
      "loss": 2.559434413909912,
      "step": 4154
    },
    {
      "epoch": 0.19790476190476192,
      "grad_norm": 0.035185348242521286,
      "learning_rate": 0.024000000208616257,
      "loss": 2.575758934020996,
      "step": 4156
    },
    {
      "epoch": 0.198,
      "grad_norm": 0.03437882661819458,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5567078590393066,
      "step": 4158
    },
    {
      "epoch": 0.1980952380952381,
      "grad_norm": 0.03348381072282791,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5781168937683105,
      "step": 4160
    },
    {
      "epoch": 0.1981904761904762,
      "grad_norm": 0.03479679301381111,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5755772590637207,
      "step": 4162
    },
    {
      "epoch": 0.1982857142857143,
      "grad_norm": 0.03382532298564911,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5698370933532715,
      "step": 4164
    },
    {
      "epoch": 0.19838095238095238,
      "grad_norm": 0.03474079445004463,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5536069869995117,
      "step": 4166
    },
    {
      "epoch": 0.19847619047619047,
      "grad_norm": 0.034420426934957504,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5331621170043945,
      "step": 4168
    },
    {
      "epoch": 0.19857142857142857,
      "grad_norm": 0.03360233083367348,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5695924758911133,
      "step": 4170
    },
    {
      "epoch": 0.19866666666666666,
      "grad_norm": 0.03315082564949989,
      "learning_rate": 0.024000000208616257,
      "loss": 2.550663471221924,
      "step": 4172
    },
    {
      "epoch": 0.19876190476190475,
      "grad_norm": 0.03396622836589813,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5698413848876953,
      "step": 4174
    },
    {
      "epoch": 0.19885714285714284,
      "grad_norm": 0.033119507133960724,
      "learning_rate": 0.024000000208616257,
      "loss": 2.582426071166992,
      "step": 4176
    },
    {
      "epoch": 0.19895238095238096,
      "grad_norm": 0.03445888310670853,
      "learning_rate": 0.024000000208616257,
      "loss": 2.528024196624756,
      "step": 4178
    },
    {
      "epoch": 0.19904761904761906,
      "grad_norm": 0.036749254912137985,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5548200607299805,
      "step": 4180
    },
    {
      "epoch": 0.19914285714285715,
      "grad_norm": 0.03549132123589516,
      "learning_rate": 0.024000000208616257,
      "loss": 2.52915096282959,
      "step": 4182
    },
    {
      "epoch": 0.19923809523809524,
      "grad_norm": 0.03325216472148895,
      "learning_rate": 0.024000000208616257,
      "loss": 2.549269199371338,
      "step": 4184
    },
    {
      "epoch": 0.19933333333333333,
      "grad_norm": 0.034001853317022324,
      "learning_rate": 0.024000000208616257,
      "loss": 2.544243574142456,
      "step": 4186
    },
    {
      "epoch": 0.19942857142857143,
      "grad_norm": 0.03470718860626221,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5854907035827637,
      "step": 4188
    },
    {
      "epoch": 0.19952380952380952,
      "grad_norm": 0.03501201793551445,
      "learning_rate": 0.024000000208616257,
      "loss": 2.594510316848755,
      "step": 4190
    },
    {
      "epoch": 0.1996190476190476,
      "grad_norm": 0.032622918486595154,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5490732192993164,
      "step": 4192
    },
    {
      "epoch": 0.1997142857142857,
      "grad_norm": 0.034185562282800674,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5586962699890137,
      "step": 4194
    },
    {
      "epoch": 0.1998095238095238,
      "grad_norm": 0.034773487597703934,
      "learning_rate": 0.024000000208616257,
      "loss": 2.558466911315918,
      "step": 4196
    },
    {
      "epoch": 0.19990476190476192,
      "grad_norm": 0.033346258103847504,
      "learning_rate": 0.024000000208616257,
      "loss": 2.553213596343994,
      "step": 4198
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.038092419505119324,
      "learning_rate": 0.024000000208616257,
      "loss": 2.536980628967285,
      "step": 4200
    },
    {
      "epoch": 0.2000952380952381,
      "grad_norm": 0.03703172877430916,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5176210403442383,
      "step": 4202
    },
    {
      "epoch": 0.2001904761904762,
      "grad_norm": 0.03579559177160263,
      "learning_rate": 0.024000000208616257,
      "loss": 2.521723985671997,
      "step": 4204
    },
    {
      "epoch": 0.2002857142857143,
      "grad_norm": 0.03691945970058441,
      "learning_rate": 0.024000000208616257,
      "loss": 2.563967227935791,
      "step": 4206
    },
    {
      "epoch": 0.20038095238095238,
      "grad_norm": 0.03375416249036789,
      "learning_rate": 0.024000000208616257,
      "loss": 2.559211254119873,
      "step": 4208
    },
    {
      "epoch": 0.20047619047619047,
      "grad_norm": 0.03508751466870308,
      "learning_rate": 0.024000000208616257,
      "loss": 2.528923988342285,
      "step": 4210
    },
    {
      "epoch": 0.20057142857142857,
      "grad_norm": 0.033974599093198776,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5746030807495117,
      "step": 4212
    },
    {
      "epoch": 0.20066666666666666,
      "grad_norm": 0.035566989332437515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5523791313171387,
      "step": 4214
    },
    {
      "epoch": 0.20076190476190475,
      "grad_norm": 0.03364123776555061,
      "learning_rate": 0.024000000208616257,
      "loss": 2.532118082046509,
      "step": 4216
    },
    {
      "epoch": 0.20085714285714285,
      "grad_norm": 0.03445471078157425,
      "learning_rate": 0.024000000208616257,
      "loss": 2.529230833053589,
      "step": 4218
    },
    {
      "epoch": 0.20095238095238097,
      "grad_norm": 0.03392660245299339,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5790212154388428,
      "step": 4220
    },
    {
      "epoch": 0.20104761904761906,
      "grad_norm": 0.03424451872706413,
      "learning_rate": 0.024000000208616257,
      "loss": 2.566389560699463,
      "step": 4222
    },
    {
      "epoch": 0.20114285714285715,
      "grad_norm": 0.03344564884901047,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5602786540985107,
      "step": 4224
    },
    {
      "epoch": 0.20123809523809524,
      "grad_norm": 0.03338630869984627,
      "learning_rate": 0.024000000208616257,
      "loss": 2.547391176223755,
      "step": 4226
    },
    {
      "epoch": 0.20133333333333334,
      "grad_norm": 0.034130342304706573,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5384676456451416,
      "step": 4228
    },
    {
      "epoch": 0.20142857142857143,
      "grad_norm": 0.03478436544537544,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5631625652313232,
      "step": 4230
    },
    {
      "epoch": 0.20152380952380952,
      "grad_norm": 0.0344911552965641,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5087623596191406,
      "step": 4232
    },
    {
      "epoch": 0.20161904761904761,
      "grad_norm": 0.03439908102154732,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5792431831359863,
      "step": 4234
    },
    {
      "epoch": 0.2017142857142857,
      "grad_norm": 0.03591718152165413,
      "learning_rate": 0.024000000208616257,
      "loss": 2.553229331970215,
      "step": 4236
    },
    {
      "epoch": 0.2018095238095238,
      "grad_norm": 0.036291904747486115,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5471065044403076,
      "step": 4238
    },
    {
      "epoch": 0.2019047619047619,
      "grad_norm": 0.03559035435318947,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5428764820098877,
      "step": 4240
    },
    {
      "epoch": 0.202,
      "grad_norm": 0.03476385772228241,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4972805976867676,
      "step": 4242
    },
    {
      "epoch": 0.2020952380952381,
      "grad_norm": 0.03598589077591896,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5257558822631836,
      "step": 4244
    },
    {
      "epoch": 0.2021904761904762,
      "grad_norm": 0.03531322255730629,
      "learning_rate": 0.024000000208616257,
      "loss": 2.563516139984131,
      "step": 4246
    },
    {
      "epoch": 0.2022857142857143,
      "grad_norm": 0.03370671346783638,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5285613536834717,
      "step": 4248
    },
    {
      "epoch": 0.20238095238095238,
      "grad_norm": 0.03372704237699509,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5139267444610596,
      "step": 4250
    },
    {
      "epoch": 0.20247619047619048,
      "grad_norm": 0.038478851318359375,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5600790977478027,
      "step": 4252
    },
    {
      "epoch": 0.20257142857142857,
      "grad_norm": 0.03588740527629852,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5254406929016113,
      "step": 4254
    },
    {
      "epoch": 0.20266666666666666,
      "grad_norm": 0.03408046439290047,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5484728813171387,
      "step": 4256
    },
    {
      "epoch": 0.20276190476190475,
      "grad_norm": 0.033602163195610046,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5490241050720215,
      "step": 4258
    },
    {
      "epoch": 0.20285714285714285,
      "grad_norm": 0.03280656784772873,
      "learning_rate": 0.024000000208616257,
      "loss": 2.52659273147583,
      "step": 4260
    },
    {
      "epoch": 0.20295238095238094,
      "grad_norm": 0.03715810924768448,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5310158729553223,
      "step": 4262
    },
    {
      "epoch": 0.20304761904761906,
      "grad_norm": 0.0334891676902771,
      "learning_rate": 0.024000000208616257,
      "loss": 2.569647789001465,
      "step": 4264
    },
    {
      "epoch": 0.20314285714285715,
      "grad_norm": 0.03255469724535942,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5483012199401855,
      "step": 4266
    },
    {
      "epoch": 0.20323809523809525,
      "grad_norm": 0.033610180020332336,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5678834915161133,
      "step": 4268
    },
    {
      "epoch": 0.20333333333333334,
      "grad_norm": 0.034170523285865784,
      "learning_rate": 0.024000000208616257,
      "loss": 2.554849147796631,
      "step": 4270
    },
    {
      "epoch": 0.20342857142857143,
      "grad_norm": 0.03450014069676399,
      "learning_rate": 0.024000000208616257,
      "loss": 2.542884349822998,
      "step": 4272
    },
    {
      "epoch": 0.20352380952380952,
      "grad_norm": 0.03735754266381264,
      "learning_rate": 0.024000000208616257,
      "loss": 2.547081470489502,
      "step": 4274
    },
    {
      "epoch": 0.20361904761904762,
      "grad_norm": 0.03440806269645691,
      "learning_rate": 0.024000000208616257,
      "loss": 2.525129795074463,
      "step": 4276
    },
    {
      "epoch": 0.2037142857142857,
      "grad_norm": 0.03361160308122635,
      "learning_rate": 0.024000000208616257,
      "loss": 2.536144256591797,
      "step": 4278
    },
    {
      "epoch": 0.2038095238095238,
      "grad_norm": 0.034731630235910416,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5444281101226807,
      "step": 4280
    },
    {
      "epoch": 0.2039047619047619,
      "grad_norm": 0.03444270044565201,
      "learning_rate": 0.024000000208616257,
      "loss": 2.54176664352417,
      "step": 4282
    },
    {
      "epoch": 0.204,
      "grad_norm": 0.03534238412976265,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5383758544921875,
      "step": 4284
    },
    {
      "epoch": 0.2040952380952381,
      "grad_norm": 0.0349477082490921,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5721023082733154,
      "step": 4286
    },
    {
      "epoch": 0.2041904761904762,
      "grad_norm": 0.03418055921792984,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5455541610717773,
      "step": 4288
    },
    {
      "epoch": 0.2042857142857143,
      "grad_norm": 0.034354519098997116,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5358781814575195,
      "step": 4290
    },
    {
      "epoch": 0.20438095238095239,
      "grad_norm": 0.03376094251871109,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5488271713256836,
      "step": 4292
    },
    {
      "epoch": 0.20447619047619048,
      "grad_norm": 0.03471655398607254,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5654683113098145,
      "step": 4294
    },
    {
      "epoch": 0.20457142857142857,
      "grad_norm": 0.033437296748161316,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5338683128356934,
      "step": 4296
    },
    {
      "epoch": 0.20466666666666666,
      "grad_norm": 0.03415635600686073,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5295462608337402,
      "step": 4298
    },
    {
      "epoch": 0.20476190476190476,
      "grad_norm": 0.03446052223443985,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5344467163085938,
      "step": 4300
    },
    {
      "epoch": 0.20485714285714285,
      "grad_norm": 0.03392282500863075,
      "learning_rate": 0.024000000208616257,
      "loss": 2.548213005065918,
      "step": 4302
    },
    {
      "epoch": 0.20495238095238094,
      "grad_norm": 0.035806745290756226,
      "learning_rate": 0.024000000208616257,
      "loss": 2.524418830871582,
      "step": 4304
    },
    {
      "epoch": 0.20504761904761903,
      "grad_norm": 0.03668132424354553,
      "learning_rate": 0.024000000208616257,
      "loss": 2.532484531402588,
      "step": 4306
    },
    {
      "epoch": 0.20514285714285715,
      "grad_norm": 0.03354937583208084,
      "learning_rate": 0.024000000208616257,
      "loss": 2.546436309814453,
      "step": 4308
    },
    {
      "epoch": 0.20523809523809525,
      "grad_norm": 0.03616217523813248,
      "learning_rate": 0.024000000208616257,
      "loss": 2.547828435897827,
      "step": 4310
    },
    {
      "epoch": 0.20533333333333334,
      "grad_norm": 0.03588027507066727,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5271401405334473,
      "step": 4312
    },
    {
      "epoch": 0.20542857142857143,
      "grad_norm": 0.03528290241956711,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5541863441467285,
      "step": 4314
    },
    {
      "epoch": 0.20552380952380953,
      "grad_norm": 0.03466029465198517,
      "learning_rate": 0.024000000208616257,
      "loss": 2.557539701461792,
      "step": 4316
    },
    {
      "epoch": 0.20561904761904762,
      "grad_norm": 0.03438291326165199,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5272841453552246,
      "step": 4318
    },
    {
      "epoch": 0.2057142857142857,
      "grad_norm": 0.03285382315516472,
      "learning_rate": 0.024000000208616257,
      "loss": 2.536543846130371,
      "step": 4320
    },
    {
      "epoch": 0.2058095238095238,
      "grad_norm": 0.03604944795370102,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5464882850646973,
      "step": 4322
    },
    {
      "epoch": 0.2059047619047619,
      "grad_norm": 0.034906331449747086,
      "learning_rate": 0.024000000208616257,
      "loss": 2.542004108428955,
      "step": 4324
    },
    {
      "epoch": 0.206,
      "grad_norm": 0.03771238029003143,
      "learning_rate": 0.024000000208616257,
      "loss": 2.565619945526123,
      "step": 4326
    },
    {
      "epoch": 0.2060952380952381,
      "grad_norm": 0.03677478805184364,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5475664138793945,
      "step": 4328
    },
    {
      "epoch": 0.2061904761904762,
      "grad_norm": 0.034278951585292816,
      "learning_rate": 0.024000000208616257,
      "loss": 2.515104293823242,
      "step": 4330
    },
    {
      "epoch": 0.2062857142857143,
      "grad_norm": 0.03611103072762489,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5490758419036865,
      "step": 4332
    },
    {
      "epoch": 0.2063809523809524,
      "grad_norm": 0.038032591342926025,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5485267639160156,
      "step": 4334
    },
    {
      "epoch": 0.20647619047619048,
      "grad_norm": 0.03464003652334213,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5354647636413574,
      "step": 4336
    },
    {
      "epoch": 0.20657142857142857,
      "grad_norm": 0.03314501792192459,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5331592559814453,
      "step": 4338
    },
    {
      "epoch": 0.20666666666666667,
      "grad_norm": 0.032904576510190964,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5358572006225586,
      "step": 4340
    },
    {
      "epoch": 0.20676190476190476,
      "grad_norm": 0.03331261873245239,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5389065742492676,
      "step": 4342
    },
    {
      "epoch": 0.20685714285714285,
      "grad_norm": 0.03595581650733948,
      "learning_rate": 0.024000000208616257,
      "loss": 2.494047164916992,
      "step": 4344
    },
    {
      "epoch": 0.20695238095238094,
      "grad_norm": 0.03399411588907242,
      "learning_rate": 0.024000000208616257,
      "loss": 2.527601718902588,
      "step": 4346
    },
    {
      "epoch": 0.20704761904761904,
      "grad_norm": 0.03522687032818794,
      "learning_rate": 0.024000000208616257,
      "loss": 2.535533905029297,
      "step": 4348
    },
    {
      "epoch": 0.20714285714285716,
      "grad_norm": 0.035905659198760986,
      "learning_rate": 0.024000000208616257,
      "loss": 2.525843620300293,
      "step": 4350
    },
    {
      "epoch": 0.20723809523809525,
      "grad_norm": 0.033180661499500275,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5366525650024414,
      "step": 4352
    },
    {
      "epoch": 0.20733333333333334,
      "grad_norm": 0.03493064269423485,
      "learning_rate": 0.024000000208616257,
      "loss": 2.52485728263855,
      "step": 4354
    },
    {
      "epoch": 0.20742857142857143,
      "grad_norm": 0.03337298706173897,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5178732872009277,
      "step": 4356
    },
    {
      "epoch": 0.20752380952380953,
      "grad_norm": 0.034250009804964066,
      "learning_rate": 0.024000000208616257,
      "loss": 2.514664649963379,
      "step": 4358
    },
    {
      "epoch": 0.20761904761904762,
      "grad_norm": 0.03314585238695145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.540104389190674,
      "step": 4360
    },
    {
      "epoch": 0.2077142857142857,
      "grad_norm": 0.03412733972072601,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5046305656433105,
      "step": 4362
    },
    {
      "epoch": 0.2078095238095238,
      "grad_norm": 0.033542972058057785,
      "learning_rate": 0.024000000208616257,
      "loss": 2.528446674346924,
      "step": 4364
    },
    {
      "epoch": 0.2079047619047619,
      "grad_norm": 0.034303974360227585,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5238394737243652,
      "step": 4366
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.03367145359516144,
      "learning_rate": 0.024000000208616257,
      "loss": 2.53507137298584,
      "step": 4368
    },
    {
      "epoch": 0.20809523809523808,
      "grad_norm": 0.0325499027967453,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5354156494140625,
      "step": 4370
    },
    {
      "epoch": 0.2081904761904762,
      "grad_norm": 0.0342954583466053,
      "learning_rate": 0.024000000208616257,
      "loss": 2.518108606338501,
      "step": 4372
    },
    {
      "epoch": 0.2082857142857143,
      "grad_norm": 0.0355491004884243,
      "learning_rate": 0.024000000208616257,
      "loss": 2.525071382522583,
      "step": 4374
    },
    {
      "epoch": 0.2083809523809524,
      "grad_norm": 0.03557267412543297,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5628819465637207,
      "step": 4376
    },
    {
      "epoch": 0.20847619047619048,
      "grad_norm": 0.0363098680973053,
      "learning_rate": 0.024000000208616257,
      "loss": 2.502676010131836,
      "step": 4378
    },
    {
      "epoch": 0.20857142857142857,
      "grad_norm": 0.03658955916762352,
      "learning_rate": 0.024000000208616257,
      "loss": 2.569309711456299,
      "step": 4380
    },
    {
      "epoch": 0.20866666666666667,
      "grad_norm": 0.0328185148537159,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5097224712371826,
      "step": 4382
    },
    {
      "epoch": 0.20876190476190476,
      "grad_norm": 0.033404331654310226,
      "learning_rate": 0.024000000208616257,
      "loss": 2.539158344268799,
      "step": 4384
    },
    {
      "epoch": 0.20885714285714285,
      "grad_norm": 0.033022839576005936,
      "learning_rate": 0.024000000208616257,
      "loss": 2.505321979522705,
      "step": 4386
    },
    {
      "epoch": 0.20895238095238095,
      "grad_norm": 0.03271230682730675,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5423264503479004,
      "step": 4388
    },
    {
      "epoch": 0.20904761904761904,
      "grad_norm": 0.03270036354660988,
      "learning_rate": 0.024000000208616257,
      "loss": 2.536475658416748,
      "step": 4390
    },
    {
      "epoch": 0.20914285714285713,
      "grad_norm": 0.032624728977680206,
      "learning_rate": 0.024000000208616257,
      "loss": 2.513199806213379,
      "step": 4392
    },
    {
      "epoch": 0.20923809523809525,
      "grad_norm": 0.03357968106865883,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5137739181518555,
      "step": 4394
    },
    {
      "epoch": 0.20933333333333334,
      "grad_norm": 0.03704063594341278,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5288352966308594,
      "step": 4396
    },
    {
      "epoch": 0.20942857142857144,
      "grad_norm": 0.041204676032066345,
      "learning_rate": 0.024000000208616257,
      "loss": 2.522641181945801,
      "step": 4398
    },
    {
      "epoch": 0.20952380952380953,
      "grad_norm": 0.039927005767822266,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5612282752990723,
      "step": 4400
    },
    {
      "epoch": 0.20961904761904762,
      "grad_norm": 0.03472644463181496,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4999916553497314,
      "step": 4402
    },
    {
      "epoch": 0.20971428571428571,
      "grad_norm": 0.034512702375650406,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4978413581848145,
      "step": 4404
    },
    {
      "epoch": 0.2098095238095238,
      "grad_norm": 0.034627534449100494,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5325844287872314,
      "step": 4406
    },
    {
      "epoch": 0.2099047619047619,
      "grad_norm": 0.039979320019483566,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5309534072875977,
      "step": 4408
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.038033824414014816,
      "learning_rate": 0.024000000208616257,
      "loss": 2.533867359161377,
      "step": 4410
    },
    {
      "epoch": 0.21009523809523808,
      "grad_norm": 0.03281286731362343,
      "learning_rate": 0.024000000208616257,
      "loss": 2.557868480682373,
      "step": 4412
    },
    {
      "epoch": 0.21019047619047618,
      "grad_norm": 0.03455791249871254,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4867100715637207,
      "step": 4414
    },
    {
      "epoch": 0.2102857142857143,
      "grad_norm": 0.032675351947546005,
      "learning_rate": 0.024000000208616257,
      "loss": 2.562894344329834,
      "step": 4416
    },
    {
      "epoch": 0.2103809523809524,
      "grad_norm": 0.032946377992630005,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5473110675811768,
      "step": 4418
    },
    {
      "epoch": 0.21047619047619048,
      "grad_norm": 0.03738332539796829,
      "learning_rate": 0.024000000208616257,
      "loss": 2.544037342071533,
      "step": 4420
    },
    {
      "epoch": 0.21057142857142858,
      "grad_norm": 0.0349770188331604,
      "learning_rate": 0.024000000208616257,
      "loss": 2.514040946960449,
      "step": 4422
    },
    {
      "epoch": 0.21066666666666667,
      "grad_norm": 0.033789392560720444,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5035452842712402,
      "step": 4424
    },
    {
      "epoch": 0.21076190476190476,
      "grad_norm": 0.032671403139829636,
      "learning_rate": 0.024000000208616257,
      "loss": 2.517800807952881,
      "step": 4426
    },
    {
      "epoch": 0.21085714285714285,
      "grad_norm": 0.03323913738131523,
      "learning_rate": 0.024000000208616257,
      "loss": 2.531562089920044,
      "step": 4428
    },
    {
      "epoch": 0.21095238095238095,
      "grad_norm": 0.03403555229306221,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5224225521087646,
      "step": 4430
    },
    {
      "epoch": 0.21104761904761904,
      "grad_norm": 0.033003002405166626,
      "learning_rate": 0.024000000208616257,
      "loss": 2.538353443145752,
      "step": 4432
    },
    {
      "epoch": 0.21114285714285713,
      "grad_norm": 0.03236225247383118,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5520615577697754,
      "step": 4434
    },
    {
      "epoch": 0.21123809523809522,
      "grad_norm": 0.03290961682796478,
      "learning_rate": 0.024000000208616257,
      "loss": 2.534841299057007,
      "step": 4436
    },
    {
      "epoch": 0.21133333333333335,
      "grad_norm": 0.035999197512865067,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5638504028320312,
      "step": 4438
    },
    {
      "epoch": 0.21142857142857144,
      "grad_norm": 0.03413056582212448,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5225605964660645,
      "step": 4440
    },
    {
      "epoch": 0.21152380952380953,
      "grad_norm": 0.037534695118665695,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5434000492095947,
      "step": 4442
    },
    {
      "epoch": 0.21161904761904762,
      "grad_norm": 0.039412762969732285,
      "learning_rate": 0.024000000208616257,
      "loss": 2.532942295074463,
      "step": 4444
    },
    {
      "epoch": 0.21171428571428572,
      "grad_norm": 0.040636852383613586,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5380477905273438,
      "step": 4446
    },
    {
      "epoch": 0.2118095238095238,
      "grad_norm": 0.0446440614759922,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5187301635742188,
      "step": 4448
    },
    {
      "epoch": 0.2119047619047619,
      "grad_norm": 0.03875953331589699,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5435643196105957,
      "step": 4450
    },
    {
      "epoch": 0.212,
      "grad_norm": 0.035098735243082047,
      "learning_rate": 0.024000000208616257,
      "loss": 2.50911021232605,
      "step": 4452
    },
    {
      "epoch": 0.2120952380952381,
      "grad_norm": 0.03352537006139755,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5244617462158203,
      "step": 4454
    },
    {
      "epoch": 0.21219047619047618,
      "grad_norm": 0.03236570581793785,
      "learning_rate": 0.024000000208616257,
      "loss": 2.491126775741577,
      "step": 4456
    },
    {
      "epoch": 0.21228571428571427,
      "grad_norm": 0.033949751406908035,
      "learning_rate": 0.024000000208616257,
      "loss": 2.532191753387451,
      "step": 4458
    },
    {
      "epoch": 0.2123809523809524,
      "grad_norm": 0.0338665246963501,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5266828536987305,
      "step": 4460
    },
    {
      "epoch": 0.21247619047619049,
      "grad_norm": 0.035945914685726166,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5167245864868164,
      "step": 4462
    },
    {
      "epoch": 0.21257142857142858,
      "grad_norm": 0.0345463752746582,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5311954021453857,
      "step": 4464
    },
    {
      "epoch": 0.21266666666666667,
      "grad_norm": 0.033228322863578796,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5617475509643555,
      "step": 4466
    },
    {
      "epoch": 0.21276190476190476,
      "grad_norm": 0.03718763589859009,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5259196758270264,
      "step": 4468
    },
    {
      "epoch": 0.21285714285714286,
      "grad_norm": 0.03823253884911537,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5431456565856934,
      "step": 4470
    },
    {
      "epoch": 0.21295238095238095,
      "grad_norm": 0.036060940474271774,
      "learning_rate": 0.024000000208616257,
      "loss": 2.54702091217041,
      "step": 4472
    },
    {
      "epoch": 0.21304761904761904,
      "grad_norm": 0.035043928772211075,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5182619094848633,
      "step": 4474
    },
    {
      "epoch": 0.21314285714285713,
      "grad_norm": 0.036386262625455856,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5487160682678223,
      "step": 4476
    },
    {
      "epoch": 0.21323809523809523,
      "grad_norm": 0.033398017287254333,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5150184631347656,
      "step": 4478
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.03358172997832298,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5187830924987793,
      "step": 4480
    },
    {
      "epoch": 0.21342857142857144,
      "grad_norm": 0.03653724119067192,
      "learning_rate": 0.024000000208616257,
      "loss": 2.543489694595337,
      "step": 4482
    },
    {
      "epoch": 0.21352380952380953,
      "grad_norm": 0.03563816100358963,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5448641777038574,
      "step": 4484
    },
    {
      "epoch": 0.21361904761904763,
      "grad_norm": 0.03284958377480507,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5092697143554688,
      "step": 4486
    },
    {
      "epoch": 0.21371428571428572,
      "grad_norm": 0.033849239349365234,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5381088256835938,
      "step": 4488
    },
    {
      "epoch": 0.2138095238095238,
      "grad_norm": 0.036182768642902374,
      "learning_rate": 0.024000000208616257,
      "loss": 2.549259662628174,
      "step": 4490
    },
    {
      "epoch": 0.2139047619047619,
      "grad_norm": 0.03546156361699104,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5267562866210938,
      "step": 4492
    },
    {
      "epoch": 0.214,
      "grad_norm": 0.033753640949726105,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5465245246887207,
      "step": 4494
    },
    {
      "epoch": 0.2140952380952381,
      "grad_norm": 0.03611188009381294,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5199685096740723,
      "step": 4496
    },
    {
      "epoch": 0.21419047619047618,
      "grad_norm": 0.03576482832431793,
      "learning_rate": 0.024000000208616257,
      "loss": 2.527052640914917,
      "step": 4498
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.03295337036252022,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5369246006011963,
      "step": 4500
    },
    {
      "epoch": 0.2143809523809524,
      "grad_norm": 0.035085730254650116,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5123918056488037,
      "step": 4502
    },
    {
      "epoch": 0.2144761904761905,
      "grad_norm": 0.03674199804663658,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5417592525482178,
      "step": 4504
    },
    {
      "epoch": 0.21457142857142858,
      "grad_norm": 0.037691380828619,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5334744453430176,
      "step": 4506
    },
    {
      "epoch": 0.21466666666666667,
      "grad_norm": 0.03839509189128876,
      "learning_rate": 0.024000000208616257,
      "loss": 2.534432888031006,
      "step": 4508
    },
    {
      "epoch": 0.21476190476190476,
      "grad_norm": 0.03833772614598274,
      "learning_rate": 0.024000000208616257,
      "loss": 2.552985668182373,
      "step": 4510
    },
    {
      "epoch": 0.21485714285714286,
      "grad_norm": 0.0371977873146534,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5208640098571777,
      "step": 4512
    },
    {
      "epoch": 0.21495238095238095,
      "grad_norm": 0.03456805273890495,
      "learning_rate": 0.024000000208616257,
      "loss": 2.531186103820801,
      "step": 4514
    },
    {
      "epoch": 0.21504761904761904,
      "grad_norm": 0.03650466725230217,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5356812477111816,
      "step": 4516
    },
    {
      "epoch": 0.21514285714285714,
      "grad_norm": 0.03770649433135986,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5185694694519043,
      "step": 4518
    },
    {
      "epoch": 0.21523809523809523,
      "grad_norm": 0.03444680944085121,
      "learning_rate": 0.024000000208616257,
      "loss": 2.547921657562256,
      "step": 4520
    },
    {
      "epoch": 0.21533333333333332,
      "grad_norm": 0.033605463802814484,
      "learning_rate": 0.024000000208616257,
      "loss": 2.540973663330078,
      "step": 4522
    },
    {
      "epoch": 0.21542857142857144,
      "grad_norm": 0.032531023025512695,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5361900329589844,
      "step": 4524
    },
    {
      "epoch": 0.21552380952380953,
      "grad_norm": 0.034784428775310516,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5268607139587402,
      "step": 4526
    },
    {
      "epoch": 0.21561904761904763,
      "grad_norm": 0.03367426618933678,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5019431114196777,
      "step": 4528
    },
    {
      "epoch": 0.21571428571428572,
      "grad_norm": 0.03489496558904648,
      "learning_rate": 0.024000000208616257,
      "loss": 2.51299786567688,
      "step": 4530
    },
    {
      "epoch": 0.2158095238095238,
      "grad_norm": 0.033294208347797394,
      "learning_rate": 0.024000000208616257,
      "loss": 2.540041923522949,
      "step": 4532
    },
    {
      "epoch": 0.2159047619047619,
      "grad_norm": 0.0333281047642231,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5490341186523438,
      "step": 4534
    },
    {
      "epoch": 0.216,
      "grad_norm": 0.03352000191807747,
      "learning_rate": 0.024000000208616257,
      "loss": 2.520047664642334,
      "step": 4536
    },
    {
      "epoch": 0.2160952380952381,
      "grad_norm": 0.03288310393691063,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5271425247192383,
      "step": 4538
    },
    {
      "epoch": 0.21619047619047618,
      "grad_norm": 0.033776070922613144,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5707273483276367,
      "step": 4540
    },
    {
      "epoch": 0.21628571428571428,
      "grad_norm": 0.03227996453642845,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5074830055236816,
      "step": 4542
    },
    {
      "epoch": 0.21638095238095237,
      "grad_norm": 0.033395055681467056,
      "learning_rate": 0.024000000208616257,
      "loss": 2.512935161590576,
      "step": 4544
    },
    {
      "epoch": 0.2164761904761905,
      "grad_norm": 0.032724812626838684,
      "learning_rate": 0.024000000208616257,
      "loss": 2.526822805404663,
      "step": 4546
    },
    {
      "epoch": 0.21657142857142858,
      "grad_norm": 0.031997498124837875,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5426082611083984,
      "step": 4548
    },
    {
      "epoch": 0.21666666666666667,
      "grad_norm": 0.032237350940704346,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5361456871032715,
      "step": 4550
    },
    {
      "epoch": 0.21676190476190477,
      "grad_norm": 0.032982662320137024,
      "learning_rate": 0.024000000208616257,
      "loss": 2.516247272491455,
      "step": 4552
    },
    {
      "epoch": 0.21685714285714286,
      "grad_norm": 0.0333019457757473,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5143885612487793,
      "step": 4554
    },
    {
      "epoch": 0.21695238095238095,
      "grad_norm": 0.040621910244226456,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5446953773498535,
      "step": 4556
    },
    {
      "epoch": 0.21704761904761904,
      "grad_norm": 0.03408082574605942,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5283713340759277,
      "step": 4558
    },
    {
      "epoch": 0.21714285714285714,
      "grad_norm": 0.03341643512248993,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4959630966186523,
      "step": 4560
    },
    {
      "epoch": 0.21723809523809523,
      "grad_norm": 0.03297030180692673,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5189292430877686,
      "step": 4562
    },
    {
      "epoch": 0.21733333333333332,
      "grad_norm": 0.03357742354273796,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5043249130249023,
      "step": 4564
    },
    {
      "epoch": 0.21742857142857142,
      "grad_norm": 0.0326324924826622,
      "learning_rate": 0.024000000208616257,
      "loss": 2.516298294067383,
      "step": 4566
    },
    {
      "epoch": 0.21752380952380954,
      "grad_norm": 0.03301847726106644,
      "learning_rate": 0.024000000208616257,
      "loss": 2.528064012527466,
      "step": 4568
    },
    {
      "epoch": 0.21761904761904763,
      "grad_norm": 0.03308906778693199,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5097556114196777,
      "step": 4570
    },
    {
      "epoch": 0.21771428571428572,
      "grad_norm": 0.03181307762861252,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5526371002197266,
      "step": 4572
    },
    {
      "epoch": 0.21780952380952381,
      "grad_norm": 0.03568853437900543,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5395641326904297,
      "step": 4574
    },
    {
      "epoch": 0.2179047619047619,
      "grad_norm": 0.033837441354990005,
      "learning_rate": 0.024000000208616257,
      "loss": 2.539579153060913,
      "step": 4576
    },
    {
      "epoch": 0.218,
      "grad_norm": 0.033466652035713196,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5416531562805176,
      "step": 4578
    },
    {
      "epoch": 0.2180952380952381,
      "grad_norm": 0.03312097117304802,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5247278213500977,
      "step": 4580
    },
    {
      "epoch": 0.21819047619047618,
      "grad_norm": 0.034171611070632935,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5573554039001465,
      "step": 4582
    },
    {
      "epoch": 0.21828571428571428,
      "grad_norm": 0.03470749408006668,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5190935134887695,
      "step": 4584
    },
    {
      "epoch": 0.21838095238095237,
      "grad_norm": 0.034388720989227295,
      "learning_rate": 0.024000000208616257,
      "loss": 2.518796682357788,
      "step": 4586
    },
    {
      "epoch": 0.21847619047619046,
      "grad_norm": 0.03461368754506111,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5102837085723877,
      "step": 4588
    },
    {
      "epoch": 0.21857142857142858,
      "grad_norm": 0.03539600223302841,
      "learning_rate": 0.024000000208616257,
      "loss": 2.51753306388855,
      "step": 4590
    },
    {
      "epoch": 0.21866666666666668,
      "grad_norm": 0.03675961121916771,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5339317321777344,
      "step": 4592
    },
    {
      "epoch": 0.21876190476190477,
      "grad_norm": 0.03296837955713272,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5272297859191895,
      "step": 4594
    },
    {
      "epoch": 0.21885714285714286,
      "grad_norm": 0.03438437357544899,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5436453819274902,
      "step": 4596
    },
    {
      "epoch": 0.21895238095238095,
      "grad_norm": 0.033531494438648224,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5085911750793457,
      "step": 4598
    },
    {
      "epoch": 0.21904761904761905,
      "grad_norm": 0.034649308770895004,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5385546684265137,
      "step": 4600
    },
    {
      "epoch": 0.21914285714285714,
      "grad_norm": 0.03643177077174187,
      "learning_rate": 0.024000000208616257,
      "loss": 2.498157501220703,
      "step": 4602
    },
    {
      "epoch": 0.21923809523809523,
      "grad_norm": 0.03386911004781723,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5184483528137207,
      "step": 4604
    },
    {
      "epoch": 0.21933333333333332,
      "grad_norm": 0.0377119816839695,
      "learning_rate": 0.024000000208616257,
      "loss": 2.502091884613037,
      "step": 4606
    },
    {
      "epoch": 0.21942857142857142,
      "grad_norm": 0.033434417098760605,
      "learning_rate": 0.024000000208616257,
      "loss": 2.481804847717285,
      "step": 4608
    },
    {
      "epoch": 0.2195238095238095,
      "grad_norm": 0.03314419835805893,
      "learning_rate": 0.024000000208616257,
      "loss": 2.532463550567627,
      "step": 4610
    },
    {
      "epoch": 0.21961904761904763,
      "grad_norm": 0.03479830175638199,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5285964012145996,
      "step": 4612
    },
    {
      "epoch": 0.21971428571428572,
      "grad_norm": 0.03205056115984917,
      "learning_rate": 0.024000000208616257,
      "loss": 2.505227565765381,
      "step": 4614
    },
    {
      "epoch": 0.21980952380952382,
      "grad_norm": 0.03296376019716263,
      "learning_rate": 0.024000000208616257,
      "loss": 2.523991584777832,
      "step": 4616
    },
    {
      "epoch": 0.2199047619047619,
      "grad_norm": 0.034120991826057434,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5006637573242188,
      "step": 4618
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.03352855145931244,
      "learning_rate": 0.024000000208616257,
      "loss": 2.509324312210083,
      "step": 4620
    },
    {
      "epoch": 0.2200952380952381,
      "grad_norm": 0.035176731646060944,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5119457244873047,
      "step": 4622
    },
    {
      "epoch": 0.2201904761904762,
      "grad_norm": 0.03612976521253586,
      "learning_rate": 0.024000000208616257,
      "loss": 2.495800495147705,
      "step": 4624
    },
    {
      "epoch": 0.22028571428571428,
      "grad_norm": 0.03457033634185791,
      "learning_rate": 0.024000000208616257,
      "loss": 2.522073745727539,
      "step": 4626
    },
    {
      "epoch": 0.22038095238095237,
      "grad_norm": 0.03367818519473076,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5222980976104736,
      "step": 4628
    },
    {
      "epoch": 0.22047619047619046,
      "grad_norm": 0.0353730246424675,
      "learning_rate": 0.024000000208616257,
      "loss": 2.504215955734253,
      "step": 4630
    },
    {
      "epoch": 0.22057142857142858,
      "grad_norm": 0.04011556878685951,
      "learning_rate": 0.024000000208616257,
      "loss": 2.510113000869751,
      "step": 4632
    },
    {
      "epoch": 0.22066666666666668,
      "grad_norm": 0.039183393120765686,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5044031143188477,
      "step": 4634
    },
    {
      "epoch": 0.22076190476190477,
      "grad_norm": 0.03414406627416611,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4958078861236572,
      "step": 4636
    },
    {
      "epoch": 0.22085714285714286,
      "grad_norm": 0.03203541785478592,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4884376525878906,
      "step": 4638
    },
    {
      "epoch": 0.22095238095238096,
      "grad_norm": 0.03392551466822624,
      "learning_rate": 0.024000000208616257,
      "loss": 2.527801752090454,
      "step": 4640
    },
    {
      "epoch": 0.22104761904761905,
      "grad_norm": 0.0336131788790226,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5130820274353027,
      "step": 4642
    },
    {
      "epoch": 0.22114285714285714,
      "grad_norm": 0.034527961164712906,
      "learning_rate": 0.024000000208616257,
      "loss": 2.509219169616699,
      "step": 4644
    },
    {
      "epoch": 0.22123809523809523,
      "grad_norm": 0.03382018953561783,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5297152996063232,
      "step": 4646
    },
    {
      "epoch": 0.22133333333333333,
      "grad_norm": 0.03411689028143883,
      "learning_rate": 0.024000000208616257,
      "loss": 2.506971597671509,
      "step": 4648
    },
    {
      "epoch": 0.22142857142857142,
      "grad_norm": 0.03284739330410957,
      "learning_rate": 0.024000000208616257,
      "loss": 2.506216526031494,
      "step": 4650
    },
    {
      "epoch": 0.2215238095238095,
      "grad_norm": 0.034139879047870636,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5216336250305176,
      "step": 4652
    },
    {
      "epoch": 0.22161904761904763,
      "grad_norm": 0.03302804380655289,
      "learning_rate": 0.024000000208616257,
      "loss": 2.521209239959717,
      "step": 4654
    },
    {
      "epoch": 0.22171428571428572,
      "grad_norm": 0.03416619822382927,
      "learning_rate": 0.024000000208616257,
      "loss": 2.494420051574707,
      "step": 4656
    },
    {
      "epoch": 0.22180952380952382,
      "grad_norm": 0.03703748807311058,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4927563667297363,
      "step": 4658
    },
    {
      "epoch": 0.2219047619047619,
      "grad_norm": 0.03289373591542244,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5145838260650635,
      "step": 4660
    },
    {
      "epoch": 0.222,
      "grad_norm": 0.033433616161346436,
      "learning_rate": 0.024000000208616257,
      "loss": 2.505565643310547,
      "step": 4662
    },
    {
      "epoch": 0.2220952380952381,
      "grad_norm": 0.034070972353219986,
      "learning_rate": 0.024000000208616257,
      "loss": 2.493682861328125,
      "step": 4664
    },
    {
      "epoch": 0.2221904761904762,
      "grad_norm": 0.03344402834773064,
      "learning_rate": 0.024000000208616257,
      "loss": 2.511896848678589,
      "step": 4666
    },
    {
      "epoch": 0.22228571428571428,
      "grad_norm": 0.033463701605796814,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4925551414489746,
      "step": 4668
    },
    {
      "epoch": 0.22238095238095237,
      "grad_norm": 0.03469507396221161,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4748990535736084,
      "step": 4670
    },
    {
      "epoch": 0.22247619047619047,
      "grad_norm": 0.032357338815927505,
      "learning_rate": 0.024000000208616257,
      "loss": 2.497532844543457,
      "step": 4672
    },
    {
      "epoch": 0.22257142857142856,
      "grad_norm": 0.03198781982064247,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4888811111450195,
      "step": 4674
    },
    {
      "epoch": 0.22266666666666668,
      "grad_norm": 0.03293994069099426,
      "learning_rate": 0.024000000208616257,
      "loss": 2.496633529663086,
      "step": 4676
    },
    {
      "epoch": 0.22276190476190477,
      "grad_norm": 0.033590011298656464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4924890995025635,
      "step": 4678
    },
    {
      "epoch": 0.22285714285714286,
      "grad_norm": 0.03398400545120239,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4944632053375244,
      "step": 4680
    },
    {
      "epoch": 0.22295238095238096,
      "grad_norm": 0.03564300760626793,
      "learning_rate": 0.024000000208616257,
      "loss": 2.493999481201172,
      "step": 4682
    },
    {
      "epoch": 0.22304761904761905,
      "grad_norm": 0.03927815705537796,
      "learning_rate": 0.024000000208616257,
      "loss": 2.490851402282715,
      "step": 4684
    },
    {
      "epoch": 0.22314285714285714,
      "grad_norm": 0.03747735917568207,
      "learning_rate": 0.024000000208616257,
      "loss": 2.482998847961426,
      "step": 4686
    },
    {
      "epoch": 0.22323809523809524,
      "grad_norm": 0.04303037375211716,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4715323448181152,
      "step": 4688
    },
    {
      "epoch": 0.22333333333333333,
      "grad_norm": 0.049164779484272,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4830098152160645,
      "step": 4690
    },
    {
      "epoch": 0.22342857142857142,
      "grad_norm": 0.03888080269098282,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5203514099121094,
      "step": 4692
    },
    {
      "epoch": 0.2235238095238095,
      "grad_norm": 0.035994600504636765,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4871225357055664,
      "step": 4694
    },
    {
      "epoch": 0.2236190476190476,
      "grad_norm": 0.03097129426896572,
      "learning_rate": 0.024000000208616257,
      "loss": 2.476266622543335,
      "step": 4696
    },
    {
      "epoch": 0.22371428571428573,
      "grad_norm": 0.03311251476407051,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4871225357055664,
      "step": 4698
    },
    {
      "epoch": 0.22380952380952382,
      "grad_norm": 0.0326714888215065,
      "learning_rate": 0.024000000208616257,
      "loss": 2.529578685760498,
      "step": 4700
    },
    {
      "epoch": 0.2239047619047619,
      "grad_norm": 0.0339653342962265,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5150890350341797,
      "step": 4702
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.032902710139751434,
      "learning_rate": 0.024000000208616257,
      "loss": 2.486980676651001,
      "step": 4704
    },
    {
      "epoch": 0.2240952380952381,
      "grad_norm": 0.03170580416917801,
      "learning_rate": 0.024000000208616257,
      "loss": 2.481626510620117,
      "step": 4706
    },
    {
      "epoch": 0.2241904761904762,
      "grad_norm": 0.03269261121749878,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4705705642700195,
      "step": 4708
    },
    {
      "epoch": 0.22428571428571428,
      "grad_norm": 0.03239228203892708,
      "learning_rate": 0.024000000208616257,
      "loss": 2.466301918029785,
      "step": 4710
    },
    {
      "epoch": 0.22438095238095238,
      "grad_norm": 0.03061547875404358,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4737918376922607,
      "step": 4712
    },
    {
      "epoch": 0.22447619047619047,
      "grad_norm": 0.03311530873179436,
      "learning_rate": 0.024000000208616257,
      "loss": 2.471072196960449,
      "step": 4714
    },
    {
      "epoch": 0.22457142857142856,
      "grad_norm": 0.032783348113298416,
      "learning_rate": 0.024000000208616257,
      "loss": 2.490107536315918,
      "step": 4716
    },
    {
      "epoch": 0.22466666666666665,
      "grad_norm": 0.03285424783825874,
      "learning_rate": 0.024000000208616257,
      "loss": 2.49782133102417,
      "step": 4718
    },
    {
      "epoch": 0.22476190476190477,
      "grad_norm": 0.034729983657598495,
      "learning_rate": 0.024000000208616257,
      "loss": 2.485132932662964,
      "step": 4720
    },
    {
      "epoch": 0.22485714285714287,
      "grad_norm": 0.03551066294312477,
      "learning_rate": 0.024000000208616257,
      "loss": 2.473823070526123,
      "step": 4722
    },
    {
      "epoch": 0.22495238095238096,
      "grad_norm": 0.03586755320429802,
      "learning_rate": 0.024000000208616257,
      "loss": 2.493802070617676,
      "step": 4724
    },
    {
      "epoch": 0.22504761904761905,
      "grad_norm": 0.03400854393839836,
      "learning_rate": 0.024000000208616257,
      "loss": 2.47141695022583,
      "step": 4726
    },
    {
      "epoch": 0.22514285714285714,
      "grad_norm": 0.03495979309082031,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4477648735046387,
      "step": 4728
    },
    {
      "epoch": 0.22523809523809524,
      "grad_norm": 0.03812415525317192,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4533185958862305,
      "step": 4730
    },
    {
      "epoch": 0.22533333333333333,
      "grad_norm": 0.03395041823387146,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4803361892700195,
      "step": 4732
    },
    {
      "epoch": 0.22542857142857142,
      "grad_norm": 0.035531654953956604,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4659948348999023,
      "step": 4734
    },
    {
      "epoch": 0.22552380952380952,
      "grad_norm": 0.03184927627444267,
      "learning_rate": 0.024000000208616257,
      "loss": 2.470083236694336,
      "step": 4736
    },
    {
      "epoch": 0.2256190476190476,
      "grad_norm": 0.03539511188864708,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5027284622192383,
      "step": 4738
    },
    {
      "epoch": 0.2257142857142857,
      "grad_norm": 0.03301730751991272,
      "learning_rate": 0.024000000208616257,
      "loss": 2.487987518310547,
      "step": 4740
    },
    {
      "epoch": 0.22580952380952382,
      "grad_norm": 0.03272976353764534,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4850611686706543,
      "step": 4742
    },
    {
      "epoch": 0.2259047619047619,
      "grad_norm": 0.03244670107960701,
      "learning_rate": 0.024000000208616257,
      "loss": 2.463935375213623,
      "step": 4744
    },
    {
      "epoch": 0.226,
      "grad_norm": 0.033064354211091995,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4852962493896484,
      "step": 4746
    },
    {
      "epoch": 0.2260952380952381,
      "grad_norm": 0.0331077016890049,
      "learning_rate": 0.024000000208616257,
      "loss": 2.453573703765869,
      "step": 4748
    },
    {
      "epoch": 0.2261904761904762,
      "grad_norm": 0.03458128869533539,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4627974033355713,
      "step": 4750
    },
    {
      "epoch": 0.22628571428571428,
      "grad_norm": 0.06377746164798737,
      "learning_rate": 0.024000000208616257,
      "loss": 2.479532480239868,
      "step": 4752
    },
    {
      "epoch": 0.22638095238095238,
      "grad_norm": 0.03307657688856125,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4590537548065186,
      "step": 4754
    },
    {
      "epoch": 0.22647619047619047,
      "grad_norm": 0.035469572991132736,
      "learning_rate": 0.024000000208616257,
      "loss": 2.446739912033081,
      "step": 4756
    },
    {
      "epoch": 0.22657142857142856,
      "grad_norm": 0.04844854772090912,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4802634716033936,
      "step": 4758
    },
    {
      "epoch": 0.22666666666666666,
      "grad_norm": 0.034526724368333817,
      "learning_rate": 0.024000000208616257,
      "loss": 2.466519832611084,
      "step": 4760
    },
    {
      "epoch": 0.22676190476190478,
      "grad_norm": 0.033050887286663055,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4680793285369873,
      "step": 4762
    },
    {
      "epoch": 0.22685714285714287,
      "grad_norm": 0.032569270581007004,
      "learning_rate": 0.024000000208616257,
      "loss": 2.503209352493286,
      "step": 4764
    },
    {
      "epoch": 0.22695238095238096,
      "grad_norm": 0.0353996679186821,
      "learning_rate": 0.024000000208616257,
      "loss": 2.511385440826416,
      "step": 4766
    },
    {
      "epoch": 0.22704761904761905,
      "grad_norm": 0.03772391378879547,
      "learning_rate": 0.024000000208616257,
      "loss": 2.46980619430542,
      "step": 4768
    },
    {
      "epoch": 0.22714285714285715,
      "grad_norm": 0.033392589539289474,
      "learning_rate": 0.024000000208616257,
      "loss": 2.467054605484009,
      "step": 4770
    },
    {
      "epoch": 0.22723809523809524,
      "grad_norm": 0.03194722533226013,
      "learning_rate": 0.024000000208616257,
      "loss": 2.470207452774048,
      "step": 4772
    },
    {
      "epoch": 0.22733333333333333,
      "grad_norm": 0.031860269606113434,
      "learning_rate": 0.024000000208616257,
      "loss": 2.480311393737793,
      "step": 4774
    },
    {
      "epoch": 0.22742857142857142,
      "grad_norm": 0.03324604406952858,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4681296348571777,
      "step": 4776
    },
    {
      "epoch": 0.22752380952380952,
      "grad_norm": 0.03417322412133217,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4642062187194824,
      "step": 4778
    },
    {
      "epoch": 0.2276190476190476,
      "grad_norm": 0.033834196627140045,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4897236824035645,
      "step": 4780
    },
    {
      "epoch": 0.2277142857142857,
      "grad_norm": 0.034872859716415405,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4771199226379395,
      "step": 4782
    },
    {
      "epoch": 0.22780952380952382,
      "grad_norm": 0.03520423546433449,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4949612617492676,
      "step": 4784
    },
    {
      "epoch": 0.22790476190476192,
      "grad_norm": 0.03513408079743385,
      "learning_rate": 0.024000000208616257,
      "loss": 2.493072986602783,
      "step": 4786
    },
    {
      "epoch": 0.228,
      "grad_norm": 0.032248999923467636,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4662251472473145,
      "step": 4788
    },
    {
      "epoch": 0.2280952380952381,
      "grad_norm": 0.03292598947882652,
      "learning_rate": 0.024000000208616257,
      "loss": 2.479724884033203,
      "step": 4790
    },
    {
      "epoch": 0.2281904761904762,
      "grad_norm": 0.033185381442308426,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5082342624664307,
      "step": 4792
    },
    {
      "epoch": 0.2282857142857143,
      "grad_norm": 0.031624529510736465,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4991869926452637,
      "step": 4794
    },
    {
      "epoch": 0.22838095238095238,
      "grad_norm": 0.03297017142176628,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4560301303863525,
      "step": 4796
    },
    {
      "epoch": 0.22847619047619047,
      "grad_norm": 0.03243574872612953,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4977002143859863,
      "step": 4798
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.03205079957842827,
      "learning_rate": 0.024000000208616257,
      "loss": 2.438514232635498,
      "step": 4800
    },
    {
      "epoch": 0.22866666666666666,
      "grad_norm": 0.03206086531281471,
      "learning_rate": 0.024000000208616257,
      "loss": 2.476102352142334,
      "step": 4802
    },
    {
      "epoch": 0.22876190476190475,
      "grad_norm": 0.03350791335105896,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4841134548187256,
      "step": 4804
    },
    {
      "epoch": 0.22885714285714287,
      "grad_norm": 0.03163295239210129,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4799461364746094,
      "step": 4806
    },
    {
      "epoch": 0.22895238095238096,
      "grad_norm": 0.03434748947620392,
      "learning_rate": 0.024000000208616257,
      "loss": 2.46063232421875,
      "step": 4808
    },
    {
      "epoch": 0.22904761904761906,
      "grad_norm": 0.035633351653814316,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4727771282196045,
      "step": 4810
    },
    {
      "epoch": 0.22914285714285715,
      "grad_norm": 0.03190416097640991,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4519174098968506,
      "step": 4812
    },
    {
      "epoch": 0.22923809523809524,
      "grad_norm": 0.032350797206163406,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4767284393310547,
      "step": 4814
    },
    {
      "epoch": 0.22933333333333333,
      "grad_norm": 0.03166979178786278,
      "learning_rate": 0.024000000208616257,
      "loss": 2.454446315765381,
      "step": 4816
    },
    {
      "epoch": 0.22942857142857143,
      "grad_norm": 0.03233880177140236,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4668867588043213,
      "step": 4818
    },
    {
      "epoch": 0.22952380952380952,
      "grad_norm": 0.03830067068338394,
      "learning_rate": 0.024000000208616257,
      "loss": 2.474236488342285,
      "step": 4820
    },
    {
      "epoch": 0.2296190476190476,
      "grad_norm": 0.03237217664718628,
      "learning_rate": 0.024000000208616257,
      "loss": 2.451942205429077,
      "step": 4822
    },
    {
      "epoch": 0.2297142857142857,
      "grad_norm": 0.031917404383420944,
      "learning_rate": 0.024000000208616257,
      "loss": 2.453573703765869,
      "step": 4824
    },
    {
      "epoch": 0.2298095238095238,
      "grad_norm": 0.031688909977674484,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4952101707458496,
      "step": 4826
    },
    {
      "epoch": 0.22990476190476192,
      "grad_norm": 0.03343017399311066,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4846277236938477,
      "step": 4828
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.03308068588376045,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4323372840881348,
      "step": 4830
    },
    {
      "epoch": 0.2300952380952381,
      "grad_norm": 0.033170945942401886,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4834601879119873,
      "step": 4832
    },
    {
      "epoch": 0.2301904761904762,
      "grad_norm": 0.03166130185127258,
      "learning_rate": 0.024000000208616257,
      "loss": 2.446880340576172,
      "step": 4834
    },
    {
      "epoch": 0.2302857142857143,
      "grad_norm": 0.03428579866886139,
      "learning_rate": 0.024000000208616257,
      "loss": 2.424360752105713,
      "step": 4836
    },
    {
      "epoch": 0.23038095238095238,
      "grad_norm": 0.034932538866996765,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4458723068237305,
      "step": 4838
    },
    {
      "epoch": 0.23047619047619047,
      "grad_norm": 0.03334333002567291,
      "learning_rate": 0.024000000208616257,
      "loss": 2.465362071990967,
      "step": 4840
    },
    {
      "epoch": 0.23057142857142857,
      "grad_norm": 0.03162964805960655,
      "learning_rate": 0.024000000208616257,
      "loss": 2.482130765914917,
      "step": 4842
    },
    {
      "epoch": 0.23066666666666666,
      "grad_norm": 0.03251060098409653,
      "learning_rate": 0.024000000208616257,
      "loss": 2.477529287338257,
      "step": 4844
    },
    {
      "epoch": 0.23076190476190475,
      "grad_norm": 0.03243162855505943,
      "learning_rate": 0.024000000208616257,
      "loss": 2.465276002883911,
      "step": 4846
    },
    {
      "epoch": 0.23085714285714284,
      "grad_norm": 0.03278768062591553,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4764599800109863,
      "step": 4848
    },
    {
      "epoch": 0.23095238095238096,
      "grad_norm": 0.033917248249053955,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4626305103302,
      "step": 4850
    },
    {
      "epoch": 0.23104761904761906,
      "grad_norm": 0.039257992058992386,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4638030529022217,
      "step": 4852
    },
    {
      "epoch": 0.23114285714285715,
      "grad_norm": 0.03927663341164589,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4814858436584473,
      "step": 4854
    },
    {
      "epoch": 0.23123809523809524,
      "grad_norm": 0.03866506740450859,
      "learning_rate": 0.024000000208616257,
      "loss": 2.442105770111084,
      "step": 4856
    },
    {
      "epoch": 0.23133333333333334,
      "grad_norm": 0.04029589146375656,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4608798027038574,
      "step": 4858
    },
    {
      "epoch": 0.23142857142857143,
      "grad_norm": 0.03455091640353203,
      "learning_rate": 0.024000000208616257,
      "loss": 2.477128505706787,
      "step": 4860
    },
    {
      "epoch": 0.23152380952380952,
      "grad_norm": 0.03391339257359505,
      "learning_rate": 0.024000000208616257,
      "loss": 2.465222120285034,
      "step": 4862
    },
    {
      "epoch": 0.2316190476190476,
      "grad_norm": 0.03234627842903137,
      "learning_rate": 0.024000000208616257,
      "loss": 2.453758955001831,
      "step": 4864
    },
    {
      "epoch": 0.2317142857142857,
      "grad_norm": 0.03263118863105774,
      "learning_rate": 0.024000000208616257,
      "loss": 2.476637363433838,
      "step": 4866
    },
    {
      "epoch": 0.2318095238095238,
      "grad_norm": 0.031855467706918716,
      "learning_rate": 0.024000000208616257,
      "loss": 2.480131149291992,
      "step": 4868
    },
    {
      "epoch": 0.2319047619047619,
      "grad_norm": 0.03309675678610802,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4571971893310547,
      "step": 4870
    },
    {
      "epoch": 0.232,
      "grad_norm": 0.03175806254148483,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4686059951782227,
      "step": 4872
    },
    {
      "epoch": 0.2320952380952381,
      "grad_norm": 0.03190731629729271,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4759392738342285,
      "step": 4874
    },
    {
      "epoch": 0.2321904761904762,
      "grad_norm": 0.032898932695388794,
      "learning_rate": 0.024000000208616257,
      "loss": 2.446603536605835,
      "step": 4876
    },
    {
      "epoch": 0.2322857142857143,
      "grad_norm": 0.032555270940065384,
      "learning_rate": 0.024000000208616257,
      "loss": 2.495856285095215,
      "step": 4878
    },
    {
      "epoch": 0.23238095238095238,
      "grad_norm": 0.03184015676379204,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4220998287200928,
      "step": 4880
    },
    {
      "epoch": 0.23247619047619048,
      "grad_norm": 0.03126243129372597,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4612503051757812,
      "step": 4882
    },
    {
      "epoch": 0.23257142857142857,
      "grad_norm": 0.032022878527641296,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4338088035583496,
      "step": 4884
    },
    {
      "epoch": 0.23266666666666666,
      "grad_norm": 0.030643606558442116,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4486780166625977,
      "step": 4886
    },
    {
      "epoch": 0.23276190476190475,
      "grad_norm": 0.031270235776901245,
      "learning_rate": 0.024000000208616257,
      "loss": 2.471735954284668,
      "step": 4888
    },
    {
      "epoch": 0.23285714285714285,
      "grad_norm": 0.03204530477523804,
      "learning_rate": 0.024000000208616257,
      "loss": 2.441758155822754,
      "step": 4890
    },
    {
      "epoch": 0.23295238095238094,
      "grad_norm": 0.03727259486913681,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4630045890808105,
      "step": 4892
    },
    {
      "epoch": 0.23304761904761906,
      "grad_norm": 0.03198296204209328,
      "learning_rate": 0.024000000208616257,
      "loss": 2.47153377532959,
      "step": 4894
    },
    {
      "epoch": 0.23314285714285715,
      "grad_norm": 0.03212233632802963,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4632205963134766,
      "step": 4896
    },
    {
      "epoch": 0.23323809523809524,
      "grad_norm": 0.0331190750002861,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4490432739257812,
      "step": 4898
    },
    {
      "epoch": 0.23333333333333334,
      "grad_norm": 0.035038381814956665,
      "learning_rate": 0.024000000208616257,
      "loss": 2.467581272125244,
      "step": 4900
    },
    {
      "epoch": 0.23342857142857143,
      "grad_norm": 0.031765926629304886,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4759902954101562,
      "step": 4902
    },
    {
      "epoch": 0.23352380952380952,
      "grad_norm": 0.032836996018886566,
      "learning_rate": 0.024000000208616257,
      "loss": 2.438633441925049,
      "step": 4904
    },
    {
      "epoch": 0.23361904761904762,
      "grad_norm": 0.03381795436143875,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4451491832733154,
      "step": 4906
    },
    {
      "epoch": 0.2337142857142857,
      "grad_norm": 0.031464677304029465,
      "learning_rate": 0.024000000208616257,
      "loss": 2.443021774291992,
      "step": 4908
    },
    {
      "epoch": 0.2338095238095238,
      "grad_norm": 0.03581545129418373,
      "learning_rate": 0.024000000208616257,
      "loss": 2.46441388130188,
      "step": 4910
    },
    {
      "epoch": 0.2339047619047619,
      "grad_norm": 0.0351780541241169,
      "learning_rate": 0.024000000208616257,
      "loss": 2.465635299682617,
      "step": 4912
    },
    {
      "epoch": 0.234,
      "grad_norm": 0.035672012716531754,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4530324935913086,
      "step": 4914
    },
    {
      "epoch": 0.2340952380952381,
      "grad_norm": 0.03306126967072487,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4424428939819336,
      "step": 4916
    },
    {
      "epoch": 0.2341904761904762,
      "grad_norm": 0.03387806937098503,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4585461616516113,
      "step": 4918
    },
    {
      "epoch": 0.2342857142857143,
      "grad_norm": 0.03452811390161514,
      "learning_rate": 0.024000000208616257,
      "loss": 2.450383186340332,
      "step": 4920
    },
    {
      "epoch": 0.23438095238095238,
      "grad_norm": 0.03414054214954376,
      "learning_rate": 0.024000000208616257,
      "loss": 2.459897518157959,
      "step": 4922
    },
    {
      "epoch": 0.23447619047619048,
      "grad_norm": 0.031202830374240875,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4620628356933594,
      "step": 4924
    },
    {
      "epoch": 0.23457142857142857,
      "grad_norm": 0.03169819712638855,
      "learning_rate": 0.024000000208616257,
      "loss": 2.460075855255127,
      "step": 4926
    },
    {
      "epoch": 0.23466666666666666,
      "grad_norm": 0.03271928057074547,
      "learning_rate": 0.024000000208616257,
      "loss": 2.428359270095825,
      "step": 4928
    },
    {
      "epoch": 0.23476190476190475,
      "grad_norm": 0.03213587403297424,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4700984954833984,
      "step": 4930
    },
    {
      "epoch": 0.23485714285714285,
      "grad_norm": 0.032468900084495544,
      "learning_rate": 0.024000000208616257,
      "loss": 2.442355155944824,
      "step": 4932
    },
    {
      "epoch": 0.23495238095238094,
      "grad_norm": 0.03291837498545647,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4532408714294434,
      "step": 4934
    },
    {
      "epoch": 0.23504761904761906,
      "grad_norm": 0.032963935285806656,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4598512649536133,
      "step": 4936
    },
    {
      "epoch": 0.23514285714285715,
      "grad_norm": 0.03321719914674759,
      "learning_rate": 0.024000000208616257,
      "loss": 2.432420253753662,
      "step": 4938
    },
    {
      "epoch": 0.23523809523809525,
      "grad_norm": 0.03281112387776375,
      "learning_rate": 0.024000000208616257,
      "loss": 2.485912322998047,
      "step": 4940
    },
    {
      "epoch": 0.23533333333333334,
      "grad_norm": 0.03154120221734047,
      "learning_rate": 0.024000000208616257,
      "loss": 2.415041446685791,
      "step": 4942
    },
    {
      "epoch": 0.23542857142857143,
      "grad_norm": 0.03073546662926674,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4707679748535156,
      "step": 4944
    },
    {
      "epoch": 0.23552380952380952,
      "grad_norm": 0.03193007782101631,
      "learning_rate": 0.024000000208616257,
      "loss": 2.455976963043213,
      "step": 4946
    },
    {
      "epoch": 0.23561904761904762,
      "grad_norm": 0.032929353415966034,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4527506828308105,
      "step": 4948
    },
    {
      "epoch": 0.2357142857142857,
      "grad_norm": 0.03670494630932808,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4717772006988525,
      "step": 4950
    },
    {
      "epoch": 0.2358095238095238,
      "grad_norm": 0.036600250750780106,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4486641883850098,
      "step": 4952
    },
    {
      "epoch": 0.2359047619047619,
      "grad_norm": 0.03244421258568764,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4315414428710938,
      "step": 4954
    },
    {
      "epoch": 0.236,
      "grad_norm": 0.03234827518463135,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4619429111480713,
      "step": 4956
    },
    {
      "epoch": 0.2360952380952381,
      "grad_norm": 0.031209534034132957,
      "learning_rate": 0.024000000208616257,
      "loss": 2.418696403503418,
      "step": 4958
    },
    {
      "epoch": 0.2361904761904762,
      "grad_norm": 0.03148431330919266,
      "learning_rate": 0.024000000208616257,
      "loss": 2.445603370666504,
      "step": 4960
    },
    {
      "epoch": 0.2362857142857143,
      "grad_norm": 0.03268168494105339,
      "learning_rate": 0.024000000208616257,
      "loss": 2.428166389465332,
      "step": 4962
    },
    {
      "epoch": 0.23638095238095239,
      "grad_norm": 0.033806633204221725,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4587693214416504,
      "step": 4964
    },
    {
      "epoch": 0.23647619047619048,
      "grad_norm": 0.03122219629585743,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4545626640319824,
      "step": 4966
    },
    {
      "epoch": 0.23657142857142857,
      "grad_norm": 0.03111090511083603,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4455060958862305,
      "step": 4968
    },
    {
      "epoch": 0.23666666666666666,
      "grad_norm": 0.03145147114992142,
      "learning_rate": 0.024000000208616257,
      "loss": 2.465826988220215,
      "step": 4970
    },
    {
      "epoch": 0.23676190476190476,
      "grad_norm": 0.0318654403090477,
      "learning_rate": 0.024000000208616257,
      "loss": 2.438039541244507,
      "step": 4972
    },
    {
      "epoch": 0.23685714285714285,
      "grad_norm": 0.032525792717933655,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4442801475524902,
      "step": 4974
    },
    {
      "epoch": 0.23695238095238094,
      "grad_norm": 0.031917039304971695,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4585940837860107,
      "step": 4976
    },
    {
      "epoch": 0.23704761904761903,
      "grad_norm": 0.03169330209493637,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4726791381835938,
      "step": 4978
    },
    {
      "epoch": 0.23714285714285716,
      "grad_norm": 0.031041502952575684,
      "learning_rate": 0.024000000208616257,
      "loss": 2.466341495513916,
      "step": 4980
    },
    {
      "epoch": 0.23723809523809525,
      "grad_norm": 0.03103133849799633,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4716062545776367,
      "step": 4982
    },
    {
      "epoch": 0.23733333333333334,
      "grad_norm": 0.03165363147854805,
      "learning_rate": 0.024000000208616257,
      "loss": 2.466639995574951,
      "step": 4984
    },
    {
      "epoch": 0.23742857142857143,
      "grad_norm": 0.0315510593354702,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4364590644836426,
      "step": 4986
    },
    {
      "epoch": 0.23752380952380953,
      "grad_norm": 0.03135395050048828,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4354429244995117,
      "step": 4988
    },
    {
      "epoch": 0.23761904761904762,
      "grad_norm": 0.03122919611632824,
      "learning_rate": 0.024000000208616257,
      "loss": 2.442389488220215,
      "step": 4990
    },
    {
      "epoch": 0.2377142857142857,
      "grad_norm": 0.03389564901590347,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4367103576660156,
      "step": 4992
    },
    {
      "epoch": 0.2378095238095238,
      "grad_norm": 0.03199462220072746,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4272329807281494,
      "step": 4994
    },
    {
      "epoch": 0.2379047619047619,
      "grad_norm": 0.031222620978951454,
      "learning_rate": 0.024000000208616257,
      "loss": 2.448513984680176,
      "step": 4996
    },
    {
      "epoch": 0.238,
      "grad_norm": 0.03075929544866085,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4437804222106934,
      "step": 4998
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.03130767121911049,
      "learning_rate": 0.024000000208616257,
      "loss": 2.455601215362549,
      "step": 5000
    },
    {
      "epoch": 0.2381904761904762,
      "grad_norm": 0.031871698796749115,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4428768157958984,
      "step": 5002
    },
    {
      "epoch": 0.2382857142857143,
      "grad_norm": 0.03178258612751961,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4369637966156006,
      "step": 5004
    },
    {
      "epoch": 0.2383809523809524,
      "grad_norm": 0.031145982444286346,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4422659873962402,
      "step": 5006
    },
    {
      "epoch": 0.23847619047619048,
      "grad_norm": 0.030917666852474213,
      "learning_rate": 0.024000000208616257,
      "loss": 2.428359270095825,
      "step": 5008
    },
    {
      "epoch": 0.23857142857142857,
      "grad_norm": 0.03079896606504917,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4289627075195312,
      "step": 5010
    },
    {
      "epoch": 0.23866666666666667,
      "grad_norm": 0.03090347908437252,
      "learning_rate": 0.024000000208616257,
      "loss": 2.435957431793213,
      "step": 5012
    },
    {
      "epoch": 0.23876190476190476,
      "grad_norm": 0.032462481409311295,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4139394760131836,
      "step": 5014
    },
    {
      "epoch": 0.23885714285714285,
      "grad_norm": 0.03191038966178894,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4671902656555176,
      "step": 5016
    },
    {
      "epoch": 0.23895238095238094,
      "grad_norm": 0.03304916247725487,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4162731170654297,
      "step": 5018
    },
    {
      "epoch": 0.23904761904761904,
      "grad_norm": 0.030691221356391907,
      "learning_rate": 0.024000000208616257,
      "loss": 2.43278169631958,
      "step": 5020
    },
    {
      "epoch": 0.23914285714285713,
      "grad_norm": 0.031826142221689224,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4596312046051025,
      "step": 5022
    },
    {
      "epoch": 0.23923809523809525,
      "grad_norm": 0.034304771572351456,
      "learning_rate": 0.024000000208616257,
      "loss": 2.439903736114502,
      "step": 5024
    },
    {
      "epoch": 0.23933333333333334,
      "grad_norm": 0.03177711367607117,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4155466556549072,
      "step": 5026
    },
    {
      "epoch": 0.23942857142857144,
      "grad_norm": 0.030806483700871468,
      "learning_rate": 0.024000000208616257,
      "loss": 2.436143398284912,
      "step": 5028
    },
    {
      "epoch": 0.23952380952380953,
      "grad_norm": 0.03254144266247749,
      "learning_rate": 0.024000000208616257,
      "loss": 2.416811943054199,
      "step": 5030
    },
    {
      "epoch": 0.23961904761904762,
      "grad_norm": 0.03276721015572548,
      "learning_rate": 0.024000000208616257,
      "loss": 2.469881534576416,
      "step": 5032
    },
    {
      "epoch": 0.2397142857142857,
      "grad_norm": 0.03270953893661499,
      "learning_rate": 0.024000000208616257,
      "loss": 2.418109178543091,
      "step": 5034
    },
    {
      "epoch": 0.2398095238095238,
      "grad_norm": 0.03366115689277649,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4488964080810547,
      "step": 5036
    },
    {
      "epoch": 0.2399047619047619,
      "grad_norm": 0.03302809223532677,
      "learning_rate": 0.024000000208616257,
      "loss": 2.435215473175049,
      "step": 5038
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.03944186493754387,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4635798931121826,
      "step": 5040
    },
    {
      "epoch": 0.24009523809523808,
      "grad_norm": 0.03841262310743332,
      "learning_rate": 0.024000000208616257,
      "loss": 2.452763080596924,
      "step": 5042
    },
    {
      "epoch": 0.2401904761904762,
      "grad_norm": 0.04079892113804817,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4526853561401367,
      "step": 5044
    },
    {
      "epoch": 0.2402857142857143,
      "grad_norm": 0.03308163583278656,
      "learning_rate": 0.024000000208616257,
      "loss": 2.452526092529297,
      "step": 5046
    },
    {
      "epoch": 0.2403809523809524,
      "grad_norm": 0.031402837485075,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4308643341064453,
      "step": 5048
    },
    {
      "epoch": 0.24047619047619048,
      "grad_norm": 0.03127182647585869,
      "learning_rate": 0.024000000208616257,
      "loss": 2.403402805328369,
      "step": 5050
    },
    {
      "epoch": 0.24057142857142857,
      "grad_norm": 0.032639604061841965,
      "learning_rate": 0.024000000208616257,
      "loss": 2.433781147003174,
      "step": 5052
    },
    {
      "epoch": 0.24066666666666667,
      "grad_norm": 0.031063782051205635,
      "learning_rate": 0.024000000208616257,
      "loss": 2.448647975921631,
      "step": 5054
    },
    {
      "epoch": 0.24076190476190476,
      "grad_norm": 0.030848462134599686,
      "learning_rate": 0.024000000208616257,
      "loss": 2.430347442626953,
      "step": 5056
    },
    {
      "epoch": 0.24085714285714285,
      "grad_norm": 0.03336739540100098,
      "learning_rate": 0.024000000208616257,
      "loss": 2.425234079360962,
      "step": 5058
    },
    {
      "epoch": 0.24095238095238095,
      "grad_norm": 0.03446685150265694,
      "learning_rate": 0.024000000208616257,
      "loss": 2.436471462249756,
      "step": 5060
    },
    {
      "epoch": 0.24104761904761904,
      "grad_norm": 0.03058784268796444,
      "learning_rate": 0.024000000208616257,
      "loss": 2.427539110183716,
      "step": 5062
    },
    {
      "epoch": 0.24114285714285713,
      "grad_norm": 0.03260588273406029,
      "learning_rate": 0.024000000208616257,
      "loss": 2.473959445953369,
      "step": 5064
    },
    {
      "epoch": 0.24123809523809525,
      "grad_norm": 0.03099987469613552,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4212918281555176,
      "step": 5066
    },
    {
      "epoch": 0.24133333333333334,
      "grad_norm": 0.03194281831383705,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4301018714904785,
      "step": 5068
    },
    {
      "epoch": 0.24142857142857144,
      "grad_norm": 0.03273751586675644,
      "learning_rate": 0.024000000208616257,
      "loss": 2.458919048309326,
      "step": 5070
    },
    {
      "epoch": 0.24152380952380953,
      "grad_norm": 0.03314734250307083,
      "learning_rate": 0.024000000208616257,
      "loss": 2.431220531463623,
      "step": 5072
    },
    {
      "epoch": 0.24161904761904762,
      "grad_norm": 0.034375905990600586,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4339160919189453,
      "step": 5074
    },
    {
      "epoch": 0.24171428571428571,
      "grad_norm": 0.031142914667725563,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4518933296203613,
      "step": 5076
    },
    {
      "epoch": 0.2418095238095238,
      "grad_norm": 0.03245391324162483,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4439516067504883,
      "step": 5078
    },
    {
      "epoch": 0.2419047619047619,
      "grad_norm": 0.031134819611907005,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4404807090759277,
      "step": 5080
    },
    {
      "epoch": 0.242,
      "grad_norm": 0.03158557042479515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4551820755004883,
      "step": 5082
    },
    {
      "epoch": 0.24209523809523809,
      "grad_norm": 0.03179480880498886,
      "learning_rate": 0.024000000208616257,
      "loss": 2.418733596801758,
      "step": 5084
    },
    {
      "epoch": 0.24219047619047618,
      "grad_norm": 0.032800834625959396,
      "learning_rate": 0.024000000208616257,
      "loss": 2.428746223449707,
      "step": 5086
    },
    {
      "epoch": 0.2422857142857143,
      "grad_norm": 0.03390571102499962,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4616050720214844,
      "step": 5088
    },
    {
      "epoch": 0.2423809523809524,
      "grad_norm": 0.030443739145994186,
      "learning_rate": 0.024000000208616257,
      "loss": 2.424319267272949,
      "step": 5090
    },
    {
      "epoch": 0.24247619047619048,
      "grad_norm": 0.03076738677918911,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4418957233428955,
      "step": 5092
    },
    {
      "epoch": 0.24257142857142858,
      "grad_norm": 0.03134721890091896,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4438211917877197,
      "step": 5094
    },
    {
      "epoch": 0.24266666666666667,
      "grad_norm": 0.03260625898838043,
      "learning_rate": 0.024000000208616257,
      "loss": 2.426510810852051,
      "step": 5096
    },
    {
      "epoch": 0.24276190476190476,
      "grad_norm": 0.033932317048311234,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4231858253479004,
      "step": 5098
    },
    {
      "epoch": 0.24285714285714285,
      "grad_norm": 0.030695075169205666,
      "learning_rate": 0.024000000208616257,
      "loss": 2.397622585296631,
      "step": 5100
    },
    {
      "epoch": 0.24295238095238095,
      "grad_norm": 0.033123329281806946,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4351375102996826,
      "step": 5102
    },
    {
      "epoch": 0.24304761904761904,
      "grad_norm": 0.03179609403014183,
      "learning_rate": 0.024000000208616257,
      "loss": 2.43538761138916,
      "step": 5104
    },
    {
      "epoch": 0.24314285714285713,
      "grad_norm": 0.03398355841636658,
      "learning_rate": 0.024000000208616257,
      "loss": 2.43318510055542,
      "step": 5106
    },
    {
      "epoch": 0.24323809523809523,
      "grad_norm": 0.03147204965353012,
      "learning_rate": 0.024000000208616257,
      "loss": 2.449779510498047,
      "step": 5108
    },
    {
      "epoch": 0.24333333333333335,
      "grad_norm": 0.03160269558429718,
      "learning_rate": 0.024000000208616257,
      "loss": 2.445330858230591,
      "step": 5110
    },
    {
      "epoch": 0.24342857142857144,
      "grad_norm": 0.03240397199988365,
      "learning_rate": 0.024000000208616257,
      "loss": 2.433645248413086,
      "step": 5112
    },
    {
      "epoch": 0.24352380952380953,
      "grad_norm": 0.031592778861522675,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4136691093444824,
      "step": 5114
    },
    {
      "epoch": 0.24361904761904762,
      "grad_norm": 0.03191974759101868,
      "learning_rate": 0.024000000208616257,
      "loss": 2.456718683242798,
      "step": 5116
    },
    {
      "epoch": 0.24371428571428572,
      "grad_norm": 0.0320778414607048,
      "learning_rate": 0.024000000208616257,
      "loss": 2.443239688873291,
      "step": 5118
    },
    {
      "epoch": 0.2438095238095238,
      "grad_norm": 0.03429703041911125,
      "learning_rate": 0.024000000208616257,
      "loss": 2.418954372406006,
      "step": 5120
    },
    {
      "epoch": 0.2439047619047619,
      "grad_norm": 0.03186912462115288,
      "learning_rate": 0.024000000208616257,
      "loss": 2.436079740524292,
      "step": 5122
    },
    {
      "epoch": 0.244,
      "grad_norm": 0.030619347468018532,
      "learning_rate": 0.024000000208616257,
      "loss": 2.438462257385254,
      "step": 5124
    },
    {
      "epoch": 0.2440952380952381,
      "grad_norm": 0.03212239593267441,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4329280853271484,
      "step": 5126
    },
    {
      "epoch": 0.24419047619047618,
      "grad_norm": 0.03162180259823799,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4421591758728027,
      "step": 5128
    },
    {
      "epoch": 0.24428571428571427,
      "grad_norm": 0.03096802905201912,
      "learning_rate": 0.024000000208616257,
      "loss": 2.442511796951294,
      "step": 5130
    },
    {
      "epoch": 0.2443809523809524,
      "grad_norm": 0.03151176497340202,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4227397441864014,
      "step": 5132
    },
    {
      "epoch": 0.24447619047619049,
      "grad_norm": 0.031776197254657745,
      "learning_rate": 0.024000000208616257,
      "loss": 2.466700315475464,
      "step": 5134
    },
    {
      "epoch": 0.24457142857142858,
      "grad_norm": 0.031946975737810135,
      "learning_rate": 0.024000000208616257,
      "loss": 2.44081449508667,
      "step": 5136
    },
    {
      "epoch": 0.24466666666666667,
      "grad_norm": 0.03297324478626251,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4492242336273193,
      "step": 5138
    },
    {
      "epoch": 0.24476190476190476,
      "grad_norm": 0.03135312348604202,
      "learning_rate": 0.024000000208616257,
      "loss": 2.438739776611328,
      "step": 5140
    },
    {
      "epoch": 0.24485714285714286,
      "grad_norm": 0.046802714467048645,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4315261840820312,
      "step": 5142
    },
    {
      "epoch": 0.24495238095238095,
      "grad_norm": 0.032544344663619995,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4568634033203125,
      "step": 5144
    },
    {
      "epoch": 0.24504761904761904,
      "grad_norm": 0.03177942335605621,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4379005432128906,
      "step": 5146
    },
    {
      "epoch": 0.24514285714285713,
      "grad_norm": 0.030634824186563492,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4551897048950195,
      "step": 5148
    },
    {
      "epoch": 0.24523809523809523,
      "grad_norm": 0.03122766688466072,
      "learning_rate": 0.024000000208616257,
      "loss": 2.431516170501709,
      "step": 5150
    },
    {
      "epoch": 0.24533333333333332,
      "grad_norm": 0.031842220574617386,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4351577758789062,
      "step": 5152
    },
    {
      "epoch": 0.24542857142857144,
      "grad_norm": 0.032036859542131424,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4063944816589355,
      "step": 5154
    },
    {
      "epoch": 0.24552380952380953,
      "grad_norm": 0.03214030712842941,
      "learning_rate": 0.024000000208616257,
      "loss": 2.454420804977417,
      "step": 5156
    },
    {
      "epoch": 0.24561904761904763,
      "grad_norm": 0.031271930783987045,
      "learning_rate": 0.024000000208616257,
      "loss": 2.43579363822937,
      "step": 5158
    },
    {
      "epoch": 0.24571428571428572,
      "grad_norm": 0.03211823105812073,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4247183799743652,
      "step": 5160
    },
    {
      "epoch": 0.2458095238095238,
      "grad_norm": 0.03172464296221733,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4152209758758545,
      "step": 5162
    },
    {
      "epoch": 0.2459047619047619,
      "grad_norm": 0.032295722514390945,
      "learning_rate": 0.024000000208616257,
      "loss": 2.445755958557129,
      "step": 5164
    },
    {
      "epoch": 0.246,
      "grad_norm": 0.03154406324028969,
      "learning_rate": 0.024000000208616257,
      "loss": 2.440610408782959,
      "step": 5166
    },
    {
      "epoch": 0.2460952380952381,
      "grad_norm": 0.03166312351822853,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4323081970214844,
      "step": 5168
    },
    {
      "epoch": 0.24619047619047618,
      "grad_norm": 0.030796948820352554,
      "learning_rate": 0.024000000208616257,
      "loss": 2.422846794128418,
      "step": 5170
    },
    {
      "epoch": 0.24628571428571427,
      "grad_norm": 0.03561779856681824,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4543561935424805,
      "step": 5172
    },
    {
      "epoch": 0.24638095238095237,
      "grad_norm": 0.031470756977796555,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4222569465637207,
      "step": 5174
    },
    {
      "epoch": 0.2464761904761905,
      "grad_norm": 0.031375687569379807,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4131088256835938,
      "step": 5176
    },
    {
      "epoch": 0.24657142857142858,
      "grad_norm": 0.03253437951207161,
      "learning_rate": 0.024000000208616257,
      "loss": 2.438693046569824,
      "step": 5178
    },
    {
      "epoch": 0.24666666666666667,
      "grad_norm": 0.03134525939822197,
      "learning_rate": 0.024000000208616257,
      "loss": 2.457665205001831,
      "step": 5180
    },
    {
      "epoch": 0.24676190476190477,
      "grad_norm": 0.030982406809926033,
      "learning_rate": 0.024000000208616257,
      "loss": 2.418596029281616,
      "step": 5182
    },
    {
      "epoch": 0.24685714285714286,
      "grad_norm": 0.03439369797706604,
      "learning_rate": 0.024000000208616257,
      "loss": 2.433413505554199,
      "step": 5184
    },
    {
      "epoch": 0.24695238095238095,
      "grad_norm": 0.03193904086947441,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4474234580993652,
      "step": 5186
    },
    {
      "epoch": 0.24704761904761904,
      "grad_norm": 0.03063969314098358,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3987245559692383,
      "step": 5188
    },
    {
      "epoch": 0.24714285714285714,
      "grad_norm": 0.032560478895902634,
      "learning_rate": 0.024000000208616257,
      "loss": 2.440870761871338,
      "step": 5190
    },
    {
      "epoch": 0.24723809523809523,
      "grad_norm": 0.031971849501132965,
      "learning_rate": 0.024000000208616257,
      "loss": 2.404054880142212,
      "step": 5192
    },
    {
      "epoch": 0.24733333333333332,
      "grad_norm": 0.03100547380745411,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4261155128479004,
      "step": 5194
    },
    {
      "epoch": 0.24742857142857144,
      "grad_norm": 0.0328497551381588,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4387073516845703,
      "step": 5196
    },
    {
      "epoch": 0.24752380952380953,
      "grad_norm": 0.03479984030127525,
      "learning_rate": 0.024000000208616257,
      "loss": 2.44690203666687,
      "step": 5198
    },
    {
      "epoch": 0.24761904761904763,
      "grad_norm": 0.031189991161227226,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4119386672973633,
      "step": 5200
    },
    {
      "epoch": 0.24771428571428572,
      "grad_norm": 0.03439142182469368,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4164228439331055,
      "step": 5202
    },
    {
      "epoch": 0.2478095238095238,
      "grad_norm": 0.03545600548386574,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4502716064453125,
      "step": 5204
    },
    {
      "epoch": 0.2479047619047619,
      "grad_norm": 0.03180856630206108,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4478044509887695,
      "step": 5206
    },
    {
      "epoch": 0.248,
      "grad_norm": 0.03133009374141693,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4523391723632812,
      "step": 5208
    },
    {
      "epoch": 0.2480952380952381,
      "grad_norm": 0.03119414858520031,
      "learning_rate": 0.024000000208616257,
      "loss": 2.416858673095703,
      "step": 5210
    },
    {
      "epoch": 0.24819047619047618,
      "grad_norm": 0.03374669700860977,
      "learning_rate": 0.024000000208616257,
      "loss": 2.435781955718994,
      "step": 5212
    },
    {
      "epoch": 0.24828571428571428,
      "grad_norm": 0.03202417120337486,
      "learning_rate": 0.024000000208616257,
      "loss": 2.413475513458252,
      "step": 5214
    },
    {
      "epoch": 0.24838095238095237,
      "grad_norm": 0.03195689246058464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.447007656097412,
      "step": 5216
    },
    {
      "epoch": 0.2484761904761905,
      "grad_norm": 0.03237782418727875,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4344301223754883,
      "step": 5218
    },
    {
      "epoch": 0.24857142857142858,
      "grad_norm": 0.031695783138275146,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4080629348754883,
      "step": 5220
    },
    {
      "epoch": 0.24866666666666667,
      "grad_norm": 0.03161827474832535,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4282302856445312,
      "step": 5222
    },
    {
      "epoch": 0.24876190476190477,
      "grad_norm": 0.031067362055182457,
      "learning_rate": 0.024000000208616257,
      "loss": 2.413761615753174,
      "step": 5224
    },
    {
      "epoch": 0.24885714285714286,
      "grad_norm": 0.03309772536158562,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4327452182769775,
      "step": 5226
    },
    {
      "epoch": 0.24895238095238095,
      "grad_norm": 0.03262703865766525,
      "learning_rate": 0.024000000208616257,
      "loss": 2.424880266189575,
      "step": 5228
    },
    {
      "epoch": 0.24904761904761905,
      "grad_norm": 0.03252482786774635,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4313392639160156,
      "step": 5230
    },
    {
      "epoch": 0.24914285714285714,
      "grad_norm": 0.032344307750463486,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4278221130371094,
      "step": 5232
    },
    {
      "epoch": 0.24923809523809523,
      "grad_norm": 0.032491255551576614,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4541258811950684,
      "step": 5234
    },
    {
      "epoch": 0.24933333333333332,
      "grad_norm": 0.03274603188037872,
      "learning_rate": 0.024000000208616257,
      "loss": 2.418567180633545,
      "step": 5236
    },
    {
      "epoch": 0.24942857142857142,
      "grad_norm": 0.030883805826306343,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3985395431518555,
      "step": 5238
    },
    {
      "epoch": 0.24952380952380954,
      "grad_norm": 0.03146642446517944,
      "learning_rate": 0.024000000208616257,
      "loss": 2.413745880126953,
      "step": 5240
    },
    {
      "epoch": 0.24961904761904763,
      "grad_norm": 0.03300030902028084,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4152746200561523,
      "step": 5242
    },
    {
      "epoch": 0.24971428571428572,
      "grad_norm": 0.0304889976978302,
      "learning_rate": 0.024000000208616257,
      "loss": 2.440913438796997,
      "step": 5244
    },
    {
      "epoch": 0.24980952380952381,
      "grad_norm": 0.03135913610458374,
      "learning_rate": 0.024000000208616257,
      "loss": 2.395047664642334,
      "step": 5246
    },
    {
      "epoch": 0.2499047619047619,
      "grad_norm": 0.031235886737704277,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3816640377044678,
      "step": 5248
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.034407131373882294,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4066357612609863,
      "step": 5250
    },
    {
      "epoch": 0.2500952380952381,
      "grad_norm": 0.03198624402284622,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4351940155029297,
      "step": 5252
    },
    {
      "epoch": 0.2501904761904762,
      "grad_norm": 0.03166883811354637,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4317636489868164,
      "step": 5254
    },
    {
      "epoch": 0.2502857142857143,
      "grad_norm": 0.032022763043642044,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4245543479919434,
      "step": 5256
    },
    {
      "epoch": 0.25038095238095237,
      "grad_norm": 0.03431449830532074,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4228672981262207,
      "step": 5258
    },
    {
      "epoch": 0.25047619047619046,
      "grad_norm": 0.030458297580480576,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4261505603790283,
      "step": 5260
    },
    {
      "epoch": 0.25057142857142856,
      "grad_norm": 0.03091929480433464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4294466972351074,
      "step": 5262
    },
    {
      "epoch": 0.25066666666666665,
      "grad_norm": 0.029844267293810844,
      "learning_rate": 0.024000000208616257,
      "loss": 2.420591115951538,
      "step": 5264
    },
    {
      "epoch": 0.25076190476190474,
      "grad_norm": 0.03049897588789463,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3999743461608887,
      "step": 5266
    },
    {
      "epoch": 0.25085714285714283,
      "grad_norm": 0.031119072809815407,
      "learning_rate": 0.024000000208616257,
      "loss": 2.408231258392334,
      "step": 5268
    },
    {
      "epoch": 0.2509523809523809,
      "grad_norm": 0.03101925179362297,
      "learning_rate": 0.024000000208616257,
      "loss": 2.430816650390625,
      "step": 5270
    },
    {
      "epoch": 0.2510476190476191,
      "grad_norm": 0.031917210668325424,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4400694370269775,
      "step": 5272
    },
    {
      "epoch": 0.25114285714285717,
      "grad_norm": 0.03450963646173477,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4098992347717285,
      "step": 5274
    },
    {
      "epoch": 0.25123809523809526,
      "grad_norm": 0.032573048025369644,
      "learning_rate": 0.024000000208616257,
      "loss": 2.377645969390869,
      "step": 5276
    },
    {
      "epoch": 0.25133333333333335,
      "grad_norm": 0.030998969450592995,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4087066650390625,
      "step": 5278
    },
    {
      "epoch": 0.25142857142857145,
      "grad_norm": 0.03612903133034706,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4326276779174805,
      "step": 5280
    },
    {
      "epoch": 0.25152380952380954,
      "grad_norm": 0.034261032938957214,
      "learning_rate": 0.024000000208616257,
      "loss": 2.391134738922119,
      "step": 5282
    },
    {
      "epoch": 0.25161904761904763,
      "grad_norm": 0.033529751002788544,
      "learning_rate": 0.024000000208616257,
      "loss": 2.425478935241699,
      "step": 5284
    },
    {
      "epoch": 0.2517142857142857,
      "grad_norm": 0.036629822105169296,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4254398345947266,
      "step": 5286
    },
    {
      "epoch": 0.2518095238095238,
      "grad_norm": 0.0319504551589489,
      "learning_rate": 0.024000000208616257,
      "loss": 2.426347494125366,
      "step": 5288
    },
    {
      "epoch": 0.2519047619047619,
      "grad_norm": 0.03081464022397995,
      "learning_rate": 0.024000000208616257,
      "loss": 2.405913829803467,
      "step": 5290
    },
    {
      "epoch": 0.252,
      "grad_norm": 0.03011227585375309,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4170477390289307,
      "step": 5292
    },
    {
      "epoch": 0.2520952380952381,
      "grad_norm": 0.03214811906218529,
      "learning_rate": 0.024000000208616257,
      "loss": 2.429774284362793,
      "step": 5294
    },
    {
      "epoch": 0.2521904761904762,
      "grad_norm": 0.03210081532597542,
      "learning_rate": 0.024000000208616257,
      "loss": 2.402398109436035,
      "step": 5296
    },
    {
      "epoch": 0.2522857142857143,
      "grad_norm": 0.03414318338036537,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4434592723846436,
      "step": 5298
    },
    {
      "epoch": 0.2523809523809524,
      "grad_norm": 0.03135037049651146,
      "learning_rate": 0.024000000208616257,
      "loss": 2.440511703491211,
      "step": 5300
    },
    {
      "epoch": 0.25247619047619047,
      "grad_norm": 0.03128252923488617,
      "learning_rate": 0.024000000208616257,
      "loss": 2.405616283416748,
      "step": 5302
    },
    {
      "epoch": 0.25257142857142856,
      "grad_norm": 0.03230244666337967,
      "learning_rate": 0.024000000208616257,
      "loss": 2.418605089187622,
      "step": 5304
    },
    {
      "epoch": 0.25266666666666665,
      "grad_norm": 0.03214823454618454,
      "learning_rate": 0.024000000208616257,
      "loss": 2.40116286277771,
      "step": 5306
    },
    {
      "epoch": 0.25276190476190474,
      "grad_norm": 0.03152569755911827,
      "learning_rate": 0.024000000208616257,
      "loss": 2.412729263305664,
      "step": 5308
    },
    {
      "epoch": 0.25285714285714284,
      "grad_norm": 0.03144894540309906,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4174251556396484,
      "step": 5310
    },
    {
      "epoch": 0.25295238095238093,
      "grad_norm": 0.032237786799669266,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4314258098602295,
      "step": 5312
    },
    {
      "epoch": 0.253047619047619,
      "grad_norm": 0.031285855919122696,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4240100383758545,
      "step": 5314
    },
    {
      "epoch": 0.25314285714285717,
      "grad_norm": 0.03219995275139809,
      "learning_rate": 0.024000000208616257,
      "loss": 2.419476270675659,
      "step": 5316
    },
    {
      "epoch": 0.25323809523809526,
      "grad_norm": 0.03115553967654705,
      "learning_rate": 0.024000000208616257,
      "loss": 2.406205892562866,
      "step": 5318
    },
    {
      "epoch": 0.25333333333333335,
      "grad_norm": 0.03059227019548416,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4381625652313232,
      "step": 5320
    },
    {
      "epoch": 0.25342857142857145,
      "grad_norm": 0.03182839974761009,
      "learning_rate": 0.024000000208616257,
      "loss": 2.434796094894409,
      "step": 5322
    },
    {
      "epoch": 0.25352380952380954,
      "grad_norm": 0.032941222190856934,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396784543991089,
      "step": 5324
    },
    {
      "epoch": 0.25361904761904763,
      "grad_norm": 0.033152636140584946,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4145662784576416,
      "step": 5326
    },
    {
      "epoch": 0.2537142857142857,
      "grad_norm": 0.03527110815048218,
      "learning_rate": 0.024000000208616257,
      "loss": 2.419447898864746,
      "step": 5328
    },
    {
      "epoch": 0.2538095238095238,
      "grad_norm": 0.032335683703422546,
      "learning_rate": 0.024000000208616257,
      "loss": 2.423704147338867,
      "step": 5330
    },
    {
      "epoch": 0.2539047619047619,
      "grad_norm": 0.03207523748278618,
      "learning_rate": 0.024000000208616257,
      "loss": 2.423095464706421,
      "step": 5332
    },
    {
      "epoch": 0.254,
      "grad_norm": 0.03262028098106384,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4136600494384766,
      "step": 5334
    },
    {
      "epoch": 0.2540952380952381,
      "grad_norm": 0.03148527815937996,
      "learning_rate": 0.024000000208616257,
      "loss": 2.425631046295166,
      "step": 5336
    },
    {
      "epoch": 0.2541904761904762,
      "grad_norm": 0.029992450028657913,
      "learning_rate": 0.024000000208616257,
      "loss": 2.422292470932007,
      "step": 5338
    },
    {
      "epoch": 0.2542857142857143,
      "grad_norm": 0.03229236602783203,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3994390964508057,
      "step": 5340
    },
    {
      "epoch": 0.2543809523809524,
      "grad_norm": 0.030337641015648842,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3979763984680176,
      "step": 5342
    },
    {
      "epoch": 0.25447619047619047,
      "grad_norm": 0.03170936182141304,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3925299644470215,
      "step": 5344
    },
    {
      "epoch": 0.25457142857142856,
      "grad_norm": 0.032768070697784424,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4084978103637695,
      "step": 5346
    },
    {
      "epoch": 0.25466666666666665,
      "grad_norm": 0.031721554696559906,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4252853393554688,
      "step": 5348
    },
    {
      "epoch": 0.25476190476190474,
      "grad_norm": 0.031533535569906235,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4356260299682617,
      "step": 5350
    },
    {
      "epoch": 0.25485714285714284,
      "grad_norm": 0.03436281904578209,
      "learning_rate": 0.024000000208616257,
      "loss": 2.404580593109131,
      "step": 5352
    },
    {
      "epoch": 0.25495238095238093,
      "grad_norm": 0.03212735056877136,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4132721424102783,
      "step": 5354
    },
    {
      "epoch": 0.255047619047619,
      "grad_norm": 0.03106311336159706,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3995931148529053,
      "step": 5356
    },
    {
      "epoch": 0.2551428571428571,
      "grad_norm": 0.029990267008543015,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3959755897521973,
      "step": 5358
    },
    {
      "epoch": 0.25523809523809526,
      "grad_norm": 0.030089790001511574,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3958911895751953,
      "step": 5360
    },
    {
      "epoch": 0.25533333333333336,
      "grad_norm": 0.032206807285547256,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4217638969421387,
      "step": 5362
    },
    {
      "epoch": 0.25542857142857145,
      "grad_norm": 0.03144534304738045,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3795628547668457,
      "step": 5364
    },
    {
      "epoch": 0.25552380952380954,
      "grad_norm": 0.030869822949171066,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4128456115722656,
      "step": 5366
    },
    {
      "epoch": 0.25561904761904763,
      "grad_norm": 0.03152036666870117,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3858389854431152,
      "step": 5368
    },
    {
      "epoch": 0.2557142857142857,
      "grad_norm": 0.033976323902606964,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3908133506774902,
      "step": 5370
    },
    {
      "epoch": 0.2558095238095238,
      "grad_norm": 0.0344674214720726,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3906283378601074,
      "step": 5372
    },
    {
      "epoch": 0.2559047619047619,
      "grad_norm": 0.032414231449365616,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4296622276306152,
      "step": 5374
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.03220691159367561,
      "learning_rate": 0.024000000208616257,
      "loss": 2.439225196838379,
      "step": 5376
    },
    {
      "epoch": 0.2560952380952381,
      "grad_norm": 0.03121328540146351,
      "learning_rate": 0.024000000208616257,
      "loss": 2.404726505279541,
      "step": 5378
    },
    {
      "epoch": 0.2561904761904762,
      "grad_norm": 0.030884698033332825,
      "learning_rate": 0.024000000208616257,
      "loss": 2.377146005630493,
      "step": 5380
    },
    {
      "epoch": 0.2562857142857143,
      "grad_norm": 0.03369889408349991,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4146528244018555,
      "step": 5382
    },
    {
      "epoch": 0.2563809523809524,
      "grad_norm": 0.03278132528066635,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3902101516723633,
      "step": 5384
    },
    {
      "epoch": 0.25647619047619047,
      "grad_norm": 0.032686688005924225,
      "learning_rate": 0.024000000208616257,
      "loss": 2.366447925567627,
      "step": 5386
    },
    {
      "epoch": 0.25657142857142856,
      "grad_norm": 0.03533146157860756,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3913917541503906,
      "step": 5388
    },
    {
      "epoch": 0.25666666666666665,
      "grad_norm": 0.03409096598625183,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4040393829345703,
      "step": 5390
    },
    {
      "epoch": 0.25676190476190475,
      "grad_norm": 0.0318492129445076,
      "learning_rate": 0.024000000208616257,
      "loss": 2.388803005218506,
      "step": 5392
    },
    {
      "epoch": 0.25685714285714284,
      "grad_norm": 0.031883712857961655,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4073195457458496,
      "step": 5394
    },
    {
      "epoch": 0.25695238095238093,
      "grad_norm": 0.032373517751693726,
      "learning_rate": 0.024000000208616257,
      "loss": 2.423096179962158,
      "step": 5396
    },
    {
      "epoch": 0.257047619047619,
      "grad_norm": 0.03214838728308678,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3928680419921875,
      "step": 5398
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.03428845852613449,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3952460289001465,
      "step": 5400
    },
    {
      "epoch": 0.25723809523809527,
      "grad_norm": 0.032713066786527634,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4059934616088867,
      "step": 5402
    },
    {
      "epoch": 0.25733333333333336,
      "grad_norm": 0.03380517661571503,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4203948974609375,
      "step": 5404
    },
    {
      "epoch": 0.25742857142857145,
      "grad_norm": 0.03241650015115738,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398283004760742,
      "step": 5406
    },
    {
      "epoch": 0.25752380952380954,
      "grad_norm": 0.030663466081023216,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3838157653808594,
      "step": 5408
    },
    {
      "epoch": 0.25761904761904764,
      "grad_norm": 0.03262992203235626,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3736727237701416,
      "step": 5410
    },
    {
      "epoch": 0.25771428571428573,
      "grad_norm": 0.03067677654325962,
      "learning_rate": 0.024000000208616257,
      "loss": 2.373810052871704,
      "step": 5412
    },
    {
      "epoch": 0.2578095238095238,
      "grad_norm": 0.029912728816270828,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3722333908081055,
      "step": 5414
    },
    {
      "epoch": 0.2579047619047619,
      "grad_norm": 0.030815914273262024,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3932852745056152,
      "step": 5416
    },
    {
      "epoch": 0.258,
      "grad_norm": 0.03538758307695389,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4033913612365723,
      "step": 5418
    },
    {
      "epoch": 0.2580952380952381,
      "grad_norm": 0.03146061301231384,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392453670501709,
      "step": 5420
    },
    {
      "epoch": 0.2581904761904762,
      "grad_norm": 0.03183531016111374,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4103665351867676,
      "step": 5422
    },
    {
      "epoch": 0.2582857142857143,
      "grad_norm": 0.03301506116986275,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4038171768188477,
      "step": 5424
    },
    {
      "epoch": 0.2583809523809524,
      "grad_norm": 0.031241508200764656,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3902828693389893,
      "step": 5426
    },
    {
      "epoch": 0.25847619047619047,
      "grad_norm": 0.03147522360086441,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3980908393859863,
      "step": 5428
    },
    {
      "epoch": 0.25857142857142856,
      "grad_norm": 0.03116549924015999,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4042224884033203,
      "step": 5430
    },
    {
      "epoch": 0.25866666666666666,
      "grad_norm": 0.03222668915987015,
      "learning_rate": 0.024000000208616257,
      "loss": 2.420657157897949,
      "step": 5432
    },
    {
      "epoch": 0.25876190476190475,
      "grad_norm": 0.031931228935718536,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3936681747436523,
      "step": 5434
    },
    {
      "epoch": 0.25885714285714284,
      "grad_norm": 0.030512044206261635,
      "learning_rate": 0.024000000208616257,
      "loss": 2.399482250213623,
      "step": 5436
    },
    {
      "epoch": 0.25895238095238093,
      "grad_norm": 0.03148795664310455,
      "learning_rate": 0.024000000208616257,
      "loss": 2.371001720428467,
      "step": 5438
    },
    {
      "epoch": 0.259047619047619,
      "grad_norm": 0.032876353710889816,
      "learning_rate": 0.024000000208616257,
      "loss": 2.417214870452881,
      "step": 5440
    },
    {
      "epoch": 0.2591428571428571,
      "grad_norm": 0.03197101876139641,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3872318267822266,
      "step": 5442
    },
    {
      "epoch": 0.2592380952380952,
      "grad_norm": 0.03068718872964382,
      "learning_rate": 0.024000000208616257,
      "loss": 2.417818546295166,
      "step": 5444
    },
    {
      "epoch": 0.25933333333333336,
      "grad_norm": 0.03265013545751572,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3997135162353516,
      "step": 5446
    },
    {
      "epoch": 0.25942857142857145,
      "grad_norm": 0.03128447011113167,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4150614738464355,
      "step": 5448
    },
    {
      "epoch": 0.25952380952380955,
      "grad_norm": 0.03170602768659592,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390566349029541,
      "step": 5450
    },
    {
      "epoch": 0.25961904761904764,
      "grad_norm": 0.031806305050849915,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3988583087921143,
      "step": 5452
    },
    {
      "epoch": 0.25971428571428573,
      "grad_norm": 0.03518638014793396,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3945212364196777,
      "step": 5454
    },
    {
      "epoch": 0.2598095238095238,
      "grad_norm": 0.03182811290025711,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3916609287261963,
      "step": 5456
    },
    {
      "epoch": 0.2599047619047619,
      "grad_norm": 0.029905378818511963,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3958840370178223,
      "step": 5458
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.03145475685596466,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4036684036254883,
      "step": 5460
    },
    {
      "epoch": 0.2600952380952381,
      "grad_norm": 0.031111933290958405,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382187843322754,
      "step": 5462
    },
    {
      "epoch": 0.2601904761904762,
      "grad_norm": 0.03093023970723152,
      "learning_rate": 0.024000000208616257,
      "loss": 2.388195037841797,
      "step": 5464
    },
    {
      "epoch": 0.2602857142857143,
      "grad_norm": 0.03347831591963768,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3881871700286865,
      "step": 5466
    },
    {
      "epoch": 0.2603809523809524,
      "grad_norm": 0.03536050394177437,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38173770904541,
      "step": 5468
    },
    {
      "epoch": 0.2604761904761905,
      "grad_norm": 0.035065703094005585,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3804469108581543,
      "step": 5470
    },
    {
      "epoch": 0.26057142857142856,
      "grad_norm": 0.03124040924012661,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3876523971557617,
      "step": 5472
    },
    {
      "epoch": 0.26066666666666666,
      "grad_norm": 0.030609548091888428,
      "learning_rate": 0.024000000208616257,
      "loss": 2.369189739227295,
      "step": 5474
    },
    {
      "epoch": 0.26076190476190475,
      "grad_norm": 0.031035082414746284,
      "learning_rate": 0.024000000208616257,
      "loss": 2.397982120513916,
      "step": 5476
    },
    {
      "epoch": 0.26085714285714284,
      "grad_norm": 0.030819550156593323,
      "learning_rate": 0.024000000208616257,
      "loss": 2.369689702987671,
      "step": 5478
    },
    {
      "epoch": 0.26095238095238094,
      "grad_norm": 0.02973431535065174,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3851356506347656,
      "step": 5480
    },
    {
      "epoch": 0.26104761904761903,
      "grad_norm": 0.030935391783714294,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4049510955810547,
      "step": 5482
    },
    {
      "epoch": 0.2611428571428571,
      "grad_norm": 0.030150095000863075,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392129898071289,
      "step": 5484
    },
    {
      "epoch": 0.2612380952380952,
      "grad_norm": 0.03226688504219055,
      "learning_rate": 0.024000000208616257,
      "loss": 2.39337158203125,
      "step": 5486
    },
    {
      "epoch": 0.2613333333333333,
      "grad_norm": 0.03114429861307144,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3421168327331543,
      "step": 5488
    },
    {
      "epoch": 0.26142857142857145,
      "grad_norm": 0.03041151724755764,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3760592937469482,
      "step": 5490
    },
    {
      "epoch": 0.26152380952380955,
      "grad_norm": 0.031533583998680115,
      "learning_rate": 0.024000000208616257,
      "loss": 2.391040325164795,
      "step": 5492
    },
    {
      "epoch": 0.26161904761904764,
      "grad_norm": 0.030382411554455757,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3917789459228516,
      "step": 5494
    },
    {
      "epoch": 0.26171428571428573,
      "grad_norm": 0.03187396749854088,
      "learning_rate": 0.024000000208616257,
      "loss": 2.364685535430908,
      "step": 5496
    },
    {
      "epoch": 0.2618095238095238,
      "grad_norm": 0.03608180209994316,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38401460647583,
      "step": 5498
    },
    {
      "epoch": 0.2619047619047619,
      "grad_norm": 0.030125068500638008,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3981082439422607,
      "step": 5500
    },
    {
      "epoch": 0.262,
      "grad_norm": 0.03047472983598709,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380566120147705,
      "step": 5502
    },
    {
      "epoch": 0.2620952380952381,
      "grad_norm": 0.030002737417817116,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3586506843566895,
      "step": 5504
    },
    {
      "epoch": 0.2621904761904762,
      "grad_norm": 0.030061883851885796,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3555164337158203,
      "step": 5506
    },
    {
      "epoch": 0.2622857142857143,
      "grad_norm": 0.03263762965798378,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3913028240203857,
      "step": 5508
    },
    {
      "epoch": 0.2623809523809524,
      "grad_norm": 0.03217017650604248,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3252928256988525,
      "step": 5510
    },
    {
      "epoch": 0.2624761904761905,
      "grad_norm": 0.03119669295847416,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3905091285705566,
      "step": 5512
    },
    {
      "epoch": 0.26257142857142857,
      "grad_norm": 0.031353577971458435,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3937129974365234,
      "step": 5514
    },
    {
      "epoch": 0.26266666666666666,
      "grad_norm": 0.0303814597427845,
      "learning_rate": 0.024000000208616257,
      "loss": 2.394263744354248,
      "step": 5516
    },
    {
      "epoch": 0.26276190476190475,
      "grad_norm": 0.03217311203479767,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3815956115722656,
      "step": 5518
    },
    {
      "epoch": 0.26285714285714284,
      "grad_norm": 0.031240256503224373,
      "learning_rate": 0.024000000208616257,
      "loss": 2.343517780303955,
      "step": 5520
    },
    {
      "epoch": 0.26295238095238094,
      "grad_norm": 0.03436282277107239,
      "learning_rate": 0.024000000208616257,
      "loss": 2.402054786682129,
      "step": 5522
    },
    {
      "epoch": 0.26304761904761903,
      "grad_norm": 0.032754965126514435,
      "learning_rate": 0.024000000208616257,
      "loss": 2.366446018218994,
      "step": 5524
    },
    {
      "epoch": 0.2631428571428571,
      "grad_norm": 0.03386955335736275,
      "learning_rate": 0.024000000208616257,
      "loss": 2.37076997756958,
      "step": 5526
    },
    {
      "epoch": 0.2632380952380952,
      "grad_norm": 0.03378401696681976,
      "learning_rate": 0.024000000208616257,
      "loss": 2.370576858520508,
      "step": 5528
    },
    {
      "epoch": 0.2633333333333333,
      "grad_norm": 0.03179125487804413,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3701069355010986,
      "step": 5530
    },
    {
      "epoch": 0.2634285714285714,
      "grad_norm": 0.030285989865660667,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398491859436035,
      "step": 5532
    },
    {
      "epoch": 0.26352380952380955,
      "grad_norm": 0.03089715912938118,
      "learning_rate": 0.024000000208616257,
      "loss": 2.366664409637451,
      "step": 5534
    },
    {
      "epoch": 0.26361904761904764,
      "grad_norm": 0.03126239776611328,
      "learning_rate": 0.024000000208616257,
      "loss": 2.360291004180908,
      "step": 5536
    },
    {
      "epoch": 0.26371428571428573,
      "grad_norm": 0.029945041984319687,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3588266372680664,
      "step": 5538
    },
    {
      "epoch": 0.2638095238095238,
      "grad_norm": 0.02908904291689396,
      "learning_rate": 0.024000000208616257,
      "loss": 2.349623441696167,
      "step": 5540
    },
    {
      "epoch": 0.2639047619047619,
      "grad_norm": 0.03077501803636551,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3620495796203613,
      "step": 5542
    },
    {
      "epoch": 0.264,
      "grad_norm": 0.03151123970746994,
      "learning_rate": 0.024000000208616257,
      "loss": 2.358649730682373,
      "step": 5544
    },
    {
      "epoch": 0.2640952380952381,
      "grad_norm": 0.029449881985783577,
      "learning_rate": 0.024000000208616257,
      "loss": 2.373584032058716,
      "step": 5546
    },
    {
      "epoch": 0.2641904761904762,
      "grad_norm": 0.03158615902066231,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3515772819519043,
      "step": 5548
    },
    {
      "epoch": 0.2642857142857143,
      "grad_norm": 0.03116215020418167,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3411803245544434,
      "step": 5550
    },
    {
      "epoch": 0.2643809523809524,
      "grad_norm": 0.030420923605561256,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3383848667144775,
      "step": 5552
    },
    {
      "epoch": 0.2644761904761905,
      "grad_norm": 0.030973205342888832,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382458209991455,
      "step": 5554
    },
    {
      "epoch": 0.26457142857142857,
      "grad_norm": 0.0308368019759655,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384258270263672,
      "step": 5556
    },
    {
      "epoch": 0.26466666666666666,
      "grad_norm": 0.0317256785929203,
      "learning_rate": 0.024000000208616257,
      "loss": 2.400378704071045,
      "step": 5558
    },
    {
      "epoch": 0.26476190476190475,
      "grad_norm": 0.03256650269031525,
      "learning_rate": 0.024000000208616257,
      "loss": 2.337237596511841,
      "step": 5560
    },
    {
      "epoch": 0.26485714285714285,
      "grad_norm": 0.03197898343205452,
      "learning_rate": 0.024000000208616257,
      "loss": 2.381927251815796,
      "step": 5562
    },
    {
      "epoch": 0.26495238095238094,
      "grad_norm": 0.03032790496945381,
      "learning_rate": 0.024000000208616257,
      "loss": 2.348811149597168,
      "step": 5564
    },
    {
      "epoch": 0.26504761904761903,
      "grad_norm": 0.031524743884801865,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3604493141174316,
      "step": 5566
    },
    {
      "epoch": 0.2651428571428571,
      "grad_norm": 0.03121861256659031,
      "learning_rate": 0.024000000208616257,
      "loss": 2.354872703552246,
      "step": 5568
    },
    {
      "epoch": 0.2652380952380952,
      "grad_norm": 0.03033018857240677,
      "learning_rate": 0.024000000208616257,
      "loss": 2.357921600341797,
      "step": 5570
    },
    {
      "epoch": 0.2653333333333333,
      "grad_norm": 0.030038518831133842,
      "learning_rate": 0.024000000208616257,
      "loss": 2.336320400238037,
      "step": 5572
    },
    {
      "epoch": 0.2654285714285714,
      "grad_norm": 0.03146941587328911,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3681459426879883,
      "step": 5574
    },
    {
      "epoch": 0.26552380952380955,
      "grad_norm": 0.032695941627025604,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3523476123809814,
      "step": 5576
    },
    {
      "epoch": 0.26561904761904764,
      "grad_norm": 0.02979757823050022,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3498802185058594,
      "step": 5578
    },
    {
      "epoch": 0.26571428571428574,
      "grad_norm": 0.030307264998555183,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3460097312927246,
      "step": 5580
    },
    {
      "epoch": 0.26580952380952383,
      "grad_norm": 0.031003162264823914,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3418400287628174,
      "step": 5582
    },
    {
      "epoch": 0.2659047619047619,
      "grad_norm": 0.030828263610601425,
      "learning_rate": 0.024000000208616257,
      "loss": 2.37935209274292,
      "step": 5584
    },
    {
      "epoch": 0.266,
      "grad_norm": 0.029439439997076988,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3601272106170654,
      "step": 5586
    },
    {
      "epoch": 0.2660952380952381,
      "grad_norm": 0.030675796791911125,
      "learning_rate": 0.024000000208616257,
      "loss": 2.376600742340088,
      "step": 5588
    },
    {
      "epoch": 0.2661904761904762,
      "grad_norm": 0.031092649325728416,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3602662086486816,
      "step": 5590
    },
    {
      "epoch": 0.2662857142857143,
      "grad_norm": 0.03197270631790161,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3579111099243164,
      "step": 5592
    },
    {
      "epoch": 0.2663809523809524,
      "grad_norm": 0.030018623918294907,
      "learning_rate": 0.024000000208616257,
      "loss": 2.359997034072876,
      "step": 5594
    },
    {
      "epoch": 0.2664761904761905,
      "grad_norm": 0.031238991767168045,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363828182220459,
      "step": 5596
    },
    {
      "epoch": 0.26657142857142857,
      "grad_norm": 0.031249355524778366,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3664472103118896,
      "step": 5598
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.031046612188220024,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3357787132263184,
      "step": 5600
    },
    {
      "epoch": 0.26676190476190476,
      "grad_norm": 0.03087741881608963,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3542094230651855,
      "step": 5602
    },
    {
      "epoch": 0.26685714285714285,
      "grad_norm": 0.030984893441200256,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3543248176574707,
      "step": 5604
    },
    {
      "epoch": 0.26695238095238094,
      "grad_norm": 0.030332420021295547,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3311848640441895,
      "step": 5606
    },
    {
      "epoch": 0.26704761904761903,
      "grad_norm": 0.0326809398829937,
      "learning_rate": 0.024000000208616257,
      "loss": 2.346945285797119,
      "step": 5608
    },
    {
      "epoch": 0.2671428571428571,
      "grad_norm": 0.03469430282711983,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350297451019287,
      "step": 5610
    },
    {
      "epoch": 0.2672380952380952,
      "grad_norm": 0.03799416124820709,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3583927154541016,
      "step": 5612
    },
    {
      "epoch": 0.2673333333333333,
      "grad_norm": 0.03941074386239052,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3362317085266113,
      "step": 5614
    },
    {
      "epoch": 0.2674285714285714,
      "grad_norm": 0.03505103662610054,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3791117668151855,
      "step": 5616
    },
    {
      "epoch": 0.2675238095238095,
      "grad_norm": 0.032357458025217056,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345334529876709,
      "step": 5618
    },
    {
      "epoch": 0.26761904761904765,
      "grad_norm": 0.03324982896447182,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3328990936279297,
      "step": 5620
    },
    {
      "epoch": 0.26771428571428574,
      "grad_norm": 0.03330742567777634,
      "learning_rate": 0.024000000208616257,
      "loss": 2.317239284515381,
      "step": 5622
    },
    {
      "epoch": 0.26780952380952383,
      "grad_norm": 0.03097325749695301,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3282556533813477,
      "step": 5624
    },
    {
      "epoch": 0.2679047619047619,
      "grad_norm": 0.03345143049955368,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350015878677368,
      "step": 5626
    },
    {
      "epoch": 0.268,
      "grad_norm": 0.031195860356092453,
      "learning_rate": 0.024000000208616257,
      "loss": 2.32436466217041,
      "step": 5628
    },
    {
      "epoch": 0.2680952380952381,
      "grad_norm": 0.031183049082756042,
      "learning_rate": 0.024000000208616257,
      "loss": 2.335273504257202,
      "step": 5630
    },
    {
      "epoch": 0.2681904761904762,
      "grad_norm": 0.03473105654120445,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3523812294006348,
      "step": 5632
    },
    {
      "epoch": 0.2682857142857143,
      "grad_norm": 0.033637866377830505,
      "learning_rate": 0.024000000208616257,
      "loss": 2.370361328125,
      "step": 5634
    },
    {
      "epoch": 0.2683809523809524,
      "grad_norm": 0.0321369394659996,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3747334480285645,
      "step": 5636
    },
    {
      "epoch": 0.2684761904761905,
      "grad_norm": 0.03171514347195625,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345963716506958,
      "step": 5638
    },
    {
      "epoch": 0.26857142857142857,
      "grad_norm": 0.035894837230443954,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3880069255828857,
      "step": 5640
    },
    {
      "epoch": 0.26866666666666666,
      "grad_norm": 0.033222734928131104,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350543737411499,
      "step": 5642
    },
    {
      "epoch": 0.26876190476190476,
      "grad_norm": 0.03295835852622986,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3739542961120605,
      "step": 5644
    },
    {
      "epoch": 0.26885714285714285,
      "grad_norm": 0.03131318837404251,
      "learning_rate": 0.024000000208616257,
      "loss": 2.347900867462158,
      "step": 5646
    },
    {
      "epoch": 0.26895238095238094,
      "grad_norm": 0.030047079548239708,
      "learning_rate": 0.024000000208616257,
      "loss": 2.333242416381836,
      "step": 5648
    },
    {
      "epoch": 0.26904761904761904,
      "grad_norm": 0.03024309128522873,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356759548187256,
      "step": 5650
    },
    {
      "epoch": 0.26914285714285713,
      "grad_norm": 0.029195228591561317,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3740644454956055,
      "step": 5652
    },
    {
      "epoch": 0.2692380952380952,
      "grad_norm": 0.03100462816655636,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3597240447998047,
      "step": 5654
    },
    {
      "epoch": 0.2693333333333333,
      "grad_norm": 0.030258873477578163,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3590290546417236,
      "step": 5656
    },
    {
      "epoch": 0.2694285714285714,
      "grad_norm": 0.029631292447447777,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3765764236450195,
      "step": 5658
    },
    {
      "epoch": 0.2695238095238095,
      "grad_norm": 0.029591379687190056,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383760929107666,
      "step": 5660
    },
    {
      "epoch": 0.2696190476190476,
      "grad_norm": 0.029307687655091286,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3615593910217285,
      "step": 5662
    },
    {
      "epoch": 0.26971428571428574,
      "grad_norm": 0.030834274366497993,
      "learning_rate": 0.024000000208616257,
      "loss": 2.323805570602417,
      "step": 5664
    },
    {
      "epoch": 0.26980952380952383,
      "grad_norm": 0.030637772753834724,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38694167137146,
      "step": 5666
    },
    {
      "epoch": 0.2699047619047619,
      "grad_norm": 0.030719108879566193,
      "learning_rate": 0.024000000208616257,
      "loss": 2.370029926300049,
      "step": 5668
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.03047424927353859,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3631162643432617,
      "step": 5670
    },
    {
      "epoch": 0.2700952380952381,
      "grad_norm": 0.029626766219735146,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3667399883270264,
      "step": 5672
    },
    {
      "epoch": 0.2701904761904762,
      "grad_norm": 0.03091883845627308,
      "learning_rate": 0.024000000208616257,
      "loss": 2.352130651473999,
      "step": 5674
    },
    {
      "epoch": 0.2702857142857143,
      "grad_norm": 0.028811350464820862,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3777520656585693,
      "step": 5676
    },
    {
      "epoch": 0.2703809523809524,
      "grad_norm": 0.029614171013236046,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356661319732666,
      "step": 5678
    },
    {
      "epoch": 0.2704761904761905,
      "grad_norm": 0.030678682029247284,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38134503364563,
      "step": 5680
    },
    {
      "epoch": 0.2705714285714286,
      "grad_norm": 0.03133947774767876,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3359451293945312,
      "step": 5682
    },
    {
      "epoch": 0.27066666666666667,
      "grad_norm": 0.031092673540115356,
      "learning_rate": 0.024000000208616257,
      "loss": 2.364501953125,
      "step": 5684
    },
    {
      "epoch": 0.27076190476190476,
      "grad_norm": 0.03010372817516327,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3934712409973145,
      "step": 5686
    },
    {
      "epoch": 0.27085714285714285,
      "grad_norm": 0.029989907518029213,
      "learning_rate": 0.024000000208616257,
      "loss": 2.369211196899414,
      "step": 5688
    },
    {
      "epoch": 0.27095238095238094,
      "grad_norm": 0.029657233506441116,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384408473968506,
      "step": 5690
    },
    {
      "epoch": 0.27104761904761904,
      "grad_norm": 0.031768783926963806,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3514742851257324,
      "step": 5692
    },
    {
      "epoch": 0.27114285714285713,
      "grad_norm": 0.02888263389468193,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3660521507263184,
      "step": 5694
    },
    {
      "epoch": 0.2712380952380952,
      "grad_norm": 0.03063563071191311,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4015254974365234,
      "step": 5696
    },
    {
      "epoch": 0.2713333333333333,
      "grad_norm": 0.02979939803481102,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3679232597351074,
      "step": 5698
    },
    {
      "epoch": 0.2714285714285714,
      "grad_norm": 0.029716938734054565,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3737292289733887,
      "step": 5700
    },
    {
      "epoch": 0.2715238095238095,
      "grad_norm": 0.02936519682407379,
      "learning_rate": 0.024000000208616257,
      "loss": 2.357970952987671,
      "step": 5702
    },
    {
      "epoch": 0.2716190476190476,
      "grad_norm": 0.03139244392514229,
      "learning_rate": 0.024000000208616257,
      "loss": 2.389012575149536,
      "step": 5704
    },
    {
      "epoch": 0.27171428571428574,
      "grad_norm": 0.030890971422195435,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383584976196289,
      "step": 5706
    },
    {
      "epoch": 0.27180952380952383,
      "grad_norm": 0.030820494517683983,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3855247497558594,
      "step": 5708
    },
    {
      "epoch": 0.2719047619047619,
      "grad_norm": 0.029483675956726074,
      "learning_rate": 0.024000000208616257,
      "loss": 2.370877742767334,
      "step": 5710
    },
    {
      "epoch": 0.272,
      "grad_norm": 0.03058786317706108,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3875691890716553,
      "step": 5712
    },
    {
      "epoch": 0.2720952380952381,
      "grad_norm": 0.029739484190940857,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3502001762390137,
      "step": 5714
    },
    {
      "epoch": 0.2721904761904762,
      "grad_norm": 0.029705015942454338,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383249282836914,
      "step": 5716
    },
    {
      "epoch": 0.2722857142857143,
      "grad_norm": 0.030878661200404167,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3641953468322754,
      "step": 5718
    },
    {
      "epoch": 0.2723809523809524,
      "grad_norm": 0.030482063069939613,
      "learning_rate": 0.024000000208616257,
      "loss": 2.386033058166504,
      "step": 5720
    },
    {
      "epoch": 0.2724761904761905,
      "grad_norm": 0.03032311424612999,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3667593002319336,
      "step": 5722
    },
    {
      "epoch": 0.2725714285714286,
      "grad_norm": 0.03141382336616516,
      "learning_rate": 0.024000000208616257,
      "loss": 2.394498348236084,
      "step": 5724
    },
    {
      "epoch": 0.27266666666666667,
      "grad_norm": 0.031148390844464302,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3648557662963867,
      "step": 5726
    },
    {
      "epoch": 0.27276190476190476,
      "grad_norm": 0.03136315569281578,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3882956504821777,
      "step": 5728
    },
    {
      "epoch": 0.27285714285714285,
      "grad_norm": 0.03153848648071289,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4062252044677734,
      "step": 5730
    },
    {
      "epoch": 0.27295238095238095,
      "grad_norm": 0.03303917124867439,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3766307830810547,
      "step": 5732
    },
    {
      "epoch": 0.27304761904761904,
      "grad_norm": 0.030601607635617256,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4215803146362305,
      "step": 5734
    },
    {
      "epoch": 0.27314285714285713,
      "grad_norm": 0.030997153371572495,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4154105186462402,
      "step": 5736
    },
    {
      "epoch": 0.2732380952380952,
      "grad_norm": 0.03183874487876892,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4141149520874023,
      "step": 5738
    },
    {
      "epoch": 0.2733333333333333,
      "grad_norm": 0.032041873782873154,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4305315017700195,
      "step": 5740
    },
    {
      "epoch": 0.2734285714285714,
      "grad_norm": 0.031616147607564926,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3914988040924072,
      "step": 5742
    },
    {
      "epoch": 0.2735238095238095,
      "grad_norm": 0.031568653881549835,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3880224227905273,
      "step": 5744
    },
    {
      "epoch": 0.2736190476190476,
      "grad_norm": 0.030253177508711815,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3706729412078857,
      "step": 5746
    },
    {
      "epoch": 0.2737142857142857,
      "grad_norm": 0.030606726184487343,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3803834915161133,
      "step": 5748
    },
    {
      "epoch": 0.27380952380952384,
      "grad_norm": 0.028942739591002464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4107675552368164,
      "step": 5750
    },
    {
      "epoch": 0.27390476190476193,
      "grad_norm": 0.031044071540236473,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3632001876831055,
      "step": 5752
    },
    {
      "epoch": 0.274,
      "grad_norm": 0.03031793422996998,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4055025577545166,
      "step": 5754
    },
    {
      "epoch": 0.2740952380952381,
      "grad_norm": 0.029864395037293434,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3842110633850098,
      "step": 5756
    },
    {
      "epoch": 0.2741904761904762,
      "grad_norm": 0.03216216340661049,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4126155376434326,
      "step": 5758
    },
    {
      "epoch": 0.2742857142857143,
      "grad_norm": 0.030200988054275513,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3713507652282715,
      "step": 5760
    },
    {
      "epoch": 0.2743809523809524,
      "grad_norm": 0.03243393078446388,
      "learning_rate": 0.024000000208616257,
      "loss": 2.408329963684082,
      "step": 5762
    },
    {
      "epoch": 0.2744761904761905,
      "grad_norm": 0.03118664212524891,
      "learning_rate": 0.024000000208616257,
      "loss": 2.411752462387085,
      "step": 5764
    },
    {
      "epoch": 0.2745714285714286,
      "grad_norm": 0.03087531588971615,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4026360511779785,
      "step": 5766
    },
    {
      "epoch": 0.27466666666666667,
      "grad_norm": 0.030484450981020927,
      "learning_rate": 0.024000000208616257,
      "loss": 2.407597541809082,
      "step": 5768
    },
    {
      "epoch": 0.27476190476190476,
      "grad_norm": 0.029965482652187347,
      "learning_rate": 0.024000000208616257,
      "loss": 2.39113187789917,
      "step": 5770
    },
    {
      "epoch": 0.27485714285714286,
      "grad_norm": 0.029695620760321617,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4156126976013184,
      "step": 5772
    },
    {
      "epoch": 0.27495238095238095,
      "grad_norm": 0.02998894266784191,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3926312923431396,
      "step": 5774
    },
    {
      "epoch": 0.27504761904761904,
      "grad_norm": 0.030583802610635757,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3898768424987793,
      "step": 5776
    },
    {
      "epoch": 0.27514285714285713,
      "grad_norm": 0.029758738353848457,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4197874069213867,
      "step": 5778
    },
    {
      "epoch": 0.2752380952380952,
      "grad_norm": 0.030063819140195847,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4245834350585938,
      "step": 5780
    },
    {
      "epoch": 0.2753333333333333,
      "grad_norm": 0.036366213113069534,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3916614055633545,
      "step": 5782
    },
    {
      "epoch": 0.2754285714285714,
      "grad_norm": 0.029278889298439026,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4042398929595947,
      "step": 5784
    },
    {
      "epoch": 0.2755238095238095,
      "grad_norm": 0.02976561151444912,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4256763458251953,
      "step": 5786
    },
    {
      "epoch": 0.2756190476190476,
      "grad_norm": 0.029811810702085495,
      "learning_rate": 0.024000000208616257,
      "loss": 2.428471088409424,
      "step": 5788
    },
    {
      "epoch": 0.2757142857142857,
      "grad_norm": 0.029828064143657684,
      "learning_rate": 0.024000000208616257,
      "loss": 2.400719404220581,
      "step": 5790
    },
    {
      "epoch": 0.2758095238095238,
      "grad_norm": 0.0323733426630497,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4038443565368652,
      "step": 5792
    },
    {
      "epoch": 0.27590476190476193,
      "grad_norm": 0.030476409941911697,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4149794578552246,
      "step": 5794
    },
    {
      "epoch": 0.276,
      "grad_norm": 0.02959195151925087,
      "learning_rate": 0.024000000208616257,
      "loss": 2.391429901123047,
      "step": 5796
    },
    {
      "epoch": 0.2760952380952381,
      "grad_norm": 0.058632317930459976,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4086430072784424,
      "step": 5798
    },
    {
      "epoch": 0.2761904761904762,
      "grad_norm": 0.0296334158629179,
      "learning_rate": 0.024000000208616257,
      "loss": 2.422232151031494,
      "step": 5800
    },
    {
      "epoch": 0.2762857142857143,
      "grad_norm": 0.030686156824231148,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4156665802001953,
      "step": 5802
    },
    {
      "epoch": 0.2763809523809524,
      "grad_norm": 0.03082870878279209,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4272632598876953,
      "step": 5804
    },
    {
      "epoch": 0.2764761904761905,
      "grad_norm": 0.031824421137571335,
      "learning_rate": 0.024000000208616257,
      "loss": 2.407200574874878,
      "step": 5806
    },
    {
      "epoch": 0.2765714285714286,
      "grad_norm": 0.03195144608616829,
      "learning_rate": 0.024000000208616257,
      "loss": 2.426790237426758,
      "step": 5808
    },
    {
      "epoch": 0.27666666666666667,
      "grad_norm": 0.029865527525544167,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4093780517578125,
      "step": 5810
    },
    {
      "epoch": 0.27676190476190476,
      "grad_norm": 0.03131138160824776,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3871772289276123,
      "step": 5812
    },
    {
      "epoch": 0.27685714285714286,
      "grad_norm": 0.030682815238833427,
      "learning_rate": 0.024000000208616257,
      "loss": 2.434083938598633,
      "step": 5814
    },
    {
      "epoch": 0.27695238095238095,
      "grad_norm": 0.029853370040655136,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4320850372314453,
      "step": 5816
    },
    {
      "epoch": 0.27704761904761904,
      "grad_norm": 0.029118241742253304,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4554178714752197,
      "step": 5818
    },
    {
      "epoch": 0.27714285714285714,
      "grad_norm": 0.030012013390660286,
      "learning_rate": 0.024000000208616257,
      "loss": 2.416299343109131,
      "step": 5820
    },
    {
      "epoch": 0.27723809523809523,
      "grad_norm": 0.030942445620894432,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4044718742370605,
      "step": 5822
    },
    {
      "epoch": 0.2773333333333333,
      "grad_norm": 0.03235562518239021,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3971140384674072,
      "step": 5824
    },
    {
      "epoch": 0.2774285714285714,
      "grad_norm": 0.029301339760422707,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4264016151428223,
      "step": 5826
    },
    {
      "epoch": 0.2775238095238095,
      "grad_norm": 0.02982015162706375,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3821322917938232,
      "step": 5828
    },
    {
      "epoch": 0.2776190476190476,
      "grad_norm": 0.029927169904112816,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4009532928466797,
      "step": 5830
    },
    {
      "epoch": 0.2777142857142857,
      "grad_norm": 0.030418438836932182,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4005284309387207,
      "step": 5832
    },
    {
      "epoch": 0.2778095238095238,
      "grad_norm": 0.030684638768434525,
      "learning_rate": 0.024000000208616257,
      "loss": 2.414228916168213,
      "step": 5834
    },
    {
      "epoch": 0.27790476190476193,
      "grad_norm": 0.03265624865889549,
      "learning_rate": 0.024000000208616257,
      "loss": 2.433143377304077,
      "step": 5836
    },
    {
      "epoch": 0.278,
      "grad_norm": 0.03039715625345707,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396028995513916,
      "step": 5838
    },
    {
      "epoch": 0.2780952380952381,
      "grad_norm": 0.03147202730178833,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4114882946014404,
      "step": 5840
    },
    {
      "epoch": 0.2781904761904762,
      "grad_norm": 0.03060498647391796,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4203648567199707,
      "step": 5842
    },
    {
      "epoch": 0.2782857142857143,
      "grad_norm": 0.03036491386592388,
      "learning_rate": 0.024000000208616257,
      "loss": 2.411343574523926,
      "step": 5844
    },
    {
      "epoch": 0.2783809523809524,
      "grad_norm": 0.030922388657927513,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4372682571411133,
      "step": 5846
    },
    {
      "epoch": 0.2784761904761905,
      "grad_norm": 0.030658042058348656,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4245033264160156,
      "step": 5848
    },
    {
      "epoch": 0.2785714285714286,
      "grad_norm": 0.030271856114268303,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4290285110473633,
      "step": 5850
    },
    {
      "epoch": 0.2786666666666667,
      "grad_norm": 0.0326555073261261,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4156975746154785,
      "step": 5852
    },
    {
      "epoch": 0.27876190476190477,
      "grad_norm": 0.032148003578186035,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4301958084106445,
      "step": 5854
    },
    {
      "epoch": 0.27885714285714286,
      "grad_norm": 0.030641939491033554,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4277498722076416,
      "step": 5856
    },
    {
      "epoch": 0.27895238095238095,
      "grad_norm": 0.03276839479804039,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396897315979004,
      "step": 5858
    },
    {
      "epoch": 0.27904761904761904,
      "grad_norm": 0.030939828604459763,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4265904426574707,
      "step": 5860
    },
    {
      "epoch": 0.27914285714285714,
      "grad_norm": 0.03142239525914192,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4034807682037354,
      "step": 5862
    },
    {
      "epoch": 0.27923809523809523,
      "grad_norm": 0.030514512211084366,
      "learning_rate": 0.024000000208616257,
      "loss": 2.422686815261841,
      "step": 5864
    },
    {
      "epoch": 0.2793333333333333,
      "grad_norm": 0.03158054128289223,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4423422813415527,
      "step": 5866
    },
    {
      "epoch": 0.2794285714285714,
      "grad_norm": 0.0318450964987278,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4191980361938477,
      "step": 5868
    },
    {
      "epoch": 0.2795238095238095,
      "grad_norm": 0.03094335086643696,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3904128074645996,
      "step": 5870
    },
    {
      "epoch": 0.2796190476190476,
      "grad_norm": 0.030817558988928795,
      "learning_rate": 0.024000000208616257,
      "loss": 2.407219886779785,
      "step": 5872
    },
    {
      "epoch": 0.2797142857142857,
      "grad_norm": 0.030856719240546227,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4635071754455566,
      "step": 5874
    },
    {
      "epoch": 0.2798095238095238,
      "grad_norm": 0.030706841498613358,
      "learning_rate": 0.024000000208616257,
      "loss": 2.422023296356201,
      "step": 5876
    },
    {
      "epoch": 0.2799047619047619,
      "grad_norm": 0.030507419258356094,
      "learning_rate": 0.024000000208616257,
      "loss": 2.434332847595215,
      "step": 5878
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.0305364690721035,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4260849952697754,
      "step": 5880
    },
    {
      "epoch": 0.2800952380952381,
      "grad_norm": 0.030062181875109673,
      "learning_rate": 0.024000000208616257,
      "loss": 2.443648338317871,
      "step": 5882
    },
    {
      "epoch": 0.2801904761904762,
      "grad_norm": 0.030890069901943207,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4268362522125244,
      "step": 5884
    },
    {
      "epoch": 0.2802857142857143,
      "grad_norm": 0.030952278524637222,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4190869331359863,
      "step": 5886
    },
    {
      "epoch": 0.2803809523809524,
      "grad_norm": 0.03146212920546532,
      "learning_rate": 0.024000000208616257,
      "loss": 2.415541887283325,
      "step": 5888
    },
    {
      "epoch": 0.2804761904761905,
      "grad_norm": 0.033116914331912994,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4002814292907715,
      "step": 5890
    },
    {
      "epoch": 0.2805714285714286,
      "grad_norm": 0.02966638281941414,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4321484565734863,
      "step": 5892
    },
    {
      "epoch": 0.2806666666666667,
      "grad_norm": 0.030536027625203133,
      "learning_rate": 0.024000000208616257,
      "loss": 2.432981014251709,
      "step": 5894
    },
    {
      "epoch": 0.28076190476190477,
      "grad_norm": 0.030000286176800728,
      "learning_rate": 0.024000000208616257,
      "loss": 2.462693452835083,
      "step": 5896
    },
    {
      "epoch": 0.28085714285714286,
      "grad_norm": 0.03132905066013336,
      "learning_rate": 0.024000000208616257,
      "loss": 2.44435715675354,
      "step": 5898
    },
    {
      "epoch": 0.28095238095238095,
      "grad_norm": 0.03006170690059662,
      "learning_rate": 0.024000000208616257,
      "loss": 2.408829689025879,
      "step": 5900
    },
    {
      "epoch": 0.28104761904761905,
      "grad_norm": 0.042367253452539444,
      "learning_rate": 0.024000000208616257,
      "loss": 2.442535400390625,
      "step": 5902
    },
    {
      "epoch": 0.28114285714285714,
      "grad_norm": 0.02926708571612835,
      "learning_rate": 0.024000000208616257,
      "loss": 2.448160171508789,
      "step": 5904
    },
    {
      "epoch": 0.28123809523809523,
      "grad_norm": 0.02941136620938778,
      "learning_rate": 0.024000000208616257,
      "loss": 2.438758373260498,
      "step": 5906
    },
    {
      "epoch": 0.2813333333333333,
      "grad_norm": 0.030222484841942787,
      "learning_rate": 0.024000000208616257,
      "loss": 2.453409194946289,
      "step": 5908
    },
    {
      "epoch": 0.2814285714285714,
      "grad_norm": 0.03157392516732216,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4113287925720215,
      "step": 5910
    },
    {
      "epoch": 0.2815238095238095,
      "grad_norm": 0.030759355053305626,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4548630714416504,
      "step": 5912
    },
    {
      "epoch": 0.2816190476190476,
      "grad_norm": 0.03189796209335327,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4435319900512695,
      "step": 5914
    },
    {
      "epoch": 0.2817142857142857,
      "grad_norm": 0.030552860349416733,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4451098442077637,
      "step": 5916
    },
    {
      "epoch": 0.2818095238095238,
      "grad_norm": 0.03157641738653183,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4091122150421143,
      "step": 5918
    },
    {
      "epoch": 0.2819047619047619,
      "grad_norm": 0.030215976759791374,
      "learning_rate": 0.024000000208616257,
      "loss": 2.455050230026245,
      "step": 5920
    },
    {
      "epoch": 0.282,
      "grad_norm": 0.030391469597816467,
      "learning_rate": 0.024000000208616257,
      "loss": 2.465106964111328,
      "step": 5922
    },
    {
      "epoch": 0.2820952380952381,
      "grad_norm": 0.030669523403048515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.42185115814209,
      "step": 5924
    },
    {
      "epoch": 0.2821904761904762,
      "grad_norm": 0.031293995678424835,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4440572261810303,
      "step": 5926
    },
    {
      "epoch": 0.2822857142857143,
      "grad_norm": 0.03026038408279419,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4374523162841797,
      "step": 5928
    },
    {
      "epoch": 0.2823809523809524,
      "grad_norm": 0.03130428120493889,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4716503620147705,
      "step": 5930
    },
    {
      "epoch": 0.2824761904761905,
      "grad_norm": 0.03031715378165245,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4383721351623535,
      "step": 5932
    },
    {
      "epoch": 0.2825714285714286,
      "grad_norm": 0.02880058065056801,
      "learning_rate": 0.024000000208616257,
      "loss": 2.437473773956299,
      "step": 5934
    },
    {
      "epoch": 0.2826666666666667,
      "grad_norm": 0.029868222773075104,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4578170776367188,
      "step": 5936
    },
    {
      "epoch": 0.28276190476190477,
      "grad_norm": 0.02971893921494484,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4463019371032715,
      "step": 5938
    },
    {
      "epoch": 0.28285714285714286,
      "grad_norm": 0.03051190823316574,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4293582439422607,
      "step": 5940
    },
    {
      "epoch": 0.28295238095238096,
      "grad_norm": 0.030507436022162437,
      "learning_rate": 0.024000000208616257,
      "loss": 2.422360897064209,
      "step": 5942
    },
    {
      "epoch": 0.28304761904761905,
      "grad_norm": 0.03896540775895119,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4102280139923096,
      "step": 5944
    },
    {
      "epoch": 0.28314285714285714,
      "grad_norm": 0.030348259955644608,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4459686279296875,
      "step": 5946
    },
    {
      "epoch": 0.28323809523809523,
      "grad_norm": 0.03088482841849327,
      "learning_rate": 0.024000000208616257,
      "loss": 2.459184169769287,
      "step": 5948
    },
    {
      "epoch": 0.2833333333333333,
      "grad_norm": 0.03666742518544197,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4459586143493652,
      "step": 5950
    },
    {
      "epoch": 0.2834285714285714,
      "grad_norm": 0.0362592376768589,
      "learning_rate": 0.024000000208616257,
      "loss": 2.457650899887085,
      "step": 5952
    },
    {
      "epoch": 0.2835238095238095,
      "grad_norm": 0.0316927470266819,
      "learning_rate": 0.024000000208616257,
      "loss": 2.414156913757324,
      "step": 5954
    },
    {
      "epoch": 0.2836190476190476,
      "grad_norm": 0.030011707916855812,
      "learning_rate": 0.024000000208616257,
      "loss": 2.45534086227417,
      "step": 5956
    },
    {
      "epoch": 0.2837142857142857,
      "grad_norm": 0.03207464516162872,
      "learning_rate": 0.024000000208616257,
      "loss": 2.41400408744812,
      "step": 5958
    },
    {
      "epoch": 0.2838095238095238,
      "grad_norm": 0.031174369156360626,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4285173416137695,
      "step": 5960
    },
    {
      "epoch": 0.2839047619047619,
      "grad_norm": 0.03004782274365425,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4439992904663086,
      "step": 5962
    },
    {
      "epoch": 0.284,
      "grad_norm": 0.030384056270122528,
      "learning_rate": 0.024000000208616257,
      "loss": 2.467072010040283,
      "step": 5964
    },
    {
      "epoch": 0.2840952380952381,
      "grad_norm": 0.029556630179286003,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4379634857177734,
      "step": 5966
    },
    {
      "epoch": 0.2841904761904762,
      "grad_norm": 0.029750768095254898,
      "learning_rate": 0.024000000208616257,
      "loss": 2.418501377105713,
      "step": 5968
    },
    {
      "epoch": 0.2842857142857143,
      "grad_norm": 0.030030805617570877,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4351024627685547,
      "step": 5970
    },
    {
      "epoch": 0.2843809523809524,
      "grad_norm": 0.03052358143031597,
      "learning_rate": 0.024000000208616257,
      "loss": 2.462615966796875,
      "step": 5972
    },
    {
      "epoch": 0.2844761904761905,
      "grad_norm": 0.0323866605758667,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4661035537719727,
      "step": 5974
    },
    {
      "epoch": 0.2845714285714286,
      "grad_norm": 0.036895908415317535,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4586734771728516,
      "step": 5976
    },
    {
      "epoch": 0.2846666666666667,
      "grad_norm": 0.03144415467977524,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4502320289611816,
      "step": 5978
    },
    {
      "epoch": 0.28476190476190477,
      "grad_norm": 0.03169401362538338,
      "learning_rate": 0.024000000208616257,
      "loss": 2.444697380065918,
      "step": 5980
    },
    {
      "epoch": 0.28485714285714286,
      "grad_norm": 0.032523639500141144,
      "learning_rate": 0.024000000208616257,
      "loss": 2.434568405151367,
      "step": 5982
    },
    {
      "epoch": 0.28495238095238096,
      "grad_norm": 0.03473818674683571,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4619975090026855,
      "step": 5984
    },
    {
      "epoch": 0.28504761904761905,
      "grad_norm": 0.03704117611050606,
      "learning_rate": 0.024000000208616257,
      "loss": 2.436497211456299,
      "step": 5986
    },
    {
      "epoch": 0.28514285714285714,
      "grad_norm": 0.03641713038086891,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4565939903259277,
      "step": 5988
    },
    {
      "epoch": 0.28523809523809524,
      "grad_norm": 0.029314879328012466,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4084320068359375,
      "step": 5990
    },
    {
      "epoch": 0.2853333333333333,
      "grad_norm": 0.033886510878801346,
      "learning_rate": 0.024000000208616257,
      "loss": 2.450089931488037,
      "step": 5992
    },
    {
      "epoch": 0.2854285714285714,
      "grad_norm": 0.03232895955443382,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4570064544677734,
      "step": 5994
    },
    {
      "epoch": 0.2855238095238095,
      "grad_norm": 0.029789892956614494,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4474434852600098,
      "step": 5996
    },
    {
      "epoch": 0.2856190476190476,
      "grad_norm": 0.029370378702878952,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4588401317596436,
      "step": 5998
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.02948187105357647,
      "learning_rate": 0.024000000208616257,
      "loss": 2.442338466644287,
      "step": 6000
    },
    {
      "epoch": 0.2858095238095238,
      "grad_norm": 0.028529956936836243,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4520909786224365,
      "step": 6002
    },
    {
      "epoch": 0.2859047619047619,
      "grad_norm": 0.02919137477874756,
      "learning_rate": 0.024000000208616257,
      "loss": 2.428828716278076,
      "step": 6004
    },
    {
      "epoch": 0.286,
      "grad_norm": 0.030001148581504822,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4451889991760254,
      "step": 6006
    },
    {
      "epoch": 0.28609523809523807,
      "grad_norm": 0.031731296330690384,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4798943996429443,
      "step": 6008
    },
    {
      "epoch": 0.2861904761904762,
      "grad_norm": 0.033025581389665604,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4376304149627686,
      "step": 6010
    },
    {
      "epoch": 0.2862857142857143,
      "grad_norm": 0.03402454033493996,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4606308937072754,
      "step": 6012
    },
    {
      "epoch": 0.2863809523809524,
      "grad_norm": 0.03207368031144142,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4566006660461426,
      "step": 6014
    },
    {
      "epoch": 0.2864761904761905,
      "grad_norm": 0.03041372261941433,
      "learning_rate": 0.024000000208616257,
      "loss": 2.402761459350586,
      "step": 6016
    },
    {
      "epoch": 0.2865714285714286,
      "grad_norm": 0.029119379818439484,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4449515342712402,
      "step": 6018
    },
    {
      "epoch": 0.2866666666666667,
      "grad_norm": 0.029493533074855804,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4315128326416016,
      "step": 6020
    },
    {
      "epoch": 0.2867619047619048,
      "grad_norm": 0.03053133375942707,
      "learning_rate": 0.024000000208616257,
      "loss": 2.442108631134033,
      "step": 6022
    },
    {
      "epoch": 0.28685714285714287,
      "grad_norm": 0.03064528852701187,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4401040077209473,
      "step": 6024
    },
    {
      "epoch": 0.28695238095238096,
      "grad_norm": 0.03047105297446251,
      "learning_rate": 0.024000000208616257,
      "loss": 2.445969343185425,
      "step": 6026
    },
    {
      "epoch": 0.28704761904761905,
      "grad_norm": 0.030832571908831596,
      "learning_rate": 0.024000000208616257,
      "loss": 2.442370891571045,
      "step": 6028
    },
    {
      "epoch": 0.28714285714285714,
      "grad_norm": 0.02906797267496586,
      "learning_rate": 0.024000000208616257,
      "loss": 2.429640769958496,
      "step": 6030
    },
    {
      "epoch": 0.28723809523809524,
      "grad_norm": 0.030353711917996407,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4413981437683105,
      "step": 6032
    },
    {
      "epoch": 0.28733333333333333,
      "grad_norm": 0.029831325635313988,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4416310787200928,
      "step": 6034
    },
    {
      "epoch": 0.2874285714285714,
      "grad_norm": 0.03156975284218788,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4126768112182617,
      "step": 6036
    },
    {
      "epoch": 0.2875238095238095,
      "grad_norm": 0.031732089817523956,
      "learning_rate": 0.024000000208616257,
      "loss": 2.435192108154297,
      "step": 6038
    },
    {
      "epoch": 0.2876190476190476,
      "grad_norm": 0.0311430636793375,
      "learning_rate": 0.024000000208616257,
      "loss": 2.419882297515869,
      "step": 6040
    },
    {
      "epoch": 0.2877142857142857,
      "grad_norm": 0.030729148536920547,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4247310161590576,
      "step": 6042
    },
    {
      "epoch": 0.2878095238095238,
      "grad_norm": 0.02981674298644066,
      "learning_rate": 0.024000000208616257,
      "loss": 2.476203441619873,
      "step": 6044
    },
    {
      "epoch": 0.2879047619047619,
      "grad_norm": 0.030511224642395973,
      "learning_rate": 0.024000000208616257,
      "loss": 2.411952495574951,
      "step": 6046
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.030743755400180817,
      "learning_rate": 0.024000000208616257,
      "loss": 2.43540358543396,
      "step": 6048
    },
    {
      "epoch": 0.28809523809523807,
      "grad_norm": 0.030877428129315376,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4507858753204346,
      "step": 6050
    },
    {
      "epoch": 0.28819047619047616,
      "grad_norm": 0.03416414558887482,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4343767166137695,
      "step": 6052
    },
    {
      "epoch": 0.2882857142857143,
      "grad_norm": 0.031241370365023613,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4218082427978516,
      "step": 6054
    },
    {
      "epoch": 0.2883809523809524,
      "grad_norm": 0.032552652060985565,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4002015590667725,
      "step": 6056
    },
    {
      "epoch": 0.2884761904761905,
      "grad_norm": 0.031226124614477158,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4340744018554688,
      "step": 6058
    },
    {
      "epoch": 0.2885714285714286,
      "grad_norm": 0.03198246657848358,
      "learning_rate": 0.024000000208616257,
      "loss": 2.421462297439575,
      "step": 6060
    },
    {
      "epoch": 0.2886666666666667,
      "grad_norm": 0.03484688699245453,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4347500801086426,
      "step": 6062
    },
    {
      "epoch": 0.2887619047619048,
      "grad_norm": 0.032333992421627045,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4126620292663574,
      "step": 6064
    },
    {
      "epoch": 0.28885714285714287,
      "grad_norm": 0.03032061643898487,
      "learning_rate": 0.024000000208616257,
      "loss": 2.432344913482666,
      "step": 6066
    },
    {
      "epoch": 0.28895238095238096,
      "grad_norm": 0.033521492034196854,
      "learning_rate": 0.024000000208616257,
      "loss": 2.409395694732666,
      "step": 6068
    },
    {
      "epoch": 0.28904761904761905,
      "grad_norm": 0.03254038840532303,
      "learning_rate": 0.024000000208616257,
      "loss": 2.428349494934082,
      "step": 6070
    },
    {
      "epoch": 0.28914285714285715,
      "grad_norm": 0.034831512719392776,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4277501106262207,
      "step": 6072
    },
    {
      "epoch": 0.28923809523809524,
      "grad_norm": 0.030766239389777184,
      "learning_rate": 0.024000000208616257,
      "loss": 2.44272518157959,
      "step": 6074
    },
    {
      "epoch": 0.28933333333333333,
      "grad_norm": 0.029845865443348885,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4152283668518066,
      "step": 6076
    },
    {
      "epoch": 0.2894285714285714,
      "grad_norm": 0.029288778081536293,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4004945755004883,
      "step": 6078
    },
    {
      "epoch": 0.2895238095238095,
      "grad_norm": 0.03152845799922943,
      "learning_rate": 0.024000000208616257,
      "loss": 2.41096830368042,
      "step": 6080
    },
    {
      "epoch": 0.2896190476190476,
      "grad_norm": 0.030044732615351677,
      "learning_rate": 0.024000000208616257,
      "loss": 2.414048671722412,
      "step": 6082
    },
    {
      "epoch": 0.2897142857142857,
      "grad_norm": 0.03080243244767189,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390315055847168,
      "step": 6084
    },
    {
      "epoch": 0.2898095238095238,
      "grad_norm": 0.030726013705134392,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4305622577667236,
      "step": 6086
    },
    {
      "epoch": 0.2899047619047619,
      "grad_norm": 0.029803413897752762,
      "learning_rate": 0.024000000208616257,
      "loss": 2.410399913787842,
      "step": 6088
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.030176175758242607,
      "learning_rate": 0.024000000208616257,
      "loss": 2.425286293029785,
      "step": 6090
    },
    {
      "epoch": 0.2900952380952381,
      "grad_norm": 0.029367558658123016,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4391725063323975,
      "step": 6092
    },
    {
      "epoch": 0.29019047619047617,
      "grad_norm": 0.029218891635537148,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4036412239074707,
      "step": 6094
    },
    {
      "epoch": 0.29028571428571426,
      "grad_norm": 0.031588565558195114,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4270992279052734,
      "step": 6096
    },
    {
      "epoch": 0.2903809523809524,
      "grad_norm": 0.03142644837498665,
      "learning_rate": 0.024000000208616257,
      "loss": 2.415203094482422,
      "step": 6098
    },
    {
      "epoch": 0.2904761904761905,
      "grad_norm": 0.03253505006432533,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4203741550445557,
      "step": 6100
    },
    {
      "epoch": 0.2905714285714286,
      "grad_norm": 0.030857732519507408,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390652656555176,
      "step": 6102
    },
    {
      "epoch": 0.2906666666666667,
      "grad_norm": 0.030531033873558044,
      "learning_rate": 0.024000000208616257,
      "loss": 2.408663272857666,
      "step": 6104
    },
    {
      "epoch": 0.2907619047619048,
      "grad_norm": 0.030398381873965263,
      "learning_rate": 0.024000000208616257,
      "loss": 2.399930000305176,
      "step": 6106
    },
    {
      "epoch": 0.29085714285714287,
      "grad_norm": 0.03529582917690277,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4278907775878906,
      "step": 6108
    },
    {
      "epoch": 0.29095238095238096,
      "grad_norm": 0.03846205025911331,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4219956398010254,
      "step": 6110
    },
    {
      "epoch": 0.29104761904761905,
      "grad_norm": 0.032568562775850296,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4198341369628906,
      "step": 6112
    },
    {
      "epoch": 0.29114285714285715,
      "grad_norm": 0.03220415860414505,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4088635444641113,
      "step": 6114
    },
    {
      "epoch": 0.29123809523809524,
      "grad_norm": 0.030578719452023506,
      "learning_rate": 0.024000000208616257,
      "loss": 2.432494640350342,
      "step": 6116
    },
    {
      "epoch": 0.29133333333333333,
      "grad_norm": 0.02890986204147339,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392268657684326,
      "step": 6118
    },
    {
      "epoch": 0.2914285714285714,
      "grad_norm": 0.029330482706427574,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392806053161621,
      "step": 6120
    },
    {
      "epoch": 0.2915238095238095,
      "grad_norm": 0.029655836522579193,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4184155464172363,
      "step": 6122
    },
    {
      "epoch": 0.2916190476190476,
      "grad_norm": 0.028696781024336815,
      "learning_rate": 0.024000000208616257,
      "loss": 2.438741683959961,
      "step": 6124
    },
    {
      "epoch": 0.2917142857142857,
      "grad_norm": 0.028648799285292625,
      "learning_rate": 0.024000000208616257,
      "loss": 2.43717885017395,
      "step": 6126
    },
    {
      "epoch": 0.2918095238095238,
      "grad_norm": 0.029009662568569183,
      "learning_rate": 0.024000000208616257,
      "loss": 2.387840747833252,
      "step": 6128
    },
    {
      "epoch": 0.2919047619047619,
      "grad_norm": 0.030119992792606354,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4254977703094482,
      "step": 6130
    },
    {
      "epoch": 0.292,
      "grad_norm": 0.030130447819828987,
      "learning_rate": 0.024000000208616257,
      "loss": 2.413989305496216,
      "step": 6132
    },
    {
      "epoch": 0.2920952380952381,
      "grad_norm": 0.02928055077791214,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398425579071045,
      "step": 6134
    },
    {
      "epoch": 0.29219047619047617,
      "grad_norm": 0.028877263888716698,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396592378616333,
      "step": 6136
    },
    {
      "epoch": 0.29228571428571426,
      "grad_norm": 0.030785128474235535,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3794426918029785,
      "step": 6138
    },
    {
      "epoch": 0.2923809523809524,
      "grad_norm": 0.03520051762461662,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3855576515197754,
      "step": 6140
    },
    {
      "epoch": 0.2924761904761905,
      "grad_norm": 0.030070243403315544,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4246721267700195,
      "step": 6142
    },
    {
      "epoch": 0.2925714285714286,
      "grad_norm": 0.03379165381193161,
      "learning_rate": 0.024000000208616257,
      "loss": 2.408130407333374,
      "step": 6144
    },
    {
      "epoch": 0.2926666666666667,
      "grad_norm": 0.030511919409036636,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4117136001586914,
      "step": 6146
    },
    {
      "epoch": 0.2927619047619048,
      "grad_norm": 0.03049665316939354,
      "learning_rate": 0.024000000208616257,
      "loss": 2.400404453277588,
      "step": 6148
    },
    {
      "epoch": 0.29285714285714287,
      "grad_norm": 0.02921309694647789,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3985371589660645,
      "step": 6150
    },
    {
      "epoch": 0.29295238095238096,
      "grad_norm": 0.030633147805929184,
      "learning_rate": 0.024000000208616257,
      "loss": 2.413053512573242,
      "step": 6152
    },
    {
      "epoch": 0.29304761904761906,
      "grad_norm": 0.02924421802163124,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398658514022827,
      "step": 6154
    },
    {
      "epoch": 0.29314285714285715,
      "grad_norm": 0.028627166524529457,
      "learning_rate": 0.024000000208616257,
      "loss": 2.418416976928711,
      "step": 6156
    },
    {
      "epoch": 0.29323809523809524,
      "grad_norm": 0.029889678582549095,
      "learning_rate": 0.024000000208616257,
      "loss": 2.404519557952881,
      "step": 6158
    },
    {
      "epoch": 0.29333333333333333,
      "grad_norm": 0.02967916801571846,
      "learning_rate": 0.024000000208616257,
      "loss": 2.420391798019409,
      "step": 6160
    },
    {
      "epoch": 0.2934285714285714,
      "grad_norm": 0.03018069639801979,
      "learning_rate": 0.024000000208616257,
      "loss": 2.404752254486084,
      "step": 6162
    },
    {
      "epoch": 0.2935238095238095,
      "grad_norm": 0.031207526102662086,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3971452713012695,
      "step": 6164
    },
    {
      "epoch": 0.2936190476190476,
      "grad_norm": 0.029452545568346977,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4290828704833984,
      "step": 6166
    },
    {
      "epoch": 0.2937142857142857,
      "grad_norm": 0.0295589379966259,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4010298252105713,
      "step": 6168
    },
    {
      "epoch": 0.2938095238095238,
      "grad_norm": 0.030462097376585007,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384692668914795,
      "step": 6170
    },
    {
      "epoch": 0.2939047619047619,
      "grad_norm": 0.030001798644661903,
      "learning_rate": 0.024000000208616257,
      "loss": 2.410719394683838,
      "step": 6172
    },
    {
      "epoch": 0.294,
      "grad_norm": 0.030867138877511024,
      "learning_rate": 0.024000000208616257,
      "loss": 2.387799024581909,
      "step": 6174
    },
    {
      "epoch": 0.2940952380952381,
      "grad_norm": 0.03122049756348133,
      "learning_rate": 0.024000000208616257,
      "loss": 2.408491373062134,
      "step": 6176
    },
    {
      "epoch": 0.29419047619047617,
      "grad_norm": 0.030473507940769196,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4553112983703613,
      "step": 6178
    },
    {
      "epoch": 0.29428571428571426,
      "grad_norm": 0.031921081244945526,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4028406143188477,
      "step": 6180
    },
    {
      "epoch": 0.29438095238095235,
      "grad_norm": 0.03799763694405556,
      "learning_rate": 0.024000000208616257,
      "loss": 2.386849880218506,
      "step": 6182
    },
    {
      "epoch": 0.2944761904761905,
      "grad_norm": 0.03744405880570412,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383111000061035,
      "step": 6184
    },
    {
      "epoch": 0.2945714285714286,
      "grad_norm": 0.03520790487527847,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396151065826416,
      "step": 6186
    },
    {
      "epoch": 0.2946666666666667,
      "grad_norm": 0.032545480877161026,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3864550590515137,
      "step": 6188
    },
    {
      "epoch": 0.2947619047619048,
      "grad_norm": 0.029453841969370842,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4271655082702637,
      "step": 6190
    },
    {
      "epoch": 0.2948571428571429,
      "grad_norm": 0.03266867995262146,
      "learning_rate": 0.024000000208616257,
      "loss": 2.376993417739868,
      "step": 6192
    },
    {
      "epoch": 0.29495238095238097,
      "grad_norm": 0.029969044029712677,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396732807159424,
      "step": 6194
    },
    {
      "epoch": 0.29504761904761906,
      "grad_norm": 0.02913718856871128,
      "learning_rate": 0.024000000208616257,
      "loss": 2.404344081878662,
      "step": 6196
    },
    {
      "epoch": 0.29514285714285715,
      "grad_norm": 0.030002065002918243,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4053454399108887,
      "step": 6198
    },
    {
      "epoch": 0.29523809523809524,
      "grad_norm": 0.029469219967722893,
      "learning_rate": 0.024000000208616257,
      "loss": 2.41013240814209,
      "step": 6200
    },
    {
      "epoch": 0.29533333333333334,
      "grad_norm": 0.03019625134766102,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4061102867126465,
      "step": 6202
    },
    {
      "epoch": 0.29542857142857143,
      "grad_norm": 0.02869257889688015,
      "learning_rate": 0.024000000208616257,
      "loss": 2.410395622253418,
      "step": 6204
    },
    {
      "epoch": 0.2955238095238095,
      "grad_norm": 0.02923528105020523,
      "learning_rate": 0.024000000208616257,
      "loss": 2.39755916595459,
      "step": 6206
    },
    {
      "epoch": 0.2956190476190476,
      "grad_norm": 0.029516516253352165,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3845150470733643,
      "step": 6208
    },
    {
      "epoch": 0.2957142857142857,
      "grad_norm": 0.02876441180706024,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4046125411987305,
      "step": 6210
    },
    {
      "epoch": 0.2958095238095238,
      "grad_norm": 0.029344074428081512,
      "learning_rate": 0.024000000208616257,
      "loss": 2.381272315979004,
      "step": 6212
    },
    {
      "epoch": 0.2959047619047619,
      "grad_norm": 0.02884243056178093,
      "learning_rate": 0.024000000208616257,
      "loss": 2.379793643951416,
      "step": 6214
    },
    {
      "epoch": 0.296,
      "grad_norm": 0.028938455507159233,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3947997093200684,
      "step": 6216
    },
    {
      "epoch": 0.2960952380952381,
      "grad_norm": 0.0319499671459198,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3873093128204346,
      "step": 6218
    },
    {
      "epoch": 0.29619047619047617,
      "grad_norm": 0.03386876359581947,
      "learning_rate": 0.024000000208616257,
      "loss": 2.394594669342041,
      "step": 6220
    },
    {
      "epoch": 0.29628571428571426,
      "grad_norm": 0.03166278824210167,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385469913482666,
      "step": 6222
    },
    {
      "epoch": 0.29638095238095236,
      "grad_norm": 0.029478229582309723,
      "learning_rate": 0.024000000208616257,
      "loss": 2.386821985244751,
      "step": 6224
    },
    {
      "epoch": 0.29647619047619045,
      "grad_norm": 0.0299871563911438,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382486581802368,
      "step": 6226
    },
    {
      "epoch": 0.2965714285714286,
      "grad_norm": 0.02832522988319397,
      "learning_rate": 0.024000000208616257,
      "loss": 2.386258125305176,
      "step": 6228
    },
    {
      "epoch": 0.2966666666666667,
      "grad_norm": 0.03017774224281311,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398681163787842,
      "step": 6230
    },
    {
      "epoch": 0.2967619047619048,
      "grad_norm": 0.02863307110965252,
      "learning_rate": 0.024000000208616257,
      "loss": 2.378185272216797,
      "step": 6232
    },
    {
      "epoch": 0.2968571428571429,
      "grad_norm": 0.02968939207494259,
      "learning_rate": 0.024000000208616257,
      "loss": 2.375802993774414,
      "step": 6234
    },
    {
      "epoch": 0.29695238095238097,
      "grad_norm": 0.029388248920440674,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3913650512695312,
      "step": 6236
    },
    {
      "epoch": 0.29704761904761906,
      "grad_norm": 0.03103412501513958,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38293719291687,
      "step": 6238
    },
    {
      "epoch": 0.29714285714285715,
      "grad_norm": 0.028028704226017,
      "learning_rate": 0.024000000208616257,
      "loss": 2.393132209777832,
      "step": 6240
    },
    {
      "epoch": 0.29723809523809525,
      "grad_norm": 0.03213810175657272,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3867733478546143,
      "step": 6242
    },
    {
      "epoch": 0.29733333333333334,
      "grad_norm": 0.029475048184394836,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3856635093688965,
      "step": 6244
    },
    {
      "epoch": 0.29742857142857143,
      "grad_norm": 0.03102121688425541,
      "learning_rate": 0.024000000208616257,
      "loss": 2.374415874481201,
      "step": 6246
    },
    {
      "epoch": 0.2975238095238095,
      "grad_norm": 0.029679862782359123,
      "learning_rate": 0.024000000208616257,
      "loss": 2.391484260559082,
      "step": 6248
    },
    {
      "epoch": 0.2976190476190476,
      "grad_norm": 0.028446072712540627,
      "learning_rate": 0.024000000208616257,
      "loss": 2.359140634536743,
      "step": 6250
    },
    {
      "epoch": 0.2977142857142857,
      "grad_norm": 0.028913788497447968,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398242235183716,
      "step": 6252
    },
    {
      "epoch": 0.2978095238095238,
      "grad_norm": 0.028609566390514374,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4083738327026367,
      "step": 6254
    },
    {
      "epoch": 0.2979047619047619,
      "grad_norm": 0.029605332762002945,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3719067573547363,
      "step": 6256
    },
    {
      "epoch": 0.298,
      "grad_norm": 0.030333707109093666,
      "learning_rate": 0.024000000208616257,
      "loss": 2.374971628189087,
      "step": 6258
    },
    {
      "epoch": 0.2980952380952381,
      "grad_norm": 0.030277365818619728,
      "learning_rate": 0.024000000208616257,
      "loss": 2.362861156463623,
      "step": 6260
    },
    {
      "epoch": 0.2981904761904762,
      "grad_norm": 0.03067701682448387,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3669614791870117,
      "step": 6262
    },
    {
      "epoch": 0.29828571428571427,
      "grad_norm": 0.029332464560866356,
      "learning_rate": 0.024000000208616257,
      "loss": 2.386892795562744,
      "step": 6264
    },
    {
      "epoch": 0.29838095238095236,
      "grad_norm": 0.028934013098478317,
      "learning_rate": 0.024000000208616257,
      "loss": 2.369574785232544,
      "step": 6266
    },
    {
      "epoch": 0.29847619047619045,
      "grad_norm": 0.029047660529613495,
      "learning_rate": 0.024000000208616257,
      "loss": 2.40632963180542,
      "step": 6268
    },
    {
      "epoch": 0.2985714285714286,
      "grad_norm": 0.030155565589666367,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4218883514404297,
      "step": 6270
    },
    {
      "epoch": 0.2986666666666667,
      "grad_norm": 0.030807355418801308,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4023821353912354,
      "step": 6272
    },
    {
      "epoch": 0.2987619047619048,
      "grad_norm": 0.030271202325820923,
      "learning_rate": 0.024000000208616257,
      "loss": 2.348284959793091,
      "step": 6274
    },
    {
      "epoch": 0.2988571428571429,
      "grad_norm": 0.030739858746528625,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3717989921569824,
      "step": 6276
    },
    {
      "epoch": 0.29895238095238097,
      "grad_norm": 0.031769488006830215,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3772706985473633,
      "step": 6278
    },
    {
      "epoch": 0.29904761904761906,
      "grad_norm": 0.030596574768424034,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3405585289001465,
      "step": 6280
    },
    {
      "epoch": 0.29914285714285715,
      "grad_norm": 0.028767000883817673,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3589296340942383,
      "step": 6282
    },
    {
      "epoch": 0.29923809523809525,
      "grad_norm": 0.02941076084971428,
      "learning_rate": 0.024000000208616257,
      "loss": 2.386852741241455,
      "step": 6284
    },
    {
      "epoch": 0.29933333333333334,
      "grad_norm": 0.030165476724505424,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3803796768188477,
      "step": 6286
    },
    {
      "epoch": 0.29942857142857143,
      "grad_norm": 0.02997790463268757,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380345344543457,
      "step": 6288
    },
    {
      "epoch": 0.2995238095238095,
      "grad_norm": 0.02986382693052292,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3663761615753174,
      "step": 6290
    },
    {
      "epoch": 0.2996190476190476,
      "grad_norm": 0.029478663578629494,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3664679527282715,
      "step": 6292
    },
    {
      "epoch": 0.2997142857142857,
      "grad_norm": 0.029559725895524025,
      "learning_rate": 0.024000000208616257,
      "loss": 2.394038677215576,
      "step": 6294
    },
    {
      "epoch": 0.2998095238095238,
      "grad_norm": 0.02897718735039234,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3769140243530273,
      "step": 6296
    },
    {
      "epoch": 0.2999047619047619,
      "grad_norm": 0.033866360783576965,
      "learning_rate": 0.024000000208616257,
      "loss": 2.371870994567871,
      "step": 6298
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.029873307794332504,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3710203170776367,
      "step": 6300
    },
    {
      "epoch": 0.3000952380952381,
      "grad_norm": 0.03052469715476036,
      "learning_rate": 0.024000000208616257,
      "loss": 2.349310874938965,
      "step": 6302
    },
    {
      "epoch": 0.3001904761904762,
      "grad_norm": 0.028601093217730522,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3943562507629395,
      "step": 6304
    },
    {
      "epoch": 0.30028571428571427,
      "grad_norm": 0.02900421991944313,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3869071006774902,
      "step": 6306
    },
    {
      "epoch": 0.30038095238095236,
      "grad_norm": 0.02909754402935505,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3714840412139893,
      "step": 6308
    },
    {
      "epoch": 0.30047619047619045,
      "grad_norm": 0.030261747539043427,
      "learning_rate": 0.024000000208616257,
      "loss": 2.368900775909424,
      "step": 6310
    },
    {
      "epoch": 0.30057142857142854,
      "grad_norm": 0.034732263535261154,
      "learning_rate": 0.024000000208616257,
      "loss": 2.353426933288574,
      "step": 6312
    },
    {
      "epoch": 0.3006666666666667,
      "grad_norm": 0.030732370913028717,
      "learning_rate": 0.024000000208616257,
      "loss": 2.36553955078125,
      "step": 6314
    },
    {
      "epoch": 0.3007619047619048,
      "grad_norm": 0.03006397746503353,
      "learning_rate": 0.024000000208616257,
      "loss": 2.34895396232605,
      "step": 6316
    },
    {
      "epoch": 0.3008571428571429,
      "grad_norm": 0.02850496396422386,
      "learning_rate": 0.024000000208616257,
      "loss": 2.391019821166992,
      "step": 6318
    },
    {
      "epoch": 0.30095238095238097,
      "grad_norm": 0.02953995019197464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3627352714538574,
      "step": 6320
    },
    {
      "epoch": 0.30104761904761906,
      "grad_norm": 0.03028881922364235,
      "learning_rate": 0.024000000208616257,
      "loss": 2.36260986328125,
      "step": 6322
    },
    {
      "epoch": 0.30114285714285716,
      "grad_norm": 0.02920750342309475,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3778300285339355,
      "step": 6324
    },
    {
      "epoch": 0.30123809523809525,
      "grad_norm": 0.029049871489405632,
      "learning_rate": 0.024000000208616257,
      "loss": 2.34736967086792,
      "step": 6326
    },
    {
      "epoch": 0.30133333333333334,
      "grad_norm": 0.03125058859586716,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3484573364257812,
      "step": 6328
    },
    {
      "epoch": 0.30142857142857143,
      "grad_norm": 0.028908133506774902,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3630216121673584,
      "step": 6330
    },
    {
      "epoch": 0.3015238095238095,
      "grad_norm": 0.030415229499340057,
      "learning_rate": 0.024000000208616257,
      "loss": 2.364722490310669,
      "step": 6332
    },
    {
      "epoch": 0.3016190476190476,
      "grad_norm": 0.035677410662174225,
      "learning_rate": 0.024000000208616257,
      "loss": 2.340344190597534,
      "step": 6334
    },
    {
      "epoch": 0.3017142857142857,
      "grad_norm": 0.029970012605190277,
      "learning_rate": 0.024000000208616257,
      "loss": 2.349818229675293,
      "step": 6336
    },
    {
      "epoch": 0.3018095238095238,
      "grad_norm": 0.031508028507232666,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4211959838867188,
      "step": 6338
    },
    {
      "epoch": 0.3019047619047619,
      "grad_norm": 0.03199058771133423,
      "learning_rate": 0.024000000208616257,
      "loss": 2.36906099319458,
      "step": 6340
    },
    {
      "epoch": 0.302,
      "grad_norm": 0.033742476254701614,
      "learning_rate": 0.024000000208616257,
      "loss": 2.348757743835449,
      "step": 6342
    },
    {
      "epoch": 0.3020952380952381,
      "grad_norm": 0.032974131405353546,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3575143814086914,
      "step": 6344
    },
    {
      "epoch": 0.3021904761904762,
      "grad_norm": 0.0315173864364624,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3412365913391113,
      "step": 6346
    },
    {
      "epoch": 0.30228571428571427,
      "grad_norm": 0.03073800541460514,
      "learning_rate": 0.024000000208616257,
      "loss": 2.370591163635254,
      "step": 6348
    },
    {
      "epoch": 0.30238095238095236,
      "grad_norm": 0.030811628326773643,
      "learning_rate": 0.024000000208616257,
      "loss": 2.35609769821167,
      "step": 6350
    },
    {
      "epoch": 0.30247619047619045,
      "grad_norm": 0.0296856127679348,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3591532707214355,
      "step": 6352
    },
    {
      "epoch": 0.30257142857142855,
      "grad_norm": 0.030461115762591362,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3573710918426514,
      "step": 6354
    },
    {
      "epoch": 0.30266666666666664,
      "grad_norm": 0.030828215181827545,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3749890327453613,
      "step": 6356
    },
    {
      "epoch": 0.3027619047619048,
      "grad_norm": 0.02959151193499565,
      "learning_rate": 0.024000000208616257,
      "loss": 2.361171245574951,
      "step": 6358
    },
    {
      "epoch": 0.3028571428571429,
      "grad_norm": 0.029876986518502235,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3493261337280273,
      "step": 6360
    },
    {
      "epoch": 0.302952380952381,
      "grad_norm": 0.030514022335410118,
      "learning_rate": 0.024000000208616257,
      "loss": 2.305880546569824,
      "step": 6362
    },
    {
      "epoch": 0.30304761904761907,
      "grad_norm": 0.029770568013191223,
      "learning_rate": 0.024000000208616257,
      "loss": 2.368907928466797,
      "step": 6364
    },
    {
      "epoch": 0.30314285714285716,
      "grad_norm": 0.029339954257011414,
      "learning_rate": 0.024000000208616257,
      "loss": 2.317441463470459,
      "step": 6366
    },
    {
      "epoch": 0.30323809523809525,
      "grad_norm": 0.03049355372786522,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3394582271575928,
      "step": 6368
    },
    {
      "epoch": 0.30333333333333334,
      "grad_norm": 0.030364181846380234,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3430709838867188,
      "step": 6370
    },
    {
      "epoch": 0.30342857142857144,
      "grad_norm": 0.029699547216296196,
      "learning_rate": 0.024000000208616257,
      "loss": 2.332200050354004,
      "step": 6372
    },
    {
      "epoch": 0.30352380952380953,
      "grad_norm": 0.03139529377222061,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3433914184570312,
      "step": 6374
    },
    {
      "epoch": 0.3036190476190476,
      "grad_norm": 0.031691379845142365,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3571670055389404,
      "step": 6376
    },
    {
      "epoch": 0.3037142857142857,
      "grad_norm": 0.039775218814611435,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3537678718566895,
      "step": 6378
    },
    {
      "epoch": 0.3038095238095238,
      "grad_norm": 0.0333886444568634,
      "learning_rate": 0.024000000208616257,
      "loss": 2.33561372756958,
      "step": 6380
    },
    {
      "epoch": 0.3039047619047619,
      "grad_norm": 0.03307177871465683,
      "learning_rate": 0.024000000208616257,
      "loss": 2.352508068084717,
      "step": 6382
    },
    {
      "epoch": 0.304,
      "grad_norm": 0.0321136899292469,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3266265392303467,
      "step": 6384
    },
    {
      "epoch": 0.3040952380952381,
      "grad_norm": 0.03006013110280037,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3507261276245117,
      "step": 6386
    },
    {
      "epoch": 0.3041904761904762,
      "grad_norm": 0.032090723514556885,
      "learning_rate": 0.024000000208616257,
      "loss": 2.353166103363037,
      "step": 6388
    },
    {
      "epoch": 0.30428571428571427,
      "grad_norm": 0.028613679111003876,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3557522296905518,
      "step": 6390
    },
    {
      "epoch": 0.30438095238095236,
      "grad_norm": 0.030914470553398132,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3342013359069824,
      "step": 6392
    },
    {
      "epoch": 0.30447619047619046,
      "grad_norm": 0.032159507274627686,
      "learning_rate": 0.024000000208616257,
      "loss": 2.325378656387329,
      "step": 6394
    },
    {
      "epoch": 0.30457142857142855,
      "grad_norm": 0.030638545751571655,
      "learning_rate": 0.024000000208616257,
      "loss": 2.339792251586914,
      "step": 6396
    },
    {
      "epoch": 0.30466666666666664,
      "grad_norm": 0.030159857124090195,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3391616344451904,
      "step": 6398
    },
    {
      "epoch": 0.3047619047619048,
      "grad_norm": 0.03119141422212124,
      "learning_rate": 0.024000000208616257,
      "loss": 2.325261116027832,
      "step": 6400
    },
    {
      "epoch": 0.3048571428571429,
      "grad_norm": 0.029116680845618248,
      "learning_rate": 0.024000000208616257,
      "loss": 2.340701103210449,
      "step": 6402
    },
    {
      "epoch": 0.304952380952381,
      "grad_norm": 0.028415976092219353,
      "learning_rate": 0.024000000208616257,
      "loss": 2.351290225982666,
      "step": 6404
    },
    {
      "epoch": 0.30504761904761907,
      "grad_norm": 0.03050910122692585,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3352484703063965,
      "step": 6406
    },
    {
      "epoch": 0.30514285714285716,
      "grad_norm": 0.028967514634132385,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3293559551239014,
      "step": 6408
    },
    {
      "epoch": 0.30523809523809525,
      "grad_norm": 0.02979886159300804,
      "learning_rate": 0.024000000208616257,
      "loss": 2.376918077468872,
      "step": 6410
    },
    {
      "epoch": 0.30533333333333335,
      "grad_norm": 0.028688542544841766,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3602054119110107,
      "step": 6412
    },
    {
      "epoch": 0.30542857142857144,
      "grad_norm": 0.028866274282336235,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3494038581848145,
      "step": 6414
    },
    {
      "epoch": 0.30552380952380953,
      "grad_norm": 0.029814528301358223,
      "learning_rate": 0.024000000208616257,
      "loss": 2.337566375732422,
      "step": 6416
    },
    {
      "epoch": 0.3056190476190476,
      "grad_norm": 0.02985096164047718,
      "learning_rate": 0.024000000208616257,
      "loss": 2.342189311981201,
      "step": 6418
    },
    {
      "epoch": 0.3057142857142857,
      "grad_norm": 0.031116409227252007,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3239994049072266,
      "step": 6420
    },
    {
      "epoch": 0.3058095238095238,
      "grad_norm": 0.028099246323108673,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3329596519470215,
      "step": 6422
    },
    {
      "epoch": 0.3059047619047619,
      "grad_norm": 0.031047286465764046,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3285062313079834,
      "step": 6424
    },
    {
      "epoch": 0.306,
      "grad_norm": 0.030233638361096382,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3415894508361816,
      "step": 6426
    },
    {
      "epoch": 0.3060952380952381,
      "grad_norm": 0.029204512014985085,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3137500286102295,
      "step": 6428
    },
    {
      "epoch": 0.3061904761904762,
      "grad_norm": 0.029379330575466156,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3079605102539062,
      "step": 6430
    },
    {
      "epoch": 0.3062857142857143,
      "grad_norm": 0.028447212651371956,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3419177532196045,
      "step": 6432
    },
    {
      "epoch": 0.30638095238095236,
      "grad_norm": 0.02918078750371933,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3258371353149414,
      "step": 6434
    },
    {
      "epoch": 0.30647619047619046,
      "grad_norm": 0.03030138835310936,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3137145042419434,
      "step": 6436
    },
    {
      "epoch": 0.30657142857142855,
      "grad_norm": 0.028849851340055466,
      "learning_rate": 0.024000000208616257,
      "loss": 2.312994956970215,
      "step": 6438
    },
    {
      "epoch": 0.30666666666666664,
      "grad_norm": 0.034059129655361176,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3687191009521484,
      "step": 6440
    },
    {
      "epoch": 0.30676190476190474,
      "grad_norm": 0.029895341023802757,
      "learning_rate": 0.024000000208616257,
      "loss": 2.320673942565918,
      "step": 6442
    },
    {
      "epoch": 0.3068571428571429,
      "grad_norm": 0.029393669217824936,
      "learning_rate": 0.024000000208616257,
      "loss": 2.334285259246826,
      "step": 6444
    },
    {
      "epoch": 0.306952380952381,
      "grad_norm": 0.02984684891998768,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3269519805908203,
      "step": 6446
    },
    {
      "epoch": 0.30704761904761907,
      "grad_norm": 0.028513114899396896,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3411808013916016,
      "step": 6448
    },
    {
      "epoch": 0.30714285714285716,
      "grad_norm": 0.029769014567136765,
      "learning_rate": 0.024000000208616257,
      "loss": 2.305899143218994,
      "step": 6450
    },
    {
      "epoch": 0.30723809523809525,
      "grad_norm": 0.028367046266794205,
      "learning_rate": 0.024000000208616257,
      "loss": 2.342182159423828,
      "step": 6452
    },
    {
      "epoch": 0.30733333333333335,
      "grad_norm": 0.029349738731980324,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356308937072754,
      "step": 6454
    },
    {
      "epoch": 0.30742857142857144,
      "grad_norm": 0.02835014835000038,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3111329078674316,
      "step": 6456
    },
    {
      "epoch": 0.30752380952380953,
      "grad_norm": 0.028373422101140022,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3310675621032715,
      "step": 6458
    },
    {
      "epoch": 0.3076190476190476,
      "grad_norm": 0.03005264885723591,
      "learning_rate": 0.024000000208616257,
      "loss": 2.319322347640991,
      "step": 6460
    },
    {
      "epoch": 0.3077142857142857,
      "grad_norm": 0.028897160664200783,
      "learning_rate": 0.024000000208616257,
      "loss": 2.312281370162964,
      "step": 6462
    },
    {
      "epoch": 0.3078095238095238,
      "grad_norm": 0.02857542783021927,
      "learning_rate": 0.024000000208616257,
      "loss": 2.33115291595459,
      "step": 6464
    },
    {
      "epoch": 0.3079047619047619,
      "grad_norm": 0.029262132942676544,
      "learning_rate": 0.024000000208616257,
      "loss": 2.298640727996826,
      "step": 6466
    },
    {
      "epoch": 0.308,
      "grad_norm": 0.028896832838654518,
      "learning_rate": 0.024000000208616257,
      "loss": 2.324201822280884,
      "step": 6468
    },
    {
      "epoch": 0.3080952380952381,
      "grad_norm": 0.02913055568933487,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3362958431243896,
      "step": 6470
    },
    {
      "epoch": 0.3081904761904762,
      "grad_norm": 0.028997665271162987,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3058416843414307,
      "step": 6472
    },
    {
      "epoch": 0.3082857142857143,
      "grad_norm": 0.029276883229613304,
      "learning_rate": 0.024000000208616257,
      "loss": 2.290177822113037,
      "step": 6474
    },
    {
      "epoch": 0.30838095238095237,
      "grad_norm": 0.028262533247470856,
      "learning_rate": 0.024000000208616257,
      "loss": 2.327847957611084,
      "step": 6476
    },
    {
      "epoch": 0.30847619047619046,
      "grad_norm": 0.03180812671780586,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2909553050994873,
      "step": 6478
    },
    {
      "epoch": 0.30857142857142855,
      "grad_norm": 0.030663711950182915,
      "learning_rate": 0.024000000208616257,
      "loss": 2.313873052597046,
      "step": 6480
    },
    {
      "epoch": 0.30866666666666664,
      "grad_norm": 0.029575012624263763,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3010506629943848,
      "step": 6482
    },
    {
      "epoch": 0.30876190476190474,
      "grad_norm": 0.031017595902085304,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3361008167266846,
      "step": 6484
    },
    {
      "epoch": 0.30885714285714283,
      "grad_norm": 0.030826469883322716,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3304443359375,
      "step": 6486
    },
    {
      "epoch": 0.308952380952381,
      "grad_norm": 0.029857560992240906,
      "learning_rate": 0.024000000208616257,
      "loss": 2.343198299407959,
      "step": 6488
    },
    {
      "epoch": 0.30904761904761907,
      "grad_norm": 0.03165281191468239,
      "learning_rate": 0.024000000208616257,
      "loss": 2.323134422302246,
      "step": 6490
    },
    {
      "epoch": 0.30914285714285716,
      "grad_norm": 0.031169898808002472,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2684202194213867,
      "step": 6492
    },
    {
      "epoch": 0.30923809523809526,
      "grad_norm": 0.030998406931757927,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3110828399658203,
      "step": 6494
    },
    {
      "epoch": 0.30933333333333335,
      "grad_norm": 0.03100859746336937,
      "learning_rate": 0.024000000208616257,
      "loss": 2.317997932434082,
      "step": 6496
    },
    {
      "epoch": 0.30942857142857144,
      "grad_norm": 0.032150231301784515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2934441566467285,
      "step": 6498
    },
    {
      "epoch": 0.30952380952380953,
      "grad_norm": 0.03440959006547928,
      "learning_rate": 0.024000000208616257,
      "loss": 2.299736976623535,
      "step": 6500
    },
    {
      "epoch": 0.3096190476190476,
      "grad_norm": 0.03243481367826462,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3151302337646484,
      "step": 6502
    },
    {
      "epoch": 0.3097142857142857,
      "grad_norm": 0.030160514637827873,
      "learning_rate": 0.024000000208616257,
      "loss": 2.316957473754883,
      "step": 6504
    },
    {
      "epoch": 0.3098095238095238,
      "grad_norm": 0.029033947736024857,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3279778957366943,
      "step": 6506
    },
    {
      "epoch": 0.3099047619047619,
      "grad_norm": 0.032126832753419876,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3131799697875977,
      "step": 6508
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.029689760878682137,
      "learning_rate": 0.024000000208616257,
      "loss": 2.294799566268921,
      "step": 6510
    },
    {
      "epoch": 0.3100952380952381,
      "grad_norm": 0.030131082981824875,
      "learning_rate": 0.024000000208616257,
      "loss": 2.321272373199463,
      "step": 6512
    },
    {
      "epoch": 0.3101904761904762,
      "grad_norm": 0.029904279857873917,
      "learning_rate": 0.024000000208616257,
      "loss": 2.296316623687744,
      "step": 6514
    },
    {
      "epoch": 0.3102857142857143,
      "grad_norm": 0.029554761946201324,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3266029357910156,
      "step": 6516
    },
    {
      "epoch": 0.31038095238095237,
      "grad_norm": 0.030398434028029442,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3038394451141357,
      "step": 6518
    },
    {
      "epoch": 0.31047619047619046,
      "grad_norm": 0.03139033168554306,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3312878608703613,
      "step": 6520
    },
    {
      "epoch": 0.31057142857142855,
      "grad_norm": 0.032367806881666183,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3026113510131836,
      "step": 6522
    },
    {
      "epoch": 0.31066666666666665,
      "grad_norm": 0.028709443286061287,
      "learning_rate": 0.024000000208616257,
      "loss": 2.333828926086426,
      "step": 6524
    },
    {
      "epoch": 0.31076190476190474,
      "grad_norm": 0.028709562495350838,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3659114837646484,
      "step": 6526
    },
    {
      "epoch": 0.31085714285714283,
      "grad_norm": 0.029420573264360428,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3149476051330566,
      "step": 6528
    },
    {
      "epoch": 0.310952380952381,
      "grad_norm": 0.02859511412680149,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3383634090423584,
      "step": 6530
    },
    {
      "epoch": 0.3110476190476191,
      "grad_norm": 0.02823934704065323,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3382184505462646,
      "step": 6532
    },
    {
      "epoch": 0.31114285714285717,
      "grad_norm": 0.0287617314606905,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3064022064208984,
      "step": 6534
    },
    {
      "epoch": 0.31123809523809526,
      "grad_norm": 0.02918027900159359,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356049060821533,
      "step": 6536
    },
    {
      "epoch": 0.31133333333333335,
      "grad_norm": 0.03052075207233429,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3003015518188477,
      "step": 6538
    },
    {
      "epoch": 0.31142857142857144,
      "grad_norm": 0.02977004647254944,
      "learning_rate": 0.024000000208616257,
      "loss": 2.310786724090576,
      "step": 6540
    },
    {
      "epoch": 0.31152380952380954,
      "grad_norm": 0.028594976291060448,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3311147689819336,
      "step": 6542
    },
    {
      "epoch": 0.31161904761904763,
      "grad_norm": 0.029462821781635284,
      "learning_rate": 0.024000000208616257,
      "loss": 2.282050132751465,
      "step": 6544
    },
    {
      "epoch": 0.3117142857142857,
      "grad_norm": 0.030693713575601578,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3141465187072754,
      "step": 6546
    },
    {
      "epoch": 0.3118095238095238,
      "grad_norm": 0.029452495276927948,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3095901012420654,
      "step": 6548
    },
    {
      "epoch": 0.3119047619047619,
      "grad_norm": 0.029399117454886436,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3280012607574463,
      "step": 6550
    },
    {
      "epoch": 0.312,
      "grad_norm": 0.028573788702487946,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3171677589416504,
      "step": 6552
    },
    {
      "epoch": 0.3120952380952381,
      "grad_norm": 0.029009908437728882,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2949657440185547,
      "step": 6554
    },
    {
      "epoch": 0.3121904761904762,
      "grad_norm": 0.030307289212942123,
      "learning_rate": 0.024000000208616257,
      "loss": 2.292551040649414,
      "step": 6556
    },
    {
      "epoch": 0.3122857142857143,
      "grad_norm": 0.0292578786611557,
      "learning_rate": 0.024000000208616257,
      "loss": 2.341674327850342,
      "step": 6558
    },
    {
      "epoch": 0.31238095238095237,
      "grad_norm": 0.02938046120107174,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3232929706573486,
      "step": 6560
    },
    {
      "epoch": 0.31247619047619046,
      "grad_norm": 0.03140236437320709,
      "learning_rate": 0.024000000208616257,
      "loss": 2.331082344055176,
      "step": 6562
    },
    {
      "epoch": 0.31257142857142856,
      "grad_norm": 0.03176737204194069,
      "learning_rate": 0.024000000208616257,
      "loss": 2.300539970397949,
      "step": 6564
    },
    {
      "epoch": 0.31266666666666665,
      "grad_norm": 0.03085075505077839,
      "learning_rate": 0.024000000208616257,
      "loss": 2.306908130645752,
      "step": 6566
    },
    {
      "epoch": 0.31276190476190474,
      "grad_norm": 0.03405633568763733,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3460350036621094,
      "step": 6568
    },
    {
      "epoch": 0.31285714285714283,
      "grad_norm": 0.03649013116955757,
      "learning_rate": 0.024000000208616257,
      "loss": 2.318842887878418,
      "step": 6570
    },
    {
      "epoch": 0.3129523809523809,
      "grad_norm": 0.03427470847964287,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3351383209228516,
      "step": 6572
    },
    {
      "epoch": 0.3130476190476191,
      "grad_norm": 0.02971455082297325,
      "learning_rate": 0.024000000208616257,
      "loss": 2.311009407043457,
      "step": 6574
    },
    {
      "epoch": 0.31314285714285717,
      "grad_norm": 0.027818987146019936,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3370628356933594,
      "step": 6576
    },
    {
      "epoch": 0.31323809523809526,
      "grad_norm": 0.030287202447652817,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3272042274475098,
      "step": 6578
    },
    {
      "epoch": 0.31333333333333335,
      "grad_norm": 0.029654696583747864,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3328592777252197,
      "step": 6580
    },
    {
      "epoch": 0.31342857142857145,
      "grad_norm": 0.030140697956085205,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3344874382019043,
      "step": 6582
    },
    {
      "epoch": 0.31352380952380954,
      "grad_norm": 0.03535059466958046,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3042070865631104,
      "step": 6584
    },
    {
      "epoch": 0.31361904761904763,
      "grad_norm": 0.03976230323314667,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3257813453674316,
      "step": 6586
    },
    {
      "epoch": 0.3137142857142857,
      "grad_norm": 0.041739098727703094,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3564138412475586,
      "step": 6588
    },
    {
      "epoch": 0.3138095238095238,
      "grad_norm": 0.03081522136926651,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3330435752868652,
      "step": 6590
    },
    {
      "epoch": 0.3139047619047619,
      "grad_norm": 0.029866332188248634,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3302152156829834,
      "step": 6592
    },
    {
      "epoch": 0.314,
      "grad_norm": 0.030008263885974884,
      "learning_rate": 0.024000000208616257,
      "loss": 2.342397689819336,
      "step": 6594
    },
    {
      "epoch": 0.3140952380952381,
      "grad_norm": 0.029518095776438713,
      "learning_rate": 0.024000000208616257,
      "loss": 2.331911563873291,
      "step": 6596
    },
    {
      "epoch": 0.3141904761904762,
      "grad_norm": 0.028048476204276085,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363534927368164,
      "step": 6598
    },
    {
      "epoch": 0.3142857142857143,
      "grad_norm": 0.028625955805182457,
      "learning_rate": 0.024000000208616257,
      "loss": 2.335629940032959,
      "step": 6600
    },
    {
      "epoch": 0.31438095238095237,
      "grad_norm": 0.02924981154501438,
      "learning_rate": 0.024000000208616257,
      "loss": 2.300017833709717,
      "step": 6602
    },
    {
      "epoch": 0.31447619047619046,
      "grad_norm": 0.028616972267627716,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3265857696533203,
      "step": 6604
    },
    {
      "epoch": 0.31457142857142856,
      "grad_norm": 0.0298260860145092,
      "learning_rate": 0.024000000208616257,
      "loss": 2.324106216430664,
      "step": 6606
    },
    {
      "epoch": 0.31466666666666665,
      "grad_norm": 0.030582770705223083,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355809211730957,
      "step": 6608
    },
    {
      "epoch": 0.31476190476190474,
      "grad_norm": 0.02805759571492672,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3221237659454346,
      "step": 6610
    },
    {
      "epoch": 0.31485714285714284,
      "grad_norm": 0.02839668095111847,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3380656242370605,
      "step": 6612
    },
    {
      "epoch": 0.31495238095238093,
      "grad_norm": 0.029600270092487335,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3537635803222656,
      "step": 6614
    },
    {
      "epoch": 0.315047619047619,
      "grad_norm": 0.029355807229876518,
      "learning_rate": 0.024000000208616257,
      "loss": 2.37713623046875,
      "step": 6616
    },
    {
      "epoch": 0.31514285714285717,
      "grad_norm": 0.029095949605107307,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338749647140503,
      "step": 6618
    },
    {
      "epoch": 0.31523809523809526,
      "grad_norm": 0.02888203039765358,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2921230792999268,
      "step": 6620
    },
    {
      "epoch": 0.31533333333333335,
      "grad_norm": 0.029153017327189445,
      "learning_rate": 0.024000000208616257,
      "loss": 2.289492130279541,
      "step": 6622
    },
    {
      "epoch": 0.31542857142857145,
      "grad_norm": 0.029823293909430504,
      "learning_rate": 0.024000000208616257,
      "loss": 2.346759796142578,
      "step": 6624
    },
    {
      "epoch": 0.31552380952380954,
      "grad_norm": 0.03087831288576126,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3074631690979004,
      "step": 6626
    },
    {
      "epoch": 0.31561904761904763,
      "grad_norm": 0.030142977833747864,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3296914100646973,
      "step": 6628
    },
    {
      "epoch": 0.3157142857142857,
      "grad_norm": 0.02920375019311905,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3437232971191406,
      "step": 6630
    },
    {
      "epoch": 0.3158095238095238,
      "grad_norm": 0.031672459095716476,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3556675910949707,
      "step": 6632
    },
    {
      "epoch": 0.3159047619047619,
      "grad_norm": 0.030668728053569794,
      "learning_rate": 0.024000000208616257,
      "loss": 2.354781150817871,
      "step": 6634
    },
    {
      "epoch": 0.316,
      "grad_norm": 0.029729878529906273,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3499631881713867,
      "step": 6636
    },
    {
      "epoch": 0.3160952380952381,
      "grad_norm": 0.02825327217578888,
      "learning_rate": 0.024000000208616257,
      "loss": 2.359105110168457,
      "step": 6638
    },
    {
      "epoch": 0.3161904761904762,
      "grad_norm": 0.03172089532017708,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3593931198120117,
      "step": 6640
    },
    {
      "epoch": 0.3162857142857143,
      "grad_norm": 0.030128180980682373,
      "learning_rate": 0.024000000208616257,
      "loss": 2.337581157684326,
      "step": 6642
    },
    {
      "epoch": 0.3163809523809524,
      "grad_norm": 0.030262082815170288,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3297014236450195,
      "step": 6644
    },
    {
      "epoch": 0.31647619047619047,
      "grad_norm": 0.03131818771362305,
      "learning_rate": 0.024000000208616257,
      "loss": 2.375129461288452,
      "step": 6646
    },
    {
      "epoch": 0.31657142857142856,
      "grad_norm": 0.03253898397088051,
      "learning_rate": 0.024000000208616257,
      "loss": 2.35223388671875,
      "step": 6648
    },
    {
      "epoch": 0.31666666666666665,
      "grad_norm": 0.03146529942750931,
      "learning_rate": 0.024000000208616257,
      "loss": 2.344130039215088,
      "step": 6650
    },
    {
      "epoch": 0.31676190476190474,
      "grad_norm": 0.030744455754756927,
      "learning_rate": 0.024000000208616257,
      "loss": 2.342435836791992,
      "step": 6652
    },
    {
      "epoch": 0.31685714285714284,
      "grad_norm": 0.030047748237848282,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3624284267425537,
      "step": 6654
    },
    {
      "epoch": 0.31695238095238093,
      "grad_norm": 0.028113337233662605,
      "learning_rate": 0.024000000208616257,
      "loss": 2.347626209259033,
      "step": 6656
    },
    {
      "epoch": 0.317047619047619,
      "grad_norm": 0.029134491458535194,
      "learning_rate": 0.024000000208616257,
      "loss": 2.335148334503174,
      "step": 6658
    },
    {
      "epoch": 0.3171428571428571,
      "grad_norm": 0.029101917520165443,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3474507331848145,
      "step": 6660
    },
    {
      "epoch": 0.31723809523809526,
      "grad_norm": 0.03106527216732502,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3615317344665527,
      "step": 6662
    },
    {
      "epoch": 0.31733333333333336,
      "grad_norm": 0.028606345877051353,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3369333744049072,
      "step": 6664
    },
    {
      "epoch": 0.31742857142857145,
      "grad_norm": 0.029963959008455276,
      "learning_rate": 0.024000000208616257,
      "loss": 2.360109329223633,
      "step": 6666
    },
    {
      "epoch": 0.31752380952380954,
      "grad_norm": 0.029881037771701813,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3249053955078125,
      "step": 6668
    },
    {
      "epoch": 0.31761904761904763,
      "grad_norm": 0.029798684641718864,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3431034088134766,
      "step": 6670
    },
    {
      "epoch": 0.3177142857142857,
      "grad_norm": 0.030057916417717934,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3436026573181152,
      "step": 6672
    },
    {
      "epoch": 0.3178095238095238,
      "grad_norm": 0.029155798256397247,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3344974517822266,
      "step": 6674
    },
    {
      "epoch": 0.3179047619047619,
      "grad_norm": 0.028540829196572304,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3181653022766113,
      "step": 6676
    },
    {
      "epoch": 0.318,
      "grad_norm": 0.02922496199607849,
      "learning_rate": 0.024000000208616257,
      "loss": 2.33772611618042,
      "step": 6678
    },
    {
      "epoch": 0.3180952380952381,
      "grad_norm": 0.028826560825109482,
      "learning_rate": 0.024000000208616257,
      "loss": 2.361253023147583,
      "step": 6680
    },
    {
      "epoch": 0.3181904761904762,
      "grad_norm": 0.02881036326289177,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3275647163391113,
      "step": 6682
    },
    {
      "epoch": 0.3182857142857143,
      "grad_norm": 0.030000587925314903,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345825672149658,
      "step": 6684
    },
    {
      "epoch": 0.3183809523809524,
      "grad_norm": 0.031596262007951736,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3597512245178223,
      "step": 6686
    },
    {
      "epoch": 0.31847619047619047,
      "grad_norm": 0.028911059722304344,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3646888732910156,
      "step": 6688
    },
    {
      "epoch": 0.31857142857142856,
      "grad_norm": 0.02899034135043621,
      "learning_rate": 0.024000000208616257,
      "loss": 2.35548734664917,
      "step": 6690
    },
    {
      "epoch": 0.31866666666666665,
      "grad_norm": 0.028659792616963387,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355567455291748,
      "step": 6692
    },
    {
      "epoch": 0.31876190476190475,
      "grad_norm": 0.031580351293087006,
      "learning_rate": 0.024000000208616257,
      "loss": 2.36421275138855,
      "step": 6694
    },
    {
      "epoch": 0.31885714285714284,
      "grad_norm": 0.029118487611413002,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3590779304504395,
      "step": 6696
    },
    {
      "epoch": 0.31895238095238093,
      "grad_norm": 0.02990548126399517,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3388471603393555,
      "step": 6698
    },
    {
      "epoch": 0.319047619047619,
      "grad_norm": 0.029720649123191833,
      "learning_rate": 0.024000000208616257,
      "loss": 2.339114189147949,
      "step": 6700
    },
    {
      "epoch": 0.3191428571428571,
      "grad_norm": 0.0306615699082613,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3610129356384277,
      "step": 6702
    },
    {
      "epoch": 0.31923809523809527,
      "grad_norm": 0.032338354736566544,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350888729095459,
      "step": 6704
    },
    {
      "epoch": 0.31933333333333336,
      "grad_norm": 0.03412037342786789,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3385887145996094,
      "step": 6706
    },
    {
      "epoch": 0.31942857142857145,
      "grad_norm": 0.03057759255170822,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3421730995178223,
      "step": 6708
    },
    {
      "epoch": 0.31952380952380954,
      "grad_norm": 0.030888650566339493,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3476104736328125,
      "step": 6710
    },
    {
      "epoch": 0.31961904761904764,
      "grad_norm": 0.028536031022667885,
      "learning_rate": 0.024000000208616257,
      "loss": 2.364065170288086,
      "step": 6712
    },
    {
      "epoch": 0.31971428571428573,
      "grad_norm": 0.029843401163816452,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3941855430603027,
      "step": 6714
    },
    {
      "epoch": 0.3198095238095238,
      "grad_norm": 0.029957100749015808,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3491902351379395,
      "step": 6716
    },
    {
      "epoch": 0.3199047619047619,
      "grad_norm": 0.029425516724586487,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3537135124206543,
      "step": 6718
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.02858414128422737,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3724772930145264,
      "step": 6720
    },
    {
      "epoch": 0.3200952380952381,
      "grad_norm": 0.03299523890018463,
      "learning_rate": 0.024000000208616257,
      "loss": 2.360440969467163,
      "step": 6722
    },
    {
      "epoch": 0.3201904761904762,
      "grad_norm": 0.028430329635739326,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3424034118652344,
      "step": 6724
    },
    {
      "epoch": 0.3202857142857143,
      "grad_norm": 0.02861458621919155,
      "learning_rate": 0.024000000208616257,
      "loss": 2.34429669380188,
      "step": 6726
    },
    {
      "epoch": 0.3203809523809524,
      "grad_norm": 0.029941774904727936,
      "learning_rate": 0.024000000208616257,
      "loss": 2.341630458831787,
      "step": 6728
    },
    {
      "epoch": 0.32047619047619047,
      "grad_norm": 0.028318598866462708,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4075822830200195,
      "step": 6730
    },
    {
      "epoch": 0.32057142857142856,
      "grad_norm": 0.029113972559571266,
      "learning_rate": 0.024000000208616257,
      "loss": 2.358125686645508,
      "step": 6732
    },
    {
      "epoch": 0.32066666666666666,
      "grad_norm": 0.030636440962553024,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3770601749420166,
      "step": 6734
    },
    {
      "epoch": 0.32076190476190475,
      "grad_norm": 0.028409449383616447,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4204659461975098,
      "step": 6736
    },
    {
      "epoch": 0.32085714285714284,
      "grad_norm": 0.030893204733729362,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3892459869384766,
      "step": 6738
    },
    {
      "epoch": 0.32095238095238093,
      "grad_norm": 0.02968692034482956,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355163097381592,
      "step": 6740
    },
    {
      "epoch": 0.321047619047619,
      "grad_norm": 0.028388556092977524,
      "learning_rate": 0.024000000208616257,
      "loss": 2.372467517852783,
      "step": 6742
    },
    {
      "epoch": 0.3211428571428571,
      "grad_norm": 0.030175594612956047,
      "learning_rate": 0.024000000208616257,
      "loss": 2.407804489135742,
      "step": 6744
    },
    {
      "epoch": 0.3212380952380952,
      "grad_norm": 0.029180334880948067,
      "learning_rate": 0.024000000208616257,
      "loss": 2.361778497695923,
      "step": 6746
    },
    {
      "epoch": 0.32133333333333336,
      "grad_norm": 0.031550295650959015,
      "learning_rate": 0.024000000208616257,
      "loss": 2.374695301055908,
      "step": 6748
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 0.035255640745162964,
      "learning_rate": 0.024000000208616257,
      "loss": 2.335714340209961,
      "step": 6750
    },
    {
      "epoch": 0.32152380952380955,
      "grad_norm": 0.029872020706534386,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3993616104125977,
      "step": 6752
    },
    {
      "epoch": 0.32161904761904764,
      "grad_norm": 0.0291373860090971,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3874149322509766,
      "step": 6754
    },
    {
      "epoch": 0.32171428571428573,
      "grad_norm": 0.030344711616635323,
      "learning_rate": 0.024000000208616257,
      "loss": 2.365351676940918,
      "step": 6756
    },
    {
      "epoch": 0.3218095238095238,
      "grad_norm": 0.029092896729707718,
      "learning_rate": 0.024000000208616257,
      "loss": 2.361419677734375,
      "step": 6758
    },
    {
      "epoch": 0.3219047619047619,
      "grad_norm": 0.028762144967913628,
      "learning_rate": 0.024000000208616257,
      "loss": 2.394111156463623,
      "step": 6760
    },
    {
      "epoch": 0.322,
      "grad_norm": 0.028395377099514008,
      "learning_rate": 0.024000000208616257,
      "loss": 2.403046131134033,
      "step": 6762
    },
    {
      "epoch": 0.3220952380952381,
      "grad_norm": 0.0339694507420063,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3714747428894043,
      "step": 6764
    },
    {
      "epoch": 0.3221904761904762,
      "grad_norm": 0.03127436339855194,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382192611694336,
      "step": 6766
    },
    {
      "epoch": 0.3222857142857143,
      "grad_norm": 0.02861054800450802,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382972240447998,
      "step": 6768
    },
    {
      "epoch": 0.3223809523809524,
      "grad_norm": 0.029353581368923187,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38801908493042,
      "step": 6770
    },
    {
      "epoch": 0.32247619047619047,
      "grad_norm": 0.0296561811119318,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3707282543182373,
      "step": 6772
    },
    {
      "epoch": 0.32257142857142856,
      "grad_norm": 0.02969769947230816,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384158134460449,
      "step": 6774
    },
    {
      "epoch": 0.32266666666666666,
      "grad_norm": 0.03448229283094406,
      "learning_rate": 0.024000000208616257,
      "loss": 2.366119861602783,
      "step": 6776
    },
    {
      "epoch": 0.32276190476190475,
      "grad_norm": 0.029626045376062393,
      "learning_rate": 0.024000000208616257,
      "loss": 2.394411563873291,
      "step": 6778
    },
    {
      "epoch": 0.32285714285714284,
      "grad_norm": 0.030190495774149895,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4092397689819336,
      "step": 6780
    },
    {
      "epoch": 0.32295238095238094,
      "grad_norm": 0.028880007565021515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38751482963562,
      "step": 6782
    },
    {
      "epoch": 0.32304761904761903,
      "grad_norm": 0.029009686782956123,
      "learning_rate": 0.024000000208616257,
      "loss": 2.403639793395996,
      "step": 6784
    },
    {
      "epoch": 0.3231428571428571,
      "grad_norm": 0.029632573947310448,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3590686321258545,
      "step": 6786
    },
    {
      "epoch": 0.3232380952380952,
      "grad_norm": 0.029860898852348328,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380467414855957,
      "step": 6788
    },
    {
      "epoch": 0.3233333333333333,
      "grad_norm": 0.030146099627017975,
      "learning_rate": 0.024000000208616257,
      "loss": 2.370199203491211,
      "step": 6790
    },
    {
      "epoch": 0.32342857142857145,
      "grad_norm": 0.030649010092020035,
      "learning_rate": 0.024000000208616257,
      "loss": 2.372230052947998,
      "step": 6792
    },
    {
      "epoch": 0.32352380952380955,
      "grad_norm": 0.03249740228056908,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3918845653533936,
      "step": 6794
    },
    {
      "epoch": 0.32361904761904764,
      "grad_norm": 0.034145697951316833,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3606655597686768,
      "step": 6796
    },
    {
      "epoch": 0.32371428571428573,
      "grad_norm": 0.03330729156732559,
      "learning_rate": 0.024000000208616257,
      "loss": 2.342175006866455,
      "step": 6798
    },
    {
      "epoch": 0.3238095238095238,
      "grad_norm": 0.03220066800713539,
      "learning_rate": 0.024000000208616257,
      "loss": 2.391664981842041,
      "step": 6800
    },
    {
      "epoch": 0.3239047619047619,
      "grad_norm": 0.029995650053024292,
      "learning_rate": 0.024000000208616257,
      "loss": 2.36269474029541,
      "step": 6802
    },
    {
      "epoch": 0.324,
      "grad_norm": 0.03163720667362213,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380225658416748,
      "step": 6804
    },
    {
      "epoch": 0.3240952380952381,
      "grad_norm": 0.030561575666069984,
      "learning_rate": 0.024000000208616257,
      "loss": 2.391545534133911,
      "step": 6806
    },
    {
      "epoch": 0.3241904761904762,
      "grad_norm": 0.03141254931688309,
      "learning_rate": 0.024000000208616257,
      "loss": 2.357654094696045,
      "step": 6808
    },
    {
      "epoch": 0.3242857142857143,
      "grad_norm": 0.02883581444621086,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3747992515563965,
      "step": 6810
    },
    {
      "epoch": 0.3243809523809524,
      "grad_norm": 0.039441872388124466,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3972387313842773,
      "step": 6812
    },
    {
      "epoch": 0.3244761904761905,
      "grad_norm": 0.032467689365148544,
      "learning_rate": 0.024000000208616257,
      "loss": 2.339588165283203,
      "step": 6814
    },
    {
      "epoch": 0.32457142857142857,
      "grad_norm": 0.03031005524098873,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3729465007781982,
      "step": 6816
    },
    {
      "epoch": 0.32466666666666666,
      "grad_norm": 0.02971688285470009,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383436679840088,
      "step": 6818
    },
    {
      "epoch": 0.32476190476190475,
      "grad_norm": 0.02917535975575447,
      "learning_rate": 0.024000000208616257,
      "loss": 2.361727714538574,
      "step": 6820
    },
    {
      "epoch": 0.32485714285714284,
      "grad_norm": 0.029190370813012123,
      "learning_rate": 0.024000000208616257,
      "loss": 2.360609292984009,
      "step": 6822
    },
    {
      "epoch": 0.32495238095238094,
      "grad_norm": 0.029350455850362778,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3561253547668457,
      "step": 6824
    },
    {
      "epoch": 0.32504761904761903,
      "grad_norm": 0.028233183547854424,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338207244873047,
      "step": 6826
    },
    {
      "epoch": 0.3251428571428571,
      "grad_norm": 0.028721828013658524,
      "learning_rate": 0.024000000208616257,
      "loss": 2.373077392578125,
      "step": 6828
    },
    {
      "epoch": 0.3252380952380952,
      "grad_norm": 0.03025970421731472,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3636488914489746,
      "step": 6830
    },
    {
      "epoch": 0.3253333333333333,
      "grad_norm": 0.02994028851389885,
      "learning_rate": 0.024000000208616257,
      "loss": 2.357119083404541,
      "step": 6832
    },
    {
      "epoch": 0.32542857142857146,
      "grad_norm": 0.030633581802248955,
      "learning_rate": 0.024000000208616257,
      "loss": 2.326077461242676,
      "step": 6834
    },
    {
      "epoch": 0.32552380952380955,
      "grad_norm": 0.0305038932710886,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3835806846618652,
      "step": 6836
    },
    {
      "epoch": 0.32561904761904764,
      "grad_norm": 0.029431983828544617,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3587985038757324,
      "step": 6838
    },
    {
      "epoch": 0.32571428571428573,
      "grad_norm": 0.03369675576686859,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3676254749298096,
      "step": 6840
    },
    {
      "epoch": 0.3258095238095238,
      "grad_norm": 0.031320299953222275,
      "learning_rate": 0.024000000208616257,
      "loss": 2.379446029663086,
      "step": 6842
    },
    {
      "epoch": 0.3259047619047619,
      "grad_norm": 0.03001028299331665,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3561086654663086,
      "step": 6844
    },
    {
      "epoch": 0.326,
      "grad_norm": 0.030707336962223053,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3800477981567383,
      "step": 6846
    },
    {
      "epoch": 0.3260952380952381,
      "grad_norm": 0.03069991059601307,
      "learning_rate": 0.024000000208616257,
      "loss": 2.379668712615967,
      "step": 6848
    },
    {
      "epoch": 0.3261904761904762,
      "grad_norm": 0.030798401683568954,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3752713203430176,
      "step": 6850
    },
    {
      "epoch": 0.3262857142857143,
      "grad_norm": 0.03111075609922409,
      "learning_rate": 0.024000000208616257,
      "loss": 2.381896495819092,
      "step": 6852
    },
    {
      "epoch": 0.3263809523809524,
      "grad_norm": 0.029117895290255547,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3652634620666504,
      "step": 6854
    },
    {
      "epoch": 0.3264761904761905,
      "grad_norm": 0.030826520174741745,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3466575145721436,
      "step": 6856
    },
    {
      "epoch": 0.32657142857142857,
      "grad_norm": 0.03189202770590782,
      "learning_rate": 0.024000000208616257,
      "loss": 2.360050678253174,
      "step": 6858
    },
    {
      "epoch": 0.32666666666666666,
      "grad_norm": 0.03183364495635033,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3649508953094482,
      "step": 6860
    },
    {
      "epoch": 0.32676190476190475,
      "grad_norm": 0.0303238183259964,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4177331924438477,
      "step": 6862
    },
    {
      "epoch": 0.32685714285714285,
      "grad_norm": 0.029735160991549492,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3377346992492676,
      "step": 6864
    },
    {
      "epoch": 0.32695238095238094,
      "grad_norm": 0.029342984780669212,
      "learning_rate": 0.024000000208616257,
      "loss": 2.368034839630127,
      "step": 6866
    },
    {
      "epoch": 0.32704761904761903,
      "grad_norm": 0.030503233894705772,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3845431804656982,
      "step": 6868
    },
    {
      "epoch": 0.3271428571428571,
      "grad_norm": 0.030803989619016647,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350325107574463,
      "step": 6870
    },
    {
      "epoch": 0.3272380952380952,
      "grad_norm": 0.028206681832671165,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3423924446105957,
      "step": 6872
    },
    {
      "epoch": 0.3273333333333333,
      "grad_norm": 0.028482219204306602,
      "learning_rate": 0.024000000208616257,
      "loss": 2.367105722427368,
      "step": 6874
    },
    {
      "epoch": 0.3274285714285714,
      "grad_norm": 0.02842320315539837,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380890369415283,
      "step": 6876
    },
    {
      "epoch": 0.32752380952380955,
      "grad_norm": 0.030156293883919716,
      "learning_rate": 0.024000000208616257,
      "loss": 2.362187385559082,
      "step": 6878
    },
    {
      "epoch": 0.32761904761904764,
      "grad_norm": 0.029826704412698746,
      "learning_rate": 0.024000000208616257,
      "loss": 2.373478412628174,
      "step": 6880
    },
    {
      "epoch": 0.32771428571428574,
      "grad_norm": 0.0359187014400959,
      "learning_rate": 0.024000000208616257,
      "loss": 2.366511821746826,
      "step": 6882
    },
    {
      "epoch": 0.32780952380952383,
      "grad_norm": 0.03139779716730118,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4161458015441895,
      "step": 6884
    },
    {
      "epoch": 0.3279047619047619,
      "grad_norm": 0.033382683992385864,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390726089477539,
      "step": 6886
    },
    {
      "epoch": 0.328,
      "grad_norm": 0.031857602298259735,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3766746520996094,
      "step": 6888
    },
    {
      "epoch": 0.3280952380952381,
      "grad_norm": 0.03072267398238182,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3787970542907715,
      "step": 6890
    },
    {
      "epoch": 0.3281904761904762,
      "grad_norm": 0.028397629037499428,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4100608825683594,
      "step": 6892
    },
    {
      "epoch": 0.3282857142857143,
      "grad_norm": 0.02880684658885002,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3839926719665527,
      "step": 6894
    },
    {
      "epoch": 0.3283809523809524,
      "grad_norm": 0.029076935723423958,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3692197799682617,
      "step": 6896
    },
    {
      "epoch": 0.3284761904761905,
      "grad_norm": 0.029319530352950096,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398632526397705,
      "step": 6898
    },
    {
      "epoch": 0.32857142857142857,
      "grad_norm": 0.029993785545229912,
      "learning_rate": 0.024000000208616257,
      "loss": 2.388760566711426,
      "step": 6900
    },
    {
      "epoch": 0.32866666666666666,
      "grad_norm": 0.029682567343115807,
      "learning_rate": 0.024000000208616257,
      "loss": 2.340564489364624,
      "step": 6902
    },
    {
      "epoch": 0.32876190476190476,
      "grad_norm": 0.031599901616573334,
      "learning_rate": 0.024000000208616257,
      "loss": 2.330897808074951,
      "step": 6904
    },
    {
      "epoch": 0.32885714285714285,
      "grad_norm": 0.030086439102888107,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3525290489196777,
      "step": 6906
    },
    {
      "epoch": 0.32895238095238094,
      "grad_norm": 0.029382184147834778,
      "learning_rate": 0.024000000208616257,
      "loss": 2.393484354019165,
      "step": 6908
    },
    {
      "epoch": 0.32904761904761903,
      "grad_norm": 0.028108954429626465,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3695590496063232,
      "step": 6910
    },
    {
      "epoch": 0.3291428571428571,
      "grad_norm": 0.02977841906249523,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4104251861572266,
      "step": 6912
    },
    {
      "epoch": 0.3292380952380952,
      "grad_norm": 0.02960912510752678,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3727331161499023,
      "step": 6914
    },
    {
      "epoch": 0.3293333333333333,
      "grad_norm": 0.02889445051550865,
      "learning_rate": 0.024000000208616257,
      "loss": 2.386174201965332,
      "step": 6916
    },
    {
      "epoch": 0.3294285714285714,
      "grad_norm": 0.030402930453419685,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3924994468688965,
      "step": 6918
    },
    {
      "epoch": 0.3295238095238095,
      "grad_norm": 0.028691446408629417,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3647494316101074,
      "step": 6920
    },
    {
      "epoch": 0.32961904761904764,
      "grad_norm": 0.03016674518585205,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363886833190918,
      "step": 6922
    },
    {
      "epoch": 0.32971428571428574,
      "grad_norm": 0.03133035823702812,
      "learning_rate": 0.024000000208616257,
      "loss": 2.410017967224121,
      "step": 6924
    },
    {
      "epoch": 0.32980952380952383,
      "grad_norm": 0.029157087206840515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.403724193572998,
      "step": 6926
    },
    {
      "epoch": 0.3299047619047619,
      "grad_norm": 0.02887115441262722,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390021324157715,
      "step": 6928
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.02816702052950859,
      "learning_rate": 0.024000000208616257,
      "loss": 2.40718936920166,
      "step": 6930
    },
    {
      "epoch": 0.3300952380952381,
      "grad_norm": 0.029356172308325768,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3882508277893066,
      "step": 6932
    },
    {
      "epoch": 0.3301904761904762,
      "grad_norm": 0.03039124235510826,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4030556678771973,
      "step": 6934
    },
    {
      "epoch": 0.3302857142857143,
      "grad_norm": 0.03127926215529442,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4271087646484375,
      "step": 6936
    },
    {
      "epoch": 0.3303809523809524,
      "grad_norm": 0.03440895676612854,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3990509510040283,
      "step": 6938
    },
    {
      "epoch": 0.3304761904761905,
      "grad_norm": 0.030441921204328537,
      "learning_rate": 0.024000000208616257,
      "loss": 2.417489528656006,
      "step": 6940
    },
    {
      "epoch": 0.33057142857142857,
      "grad_norm": 0.029313666746020317,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3929853439331055,
      "step": 6942
    },
    {
      "epoch": 0.33066666666666666,
      "grad_norm": 0.02986820414662361,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4304940700531006,
      "step": 6944
    },
    {
      "epoch": 0.33076190476190476,
      "grad_norm": 0.029990557581186295,
      "learning_rate": 0.024000000208616257,
      "loss": 2.411107063293457,
      "step": 6946
    },
    {
      "epoch": 0.33085714285714285,
      "grad_norm": 0.034136075526475906,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383619546890259,
      "step": 6948
    },
    {
      "epoch": 0.33095238095238094,
      "grad_norm": 0.02885344997048378,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3991527557373047,
      "step": 6950
    },
    {
      "epoch": 0.33104761904761904,
      "grad_norm": 0.02897188812494278,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3875036239624023,
      "step": 6952
    },
    {
      "epoch": 0.3311428571428571,
      "grad_norm": 0.029557017609477043,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3957831859588623,
      "step": 6954
    },
    {
      "epoch": 0.3312380952380952,
      "grad_norm": 0.029947176575660706,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390134811401367,
      "step": 6956
    },
    {
      "epoch": 0.3313333333333333,
      "grad_norm": 0.02990059182047844,
      "learning_rate": 0.024000000208616257,
      "loss": 2.381887912750244,
      "step": 6958
    },
    {
      "epoch": 0.3314285714285714,
      "grad_norm": 0.02921842411160469,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4007344245910645,
      "step": 6960
    },
    {
      "epoch": 0.3315238095238095,
      "grad_norm": 0.028914738446474075,
      "learning_rate": 0.024000000208616257,
      "loss": 2.40413236618042,
      "step": 6962
    },
    {
      "epoch": 0.33161904761904765,
      "grad_norm": 0.029783714562654495,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4362387657165527,
      "step": 6964
    },
    {
      "epoch": 0.33171428571428574,
      "grad_norm": 0.02916163206100464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4320926666259766,
      "step": 6966
    },
    {
      "epoch": 0.33180952380952383,
      "grad_norm": 0.029726408421993256,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4382853507995605,
      "step": 6968
    },
    {
      "epoch": 0.3319047619047619,
      "grad_norm": 0.029048137366771698,
      "learning_rate": 0.024000000208616257,
      "loss": 2.393087863922119,
      "step": 6970
    },
    {
      "epoch": 0.332,
      "grad_norm": 0.028565706685185432,
      "learning_rate": 0.024000000208616257,
      "loss": 2.452376365661621,
      "step": 6972
    },
    {
      "epoch": 0.3320952380952381,
      "grad_norm": 0.02989874966442585,
      "learning_rate": 0.024000000208616257,
      "loss": 2.438532829284668,
      "step": 6974
    },
    {
      "epoch": 0.3321904761904762,
      "grad_norm": 0.02967716194689274,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3955397605895996,
      "step": 6976
    },
    {
      "epoch": 0.3322857142857143,
      "grad_norm": 0.029272885993123055,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4064364433288574,
      "step": 6978
    },
    {
      "epoch": 0.3323809523809524,
      "grad_norm": 0.028716832399368286,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4012181758880615,
      "step": 6980
    },
    {
      "epoch": 0.3324761904761905,
      "grad_norm": 0.029680602252483368,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4292726516723633,
      "step": 6982
    },
    {
      "epoch": 0.3325714285714286,
      "grad_norm": 0.028991740196943283,
      "learning_rate": 0.024000000208616257,
      "loss": 2.421337604522705,
      "step": 6984
    },
    {
      "epoch": 0.33266666666666667,
      "grad_norm": 0.02994304709136486,
      "learning_rate": 0.024000000208616257,
      "loss": 2.420278549194336,
      "step": 6986
    },
    {
      "epoch": 0.33276190476190476,
      "grad_norm": 0.02911573089659214,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4111337661743164,
      "step": 6988
    },
    {
      "epoch": 0.33285714285714285,
      "grad_norm": 0.027842700481414795,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4446821212768555,
      "step": 6990
    },
    {
      "epoch": 0.33295238095238094,
      "grad_norm": 0.028856541961431503,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4105172157287598,
      "step": 6992
    },
    {
      "epoch": 0.33304761904761904,
      "grad_norm": 0.029169991612434387,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4082086086273193,
      "step": 6994
    },
    {
      "epoch": 0.33314285714285713,
      "grad_norm": 0.02955012582242489,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4080920219421387,
      "step": 6996
    },
    {
      "epoch": 0.3332380952380952,
      "grad_norm": 0.030604831874370575,
      "learning_rate": 0.024000000208616257,
      "loss": 2.424211025238037,
      "step": 6998
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.03272611275315285,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4005627632141113,
      "step": 7000
    },
    {
      "epoch": 0.3334285714285714,
      "grad_norm": 0.03470318764448166,
      "learning_rate": 0.024000000208616257,
      "loss": 2.431544303894043,
      "step": 7002
    },
    {
      "epoch": 0.3335238095238095,
      "grad_norm": 0.034915074706077576,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4524762630462646,
      "step": 7004
    },
    {
      "epoch": 0.3336190476190476,
      "grad_norm": 0.028626343235373497,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4053690433502197,
      "step": 7006
    },
    {
      "epoch": 0.33371428571428574,
      "grad_norm": 0.030348224565386772,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4384469985961914,
      "step": 7008
    },
    {
      "epoch": 0.33380952380952383,
      "grad_norm": 0.03393451124429703,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4207677841186523,
      "step": 7010
    },
    {
      "epoch": 0.3339047619047619,
      "grad_norm": 0.028987819328904152,
      "learning_rate": 0.024000000208616257,
      "loss": 2.446026086807251,
      "step": 7012
    },
    {
      "epoch": 0.334,
      "grad_norm": 0.029999880120158195,
      "learning_rate": 0.024000000208616257,
      "loss": 2.424818754196167,
      "step": 7014
    },
    {
      "epoch": 0.3340952380952381,
      "grad_norm": 0.029403716325759888,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4614667892456055,
      "step": 7016
    },
    {
      "epoch": 0.3341904761904762,
      "grad_norm": 0.030864877626299858,
      "learning_rate": 0.024000000208616257,
      "loss": 2.408066749572754,
      "step": 7018
    },
    {
      "epoch": 0.3342857142857143,
      "grad_norm": 0.028570184484124184,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4517722129821777,
      "step": 7020
    },
    {
      "epoch": 0.3343809523809524,
      "grad_norm": 0.02860090136528015,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3968334197998047,
      "step": 7022
    },
    {
      "epoch": 0.3344761904761905,
      "grad_norm": 0.029398715123534203,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4032046794891357,
      "step": 7024
    },
    {
      "epoch": 0.3345714285714286,
      "grad_norm": 0.02817380800843239,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4293770790100098,
      "step": 7026
    },
    {
      "epoch": 0.33466666666666667,
      "grad_norm": 0.02911488339304924,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4307146072387695,
      "step": 7028
    },
    {
      "epoch": 0.33476190476190476,
      "grad_norm": 0.027685437351465225,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4240169525146484,
      "step": 7030
    },
    {
      "epoch": 0.33485714285714285,
      "grad_norm": 0.028887353837490082,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4378843307495117,
      "step": 7032
    },
    {
      "epoch": 0.33495238095238095,
      "grad_norm": 0.02963896654546261,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4065303802490234,
      "step": 7034
    },
    {
      "epoch": 0.33504761904761904,
      "grad_norm": 0.03217792883515358,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4400086402893066,
      "step": 7036
    },
    {
      "epoch": 0.33514285714285713,
      "grad_norm": 0.030193371698260307,
      "learning_rate": 0.024000000208616257,
      "loss": 2.421281337738037,
      "step": 7038
    },
    {
      "epoch": 0.3352380952380952,
      "grad_norm": 0.02918841689825058,
      "learning_rate": 0.024000000208616257,
      "loss": 2.459702491760254,
      "step": 7040
    },
    {
      "epoch": 0.3353333333333333,
      "grad_norm": 0.028700634837150574,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4330642223358154,
      "step": 7042
    },
    {
      "epoch": 0.3354285714285714,
      "grad_norm": 0.028685132041573524,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4279274940490723,
      "step": 7044
    },
    {
      "epoch": 0.3355238095238095,
      "grad_norm": 0.029339410364627838,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4440269470214844,
      "step": 7046
    },
    {
      "epoch": 0.3356190476190476,
      "grad_norm": 0.029520118609070778,
      "learning_rate": 0.024000000208616257,
      "loss": 2.418275833129883,
      "step": 7048
    },
    {
      "epoch": 0.3357142857142857,
      "grad_norm": 0.030472509562969208,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4447946548461914,
      "step": 7050
    },
    {
      "epoch": 0.33580952380952384,
      "grad_norm": 0.02895457297563553,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4198036193847656,
      "step": 7052
    },
    {
      "epoch": 0.33590476190476193,
      "grad_norm": 0.029851580038666725,
      "learning_rate": 0.024000000208616257,
      "loss": 2.462186813354492,
      "step": 7054
    },
    {
      "epoch": 0.336,
      "grad_norm": 0.028468342497944832,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4431376457214355,
      "step": 7056
    },
    {
      "epoch": 0.3360952380952381,
      "grad_norm": 0.028307003900408745,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4455180168151855,
      "step": 7058
    },
    {
      "epoch": 0.3361904761904762,
      "grad_norm": 0.029147827997803688,
      "learning_rate": 0.024000000208616257,
      "loss": 2.437354564666748,
      "step": 7060
    },
    {
      "epoch": 0.3362857142857143,
      "grad_norm": 0.028990380465984344,
      "learning_rate": 0.024000000208616257,
      "loss": 2.433863878250122,
      "step": 7062
    },
    {
      "epoch": 0.3363809523809524,
      "grad_norm": 0.02805459499359131,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4258453845977783,
      "step": 7064
    },
    {
      "epoch": 0.3364761904761905,
      "grad_norm": 0.02866201661527157,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4297640323638916,
      "step": 7066
    },
    {
      "epoch": 0.3365714285714286,
      "grad_norm": 0.02888469584286213,
      "learning_rate": 0.024000000208616257,
      "loss": 2.422247886657715,
      "step": 7068
    },
    {
      "epoch": 0.33666666666666667,
      "grad_norm": 0.02833429165184498,
      "learning_rate": 0.024000000208616257,
      "loss": 2.473562479019165,
      "step": 7070
    },
    {
      "epoch": 0.33676190476190476,
      "grad_norm": 0.028570959344506264,
      "learning_rate": 0.024000000208616257,
      "loss": 2.482819080352783,
      "step": 7072
    },
    {
      "epoch": 0.33685714285714285,
      "grad_norm": 0.030939733609557152,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4534223079681396,
      "step": 7074
    },
    {
      "epoch": 0.33695238095238095,
      "grad_norm": 0.03351357951760292,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4560351371765137,
      "step": 7076
    },
    {
      "epoch": 0.33704761904761904,
      "grad_norm": 0.03135859966278076,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4564695358276367,
      "step": 7078
    },
    {
      "epoch": 0.33714285714285713,
      "grad_norm": 0.028630919754505157,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4311838150024414,
      "step": 7080
    },
    {
      "epoch": 0.3372380952380952,
      "grad_norm": 0.029535846784710884,
      "learning_rate": 0.024000000208616257,
      "loss": 2.486880302429199,
      "step": 7082
    },
    {
      "epoch": 0.3373333333333333,
      "grad_norm": 0.029725566506385803,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4400253295898438,
      "step": 7084
    },
    {
      "epoch": 0.3374285714285714,
      "grad_norm": 0.031099854037165642,
      "learning_rate": 0.024000000208616257,
      "loss": 2.471480131149292,
      "step": 7086
    },
    {
      "epoch": 0.3375238095238095,
      "grad_norm": 0.028955642133951187,
      "learning_rate": 0.024000000208616257,
      "loss": 2.452303647994995,
      "step": 7088
    },
    {
      "epoch": 0.3376190476190476,
      "grad_norm": 0.0295866746455431,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4470043182373047,
      "step": 7090
    },
    {
      "epoch": 0.3377142857142857,
      "grad_norm": 0.028985003009438515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4337213039398193,
      "step": 7092
    },
    {
      "epoch": 0.3378095238095238,
      "grad_norm": 0.029296183958649635,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4490256309509277,
      "step": 7094
    },
    {
      "epoch": 0.33790476190476193,
      "grad_norm": 0.029807470738887787,
      "learning_rate": 0.024000000208616257,
      "loss": 2.463074207305908,
      "step": 7096
    },
    {
      "epoch": 0.338,
      "grad_norm": 0.03494802117347717,
      "learning_rate": 0.024000000208616257,
      "loss": 2.464341163635254,
      "step": 7098
    },
    {
      "epoch": 0.3380952380952381,
      "grad_norm": 0.0339457169175148,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4417307376861572,
      "step": 7100
    },
    {
      "epoch": 0.3381904761904762,
      "grad_norm": 0.030883677303791046,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4456703662872314,
      "step": 7102
    },
    {
      "epoch": 0.3382857142857143,
      "grad_norm": 0.030917132273316383,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4294309616088867,
      "step": 7104
    },
    {
      "epoch": 0.3383809523809524,
      "grad_norm": 0.031940482556819916,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4503893852233887,
      "step": 7106
    },
    {
      "epoch": 0.3384761904761905,
      "grad_norm": 0.02850324474275112,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4551210403442383,
      "step": 7108
    },
    {
      "epoch": 0.3385714285714286,
      "grad_norm": 0.02892199344933033,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4666802883148193,
      "step": 7110
    },
    {
      "epoch": 0.33866666666666667,
      "grad_norm": 0.02926999144256115,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4730470180511475,
      "step": 7112
    },
    {
      "epoch": 0.33876190476190476,
      "grad_norm": 0.02862759493291378,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4827075004577637,
      "step": 7114
    },
    {
      "epoch": 0.33885714285714286,
      "grad_norm": 0.03394423425197601,
      "learning_rate": 0.024000000208616257,
      "loss": 2.495112419128418,
      "step": 7116
    },
    {
      "epoch": 0.33895238095238095,
      "grad_norm": 0.03292897343635559,
      "learning_rate": 0.024000000208616257,
      "loss": 2.462902545928955,
      "step": 7118
    },
    {
      "epoch": 0.33904761904761904,
      "grad_norm": 0.029087886214256287,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4767870903015137,
      "step": 7120
    },
    {
      "epoch": 0.33914285714285713,
      "grad_norm": 0.02848999947309494,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4535558223724365,
      "step": 7122
    },
    {
      "epoch": 0.3392380952380952,
      "grad_norm": 0.028942549601197243,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4633374214172363,
      "step": 7124
    },
    {
      "epoch": 0.3393333333333333,
      "grad_norm": 0.030422993004322052,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4641377925872803,
      "step": 7126
    },
    {
      "epoch": 0.3394285714285714,
      "grad_norm": 0.0298859104514122,
      "learning_rate": 0.024000000208616257,
      "loss": 2.443366527557373,
      "step": 7128
    },
    {
      "epoch": 0.3395238095238095,
      "grad_norm": 0.02830277569591999,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4580540657043457,
      "step": 7130
    },
    {
      "epoch": 0.3396190476190476,
      "grad_norm": 0.02830120548605919,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4298129081726074,
      "step": 7132
    },
    {
      "epoch": 0.3397142857142857,
      "grad_norm": 0.03011920116841793,
      "learning_rate": 0.024000000208616257,
      "loss": 2.423710584640503,
      "step": 7134
    },
    {
      "epoch": 0.3398095238095238,
      "grad_norm": 0.031069522723555565,
      "learning_rate": 0.024000000208616257,
      "loss": 2.498598098754883,
      "step": 7136
    },
    {
      "epoch": 0.33990476190476193,
      "grad_norm": 0.027827180922031403,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4385294914245605,
      "step": 7138
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.02812875248491764,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4477288722991943,
      "step": 7140
    },
    {
      "epoch": 0.3400952380952381,
      "grad_norm": 0.02960381656885147,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4679620265960693,
      "step": 7142
    },
    {
      "epoch": 0.3401904761904762,
      "grad_norm": 0.028551479801535606,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4510841369628906,
      "step": 7144
    },
    {
      "epoch": 0.3402857142857143,
      "grad_norm": 0.03191690146923065,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4956512451171875,
      "step": 7146
    },
    {
      "epoch": 0.3403809523809524,
      "grad_norm": 0.0351298525929451,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4695401191711426,
      "step": 7148
    },
    {
      "epoch": 0.3404761904761905,
      "grad_norm": 0.033132974058389664,
      "learning_rate": 0.024000000208616257,
      "loss": 2.46604585647583,
      "step": 7150
    },
    {
      "epoch": 0.3405714285714286,
      "grad_norm": 0.030658526346087456,
      "learning_rate": 0.024000000208616257,
      "loss": 2.463367462158203,
      "step": 7152
    },
    {
      "epoch": 0.3406666666666667,
      "grad_norm": 0.029598530381917953,
      "learning_rate": 0.024000000208616257,
      "loss": 2.523293972015381,
      "step": 7154
    },
    {
      "epoch": 0.34076190476190477,
      "grad_norm": 0.029483787715435028,
      "learning_rate": 0.024000000208616257,
      "loss": 2.466376781463623,
      "step": 7156
    },
    {
      "epoch": 0.34085714285714286,
      "grad_norm": 0.028604887425899506,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4673075675964355,
      "step": 7158
    },
    {
      "epoch": 0.34095238095238095,
      "grad_norm": 0.029819631949067116,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4544901847839355,
      "step": 7160
    },
    {
      "epoch": 0.34104761904761904,
      "grad_norm": 0.02974962256848812,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4503908157348633,
      "step": 7162
    },
    {
      "epoch": 0.34114285714285714,
      "grad_norm": 0.027605820447206497,
      "learning_rate": 0.024000000208616257,
      "loss": 2.500955820083618,
      "step": 7164
    },
    {
      "epoch": 0.34123809523809523,
      "grad_norm": 0.028526684269309044,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4901552200317383,
      "step": 7166
    },
    {
      "epoch": 0.3413333333333333,
      "grad_norm": 0.028147904202342033,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4575531482696533,
      "step": 7168
    },
    {
      "epoch": 0.3414285714285714,
      "grad_norm": 0.029349802061915398,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4632768630981445,
      "step": 7170
    },
    {
      "epoch": 0.3415238095238095,
      "grad_norm": 0.03037298657000065,
      "learning_rate": 0.024000000208616257,
      "loss": 2.457612991333008,
      "step": 7172
    },
    {
      "epoch": 0.3416190476190476,
      "grad_norm": 0.031271085143089294,
      "learning_rate": 0.024000000208616257,
      "loss": 2.464320659637451,
      "step": 7174
    },
    {
      "epoch": 0.3417142857142857,
      "grad_norm": 0.029048999771475792,
      "learning_rate": 0.024000000208616257,
      "loss": 2.463287830352783,
      "step": 7176
    },
    {
      "epoch": 0.3418095238095238,
      "grad_norm": 0.02924540266394615,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4439172744750977,
      "step": 7178
    },
    {
      "epoch": 0.3419047619047619,
      "grad_norm": 0.02843838930130005,
      "learning_rate": 0.024000000208616257,
      "loss": 2.423173427581787,
      "step": 7180
    },
    {
      "epoch": 0.342,
      "grad_norm": 0.027904484421014786,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4402568340301514,
      "step": 7182
    },
    {
      "epoch": 0.3420952380952381,
      "grad_norm": 0.030173301696777344,
      "learning_rate": 0.024000000208616257,
      "loss": 2.472141742706299,
      "step": 7184
    },
    {
      "epoch": 0.3421904761904762,
      "grad_norm": 0.03218153119087219,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4705193042755127,
      "step": 7186
    },
    {
      "epoch": 0.3422857142857143,
      "grad_norm": 0.02841062657535076,
      "learning_rate": 0.024000000208616257,
      "loss": 2.45914363861084,
      "step": 7188
    },
    {
      "epoch": 0.3423809523809524,
      "grad_norm": 0.028493352234363556,
      "learning_rate": 0.024000000208616257,
      "loss": 2.519477128982544,
      "step": 7190
    },
    {
      "epoch": 0.3424761904761905,
      "grad_norm": 0.02945573255419731,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4674437046051025,
      "step": 7192
    },
    {
      "epoch": 0.3425714285714286,
      "grad_norm": 0.028700729832053185,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4787631034851074,
      "step": 7194
    },
    {
      "epoch": 0.3426666666666667,
      "grad_norm": 0.029406318441033363,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4980711936950684,
      "step": 7196
    },
    {
      "epoch": 0.34276190476190477,
      "grad_norm": 0.03115459345281124,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4907050132751465,
      "step": 7198
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.030964750796556473,
      "learning_rate": 0.024000000208616257,
      "loss": 2.490243911743164,
      "step": 7200
    },
    {
      "epoch": 0.34295238095238095,
      "grad_norm": 0.029313424602150917,
      "learning_rate": 0.024000000208616257,
      "loss": 2.504526138305664,
      "step": 7202
    },
    {
      "epoch": 0.34304761904761905,
      "grad_norm": 0.030464263632893562,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5088295936584473,
      "step": 7204
    },
    {
      "epoch": 0.34314285714285714,
      "grad_norm": 0.031024502590298653,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5073044300079346,
      "step": 7206
    },
    {
      "epoch": 0.34323809523809523,
      "grad_norm": 0.029009822756052017,
      "learning_rate": 0.024000000208616257,
      "loss": 2.462553024291992,
      "step": 7208
    },
    {
      "epoch": 0.3433333333333333,
      "grad_norm": 0.0356479249894619,
      "learning_rate": 0.024000000208616257,
      "loss": 2.450239419937134,
      "step": 7210
    },
    {
      "epoch": 0.3434285714285714,
      "grad_norm": 0.03435588628053665,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4902901649475098,
      "step": 7212
    },
    {
      "epoch": 0.3435238095238095,
      "grad_norm": 0.033255435526371,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4574522972106934,
      "step": 7214
    },
    {
      "epoch": 0.3436190476190476,
      "grad_norm": 0.04126044362783432,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4765820503234863,
      "step": 7216
    },
    {
      "epoch": 0.3437142857142857,
      "grad_norm": 0.030936727300286293,
      "learning_rate": 0.024000000208616257,
      "loss": 2.458669662475586,
      "step": 7218
    },
    {
      "epoch": 0.3438095238095238,
      "grad_norm": 0.03068406507372856,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4737532138824463,
      "step": 7220
    },
    {
      "epoch": 0.3439047619047619,
      "grad_norm": 0.03037591464817524,
      "learning_rate": 0.024000000208616257,
      "loss": 2.474289894104004,
      "step": 7222
    },
    {
      "epoch": 0.344,
      "grad_norm": 0.029864152893424034,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4798991680145264,
      "step": 7224
    },
    {
      "epoch": 0.3440952380952381,
      "grad_norm": 0.02870749495923519,
      "learning_rate": 0.024000000208616257,
      "loss": 2.491424322128296,
      "step": 7226
    },
    {
      "epoch": 0.3441904761904762,
      "grad_norm": 0.02912965975701809,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4716386795043945,
      "step": 7228
    },
    {
      "epoch": 0.3442857142857143,
      "grad_norm": 0.028883563354611397,
      "learning_rate": 0.024000000208616257,
      "loss": 2.468576669692993,
      "step": 7230
    },
    {
      "epoch": 0.3443809523809524,
      "grad_norm": 0.030738983303308487,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5450081825256348,
      "step": 7232
    },
    {
      "epoch": 0.3444761904761905,
      "grad_norm": 0.03250139206647873,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4857592582702637,
      "step": 7234
    },
    {
      "epoch": 0.3445714285714286,
      "grad_norm": 0.029801970347762108,
      "learning_rate": 0.024000000208616257,
      "loss": 2.487823486328125,
      "step": 7236
    },
    {
      "epoch": 0.3446666666666667,
      "grad_norm": 0.02863362245261669,
      "learning_rate": 0.024000000208616257,
      "loss": 2.457735538482666,
      "step": 7238
    },
    {
      "epoch": 0.34476190476190477,
      "grad_norm": 0.03034256398677826,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5020687580108643,
      "step": 7240
    },
    {
      "epoch": 0.34485714285714286,
      "grad_norm": 0.02942848391830921,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5086185932159424,
      "step": 7242
    },
    {
      "epoch": 0.34495238095238095,
      "grad_norm": 0.031980857253074646,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4664902687072754,
      "step": 7244
    },
    {
      "epoch": 0.34504761904761905,
      "grad_norm": 0.02999952808022499,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5107102394104004,
      "step": 7246
    },
    {
      "epoch": 0.34514285714285714,
      "grad_norm": 0.029638033360242844,
      "learning_rate": 0.024000000208616257,
      "loss": 2.492959499359131,
      "step": 7248
    },
    {
      "epoch": 0.34523809523809523,
      "grad_norm": 0.03213273733854294,
      "learning_rate": 0.024000000208616257,
      "loss": 2.501483201980591,
      "step": 7250
    },
    {
      "epoch": 0.3453333333333333,
      "grad_norm": 0.030824650079011917,
      "learning_rate": 0.024000000208616257,
      "loss": 2.455821990966797,
      "step": 7252
    },
    {
      "epoch": 0.3454285714285714,
      "grad_norm": 0.031094126403331757,
      "learning_rate": 0.024000000208616257,
      "loss": 2.505587577819824,
      "step": 7254
    },
    {
      "epoch": 0.3455238095238095,
      "grad_norm": 0.028878873214125633,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4963369369506836,
      "step": 7256
    },
    {
      "epoch": 0.3456190476190476,
      "grad_norm": 0.03145955875515938,
      "learning_rate": 0.024000000208616257,
      "loss": 2.480407238006592,
      "step": 7258
    },
    {
      "epoch": 0.3457142857142857,
      "grad_norm": 0.029653044417500496,
      "learning_rate": 0.024000000208616257,
      "loss": 2.487546920776367,
      "step": 7260
    },
    {
      "epoch": 0.3458095238095238,
      "grad_norm": 0.028438007459044456,
      "learning_rate": 0.024000000208616257,
      "loss": 2.501030921936035,
      "step": 7262
    },
    {
      "epoch": 0.3459047619047619,
      "grad_norm": 0.0294172465801239,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5115904808044434,
      "step": 7264
    },
    {
      "epoch": 0.346,
      "grad_norm": 0.03162037208676338,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4564995765686035,
      "step": 7266
    },
    {
      "epoch": 0.3460952380952381,
      "grad_norm": 0.029247205704450607,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4929494857788086,
      "step": 7268
    },
    {
      "epoch": 0.3461904761904762,
      "grad_norm": 0.029292277991771698,
      "learning_rate": 0.024000000208616257,
      "loss": 2.491727352142334,
      "step": 7270
    },
    {
      "epoch": 0.3462857142857143,
      "grad_norm": 0.03074842132627964,
      "learning_rate": 0.024000000208616257,
      "loss": 2.488158941268921,
      "step": 7272
    },
    {
      "epoch": 0.3463809523809524,
      "grad_norm": 0.029288263991475105,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4573826789855957,
      "step": 7274
    },
    {
      "epoch": 0.3464761904761905,
      "grad_norm": 0.029053131118416786,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4834744930267334,
      "step": 7276
    },
    {
      "epoch": 0.3465714285714286,
      "grad_norm": 0.03181622922420502,
      "learning_rate": 0.024000000208616257,
      "loss": 2.484112501144409,
      "step": 7278
    },
    {
      "epoch": 0.3466666666666667,
      "grad_norm": 0.029723549261689186,
      "learning_rate": 0.024000000208616257,
      "loss": 2.501946449279785,
      "step": 7280
    },
    {
      "epoch": 0.34676190476190477,
      "grad_norm": 0.02847200259566307,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4886326789855957,
      "step": 7282
    },
    {
      "epoch": 0.34685714285714286,
      "grad_norm": 0.03247971087694168,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4997291564941406,
      "step": 7284
    },
    {
      "epoch": 0.34695238095238096,
      "grad_norm": 0.031090058386325836,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4824271202087402,
      "step": 7286
    },
    {
      "epoch": 0.34704761904761905,
      "grad_norm": 0.03372269496321678,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5186023712158203,
      "step": 7288
    },
    {
      "epoch": 0.34714285714285714,
      "grad_norm": 0.030349712818861008,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4743456840515137,
      "step": 7290
    },
    {
      "epoch": 0.34723809523809523,
      "grad_norm": 0.03018053062260151,
      "learning_rate": 0.024000000208616257,
      "loss": 2.495062828063965,
      "step": 7292
    },
    {
      "epoch": 0.3473333333333333,
      "grad_norm": 0.03062352165579796,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4721741676330566,
      "step": 7294
    },
    {
      "epoch": 0.3474285714285714,
      "grad_norm": 0.031229838728904724,
      "learning_rate": 0.024000000208616257,
      "loss": 2.485973358154297,
      "step": 7296
    },
    {
      "epoch": 0.3475238095238095,
      "grad_norm": 0.03474581614136696,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5063843727111816,
      "step": 7298
    },
    {
      "epoch": 0.3476190476190476,
      "grad_norm": 0.02930903434753418,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4806158542633057,
      "step": 7300
    },
    {
      "epoch": 0.3477142857142857,
      "grad_norm": 0.030748963356018066,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5157411098480225,
      "step": 7302
    },
    {
      "epoch": 0.3478095238095238,
      "grad_norm": 0.032289985567331314,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4714863300323486,
      "step": 7304
    },
    {
      "epoch": 0.3479047619047619,
      "grad_norm": 0.02843460626900196,
      "learning_rate": 0.024000000208616257,
      "loss": 2.483907461166382,
      "step": 7306
    },
    {
      "epoch": 0.348,
      "grad_norm": 0.029354147613048553,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4782252311706543,
      "step": 7308
    },
    {
      "epoch": 0.34809523809523807,
      "grad_norm": 0.028046205639839172,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4735186100006104,
      "step": 7310
    },
    {
      "epoch": 0.3481904761904762,
      "grad_norm": 0.028843354433774948,
      "learning_rate": 0.024000000208616257,
      "loss": 2.515306234359741,
      "step": 7312
    },
    {
      "epoch": 0.3482857142857143,
      "grad_norm": 0.028741387650370598,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4904439449310303,
      "step": 7314
    },
    {
      "epoch": 0.3483809523809524,
      "grad_norm": 0.029219195246696472,
      "learning_rate": 0.024000000208616257,
      "loss": 2.510493755340576,
      "step": 7316
    },
    {
      "epoch": 0.3484761904761905,
      "grad_norm": 0.02917374111711979,
      "learning_rate": 0.024000000208616257,
      "loss": 2.494441032409668,
      "step": 7318
    },
    {
      "epoch": 0.3485714285714286,
      "grad_norm": 0.02960243634879589,
      "learning_rate": 0.024000000208616257,
      "loss": 2.536618709564209,
      "step": 7320
    },
    {
      "epoch": 0.3486666666666667,
      "grad_norm": 0.03237590193748474,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4856107234954834,
      "step": 7322
    },
    {
      "epoch": 0.3487619047619048,
      "grad_norm": 0.030879424884915352,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5114712715148926,
      "step": 7324
    },
    {
      "epoch": 0.34885714285714287,
      "grad_norm": 0.029863355681300163,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4567670822143555,
      "step": 7326
    },
    {
      "epoch": 0.34895238095238096,
      "grad_norm": 0.029317473992705345,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5172688961029053,
      "step": 7328
    },
    {
      "epoch": 0.34904761904761905,
      "grad_norm": 0.03155161812901497,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4531140327453613,
      "step": 7330
    },
    {
      "epoch": 0.34914285714285714,
      "grad_norm": 0.029375853016972542,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5044302940368652,
      "step": 7332
    },
    {
      "epoch": 0.34923809523809524,
      "grad_norm": 0.030677493661642075,
      "learning_rate": 0.024000000208616257,
      "loss": 2.454068183898926,
      "step": 7334
    },
    {
      "epoch": 0.34933333333333333,
      "grad_norm": 0.028836466372013092,
      "learning_rate": 0.024000000208616257,
      "loss": 2.537696361541748,
      "step": 7336
    },
    {
      "epoch": 0.3494285714285714,
      "grad_norm": 0.029719866812229156,
      "learning_rate": 0.024000000208616257,
      "loss": 2.473372459411621,
      "step": 7338
    },
    {
      "epoch": 0.3495238095238095,
      "grad_norm": 0.02897462248802185,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4680652618408203,
      "step": 7340
    },
    {
      "epoch": 0.3496190476190476,
      "grad_norm": 0.033235035836696625,
      "learning_rate": 0.024000000208616257,
      "loss": 2.484823703765869,
      "step": 7342
    },
    {
      "epoch": 0.3497142857142857,
      "grad_norm": 0.02991124801337719,
      "learning_rate": 0.024000000208616257,
      "loss": 2.450178623199463,
      "step": 7344
    },
    {
      "epoch": 0.3498095238095238,
      "grad_norm": 0.030203593894839287,
      "learning_rate": 0.024000000208616257,
      "loss": 2.491995334625244,
      "step": 7346
    },
    {
      "epoch": 0.3499047619047619,
      "grad_norm": 0.03270898386836052,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4693045616149902,
      "step": 7348
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.03570309653878212,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4796905517578125,
      "step": 7350
    },
    {
      "epoch": 0.35009523809523807,
      "grad_norm": 0.034593235701322556,
      "learning_rate": 0.024000000208616257,
      "loss": 2.472975254058838,
      "step": 7352
    },
    {
      "epoch": 0.35019047619047616,
      "grad_norm": 0.030379949137568474,
      "learning_rate": 0.024000000208616257,
      "loss": 2.486605644226074,
      "step": 7354
    },
    {
      "epoch": 0.3502857142857143,
      "grad_norm": 0.030839839950203896,
      "learning_rate": 0.024000000208616257,
      "loss": 2.458967685699463,
      "step": 7356
    },
    {
      "epoch": 0.3503809523809524,
      "grad_norm": 0.029235225170850754,
      "learning_rate": 0.024000000208616257,
      "loss": 2.526707649230957,
      "step": 7358
    },
    {
      "epoch": 0.3504761904761905,
      "grad_norm": 0.03129074349999428,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4783668518066406,
      "step": 7360
    },
    {
      "epoch": 0.3505714285714286,
      "grad_norm": 0.029996979981660843,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4763309955596924,
      "step": 7362
    },
    {
      "epoch": 0.3506666666666667,
      "grad_norm": 0.03106936439871788,
      "learning_rate": 0.024000000208616257,
      "loss": 2.471195697784424,
      "step": 7364
    },
    {
      "epoch": 0.3507619047619048,
      "grad_norm": 0.02984689362347126,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4661970138549805,
      "step": 7366
    },
    {
      "epoch": 0.35085714285714287,
      "grad_norm": 0.030764013528823853,
      "learning_rate": 0.024000000208616257,
      "loss": 2.484631061553955,
      "step": 7368
    },
    {
      "epoch": 0.35095238095238096,
      "grad_norm": 0.029097070917487144,
      "learning_rate": 0.024000000208616257,
      "loss": 2.501878261566162,
      "step": 7370
    },
    {
      "epoch": 0.35104761904761905,
      "grad_norm": 0.028702927753329277,
      "learning_rate": 0.024000000208616257,
      "loss": 2.489495277404785,
      "step": 7372
    },
    {
      "epoch": 0.35114285714285715,
      "grad_norm": 0.031982388347387314,
      "learning_rate": 0.024000000208616257,
      "loss": 2.46821665763855,
      "step": 7374
    },
    {
      "epoch": 0.35123809523809524,
      "grad_norm": 0.030151236802339554,
      "learning_rate": 0.024000000208616257,
      "loss": 2.517869472503662,
      "step": 7376
    },
    {
      "epoch": 0.35133333333333333,
      "grad_norm": 0.03283766657114029,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4893906116485596,
      "step": 7378
    },
    {
      "epoch": 0.3514285714285714,
      "grad_norm": 0.030716801062226295,
      "learning_rate": 0.024000000208616257,
      "loss": 2.453476667404175,
      "step": 7380
    },
    {
      "epoch": 0.3515238095238095,
      "grad_norm": 0.030580205842852592,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4545035362243652,
      "step": 7382
    },
    {
      "epoch": 0.3516190476190476,
      "grad_norm": 0.02914385125041008,
      "learning_rate": 0.024000000208616257,
      "loss": 2.437777519226074,
      "step": 7384
    },
    {
      "epoch": 0.3517142857142857,
      "grad_norm": 0.029267074540257454,
      "learning_rate": 0.024000000208616257,
      "loss": 2.466407299041748,
      "step": 7386
    },
    {
      "epoch": 0.3518095238095238,
      "grad_norm": 0.02974027581512928,
      "learning_rate": 0.024000000208616257,
      "loss": 2.472499370574951,
      "step": 7388
    },
    {
      "epoch": 0.3519047619047619,
      "grad_norm": 0.030461251735687256,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5239787101745605,
      "step": 7390
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.02885858155786991,
      "learning_rate": 0.024000000208616257,
      "loss": 2.482952117919922,
      "step": 7392
    },
    {
      "epoch": 0.3520952380952381,
      "grad_norm": 0.029422996565699577,
      "learning_rate": 0.024000000208616257,
      "loss": 2.463258743286133,
      "step": 7394
    },
    {
      "epoch": 0.35219047619047616,
      "grad_norm": 0.029847247526049614,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5085182189941406,
      "step": 7396
    },
    {
      "epoch": 0.3522857142857143,
      "grad_norm": 0.030343718826770782,
      "learning_rate": 0.024000000208616257,
      "loss": 2.492072582244873,
      "step": 7398
    },
    {
      "epoch": 0.3523809523809524,
      "grad_norm": 0.03337286040186882,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5099477767944336,
      "step": 7400
    },
    {
      "epoch": 0.3524761904761905,
      "grad_norm": 0.030504466965794563,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4763784408569336,
      "step": 7402
    },
    {
      "epoch": 0.3525714285714286,
      "grad_norm": 0.03060448355972767,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4875996112823486,
      "step": 7404
    },
    {
      "epoch": 0.3526666666666667,
      "grad_norm": 0.031309135258197784,
      "learning_rate": 0.024000000208616257,
      "loss": 2.478215456008911,
      "step": 7406
    },
    {
      "epoch": 0.3527619047619048,
      "grad_norm": 0.03097343258559704,
      "learning_rate": 0.024000000208616257,
      "loss": 2.499499797821045,
      "step": 7408
    },
    {
      "epoch": 0.35285714285714287,
      "grad_norm": 0.030008548870682716,
      "learning_rate": 0.024000000208616257,
      "loss": 2.510662078857422,
      "step": 7410
    },
    {
      "epoch": 0.35295238095238096,
      "grad_norm": 0.03203392028808594,
      "learning_rate": 0.024000000208616257,
      "loss": 2.477509021759033,
      "step": 7412
    },
    {
      "epoch": 0.35304761904761905,
      "grad_norm": 0.031908582895994186,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5191140174865723,
      "step": 7414
    },
    {
      "epoch": 0.35314285714285715,
      "grad_norm": 0.03092641942203045,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4559121131896973,
      "step": 7416
    },
    {
      "epoch": 0.35323809523809524,
      "grad_norm": 0.029326114803552628,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4772567749023438,
      "step": 7418
    },
    {
      "epoch": 0.35333333333333333,
      "grad_norm": 0.03299442678689957,
      "learning_rate": 0.024000000208616257,
      "loss": 2.478175640106201,
      "step": 7420
    },
    {
      "epoch": 0.3534285714285714,
      "grad_norm": 0.029913930222392082,
      "learning_rate": 0.024000000208616257,
      "loss": 2.501631259918213,
      "step": 7422
    },
    {
      "epoch": 0.3535238095238095,
      "grad_norm": 0.02963915280997753,
      "learning_rate": 0.024000000208616257,
      "loss": 2.490828037261963,
      "step": 7424
    },
    {
      "epoch": 0.3536190476190476,
      "grad_norm": 0.029659969732165337,
      "learning_rate": 0.024000000208616257,
      "loss": 2.486884593963623,
      "step": 7426
    },
    {
      "epoch": 0.3537142857142857,
      "grad_norm": 0.02816743031144142,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4832983016967773,
      "step": 7428
    },
    {
      "epoch": 0.3538095238095238,
      "grad_norm": 0.029104989022016525,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5229010581970215,
      "step": 7430
    },
    {
      "epoch": 0.3539047619047619,
      "grad_norm": 0.02909243479371071,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4786200523376465,
      "step": 7432
    },
    {
      "epoch": 0.354,
      "grad_norm": 0.028102625161409378,
      "learning_rate": 0.024000000208616257,
      "loss": 2.488201379776001,
      "step": 7434
    },
    {
      "epoch": 0.3540952380952381,
      "grad_norm": 0.028283845633268356,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4909451007843018,
      "step": 7436
    },
    {
      "epoch": 0.35419047619047617,
      "grad_norm": 0.02982216328382492,
      "learning_rate": 0.024000000208616257,
      "loss": 2.468583583831787,
      "step": 7438
    },
    {
      "epoch": 0.35428571428571426,
      "grad_norm": 0.028986232355237007,
      "learning_rate": 0.024000000208616257,
      "loss": 2.482180118560791,
      "step": 7440
    },
    {
      "epoch": 0.3543809523809524,
      "grad_norm": 0.02950805053114891,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5043275356292725,
      "step": 7442
    },
    {
      "epoch": 0.3544761904761905,
      "grad_norm": 0.028700657188892365,
      "learning_rate": 0.024000000208616257,
      "loss": 2.480087995529175,
      "step": 7444
    },
    {
      "epoch": 0.3545714285714286,
      "grad_norm": 0.029247336089611053,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4753594398498535,
      "step": 7446
    },
    {
      "epoch": 0.3546666666666667,
      "grad_norm": 0.030460497364401817,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4713218212127686,
      "step": 7448
    },
    {
      "epoch": 0.3547619047619048,
      "grad_norm": 0.029349435120821,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4978508949279785,
      "step": 7450
    },
    {
      "epoch": 0.35485714285714287,
      "grad_norm": 0.029993444681167603,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5039737224578857,
      "step": 7452
    },
    {
      "epoch": 0.35495238095238096,
      "grad_norm": 0.028877366334199905,
      "learning_rate": 0.024000000208616257,
      "loss": 2.46929931640625,
      "step": 7454
    },
    {
      "epoch": 0.35504761904761906,
      "grad_norm": 0.02925742417573929,
      "learning_rate": 0.024000000208616257,
      "loss": 2.463090419769287,
      "step": 7456
    },
    {
      "epoch": 0.35514285714285715,
      "grad_norm": 0.03274105116724968,
      "learning_rate": 0.024000000208616257,
      "loss": 2.479149103164673,
      "step": 7458
    },
    {
      "epoch": 0.35523809523809524,
      "grad_norm": 0.03168944641947746,
      "learning_rate": 0.024000000208616257,
      "loss": 2.516313314437866,
      "step": 7460
    },
    {
      "epoch": 0.35533333333333333,
      "grad_norm": 0.030370492488145828,
      "learning_rate": 0.024000000208616257,
      "loss": 2.494283437728882,
      "step": 7462
    },
    {
      "epoch": 0.3554285714285714,
      "grad_norm": 0.02851349487900734,
      "learning_rate": 0.024000000208616257,
      "loss": 2.456425428390503,
      "step": 7464
    },
    {
      "epoch": 0.3555238095238095,
      "grad_norm": 0.02843330428004265,
      "learning_rate": 0.024000000208616257,
      "loss": 2.480900764465332,
      "step": 7466
    },
    {
      "epoch": 0.3556190476190476,
      "grad_norm": 0.03043600358068943,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4317424297332764,
      "step": 7468
    },
    {
      "epoch": 0.3557142857142857,
      "grad_norm": 0.029564805328845978,
      "learning_rate": 0.024000000208616257,
      "loss": 2.457010507583618,
      "step": 7470
    },
    {
      "epoch": 0.3558095238095238,
      "grad_norm": 0.029780447483062744,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4544053077697754,
      "step": 7472
    },
    {
      "epoch": 0.3559047619047619,
      "grad_norm": 0.028644749894738197,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4319982528686523,
      "step": 7474
    },
    {
      "epoch": 0.356,
      "grad_norm": 0.02905803732573986,
      "learning_rate": 0.024000000208616257,
      "loss": 2.476264476776123,
      "step": 7476
    },
    {
      "epoch": 0.3560952380952381,
      "grad_norm": 0.02941397950053215,
      "learning_rate": 0.024000000208616257,
      "loss": 2.497739553451538,
      "step": 7478
    },
    {
      "epoch": 0.35619047619047617,
      "grad_norm": 0.030269697308540344,
      "learning_rate": 0.024000000208616257,
      "loss": 2.450881004333496,
      "step": 7480
    },
    {
      "epoch": 0.35628571428571426,
      "grad_norm": 0.028688127174973488,
      "learning_rate": 0.024000000208616257,
      "loss": 2.448216438293457,
      "step": 7482
    },
    {
      "epoch": 0.35638095238095235,
      "grad_norm": 0.027922969311475754,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4772512912750244,
      "step": 7484
    },
    {
      "epoch": 0.3564761904761905,
      "grad_norm": 0.029066462069749832,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5185322761535645,
      "step": 7486
    },
    {
      "epoch": 0.3565714285714286,
      "grad_norm": 0.029376937076449394,
      "learning_rate": 0.024000000208616257,
      "loss": 2.456643581390381,
      "step": 7488
    },
    {
      "epoch": 0.3566666666666667,
      "grad_norm": 0.029913054779171944,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4898881912231445,
      "step": 7490
    },
    {
      "epoch": 0.3567619047619048,
      "grad_norm": 0.029282063245773315,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4743411540985107,
      "step": 7492
    },
    {
      "epoch": 0.3568571428571429,
      "grad_norm": 0.028897307813167572,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4848525524139404,
      "step": 7494
    },
    {
      "epoch": 0.35695238095238097,
      "grad_norm": 0.030271543189883232,
      "learning_rate": 0.024000000208616257,
      "loss": 2.483419418334961,
      "step": 7496
    },
    {
      "epoch": 0.35704761904761906,
      "grad_norm": 0.029247567057609558,
      "learning_rate": 0.024000000208616257,
      "loss": 2.436640739440918,
      "step": 7498
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.030555840581655502,
      "learning_rate": 0.024000000208616257,
      "loss": 2.48775577545166,
      "step": 7500
    },
    {
      "epoch": 0.35723809523809524,
      "grad_norm": 0.03313332796096802,
      "learning_rate": 0.024000000208616257,
      "loss": 2.482847213745117,
      "step": 7502
    },
    {
      "epoch": 0.35733333333333334,
      "grad_norm": 0.02917507477104664,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4977848529815674,
      "step": 7504
    },
    {
      "epoch": 0.35742857142857143,
      "grad_norm": 0.030479153618216515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.493488311767578,
      "step": 7506
    },
    {
      "epoch": 0.3575238095238095,
      "grad_norm": 0.029542014002799988,
      "learning_rate": 0.024000000208616257,
      "loss": 2.528918981552124,
      "step": 7508
    },
    {
      "epoch": 0.3576190476190476,
      "grad_norm": 0.02890731953084469,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4897751808166504,
      "step": 7510
    },
    {
      "epoch": 0.3577142857142857,
      "grad_norm": 0.028727268800139427,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5099620819091797,
      "step": 7512
    },
    {
      "epoch": 0.3578095238095238,
      "grad_norm": 0.02899094671010971,
      "learning_rate": 0.024000000208616257,
      "loss": 2.478609800338745,
      "step": 7514
    },
    {
      "epoch": 0.3579047619047619,
      "grad_norm": 0.02854040078818798,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4880685806274414,
      "step": 7516
    },
    {
      "epoch": 0.358,
      "grad_norm": 0.02883659116923809,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4942140579223633,
      "step": 7518
    },
    {
      "epoch": 0.3580952380952381,
      "grad_norm": 0.03091655671596527,
      "learning_rate": 0.024000000208616257,
      "loss": 2.484349250793457,
      "step": 7520
    },
    {
      "epoch": 0.35819047619047617,
      "grad_norm": 0.03304492309689522,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4954049587249756,
      "step": 7522
    },
    {
      "epoch": 0.35828571428571426,
      "grad_norm": 0.029811056330800056,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4957375526428223,
      "step": 7524
    },
    {
      "epoch": 0.35838095238095236,
      "grad_norm": 0.028990549966692924,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4696226119995117,
      "step": 7526
    },
    {
      "epoch": 0.3584761904761905,
      "grad_norm": 0.029515385627746582,
      "learning_rate": 0.024000000208616257,
      "loss": 2.499206066131592,
      "step": 7528
    },
    {
      "epoch": 0.3585714285714286,
      "grad_norm": 0.029762782156467438,
      "learning_rate": 0.024000000208616257,
      "loss": 2.504568338394165,
      "step": 7530
    },
    {
      "epoch": 0.3586666666666667,
      "grad_norm": 0.028197282925248146,
      "learning_rate": 0.024000000208616257,
      "loss": 2.473376512527466,
      "step": 7532
    },
    {
      "epoch": 0.3587619047619048,
      "grad_norm": 0.02801641635596752,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5047898292541504,
      "step": 7534
    },
    {
      "epoch": 0.3588571428571429,
      "grad_norm": 0.029196398332715034,
      "learning_rate": 0.024000000208616257,
      "loss": 2.51065993309021,
      "step": 7536
    },
    {
      "epoch": 0.35895238095238097,
      "grad_norm": 0.0327506959438324,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4951534271240234,
      "step": 7538
    },
    {
      "epoch": 0.35904761904761906,
      "grad_norm": 0.031637679785490036,
      "learning_rate": 0.024000000208616257,
      "loss": 2.456279754638672,
      "step": 7540
    },
    {
      "epoch": 0.35914285714285715,
      "grad_norm": 0.035517629235982895,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4517698287963867,
      "step": 7542
    },
    {
      "epoch": 0.35923809523809525,
      "grad_norm": 0.032872457057237625,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5081593990325928,
      "step": 7544
    },
    {
      "epoch": 0.35933333333333334,
      "grad_norm": 0.032976653426885605,
      "learning_rate": 0.024000000208616257,
      "loss": 2.483184814453125,
      "step": 7546
    },
    {
      "epoch": 0.35942857142857143,
      "grad_norm": 0.031915951520204544,
      "learning_rate": 0.024000000208616257,
      "loss": 2.478771448135376,
      "step": 7548
    },
    {
      "epoch": 0.3595238095238095,
      "grad_norm": 0.027942590415477753,
      "learning_rate": 0.024000000208616257,
      "loss": 2.488023281097412,
      "step": 7550
    },
    {
      "epoch": 0.3596190476190476,
      "grad_norm": 0.030303698033094406,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4821338653564453,
      "step": 7552
    },
    {
      "epoch": 0.3597142857142857,
      "grad_norm": 0.029949450865387917,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4945976734161377,
      "step": 7554
    },
    {
      "epoch": 0.3598095238095238,
      "grad_norm": 0.030359257012605667,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4935851097106934,
      "step": 7556
    },
    {
      "epoch": 0.3599047619047619,
      "grad_norm": 0.02890615165233612,
      "learning_rate": 0.024000000208616257,
      "loss": 2.486807346343994,
      "step": 7558
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.028664810582995415,
      "learning_rate": 0.024000000208616257,
      "loss": 2.462501287460327,
      "step": 7560
    },
    {
      "epoch": 0.3600952380952381,
      "grad_norm": 0.03124232590198517,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4615330696105957,
      "step": 7562
    },
    {
      "epoch": 0.36019047619047617,
      "grad_norm": 0.028973368927836418,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5193405151367188,
      "step": 7564
    },
    {
      "epoch": 0.36028571428571426,
      "grad_norm": 0.02797664888203144,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4477133750915527,
      "step": 7566
    },
    {
      "epoch": 0.36038095238095236,
      "grad_norm": 0.031132953241467476,
      "learning_rate": 0.024000000208616257,
      "loss": 2.465818405151367,
      "step": 7568
    },
    {
      "epoch": 0.36047619047619045,
      "grad_norm": 0.0317101813852787,
      "learning_rate": 0.024000000208616257,
      "loss": 2.476649761199951,
      "step": 7570
    },
    {
      "epoch": 0.3605714285714286,
      "grad_norm": 0.028868285939097404,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4794998168945312,
      "step": 7572
    },
    {
      "epoch": 0.3606666666666667,
      "grad_norm": 0.029143821448087692,
      "learning_rate": 0.024000000208616257,
      "loss": 2.512355327606201,
      "step": 7574
    },
    {
      "epoch": 0.3607619047619048,
      "grad_norm": 0.02819014899432659,
      "learning_rate": 0.024000000208616257,
      "loss": 2.475674629211426,
      "step": 7576
    },
    {
      "epoch": 0.3608571428571429,
      "grad_norm": 0.028959864750504494,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4761769771575928,
      "step": 7578
    },
    {
      "epoch": 0.36095238095238097,
      "grad_norm": 0.02932652086019516,
      "learning_rate": 0.024000000208616257,
      "loss": 2.514834403991699,
      "step": 7580
    },
    {
      "epoch": 0.36104761904761906,
      "grad_norm": 0.02883383445441723,
      "learning_rate": 0.024000000208616257,
      "loss": 2.515957832336426,
      "step": 7582
    },
    {
      "epoch": 0.36114285714285715,
      "grad_norm": 0.030183840543031693,
      "learning_rate": 0.024000000208616257,
      "loss": 2.472200870513916,
      "step": 7584
    },
    {
      "epoch": 0.36123809523809525,
      "grad_norm": 0.028086630627512932,
      "learning_rate": 0.024000000208616257,
      "loss": 2.482262134552002,
      "step": 7586
    },
    {
      "epoch": 0.36133333333333334,
      "grad_norm": 0.03126629441976547,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5165367126464844,
      "step": 7588
    },
    {
      "epoch": 0.36142857142857143,
      "grad_norm": 0.03489893674850464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4762377738952637,
      "step": 7590
    },
    {
      "epoch": 0.3615238095238095,
      "grad_norm": 0.03232874348759651,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5103416442871094,
      "step": 7592
    },
    {
      "epoch": 0.3616190476190476,
      "grad_norm": 0.03388991206884384,
      "learning_rate": 0.024000000208616257,
      "loss": 2.478438377380371,
      "step": 7594
    },
    {
      "epoch": 0.3617142857142857,
      "grad_norm": 0.029955795034766197,
      "learning_rate": 0.024000000208616257,
      "loss": 2.45986008644104,
      "step": 7596
    },
    {
      "epoch": 0.3618095238095238,
      "grad_norm": 0.030252832919359207,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4841837882995605,
      "step": 7598
    },
    {
      "epoch": 0.3619047619047619,
      "grad_norm": 0.030670886859297752,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4674863815307617,
      "step": 7600
    },
    {
      "epoch": 0.362,
      "grad_norm": 0.029035434126853943,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4723687171936035,
      "step": 7602
    },
    {
      "epoch": 0.3620952380952381,
      "grad_norm": 0.02931477688252926,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4744162559509277,
      "step": 7604
    },
    {
      "epoch": 0.3621904761904762,
      "grad_norm": 0.029019296169281006,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4842188358306885,
      "step": 7606
    },
    {
      "epoch": 0.36228571428571427,
      "grad_norm": 0.03260951489210129,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4846415519714355,
      "step": 7608
    },
    {
      "epoch": 0.36238095238095236,
      "grad_norm": 0.028813229873776436,
      "learning_rate": 0.024000000208616257,
      "loss": 2.482565402984619,
      "step": 7610
    },
    {
      "epoch": 0.36247619047619045,
      "grad_norm": 0.029857659712433815,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5206589698791504,
      "step": 7612
    },
    {
      "epoch": 0.36257142857142854,
      "grad_norm": 0.02877364680171013,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4918158054351807,
      "step": 7614
    },
    {
      "epoch": 0.3626666666666667,
      "grad_norm": 0.029010774567723274,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4802300930023193,
      "step": 7616
    },
    {
      "epoch": 0.3627619047619048,
      "grad_norm": 0.03279303014278412,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4811625480651855,
      "step": 7618
    },
    {
      "epoch": 0.3628571428571429,
      "grad_norm": 0.030422266572713852,
      "learning_rate": 0.024000000208616257,
      "loss": 2.486894130706787,
      "step": 7620
    },
    {
      "epoch": 0.36295238095238097,
      "grad_norm": 0.03010830096900463,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4806289672851562,
      "step": 7622
    },
    {
      "epoch": 0.36304761904761906,
      "grad_norm": 0.028960665687918663,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4967689514160156,
      "step": 7624
    },
    {
      "epoch": 0.36314285714285716,
      "grad_norm": 0.029764987528324127,
      "learning_rate": 0.024000000208616257,
      "loss": 2.497102975845337,
      "step": 7626
    },
    {
      "epoch": 0.36323809523809525,
      "grad_norm": 0.029288968071341515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.478687286376953,
      "step": 7628
    },
    {
      "epoch": 0.36333333333333334,
      "grad_norm": 0.03399905934929848,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4739787578582764,
      "step": 7630
    },
    {
      "epoch": 0.36342857142857143,
      "grad_norm": 0.031617578119039536,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4638476371765137,
      "step": 7632
    },
    {
      "epoch": 0.3635238095238095,
      "grad_norm": 0.02862219698727131,
      "learning_rate": 0.024000000208616257,
      "loss": 2.467074394226074,
      "step": 7634
    },
    {
      "epoch": 0.3636190476190476,
      "grad_norm": 0.028064021840691566,
      "learning_rate": 0.024000000208616257,
      "loss": 2.451108455657959,
      "step": 7636
    },
    {
      "epoch": 0.3637142857142857,
      "grad_norm": 0.028613870963454247,
      "learning_rate": 0.024000000208616257,
      "loss": 2.479719877243042,
      "step": 7638
    },
    {
      "epoch": 0.3638095238095238,
      "grad_norm": 0.028845489025115967,
      "learning_rate": 0.024000000208616257,
      "loss": 2.51174259185791,
      "step": 7640
    },
    {
      "epoch": 0.3639047619047619,
      "grad_norm": 0.028858181089162827,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4570703506469727,
      "step": 7642
    },
    {
      "epoch": 0.364,
      "grad_norm": 0.02911129966378212,
      "learning_rate": 0.024000000208616257,
      "loss": 2.486337184906006,
      "step": 7644
    },
    {
      "epoch": 0.3640952380952381,
      "grad_norm": 0.029168998822569847,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4589905738830566,
      "step": 7646
    },
    {
      "epoch": 0.3641904761904762,
      "grad_norm": 0.029078731313347816,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4868040084838867,
      "step": 7648
    },
    {
      "epoch": 0.36428571428571427,
      "grad_norm": 0.0291838850826025,
      "learning_rate": 0.024000000208616257,
      "loss": 2.459883213043213,
      "step": 7650
    },
    {
      "epoch": 0.36438095238095236,
      "grad_norm": 0.029648853465914726,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4761171340942383,
      "step": 7652
    },
    {
      "epoch": 0.36447619047619045,
      "grad_norm": 0.030141551047563553,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4592690467834473,
      "step": 7654
    },
    {
      "epoch": 0.36457142857142855,
      "grad_norm": 0.02982792630791664,
      "learning_rate": 0.024000000208616257,
      "loss": 2.455930233001709,
      "step": 7656
    },
    {
      "epoch": 0.36466666666666664,
      "grad_norm": 0.031613193452358246,
      "learning_rate": 0.024000000208616257,
      "loss": 2.465869426727295,
      "step": 7658
    },
    {
      "epoch": 0.3647619047619048,
      "grad_norm": 0.03213758394122124,
      "learning_rate": 0.024000000208616257,
      "loss": 2.450643539428711,
      "step": 7660
    },
    {
      "epoch": 0.3648571428571429,
      "grad_norm": 0.02987268753349781,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4448184967041016,
      "step": 7662
    },
    {
      "epoch": 0.364952380952381,
      "grad_norm": 0.02863566391170025,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4726619720458984,
      "step": 7664
    },
    {
      "epoch": 0.36504761904761907,
      "grad_norm": 0.028811711817979813,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4858314990997314,
      "step": 7666
    },
    {
      "epoch": 0.36514285714285716,
      "grad_norm": 0.0283164381980896,
      "learning_rate": 0.024000000208616257,
      "loss": 2.446596145629883,
      "step": 7668
    },
    {
      "epoch": 0.36523809523809525,
      "grad_norm": 0.02935020625591278,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4648499488830566,
      "step": 7670
    },
    {
      "epoch": 0.36533333333333334,
      "grad_norm": 0.029865624383091927,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4571075439453125,
      "step": 7672
    },
    {
      "epoch": 0.36542857142857144,
      "grad_norm": 0.029210304841399193,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4717917442321777,
      "step": 7674
    },
    {
      "epoch": 0.36552380952380953,
      "grad_norm": 0.0304243341088295,
      "learning_rate": 0.024000000208616257,
      "loss": 2.496170997619629,
      "step": 7676
    },
    {
      "epoch": 0.3656190476190476,
      "grad_norm": 0.02939593605697155,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4544975757598877,
      "step": 7678
    },
    {
      "epoch": 0.3657142857142857,
      "grad_norm": 0.02932063117623329,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4812445640563965,
      "step": 7680
    },
    {
      "epoch": 0.3658095238095238,
      "grad_norm": 0.02930006943643093,
      "learning_rate": 0.024000000208616257,
      "loss": 2.476292371749878,
      "step": 7682
    },
    {
      "epoch": 0.3659047619047619,
      "grad_norm": 0.028567077592015266,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4851808547973633,
      "step": 7684
    },
    {
      "epoch": 0.366,
      "grad_norm": 0.02893061935901642,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4723830223083496,
      "step": 7686
    },
    {
      "epoch": 0.3660952380952381,
      "grad_norm": 0.03239154443144798,
      "learning_rate": 0.024000000208616257,
      "loss": 2.475691318511963,
      "step": 7688
    },
    {
      "epoch": 0.3661904761904762,
      "grad_norm": 0.03444777801632881,
      "learning_rate": 0.024000000208616257,
      "loss": 2.434414863586426,
      "step": 7690
    },
    {
      "epoch": 0.36628571428571427,
      "grad_norm": 0.03228279575705528,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4844565391540527,
      "step": 7692
    },
    {
      "epoch": 0.36638095238095236,
      "grad_norm": 0.034106962382793427,
      "learning_rate": 0.024000000208616257,
      "loss": 2.435267925262451,
      "step": 7694
    },
    {
      "epoch": 0.36647619047619046,
      "grad_norm": 0.02891671285033226,
      "learning_rate": 0.024000000208616257,
      "loss": 2.474501132965088,
      "step": 7696
    },
    {
      "epoch": 0.36657142857142855,
      "grad_norm": 0.03212910518050194,
      "learning_rate": 0.024000000208616257,
      "loss": 2.456634044647217,
      "step": 7698
    },
    {
      "epoch": 0.36666666666666664,
      "grad_norm": 0.03376142680644989,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4908218383789062,
      "step": 7700
    },
    {
      "epoch": 0.3667619047619048,
      "grad_norm": 0.030344713479280472,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4916605949401855,
      "step": 7702
    },
    {
      "epoch": 0.3668571428571429,
      "grad_norm": 0.02952144481241703,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4520771503448486,
      "step": 7704
    },
    {
      "epoch": 0.366952380952381,
      "grad_norm": 0.03057491034269333,
      "learning_rate": 0.024000000208616257,
      "loss": 2.479822874069214,
      "step": 7706
    },
    {
      "epoch": 0.36704761904761907,
      "grad_norm": 0.029973480850458145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4586353302001953,
      "step": 7708
    },
    {
      "epoch": 0.36714285714285716,
      "grad_norm": 0.030675597488880157,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4854512214660645,
      "step": 7710
    },
    {
      "epoch": 0.36723809523809525,
      "grad_norm": 0.029203616082668304,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4642021656036377,
      "step": 7712
    },
    {
      "epoch": 0.36733333333333335,
      "grad_norm": 0.029890678822994232,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4495439529418945,
      "step": 7714
    },
    {
      "epoch": 0.36742857142857144,
      "grad_norm": 0.029768139123916626,
      "learning_rate": 0.024000000208616257,
      "loss": 2.44974946975708,
      "step": 7716
    },
    {
      "epoch": 0.36752380952380953,
      "grad_norm": 0.03182975947856903,
      "learning_rate": 0.024000000208616257,
      "loss": 2.479536533355713,
      "step": 7718
    },
    {
      "epoch": 0.3676190476190476,
      "grad_norm": 0.030254388228058815,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4648499488830566,
      "step": 7720
    },
    {
      "epoch": 0.3677142857142857,
      "grad_norm": 0.03065762296319008,
      "learning_rate": 0.024000000208616257,
      "loss": 2.473808526992798,
      "step": 7722
    },
    {
      "epoch": 0.3678095238095238,
      "grad_norm": 0.03165201470255852,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4754252433776855,
      "step": 7724
    },
    {
      "epoch": 0.3679047619047619,
      "grad_norm": 0.029392611235380173,
      "learning_rate": 0.024000000208616257,
      "loss": 2.461433172225952,
      "step": 7726
    },
    {
      "epoch": 0.368,
      "grad_norm": 0.03300875052809715,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4809651374816895,
      "step": 7728
    },
    {
      "epoch": 0.3680952380952381,
      "grad_norm": 0.02925111912190914,
      "learning_rate": 0.024000000208616257,
      "loss": 2.458942413330078,
      "step": 7730
    },
    {
      "epoch": 0.3681904761904762,
      "grad_norm": 0.03153614327311516,
      "learning_rate": 0.024000000208616257,
      "loss": 2.462320566177368,
      "step": 7732
    },
    {
      "epoch": 0.36828571428571427,
      "grad_norm": 0.029245393350720406,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4462013244628906,
      "step": 7734
    },
    {
      "epoch": 0.36838095238095236,
      "grad_norm": 0.02996732108294964,
      "learning_rate": 0.024000000208616257,
      "loss": 2.476162910461426,
      "step": 7736
    },
    {
      "epoch": 0.36847619047619046,
      "grad_norm": 0.02812080644071102,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4331178665161133,
      "step": 7738
    },
    {
      "epoch": 0.36857142857142855,
      "grad_norm": 0.028248442336916924,
      "learning_rate": 0.024000000208616257,
      "loss": 2.423067569732666,
      "step": 7740
    },
    {
      "epoch": 0.36866666666666664,
      "grad_norm": 0.028244096785783768,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4537453651428223,
      "step": 7742
    },
    {
      "epoch": 0.36876190476190474,
      "grad_norm": 0.029661426320672035,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4783201217651367,
      "step": 7744
    },
    {
      "epoch": 0.3688571428571429,
      "grad_norm": 0.030969034880399704,
      "learning_rate": 0.024000000208616257,
      "loss": 2.46390438079834,
      "step": 7746
    },
    {
      "epoch": 0.368952380952381,
      "grad_norm": 0.030927559360861778,
      "learning_rate": 0.024000000208616257,
      "loss": 2.43117094039917,
      "step": 7748
    },
    {
      "epoch": 0.36904761904761907,
      "grad_norm": 0.02833808772265911,
      "learning_rate": 0.024000000208616257,
      "loss": 2.447091817855835,
      "step": 7750
    },
    {
      "epoch": 0.36914285714285716,
      "grad_norm": 0.02829948626458645,
      "learning_rate": 0.024000000208616257,
      "loss": 2.445448160171509,
      "step": 7752
    },
    {
      "epoch": 0.36923809523809525,
      "grad_norm": 0.029689228162169456,
      "learning_rate": 0.024000000208616257,
      "loss": 2.431213855743408,
      "step": 7754
    },
    {
      "epoch": 0.36933333333333335,
      "grad_norm": 0.02909223735332489,
      "learning_rate": 0.024000000208616257,
      "loss": 2.446207046508789,
      "step": 7756
    },
    {
      "epoch": 0.36942857142857144,
      "grad_norm": 0.029704894870519638,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4604501724243164,
      "step": 7758
    },
    {
      "epoch": 0.36952380952380953,
      "grad_norm": 0.03131707012653351,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4246201515197754,
      "step": 7760
    },
    {
      "epoch": 0.3696190476190476,
      "grad_norm": 0.03186832740902901,
      "learning_rate": 0.024000000208616257,
      "loss": 2.453251838684082,
      "step": 7762
    },
    {
      "epoch": 0.3697142857142857,
      "grad_norm": 0.029842182993888855,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4685559272766113,
      "step": 7764
    },
    {
      "epoch": 0.3698095238095238,
      "grad_norm": 0.028950653970241547,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4419355392456055,
      "step": 7766
    },
    {
      "epoch": 0.3699047619047619,
      "grad_norm": 0.0296019334346056,
      "learning_rate": 0.024000000208616257,
      "loss": 2.403416633605957,
      "step": 7768
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.029091089963912964,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4395499229431152,
      "step": 7770
    },
    {
      "epoch": 0.3700952380952381,
      "grad_norm": 0.029504654929041862,
      "learning_rate": 0.024000000208616257,
      "loss": 2.452195405960083,
      "step": 7772
    },
    {
      "epoch": 0.3701904761904762,
      "grad_norm": 0.028800232335925102,
      "learning_rate": 0.024000000208616257,
      "loss": 2.427269458770752,
      "step": 7774
    },
    {
      "epoch": 0.3702857142857143,
      "grad_norm": 0.028670575469732285,
      "learning_rate": 0.024000000208616257,
      "loss": 2.451760768890381,
      "step": 7776
    },
    {
      "epoch": 0.37038095238095237,
      "grad_norm": 0.029589397832751274,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4747424125671387,
      "step": 7778
    },
    {
      "epoch": 0.37047619047619046,
      "grad_norm": 0.029093921184539795,
      "learning_rate": 0.024000000208616257,
      "loss": 2.447688341140747,
      "step": 7780
    },
    {
      "epoch": 0.37057142857142855,
      "grad_norm": 0.032775137573480606,
      "learning_rate": 0.024000000208616257,
      "loss": 2.433868408203125,
      "step": 7782
    },
    {
      "epoch": 0.37066666666666664,
      "grad_norm": 0.031652603298425674,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4588804244995117,
      "step": 7784
    },
    {
      "epoch": 0.37076190476190474,
      "grad_norm": 0.03186587244272232,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4255242347717285,
      "step": 7786
    },
    {
      "epoch": 0.37085714285714283,
      "grad_norm": 0.028897961601614952,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4450230598449707,
      "step": 7788
    },
    {
      "epoch": 0.370952380952381,
      "grad_norm": 0.028758151456713676,
      "learning_rate": 0.024000000208616257,
      "loss": 2.436697006225586,
      "step": 7790
    },
    {
      "epoch": 0.37104761904761907,
      "grad_norm": 0.028884248808026314,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4664530754089355,
      "step": 7792
    },
    {
      "epoch": 0.37114285714285716,
      "grad_norm": 0.029837369918823242,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4731051921844482,
      "step": 7794
    },
    {
      "epoch": 0.37123809523809526,
      "grad_norm": 0.029959818348288536,
      "learning_rate": 0.024000000208616257,
      "loss": 2.5066590309143066,
      "step": 7796
    },
    {
      "epoch": 0.37133333333333335,
      "grad_norm": 0.0298271756619215,
      "learning_rate": 0.024000000208616257,
      "loss": 2.455813407897949,
      "step": 7798
    },
    {
      "epoch": 0.37142857142857144,
      "grad_norm": 0.030976271256804466,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4044947624206543,
      "step": 7800
    },
    {
      "epoch": 0.37152380952380953,
      "grad_norm": 0.030658384785056114,
      "learning_rate": 0.024000000208616257,
      "loss": 2.460048198699951,
      "step": 7802
    },
    {
      "epoch": 0.3716190476190476,
      "grad_norm": 0.030296294018626213,
      "learning_rate": 0.024000000208616257,
      "loss": 2.470064163208008,
      "step": 7804
    },
    {
      "epoch": 0.3717142857142857,
      "grad_norm": 0.03031502477824688,
      "learning_rate": 0.024000000208616257,
      "loss": 2.433128595352173,
      "step": 7806
    },
    {
      "epoch": 0.3718095238095238,
      "grad_norm": 0.029653269797563553,
      "learning_rate": 0.024000000208616257,
      "loss": 2.484334945678711,
      "step": 7808
    },
    {
      "epoch": 0.3719047619047619,
      "grad_norm": 0.03042561002075672,
      "learning_rate": 0.024000000208616257,
      "loss": 2.443537712097168,
      "step": 7810
    },
    {
      "epoch": 0.372,
      "grad_norm": 0.029283063486218452,
      "learning_rate": 0.024000000208616257,
      "loss": 2.459822177886963,
      "step": 7812
    },
    {
      "epoch": 0.3720952380952381,
      "grad_norm": 0.028847619891166687,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4484548568725586,
      "step": 7814
    },
    {
      "epoch": 0.3721904761904762,
      "grad_norm": 0.028816167265176773,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4571311473846436,
      "step": 7816
    },
    {
      "epoch": 0.3722857142857143,
      "grad_norm": 0.03056853823363781,
      "learning_rate": 0.024000000208616257,
      "loss": 2.460139751434326,
      "step": 7818
    },
    {
      "epoch": 0.37238095238095237,
      "grad_norm": 0.03138864412903786,
      "learning_rate": 0.024000000208616257,
      "loss": 2.425081253051758,
      "step": 7820
    },
    {
      "epoch": 0.37247619047619046,
      "grad_norm": 0.029464127495884895,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4527788162231445,
      "step": 7822
    },
    {
      "epoch": 0.37257142857142855,
      "grad_norm": 0.030216645449399948,
      "learning_rate": 0.024000000208616257,
      "loss": 2.436513662338257,
      "step": 7824
    },
    {
      "epoch": 0.37266666666666665,
      "grad_norm": 0.028864718973636627,
      "learning_rate": 0.024000000208616257,
      "loss": 2.423444986343384,
      "step": 7826
    },
    {
      "epoch": 0.37276190476190474,
      "grad_norm": 0.031557969748973846,
      "learning_rate": 0.024000000208616257,
      "loss": 2.458949327468872,
      "step": 7828
    },
    {
      "epoch": 0.37285714285714283,
      "grad_norm": 0.03171972557902336,
      "learning_rate": 0.024000000208616257,
      "loss": 2.452648162841797,
      "step": 7830
    },
    {
      "epoch": 0.372952380952381,
      "grad_norm": 0.03247501328587532,
      "learning_rate": 0.024000000208616257,
      "loss": 2.432769536972046,
      "step": 7832
    },
    {
      "epoch": 0.3730476190476191,
      "grad_norm": 0.03633379191160202,
      "learning_rate": 0.024000000208616257,
      "loss": 2.420285701751709,
      "step": 7834
    },
    {
      "epoch": 0.37314285714285716,
      "grad_norm": 0.036557771265506744,
      "learning_rate": 0.024000000208616257,
      "loss": 2.441042900085449,
      "step": 7836
    },
    {
      "epoch": 0.37323809523809526,
      "grad_norm": 0.03071487322449684,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4126367568969727,
      "step": 7838
    },
    {
      "epoch": 0.37333333333333335,
      "grad_norm": 0.02945101074874401,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4435384273529053,
      "step": 7840
    },
    {
      "epoch": 0.37342857142857144,
      "grad_norm": 0.0289284810423851,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4197590351104736,
      "step": 7842
    },
    {
      "epoch": 0.37352380952380954,
      "grad_norm": 0.028454801067709923,
      "learning_rate": 0.024000000208616257,
      "loss": 2.440265655517578,
      "step": 7844
    },
    {
      "epoch": 0.37361904761904763,
      "grad_norm": 0.03025783598423004,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4348204135894775,
      "step": 7846
    },
    {
      "epoch": 0.3737142857142857,
      "grad_norm": 0.03496683016419411,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4629476070404053,
      "step": 7848
    },
    {
      "epoch": 0.3738095238095238,
      "grad_norm": 0.030315641313791275,
      "learning_rate": 0.024000000208616257,
      "loss": 2.44124698638916,
      "step": 7850
    },
    {
      "epoch": 0.3739047619047619,
      "grad_norm": 0.0288659930229187,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4049103260040283,
      "step": 7852
    },
    {
      "epoch": 0.374,
      "grad_norm": 0.029200775548815727,
      "learning_rate": 0.024000000208616257,
      "loss": 2.43748140335083,
      "step": 7854
    },
    {
      "epoch": 0.3740952380952381,
      "grad_norm": 0.028051774948835373,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4556164741516113,
      "step": 7856
    },
    {
      "epoch": 0.3741904761904762,
      "grad_norm": 0.028785381466150284,
      "learning_rate": 0.024000000208616257,
      "loss": 2.438769817352295,
      "step": 7858
    },
    {
      "epoch": 0.3742857142857143,
      "grad_norm": 0.02994595468044281,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4150390625,
      "step": 7860
    },
    {
      "epoch": 0.37438095238095237,
      "grad_norm": 0.030494481325149536,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4297571182250977,
      "step": 7862
    },
    {
      "epoch": 0.37447619047619046,
      "grad_norm": 0.030371379107236862,
      "learning_rate": 0.024000000208616257,
      "loss": 2.41623592376709,
      "step": 7864
    },
    {
      "epoch": 0.37457142857142856,
      "grad_norm": 0.028989948332309723,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384580612182617,
      "step": 7866
    },
    {
      "epoch": 0.37466666666666665,
      "grad_norm": 0.02777065522968769,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4850404262542725,
      "step": 7868
    },
    {
      "epoch": 0.37476190476190474,
      "grad_norm": 0.027975386008620262,
      "learning_rate": 0.024000000208616257,
      "loss": 2.439223289489746,
      "step": 7870
    },
    {
      "epoch": 0.37485714285714283,
      "grad_norm": 0.028820427134633064,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4072394371032715,
      "step": 7872
    },
    {
      "epoch": 0.3749523809523809,
      "grad_norm": 0.028393246233463287,
      "learning_rate": 0.024000000208616257,
      "loss": 2.457364559173584,
      "step": 7874
    },
    {
      "epoch": 0.3750476190476191,
      "grad_norm": 0.02920963056385517,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4492745399475098,
      "step": 7876
    },
    {
      "epoch": 0.37514285714285717,
      "grad_norm": 0.028912536799907684,
      "learning_rate": 0.024000000208616257,
      "loss": 2.421586036682129,
      "step": 7878
    },
    {
      "epoch": 0.37523809523809526,
      "grad_norm": 0.0279832910746336,
      "learning_rate": 0.024000000208616257,
      "loss": 2.469599962234497,
      "step": 7880
    },
    {
      "epoch": 0.37533333333333335,
      "grad_norm": 0.02839517593383789,
      "learning_rate": 0.024000000208616257,
      "loss": 2.424380302429199,
      "step": 7882
    },
    {
      "epoch": 0.37542857142857144,
      "grad_norm": 0.028263872489333153,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4414596557617188,
      "step": 7884
    },
    {
      "epoch": 0.37552380952380954,
      "grad_norm": 0.02818380296230316,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4414939880371094,
      "step": 7886
    },
    {
      "epoch": 0.37561904761904763,
      "grad_norm": 0.02882547676563263,
      "learning_rate": 0.024000000208616257,
      "loss": 2.443189859390259,
      "step": 7888
    },
    {
      "epoch": 0.3757142857142857,
      "grad_norm": 0.029784325510263443,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4405150413513184,
      "step": 7890
    },
    {
      "epoch": 0.3758095238095238,
      "grad_norm": 0.03142411261796951,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4202585220336914,
      "step": 7892
    },
    {
      "epoch": 0.3759047619047619,
      "grad_norm": 0.029436852782964706,
      "learning_rate": 0.024000000208616257,
      "loss": 2.443398952484131,
      "step": 7894
    },
    {
      "epoch": 0.376,
      "grad_norm": 0.028339795768260956,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4409894943237305,
      "step": 7896
    },
    {
      "epoch": 0.3760952380952381,
      "grad_norm": 0.0277994554489851,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4607491493225098,
      "step": 7898
    },
    {
      "epoch": 0.3761904761904762,
      "grad_norm": 0.028062719851732254,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4404945373535156,
      "step": 7900
    },
    {
      "epoch": 0.3762857142857143,
      "grad_norm": 0.029599038884043694,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4332189559936523,
      "step": 7902
    },
    {
      "epoch": 0.37638095238095237,
      "grad_norm": 0.029335658997297287,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4495372772216797,
      "step": 7904
    },
    {
      "epoch": 0.37647619047619046,
      "grad_norm": 0.027667760848999023,
      "learning_rate": 0.024000000208616257,
      "loss": 2.410395622253418,
      "step": 7906
    },
    {
      "epoch": 0.37657142857142856,
      "grad_norm": 0.02912190370261669,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4394338130950928,
      "step": 7908
    },
    {
      "epoch": 0.37666666666666665,
      "grad_norm": 0.02933194488286972,
      "learning_rate": 0.024000000208616257,
      "loss": 2.427926540374756,
      "step": 7910
    },
    {
      "epoch": 0.37676190476190474,
      "grad_norm": 0.027715632691979408,
      "learning_rate": 0.024000000208616257,
      "loss": 2.399934768676758,
      "step": 7912
    },
    {
      "epoch": 0.37685714285714284,
      "grad_norm": 0.028720274567604065,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4178452491760254,
      "step": 7914
    },
    {
      "epoch": 0.3769523809523809,
      "grad_norm": 0.028340080752968788,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4195823669433594,
      "step": 7916
    },
    {
      "epoch": 0.377047619047619,
      "grad_norm": 0.029521144926548004,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4333229064941406,
      "step": 7918
    },
    {
      "epoch": 0.37714285714285717,
      "grad_norm": 0.029114585369825363,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4116251468658447,
      "step": 7920
    },
    {
      "epoch": 0.37723809523809526,
      "grad_norm": 0.0309908427298069,
      "learning_rate": 0.024000000208616257,
      "loss": 2.454404830932617,
      "step": 7922
    },
    {
      "epoch": 0.37733333333333335,
      "grad_norm": 0.030011024326086044,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4064207077026367,
      "step": 7924
    },
    {
      "epoch": 0.37742857142857145,
      "grad_norm": 0.029047660529613495,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4633049964904785,
      "step": 7926
    },
    {
      "epoch": 0.37752380952380954,
      "grad_norm": 0.028000539168715477,
      "learning_rate": 0.024000000208616257,
      "loss": 2.452277183532715,
      "step": 7928
    },
    {
      "epoch": 0.37761904761904763,
      "grad_norm": 0.028581589460372925,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392200469970703,
      "step": 7930
    },
    {
      "epoch": 0.3777142857142857,
      "grad_norm": 0.02968982793390751,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4006316661834717,
      "step": 7932
    },
    {
      "epoch": 0.3778095238095238,
      "grad_norm": 0.02924474887549877,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3983373641967773,
      "step": 7934
    },
    {
      "epoch": 0.3779047619047619,
      "grad_norm": 0.028637468814849854,
      "learning_rate": 0.024000000208616257,
      "loss": 2.439976692199707,
      "step": 7936
    },
    {
      "epoch": 0.378,
      "grad_norm": 0.03025992028415203,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4477944374084473,
      "step": 7938
    },
    {
      "epoch": 0.3780952380952381,
      "grad_norm": 0.028772177174687386,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4352502822875977,
      "step": 7940
    },
    {
      "epoch": 0.3781904761904762,
      "grad_norm": 0.028234926983714104,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4501125812530518,
      "step": 7942
    },
    {
      "epoch": 0.3782857142857143,
      "grad_norm": 0.03026161901652813,
      "learning_rate": 0.024000000208616257,
      "loss": 2.434540271759033,
      "step": 7944
    },
    {
      "epoch": 0.3783809523809524,
      "grad_norm": 0.028540410101413727,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4307427406311035,
      "step": 7946
    },
    {
      "epoch": 0.37847619047619047,
      "grad_norm": 0.029920483008027077,
      "learning_rate": 0.024000000208616257,
      "loss": 2.406980037689209,
      "step": 7948
    },
    {
      "epoch": 0.37857142857142856,
      "grad_norm": 0.029097573831677437,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4063053131103516,
      "step": 7950
    },
    {
      "epoch": 0.37866666666666665,
      "grad_norm": 0.027972117066383362,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4018518924713135,
      "step": 7952
    },
    {
      "epoch": 0.37876190476190474,
      "grad_norm": 0.02733480930328369,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3996734619140625,
      "step": 7954
    },
    {
      "epoch": 0.37885714285714284,
      "grad_norm": 0.028437677770853043,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3846287727355957,
      "step": 7956
    },
    {
      "epoch": 0.37895238095238093,
      "grad_norm": 0.029251739382743835,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4032130241394043,
      "step": 7958
    },
    {
      "epoch": 0.379047619047619,
      "grad_norm": 0.03025747649371624,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4173378944396973,
      "step": 7960
    },
    {
      "epoch": 0.37914285714285717,
      "grad_norm": 0.028140155598521233,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3998188972473145,
      "step": 7962
    },
    {
      "epoch": 0.37923809523809526,
      "grad_norm": 0.028313225135207176,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4070193767547607,
      "step": 7964
    },
    {
      "epoch": 0.37933333333333336,
      "grad_norm": 0.02984193153679371,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4260950088500977,
      "step": 7966
    },
    {
      "epoch": 0.37942857142857145,
      "grad_norm": 0.029521387070417404,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4084835052490234,
      "step": 7968
    },
    {
      "epoch": 0.37952380952380954,
      "grad_norm": 0.028538821265101433,
      "learning_rate": 0.024000000208616257,
      "loss": 2.443000316619873,
      "step": 7970
    },
    {
      "epoch": 0.37961904761904763,
      "grad_norm": 0.02874407172203064,
      "learning_rate": 0.024000000208616257,
      "loss": 2.405698537826538,
      "step": 7972
    },
    {
      "epoch": 0.3797142857142857,
      "grad_norm": 0.03067825548350811,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4192276000976562,
      "step": 7974
    },
    {
      "epoch": 0.3798095238095238,
      "grad_norm": 0.02825484797358513,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3756394386291504,
      "step": 7976
    },
    {
      "epoch": 0.3799047619047619,
      "grad_norm": 0.02877754345536232,
      "learning_rate": 0.024000000208616257,
      "loss": 2.371441602706909,
      "step": 7978
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.027960767969489098,
      "learning_rate": 0.024000000208616257,
      "loss": 2.445590019226074,
      "step": 7980
    },
    {
      "epoch": 0.3800952380952381,
      "grad_norm": 0.028159404173493385,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3857991695404053,
      "step": 7982
    },
    {
      "epoch": 0.3801904761904762,
      "grad_norm": 0.02837482839822769,
      "learning_rate": 0.024000000208616257,
      "loss": 2.423754930496216,
      "step": 7984
    },
    {
      "epoch": 0.3802857142857143,
      "grad_norm": 0.03342810645699501,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3966898918151855,
      "step": 7986
    },
    {
      "epoch": 0.3803809523809524,
      "grad_norm": 0.03137626126408577,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382143020629883,
      "step": 7988
    },
    {
      "epoch": 0.38047619047619047,
      "grad_norm": 0.02733631245791912,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4120984077453613,
      "step": 7990
    },
    {
      "epoch": 0.38057142857142856,
      "grad_norm": 0.02795199304819107,
      "learning_rate": 0.024000000208616257,
      "loss": 2.406386375427246,
      "step": 7992
    },
    {
      "epoch": 0.38066666666666665,
      "grad_norm": 0.029779259115457535,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4212799072265625,
      "step": 7994
    },
    {
      "epoch": 0.38076190476190475,
      "grad_norm": 0.028144316747784615,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3986973762512207,
      "step": 7996
    },
    {
      "epoch": 0.38085714285714284,
      "grad_norm": 0.03164883330464363,
      "learning_rate": 0.024000000208616257,
      "loss": 2.407953977584839,
      "step": 7998
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.029638055711984634,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4183053970336914,
      "step": 8000
    },
    {
      "epoch": 0.381047619047619,
      "grad_norm": 0.030216258019208908,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4385006427764893,
      "step": 8002
    },
    {
      "epoch": 0.3811428571428571,
      "grad_norm": 0.03007127158343792,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4138636589050293,
      "step": 8004
    },
    {
      "epoch": 0.38123809523809526,
      "grad_norm": 0.029564345255494118,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4123446941375732,
      "step": 8006
    },
    {
      "epoch": 0.38133333333333336,
      "grad_norm": 0.028302181512117386,
      "learning_rate": 0.024000000208616257,
      "loss": 2.436107635498047,
      "step": 8008
    },
    {
      "epoch": 0.38142857142857145,
      "grad_norm": 0.03255651891231537,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4111504554748535,
      "step": 8010
    },
    {
      "epoch": 0.38152380952380954,
      "grad_norm": 0.030574722215533257,
      "learning_rate": 0.024000000208616257,
      "loss": 2.420630931854248,
      "step": 8012
    },
    {
      "epoch": 0.38161904761904764,
      "grad_norm": 0.037482671439647675,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4222002029418945,
      "step": 8014
    },
    {
      "epoch": 0.38171428571428573,
      "grad_norm": 0.04023033007979393,
      "learning_rate": 0.024000000208616257,
      "loss": 2.403219223022461,
      "step": 8016
    },
    {
      "epoch": 0.3818095238095238,
      "grad_norm": 0.03250053524971008,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4136571884155273,
      "step": 8018
    },
    {
      "epoch": 0.3819047619047619,
      "grad_norm": 0.02878623828291893,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4211456775665283,
      "step": 8020
    },
    {
      "epoch": 0.382,
      "grad_norm": 0.029791178181767464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4281234741210938,
      "step": 8022
    },
    {
      "epoch": 0.3820952380952381,
      "grad_norm": 0.02939440682530403,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4083919525146484,
      "step": 8024
    },
    {
      "epoch": 0.3821904761904762,
      "grad_norm": 0.027963915839791298,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4300785064697266,
      "step": 8026
    },
    {
      "epoch": 0.3822857142857143,
      "grad_norm": 0.029462475329637527,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3846471309661865,
      "step": 8028
    },
    {
      "epoch": 0.3823809523809524,
      "grad_norm": 0.028075769543647766,
      "learning_rate": 0.024000000208616257,
      "loss": 2.415012836456299,
      "step": 8030
    },
    {
      "epoch": 0.38247619047619047,
      "grad_norm": 0.028231319040060043,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3944473266601562,
      "step": 8032
    },
    {
      "epoch": 0.38257142857142856,
      "grad_norm": 0.028056960552930832,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4207353591918945,
      "step": 8034
    },
    {
      "epoch": 0.38266666666666665,
      "grad_norm": 0.02782498300075531,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4154305458068848,
      "step": 8036
    },
    {
      "epoch": 0.38276190476190475,
      "grad_norm": 0.027863286435604095,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4337856769561768,
      "step": 8038
    },
    {
      "epoch": 0.38285714285714284,
      "grad_norm": 0.031806278973817825,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3991880416870117,
      "step": 8040
    },
    {
      "epoch": 0.38295238095238093,
      "grad_norm": 0.03415636345744133,
      "learning_rate": 0.024000000208616257,
      "loss": 2.417142391204834,
      "step": 8042
    },
    {
      "epoch": 0.383047619047619,
      "grad_norm": 0.028553329408168793,
      "learning_rate": 0.024000000208616257,
      "loss": 2.417614698410034,
      "step": 8044
    },
    {
      "epoch": 0.3831428571428571,
      "grad_norm": 0.028021221980452538,
      "learning_rate": 0.024000000208616257,
      "loss": 2.399876594543457,
      "step": 8046
    },
    {
      "epoch": 0.3832380952380952,
      "grad_norm": 0.028488734737038612,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3898541927337646,
      "step": 8048
    },
    {
      "epoch": 0.38333333333333336,
      "grad_norm": 0.028799377381801605,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4176101684570312,
      "step": 8050
    },
    {
      "epoch": 0.38342857142857145,
      "grad_norm": 0.030246607959270477,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384399652481079,
      "step": 8052
    },
    {
      "epoch": 0.38352380952380954,
      "grad_norm": 0.035926271229982376,
      "learning_rate": 0.024000000208616257,
      "loss": 2.391172409057617,
      "step": 8054
    },
    {
      "epoch": 0.38361904761904764,
      "grad_norm": 0.03170817345380783,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401005744934082,
      "step": 8056
    },
    {
      "epoch": 0.38371428571428573,
      "grad_norm": 0.03140395134687424,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4363880157470703,
      "step": 8058
    },
    {
      "epoch": 0.3838095238095238,
      "grad_norm": 0.030085716396570206,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4224977493286133,
      "step": 8060
    },
    {
      "epoch": 0.3839047619047619,
      "grad_norm": 0.028978794813156128,
      "learning_rate": 0.024000000208616257,
      "loss": 2.360154628753662,
      "step": 8062
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.029008228331804276,
      "learning_rate": 0.024000000208616257,
      "loss": 2.424927234649658,
      "step": 8064
    },
    {
      "epoch": 0.3840952380952381,
      "grad_norm": 0.028758998960256577,
      "learning_rate": 0.024000000208616257,
      "loss": 2.393003463745117,
      "step": 8066
    },
    {
      "epoch": 0.3841904761904762,
      "grad_norm": 0.028207242488861084,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3995838165283203,
      "step": 8068
    },
    {
      "epoch": 0.3842857142857143,
      "grad_norm": 0.0287872776389122,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4063005447387695,
      "step": 8070
    },
    {
      "epoch": 0.3843809523809524,
      "grad_norm": 0.02903800830245018,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3890509605407715,
      "step": 8072
    },
    {
      "epoch": 0.38447619047619047,
      "grad_norm": 0.02937864512205124,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4275288581848145,
      "step": 8074
    },
    {
      "epoch": 0.38457142857142856,
      "grad_norm": 0.030724700540304184,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3872509002685547,
      "step": 8076
    },
    {
      "epoch": 0.38466666666666666,
      "grad_norm": 0.02854529581964016,
      "learning_rate": 0.024000000208616257,
      "loss": 2.402254104614258,
      "step": 8078
    },
    {
      "epoch": 0.38476190476190475,
      "grad_norm": 0.028767447918653488,
      "learning_rate": 0.024000000208616257,
      "loss": 2.391077756881714,
      "step": 8080
    },
    {
      "epoch": 0.38485714285714284,
      "grad_norm": 0.027745762839913368,
      "learning_rate": 0.024000000208616257,
      "loss": 2.406521797180176,
      "step": 8082
    },
    {
      "epoch": 0.38495238095238093,
      "grad_norm": 0.028376711532473564,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4107666015625,
      "step": 8084
    },
    {
      "epoch": 0.385047619047619,
      "grad_norm": 0.027647122740745544,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4156739711761475,
      "step": 8086
    },
    {
      "epoch": 0.3851428571428571,
      "grad_norm": 0.03119072876870632,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4296696186065674,
      "step": 8088
    },
    {
      "epoch": 0.3852380952380952,
      "grad_norm": 0.027812017127871513,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3683009147644043,
      "step": 8090
    },
    {
      "epoch": 0.38533333333333336,
      "grad_norm": 0.028261560946702957,
      "learning_rate": 0.024000000208616257,
      "loss": 2.413783550262451,
      "step": 8092
    },
    {
      "epoch": 0.38542857142857145,
      "grad_norm": 0.027989903464913368,
      "learning_rate": 0.024000000208616257,
      "loss": 2.426837205886841,
      "step": 8094
    },
    {
      "epoch": 0.38552380952380955,
      "grad_norm": 0.02883002534508705,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3937430381774902,
      "step": 8096
    },
    {
      "epoch": 0.38561904761904764,
      "grad_norm": 0.0283648744225502,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3749618530273438,
      "step": 8098
    },
    {
      "epoch": 0.38571428571428573,
      "grad_norm": 0.0314413458108902,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4014320373535156,
      "step": 8100
    },
    {
      "epoch": 0.3858095238095238,
      "grad_norm": 0.031130686402320862,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4279770851135254,
      "step": 8102
    },
    {
      "epoch": 0.3859047619047619,
      "grad_norm": 0.03453836590051651,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3890111446380615,
      "step": 8104
    },
    {
      "epoch": 0.386,
      "grad_norm": 0.03142851963639259,
      "learning_rate": 0.024000000208616257,
      "loss": 2.408669948577881,
      "step": 8106
    },
    {
      "epoch": 0.3860952380952381,
      "grad_norm": 0.032724298536777496,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385160446166992,
      "step": 8108
    },
    {
      "epoch": 0.3861904761904762,
      "grad_norm": 0.028042089194059372,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3673155307769775,
      "step": 8110
    },
    {
      "epoch": 0.3862857142857143,
      "grad_norm": 0.02864069864153862,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4150021076202393,
      "step": 8112
    },
    {
      "epoch": 0.3863809523809524,
      "grad_norm": 0.02857063151896,
      "learning_rate": 0.024000000208616257,
      "loss": 2.406463623046875,
      "step": 8114
    },
    {
      "epoch": 0.3864761904761905,
      "grad_norm": 0.030241133645176888,
      "learning_rate": 0.024000000208616257,
      "loss": 2.420328140258789,
      "step": 8116
    },
    {
      "epoch": 0.38657142857142857,
      "grad_norm": 0.02935524843633175,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3876240253448486,
      "step": 8118
    },
    {
      "epoch": 0.38666666666666666,
      "grad_norm": 0.028986966237425804,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4159841537475586,
      "step": 8120
    },
    {
      "epoch": 0.38676190476190475,
      "grad_norm": 0.030956147238612175,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4029667377471924,
      "step": 8122
    },
    {
      "epoch": 0.38685714285714284,
      "grad_norm": 0.027675064280629158,
      "learning_rate": 0.024000000208616257,
      "loss": 2.402059555053711,
      "step": 8124
    },
    {
      "epoch": 0.38695238095238094,
      "grad_norm": 0.027650609612464905,
      "learning_rate": 0.024000000208616257,
      "loss": 2.403700351715088,
      "step": 8126
    },
    {
      "epoch": 0.38704761904761903,
      "grad_norm": 0.02726244367659092,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3871469497680664,
      "step": 8128
    },
    {
      "epoch": 0.3871428571428571,
      "grad_norm": 0.029704295098781586,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3965277671813965,
      "step": 8130
    },
    {
      "epoch": 0.3872380952380952,
      "grad_norm": 0.026865532621741295,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396368980407715,
      "step": 8132
    },
    {
      "epoch": 0.3873333333333333,
      "grad_norm": 0.027943462133407593,
      "learning_rate": 0.024000000208616257,
      "loss": 2.375339984893799,
      "step": 8134
    },
    {
      "epoch": 0.38742857142857146,
      "grad_norm": 0.028090450912714005,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3947372436523438,
      "step": 8136
    },
    {
      "epoch": 0.38752380952380955,
      "grad_norm": 0.02923293225467205,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4054272174835205,
      "step": 8138
    },
    {
      "epoch": 0.38761904761904764,
      "grad_norm": 0.027735648676753044,
      "learning_rate": 0.024000000208616257,
      "loss": 2.381399154663086,
      "step": 8140
    },
    {
      "epoch": 0.38771428571428573,
      "grad_norm": 0.02893795818090439,
      "learning_rate": 0.024000000208616257,
      "loss": 2.412998676300049,
      "step": 8142
    },
    {
      "epoch": 0.3878095238095238,
      "grad_norm": 0.02903169021010399,
      "learning_rate": 0.024000000208616257,
      "loss": 2.440553903579712,
      "step": 8144
    },
    {
      "epoch": 0.3879047619047619,
      "grad_norm": 0.029780875891447067,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3812618255615234,
      "step": 8146
    },
    {
      "epoch": 0.388,
      "grad_norm": 0.031076887622475624,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3950014114379883,
      "step": 8148
    },
    {
      "epoch": 0.3880952380952381,
      "grad_norm": 0.030158033594489098,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390374183654785,
      "step": 8150
    },
    {
      "epoch": 0.3881904761904762,
      "grad_norm": 0.03248704597353935,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3606462478637695,
      "step": 8152
    },
    {
      "epoch": 0.3882857142857143,
      "grad_norm": 0.030936649069190025,
      "learning_rate": 0.024000000208616257,
      "loss": 2.421095132827759,
      "step": 8154
    },
    {
      "epoch": 0.3883809523809524,
      "grad_norm": 0.02911587990820408,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382349729537964,
      "step": 8156
    },
    {
      "epoch": 0.3884761904761905,
      "grad_norm": 0.02945566549897194,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3850114345550537,
      "step": 8158
    },
    {
      "epoch": 0.38857142857142857,
      "grad_norm": 0.028396569192409515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4073710441589355,
      "step": 8160
    },
    {
      "epoch": 0.38866666666666666,
      "grad_norm": 0.028683774173259735,
      "learning_rate": 0.024000000208616257,
      "loss": 2.393578052520752,
      "step": 8162
    },
    {
      "epoch": 0.38876190476190475,
      "grad_norm": 0.02782920002937317,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3586039543151855,
      "step": 8164
    },
    {
      "epoch": 0.38885714285714285,
      "grad_norm": 0.02891562320291996,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4334371089935303,
      "step": 8166
    },
    {
      "epoch": 0.38895238095238094,
      "grad_norm": 0.02836264856159687,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392763137817383,
      "step": 8168
    },
    {
      "epoch": 0.38904761904761903,
      "grad_norm": 0.02778981812298298,
      "learning_rate": 0.024000000208616257,
      "loss": 2.439849853515625,
      "step": 8170
    },
    {
      "epoch": 0.3891428571428571,
      "grad_norm": 0.02963663451373577,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4108645915985107,
      "step": 8172
    },
    {
      "epoch": 0.3892380952380952,
      "grad_norm": 0.02889464981853962,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4064290523529053,
      "step": 8174
    },
    {
      "epoch": 0.3893333333333333,
      "grad_norm": 0.029959242790937424,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3923683166503906,
      "step": 8176
    },
    {
      "epoch": 0.3894285714285714,
      "grad_norm": 0.02911071479320526,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3882713317871094,
      "step": 8178
    },
    {
      "epoch": 0.38952380952380955,
      "grad_norm": 0.027831431478261948,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3817667961120605,
      "step": 8180
    },
    {
      "epoch": 0.38961904761904764,
      "grad_norm": 0.028713926672935486,
      "learning_rate": 0.024000000208616257,
      "loss": 2.368633985519409,
      "step": 8182
    },
    {
      "epoch": 0.38971428571428574,
      "grad_norm": 0.027670959010720253,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3836326599121094,
      "step": 8184
    },
    {
      "epoch": 0.38980952380952383,
      "grad_norm": 0.030387623235583305,
      "learning_rate": 0.024000000208616257,
      "loss": 2.40157151222229,
      "step": 8186
    },
    {
      "epoch": 0.3899047619047619,
      "grad_norm": 0.03013112023472786,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392521381378174,
      "step": 8188
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.02917291410267353,
      "learning_rate": 0.024000000208616257,
      "loss": 2.395615577697754,
      "step": 8190
    },
    {
      "epoch": 0.3900952380952381,
      "grad_norm": 0.0393579825758934,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3796324729919434,
      "step": 8192
    },
    {
      "epoch": 0.3901904761904762,
      "grad_norm": 0.03853415697813034,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3796048164367676,
      "step": 8194
    },
    {
      "epoch": 0.3902857142857143,
      "grad_norm": 0.040121495723724365,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4220833778381348,
      "step": 8196
    },
    {
      "epoch": 0.3903809523809524,
      "grad_norm": 0.03342856094241142,
      "learning_rate": 0.024000000208616257,
      "loss": 2.40506649017334,
      "step": 8198
    },
    {
      "epoch": 0.3904761904761905,
      "grad_norm": 0.02867874875664711,
      "learning_rate": 0.024000000208616257,
      "loss": 2.430418014526367,
      "step": 8200
    },
    {
      "epoch": 0.39057142857142857,
      "grad_norm": 0.030486011877655983,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3935654163360596,
      "step": 8202
    },
    {
      "epoch": 0.39066666666666666,
      "grad_norm": 0.028980495408177376,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4220356941223145,
      "step": 8204
    },
    {
      "epoch": 0.39076190476190475,
      "grad_norm": 0.02748771570622921,
      "learning_rate": 0.024000000208616257,
      "loss": 2.399390697479248,
      "step": 8206
    },
    {
      "epoch": 0.39085714285714285,
      "grad_norm": 0.029958028346300125,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4119906425476074,
      "step": 8208
    },
    {
      "epoch": 0.39095238095238094,
      "grad_norm": 0.029549023136496544,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3912391662597656,
      "step": 8210
    },
    {
      "epoch": 0.39104761904761903,
      "grad_norm": 0.02851077914237976,
      "learning_rate": 0.024000000208616257,
      "loss": 2.378653049468994,
      "step": 8212
    },
    {
      "epoch": 0.3911428571428571,
      "grad_norm": 0.027724167332053185,
      "learning_rate": 0.024000000208616257,
      "loss": 2.414029598236084,
      "step": 8214
    },
    {
      "epoch": 0.3912380952380952,
      "grad_norm": 0.030015980824828148,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3842036724090576,
      "step": 8216
    },
    {
      "epoch": 0.3913333333333333,
      "grad_norm": 0.02857678383588791,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3494200706481934,
      "step": 8218
    },
    {
      "epoch": 0.3914285714285714,
      "grad_norm": 0.027653401717543602,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4120776653289795,
      "step": 8220
    },
    {
      "epoch": 0.3915238095238095,
      "grad_norm": 0.02837136760354042,
      "learning_rate": 0.024000000208616257,
      "loss": 2.410022735595703,
      "step": 8222
    },
    {
      "epoch": 0.39161904761904764,
      "grad_norm": 0.03085894137620926,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38316011428833,
      "step": 8224
    },
    {
      "epoch": 0.39171428571428574,
      "grad_norm": 0.028162896633148193,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3826937675476074,
      "step": 8226
    },
    {
      "epoch": 0.39180952380952383,
      "grad_norm": 0.027698319405317307,
      "learning_rate": 0.024000000208616257,
      "loss": 2.425629138946533,
      "step": 8228
    },
    {
      "epoch": 0.3919047619047619,
      "grad_norm": 0.028594540432095528,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4014925956726074,
      "step": 8230
    },
    {
      "epoch": 0.392,
      "grad_norm": 0.027523184195160866,
      "learning_rate": 0.024000000208616257,
      "loss": 2.40240478515625,
      "step": 8232
    },
    {
      "epoch": 0.3920952380952381,
      "grad_norm": 0.02799816243350506,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382744789123535,
      "step": 8234
    },
    {
      "epoch": 0.3921904761904762,
      "grad_norm": 0.028344588354229927,
      "learning_rate": 0.024000000208616257,
      "loss": 2.366563320159912,
      "step": 8236
    },
    {
      "epoch": 0.3922857142857143,
      "grad_norm": 0.03379670903086662,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401797294616699,
      "step": 8238
    },
    {
      "epoch": 0.3923809523809524,
      "grad_norm": 0.029196081683039665,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4031734466552734,
      "step": 8240
    },
    {
      "epoch": 0.3924761904761905,
      "grad_norm": 0.030756859108805656,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3939080238342285,
      "step": 8242
    },
    {
      "epoch": 0.39257142857142857,
      "grad_norm": 0.0316547229886055,
      "learning_rate": 0.024000000208616257,
      "loss": 2.411996841430664,
      "step": 8244
    },
    {
      "epoch": 0.39266666666666666,
      "grad_norm": 0.03331702575087547,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4130964279174805,
      "step": 8246
    },
    {
      "epoch": 0.39276190476190476,
      "grad_norm": 0.031602561473846436,
      "learning_rate": 0.024000000208616257,
      "loss": 2.354173183441162,
      "step": 8248
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 0.028793461620807648,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4169697761535645,
      "step": 8250
    },
    {
      "epoch": 0.39295238095238094,
      "grad_norm": 0.029268482699990273,
      "learning_rate": 0.024000000208616257,
      "loss": 2.408018112182617,
      "step": 8252
    },
    {
      "epoch": 0.39304761904761903,
      "grad_norm": 0.027068397030234337,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3988542556762695,
      "step": 8254
    },
    {
      "epoch": 0.3931428571428571,
      "grad_norm": 0.02816309966146946,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4061968326568604,
      "step": 8256
    },
    {
      "epoch": 0.3932380952380952,
      "grad_norm": 0.02733832411468029,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4075047969818115,
      "step": 8258
    },
    {
      "epoch": 0.3933333333333333,
      "grad_norm": 0.031986381858587265,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3895459175109863,
      "step": 8260
    },
    {
      "epoch": 0.3934285714285714,
      "grad_norm": 0.030595285817980766,
      "learning_rate": 0.024000000208616257,
      "loss": 2.413191795349121,
      "step": 8262
    },
    {
      "epoch": 0.3935238095238095,
      "grad_norm": 0.027916697785258293,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363070249557495,
      "step": 8264
    },
    {
      "epoch": 0.39361904761904765,
      "grad_norm": 0.02857441082596779,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398284673690796,
      "step": 8266
    },
    {
      "epoch": 0.39371428571428574,
      "grad_norm": 0.028194110840559006,
      "learning_rate": 0.024000000208616257,
      "loss": 2.376844882965088,
      "step": 8268
    },
    {
      "epoch": 0.39380952380952383,
      "grad_norm": 0.027285242453217506,
      "learning_rate": 0.024000000208616257,
      "loss": 2.40132737159729,
      "step": 8270
    },
    {
      "epoch": 0.3939047619047619,
      "grad_norm": 0.028201580047607422,
      "learning_rate": 0.024000000208616257,
      "loss": 2.395318031311035,
      "step": 8272
    },
    {
      "epoch": 0.394,
      "grad_norm": 0.0269472599029541,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384045124053955,
      "step": 8274
    },
    {
      "epoch": 0.3940952380952381,
      "grad_norm": 0.02856915071606636,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4184153079986572,
      "step": 8276
    },
    {
      "epoch": 0.3941904761904762,
      "grad_norm": 0.02848232351243496,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3547134399414062,
      "step": 8278
    },
    {
      "epoch": 0.3942857142857143,
      "grad_norm": 0.027912689372897148,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3985934257507324,
      "step": 8280
    },
    {
      "epoch": 0.3943809523809524,
      "grad_norm": 0.0296489205211401,
      "learning_rate": 0.024000000208616257,
      "loss": 2.412397861480713,
      "step": 8282
    },
    {
      "epoch": 0.3944761904761905,
      "grad_norm": 0.027641819790005684,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3941755294799805,
      "step": 8284
    },
    {
      "epoch": 0.3945714285714286,
      "grad_norm": 0.02812846563756466,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3984222412109375,
      "step": 8286
    },
    {
      "epoch": 0.39466666666666667,
      "grad_norm": 0.029841486364603043,
      "learning_rate": 0.024000000208616257,
      "loss": 2.400709629058838,
      "step": 8288
    },
    {
      "epoch": 0.39476190476190476,
      "grad_norm": 0.027592938393354416,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390205144882202,
      "step": 8290
    },
    {
      "epoch": 0.39485714285714285,
      "grad_norm": 0.02837199717760086,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3462467193603516,
      "step": 8292
    },
    {
      "epoch": 0.39495238095238094,
      "grad_norm": 0.03157012537121773,
      "learning_rate": 0.024000000208616257,
      "loss": 2.386631965637207,
      "step": 8294
    },
    {
      "epoch": 0.39504761904761904,
      "grad_norm": 0.028600599616765976,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385531187057495,
      "step": 8296
    },
    {
      "epoch": 0.39514285714285713,
      "grad_norm": 0.02876421995460987,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3923850059509277,
      "step": 8298
    },
    {
      "epoch": 0.3952380952380952,
      "grad_norm": 0.02994121052324772,
      "learning_rate": 0.024000000208616257,
      "loss": 2.412867546081543,
      "step": 8300
    },
    {
      "epoch": 0.3953333333333333,
      "grad_norm": 0.028619103133678436,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3843612670898438,
      "step": 8302
    },
    {
      "epoch": 0.3954285714285714,
      "grad_norm": 0.028315668925642967,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3896689414978027,
      "step": 8304
    },
    {
      "epoch": 0.3955238095238095,
      "grad_norm": 0.02968328818678856,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3948962688446045,
      "step": 8306
    },
    {
      "epoch": 0.3956190476190476,
      "grad_norm": 0.028994450345635414,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3938236236572266,
      "step": 8308
    },
    {
      "epoch": 0.39571428571428574,
      "grad_norm": 0.0287022702395916,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3781380653381348,
      "step": 8310
    },
    {
      "epoch": 0.39580952380952383,
      "grad_norm": 0.02936253324151039,
      "learning_rate": 0.024000000208616257,
      "loss": 2.40885066986084,
      "step": 8312
    },
    {
      "epoch": 0.3959047619047619,
      "grad_norm": 0.029181092977523804,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3969101905822754,
      "step": 8314
    },
    {
      "epoch": 0.396,
      "grad_norm": 0.03232038766145706,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3807618618011475,
      "step": 8316
    },
    {
      "epoch": 0.3960952380952381,
      "grad_norm": 0.02935199998319149,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3908839225769043,
      "step": 8318
    },
    {
      "epoch": 0.3961904761904762,
      "grad_norm": 0.02771443873643875,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3800368309020996,
      "step": 8320
    },
    {
      "epoch": 0.3962857142857143,
      "grad_norm": 0.027311891317367554,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3895773887634277,
      "step": 8322
    },
    {
      "epoch": 0.3963809523809524,
      "grad_norm": 0.02933877520263195,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4067039489746094,
      "step": 8324
    },
    {
      "epoch": 0.3964761904761905,
      "grad_norm": 0.027190616354346275,
      "learning_rate": 0.024000000208616257,
      "loss": 2.400641918182373,
      "step": 8326
    },
    {
      "epoch": 0.3965714285714286,
      "grad_norm": 0.028106415644288063,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401974678039551,
      "step": 8328
    },
    {
      "epoch": 0.39666666666666667,
      "grad_norm": 0.030319947749376297,
      "learning_rate": 0.024000000208616257,
      "loss": 2.379021644592285,
      "step": 8330
    },
    {
      "epoch": 0.39676190476190476,
      "grad_norm": 0.030503982678055763,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38448429107666,
      "step": 8332
    },
    {
      "epoch": 0.39685714285714285,
      "grad_norm": 0.034917764365673065,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3964133262634277,
      "step": 8334
    },
    {
      "epoch": 0.39695238095238095,
      "grad_norm": 0.03530740365386009,
      "learning_rate": 0.024000000208616257,
      "loss": 2.415297508239746,
      "step": 8336
    },
    {
      "epoch": 0.39704761904761904,
      "grad_norm": 0.028398558497428894,
      "learning_rate": 0.024000000208616257,
      "loss": 2.458207130432129,
      "step": 8338
    },
    {
      "epoch": 0.39714285714285713,
      "grad_norm": 0.028420789167284966,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3903515338897705,
      "step": 8340
    },
    {
      "epoch": 0.3972380952380952,
      "grad_norm": 0.027277396991848946,
      "learning_rate": 0.024000000208616257,
      "loss": 2.429572820663452,
      "step": 8342
    },
    {
      "epoch": 0.3973333333333333,
      "grad_norm": 0.030627408996224403,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3871617317199707,
      "step": 8344
    },
    {
      "epoch": 0.3974285714285714,
      "grad_norm": 0.028153130784630775,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4435393810272217,
      "step": 8346
    },
    {
      "epoch": 0.3975238095238095,
      "grad_norm": 0.0276272501796484,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383948802947998,
      "step": 8348
    },
    {
      "epoch": 0.3976190476190476,
      "grad_norm": 0.026846885681152344,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396083354949951,
      "step": 8350
    },
    {
      "epoch": 0.3977142857142857,
      "grad_norm": 0.03224263712763786,
      "learning_rate": 0.024000000208616257,
      "loss": 2.381570816040039,
      "step": 8352
    },
    {
      "epoch": 0.39780952380952384,
      "grad_norm": 0.02929544262588024,
      "learning_rate": 0.024000000208616257,
      "loss": 2.451720714569092,
      "step": 8354
    },
    {
      "epoch": 0.3979047619047619,
      "grad_norm": 0.028361571952700615,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4281210899353027,
      "step": 8356
    },
    {
      "epoch": 0.398,
      "grad_norm": 0.03200922906398773,
      "learning_rate": 0.024000000208616257,
      "loss": 2.403010845184326,
      "step": 8358
    },
    {
      "epoch": 0.3980952380952381,
      "grad_norm": 0.029426053166389465,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4145288467407227,
      "step": 8360
    },
    {
      "epoch": 0.3981904761904762,
      "grad_norm": 0.02891813963651657,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4068069458007812,
      "step": 8362
    },
    {
      "epoch": 0.3982857142857143,
      "grad_norm": 0.031707100570201874,
      "learning_rate": 0.024000000208616257,
      "loss": 2.388723134994507,
      "step": 8364
    },
    {
      "epoch": 0.3983809523809524,
      "grad_norm": 0.03351038694381714,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4120843410491943,
      "step": 8366
    },
    {
      "epoch": 0.3984761904761905,
      "grad_norm": 0.02888479456305504,
      "learning_rate": 0.024000000208616257,
      "loss": 2.373612403869629,
      "step": 8368
    },
    {
      "epoch": 0.3985714285714286,
      "grad_norm": 0.029966363683342934,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3948447704315186,
      "step": 8370
    },
    {
      "epoch": 0.39866666666666667,
      "grad_norm": 0.0347198061645031,
      "learning_rate": 0.024000000208616257,
      "loss": 2.425595760345459,
      "step": 8372
    },
    {
      "epoch": 0.39876190476190476,
      "grad_norm": 0.03103848174214363,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4182000160217285,
      "step": 8374
    },
    {
      "epoch": 0.39885714285714285,
      "grad_norm": 0.02863946743309498,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4258298873901367,
      "step": 8376
    },
    {
      "epoch": 0.39895238095238095,
      "grad_norm": 0.030011536553502083,
      "learning_rate": 0.024000000208616257,
      "loss": 2.418600082397461,
      "step": 8378
    },
    {
      "epoch": 0.39904761904761904,
      "grad_norm": 0.030882321298122406,
      "learning_rate": 0.024000000208616257,
      "loss": 2.413662910461426,
      "step": 8380
    },
    {
      "epoch": 0.39914285714285713,
      "grad_norm": 0.02987387776374817,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4082579612731934,
      "step": 8382
    },
    {
      "epoch": 0.3992380952380952,
      "grad_norm": 0.02853129431605339,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4323344230651855,
      "step": 8384
    },
    {
      "epoch": 0.3993333333333333,
      "grad_norm": 0.030858153477311134,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396426200866699,
      "step": 8386
    },
    {
      "epoch": 0.3994285714285714,
      "grad_norm": 0.029824258759617805,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3860530853271484,
      "step": 8388
    },
    {
      "epoch": 0.3995238095238095,
      "grad_norm": 0.02899234928190708,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4157533645629883,
      "step": 8390
    },
    {
      "epoch": 0.3996190476190476,
      "grad_norm": 0.028678178787231445,
      "learning_rate": 0.024000000208616257,
      "loss": 2.420560359954834,
      "step": 8392
    },
    {
      "epoch": 0.3997142857142857,
      "grad_norm": 0.02889799140393734,
      "learning_rate": 0.024000000208616257,
      "loss": 2.43172550201416,
      "step": 8394
    },
    {
      "epoch": 0.39980952380952384,
      "grad_norm": 0.028679251670837402,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4258341789245605,
      "step": 8396
    },
    {
      "epoch": 0.39990476190476193,
      "grad_norm": 0.0306342002004385,
      "learning_rate": 0.024000000208616257,
      "loss": 2.420658588409424,
      "step": 8398
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.028866929933428764,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4167237281799316,
      "step": 8400
    },
    {
      "epoch": 0.4000952380952381,
      "grad_norm": 0.027677226811647415,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383977174758911,
      "step": 8402
    },
    {
      "epoch": 0.4001904761904762,
      "grad_norm": 0.028417101129889488,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4031386375427246,
      "step": 8404
    },
    {
      "epoch": 0.4002857142857143,
      "grad_norm": 0.029537823051214218,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3997793197631836,
      "step": 8406
    },
    {
      "epoch": 0.4003809523809524,
      "grad_norm": 0.027978166937828064,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4204039573669434,
      "step": 8408
    },
    {
      "epoch": 0.4004761904761905,
      "grad_norm": 0.028987010940909386,
      "learning_rate": 0.024000000208616257,
      "loss": 2.41776704788208,
      "step": 8410
    },
    {
      "epoch": 0.4005714285714286,
      "grad_norm": 0.032575443387031555,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4327659606933594,
      "step": 8412
    },
    {
      "epoch": 0.40066666666666667,
      "grad_norm": 0.028114238753914833,
      "learning_rate": 0.024000000208616257,
      "loss": 2.402665138244629,
      "step": 8414
    },
    {
      "epoch": 0.40076190476190476,
      "grad_norm": 0.02887202985584736,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4323787689208984,
      "step": 8416
    },
    {
      "epoch": 0.40085714285714286,
      "grad_norm": 0.030073458328843117,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4015049934387207,
      "step": 8418
    },
    {
      "epoch": 0.40095238095238095,
      "grad_norm": 0.028758374974131584,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3947036266326904,
      "step": 8420
    },
    {
      "epoch": 0.40104761904761904,
      "grad_norm": 0.03157670423388481,
      "learning_rate": 0.024000000208616257,
      "loss": 2.429417133331299,
      "step": 8422
    },
    {
      "epoch": 0.40114285714285713,
      "grad_norm": 0.028206169605255127,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4329676628112793,
      "step": 8424
    },
    {
      "epoch": 0.4012380952380952,
      "grad_norm": 0.027986960485577583,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4135873317718506,
      "step": 8426
    },
    {
      "epoch": 0.4013333333333333,
      "grad_norm": 0.028139593079686165,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4097800254821777,
      "step": 8428
    },
    {
      "epoch": 0.4014285714285714,
      "grad_norm": 0.028753571212291718,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4119062423706055,
      "step": 8430
    },
    {
      "epoch": 0.4015238095238095,
      "grad_norm": 0.028460649773478508,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4330291748046875,
      "step": 8432
    },
    {
      "epoch": 0.4016190476190476,
      "grad_norm": 0.028921417891979218,
      "learning_rate": 0.024000000208616257,
      "loss": 2.409811496734619,
      "step": 8434
    },
    {
      "epoch": 0.4017142857142857,
      "grad_norm": 0.029603848233819008,
      "learning_rate": 0.024000000208616257,
      "loss": 2.413332462310791,
      "step": 8436
    },
    {
      "epoch": 0.4018095238095238,
      "grad_norm": 0.028524653986096382,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3986940383911133,
      "step": 8438
    },
    {
      "epoch": 0.40190476190476193,
      "grad_norm": 0.028132494539022446,
      "learning_rate": 0.024000000208616257,
      "loss": 2.423454523086548,
      "step": 8440
    },
    {
      "epoch": 0.402,
      "grad_norm": 0.02978750318288803,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3883328437805176,
      "step": 8442
    },
    {
      "epoch": 0.4020952380952381,
      "grad_norm": 0.029420049861073494,
      "learning_rate": 0.024000000208616257,
      "loss": 2.425114154815674,
      "step": 8444
    },
    {
      "epoch": 0.4021904761904762,
      "grad_norm": 0.031046396121382713,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4198732376098633,
      "step": 8446
    },
    {
      "epoch": 0.4022857142857143,
      "grad_norm": 0.028428737074136734,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4240546226501465,
      "step": 8448
    },
    {
      "epoch": 0.4023809523809524,
      "grad_norm": 0.029311995953321457,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4208474159240723,
      "step": 8450
    },
    {
      "epoch": 0.4024761904761905,
      "grad_norm": 0.03175165131688118,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4246749877929688,
      "step": 8452
    },
    {
      "epoch": 0.4025714285714286,
      "grad_norm": 0.032463107258081436,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4115803241729736,
      "step": 8454
    },
    {
      "epoch": 0.4026666666666667,
      "grad_norm": 0.028611235320568085,
      "learning_rate": 0.024000000208616257,
      "loss": 2.377516508102417,
      "step": 8456
    },
    {
      "epoch": 0.40276190476190477,
      "grad_norm": 0.028260845690965652,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4290077686309814,
      "step": 8458
    },
    {
      "epoch": 0.40285714285714286,
      "grad_norm": 0.02725987695157528,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4099388122558594,
      "step": 8460
    },
    {
      "epoch": 0.40295238095238095,
      "grad_norm": 0.027549676597118378,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4085099697113037,
      "step": 8462
    },
    {
      "epoch": 0.40304761904761904,
      "grad_norm": 0.02863912843167782,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4016945362091064,
      "step": 8464
    },
    {
      "epoch": 0.40314285714285714,
      "grad_norm": 0.02963332273066044,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4450783729553223,
      "step": 8466
    },
    {
      "epoch": 0.40323809523809523,
      "grad_norm": 0.03126293048262596,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4557037353515625,
      "step": 8468
    },
    {
      "epoch": 0.4033333333333333,
      "grad_norm": 0.02896295115351677,
      "learning_rate": 0.024000000208616257,
      "loss": 2.433246612548828,
      "step": 8470
    },
    {
      "epoch": 0.4034285714285714,
      "grad_norm": 0.028939371928572655,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4067702293395996,
      "step": 8472
    },
    {
      "epoch": 0.4035238095238095,
      "grad_norm": 0.027696840465068817,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4423818588256836,
      "step": 8474
    },
    {
      "epoch": 0.4036190476190476,
      "grad_norm": 0.03046509064733982,
      "learning_rate": 0.024000000208616257,
      "loss": 2.413247585296631,
      "step": 8476
    },
    {
      "epoch": 0.4037142857142857,
      "grad_norm": 0.034054018557071686,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4419126510620117,
      "step": 8478
    },
    {
      "epoch": 0.4038095238095238,
      "grad_norm": 0.030712060630321503,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4280776977539062,
      "step": 8480
    },
    {
      "epoch": 0.4039047619047619,
      "grad_norm": 0.02851826697587967,
      "learning_rate": 0.024000000208616257,
      "loss": 2.411872148513794,
      "step": 8482
    },
    {
      "epoch": 0.404,
      "grad_norm": 0.029300732538104057,
      "learning_rate": 0.024000000208616257,
      "loss": 2.422642707824707,
      "step": 8484
    },
    {
      "epoch": 0.4040952380952381,
      "grad_norm": 0.02849431149661541,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4047927856445312,
      "step": 8486
    },
    {
      "epoch": 0.4041904761904762,
      "grad_norm": 0.030919024720788002,
      "learning_rate": 0.024000000208616257,
      "loss": 2.391296863555908,
      "step": 8488
    },
    {
      "epoch": 0.4042857142857143,
      "grad_norm": 0.029280927032232285,
      "learning_rate": 0.024000000208616257,
      "loss": 2.427553653717041,
      "step": 8490
    },
    {
      "epoch": 0.4043809523809524,
      "grad_norm": 0.027651485055685043,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4192428588867188,
      "step": 8492
    },
    {
      "epoch": 0.4044761904761905,
      "grad_norm": 0.027856430038809776,
      "learning_rate": 0.024000000208616257,
      "loss": 2.427760124206543,
      "step": 8494
    },
    {
      "epoch": 0.4045714285714286,
      "grad_norm": 0.028155352920293808,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3973073959350586,
      "step": 8496
    },
    {
      "epoch": 0.4046666666666667,
      "grad_norm": 0.029455874115228653,
      "learning_rate": 0.024000000208616257,
      "loss": 2.37221622467041,
      "step": 8498
    },
    {
      "epoch": 0.40476190476190477,
      "grad_norm": 0.031499918550252914,
      "learning_rate": 0.024000000208616257,
      "loss": 2.417659282684326,
      "step": 8500
    },
    {
      "epoch": 0.40485714285714286,
      "grad_norm": 0.033624183386564255,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4067299365997314,
      "step": 8502
    },
    {
      "epoch": 0.40495238095238095,
      "grad_norm": 0.03704431280493736,
      "learning_rate": 0.024000000208616257,
      "loss": 2.404458999633789,
      "step": 8504
    },
    {
      "epoch": 0.40504761904761905,
      "grad_norm": 0.03259526938199997,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4104981422424316,
      "step": 8506
    },
    {
      "epoch": 0.40514285714285714,
      "grad_norm": 0.03221463784575462,
      "learning_rate": 0.024000000208616257,
      "loss": 2.426957607269287,
      "step": 8508
    },
    {
      "epoch": 0.40523809523809523,
      "grad_norm": 0.029582083225250244,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4252851009368896,
      "step": 8510
    },
    {
      "epoch": 0.4053333333333333,
      "grad_norm": 0.028268737718462944,
      "learning_rate": 0.024000000208616257,
      "loss": 2.406226634979248,
      "step": 8512
    },
    {
      "epoch": 0.4054285714285714,
      "grad_norm": 0.03135263919830322,
      "learning_rate": 0.024000000208616257,
      "loss": 2.37675404548645,
      "step": 8514
    },
    {
      "epoch": 0.4055238095238095,
      "grad_norm": 0.03464667871594429,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4106078147888184,
      "step": 8516
    },
    {
      "epoch": 0.4056190476190476,
      "grad_norm": 0.03309556469321251,
      "learning_rate": 0.024000000208616257,
      "loss": 2.395895481109619,
      "step": 8518
    },
    {
      "epoch": 0.4057142857142857,
      "grad_norm": 0.0331445038318634,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3980445861816406,
      "step": 8520
    },
    {
      "epoch": 0.4058095238095238,
      "grad_norm": 0.03293796256184578,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3930985927581787,
      "step": 8522
    },
    {
      "epoch": 0.4059047619047619,
      "grad_norm": 0.034089960157871246,
      "learning_rate": 0.024000000208616257,
      "loss": 2.442255973815918,
      "step": 8524
    },
    {
      "epoch": 0.406,
      "grad_norm": 0.02809484861791134,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4179234504699707,
      "step": 8526
    },
    {
      "epoch": 0.4060952380952381,
      "grad_norm": 0.030256453901529312,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4024062156677246,
      "step": 8528
    },
    {
      "epoch": 0.4061904761904762,
      "grad_norm": 0.028343437239527702,
      "learning_rate": 0.024000000208616257,
      "loss": 2.394216537475586,
      "step": 8530
    },
    {
      "epoch": 0.4062857142857143,
      "grad_norm": 0.02855972945690155,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3841936588287354,
      "step": 8532
    },
    {
      "epoch": 0.4063809523809524,
      "grad_norm": 0.02769876830279827,
      "learning_rate": 0.024000000208616257,
      "loss": 2.408064842224121,
      "step": 8534
    },
    {
      "epoch": 0.4064761904761905,
      "grad_norm": 0.029525890946388245,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3879451751708984,
      "step": 8536
    },
    {
      "epoch": 0.4065714285714286,
      "grad_norm": 0.028882281854748726,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4096553325653076,
      "step": 8538
    },
    {
      "epoch": 0.4066666666666667,
      "grad_norm": 0.028937602415680885,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3812437057495117,
      "step": 8540
    },
    {
      "epoch": 0.40676190476190477,
      "grad_norm": 0.029187051579356194,
      "learning_rate": 0.024000000208616257,
      "loss": 2.424837112426758,
      "step": 8542
    },
    {
      "epoch": 0.40685714285714286,
      "grad_norm": 0.029252469539642334,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3651609420776367,
      "step": 8544
    },
    {
      "epoch": 0.40695238095238095,
      "grad_norm": 0.03024929203093052,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3910269737243652,
      "step": 8546
    },
    {
      "epoch": 0.40704761904761905,
      "grad_norm": 0.03314036503434181,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4082157611846924,
      "step": 8548
    },
    {
      "epoch": 0.40714285714285714,
      "grad_norm": 0.027716076001524925,
      "learning_rate": 0.024000000208616257,
      "loss": 2.368626117706299,
      "step": 8550
    },
    {
      "epoch": 0.40723809523809523,
      "grad_norm": 0.0323333702981472,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3986659049987793,
      "step": 8552
    },
    {
      "epoch": 0.4073333333333333,
      "grad_norm": 0.03008875995874405,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3918967247009277,
      "step": 8554
    },
    {
      "epoch": 0.4074285714285714,
      "grad_norm": 0.029051316902041435,
      "learning_rate": 0.024000000208616257,
      "loss": 2.427346706390381,
      "step": 8556
    },
    {
      "epoch": 0.4075238095238095,
      "grad_norm": 0.03350785747170448,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4157657623291016,
      "step": 8558
    },
    {
      "epoch": 0.4076190476190476,
      "grad_norm": 0.028726939111948013,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4000539779663086,
      "step": 8560
    },
    {
      "epoch": 0.4077142857142857,
      "grad_norm": 0.029321324080228806,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3538923263549805,
      "step": 8562
    },
    {
      "epoch": 0.4078095238095238,
      "grad_norm": 0.0291151013225317,
      "learning_rate": 0.024000000208616257,
      "loss": 2.415964126586914,
      "step": 8564
    },
    {
      "epoch": 0.4079047619047619,
      "grad_norm": 0.029862845316529274,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3915255069732666,
      "step": 8566
    },
    {
      "epoch": 0.408,
      "grad_norm": 0.029569001868367195,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3917267322540283,
      "step": 8568
    },
    {
      "epoch": 0.4080952380952381,
      "grad_norm": 0.02835746854543686,
      "learning_rate": 0.024000000208616257,
      "loss": 2.40269136428833,
      "step": 8570
    },
    {
      "epoch": 0.4081904761904762,
      "grad_norm": 0.02766149304807186,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385223388671875,
      "step": 8572
    },
    {
      "epoch": 0.4082857142857143,
      "grad_norm": 0.027308430522680283,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3730080127716064,
      "step": 8574
    },
    {
      "epoch": 0.4083809523809524,
      "grad_norm": 0.0279783196747303,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3820314407348633,
      "step": 8576
    },
    {
      "epoch": 0.4084761904761905,
      "grad_norm": 0.03151135891675949,
      "learning_rate": 0.024000000208616257,
      "loss": 2.376762628555298,
      "step": 8578
    },
    {
      "epoch": 0.4085714285714286,
      "grad_norm": 0.02796252630650997,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3783860206604004,
      "step": 8580
    },
    {
      "epoch": 0.4086666666666667,
      "grad_norm": 0.027307024225592613,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38754940032959,
      "step": 8582
    },
    {
      "epoch": 0.40876190476190477,
      "grad_norm": 0.028838537633419037,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3762900829315186,
      "step": 8584
    },
    {
      "epoch": 0.40885714285714286,
      "grad_norm": 0.02917453646659851,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3894200325012207,
      "step": 8586
    },
    {
      "epoch": 0.40895238095238096,
      "grad_norm": 0.0298289954662323,
      "learning_rate": 0.024000000208616257,
      "loss": 2.370894432067871,
      "step": 8588
    },
    {
      "epoch": 0.40904761904761905,
      "grad_norm": 0.02913781814277172,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396544933319092,
      "step": 8590
    },
    {
      "epoch": 0.40914285714285714,
      "grad_norm": 0.02824784442782402,
      "learning_rate": 0.024000000208616257,
      "loss": 2.358999013900757,
      "step": 8592
    },
    {
      "epoch": 0.40923809523809523,
      "grad_norm": 0.028237739577889442,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3561625480651855,
      "step": 8594
    },
    {
      "epoch": 0.4093333333333333,
      "grad_norm": 0.028952833265066147,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3888940811157227,
      "step": 8596
    },
    {
      "epoch": 0.4094285714285714,
      "grad_norm": 0.028733909130096436,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3867313861846924,
      "step": 8598
    },
    {
      "epoch": 0.4095238095238095,
      "grad_norm": 0.02910713665187359,
      "learning_rate": 0.024000000208616257,
      "loss": 2.361666679382324,
      "step": 8600
    },
    {
      "epoch": 0.4096190476190476,
      "grad_norm": 0.02834095060825348,
      "learning_rate": 0.024000000208616257,
      "loss": 2.395312786102295,
      "step": 8602
    },
    {
      "epoch": 0.4097142857142857,
      "grad_norm": 0.028147846460342407,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4097023010253906,
      "step": 8604
    },
    {
      "epoch": 0.4098095238095238,
      "grad_norm": 0.027452656999230385,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3922781944274902,
      "step": 8606
    },
    {
      "epoch": 0.4099047619047619,
      "grad_norm": 0.030189277604222298,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3967628479003906,
      "step": 8608
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.02851281128823757,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3694095611572266,
      "step": 8610
    },
    {
      "epoch": 0.41009523809523807,
      "grad_norm": 0.027907071635127068,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3885655403137207,
      "step": 8612
    },
    {
      "epoch": 0.4101904761904762,
      "grad_norm": 0.029052453115582466,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383143663406372,
      "step": 8614
    },
    {
      "epoch": 0.4102857142857143,
      "grad_norm": 0.029071267694234848,
      "learning_rate": 0.024000000208616257,
      "loss": 2.369743824005127,
      "step": 8616
    },
    {
      "epoch": 0.4103809523809524,
      "grad_norm": 0.03196486830711365,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3820531368255615,
      "step": 8618
    },
    {
      "epoch": 0.4104761904761905,
      "grad_norm": 0.03251475840806961,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382456064224243,
      "step": 8620
    },
    {
      "epoch": 0.4105714285714286,
      "grad_norm": 0.02794325165450573,
      "learning_rate": 0.024000000208616257,
      "loss": 2.366370677947998,
      "step": 8622
    },
    {
      "epoch": 0.4106666666666667,
      "grad_norm": 0.027666492387652397,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3603758811950684,
      "step": 8624
    },
    {
      "epoch": 0.4107619047619048,
      "grad_norm": 0.02891085110604763,
      "learning_rate": 0.024000000208616257,
      "loss": 2.368713140487671,
      "step": 8626
    },
    {
      "epoch": 0.41085714285714287,
      "grad_norm": 0.02850506268441677,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4133529663085938,
      "step": 8628
    },
    {
      "epoch": 0.41095238095238096,
      "grad_norm": 0.028077976778149605,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4039368629455566,
      "step": 8630
    },
    {
      "epoch": 0.41104761904761905,
      "grad_norm": 0.027607256546616554,
      "learning_rate": 0.024000000208616257,
      "loss": 2.386765718460083,
      "step": 8632
    },
    {
      "epoch": 0.41114285714285714,
      "grad_norm": 0.02872728556394577,
      "learning_rate": 0.024000000208616257,
      "loss": 2.409757614135742,
      "step": 8634
    },
    {
      "epoch": 0.41123809523809524,
      "grad_norm": 0.02785702794790268,
      "learning_rate": 0.024000000208616257,
      "loss": 2.373567581176758,
      "step": 8636
    },
    {
      "epoch": 0.41133333333333333,
      "grad_norm": 0.02784176729619503,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3707168102264404,
      "step": 8638
    },
    {
      "epoch": 0.4114285714285714,
      "grad_norm": 0.029232988134026527,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4145069122314453,
      "step": 8640
    },
    {
      "epoch": 0.4115238095238095,
      "grad_norm": 0.03075806237757206,
      "learning_rate": 0.024000000208616257,
      "loss": 2.372728109359741,
      "step": 8642
    },
    {
      "epoch": 0.4116190476190476,
      "grad_norm": 0.02867792919278145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3946642875671387,
      "step": 8644
    },
    {
      "epoch": 0.4117142857142857,
      "grad_norm": 0.028068047016859055,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3682327270507812,
      "step": 8646
    },
    {
      "epoch": 0.4118095238095238,
      "grad_norm": 0.029961643740534782,
      "learning_rate": 0.024000000208616257,
      "loss": 2.370809555053711,
      "step": 8648
    },
    {
      "epoch": 0.4119047619047619,
      "grad_norm": 0.03122568130493164,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3654398918151855,
      "step": 8650
    },
    {
      "epoch": 0.412,
      "grad_norm": 0.028222404420375824,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4157161712646484,
      "step": 8652
    },
    {
      "epoch": 0.41209523809523807,
      "grad_norm": 0.027757318690419197,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3932766914367676,
      "step": 8654
    },
    {
      "epoch": 0.4121904761904762,
      "grad_norm": 0.03595483675599098,
      "learning_rate": 0.024000000208616257,
      "loss": 2.381175994873047,
      "step": 8656
    },
    {
      "epoch": 0.4122857142857143,
      "grad_norm": 0.028240887448191643,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382108688354492,
      "step": 8658
    },
    {
      "epoch": 0.4123809523809524,
      "grad_norm": 0.029369203373789787,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390958547592163,
      "step": 8660
    },
    {
      "epoch": 0.4124761904761905,
      "grad_norm": 0.031000453978776932,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4081215858459473,
      "step": 8662
    },
    {
      "epoch": 0.4125714285714286,
      "grad_norm": 0.02909238077700138,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384124279022217,
      "step": 8664
    },
    {
      "epoch": 0.4126666666666667,
      "grad_norm": 0.028635093942284584,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3820154666900635,
      "step": 8666
    },
    {
      "epoch": 0.4127619047619048,
      "grad_norm": 0.028215985745191574,
      "learning_rate": 0.024000000208616257,
      "loss": 2.411125421524048,
      "step": 8668
    },
    {
      "epoch": 0.41285714285714287,
      "grad_norm": 0.027840478345751762,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4025189876556396,
      "step": 8670
    },
    {
      "epoch": 0.41295238095238096,
      "grad_norm": 0.027813784778118134,
      "learning_rate": 0.024000000208616257,
      "loss": 2.386345863342285,
      "step": 8672
    },
    {
      "epoch": 0.41304761904761905,
      "grad_norm": 0.028114331886172295,
      "learning_rate": 0.024000000208616257,
      "loss": 2.374229669570923,
      "step": 8674
    },
    {
      "epoch": 0.41314285714285715,
      "grad_norm": 0.02865610085427761,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4020609855651855,
      "step": 8676
    },
    {
      "epoch": 0.41323809523809524,
      "grad_norm": 0.033085115253925323,
      "learning_rate": 0.024000000208616257,
      "loss": 2.358088970184326,
      "step": 8678
    },
    {
      "epoch": 0.41333333333333333,
      "grad_norm": 0.030835825949907303,
      "learning_rate": 0.024000000208616257,
      "loss": 2.369656562805176,
      "step": 8680
    },
    {
      "epoch": 0.4134285714285714,
      "grad_norm": 0.029383324086666107,
      "learning_rate": 0.024000000208616257,
      "loss": 2.428968906402588,
      "step": 8682
    },
    {
      "epoch": 0.4135238095238095,
      "grad_norm": 0.028283216059207916,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392409324645996,
      "step": 8684
    },
    {
      "epoch": 0.4136190476190476,
      "grad_norm": 0.027817580848932266,
      "learning_rate": 0.024000000208616257,
      "loss": 2.399590253829956,
      "step": 8686
    },
    {
      "epoch": 0.4137142857142857,
      "grad_norm": 0.029930664226412773,
      "learning_rate": 0.024000000208616257,
      "loss": 2.405524969100952,
      "step": 8688
    },
    {
      "epoch": 0.4138095238095238,
      "grad_norm": 0.028788728639483452,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3226780891418457,
      "step": 8690
    },
    {
      "epoch": 0.4139047619047619,
      "grad_norm": 0.028576482087373734,
      "learning_rate": 0.024000000208616257,
      "loss": 2.397592067718506,
      "step": 8692
    },
    {
      "epoch": 0.414,
      "grad_norm": 0.028158554807305336,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355776071548462,
      "step": 8694
    },
    {
      "epoch": 0.41409523809523807,
      "grad_norm": 0.03083634376525879,
      "learning_rate": 0.024000000208616257,
      "loss": 2.372908592224121,
      "step": 8696
    },
    {
      "epoch": 0.41419047619047616,
      "grad_norm": 0.03057744726538658,
      "learning_rate": 0.024000000208616257,
      "loss": 2.359283447265625,
      "step": 8698
    },
    {
      "epoch": 0.4142857142857143,
      "grad_norm": 0.02869408018887043,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38350248336792,
      "step": 8700
    },
    {
      "epoch": 0.4143809523809524,
      "grad_norm": 0.029824640601873398,
      "learning_rate": 0.024000000208616257,
      "loss": 2.386735439300537,
      "step": 8702
    },
    {
      "epoch": 0.4144761904761905,
      "grad_norm": 0.028572168201208115,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4037718772888184,
      "step": 8704
    },
    {
      "epoch": 0.4145714285714286,
      "grad_norm": 0.03251141309738159,
      "learning_rate": 0.024000000208616257,
      "loss": 2.42539644241333,
      "step": 8706
    },
    {
      "epoch": 0.4146666666666667,
      "grad_norm": 0.030351558700203896,
      "learning_rate": 0.024000000208616257,
      "loss": 2.389285087585449,
      "step": 8708
    },
    {
      "epoch": 0.4147619047619048,
      "grad_norm": 0.030525213107466698,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3621091842651367,
      "step": 8710
    },
    {
      "epoch": 0.41485714285714287,
      "grad_norm": 0.03339897096157074,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380493640899658,
      "step": 8712
    },
    {
      "epoch": 0.41495238095238096,
      "grad_norm": 0.02965432032942772,
      "learning_rate": 0.024000000208616257,
      "loss": 2.378559112548828,
      "step": 8714
    },
    {
      "epoch": 0.41504761904761905,
      "grad_norm": 0.029434259980916977,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4004878997802734,
      "step": 8716
    },
    {
      "epoch": 0.41514285714285715,
      "grad_norm": 0.030041789636015892,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3750994205474854,
      "step": 8718
    },
    {
      "epoch": 0.41523809523809524,
      "grad_norm": 0.02846921794116497,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3939504623413086,
      "step": 8720
    },
    {
      "epoch": 0.41533333333333333,
      "grad_norm": 0.028809739276766777,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3708648681640625,
      "step": 8722
    },
    {
      "epoch": 0.4154285714285714,
      "grad_norm": 0.030722646042704582,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3695244789123535,
      "step": 8724
    },
    {
      "epoch": 0.4155238095238095,
      "grad_norm": 0.0291142500936985,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3368406295776367,
      "step": 8726
    },
    {
      "epoch": 0.4156190476190476,
      "grad_norm": 0.030282434076070786,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4001379013061523,
      "step": 8728
    },
    {
      "epoch": 0.4157142857142857,
      "grad_norm": 0.028060955926775932,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3611807823181152,
      "step": 8730
    },
    {
      "epoch": 0.4158095238095238,
      "grad_norm": 0.027249889448285103,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3634748458862305,
      "step": 8732
    },
    {
      "epoch": 0.4159047619047619,
      "grad_norm": 0.028116682544350624,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384803533554077,
      "step": 8734
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.02895679511129856,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3715391159057617,
      "step": 8736
    },
    {
      "epoch": 0.4160952380952381,
      "grad_norm": 0.027556313201785088,
      "learning_rate": 0.024000000208616257,
      "loss": 2.357240915298462,
      "step": 8738
    },
    {
      "epoch": 0.41619047619047617,
      "grad_norm": 0.03009495511651039,
      "learning_rate": 0.024000000208616257,
      "loss": 2.358743667602539,
      "step": 8740
    },
    {
      "epoch": 0.41628571428571426,
      "grad_norm": 0.028083328157663345,
      "learning_rate": 0.024000000208616257,
      "loss": 2.370042085647583,
      "step": 8742
    },
    {
      "epoch": 0.4163809523809524,
      "grad_norm": 0.02936234138906002,
      "learning_rate": 0.024000000208616257,
      "loss": 2.400932788848877,
      "step": 8744
    },
    {
      "epoch": 0.4164761904761905,
      "grad_norm": 0.028744617477059364,
      "learning_rate": 0.024000000208616257,
      "loss": 2.361110210418701,
      "step": 8746
    },
    {
      "epoch": 0.4165714285714286,
      "grad_norm": 0.027416599914431572,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3739113807678223,
      "step": 8748
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 0.028701074421405792,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392134666442871,
      "step": 8750
    },
    {
      "epoch": 0.4167619047619048,
      "grad_norm": 0.02878420427441597,
      "learning_rate": 0.024000000208616257,
      "loss": 2.395235538482666,
      "step": 8752
    },
    {
      "epoch": 0.41685714285714287,
      "grad_norm": 0.028212711215019226,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3982765674591064,
      "step": 8754
    },
    {
      "epoch": 0.41695238095238096,
      "grad_norm": 0.02754022926092148,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3637895584106445,
      "step": 8756
    },
    {
      "epoch": 0.41704761904761906,
      "grad_norm": 0.029884127900004387,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356395721435547,
      "step": 8758
    },
    {
      "epoch": 0.41714285714285715,
      "grad_norm": 0.03174874186515808,
      "learning_rate": 0.024000000208616257,
      "loss": 2.353262424468994,
      "step": 8760
    },
    {
      "epoch": 0.41723809523809524,
      "grad_norm": 0.029762398451566696,
      "learning_rate": 0.024000000208616257,
      "loss": 2.358705520629883,
      "step": 8762
    },
    {
      "epoch": 0.41733333333333333,
      "grad_norm": 0.032076217234134674,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3729472160339355,
      "step": 8764
    },
    {
      "epoch": 0.4174285714285714,
      "grad_norm": 0.03749838471412659,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3866167068481445,
      "step": 8766
    },
    {
      "epoch": 0.4175238095238095,
      "grad_norm": 0.034424398094415665,
      "learning_rate": 0.024000000208616257,
      "loss": 2.381244421005249,
      "step": 8768
    },
    {
      "epoch": 0.4176190476190476,
      "grad_norm": 0.030016016215085983,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3936445713043213,
      "step": 8770
    },
    {
      "epoch": 0.4177142857142857,
      "grad_norm": 0.027921197935938835,
      "learning_rate": 0.024000000208616257,
      "loss": 2.367839813232422,
      "step": 8772
    },
    {
      "epoch": 0.4178095238095238,
      "grad_norm": 0.027481386438012123,
      "learning_rate": 0.024000000208616257,
      "loss": 2.343400001525879,
      "step": 8774
    },
    {
      "epoch": 0.4179047619047619,
      "grad_norm": 0.027588602155447006,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3879871368408203,
      "step": 8776
    },
    {
      "epoch": 0.418,
      "grad_norm": 0.029246976599097252,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345069408416748,
      "step": 8778
    },
    {
      "epoch": 0.4180952380952381,
      "grad_norm": 0.028825901448726654,
      "learning_rate": 0.024000000208616257,
      "loss": 2.377622127532959,
      "step": 8780
    },
    {
      "epoch": 0.41819047619047617,
      "grad_norm": 0.028490792959928513,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3594582080841064,
      "step": 8782
    },
    {
      "epoch": 0.41828571428571426,
      "grad_norm": 0.028601666912436485,
      "learning_rate": 0.024000000208616257,
      "loss": 2.412590980529785,
      "step": 8784
    },
    {
      "epoch": 0.41838095238095235,
      "grad_norm": 0.027477338910102844,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385411262512207,
      "step": 8786
    },
    {
      "epoch": 0.4184761904761905,
      "grad_norm": 0.027431245893239975,
      "learning_rate": 0.024000000208616257,
      "loss": 2.36716365814209,
      "step": 8788
    },
    {
      "epoch": 0.4185714285714286,
      "grad_norm": 0.028307203203439713,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3563172817230225,
      "step": 8790
    },
    {
      "epoch": 0.4186666666666667,
      "grad_norm": 0.027588266879320145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3540444374084473,
      "step": 8792
    },
    {
      "epoch": 0.4187619047619048,
      "grad_norm": 0.02731459029018879,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383279800415039,
      "step": 8794
    },
    {
      "epoch": 0.4188571428571429,
      "grad_norm": 0.03151696175336838,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4120535850524902,
      "step": 8796
    },
    {
      "epoch": 0.41895238095238096,
      "grad_norm": 0.029519764706492424,
      "learning_rate": 0.024000000208616257,
      "loss": 2.404691219329834,
      "step": 8798
    },
    {
      "epoch": 0.41904761904761906,
      "grad_norm": 0.027979860082268715,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4027507305145264,
      "step": 8800
    },
    {
      "epoch": 0.41914285714285715,
      "grad_norm": 0.029552049934864044,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3583920001983643,
      "step": 8802
    },
    {
      "epoch": 0.41923809523809524,
      "grad_norm": 0.028702976182103157,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3957467079162598,
      "step": 8804
    },
    {
      "epoch": 0.41933333333333334,
      "grad_norm": 0.028970817103981972,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3716554641723633,
      "step": 8806
    },
    {
      "epoch": 0.41942857142857143,
      "grad_norm": 0.028386857360601425,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3682212829589844,
      "step": 8808
    },
    {
      "epoch": 0.4195238095238095,
      "grad_norm": 0.0294032022356987,
      "learning_rate": 0.024000000208616257,
      "loss": 2.348231315612793,
      "step": 8810
    },
    {
      "epoch": 0.4196190476190476,
      "grad_norm": 0.029103854671120644,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385281562805176,
      "step": 8812
    },
    {
      "epoch": 0.4197142857142857,
      "grad_norm": 0.029604949057102203,
      "learning_rate": 0.024000000208616257,
      "loss": 2.405831813812256,
      "step": 8814
    },
    {
      "epoch": 0.4198095238095238,
      "grad_norm": 0.027694756165146828,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3791842460632324,
      "step": 8816
    },
    {
      "epoch": 0.4199047619047619,
      "grad_norm": 0.03466641157865524,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3672256469726562,
      "step": 8818
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.03190147131681442,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3572263717651367,
      "step": 8820
    },
    {
      "epoch": 0.4200952380952381,
      "grad_norm": 0.030305637046694756,
      "learning_rate": 0.024000000208616257,
      "loss": 2.410675525665283,
      "step": 8822
    },
    {
      "epoch": 0.42019047619047617,
      "grad_norm": 0.029811952263116837,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3767194747924805,
      "step": 8824
    },
    {
      "epoch": 0.42028571428571426,
      "grad_norm": 0.02962806262075901,
      "learning_rate": 0.024000000208616257,
      "loss": 2.410407543182373,
      "step": 8826
    },
    {
      "epoch": 0.42038095238095236,
      "grad_norm": 0.028622925281524658,
      "learning_rate": 0.024000000208616257,
      "loss": 2.405086040496826,
      "step": 8828
    },
    {
      "epoch": 0.4204761904761905,
      "grad_norm": 0.0289701409637928,
      "learning_rate": 0.024000000208616257,
      "loss": 2.407320022583008,
      "step": 8830
    },
    {
      "epoch": 0.4205714285714286,
      "grad_norm": 0.028698498383164406,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3762834072113037,
      "step": 8832
    },
    {
      "epoch": 0.4206666666666667,
      "grad_norm": 0.035566240549087524,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3984375,
      "step": 8834
    },
    {
      "epoch": 0.4207619047619048,
      "grad_norm": 0.03604840859770775,
      "learning_rate": 0.024000000208616257,
      "loss": 2.374535083770752,
      "step": 8836
    },
    {
      "epoch": 0.4208571428571429,
      "grad_norm": 0.03476789966225624,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3782010078430176,
      "step": 8838
    },
    {
      "epoch": 0.42095238095238097,
      "grad_norm": 0.03898259252309799,
      "learning_rate": 0.024000000208616257,
      "loss": 2.374406337738037,
      "step": 8840
    },
    {
      "epoch": 0.42104761904761906,
      "grad_norm": 0.02927827648818493,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355314016342163,
      "step": 8842
    },
    {
      "epoch": 0.42114285714285715,
      "grad_norm": 0.027636639773845673,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3757996559143066,
      "step": 8844
    },
    {
      "epoch": 0.42123809523809524,
      "grad_norm": 0.03142423927783966,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3432796001434326,
      "step": 8846
    },
    {
      "epoch": 0.42133333333333334,
      "grad_norm": 0.028128135949373245,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4081358909606934,
      "step": 8848
    },
    {
      "epoch": 0.42142857142857143,
      "grad_norm": 0.028597604483366013,
      "learning_rate": 0.024000000208616257,
      "loss": 2.389889717102051,
      "step": 8850
    },
    {
      "epoch": 0.4215238095238095,
      "grad_norm": 0.029007166624069214,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3809022903442383,
      "step": 8852
    },
    {
      "epoch": 0.4216190476190476,
      "grad_norm": 0.028168171644210815,
      "learning_rate": 0.024000000208616257,
      "loss": 2.377997398376465,
      "step": 8854
    },
    {
      "epoch": 0.4217142857142857,
      "grad_norm": 0.028559161350131035,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3708102703094482,
      "step": 8856
    },
    {
      "epoch": 0.4218095238095238,
      "grad_norm": 0.02928326651453972,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383659839630127,
      "step": 8858
    },
    {
      "epoch": 0.4219047619047619,
      "grad_norm": 0.02823219634592533,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3759264945983887,
      "step": 8860
    },
    {
      "epoch": 0.422,
      "grad_norm": 0.029119038954377174,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3723344802856445,
      "step": 8862
    },
    {
      "epoch": 0.4220952380952381,
      "grad_norm": 0.030809829011559486,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3855221271514893,
      "step": 8864
    },
    {
      "epoch": 0.42219047619047617,
      "grad_norm": 0.03005507029592991,
      "learning_rate": 0.024000000208616257,
      "loss": 2.371222972869873,
      "step": 8866
    },
    {
      "epoch": 0.42228571428571426,
      "grad_norm": 0.027903946116566658,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396554946899414,
      "step": 8868
    },
    {
      "epoch": 0.42238095238095236,
      "grad_norm": 0.027913734316825867,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3996644020080566,
      "step": 8870
    },
    {
      "epoch": 0.42247619047619045,
      "grad_norm": 0.028608746826648712,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3832874298095703,
      "step": 8872
    },
    {
      "epoch": 0.4225714285714286,
      "grad_norm": 0.028215594589710236,
      "learning_rate": 0.024000000208616257,
      "loss": 2.417222261428833,
      "step": 8874
    },
    {
      "epoch": 0.4226666666666667,
      "grad_norm": 0.027790335938334465,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3648343086242676,
      "step": 8876
    },
    {
      "epoch": 0.4227619047619048,
      "grad_norm": 0.03357674553990364,
      "learning_rate": 0.024000000208616257,
      "loss": 2.394716262817383,
      "step": 8878
    },
    {
      "epoch": 0.4228571428571429,
      "grad_norm": 0.028430793434381485,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4082422256469727,
      "step": 8880
    },
    {
      "epoch": 0.42295238095238097,
      "grad_norm": 0.027991903945803642,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3973593711853027,
      "step": 8882
    },
    {
      "epoch": 0.42304761904761906,
      "grad_norm": 0.02954568713903427,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401669979095459,
      "step": 8884
    },
    {
      "epoch": 0.42314285714285715,
      "grad_norm": 0.030164401978254318,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398904800415039,
      "step": 8886
    },
    {
      "epoch": 0.42323809523809525,
      "grad_norm": 0.030544307082891464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3976638317108154,
      "step": 8888
    },
    {
      "epoch": 0.42333333333333334,
      "grad_norm": 0.028294509276747704,
      "learning_rate": 0.024000000208616257,
      "loss": 2.406590700149536,
      "step": 8890
    },
    {
      "epoch": 0.42342857142857143,
      "grad_norm": 0.028184019029140472,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4162750244140625,
      "step": 8892
    },
    {
      "epoch": 0.4235238095238095,
      "grad_norm": 0.028247615322470665,
      "learning_rate": 0.024000000208616257,
      "loss": 2.40553879737854,
      "step": 8894
    },
    {
      "epoch": 0.4236190476190476,
      "grad_norm": 0.028638694435358047,
      "learning_rate": 0.024000000208616257,
      "loss": 2.391359329223633,
      "step": 8896
    },
    {
      "epoch": 0.4237142857142857,
      "grad_norm": 0.029370035976171494,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3908352851867676,
      "step": 8898
    },
    {
      "epoch": 0.4238095238095238,
      "grad_norm": 0.02767726220190525,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3958001136779785,
      "step": 8900
    },
    {
      "epoch": 0.4239047619047619,
      "grad_norm": 0.02793535217642784,
      "learning_rate": 0.024000000208616257,
      "loss": 2.394709348678589,
      "step": 8902
    },
    {
      "epoch": 0.424,
      "grad_norm": 0.028737856075167656,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392455577850342,
      "step": 8904
    },
    {
      "epoch": 0.4240952380952381,
      "grad_norm": 0.028089400380849838,
      "learning_rate": 0.024000000208616257,
      "loss": 2.389030933380127,
      "step": 8906
    },
    {
      "epoch": 0.4241904761904762,
      "grad_norm": 0.02927340567111969,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3838601112365723,
      "step": 8908
    },
    {
      "epoch": 0.42428571428571427,
      "grad_norm": 0.02983511984348297,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4132885932922363,
      "step": 8910
    },
    {
      "epoch": 0.42438095238095236,
      "grad_norm": 0.027599100023508072,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398996353149414,
      "step": 8912
    },
    {
      "epoch": 0.42447619047619045,
      "grad_norm": 0.028182635083794594,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3458621501922607,
      "step": 8914
    },
    {
      "epoch": 0.42457142857142854,
      "grad_norm": 0.028079507872462273,
      "learning_rate": 0.024000000208616257,
      "loss": 2.394920825958252,
      "step": 8916
    },
    {
      "epoch": 0.4246666666666667,
      "grad_norm": 0.028593968600034714,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4129323959350586,
      "step": 8918
    },
    {
      "epoch": 0.4247619047619048,
      "grad_norm": 0.02770584262907505,
      "learning_rate": 0.024000000208616257,
      "loss": 2.419157028198242,
      "step": 8920
    },
    {
      "epoch": 0.4248571428571429,
      "grad_norm": 0.029557600617408752,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3848280906677246,
      "step": 8922
    },
    {
      "epoch": 0.42495238095238097,
      "grad_norm": 0.02827785536646843,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3857474327087402,
      "step": 8924
    },
    {
      "epoch": 0.42504761904761906,
      "grad_norm": 0.030707335099577904,
      "learning_rate": 0.024000000208616257,
      "loss": 2.425172805786133,
      "step": 8926
    },
    {
      "epoch": 0.42514285714285716,
      "grad_norm": 0.029108062386512756,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4167542457580566,
      "step": 8928
    },
    {
      "epoch": 0.42523809523809525,
      "grad_norm": 0.028227131813764572,
      "learning_rate": 0.024000000208616257,
      "loss": 2.400527000427246,
      "step": 8930
    },
    {
      "epoch": 0.42533333333333334,
      "grad_norm": 0.029098976403474808,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380767345428467,
      "step": 8932
    },
    {
      "epoch": 0.42542857142857143,
      "grad_norm": 0.028575850650668144,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4226958751678467,
      "step": 8934
    },
    {
      "epoch": 0.4255238095238095,
      "grad_norm": 0.027916917577385902,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3965258598327637,
      "step": 8936
    },
    {
      "epoch": 0.4256190476190476,
      "grad_norm": 0.027749748900532722,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390777111053467,
      "step": 8938
    },
    {
      "epoch": 0.4257142857142857,
      "grad_norm": 0.02717713452875614,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3472843170166016,
      "step": 8940
    },
    {
      "epoch": 0.4258095238095238,
      "grad_norm": 0.02825913205742836,
      "learning_rate": 0.024000000208616257,
      "loss": 2.420790195465088,
      "step": 8942
    },
    {
      "epoch": 0.4259047619047619,
      "grad_norm": 0.028180385008454323,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384399890899658,
      "step": 8944
    },
    {
      "epoch": 0.426,
      "grad_norm": 0.027623988687992096,
      "learning_rate": 0.024000000208616257,
      "loss": 2.39589262008667,
      "step": 8946
    },
    {
      "epoch": 0.4260952380952381,
      "grad_norm": 0.029128944501280785,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4092087745666504,
      "step": 8948
    },
    {
      "epoch": 0.4261904761904762,
      "grad_norm": 0.02833976037800312,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4063515663146973,
      "step": 8950
    },
    {
      "epoch": 0.42628571428571427,
      "grad_norm": 0.028124205768108368,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3614089488983154,
      "step": 8952
    },
    {
      "epoch": 0.42638095238095236,
      "grad_norm": 0.029180757701396942,
      "learning_rate": 0.024000000208616257,
      "loss": 2.378551959991455,
      "step": 8954
    },
    {
      "epoch": 0.42647619047619045,
      "grad_norm": 0.029025059193372726,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3874049186706543,
      "step": 8956
    },
    {
      "epoch": 0.42657142857142855,
      "grad_norm": 0.02911739982664585,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3998255729675293,
      "step": 8958
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.028309162706136703,
      "learning_rate": 0.024000000208616257,
      "loss": 2.379746913909912,
      "step": 8960
    },
    {
      "epoch": 0.4267619047619048,
      "grad_norm": 0.027975736185908318,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3815877437591553,
      "step": 8962
    },
    {
      "epoch": 0.4268571428571429,
      "grad_norm": 0.029874030500650406,
      "learning_rate": 0.024000000208616257,
      "loss": 2.419144630432129,
      "step": 8964
    },
    {
      "epoch": 0.42695238095238097,
      "grad_norm": 0.03617100417613983,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3784449100494385,
      "step": 8966
    },
    {
      "epoch": 0.42704761904761906,
      "grad_norm": 0.036203205585479736,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4012818336486816,
      "step": 8968
    },
    {
      "epoch": 0.42714285714285716,
      "grad_norm": 0.031293537467718124,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4211175441741943,
      "step": 8970
    },
    {
      "epoch": 0.42723809523809525,
      "grad_norm": 0.02988698147237301,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3958005905151367,
      "step": 8972
    },
    {
      "epoch": 0.42733333333333334,
      "grad_norm": 0.02878720872104168,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363845109939575,
      "step": 8974
    },
    {
      "epoch": 0.42742857142857144,
      "grad_norm": 0.029942963272333145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380354404449463,
      "step": 8976
    },
    {
      "epoch": 0.42752380952380953,
      "grad_norm": 0.030672509223222733,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385962724685669,
      "step": 8978
    },
    {
      "epoch": 0.4276190476190476,
      "grad_norm": 0.028806721791625023,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3956751823425293,
      "step": 8980
    },
    {
      "epoch": 0.4277142857142857,
      "grad_norm": 0.028077060356736183,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3872146606445312,
      "step": 8982
    },
    {
      "epoch": 0.4278095238095238,
      "grad_norm": 0.03069433383643627,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3864569664001465,
      "step": 8984
    },
    {
      "epoch": 0.4279047619047619,
      "grad_norm": 0.02952544391155243,
      "learning_rate": 0.024000000208616257,
      "loss": 2.391249656677246,
      "step": 8986
    },
    {
      "epoch": 0.428,
      "grad_norm": 0.028817277401685715,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4115214347839355,
      "step": 8988
    },
    {
      "epoch": 0.4280952380952381,
      "grad_norm": 0.02820689044892788,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3746113777160645,
      "step": 8990
    },
    {
      "epoch": 0.4281904761904762,
      "grad_norm": 0.02865717187523842,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380384922027588,
      "step": 8992
    },
    {
      "epoch": 0.42828571428571427,
      "grad_norm": 0.027404526248574257,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3933982849121094,
      "step": 8994
    },
    {
      "epoch": 0.42838095238095236,
      "grad_norm": 0.02942366525530815,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3903608322143555,
      "step": 8996
    },
    {
      "epoch": 0.42847619047619045,
      "grad_norm": 0.03117830492556095,
      "learning_rate": 0.024000000208616257,
      "loss": 2.373185157775879,
      "step": 8998
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.03523966670036316,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4004719257354736,
      "step": 9000
    },
    {
      "epoch": 0.42866666666666664,
      "grad_norm": 0.03405916690826416,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3559722900390625,
      "step": 9002
    },
    {
      "epoch": 0.4287619047619048,
      "grad_norm": 0.029005834832787514,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4053149223327637,
      "step": 9004
    },
    {
      "epoch": 0.4288571428571429,
      "grad_norm": 0.030313163995742798,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4025492668151855,
      "step": 9006
    },
    {
      "epoch": 0.428952380952381,
      "grad_norm": 0.02873353473842144,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383552312850952,
      "step": 9008
    },
    {
      "epoch": 0.42904761904761907,
      "grad_norm": 0.030611436814069748,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3798089027404785,
      "step": 9010
    },
    {
      "epoch": 0.42914285714285716,
      "grad_norm": 0.02905920520424843,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4062371253967285,
      "step": 9012
    },
    {
      "epoch": 0.42923809523809525,
      "grad_norm": 0.028665609657764435,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4192423820495605,
      "step": 9014
    },
    {
      "epoch": 0.42933333333333334,
      "grad_norm": 0.03634175285696983,
      "learning_rate": 0.024000000208616257,
      "loss": 2.413203239440918,
      "step": 9016
    },
    {
      "epoch": 0.42942857142857144,
      "grad_norm": 0.031697094440460205,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390641689300537,
      "step": 9018
    },
    {
      "epoch": 0.42952380952380953,
      "grad_norm": 0.02975546196103096,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3991880416870117,
      "step": 9020
    },
    {
      "epoch": 0.4296190476190476,
      "grad_norm": 0.029156647622585297,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3745288848876953,
      "step": 9022
    },
    {
      "epoch": 0.4297142857142857,
      "grad_norm": 0.029985791072249413,
      "learning_rate": 0.024000000208616257,
      "loss": 2.378373146057129,
      "step": 9024
    },
    {
      "epoch": 0.4298095238095238,
      "grad_norm": 0.0279811043292284,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3877735137939453,
      "step": 9026
    },
    {
      "epoch": 0.4299047619047619,
      "grad_norm": 0.028361229225993156,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3858883380889893,
      "step": 9028
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.028564590960741043,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3517141342163086,
      "step": 9030
    },
    {
      "epoch": 0.4300952380952381,
      "grad_norm": 0.029876114800572395,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3586623668670654,
      "step": 9032
    },
    {
      "epoch": 0.4301904761904762,
      "grad_norm": 0.02806258201599121,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3926849365234375,
      "step": 9034
    },
    {
      "epoch": 0.43028571428571427,
      "grad_norm": 0.029256002977490425,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3619863986968994,
      "step": 9036
    },
    {
      "epoch": 0.43038095238095236,
      "grad_norm": 0.03004753217101097,
      "learning_rate": 0.024000000208616257,
      "loss": 2.378493309020996,
      "step": 9038
    },
    {
      "epoch": 0.43047619047619046,
      "grad_norm": 0.028512585908174515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3447952270507812,
      "step": 9040
    },
    {
      "epoch": 0.43057142857142855,
      "grad_norm": 0.027756379917263985,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3509650230407715,
      "step": 9042
    },
    {
      "epoch": 0.43066666666666664,
      "grad_norm": 0.029347939416766167,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4130966663360596,
      "step": 9044
    },
    {
      "epoch": 0.43076190476190473,
      "grad_norm": 0.028943981975317,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3701226711273193,
      "step": 9046
    },
    {
      "epoch": 0.4308571428571429,
      "grad_norm": 0.029909910634160042,
      "learning_rate": 0.024000000208616257,
      "loss": 2.364152431488037,
      "step": 9048
    },
    {
      "epoch": 0.430952380952381,
      "grad_norm": 0.027944818139076233,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3523828983306885,
      "step": 9050
    },
    {
      "epoch": 0.43104761904761907,
      "grad_norm": 0.027859438210725784,
      "learning_rate": 0.024000000208616257,
      "loss": 2.352377414703369,
      "step": 9052
    },
    {
      "epoch": 0.43114285714285716,
      "grad_norm": 0.02836262248456478,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3822622299194336,
      "step": 9054
    },
    {
      "epoch": 0.43123809523809525,
      "grad_norm": 0.028515787795186043,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3562607765197754,
      "step": 9056
    },
    {
      "epoch": 0.43133333333333335,
      "grad_norm": 0.02780604362487793,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3528590202331543,
      "step": 9058
    },
    {
      "epoch": 0.43142857142857144,
      "grad_norm": 0.026693029329180717,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3281102180480957,
      "step": 9060
    },
    {
      "epoch": 0.43152380952380953,
      "grad_norm": 0.028249425813555717,
      "learning_rate": 0.024000000208616257,
      "loss": 2.35697603225708,
      "step": 9062
    },
    {
      "epoch": 0.4316190476190476,
      "grad_norm": 0.028213011100888252,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3647172451019287,
      "step": 9064
    },
    {
      "epoch": 0.4317142857142857,
      "grad_norm": 0.02775024063885212,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3585379123687744,
      "step": 9066
    },
    {
      "epoch": 0.4318095238095238,
      "grad_norm": 0.03312710300087929,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3522555828094482,
      "step": 9068
    },
    {
      "epoch": 0.4319047619047619,
      "grad_norm": 0.027743497863411903,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382769823074341,
      "step": 9070
    },
    {
      "epoch": 0.432,
      "grad_norm": 0.028522051870822906,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3572816848754883,
      "step": 9072
    },
    {
      "epoch": 0.4320952380952381,
      "grad_norm": 0.03035544976592064,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3590798377990723,
      "step": 9074
    },
    {
      "epoch": 0.4321904761904762,
      "grad_norm": 0.029559891670942307,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3719429969787598,
      "step": 9076
    },
    {
      "epoch": 0.4322857142857143,
      "grad_norm": 0.02865804359316826,
      "learning_rate": 0.024000000208616257,
      "loss": 2.359708547592163,
      "step": 9078
    },
    {
      "epoch": 0.43238095238095237,
      "grad_norm": 0.027760835364460945,
      "learning_rate": 0.024000000208616257,
      "loss": 2.334477424621582,
      "step": 9080
    },
    {
      "epoch": 0.43247619047619046,
      "grad_norm": 0.028866374865174294,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3389463424682617,
      "step": 9082
    },
    {
      "epoch": 0.43257142857142855,
      "grad_norm": 0.028205377981066704,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356444835662842,
      "step": 9084
    },
    {
      "epoch": 0.43266666666666664,
      "grad_norm": 0.028116052970290184,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3706278800964355,
      "step": 9086
    },
    {
      "epoch": 0.43276190476190474,
      "grad_norm": 0.028490185737609863,
      "learning_rate": 0.024000000208616257,
      "loss": 2.351410388946533,
      "step": 9088
    },
    {
      "epoch": 0.4328571428571429,
      "grad_norm": 0.029845569282770157,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2891793251037598,
      "step": 9090
    },
    {
      "epoch": 0.432952380952381,
      "grad_norm": 0.029228800907731056,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3575100898742676,
      "step": 9092
    },
    {
      "epoch": 0.43304761904761907,
      "grad_norm": 0.027797671034932137,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3387327194213867,
      "step": 9094
    },
    {
      "epoch": 0.43314285714285716,
      "grad_norm": 0.0281207412481308,
      "learning_rate": 0.024000000208616257,
      "loss": 2.362405776977539,
      "step": 9096
    },
    {
      "epoch": 0.43323809523809526,
      "grad_norm": 0.028207965195178986,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3653647899627686,
      "step": 9098
    },
    {
      "epoch": 0.43333333333333335,
      "grad_norm": 0.028742102906107903,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355485200881958,
      "step": 9100
    },
    {
      "epoch": 0.43342857142857144,
      "grad_norm": 0.0288411695510149,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3295974731445312,
      "step": 9102
    },
    {
      "epoch": 0.43352380952380953,
      "grad_norm": 0.0281478613615036,
      "learning_rate": 0.024000000208616257,
      "loss": 2.333043336868286,
      "step": 9104
    },
    {
      "epoch": 0.4336190476190476,
      "grad_norm": 0.02724134922027588,
      "learning_rate": 0.024000000208616257,
      "loss": 2.33766508102417,
      "step": 9106
    },
    {
      "epoch": 0.4337142857142857,
      "grad_norm": 0.028929250314831734,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345017910003662,
      "step": 9108
    },
    {
      "epoch": 0.4338095238095238,
      "grad_norm": 0.028461456298828125,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350186824798584,
      "step": 9110
    },
    {
      "epoch": 0.4339047619047619,
      "grad_norm": 0.0273346696048975,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3620619773864746,
      "step": 9112
    },
    {
      "epoch": 0.434,
      "grad_norm": 0.028465617448091507,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338608503341675,
      "step": 9114
    },
    {
      "epoch": 0.4340952380952381,
      "grad_norm": 0.02938041463494301,
      "learning_rate": 0.024000000208616257,
      "loss": 2.314039707183838,
      "step": 9116
    },
    {
      "epoch": 0.4341904761904762,
      "grad_norm": 0.027038980275392532,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3947505950927734,
      "step": 9118
    },
    {
      "epoch": 0.4342857142857143,
      "grad_norm": 0.027601825073361397,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3548715114593506,
      "step": 9120
    },
    {
      "epoch": 0.43438095238095237,
      "grad_norm": 0.029361777007579803,
      "learning_rate": 0.024000000208616257,
      "loss": 2.32605242729187,
      "step": 9122
    },
    {
      "epoch": 0.43447619047619046,
      "grad_norm": 0.02742251753807068,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3472585678100586,
      "step": 9124
    },
    {
      "epoch": 0.43457142857142855,
      "grad_norm": 0.02849576622247696,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3390560150146484,
      "step": 9126
    },
    {
      "epoch": 0.43466666666666665,
      "grad_norm": 0.028344089165329933,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355100631713867,
      "step": 9128
    },
    {
      "epoch": 0.43476190476190474,
      "grad_norm": 0.028987081721425056,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350504159927368,
      "step": 9130
    },
    {
      "epoch": 0.43485714285714283,
      "grad_norm": 0.027934571728110313,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3519961833953857,
      "step": 9132
    },
    {
      "epoch": 0.434952380952381,
      "grad_norm": 0.027751972898840904,
      "learning_rate": 0.024000000208616257,
      "loss": 2.337620735168457,
      "step": 9134
    },
    {
      "epoch": 0.43504761904761907,
      "grad_norm": 0.029858769848942757,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355635166168213,
      "step": 9136
    },
    {
      "epoch": 0.43514285714285716,
      "grad_norm": 0.03078494407236576,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3213820457458496,
      "step": 9138
    },
    {
      "epoch": 0.43523809523809526,
      "grad_norm": 0.02921787090599537,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3486857414245605,
      "step": 9140
    },
    {
      "epoch": 0.43533333333333335,
      "grad_norm": 0.028577422723174095,
      "learning_rate": 0.024000000208616257,
      "loss": 2.305108070373535,
      "step": 9142
    },
    {
      "epoch": 0.43542857142857144,
      "grad_norm": 0.02783380076289177,
      "learning_rate": 0.024000000208616257,
      "loss": 2.369715690612793,
      "step": 9144
    },
    {
      "epoch": 0.43552380952380954,
      "grad_norm": 0.027717089280486107,
      "learning_rate": 0.024000000208616257,
      "loss": 2.347748279571533,
      "step": 9146
    },
    {
      "epoch": 0.43561904761904763,
      "grad_norm": 0.02970797009766102,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3604211807250977,
      "step": 9148
    },
    {
      "epoch": 0.4357142857142857,
      "grad_norm": 0.027706023305654526,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3440728187561035,
      "step": 9150
    },
    {
      "epoch": 0.4358095238095238,
      "grad_norm": 0.0280055683106184,
      "learning_rate": 0.024000000208616257,
      "loss": 2.337491273880005,
      "step": 9152
    },
    {
      "epoch": 0.4359047619047619,
      "grad_norm": 0.02879980579018593,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3120040893554688,
      "step": 9154
    },
    {
      "epoch": 0.436,
      "grad_norm": 0.027909833937883377,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3361401557922363,
      "step": 9156
    },
    {
      "epoch": 0.4360952380952381,
      "grad_norm": 0.029643921181559563,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3460915088653564,
      "step": 9158
    },
    {
      "epoch": 0.4361904761904762,
      "grad_norm": 0.02942373976111412,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3544764518737793,
      "step": 9160
    },
    {
      "epoch": 0.4362857142857143,
      "grad_norm": 0.02738555148243904,
      "learning_rate": 0.024000000208616257,
      "loss": 2.333406448364258,
      "step": 9162
    },
    {
      "epoch": 0.43638095238095237,
      "grad_norm": 0.027961213141679764,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3226091861724854,
      "step": 9164
    },
    {
      "epoch": 0.43647619047619046,
      "grad_norm": 0.031490132212638855,
      "learning_rate": 0.024000000208616257,
      "loss": 2.331057548522949,
      "step": 9166
    },
    {
      "epoch": 0.43657142857142855,
      "grad_norm": 0.029992345720529556,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3297314643859863,
      "step": 9168
    },
    {
      "epoch": 0.43666666666666665,
      "grad_norm": 0.027628175914287567,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3171863555908203,
      "step": 9170
    },
    {
      "epoch": 0.43676190476190474,
      "grad_norm": 0.02770528383553028,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3490729331970215,
      "step": 9172
    },
    {
      "epoch": 0.43685714285714283,
      "grad_norm": 0.027597198262810707,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3382749557495117,
      "step": 9174
    },
    {
      "epoch": 0.4369523809523809,
      "grad_norm": 0.02883792854845524,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3087053298950195,
      "step": 9176
    },
    {
      "epoch": 0.4370476190476191,
      "grad_norm": 0.0297683198004961,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3121423721313477,
      "step": 9178
    },
    {
      "epoch": 0.43714285714285717,
      "grad_norm": 0.028145257383584976,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3345463275909424,
      "step": 9180
    },
    {
      "epoch": 0.43723809523809526,
      "grad_norm": 0.03166046738624573,
      "learning_rate": 0.024000000208616257,
      "loss": 2.336369037628174,
      "step": 9182
    },
    {
      "epoch": 0.43733333333333335,
      "grad_norm": 0.028022386133670807,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2963857650756836,
      "step": 9184
    },
    {
      "epoch": 0.43742857142857144,
      "grad_norm": 0.02725226804614067,
      "learning_rate": 0.024000000208616257,
      "loss": 2.323737621307373,
      "step": 9186
    },
    {
      "epoch": 0.43752380952380954,
      "grad_norm": 0.03035493940114975,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345534563064575,
      "step": 9188
    },
    {
      "epoch": 0.43761904761904763,
      "grad_norm": 0.029918387532234192,
      "learning_rate": 0.024000000208616257,
      "loss": 2.321889877319336,
      "step": 9190
    },
    {
      "epoch": 0.4377142857142857,
      "grad_norm": 0.03648152947425842,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3370866775512695,
      "step": 9192
    },
    {
      "epoch": 0.4378095238095238,
      "grad_norm": 0.028453223407268524,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2843947410583496,
      "step": 9194
    },
    {
      "epoch": 0.4379047619047619,
      "grad_norm": 0.026725279167294502,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3112940788269043,
      "step": 9196
    },
    {
      "epoch": 0.438,
      "grad_norm": 0.02683115005493164,
      "learning_rate": 0.024000000208616257,
      "loss": 2.30354642868042,
      "step": 9198
    },
    {
      "epoch": 0.4380952380952381,
      "grad_norm": 0.02880522795021534,
      "learning_rate": 0.024000000208616257,
      "loss": 2.315157651901245,
      "step": 9200
    },
    {
      "epoch": 0.4381904761904762,
      "grad_norm": 0.027617620304226875,
      "learning_rate": 0.024000000208616257,
      "loss": 2.305635929107666,
      "step": 9202
    },
    {
      "epoch": 0.4382857142857143,
      "grad_norm": 0.02760431356728077,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3289542198181152,
      "step": 9204
    },
    {
      "epoch": 0.43838095238095237,
      "grad_norm": 0.027735479176044464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.319901943206787,
      "step": 9206
    },
    {
      "epoch": 0.43847619047619046,
      "grad_norm": 0.027308864519000053,
      "learning_rate": 0.024000000208616257,
      "loss": 2.285004138946533,
      "step": 9208
    },
    {
      "epoch": 0.43857142857142856,
      "grad_norm": 0.03012416884303093,
      "learning_rate": 0.024000000208616257,
      "loss": 2.334378480911255,
      "step": 9210
    },
    {
      "epoch": 0.43866666666666665,
      "grad_norm": 0.03310755267739296,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3463902473449707,
      "step": 9212
    },
    {
      "epoch": 0.43876190476190474,
      "grad_norm": 0.028550148010253906,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3071417808532715,
      "step": 9214
    },
    {
      "epoch": 0.43885714285714283,
      "grad_norm": 0.02778642065823078,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3291263580322266,
      "step": 9216
    },
    {
      "epoch": 0.4389523809523809,
      "grad_norm": 0.028854526579380035,
      "learning_rate": 0.024000000208616257,
      "loss": 2.328357219696045,
      "step": 9218
    },
    {
      "epoch": 0.439047619047619,
      "grad_norm": 0.028664732351899147,
      "learning_rate": 0.024000000208616257,
      "loss": 2.337904930114746,
      "step": 9220
    },
    {
      "epoch": 0.43914285714285717,
      "grad_norm": 0.027487175539135933,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3236260414123535,
      "step": 9222
    },
    {
      "epoch": 0.43923809523809526,
      "grad_norm": 0.02761923521757126,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3282980918884277,
      "step": 9224
    },
    {
      "epoch": 0.43933333333333335,
      "grad_norm": 0.027788328006863594,
      "learning_rate": 0.024000000208616257,
      "loss": 2.335744619369507,
      "step": 9226
    },
    {
      "epoch": 0.43942857142857145,
      "grad_norm": 0.028515398502349854,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3068628311157227,
      "step": 9228
    },
    {
      "epoch": 0.43952380952380954,
      "grad_norm": 0.02879527397453785,
      "learning_rate": 0.024000000208616257,
      "loss": 2.272233009338379,
      "step": 9230
    },
    {
      "epoch": 0.43961904761904763,
      "grad_norm": 0.028757473453879356,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2855284214019775,
      "step": 9232
    },
    {
      "epoch": 0.4397142857142857,
      "grad_norm": 0.030150171369314194,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3178787231445312,
      "step": 9234
    },
    {
      "epoch": 0.4398095238095238,
      "grad_norm": 0.033810000866651535,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3347020149230957,
      "step": 9236
    },
    {
      "epoch": 0.4399047619047619,
      "grad_norm": 0.02755209058523178,
      "learning_rate": 0.024000000208616257,
      "loss": 2.328901767730713,
      "step": 9238
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.02720773033797741,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3099112510681152,
      "step": 9240
    },
    {
      "epoch": 0.4400952380952381,
      "grad_norm": 0.02991933375597,
      "learning_rate": 0.024000000208616257,
      "loss": 2.322160243988037,
      "step": 9242
    },
    {
      "epoch": 0.4401904761904762,
      "grad_norm": 0.030437249690294266,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3206076622009277,
      "step": 9244
    },
    {
      "epoch": 0.4402857142857143,
      "grad_norm": 0.031191358342766762,
      "learning_rate": 0.024000000208616257,
      "loss": 2.300386905670166,
      "step": 9246
    },
    {
      "epoch": 0.4403809523809524,
      "grad_norm": 0.03177332505583763,
      "learning_rate": 0.024000000208616257,
      "loss": 2.303947925567627,
      "step": 9248
    },
    {
      "epoch": 0.44047619047619047,
      "grad_norm": 0.031711477786302567,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2967166900634766,
      "step": 9250
    },
    {
      "epoch": 0.44057142857142856,
      "grad_norm": 0.03007437475025654,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3379855155944824,
      "step": 9252
    },
    {
      "epoch": 0.44066666666666665,
      "grad_norm": 0.02883048728108406,
      "learning_rate": 0.024000000208616257,
      "loss": 2.306523323059082,
      "step": 9254
    },
    {
      "epoch": 0.44076190476190474,
      "grad_norm": 0.02765863947570324,
      "learning_rate": 0.024000000208616257,
      "loss": 2.320063591003418,
      "step": 9256
    },
    {
      "epoch": 0.44085714285714284,
      "grad_norm": 0.0276725422590971,
      "learning_rate": 0.024000000208616257,
      "loss": 2.319469928741455,
      "step": 9258
    },
    {
      "epoch": 0.44095238095238093,
      "grad_norm": 0.027647070586681366,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3497257232666016,
      "step": 9260
    },
    {
      "epoch": 0.441047619047619,
      "grad_norm": 0.02744031511247158,
      "learning_rate": 0.024000000208616257,
      "loss": 2.306821584701538,
      "step": 9262
    },
    {
      "epoch": 0.44114285714285717,
      "grad_norm": 0.027942266315221786,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3317253589630127,
      "step": 9264
    },
    {
      "epoch": 0.44123809523809526,
      "grad_norm": 0.02844003401696682,
      "learning_rate": 0.024000000208616257,
      "loss": 2.323493480682373,
      "step": 9266
    },
    {
      "epoch": 0.44133333333333336,
      "grad_norm": 0.026817871257662773,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3559823036193848,
      "step": 9268
    },
    {
      "epoch": 0.44142857142857145,
      "grad_norm": 0.027005689218640327,
      "learning_rate": 0.024000000208616257,
      "loss": 2.337440013885498,
      "step": 9270
    },
    {
      "epoch": 0.44152380952380954,
      "grad_norm": 0.028705066069960594,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3223071098327637,
      "step": 9272
    },
    {
      "epoch": 0.44161904761904763,
      "grad_norm": 0.027293846011161804,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3067827224731445,
      "step": 9274
    },
    {
      "epoch": 0.4417142857142857,
      "grad_norm": 0.027812259271740913,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3056554794311523,
      "step": 9276
    },
    {
      "epoch": 0.4418095238095238,
      "grad_norm": 0.027697600424289703,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3389148712158203,
      "step": 9278
    },
    {
      "epoch": 0.4419047619047619,
      "grad_norm": 0.026890572160482407,
      "learning_rate": 0.024000000208616257,
      "loss": 2.304771900177002,
      "step": 9280
    },
    {
      "epoch": 0.442,
      "grad_norm": 0.02823222242295742,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3085927963256836,
      "step": 9282
    },
    {
      "epoch": 0.4420952380952381,
      "grad_norm": 0.026768820360302925,
      "learning_rate": 0.024000000208616257,
      "loss": 2.325934410095215,
      "step": 9284
    },
    {
      "epoch": 0.4421904761904762,
      "grad_norm": 0.027939602732658386,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3458828926086426,
      "step": 9286
    },
    {
      "epoch": 0.4422857142857143,
      "grad_norm": 0.03203938901424408,
      "learning_rate": 0.024000000208616257,
      "loss": 2.326932430267334,
      "step": 9288
    },
    {
      "epoch": 0.4423809523809524,
      "grad_norm": 0.03307581692934036,
      "learning_rate": 0.024000000208616257,
      "loss": 2.328409194946289,
      "step": 9290
    },
    {
      "epoch": 0.44247619047619047,
      "grad_norm": 0.030818110331892967,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3399481773376465,
      "step": 9292
    },
    {
      "epoch": 0.44257142857142856,
      "grad_norm": 0.026863466948270798,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3263933658599854,
      "step": 9294
    },
    {
      "epoch": 0.44266666666666665,
      "grad_norm": 0.02961041033267975,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3514602184295654,
      "step": 9296
    },
    {
      "epoch": 0.44276190476190475,
      "grad_norm": 0.031652264297008514,
      "learning_rate": 0.024000000208616257,
      "loss": 2.326202630996704,
      "step": 9298
    },
    {
      "epoch": 0.44285714285714284,
      "grad_norm": 0.027950717136263847,
      "learning_rate": 0.024000000208616257,
      "loss": 2.343456745147705,
      "step": 9300
    },
    {
      "epoch": 0.44295238095238093,
      "grad_norm": 0.027578748762607574,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3384766578674316,
      "step": 9302
    },
    {
      "epoch": 0.443047619047619,
      "grad_norm": 0.027901889756321907,
      "learning_rate": 0.024000000208616257,
      "loss": 2.297211170196533,
      "step": 9304
    },
    {
      "epoch": 0.4431428571428571,
      "grad_norm": 0.02748989872634411,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3454885482788086,
      "step": 9306
    },
    {
      "epoch": 0.44323809523809526,
      "grad_norm": 0.03125539794564247,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3265151977539062,
      "step": 9308
    },
    {
      "epoch": 0.44333333333333336,
      "grad_norm": 0.03674205020070076,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3341288566589355,
      "step": 9310
    },
    {
      "epoch": 0.44342857142857145,
      "grad_norm": 0.03825412318110466,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3060426712036133,
      "step": 9312
    },
    {
      "epoch": 0.44352380952380954,
      "grad_norm": 0.03219965472817421,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3392367362976074,
      "step": 9314
    },
    {
      "epoch": 0.44361904761904764,
      "grad_norm": 0.026971925050020218,
      "learning_rate": 0.024000000208616257,
      "loss": 2.34959077835083,
      "step": 9316
    },
    {
      "epoch": 0.4437142857142857,
      "grad_norm": 0.028325650840997696,
      "learning_rate": 0.024000000208616257,
      "loss": 2.318349838256836,
      "step": 9318
    },
    {
      "epoch": 0.4438095238095238,
      "grad_norm": 0.030183926224708557,
      "learning_rate": 0.024000000208616257,
      "loss": 2.309781074523926,
      "step": 9320
    },
    {
      "epoch": 0.4439047619047619,
      "grad_norm": 0.029603036120533943,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2945520877838135,
      "step": 9322
    },
    {
      "epoch": 0.444,
      "grad_norm": 0.027431625872850418,
      "learning_rate": 0.024000000208616257,
      "loss": 2.297065019607544,
      "step": 9324
    },
    {
      "epoch": 0.4440952380952381,
      "grad_norm": 0.029024144634604454,
      "learning_rate": 0.024000000208616257,
      "loss": 2.333747386932373,
      "step": 9326
    },
    {
      "epoch": 0.4441904761904762,
      "grad_norm": 0.029375189915299416,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3567450046539307,
      "step": 9328
    },
    {
      "epoch": 0.4442857142857143,
      "grad_norm": 0.028945432975888252,
      "learning_rate": 0.024000000208616257,
      "loss": 2.304704189300537,
      "step": 9330
    },
    {
      "epoch": 0.4443809523809524,
      "grad_norm": 0.028592588379979134,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3329732418060303,
      "step": 9332
    },
    {
      "epoch": 0.44447619047619047,
      "grad_norm": 0.02752716839313507,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3122353553771973,
      "step": 9334
    },
    {
      "epoch": 0.44457142857142856,
      "grad_norm": 0.027412498369812965,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2966272830963135,
      "step": 9336
    },
    {
      "epoch": 0.44466666666666665,
      "grad_norm": 0.028113368898630142,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3240535259246826,
      "step": 9338
    },
    {
      "epoch": 0.44476190476190475,
      "grad_norm": 0.03146934136748314,
      "learning_rate": 0.024000000208616257,
      "loss": 2.366851329803467,
      "step": 9340
    },
    {
      "epoch": 0.44485714285714284,
      "grad_norm": 0.03637567162513733,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3399949073791504,
      "step": 9342
    },
    {
      "epoch": 0.44495238095238093,
      "grad_norm": 0.03121298924088478,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3217825889587402,
      "step": 9344
    },
    {
      "epoch": 0.445047619047619,
      "grad_norm": 0.02819632738828659,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3186569213867188,
      "step": 9346
    },
    {
      "epoch": 0.4451428571428571,
      "grad_norm": 0.027306344360113144,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3810973167419434,
      "step": 9348
    },
    {
      "epoch": 0.4452380952380952,
      "grad_norm": 0.02779257483780384,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3331713676452637,
      "step": 9350
    },
    {
      "epoch": 0.44533333333333336,
      "grad_norm": 0.02833339013159275,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3122785091400146,
      "step": 9352
    },
    {
      "epoch": 0.44542857142857145,
      "grad_norm": 0.027588196098804474,
      "learning_rate": 0.024000000208616257,
      "loss": 2.358957290649414,
      "step": 9354
    },
    {
      "epoch": 0.44552380952380954,
      "grad_norm": 0.028243109583854675,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3577661514282227,
      "step": 9356
    },
    {
      "epoch": 0.44561904761904764,
      "grad_norm": 0.02889030985534191,
      "learning_rate": 0.024000000208616257,
      "loss": 2.31154203414917,
      "step": 9358
    },
    {
      "epoch": 0.44571428571428573,
      "grad_norm": 0.027423404157161713,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3048300743103027,
      "step": 9360
    },
    {
      "epoch": 0.4458095238095238,
      "grad_norm": 0.028350796550512314,
      "learning_rate": 0.024000000208616257,
      "loss": 2.346247434616089,
      "step": 9362
    },
    {
      "epoch": 0.4459047619047619,
      "grad_norm": 0.028323518112301826,
      "learning_rate": 0.024000000208616257,
      "loss": 2.341341495513916,
      "step": 9364
    },
    {
      "epoch": 0.446,
      "grad_norm": 0.0291711688041687,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3666720390319824,
      "step": 9366
    },
    {
      "epoch": 0.4460952380952381,
      "grad_norm": 0.03136400878429413,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3444252014160156,
      "step": 9368
    },
    {
      "epoch": 0.4461904761904762,
      "grad_norm": 0.028995772823691368,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4061331748962402,
      "step": 9370
    },
    {
      "epoch": 0.4462857142857143,
      "grad_norm": 0.028245816007256508,
      "learning_rate": 0.024000000208616257,
      "loss": 2.320417881011963,
      "step": 9372
    },
    {
      "epoch": 0.4463809523809524,
      "grad_norm": 0.028446059674024582,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3208670616149902,
      "step": 9374
    },
    {
      "epoch": 0.44647619047619047,
      "grad_norm": 0.029107604175806046,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3443875312805176,
      "step": 9376
    },
    {
      "epoch": 0.44657142857142856,
      "grad_norm": 0.028971053659915924,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3428051471710205,
      "step": 9378
    },
    {
      "epoch": 0.44666666666666666,
      "grad_norm": 0.027278222143650055,
      "learning_rate": 0.024000000208616257,
      "loss": 2.310889959335327,
      "step": 9380
    },
    {
      "epoch": 0.44676190476190475,
      "grad_norm": 0.02797379344701767,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3311104774475098,
      "step": 9382
    },
    {
      "epoch": 0.44685714285714284,
      "grad_norm": 0.029069215059280396,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3561208248138428,
      "step": 9384
    },
    {
      "epoch": 0.44695238095238093,
      "grad_norm": 0.02846992202103138,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3437466621398926,
      "step": 9386
    },
    {
      "epoch": 0.447047619047619,
      "grad_norm": 0.02759224735200405,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3430566787719727,
      "step": 9388
    },
    {
      "epoch": 0.4471428571428571,
      "grad_norm": 0.027249081060290337,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3393008708953857,
      "step": 9390
    },
    {
      "epoch": 0.4472380952380952,
      "grad_norm": 0.029575655236840248,
      "learning_rate": 0.024000000208616257,
      "loss": 2.344088554382324,
      "step": 9392
    },
    {
      "epoch": 0.44733333333333336,
      "grad_norm": 0.030211223289370537,
      "learning_rate": 0.024000000208616257,
      "loss": 2.317172050476074,
      "step": 9394
    },
    {
      "epoch": 0.44742857142857145,
      "grad_norm": 0.02917393110692501,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3711228370666504,
      "step": 9396
    },
    {
      "epoch": 0.44752380952380955,
      "grad_norm": 0.028596844524145126,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3151001930236816,
      "step": 9398
    },
    {
      "epoch": 0.44761904761904764,
      "grad_norm": 0.02734028361737728,
      "learning_rate": 0.024000000208616257,
      "loss": 2.343313217163086,
      "step": 9400
    },
    {
      "epoch": 0.44771428571428573,
      "grad_norm": 0.029025908559560776,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3358941078186035,
      "step": 9402
    },
    {
      "epoch": 0.4478095238095238,
      "grad_norm": 0.027924539521336555,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363172769546509,
      "step": 9404
    },
    {
      "epoch": 0.4479047619047619,
      "grad_norm": 0.026821376755833626,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3435544967651367,
      "step": 9406
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.02856476604938507,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3566527366638184,
      "step": 9408
    },
    {
      "epoch": 0.4480952380952381,
      "grad_norm": 0.02764582261443138,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3228306770324707,
      "step": 9410
    },
    {
      "epoch": 0.4481904761904762,
      "grad_norm": 0.027743563055992126,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3885042667388916,
      "step": 9412
    },
    {
      "epoch": 0.4482857142857143,
      "grad_norm": 0.027027038857340813,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3647990226745605,
      "step": 9414
    },
    {
      "epoch": 0.4483809523809524,
      "grad_norm": 0.02855653688311577,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3775243759155273,
      "step": 9416
    },
    {
      "epoch": 0.4484761904761905,
      "grad_norm": 0.028720472007989883,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3454413414001465,
      "step": 9418
    },
    {
      "epoch": 0.44857142857142857,
      "grad_norm": 0.028947889804840088,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3521575927734375,
      "step": 9420
    },
    {
      "epoch": 0.44866666666666666,
      "grad_norm": 0.031203050166368484,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338522434234619,
      "step": 9422
    },
    {
      "epoch": 0.44876190476190475,
      "grad_norm": 0.027892766520380974,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3732895851135254,
      "step": 9424
    },
    {
      "epoch": 0.44885714285714284,
      "grad_norm": 0.029060937464237213,
      "learning_rate": 0.024000000208616257,
      "loss": 2.375776767730713,
      "step": 9426
    },
    {
      "epoch": 0.44895238095238094,
      "grad_norm": 0.02677522972226143,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3854103088378906,
      "step": 9428
    },
    {
      "epoch": 0.44904761904761903,
      "grad_norm": 0.028287729248404503,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3508963584899902,
      "step": 9430
    },
    {
      "epoch": 0.4491428571428571,
      "grad_norm": 0.028318390250205994,
      "learning_rate": 0.024000000208616257,
      "loss": 2.35878586769104,
      "step": 9432
    },
    {
      "epoch": 0.4492380952380952,
      "grad_norm": 0.02873067930340767,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3581151962280273,
      "step": 9434
    },
    {
      "epoch": 0.4493333333333333,
      "grad_norm": 0.02905939519405365,
      "learning_rate": 0.024000000208616257,
      "loss": 2.368133068084717,
      "step": 9436
    },
    {
      "epoch": 0.44942857142857146,
      "grad_norm": 0.03444549813866615,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3557329177856445,
      "step": 9438
    },
    {
      "epoch": 0.44952380952380955,
      "grad_norm": 0.029895273968577385,
      "learning_rate": 0.024000000208616257,
      "loss": 2.373685836791992,
      "step": 9440
    },
    {
      "epoch": 0.44961904761904764,
      "grad_norm": 0.027424940839409828,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3646469116210938,
      "step": 9442
    },
    {
      "epoch": 0.44971428571428573,
      "grad_norm": 0.028541767969727516,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363098382949829,
      "step": 9444
    },
    {
      "epoch": 0.4498095238095238,
      "grad_norm": 0.029866786673665047,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3876795768737793,
      "step": 9446
    },
    {
      "epoch": 0.4499047619047619,
      "grad_norm": 0.029006849974393845,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3764429092407227,
      "step": 9448
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.027323361486196518,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3798470497131348,
      "step": 9450
    },
    {
      "epoch": 0.4500952380952381,
      "grad_norm": 0.02812323346734047,
      "learning_rate": 0.024000000208616257,
      "loss": 2.373399496078491,
      "step": 9452
    },
    {
      "epoch": 0.4501904761904762,
      "grad_norm": 0.02928830310702324,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3675971031188965,
      "step": 9454
    },
    {
      "epoch": 0.4502857142857143,
      "grad_norm": 0.02783268876373768,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3551583290100098,
      "step": 9456
    },
    {
      "epoch": 0.4503809523809524,
      "grad_norm": 0.026964876800775528,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3853836059570312,
      "step": 9458
    },
    {
      "epoch": 0.4504761904761905,
      "grad_norm": 0.02846411243081093,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3736214637756348,
      "step": 9460
    },
    {
      "epoch": 0.45057142857142857,
      "grad_norm": 0.027485469356179237,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3665194511413574,
      "step": 9462
    },
    {
      "epoch": 0.45066666666666666,
      "grad_norm": 0.03150163218379021,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3583173751831055,
      "step": 9464
    },
    {
      "epoch": 0.45076190476190475,
      "grad_norm": 0.028467411175370216,
      "learning_rate": 0.024000000208616257,
      "loss": 2.389822483062744,
      "step": 9466
    },
    {
      "epoch": 0.45085714285714285,
      "grad_norm": 0.027167508378624916,
      "learning_rate": 0.024000000208616257,
      "loss": 2.400430917739868,
      "step": 9468
    },
    {
      "epoch": 0.45095238095238094,
      "grad_norm": 0.05745549872517586,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3882322311401367,
      "step": 9470
    },
    {
      "epoch": 0.45104761904761903,
      "grad_norm": 0.029168561100959778,
      "learning_rate": 0.024000000208616257,
      "loss": 2.365302562713623,
      "step": 9472
    },
    {
      "epoch": 0.4511428571428571,
      "grad_norm": 0.02908279001712799,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3743128776550293,
      "step": 9474
    },
    {
      "epoch": 0.4512380952380952,
      "grad_norm": 0.030048049986362457,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3569440841674805,
      "step": 9476
    },
    {
      "epoch": 0.4513333333333333,
      "grad_norm": 0.02787018194794655,
      "learning_rate": 0.024000000208616257,
      "loss": 2.372798442840576,
      "step": 9478
    },
    {
      "epoch": 0.4514285714285714,
      "grad_norm": 0.03107086569070816,
      "learning_rate": 0.024000000208616257,
      "loss": 2.422485828399658,
      "step": 9480
    },
    {
      "epoch": 0.45152380952380955,
      "grad_norm": 0.035302795469760895,
      "learning_rate": 0.024000000208616257,
      "loss": 2.379471778869629,
      "step": 9482
    },
    {
      "epoch": 0.45161904761904764,
      "grad_norm": 0.030484704300761223,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3697214126586914,
      "step": 9484
    },
    {
      "epoch": 0.45171428571428573,
      "grad_norm": 0.02737436071038246,
      "learning_rate": 0.024000000208616257,
      "loss": 2.391493797302246,
      "step": 9486
    },
    {
      "epoch": 0.4518095238095238,
      "grad_norm": 0.02764594927430153,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3534798622131348,
      "step": 9488
    },
    {
      "epoch": 0.4519047619047619,
      "grad_norm": 0.028327714651823044,
      "learning_rate": 0.024000000208616257,
      "loss": 2.397919178009033,
      "step": 9490
    },
    {
      "epoch": 0.452,
      "grad_norm": 0.029418958351016045,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3671231269836426,
      "step": 9492
    },
    {
      "epoch": 0.4520952380952381,
      "grad_norm": 0.02784191258251667,
      "learning_rate": 0.024000000208616257,
      "loss": 2.374255895614624,
      "step": 9494
    },
    {
      "epoch": 0.4521904761904762,
      "grad_norm": 0.028004489839076996,
      "learning_rate": 0.024000000208616257,
      "loss": 2.389178514480591,
      "step": 9496
    },
    {
      "epoch": 0.4522857142857143,
      "grad_norm": 0.02681109867990017,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3943874835968018,
      "step": 9498
    },
    {
      "epoch": 0.4523809523809524,
      "grad_norm": 0.02777627296745777,
      "learning_rate": 0.024000000208616257,
      "loss": 2.376643419265747,
      "step": 9500
    },
    {
      "epoch": 0.4524761904761905,
      "grad_norm": 0.029439652338624,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3808984756469727,
      "step": 9502
    },
    {
      "epoch": 0.45257142857142857,
      "grad_norm": 0.0284713301807642,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4102888107299805,
      "step": 9504
    },
    {
      "epoch": 0.45266666666666666,
      "grad_norm": 0.028019733726978302,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3703067302703857,
      "step": 9506
    },
    {
      "epoch": 0.45276190476190475,
      "grad_norm": 0.02669699303805828,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3696303367614746,
      "step": 9508
    },
    {
      "epoch": 0.45285714285714285,
      "grad_norm": 0.026749474927783012,
      "learning_rate": 0.024000000208616257,
      "loss": 2.367342472076416,
      "step": 9510
    },
    {
      "epoch": 0.45295238095238094,
      "grad_norm": 0.028304141014814377,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3972115516662598,
      "step": 9512
    },
    {
      "epoch": 0.45304761904761903,
      "grad_norm": 0.026691164821386337,
      "learning_rate": 0.024000000208616257,
      "loss": 2.369424343109131,
      "step": 9514
    },
    {
      "epoch": 0.4531428571428571,
      "grad_norm": 0.027282293885946274,
      "learning_rate": 0.024000000208616257,
      "loss": 2.408133029937744,
      "step": 9516
    },
    {
      "epoch": 0.4532380952380952,
      "grad_norm": 0.027041533961892128,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4174842834472656,
      "step": 9518
    },
    {
      "epoch": 0.4533333333333333,
      "grad_norm": 0.027747895568609238,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4196271896362305,
      "step": 9520
    },
    {
      "epoch": 0.4534285714285714,
      "grad_norm": 0.027682824060320854,
      "learning_rate": 0.024000000208616257,
      "loss": 2.440107822418213,
      "step": 9522
    },
    {
      "epoch": 0.45352380952380955,
      "grad_norm": 0.02867613546550274,
      "learning_rate": 0.024000000208616257,
      "loss": 2.400573968887329,
      "step": 9524
    },
    {
      "epoch": 0.45361904761904764,
      "grad_norm": 0.028987908735871315,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3783106803894043,
      "step": 9526
    },
    {
      "epoch": 0.45371428571428574,
      "grad_norm": 0.027644844725728035,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4074182510375977,
      "step": 9528
    },
    {
      "epoch": 0.45380952380952383,
      "grad_norm": 0.030129099264740944,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382225513458252,
      "step": 9530
    },
    {
      "epoch": 0.4539047619047619,
      "grad_norm": 0.02961174212396145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4109396934509277,
      "step": 9532
    },
    {
      "epoch": 0.454,
      "grad_norm": 0.027216212823987007,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3909192085266113,
      "step": 9534
    },
    {
      "epoch": 0.4540952380952381,
      "grad_norm": 0.027351049706339836,
      "learning_rate": 0.024000000208616257,
      "loss": 2.393967628479004,
      "step": 9536
    },
    {
      "epoch": 0.4541904761904762,
      "grad_norm": 0.02777104638516903,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4091384410858154,
      "step": 9538
    },
    {
      "epoch": 0.4542857142857143,
      "grad_norm": 0.0292830690741539,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3610713481903076,
      "step": 9540
    },
    {
      "epoch": 0.4543809523809524,
      "grad_norm": 0.03030133992433548,
      "learning_rate": 0.024000000208616257,
      "loss": 2.364302635192871,
      "step": 9542
    },
    {
      "epoch": 0.4544761904761905,
      "grad_norm": 0.02817436493933201,
      "learning_rate": 0.024000000208616257,
      "loss": 2.41829776763916,
      "step": 9544
    },
    {
      "epoch": 0.45457142857142857,
      "grad_norm": 0.031827934086322784,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4082417488098145,
      "step": 9546
    },
    {
      "epoch": 0.45466666666666666,
      "grad_norm": 0.02843688242137432,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4033021926879883,
      "step": 9548
    },
    {
      "epoch": 0.45476190476190476,
      "grad_norm": 0.028740566223859787,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4150524139404297,
      "step": 9550
    },
    {
      "epoch": 0.45485714285714285,
      "grad_norm": 0.026711007580161095,
      "learning_rate": 0.024000000208616257,
      "loss": 2.375730514526367,
      "step": 9552
    },
    {
      "epoch": 0.45495238095238094,
      "grad_norm": 0.028992997482419014,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4089314937591553,
      "step": 9554
    },
    {
      "epoch": 0.45504761904761903,
      "grad_norm": 0.02872411161661148,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4300498962402344,
      "step": 9556
    },
    {
      "epoch": 0.4551428571428571,
      "grad_norm": 0.029075758531689644,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3912532329559326,
      "step": 9558
    },
    {
      "epoch": 0.4552380952380952,
      "grad_norm": 0.027898570522665977,
      "learning_rate": 0.024000000208616257,
      "loss": 2.403975486755371,
      "step": 9560
    },
    {
      "epoch": 0.4553333333333333,
      "grad_norm": 0.0307011641561985,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3919548988342285,
      "step": 9562
    },
    {
      "epoch": 0.4554285714285714,
      "grad_norm": 0.02728140912950039,
      "learning_rate": 0.024000000208616257,
      "loss": 2.378754138946533,
      "step": 9564
    },
    {
      "epoch": 0.4555238095238095,
      "grad_norm": 0.026572877541184425,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3914191722869873,
      "step": 9566
    },
    {
      "epoch": 0.45561904761904765,
      "grad_norm": 0.02776160277426243,
      "learning_rate": 0.024000000208616257,
      "loss": 2.418177843093872,
      "step": 9568
    },
    {
      "epoch": 0.45571428571428574,
      "grad_norm": 0.028324859216809273,
      "learning_rate": 0.024000000208616257,
      "loss": 2.433095693588257,
      "step": 9570
    },
    {
      "epoch": 0.45580952380952383,
      "grad_norm": 0.028692277148365974,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4323055744171143,
      "step": 9572
    },
    {
      "epoch": 0.4559047619047619,
      "grad_norm": 0.027788469567894936,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3905270099639893,
      "step": 9574
    },
    {
      "epoch": 0.456,
      "grad_norm": 0.02931338921189308,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4258956909179688,
      "step": 9576
    },
    {
      "epoch": 0.4560952380952381,
      "grad_norm": 0.02802826650440693,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3914456367492676,
      "step": 9578
    },
    {
      "epoch": 0.4561904761904762,
      "grad_norm": 0.029379328712821007,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3670308589935303,
      "step": 9580
    },
    {
      "epoch": 0.4562857142857143,
      "grad_norm": 0.029332218691706657,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3934900760650635,
      "step": 9582
    },
    {
      "epoch": 0.4563809523809524,
      "grad_norm": 0.03357872739434242,
      "learning_rate": 0.024000000208616257,
      "loss": 2.375843048095703,
      "step": 9584
    },
    {
      "epoch": 0.4564761904761905,
      "grad_norm": 0.02923494763672352,
      "learning_rate": 0.024000000208616257,
      "loss": 2.415560245513916,
      "step": 9586
    },
    {
      "epoch": 0.4565714285714286,
      "grad_norm": 0.02801583893597126,
      "learning_rate": 0.024000000208616257,
      "loss": 2.402529716491699,
      "step": 9588
    },
    {
      "epoch": 0.45666666666666667,
      "grad_norm": 0.02959945984184742,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4189181327819824,
      "step": 9590
    },
    {
      "epoch": 0.45676190476190476,
      "grad_norm": 0.027532238513231277,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4381072521209717,
      "step": 9592
    },
    {
      "epoch": 0.45685714285714285,
      "grad_norm": 0.028944674879312515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3884191513061523,
      "step": 9594
    },
    {
      "epoch": 0.45695238095238094,
      "grad_norm": 0.026757895946502686,
      "learning_rate": 0.024000000208616257,
      "loss": 2.360382556915283,
      "step": 9596
    },
    {
      "epoch": 0.45704761904761904,
      "grad_norm": 0.027503514662384987,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384544610977173,
      "step": 9598
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.027925431728363037,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4171979427337646,
      "step": 9600
    },
    {
      "epoch": 0.4572380952380952,
      "grad_norm": 0.027668580412864685,
      "learning_rate": 0.024000000208616257,
      "loss": 2.393979787826538,
      "step": 9602
    },
    {
      "epoch": 0.4573333333333333,
      "grad_norm": 0.02744406647980213,
      "learning_rate": 0.024000000208616257,
      "loss": 2.402585506439209,
      "step": 9604
    },
    {
      "epoch": 0.4574285714285714,
      "grad_norm": 0.02696811594069004,
      "learning_rate": 0.024000000208616257,
      "loss": 2.420192241668701,
      "step": 9606
    },
    {
      "epoch": 0.4575238095238095,
      "grad_norm": 0.02883901633322239,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4119696617126465,
      "step": 9608
    },
    {
      "epoch": 0.4576190476190476,
      "grad_norm": 0.027778422459959984,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383331298828125,
      "step": 9610
    },
    {
      "epoch": 0.45771428571428574,
      "grad_norm": 0.03360723331570625,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398616075515747,
      "step": 9612
    },
    {
      "epoch": 0.45780952380952383,
      "grad_norm": 0.028786320239305496,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3967337608337402,
      "step": 9614
    },
    {
      "epoch": 0.4579047619047619,
      "grad_norm": 0.029972322285175323,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3966898918151855,
      "step": 9616
    },
    {
      "epoch": 0.458,
      "grad_norm": 0.03117413818836212,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4118895530700684,
      "step": 9618
    },
    {
      "epoch": 0.4580952380952381,
      "grad_norm": 0.031230362132191658,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4379684925079346,
      "step": 9620
    },
    {
      "epoch": 0.4581904761904762,
      "grad_norm": 0.02990667335689068,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4086246490478516,
      "step": 9622
    },
    {
      "epoch": 0.4582857142857143,
      "grad_norm": 0.028409266844391823,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4185707569122314,
      "step": 9624
    },
    {
      "epoch": 0.4583809523809524,
      "grad_norm": 0.026928888633847237,
      "learning_rate": 0.024000000208616257,
      "loss": 2.405447483062744,
      "step": 9626
    },
    {
      "epoch": 0.4584761904761905,
      "grad_norm": 0.029845738783478737,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4026927947998047,
      "step": 9628
    },
    {
      "epoch": 0.4585714285714286,
      "grad_norm": 0.028702422976493835,
      "learning_rate": 0.024000000208616257,
      "loss": 2.395643711090088,
      "step": 9630
    },
    {
      "epoch": 0.45866666666666667,
      "grad_norm": 0.027479980140924454,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3961575031280518,
      "step": 9632
    },
    {
      "epoch": 0.45876190476190476,
      "grad_norm": 0.0297574233263731,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3752875328063965,
      "step": 9634
    },
    {
      "epoch": 0.45885714285714285,
      "grad_norm": 0.02707689441740513,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4272255897521973,
      "step": 9636
    },
    {
      "epoch": 0.45895238095238095,
      "grad_norm": 0.030102115124464035,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4044361114501953,
      "step": 9638
    },
    {
      "epoch": 0.45904761904761904,
      "grad_norm": 0.029613139107823372,
      "learning_rate": 0.024000000208616257,
      "loss": 2.458073139190674,
      "step": 9640
    },
    {
      "epoch": 0.45914285714285713,
      "grad_norm": 0.0299572441726923,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4113402366638184,
      "step": 9642
    },
    {
      "epoch": 0.4592380952380952,
      "grad_norm": 0.03133881464600563,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3938775062561035,
      "step": 9644
    },
    {
      "epoch": 0.4593333333333333,
      "grad_norm": 0.027347762137651443,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384188652038574,
      "step": 9646
    },
    {
      "epoch": 0.4594285714285714,
      "grad_norm": 0.027912719175219536,
      "learning_rate": 0.024000000208616257,
      "loss": 2.425873279571533,
      "step": 9648
    },
    {
      "epoch": 0.4595238095238095,
      "grad_norm": 0.029102273285388947,
      "learning_rate": 0.024000000208616257,
      "loss": 2.428652286529541,
      "step": 9650
    },
    {
      "epoch": 0.4596190476190476,
      "grad_norm": 0.028538865968585014,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401113510131836,
      "step": 9652
    },
    {
      "epoch": 0.45971428571428574,
      "grad_norm": 0.02748601883649826,
      "learning_rate": 0.024000000208616257,
      "loss": 2.379128932952881,
      "step": 9654
    },
    {
      "epoch": 0.45980952380952383,
      "grad_norm": 0.028702300041913986,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3759827613830566,
      "step": 9656
    },
    {
      "epoch": 0.4599047619047619,
      "grad_norm": 0.03286690637469292,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3750624656677246,
      "step": 9658
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.027432167902588844,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4118542671203613,
      "step": 9660
    },
    {
      "epoch": 0.4600952380952381,
      "grad_norm": 0.0292705986648798,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3827476501464844,
      "step": 9662
    },
    {
      "epoch": 0.4601904761904762,
      "grad_norm": 0.028063638135790825,
      "learning_rate": 0.024000000208616257,
      "loss": 2.441871166229248,
      "step": 9664
    },
    {
      "epoch": 0.4602857142857143,
      "grad_norm": 0.02958506904542446,
      "learning_rate": 0.024000000208616257,
      "loss": 2.412736415863037,
      "step": 9666
    },
    {
      "epoch": 0.4603809523809524,
      "grad_norm": 0.03151559457182884,
      "learning_rate": 0.024000000208616257,
      "loss": 2.479234218597412,
      "step": 9668
    },
    {
      "epoch": 0.4604761904761905,
      "grad_norm": 0.028072070330381393,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4003896713256836,
      "step": 9670
    },
    {
      "epoch": 0.4605714285714286,
      "grad_norm": 0.028879625722765923,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4045653343200684,
      "step": 9672
    },
    {
      "epoch": 0.46066666666666667,
      "grad_norm": 0.029464775696396828,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4490318298339844,
      "step": 9674
    },
    {
      "epoch": 0.46076190476190476,
      "grad_norm": 0.02812976948916912,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4104185104370117,
      "step": 9676
    },
    {
      "epoch": 0.46085714285714285,
      "grad_norm": 0.02979235164821148,
      "learning_rate": 0.024000000208616257,
      "loss": 2.389209032058716,
      "step": 9678
    },
    {
      "epoch": 0.46095238095238095,
      "grad_norm": 0.029084114357829094,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3891959190368652,
      "step": 9680
    },
    {
      "epoch": 0.46104761904761904,
      "grad_norm": 0.026826409623026848,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4062013626098633,
      "step": 9682
    },
    {
      "epoch": 0.46114285714285713,
      "grad_norm": 0.027682090178132057,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3799524307250977,
      "step": 9684
    },
    {
      "epoch": 0.4612380952380952,
      "grad_norm": 0.030326949432492256,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4147942066192627,
      "step": 9686
    },
    {
      "epoch": 0.4613333333333333,
      "grad_norm": 0.03130254149436951,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3786330223083496,
      "step": 9688
    },
    {
      "epoch": 0.4614285714285714,
      "grad_norm": 0.03372962400317192,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4513511657714844,
      "step": 9690
    },
    {
      "epoch": 0.4615238095238095,
      "grad_norm": 0.03526012971997261,
      "learning_rate": 0.024000000208616257,
      "loss": 2.427015542984009,
      "step": 9692
    },
    {
      "epoch": 0.4616190476190476,
      "grad_norm": 0.03287767618894577,
      "learning_rate": 0.024000000208616257,
      "loss": 2.454249858856201,
      "step": 9694
    },
    {
      "epoch": 0.4617142857142857,
      "grad_norm": 0.028745340183377266,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4227333068847656,
      "step": 9696
    },
    {
      "epoch": 0.46180952380952384,
      "grad_norm": 0.029446735978126526,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4186789989471436,
      "step": 9698
    },
    {
      "epoch": 0.46190476190476193,
      "grad_norm": 0.027752596884965897,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4097514152526855,
      "step": 9700
    },
    {
      "epoch": 0.462,
      "grad_norm": 0.026990892365574837,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4137215614318848,
      "step": 9702
    },
    {
      "epoch": 0.4620952380952381,
      "grad_norm": 0.027844766154885292,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3930788040161133,
      "step": 9704
    },
    {
      "epoch": 0.4621904761904762,
      "grad_norm": 0.02752419002354145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.410269021987915,
      "step": 9706
    },
    {
      "epoch": 0.4622857142857143,
      "grad_norm": 0.02817031927406788,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3947248458862305,
      "step": 9708
    },
    {
      "epoch": 0.4623809523809524,
      "grad_norm": 0.03267033398151398,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4106931686401367,
      "step": 9710
    },
    {
      "epoch": 0.4624761904761905,
      "grad_norm": 0.030359597876667976,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4289374351501465,
      "step": 9712
    },
    {
      "epoch": 0.4625714285714286,
      "grad_norm": 0.028795715421438217,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4231770038604736,
      "step": 9714
    },
    {
      "epoch": 0.46266666666666667,
      "grad_norm": 0.02912251465022564,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4293136596679688,
      "step": 9716
    },
    {
      "epoch": 0.46276190476190476,
      "grad_norm": 0.03133673965930939,
      "learning_rate": 0.024000000208616257,
      "loss": 2.453528881072998,
      "step": 9718
    },
    {
      "epoch": 0.46285714285714286,
      "grad_norm": 0.027860889211297035,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401860237121582,
      "step": 9720
    },
    {
      "epoch": 0.46295238095238095,
      "grad_norm": 0.030594371259212494,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4490561485290527,
      "step": 9722
    },
    {
      "epoch": 0.46304761904761904,
      "grad_norm": 0.03640897572040558,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3737952709198,
      "step": 9724
    },
    {
      "epoch": 0.46314285714285713,
      "grad_norm": 0.03470343351364136,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4211573600769043,
      "step": 9726
    },
    {
      "epoch": 0.4632380952380952,
      "grad_norm": 0.0335831381380558,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4340081214904785,
      "step": 9728
    },
    {
      "epoch": 0.4633333333333333,
      "grad_norm": 0.029743408784270287,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4091577529907227,
      "step": 9730
    },
    {
      "epoch": 0.4634285714285714,
      "grad_norm": 0.028803130611777306,
      "learning_rate": 0.024000000208616257,
      "loss": 2.438840866088867,
      "step": 9732
    },
    {
      "epoch": 0.4635238095238095,
      "grad_norm": 0.02830471470952034,
      "learning_rate": 0.024000000208616257,
      "loss": 2.429544448852539,
      "step": 9734
    },
    {
      "epoch": 0.4636190476190476,
      "grad_norm": 0.028163528069853783,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4075613021850586,
      "step": 9736
    },
    {
      "epoch": 0.4637142857142857,
      "grad_norm": 0.02927687205374241,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4215495586395264,
      "step": 9738
    },
    {
      "epoch": 0.4638095238095238,
      "grad_norm": 0.030236592516303062,
      "learning_rate": 0.024000000208616257,
      "loss": 2.435542583465576,
      "step": 9740
    },
    {
      "epoch": 0.46390476190476193,
      "grad_norm": 0.02805175818502903,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4077186584472656,
      "step": 9742
    },
    {
      "epoch": 0.464,
      "grad_norm": 0.027308957651257515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.407886028289795,
      "step": 9744
    },
    {
      "epoch": 0.4640952380952381,
      "grad_norm": 0.028369860723614693,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4117960929870605,
      "step": 9746
    },
    {
      "epoch": 0.4641904761904762,
      "grad_norm": 0.028459394350647926,
      "learning_rate": 0.024000000208616257,
      "loss": 2.421200752258301,
      "step": 9748
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 0.027553565800189972,
      "learning_rate": 0.024000000208616257,
      "loss": 2.419936418533325,
      "step": 9750
    },
    {
      "epoch": 0.4643809523809524,
      "grad_norm": 0.027798959985375404,
      "learning_rate": 0.024000000208616257,
      "loss": 2.433480739593506,
      "step": 9752
    },
    {
      "epoch": 0.4644761904761905,
      "grad_norm": 0.027961814776062965,
      "learning_rate": 0.024000000208616257,
      "loss": 2.393953561782837,
      "step": 9754
    },
    {
      "epoch": 0.4645714285714286,
      "grad_norm": 0.027384785935282707,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4259464740753174,
      "step": 9756
    },
    {
      "epoch": 0.4646666666666667,
      "grad_norm": 0.032850634306669235,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4124345779418945,
      "step": 9758
    },
    {
      "epoch": 0.46476190476190476,
      "grad_norm": 0.03907986357808113,
      "learning_rate": 0.024000000208616257,
      "loss": 2.381958246231079,
      "step": 9760
    },
    {
      "epoch": 0.46485714285714286,
      "grad_norm": 0.035401783883571625,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4172120094299316,
      "step": 9762
    },
    {
      "epoch": 0.46495238095238095,
      "grad_norm": 0.028843175619840622,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4277195930480957,
      "step": 9764
    },
    {
      "epoch": 0.46504761904761904,
      "grad_norm": 0.027424784377217293,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4315013885498047,
      "step": 9766
    },
    {
      "epoch": 0.46514285714285714,
      "grad_norm": 0.0287105031311512,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3974082469940186,
      "step": 9768
    },
    {
      "epoch": 0.46523809523809523,
      "grad_norm": 0.027529843151569366,
      "learning_rate": 0.024000000208616257,
      "loss": 2.394972801208496,
      "step": 9770
    },
    {
      "epoch": 0.4653333333333333,
      "grad_norm": 0.02898828312754631,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4103245735168457,
      "step": 9772
    },
    {
      "epoch": 0.4654285714285714,
      "grad_norm": 0.02782541885972023,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4231138229370117,
      "step": 9774
    },
    {
      "epoch": 0.4655238095238095,
      "grad_norm": 0.027290141209959984,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3970236778259277,
      "step": 9776
    },
    {
      "epoch": 0.4656190476190476,
      "grad_norm": 0.0297524593770504,
      "learning_rate": 0.024000000208616257,
      "loss": 2.388180732727051,
      "step": 9778
    },
    {
      "epoch": 0.4657142857142857,
      "grad_norm": 0.027525220066308975,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3948302268981934,
      "step": 9780
    },
    {
      "epoch": 0.4658095238095238,
      "grad_norm": 0.02752193622291088,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3952696323394775,
      "step": 9782
    },
    {
      "epoch": 0.4659047619047619,
      "grad_norm": 0.026625387370586395,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4264273643493652,
      "step": 9784
    },
    {
      "epoch": 0.466,
      "grad_norm": 0.02865925244987011,
      "learning_rate": 0.024000000208616257,
      "loss": 2.443699359893799,
      "step": 9786
    },
    {
      "epoch": 0.4660952380952381,
      "grad_norm": 0.028792914003133774,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3822336196899414,
      "step": 9788
    },
    {
      "epoch": 0.4661904761904762,
      "grad_norm": 0.027698436751961708,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384181022644043,
      "step": 9790
    },
    {
      "epoch": 0.4662857142857143,
      "grad_norm": 0.02840881422162056,
      "learning_rate": 0.024000000208616257,
      "loss": 2.404430389404297,
      "step": 9792
    },
    {
      "epoch": 0.4663809523809524,
      "grad_norm": 0.02724684588611126,
      "learning_rate": 0.024000000208616257,
      "loss": 2.428399085998535,
      "step": 9794
    },
    {
      "epoch": 0.4664761904761905,
      "grad_norm": 0.02851618267595768,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3953495025634766,
      "step": 9796
    },
    {
      "epoch": 0.4665714285714286,
      "grad_norm": 0.027589641511440277,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3903379440307617,
      "step": 9798
    },
    {
      "epoch": 0.4666666666666667,
      "grad_norm": 0.028072193264961243,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3746042251586914,
      "step": 9800
    },
    {
      "epoch": 0.46676190476190477,
      "grad_norm": 0.02898465469479561,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3924190998077393,
      "step": 9802
    },
    {
      "epoch": 0.46685714285714286,
      "grad_norm": 0.031229810789227486,
      "learning_rate": 0.024000000208616257,
      "loss": 2.421272039413452,
      "step": 9804
    },
    {
      "epoch": 0.46695238095238095,
      "grad_norm": 0.027267800644040108,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4338417053222656,
      "step": 9806
    },
    {
      "epoch": 0.46704761904761904,
      "grad_norm": 0.027654821053147316,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4098522663116455,
      "step": 9808
    },
    {
      "epoch": 0.46714285714285714,
      "grad_norm": 0.027849221602082253,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3878118991851807,
      "step": 9810
    },
    {
      "epoch": 0.46723809523809523,
      "grad_norm": 0.0328669510781765,
      "learning_rate": 0.024000000208616257,
      "loss": 2.416998863220215,
      "step": 9812
    },
    {
      "epoch": 0.4673333333333333,
      "grad_norm": 0.02861207351088524,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4045770168304443,
      "step": 9814
    },
    {
      "epoch": 0.4674285714285714,
      "grad_norm": 0.03166454657912254,
      "learning_rate": 0.024000000208616257,
      "loss": 2.421844482421875,
      "step": 9816
    },
    {
      "epoch": 0.4675238095238095,
      "grad_norm": 0.02635366842150688,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4056246280670166,
      "step": 9818
    },
    {
      "epoch": 0.4676190476190476,
      "grad_norm": 0.026935560628771782,
      "learning_rate": 0.024000000208616257,
      "loss": 2.417201519012451,
      "step": 9820
    },
    {
      "epoch": 0.4677142857142857,
      "grad_norm": 0.026827208697795868,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4266419410705566,
      "step": 9822
    },
    {
      "epoch": 0.4678095238095238,
      "grad_norm": 0.026519855484366417,
      "learning_rate": 0.024000000208616257,
      "loss": 2.419062614440918,
      "step": 9824
    },
    {
      "epoch": 0.4679047619047619,
      "grad_norm": 0.02895374409854412,
      "learning_rate": 0.024000000208616257,
      "loss": 2.371206521987915,
      "step": 9826
    },
    {
      "epoch": 0.468,
      "grad_norm": 0.028737282380461693,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4006173610687256,
      "step": 9828
    },
    {
      "epoch": 0.4680952380952381,
      "grad_norm": 0.02778460457921028,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4113423824310303,
      "step": 9830
    },
    {
      "epoch": 0.4681904761904762,
      "grad_norm": 0.02690371312201023,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3814520835876465,
      "step": 9832
    },
    {
      "epoch": 0.4682857142857143,
      "grad_norm": 0.02867203764617443,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4217982292175293,
      "step": 9834
    },
    {
      "epoch": 0.4683809523809524,
      "grad_norm": 0.027330975979566574,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4113473892211914,
      "step": 9836
    },
    {
      "epoch": 0.4684761904761905,
      "grad_norm": 0.027006328105926514,
      "learning_rate": 0.024000000208616257,
      "loss": 2.419776439666748,
      "step": 9838
    },
    {
      "epoch": 0.4685714285714286,
      "grad_norm": 0.03005649521946907,
      "learning_rate": 0.024000000208616257,
      "loss": 2.379434823989868,
      "step": 9840
    },
    {
      "epoch": 0.4686666666666667,
      "grad_norm": 0.026849761605262756,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3864314556121826,
      "step": 9842
    },
    {
      "epoch": 0.46876190476190477,
      "grad_norm": 0.028481347486376762,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4037342071533203,
      "step": 9844
    },
    {
      "epoch": 0.46885714285714286,
      "grad_norm": 0.029926519840955734,
      "learning_rate": 0.024000000208616257,
      "loss": 2.397359848022461,
      "step": 9846
    },
    {
      "epoch": 0.46895238095238095,
      "grad_norm": 0.028411971405148506,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3800208568573,
      "step": 9848
    },
    {
      "epoch": 0.46904761904761905,
      "grad_norm": 0.0330529659986496,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4032797813415527,
      "step": 9850
    },
    {
      "epoch": 0.46914285714285714,
      "grad_norm": 0.027527455240488052,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3597657680511475,
      "step": 9852
    },
    {
      "epoch": 0.46923809523809523,
      "grad_norm": 0.027093110606074333,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4127449989318848,
      "step": 9854
    },
    {
      "epoch": 0.4693333333333333,
      "grad_norm": 0.029034392908215523,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3762075901031494,
      "step": 9856
    },
    {
      "epoch": 0.4694285714285714,
      "grad_norm": 0.032121945172548294,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3932600021362305,
      "step": 9858
    },
    {
      "epoch": 0.4695238095238095,
      "grad_norm": 0.027836289256811142,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3958420753479004,
      "step": 9860
    },
    {
      "epoch": 0.4696190476190476,
      "grad_norm": 0.028180699795484543,
      "learning_rate": 0.024000000208616257,
      "loss": 2.400053024291992,
      "step": 9862
    },
    {
      "epoch": 0.4697142857142857,
      "grad_norm": 0.027426665648818016,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4358956813812256,
      "step": 9864
    },
    {
      "epoch": 0.4698095238095238,
      "grad_norm": 0.028130456805229187,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3990349769592285,
      "step": 9866
    },
    {
      "epoch": 0.4699047619047619,
      "grad_norm": 0.032637231051921844,
      "learning_rate": 0.024000000208616257,
      "loss": 2.393807888031006,
      "step": 9868
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.030466215685009956,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3856711387634277,
      "step": 9870
    },
    {
      "epoch": 0.4700952380952381,
      "grad_norm": 0.027393050491809845,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3828086853027344,
      "step": 9872
    },
    {
      "epoch": 0.4701904761904762,
      "grad_norm": 0.027382301166653633,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3785622119903564,
      "step": 9874
    },
    {
      "epoch": 0.4702857142857143,
      "grad_norm": 0.02788218855857849,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3982553482055664,
      "step": 9876
    },
    {
      "epoch": 0.4703809523809524,
      "grad_norm": 0.027489084750413895,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4008800983428955,
      "step": 9878
    },
    {
      "epoch": 0.4704761904761905,
      "grad_norm": 0.028329959139227867,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4262378215789795,
      "step": 9880
    },
    {
      "epoch": 0.4705714285714286,
      "grad_norm": 0.02758204936981201,
      "learning_rate": 0.024000000208616257,
      "loss": 2.389723777770996,
      "step": 9882
    },
    {
      "epoch": 0.4706666666666667,
      "grad_norm": 0.02782687358558178,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3845598697662354,
      "step": 9884
    },
    {
      "epoch": 0.47076190476190477,
      "grad_norm": 0.02746100351214409,
      "learning_rate": 0.024000000208616257,
      "loss": 2.407313346862793,
      "step": 9886
    },
    {
      "epoch": 0.47085714285714286,
      "grad_norm": 0.0273442342877388,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3965110778808594,
      "step": 9888
    },
    {
      "epoch": 0.47095238095238096,
      "grad_norm": 0.026217283681035042,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3792271614074707,
      "step": 9890
    },
    {
      "epoch": 0.47104761904761905,
      "grad_norm": 0.027188045904040337,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3533053398132324,
      "step": 9892
    },
    {
      "epoch": 0.47114285714285714,
      "grad_norm": 0.02856392227113247,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3813014030456543,
      "step": 9894
    },
    {
      "epoch": 0.47123809523809523,
      "grad_norm": 0.02760476805269718,
      "learning_rate": 0.024000000208616257,
      "loss": 2.389249563217163,
      "step": 9896
    },
    {
      "epoch": 0.4713333333333333,
      "grad_norm": 0.028427202254533768,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4059650897979736,
      "step": 9898
    },
    {
      "epoch": 0.4714285714285714,
      "grad_norm": 0.028976406902074814,
      "learning_rate": 0.024000000208616257,
      "loss": 2.395256519317627,
      "step": 9900
    },
    {
      "epoch": 0.4715238095238095,
      "grad_norm": 0.029843473806977272,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3877458572387695,
      "step": 9902
    },
    {
      "epoch": 0.4716190476190476,
      "grad_norm": 0.027722317725419998,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384848117828369,
      "step": 9904
    },
    {
      "epoch": 0.4717142857142857,
      "grad_norm": 0.027992477640509605,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38270902633667,
      "step": 9906
    },
    {
      "epoch": 0.4718095238095238,
      "grad_norm": 0.02803727239370346,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3942718505859375,
      "step": 9908
    },
    {
      "epoch": 0.4719047619047619,
      "grad_norm": 0.03201549872756004,
      "learning_rate": 0.024000000208616257,
      "loss": 2.388650894165039,
      "step": 9910
    },
    {
      "epoch": 0.472,
      "grad_norm": 0.02901902049779892,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3584015369415283,
      "step": 9912
    },
    {
      "epoch": 0.47209523809523807,
      "grad_norm": 0.028400003910064697,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4226434230804443,
      "step": 9914
    },
    {
      "epoch": 0.4721904761904762,
      "grad_norm": 0.027030253782868385,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382664203643799,
      "step": 9916
    },
    {
      "epoch": 0.4722857142857143,
      "grad_norm": 0.029758557677268982,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3798375129699707,
      "step": 9918
    },
    {
      "epoch": 0.4723809523809524,
      "grad_norm": 0.026546809822320938,
      "learning_rate": 0.024000000208616257,
      "loss": 2.354029655456543,
      "step": 9920
    },
    {
      "epoch": 0.4724761904761905,
      "grad_norm": 0.029138777405023575,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398613452911377,
      "step": 9922
    },
    {
      "epoch": 0.4725714285714286,
      "grad_norm": 0.029673699289560318,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3799705505371094,
      "step": 9924
    },
    {
      "epoch": 0.4726666666666667,
      "grad_norm": 0.02682509459555149,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3747687339782715,
      "step": 9926
    },
    {
      "epoch": 0.47276190476190477,
      "grad_norm": 0.03200381249189377,
      "learning_rate": 0.024000000208616257,
      "loss": 2.379835367202759,
      "step": 9928
    },
    {
      "epoch": 0.47285714285714286,
      "grad_norm": 0.028869330883026123,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390997886657715,
      "step": 9930
    },
    {
      "epoch": 0.47295238095238096,
      "grad_norm": 0.026885351166129112,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3756251335144043,
      "step": 9932
    },
    {
      "epoch": 0.47304761904761905,
      "grad_norm": 0.03048570826649666,
      "learning_rate": 0.024000000208616257,
      "loss": 2.404616117477417,
      "step": 9934
    },
    {
      "epoch": 0.47314285714285714,
      "grad_norm": 0.02878928929567337,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4151835441589355,
      "step": 9936
    },
    {
      "epoch": 0.47323809523809524,
      "grad_norm": 0.028778493404388428,
      "learning_rate": 0.024000000208616257,
      "loss": 2.419722557067871,
      "step": 9938
    },
    {
      "epoch": 0.47333333333333333,
      "grad_norm": 0.02844041958451271,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3810439109802246,
      "step": 9940
    },
    {
      "epoch": 0.4734285714285714,
      "grad_norm": 0.027770154178142548,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4001097679138184,
      "step": 9942
    },
    {
      "epoch": 0.4735238095238095,
      "grad_norm": 0.032141733914613724,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392026424407959,
      "step": 9944
    },
    {
      "epoch": 0.4736190476190476,
      "grad_norm": 0.029453713446855545,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392915725708008,
      "step": 9946
    },
    {
      "epoch": 0.4737142857142857,
      "grad_norm": 0.03274424001574516,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3759260177612305,
      "step": 9948
    },
    {
      "epoch": 0.4738095238095238,
      "grad_norm": 0.028404146432876587,
      "learning_rate": 0.024000000208616257,
      "loss": 2.410867214202881,
      "step": 9950
    },
    {
      "epoch": 0.4739047619047619,
      "grad_norm": 0.028306415304541588,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3642899990081787,
      "step": 9952
    },
    {
      "epoch": 0.474,
      "grad_norm": 0.027273990213871002,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398806095123291,
      "step": 9954
    },
    {
      "epoch": 0.47409523809523807,
      "grad_norm": 0.02936621755361557,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3682875633239746,
      "step": 9956
    },
    {
      "epoch": 0.4741904761904762,
      "grad_norm": 0.030001014471054077,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3932385444641113,
      "step": 9958
    },
    {
      "epoch": 0.4742857142857143,
      "grad_norm": 0.03024931624531746,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4080052375793457,
      "step": 9960
    },
    {
      "epoch": 0.4743809523809524,
      "grad_norm": 0.031176205724477768,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3820619583129883,
      "step": 9962
    },
    {
      "epoch": 0.4744761904761905,
      "grad_norm": 0.03262626752257347,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384397506713867,
      "step": 9964
    },
    {
      "epoch": 0.4745714285714286,
      "grad_norm": 0.027785642072558403,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401827573776245,
      "step": 9966
    },
    {
      "epoch": 0.4746666666666667,
      "grad_norm": 0.027613768354058266,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385213851928711,
      "step": 9968
    },
    {
      "epoch": 0.4747619047619048,
      "grad_norm": 0.027302272617816925,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390568733215332,
      "step": 9970
    },
    {
      "epoch": 0.47485714285714287,
      "grad_norm": 0.02754071354866028,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3981831073760986,
      "step": 9972
    },
    {
      "epoch": 0.47495238095238096,
      "grad_norm": 0.02673739194869995,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3774538040161133,
      "step": 9974
    },
    {
      "epoch": 0.47504761904761905,
      "grad_norm": 0.02807868830859661,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4339356422424316,
      "step": 9976
    },
    {
      "epoch": 0.47514285714285714,
      "grad_norm": 0.02727210894227028,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3717041015625,
      "step": 9978
    },
    {
      "epoch": 0.47523809523809524,
      "grad_norm": 0.028389863669872284,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3940269947052,
      "step": 9980
    },
    {
      "epoch": 0.47533333333333333,
      "grad_norm": 0.02842022106051445,
      "learning_rate": 0.024000000208616257,
      "loss": 2.36936616897583,
      "step": 9982
    },
    {
      "epoch": 0.4754285714285714,
      "grad_norm": 0.028652695938944817,
      "learning_rate": 0.024000000208616257,
      "loss": 2.362590789794922,
      "step": 9984
    },
    {
      "epoch": 0.4755238095238095,
      "grad_norm": 0.027350710704922676,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3770556449890137,
      "step": 9986
    },
    {
      "epoch": 0.4756190476190476,
      "grad_norm": 0.026875663548707962,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4053473472595215,
      "step": 9988
    },
    {
      "epoch": 0.4757142857142857,
      "grad_norm": 0.02816944755613804,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4024271965026855,
      "step": 9990
    },
    {
      "epoch": 0.4758095238095238,
      "grad_norm": 0.028403881937265396,
      "learning_rate": 0.024000000208616257,
      "loss": 2.41587495803833,
      "step": 9992
    },
    {
      "epoch": 0.4759047619047619,
      "grad_norm": 0.030948694795370102,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3881754875183105,
      "step": 9994
    },
    {
      "epoch": 0.476,
      "grad_norm": 0.02736280858516693,
      "learning_rate": 0.024000000208616257,
      "loss": 2.379861354827881,
      "step": 9996
    },
    {
      "epoch": 0.47609523809523807,
      "grad_norm": 0.02905181795358658,
      "learning_rate": 0.024000000208616257,
      "loss": 2.409634590148926,
      "step": 9998
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.03448755666613579,
      "learning_rate": 0.024000000208616257,
      "loss": 2.362757682800293,
      "step": 10000
    },
    {
      "epoch": 0.4762857142857143,
      "grad_norm": 0.031099481508135796,
      "learning_rate": 0.024000000208616257,
      "loss": 2.395456552505493,
      "step": 10002
    },
    {
      "epoch": 0.4763809523809524,
      "grad_norm": 0.027221621945500374,
      "learning_rate": 0.024000000208616257,
      "loss": 2.387814998626709,
      "step": 10004
    },
    {
      "epoch": 0.4764761904761905,
      "grad_norm": 0.02771640755236149,
      "learning_rate": 0.024000000208616257,
      "loss": 2.414316415786743,
      "step": 10006
    },
    {
      "epoch": 0.4765714285714286,
      "grad_norm": 0.027244526892900467,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3965513706207275,
      "step": 10008
    },
    {
      "epoch": 0.4766666666666667,
      "grad_norm": 0.026610156521201134,
      "learning_rate": 0.024000000208616257,
      "loss": 2.342679023742676,
      "step": 10010
    },
    {
      "epoch": 0.4767619047619048,
      "grad_norm": 0.02639857865869999,
      "learning_rate": 0.024000000208616257,
      "loss": 2.425063371658325,
      "step": 10012
    },
    {
      "epoch": 0.47685714285714287,
      "grad_norm": 0.03007633052766323,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3571979999542236,
      "step": 10014
    },
    {
      "epoch": 0.47695238095238096,
      "grad_norm": 0.026919908821582794,
      "learning_rate": 0.024000000208616257,
      "loss": 2.397088050842285,
      "step": 10016
    },
    {
      "epoch": 0.47704761904761905,
      "grad_norm": 0.026890620589256287,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3682713508605957,
      "step": 10018
    },
    {
      "epoch": 0.47714285714285715,
      "grad_norm": 0.027897093445062637,
      "learning_rate": 0.024000000208616257,
      "loss": 2.373136043548584,
      "step": 10020
    },
    {
      "epoch": 0.47723809523809524,
      "grad_norm": 0.02875993773341179,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4095726013183594,
      "step": 10022
    },
    {
      "epoch": 0.47733333333333333,
      "grad_norm": 0.03217899054288864,
      "learning_rate": 0.024000000208616257,
      "loss": 2.41660475730896,
      "step": 10024
    },
    {
      "epoch": 0.4774285714285714,
      "grad_norm": 0.029196428135037422,
      "learning_rate": 0.024000000208616257,
      "loss": 2.349377155303955,
      "step": 10026
    },
    {
      "epoch": 0.4775238095238095,
      "grad_norm": 0.031200025230646133,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3573763370513916,
      "step": 10028
    },
    {
      "epoch": 0.4776190476190476,
      "grad_norm": 0.03319297730922699,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3980531692504883,
      "step": 10030
    },
    {
      "epoch": 0.4777142857142857,
      "grad_norm": 0.028772437945008278,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3570303916931152,
      "step": 10032
    },
    {
      "epoch": 0.4778095238095238,
      "grad_norm": 0.029931947588920593,
      "learning_rate": 0.024000000208616257,
      "loss": 2.407946825027466,
      "step": 10034
    },
    {
      "epoch": 0.4779047619047619,
      "grad_norm": 0.027142351493239403,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3768985271453857,
      "step": 10036
    },
    {
      "epoch": 0.478,
      "grad_norm": 0.02707965485751629,
      "learning_rate": 0.024000000208616257,
      "loss": 2.381023406982422,
      "step": 10038
    },
    {
      "epoch": 0.4780952380952381,
      "grad_norm": 0.02844320423901081,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396423578262329,
      "step": 10040
    },
    {
      "epoch": 0.47819047619047617,
      "grad_norm": 0.02750728465616703,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3781023025512695,
      "step": 10042
    },
    {
      "epoch": 0.47828571428571426,
      "grad_norm": 0.02619764767587185,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3875579833984375,
      "step": 10044
    },
    {
      "epoch": 0.4783809523809524,
      "grad_norm": 0.02995794080197811,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4066715240478516,
      "step": 10046
    },
    {
      "epoch": 0.4784761904761905,
      "grad_norm": 0.02667129784822464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3738455772399902,
      "step": 10048
    },
    {
      "epoch": 0.4785714285714286,
      "grad_norm": 0.027780622243881226,
      "learning_rate": 0.024000000208616257,
      "loss": 2.419355869293213,
      "step": 10050
    },
    {
      "epoch": 0.4786666666666667,
      "grad_norm": 0.027933992445468903,
      "learning_rate": 0.024000000208616257,
      "loss": 2.409144639968872,
      "step": 10052
    },
    {
      "epoch": 0.4787619047619048,
      "grad_norm": 0.02624589577317238,
      "learning_rate": 0.024000000208616257,
      "loss": 2.372213840484619,
      "step": 10054
    },
    {
      "epoch": 0.47885714285714287,
      "grad_norm": 0.030824007466435432,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3850021362304688,
      "step": 10056
    },
    {
      "epoch": 0.47895238095238096,
      "grad_norm": 0.04975249618291855,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3759756088256836,
      "step": 10058
    },
    {
      "epoch": 0.47904761904761906,
      "grad_norm": 0.02735336311161518,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3726749420166016,
      "step": 10060
    },
    {
      "epoch": 0.47914285714285715,
      "grad_norm": 0.026581650599837303,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390812873840332,
      "step": 10062
    },
    {
      "epoch": 0.47923809523809524,
      "grad_norm": 0.02958527021110058,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380431652069092,
      "step": 10064
    },
    {
      "epoch": 0.47933333333333333,
      "grad_norm": 0.030373990535736084,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3667640686035156,
      "step": 10066
    },
    {
      "epoch": 0.4794285714285714,
      "grad_norm": 0.027469443157315254,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4038615226745605,
      "step": 10068
    },
    {
      "epoch": 0.4795238095238095,
      "grad_norm": 0.02719299867749214,
      "learning_rate": 0.024000000208616257,
      "loss": 2.342175006866455,
      "step": 10070
    },
    {
      "epoch": 0.4796190476190476,
      "grad_norm": 0.030503304675221443,
      "learning_rate": 0.024000000208616257,
      "loss": 2.378537893295288,
      "step": 10072
    },
    {
      "epoch": 0.4797142857142857,
      "grad_norm": 0.02689477801322937,
      "learning_rate": 0.024000000208616257,
      "loss": 2.346190929412842,
      "step": 10074
    },
    {
      "epoch": 0.4798095238095238,
      "grad_norm": 0.030311236158013344,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3941919803619385,
      "step": 10076
    },
    {
      "epoch": 0.4799047619047619,
      "grad_norm": 0.027020586654543877,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3604700565338135,
      "step": 10078
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.029461253434419632,
      "learning_rate": 0.024000000208616257,
      "loss": 2.387509346008301,
      "step": 10080
    },
    {
      "epoch": 0.4800952380952381,
      "grad_norm": 0.026926415041089058,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401183605194092,
      "step": 10082
    },
    {
      "epoch": 0.48019047619047617,
      "grad_norm": 0.02852713316679001,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4117960929870605,
      "step": 10084
    },
    {
      "epoch": 0.48028571428571426,
      "grad_norm": 0.030431294813752174,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3548054695129395,
      "step": 10086
    },
    {
      "epoch": 0.4803809523809524,
      "grad_norm": 0.03066428378224373,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4255194664001465,
      "step": 10088
    },
    {
      "epoch": 0.4804761904761905,
      "grad_norm": 0.02827756106853485,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3899855613708496,
      "step": 10090
    },
    {
      "epoch": 0.4805714285714286,
      "grad_norm": 0.02837781049311161,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3861241340637207,
      "step": 10092
    },
    {
      "epoch": 0.4806666666666667,
      "grad_norm": 0.028624994680285454,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380371570587158,
      "step": 10094
    },
    {
      "epoch": 0.4807619047619048,
      "grad_norm": 0.027287524193525314,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3760323524475098,
      "step": 10096
    },
    {
      "epoch": 0.48085714285714287,
      "grad_norm": 0.027077743783593178,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3969521522521973,
      "step": 10098
    },
    {
      "epoch": 0.48095238095238096,
      "grad_norm": 0.03918096795678139,
      "learning_rate": 0.024000000208616257,
      "loss": 2.387248992919922,
      "step": 10100
    },
    {
      "epoch": 0.48104761904761906,
      "grad_norm": 0.0328391008079052,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3877406120300293,
      "step": 10102
    },
    {
      "epoch": 0.48114285714285715,
      "grad_norm": 0.03308192268013954,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4203927516937256,
      "step": 10104
    },
    {
      "epoch": 0.48123809523809524,
      "grad_norm": 0.03151126205921173,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4132914543151855,
      "step": 10106
    },
    {
      "epoch": 0.48133333333333334,
      "grad_norm": 0.028975995257496834,
      "learning_rate": 0.024000000208616257,
      "loss": 2.399506092071533,
      "step": 10108
    },
    {
      "epoch": 0.48142857142857143,
      "grad_norm": 0.027203459292650223,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3901867866516113,
      "step": 10110
    },
    {
      "epoch": 0.4815238095238095,
      "grad_norm": 0.027612464502453804,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3984010219573975,
      "step": 10112
    },
    {
      "epoch": 0.4816190476190476,
      "grad_norm": 0.029255075380206108,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3870596885681152,
      "step": 10114
    },
    {
      "epoch": 0.4817142857142857,
      "grad_norm": 0.03142564743757248,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385535478591919,
      "step": 10116
    },
    {
      "epoch": 0.4818095238095238,
      "grad_norm": 0.030324948951601982,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3819799423217773,
      "step": 10118
    },
    {
      "epoch": 0.4819047619047619,
      "grad_norm": 0.033982809633016586,
      "learning_rate": 0.024000000208616257,
      "loss": 2.377683639526367,
      "step": 10120
    },
    {
      "epoch": 0.482,
      "grad_norm": 0.03045128472149372,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392484426498413,
      "step": 10122
    },
    {
      "epoch": 0.4820952380952381,
      "grad_norm": 0.029974374920129776,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3898448944091797,
      "step": 10124
    },
    {
      "epoch": 0.48219047619047617,
      "grad_norm": 0.03177972510457039,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3759841918945312,
      "step": 10126
    },
    {
      "epoch": 0.48228571428571426,
      "grad_norm": 0.027963314205408096,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384392261505127,
      "step": 10128
    },
    {
      "epoch": 0.48238095238095235,
      "grad_norm": 0.02714836224913597,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3831257820129395,
      "step": 10130
    },
    {
      "epoch": 0.4824761904761905,
      "grad_norm": 0.02660280466079712,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3647303581237793,
      "step": 10132
    },
    {
      "epoch": 0.4825714285714286,
      "grad_norm": 0.02706044539809227,
      "learning_rate": 0.024000000208616257,
      "loss": 2.371131420135498,
      "step": 10134
    },
    {
      "epoch": 0.4826666666666667,
      "grad_norm": 0.028194701299071312,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4301764965057373,
      "step": 10136
    },
    {
      "epoch": 0.4827619047619048,
      "grad_norm": 0.028660066425800323,
      "learning_rate": 0.024000000208616257,
      "loss": 2.406299352645874,
      "step": 10138
    },
    {
      "epoch": 0.4828571428571429,
      "grad_norm": 0.02691282145678997,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380547285079956,
      "step": 10140
    },
    {
      "epoch": 0.48295238095238097,
      "grad_norm": 0.02695193886756897,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3613827228546143,
      "step": 10142
    },
    {
      "epoch": 0.48304761904761906,
      "grad_norm": 0.02665434591472149,
      "learning_rate": 0.024000000208616257,
      "loss": 2.342787742614746,
      "step": 10144
    },
    {
      "epoch": 0.48314285714285715,
      "grad_norm": 0.02689075842499733,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4120121002197266,
      "step": 10146
    },
    {
      "epoch": 0.48323809523809524,
      "grad_norm": 0.02799226902425289,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4122424125671387,
      "step": 10148
    },
    {
      "epoch": 0.48333333333333334,
      "grad_norm": 0.026937026530504227,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4061670303344727,
      "step": 10150
    },
    {
      "epoch": 0.48342857142857143,
      "grad_norm": 0.027699975296854973,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3900060653686523,
      "step": 10152
    },
    {
      "epoch": 0.4835238095238095,
      "grad_norm": 0.027510402724146843,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4064788818359375,
      "step": 10154
    },
    {
      "epoch": 0.4836190476190476,
      "grad_norm": 0.027741950005292892,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3524694442749023,
      "step": 10156
    },
    {
      "epoch": 0.4837142857142857,
      "grad_norm": 0.030192816630005836,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3833401203155518,
      "step": 10158
    },
    {
      "epoch": 0.4838095238095238,
      "grad_norm": 0.03033248335123062,
      "learning_rate": 0.024000000208616257,
      "loss": 2.371107578277588,
      "step": 10160
    },
    {
      "epoch": 0.4839047619047619,
      "grad_norm": 0.02868136577308178,
      "learning_rate": 0.024000000208616257,
      "loss": 2.378054141998291,
      "step": 10162
    },
    {
      "epoch": 0.484,
      "grad_norm": 0.029922669753432274,
      "learning_rate": 0.024000000208616257,
      "loss": 2.414125919342041,
      "step": 10164
    },
    {
      "epoch": 0.4840952380952381,
      "grad_norm": 0.02896857261657715,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3873491287231445,
      "step": 10166
    },
    {
      "epoch": 0.48419047619047617,
      "grad_norm": 0.03220432996749878,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3905224800109863,
      "step": 10168
    },
    {
      "epoch": 0.48428571428571426,
      "grad_norm": 0.03295639529824257,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3979153633117676,
      "step": 10170
    },
    {
      "epoch": 0.48438095238095236,
      "grad_norm": 0.028126195073127747,
      "learning_rate": 0.024000000208616257,
      "loss": 2.357306480407715,
      "step": 10172
    },
    {
      "epoch": 0.48447619047619045,
      "grad_norm": 0.027785276994109154,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4028420448303223,
      "step": 10174
    },
    {
      "epoch": 0.4845714285714286,
      "grad_norm": 0.02644316479563713,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3753714561462402,
      "step": 10176
    },
    {
      "epoch": 0.4846666666666667,
      "grad_norm": 0.028828473761677742,
      "learning_rate": 0.024000000208616257,
      "loss": 2.404844284057617,
      "step": 10178
    },
    {
      "epoch": 0.4847619047619048,
      "grad_norm": 0.02913374826312065,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383476972579956,
      "step": 10180
    },
    {
      "epoch": 0.4848571428571429,
      "grad_norm": 0.028568962588906288,
      "learning_rate": 0.024000000208616257,
      "loss": 2.402207851409912,
      "step": 10182
    },
    {
      "epoch": 0.48495238095238097,
      "grad_norm": 0.029462585225701332,
      "learning_rate": 0.024000000208616257,
      "loss": 2.397925615310669,
      "step": 10184
    },
    {
      "epoch": 0.48504761904761906,
      "grad_norm": 0.027329323813319206,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3756608963012695,
      "step": 10186
    },
    {
      "epoch": 0.48514285714285715,
      "grad_norm": 0.03061649203300476,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3940064907073975,
      "step": 10188
    },
    {
      "epoch": 0.48523809523809525,
      "grad_norm": 0.029248856008052826,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4057869911193848,
      "step": 10190
    },
    {
      "epoch": 0.48533333333333334,
      "grad_norm": 0.027735678479075432,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398174285888672,
      "step": 10192
    },
    {
      "epoch": 0.48542857142857143,
      "grad_norm": 0.027309056371450424,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4100871086120605,
      "step": 10194
    },
    {
      "epoch": 0.4855238095238095,
      "grad_norm": 0.029020974412560463,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3965671062469482,
      "step": 10196
    },
    {
      "epoch": 0.4856190476190476,
      "grad_norm": 0.02876860275864601,
      "learning_rate": 0.024000000208616257,
      "loss": 2.414745807647705,
      "step": 10198
    },
    {
      "epoch": 0.4857142857142857,
      "grad_norm": 0.031795866787433624,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4207489490509033,
      "step": 10200
    },
    {
      "epoch": 0.4858095238095238,
      "grad_norm": 0.029908791184425354,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3889646530151367,
      "step": 10202
    },
    {
      "epoch": 0.4859047619047619,
      "grad_norm": 0.026536675170063972,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4028429985046387,
      "step": 10204
    },
    {
      "epoch": 0.486,
      "grad_norm": 0.028548024594783783,
      "learning_rate": 0.024000000208616257,
      "loss": 2.395512104034424,
      "step": 10206
    },
    {
      "epoch": 0.4860952380952381,
      "grad_norm": 0.027985280379652977,
      "learning_rate": 0.024000000208616257,
      "loss": 2.376032829284668,
      "step": 10208
    },
    {
      "epoch": 0.4861904761904762,
      "grad_norm": 0.03454270213842392,
      "learning_rate": 0.024000000208616257,
      "loss": 2.400205612182617,
      "step": 10210
    },
    {
      "epoch": 0.48628571428571427,
      "grad_norm": 0.027781959623098373,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3736801147460938,
      "step": 10212
    },
    {
      "epoch": 0.48638095238095236,
      "grad_norm": 0.028802137821912766,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3977699279785156,
      "step": 10214
    },
    {
      "epoch": 0.48647619047619045,
      "grad_norm": 0.03047909587621689,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4163975715637207,
      "step": 10216
    },
    {
      "epoch": 0.4865714285714286,
      "grad_norm": 0.02823873795568943,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401578187942505,
      "step": 10218
    },
    {
      "epoch": 0.4866666666666667,
      "grad_norm": 0.029094893485307693,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4045052528381348,
      "step": 10220
    },
    {
      "epoch": 0.4867619047619048,
      "grad_norm": 0.026411380618810654,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4160115718841553,
      "step": 10222
    },
    {
      "epoch": 0.4868571428571429,
      "grad_norm": 0.027514252811670303,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385097026824951,
      "step": 10224
    },
    {
      "epoch": 0.48695238095238097,
      "grad_norm": 0.02706778235733509,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4313690662384033,
      "step": 10226
    },
    {
      "epoch": 0.48704761904761906,
      "grad_norm": 0.027516353875398636,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4033517837524414,
      "step": 10228
    },
    {
      "epoch": 0.48714285714285716,
      "grad_norm": 0.02714160457253456,
      "learning_rate": 0.024000000208616257,
      "loss": 2.387263774871826,
      "step": 10230
    },
    {
      "epoch": 0.48723809523809525,
      "grad_norm": 0.02735537849366665,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3928275108337402,
      "step": 10232
    },
    {
      "epoch": 0.48733333333333334,
      "grad_norm": 0.02976968325674534,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401752233505249,
      "step": 10234
    },
    {
      "epoch": 0.48742857142857143,
      "grad_norm": 0.02955271489918232,
      "learning_rate": 0.024000000208616257,
      "loss": 2.408371925354004,
      "step": 10236
    },
    {
      "epoch": 0.4875238095238095,
      "grad_norm": 0.026625744998455048,
      "learning_rate": 0.024000000208616257,
      "loss": 2.378131866455078,
      "step": 10238
    },
    {
      "epoch": 0.4876190476190476,
      "grad_norm": 0.02860495261847973,
      "learning_rate": 0.024000000208616257,
      "loss": 2.402113914489746,
      "step": 10240
    },
    {
      "epoch": 0.4877142857142857,
      "grad_norm": 0.02826939895749092,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3969550132751465,
      "step": 10242
    },
    {
      "epoch": 0.4878095238095238,
      "grad_norm": 0.0305863656103611,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4257216453552246,
      "step": 10244
    },
    {
      "epoch": 0.4879047619047619,
      "grad_norm": 0.02695903554558754,
      "learning_rate": 0.024000000208616257,
      "loss": 2.438490867614746,
      "step": 10246
    },
    {
      "epoch": 0.488,
      "grad_norm": 0.030944058671593666,
      "learning_rate": 0.024000000208616257,
      "loss": 2.389352321624756,
      "step": 10248
    },
    {
      "epoch": 0.4880952380952381,
      "grad_norm": 0.03132271021604538,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4251255989074707,
      "step": 10250
    },
    {
      "epoch": 0.4881904761904762,
      "grad_norm": 0.030158884823322296,
      "learning_rate": 0.024000000208616257,
      "loss": 2.409162759780884,
      "step": 10252
    },
    {
      "epoch": 0.48828571428571427,
      "grad_norm": 0.03210701048374176,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401486396789551,
      "step": 10254
    },
    {
      "epoch": 0.48838095238095236,
      "grad_norm": 0.028029276058077812,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3880395889282227,
      "step": 10256
    },
    {
      "epoch": 0.48847619047619045,
      "grad_norm": 0.02785279043018818,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3978278636932373,
      "step": 10258
    },
    {
      "epoch": 0.48857142857142855,
      "grad_norm": 0.02776709757745266,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4327378273010254,
      "step": 10260
    },
    {
      "epoch": 0.4886666666666667,
      "grad_norm": 0.029374267905950546,
      "learning_rate": 0.024000000208616257,
      "loss": 2.414071798324585,
      "step": 10262
    },
    {
      "epoch": 0.4887619047619048,
      "grad_norm": 0.02675914205610752,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4138622283935547,
      "step": 10264
    },
    {
      "epoch": 0.4888571428571429,
      "grad_norm": 0.02667129784822464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4251785278320312,
      "step": 10266
    },
    {
      "epoch": 0.48895238095238097,
      "grad_norm": 0.029442772269248962,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3709793090820312,
      "step": 10268
    },
    {
      "epoch": 0.48904761904761906,
      "grad_norm": 0.02904820814728737,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3844997882843018,
      "step": 10270
    },
    {
      "epoch": 0.48914285714285716,
      "grad_norm": 0.02770475670695305,
      "learning_rate": 0.024000000208616257,
      "loss": 2.399033784866333,
      "step": 10272
    },
    {
      "epoch": 0.48923809523809525,
      "grad_norm": 0.02684980444610119,
      "learning_rate": 0.024000000208616257,
      "loss": 2.425713062286377,
      "step": 10274
    },
    {
      "epoch": 0.48933333333333334,
      "grad_norm": 0.029651954770088196,
      "learning_rate": 0.024000000208616257,
      "loss": 2.402139663696289,
      "step": 10276
    },
    {
      "epoch": 0.48942857142857144,
      "grad_norm": 0.028704963624477386,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4109303951263428,
      "step": 10278
    },
    {
      "epoch": 0.4895238095238095,
      "grad_norm": 0.02856304869055748,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4044077396392822,
      "step": 10280
    },
    {
      "epoch": 0.4896190476190476,
      "grad_norm": 0.030733058229088783,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3972554206848145,
      "step": 10282
    },
    {
      "epoch": 0.4897142857142857,
      "grad_norm": 0.026952063664793968,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396864891052246,
      "step": 10284
    },
    {
      "epoch": 0.4898095238095238,
      "grad_norm": 0.027185404673218727,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4050590991973877,
      "step": 10286
    },
    {
      "epoch": 0.4899047619047619,
      "grad_norm": 0.02783147059381008,
      "learning_rate": 0.024000000208616257,
      "loss": 2.393479824066162,
      "step": 10288
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.027866318821907043,
      "learning_rate": 0.024000000208616257,
      "loss": 2.399815082550049,
      "step": 10290
    },
    {
      "epoch": 0.4900952380952381,
      "grad_norm": 0.030500713735818863,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4170444011688232,
      "step": 10292
    },
    {
      "epoch": 0.4901904761904762,
      "grad_norm": 0.02655445598065853,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392690658569336,
      "step": 10294
    },
    {
      "epoch": 0.49028571428571427,
      "grad_norm": 0.02892918512225151,
      "learning_rate": 0.024000000208616257,
      "loss": 2.412971258163452,
      "step": 10296
    },
    {
      "epoch": 0.49038095238095236,
      "grad_norm": 0.027988040819764137,
      "learning_rate": 0.024000000208616257,
      "loss": 2.409470558166504,
      "step": 10298
    },
    {
      "epoch": 0.49047619047619045,
      "grad_norm": 0.02809884026646614,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3994412422180176,
      "step": 10300
    },
    {
      "epoch": 0.49057142857142855,
      "grad_norm": 0.027279235422611237,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3706302642822266,
      "step": 10302
    },
    {
      "epoch": 0.49066666666666664,
      "grad_norm": 0.02656668983399868,
      "learning_rate": 0.024000000208616257,
      "loss": 2.386965751647949,
      "step": 10304
    },
    {
      "epoch": 0.4907619047619048,
      "grad_norm": 0.029105477035045624,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4173858165740967,
      "step": 10306
    },
    {
      "epoch": 0.4908571428571429,
      "grad_norm": 0.035119518637657166,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3865482807159424,
      "step": 10308
    },
    {
      "epoch": 0.490952380952381,
      "grad_norm": 0.03714201971888542,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4167704582214355,
      "step": 10310
    },
    {
      "epoch": 0.49104761904761907,
      "grad_norm": 0.029136816039681435,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3885631561279297,
      "step": 10312
    },
    {
      "epoch": 0.49114285714285716,
      "grad_norm": 0.027419190853834152,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3931968212127686,
      "step": 10314
    },
    {
      "epoch": 0.49123809523809525,
      "grad_norm": 0.026709571480751038,
      "learning_rate": 0.024000000208616257,
      "loss": 2.414834499359131,
      "step": 10316
    },
    {
      "epoch": 0.49133333333333334,
      "grad_norm": 0.0270709041506052,
      "learning_rate": 0.024000000208616257,
      "loss": 2.409512996673584,
      "step": 10318
    },
    {
      "epoch": 0.49142857142857144,
      "grad_norm": 0.027681641280651093,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4084997177124023,
      "step": 10320
    },
    {
      "epoch": 0.49152380952380953,
      "grad_norm": 0.026396803557872772,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4036223888397217,
      "step": 10322
    },
    {
      "epoch": 0.4916190476190476,
      "grad_norm": 0.02638797089457512,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4137895107269287,
      "step": 10324
    },
    {
      "epoch": 0.4917142857142857,
      "grad_norm": 0.027811702340841293,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4262070655822754,
      "step": 10326
    },
    {
      "epoch": 0.4918095238095238,
      "grad_norm": 0.02686273120343685,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3962628841400146,
      "step": 10328
    },
    {
      "epoch": 0.4919047619047619,
      "grad_norm": 0.025733133777976036,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3780581951141357,
      "step": 10330
    },
    {
      "epoch": 0.492,
      "grad_norm": 0.027483344078063965,
      "learning_rate": 0.024000000208616257,
      "loss": 2.391854763031006,
      "step": 10332
    },
    {
      "epoch": 0.4920952380952381,
      "grad_norm": 0.02856365405023098,
      "learning_rate": 0.024000000208616257,
      "loss": 2.418821334838867,
      "step": 10334
    },
    {
      "epoch": 0.4921904761904762,
      "grad_norm": 0.027196187525987625,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3839521408081055,
      "step": 10336
    },
    {
      "epoch": 0.49228571428571427,
      "grad_norm": 0.02654234506189823,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3845396041870117,
      "step": 10338
    },
    {
      "epoch": 0.49238095238095236,
      "grad_norm": 0.027982456609606743,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3854191303253174,
      "step": 10340
    },
    {
      "epoch": 0.49247619047619046,
      "grad_norm": 0.028073176741600037,
      "learning_rate": 0.024000000208616257,
      "loss": 2.406831979751587,
      "step": 10342
    },
    {
      "epoch": 0.49257142857142855,
      "grad_norm": 0.028383901342749596,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4148969650268555,
      "step": 10344
    },
    {
      "epoch": 0.49266666666666664,
      "grad_norm": 0.03246552497148514,
      "learning_rate": 0.024000000208616257,
      "loss": 2.408151388168335,
      "step": 10346
    },
    {
      "epoch": 0.49276190476190473,
      "grad_norm": 0.02916114032268524,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3920297622680664,
      "step": 10348
    },
    {
      "epoch": 0.4928571428571429,
      "grad_norm": 0.029290588572621346,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4164390563964844,
      "step": 10350
    },
    {
      "epoch": 0.492952380952381,
      "grad_norm": 0.027892330661416054,
      "learning_rate": 0.024000000208616257,
      "loss": 2.407414436340332,
      "step": 10352
    },
    {
      "epoch": 0.49304761904761907,
      "grad_norm": 0.029612164944410324,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380706548690796,
      "step": 10354
    },
    {
      "epoch": 0.49314285714285716,
      "grad_norm": 0.02719537727534771,
      "learning_rate": 0.024000000208616257,
      "loss": 2.417814254760742,
      "step": 10356
    },
    {
      "epoch": 0.49323809523809525,
      "grad_norm": 0.028703797608613968,
      "learning_rate": 0.024000000208616257,
      "loss": 2.422257900238037,
      "step": 10358
    },
    {
      "epoch": 0.49333333333333335,
      "grad_norm": 0.026958374306559563,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3758392333984375,
      "step": 10360
    },
    {
      "epoch": 0.49342857142857144,
      "grad_norm": 0.028875578194856644,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4475560188293457,
      "step": 10362
    },
    {
      "epoch": 0.49352380952380953,
      "grad_norm": 0.02690201997756958,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4166336059570312,
      "step": 10364
    },
    {
      "epoch": 0.4936190476190476,
      "grad_norm": 0.032832592725753784,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4439778327941895,
      "step": 10366
    },
    {
      "epoch": 0.4937142857142857,
      "grad_norm": 0.03506319597363472,
      "learning_rate": 0.024000000208616257,
      "loss": 2.421558380126953,
      "step": 10368
    },
    {
      "epoch": 0.4938095238095238,
      "grad_norm": 0.030999988317489624,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4165844917297363,
      "step": 10370
    },
    {
      "epoch": 0.4939047619047619,
      "grad_norm": 0.027687108144164085,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4129018783569336,
      "step": 10372
    },
    {
      "epoch": 0.494,
      "grad_norm": 0.02860761620104313,
      "learning_rate": 0.024000000208616257,
      "loss": 2.415283203125,
      "step": 10374
    },
    {
      "epoch": 0.4940952380952381,
      "grad_norm": 0.02786959707736969,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4275870323181152,
      "step": 10376
    },
    {
      "epoch": 0.4941904761904762,
      "grad_norm": 0.027879640460014343,
      "learning_rate": 0.024000000208616257,
      "loss": 2.408388376235962,
      "step": 10378
    },
    {
      "epoch": 0.4942857142857143,
      "grad_norm": 0.02761046215891838,
      "learning_rate": 0.024000000208616257,
      "loss": 2.404641628265381,
      "step": 10380
    },
    {
      "epoch": 0.49438095238095237,
      "grad_norm": 0.03297905996441841,
      "learning_rate": 0.024000000208616257,
      "loss": 2.403665781021118,
      "step": 10382
    },
    {
      "epoch": 0.49447619047619046,
      "grad_norm": 0.030208664014935493,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4113972187042236,
      "step": 10384
    },
    {
      "epoch": 0.49457142857142855,
      "grad_norm": 0.02959398739039898,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3691420555114746,
      "step": 10386
    },
    {
      "epoch": 0.49466666666666664,
      "grad_norm": 0.027961058542132378,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4214978218078613,
      "step": 10388
    },
    {
      "epoch": 0.49476190476190474,
      "grad_norm": 0.027629004791378975,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3918569087982178,
      "step": 10390
    },
    {
      "epoch": 0.4948571428571429,
      "grad_norm": 0.027133813127875328,
      "learning_rate": 0.024000000208616257,
      "loss": 2.405062198638916,
      "step": 10392
    },
    {
      "epoch": 0.494952380952381,
      "grad_norm": 0.030379289761185646,
      "learning_rate": 0.024000000208616257,
      "loss": 2.426683187484741,
      "step": 10394
    },
    {
      "epoch": 0.49504761904761907,
      "grad_norm": 0.03137844428420067,
      "learning_rate": 0.024000000208616257,
      "loss": 2.426130533218384,
      "step": 10396
    },
    {
      "epoch": 0.49514285714285716,
      "grad_norm": 0.02916034683585167,
      "learning_rate": 0.024000000208616257,
      "loss": 2.409576177597046,
      "step": 10398
    },
    {
      "epoch": 0.49523809523809526,
      "grad_norm": 0.02724851481616497,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4183645248413086,
      "step": 10400
    },
    {
      "epoch": 0.49533333333333335,
      "grad_norm": 0.02891296148300171,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4351041316986084,
      "step": 10402
    },
    {
      "epoch": 0.49542857142857144,
      "grad_norm": 0.0291142575442791,
      "learning_rate": 0.024000000208616257,
      "loss": 2.399219036102295,
      "step": 10404
    },
    {
      "epoch": 0.49552380952380953,
      "grad_norm": 0.031118957325816154,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4014697074890137,
      "step": 10406
    },
    {
      "epoch": 0.4956190476190476,
      "grad_norm": 0.03247349336743355,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4389960765838623,
      "step": 10408
    },
    {
      "epoch": 0.4957142857142857,
      "grad_norm": 0.030827339738607407,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4184679985046387,
      "step": 10410
    },
    {
      "epoch": 0.4958095238095238,
      "grad_norm": 0.02871031127870083,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4270668029785156,
      "step": 10412
    },
    {
      "epoch": 0.4959047619047619,
      "grad_norm": 0.029219098389148712,
      "learning_rate": 0.024000000208616257,
      "loss": 2.408916473388672,
      "step": 10414
    },
    {
      "epoch": 0.496,
      "grad_norm": 0.03297557309269905,
      "learning_rate": 0.024000000208616257,
      "loss": 2.434946298599243,
      "step": 10416
    },
    {
      "epoch": 0.4960952380952381,
      "grad_norm": 0.035917554050683975,
      "learning_rate": 0.024000000208616257,
      "loss": 2.414741039276123,
      "step": 10418
    },
    {
      "epoch": 0.4961904761904762,
      "grad_norm": 0.03540509566664696,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4252724647521973,
      "step": 10420
    },
    {
      "epoch": 0.4962857142857143,
      "grad_norm": 0.03094058856368065,
      "learning_rate": 0.024000000208616257,
      "loss": 2.427158832550049,
      "step": 10422
    },
    {
      "epoch": 0.49638095238095237,
      "grad_norm": 0.03339220583438873,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390956401824951,
      "step": 10424
    },
    {
      "epoch": 0.49647619047619046,
      "grad_norm": 0.031154071912169456,
      "learning_rate": 0.024000000208616257,
      "loss": 2.39162540435791,
      "step": 10426
    },
    {
      "epoch": 0.49657142857142855,
      "grad_norm": 0.031000295653939247,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392042636871338,
      "step": 10428
    },
    {
      "epoch": 0.49666666666666665,
      "grad_norm": 0.0329836867749691,
      "learning_rate": 0.024000000208616257,
      "loss": 2.416778087615967,
      "step": 10430
    },
    {
      "epoch": 0.49676190476190474,
      "grad_norm": 0.02694794535636902,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4058566093444824,
      "step": 10432
    },
    {
      "epoch": 0.49685714285714283,
      "grad_norm": 0.028465168550610542,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4282660484313965,
      "step": 10434
    },
    {
      "epoch": 0.496952380952381,
      "grad_norm": 0.027982857078313828,
      "learning_rate": 0.024000000208616257,
      "loss": 2.408712148666382,
      "step": 10436
    },
    {
      "epoch": 0.49704761904761907,
      "grad_norm": 0.027554618194699287,
      "learning_rate": 0.024000000208616257,
      "loss": 2.438115119934082,
      "step": 10438
    },
    {
      "epoch": 0.49714285714285716,
      "grad_norm": 0.027580024674534798,
      "learning_rate": 0.024000000208616257,
      "loss": 2.410701274871826,
      "step": 10440
    },
    {
      "epoch": 0.49723809523809526,
      "grad_norm": 0.026654459536075592,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4243993759155273,
      "step": 10442
    },
    {
      "epoch": 0.49733333333333335,
      "grad_norm": 0.026882920414209366,
      "learning_rate": 0.024000000208616257,
      "loss": 2.418551445007324,
      "step": 10444
    },
    {
      "epoch": 0.49742857142857144,
      "grad_norm": 0.027907835319638252,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4145541191101074,
      "step": 10446
    },
    {
      "epoch": 0.49752380952380953,
      "grad_norm": 0.02723315916955471,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4320261478424072,
      "step": 10448
    },
    {
      "epoch": 0.4976190476190476,
      "grad_norm": 0.029031608253717422,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4340081214904785,
      "step": 10450
    },
    {
      "epoch": 0.4977142857142857,
      "grad_norm": 0.028427282348275185,
      "learning_rate": 0.024000000208616257,
      "loss": 2.411557197570801,
      "step": 10452
    },
    {
      "epoch": 0.4978095238095238,
      "grad_norm": 0.027455875650048256,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4289140701293945,
      "step": 10454
    },
    {
      "epoch": 0.4979047619047619,
      "grad_norm": 0.026953013613820076,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3944435119628906,
      "step": 10456
    },
    {
      "epoch": 0.498,
      "grad_norm": 0.026954088360071182,
      "learning_rate": 0.024000000208616257,
      "loss": 2.399995803833008,
      "step": 10458
    },
    {
      "epoch": 0.4980952380952381,
      "grad_norm": 0.026730768382549286,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4306483268737793,
      "step": 10460
    },
    {
      "epoch": 0.4981904761904762,
      "grad_norm": 0.028138939291238785,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4385855197906494,
      "step": 10462
    },
    {
      "epoch": 0.4982857142857143,
      "grad_norm": 0.03093055635690689,
      "learning_rate": 0.024000000208616257,
      "loss": 2.465585708618164,
      "step": 10464
    },
    {
      "epoch": 0.49838095238095237,
      "grad_norm": 0.0323898047208786,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4489054679870605,
      "step": 10466
    },
    {
      "epoch": 0.49847619047619046,
      "grad_norm": 0.02801920287311077,
      "learning_rate": 0.024000000208616257,
      "loss": 2.419431209564209,
      "step": 10468
    },
    {
      "epoch": 0.49857142857142855,
      "grad_norm": 0.029940670356154442,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4624452590942383,
      "step": 10470
    },
    {
      "epoch": 0.49866666666666665,
      "grad_norm": 0.028959928080439568,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4016637802124023,
      "step": 10472
    },
    {
      "epoch": 0.49876190476190474,
      "grad_norm": 0.027238398790359497,
      "learning_rate": 0.024000000208616257,
      "loss": 2.417938709259033,
      "step": 10474
    },
    {
      "epoch": 0.49885714285714283,
      "grad_norm": 0.026756426319479942,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4164299964904785,
      "step": 10476
    },
    {
      "epoch": 0.4989523809523809,
      "grad_norm": 0.026669859886169434,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4323248863220215,
      "step": 10478
    },
    {
      "epoch": 0.4990476190476191,
      "grad_norm": 0.025992702692747116,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4506709575653076,
      "step": 10480
    },
    {
      "epoch": 0.49914285714285717,
      "grad_norm": 0.027653198689222336,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4417662620544434,
      "step": 10482
    },
    {
      "epoch": 0.49923809523809526,
      "grad_norm": 0.026910757645964622,
      "learning_rate": 0.024000000208616257,
      "loss": 2.402069568634033,
      "step": 10484
    },
    {
      "epoch": 0.49933333333333335,
      "grad_norm": 0.0285795871168375,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4389047622680664,
      "step": 10486
    },
    {
      "epoch": 0.49942857142857144,
      "grad_norm": 0.02746466174721718,
      "learning_rate": 0.024000000208616257,
      "loss": 2.453268527984619,
      "step": 10488
    },
    {
      "epoch": 0.49952380952380954,
      "grad_norm": 0.027365917339920998,
      "learning_rate": 0.024000000208616257,
      "loss": 2.430497646331787,
      "step": 10490
    },
    {
      "epoch": 0.49961904761904763,
      "grad_norm": 0.027393141761422157,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4256608486175537,
      "step": 10492
    },
    {
      "epoch": 0.4997142857142857,
      "grad_norm": 0.027603358030319214,
      "learning_rate": 0.024000000208616257,
      "loss": 2.412686824798584,
      "step": 10494
    },
    {
      "epoch": 0.4998095238095238,
      "grad_norm": 0.026735549792647362,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4485809803009033,
      "step": 10496
    },
    {
      "epoch": 0.4999047619047619,
      "grad_norm": 0.02984875626862049,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4758517742156982,
      "step": 10498
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.030420610681176186,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4374406337738037,
      "step": 10500
    },
    {
      "epoch": 0.5000952380952381,
      "grad_norm": 0.030204081907868385,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4060349464416504,
      "step": 10502
    },
    {
      "epoch": 0.5001904761904762,
      "grad_norm": 0.027147255837917328,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4491779804229736,
      "step": 10504
    },
    {
      "epoch": 0.5002857142857143,
      "grad_norm": 0.03571924939751625,
      "learning_rate": 0.024000000208616257,
      "loss": 2.43693208694458,
      "step": 10506
    },
    {
      "epoch": 0.5003809523809524,
      "grad_norm": 0.03682103380560875,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4619345664978027,
      "step": 10508
    },
    {
      "epoch": 0.5004761904761905,
      "grad_norm": 0.02838040329515934,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4433932304382324,
      "step": 10510
    },
    {
      "epoch": 0.5005714285714286,
      "grad_norm": 0.027335135266184807,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4327163696289062,
      "step": 10512
    },
    {
      "epoch": 0.5006666666666667,
      "grad_norm": 0.029031334444880486,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4532408714294434,
      "step": 10514
    },
    {
      "epoch": 0.5007619047619047,
      "grad_norm": 0.031321391463279724,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4431686401367188,
      "step": 10516
    },
    {
      "epoch": 0.5008571428571429,
      "grad_norm": 0.03142645210027695,
      "learning_rate": 0.024000000208616257,
      "loss": 2.428006649017334,
      "step": 10518
    },
    {
      "epoch": 0.5009523809523809,
      "grad_norm": 0.03014472685754299,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4350976943969727,
      "step": 10520
    },
    {
      "epoch": 0.5010476190476191,
      "grad_norm": 0.02793862484395504,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4364380836486816,
      "step": 10522
    },
    {
      "epoch": 0.5011428571428571,
      "grad_norm": 0.02991153672337532,
      "learning_rate": 0.024000000208616257,
      "loss": 2.458343982696533,
      "step": 10524
    },
    {
      "epoch": 0.5012380952380953,
      "grad_norm": 0.02777714841067791,
      "learning_rate": 0.024000000208616257,
      "loss": 2.437988758087158,
      "step": 10526
    },
    {
      "epoch": 0.5013333333333333,
      "grad_norm": 0.027824705466628075,
      "learning_rate": 0.024000000208616257,
      "loss": 2.415890693664551,
      "step": 10528
    },
    {
      "epoch": 0.5014285714285714,
      "grad_norm": 0.029599815607070923,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4483466148376465,
      "step": 10530
    },
    {
      "epoch": 0.5015238095238095,
      "grad_norm": 0.027131836861371994,
      "learning_rate": 0.024000000208616257,
      "loss": 2.434523582458496,
      "step": 10532
    },
    {
      "epoch": 0.5016190476190476,
      "grad_norm": 0.026493661105632782,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4277215003967285,
      "step": 10534
    },
    {
      "epoch": 0.5017142857142857,
      "grad_norm": 0.02984180673956871,
      "learning_rate": 0.024000000208616257,
      "loss": 2.461825370788574,
      "step": 10536
    },
    {
      "epoch": 0.5018095238095238,
      "grad_norm": 0.026190048083662987,
      "learning_rate": 0.024000000208616257,
      "loss": 2.479802370071411,
      "step": 10538
    },
    {
      "epoch": 0.5019047619047619,
      "grad_norm": 0.027719635516405106,
      "learning_rate": 0.024000000208616257,
      "loss": 2.435533046722412,
      "step": 10540
    },
    {
      "epoch": 0.502,
      "grad_norm": 0.027317533269524574,
      "learning_rate": 0.024000000208616257,
      "loss": 2.452331066131592,
      "step": 10542
    },
    {
      "epoch": 0.5020952380952381,
      "grad_norm": 0.028682595118880272,
      "learning_rate": 0.024000000208616257,
      "loss": 2.464838981628418,
      "step": 10544
    },
    {
      "epoch": 0.5021904761904762,
      "grad_norm": 0.027929341420531273,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4573774337768555,
      "step": 10546
    },
    {
      "epoch": 0.5022857142857143,
      "grad_norm": 0.02744869329035282,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4293107986450195,
      "step": 10548
    },
    {
      "epoch": 0.5023809523809524,
      "grad_norm": 0.026700438931584358,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4308342933654785,
      "step": 10550
    },
    {
      "epoch": 0.5024761904761905,
      "grad_norm": 0.027053477242588997,
      "learning_rate": 0.024000000208616257,
      "loss": 2.451044797897339,
      "step": 10552
    },
    {
      "epoch": 0.5025714285714286,
      "grad_norm": 0.029234807938337326,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4647469520568848,
      "step": 10554
    },
    {
      "epoch": 0.5026666666666667,
      "grad_norm": 0.0276576429605484,
      "learning_rate": 0.024000000208616257,
      "loss": 2.467348337173462,
      "step": 10556
    },
    {
      "epoch": 0.5027619047619047,
      "grad_norm": 0.026910077780485153,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4328184127807617,
      "step": 10558
    },
    {
      "epoch": 0.5028571428571429,
      "grad_norm": 0.028046056628227234,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4527924060821533,
      "step": 10560
    },
    {
      "epoch": 0.5029523809523809,
      "grad_norm": 0.028252216055989265,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4777774810791016,
      "step": 10562
    },
    {
      "epoch": 0.5030476190476191,
      "grad_norm": 0.035288192331790924,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4141950607299805,
      "step": 10564
    },
    {
      "epoch": 0.5031428571428571,
      "grad_norm": 0.030102265998721123,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4389536380767822,
      "step": 10566
    },
    {
      "epoch": 0.5032380952380953,
      "grad_norm": 0.029392516240477562,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4202775955200195,
      "step": 10568
    },
    {
      "epoch": 0.5033333333333333,
      "grad_norm": 0.02779567614197731,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4519314765930176,
      "step": 10570
    },
    {
      "epoch": 0.5034285714285714,
      "grad_norm": 0.02843274548649788,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4480552673339844,
      "step": 10572
    },
    {
      "epoch": 0.5035238095238095,
      "grad_norm": 0.028056619688868523,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4596121311187744,
      "step": 10574
    },
    {
      "epoch": 0.5036190476190476,
      "grad_norm": 0.029085010290145874,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4349260330200195,
      "step": 10576
    },
    {
      "epoch": 0.5037142857142857,
      "grad_norm": 0.02789931744337082,
      "learning_rate": 0.024000000208616257,
      "loss": 2.463022232055664,
      "step": 10578
    },
    {
      "epoch": 0.5038095238095238,
      "grad_norm": 0.027265572920441628,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4229609966278076,
      "step": 10580
    },
    {
      "epoch": 0.5039047619047619,
      "grad_norm": 0.029024740681052208,
      "learning_rate": 0.024000000208616257,
      "loss": 2.451295852661133,
      "step": 10582
    },
    {
      "epoch": 0.504,
      "grad_norm": 0.02868027798831463,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4367551803588867,
      "step": 10584
    },
    {
      "epoch": 0.504095238095238,
      "grad_norm": 0.027595125138759613,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4224343299865723,
      "step": 10586
    },
    {
      "epoch": 0.5041904761904762,
      "grad_norm": 0.027235988527536392,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4633827209472656,
      "step": 10588
    },
    {
      "epoch": 0.5042857142857143,
      "grad_norm": 0.028152260929346085,
      "learning_rate": 0.024000000208616257,
      "loss": 2.426318645477295,
      "step": 10590
    },
    {
      "epoch": 0.5043809523809524,
      "grad_norm": 0.030847476795315742,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4518537521362305,
      "step": 10592
    },
    {
      "epoch": 0.5044761904761905,
      "grad_norm": 0.0275142602622509,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4528770446777344,
      "step": 10594
    },
    {
      "epoch": 0.5045714285714286,
      "grad_norm": 0.027242980897426605,
      "learning_rate": 0.024000000208616257,
      "loss": 2.423563003540039,
      "step": 10596
    },
    {
      "epoch": 0.5046666666666667,
      "grad_norm": 0.02904028631746769,
      "learning_rate": 0.024000000208616257,
      "loss": 2.447375774383545,
      "step": 10598
    },
    {
      "epoch": 0.5047619047619047,
      "grad_norm": 0.028056412935256958,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4469761848449707,
      "step": 10600
    },
    {
      "epoch": 0.5048571428571429,
      "grad_norm": 0.02916330099105835,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4272971153259277,
      "step": 10602
    },
    {
      "epoch": 0.5049523809523809,
      "grad_norm": 0.02669353038072586,
      "learning_rate": 0.024000000208616257,
      "loss": 2.437255859375,
      "step": 10604
    },
    {
      "epoch": 0.5050476190476191,
      "grad_norm": 0.027442852035164833,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4768054485321045,
      "step": 10606
    },
    {
      "epoch": 0.5051428571428571,
      "grad_norm": 0.026943741366267204,
      "learning_rate": 0.024000000208616257,
      "loss": 2.445418357849121,
      "step": 10608
    },
    {
      "epoch": 0.5052380952380953,
      "grad_norm": 0.02796977385878563,
      "learning_rate": 0.024000000208616257,
      "loss": 2.46488881111145,
      "step": 10610
    },
    {
      "epoch": 0.5053333333333333,
      "grad_norm": 0.02829703874886036,
      "learning_rate": 0.024000000208616257,
      "loss": 2.399935722351074,
      "step": 10612
    },
    {
      "epoch": 0.5054285714285714,
      "grad_norm": 0.027495479211211205,
      "learning_rate": 0.024000000208616257,
      "loss": 2.470089912414551,
      "step": 10614
    },
    {
      "epoch": 0.5055238095238095,
      "grad_norm": 0.030557241290807724,
      "learning_rate": 0.024000000208616257,
      "loss": 2.454024314880371,
      "step": 10616
    },
    {
      "epoch": 0.5056190476190476,
      "grad_norm": 0.027526525780558586,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4555253982543945,
      "step": 10618
    },
    {
      "epoch": 0.5057142857142857,
      "grad_norm": 0.02985428087413311,
      "learning_rate": 0.024000000208616257,
      "loss": 2.438883066177368,
      "step": 10620
    },
    {
      "epoch": 0.5058095238095238,
      "grad_norm": 0.027097798883914948,
      "learning_rate": 0.024000000208616257,
      "loss": 2.430593490600586,
      "step": 10622
    },
    {
      "epoch": 0.5059047619047619,
      "grad_norm": 0.02754295989871025,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4198389053344727,
      "step": 10624
    },
    {
      "epoch": 0.506,
      "grad_norm": 0.027297940105199814,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4563076496124268,
      "step": 10626
    },
    {
      "epoch": 0.506095238095238,
      "grad_norm": 0.02699265256524086,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4345457553863525,
      "step": 10628
    },
    {
      "epoch": 0.5061904761904762,
      "grad_norm": 0.0282902829349041,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4192466735839844,
      "step": 10630
    },
    {
      "epoch": 0.5062857142857143,
      "grad_norm": 0.033406540751457214,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4340994358062744,
      "step": 10632
    },
    {
      "epoch": 0.5063809523809524,
      "grad_norm": 0.030291905626654625,
      "learning_rate": 0.024000000208616257,
      "loss": 2.462829828262329,
      "step": 10634
    },
    {
      "epoch": 0.5064761904761905,
      "grad_norm": 0.02736188843846321,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4303998947143555,
      "step": 10636
    },
    {
      "epoch": 0.5065714285714286,
      "grad_norm": 0.02941037528216839,
      "learning_rate": 0.024000000208616257,
      "loss": 2.45393705368042,
      "step": 10638
    },
    {
      "epoch": 0.5066666666666667,
      "grad_norm": 0.026944266632199287,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4170398712158203,
      "step": 10640
    },
    {
      "epoch": 0.5067619047619047,
      "grad_norm": 0.027776921167969704,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4149038791656494,
      "step": 10642
    },
    {
      "epoch": 0.5068571428571429,
      "grad_norm": 0.028152089565992355,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4621713161468506,
      "step": 10644
    },
    {
      "epoch": 0.5069523809523809,
      "grad_norm": 0.02801678143441677,
      "learning_rate": 0.024000000208616257,
      "loss": 2.415541172027588,
      "step": 10646
    },
    {
      "epoch": 0.5070476190476191,
      "grad_norm": 0.0284360833466053,
      "learning_rate": 0.024000000208616257,
      "loss": 2.422945499420166,
      "step": 10648
    },
    {
      "epoch": 0.5071428571428571,
      "grad_norm": 0.027714064344763756,
      "learning_rate": 0.024000000208616257,
      "loss": 2.430230140686035,
      "step": 10650
    },
    {
      "epoch": 0.5072380952380953,
      "grad_norm": 0.02753283455967903,
      "learning_rate": 0.024000000208616257,
      "loss": 2.428250551223755,
      "step": 10652
    },
    {
      "epoch": 0.5073333333333333,
      "grad_norm": 0.028864799067378044,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4289631843566895,
      "step": 10654
    },
    {
      "epoch": 0.5074285714285715,
      "grad_norm": 0.02773326449096203,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4538445472717285,
      "step": 10656
    },
    {
      "epoch": 0.5075238095238095,
      "grad_norm": 0.028690950945019722,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4332919120788574,
      "step": 10658
    },
    {
      "epoch": 0.5076190476190476,
      "grad_norm": 0.027461759746074677,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4106812477111816,
      "step": 10660
    },
    {
      "epoch": 0.5077142857142857,
      "grad_norm": 0.028255412355065346,
      "learning_rate": 0.024000000208616257,
      "loss": 2.450730323791504,
      "step": 10662
    },
    {
      "epoch": 0.5078095238095238,
      "grad_norm": 0.027058904990553856,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4064207077026367,
      "step": 10664
    },
    {
      "epoch": 0.5079047619047619,
      "grad_norm": 0.031714972108602524,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4432473182678223,
      "step": 10666
    },
    {
      "epoch": 0.508,
      "grad_norm": 0.026700342074036598,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4073476791381836,
      "step": 10668
    },
    {
      "epoch": 0.508095238095238,
      "grad_norm": 0.02770339325070381,
      "learning_rate": 0.024000000208616257,
      "loss": 2.433797597885132,
      "step": 10670
    },
    {
      "epoch": 0.5081904761904762,
      "grad_norm": 0.026324082165956497,
      "learning_rate": 0.024000000208616257,
      "loss": 2.431698799133301,
      "step": 10672
    },
    {
      "epoch": 0.5082857142857143,
      "grad_norm": 0.028448810800909996,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4154505729675293,
      "step": 10674
    },
    {
      "epoch": 0.5083809523809524,
      "grad_norm": 0.026210259646177292,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4191741943359375,
      "step": 10676
    },
    {
      "epoch": 0.5084761904761905,
      "grad_norm": 0.028098348528146744,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4259657859802246,
      "step": 10678
    },
    {
      "epoch": 0.5085714285714286,
      "grad_norm": 0.027027495205402374,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4382333755493164,
      "step": 10680
    },
    {
      "epoch": 0.5086666666666667,
      "grad_norm": 0.027239730581641197,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4388175010681152,
      "step": 10682
    },
    {
      "epoch": 0.5087619047619047,
      "grad_norm": 0.031195566058158875,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4484543800354004,
      "step": 10684
    },
    {
      "epoch": 0.5088571428571429,
      "grad_norm": 0.031367089599370956,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3834757804870605,
      "step": 10686
    },
    {
      "epoch": 0.5089523809523809,
      "grad_norm": 0.028450176119804382,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4651589393615723,
      "step": 10688
    },
    {
      "epoch": 0.5090476190476191,
      "grad_norm": 0.02712199091911316,
      "learning_rate": 0.024000000208616257,
      "loss": 2.446445941925049,
      "step": 10690
    },
    {
      "epoch": 0.5091428571428571,
      "grad_norm": 0.0313868522644043,
      "learning_rate": 0.024000000208616257,
      "loss": 2.423309087753296,
      "step": 10692
    },
    {
      "epoch": 0.5092380952380953,
      "grad_norm": 0.02969011478126049,
      "learning_rate": 0.024000000208616257,
      "loss": 2.420013427734375,
      "step": 10694
    },
    {
      "epoch": 0.5093333333333333,
      "grad_norm": 0.02757384069263935,
      "learning_rate": 0.024000000208616257,
      "loss": 2.434798002243042,
      "step": 10696
    },
    {
      "epoch": 0.5094285714285715,
      "grad_norm": 0.029611356556415558,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4420108795166016,
      "step": 10698
    },
    {
      "epoch": 0.5095238095238095,
      "grad_norm": 0.030738957226276398,
      "learning_rate": 0.024000000208616257,
      "loss": 2.428284168243408,
      "step": 10700
    },
    {
      "epoch": 0.5096190476190476,
      "grad_norm": 0.03290248662233353,
      "learning_rate": 0.024000000208616257,
      "loss": 2.433021068572998,
      "step": 10702
    },
    {
      "epoch": 0.5097142857142857,
      "grad_norm": 0.02936279959976673,
      "learning_rate": 0.024000000208616257,
      "loss": 2.437680244445801,
      "step": 10704
    },
    {
      "epoch": 0.5098095238095238,
      "grad_norm": 0.03234749287366867,
      "learning_rate": 0.024000000208616257,
      "loss": 2.422527551651001,
      "step": 10706
    },
    {
      "epoch": 0.5099047619047619,
      "grad_norm": 0.02763894759118557,
      "learning_rate": 0.024000000208616257,
      "loss": 2.41082763671875,
      "step": 10708
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.026939023286104202,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4541029930114746,
      "step": 10710
    },
    {
      "epoch": 0.510095238095238,
      "grad_norm": 0.0280812568962574,
      "learning_rate": 0.024000000208616257,
      "loss": 2.419034481048584,
      "step": 10712
    },
    {
      "epoch": 0.5101904761904762,
      "grad_norm": 0.027115436270833015,
      "learning_rate": 0.024000000208616257,
      "loss": 2.464656352996826,
      "step": 10714
    },
    {
      "epoch": 0.5102857142857142,
      "grad_norm": 0.028406810015439987,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4440126419067383,
      "step": 10716
    },
    {
      "epoch": 0.5103809523809524,
      "grad_norm": 0.02984136901795864,
      "learning_rate": 0.024000000208616257,
      "loss": 2.433138370513916,
      "step": 10718
    },
    {
      "epoch": 0.5104761904761905,
      "grad_norm": 0.027627650648355484,
      "learning_rate": 0.024000000208616257,
      "loss": 2.439250946044922,
      "step": 10720
    },
    {
      "epoch": 0.5105714285714286,
      "grad_norm": 0.02787013165652752,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4390711784362793,
      "step": 10722
    },
    {
      "epoch": 0.5106666666666667,
      "grad_norm": 0.02688511647284031,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4529800415039062,
      "step": 10724
    },
    {
      "epoch": 0.5107619047619048,
      "grad_norm": 0.03191622346639633,
      "learning_rate": 0.024000000208616257,
      "loss": 2.433412551879883,
      "step": 10726
    },
    {
      "epoch": 0.5108571428571429,
      "grad_norm": 0.02716859243810177,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4432907104492188,
      "step": 10728
    },
    {
      "epoch": 0.5109523809523809,
      "grad_norm": 0.029734769836068153,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4042727947235107,
      "step": 10730
    },
    {
      "epoch": 0.5110476190476191,
      "grad_norm": 0.02726336382329464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4278810024261475,
      "step": 10732
    },
    {
      "epoch": 0.5111428571428571,
      "grad_norm": 0.029170295223593712,
      "learning_rate": 0.024000000208616257,
      "loss": 2.440880060195923,
      "step": 10734
    },
    {
      "epoch": 0.5112380952380953,
      "grad_norm": 0.03113229013979435,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4125707149505615,
      "step": 10736
    },
    {
      "epoch": 0.5113333333333333,
      "grad_norm": 0.028234543278813362,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4556307792663574,
      "step": 10738
    },
    {
      "epoch": 0.5114285714285715,
      "grad_norm": 0.02789166383445263,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4220004081726074,
      "step": 10740
    },
    {
      "epoch": 0.5115238095238095,
      "grad_norm": 0.02681007795035839,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4198851585388184,
      "step": 10742
    },
    {
      "epoch": 0.5116190476190476,
      "grad_norm": 0.02697092667222023,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4243569374084473,
      "step": 10744
    },
    {
      "epoch": 0.5117142857142857,
      "grad_norm": 0.029569095000624657,
      "learning_rate": 0.024000000208616257,
      "loss": 2.412090301513672,
      "step": 10746
    },
    {
      "epoch": 0.5118095238095238,
      "grad_norm": 0.029564835131168365,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4282002449035645,
      "step": 10748
    },
    {
      "epoch": 0.5119047619047619,
      "grad_norm": 0.02728309854865074,
      "learning_rate": 0.024000000208616257,
      "loss": 2.425595760345459,
      "step": 10750
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.027898941189050674,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385802745819092,
      "step": 10752
    },
    {
      "epoch": 0.512095238095238,
      "grad_norm": 0.03258281573653221,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4370594024658203,
      "step": 10754
    },
    {
      "epoch": 0.5121904761904762,
      "grad_norm": 0.02785218134522438,
      "learning_rate": 0.024000000208616257,
      "loss": 2.423847198486328,
      "step": 10756
    },
    {
      "epoch": 0.5122857142857142,
      "grad_norm": 0.033212609589099884,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4045321941375732,
      "step": 10758
    },
    {
      "epoch": 0.5123809523809524,
      "grad_norm": 0.02857373096048832,
      "learning_rate": 0.024000000208616257,
      "loss": 2.457590341567993,
      "step": 10760
    },
    {
      "epoch": 0.5124761904761905,
      "grad_norm": 0.028279412537813187,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4311556816101074,
      "step": 10762
    },
    {
      "epoch": 0.5125714285714286,
      "grad_norm": 0.030454231426119804,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4481582641601562,
      "step": 10764
    },
    {
      "epoch": 0.5126666666666667,
      "grad_norm": 0.02754177339375019,
      "learning_rate": 0.024000000208616257,
      "loss": 2.427992582321167,
      "step": 10766
    },
    {
      "epoch": 0.5127619047619048,
      "grad_norm": 0.031118139624595642,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4154305458068848,
      "step": 10768
    },
    {
      "epoch": 0.5128571428571429,
      "grad_norm": 0.03571861609816551,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4215152263641357,
      "step": 10770
    },
    {
      "epoch": 0.5129523809523809,
      "grad_norm": 0.043497152626514435,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4135520458221436,
      "step": 10772
    },
    {
      "epoch": 0.5130476190476191,
      "grad_norm": 0.04533176124095917,
      "learning_rate": 0.024000000208616257,
      "loss": 2.418574333190918,
      "step": 10774
    },
    {
      "epoch": 0.5131428571428571,
      "grad_norm": 0.03467651829123497,
      "learning_rate": 0.024000000208616257,
      "loss": 2.444568157196045,
      "step": 10776
    },
    {
      "epoch": 0.5132380952380953,
      "grad_norm": 0.03260539099574089,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4605817794799805,
      "step": 10778
    },
    {
      "epoch": 0.5133333333333333,
      "grad_norm": 0.02711736597120762,
      "learning_rate": 0.024000000208616257,
      "loss": 2.405381679534912,
      "step": 10780
    },
    {
      "epoch": 0.5134285714285715,
      "grad_norm": 0.027648475021123886,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4513559341430664,
      "step": 10782
    },
    {
      "epoch": 0.5135238095238095,
      "grad_norm": 0.027604317292571068,
      "learning_rate": 0.024000000208616257,
      "loss": 2.379446506500244,
      "step": 10784
    },
    {
      "epoch": 0.5136190476190476,
      "grad_norm": 0.0269109345972538,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4433422088623047,
      "step": 10786
    },
    {
      "epoch": 0.5137142857142857,
      "grad_norm": 0.02740618772804737,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3776769638061523,
      "step": 10788
    },
    {
      "epoch": 0.5138095238095238,
      "grad_norm": 0.03022061660885811,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4248032569885254,
      "step": 10790
    },
    {
      "epoch": 0.5139047619047619,
      "grad_norm": 0.03221261873841286,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4208693504333496,
      "step": 10792
    },
    {
      "epoch": 0.514,
      "grad_norm": 0.028901338577270508,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4371752738952637,
      "step": 10794
    },
    {
      "epoch": 0.514095238095238,
      "grad_norm": 0.028612300753593445,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4397635459899902,
      "step": 10796
    },
    {
      "epoch": 0.5141904761904762,
      "grad_norm": 0.026482941582798958,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4774627685546875,
      "step": 10798
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.027085842564702034,
      "learning_rate": 0.024000000208616257,
      "loss": 2.409822463989258,
      "step": 10800
    },
    {
      "epoch": 0.5143809523809524,
      "grad_norm": 0.030337488278746605,
      "learning_rate": 0.024000000208616257,
      "loss": 2.423346519470215,
      "step": 10802
    },
    {
      "epoch": 0.5144761904761905,
      "grad_norm": 0.03300487622618675,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4265012741088867,
      "step": 10804
    },
    {
      "epoch": 0.5145714285714286,
      "grad_norm": 0.031124280765652657,
      "learning_rate": 0.024000000208616257,
      "loss": 2.426905632019043,
      "step": 10806
    },
    {
      "epoch": 0.5146666666666667,
      "grad_norm": 0.027340702712535858,
      "learning_rate": 0.024000000208616257,
      "loss": 2.438143730163574,
      "step": 10808
    },
    {
      "epoch": 0.5147619047619048,
      "grad_norm": 0.029811980202794075,
      "learning_rate": 0.024000000208616257,
      "loss": 2.45957088470459,
      "step": 10810
    },
    {
      "epoch": 0.5148571428571429,
      "grad_norm": 0.027415955439209938,
      "learning_rate": 0.024000000208616257,
      "loss": 2.431168556213379,
      "step": 10812
    },
    {
      "epoch": 0.5149523809523809,
      "grad_norm": 0.029767345637083054,
      "learning_rate": 0.024000000208616257,
      "loss": 2.411663293838501,
      "step": 10814
    },
    {
      "epoch": 0.5150476190476191,
      "grad_norm": 0.029197830706834793,
      "learning_rate": 0.024000000208616257,
      "loss": 2.404855251312256,
      "step": 10816
    },
    {
      "epoch": 0.5151428571428571,
      "grad_norm": 0.02758631482720375,
      "learning_rate": 0.024000000208616257,
      "loss": 2.420595645904541,
      "step": 10818
    },
    {
      "epoch": 0.5152380952380953,
      "grad_norm": 0.02917136810719967,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4288551807403564,
      "step": 10820
    },
    {
      "epoch": 0.5153333333333333,
      "grad_norm": 0.027326438575983047,
      "learning_rate": 0.024000000208616257,
      "loss": 2.440446138381958,
      "step": 10822
    },
    {
      "epoch": 0.5154285714285715,
      "grad_norm": 0.030733846127986908,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4471354484558105,
      "step": 10824
    },
    {
      "epoch": 0.5155238095238095,
      "grad_norm": 0.027158789336681366,
      "learning_rate": 0.024000000208616257,
      "loss": 2.426403045654297,
      "step": 10826
    },
    {
      "epoch": 0.5156190476190476,
      "grad_norm": 0.028114357963204384,
      "learning_rate": 0.024000000208616257,
      "loss": 2.419297218322754,
      "step": 10828
    },
    {
      "epoch": 0.5157142857142857,
      "grad_norm": 0.02671000547707081,
      "learning_rate": 0.024000000208616257,
      "loss": 2.409165859222412,
      "step": 10830
    },
    {
      "epoch": 0.5158095238095238,
      "grad_norm": 0.02869689092040062,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401791572570801,
      "step": 10832
    },
    {
      "epoch": 0.5159047619047619,
      "grad_norm": 0.028429705649614334,
      "learning_rate": 0.024000000208616257,
      "loss": 2.438840389251709,
      "step": 10834
    },
    {
      "epoch": 0.516,
      "grad_norm": 0.02853168360888958,
      "learning_rate": 0.024000000208616257,
      "loss": 2.422635555267334,
      "step": 10836
    },
    {
      "epoch": 0.516095238095238,
      "grad_norm": 0.027284730225801468,
      "learning_rate": 0.024000000208616257,
      "loss": 2.434631586074829,
      "step": 10838
    },
    {
      "epoch": 0.5161904761904762,
      "grad_norm": 0.02696293033659458,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4332311153411865,
      "step": 10840
    },
    {
      "epoch": 0.5162857142857142,
      "grad_norm": 0.028007159009575844,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3859901428222656,
      "step": 10842
    },
    {
      "epoch": 0.5163809523809524,
      "grad_norm": 0.027695976197719574,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3970654010772705,
      "step": 10844
    },
    {
      "epoch": 0.5164761904761904,
      "grad_norm": 0.029894325882196426,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3980603218078613,
      "step": 10846
    },
    {
      "epoch": 0.5165714285714286,
      "grad_norm": 0.0275436844676733,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4179580211639404,
      "step": 10848
    },
    {
      "epoch": 0.5166666666666667,
      "grad_norm": 0.02733805775642395,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4248297214508057,
      "step": 10850
    },
    {
      "epoch": 0.5167619047619048,
      "grad_norm": 0.027735982090234756,
      "learning_rate": 0.024000000208616257,
      "loss": 2.381918430328369,
      "step": 10852
    },
    {
      "epoch": 0.5168571428571429,
      "grad_norm": 0.027335919439792633,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4256386756896973,
      "step": 10854
    },
    {
      "epoch": 0.5169523809523809,
      "grad_norm": 0.027062591165304184,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4205195903778076,
      "step": 10856
    },
    {
      "epoch": 0.5170476190476191,
      "grad_norm": 0.028590183705091476,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4076125621795654,
      "step": 10858
    },
    {
      "epoch": 0.5171428571428571,
      "grad_norm": 0.027816032990813255,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4182631969451904,
      "step": 10860
    },
    {
      "epoch": 0.5172380952380953,
      "grad_norm": 0.02840322069823742,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3900861740112305,
      "step": 10862
    },
    {
      "epoch": 0.5173333333333333,
      "grad_norm": 0.02666543796658516,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4119417667388916,
      "step": 10864
    },
    {
      "epoch": 0.5174285714285715,
      "grad_norm": 0.02678517997264862,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4183881282806396,
      "step": 10866
    },
    {
      "epoch": 0.5175238095238095,
      "grad_norm": 0.027600247412919998,
      "learning_rate": 0.024000000208616257,
      "loss": 2.404691696166992,
      "step": 10868
    },
    {
      "epoch": 0.5176190476190476,
      "grad_norm": 0.02743578515946865,
      "learning_rate": 0.024000000208616257,
      "loss": 2.425474166870117,
      "step": 10870
    },
    {
      "epoch": 0.5177142857142857,
      "grad_norm": 0.029706701636314392,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4125113487243652,
      "step": 10872
    },
    {
      "epoch": 0.5178095238095238,
      "grad_norm": 0.027538591995835304,
      "learning_rate": 0.024000000208616257,
      "loss": 2.39963436126709,
      "step": 10874
    },
    {
      "epoch": 0.5179047619047619,
      "grad_norm": 0.026627980172634125,
      "learning_rate": 0.024000000208616257,
      "loss": 2.373406410217285,
      "step": 10876
    },
    {
      "epoch": 0.518,
      "grad_norm": 0.026556629687547684,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4311232566833496,
      "step": 10878
    },
    {
      "epoch": 0.518095238095238,
      "grad_norm": 0.027132030576467514,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3812549114227295,
      "step": 10880
    },
    {
      "epoch": 0.5181904761904762,
      "grad_norm": 0.027945758774876595,
      "learning_rate": 0.024000000208616257,
      "loss": 2.409986972808838,
      "step": 10882
    },
    {
      "epoch": 0.5182857142857142,
      "grad_norm": 0.030229704454541206,
      "learning_rate": 0.024000000208616257,
      "loss": 2.371941328048706,
      "step": 10884
    },
    {
      "epoch": 0.5183809523809524,
      "grad_norm": 0.026768120005726814,
      "learning_rate": 0.024000000208616257,
      "loss": 2.403003215789795,
      "step": 10886
    },
    {
      "epoch": 0.5184761904761904,
      "grad_norm": 0.02787279337644577,
      "learning_rate": 0.024000000208616257,
      "loss": 2.395101547241211,
      "step": 10888
    },
    {
      "epoch": 0.5185714285714286,
      "grad_norm": 0.02718157321214676,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401400566101074,
      "step": 10890
    },
    {
      "epoch": 0.5186666666666667,
      "grad_norm": 0.027039825916290283,
      "learning_rate": 0.024000000208616257,
      "loss": 2.368460178375244,
      "step": 10892
    },
    {
      "epoch": 0.5187619047619048,
      "grad_norm": 0.03323078528046608,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3997457027435303,
      "step": 10894
    },
    {
      "epoch": 0.5188571428571429,
      "grad_norm": 0.027272474020719528,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396824359893799,
      "step": 10896
    },
    {
      "epoch": 0.5189523809523809,
      "grad_norm": 0.027813421562314034,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3734545707702637,
      "step": 10898
    },
    {
      "epoch": 0.5190476190476191,
      "grad_norm": 0.027445625513792038,
      "learning_rate": 0.024000000208616257,
      "loss": 2.376365900039673,
      "step": 10900
    },
    {
      "epoch": 0.5191428571428571,
      "grad_norm": 0.028931185603141785,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4106640815734863,
      "step": 10902
    },
    {
      "epoch": 0.5192380952380953,
      "grad_norm": 0.03152277693152428,
      "learning_rate": 0.024000000208616257,
      "loss": 2.349529504776001,
      "step": 10904
    },
    {
      "epoch": 0.5193333333333333,
      "grad_norm": 0.0283840112388134,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3683528900146484,
      "step": 10906
    },
    {
      "epoch": 0.5194285714285715,
      "grad_norm": 0.026969676837325096,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3616185188293457,
      "step": 10908
    },
    {
      "epoch": 0.5195238095238095,
      "grad_norm": 0.02846386469900608,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3853394985198975,
      "step": 10910
    },
    {
      "epoch": 0.5196190476190476,
      "grad_norm": 0.028119977563619614,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3827872276306152,
      "step": 10912
    },
    {
      "epoch": 0.5197142857142857,
      "grad_norm": 0.027044815942645073,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398042678833008,
      "step": 10914
    },
    {
      "epoch": 0.5198095238095238,
      "grad_norm": 0.02817191742360592,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3940420150756836,
      "step": 10916
    },
    {
      "epoch": 0.5199047619047619,
      "grad_norm": 0.02781887724995613,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4250102043151855,
      "step": 10918
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.027518128976225853,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363058090209961,
      "step": 10920
    },
    {
      "epoch": 0.520095238095238,
      "grad_norm": 0.026773935183882713,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3985869884490967,
      "step": 10922
    },
    {
      "epoch": 0.5201904761904762,
      "grad_norm": 0.02828143909573555,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3532557487487793,
      "step": 10924
    },
    {
      "epoch": 0.5202857142857142,
      "grad_norm": 0.028142159804701805,
      "learning_rate": 0.024000000208616257,
      "loss": 2.417469024658203,
      "step": 10926
    },
    {
      "epoch": 0.5203809523809524,
      "grad_norm": 0.028300350531935692,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401857852935791,
      "step": 10928
    },
    {
      "epoch": 0.5204761904761904,
      "grad_norm": 0.028452519327402115,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3957650661468506,
      "step": 10930
    },
    {
      "epoch": 0.5205714285714286,
      "grad_norm": 0.0280751995742321,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3765361309051514,
      "step": 10932
    },
    {
      "epoch": 0.5206666666666667,
      "grad_norm": 0.02676212601363659,
      "learning_rate": 0.024000000208616257,
      "loss": 2.389497995376587,
      "step": 10934
    },
    {
      "epoch": 0.5207619047619048,
      "grad_norm": 0.026592198759317398,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3653082847595215,
      "step": 10936
    },
    {
      "epoch": 0.5208571428571429,
      "grad_norm": 0.028094664216041565,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382047176361084,
      "step": 10938
    },
    {
      "epoch": 0.520952380952381,
      "grad_norm": 0.02886667102575302,
      "learning_rate": 0.024000000208616257,
      "loss": 2.365175247192383,
      "step": 10940
    },
    {
      "epoch": 0.5210476190476191,
      "grad_norm": 0.030030475929379463,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3671762943267822,
      "step": 10942
    },
    {
      "epoch": 0.5211428571428571,
      "grad_norm": 0.026599282398819923,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3536267280578613,
      "step": 10944
    },
    {
      "epoch": 0.5212380952380953,
      "grad_norm": 0.02759343571960926,
      "learning_rate": 0.024000000208616257,
      "loss": 2.371765375137329,
      "step": 10946
    },
    {
      "epoch": 0.5213333333333333,
      "grad_norm": 0.02849097177386284,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3817193508148193,
      "step": 10948
    },
    {
      "epoch": 0.5214285714285715,
      "grad_norm": 0.028304601088166237,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3891706466674805,
      "step": 10950
    },
    {
      "epoch": 0.5215238095238095,
      "grad_norm": 0.027825558558106422,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3703360557556152,
      "step": 10952
    },
    {
      "epoch": 0.5216190476190476,
      "grad_norm": 0.03053438477218151,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382521629333496,
      "step": 10954
    },
    {
      "epoch": 0.5217142857142857,
      "grad_norm": 0.030610226094722748,
      "learning_rate": 0.024000000208616257,
      "loss": 2.373490333557129,
      "step": 10956
    },
    {
      "epoch": 0.5218095238095238,
      "grad_norm": 0.032395727932453156,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3874850273132324,
      "step": 10958
    },
    {
      "epoch": 0.5219047619047619,
      "grad_norm": 0.02782427705824375,
      "learning_rate": 0.024000000208616257,
      "loss": 2.393272876739502,
      "step": 10960
    },
    {
      "epoch": 0.522,
      "grad_norm": 0.028692664578557014,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38773250579834,
      "step": 10962
    },
    {
      "epoch": 0.5220952380952381,
      "grad_norm": 0.028684629127383232,
      "learning_rate": 0.024000000208616257,
      "loss": 2.372535228729248,
      "step": 10964
    },
    {
      "epoch": 0.5221904761904762,
      "grad_norm": 0.028519008308649063,
      "learning_rate": 0.024000000208616257,
      "loss": 2.364248275756836,
      "step": 10966
    },
    {
      "epoch": 0.5222857142857142,
      "grad_norm": 0.03039529174566269,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4036483764648438,
      "step": 10968
    },
    {
      "epoch": 0.5223809523809524,
      "grad_norm": 0.027386900037527084,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3781886100769043,
      "step": 10970
    },
    {
      "epoch": 0.5224761904761904,
      "grad_norm": 0.02808213420212269,
      "learning_rate": 0.024000000208616257,
      "loss": 2.377593755722046,
      "step": 10972
    },
    {
      "epoch": 0.5225714285714286,
      "grad_norm": 0.03017336316406727,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3923425674438477,
      "step": 10974
    },
    {
      "epoch": 0.5226666666666666,
      "grad_norm": 0.030408494174480438,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3535449504852295,
      "step": 10976
    },
    {
      "epoch": 0.5227619047619048,
      "grad_norm": 0.02894972637295723,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3772740364074707,
      "step": 10978
    },
    {
      "epoch": 0.5228571428571429,
      "grad_norm": 0.028558552265167236,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3603782653808594,
      "step": 10980
    },
    {
      "epoch": 0.522952380952381,
      "grad_norm": 0.028046581894159317,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3754918575286865,
      "step": 10982
    },
    {
      "epoch": 0.5230476190476191,
      "grad_norm": 0.03348696231842041,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3791589736938477,
      "step": 10984
    },
    {
      "epoch": 0.5231428571428571,
      "grad_norm": 0.028050348162651062,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4229931831359863,
      "step": 10986
    },
    {
      "epoch": 0.5232380952380953,
      "grad_norm": 0.026278799399733543,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380277633666992,
      "step": 10988
    },
    {
      "epoch": 0.5233333333333333,
      "grad_norm": 0.028793940320611,
      "learning_rate": 0.024000000208616257,
      "loss": 2.379754066467285,
      "step": 10990
    },
    {
      "epoch": 0.5234285714285715,
      "grad_norm": 0.029690174385905266,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3935444355010986,
      "step": 10992
    },
    {
      "epoch": 0.5235238095238095,
      "grad_norm": 0.03092595748603344,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396070957183838,
      "step": 10994
    },
    {
      "epoch": 0.5236190476190477,
      "grad_norm": 0.03342796117067337,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3956539630889893,
      "step": 10996
    },
    {
      "epoch": 0.5237142857142857,
      "grad_norm": 0.028770800679922104,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3547701835632324,
      "step": 10998
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 0.027517497539520264,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3856568336486816,
      "step": 11000
    },
    {
      "epoch": 0.5239047619047619,
      "grad_norm": 0.026922021061182022,
      "learning_rate": 0.024000000208616257,
      "loss": 2.377323627471924,
      "step": 11002
    },
    {
      "epoch": 0.524,
      "grad_norm": 0.03069390170276165,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3994216918945312,
      "step": 11004
    },
    {
      "epoch": 0.5240952380952381,
      "grad_norm": 0.029388021677732468,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380122184753418,
      "step": 11006
    },
    {
      "epoch": 0.5241904761904762,
      "grad_norm": 0.028747260570526123,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3971943855285645,
      "step": 11008
    },
    {
      "epoch": 0.5242857142857142,
      "grad_norm": 0.028057722374796867,
      "learning_rate": 0.024000000208616257,
      "loss": 2.352389335632324,
      "step": 11010
    },
    {
      "epoch": 0.5243809523809524,
      "grad_norm": 0.026997411623597145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385406494140625,
      "step": 11012
    },
    {
      "epoch": 0.5244761904761904,
      "grad_norm": 0.02697424590587616,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3847432136535645,
      "step": 11014
    },
    {
      "epoch": 0.5245714285714286,
      "grad_norm": 0.027413535863161087,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4013118743896484,
      "step": 11016
    },
    {
      "epoch": 0.5246666666666666,
      "grad_norm": 0.028676962479948997,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4020252227783203,
      "step": 11018
    },
    {
      "epoch": 0.5247619047619048,
      "grad_norm": 0.027797499671578407,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385441780090332,
      "step": 11020
    },
    {
      "epoch": 0.5248571428571429,
      "grad_norm": 0.02737533114850521,
      "learning_rate": 0.024000000208616257,
      "loss": 2.394955635070801,
      "step": 11022
    },
    {
      "epoch": 0.524952380952381,
      "grad_norm": 0.028084510937333107,
      "learning_rate": 0.024000000208616257,
      "loss": 2.399773597717285,
      "step": 11024
    },
    {
      "epoch": 0.5250476190476191,
      "grad_norm": 0.027968719601631165,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3828110694885254,
      "step": 11026
    },
    {
      "epoch": 0.5251428571428571,
      "grad_norm": 0.027594784274697304,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3895044326782227,
      "step": 11028
    },
    {
      "epoch": 0.5252380952380953,
      "grad_norm": 0.028636446222662926,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380718231201172,
      "step": 11030
    },
    {
      "epoch": 0.5253333333333333,
      "grad_norm": 0.03015761822462082,
      "learning_rate": 0.024000000208616257,
      "loss": 2.395009994506836,
      "step": 11032
    },
    {
      "epoch": 0.5254285714285715,
      "grad_norm": 0.031124062836170197,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3714871406555176,
      "step": 11034
    },
    {
      "epoch": 0.5255238095238095,
      "grad_norm": 0.031375668942928314,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3795337677001953,
      "step": 11036
    },
    {
      "epoch": 0.5256190476190477,
      "grad_norm": 0.026825549080967903,
      "learning_rate": 0.024000000208616257,
      "loss": 2.395346164703369,
      "step": 11038
    },
    {
      "epoch": 0.5257142857142857,
      "grad_norm": 0.028343046084046364,
      "learning_rate": 0.024000000208616257,
      "loss": 2.378469467163086,
      "step": 11040
    },
    {
      "epoch": 0.5258095238095238,
      "grad_norm": 0.029953889548778534,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3791890144348145,
      "step": 11042
    },
    {
      "epoch": 0.5259047619047619,
      "grad_norm": 0.02761927619576454,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3651442527770996,
      "step": 11044
    },
    {
      "epoch": 0.526,
      "grad_norm": 0.02757984586060047,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3621644973754883,
      "step": 11046
    },
    {
      "epoch": 0.5260952380952381,
      "grad_norm": 0.029991870746016502,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3863306045532227,
      "step": 11048
    },
    {
      "epoch": 0.5261904761904762,
      "grad_norm": 0.0356031209230423,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3561859130859375,
      "step": 11050
    },
    {
      "epoch": 0.5262857142857142,
      "grad_norm": 0.028012128546833992,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3734779357910156,
      "step": 11052
    },
    {
      "epoch": 0.5263809523809524,
      "grad_norm": 0.026408618316054344,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3618178367614746,
      "step": 11054
    },
    {
      "epoch": 0.5264761904761904,
      "grad_norm": 0.027616988867521286,
      "learning_rate": 0.024000000208616257,
      "loss": 2.409976005554199,
      "step": 11056
    },
    {
      "epoch": 0.5265714285714286,
      "grad_norm": 0.031077546998858452,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3813650608062744,
      "step": 11058
    },
    {
      "epoch": 0.5266666666666666,
      "grad_norm": 0.028142599388957024,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3801722526550293,
      "step": 11060
    },
    {
      "epoch": 0.5267619047619048,
      "grad_norm": 0.02808581292629242,
      "learning_rate": 0.024000000208616257,
      "loss": 2.389758586883545,
      "step": 11062
    },
    {
      "epoch": 0.5268571428571428,
      "grad_norm": 0.032819002866744995,
      "learning_rate": 0.024000000208616257,
      "loss": 2.407188653945923,
      "step": 11064
    },
    {
      "epoch": 0.526952380952381,
      "grad_norm": 0.027570469304919243,
      "learning_rate": 0.024000000208616257,
      "loss": 2.365492582321167,
      "step": 11066
    },
    {
      "epoch": 0.5270476190476191,
      "grad_norm": 0.030326316133141518,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3539249897003174,
      "step": 11068
    },
    {
      "epoch": 0.5271428571428571,
      "grad_norm": 0.028578324243426323,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3629660606384277,
      "step": 11070
    },
    {
      "epoch": 0.5272380952380953,
      "grad_norm": 0.02929593250155449,
      "learning_rate": 0.024000000208616257,
      "loss": 2.372921943664551,
      "step": 11072
    },
    {
      "epoch": 0.5273333333333333,
      "grad_norm": 0.026652446016669273,
      "learning_rate": 0.024000000208616257,
      "loss": 2.377102851867676,
      "step": 11074
    },
    {
      "epoch": 0.5274285714285715,
      "grad_norm": 0.02578708902001381,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3523337841033936,
      "step": 11076
    },
    {
      "epoch": 0.5275238095238095,
      "grad_norm": 0.027509555220603943,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3842384815216064,
      "step": 11078
    },
    {
      "epoch": 0.5276190476190477,
      "grad_norm": 0.027045611292123795,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4017410278320312,
      "step": 11080
    },
    {
      "epoch": 0.5277142857142857,
      "grad_norm": 0.027369288727641106,
      "learning_rate": 0.024000000208616257,
      "loss": 2.351515293121338,
      "step": 11082
    },
    {
      "epoch": 0.5278095238095238,
      "grad_norm": 0.029159268364310265,
      "learning_rate": 0.024000000208616257,
      "loss": 2.348139762878418,
      "step": 11084
    },
    {
      "epoch": 0.5279047619047619,
      "grad_norm": 0.03543887659907341,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3817386627197266,
      "step": 11086
    },
    {
      "epoch": 0.528,
      "grad_norm": 0.031070737168192863,
      "learning_rate": 0.024000000208616257,
      "loss": 2.354475975036621,
      "step": 11088
    },
    {
      "epoch": 0.5280952380952381,
      "grad_norm": 0.02954612858593464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3552088737487793,
      "step": 11090
    },
    {
      "epoch": 0.5281904761904762,
      "grad_norm": 0.036063302308321,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3837406635284424,
      "step": 11092
    },
    {
      "epoch": 0.5282857142857142,
      "grad_norm": 0.033483944833278656,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380246162414551,
      "step": 11094
    },
    {
      "epoch": 0.5283809523809524,
      "grad_norm": 0.030107146129012108,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380235433578491,
      "step": 11096
    },
    {
      "epoch": 0.5284761904761904,
      "grad_norm": 0.02663325145840645,
      "learning_rate": 0.024000000208616257,
      "loss": 2.357118844985962,
      "step": 11098
    },
    {
      "epoch": 0.5285714285714286,
      "grad_norm": 0.02690831944346428,
      "learning_rate": 0.024000000208616257,
      "loss": 2.365609645843506,
      "step": 11100
    },
    {
      "epoch": 0.5286666666666666,
      "grad_norm": 0.027078067883849144,
      "learning_rate": 0.024000000208616257,
      "loss": 2.374390125274658,
      "step": 11102
    },
    {
      "epoch": 0.5287619047619048,
      "grad_norm": 0.031092600896954536,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4152374267578125,
      "step": 11104
    },
    {
      "epoch": 0.5288571428571428,
      "grad_norm": 0.027397634461522102,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3779001235961914,
      "step": 11106
    },
    {
      "epoch": 0.528952380952381,
      "grad_norm": 0.026688920333981514,
      "learning_rate": 0.024000000208616257,
      "loss": 2.374969244003296,
      "step": 11108
    },
    {
      "epoch": 0.5290476190476191,
      "grad_norm": 0.030637159943580627,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396486282348633,
      "step": 11110
    },
    {
      "epoch": 0.5291428571428571,
      "grad_norm": 0.03063754364848137,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3848512172698975,
      "step": 11112
    },
    {
      "epoch": 0.5292380952380953,
      "grad_norm": 0.029082894325256348,
      "learning_rate": 0.024000000208616257,
      "loss": 2.366140842437744,
      "step": 11114
    },
    {
      "epoch": 0.5293333333333333,
      "grad_norm": 0.027403520420193672,
      "learning_rate": 0.024000000208616257,
      "loss": 2.409027576446533,
      "step": 11116
    },
    {
      "epoch": 0.5294285714285715,
      "grad_norm": 0.02755184844136238,
      "learning_rate": 0.024000000208616257,
      "loss": 2.360198497772217,
      "step": 11118
    },
    {
      "epoch": 0.5295238095238095,
      "grad_norm": 0.02662978135049343,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3225224018096924,
      "step": 11120
    },
    {
      "epoch": 0.5296190476190477,
      "grad_norm": 0.028253525495529175,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3467488288879395,
      "step": 11122
    },
    {
      "epoch": 0.5297142857142857,
      "grad_norm": 0.027419311925768852,
      "learning_rate": 0.024000000208616257,
      "loss": 2.347034454345703,
      "step": 11124
    },
    {
      "epoch": 0.5298095238095238,
      "grad_norm": 0.027173228561878204,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3754782676696777,
      "step": 11126
    },
    {
      "epoch": 0.5299047619047619,
      "grad_norm": 0.0273845586925745,
      "learning_rate": 0.024000000208616257,
      "loss": 2.39947509765625,
      "step": 11128
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.031402427703142166,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3544037342071533,
      "step": 11130
    },
    {
      "epoch": 0.5300952380952381,
      "grad_norm": 0.029914598912000656,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3619093894958496,
      "step": 11132
    },
    {
      "epoch": 0.5301904761904762,
      "grad_norm": 0.03066035360097885,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3275694847106934,
      "step": 11134
    },
    {
      "epoch": 0.5302857142857142,
      "grad_norm": 0.028541622683405876,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38793683052063,
      "step": 11136
    },
    {
      "epoch": 0.5303809523809524,
      "grad_norm": 0.02721686102449894,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4074301719665527,
      "step": 11138
    },
    {
      "epoch": 0.5304761904761904,
      "grad_norm": 0.02796047553420067,
      "learning_rate": 0.024000000208616257,
      "loss": 2.407209873199463,
      "step": 11140
    },
    {
      "epoch": 0.5305714285714286,
      "grad_norm": 0.027987850829958916,
      "learning_rate": 0.024000000208616257,
      "loss": 2.365279197692871,
      "step": 11142
    },
    {
      "epoch": 0.5306666666666666,
      "grad_norm": 0.027056042104959488,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3440940380096436,
      "step": 11144
    },
    {
      "epoch": 0.5307619047619048,
      "grad_norm": 0.027407553046941757,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3624470233917236,
      "step": 11146
    },
    {
      "epoch": 0.5308571428571428,
      "grad_norm": 0.029195748269557953,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3518383502960205,
      "step": 11148
    },
    {
      "epoch": 0.530952380952381,
      "grad_norm": 0.027737673372030258,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382370948791504,
      "step": 11150
    },
    {
      "epoch": 0.5310476190476191,
      "grad_norm": 0.02785484679043293,
      "learning_rate": 0.024000000208616257,
      "loss": 2.377800941467285,
      "step": 11152
    },
    {
      "epoch": 0.5311428571428571,
      "grad_norm": 0.02955338917672634,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385396957397461,
      "step": 11154
    },
    {
      "epoch": 0.5312380952380953,
      "grad_norm": 0.027256552129983902,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3587851524353027,
      "step": 11156
    },
    {
      "epoch": 0.5313333333333333,
      "grad_norm": 0.027779756113886833,
      "learning_rate": 0.024000000208616257,
      "loss": 2.395404815673828,
      "step": 11158
    },
    {
      "epoch": 0.5314285714285715,
      "grad_norm": 0.028377661481499672,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355616569519043,
      "step": 11160
    },
    {
      "epoch": 0.5315238095238095,
      "grad_norm": 0.026550384238362312,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3815488815307617,
      "step": 11162
    },
    {
      "epoch": 0.5316190476190477,
      "grad_norm": 0.029107529670000076,
      "learning_rate": 0.024000000208616257,
      "loss": 2.386756181716919,
      "step": 11164
    },
    {
      "epoch": 0.5317142857142857,
      "grad_norm": 0.027550548315048218,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4085843563079834,
      "step": 11166
    },
    {
      "epoch": 0.5318095238095238,
      "grad_norm": 0.026696396991610527,
      "learning_rate": 0.024000000208616257,
      "loss": 2.368638277053833,
      "step": 11168
    },
    {
      "epoch": 0.5319047619047619,
      "grad_norm": 0.029446523636579514,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3419272899627686,
      "step": 11170
    },
    {
      "epoch": 0.532,
      "grad_norm": 0.03325372561812401,
      "learning_rate": 0.024000000208616257,
      "loss": 2.365987539291382,
      "step": 11172
    },
    {
      "epoch": 0.5320952380952381,
      "grad_norm": 0.031305115669965744,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3478620052337646,
      "step": 11174
    },
    {
      "epoch": 0.5321904761904762,
      "grad_norm": 0.027045704424381256,
      "learning_rate": 0.024000000208616257,
      "loss": 2.347343683242798,
      "step": 11176
    },
    {
      "epoch": 0.5322857142857143,
      "grad_norm": 0.03274499997496605,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3712480068206787,
      "step": 11178
    },
    {
      "epoch": 0.5323809523809524,
      "grad_norm": 0.027391299605369568,
      "learning_rate": 0.024000000208616257,
      "loss": 2.353050470352173,
      "step": 11180
    },
    {
      "epoch": 0.5324761904761904,
      "grad_norm": 0.02877148613333702,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350368022918701,
      "step": 11182
    },
    {
      "epoch": 0.5325714285714286,
      "grad_norm": 0.027596522122621536,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3735809326171875,
      "step": 11184
    },
    {
      "epoch": 0.5326666666666666,
      "grad_norm": 0.027726229280233383,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3483333587646484,
      "step": 11186
    },
    {
      "epoch": 0.5327619047619048,
      "grad_norm": 0.026665691286325455,
      "learning_rate": 0.024000000208616257,
      "loss": 2.332397222518921,
      "step": 11188
    },
    {
      "epoch": 0.5328571428571428,
      "grad_norm": 0.02678600139915943,
      "learning_rate": 0.024000000208616257,
      "loss": 2.344310760498047,
      "step": 11190
    },
    {
      "epoch": 0.532952380952381,
      "grad_norm": 0.0275727491825819,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363680839538574,
      "step": 11192
    },
    {
      "epoch": 0.533047619047619,
      "grad_norm": 0.02749115787446499,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3786463737487793,
      "step": 11194
    },
    {
      "epoch": 0.5331428571428571,
      "grad_norm": 0.02801203541457653,
      "learning_rate": 0.024000000208616257,
      "loss": 2.313913583755493,
      "step": 11196
    },
    {
      "epoch": 0.5332380952380953,
      "grad_norm": 0.029240012168884277,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363111972808838,
      "step": 11198
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.026617715135216713,
      "learning_rate": 0.024000000208616257,
      "loss": 2.371135711669922,
      "step": 11200
    },
    {
      "epoch": 0.5334285714285715,
      "grad_norm": 0.026866406202316284,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3525633811950684,
      "step": 11202
    },
    {
      "epoch": 0.5335238095238095,
      "grad_norm": 0.029019754379987717,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401376485824585,
      "step": 11204
    },
    {
      "epoch": 0.5336190476190477,
      "grad_norm": 0.02689780667424202,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3599209785461426,
      "step": 11206
    },
    {
      "epoch": 0.5337142857142857,
      "grad_norm": 0.030253170058131218,
      "learning_rate": 0.024000000208616257,
      "loss": 2.371490001678467,
      "step": 11208
    },
    {
      "epoch": 0.5338095238095238,
      "grad_norm": 0.02697974257171154,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3434603214263916,
      "step": 11210
    },
    {
      "epoch": 0.5339047619047619,
      "grad_norm": 0.027974454686045647,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3613295555114746,
      "step": 11212
    },
    {
      "epoch": 0.534,
      "grad_norm": 0.02982674539089203,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3797645568847656,
      "step": 11214
    },
    {
      "epoch": 0.5340952380952381,
      "grad_norm": 0.026322640478610992,
      "learning_rate": 0.024000000208616257,
      "loss": 2.366943359375,
      "step": 11216
    },
    {
      "epoch": 0.5341904761904762,
      "grad_norm": 0.0302659273147583,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3664722442626953,
      "step": 11218
    },
    {
      "epoch": 0.5342857142857143,
      "grad_norm": 0.02764955535531044,
      "learning_rate": 0.024000000208616257,
      "loss": 2.369924545288086,
      "step": 11220
    },
    {
      "epoch": 0.5343809523809524,
      "grad_norm": 0.030198704451322556,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3867878913879395,
      "step": 11222
    },
    {
      "epoch": 0.5344761904761904,
      "grad_norm": 0.028805473819375038,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3587377071380615,
      "step": 11224
    },
    {
      "epoch": 0.5345714285714286,
      "grad_norm": 0.0269580390304327,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3616998195648193,
      "step": 11226
    },
    {
      "epoch": 0.5346666666666666,
      "grad_norm": 0.02750840038061142,
      "learning_rate": 0.024000000208616257,
      "loss": 2.375352382659912,
      "step": 11228
    },
    {
      "epoch": 0.5347619047619048,
      "grad_norm": 0.029530763626098633,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38437557220459,
      "step": 11230
    },
    {
      "epoch": 0.5348571428571428,
      "grad_norm": 0.027558201923966408,
      "learning_rate": 0.024000000208616257,
      "loss": 2.354940891265869,
      "step": 11232
    },
    {
      "epoch": 0.534952380952381,
      "grad_norm": 0.02874298393726349,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3428750038146973,
      "step": 11234
    },
    {
      "epoch": 0.535047619047619,
      "grad_norm": 0.02806907147169113,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3691482543945312,
      "step": 11236
    },
    {
      "epoch": 0.5351428571428571,
      "grad_norm": 0.02738245017826557,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3742940425872803,
      "step": 11238
    },
    {
      "epoch": 0.5352380952380953,
      "grad_norm": 0.02597632445394993,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3279552459716797,
      "step": 11240
    },
    {
      "epoch": 0.5353333333333333,
      "grad_norm": 0.02695298194885254,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3330740928649902,
      "step": 11242
    },
    {
      "epoch": 0.5354285714285715,
      "grad_norm": 0.025878259912133217,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392328977584839,
      "step": 11244
    },
    {
      "epoch": 0.5355238095238095,
      "grad_norm": 0.02664206549525261,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3753774166107178,
      "step": 11246
    },
    {
      "epoch": 0.5356190476190477,
      "grad_norm": 0.02691582404077053,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3392393589019775,
      "step": 11248
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 0.027866017073392868,
      "learning_rate": 0.024000000208616257,
      "loss": 2.379930019378662,
      "step": 11250
    },
    {
      "epoch": 0.5358095238095238,
      "grad_norm": 0.02889213338494301,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3540284633636475,
      "step": 11252
    },
    {
      "epoch": 0.5359047619047619,
      "grad_norm": 0.029019227251410484,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3030784130096436,
      "step": 11254
    },
    {
      "epoch": 0.536,
      "grad_norm": 0.02821970358490944,
      "learning_rate": 0.024000000208616257,
      "loss": 2.328108310699463,
      "step": 11256
    },
    {
      "epoch": 0.5360952380952381,
      "grad_norm": 0.03890227526426315,
      "learning_rate": 0.024000000208616257,
      "loss": 2.344332218170166,
      "step": 11258
    },
    {
      "epoch": 0.5361904761904762,
      "grad_norm": 0.03116464614868164,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363426685333252,
      "step": 11260
    },
    {
      "epoch": 0.5362857142857143,
      "grad_norm": 0.0287016611546278,
      "learning_rate": 0.024000000208616257,
      "loss": 2.35280179977417,
      "step": 11262
    },
    {
      "epoch": 0.5363809523809524,
      "grad_norm": 0.026743680238723755,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3729398250579834,
      "step": 11264
    },
    {
      "epoch": 0.5364761904761904,
      "grad_norm": 0.02783118560910225,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3434650897979736,
      "step": 11266
    },
    {
      "epoch": 0.5365714285714286,
      "grad_norm": 0.028421372175216675,
      "learning_rate": 0.024000000208616257,
      "loss": 2.344041347503662,
      "step": 11268
    },
    {
      "epoch": 0.5366666666666666,
      "grad_norm": 0.028583701699972153,
      "learning_rate": 0.024000000208616257,
      "loss": 2.354079246520996,
      "step": 11270
    },
    {
      "epoch": 0.5367619047619048,
      "grad_norm": 0.027852723374962807,
      "learning_rate": 0.024000000208616257,
      "loss": 2.321941614151001,
      "step": 11272
    },
    {
      "epoch": 0.5368571428571428,
      "grad_norm": 0.02842511236667633,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3423471450805664,
      "step": 11274
    },
    {
      "epoch": 0.536952380952381,
      "grad_norm": 0.02788008563220501,
      "learning_rate": 0.024000000208616257,
      "loss": 2.381067991256714,
      "step": 11276
    },
    {
      "epoch": 0.537047619047619,
      "grad_norm": 0.029230304062366486,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350654125213623,
      "step": 11278
    },
    {
      "epoch": 0.5371428571428571,
      "grad_norm": 0.02772466279566288,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3466334342956543,
      "step": 11280
    },
    {
      "epoch": 0.5372380952380953,
      "grad_norm": 0.027043815702199936,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3325819969177246,
      "step": 11282
    },
    {
      "epoch": 0.5373333333333333,
      "grad_norm": 0.0284291822463274,
      "learning_rate": 0.024000000208616257,
      "loss": 2.315737724304199,
      "step": 11284
    },
    {
      "epoch": 0.5374285714285715,
      "grad_norm": 0.028794461861252785,
      "learning_rate": 0.024000000208616257,
      "loss": 2.309389591217041,
      "step": 11286
    },
    {
      "epoch": 0.5375238095238095,
      "grad_norm": 0.027796590700745583,
      "learning_rate": 0.024000000208616257,
      "loss": 2.351919412612915,
      "step": 11288
    },
    {
      "epoch": 0.5376190476190477,
      "grad_norm": 0.02857709862291813,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3385977745056152,
      "step": 11290
    },
    {
      "epoch": 0.5377142857142857,
      "grad_norm": 0.027550075203180313,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3347578048706055,
      "step": 11292
    },
    {
      "epoch": 0.5378095238095238,
      "grad_norm": 0.02713826857507229,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3463428020477295,
      "step": 11294
    },
    {
      "epoch": 0.5379047619047619,
      "grad_norm": 0.027881138026714325,
      "learning_rate": 0.024000000208616257,
      "loss": 2.307072162628174,
      "step": 11296
    },
    {
      "epoch": 0.538,
      "grad_norm": 0.027384445071220398,
      "learning_rate": 0.024000000208616257,
      "loss": 2.322704553604126,
      "step": 11298
    },
    {
      "epoch": 0.5380952380952381,
      "grad_norm": 0.02742314152419567,
      "learning_rate": 0.024000000208616257,
      "loss": 2.352038860321045,
      "step": 11300
    },
    {
      "epoch": 0.5381904761904762,
      "grad_norm": 0.03344586491584778,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363370895385742,
      "step": 11302
    },
    {
      "epoch": 0.5382857142857143,
      "grad_norm": 0.026863789185881615,
      "learning_rate": 0.024000000208616257,
      "loss": 2.315906524658203,
      "step": 11304
    },
    {
      "epoch": 0.5383809523809524,
      "grad_norm": 0.028193460777401924,
      "learning_rate": 0.024000000208616257,
      "loss": 2.327467441558838,
      "step": 11306
    },
    {
      "epoch": 0.5384761904761904,
      "grad_norm": 0.02713138610124588,
      "learning_rate": 0.024000000208616257,
      "loss": 2.372037410736084,
      "step": 11308
    },
    {
      "epoch": 0.5385714285714286,
      "grad_norm": 0.02603268064558506,
      "learning_rate": 0.024000000208616257,
      "loss": 2.352116107940674,
      "step": 11310
    },
    {
      "epoch": 0.5386666666666666,
      "grad_norm": 0.030325913801789284,
      "learning_rate": 0.024000000208616257,
      "loss": 2.323071002960205,
      "step": 11312
    },
    {
      "epoch": 0.5387619047619048,
      "grad_norm": 0.0349159762263298,
      "learning_rate": 0.024000000208616257,
      "loss": 2.336726665496826,
      "step": 11314
    },
    {
      "epoch": 0.5388571428571428,
      "grad_norm": 0.030010191723704338,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3407516479492188,
      "step": 11316
    },
    {
      "epoch": 0.538952380952381,
      "grad_norm": 0.0318528488278389,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3268747329711914,
      "step": 11318
    },
    {
      "epoch": 0.539047619047619,
      "grad_norm": 0.0325266532599926,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3324804306030273,
      "step": 11320
    },
    {
      "epoch": 0.5391428571428571,
      "grad_norm": 0.02628404274582863,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3390073776245117,
      "step": 11322
    },
    {
      "epoch": 0.5392380952380952,
      "grad_norm": 0.027256371453404427,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3394694328308105,
      "step": 11324
    },
    {
      "epoch": 0.5393333333333333,
      "grad_norm": 0.027137132361531258,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3127965927124023,
      "step": 11326
    },
    {
      "epoch": 0.5394285714285715,
      "grad_norm": 0.028431594371795654,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3514933586120605,
      "step": 11328
    },
    {
      "epoch": 0.5395238095238095,
      "grad_norm": 0.029106322675943375,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3167471885681152,
      "step": 11330
    },
    {
      "epoch": 0.5396190476190477,
      "grad_norm": 0.030645618215203285,
      "learning_rate": 0.024000000208616257,
      "loss": 2.346553325653076,
      "step": 11332
    },
    {
      "epoch": 0.5397142857142857,
      "grad_norm": 0.027858396992087364,
      "learning_rate": 0.024000000208616257,
      "loss": 2.316018581390381,
      "step": 11334
    },
    {
      "epoch": 0.5398095238095239,
      "grad_norm": 0.02922271564602852,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3240671157836914,
      "step": 11336
    },
    {
      "epoch": 0.5399047619047619,
      "grad_norm": 0.02769148163497448,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3137869834899902,
      "step": 11338
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.03195439651608467,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3355460166931152,
      "step": 11340
    },
    {
      "epoch": 0.5400952380952381,
      "grad_norm": 0.02968500182032585,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3550500869750977,
      "step": 11342
    },
    {
      "epoch": 0.5401904761904762,
      "grad_norm": 0.027186688035726547,
      "learning_rate": 0.024000000208616257,
      "loss": 2.343122959136963,
      "step": 11344
    },
    {
      "epoch": 0.5402857142857143,
      "grad_norm": 0.026452461257576942,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2987594604492188,
      "step": 11346
    },
    {
      "epoch": 0.5403809523809524,
      "grad_norm": 0.029168227687478065,
      "learning_rate": 0.024000000208616257,
      "loss": 2.319884777069092,
      "step": 11348
    },
    {
      "epoch": 0.5404761904761904,
      "grad_norm": 0.026836229488253593,
      "learning_rate": 0.024000000208616257,
      "loss": 2.326570510864258,
      "step": 11350
    },
    {
      "epoch": 0.5405714285714286,
      "grad_norm": 0.026590637862682343,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3542263507843018,
      "step": 11352
    },
    {
      "epoch": 0.5406666666666666,
      "grad_norm": 0.02848634496331215,
      "learning_rate": 0.024000000208616257,
      "loss": 2.353811025619507,
      "step": 11354
    },
    {
      "epoch": 0.5407619047619048,
      "grad_norm": 0.026729915291070938,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3356571197509766,
      "step": 11356
    },
    {
      "epoch": 0.5408571428571428,
      "grad_norm": 0.027239976450800896,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3033957481384277,
      "step": 11358
    },
    {
      "epoch": 0.540952380952381,
      "grad_norm": 0.028224997222423553,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3063106536865234,
      "step": 11360
    },
    {
      "epoch": 0.541047619047619,
      "grad_norm": 0.02719128131866455,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2901268005371094,
      "step": 11362
    },
    {
      "epoch": 0.5411428571428571,
      "grad_norm": 0.02844875305891037,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3139028549194336,
      "step": 11364
    },
    {
      "epoch": 0.5412380952380952,
      "grad_norm": 0.027386561036109924,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3276259899139404,
      "step": 11366
    },
    {
      "epoch": 0.5413333333333333,
      "grad_norm": 0.027147848159074783,
      "learning_rate": 0.024000000208616257,
      "loss": 2.329568862915039,
      "step": 11368
    },
    {
      "epoch": 0.5414285714285715,
      "grad_norm": 0.02728341519832611,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3267714977264404,
      "step": 11370
    },
    {
      "epoch": 0.5415238095238095,
      "grad_norm": 0.03087979182600975,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3554744720458984,
      "step": 11372
    },
    {
      "epoch": 0.5416190476190477,
      "grad_norm": 0.02672078087925911,
      "learning_rate": 0.024000000208616257,
      "loss": 2.302905797958374,
      "step": 11374
    },
    {
      "epoch": 0.5417142857142857,
      "grad_norm": 0.027271756902337074,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3443007469177246,
      "step": 11376
    },
    {
      "epoch": 0.5418095238095239,
      "grad_norm": 0.028215689584612846,
      "learning_rate": 0.024000000208616257,
      "loss": 2.327751636505127,
      "step": 11378
    },
    {
      "epoch": 0.5419047619047619,
      "grad_norm": 0.027604691684246063,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3244810104370117,
      "step": 11380
    },
    {
      "epoch": 0.542,
      "grad_norm": 0.03482496365904808,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3189103603363037,
      "step": 11382
    },
    {
      "epoch": 0.5420952380952381,
      "grad_norm": 0.02731895260512829,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3393666744232178,
      "step": 11384
    },
    {
      "epoch": 0.5421904761904762,
      "grad_norm": 0.027753904461860657,
      "learning_rate": 0.024000000208616257,
      "loss": 2.297027587890625,
      "step": 11386
    },
    {
      "epoch": 0.5422857142857143,
      "grad_norm": 0.027554703876376152,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3342299461364746,
      "step": 11388
    },
    {
      "epoch": 0.5423809523809524,
      "grad_norm": 0.026128727942705154,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3422980308532715,
      "step": 11390
    },
    {
      "epoch": 0.5424761904761904,
      "grad_norm": 0.028191369026899338,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3168540000915527,
      "step": 11392
    },
    {
      "epoch": 0.5425714285714286,
      "grad_norm": 0.02873975783586502,
      "learning_rate": 0.024000000208616257,
      "loss": 2.32405424118042,
      "step": 11394
    },
    {
      "epoch": 0.5426666666666666,
      "grad_norm": 0.027144305408000946,
      "learning_rate": 0.024000000208616257,
      "loss": 2.324606418609619,
      "step": 11396
    },
    {
      "epoch": 0.5427619047619048,
      "grad_norm": 0.029704570770263672,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3326940536499023,
      "step": 11398
    },
    {
      "epoch": 0.5428571428571428,
      "grad_norm": 0.03382531553506851,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3406944274902344,
      "step": 11400
    },
    {
      "epoch": 0.542952380952381,
      "grad_norm": 0.030125193297863007,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3276166915893555,
      "step": 11402
    },
    {
      "epoch": 0.543047619047619,
      "grad_norm": 0.02921150252223015,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3157100677490234,
      "step": 11404
    },
    {
      "epoch": 0.5431428571428571,
      "grad_norm": 0.02838355116546154,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355225086212158,
      "step": 11406
    },
    {
      "epoch": 0.5432380952380952,
      "grad_norm": 0.026412522420287132,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2637782096862793,
      "step": 11408
    },
    {
      "epoch": 0.5433333333333333,
      "grad_norm": 0.02890828251838684,
      "learning_rate": 0.024000000208616257,
      "loss": 2.310126304626465,
      "step": 11410
    },
    {
      "epoch": 0.5434285714285715,
      "grad_norm": 0.027001991868019104,
      "learning_rate": 0.024000000208616257,
      "loss": 2.34928822517395,
      "step": 11412
    },
    {
      "epoch": 0.5435238095238095,
      "grad_norm": 0.02838956192135811,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3389601707458496,
      "step": 11414
    },
    {
      "epoch": 0.5436190476190477,
      "grad_norm": 0.028525574132800102,
      "learning_rate": 0.024000000208616257,
      "loss": 2.298464775085449,
      "step": 11416
    },
    {
      "epoch": 0.5437142857142857,
      "grad_norm": 0.029226722195744514,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3607170581817627,
      "step": 11418
    },
    {
      "epoch": 0.5438095238095239,
      "grad_norm": 0.02888612449169159,
      "learning_rate": 0.024000000208616257,
      "loss": 2.341249465942383,
      "step": 11420
    },
    {
      "epoch": 0.5439047619047619,
      "grad_norm": 0.028292596340179443,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3353967666625977,
      "step": 11422
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.02623925171792507,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2992746829986572,
      "step": 11424
    },
    {
      "epoch": 0.5440952380952381,
      "grad_norm": 0.02578444965183735,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2933833599090576,
      "step": 11426
    },
    {
      "epoch": 0.5441904761904762,
      "grad_norm": 0.02662685140967369,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3377604484558105,
      "step": 11428
    },
    {
      "epoch": 0.5442857142857143,
      "grad_norm": 0.026670515537261963,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3214359283447266,
      "step": 11430
    },
    {
      "epoch": 0.5443809523809524,
      "grad_norm": 0.02957085892558098,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3313357830047607,
      "step": 11432
    },
    {
      "epoch": 0.5444761904761904,
      "grad_norm": 0.028309449553489685,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338141918182373,
      "step": 11434
    },
    {
      "epoch": 0.5445714285714286,
      "grad_norm": 0.02861526422202587,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3354530334472656,
      "step": 11436
    },
    {
      "epoch": 0.5446666666666666,
      "grad_norm": 0.026940099895000458,
      "learning_rate": 0.024000000208616257,
      "loss": 2.360922336578369,
      "step": 11438
    },
    {
      "epoch": 0.5447619047619048,
      "grad_norm": 0.02660289965569973,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3238401412963867,
      "step": 11440
    },
    {
      "epoch": 0.5448571428571428,
      "grad_norm": 0.0282294899225235,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3038415908813477,
      "step": 11442
    },
    {
      "epoch": 0.544952380952381,
      "grad_norm": 0.026802964508533478,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3280913829803467,
      "step": 11444
    },
    {
      "epoch": 0.545047619047619,
      "grad_norm": 0.02935916930437088,
      "learning_rate": 0.024000000208616257,
      "loss": 2.340754508972168,
      "step": 11446
    },
    {
      "epoch": 0.5451428571428572,
      "grad_norm": 0.027455341070890427,
      "learning_rate": 0.024000000208616257,
      "loss": 2.335204601287842,
      "step": 11448
    },
    {
      "epoch": 0.5452380952380952,
      "grad_norm": 0.02842528373003006,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3018689155578613,
      "step": 11450
    },
    {
      "epoch": 0.5453333333333333,
      "grad_norm": 0.027580365538597107,
      "learning_rate": 0.024000000208616257,
      "loss": 2.326573371887207,
      "step": 11452
    },
    {
      "epoch": 0.5454285714285714,
      "grad_norm": 0.03127443045377731,
      "learning_rate": 0.024000000208616257,
      "loss": 2.351747989654541,
      "step": 11454
    },
    {
      "epoch": 0.5455238095238095,
      "grad_norm": 0.03176545724272728,
      "learning_rate": 0.024000000208616257,
      "loss": 2.337864637374878,
      "step": 11456
    },
    {
      "epoch": 0.5456190476190477,
      "grad_norm": 0.03121347166597843,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3298590183258057,
      "step": 11458
    },
    {
      "epoch": 0.5457142857142857,
      "grad_norm": 0.029158752411603928,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3382937908172607,
      "step": 11460
    },
    {
      "epoch": 0.5458095238095239,
      "grad_norm": 0.027094358578324318,
      "learning_rate": 0.024000000208616257,
      "loss": 2.307648181915283,
      "step": 11462
    },
    {
      "epoch": 0.5459047619047619,
      "grad_norm": 0.02719585970044136,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3512940406799316,
      "step": 11464
    },
    {
      "epoch": 0.546,
      "grad_norm": 0.02779252454638481,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350095748901367,
      "step": 11466
    },
    {
      "epoch": 0.5460952380952381,
      "grad_norm": 0.026557421311736107,
      "learning_rate": 0.024000000208616257,
      "loss": 2.328439235687256,
      "step": 11468
    },
    {
      "epoch": 0.5461904761904762,
      "grad_norm": 0.027461452409625053,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3291854858398438,
      "step": 11470
    },
    {
      "epoch": 0.5462857142857143,
      "grad_norm": 0.02789386734366417,
      "learning_rate": 0.024000000208616257,
      "loss": 2.325148105621338,
      "step": 11472
    },
    {
      "epoch": 0.5463809523809524,
      "grad_norm": 0.026754075661301613,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3358876705169678,
      "step": 11474
    },
    {
      "epoch": 0.5464761904761904,
      "grad_norm": 0.02665163017809391,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3180582523345947,
      "step": 11476
    },
    {
      "epoch": 0.5465714285714286,
      "grad_norm": 0.02642993815243244,
      "learning_rate": 0.024000000208616257,
      "loss": 2.321228504180908,
      "step": 11478
    },
    {
      "epoch": 0.5466666666666666,
      "grad_norm": 0.0265633687376976,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3382656574249268,
      "step": 11480
    },
    {
      "epoch": 0.5467619047619048,
      "grad_norm": 0.02903806045651436,
      "learning_rate": 0.024000000208616257,
      "loss": 2.344818592071533,
      "step": 11482
    },
    {
      "epoch": 0.5468571428571428,
      "grad_norm": 0.028489191085100174,
      "learning_rate": 0.024000000208616257,
      "loss": 2.339078426361084,
      "step": 11484
    },
    {
      "epoch": 0.546952380952381,
      "grad_norm": 0.02753620222210884,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3757481575012207,
      "step": 11486
    },
    {
      "epoch": 0.547047619047619,
      "grad_norm": 0.027713865041732788,
      "learning_rate": 0.024000000208616257,
      "loss": 2.336677312850952,
      "step": 11488
    },
    {
      "epoch": 0.5471428571428572,
      "grad_norm": 0.025728750973939896,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3227033615112305,
      "step": 11490
    },
    {
      "epoch": 0.5472380952380952,
      "grad_norm": 0.033267516642808914,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345290422439575,
      "step": 11492
    },
    {
      "epoch": 0.5473333333333333,
      "grad_norm": 0.02624606341123581,
      "learning_rate": 0.024000000208616257,
      "loss": 2.342960834503174,
      "step": 11494
    },
    {
      "epoch": 0.5474285714285714,
      "grad_norm": 0.027091940864920616,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350767135620117,
      "step": 11496
    },
    {
      "epoch": 0.5475238095238095,
      "grad_norm": 0.028821831569075584,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3253750801086426,
      "step": 11498
    },
    {
      "epoch": 0.5476190476190477,
      "grad_norm": 0.028333749622106552,
      "learning_rate": 0.024000000208616257,
      "loss": 2.352839469909668,
      "step": 11500
    },
    {
      "epoch": 0.5477142857142857,
      "grad_norm": 0.027134481817483902,
      "learning_rate": 0.024000000208616257,
      "loss": 2.341758966445923,
      "step": 11502
    },
    {
      "epoch": 0.5478095238095239,
      "grad_norm": 0.02842690981924534,
      "learning_rate": 0.024000000208616257,
      "loss": 2.320737361907959,
      "step": 11504
    },
    {
      "epoch": 0.5479047619047619,
      "grad_norm": 0.026952853426337242,
      "learning_rate": 0.024000000208616257,
      "loss": 2.336824417114258,
      "step": 11506
    },
    {
      "epoch": 0.548,
      "grad_norm": 0.02725117839872837,
      "learning_rate": 0.024000000208616257,
      "loss": 2.317333936691284,
      "step": 11508
    },
    {
      "epoch": 0.5480952380952381,
      "grad_norm": 0.028060687705874443,
      "learning_rate": 0.024000000208616257,
      "loss": 2.341157913208008,
      "step": 11510
    },
    {
      "epoch": 0.5481904761904762,
      "grad_norm": 0.026077980175614357,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3464975357055664,
      "step": 11512
    },
    {
      "epoch": 0.5482857142857143,
      "grad_norm": 0.026468636468052864,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3564586639404297,
      "step": 11514
    },
    {
      "epoch": 0.5483809523809524,
      "grad_norm": 0.02702043019235134,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3315463066101074,
      "step": 11516
    },
    {
      "epoch": 0.5484761904761905,
      "grad_norm": 0.02828012965619564,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3468642234802246,
      "step": 11518
    },
    {
      "epoch": 0.5485714285714286,
      "grad_norm": 0.027702011168003082,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3332180976867676,
      "step": 11520
    },
    {
      "epoch": 0.5486666666666666,
      "grad_norm": 0.02634279802441597,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3043928146362305,
      "step": 11522
    },
    {
      "epoch": 0.5487619047619048,
      "grad_norm": 0.02636764571070671,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3362245559692383,
      "step": 11524
    },
    {
      "epoch": 0.5488571428571428,
      "grad_norm": 0.02783423475921154,
      "learning_rate": 0.024000000208616257,
      "loss": 2.342878818511963,
      "step": 11526
    },
    {
      "epoch": 0.548952380952381,
      "grad_norm": 0.027032919228076935,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3478546142578125,
      "step": 11528
    },
    {
      "epoch": 0.549047619047619,
      "grad_norm": 0.02703034318983555,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3160433769226074,
      "step": 11530
    },
    {
      "epoch": 0.5491428571428572,
      "grad_norm": 0.02775966003537178,
      "learning_rate": 0.024000000208616257,
      "loss": 2.346668243408203,
      "step": 11532
    },
    {
      "epoch": 0.5492380952380952,
      "grad_norm": 0.026943642646074295,
      "learning_rate": 0.024000000208616257,
      "loss": 2.333831787109375,
      "step": 11534
    },
    {
      "epoch": 0.5493333333333333,
      "grad_norm": 0.02711714617908001,
      "learning_rate": 0.024000000208616257,
      "loss": 2.357212543487549,
      "step": 11536
    },
    {
      "epoch": 0.5494285714285714,
      "grad_norm": 0.02846549078822136,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3608086109161377,
      "step": 11538
    },
    {
      "epoch": 0.5495238095238095,
      "grad_norm": 0.02907215990126133,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3233518600463867,
      "step": 11540
    },
    {
      "epoch": 0.5496190476190477,
      "grad_norm": 0.030146010220050812,
      "learning_rate": 0.024000000208616257,
      "loss": 2.368389129638672,
      "step": 11542
    },
    {
      "epoch": 0.5497142857142857,
      "grad_norm": 0.027005961164832115,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3474745750427246,
      "step": 11544
    },
    {
      "epoch": 0.5498095238095239,
      "grad_norm": 0.027069371193647385,
      "learning_rate": 0.024000000208616257,
      "loss": 2.330440044403076,
      "step": 11546
    },
    {
      "epoch": 0.5499047619047619,
      "grad_norm": 0.02675453945994377,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3367724418640137,
      "step": 11548
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.027197476476430893,
      "learning_rate": 0.024000000208616257,
      "loss": 2.362034320831299,
      "step": 11550
    },
    {
      "epoch": 0.5500952380952381,
      "grad_norm": 0.026587283238768578,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3671979904174805,
      "step": 11552
    },
    {
      "epoch": 0.5501904761904762,
      "grad_norm": 0.028690287843346596,
      "learning_rate": 0.024000000208616257,
      "loss": 2.358546018600464,
      "step": 11554
    },
    {
      "epoch": 0.5502857142857143,
      "grad_norm": 0.02589850127696991,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345900535583496,
      "step": 11556
    },
    {
      "epoch": 0.5503809523809524,
      "grad_norm": 0.02757401205599308,
      "learning_rate": 0.024000000208616257,
      "loss": 2.33786678314209,
      "step": 11558
    },
    {
      "epoch": 0.5504761904761905,
      "grad_norm": 0.028887109830975533,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3855342864990234,
      "step": 11560
    },
    {
      "epoch": 0.5505714285714286,
      "grad_norm": 0.03011605143547058,
      "learning_rate": 0.024000000208616257,
      "loss": 2.361937999725342,
      "step": 11562
    },
    {
      "epoch": 0.5506666666666666,
      "grad_norm": 0.028911270201206207,
      "learning_rate": 0.024000000208616257,
      "loss": 2.346250534057617,
      "step": 11564
    },
    {
      "epoch": 0.5507619047619048,
      "grad_norm": 0.02961224690079689,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3415703773498535,
      "step": 11566
    },
    {
      "epoch": 0.5508571428571428,
      "grad_norm": 0.027090098708868027,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3599281311035156,
      "step": 11568
    },
    {
      "epoch": 0.550952380952381,
      "grad_norm": 0.027486391365528107,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3865761756896973,
      "step": 11570
    },
    {
      "epoch": 0.551047619047619,
      "grad_norm": 0.028731338679790497,
      "learning_rate": 0.024000000208616257,
      "loss": 2.34623122215271,
      "step": 11572
    },
    {
      "epoch": 0.5511428571428572,
      "grad_norm": 0.02670573629438877,
      "learning_rate": 0.024000000208616257,
      "loss": 2.352410316467285,
      "step": 11574
    },
    {
      "epoch": 0.5512380952380952,
      "grad_norm": 0.027536876499652863,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3282277584075928,
      "step": 11576
    },
    {
      "epoch": 0.5513333333333333,
      "grad_norm": 0.026344764977693558,
      "learning_rate": 0.024000000208616257,
      "loss": 2.354245662689209,
      "step": 11578
    },
    {
      "epoch": 0.5514285714285714,
      "grad_norm": 0.026564935222268105,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3455891609191895,
      "step": 11580
    },
    {
      "epoch": 0.5515238095238095,
      "grad_norm": 0.02683205157518387,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3703951835632324,
      "step": 11582
    },
    {
      "epoch": 0.5516190476190476,
      "grad_norm": 0.028238506987690926,
      "learning_rate": 0.024000000208616257,
      "loss": 2.375764846801758,
      "step": 11584
    },
    {
      "epoch": 0.5517142857142857,
      "grad_norm": 0.03095724619925022,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3551523685455322,
      "step": 11586
    },
    {
      "epoch": 0.5518095238095239,
      "grad_norm": 0.028508123010396957,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3548922538757324,
      "step": 11588
    },
    {
      "epoch": 0.5519047619047619,
      "grad_norm": 0.02888420596718788,
      "learning_rate": 0.024000000208616257,
      "loss": 2.323737859725952,
      "step": 11590
    },
    {
      "epoch": 0.552,
      "grad_norm": 0.02904219552874565,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3881301879882812,
      "step": 11592
    },
    {
      "epoch": 0.5520952380952381,
      "grad_norm": 0.02667057327926159,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3683009147644043,
      "step": 11594
    },
    {
      "epoch": 0.5521904761904762,
      "grad_norm": 0.027354205027222633,
      "learning_rate": 0.024000000208616257,
      "loss": 2.331357955932617,
      "step": 11596
    },
    {
      "epoch": 0.5522857142857143,
      "grad_norm": 0.027552412822842598,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3733839988708496,
      "step": 11598
    },
    {
      "epoch": 0.5523809523809524,
      "grad_norm": 0.02816098742187023,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3592400550842285,
      "step": 11600
    },
    {
      "epoch": 0.5524761904761905,
      "grad_norm": 0.026311248540878296,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3923707008361816,
      "step": 11602
    },
    {
      "epoch": 0.5525714285714286,
      "grad_norm": 0.027601316571235657,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3495290279388428,
      "step": 11604
    },
    {
      "epoch": 0.5526666666666666,
      "grad_norm": 0.03042791038751602,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3523764610290527,
      "step": 11606
    },
    {
      "epoch": 0.5527619047619048,
      "grad_norm": 0.02999754808843136,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3537206649780273,
      "step": 11608
    },
    {
      "epoch": 0.5528571428571428,
      "grad_norm": 0.02760937809944153,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3785505294799805,
      "step": 11610
    },
    {
      "epoch": 0.552952380952381,
      "grad_norm": 0.03170493245124817,
      "learning_rate": 0.024000000208616257,
      "loss": 2.336913585662842,
      "step": 11612
    },
    {
      "epoch": 0.553047619047619,
      "grad_norm": 0.03565357252955437,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3830833435058594,
      "step": 11614
    },
    {
      "epoch": 0.5531428571428572,
      "grad_norm": 0.032544393092393875,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3509232997894287,
      "step": 11616
    },
    {
      "epoch": 0.5532380952380952,
      "grad_norm": 0.03005436435341835,
      "learning_rate": 0.024000000208616257,
      "loss": 2.382276773452759,
      "step": 11618
    },
    {
      "epoch": 0.5533333333333333,
      "grad_norm": 0.028050849214196205,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3539581298828125,
      "step": 11620
    },
    {
      "epoch": 0.5534285714285714,
      "grad_norm": 0.031884316354990005,
      "learning_rate": 0.024000000208616257,
      "loss": 2.374504566192627,
      "step": 11622
    },
    {
      "epoch": 0.5535238095238095,
      "grad_norm": 0.030841164290905,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3495638370513916,
      "step": 11624
    },
    {
      "epoch": 0.5536190476190476,
      "grad_norm": 0.0320441871881485,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3633079528808594,
      "step": 11626
    },
    {
      "epoch": 0.5537142857142857,
      "grad_norm": 0.03710407018661499,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338901996612549,
      "step": 11628
    },
    {
      "epoch": 0.5538095238095239,
      "grad_norm": 0.03634733706712723,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3781137466430664,
      "step": 11630
    },
    {
      "epoch": 0.5539047619047619,
      "grad_norm": 0.029237018898129463,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350100517272949,
      "step": 11632
    },
    {
      "epoch": 0.554,
      "grad_norm": 0.028966136276721954,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3843624591827393,
      "step": 11634
    },
    {
      "epoch": 0.5540952380952381,
      "grad_norm": 0.028479572385549545,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3687233924865723,
      "step": 11636
    },
    {
      "epoch": 0.5541904761904762,
      "grad_norm": 0.027554329484701157,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3665213584899902,
      "step": 11638
    },
    {
      "epoch": 0.5542857142857143,
      "grad_norm": 0.02754330262541771,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4134750366210938,
      "step": 11640
    },
    {
      "epoch": 0.5543809523809524,
      "grad_norm": 0.026990201324224472,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3701086044311523,
      "step": 11642
    },
    {
      "epoch": 0.5544761904761905,
      "grad_norm": 0.0267369095236063,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3446578979492188,
      "step": 11644
    },
    {
      "epoch": 0.5545714285714286,
      "grad_norm": 0.02691490203142166,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3850257396698,
      "step": 11646
    },
    {
      "epoch": 0.5546666666666666,
      "grad_norm": 0.029200926423072815,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3730545043945312,
      "step": 11648
    },
    {
      "epoch": 0.5547619047619048,
      "grad_norm": 0.028163690119981766,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3617539405822754,
      "step": 11650
    },
    {
      "epoch": 0.5548571428571428,
      "grad_norm": 0.02898457646369934,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3833556175231934,
      "step": 11652
    },
    {
      "epoch": 0.554952380952381,
      "grad_norm": 0.03168214112520218,
      "learning_rate": 0.024000000208616257,
      "loss": 2.365738868713379,
      "step": 11654
    },
    {
      "epoch": 0.555047619047619,
      "grad_norm": 0.02692132443189621,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3955206871032715,
      "step": 11656
    },
    {
      "epoch": 0.5551428571428572,
      "grad_norm": 0.028724946081638336,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3970301151275635,
      "step": 11658
    },
    {
      "epoch": 0.5552380952380952,
      "grad_norm": 0.027694096788764,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3709113597869873,
      "step": 11660
    },
    {
      "epoch": 0.5553333333333333,
      "grad_norm": 0.025902649387717247,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3446760177612305,
      "step": 11662
    },
    {
      "epoch": 0.5554285714285714,
      "grad_norm": 0.028222251683473587,
      "learning_rate": 0.024000000208616257,
      "loss": 2.387937068939209,
      "step": 11664
    },
    {
      "epoch": 0.5555238095238095,
      "grad_norm": 0.02727648615837097,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3992462158203125,
      "step": 11666
    },
    {
      "epoch": 0.5556190476190476,
      "grad_norm": 0.02796284109354019,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383162498474121,
      "step": 11668
    },
    {
      "epoch": 0.5557142857142857,
      "grad_norm": 0.03134676441550255,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3964271545410156,
      "step": 11670
    },
    {
      "epoch": 0.5558095238095239,
      "grad_norm": 0.026685362681746483,
      "learning_rate": 0.024000000208616257,
      "loss": 2.370635509490967,
      "step": 11672
    },
    {
      "epoch": 0.5559047619047619,
      "grad_norm": 0.02817283384501934,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3659565448760986,
      "step": 11674
    },
    {
      "epoch": 0.556,
      "grad_norm": 0.026936767622828484,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4207801818847656,
      "step": 11676
    },
    {
      "epoch": 0.5560952380952381,
      "grad_norm": 0.0289921797811985,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3779191970825195,
      "step": 11678
    },
    {
      "epoch": 0.5561904761904762,
      "grad_norm": 0.0290316641330719,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363281726837158,
      "step": 11680
    },
    {
      "epoch": 0.5562857142857143,
      "grad_norm": 0.026474326848983765,
      "learning_rate": 0.024000000208616257,
      "loss": 2.368346929550171,
      "step": 11682
    },
    {
      "epoch": 0.5563809523809524,
      "grad_norm": 0.02933529019355774,
      "learning_rate": 0.024000000208616257,
      "loss": 2.340019702911377,
      "step": 11684
    },
    {
      "epoch": 0.5564761904761905,
      "grad_norm": 0.028024088591337204,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3529739379882812,
      "step": 11686
    },
    {
      "epoch": 0.5565714285714286,
      "grad_norm": 0.03148061782121658,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401454448699951,
      "step": 11688
    },
    {
      "epoch": 0.5566666666666666,
      "grad_norm": 0.02666826732456684,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3552165031433105,
      "step": 11690
    },
    {
      "epoch": 0.5567619047619048,
      "grad_norm": 0.027638984844088554,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3734161853790283,
      "step": 11692
    },
    {
      "epoch": 0.5568571428571428,
      "grad_norm": 0.028412075713276863,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3997890949249268,
      "step": 11694
    },
    {
      "epoch": 0.556952380952381,
      "grad_norm": 0.03170473128557205,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356121063232422,
      "step": 11696
    },
    {
      "epoch": 0.557047619047619,
      "grad_norm": 0.027247890830039978,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3821167945861816,
      "step": 11698
    },
    {
      "epoch": 0.5571428571428572,
      "grad_norm": 0.02652345411479473,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3924365043640137,
      "step": 11700
    },
    {
      "epoch": 0.5572380952380952,
      "grad_norm": 0.02756977267563343,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4149527549743652,
      "step": 11702
    },
    {
      "epoch": 0.5573333333333333,
      "grad_norm": 0.02998759038746357,
      "learning_rate": 0.024000000208616257,
      "loss": 2.404186248779297,
      "step": 11704
    },
    {
      "epoch": 0.5574285714285714,
      "grad_norm": 0.028125621378421783,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3857054710388184,
      "step": 11706
    },
    {
      "epoch": 0.5575238095238095,
      "grad_norm": 0.027212129905819893,
      "learning_rate": 0.024000000208616257,
      "loss": 2.40315580368042,
      "step": 11708
    },
    {
      "epoch": 0.5576190476190476,
      "grad_norm": 0.02735554613173008,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3963379859924316,
      "step": 11710
    },
    {
      "epoch": 0.5577142857142857,
      "grad_norm": 0.0264605563133955,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3812031745910645,
      "step": 11712
    },
    {
      "epoch": 0.5578095238095238,
      "grad_norm": 0.027901597321033478,
      "learning_rate": 0.024000000208616257,
      "loss": 2.371077060699463,
      "step": 11714
    },
    {
      "epoch": 0.5579047619047619,
      "grad_norm": 0.027435969561338425,
      "learning_rate": 0.024000000208616257,
      "loss": 2.387395143508911,
      "step": 11716
    },
    {
      "epoch": 0.558,
      "grad_norm": 0.027148224413394928,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3772969245910645,
      "step": 11718
    },
    {
      "epoch": 0.5580952380952381,
      "grad_norm": 0.029859330505132675,
      "learning_rate": 0.024000000208616257,
      "loss": 2.365114688873291,
      "step": 11720
    },
    {
      "epoch": 0.5581904761904762,
      "grad_norm": 0.03209460526704788,
      "learning_rate": 0.024000000208616257,
      "loss": 2.395850896835327,
      "step": 11722
    },
    {
      "epoch": 0.5582857142857143,
      "grad_norm": 0.027224106714129448,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3623251914978027,
      "step": 11724
    },
    {
      "epoch": 0.5583809523809524,
      "grad_norm": 0.027106348425149918,
      "learning_rate": 0.024000000208616257,
      "loss": 2.373490333557129,
      "step": 11726
    },
    {
      "epoch": 0.5584761904761905,
      "grad_norm": 0.027433348819613457,
      "learning_rate": 0.024000000208616257,
      "loss": 2.434675693511963,
      "step": 11728
    },
    {
      "epoch": 0.5585714285714286,
      "grad_norm": 0.029519250616431236,
      "learning_rate": 0.024000000208616257,
      "loss": 2.369201898574829,
      "step": 11730
    },
    {
      "epoch": 0.5586666666666666,
      "grad_norm": 0.02793247438967228,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3748526573181152,
      "step": 11732
    },
    {
      "epoch": 0.5587619047619048,
      "grad_norm": 0.028797732666134834,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4151458740234375,
      "step": 11734
    },
    {
      "epoch": 0.5588571428571428,
      "grad_norm": 0.03396514430642128,
      "learning_rate": 0.024000000208616257,
      "loss": 2.386821746826172,
      "step": 11736
    },
    {
      "epoch": 0.558952380952381,
      "grad_norm": 0.02662402018904686,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3923869132995605,
      "step": 11738
    },
    {
      "epoch": 0.559047619047619,
      "grad_norm": 0.02719794772565365,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3945720195770264,
      "step": 11740
    },
    {
      "epoch": 0.5591428571428572,
      "grad_norm": 0.02929822914302349,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3931643962860107,
      "step": 11742
    },
    {
      "epoch": 0.5592380952380952,
      "grad_norm": 0.02764900214970112,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3858532905578613,
      "step": 11744
    },
    {
      "epoch": 0.5593333333333333,
      "grad_norm": 0.027928147464990616,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3655853271484375,
      "step": 11746
    },
    {
      "epoch": 0.5594285714285714,
      "grad_norm": 0.028253493830561638,
      "learning_rate": 0.024000000208616257,
      "loss": 2.359161853790283,
      "step": 11748
    },
    {
      "epoch": 0.5595238095238095,
      "grad_norm": 0.02696853317320347,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3587756156921387,
      "step": 11750
    },
    {
      "epoch": 0.5596190476190476,
      "grad_norm": 0.02765403874218464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3769583702087402,
      "step": 11752
    },
    {
      "epoch": 0.5597142857142857,
      "grad_norm": 0.030442198738455772,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3707683086395264,
      "step": 11754
    },
    {
      "epoch": 0.5598095238095238,
      "grad_norm": 0.03303159028291702,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3896474838256836,
      "step": 11756
    },
    {
      "epoch": 0.5599047619047619,
      "grad_norm": 0.03317727893590927,
      "learning_rate": 0.024000000208616257,
      "loss": 2.368150472640991,
      "step": 11758
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.03270053490996361,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4153366088867188,
      "step": 11760
    },
    {
      "epoch": 0.5600952380952381,
      "grad_norm": 0.027580972760915756,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38938045501709,
      "step": 11762
    },
    {
      "epoch": 0.5601904761904762,
      "grad_norm": 0.031025800853967667,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3984925746917725,
      "step": 11764
    },
    {
      "epoch": 0.5602857142857143,
      "grad_norm": 0.03170143812894821,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4043025970458984,
      "step": 11766
    },
    {
      "epoch": 0.5603809523809524,
      "grad_norm": 0.02960234507918358,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3729753494262695,
      "step": 11768
    },
    {
      "epoch": 0.5604761904761905,
      "grad_norm": 0.027697782963514328,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3756728172302246,
      "step": 11770
    },
    {
      "epoch": 0.5605714285714286,
      "grad_norm": 0.027014564722776413,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383561611175537,
      "step": 11772
    },
    {
      "epoch": 0.5606666666666666,
      "grad_norm": 0.026594802737236023,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3946781158447266,
      "step": 11774
    },
    {
      "epoch": 0.5607619047619048,
      "grad_norm": 0.026822369545698166,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4072062969207764,
      "step": 11776
    },
    {
      "epoch": 0.5608571428571428,
      "grad_norm": 0.02653142809867859,
      "learning_rate": 0.024000000208616257,
      "loss": 2.361722707748413,
      "step": 11778
    },
    {
      "epoch": 0.560952380952381,
      "grad_norm": 0.02665015496313572,
      "learning_rate": 0.024000000208616257,
      "loss": 2.426913261413574,
      "step": 11780
    },
    {
      "epoch": 0.561047619047619,
      "grad_norm": 0.027637140825390816,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4032371044158936,
      "step": 11782
    },
    {
      "epoch": 0.5611428571428572,
      "grad_norm": 0.028320258483290672,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3576879501342773,
      "step": 11784
    },
    {
      "epoch": 0.5612380952380952,
      "grad_norm": 0.02741563878953457,
      "learning_rate": 0.024000000208616257,
      "loss": 2.40246844291687,
      "step": 11786
    },
    {
      "epoch": 0.5613333333333334,
      "grad_norm": 0.026127135381102562,
      "learning_rate": 0.024000000208616257,
      "loss": 2.369079113006592,
      "step": 11788
    },
    {
      "epoch": 0.5614285714285714,
      "grad_norm": 0.027854405343532562,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3997554779052734,
      "step": 11790
    },
    {
      "epoch": 0.5615238095238095,
      "grad_norm": 0.026747651398181915,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3670902252197266,
      "step": 11792
    },
    {
      "epoch": 0.5616190476190476,
      "grad_norm": 0.02615051530301571,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3848843574523926,
      "step": 11794
    },
    {
      "epoch": 0.5617142857142857,
      "grad_norm": 0.027781156823039055,
      "learning_rate": 0.024000000208616257,
      "loss": 2.414494752883911,
      "step": 11796
    },
    {
      "epoch": 0.5618095238095238,
      "grad_norm": 0.02637512981891632,
      "learning_rate": 0.024000000208616257,
      "loss": 2.41799259185791,
      "step": 11798
    },
    {
      "epoch": 0.5619047619047619,
      "grad_norm": 0.029127303510904312,
      "learning_rate": 0.024000000208616257,
      "loss": 2.394076347351074,
      "step": 11800
    },
    {
      "epoch": 0.562,
      "grad_norm": 0.028838852420449257,
      "learning_rate": 0.024000000208616257,
      "loss": 2.421950340270996,
      "step": 11802
    },
    {
      "epoch": 0.5620952380952381,
      "grad_norm": 0.033338211476802826,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4004435539245605,
      "step": 11804
    },
    {
      "epoch": 0.5621904761904762,
      "grad_norm": 0.028502605855464935,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4278056621551514,
      "step": 11806
    },
    {
      "epoch": 0.5622857142857143,
      "grad_norm": 0.02709316462278366,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3776535987854004,
      "step": 11808
    },
    {
      "epoch": 0.5623809523809524,
      "grad_norm": 0.028490852564573288,
      "learning_rate": 0.024000000208616257,
      "loss": 2.366140842437744,
      "step": 11810
    },
    {
      "epoch": 0.5624761904761905,
      "grad_norm": 0.02827576920390129,
      "learning_rate": 0.024000000208616257,
      "loss": 2.410656452178955,
      "step": 11812
    },
    {
      "epoch": 0.5625714285714286,
      "grad_norm": 0.028827479109168053,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398906946182251,
      "step": 11814
    },
    {
      "epoch": 0.5626666666666666,
      "grad_norm": 0.02899826504290104,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4030466079711914,
      "step": 11816
    },
    {
      "epoch": 0.5627619047619048,
      "grad_norm": 0.028786828741431236,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3595104217529297,
      "step": 11818
    },
    {
      "epoch": 0.5628571428571428,
      "grad_norm": 0.027258917689323425,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3988544940948486,
      "step": 11820
    },
    {
      "epoch": 0.562952380952381,
      "grad_norm": 0.02712741680443287,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356430768966675,
      "step": 11822
    },
    {
      "epoch": 0.563047619047619,
      "grad_norm": 0.032179877161979675,
      "learning_rate": 0.024000000208616257,
      "loss": 2.410379409790039,
      "step": 11824
    },
    {
      "epoch": 0.5631428571428572,
      "grad_norm": 0.0374365895986557,
      "learning_rate": 0.024000000208616257,
      "loss": 2.392821788787842,
      "step": 11826
    },
    {
      "epoch": 0.5632380952380952,
      "grad_norm": 0.03261224180459976,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3795828819274902,
      "step": 11828
    },
    {
      "epoch": 0.5633333333333334,
      "grad_norm": 0.027875836938619614,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3890552520751953,
      "step": 11830
    },
    {
      "epoch": 0.5634285714285714,
      "grad_norm": 0.02720075659453869,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3892011642456055,
      "step": 11832
    },
    {
      "epoch": 0.5635238095238095,
      "grad_norm": 0.026403630152344704,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4058310985565186,
      "step": 11834
    },
    {
      "epoch": 0.5636190476190476,
      "grad_norm": 0.028198963031172752,
      "learning_rate": 0.024000000208616257,
      "loss": 2.381135940551758,
      "step": 11836
    },
    {
      "epoch": 0.5637142857142857,
      "grad_norm": 0.026485325768589973,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4167516231536865,
      "step": 11838
    },
    {
      "epoch": 0.5638095238095238,
      "grad_norm": 0.02617916651070118,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4072370529174805,
      "step": 11840
    },
    {
      "epoch": 0.5639047619047619,
      "grad_norm": 0.02686414308845997,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4178428649902344,
      "step": 11842
    },
    {
      "epoch": 0.564,
      "grad_norm": 0.028468754142522812,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4135141372680664,
      "step": 11844
    },
    {
      "epoch": 0.5640952380952381,
      "grad_norm": 0.027934648096561432,
      "learning_rate": 0.024000000208616257,
      "loss": 2.396803855895996,
      "step": 11846
    },
    {
      "epoch": 0.5641904761904762,
      "grad_norm": 0.027997862547636032,
      "learning_rate": 0.024000000208616257,
      "loss": 2.370863914489746,
      "step": 11848
    },
    {
      "epoch": 0.5642857142857143,
      "grad_norm": 0.027191510424017906,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4401326179504395,
      "step": 11850
    },
    {
      "epoch": 0.5643809523809524,
      "grad_norm": 0.028223494067788124,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385915756225586,
      "step": 11852
    },
    {
      "epoch": 0.5644761904761905,
      "grad_norm": 0.028993984684348106,
      "learning_rate": 0.024000000208616257,
      "loss": 2.410801887512207,
      "step": 11854
    },
    {
      "epoch": 0.5645714285714286,
      "grad_norm": 0.030110890045762062,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4010443687438965,
      "step": 11856
    },
    {
      "epoch": 0.5646666666666667,
      "grad_norm": 0.03209001198410988,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3422765731811523,
      "step": 11858
    },
    {
      "epoch": 0.5647619047619048,
      "grad_norm": 0.02704070881009102,
      "learning_rate": 0.024000000208616257,
      "loss": 2.386552333831787,
      "step": 11860
    },
    {
      "epoch": 0.5648571428571428,
      "grad_norm": 0.02788064442574978,
      "learning_rate": 0.024000000208616257,
      "loss": 2.412464141845703,
      "step": 11862
    },
    {
      "epoch": 0.564952380952381,
      "grad_norm": 0.033810414373874664,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4252872467041016,
      "step": 11864
    },
    {
      "epoch": 0.565047619047619,
      "grad_norm": 0.03061581216752529,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3955793380737305,
      "step": 11866
    },
    {
      "epoch": 0.5651428571428572,
      "grad_norm": 0.028137125074863434,
      "learning_rate": 0.024000000208616257,
      "loss": 2.397726058959961,
      "step": 11868
    },
    {
      "epoch": 0.5652380952380952,
      "grad_norm": 0.02731219306588173,
      "learning_rate": 0.024000000208616257,
      "loss": 2.393878698348999,
      "step": 11870
    },
    {
      "epoch": 0.5653333333333334,
      "grad_norm": 0.02575621008872986,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3558855056762695,
      "step": 11872
    },
    {
      "epoch": 0.5654285714285714,
      "grad_norm": 0.027885738760232925,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3982181549072266,
      "step": 11874
    },
    {
      "epoch": 0.5655238095238095,
      "grad_norm": 0.026431666687130928,
      "learning_rate": 0.024000000208616257,
      "loss": 2.424595832824707,
      "step": 11876
    },
    {
      "epoch": 0.5656190476190476,
      "grad_norm": 0.02623271383345127,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4235148429870605,
      "step": 11878
    },
    {
      "epoch": 0.5657142857142857,
      "grad_norm": 0.02769532985985279,
      "learning_rate": 0.024000000208616257,
      "loss": 2.398388147354126,
      "step": 11880
    },
    {
      "epoch": 0.5658095238095238,
      "grad_norm": 0.02768261730670929,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3793158531188965,
      "step": 11882
    },
    {
      "epoch": 0.5659047619047619,
      "grad_norm": 0.026300588622689247,
      "learning_rate": 0.024000000208616257,
      "loss": 2.411929130554199,
      "step": 11884
    },
    {
      "epoch": 0.566,
      "grad_norm": 0.026283279061317444,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390958309173584,
      "step": 11886
    },
    {
      "epoch": 0.5660952380952381,
      "grad_norm": 0.028361573815345764,
      "learning_rate": 0.024000000208616257,
      "loss": 2.424976348876953,
      "step": 11888
    },
    {
      "epoch": 0.5661904761904762,
      "grad_norm": 0.03472631052136421,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3859362602233887,
      "step": 11890
    },
    {
      "epoch": 0.5662857142857143,
      "grad_norm": 0.026570633053779602,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4072933197021484,
      "step": 11892
    },
    {
      "epoch": 0.5663809523809524,
      "grad_norm": 0.029790276661515236,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4148507118225098,
      "step": 11894
    },
    {
      "epoch": 0.5664761904761905,
      "grad_norm": 0.0275239460170269,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3792552947998047,
      "step": 11896
    },
    {
      "epoch": 0.5665714285714286,
      "grad_norm": 0.029938874766230583,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4075934886932373,
      "step": 11898
    },
    {
      "epoch": 0.5666666666666667,
      "grad_norm": 0.027736926451325417,
      "learning_rate": 0.024000000208616257,
      "loss": 2.401994228363037,
      "step": 11900
    },
    {
      "epoch": 0.5667619047619048,
      "grad_norm": 0.02677297033369541,
      "learning_rate": 0.024000000208616257,
      "loss": 2.407911777496338,
      "step": 11902
    },
    {
      "epoch": 0.5668571428571428,
      "grad_norm": 0.02715601772069931,
      "learning_rate": 0.024000000208616257,
      "loss": 2.445923328399658,
      "step": 11904
    },
    {
      "epoch": 0.566952380952381,
      "grad_norm": 0.027524812147021294,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4026103019714355,
      "step": 11906
    },
    {
      "epoch": 0.567047619047619,
      "grad_norm": 0.026737729087471962,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3795862197875977,
      "step": 11908
    },
    {
      "epoch": 0.5671428571428572,
      "grad_norm": 0.02809365652501583,
      "learning_rate": 0.024000000208616257,
      "loss": 2.39754581451416,
      "step": 11910
    },
    {
      "epoch": 0.5672380952380952,
      "grad_norm": 0.026973308995366096,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4105992317199707,
      "step": 11912
    },
    {
      "epoch": 0.5673333333333334,
      "grad_norm": 0.028450869023799896,
      "learning_rate": 0.024000000208616257,
      "loss": 2.42653489112854,
      "step": 11914
    },
    {
      "epoch": 0.5674285714285714,
      "grad_norm": 0.0281474981456995,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3944928646087646,
      "step": 11916
    },
    {
      "epoch": 0.5675238095238095,
      "grad_norm": 0.028904829174280167,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3827826976776123,
      "step": 11918
    },
    {
      "epoch": 0.5676190476190476,
      "grad_norm": 0.026810213923454285,
      "learning_rate": 0.024000000208616257,
      "loss": 2.393251419067383,
      "step": 11920
    },
    {
      "epoch": 0.5677142857142857,
      "grad_norm": 0.027721336111426353,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380338191986084,
      "step": 11922
    },
    {
      "epoch": 0.5678095238095238,
      "grad_norm": 0.026056909933686256,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3793418407440186,
      "step": 11924
    },
    {
      "epoch": 0.5679047619047619,
      "grad_norm": 0.02689511887729168,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3818044662475586,
      "step": 11926
    },
    {
      "epoch": 0.568,
      "grad_norm": 0.025967076420783997,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383652925491333,
      "step": 11928
    },
    {
      "epoch": 0.5680952380952381,
      "grad_norm": 0.0290982723236084,
      "learning_rate": 0.024000000208616257,
      "loss": 2.377939462661743,
      "step": 11930
    },
    {
      "epoch": 0.5681904761904762,
      "grad_norm": 0.0315236821770668,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3754167556762695,
      "step": 11932
    },
    {
      "epoch": 0.5682857142857143,
      "grad_norm": 0.03377240151166916,
      "learning_rate": 0.024000000208616257,
      "loss": 2.376749038696289,
      "step": 11934
    },
    {
      "epoch": 0.5683809523809524,
      "grad_norm": 0.029450448229908943,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3851659297943115,
      "step": 11936
    },
    {
      "epoch": 0.5684761904761905,
      "grad_norm": 0.027942262589931488,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4040608406066895,
      "step": 11938
    },
    {
      "epoch": 0.5685714285714286,
      "grad_norm": 0.028733406215906143,
      "learning_rate": 0.024000000208616257,
      "loss": 2.37733793258667,
      "step": 11940
    },
    {
      "epoch": 0.5686666666666667,
      "grad_norm": 0.02714967355132103,
      "learning_rate": 0.024000000208616257,
      "loss": 2.389890670776367,
      "step": 11942
    },
    {
      "epoch": 0.5687619047619048,
      "grad_norm": 0.03358941525220871,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3933796882629395,
      "step": 11944
    },
    {
      "epoch": 0.5688571428571428,
      "grad_norm": 0.026132069528102875,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3476994037628174,
      "step": 11946
    },
    {
      "epoch": 0.568952380952381,
      "grad_norm": 0.026798171922564507,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3667874336242676,
      "step": 11948
    },
    {
      "epoch": 0.569047619047619,
      "grad_norm": 0.02614966221153736,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3871657848358154,
      "step": 11950
    },
    {
      "epoch": 0.5691428571428572,
      "grad_norm": 0.025991378352046013,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3951797485351562,
      "step": 11952
    },
    {
      "epoch": 0.5692380952380952,
      "grad_norm": 0.029850678518414497,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363391876220703,
      "step": 11954
    },
    {
      "epoch": 0.5693333333333334,
      "grad_norm": 0.02797987125813961,
      "learning_rate": 0.024000000208616257,
      "loss": 2.368868589401245,
      "step": 11956
    },
    {
      "epoch": 0.5694285714285714,
      "grad_norm": 0.026213806122541428,
      "learning_rate": 0.024000000208616257,
      "loss": 2.378498077392578,
      "step": 11958
    },
    {
      "epoch": 0.5695238095238095,
      "grad_norm": 0.02835642173886299,
      "learning_rate": 0.024000000208616257,
      "loss": 2.357682704925537,
      "step": 11960
    },
    {
      "epoch": 0.5696190476190476,
      "grad_norm": 0.026407821103930473,
      "learning_rate": 0.024000000208616257,
      "loss": 2.383315086364746,
      "step": 11962
    },
    {
      "epoch": 0.5697142857142857,
      "grad_norm": 0.027547726407647133,
      "learning_rate": 0.024000000208616257,
      "loss": 2.373159408569336,
      "step": 11964
    },
    {
      "epoch": 0.5698095238095238,
      "grad_norm": 0.028590090572834015,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3987836837768555,
      "step": 11966
    },
    {
      "epoch": 0.5699047619047619,
      "grad_norm": 0.027351878583431244,
      "learning_rate": 0.024000000208616257,
      "loss": 2.372422695159912,
      "step": 11968
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.027674036100506783,
      "learning_rate": 0.024000000208616257,
      "loss": 2.371316432952881,
      "step": 11970
    },
    {
      "epoch": 0.5700952380952381,
      "grad_norm": 0.027821380645036697,
      "learning_rate": 0.024000000208616257,
      "loss": 2.390519142150879,
      "step": 11972
    },
    {
      "epoch": 0.5701904761904761,
      "grad_norm": 0.032634418457746506,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3969502449035645,
      "step": 11974
    },
    {
      "epoch": 0.5702857142857143,
      "grad_norm": 0.03397964686155319,
      "learning_rate": 0.024000000208616257,
      "loss": 2.388268232345581,
      "step": 11976
    },
    {
      "epoch": 0.5703809523809524,
      "grad_norm": 0.031192194670438766,
      "learning_rate": 0.024000000208616257,
      "loss": 2.361647129058838,
      "step": 11978
    },
    {
      "epoch": 0.5704761904761905,
      "grad_norm": 0.02768099494278431,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3884663581848145,
      "step": 11980
    },
    {
      "epoch": 0.5705714285714286,
      "grad_norm": 0.02773672714829445,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3836612701416016,
      "step": 11982
    },
    {
      "epoch": 0.5706666666666667,
      "grad_norm": 0.02740389108657837,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3707594871520996,
      "step": 11984
    },
    {
      "epoch": 0.5707619047619048,
      "grad_norm": 0.027572067454457283,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3987627029418945,
      "step": 11986
    },
    {
      "epoch": 0.5708571428571428,
      "grad_norm": 0.026267485693097115,
      "learning_rate": 0.024000000208616257,
      "loss": 2.377957344055176,
      "step": 11988
    },
    {
      "epoch": 0.570952380952381,
      "grad_norm": 0.027462778612971306,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4075233936309814,
      "step": 11990
    },
    {
      "epoch": 0.571047619047619,
      "grad_norm": 0.0304377693682909,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3813695907592773,
      "step": 11992
    },
    {
      "epoch": 0.5711428571428572,
      "grad_norm": 0.029131056740880013,
      "learning_rate": 0.024000000208616257,
      "loss": 2.349332332611084,
      "step": 11994
    },
    {
      "epoch": 0.5712380952380952,
      "grad_norm": 0.02791123278439045,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3552846908569336,
      "step": 11996
    },
    {
      "epoch": 0.5713333333333334,
      "grad_norm": 0.026262443512678146,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385002613067627,
      "step": 11998
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.028073741123080254,
      "learning_rate": 0.024000000208616257,
      "loss": 2.362030506134033,
      "step": 12000
    },
    {
      "epoch": 0.5715238095238095,
      "grad_norm": 0.02741781622171402,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345831871032715,
      "step": 12002
    },
    {
      "epoch": 0.5716190476190476,
      "grad_norm": 0.029092220589518547,
      "learning_rate": 0.024000000208616257,
      "loss": 2.364293098449707,
      "step": 12004
    },
    {
      "epoch": 0.5717142857142857,
      "grad_norm": 0.02629227563738823,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3524832725524902,
      "step": 12006
    },
    {
      "epoch": 0.5718095238095238,
      "grad_norm": 0.029001163318753242,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3268256187438965,
      "step": 12008
    },
    {
      "epoch": 0.5719047619047619,
      "grad_norm": 0.029615288600325584,
      "learning_rate": 0.024000000208616257,
      "loss": 2.381591320037842,
      "step": 12010
    },
    {
      "epoch": 0.572,
      "grad_norm": 0.02613680437207222,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3409624099731445,
      "step": 12012
    },
    {
      "epoch": 0.5720952380952381,
      "grad_norm": 0.030383866280317307,
      "learning_rate": 0.024000000208616257,
      "loss": 2.399507999420166,
      "step": 12014
    },
    {
      "epoch": 0.5721904761904761,
      "grad_norm": 0.02806154452264309,
      "learning_rate": 0.024000000208616257,
      "loss": 2.353208541870117,
      "step": 12016
    },
    {
      "epoch": 0.5722857142857143,
      "grad_norm": 0.026065826416015625,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3608264923095703,
      "step": 12018
    },
    {
      "epoch": 0.5723809523809524,
      "grad_norm": 0.025845026597380638,
      "learning_rate": 0.024000000208616257,
      "loss": 2.34208607673645,
      "step": 12020
    },
    {
      "epoch": 0.5724761904761905,
      "grad_norm": 0.02599179372191429,
      "learning_rate": 0.024000000208616257,
      "loss": 2.308591365814209,
      "step": 12022
    },
    {
      "epoch": 0.5725714285714286,
      "grad_norm": 0.027212942019104958,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3471596240997314,
      "step": 12024
    },
    {
      "epoch": 0.5726666666666667,
      "grad_norm": 0.02945045568048954,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3460493087768555,
      "step": 12026
    },
    {
      "epoch": 0.5727619047619048,
      "grad_norm": 0.026909422129392624,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4002628326416016,
      "step": 12028
    },
    {
      "epoch": 0.5728571428571428,
      "grad_norm": 0.0271657332777977,
      "learning_rate": 0.024000000208616257,
      "loss": 2.357485294342041,
      "step": 12030
    },
    {
      "epoch": 0.572952380952381,
      "grad_norm": 0.02977743186056614,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3559727668762207,
      "step": 12032
    },
    {
      "epoch": 0.573047619047619,
      "grad_norm": 0.027855856344103813,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3967549800872803,
      "step": 12034
    },
    {
      "epoch": 0.5731428571428572,
      "grad_norm": 0.02740192599594593,
      "learning_rate": 0.024000000208616257,
      "loss": 2.349224805831909,
      "step": 12036
    },
    {
      "epoch": 0.5732380952380952,
      "grad_norm": 0.02902146242558956,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3588223457336426,
      "step": 12038
    },
    {
      "epoch": 0.5733333333333334,
      "grad_norm": 0.025933291763067245,
      "learning_rate": 0.024000000208616257,
      "loss": 2.364809989929199,
      "step": 12040
    },
    {
      "epoch": 0.5734285714285714,
      "grad_norm": 0.0273410864174366,
      "learning_rate": 0.024000000208616257,
      "loss": 2.362722873687744,
      "step": 12042
    },
    {
      "epoch": 0.5735238095238095,
      "grad_norm": 0.026517538353800774,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3636093139648438,
      "step": 12044
    },
    {
      "epoch": 0.5736190476190476,
      "grad_norm": 0.03135243058204651,
      "learning_rate": 0.024000000208616257,
      "loss": 2.372227191925049,
      "step": 12046
    },
    {
      "epoch": 0.5737142857142857,
      "grad_norm": 0.026931172236800194,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356426239013672,
      "step": 12048
    },
    {
      "epoch": 0.5738095238095238,
      "grad_norm": 0.027868807315826416,
      "learning_rate": 0.024000000208616257,
      "loss": 2.38834285736084,
      "step": 12050
    },
    {
      "epoch": 0.5739047619047619,
      "grad_norm": 0.025815904140472412,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3761842250823975,
      "step": 12052
    },
    {
      "epoch": 0.574,
      "grad_norm": 0.02732386440038681,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3679614067077637,
      "step": 12054
    },
    {
      "epoch": 0.5740952380952381,
      "grad_norm": 0.02802446484565735,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3353614807128906,
      "step": 12056
    },
    {
      "epoch": 0.5741904761904761,
      "grad_norm": 0.030031096190214157,
      "learning_rate": 0.024000000208616257,
      "loss": 2.333435535430908,
      "step": 12058
    },
    {
      "epoch": 0.5742857142857143,
      "grad_norm": 0.029843872413039207,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3155641555786133,
      "step": 12060
    },
    {
      "epoch": 0.5743809523809524,
      "grad_norm": 0.02829231135547161,
      "learning_rate": 0.024000000208616257,
      "loss": 2.329784870147705,
      "step": 12062
    },
    {
      "epoch": 0.5744761904761905,
      "grad_norm": 0.028612583875656128,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3695459365844727,
      "step": 12064
    },
    {
      "epoch": 0.5745714285714286,
      "grad_norm": 0.02696160040795803,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3367419242858887,
      "step": 12066
    },
    {
      "epoch": 0.5746666666666667,
      "grad_norm": 0.030487604439258575,
      "learning_rate": 0.024000000208616257,
      "loss": 2.362741231918335,
      "step": 12068
    },
    {
      "epoch": 0.5747619047619048,
      "grad_norm": 0.027514124289155006,
      "learning_rate": 0.024000000208616257,
      "loss": 2.344200849533081,
      "step": 12070
    },
    {
      "epoch": 0.5748571428571428,
      "grad_norm": 0.026624947786331177,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3395705223083496,
      "step": 12072
    },
    {
      "epoch": 0.574952380952381,
      "grad_norm": 0.028573932126164436,
      "learning_rate": 0.024000000208616257,
      "loss": 2.317322254180908,
      "step": 12074
    },
    {
      "epoch": 0.575047619047619,
      "grad_norm": 0.027427705004811287,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3413901329040527,
      "step": 12076
    },
    {
      "epoch": 0.5751428571428572,
      "grad_norm": 0.028706112876534462,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3419628143310547,
      "step": 12078
    },
    {
      "epoch": 0.5752380952380952,
      "grad_norm": 0.0264842938631773,
      "learning_rate": 0.024000000208616257,
      "loss": 2.34963321685791,
      "step": 12080
    },
    {
      "epoch": 0.5753333333333334,
      "grad_norm": 0.029379885643720627,
      "learning_rate": 0.024000000208616257,
      "loss": 2.336191177368164,
      "step": 12082
    },
    {
      "epoch": 0.5754285714285714,
      "grad_norm": 0.02802962437272072,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3159284591674805,
      "step": 12084
    },
    {
      "epoch": 0.5755238095238095,
      "grad_norm": 0.032924070954322815,
      "learning_rate": 0.024000000208616257,
      "loss": 2.306708812713623,
      "step": 12086
    },
    {
      "epoch": 0.5756190476190476,
      "grad_norm": 0.02585965394973755,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3344597816467285,
      "step": 12088
    },
    {
      "epoch": 0.5757142857142857,
      "grad_norm": 0.030494172126054764,
      "learning_rate": 0.024000000208616257,
      "loss": 2.33652400970459,
      "step": 12090
    },
    {
      "epoch": 0.5758095238095238,
      "grad_norm": 0.03373820707201958,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3337743282318115,
      "step": 12092
    },
    {
      "epoch": 0.5759047619047619,
      "grad_norm": 0.026861783117055893,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3262901306152344,
      "step": 12094
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.027221743017435074,
      "learning_rate": 0.024000000208616257,
      "loss": 2.341005325317383,
      "step": 12096
    },
    {
      "epoch": 0.5760952380952381,
      "grad_norm": 0.026152167469263077,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3406200408935547,
      "step": 12098
    },
    {
      "epoch": 0.5761904761904761,
      "grad_norm": 0.026923242956399918,
      "learning_rate": 0.024000000208616257,
      "loss": 2.336327075958252,
      "step": 12100
    },
    {
      "epoch": 0.5762857142857143,
      "grad_norm": 0.02713662199676037,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2999496459960938,
      "step": 12102
    },
    {
      "epoch": 0.5763809523809523,
      "grad_norm": 0.026998624205589294,
      "learning_rate": 0.024000000208616257,
      "loss": 2.327702045440674,
      "step": 12104
    },
    {
      "epoch": 0.5764761904761905,
      "grad_norm": 0.029741067439317703,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3371896743774414,
      "step": 12106
    },
    {
      "epoch": 0.5765714285714286,
      "grad_norm": 0.027055000886321068,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3546218872070312,
      "step": 12108
    },
    {
      "epoch": 0.5766666666666667,
      "grad_norm": 0.0309158805757761,
      "learning_rate": 0.024000000208616257,
      "loss": 2.364199638366699,
      "step": 12110
    },
    {
      "epoch": 0.5767619047619048,
      "grad_norm": 0.03145656734704971,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3280515670776367,
      "step": 12112
    },
    {
      "epoch": 0.5768571428571428,
      "grad_norm": 0.028398284688591957,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3045430183410645,
      "step": 12114
    },
    {
      "epoch": 0.576952380952381,
      "grad_norm": 0.027556344866752625,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3469676971435547,
      "step": 12116
    },
    {
      "epoch": 0.577047619047619,
      "grad_norm": 0.027510613203048706,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2907609939575195,
      "step": 12118
    },
    {
      "epoch": 0.5771428571428572,
      "grad_norm": 0.025948787108063698,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3162035942077637,
      "step": 12120
    },
    {
      "epoch": 0.5772380952380952,
      "grad_norm": 0.02753136307001114,
      "learning_rate": 0.024000000208616257,
      "loss": 2.335094451904297,
      "step": 12122
    },
    {
      "epoch": 0.5773333333333334,
      "grad_norm": 0.02658761292695999,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3481264114379883,
      "step": 12124
    },
    {
      "epoch": 0.5774285714285714,
      "grad_norm": 0.026946162804961205,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3794147968292236,
      "step": 12126
    },
    {
      "epoch": 0.5775238095238096,
      "grad_norm": 0.026795808225870132,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3377275466918945,
      "step": 12128
    },
    {
      "epoch": 0.5776190476190476,
      "grad_norm": 0.028012150898575783,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3536791801452637,
      "step": 12130
    },
    {
      "epoch": 0.5777142857142857,
      "grad_norm": 0.028223508968949318,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3557286262512207,
      "step": 12132
    },
    {
      "epoch": 0.5778095238095238,
      "grad_norm": 0.028580958023667336,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3539390563964844,
      "step": 12134
    },
    {
      "epoch": 0.5779047619047619,
      "grad_norm": 0.029166195541620255,
      "learning_rate": 0.024000000208616257,
      "loss": 2.311408519744873,
      "step": 12136
    },
    {
      "epoch": 0.578,
      "grad_norm": 0.026748839765787125,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3171491622924805,
      "step": 12138
    },
    {
      "epoch": 0.5780952380952381,
      "grad_norm": 0.025770820677280426,
      "learning_rate": 0.024000000208616257,
      "loss": 2.306121587753296,
      "step": 12140
    },
    {
      "epoch": 0.5781904761904761,
      "grad_norm": 0.026084300130605698,
      "learning_rate": 0.024000000208616257,
      "loss": 2.323335647583008,
      "step": 12142
    },
    {
      "epoch": 0.5782857142857143,
      "grad_norm": 0.026504257693886757,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3289356231689453,
      "step": 12144
    },
    {
      "epoch": 0.5783809523809523,
      "grad_norm": 0.02665271796286106,
      "learning_rate": 0.024000000208616257,
      "loss": 2.299745559692383,
      "step": 12146
    },
    {
      "epoch": 0.5784761904761905,
      "grad_norm": 0.027084674686193466,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3327455520629883,
      "step": 12148
    },
    {
      "epoch": 0.5785714285714286,
      "grad_norm": 0.028540339320898056,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3244247436523438,
      "step": 12150
    },
    {
      "epoch": 0.5786666666666667,
      "grad_norm": 0.027856744825839996,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3036251068115234,
      "step": 12152
    },
    {
      "epoch": 0.5787619047619048,
      "grad_norm": 0.026809196919202805,
      "learning_rate": 0.024000000208616257,
      "loss": 2.324432373046875,
      "step": 12154
    },
    {
      "epoch": 0.5788571428571428,
      "grad_norm": 0.028046058490872383,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3662359714508057,
      "step": 12156
    },
    {
      "epoch": 0.578952380952381,
      "grad_norm": 0.027851583436131477,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3113880157470703,
      "step": 12158
    },
    {
      "epoch": 0.579047619047619,
      "grad_norm": 0.027125252410769463,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2982168197631836,
      "step": 12160
    },
    {
      "epoch": 0.5791428571428572,
      "grad_norm": 0.02890186756849289,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338730812072754,
      "step": 12162
    },
    {
      "epoch": 0.5792380952380952,
      "grad_norm": 0.028973866254091263,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3199520111083984,
      "step": 12164
    },
    {
      "epoch": 0.5793333333333334,
      "grad_norm": 0.027984997257590294,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3168087005615234,
      "step": 12166
    },
    {
      "epoch": 0.5794285714285714,
      "grad_norm": 0.027805211022496223,
      "learning_rate": 0.024000000208616257,
      "loss": 2.310680866241455,
      "step": 12168
    },
    {
      "epoch": 0.5795238095238096,
      "grad_norm": 0.02701435051858425,
      "learning_rate": 0.024000000208616257,
      "loss": 2.30135440826416,
      "step": 12170
    },
    {
      "epoch": 0.5796190476190476,
      "grad_norm": 0.02834789641201496,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345079183578491,
      "step": 12172
    },
    {
      "epoch": 0.5797142857142857,
      "grad_norm": 0.028523709625005722,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3472061157226562,
      "step": 12174
    },
    {
      "epoch": 0.5798095238095238,
      "grad_norm": 0.02786180004477501,
      "learning_rate": 0.024000000208616257,
      "loss": 2.367483139038086,
      "step": 12176
    },
    {
      "epoch": 0.5799047619047619,
      "grad_norm": 0.027829425409436226,
      "learning_rate": 0.024000000208616257,
      "loss": 2.312840461730957,
      "step": 12178
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.02847628854215145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.342899799346924,
      "step": 12180
    },
    {
      "epoch": 0.5800952380952381,
      "grad_norm": 0.02684679627418518,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3088324069976807,
      "step": 12182
    },
    {
      "epoch": 0.5801904761904761,
      "grad_norm": 0.028722072020173073,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3582024574279785,
      "step": 12184
    },
    {
      "epoch": 0.5802857142857143,
      "grad_norm": 0.027050629258155823,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3228578567504883,
      "step": 12186
    },
    {
      "epoch": 0.5803809523809523,
      "grad_norm": 0.026955096051096916,
      "learning_rate": 0.024000000208616257,
      "loss": 2.306852340698242,
      "step": 12188
    },
    {
      "epoch": 0.5804761904761905,
      "grad_norm": 0.027379417791962624,
      "learning_rate": 0.024000000208616257,
      "loss": 2.347888708114624,
      "step": 12190
    },
    {
      "epoch": 0.5805714285714285,
      "grad_norm": 0.026718558743596077,
      "learning_rate": 0.024000000208616257,
      "loss": 2.318300247192383,
      "step": 12192
    },
    {
      "epoch": 0.5806666666666667,
      "grad_norm": 0.028107907623052597,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3139748573303223,
      "step": 12194
    },
    {
      "epoch": 0.5807619047619048,
      "grad_norm": 0.027575552463531494,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3176004886627197,
      "step": 12196
    },
    {
      "epoch": 0.5808571428571428,
      "grad_norm": 0.02656383439898491,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3347442150115967,
      "step": 12198
    },
    {
      "epoch": 0.580952380952381,
      "grad_norm": 0.027088945731520653,
      "learning_rate": 0.024000000208616257,
      "loss": 2.315256118774414,
      "step": 12200
    },
    {
      "epoch": 0.581047619047619,
      "grad_norm": 0.026894284412264824,
      "learning_rate": 0.024000000208616257,
      "loss": 2.315056324005127,
      "step": 12202
    },
    {
      "epoch": 0.5811428571428572,
      "grad_norm": 0.02698647417128086,
      "learning_rate": 0.024000000208616257,
      "loss": 2.334862470626831,
      "step": 12204
    },
    {
      "epoch": 0.5812380952380952,
      "grad_norm": 0.030697818845510483,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3071393966674805,
      "step": 12206
    },
    {
      "epoch": 0.5813333333333334,
      "grad_norm": 0.03349713236093521,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3386688232421875,
      "step": 12208
    },
    {
      "epoch": 0.5814285714285714,
      "grad_norm": 0.028439899906516075,
      "learning_rate": 0.024000000208616257,
      "loss": 2.348507881164551,
      "step": 12210
    },
    {
      "epoch": 0.5815238095238096,
      "grad_norm": 0.029070058837532997,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3025574684143066,
      "step": 12212
    },
    {
      "epoch": 0.5816190476190476,
      "grad_norm": 0.027474218979477882,
      "learning_rate": 0.024000000208616257,
      "loss": 2.309096574783325,
      "step": 12214
    },
    {
      "epoch": 0.5817142857142857,
      "grad_norm": 0.02623731829226017,
      "learning_rate": 0.024000000208616257,
      "loss": 2.343217372894287,
      "step": 12216
    },
    {
      "epoch": 0.5818095238095238,
      "grad_norm": 0.026599377393722534,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3469274044036865,
      "step": 12218
    },
    {
      "epoch": 0.5819047619047619,
      "grad_norm": 0.02796119637787342,
      "learning_rate": 0.024000000208616257,
      "loss": 2.34367036819458,
      "step": 12220
    },
    {
      "epoch": 0.582,
      "grad_norm": 0.03024294041097164,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3057937622070312,
      "step": 12222
    },
    {
      "epoch": 0.5820952380952381,
      "grad_norm": 0.026055337861180305,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3350911140441895,
      "step": 12224
    },
    {
      "epoch": 0.5821904761904761,
      "grad_norm": 0.029072187840938568,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3408827781677246,
      "step": 12226
    },
    {
      "epoch": 0.5822857142857143,
      "grad_norm": 0.02599361166357994,
      "learning_rate": 0.024000000208616257,
      "loss": 2.336026668548584,
      "step": 12228
    },
    {
      "epoch": 0.5823809523809523,
      "grad_norm": 0.029126591980457306,
      "learning_rate": 0.024000000208616257,
      "loss": 2.312204122543335,
      "step": 12230
    },
    {
      "epoch": 0.5824761904761905,
      "grad_norm": 0.026838034391403198,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3392133712768555,
      "step": 12232
    },
    {
      "epoch": 0.5825714285714285,
      "grad_norm": 0.0266078133136034,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3402481079101562,
      "step": 12234
    },
    {
      "epoch": 0.5826666666666667,
      "grad_norm": 0.026904258877038956,
      "learning_rate": 0.024000000208616257,
      "loss": 2.312600612640381,
      "step": 12236
    },
    {
      "epoch": 0.5827619047619048,
      "grad_norm": 0.02651767060160637,
      "learning_rate": 0.024000000208616257,
      "loss": 2.339435577392578,
      "step": 12238
    },
    {
      "epoch": 0.5828571428571429,
      "grad_norm": 0.027102889493107796,
      "learning_rate": 0.024000000208616257,
      "loss": 2.312227725982666,
      "step": 12240
    },
    {
      "epoch": 0.582952380952381,
      "grad_norm": 0.025417771190404892,
      "learning_rate": 0.024000000208616257,
      "loss": 2.309314250946045,
      "step": 12242
    },
    {
      "epoch": 0.583047619047619,
      "grad_norm": 0.027607902884483337,
      "learning_rate": 0.024000000208616257,
      "loss": 2.326785087585449,
      "step": 12244
    },
    {
      "epoch": 0.5831428571428572,
      "grad_norm": 0.03293485566973686,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3391613960266113,
      "step": 12246
    },
    {
      "epoch": 0.5832380952380952,
      "grad_norm": 0.03009520098567009,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3243424892425537,
      "step": 12248
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 0.027315916493535042,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2892696857452393,
      "step": 12250
    },
    {
      "epoch": 0.5834285714285714,
      "grad_norm": 0.028781428933143616,
      "learning_rate": 0.024000000208616257,
      "loss": 2.320204257965088,
      "step": 12252
    },
    {
      "epoch": 0.5835238095238096,
      "grad_norm": 0.026021920144557953,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3069097995758057,
      "step": 12254
    },
    {
      "epoch": 0.5836190476190476,
      "grad_norm": 0.030875086784362793,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3209919929504395,
      "step": 12256
    },
    {
      "epoch": 0.5837142857142857,
      "grad_norm": 0.027486611157655716,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3185629844665527,
      "step": 12258
    },
    {
      "epoch": 0.5838095238095238,
      "grad_norm": 0.0344439335167408,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3315703868865967,
      "step": 12260
    },
    {
      "epoch": 0.5839047619047619,
      "grad_norm": 0.029307818040251732,
      "learning_rate": 0.024000000208616257,
      "loss": 2.326796531677246,
      "step": 12262
    },
    {
      "epoch": 0.584,
      "grad_norm": 0.029890306293964386,
      "learning_rate": 0.024000000208616257,
      "loss": 2.351973533630371,
      "step": 12264
    },
    {
      "epoch": 0.5840952380952381,
      "grad_norm": 0.030015964061021805,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3068652153015137,
      "step": 12266
    },
    {
      "epoch": 0.5841904761904761,
      "grad_norm": 0.02605317533016205,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3384909629821777,
      "step": 12268
    },
    {
      "epoch": 0.5842857142857143,
      "grad_norm": 0.027455009520053864,
      "learning_rate": 0.024000000208616257,
      "loss": 2.328835964202881,
      "step": 12270
    },
    {
      "epoch": 0.5843809523809523,
      "grad_norm": 0.027896905317902565,
      "learning_rate": 0.024000000208616257,
      "loss": 2.320535898208618,
      "step": 12272
    },
    {
      "epoch": 0.5844761904761905,
      "grad_norm": 0.0275722686201334,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3253555297851562,
      "step": 12274
    },
    {
      "epoch": 0.5845714285714285,
      "grad_norm": 0.027721311897039413,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3308303356170654,
      "step": 12276
    },
    {
      "epoch": 0.5846666666666667,
      "grad_norm": 0.02587936446070671,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3376612663269043,
      "step": 12278
    },
    {
      "epoch": 0.5847619047619048,
      "grad_norm": 0.027317168191075325,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3483242988586426,
      "step": 12280
    },
    {
      "epoch": 0.5848571428571429,
      "grad_norm": 0.028771329671144485,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3436343669891357,
      "step": 12282
    },
    {
      "epoch": 0.584952380952381,
      "grad_norm": 0.026538895443081856,
      "learning_rate": 0.024000000208616257,
      "loss": 2.320572853088379,
      "step": 12284
    },
    {
      "epoch": 0.585047619047619,
      "grad_norm": 0.027500299736857414,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3324151039123535,
      "step": 12286
    },
    {
      "epoch": 0.5851428571428572,
      "grad_norm": 0.027250854298472404,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3393595218658447,
      "step": 12288
    },
    {
      "epoch": 0.5852380952380952,
      "grad_norm": 0.02943519316613674,
      "learning_rate": 0.024000000208616257,
      "loss": 2.324178457260132,
      "step": 12290
    },
    {
      "epoch": 0.5853333333333334,
      "grad_norm": 0.03305273503065109,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3183083534240723,
      "step": 12292
    },
    {
      "epoch": 0.5854285714285714,
      "grad_norm": 0.026793256402015686,
      "learning_rate": 0.024000000208616257,
      "loss": 2.303107261657715,
      "step": 12294
    },
    {
      "epoch": 0.5855238095238096,
      "grad_norm": 0.030139654874801636,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3439459800720215,
      "step": 12296
    },
    {
      "epoch": 0.5856190476190476,
      "grad_norm": 0.02684975601732731,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3258416652679443,
      "step": 12298
    },
    {
      "epoch": 0.5857142857142857,
      "grad_norm": 0.02996896766126156,
      "learning_rate": 0.024000000208616257,
      "loss": 2.330080509185791,
      "step": 12300
    },
    {
      "epoch": 0.5858095238095238,
      "grad_norm": 0.027806660160422325,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3639535903930664,
      "step": 12302
    },
    {
      "epoch": 0.5859047619047619,
      "grad_norm": 0.026629945263266563,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3559226989746094,
      "step": 12304
    },
    {
      "epoch": 0.586,
      "grad_norm": 0.02670132927596569,
      "learning_rate": 0.024000000208616257,
      "loss": 2.309173107147217,
      "step": 12306
    },
    {
      "epoch": 0.5860952380952381,
      "grad_norm": 0.02699791081249714,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3401060104370117,
      "step": 12308
    },
    {
      "epoch": 0.5861904761904762,
      "grad_norm": 0.027892736718058586,
      "learning_rate": 0.024000000208616257,
      "loss": 2.341721534729004,
      "step": 12310
    },
    {
      "epoch": 0.5862857142857143,
      "grad_norm": 0.02787058986723423,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356400728225708,
      "step": 12312
    },
    {
      "epoch": 0.5863809523809523,
      "grad_norm": 0.02884187549352646,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3564813137054443,
      "step": 12314
    },
    {
      "epoch": 0.5864761904761905,
      "grad_norm": 0.027980411425232887,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3304669857025146,
      "step": 12316
    },
    {
      "epoch": 0.5865714285714285,
      "grad_norm": 0.027060315012931824,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3534576892852783,
      "step": 12318
    },
    {
      "epoch": 0.5866666666666667,
      "grad_norm": 0.02706301212310791,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345503330230713,
      "step": 12320
    },
    {
      "epoch": 0.5867619047619047,
      "grad_norm": 0.02708302065730095,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3420448303222656,
      "step": 12322
    },
    {
      "epoch": 0.5868571428571429,
      "grad_norm": 0.027856647968292236,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3293380737304688,
      "step": 12324
    },
    {
      "epoch": 0.586952380952381,
      "grad_norm": 0.02805522084236145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3376917839050293,
      "step": 12326
    },
    {
      "epoch": 0.587047619047619,
      "grad_norm": 0.032565273344516754,
      "learning_rate": 0.024000000208616257,
      "loss": 2.340536594390869,
      "step": 12328
    },
    {
      "epoch": 0.5871428571428572,
      "grad_norm": 0.02631809376180172,
      "learning_rate": 0.024000000208616257,
      "loss": 2.319396495819092,
      "step": 12330
    },
    {
      "epoch": 0.5872380952380952,
      "grad_norm": 0.027144981548190117,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3064870834350586,
      "step": 12332
    },
    {
      "epoch": 0.5873333333333334,
      "grad_norm": 0.025783292949199677,
      "learning_rate": 0.024000000208616257,
      "loss": 2.340022563934326,
      "step": 12334
    },
    {
      "epoch": 0.5874285714285714,
      "grad_norm": 0.02638058364391327,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3246359825134277,
      "step": 12336
    },
    {
      "epoch": 0.5875238095238096,
      "grad_norm": 0.026182666420936584,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3249261379241943,
      "step": 12338
    },
    {
      "epoch": 0.5876190476190476,
      "grad_norm": 0.033075448125600815,
      "learning_rate": 0.024000000208616257,
      "loss": 2.29268217086792,
      "step": 12340
    },
    {
      "epoch": 0.5877142857142857,
      "grad_norm": 0.02754410356283188,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3230533599853516,
      "step": 12342
    },
    {
      "epoch": 0.5878095238095238,
      "grad_norm": 0.026523010805249214,
      "learning_rate": 0.024000000208616257,
      "loss": 2.343830108642578,
      "step": 12344
    },
    {
      "epoch": 0.5879047619047619,
      "grad_norm": 0.026724819093942642,
      "learning_rate": 0.024000000208616257,
      "loss": 2.331662654876709,
      "step": 12346
    },
    {
      "epoch": 0.588,
      "grad_norm": 0.028180018067359924,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3533096313476562,
      "step": 12348
    },
    {
      "epoch": 0.5880952380952381,
      "grad_norm": 0.026779726147651672,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3607592582702637,
      "step": 12350
    },
    {
      "epoch": 0.5881904761904762,
      "grad_norm": 0.026308685541152954,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3370213508605957,
      "step": 12352
    },
    {
      "epoch": 0.5882857142857143,
      "grad_norm": 0.025329962372779846,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3243541717529297,
      "step": 12354
    },
    {
      "epoch": 0.5883809523809523,
      "grad_norm": 0.026027774438261986,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356414794921875,
      "step": 12356
    },
    {
      "epoch": 0.5884761904761905,
      "grad_norm": 0.029304828494787216,
      "learning_rate": 0.024000000208616257,
      "loss": 2.349241018295288,
      "step": 12358
    },
    {
      "epoch": 0.5885714285714285,
      "grad_norm": 0.027344312518835068,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3188869953155518,
      "step": 12360
    },
    {
      "epoch": 0.5886666666666667,
      "grad_norm": 0.026703765615820885,
      "learning_rate": 0.024000000208616257,
      "loss": 2.336775779724121,
      "step": 12362
    },
    {
      "epoch": 0.5887619047619047,
      "grad_norm": 0.027941081672906876,
      "learning_rate": 0.024000000208616257,
      "loss": 2.343597650527954,
      "step": 12364
    },
    {
      "epoch": 0.5888571428571429,
      "grad_norm": 0.026447713375091553,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3235812187194824,
      "step": 12366
    },
    {
      "epoch": 0.588952380952381,
      "grad_norm": 0.026614967733621597,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3381810188293457,
      "step": 12368
    },
    {
      "epoch": 0.589047619047619,
      "grad_norm": 0.026431800797581673,
      "learning_rate": 0.024000000208616257,
      "loss": 2.327434539794922,
      "step": 12370
    },
    {
      "epoch": 0.5891428571428572,
      "grad_norm": 0.027294442057609558,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3307201862335205,
      "step": 12372
    },
    {
      "epoch": 0.5892380952380952,
      "grad_norm": 0.026529692113399506,
      "learning_rate": 0.024000000208616257,
      "loss": 2.347377300262451,
      "step": 12374
    },
    {
      "epoch": 0.5893333333333334,
      "grad_norm": 0.028011338785290718,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3640365600585938,
      "step": 12376
    },
    {
      "epoch": 0.5894285714285714,
      "grad_norm": 0.028010698035359383,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3259787559509277,
      "step": 12378
    },
    {
      "epoch": 0.5895238095238096,
      "grad_norm": 0.028253963217139244,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3724029064178467,
      "step": 12380
    },
    {
      "epoch": 0.5896190476190476,
      "grad_norm": 0.028004534542560577,
      "learning_rate": 0.024000000208616257,
      "loss": 2.335995674133301,
      "step": 12382
    },
    {
      "epoch": 0.5897142857142857,
      "grad_norm": 0.028582008555531502,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3766250610351562,
      "step": 12384
    },
    {
      "epoch": 0.5898095238095238,
      "grad_norm": 0.030090680345892906,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3355250358581543,
      "step": 12386
    },
    {
      "epoch": 0.5899047619047619,
      "grad_norm": 0.03152906149625778,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3816866874694824,
      "step": 12388
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.02908134087920189,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3915066719055176,
      "step": 12390
    },
    {
      "epoch": 0.5900952380952381,
      "grad_norm": 0.027962446212768555,
      "learning_rate": 0.024000000208616257,
      "loss": 2.343268871307373,
      "step": 12392
    },
    {
      "epoch": 0.5901904761904762,
      "grad_norm": 0.03523149713873863,
      "learning_rate": 0.024000000208616257,
      "loss": 2.33189058303833,
      "step": 12394
    },
    {
      "epoch": 0.5902857142857143,
      "grad_norm": 0.029791386798024178,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3295650482177734,
      "step": 12396
    },
    {
      "epoch": 0.5903809523809523,
      "grad_norm": 0.02732100524008274,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3376755714416504,
      "step": 12398
    },
    {
      "epoch": 0.5904761904761905,
      "grad_norm": 0.03017984889447689,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3291897773742676,
      "step": 12400
    },
    {
      "epoch": 0.5905714285714285,
      "grad_norm": 0.02772781439125538,
      "learning_rate": 0.024000000208616257,
      "loss": 2.33034086227417,
      "step": 12402
    },
    {
      "epoch": 0.5906666666666667,
      "grad_norm": 0.028456561267375946,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3555893898010254,
      "step": 12404
    },
    {
      "epoch": 0.5907619047619047,
      "grad_norm": 0.02865447662770748,
      "learning_rate": 0.024000000208616257,
      "loss": 2.317617177963257,
      "step": 12406
    },
    {
      "epoch": 0.5908571428571429,
      "grad_norm": 0.027223162353038788,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3155107498168945,
      "step": 12408
    },
    {
      "epoch": 0.590952380952381,
      "grad_norm": 0.026319595053792,
      "learning_rate": 0.024000000208616257,
      "loss": 2.322434186935425,
      "step": 12410
    },
    {
      "epoch": 0.591047619047619,
      "grad_norm": 0.026857294142246246,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3375067710876465,
      "step": 12412
    },
    {
      "epoch": 0.5911428571428572,
      "grad_norm": 0.02672337181866169,
      "learning_rate": 0.024000000208616257,
      "loss": 2.347041130065918,
      "step": 12414
    },
    {
      "epoch": 0.5912380952380952,
      "grad_norm": 0.03202202171087265,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3503715991973877,
      "step": 12416
    },
    {
      "epoch": 0.5913333333333334,
      "grad_norm": 0.02628675475716591,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3528566360473633,
      "step": 12418
    },
    {
      "epoch": 0.5914285714285714,
      "grad_norm": 0.026766879484057426,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3171932697296143,
      "step": 12420
    },
    {
      "epoch": 0.5915238095238096,
      "grad_norm": 0.026564452797174454,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3435921669006348,
      "step": 12422
    },
    {
      "epoch": 0.5916190476190476,
      "grad_norm": 0.027140658348798752,
      "learning_rate": 0.024000000208616257,
      "loss": 2.354954957962036,
      "step": 12424
    },
    {
      "epoch": 0.5917142857142857,
      "grad_norm": 0.02736849896609783,
      "learning_rate": 0.024000000208616257,
      "loss": 2.330613613128662,
      "step": 12426
    },
    {
      "epoch": 0.5918095238095238,
      "grad_norm": 0.026462169364094734,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3458335399627686,
      "step": 12428
    },
    {
      "epoch": 0.5919047619047619,
      "grad_norm": 0.02690066583454609,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356632709503174,
      "step": 12430
    },
    {
      "epoch": 0.592,
      "grad_norm": 0.028632424771785736,
      "learning_rate": 0.024000000208616257,
      "loss": 2.357645034790039,
      "step": 12432
    },
    {
      "epoch": 0.5920952380952381,
      "grad_norm": 0.027319952845573425,
      "learning_rate": 0.024000000208616257,
      "loss": 2.343433380126953,
      "step": 12434
    },
    {
      "epoch": 0.5921904761904762,
      "grad_norm": 0.02761332131922245,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3578267097473145,
      "step": 12436
    },
    {
      "epoch": 0.5922857142857143,
      "grad_norm": 0.03052588365972042,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3333020210266113,
      "step": 12438
    },
    {
      "epoch": 0.5923809523809523,
      "grad_norm": 0.02854655683040619,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355045795440674,
      "step": 12440
    },
    {
      "epoch": 0.5924761904761905,
      "grad_norm": 0.030274339020252228,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3438355922698975,
      "step": 12442
    },
    {
      "epoch": 0.5925714285714285,
      "grad_norm": 0.0349469892680645,
      "learning_rate": 0.024000000208616257,
      "loss": 2.333352565765381,
      "step": 12444
    },
    {
      "epoch": 0.5926666666666667,
      "grad_norm": 0.02886793576180935,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3508360385894775,
      "step": 12446
    },
    {
      "epoch": 0.5927619047619047,
      "grad_norm": 0.026890235021710396,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3316636085510254,
      "step": 12448
    },
    {
      "epoch": 0.5928571428571429,
      "grad_norm": 0.02662172168493271,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3562984466552734,
      "step": 12450
    },
    {
      "epoch": 0.5929523809523809,
      "grad_norm": 0.026432164013385773,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3230042457580566,
      "step": 12452
    },
    {
      "epoch": 0.593047619047619,
      "grad_norm": 0.0261069368571043,
      "learning_rate": 0.024000000208616257,
      "loss": 2.348151922225952,
      "step": 12454
    },
    {
      "epoch": 0.5931428571428572,
      "grad_norm": 0.026898618787527084,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350335121154785,
      "step": 12456
    },
    {
      "epoch": 0.5932380952380952,
      "grad_norm": 0.026696782559156418,
      "learning_rate": 0.024000000208616257,
      "loss": 2.365729570388794,
      "step": 12458
    },
    {
      "epoch": 0.5933333333333334,
      "grad_norm": 0.027331866323947906,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3474931716918945,
      "step": 12460
    },
    {
      "epoch": 0.5934285714285714,
      "grad_norm": 0.027852287515997887,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3323676586151123,
      "step": 12462
    },
    {
      "epoch": 0.5935238095238096,
      "grad_norm": 0.026050524786114693,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3228673934936523,
      "step": 12464
    },
    {
      "epoch": 0.5936190476190476,
      "grad_norm": 0.02731472998857498,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363190174102783,
      "step": 12466
    },
    {
      "epoch": 0.5937142857142857,
      "grad_norm": 0.030785121023654938,
      "learning_rate": 0.024000000208616257,
      "loss": 2.326927661895752,
      "step": 12468
    },
    {
      "epoch": 0.5938095238095238,
      "grad_norm": 0.027796080335974693,
      "learning_rate": 0.024000000208616257,
      "loss": 2.317498207092285,
      "step": 12470
    },
    {
      "epoch": 0.5939047619047619,
      "grad_norm": 0.02713398076593876,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3475654125213623,
      "step": 12472
    },
    {
      "epoch": 0.594,
      "grad_norm": 0.026809845119714737,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3509764671325684,
      "step": 12474
    },
    {
      "epoch": 0.5940952380952381,
      "grad_norm": 0.027782678604125977,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3232669830322266,
      "step": 12476
    },
    {
      "epoch": 0.5941904761904762,
      "grad_norm": 0.027042880654335022,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3173251152038574,
      "step": 12478
    },
    {
      "epoch": 0.5942857142857143,
      "grad_norm": 0.02868247963488102,
      "learning_rate": 0.024000000208616257,
      "loss": 2.369359254837036,
      "step": 12480
    },
    {
      "epoch": 0.5943809523809523,
      "grad_norm": 0.02755649946630001,
      "learning_rate": 0.024000000208616257,
      "loss": 2.347655773162842,
      "step": 12482
    },
    {
      "epoch": 0.5944761904761905,
      "grad_norm": 0.027663739398121834,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3604249954223633,
      "step": 12484
    },
    {
      "epoch": 0.5945714285714285,
      "grad_norm": 0.026832766830921173,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3375062942504883,
      "step": 12486
    },
    {
      "epoch": 0.5946666666666667,
      "grad_norm": 0.027483196929097176,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3298404216766357,
      "step": 12488
    },
    {
      "epoch": 0.5947619047619047,
      "grad_norm": 0.027147145941853523,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3186731338500977,
      "step": 12490
    },
    {
      "epoch": 0.5948571428571429,
      "grad_norm": 0.027380667626857758,
      "learning_rate": 0.024000000208616257,
      "loss": 2.358882427215576,
      "step": 12492
    },
    {
      "epoch": 0.5949523809523809,
      "grad_norm": 0.028413541615009308,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3415164947509766,
      "step": 12494
    },
    {
      "epoch": 0.595047619047619,
      "grad_norm": 0.026057524606585503,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3238089084625244,
      "step": 12496
    },
    {
      "epoch": 0.5951428571428572,
      "grad_norm": 0.026759067550301552,
      "learning_rate": 0.024000000208616257,
      "loss": 2.331364631652832,
      "step": 12498
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 0.02828497439622879,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3108692169189453,
      "step": 12500
    },
    {
      "epoch": 0.5953333333333334,
      "grad_norm": 0.0273391492664814,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3568763732910156,
      "step": 12502
    },
    {
      "epoch": 0.5954285714285714,
      "grad_norm": 0.028317231684923172,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3429791927337646,
      "step": 12504
    },
    {
      "epoch": 0.5955238095238096,
      "grad_norm": 0.026133719831705093,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3471639156341553,
      "step": 12506
    },
    {
      "epoch": 0.5956190476190476,
      "grad_norm": 0.027845311909914017,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356475353240967,
      "step": 12508
    },
    {
      "epoch": 0.5957142857142858,
      "grad_norm": 0.02655179426074028,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3567073345184326,
      "step": 12510
    },
    {
      "epoch": 0.5958095238095238,
      "grad_norm": 0.026589997112751007,
      "learning_rate": 0.024000000208616257,
      "loss": 2.333887815475464,
      "step": 12512
    },
    {
      "epoch": 0.5959047619047619,
      "grad_norm": 0.02593517303466797,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3228261470794678,
      "step": 12514
    },
    {
      "epoch": 0.596,
      "grad_norm": 0.027106067165732384,
      "learning_rate": 0.024000000208616257,
      "loss": 2.358494281768799,
      "step": 12516
    },
    {
      "epoch": 0.5960952380952381,
      "grad_norm": 0.028650598600506783,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3324925899505615,
      "step": 12518
    },
    {
      "epoch": 0.5961904761904762,
      "grad_norm": 0.026504117995500565,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3487460613250732,
      "step": 12520
    },
    {
      "epoch": 0.5962857142857143,
      "grad_norm": 0.02852259948849678,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3605175018310547,
      "step": 12522
    },
    {
      "epoch": 0.5963809523809523,
      "grad_norm": 0.02709975279867649,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3561506271362305,
      "step": 12524
    },
    {
      "epoch": 0.5964761904761905,
      "grad_norm": 0.029831059277057648,
      "learning_rate": 0.024000000208616257,
      "loss": 2.357992172241211,
      "step": 12526
    },
    {
      "epoch": 0.5965714285714285,
      "grad_norm": 0.02590150758624077,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3157308101654053,
      "step": 12528
    },
    {
      "epoch": 0.5966666666666667,
      "grad_norm": 0.026988904923200607,
      "learning_rate": 0.024000000208616257,
      "loss": 2.34720778465271,
      "step": 12530
    },
    {
      "epoch": 0.5967619047619047,
      "grad_norm": 0.027603531256318092,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3240599632263184,
      "step": 12532
    },
    {
      "epoch": 0.5968571428571429,
      "grad_norm": 0.030643336474895477,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3731141090393066,
      "step": 12534
    },
    {
      "epoch": 0.5969523809523809,
      "grad_norm": 0.028236741200089455,
      "learning_rate": 0.024000000208616257,
      "loss": 2.341582775115967,
      "step": 12536
    },
    {
      "epoch": 0.597047619047619,
      "grad_norm": 0.02848188951611519,
      "learning_rate": 0.024000000208616257,
      "loss": 2.329777717590332,
      "step": 12538
    },
    {
      "epoch": 0.5971428571428572,
      "grad_norm": 0.028160255402326584,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3614683151245117,
      "step": 12540
    },
    {
      "epoch": 0.5972380952380952,
      "grad_norm": 0.025809507817029953,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3435652256011963,
      "step": 12542
    },
    {
      "epoch": 0.5973333333333334,
      "grad_norm": 0.02808268368244171,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3469011783599854,
      "step": 12544
    },
    {
      "epoch": 0.5974285714285714,
      "grad_norm": 0.027348650619387627,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3368301391601562,
      "step": 12546
    },
    {
      "epoch": 0.5975238095238096,
      "grad_norm": 0.02758782170712948,
      "learning_rate": 0.024000000208616257,
      "loss": 2.318479537963867,
      "step": 12548
    },
    {
      "epoch": 0.5976190476190476,
      "grad_norm": 0.027248887345194817,
      "learning_rate": 0.024000000208616257,
      "loss": 2.385605812072754,
      "step": 12550
    },
    {
      "epoch": 0.5977142857142858,
      "grad_norm": 0.02952159382402897,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3686916828155518,
      "step": 12552
    },
    {
      "epoch": 0.5978095238095238,
      "grad_norm": 0.026783905923366547,
      "learning_rate": 0.024000000208616257,
      "loss": 2.378345489501953,
      "step": 12554
    },
    {
      "epoch": 0.5979047619047619,
      "grad_norm": 0.026729974895715714,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3604037761688232,
      "step": 12556
    },
    {
      "epoch": 0.598,
      "grad_norm": 0.02637012116611004,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3488264083862305,
      "step": 12558
    },
    {
      "epoch": 0.5980952380952381,
      "grad_norm": 0.026248708367347717,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3552913665771484,
      "step": 12560
    },
    {
      "epoch": 0.5981904761904762,
      "grad_norm": 0.03063446283340454,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3377737998962402,
      "step": 12562
    },
    {
      "epoch": 0.5982857142857143,
      "grad_norm": 0.031327299773693085,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3280606269836426,
      "step": 12564
    },
    {
      "epoch": 0.5983809523809523,
      "grad_norm": 0.025896644219756126,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345973491668701,
      "step": 12566
    },
    {
      "epoch": 0.5984761904761905,
      "grad_norm": 0.02605678141117096,
      "learning_rate": 0.024000000208616257,
      "loss": 2.388899803161621,
      "step": 12568
    },
    {
      "epoch": 0.5985714285714285,
      "grad_norm": 0.031516142189502716,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345851421356201,
      "step": 12570
    },
    {
      "epoch": 0.5986666666666667,
      "grad_norm": 0.026597822085022926,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3399815559387207,
      "step": 12572
    },
    {
      "epoch": 0.5987619047619047,
      "grad_norm": 0.025564149022102356,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3325319290161133,
      "step": 12574
    },
    {
      "epoch": 0.5988571428571429,
      "grad_norm": 0.026705164462327957,
      "learning_rate": 0.024000000208616257,
      "loss": 2.369835615158081,
      "step": 12576
    },
    {
      "epoch": 0.5989523809523809,
      "grad_norm": 0.026684381067752838,
      "learning_rate": 0.024000000208616257,
      "loss": 2.33402943611145,
      "step": 12578
    },
    {
      "epoch": 0.599047619047619,
      "grad_norm": 0.026883454993367195,
      "learning_rate": 0.024000000208616257,
      "loss": 2.344709873199463,
      "step": 12580
    },
    {
      "epoch": 0.5991428571428571,
      "grad_norm": 0.029704971238970757,
      "learning_rate": 0.024000000208616257,
      "loss": 2.354783058166504,
      "step": 12582
    },
    {
      "epoch": 0.5992380952380952,
      "grad_norm": 0.031182175502181053,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3260035514831543,
      "step": 12584
    },
    {
      "epoch": 0.5993333333333334,
      "grad_norm": 0.026243455708026886,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3362832069396973,
      "step": 12586
    },
    {
      "epoch": 0.5994285714285714,
      "grad_norm": 0.027291836217045784,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3687081336975098,
      "step": 12588
    },
    {
      "epoch": 0.5995238095238096,
      "grad_norm": 0.025836963206529617,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3225207328796387,
      "step": 12590
    },
    {
      "epoch": 0.5996190476190476,
      "grad_norm": 0.02703310176730156,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3498802185058594,
      "step": 12592
    },
    {
      "epoch": 0.5997142857142858,
      "grad_norm": 0.0267189871519804,
      "learning_rate": 0.024000000208616257,
      "loss": 2.340625286102295,
      "step": 12594
    },
    {
      "epoch": 0.5998095238095238,
      "grad_norm": 0.02759486809372902,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355551242828369,
      "step": 12596
    },
    {
      "epoch": 0.5999047619047619,
      "grad_norm": 0.02891211397945881,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3739867210388184,
      "step": 12598
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.02892109379172325,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3678574562072754,
      "step": 12600
    },
    {
      "epoch": 0.6000952380952381,
      "grad_norm": 0.028089094907045364,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3624000549316406,
      "step": 12602
    },
    {
      "epoch": 0.6001904761904762,
      "grad_norm": 0.03137904405593872,
      "learning_rate": 0.024000000208616257,
      "loss": 2.362485408782959,
      "step": 12604
    },
    {
      "epoch": 0.6002857142857143,
      "grad_norm": 0.028560757637023926,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350247859954834,
      "step": 12606
    },
    {
      "epoch": 0.6003809523809523,
      "grad_norm": 0.027531126514077187,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3453192710876465,
      "step": 12608
    },
    {
      "epoch": 0.6004761904761905,
      "grad_norm": 0.027434905990958214,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3470547199249268,
      "step": 12610
    },
    {
      "epoch": 0.6005714285714285,
      "grad_norm": 0.030104635283350945,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3538520336151123,
      "step": 12612
    },
    {
      "epoch": 0.6006666666666667,
      "grad_norm": 0.029940536245703697,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3676249980926514,
      "step": 12614
    },
    {
      "epoch": 0.6007619047619047,
      "grad_norm": 0.03274943679571152,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3707919120788574,
      "step": 12616
    },
    {
      "epoch": 0.6008571428571429,
      "grad_norm": 0.03531825914978981,
      "learning_rate": 0.024000000208616257,
      "loss": 2.339071273803711,
      "step": 12618
    },
    {
      "epoch": 0.6009523809523809,
      "grad_norm": 0.027689484879374504,
      "learning_rate": 0.024000000208616257,
      "loss": 2.358069658279419,
      "step": 12620
    },
    {
      "epoch": 0.601047619047619,
      "grad_norm": 0.025952721014618874,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3007497787475586,
      "step": 12622
    },
    {
      "epoch": 0.6011428571428571,
      "grad_norm": 0.02757319249212742,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3802051544189453,
      "step": 12624
    },
    {
      "epoch": 0.6012380952380952,
      "grad_norm": 0.025669243186712265,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3247451782226562,
      "step": 12626
    },
    {
      "epoch": 0.6013333333333334,
      "grad_norm": 0.02647377736866474,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3633780479431152,
      "step": 12628
    },
    {
      "epoch": 0.6014285714285714,
      "grad_norm": 0.027842698618769646,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3507697582244873,
      "step": 12630
    },
    {
      "epoch": 0.6015238095238096,
      "grad_norm": 0.027910031378269196,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3456008434295654,
      "step": 12632
    },
    {
      "epoch": 0.6016190476190476,
      "grad_norm": 0.02662724442780018,
      "learning_rate": 0.024000000208616257,
      "loss": 2.357271909713745,
      "step": 12634
    },
    {
      "epoch": 0.6017142857142858,
      "grad_norm": 0.02577401138842106,
      "learning_rate": 0.024000000208616257,
      "loss": 2.365009307861328,
      "step": 12636
    },
    {
      "epoch": 0.6018095238095238,
      "grad_norm": 0.030936935916543007,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3287711143493652,
      "step": 12638
    },
    {
      "epoch": 0.6019047619047619,
      "grad_norm": 0.03194577619433403,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363348960876465,
      "step": 12640
    },
    {
      "epoch": 0.602,
      "grad_norm": 0.027514800429344177,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355836868286133,
      "step": 12642
    },
    {
      "epoch": 0.6020952380952381,
      "grad_norm": 0.02590446174144745,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3483080863952637,
      "step": 12644
    },
    {
      "epoch": 0.6021904761904762,
      "grad_norm": 0.0288520697504282,
      "learning_rate": 0.024000000208616257,
      "loss": 2.357712507247925,
      "step": 12646
    },
    {
      "epoch": 0.6022857142857143,
      "grad_norm": 0.030240874737501144,
      "learning_rate": 0.024000000208616257,
      "loss": 2.369701623916626,
      "step": 12648
    },
    {
      "epoch": 0.6023809523809524,
      "grad_norm": 0.02838442102074623,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3134970664978027,
      "step": 12650
    },
    {
      "epoch": 0.6024761904761905,
      "grad_norm": 0.02775382064282894,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3728408813476562,
      "step": 12652
    },
    {
      "epoch": 0.6025714285714285,
      "grad_norm": 0.029964959248900414,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355043411254883,
      "step": 12654
    },
    {
      "epoch": 0.6026666666666667,
      "grad_norm": 0.027448218315839767,
      "learning_rate": 0.024000000208616257,
      "loss": 2.343069076538086,
      "step": 12656
    },
    {
      "epoch": 0.6027619047619047,
      "grad_norm": 0.026068510487675667,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3375322818756104,
      "step": 12658
    },
    {
      "epoch": 0.6028571428571429,
      "grad_norm": 0.02551000379025936,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3461546897888184,
      "step": 12660
    },
    {
      "epoch": 0.6029523809523809,
      "grad_norm": 0.02859029546380043,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3664181232452393,
      "step": 12662
    },
    {
      "epoch": 0.603047619047619,
      "grad_norm": 0.028291897848248482,
      "learning_rate": 0.024000000208616257,
      "loss": 2.366306781768799,
      "step": 12664
    },
    {
      "epoch": 0.6031428571428571,
      "grad_norm": 0.028434470295906067,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3201684951782227,
      "step": 12666
    },
    {
      "epoch": 0.6032380952380952,
      "grad_norm": 0.02694174088537693,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363816976547241,
      "step": 12668
    },
    {
      "epoch": 0.6033333333333334,
      "grad_norm": 0.027346139773726463,
      "learning_rate": 0.024000000208616257,
      "loss": 2.377267837524414,
      "step": 12670
    },
    {
      "epoch": 0.6034285714285714,
      "grad_norm": 0.02582586370408535,
      "learning_rate": 0.024000000208616257,
      "loss": 2.337599754333496,
      "step": 12672
    },
    {
      "epoch": 0.6035238095238096,
      "grad_norm": 0.027420490980148315,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3488059043884277,
      "step": 12674
    },
    {
      "epoch": 0.6036190476190476,
      "grad_norm": 0.026611093431711197,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3625595569610596,
      "step": 12676
    },
    {
      "epoch": 0.6037142857142858,
      "grad_norm": 0.02602340467274189,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3584866523742676,
      "step": 12678
    },
    {
      "epoch": 0.6038095238095238,
      "grad_norm": 0.02645900472998619,
      "learning_rate": 0.024000000208616257,
      "loss": 2.372117519378662,
      "step": 12680
    },
    {
      "epoch": 0.6039047619047619,
      "grad_norm": 0.02749328315258026,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3600754737854004,
      "step": 12682
    },
    {
      "epoch": 0.604,
      "grad_norm": 0.025918126106262207,
      "learning_rate": 0.024000000208616257,
      "loss": 2.365000009536743,
      "step": 12684
    },
    {
      "epoch": 0.6040952380952381,
      "grad_norm": 0.025258004665374756,
      "learning_rate": 0.024000000208616257,
      "loss": 2.360675811767578,
      "step": 12686
    },
    {
      "epoch": 0.6041904761904762,
      "grad_norm": 0.027397656813263893,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3412179946899414,
      "step": 12688
    },
    {
      "epoch": 0.6042857142857143,
      "grad_norm": 0.028736473992466927,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3601455688476562,
      "step": 12690
    },
    {
      "epoch": 0.6043809523809524,
      "grad_norm": 0.030488451942801476,
      "learning_rate": 0.024000000208616257,
      "loss": 2.381566047668457,
      "step": 12692
    },
    {
      "epoch": 0.6044761904761905,
      "grad_norm": 0.02616218663752079,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345754861831665,
      "step": 12694
    },
    {
      "epoch": 0.6045714285714285,
      "grad_norm": 0.028545774519443512,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3617336750030518,
      "step": 12696
    },
    {
      "epoch": 0.6046666666666667,
      "grad_norm": 0.026383956894278526,
      "learning_rate": 0.024000000208616257,
      "loss": 2.33538818359375,
      "step": 12698
    },
    {
      "epoch": 0.6047619047619047,
      "grad_norm": 0.02824481390416622,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3626246452331543,
      "step": 12700
    },
    {
      "epoch": 0.6048571428571429,
      "grad_norm": 0.027490301057696342,
      "learning_rate": 0.024000000208616257,
      "loss": 2.342597723007202,
      "step": 12702
    },
    {
      "epoch": 0.6049523809523809,
      "grad_norm": 0.026940977200865746,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3731257915496826,
      "step": 12704
    },
    {
      "epoch": 0.6050476190476191,
      "grad_norm": 0.030284637585282326,
      "learning_rate": 0.024000000208616257,
      "loss": 2.318316698074341,
      "step": 12706
    },
    {
      "epoch": 0.6051428571428571,
      "grad_norm": 0.03061310574412346,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3584399223327637,
      "step": 12708
    },
    {
      "epoch": 0.6052380952380952,
      "grad_norm": 0.029326634481549263,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3292131423950195,
      "step": 12710
    },
    {
      "epoch": 0.6053333333333333,
      "grad_norm": 0.02877846732735634,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338799476623535,
      "step": 12712
    },
    {
      "epoch": 0.6054285714285714,
      "grad_norm": 0.02623998560011387,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3442955017089844,
      "step": 12714
    },
    {
      "epoch": 0.6055238095238096,
      "grad_norm": 0.02787717618048191,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3518052101135254,
      "step": 12716
    },
    {
      "epoch": 0.6056190476190476,
      "grad_norm": 0.028606202453374863,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3512685298919678,
      "step": 12718
    },
    {
      "epoch": 0.6057142857142858,
      "grad_norm": 0.025832900777459145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.340134620666504,
      "step": 12720
    },
    {
      "epoch": 0.6058095238095238,
      "grad_norm": 0.027487386018037796,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3495748043060303,
      "step": 12722
    },
    {
      "epoch": 0.605904761904762,
      "grad_norm": 0.026509759947657585,
      "learning_rate": 0.024000000208616257,
      "loss": 2.351602792739868,
      "step": 12724
    },
    {
      "epoch": 0.606,
      "grad_norm": 0.025882676243782043,
      "learning_rate": 0.024000000208616257,
      "loss": 2.337894916534424,
      "step": 12726
    },
    {
      "epoch": 0.6060952380952381,
      "grad_norm": 0.029846223071217537,
      "learning_rate": 0.024000000208616257,
      "loss": 2.351273536682129,
      "step": 12728
    },
    {
      "epoch": 0.6061904761904762,
      "grad_norm": 0.026483407244086266,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3457107543945312,
      "step": 12730
    },
    {
      "epoch": 0.6062857142857143,
      "grad_norm": 0.02559743821620941,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350172519683838,
      "step": 12732
    },
    {
      "epoch": 0.6063809523809524,
      "grad_norm": 0.026274321600794792,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338510513305664,
      "step": 12734
    },
    {
      "epoch": 0.6064761904761905,
      "grad_norm": 0.026931939646601677,
      "learning_rate": 0.024000000208616257,
      "loss": 2.32676362991333,
      "step": 12736
    },
    {
      "epoch": 0.6065714285714285,
      "grad_norm": 0.0261532012373209,
      "learning_rate": 0.024000000208616257,
      "loss": 2.368873119354248,
      "step": 12738
    },
    {
      "epoch": 0.6066666666666667,
      "grad_norm": 0.02804437093436718,
      "learning_rate": 0.024000000208616257,
      "loss": 2.364927291870117,
      "step": 12740
    },
    {
      "epoch": 0.6067619047619047,
      "grad_norm": 0.02654789388179779,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350320816040039,
      "step": 12742
    },
    {
      "epoch": 0.6068571428571429,
      "grad_norm": 0.028286196291446686,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3510255813598633,
      "step": 12744
    },
    {
      "epoch": 0.6069523809523809,
      "grad_norm": 0.027663538232445717,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3475446701049805,
      "step": 12746
    },
    {
      "epoch": 0.6070476190476191,
      "grad_norm": 0.026444604620337486,
      "learning_rate": 0.024000000208616257,
      "loss": 2.351611614227295,
      "step": 12748
    },
    {
      "epoch": 0.6071428571428571,
      "grad_norm": 0.02652369998395443,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338296890258789,
      "step": 12750
    },
    {
      "epoch": 0.6072380952380952,
      "grad_norm": 0.027506934478878975,
      "learning_rate": 0.024000000208616257,
      "loss": 2.326784610748291,
      "step": 12752
    },
    {
      "epoch": 0.6073333333333333,
      "grad_norm": 0.026085510849952698,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3528716564178467,
      "step": 12754
    },
    {
      "epoch": 0.6074285714285714,
      "grad_norm": 0.025778600946068764,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3453001976013184,
      "step": 12756
    },
    {
      "epoch": 0.6075238095238096,
      "grad_norm": 0.025905203074216843,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3546667098999023,
      "step": 12758
    },
    {
      "epoch": 0.6076190476190476,
      "grad_norm": 0.02686414308845997,
      "learning_rate": 0.024000000208616257,
      "loss": 2.35843563079834,
      "step": 12760
    },
    {
      "epoch": 0.6077142857142858,
      "grad_norm": 0.026894737035036087,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3670802116394043,
      "step": 12762
    },
    {
      "epoch": 0.6078095238095238,
      "grad_norm": 0.026996105909347534,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3344674110412598,
      "step": 12764
    },
    {
      "epoch": 0.607904761904762,
      "grad_norm": 0.03081545978784561,
      "learning_rate": 0.024000000208616257,
      "loss": 2.364081859588623,
      "step": 12766
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.02665305882692337,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3721835613250732,
      "step": 12768
    },
    {
      "epoch": 0.6080952380952381,
      "grad_norm": 0.026531822979450226,
      "learning_rate": 0.024000000208616257,
      "loss": 2.32822322845459,
      "step": 12770
    },
    {
      "epoch": 0.6081904761904762,
      "grad_norm": 0.02942500077188015,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3618335723876953,
      "step": 12772
    },
    {
      "epoch": 0.6082857142857143,
      "grad_norm": 0.02596276067197323,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3395001888275146,
      "step": 12774
    },
    {
      "epoch": 0.6083809523809524,
      "grad_norm": 0.02678365632891655,
      "learning_rate": 0.024000000208616257,
      "loss": 2.359920024871826,
      "step": 12776
    },
    {
      "epoch": 0.6084761904761905,
      "grad_norm": 0.02756374143064022,
      "learning_rate": 0.024000000208616257,
      "loss": 2.365406036376953,
      "step": 12778
    },
    {
      "epoch": 0.6085714285714285,
      "grad_norm": 0.02714204415678978,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3737735748291016,
      "step": 12780
    },
    {
      "epoch": 0.6086666666666667,
      "grad_norm": 0.02816883660852909,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3572001457214355,
      "step": 12782
    },
    {
      "epoch": 0.6087619047619047,
      "grad_norm": 0.02875353768467903,
      "learning_rate": 0.024000000208616257,
      "loss": 2.344691276550293,
      "step": 12784
    },
    {
      "epoch": 0.6088571428571429,
      "grad_norm": 0.02732047811150551,
      "learning_rate": 0.024000000208616257,
      "loss": 2.365736961364746,
      "step": 12786
    },
    {
      "epoch": 0.6089523809523809,
      "grad_norm": 0.026692450046539307,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3500590324401855,
      "step": 12788
    },
    {
      "epoch": 0.6090476190476191,
      "grad_norm": 0.029871828854084015,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3860092163085938,
      "step": 12790
    },
    {
      "epoch": 0.6091428571428571,
      "grad_norm": 0.02608831226825714,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3539295196533203,
      "step": 12792
    },
    {
      "epoch": 0.6092380952380952,
      "grad_norm": 0.027160095050930977,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3473753929138184,
      "step": 12794
    },
    {
      "epoch": 0.6093333333333333,
      "grad_norm": 0.027485916391015053,
      "learning_rate": 0.024000000208616257,
      "loss": 2.360283374786377,
      "step": 12796
    },
    {
      "epoch": 0.6094285714285714,
      "grad_norm": 0.032361581921577454,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355602741241455,
      "step": 12798
    },
    {
      "epoch": 0.6095238095238096,
      "grad_norm": 0.03563147038221359,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3466663360595703,
      "step": 12800
    },
    {
      "epoch": 0.6096190476190476,
      "grad_norm": 0.02916448749601841,
      "learning_rate": 0.024000000208616257,
      "loss": 2.376577377319336,
      "step": 12802
    },
    {
      "epoch": 0.6097142857142858,
      "grad_norm": 0.028139695525169373,
      "learning_rate": 0.024000000208616257,
      "loss": 2.329564094543457,
      "step": 12804
    },
    {
      "epoch": 0.6098095238095238,
      "grad_norm": 0.02739323489367962,
      "learning_rate": 0.024000000208616257,
      "loss": 2.34096097946167,
      "step": 12806
    },
    {
      "epoch": 0.609904761904762,
      "grad_norm": 0.02622041665017605,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3497166633605957,
      "step": 12808
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.02889302372932434,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3660449981689453,
      "step": 12810
    },
    {
      "epoch": 0.6100952380952381,
      "grad_norm": 0.029785845428705215,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3726117610931396,
      "step": 12812
    },
    {
      "epoch": 0.6101904761904762,
      "grad_norm": 0.028419960290193558,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3291311264038086,
      "step": 12814
    },
    {
      "epoch": 0.6102857142857143,
      "grad_norm": 0.02635877951979637,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3412978649139404,
      "step": 12816
    },
    {
      "epoch": 0.6103809523809524,
      "grad_norm": 0.027006693184375763,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3541855812072754,
      "step": 12818
    },
    {
      "epoch": 0.6104761904761905,
      "grad_norm": 0.027454867959022522,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3455309867858887,
      "step": 12820
    },
    {
      "epoch": 0.6105714285714285,
      "grad_norm": 0.0309754665941,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3741743564605713,
      "step": 12822
    },
    {
      "epoch": 0.6106666666666667,
      "grad_norm": 0.026904497295618057,
      "learning_rate": 0.024000000208616257,
      "loss": 2.343388080596924,
      "step": 12824
    },
    {
      "epoch": 0.6107619047619047,
      "grad_norm": 0.027747489511966705,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363219976425171,
      "step": 12826
    },
    {
      "epoch": 0.6108571428571429,
      "grad_norm": 0.026881687343120575,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3715312480926514,
      "step": 12828
    },
    {
      "epoch": 0.6109523809523809,
      "grad_norm": 0.02649783343076706,
      "learning_rate": 0.024000000208616257,
      "loss": 2.376107692718506,
      "step": 12830
    },
    {
      "epoch": 0.6110476190476191,
      "grad_norm": 0.02634841948747635,
      "learning_rate": 0.024000000208616257,
      "loss": 2.361506938934326,
      "step": 12832
    },
    {
      "epoch": 0.6111428571428571,
      "grad_norm": 0.025953246280550957,
      "learning_rate": 0.024000000208616257,
      "loss": 2.334240436553955,
      "step": 12834
    },
    {
      "epoch": 0.6112380952380952,
      "grad_norm": 0.030032964423298836,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3238658905029297,
      "step": 12836
    },
    {
      "epoch": 0.6113333333333333,
      "grad_norm": 0.03030177392065525,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3534207344055176,
      "step": 12838
    },
    {
      "epoch": 0.6114285714285714,
      "grad_norm": 0.02715814858675003,
      "learning_rate": 0.024000000208616257,
      "loss": 2.328643321990967,
      "step": 12840
    },
    {
      "epoch": 0.6115238095238095,
      "grad_norm": 0.026635926216840744,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3326945304870605,
      "step": 12842
    },
    {
      "epoch": 0.6116190476190476,
      "grad_norm": 0.026586832478642464,
      "learning_rate": 0.024000000208616257,
      "loss": 2.325711727142334,
      "step": 12844
    },
    {
      "epoch": 0.6117142857142858,
      "grad_norm": 0.026076599955558777,
      "learning_rate": 0.024000000208616257,
      "loss": 2.33970308303833,
      "step": 12846
    },
    {
      "epoch": 0.6118095238095238,
      "grad_norm": 0.027399858459830284,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3499832153320312,
      "step": 12848
    },
    {
      "epoch": 0.611904761904762,
      "grad_norm": 0.028265420347452164,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3428902626037598,
      "step": 12850
    },
    {
      "epoch": 0.612,
      "grad_norm": 0.03158644586801529,
      "learning_rate": 0.024000000208616257,
      "loss": 2.348665952682495,
      "step": 12852
    },
    {
      "epoch": 0.6120952380952381,
      "grad_norm": 0.031958360224962234,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345581531524658,
      "step": 12854
    },
    {
      "epoch": 0.6121904761904762,
      "grad_norm": 0.028716005384922028,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3431296348571777,
      "step": 12856
    },
    {
      "epoch": 0.6122857142857143,
      "grad_norm": 0.027855079621076584,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3532955646514893,
      "step": 12858
    },
    {
      "epoch": 0.6123809523809524,
      "grad_norm": 0.02773091569542885,
      "learning_rate": 0.024000000208616257,
      "loss": 2.309814929962158,
      "step": 12860
    },
    {
      "epoch": 0.6124761904761905,
      "grad_norm": 0.026979560032486916,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3610196113586426,
      "step": 12862
    },
    {
      "epoch": 0.6125714285714285,
      "grad_norm": 0.02647310122847557,
      "learning_rate": 0.024000000208616257,
      "loss": 2.393610715866089,
      "step": 12864
    },
    {
      "epoch": 0.6126666666666667,
      "grad_norm": 0.0261995792388916,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3271520137786865,
      "step": 12866
    },
    {
      "epoch": 0.6127619047619047,
      "grad_norm": 0.02581246942281723,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356947422027588,
      "step": 12868
    },
    {
      "epoch": 0.6128571428571429,
      "grad_norm": 0.02567010186612606,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3754336833953857,
      "step": 12870
    },
    {
      "epoch": 0.6129523809523809,
      "grad_norm": 0.02575204335153103,
      "learning_rate": 0.024000000208616257,
      "loss": 2.33455228805542,
      "step": 12872
    },
    {
      "epoch": 0.6130476190476191,
      "grad_norm": 0.026317493990063667,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3378145694732666,
      "step": 12874
    },
    {
      "epoch": 0.6131428571428571,
      "grad_norm": 0.02593592368066311,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3502063751220703,
      "step": 12876
    },
    {
      "epoch": 0.6132380952380952,
      "grad_norm": 0.02702093869447708,
      "learning_rate": 0.024000000208616257,
      "loss": 2.327630043029785,
      "step": 12878
    },
    {
      "epoch": 0.6133333333333333,
      "grad_norm": 0.027153972536325455,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3436474800109863,
      "step": 12880
    },
    {
      "epoch": 0.6134285714285714,
      "grad_norm": 0.03182455897331238,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345731019973755,
      "step": 12882
    },
    {
      "epoch": 0.6135238095238095,
      "grad_norm": 0.029870163649320602,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3159117698669434,
      "step": 12884
    },
    {
      "epoch": 0.6136190476190476,
      "grad_norm": 0.027495993301272392,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3662161827087402,
      "step": 12886
    },
    {
      "epoch": 0.6137142857142858,
      "grad_norm": 0.0274693351238966,
      "learning_rate": 0.024000000208616257,
      "loss": 2.352544069290161,
      "step": 12888
    },
    {
      "epoch": 0.6138095238095238,
      "grad_norm": 0.026357349008321762,
      "learning_rate": 0.024000000208616257,
      "loss": 2.339498996734619,
      "step": 12890
    },
    {
      "epoch": 0.613904761904762,
      "grad_norm": 0.028688982129096985,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3622140884399414,
      "step": 12892
    },
    {
      "epoch": 0.614,
      "grad_norm": 0.027938995510339737,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3730854988098145,
      "step": 12894
    },
    {
      "epoch": 0.6140952380952381,
      "grad_norm": 0.02657589316368103,
      "learning_rate": 0.024000000208616257,
      "loss": 2.358088970184326,
      "step": 12896
    },
    {
      "epoch": 0.6141904761904762,
      "grad_norm": 0.026451680809259415,
      "learning_rate": 0.024000000208616257,
      "loss": 2.342700958251953,
      "step": 12898
    },
    {
      "epoch": 0.6142857142857143,
      "grad_norm": 0.03307356685400009,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3343896865844727,
      "step": 12900
    },
    {
      "epoch": 0.6143809523809524,
      "grad_norm": 0.029267994686961174,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3502044677734375,
      "step": 12902
    },
    {
      "epoch": 0.6144761904761905,
      "grad_norm": 0.02632918581366539,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3256356716156006,
      "step": 12904
    },
    {
      "epoch": 0.6145714285714285,
      "grad_norm": 0.028233729302883148,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338864803314209,
      "step": 12906
    },
    {
      "epoch": 0.6146666666666667,
      "grad_norm": 0.027238944545388222,
      "learning_rate": 0.024000000208616257,
      "loss": 2.343843936920166,
      "step": 12908
    },
    {
      "epoch": 0.6147619047619047,
      "grad_norm": 0.02667461521923542,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3595938682556152,
      "step": 12910
    },
    {
      "epoch": 0.6148571428571429,
      "grad_norm": 0.029039889574050903,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3457095623016357,
      "step": 12912
    },
    {
      "epoch": 0.6149523809523809,
      "grad_norm": 0.025801828131079674,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3462345600128174,
      "step": 12914
    },
    {
      "epoch": 0.6150476190476191,
      "grad_norm": 0.028681671246886253,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3420000076293945,
      "step": 12916
    },
    {
      "epoch": 0.6151428571428571,
      "grad_norm": 0.026231132447719574,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3186867237091064,
      "step": 12918
    },
    {
      "epoch": 0.6152380952380953,
      "grad_norm": 0.02707158774137497,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3502004146575928,
      "step": 12920
    },
    {
      "epoch": 0.6153333333333333,
      "grad_norm": 0.02682129293680191,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3260366916656494,
      "step": 12922
    },
    {
      "epoch": 0.6154285714285714,
      "grad_norm": 0.02738034352660179,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3354430198669434,
      "step": 12924
    },
    {
      "epoch": 0.6155238095238095,
      "grad_norm": 0.02777954936027527,
      "learning_rate": 0.024000000208616257,
      "loss": 2.327681064605713,
      "step": 12926
    },
    {
      "epoch": 0.6156190476190476,
      "grad_norm": 0.02631993778049946,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3564624786376953,
      "step": 12928
    },
    {
      "epoch": 0.6157142857142858,
      "grad_norm": 0.027443071827292442,
      "learning_rate": 0.024000000208616257,
      "loss": 2.33138108253479,
      "step": 12930
    },
    {
      "epoch": 0.6158095238095238,
      "grad_norm": 0.02753680758178234,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3619441986083984,
      "step": 12932
    },
    {
      "epoch": 0.615904761904762,
      "grad_norm": 0.027325978502631187,
      "learning_rate": 0.024000000208616257,
      "loss": 2.341294288635254,
      "step": 12934
    },
    {
      "epoch": 0.616,
      "grad_norm": 0.027930129319429398,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3529326915740967,
      "step": 12936
    },
    {
      "epoch": 0.6160952380952381,
      "grad_norm": 0.027044814079999924,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338104486465454,
      "step": 12938
    },
    {
      "epoch": 0.6161904761904762,
      "grad_norm": 0.027509864419698715,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3389954566955566,
      "step": 12940
    },
    {
      "epoch": 0.6162857142857143,
      "grad_norm": 0.02752762846648693,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3171157836914062,
      "step": 12942
    },
    {
      "epoch": 0.6163809523809524,
      "grad_norm": 0.026168687269091606,
      "learning_rate": 0.024000000208616257,
      "loss": 2.327883243560791,
      "step": 12944
    },
    {
      "epoch": 0.6164761904761905,
      "grad_norm": 0.03076166659593582,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3420166969299316,
      "step": 12946
    },
    {
      "epoch": 0.6165714285714285,
      "grad_norm": 0.028391912579536438,
      "learning_rate": 0.024000000208616257,
      "loss": 2.321561813354492,
      "step": 12948
    },
    {
      "epoch": 0.6166666666666667,
      "grad_norm": 0.028386501595377922,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3515915870666504,
      "step": 12950
    },
    {
      "epoch": 0.6167619047619047,
      "grad_norm": 0.029425479471683502,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3704466819763184,
      "step": 12952
    },
    {
      "epoch": 0.6168571428571429,
      "grad_norm": 0.027343671768903732,
      "learning_rate": 0.024000000208616257,
      "loss": 2.329987049102783,
      "step": 12954
    },
    {
      "epoch": 0.6169523809523809,
      "grad_norm": 0.028418753296136856,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3359551429748535,
      "step": 12956
    },
    {
      "epoch": 0.6170476190476191,
      "grad_norm": 0.029960842803120613,
      "learning_rate": 0.024000000208616257,
      "loss": 2.340059757232666,
      "step": 12958
    },
    {
      "epoch": 0.6171428571428571,
      "grad_norm": 0.028976187109947205,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3226122856140137,
      "step": 12960
    },
    {
      "epoch": 0.6172380952380953,
      "grad_norm": 0.02593802660703659,
      "learning_rate": 0.024000000208616257,
      "loss": 2.336517333984375,
      "step": 12962
    },
    {
      "epoch": 0.6173333333333333,
      "grad_norm": 0.026934603229165077,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3462486267089844,
      "step": 12964
    },
    {
      "epoch": 0.6174285714285714,
      "grad_norm": 0.028260285034775734,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3395333290100098,
      "step": 12966
    },
    {
      "epoch": 0.6175238095238095,
      "grad_norm": 0.02643335610628128,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3279905319213867,
      "step": 12968
    },
    {
      "epoch": 0.6176190476190476,
      "grad_norm": 0.026872986927628517,
      "learning_rate": 0.024000000208616257,
      "loss": 2.347397804260254,
      "step": 12970
    },
    {
      "epoch": 0.6177142857142857,
      "grad_norm": 0.028338907286524773,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3228728771209717,
      "step": 12972
    },
    {
      "epoch": 0.6178095238095238,
      "grad_norm": 0.030326539650559425,
      "learning_rate": 0.024000000208616257,
      "loss": 2.339743137359619,
      "step": 12974
    },
    {
      "epoch": 0.617904761904762,
      "grad_norm": 0.02755896933376789,
      "learning_rate": 0.024000000208616257,
      "loss": 2.335244655609131,
      "step": 12976
    },
    {
      "epoch": 0.618,
      "grad_norm": 0.026392323896288872,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3412833213806152,
      "step": 12978
    },
    {
      "epoch": 0.6180952380952381,
      "grad_norm": 0.02864685282111168,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2883570194244385,
      "step": 12980
    },
    {
      "epoch": 0.6181904761904762,
      "grad_norm": 0.027619389817118645,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3382568359375,
      "step": 12982
    },
    {
      "epoch": 0.6182857142857143,
      "grad_norm": 0.02893819659948349,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3461503982543945,
      "step": 12984
    },
    {
      "epoch": 0.6183809523809524,
      "grad_norm": 0.027293214574456215,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3160572052001953,
      "step": 12986
    },
    {
      "epoch": 0.6184761904761905,
      "grad_norm": 0.031480368226766586,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3249192237854004,
      "step": 12988
    },
    {
      "epoch": 0.6185714285714285,
      "grad_norm": 0.030077476054430008,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3249287605285645,
      "step": 12990
    },
    {
      "epoch": 0.6186666666666667,
      "grad_norm": 0.028584914281964302,
      "learning_rate": 0.024000000208616257,
      "loss": 2.328068971633911,
      "step": 12992
    },
    {
      "epoch": 0.6187619047619047,
      "grad_norm": 0.028343742713332176,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3296539783477783,
      "step": 12994
    },
    {
      "epoch": 0.6188571428571429,
      "grad_norm": 0.02689795382320881,
      "learning_rate": 0.024000000208616257,
      "loss": 2.332882881164551,
      "step": 12996
    },
    {
      "epoch": 0.6189523809523809,
      "grad_norm": 0.029558399692177773,
      "learning_rate": 0.024000000208616257,
      "loss": 2.322068214416504,
      "step": 12998
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 0.029502589255571365,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3345022201538086,
      "step": 13000
    },
    {
      "epoch": 0.6191428571428571,
      "grad_norm": 0.02676752395927906,
      "learning_rate": 0.024000000208616257,
      "loss": 2.343841791152954,
      "step": 13002
    },
    {
      "epoch": 0.6192380952380953,
      "grad_norm": 0.026089809834957123,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3298449516296387,
      "step": 13004
    },
    {
      "epoch": 0.6193333333333333,
      "grad_norm": 0.027594290673732758,
      "learning_rate": 0.024000000208616257,
      "loss": 2.321037769317627,
      "step": 13006
    },
    {
      "epoch": 0.6194285714285714,
      "grad_norm": 0.02901851199567318,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3264694213867188,
      "step": 13008
    },
    {
      "epoch": 0.6195238095238095,
      "grad_norm": 0.028414925560355186,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3257908821105957,
      "step": 13010
    },
    {
      "epoch": 0.6196190476190476,
      "grad_norm": 0.02687002532184124,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3583552837371826,
      "step": 13012
    },
    {
      "epoch": 0.6197142857142857,
      "grad_norm": 0.025698501616716385,
      "learning_rate": 0.024000000208616257,
      "loss": 2.316253185272217,
      "step": 13014
    },
    {
      "epoch": 0.6198095238095238,
      "grad_norm": 0.02658708021044731,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3366281986236572,
      "step": 13016
    },
    {
      "epoch": 0.619904761904762,
      "grad_norm": 0.026459945365786552,
      "learning_rate": 0.024000000208616257,
      "loss": 2.335707664489746,
      "step": 13018
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.026817796751856804,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3143582344055176,
      "step": 13020
    },
    {
      "epoch": 0.6200952380952381,
      "grad_norm": 0.028772952035069466,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3484435081481934,
      "step": 13022
    },
    {
      "epoch": 0.6201904761904762,
      "grad_norm": 0.025387994945049286,
      "learning_rate": 0.024000000208616257,
      "loss": 2.332064151763916,
      "step": 13024
    },
    {
      "epoch": 0.6202857142857143,
      "grad_norm": 0.02666841819882393,
      "learning_rate": 0.024000000208616257,
      "loss": 2.332973003387451,
      "step": 13026
    },
    {
      "epoch": 0.6203809523809524,
      "grad_norm": 0.02625969797372818,
      "learning_rate": 0.024000000208616257,
      "loss": 2.352984666824341,
      "step": 13028
    },
    {
      "epoch": 0.6204761904761905,
      "grad_norm": 0.0278334841132164,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3423306941986084,
      "step": 13030
    },
    {
      "epoch": 0.6205714285714286,
      "grad_norm": 0.025667568668723106,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3425769805908203,
      "step": 13032
    },
    {
      "epoch": 0.6206666666666667,
      "grad_norm": 0.026157086715102196,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356435775756836,
      "step": 13034
    },
    {
      "epoch": 0.6207619047619047,
      "grad_norm": 0.025584029033780098,
      "learning_rate": 0.024000000208616257,
      "loss": 2.359267234802246,
      "step": 13036
    },
    {
      "epoch": 0.6208571428571429,
      "grad_norm": 0.025980733335018158,
      "learning_rate": 0.024000000208616257,
      "loss": 2.339167594909668,
      "step": 13038
    },
    {
      "epoch": 0.6209523809523809,
      "grad_norm": 0.028092119842767715,
      "learning_rate": 0.024000000208616257,
      "loss": 2.358917713165283,
      "step": 13040
    },
    {
      "epoch": 0.6210476190476191,
      "grad_norm": 0.026068884879350662,
      "learning_rate": 0.024000000208616257,
      "loss": 2.334533929824829,
      "step": 13042
    },
    {
      "epoch": 0.6211428571428571,
      "grad_norm": 0.03022782877087593,
      "learning_rate": 0.024000000208616257,
      "loss": 2.316830635070801,
      "step": 13044
    },
    {
      "epoch": 0.6212380952380953,
      "grad_norm": 0.03148612752556801,
      "learning_rate": 0.024000000208616257,
      "loss": 2.34352970123291,
      "step": 13046
    },
    {
      "epoch": 0.6213333333333333,
      "grad_norm": 0.029063230380415916,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3271143436431885,
      "step": 13048
    },
    {
      "epoch": 0.6214285714285714,
      "grad_norm": 0.02932097762823105,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3287220001220703,
      "step": 13050
    },
    {
      "epoch": 0.6215238095238095,
      "grad_norm": 0.035525739192962646,
      "learning_rate": 0.024000000208616257,
      "loss": 2.337205410003662,
      "step": 13052
    },
    {
      "epoch": 0.6216190476190476,
      "grad_norm": 0.03037656471133232,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3388869762420654,
      "step": 13054
    },
    {
      "epoch": 0.6217142857142857,
      "grad_norm": 0.02571563981473446,
      "learning_rate": 0.024000000208616257,
      "loss": 2.332021713256836,
      "step": 13056
    },
    {
      "epoch": 0.6218095238095238,
      "grad_norm": 0.0259187500923872,
      "learning_rate": 0.024000000208616257,
      "loss": 2.35286808013916,
      "step": 13058
    },
    {
      "epoch": 0.621904761904762,
      "grad_norm": 0.0266632828861475,
      "learning_rate": 0.024000000208616257,
      "loss": 2.331009864807129,
      "step": 13060
    },
    {
      "epoch": 0.622,
      "grad_norm": 0.025708045810461044,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3289949893951416,
      "step": 13062
    },
    {
      "epoch": 0.6220952380952381,
      "grad_norm": 0.032117582857608795,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3491506576538086,
      "step": 13064
    },
    {
      "epoch": 0.6221904761904762,
      "grad_norm": 0.029229093343019485,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3463845252990723,
      "step": 13066
    },
    {
      "epoch": 0.6222857142857143,
      "grad_norm": 0.02686072327196598,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350132465362549,
      "step": 13068
    },
    {
      "epoch": 0.6223809523809524,
      "grad_norm": 0.025928467512130737,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3200888633728027,
      "step": 13070
    },
    {
      "epoch": 0.6224761904761905,
      "grad_norm": 0.026826830580830574,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3480591773986816,
      "step": 13072
    },
    {
      "epoch": 0.6225714285714286,
      "grad_norm": 0.026716923341155052,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3303568363189697,
      "step": 13074
    },
    {
      "epoch": 0.6226666666666667,
      "grad_norm": 0.025580182671546936,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338381052017212,
      "step": 13076
    },
    {
      "epoch": 0.6227619047619047,
      "grad_norm": 0.026279643177986145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.352631092071533,
      "step": 13078
    },
    {
      "epoch": 0.6228571428571429,
      "grad_norm": 0.02724381536245346,
      "learning_rate": 0.024000000208616257,
      "loss": 2.327852725982666,
      "step": 13080
    },
    {
      "epoch": 0.6229523809523809,
      "grad_norm": 0.029293382540345192,
      "learning_rate": 0.024000000208616257,
      "loss": 2.339473247528076,
      "step": 13082
    },
    {
      "epoch": 0.6230476190476191,
      "grad_norm": 0.03008410520851612,
      "learning_rate": 0.024000000208616257,
      "loss": 2.333244800567627,
      "step": 13084
    },
    {
      "epoch": 0.6231428571428571,
      "grad_norm": 0.026008648797869682,
      "learning_rate": 0.024000000208616257,
      "loss": 2.333367347717285,
      "step": 13086
    },
    {
      "epoch": 0.6232380952380953,
      "grad_norm": 0.03380769491195679,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338939666748047,
      "step": 13088
    },
    {
      "epoch": 0.6233333333333333,
      "grad_norm": 0.02699250727891922,
      "learning_rate": 0.024000000208616257,
      "loss": 2.348830223083496,
      "step": 13090
    },
    {
      "epoch": 0.6234285714285714,
      "grad_norm": 0.02783210389316082,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3402791023254395,
      "step": 13092
    },
    {
      "epoch": 0.6235238095238095,
      "grad_norm": 0.030070703476667404,
      "learning_rate": 0.024000000208616257,
      "loss": 2.329465627670288,
      "step": 13094
    },
    {
      "epoch": 0.6236190476190476,
      "grad_norm": 0.026239557191729546,
      "learning_rate": 0.024000000208616257,
      "loss": 2.315317153930664,
      "step": 13096
    },
    {
      "epoch": 0.6237142857142857,
      "grad_norm": 0.028721507638692856,
      "learning_rate": 0.024000000208616257,
      "loss": 2.331007957458496,
      "step": 13098
    },
    {
      "epoch": 0.6238095238095238,
      "grad_norm": 0.02645009569823742,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3539180755615234,
      "step": 13100
    },
    {
      "epoch": 0.6239047619047619,
      "grad_norm": 0.02669631876051426,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3314852714538574,
      "step": 13102
    },
    {
      "epoch": 0.624,
      "grad_norm": 0.02788078598678112,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356544017791748,
      "step": 13104
    },
    {
      "epoch": 0.6240952380952381,
      "grad_norm": 0.037861257791519165,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3444509506225586,
      "step": 13106
    },
    {
      "epoch": 0.6241904761904762,
      "grad_norm": 0.035712823271751404,
      "learning_rate": 0.024000000208616257,
      "loss": 2.342768430709839,
      "step": 13108
    },
    {
      "epoch": 0.6242857142857143,
      "grad_norm": 0.030714932829141617,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3588836193084717,
      "step": 13110
    },
    {
      "epoch": 0.6243809523809524,
      "grad_norm": 0.034284692257642746,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3360719680786133,
      "step": 13112
    },
    {
      "epoch": 0.6244761904761905,
      "grad_norm": 0.03196863830089569,
      "learning_rate": 0.024000000208616257,
      "loss": 2.315387725830078,
      "step": 13114
    },
    {
      "epoch": 0.6245714285714286,
      "grad_norm": 0.028304772451519966,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363865852355957,
      "step": 13116
    },
    {
      "epoch": 0.6246666666666667,
      "grad_norm": 0.027470067143440247,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356545925140381,
      "step": 13118
    },
    {
      "epoch": 0.6247619047619047,
      "grad_norm": 0.02636815793812275,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3395042419433594,
      "step": 13120
    },
    {
      "epoch": 0.6248571428571429,
      "grad_norm": 0.027767973020672798,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3665003776550293,
      "step": 13122
    },
    {
      "epoch": 0.6249523809523809,
      "grad_norm": 0.02655799314379692,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3184139728546143,
      "step": 13124
    },
    {
      "epoch": 0.6250476190476191,
      "grad_norm": 0.027806339785456657,
      "learning_rate": 0.024000000208616257,
      "loss": 2.334259510040283,
      "step": 13126
    },
    {
      "epoch": 0.6251428571428571,
      "grad_norm": 0.02665984444320202,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3350791931152344,
      "step": 13128
    },
    {
      "epoch": 0.6252380952380953,
      "grad_norm": 0.02760929800570011,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3429179191589355,
      "step": 13130
    },
    {
      "epoch": 0.6253333333333333,
      "grad_norm": 0.028537962585687637,
      "learning_rate": 0.024000000208616257,
      "loss": 2.360612154006958,
      "step": 13132
    },
    {
      "epoch": 0.6254285714285714,
      "grad_norm": 0.02720610424876213,
      "learning_rate": 0.024000000208616257,
      "loss": 2.351634979248047,
      "step": 13134
    },
    {
      "epoch": 0.6255238095238095,
      "grad_norm": 0.026047730818390846,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3387956619262695,
      "step": 13136
    },
    {
      "epoch": 0.6256190476190476,
      "grad_norm": 0.026753317564725876,
      "learning_rate": 0.024000000208616257,
      "loss": 2.380791187286377,
      "step": 13138
    },
    {
      "epoch": 0.6257142857142857,
      "grad_norm": 0.024852033704519272,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338405132293701,
      "step": 13140
    },
    {
      "epoch": 0.6258095238095238,
      "grad_norm": 0.026996789500117302,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3497891426086426,
      "step": 13142
    },
    {
      "epoch": 0.6259047619047619,
      "grad_norm": 0.02828226238489151,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3131654262542725,
      "step": 13144
    },
    {
      "epoch": 0.626,
      "grad_norm": 0.02893942780792713,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3805785179138184,
      "step": 13146
    },
    {
      "epoch": 0.6260952380952381,
      "grad_norm": 0.02911841683089733,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3523168563842773,
      "step": 13148
    },
    {
      "epoch": 0.6261904761904762,
      "grad_norm": 0.028202375397086143,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3342268466949463,
      "step": 13150
    },
    {
      "epoch": 0.6262857142857143,
      "grad_norm": 0.026485834270715714,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2990517616271973,
      "step": 13152
    },
    {
      "epoch": 0.6263809523809524,
      "grad_norm": 0.02674563229084015,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3403029441833496,
      "step": 13154
    },
    {
      "epoch": 0.6264761904761905,
      "grad_norm": 0.02641868405044079,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3498191833496094,
      "step": 13156
    },
    {
      "epoch": 0.6265714285714286,
      "grad_norm": 0.026802299544215202,
      "learning_rate": 0.024000000208616257,
      "loss": 2.378974199295044,
      "step": 13158
    },
    {
      "epoch": 0.6266666666666667,
      "grad_norm": 0.02651944011449814,
      "learning_rate": 0.024000000208616257,
      "loss": 2.327601194381714,
      "step": 13160
    },
    {
      "epoch": 0.6267619047619047,
      "grad_norm": 0.030392687767744064,
      "learning_rate": 0.024000000208616257,
      "loss": 2.364305019378662,
      "step": 13162
    },
    {
      "epoch": 0.6268571428571429,
      "grad_norm": 0.02908659353852272,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3539438247680664,
      "step": 13164
    },
    {
      "epoch": 0.6269523809523809,
      "grad_norm": 0.026239581406116486,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3392739295959473,
      "step": 13166
    },
    {
      "epoch": 0.6270476190476191,
      "grad_norm": 0.027286497876048088,
      "learning_rate": 0.024000000208616257,
      "loss": 2.330151081085205,
      "step": 13168
    },
    {
      "epoch": 0.6271428571428571,
      "grad_norm": 0.027225591242313385,
      "learning_rate": 0.024000000208616257,
      "loss": 2.320347309112549,
      "step": 13170
    },
    {
      "epoch": 0.6272380952380953,
      "grad_norm": 0.025642985478043556,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3600943088531494,
      "step": 13172
    },
    {
      "epoch": 0.6273333333333333,
      "grad_norm": 0.02858736738562584,
      "learning_rate": 0.024000000208616257,
      "loss": 2.345975399017334,
      "step": 13174
    },
    {
      "epoch": 0.6274285714285714,
      "grad_norm": 0.028882339596748352,
      "learning_rate": 0.024000000208616257,
      "loss": 2.353102445602417,
      "step": 13176
    },
    {
      "epoch": 0.6275238095238095,
      "grad_norm": 0.025990113615989685,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3358817100524902,
      "step": 13178
    },
    {
      "epoch": 0.6276190476190476,
      "grad_norm": 0.026721809059381485,
      "learning_rate": 0.024000000208616257,
      "loss": 2.377204179763794,
      "step": 13180
    },
    {
      "epoch": 0.6277142857142857,
      "grad_norm": 0.027051951736211777,
      "learning_rate": 0.024000000208616257,
      "loss": 2.327648639678955,
      "step": 13182
    },
    {
      "epoch": 0.6278095238095238,
      "grad_norm": 0.026102595031261444,
      "learning_rate": 0.024000000208616257,
      "loss": 2.341144561767578,
      "step": 13184
    },
    {
      "epoch": 0.6279047619047619,
      "grad_norm": 0.026641016826033592,
      "learning_rate": 0.024000000208616257,
      "loss": 2.358377695083618,
      "step": 13186
    },
    {
      "epoch": 0.628,
      "grad_norm": 0.025288091972470284,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3778769969940186,
      "step": 13188
    },
    {
      "epoch": 0.628095238095238,
      "grad_norm": 0.0259805116802454,
      "learning_rate": 0.024000000208616257,
      "loss": 2.386075019836426,
      "step": 13190
    },
    {
      "epoch": 0.6281904761904762,
      "grad_norm": 0.025714056566357613,
      "learning_rate": 0.024000000208616257,
      "loss": 2.339433193206787,
      "step": 13192
    },
    {
      "epoch": 0.6282857142857143,
      "grad_norm": 0.029378948733210564,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3087551593780518,
      "step": 13194
    },
    {
      "epoch": 0.6283809523809524,
      "grad_norm": 0.030280983075499535,
      "learning_rate": 0.024000000208616257,
      "loss": 2.346682548522949,
      "step": 13196
    },
    {
      "epoch": 0.6284761904761905,
      "grad_norm": 0.029611829668283463,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356922149658203,
      "step": 13198
    },
    {
      "epoch": 0.6285714285714286,
      "grad_norm": 0.026922471821308136,
      "learning_rate": 0.024000000208616257,
      "loss": 2.334521770477295,
      "step": 13200
    },
    {
      "epoch": 0.6286666666666667,
      "grad_norm": 0.029671600088477135,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3604564666748047,
      "step": 13202
    },
    {
      "epoch": 0.6287619047619047,
      "grad_norm": 0.02674475684762001,
      "learning_rate": 0.024000000208616257,
      "loss": 2.337036609649658,
      "step": 13204
    },
    {
      "epoch": 0.6288571428571429,
      "grad_norm": 0.02634275332093239,
      "learning_rate": 0.024000000208616257,
      "loss": 2.362955093383789,
      "step": 13206
    },
    {
      "epoch": 0.6289523809523809,
      "grad_norm": 0.02904757671058178,
      "learning_rate": 0.024000000208616257,
      "loss": 2.361659526824951,
      "step": 13208
    },
    {
      "epoch": 0.6290476190476191,
      "grad_norm": 0.02698448859155178,
      "learning_rate": 0.024000000208616257,
      "loss": 2.329564332962036,
      "step": 13210
    },
    {
      "epoch": 0.6291428571428571,
      "grad_norm": 0.02842383086681366,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3728950023651123,
      "step": 13212
    },
    {
      "epoch": 0.6292380952380953,
      "grad_norm": 0.028083156794309616,
      "learning_rate": 0.024000000208616257,
      "loss": 2.362534999847412,
      "step": 13214
    },
    {
      "epoch": 0.6293333333333333,
      "grad_norm": 0.028806017711758614,
      "learning_rate": 0.024000000208616257,
      "loss": 2.377142906188965,
      "step": 13216
    },
    {
      "epoch": 0.6294285714285714,
      "grad_norm": 0.027504319325089455,
      "learning_rate": 0.024000000208616257,
      "loss": 2.336264133453369,
      "step": 13218
    },
    {
      "epoch": 0.6295238095238095,
      "grad_norm": 0.02823621965944767,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3703553676605225,
      "step": 13220
    },
    {
      "epoch": 0.6296190476190476,
      "grad_norm": 0.026188526302576065,
      "learning_rate": 0.024000000208616257,
      "loss": 2.324436902999878,
      "step": 13222
    },
    {
      "epoch": 0.6297142857142857,
      "grad_norm": 0.026743769645690918,
      "learning_rate": 0.024000000208616257,
      "loss": 2.344163417816162,
      "step": 13224
    },
    {
      "epoch": 0.6298095238095238,
      "grad_norm": 0.03134665638208389,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3394763469696045,
      "step": 13226
    },
    {
      "epoch": 0.6299047619047619,
      "grad_norm": 0.026568833738565445,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3826632499694824,
      "step": 13228
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.026243049651384354,
      "learning_rate": 0.024000000208616257,
      "loss": 2.363494873046875,
      "step": 13230
    },
    {
      "epoch": 0.630095238095238,
      "grad_norm": 0.02748039737343788,
      "learning_rate": 0.024000000208616257,
      "loss": 2.381735324859619,
      "step": 13232
    },
    {
      "epoch": 0.6301904761904762,
      "grad_norm": 0.027415545657277107,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3437297344207764,
      "step": 13234
    },
    {
      "epoch": 0.6302857142857143,
      "grad_norm": 0.02696905843913555,
      "learning_rate": 0.024000000208616257,
      "loss": 2.337087631225586,
      "step": 13236
    },
    {
      "epoch": 0.6303809523809524,
      "grad_norm": 0.02704877406358719,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355355739593506,
      "step": 13238
    },
    {
      "epoch": 0.6304761904761905,
      "grad_norm": 0.029824119061231613,
      "learning_rate": 0.024000000208616257,
      "loss": 2.387906789779663,
      "step": 13240
    },
    {
      "epoch": 0.6305714285714286,
      "grad_norm": 0.026504531502723694,
      "learning_rate": 0.024000000208616257,
      "loss": 2.34358549118042,
      "step": 13242
    },
    {
      "epoch": 0.6306666666666667,
      "grad_norm": 0.026592615991830826,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3630404472351074,
      "step": 13244
    },
    {
      "epoch": 0.6307619047619047,
      "grad_norm": 0.02601058967411518,
      "learning_rate": 0.024000000208616257,
      "loss": 2.352123260498047,
      "step": 13246
    },
    {
      "epoch": 0.6308571428571429,
      "grad_norm": 0.026258371770381927,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3554012775421143,
      "step": 13248
    },
    {
      "epoch": 0.6309523809523809,
      "grad_norm": 0.026384511962532997,
      "learning_rate": 0.024000000208616257,
      "loss": 2.359368324279785,
      "step": 13250
    },
    {
      "epoch": 0.6310476190476191,
      "grad_norm": 0.028911087661981583,
      "learning_rate": 0.024000000208616257,
      "loss": 2.346548557281494,
      "step": 13252
    },
    {
      "epoch": 0.6311428571428571,
      "grad_norm": 0.028489289805293083,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3210935592651367,
      "step": 13254
    },
    {
      "epoch": 0.6312380952380953,
      "grad_norm": 0.025476671755313873,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3518218994140625,
      "step": 13256
    },
    {
      "epoch": 0.6313333333333333,
      "grad_norm": 0.026509301736950874,
      "learning_rate": 0.024000000208616257,
      "loss": 2.355173110961914,
      "step": 13258
    },
    {
      "epoch": 0.6314285714285715,
      "grad_norm": 0.027192240580916405,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3471429347991943,
      "step": 13260
    },
    {
      "epoch": 0.6315238095238095,
      "grad_norm": 0.026260249316692352,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3483166694641113,
      "step": 13262
    },
    {
      "epoch": 0.6316190476190476,
      "grad_norm": 0.025542164221405983,
      "learning_rate": 0.024000000208616257,
      "loss": 2.339723587036133,
      "step": 13264
    },
    {
      "epoch": 0.6317142857142857,
      "grad_norm": 0.028208520263433456,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3419342041015625,
      "step": 13266
    },
    {
      "epoch": 0.6318095238095238,
      "grad_norm": 0.025465495884418488,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3200159072875977,
      "step": 13268
    },
    {
      "epoch": 0.6319047619047619,
      "grad_norm": 0.0272639412432909,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3477983474731445,
      "step": 13270
    },
    {
      "epoch": 0.632,
      "grad_norm": 0.025976436212658882,
      "learning_rate": 0.024000000208616257,
      "loss": 2.367870807647705,
      "step": 13272
    },
    {
      "epoch": 0.632095238095238,
      "grad_norm": 0.025922346860170364,
      "learning_rate": 0.024000000208616257,
      "loss": 2.342684745788574,
      "step": 13274
    },
    {
      "epoch": 0.6321904761904762,
      "grad_norm": 0.027227265760302544,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3414273262023926,
      "step": 13276
    },
    {
      "epoch": 0.6322857142857143,
      "grad_norm": 0.025883983820676804,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3567628860473633,
      "step": 13278
    },
    {
      "epoch": 0.6323809523809524,
      "grad_norm": 0.028140870854258537,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3445000648498535,
      "step": 13280
    },
    {
      "epoch": 0.6324761904761905,
      "grad_norm": 0.02623731642961502,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3552660942077637,
      "step": 13282
    },
    {
      "epoch": 0.6325714285714286,
      "grad_norm": 0.030410587787628174,
      "learning_rate": 0.024000000208616257,
      "loss": 2.329660415649414,
      "step": 13284
    },
    {
      "epoch": 0.6326666666666667,
      "grad_norm": 0.03061055578291416,
      "learning_rate": 0.024000000208616257,
      "loss": 2.341439723968506,
      "step": 13286
    },
    {
      "epoch": 0.6327619047619047,
      "grad_norm": 0.030651211738586426,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3438053131103516,
      "step": 13288
    },
    {
      "epoch": 0.6328571428571429,
      "grad_norm": 0.02685139887034893,
      "learning_rate": 0.024000000208616257,
      "loss": 2.358914375305176,
      "step": 13290
    },
    {
      "epoch": 0.6329523809523809,
      "grad_norm": 0.0263872928917408,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3717737197875977,
      "step": 13292
    },
    {
      "epoch": 0.6330476190476191,
      "grad_norm": 0.025930313393473625,
      "learning_rate": 0.024000000208616257,
      "loss": 2.335601806640625,
      "step": 13294
    },
    {
      "epoch": 0.6331428571428571,
      "grad_norm": 0.027121420949697495,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3589723110198975,
      "step": 13296
    },
    {
      "epoch": 0.6332380952380953,
      "grad_norm": 0.02665618620812893,
      "learning_rate": 0.024000000208616257,
      "loss": 2.347410202026367,
      "step": 13298
    },
    {
      "epoch": 0.6333333333333333,
      "grad_norm": 0.025451792404055595,
      "learning_rate": 0.024000000208616257,
      "loss": 2.359424591064453,
      "step": 13300
    },
    {
      "epoch": 0.6334285714285715,
      "grad_norm": 0.026443740352988243,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356213092803955,
      "step": 13302
    },
    {
      "epoch": 0.6335238095238095,
      "grad_norm": 0.026632634922862053,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3701553344726562,
      "step": 13304
    },
    {
      "epoch": 0.6336190476190476,
      "grad_norm": 0.02673833817243576,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3869645595550537,
      "step": 13306
    },
    {
      "epoch": 0.6337142857142857,
      "grad_norm": 0.03788665682077408,
      "learning_rate": 0.024000000208616257,
      "loss": 2.4009952545166016,
      "step": 13308
    },
    {
      "epoch": 0.6338095238095238,
      "grad_norm": 0.030052626505494118,
      "learning_rate": 0.024000000208616257,
      "loss": 2.334084987640381,
      "step": 13310
    },
    {
      "epoch": 0.6339047619047619,
      "grad_norm": 0.026046741753816605,
      "learning_rate": 0.024000000208616257,
      "loss": 2.369744300842285,
      "step": 13312
    },
    {
      "epoch": 0.634,
      "grad_norm": 0.02956492081284523,
      "learning_rate": 0.024000000208616257,
      "loss": 2.378357410430908,
      "step": 13314
    },
    {
      "epoch": 0.634095238095238,
      "grad_norm": 0.027855949476361275,
      "learning_rate": 0.024000000208616257,
      "loss": 2.364626407623291,
      "step": 13316
    },
    {
      "epoch": 0.6341904761904762,
      "grad_norm": 0.02710629627108574,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3548429012298584,
      "step": 13318
    },
    {
      "epoch": 0.6342857142857142,
      "grad_norm": 0.027043404057621956,
      "learning_rate": 0.024000000208616257,
      "loss": 2.349822521209717,
      "step": 13320
    },
    {
      "epoch": 0.6343809523809524,
      "grad_norm": 0.025615669786930084,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3526692390441895,
      "step": 13322
    },
    {
      "epoch": 0.6344761904761905,
      "grad_norm": 0.028077464550733566,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3619375228881836,
      "step": 13324
    },
    {
      "epoch": 0.6345714285714286,
      "grad_norm": 0.02633608691394329,
      "learning_rate": 0.024000000208616257,
      "loss": 2.370145797729492,
      "step": 13326
    },
    {
      "epoch": 0.6346666666666667,
      "grad_norm": 0.025928296148777008,
      "learning_rate": 0.024000000208616257,
      "loss": 2.359598159790039,
      "step": 13328
    },
    {
      "epoch": 0.6347619047619047,
      "grad_norm": 0.02708764560520649,
      "learning_rate": 0.024000000208616257,
      "loss": 2.346619129180908,
      "step": 13330
    },
    {
      "epoch": 0.6348571428571429,
      "grad_norm": 0.026872066780924797,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350736141204834,
      "step": 13332
    },
    {
      "epoch": 0.6349523809523809,
      "grad_norm": 0.026255780830979347,
      "learning_rate": 0.024000000208616257,
      "loss": 2.384624481201172,
      "step": 13334
    },
    {
      "epoch": 0.6350476190476191,
      "grad_norm": 0.02785901166498661,
      "learning_rate": 0.024000000208616257,
      "loss": 2.349447250366211,
      "step": 13336
    },
    {
      "epoch": 0.6351428571428571,
      "grad_norm": 0.027130229398608208,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3695218563079834,
      "step": 13338
    },
    {
      "epoch": 0.6352380952380953,
      "grad_norm": 0.02628413215279579,
      "learning_rate": 0.024000000208616257,
      "loss": 2.33630108833313,
      "step": 13340
    },
    {
      "epoch": 0.6353333333333333,
      "grad_norm": 0.025782324373722076,
      "learning_rate": 0.024000000208616257,
      "loss": 2.378018856048584,
      "step": 13342
    },
    {
      "epoch": 0.6354285714285715,
      "grad_norm": 0.025963829830288887,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3736064434051514,
      "step": 13344
    },
    {
      "epoch": 0.6355238095238095,
      "grad_norm": 0.0285969115793705,
      "learning_rate": 0.024000000208616257,
      "loss": 2.342434883117676,
      "step": 13346
    },
    {
      "epoch": 0.6356190476190476,
      "grad_norm": 0.026242051273584366,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3645787239074707,
      "step": 13348
    },
    {
      "epoch": 0.6357142857142857,
      "grad_norm": 0.027478227391839027,
      "learning_rate": 0.024000000208616257,
      "loss": 2.362149953842163,
      "step": 13350
    },
    {
      "epoch": 0.6358095238095238,
      "grad_norm": 0.031268928200006485,
      "learning_rate": 0.024000000208616257,
      "loss": 2.335200786590576,
      "step": 13352
    },
    {
      "epoch": 0.6359047619047619,
      "grad_norm": 0.03064817376434803,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3485798835754395,
      "step": 13354
    },
    {
      "epoch": 0.636,
      "grad_norm": 0.02815805934369564,
      "learning_rate": 0.024000000208616257,
      "loss": 2.360966205596924,
      "step": 13356
    },
    {
      "epoch": 0.636095238095238,
      "grad_norm": 0.028651239350438118,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3647475242614746,
      "step": 13358
    },
    {
      "epoch": 0.6361904761904762,
      "grad_norm": 0.026668919250369072,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3391761779785156,
      "step": 13360
    },
    {
      "epoch": 0.6362857142857142,
      "grad_norm": 0.027184240520000458,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3704850673675537,
      "step": 13362
    },
    {
      "epoch": 0.6363809523809524,
      "grad_norm": 0.0273677259683609,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3900303840637207,
      "step": 13364
    },
    {
      "epoch": 0.6364761904761905,
      "grad_norm": 0.026003697887063026,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3781824111938477,
      "step": 13366
    },
    {
      "epoch": 0.6365714285714286,
      "grad_norm": 0.027938317507505417,
      "learning_rate": 0.024000000208616257,
      "loss": 2.364985942840576,
      "step": 13368
    },
    {
      "epoch": 0.6366666666666667,
      "grad_norm": 0.029808413237333298,
      "learning_rate": 0.024000000208616257,
      "loss": 2.373887062072754,
      "step": 13370
    },
    {
      "epoch": 0.6367619047619048,
      "grad_norm": 0.02625058963894844,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3421859741210938,
      "step": 13372
    },
    {
      "epoch": 0.6368571428571429,
      "grad_norm": 0.028442129492759705,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3470258712768555,
      "step": 13374
    },
    {
      "epoch": 0.6369523809523809,
      "grad_norm": 0.02755608595907688,
      "learning_rate": 0.024000000208616257,
      "loss": 2.351083755493164,
      "step": 13376
    },
    {
      "epoch": 0.6370476190476191,
      "grad_norm": 0.02796061523258686,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3440046310424805,
      "step": 13378
    },
    {
      "epoch": 0.6371428571428571,
      "grad_norm": 0.025532400235533714,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3781094551086426,
      "step": 13380
    },
    {
      "epoch": 0.6372380952380953,
      "grad_norm": 0.02709917724132538,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3472657203674316,
      "step": 13382
    },
    {
      "epoch": 0.6373333333333333,
      "grad_norm": 0.026633059605956078,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3412094116210938,
      "step": 13384
    },
    {
      "epoch": 0.6374285714285715,
      "grad_norm": 0.025416644290089607,
      "learning_rate": 0.024000000208616257,
      "loss": 2.364945888519287,
      "step": 13386
    },
    {
      "epoch": 0.6375238095238095,
      "grad_norm": 0.026156600564718246,
      "learning_rate": 0.024000000208616257,
      "loss": 2.322901725769043,
      "step": 13388
    },
    {
      "epoch": 0.6376190476190476,
      "grad_norm": 0.02949116937816143,
      "learning_rate": 0.024000000208616257,
      "loss": 2.344179630279541,
      "step": 13390
    },
    {
      "epoch": 0.6377142857142857,
      "grad_norm": 0.025809064507484436,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3716988563537598,
      "step": 13392
    },
    {
      "epoch": 0.6378095238095238,
      "grad_norm": 0.02943212352693081,
      "learning_rate": 0.024000000208616257,
      "loss": 2.350942611694336,
      "step": 13394
    },
    {
      "epoch": 0.6379047619047619,
      "grad_norm": 0.029288411140441895,
      "learning_rate": 0.024000000208616257,
      "loss": 2.361762762069702,
      "step": 13396
    },
    {
      "epoch": 0.638,
      "grad_norm": 0.029567524790763855,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3429641723632812,
      "step": 13398
    },
    {
      "epoch": 0.638095238095238,
      "grad_norm": 0.030667142942547798,
      "learning_rate": 0.024000000208616257,
      "loss": 2.349834442138672,
      "step": 13400
    },
    {
      "epoch": 0.6381904761904762,
      "grad_norm": 0.0313316285610199,
      "learning_rate": 0.024000000208616257,
      "loss": 2.344661235809326,
      "step": 13402
    },
    {
      "epoch": 0.6382857142857142,
      "grad_norm": 0.028920214623212814,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3443844318389893,
      "step": 13404
    },
    {
      "epoch": 0.6383809523809524,
      "grad_norm": 0.026546861976385117,
      "learning_rate": 0.024000000208616257,
      "loss": 2.357767105102539,
      "step": 13406
    },
    {
      "epoch": 0.6384761904761905,
      "grad_norm": 0.026093361899256706,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3573570251464844,
      "step": 13408
    },
    {
      "epoch": 0.6385714285714286,
      "grad_norm": 0.026127343997359276,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3456592559814453,
      "step": 13410
    },
    {
      "epoch": 0.6386666666666667,
      "grad_norm": 0.027702340856194496,
      "learning_rate": 0.024000000208616257,
      "loss": 2.340653896331787,
      "step": 13412
    },
    {
      "epoch": 0.6387619047619048,
      "grad_norm": 0.026113569736480713,
      "learning_rate": 0.024000000208616257,
      "loss": 2.362290859222412,
      "step": 13414
    },
    {
      "epoch": 0.6388571428571429,
      "grad_norm": 0.02649441920220852,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3419318199157715,
      "step": 13416
    },
    {
      "epoch": 0.6389523809523809,
      "grad_norm": 0.02544908970594406,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3418614864349365,
      "step": 13418
    },
    {
      "epoch": 0.6390476190476191,
      "grad_norm": 0.026866288855671883,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3468430042266846,
      "step": 13420
    },
    {
      "epoch": 0.6391428571428571,
      "grad_norm": 0.02673957869410515,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3507485389709473,
      "step": 13422
    },
    {
      "epoch": 0.6392380952380953,
      "grad_norm": 0.02822943776845932,
      "learning_rate": 0.024000000208616257,
      "loss": 2.341169595718384,
      "step": 13424
    },
    {
      "epoch": 0.6393333333333333,
      "grad_norm": 0.030246516689658165,
      "learning_rate": 0.024000000208616257,
      "loss": 2.373891830444336,
      "step": 13426
    },
    {
      "epoch": 0.6394285714285715,
      "grad_norm": 0.02634945511817932,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3422586917877197,
      "step": 13428
    },
    {
      "epoch": 0.6395238095238095,
      "grad_norm": 0.02584069035947323,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3326973915100098,
      "step": 13430
    },
    {
      "epoch": 0.6396190476190476,
      "grad_norm": 0.02609315700829029,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3399550914764404,
      "step": 13432
    },
    {
      "epoch": 0.6397142857142857,
      "grad_norm": 0.03060661070048809,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3443753719329834,
      "step": 13434
    },
    {
      "epoch": 0.6398095238095238,
      "grad_norm": 0.026984723284840584,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3504090309143066,
      "step": 13436
    },
    {
      "epoch": 0.6399047619047619,
      "grad_norm": 0.027948126196861267,
      "learning_rate": 0.024000000208616257,
      "loss": 2.361325263977051,
      "step": 13438
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.028229210525751114,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3538365364074707,
      "step": 13440
    },
    {
      "epoch": 0.640095238095238,
      "grad_norm": 0.027273451909422874,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3583545684814453,
      "step": 13442
    },
    {
      "epoch": 0.6401904761904762,
      "grad_norm": 0.02593955025076866,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3626389503479004,
      "step": 13444
    },
    {
      "epoch": 0.6402857142857142,
      "grad_norm": 0.026327582076191902,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3540072441101074,
      "step": 13446
    },
    {
      "epoch": 0.6403809523809524,
      "grad_norm": 0.02532309666275978,
      "learning_rate": 0.024000000208616257,
      "loss": 2.294778823852539,
      "step": 13448
    },
    {
      "epoch": 0.6404761904761904,
      "grad_norm": 0.027379902079701424,
      "learning_rate": 0.024000000208616257,
      "loss": 2.337921142578125,
      "step": 13450
    },
    {
      "epoch": 0.6405714285714286,
      "grad_norm": 0.026512375101447105,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3442158699035645,
      "step": 13452
    },
    {
      "epoch": 0.6406666666666667,
      "grad_norm": 0.027219144627451897,
      "learning_rate": 0.024000000208616257,
      "loss": 2.361191511154175,
      "step": 13454
    },
    {
      "epoch": 0.6407619047619048,
      "grad_norm": 0.03070605918765068,
      "learning_rate": 0.024000000208616257,
      "loss": 2.356577157974243,
      "step": 13456
    },
    {
      "epoch": 0.6408571428571429,
      "grad_norm": 0.026211144402623177,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3652634620666504,
      "step": 13458
    },
    {
      "epoch": 0.6409523809523809,
      "grad_norm": 0.026318160817027092,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3347320556640625,
      "step": 13460
    },
    {
      "epoch": 0.6410476190476191,
      "grad_norm": 0.029368551447987556,
      "learning_rate": 0.024000000208616257,
      "loss": 2.33782958984375,
      "step": 13462
    },
    {
      "epoch": 0.6411428571428571,
      "grad_norm": 0.02714524045586586,
      "learning_rate": 0.024000000208616257,
      "loss": 2.374044895172119,
      "step": 13464
    },
    {
      "epoch": 0.6412380952380953,
      "grad_norm": 0.029514824971556664,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3542747497558594,
      "step": 13466
    },
    {
      "epoch": 0.6413333333333333,
      "grad_norm": 0.02812490612268448,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3201067447662354,
      "step": 13468
    },
    {
      "epoch": 0.6414285714285715,
      "grad_norm": 0.0282831359654665,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3296937942504883,
      "step": 13470
    },
    {
      "epoch": 0.6415238095238095,
      "grad_norm": 0.025226183235645294,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3231940269470215,
      "step": 13472
    },
    {
      "epoch": 0.6416190476190476,
      "grad_norm": 0.029036259278655052,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3450355529785156,
      "step": 13474
    },
    {
      "epoch": 0.6417142857142857,
      "grad_norm": 0.034304842352867126,
      "learning_rate": 0.024000000208616257,
      "loss": 2.314995288848877,
      "step": 13476
    },
    {
      "epoch": 0.6418095238095238,
      "grad_norm": 0.029277322813868523,
      "learning_rate": 0.024000000208616257,
      "loss": 2.337064266204834,
      "step": 13478
    },
    {
      "epoch": 0.6419047619047619,
      "grad_norm": 0.026804303750395775,
      "learning_rate": 0.024000000208616257,
      "loss": 2.317368984222412,
      "step": 13480
    },
    {
      "epoch": 0.642,
      "grad_norm": 0.025479692965745926,
      "learning_rate": 0.024000000208616257,
      "loss": 2.334815263748169,
      "step": 13482
    },
    {
      "epoch": 0.642095238095238,
      "grad_norm": 0.02695845067501068,
      "learning_rate": 0.024000000208616257,
      "loss": 2.374192953109741,
      "step": 13484
    },
    {
      "epoch": 0.6421904761904762,
      "grad_norm": 0.026551399379968643,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3487930297851562,
      "step": 13486
    },
    {
      "epoch": 0.6422857142857142,
      "grad_norm": 0.029500022530555725,
      "learning_rate": 0.024000000208616257,
      "loss": 2.34096097946167,
      "step": 13488
    },
    {
      "epoch": 0.6423809523809524,
      "grad_norm": 0.02590310387313366,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3620681762695312,
      "step": 13490
    },
    {
      "epoch": 0.6424761904761904,
      "grad_norm": 0.02607930824160576,
      "learning_rate": 0.024000000208616257,
      "loss": 2.352266550064087,
      "step": 13492
    },
    {
      "epoch": 0.6425714285714286,
      "grad_norm": 0.02628353051841259,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3379669189453125,
      "step": 13494
    },
    {
      "epoch": 0.6426666666666667,
      "grad_norm": 0.026915421709418297,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3292932510375977,
      "step": 13496
    },
    {
      "epoch": 0.6427619047619048,
      "grad_norm": 0.0271263737231493,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3576302528381348,
      "step": 13498
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 0.02760525606572628,
      "learning_rate": 0.024000000208616257,
      "loss": 2.324751138687134,
      "step": 13500
    },
    {
      "epoch": 0.6429523809523809,
      "grad_norm": 0.028812410309910774,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338317394256592,
      "step": 13502
    },
    {
      "epoch": 0.6430476190476191,
      "grad_norm": 0.025050228461623192,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3290839195251465,
      "step": 13504
    },
    {
      "epoch": 0.6431428571428571,
      "grad_norm": 0.02801586128771305,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3457841873168945,
      "step": 13506
    },
    {
      "epoch": 0.6432380952380953,
      "grad_norm": 0.028329478576779366,
      "learning_rate": 0.024000000208616257,
      "loss": 2.343151569366455,
      "step": 13508
    },
    {
      "epoch": 0.6433333333333333,
      "grad_norm": 0.025719739496707916,
      "learning_rate": 0.024000000208616257,
      "loss": 2.318356513977051,
      "step": 13510
    },
    {
      "epoch": 0.6434285714285715,
      "grad_norm": 0.02609795145690441,
      "learning_rate": 0.024000000208616257,
      "loss": 2.347700595855713,
      "step": 13512
    },
    {
      "epoch": 0.6435238095238095,
      "grad_norm": 0.02814757078886032,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3403241634368896,
      "step": 13514
    },
    {
      "epoch": 0.6436190476190476,
      "grad_norm": 0.03170827403664589,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3517096042633057,
      "step": 13516
    },
    {
      "epoch": 0.6437142857142857,
      "grad_norm": 0.026911243796348572,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3059511184692383,
      "step": 13518
    },
    {
      "epoch": 0.6438095238095238,
      "grad_norm": 0.027298759669065475,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3269400596618652,
      "step": 13520
    },
    {
      "epoch": 0.6439047619047619,
      "grad_norm": 0.02817448414862156,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3506531715393066,
      "step": 13522
    },
    {
      "epoch": 0.644,
      "grad_norm": 0.026602545753121376,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3162617683410645,
      "step": 13524
    },
    {
      "epoch": 0.644095238095238,
      "grad_norm": 0.02853209525346756,
      "learning_rate": 0.024000000208616257,
      "loss": 2.323153495788574,
      "step": 13526
    },
    {
      "epoch": 0.6441904761904762,
      "grad_norm": 0.026273304596543312,
      "learning_rate": 0.024000000208616257,
      "loss": 2.318014144897461,
      "step": 13528
    },
    {
      "epoch": 0.6442857142857142,
      "grad_norm": 0.026607876643538475,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3304667472839355,
      "step": 13530
    },
    {
      "epoch": 0.6443809523809524,
      "grad_norm": 0.02666633017361164,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2963356971740723,
      "step": 13532
    },
    {
      "epoch": 0.6444761904761904,
      "grad_norm": 0.02665065973997116,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3375773429870605,
      "step": 13534
    },
    {
      "epoch": 0.6445714285714286,
      "grad_norm": 0.027033573016524315,
      "learning_rate": 0.024000000208616257,
      "loss": 2.325451374053955,
      "step": 13536
    },
    {
      "epoch": 0.6446666666666667,
      "grad_norm": 0.02775120548903942,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3124332427978516,
      "step": 13538
    },
    {
      "epoch": 0.6447619047619048,
      "grad_norm": 0.027195533737540245,
      "learning_rate": 0.024000000208616257,
      "loss": 2.305020332336426,
      "step": 13540
    },
    {
      "epoch": 0.6448571428571429,
      "grad_norm": 0.025890275835990906,
      "learning_rate": 0.024000000208616257,
      "loss": 2.294261932373047,
      "step": 13542
    },
    {
      "epoch": 0.6449523809523809,
      "grad_norm": 0.02639383263885975,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3237717151641846,
      "step": 13544
    },
    {
      "epoch": 0.6450476190476191,
      "grad_norm": 0.02628541924059391,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3062546253204346,
      "step": 13546
    },
    {
      "epoch": 0.6451428571428571,
      "grad_norm": 0.026940226554870605,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3182711601257324,
      "step": 13548
    },
    {
      "epoch": 0.6452380952380953,
      "grad_norm": 0.026794403791427612,
      "learning_rate": 0.024000000208616257,
      "loss": 2.320904493331909,
      "step": 13550
    },
    {
      "epoch": 0.6453333333333333,
      "grad_norm": 0.026257717981934547,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3016655445098877,
      "step": 13552
    },
    {
      "epoch": 0.6454285714285715,
      "grad_norm": 0.024893393740057945,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3275036811828613,
      "step": 13554
    },
    {
      "epoch": 0.6455238095238095,
      "grad_norm": 0.025481870397925377,
      "learning_rate": 0.024000000208616257,
      "loss": 2.306682825088501,
      "step": 13556
    },
    {
      "epoch": 0.6456190476190476,
      "grad_norm": 0.027414260432124138,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3180091381073,
      "step": 13558
    },
    {
      "epoch": 0.6457142857142857,
      "grad_norm": 0.026401903480291367,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3245818614959717,
      "step": 13560
    },
    {
      "epoch": 0.6458095238095238,
      "grad_norm": 0.026877716183662415,
      "learning_rate": 0.024000000208616257,
      "loss": 2.308922290802002,
      "step": 13562
    },
    {
      "epoch": 0.6459047619047619,
      "grad_norm": 0.0316447988152504,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338894844055176,
      "step": 13564
    },
    {
      "epoch": 0.646,
      "grad_norm": 0.026317153126001358,
      "learning_rate": 0.024000000208616257,
      "loss": 2.290193557739258,
      "step": 13566
    },
    {
      "epoch": 0.6460952380952381,
      "grad_norm": 0.02751738391816616,
      "learning_rate": 0.024000000208616257,
      "loss": 2.289158344268799,
      "step": 13568
    },
    {
      "epoch": 0.6461904761904762,
      "grad_norm": 0.02563072368502617,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3262548446655273,
      "step": 13570
    },
    {
      "epoch": 0.6462857142857142,
      "grad_norm": 0.027524426579475403,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3006439208984375,
      "step": 13572
    },
    {
      "epoch": 0.6463809523809524,
      "grad_norm": 0.026085296645760536,
      "learning_rate": 0.024000000208616257,
      "loss": 2.292401075363159,
      "step": 13574
    },
    {
      "epoch": 0.6464761904761904,
      "grad_norm": 0.026025349274277687,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3217215538024902,
      "step": 13576
    },
    {
      "epoch": 0.6465714285714286,
      "grad_norm": 0.029154418036341667,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3141207695007324,
      "step": 13578
    },
    {
      "epoch": 0.6466666666666666,
      "grad_norm": 0.025658855214715004,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2983479499816895,
      "step": 13580
    },
    {
      "epoch": 0.6467619047619048,
      "grad_norm": 0.026108691468834877,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3144431114196777,
      "step": 13582
    },
    {
      "epoch": 0.6468571428571429,
      "grad_norm": 0.02599550224840641,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3187623023986816,
      "step": 13584
    },
    {
      "epoch": 0.646952380952381,
      "grad_norm": 0.027795135974884033,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3133327960968018,
      "step": 13586
    },
    {
      "epoch": 0.6470476190476191,
      "grad_norm": 0.025512276217341423,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2997019290924072,
      "step": 13588
    },
    {
      "epoch": 0.6471428571428571,
      "grad_norm": 0.026510432362556458,
      "learning_rate": 0.024000000208616257,
      "loss": 2.309075355529785,
      "step": 13590
    },
    {
      "epoch": 0.6472380952380953,
      "grad_norm": 0.027374643832445145,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3312361240386963,
      "step": 13592
    },
    {
      "epoch": 0.6473333333333333,
      "grad_norm": 0.02588241547346115,
      "learning_rate": 0.024000000208616257,
      "loss": 2.325127601623535,
      "step": 13594
    },
    {
      "epoch": 0.6474285714285715,
      "grad_norm": 0.02937900461256504,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3067102432250977,
      "step": 13596
    },
    {
      "epoch": 0.6475238095238095,
      "grad_norm": 0.025219764560461044,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2971386909484863,
      "step": 13598
    },
    {
      "epoch": 0.6476190476190476,
      "grad_norm": 0.027537552639842033,
      "learning_rate": 0.024000000208616257,
      "loss": 2.296412944793701,
      "step": 13600
    },
    {
      "epoch": 0.6477142857142857,
      "grad_norm": 0.024867098778486252,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2801241874694824,
      "step": 13602
    },
    {
      "epoch": 0.6478095238095238,
      "grad_norm": 0.026617957279086113,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3053860664367676,
      "step": 13604
    },
    {
      "epoch": 0.6479047619047619,
      "grad_norm": 0.027912747114896774,
      "learning_rate": 0.024000000208616257,
      "loss": 2.303957462310791,
      "step": 13606
    },
    {
      "epoch": 0.648,
      "grad_norm": 0.027019700035452843,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3119401931762695,
      "step": 13608
    },
    {
      "epoch": 0.6480952380952381,
      "grad_norm": 0.02808774635195732,
      "learning_rate": 0.024000000208616257,
      "loss": 2.297861337661743,
      "step": 13610
    },
    {
      "epoch": 0.6481904761904762,
      "grad_norm": 0.027523482218384743,
      "learning_rate": 0.024000000208616257,
      "loss": 2.306699752807617,
      "step": 13612
    },
    {
      "epoch": 0.6482857142857142,
      "grad_norm": 0.02666379138827324,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3144783973693848,
      "step": 13614
    },
    {
      "epoch": 0.6483809523809524,
      "grad_norm": 0.028475837782025337,
      "learning_rate": 0.024000000208616257,
      "loss": 2.338423728942871,
      "step": 13616
    },
    {
      "epoch": 0.6484761904761904,
      "grad_norm": 0.02678670361638069,
      "learning_rate": 0.024000000208616257,
      "loss": 2.311300277709961,
      "step": 13618
    },
    {
      "epoch": 0.6485714285714286,
      "grad_norm": 0.026288671419024467,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3192718029022217,
      "step": 13620
    },
    {
      "epoch": 0.6486666666666666,
      "grad_norm": 0.02971000224351883,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3064544200897217,
      "step": 13622
    },
    {
      "epoch": 0.6487619047619048,
      "grad_norm": 0.025677843019366264,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2795891761779785,
      "step": 13624
    },
    {
      "epoch": 0.6488571428571429,
      "grad_norm": 0.026978302747011185,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2849206924438477,
      "step": 13626
    },
    {
      "epoch": 0.648952380952381,
      "grad_norm": 0.02899707667529583,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3065378665924072,
      "step": 13628
    },
    {
      "epoch": 0.6490476190476191,
      "grad_norm": 0.028749318793416023,
      "learning_rate": 0.024000000208616257,
      "loss": 2.273000717163086,
      "step": 13630
    },
    {
      "epoch": 0.6491428571428571,
      "grad_norm": 0.025052813813090324,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3056344985961914,
      "step": 13632
    },
    {
      "epoch": 0.6492380952380953,
      "grad_norm": 0.025409992784261703,
      "learning_rate": 0.024000000208616257,
      "loss": 2.288482666015625,
      "step": 13634
    },
    {
      "epoch": 0.6493333333333333,
      "grad_norm": 0.02774510346353054,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2919836044311523,
      "step": 13636
    },
    {
      "epoch": 0.6494285714285715,
      "grad_norm": 0.02521400712430477,
      "learning_rate": 0.024000000208616257,
      "loss": 2.316405773162842,
      "step": 13638
    },
    {
      "epoch": 0.6495238095238095,
      "grad_norm": 0.026741644367575645,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3041515350341797,
      "step": 13640
    },
    {
      "epoch": 0.6496190476190477,
      "grad_norm": 0.028532298281788826,
      "learning_rate": 0.024000000208616257,
      "loss": 2.284761905670166,
      "step": 13642
    },
    {
      "epoch": 0.6497142857142857,
      "grad_norm": 0.027164820581674576,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2970075607299805,
      "step": 13644
    },
    {
      "epoch": 0.6498095238095238,
      "grad_norm": 0.026672644540667534,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2881150245666504,
      "step": 13646
    },
    {
      "epoch": 0.6499047619047619,
      "grad_norm": 0.0257740318775177,
      "learning_rate": 0.024000000208616257,
      "loss": 2.291083335876465,
      "step": 13648
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.02946845069527626,
      "learning_rate": 0.024000000208616257,
      "loss": 2.294919729232788,
      "step": 13650
    },
    {
      "epoch": 0.6500952380952381,
      "grad_norm": 0.026394642889499664,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3244986534118652,
      "step": 13652
    },
    {
      "epoch": 0.6501904761904762,
      "grad_norm": 0.025780141353607178,
      "learning_rate": 0.024000000208616257,
      "loss": 2.287121295928955,
      "step": 13654
    },
    {
      "epoch": 0.6502857142857142,
      "grad_norm": 0.027314767241477966,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2802481651306152,
      "step": 13656
    },
    {
      "epoch": 0.6503809523809524,
      "grad_norm": 0.025982758030295372,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2783379554748535,
      "step": 13658
    },
    {
      "epoch": 0.6504761904761904,
      "grad_norm": 0.02667940780520439,
      "learning_rate": 0.024000000208616257,
      "loss": 2.261268138885498,
      "step": 13660
    },
    {
      "epoch": 0.6505714285714286,
      "grad_norm": 0.024642927572131157,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2585573196411133,
      "step": 13662
    },
    {
      "epoch": 0.6506666666666666,
      "grad_norm": 0.025405896827578545,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2820467948913574,
      "step": 13664
    },
    {
      "epoch": 0.6507619047619048,
      "grad_norm": 0.025449328124523163,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2773146629333496,
      "step": 13666
    },
    {
      "epoch": 0.6508571428571429,
      "grad_norm": 0.02605075016617775,
      "learning_rate": 0.024000000208616257,
      "loss": 2.264862298965454,
      "step": 13668
    },
    {
      "epoch": 0.650952380952381,
      "grad_norm": 0.026817327365279198,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2799289226531982,
      "step": 13670
    },
    {
      "epoch": 0.6510476190476191,
      "grad_norm": 0.02777864597737789,
      "learning_rate": 0.024000000208616257,
      "loss": 2.320451259613037,
      "step": 13672
    },
    {
      "epoch": 0.6511428571428571,
      "grad_norm": 0.02644948847591877,
      "learning_rate": 0.024000000208616257,
      "loss": 2.290205478668213,
      "step": 13674
    },
    {
      "epoch": 0.6512380952380953,
      "grad_norm": 0.03851320967078209,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2959935665130615,
      "step": 13676
    },
    {
      "epoch": 0.6513333333333333,
      "grad_norm": 0.02520034648478031,
      "learning_rate": 0.024000000208616257,
      "loss": 2.254105806350708,
      "step": 13678
    },
    {
      "epoch": 0.6514285714285715,
      "grad_norm": 0.026675336062908173,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2972466945648193,
      "step": 13680
    },
    {
      "epoch": 0.6515238095238095,
      "grad_norm": 0.028625493869185448,
      "learning_rate": 0.024000000208616257,
      "loss": 2.260528564453125,
      "step": 13682
    },
    {
      "epoch": 0.6516190476190477,
      "grad_norm": 0.02568153291940689,
      "learning_rate": 0.024000000208616257,
      "loss": 2.317507028579712,
      "step": 13684
    },
    {
      "epoch": 0.6517142857142857,
      "grad_norm": 0.027308402583003044,
      "learning_rate": 0.024000000208616257,
      "loss": 2.275400161743164,
      "step": 13686
    },
    {
      "epoch": 0.6518095238095238,
      "grad_norm": 0.027054190635681152,
      "learning_rate": 0.024000000208616257,
      "loss": 2.3034467697143555,
      "step": 13688
    },
    {
      "epoch": 0.6519047619047619,
      "grad_norm": 0.027860185131430626,
      "learning_rate": 0.024000000208616257,
      "loss": 2.272728443145752,
      "step": 13690
    },
    {
      "epoch": 0.652,
      "grad_norm": 0.02802259474992752,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2894906997680664,
      "step": 13692
    },
    {
      "epoch": 0.6520952380952381,
      "grad_norm": 0.03167901560664177,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2855098247528076,
      "step": 13694
    },
    {
      "epoch": 0.6521904761904762,
      "grad_norm": 0.03477407991886139,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2695364952087402,
      "step": 13696
    },
    {
      "epoch": 0.6522857142857142,
      "grad_norm": 0.036535199731588364,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2631731033325195,
      "step": 13698
    },
    {
      "epoch": 0.6523809523809524,
      "grad_norm": 0.02802099660038948,
      "learning_rate": 0.024000000208616257,
      "loss": 2.2992212772369385,
      "step": 13700
    },
    {
      "epoch": 0.6524761904761904,
      "grad_norm": 0.025464460253715515,
      "learning_rate": 0.023996712639927864,
      "loss": 2.2743160724639893,
      "step": 13702
    },
    {
      "epoch": 0.6525714285714286,
      "grad_norm": 0.029032522812485695,
      "learning_rate": 0.02399013750255108,
      "loss": 2.273268699645996,
      "step": 13704
    },
    {
      "epoch": 0.6526666666666666,
      "grad_norm": 0.03167120739817619,
      "learning_rate": 0.023983562365174294,
      "loss": 2.2575554847717285,
      "step": 13706
    },
    {
      "epoch": 0.6527619047619048,
      "grad_norm": 0.031633295118808746,
      "learning_rate": 0.02397698536515236,
      "loss": 2.2865285873413086,
      "step": 13708
    },
    {
      "epoch": 0.6528571428571428,
      "grad_norm": 0.02951199561357498,
      "learning_rate": 0.023970412090420723,
      "loss": 2.2780022621154785,
      "step": 13710
    },
    {
      "epoch": 0.652952380952381,
      "grad_norm": 0.03529676795005798,
      "learning_rate": 0.02396383509039879,
      "loss": 2.297579765319824,
      "step": 13712
    },
    {
      "epoch": 0.6530476190476191,
      "grad_norm": 0.02825985476374626,
      "learning_rate": 0.023957259953022003,
      "loss": 2.278563976287842,
      "step": 13714
    },
    {
      "epoch": 0.6531428571428571,
      "grad_norm": 0.02907525561749935,
      "learning_rate": 0.023950684815645218,
      "loss": 2.282470226287842,
      "step": 13716
    },
    {
      "epoch": 0.6532380952380953,
      "grad_norm": 0.025341622531414032,
      "learning_rate": 0.023944109678268433,
      "loss": 2.262660503387451,
      "step": 13718
    },
    {
      "epoch": 0.6533333333333333,
      "grad_norm": 0.02596926875412464,
      "learning_rate": 0.023937534540891647,
      "loss": 2.271766424179077,
      "step": 13720
    },
    {
      "epoch": 0.6534285714285715,
      "grad_norm": 0.025581128895282745,
      "learning_rate": 0.023930959403514862,
      "loss": 2.25933837890625,
      "step": 13722
    },
    {
      "epoch": 0.6535238095238095,
      "grad_norm": 0.025097142904996872,
      "learning_rate": 0.023924384266138077,
      "loss": 2.2724099159240723,
      "step": 13724
    },
    {
      "epoch": 0.6536190476190477,
      "grad_norm": 0.025472167879343033,
      "learning_rate": 0.02391780912876129,
      "loss": 2.25978946685791,
      "step": 13726
    },
    {
      "epoch": 0.6537142857142857,
      "grad_norm": 0.02455117739737034,
      "learning_rate": 0.023911232128739357,
      "loss": 2.272874593734741,
      "step": 13728
    },
    {
      "epoch": 0.6538095238095238,
      "grad_norm": 0.025745170190930367,
      "learning_rate": 0.02390465885400772,
      "loss": 2.2757601737976074,
      "step": 13730
    },
    {
      "epoch": 0.6539047619047619,
      "grad_norm": 0.02689075469970703,
      "learning_rate": 0.023898081853985786,
      "loss": 2.24599027633667,
      "step": 13732
    },
    {
      "epoch": 0.654,
      "grad_norm": 0.02673168294131756,
      "learning_rate": 0.023891506716609,
      "loss": 2.265944004058838,
      "step": 13734
    },
    {
      "epoch": 0.6540952380952381,
      "grad_norm": 0.026524445042014122,
      "learning_rate": 0.023884931579232216,
      "loss": 2.2774243354797363,
      "step": 13736
    },
    {
      "epoch": 0.6541904761904762,
      "grad_norm": 0.026278622448444366,
      "learning_rate": 0.02387835644185543,
      "loss": 2.2740225791931152,
      "step": 13738
    },
    {
      "epoch": 0.6542857142857142,
      "grad_norm": 0.028179526329040527,
      "learning_rate": 0.023871781304478645,
      "loss": 2.2826642990112305,
      "step": 13740
    },
    {
      "epoch": 0.6543809523809524,
      "grad_norm": 0.025404857471585274,
      "learning_rate": 0.02386520616710186,
      "loss": 2.264451503753662,
      "step": 13742
    },
    {
      "epoch": 0.6544761904761904,
      "grad_norm": 0.026741335168480873,
      "learning_rate": 0.023858629167079926,
      "loss": 2.2815985679626465,
      "step": 13744
    },
    {
      "epoch": 0.6545714285714286,
      "grad_norm": 0.02515765279531479,
      "learning_rate": 0.02385205589234829,
      "loss": 2.2695491313934326,
      "step": 13746
    },
    {
      "epoch": 0.6546666666666666,
      "grad_norm": 0.028794948011636734,
      "learning_rate": 0.023845478892326355,
      "loss": 2.279245138168335,
      "step": 13748
    },
    {
      "epoch": 0.6547619047619048,
      "grad_norm": 0.02579338103532791,
      "learning_rate": 0.02383890375494957,
      "loss": 2.275679111480713,
      "step": 13750
    },
    {
      "epoch": 0.6548571428571428,
      "grad_norm": 0.025264017283916473,
      "learning_rate": 0.023832328617572784,
      "loss": 2.282233715057373,
      "step": 13752
    },
    {
      "epoch": 0.654952380952381,
      "grad_norm": 0.0294125284999609,
      "learning_rate": 0.023825753480196,
      "loss": 2.2902016639709473,
      "step": 13754
    },
    {
      "epoch": 0.6550476190476191,
      "grad_norm": 0.02658984437584877,
      "learning_rate": 0.023819178342819214,
      "loss": 2.2973248958587646,
      "step": 13756
    },
    {
      "epoch": 0.6551428571428571,
      "grad_norm": 0.026273882016539574,
      "learning_rate": 0.02381260320544243,
      "loss": 2.263117790222168,
      "step": 13758
    },
    {
      "epoch": 0.6552380952380953,
      "grad_norm": 0.025658229365944862,
      "learning_rate": 0.023806028068065643,
      "loss": 2.289444923400879,
      "step": 13760
    },
    {
      "epoch": 0.6553333333333333,
      "grad_norm": 0.025446997955441475,
      "learning_rate": 0.023799452930688858,
      "loss": 2.2885921001434326,
      "step": 13762
    },
    {
      "epoch": 0.6554285714285715,
      "grad_norm": 0.0275895893573761,
      "learning_rate": 0.023792875930666924,
      "loss": 2.272137403488159,
      "step": 13764
    },
    {
      "epoch": 0.6555238095238095,
      "grad_norm": 0.025913503021001816,
      "learning_rate": 0.023786302655935287,
      "loss": 2.252169132232666,
      "step": 13766
    },
    {
      "epoch": 0.6556190476190477,
      "grad_norm": 0.025615138933062553,
      "learning_rate": 0.023779725655913353,
      "loss": 2.249197006225586,
      "step": 13768
    },
    {
      "epoch": 0.6557142857142857,
      "grad_norm": 0.025481076911091805,
      "learning_rate": 0.023773150518536568,
      "loss": 2.242800235748291,
      "step": 13770
    },
    {
      "epoch": 0.6558095238095238,
      "grad_norm": 0.025282835587859154,
      "learning_rate": 0.023766575381159782,
      "loss": 2.2566332817077637,
      "step": 13772
    },
    {
      "epoch": 0.6559047619047619,
      "grad_norm": 0.025035029277205467,
      "learning_rate": 0.023760000243782997,
      "loss": 2.2835726737976074,
      "step": 13774
    },
    {
      "epoch": 0.656,
      "grad_norm": 0.02674194611608982,
      "learning_rate": 0.023753425106406212,
      "loss": 2.3074159622192383,
      "step": 13776
    },
    {
      "epoch": 0.6560952380952381,
      "grad_norm": 0.025807714089751244,
      "learning_rate": 0.023746849969029427,
      "loss": 2.2798876762390137,
      "step": 13778
    },
    {
      "epoch": 0.6561904761904762,
      "grad_norm": 0.02826703153550625,
      "learning_rate": 0.023740272969007492,
      "loss": 2.2789645195007324,
      "step": 13780
    },
    {
      "epoch": 0.6562857142857143,
      "grad_norm": 0.02717076800763607,
      "learning_rate": 0.023733699694275856,
      "loss": 2.274322986602783,
      "step": 13782
    },
    {
      "epoch": 0.6563809523809524,
      "grad_norm": 0.026506824418902397,
      "learning_rate": 0.02372712269425392,
      "loss": 2.259265899658203,
      "step": 13784
    },
    {
      "epoch": 0.6564761904761904,
      "grad_norm": 0.02817082218825817,
      "learning_rate": 0.023720547556877136,
      "loss": 2.2781312465667725,
      "step": 13786
    },
    {
      "epoch": 0.6565714285714286,
      "grad_norm": 0.026248909533023834,
      "learning_rate": 0.02371397241950035,
      "loss": 2.266162872314453,
      "step": 13788
    },
    {
      "epoch": 0.6566666666666666,
      "grad_norm": 0.028315601870417595,
      "learning_rate": 0.023707397282123566,
      "loss": 2.253896951675415,
      "step": 13790
    },
    {
      "epoch": 0.6567619047619048,
      "grad_norm": 0.026410378515720367,
      "learning_rate": 0.02370082214474678,
      "loss": 2.262472152709961,
      "step": 13792
    },
    {
      "epoch": 0.6568571428571428,
      "grad_norm": 0.02549849823117256,
      "learning_rate": 0.023694247007369995,
      "loss": 2.282336950302124,
      "step": 13794
    },
    {
      "epoch": 0.656952380952381,
      "grad_norm": 0.027858318760991096,
      "learning_rate": 0.02368767000734806,
      "loss": 2.256436824798584,
      "step": 13796
    },
    {
      "epoch": 0.6570476190476191,
      "grad_norm": 0.027909385040402412,
      "learning_rate": 0.023681096732616425,
      "loss": 2.286224603652954,
      "step": 13798
    },
    {
      "epoch": 0.6571428571428571,
      "grad_norm": 0.026916051283478737,
      "learning_rate": 0.02367451973259449,
      "loss": 2.288536548614502,
      "step": 13800
    },
    {
      "epoch": 0.6572380952380953,
      "grad_norm": 0.026226071640849113,
      "learning_rate": 0.023667946457862854,
      "loss": 2.2680749893188477,
      "step": 13802
    },
    {
      "epoch": 0.6573333333333333,
      "grad_norm": 0.027574289590120316,
      "learning_rate": 0.02366136945784092,
      "loss": 2.2563838958740234,
      "step": 13804
    },
    {
      "epoch": 0.6574285714285715,
      "grad_norm": 0.025426939129829407,
      "learning_rate": 0.023654794320464134,
      "loss": 2.2864694595336914,
      "step": 13806
    },
    {
      "epoch": 0.6575238095238095,
      "grad_norm": 0.026789775118231773,
      "learning_rate": 0.02364821918308735,
      "loss": 2.2766809463500977,
      "step": 13808
    },
    {
      "epoch": 0.6576190476190477,
      "grad_norm": 0.026164475828409195,
      "learning_rate": 0.023641644045710564,
      "loss": 2.2579832077026367,
      "step": 13810
    },
    {
      "epoch": 0.6577142857142857,
      "grad_norm": 0.026191774755716324,
      "learning_rate": 0.02363506890833378,
      "loss": 2.291581630706787,
      "step": 13812
    },
    {
      "epoch": 0.6578095238095238,
      "grad_norm": 0.026591012254357338,
      "learning_rate": 0.023628493770956993,
      "loss": 2.295480251312256,
      "step": 13814
    },
    {
      "epoch": 0.6579047619047619,
      "grad_norm": 0.02902892418205738,
      "learning_rate": 0.02362191677093506,
      "loss": 2.281113862991333,
      "step": 13816
    },
    {
      "epoch": 0.658,
      "grad_norm": 0.027053149417042732,
      "learning_rate": 0.023615343496203423,
      "loss": 2.2671358585357666,
      "step": 13818
    },
    {
      "epoch": 0.6580952380952381,
      "grad_norm": 0.025861363857984543,
      "learning_rate": 0.023608766496181488,
      "loss": 2.2370991706848145,
      "step": 13820
    },
    {
      "epoch": 0.6581904761904762,
      "grad_norm": 0.027038410305976868,
      "learning_rate": 0.023602191358804703,
      "loss": 2.2523317337036133,
      "step": 13822
    },
    {
      "epoch": 0.6582857142857143,
      "grad_norm": 0.027807842940092087,
      "learning_rate": 0.023595616221427917,
      "loss": 2.258059024810791,
      "step": 13824
    },
    {
      "epoch": 0.6583809523809524,
      "grad_norm": 0.025792643427848816,
      "learning_rate": 0.023589041084051132,
      "loss": 2.2955801486968994,
      "step": 13826
    },
    {
      "epoch": 0.6584761904761904,
      "grad_norm": 0.025646237656474113,
      "learning_rate": 0.023582465946674347,
      "loss": 2.2790369987487793,
      "step": 13828
    },
    {
      "epoch": 0.6585714285714286,
      "grad_norm": 0.026164585724473,
      "learning_rate": 0.02357589080929756,
      "loss": 2.2415771484375,
      "step": 13830
    },
    {
      "epoch": 0.6586666666666666,
      "grad_norm": 0.02517259120941162,
      "learning_rate": 0.023569313809275627,
      "loss": 2.2256357669830322,
      "step": 13832
    },
    {
      "epoch": 0.6587619047619048,
      "grad_norm": 0.02560044825077057,
      "learning_rate": 0.02356274053454399,
      "loss": 2.265007972717285,
      "step": 13834
    },
    {
      "epoch": 0.6588571428571428,
      "grad_norm": 0.02905873768031597,
      "learning_rate": 0.023556163534522057,
      "loss": 2.2762935161590576,
      "step": 13836
    },
    {
      "epoch": 0.658952380952381,
      "grad_norm": 0.027165967971086502,
      "learning_rate": 0.02354959025979042,
      "loss": 2.2719109058380127,
      "step": 13838
    },
    {
      "epoch": 0.659047619047619,
      "grad_norm": 0.029325848445296288,
      "learning_rate": 0.023543013259768486,
      "loss": 2.281890392303467,
      "step": 13840
    },
    {
      "epoch": 0.6591428571428571,
      "grad_norm": 0.026467427611351013,
      "learning_rate": 0.0235364381223917,
      "loss": 2.293773651123047,
      "step": 13842
    },
    {
      "epoch": 0.6592380952380953,
      "grad_norm": 0.02617761678993702,
      "learning_rate": 0.023529862985014915,
      "loss": 2.2562777996063232,
      "step": 13844
    },
    {
      "epoch": 0.6593333333333333,
      "grad_norm": 0.02627277560532093,
      "learning_rate": 0.02352328784763813,
      "loss": 2.2771286964416504,
      "step": 13846
    },
    {
      "epoch": 0.6594285714285715,
      "grad_norm": 0.025281181558966637,
      "learning_rate": 0.023516712710261345,
      "loss": 2.2461938858032227,
      "step": 13848
    },
    {
      "epoch": 0.6595238095238095,
      "grad_norm": 0.027801895514130592,
      "learning_rate": 0.02351013757288456,
      "loss": 2.2715492248535156,
      "step": 13850
    },
    {
      "epoch": 0.6596190476190477,
      "grad_norm": 0.029224395751953125,
      "learning_rate": 0.023503560572862625,
      "loss": 2.277886390686035,
      "step": 13852
    },
    {
      "epoch": 0.6597142857142857,
      "grad_norm": 0.03296584263443947,
      "learning_rate": 0.02349698729813099,
      "loss": 2.252753257751465,
      "step": 13854
    },
    {
      "epoch": 0.6598095238095238,
      "grad_norm": 0.028364086523652077,
      "learning_rate": 0.023490410298109055,
      "loss": 2.2690930366516113,
      "step": 13856
    },
    {
      "epoch": 0.6599047619047619,
      "grad_norm": 0.02924221381545067,
      "learning_rate": 0.02348383516073227,
      "loss": 2.2798633575439453,
      "step": 13858
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.028292058035731316,
      "learning_rate": 0.023477260023355484,
      "loss": 2.2681307792663574,
      "step": 13860
    },
    {
      "epoch": 0.6600952380952381,
      "grad_norm": 0.025186484679579735,
      "learning_rate": 0.0234706848859787,
      "loss": 2.2882347106933594,
      "step": 13862
    },
    {
      "epoch": 0.6601904761904762,
      "grad_norm": 0.029062405228614807,
      "learning_rate": 0.023464109748601913,
      "loss": 2.259739875793457,
      "step": 13864
    },
    {
      "epoch": 0.6602857142857143,
      "grad_norm": 0.025963570922613144,
      "learning_rate": 0.023457534611225128,
      "loss": 2.2631802558898926,
      "step": 13866
    },
    {
      "epoch": 0.6603809523809524,
      "grad_norm": 0.02577928639948368,
      "learning_rate": 0.023450957611203194,
      "loss": 2.266839027404785,
      "step": 13868
    },
    {
      "epoch": 0.6604761904761904,
      "grad_norm": 0.025521885603666306,
      "learning_rate": 0.023444384336471558,
      "loss": 2.2554702758789062,
      "step": 13870
    },
    {
      "epoch": 0.6605714285714286,
      "grad_norm": 0.025916598737239838,
      "learning_rate": 0.023437807336449623,
      "loss": 2.2783141136169434,
      "step": 13872
    },
    {
      "epoch": 0.6606666666666666,
      "grad_norm": 0.02557511441409588,
      "learning_rate": 0.023431234061717987,
      "loss": 2.2660577297210693,
      "step": 13874
    },
    {
      "epoch": 0.6607619047619048,
      "grad_norm": 0.025885578244924545,
      "learning_rate": 0.023424657061696053,
      "loss": 2.260098934173584,
      "step": 13876
    },
    {
      "epoch": 0.6608571428571428,
      "grad_norm": 0.026084668934345245,
      "learning_rate": 0.023418081924319267,
      "loss": 2.2549071311950684,
      "step": 13878
    },
    {
      "epoch": 0.660952380952381,
      "grad_norm": 0.025693094357848167,
      "learning_rate": 0.023411506786942482,
      "loss": 2.2950663566589355,
      "step": 13880
    },
    {
      "epoch": 0.661047619047619,
      "grad_norm": 0.02928868494927883,
      "learning_rate": 0.023404931649565697,
      "loss": 2.294121503829956,
      "step": 13882
    },
    {
      "epoch": 0.6611428571428571,
      "grad_norm": 0.026167845353484154,
      "learning_rate": 0.02339835651218891,
      "loss": 2.26224684715271,
      "step": 13884
    },
    {
      "epoch": 0.6612380952380953,
      "grad_norm": 0.026921553537249565,
      "learning_rate": 0.023391781374812126,
      "loss": 2.266427516937256,
      "step": 13886
    },
    {
      "epoch": 0.6613333333333333,
      "grad_norm": 0.025991613045334816,
      "learning_rate": 0.02338520437479019,
      "loss": 2.268138885498047,
      "step": 13888
    },
    {
      "epoch": 0.6614285714285715,
      "grad_norm": 0.02666028030216694,
      "learning_rate": 0.023378631100058556,
      "loss": 2.233227252960205,
      "step": 13890
    },
    {
      "epoch": 0.6615238095238095,
      "grad_norm": 0.026277491822838783,
      "learning_rate": 0.02337205410003662,
      "loss": 2.262936592102051,
      "step": 13892
    },
    {
      "epoch": 0.6616190476190477,
      "grad_norm": 0.025200724601745605,
      "learning_rate": 0.023365478962659836,
      "loss": 2.245210647583008,
      "step": 13894
    },
    {
      "epoch": 0.6617142857142857,
      "grad_norm": 0.03177906572818756,
      "learning_rate": 0.02335890382528305,
      "loss": 2.250858783721924,
      "step": 13896
    },
    {
      "epoch": 0.6618095238095238,
      "grad_norm": 0.031245995312929153,
      "learning_rate": 0.023352328687906265,
      "loss": 2.2791543006896973,
      "step": 13898
    },
    {
      "epoch": 0.6619047619047619,
      "grad_norm": 0.032926030457019806,
      "learning_rate": 0.02334575355052948,
      "loss": 2.305793523788452,
      "step": 13900
    },
    {
      "epoch": 0.662,
      "grad_norm": 0.026515405625104904,
      "learning_rate": 0.023339178413152695,
      "loss": 2.2843427658081055,
      "step": 13902
    },
    {
      "epoch": 0.6620952380952381,
      "grad_norm": 0.02706746757030487,
      "learning_rate": 0.02333260327577591,
      "loss": 2.284080982208252,
      "step": 13904
    },
    {
      "epoch": 0.6621904761904762,
      "grad_norm": 0.028367886319756508,
      "learning_rate": 0.023326028138399124,
      "loss": 2.3024113178253174,
      "step": 13906
    },
    {
      "epoch": 0.6622857142857143,
      "grad_norm": 0.02703789435327053,
      "learning_rate": 0.02331945300102234,
      "loss": 2.273664951324463,
      "step": 13908
    },
    {
      "epoch": 0.6623809523809524,
      "grad_norm": 0.025872979313135147,
      "learning_rate": 0.023312876001000404,
      "loss": 2.3039541244506836,
      "step": 13910
    },
    {
      "epoch": 0.6624761904761904,
      "grad_norm": 0.02675330452620983,
      "learning_rate": 0.02330630272626877,
      "loss": 2.268782138824463,
      "step": 13912
    },
    {
      "epoch": 0.6625714285714286,
      "grad_norm": 0.026666825637221336,
      "learning_rate": 0.023299725726246834,
      "loss": 2.3063056468963623,
      "step": 13914
    },
    {
      "epoch": 0.6626666666666666,
      "grad_norm": 0.027085337787866592,
      "learning_rate": 0.023293152451515198,
      "loss": 2.3097283840179443,
      "step": 13916
    },
    {
      "epoch": 0.6627619047619048,
      "grad_norm": 0.027631156146526337,
      "learning_rate": 0.023286575451493263,
      "loss": 2.2930240631103516,
      "step": 13918
    },
    {
      "epoch": 0.6628571428571428,
      "grad_norm": 0.02719752863049507,
      "learning_rate": 0.023280000314116478,
      "loss": 2.2693352699279785,
      "step": 13920
    },
    {
      "epoch": 0.662952380952381,
      "grad_norm": 0.025919483974575996,
      "learning_rate": 0.023273425176739693,
      "loss": 2.277297019958496,
      "step": 13922
    },
    {
      "epoch": 0.663047619047619,
      "grad_norm": 0.02556609734892845,
      "learning_rate": 0.023266850039362907,
      "loss": 2.2915430068969727,
      "step": 13924
    },
    {
      "epoch": 0.6631428571428571,
      "grad_norm": 0.026384573429822922,
      "learning_rate": 0.023260274901986122,
      "loss": 2.263254165649414,
      "step": 13926
    },
    {
      "epoch": 0.6632380952380953,
      "grad_norm": 0.025196094065904617,
      "learning_rate": 0.023253699764609337,
      "loss": 2.2810349464416504,
      "step": 13928
    },
    {
      "epoch": 0.6633333333333333,
      "grad_norm": 0.026882421225309372,
      "learning_rate": 0.023247122764587402,
      "loss": 2.3085546493530273,
      "step": 13930
    },
    {
      "epoch": 0.6634285714285715,
      "grad_norm": 0.026140419766306877,
      "learning_rate": 0.023240549489855766,
      "loss": 2.2712302207946777,
      "step": 13932
    },
    {
      "epoch": 0.6635238095238095,
      "grad_norm": 0.02767927572131157,
      "learning_rate": 0.023233972489833832,
      "loss": 2.2727527618408203,
      "step": 13934
    },
    {
      "epoch": 0.6636190476190477,
      "grad_norm": 0.029079679399728775,
      "learning_rate": 0.023227397352457047,
      "loss": 2.280426025390625,
      "step": 13936
    },
    {
      "epoch": 0.6637142857142857,
      "grad_norm": 0.030750617384910583,
      "learning_rate": 0.02322082221508026,
      "loss": 2.2953414916992188,
      "step": 13938
    },
    {
      "epoch": 0.6638095238095238,
      "grad_norm": 0.025467796251177788,
      "learning_rate": 0.023214247077703476,
      "loss": 2.293576955795288,
      "step": 13940
    },
    {
      "epoch": 0.6639047619047619,
      "grad_norm": 0.025064382702112198,
      "learning_rate": 0.02320767194032669,
      "loss": 2.311157703399658,
      "step": 13942
    },
    {
      "epoch": 0.664,
      "grad_norm": 0.02512534148991108,
      "learning_rate": 0.023201096802949905,
      "loss": 2.256011962890625,
      "step": 13944
    },
    {
      "epoch": 0.6640952380952381,
      "grad_norm": 0.025339126586914062,
      "learning_rate": 0.02319451980292797,
      "loss": 2.25819730758667,
      "step": 13946
    },
    {
      "epoch": 0.6641904761904762,
      "grad_norm": 0.02622128650546074,
      "learning_rate": 0.023187946528196335,
      "loss": 2.286811351776123,
      "step": 13948
    },
    {
      "epoch": 0.6642857142857143,
      "grad_norm": 0.03163519129157066,
      "learning_rate": 0.0231813695281744,
      "loss": 2.2480249404907227,
      "step": 13950
    },
    {
      "epoch": 0.6643809523809524,
      "grad_norm": 0.02752911113202572,
      "learning_rate": 0.023174796253442764,
      "loss": 2.282597780227661,
      "step": 13952
    },
    {
      "epoch": 0.6644761904761904,
      "grad_norm": 0.025430748239159584,
      "learning_rate": 0.02316821925342083,
      "loss": 2.2765913009643555,
      "step": 13954
    },
    {
      "epoch": 0.6645714285714286,
      "grad_norm": 0.025307655334472656,
      "learning_rate": 0.023161644116044044,
      "loss": 2.2556121349334717,
      "step": 13956
    },
    {
      "epoch": 0.6646666666666666,
      "grad_norm": 0.02593464031815529,
      "learning_rate": 0.02315506897866726,
      "loss": 2.2779035568237305,
      "step": 13958
    },
    {
      "epoch": 0.6647619047619048,
      "grad_norm": 0.027253568172454834,
      "learning_rate": 0.023148493841290474,
      "loss": 2.273207664489746,
      "step": 13960
    },
    {
      "epoch": 0.6648571428571428,
      "grad_norm": 0.026256216689944267,
      "learning_rate": 0.02314191870391369,
      "loss": 2.276444435119629,
      "step": 13962
    },
    {
      "epoch": 0.664952380952381,
      "grad_norm": 0.02576153539121151,
      "learning_rate": 0.023135343566536903,
      "loss": 2.267192840576172,
      "step": 13964
    },
    {
      "epoch": 0.665047619047619,
      "grad_norm": 0.026722237467765808,
      "learning_rate": 0.02312876656651497,
      "loss": 2.2759742736816406,
      "step": 13966
    },
    {
      "epoch": 0.6651428571428571,
      "grad_norm": 0.02736702375113964,
      "learning_rate": 0.023122193291783333,
      "loss": 2.2797234058380127,
      "step": 13968
    },
    {
      "epoch": 0.6652380952380952,
      "grad_norm": 0.026535790413618088,
      "learning_rate": 0.0231156162917614,
      "loss": 2.255361557006836,
      "step": 13970
    },
    {
      "epoch": 0.6653333333333333,
      "grad_norm": 0.025803783908486366,
      "learning_rate": 0.023109041154384613,
      "loss": 2.270514965057373,
      "step": 13972
    },
    {
      "epoch": 0.6654285714285715,
      "grad_norm": 0.026214363053441048,
      "learning_rate": 0.023102466017007828,
      "loss": 2.268768787384033,
      "step": 13974
    },
    {
      "epoch": 0.6655238095238095,
      "grad_norm": 0.026481369510293007,
      "learning_rate": 0.023095890879631042,
      "loss": 2.2484543323516846,
      "step": 13976
    },
    {
      "epoch": 0.6656190476190477,
      "grad_norm": 0.03009878844022751,
      "learning_rate": 0.023089315742254257,
      "loss": 2.2713801860809326,
      "step": 13978
    },
    {
      "epoch": 0.6657142857142857,
      "grad_norm": 0.02564949542284012,
      "learning_rate": 0.023082740604877472,
      "loss": 2.256190776824951,
      "step": 13980
    },
    {
      "epoch": 0.6658095238095239,
      "grad_norm": 0.027910498902201653,
      "learning_rate": 0.023076163604855537,
      "loss": 2.316833972930908,
      "step": 13982
    },
    {
      "epoch": 0.6659047619047619,
      "grad_norm": 0.02563602663576603,
      "learning_rate": 0.0230695903301239,
      "loss": 2.272979259490967,
      "step": 13984
    },
    {
      "epoch": 0.666,
      "grad_norm": 0.025326784700155258,
      "learning_rate": 0.023063013330101967,
      "loss": 2.31478214263916,
      "step": 13986
    },
    {
      "epoch": 0.6660952380952381,
      "grad_norm": 0.02868674509227276,
      "learning_rate": 0.02305643819272518,
      "loss": 2.2893543243408203,
      "step": 13988
    },
    {
      "epoch": 0.6661904761904762,
      "grad_norm": 0.028063364326953888,
      "learning_rate": 0.023049863055348396,
      "loss": 2.27778697013855,
      "step": 13990
    },
    {
      "epoch": 0.6662857142857143,
      "grad_norm": 0.0252991896122694,
      "learning_rate": 0.02304328791797161,
      "loss": 2.30945086479187,
      "step": 13992
    },
    {
      "epoch": 0.6663809523809524,
      "grad_norm": 0.0266608577221632,
      "learning_rate": 0.023036712780594826,
      "loss": 2.311929702758789,
      "step": 13994
    },
    {
      "epoch": 0.6664761904761904,
      "grad_norm": 0.026484688743948936,
      "learning_rate": 0.02303013764321804,
      "loss": 2.2780027389526367,
      "step": 13996
    },
    {
      "epoch": 0.6665714285714286,
      "grad_norm": 0.026254871860146523,
      "learning_rate": 0.023023562505841255,
      "loss": 2.3104288578033447,
      "step": 13998
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.02771391160786152,
      "learning_rate": 0.02301698736846447,
      "loss": 2.266958475112915,
      "step": 14000
    },
    {
      "epoch": 0.6667619047619048,
      "grad_norm": 0.026367846876382828,
      "learning_rate": 0.023010410368442535,
      "loss": 2.2773687839508057,
      "step": 14002
    },
    {
      "epoch": 0.6668571428571428,
      "grad_norm": 0.02834508568048477,
      "learning_rate": 0.0230038370937109,
      "loss": 2.325556993484497,
      "step": 14004
    },
    {
      "epoch": 0.666952380952381,
      "grad_norm": 0.026125377044081688,
      "learning_rate": 0.022997260093688965,
      "loss": 2.2948391437530518,
      "step": 14006
    },
    {
      "epoch": 0.667047619047619,
      "grad_norm": 0.025822436437010765,
      "learning_rate": 0.02299068495631218,
      "loss": 2.2732672691345215,
      "step": 14008
    },
    {
      "epoch": 0.6671428571428571,
      "grad_norm": 0.0257906224578619,
      "learning_rate": 0.022984109818935394,
      "loss": 2.2673025131225586,
      "step": 14010
    },
    {
      "epoch": 0.6672380952380952,
      "grad_norm": 0.02586480602622032,
      "learning_rate": 0.02297753468155861,
      "loss": 2.2702507972717285,
      "step": 14012
    },
    {
      "epoch": 0.6673333333333333,
      "grad_norm": 0.027757668867707253,
      "learning_rate": 0.022970959544181824,
      "loss": 2.2946343421936035,
      "step": 14014
    },
    {
      "epoch": 0.6674285714285715,
      "grad_norm": 0.031673774123191833,
      "learning_rate": 0.02296438440680504,
      "loss": 2.293067455291748,
      "step": 14016
    },
    {
      "epoch": 0.6675238095238095,
      "grad_norm": 0.0277529526501894,
      "learning_rate": 0.022957807406783104,
      "loss": 2.2774949073791504,
      "step": 14018
    },
    {
      "epoch": 0.6676190476190477,
      "grad_norm": 0.026103375479578972,
      "learning_rate": 0.022951234132051468,
      "loss": 2.314190626144409,
      "step": 14020
    },
    {
      "epoch": 0.6677142857142857,
      "grad_norm": 0.026833752170205116,
      "learning_rate": 0.022944657132029533,
      "loss": 2.280405044555664,
      "step": 14022
    },
    {
      "epoch": 0.6678095238095239,
      "grad_norm": 0.027477525174617767,
      "learning_rate": 0.022938081994652748,
      "loss": 2.2885305881500244,
      "step": 14024
    },
    {
      "epoch": 0.6679047619047619,
      "grad_norm": 0.03226042166352272,
      "learning_rate": 0.022931506857275963,
      "loss": 2.258172035217285,
      "step": 14026
    },
    {
      "epoch": 0.668,
      "grad_norm": 0.028422068804502487,
      "learning_rate": 0.022924931719899178,
      "loss": 2.297588348388672,
      "step": 14028
    },
    {
      "epoch": 0.6680952380952381,
      "grad_norm": 0.032311033457517624,
      "learning_rate": 0.022918356582522392,
      "loss": 2.2863662242889404,
      "step": 14030
    },
    {
      "epoch": 0.6681904761904762,
      "grad_norm": 0.027216723188757896,
      "learning_rate": 0.022911781445145607,
      "loss": 2.281301975250244,
      "step": 14032
    },
    {
      "epoch": 0.6682857142857143,
      "grad_norm": 0.0285510141402483,
      "learning_rate": 0.02290520630776882,
      "loss": 2.2921667098999023,
      "step": 14034
    },
    {
      "epoch": 0.6683809523809524,
      "grad_norm": 0.029551036655902863,
      "learning_rate": 0.022898631170392036,
      "loss": 2.2981812953948975,
      "step": 14036
    },
    {
      "epoch": 0.6684761904761904,
      "grad_norm": 0.025521479547023773,
      "learning_rate": 0.022892054170370102,
      "loss": 2.265700340270996,
      "step": 14038
    },
    {
      "epoch": 0.6685714285714286,
      "grad_norm": 0.026212893426418304,
      "learning_rate": 0.022885480895638466,
      "loss": 2.2760095596313477,
      "step": 14040
    },
    {
      "epoch": 0.6686666666666666,
      "grad_norm": 0.026285521686077118,
      "learning_rate": 0.02287890389561653,
      "loss": 2.3080272674560547,
      "step": 14042
    },
    {
      "epoch": 0.6687619047619048,
      "grad_norm": 0.02663321979343891,
      "learning_rate": 0.022872328758239746,
      "loss": 2.2922840118408203,
      "step": 14044
    },
    {
      "epoch": 0.6688571428571428,
      "grad_norm": 0.026313336566090584,
      "learning_rate": 0.02286575362086296,
      "loss": 2.2860190868377686,
      "step": 14046
    },
    {
      "epoch": 0.668952380952381,
      "grad_norm": 0.026533709838986397,
      "learning_rate": 0.022859178483486176,
      "loss": 2.292598247528076,
      "step": 14048
    },
    {
      "epoch": 0.669047619047619,
      "grad_norm": 0.026156213134527206,
      "learning_rate": 0.02285260334610939,
      "loss": 2.279980182647705,
      "step": 14050
    },
    {
      "epoch": 0.6691428571428572,
      "grad_norm": 0.026830758899450302,
      "learning_rate": 0.022846028208732605,
      "loss": 2.289994478225708,
      "step": 14052
    },
    {
      "epoch": 0.6692380952380952,
      "grad_norm": 0.026487329974770546,
      "learning_rate": 0.02283945120871067,
      "loss": 2.3031153678894043,
      "step": 14054
    },
    {
      "epoch": 0.6693333333333333,
      "grad_norm": 0.0267647672444582,
      "learning_rate": 0.022832877933979034,
      "loss": 2.2672853469848633,
      "step": 14056
    },
    {
      "epoch": 0.6694285714285715,
      "grad_norm": 0.028629528358578682,
      "learning_rate": 0.0228263009339571,
      "loss": 2.314545154571533,
      "step": 14058
    },
    {
      "epoch": 0.6695238095238095,
      "grad_norm": 0.029828418046236038,
      "learning_rate": 0.022819725796580315,
      "loss": 2.271758794784546,
      "step": 14060
    },
    {
      "epoch": 0.6696190476190477,
      "grad_norm": 0.02573932707309723,
      "learning_rate": 0.02281315065920353,
      "loss": 2.2894701957702637,
      "step": 14062
    },
    {
      "epoch": 0.6697142857142857,
      "grad_norm": 0.026285521686077118,
      "learning_rate": 0.022806575521826744,
      "loss": 2.286254405975342,
      "step": 14064
    },
    {
      "epoch": 0.6698095238095239,
      "grad_norm": 0.02518671751022339,
      "learning_rate": 0.02280000038444996,
      "loss": 2.307157039642334,
      "step": 14066
    },
    {
      "epoch": 0.6699047619047619,
      "grad_norm": 0.02491891384124756,
      "learning_rate": 0.022793425247073174,
      "loss": 2.276672601699829,
      "step": 14068
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.0272072721272707,
      "learning_rate": 0.022786850109696388,
      "loss": 2.3106210231781006,
      "step": 14070
    },
    {
      "epoch": 0.6700952380952381,
      "grad_norm": 0.028195669874548912,
      "learning_rate": 0.022780274972319603,
      "loss": 2.294239044189453,
      "step": 14072
    },
    {
      "epoch": 0.6701904761904762,
      "grad_norm": 0.02668914385139942,
      "learning_rate": 0.02277369797229767,
      "loss": 2.3001768589019775,
      "step": 14074
    },
    {
      "epoch": 0.6702857142857143,
      "grad_norm": 0.025903869420289993,
      "learning_rate": 0.022767124697566032,
      "loss": 2.266757011413574,
      "step": 14076
    },
    {
      "epoch": 0.6703809523809524,
      "grad_norm": 0.026203742250800133,
      "learning_rate": 0.022760547697544098,
      "loss": 2.31300687789917,
      "step": 14078
    },
    {
      "epoch": 0.6704761904761904,
      "grad_norm": 0.027895255014300346,
      "learning_rate": 0.022753972560167313,
      "loss": 2.3117313385009766,
      "step": 14080
    },
    {
      "epoch": 0.6705714285714286,
      "grad_norm": 0.0256912000477314,
      "learning_rate": 0.022747397422790527,
      "loss": 2.3287618160247803,
      "step": 14082
    },
    {
      "epoch": 0.6706666666666666,
      "grad_norm": 0.02665974199771881,
      "learning_rate": 0.022740822285413742,
      "loss": 2.3123018741607666,
      "step": 14084
    },
    {
      "epoch": 0.6707619047619048,
      "grad_norm": 0.02732139267027378,
      "learning_rate": 0.022734247148036957,
      "loss": 2.2989492416381836,
      "step": 14086
    },
    {
      "epoch": 0.6708571428571428,
      "grad_norm": 0.027926906943321228,
      "learning_rate": 0.02272767201066017,
      "loss": 2.30989933013916,
      "step": 14088
    },
    {
      "epoch": 0.670952380952381,
      "grad_norm": 0.02509789913892746,
      "learning_rate": 0.022721095010638237,
      "loss": 2.304077625274658,
      "step": 14090
    },
    {
      "epoch": 0.671047619047619,
      "grad_norm": 0.02641027420759201,
      "learning_rate": 0.0227145217359066,
      "loss": 2.307368755340576,
      "step": 14092
    },
    {
      "epoch": 0.6711428571428572,
      "grad_norm": 0.025606034323573112,
      "learning_rate": 0.022707944735884666,
      "loss": 2.334171772003174,
      "step": 14094
    },
    {
      "epoch": 0.6712380952380952,
      "grad_norm": 0.025665948167443275,
      "learning_rate": 0.02270136959850788,
      "loss": 2.2780840396881104,
      "step": 14096
    },
    {
      "epoch": 0.6713333333333333,
      "grad_norm": 0.026516180485486984,
      "learning_rate": 0.022694794461131096,
      "loss": 2.333354949951172,
      "step": 14098
    },
    {
      "epoch": 0.6714285714285714,
      "grad_norm": 0.026074102148413658,
      "learning_rate": 0.02268821932375431,
      "loss": 2.30458927154541,
      "step": 14100
    },
    {
      "epoch": 0.6715238095238095,
      "grad_norm": 0.02683558501303196,
      "learning_rate": 0.022681644186377525,
      "loss": 2.3135337829589844,
      "step": 14102
    },
    {
      "epoch": 0.6716190476190477,
      "grad_norm": 0.026696646586060524,
      "learning_rate": 0.02267506904900074,
      "loss": 2.3159937858581543,
      "step": 14104
    },
    {
      "epoch": 0.6717142857142857,
      "grad_norm": 0.02567158453166485,
      "learning_rate": 0.022668493911623955,
      "loss": 2.3226752281188965,
      "step": 14106
    },
    {
      "epoch": 0.6718095238095239,
      "grad_norm": 0.024600306525826454,
      "learning_rate": 0.02266191877424717,
      "loss": 2.306046962738037,
      "step": 14108
    },
    {
      "epoch": 0.6719047619047619,
      "grad_norm": 0.028904613107442856,
      "learning_rate": 0.022655341774225235,
      "loss": 2.325171947479248,
      "step": 14110
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.02674891985952854,
      "learning_rate": 0.0226487684994936,
      "loss": 2.321098566055298,
      "step": 14112
    },
    {
      "epoch": 0.6720952380952381,
      "grad_norm": 0.025578932836651802,
      "learning_rate": 0.022642191499471664,
      "loss": 2.3364691734313965,
      "step": 14114
    },
    {
      "epoch": 0.6721904761904762,
      "grad_norm": 0.02782977931201458,
      "learning_rate": 0.02263561636209488,
      "loss": 2.2967517375946045,
      "step": 14116
    },
    {
      "epoch": 0.6722857142857143,
      "grad_norm": 0.027391355484724045,
      "learning_rate": 0.022629041224718094,
      "loss": 2.312936782836914,
      "step": 14118
    },
    {
      "epoch": 0.6723809523809524,
      "grad_norm": 0.027308614924550056,
      "learning_rate": 0.02262246608734131,
      "loss": 2.3341822624206543,
      "step": 14120
    },
    {
      "epoch": 0.6724761904761904,
      "grad_norm": 0.026905907317996025,
      "learning_rate": 0.022615890949964523,
      "loss": 2.317690372467041,
      "step": 14122
    },
    {
      "epoch": 0.6725714285714286,
      "grad_norm": 0.02542872726917267,
      "learning_rate": 0.022609315812587738,
      "loss": 2.3573782444000244,
      "step": 14124
    },
    {
      "epoch": 0.6726666666666666,
      "grad_norm": 0.026429057121276855,
      "learning_rate": 0.022602738812565804,
      "loss": 2.307079315185547,
      "step": 14126
    },
    {
      "epoch": 0.6727619047619048,
      "grad_norm": 0.025902824476361275,
      "learning_rate": 0.022596165537834167,
      "loss": 2.318695068359375,
      "step": 14128
    },
    {
      "epoch": 0.6728571428571428,
      "grad_norm": 0.025668565183877945,
      "learning_rate": 0.022589588537812233,
      "loss": 2.339277744293213,
      "step": 14130
    },
    {
      "epoch": 0.672952380952381,
      "grad_norm": 0.025559106841683388,
      "learning_rate": 0.022583013400435448,
      "loss": 2.3215181827545166,
      "step": 14132
    },
    {
      "epoch": 0.673047619047619,
      "grad_norm": 0.02565022185444832,
      "learning_rate": 0.022576438263058662,
      "loss": 2.3465447425842285,
      "step": 14134
    },
    {
      "epoch": 0.6731428571428572,
      "grad_norm": 0.02726512774825096,
      "learning_rate": 0.022569863125681877,
      "loss": 2.2976207733154297,
      "step": 14136
    },
    {
      "epoch": 0.6732380952380952,
      "grad_norm": 0.02575351670384407,
      "learning_rate": 0.022563287988305092,
      "loss": 2.3273911476135254,
      "step": 14138
    },
    {
      "epoch": 0.6733333333333333,
      "grad_norm": 0.028185267001390457,
      "learning_rate": 0.022556712850928307,
      "loss": 2.3304214477539062,
      "step": 14140
    },
    {
      "epoch": 0.6734285714285714,
      "grad_norm": 0.02671932429075241,
      "learning_rate": 0.022550135850906372,
      "loss": 2.377772569656372,
      "step": 14142
    },
    {
      "epoch": 0.6735238095238095,
      "grad_norm": 0.02573077566921711,
      "learning_rate": 0.022543562576174736,
      "loss": 2.3500499725341797,
      "step": 14144
    },
    {
      "epoch": 0.6736190476190477,
      "grad_norm": 0.026090286672115326,
      "learning_rate": 0.0225369855761528,
      "loss": 2.3311400413513184,
      "step": 14146
    },
    {
      "epoch": 0.6737142857142857,
      "grad_norm": 0.02574189007282257,
      "learning_rate": 0.022530412301421165,
      "loss": 2.346457004547119,
      "step": 14148
    },
    {
      "epoch": 0.6738095238095239,
      "grad_norm": 0.026430610567331314,
      "learning_rate": 0.02252383530139923,
      "loss": 2.3684043884277344,
      "step": 14150
    },
    {
      "epoch": 0.6739047619047619,
      "grad_norm": 0.025740336626768112,
      "learning_rate": 0.022517260164022446,
      "loss": 2.3523426055908203,
      "step": 14152
    },
    {
      "epoch": 0.674,
      "grad_norm": 0.027638215571641922,
      "learning_rate": 0.02251068502664566,
      "loss": 2.3416717052459717,
      "step": 14154
    },
    {
      "epoch": 0.6740952380952381,
      "grad_norm": 0.02584807202219963,
      "learning_rate": 0.022504109889268875,
      "loss": 2.3475918769836426,
      "step": 14156
    },
    {
      "epoch": 0.6741904761904762,
      "grad_norm": 0.02657484821975231,
      "learning_rate": 0.02249753475189209,
      "loss": 2.2797489166259766,
      "step": 14158
    },
    {
      "epoch": 0.6742857142857143,
      "grad_norm": 0.02552606165409088,
      "learning_rate": 0.022490959614515305,
      "loss": 2.3261194229125977,
      "step": 14160
    },
    {
      "epoch": 0.6743809523809524,
      "grad_norm": 0.02571888640522957,
      "learning_rate": 0.02248438261449337,
      "loss": 2.320218086242676,
      "step": 14162
    },
    {
      "epoch": 0.6744761904761905,
      "grad_norm": 0.0249288659542799,
      "learning_rate": 0.022477809339761734,
      "loss": 2.333686590194702,
      "step": 14164
    },
    {
      "epoch": 0.6745714285714286,
      "grad_norm": 0.029076458886265755,
      "learning_rate": 0.0224712323397398,
      "loss": 2.361011028289795,
      "step": 14166
    },
    {
      "epoch": 0.6746666666666666,
      "grad_norm": 0.02613682858645916,
      "learning_rate": 0.022464657202363014,
      "loss": 2.3332672119140625,
      "step": 14168
    },
    {
      "epoch": 0.6747619047619048,
      "grad_norm": 0.028046879917383194,
      "learning_rate": 0.02245808206498623,
      "loss": 2.3592653274536133,
      "step": 14170
    },
    {
      "epoch": 0.6748571428571428,
      "grad_norm": 0.02558146044611931,
      "learning_rate": 0.022451506927609444,
      "loss": 2.3431482315063477,
      "step": 14172
    },
    {
      "epoch": 0.674952380952381,
      "grad_norm": 0.025567498058080673,
      "learning_rate": 0.02244493179023266,
      "loss": 2.3682188987731934,
      "step": 14174
    },
    {
      "epoch": 0.675047619047619,
      "grad_norm": 0.026470543816685677,
      "learning_rate": 0.022438356652855873,
      "loss": 2.358126163482666,
      "step": 14176
    },
    {
      "epoch": 0.6751428571428572,
      "grad_norm": 0.02913154475390911,
      "learning_rate": 0.02243177965283394,
      "loss": 2.3738248348236084,
      "step": 14178
    },
    {
      "epoch": 0.6752380952380952,
      "grad_norm": 0.02717212587594986,
      "learning_rate": 0.022425206378102303,
      "loss": 2.3654303550720215,
      "step": 14180
    },
    {
      "epoch": 0.6753333333333333,
      "grad_norm": 0.028573499992489815,
      "learning_rate": 0.022418629378080368,
      "loss": 2.3348395824432373,
      "step": 14182
    },
    {
      "epoch": 0.6754285714285714,
      "grad_norm": 0.025991572067141533,
      "learning_rate": 0.022412056103348732,
      "loss": 2.328063488006592,
      "step": 14184
    },
    {
      "epoch": 0.6755238095238095,
      "grad_norm": 0.02600674144923687,
      "learning_rate": 0.022405479103326797,
      "loss": 2.3478035926818848,
      "step": 14186
    },
    {
      "epoch": 0.6756190476190476,
      "grad_norm": 0.025750238448381424,
      "learning_rate": 0.022398903965950012,
      "loss": 2.3517653942108154,
      "step": 14188
    },
    {
      "epoch": 0.6757142857142857,
      "grad_norm": 0.025665102526545525,
      "learning_rate": 0.022392328828573227,
      "loss": 2.38053560256958,
      "step": 14190
    },
    {
      "epoch": 0.6758095238095239,
      "grad_norm": 0.026357606053352356,
      "learning_rate": 0.02238575369119644,
      "loss": 2.3256936073303223,
      "step": 14192
    },
    {
      "epoch": 0.6759047619047619,
      "grad_norm": 0.02637265995144844,
      "learning_rate": 0.022379178553819656,
      "loss": 2.340972900390625,
      "step": 14194
    },
    {
      "epoch": 0.676,
      "grad_norm": 0.02575707621872425,
      "learning_rate": 0.02237260341644287,
      "loss": 2.3326828479766846,
      "step": 14196
    },
    {
      "epoch": 0.6760952380952381,
      "grad_norm": 0.02665610797703266,
      "learning_rate": 0.022366026416420937,
      "loss": 2.379394054412842,
      "step": 14198
    },
    {
      "epoch": 0.6761904761904762,
      "grad_norm": 0.028913678601384163,
      "learning_rate": 0.0223594531416893,
      "loss": 2.3805503845214844,
      "step": 14200
    },
    {
      "epoch": 0.6762857142857143,
      "grad_norm": 0.031401678919792175,
      "learning_rate": 0.022352876141667366,
      "loss": 2.3187222480773926,
      "step": 14202
    },
    {
      "epoch": 0.6763809523809524,
      "grad_norm": 0.026788612827658653,
      "learning_rate": 0.02234630100429058,
      "loss": 2.376297950744629,
      "step": 14204
    },
    {
      "epoch": 0.6764761904761905,
      "grad_norm": 0.027100419625639915,
      "learning_rate": 0.022339725866913795,
      "loss": 2.3527684211730957,
      "step": 14206
    },
    {
      "epoch": 0.6765714285714286,
      "grad_norm": 0.027212221175432205,
      "learning_rate": 0.02233315072953701,
      "loss": 2.334700584411621,
      "step": 14208
    },
    {
      "epoch": 0.6766666666666666,
      "grad_norm": 0.028188880532979965,
      "learning_rate": 0.022326575592160225,
      "loss": 2.359984874725342,
      "step": 14210
    },
    {
      "epoch": 0.6767619047619048,
      "grad_norm": 0.026830092072486877,
      "learning_rate": 0.02232000045478344,
      "loss": 2.3399572372436523,
      "step": 14212
    },
    {
      "epoch": 0.6768571428571428,
      "grad_norm": 0.026616139337420464,
      "learning_rate": 0.022313423454761505,
      "loss": 2.359717607498169,
      "step": 14214
    },
    {
      "epoch": 0.676952380952381,
      "grad_norm": 0.027688564732670784,
      "learning_rate": 0.02230685018002987,
      "loss": 2.348177909851074,
      "step": 14216
    },
    {
      "epoch": 0.677047619047619,
      "grad_norm": 0.025868205353617668,
      "learning_rate": 0.022300273180007935,
      "loss": 2.3673505783081055,
      "step": 14218
    },
    {
      "epoch": 0.6771428571428572,
      "grad_norm": 0.02687159925699234,
      "learning_rate": 0.0222936999052763,
      "loss": 2.3516788482666016,
      "step": 14220
    },
    {
      "epoch": 0.6772380952380952,
      "grad_norm": 0.030366528779268265,
      "learning_rate": 0.022287122905254364,
      "loss": 2.406816244125366,
      "step": 14222
    },
    {
      "epoch": 0.6773333333333333,
      "grad_norm": 0.026860591024160385,
      "learning_rate": 0.02228054776787758,
      "loss": 2.3505842685699463,
      "step": 14224
    },
    {
      "epoch": 0.6774285714285714,
      "grad_norm": 0.02672349102795124,
      "learning_rate": 0.022273972630500793,
      "loss": 2.39552903175354,
      "step": 14226
    },
    {
      "epoch": 0.6775238095238095,
      "grad_norm": 0.02936403639614582,
      "learning_rate": 0.022267397493124008,
      "loss": 2.3352115154266357,
      "step": 14228
    },
    {
      "epoch": 0.6776190476190476,
      "grad_norm": 0.026220444589853287,
      "learning_rate": 0.022260822355747223,
      "loss": 2.382309675216675,
      "step": 14230
    },
    {
      "epoch": 0.6777142857142857,
      "grad_norm": 0.02609504759311676,
      "learning_rate": 0.022254247218370438,
      "loss": 2.3698956966400146,
      "step": 14232
    },
    {
      "epoch": 0.6778095238095239,
      "grad_norm": 0.027414968237280846,
      "learning_rate": 0.022247670218348503,
      "loss": 2.366523265838623,
      "step": 14234
    },
    {
      "epoch": 0.6779047619047619,
      "grad_norm": 0.025917138904333115,
      "learning_rate": 0.022241096943616867,
      "loss": 2.364741325378418,
      "step": 14236
    },
    {
      "epoch": 0.678,
      "grad_norm": 0.02831334061920643,
      "learning_rate": 0.022234519943594933,
      "loss": 2.3743019104003906,
      "step": 14238
    },
    {
      "epoch": 0.6780952380952381,
      "grad_norm": 0.02773565612733364,
      "learning_rate": 0.022227944806218147,
      "loss": 2.4045467376708984,
      "step": 14240
    },
    {
      "epoch": 0.6781904761904762,
      "grad_norm": 0.02860456518828869,
      "learning_rate": 0.022221369668841362,
      "loss": 2.345531702041626,
      "step": 14242
    },
    {
      "epoch": 0.6782857142857143,
      "grad_norm": 0.02576429955661297,
      "learning_rate": 0.022214794531464577,
      "loss": 2.3705124855041504,
      "step": 14244
    },
    {
      "epoch": 0.6783809523809524,
      "grad_norm": 0.026126984506845474,
      "learning_rate": 0.02220821939408779,
      "loss": 2.3871092796325684,
      "step": 14246
    },
    {
      "epoch": 0.6784761904761905,
      "grad_norm": 0.026461919769644737,
      "learning_rate": 0.022201644256711006,
      "loss": 2.363941192626953,
      "step": 14248
    },
    {
      "epoch": 0.6785714285714286,
      "grad_norm": 0.026133334264159203,
      "learning_rate": 0.02219506725668907,
      "loss": 2.3858015537261963,
      "step": 14250
    },
    {
      "epoch": 0.6786666666666666,
      "grad_norm": 0.02553827501833439,
      "learning_rate": 0.022188493981957436,
      "loss": 2.4005041122436523,
      "step": 14252
    },
    {
      "epoch": 0.6787619047619048,
      "grad_norm": 0.025554582476615906,
      "learning_rate": 0.0221819169819355,
      "loss": 2.390413761138916,
      "step": 14254
    },
    {
      "epoch": 0.6788571428571428,
      "grad_norm": 0.02746669575572014,
      "learning_rate": 0.022175341844558716,
      "loss": 2.412604331970215,
      "step": 14256
    },
    {
      "epoch": 0.678952380952381,
      "grad_norm": 0.025661544874310493,
      "learning_rate": 0.02216876670718193,
      "loss": 2.3878893852233887,
      "step": 14258
    },
    {
      "epoch": 0.679047619047619,
      "grad_norm": 0.027008946985006332,
      "learning_rate": 0.022162191569805145,
      "loss": 2.4090824127197266,
      "step": 14260
    },
    {
      "epoch": 0.6791428571428572,
      "grad_norm": 0.026258356869220734,
      "learning_rate": 0.02215561643242836,
      "loss": 2.400207042694092,
      "step": 14262
    },
    {
      "epoch": 0.6792380952380952,
      "grad_norm": 0.02749725803732872,
      "learning_rate": 0.022149041295051575,
      "loss": 2.3539443016052246,
      "step": 14264
    },
    {
      "epoch": 0.6793333333333333,
      "grad_norm": 0.026628592982888222,
      "learning_rate": 0.02214246615767479,
      "loss": 2.414297580718994,
      "step": 14266
    },
    {
      "epoch": 0.6794285714285714,
      "grad_norm": 0.02638169191777706,
      "learning_rate": 0.022135891020298004,
      "loss": 2.3944127559661865,
      "step": 14268
    },
    {
      "epoch": 0.6795238095238095,
      "grad_norm": 0.025522949174046516,
      "learning_rate": 0.02212931402027607,
      "loss": 2.434760570526123,
      "step": 14270
    },
    {
      "epoch": 0.6796190476190476,
      "grad_norm": 0.02499159798026085,
      "learning_rate": 0.022122740745544434,
      "loss": 2.3967278003692627,
      "step": 14272
    },
    {
      "epoch": 0.6797142857142857,
      "grad_norm": 0.026113664731383324,
      "learning_rate": 0.0221161637455225,
      "loss": 2.412475824356079,
      "step": 14274
    },
    {
      "epoch": 0.6798095238095239,
      "grad_norm": 0.02596234902739525,
      "learning_rate": 0.022109588608145714,
      "loss": 2.4302825927734375,
      "step": 14276
    },
    {
      "epoch": 0.6799047619047619,
      "grad_norm": 0.028002314269542694,
      "learning_rate": 0.02210301347076893,
      "loss": 2.4050300121307373,
      "step": 14278
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.025324463844299316,
      "learning_rate": 0.022096438333392143,
      "loss": 2.3874306678771973,
      "step": 14280
    },
    {
      "epoch": 0.6800952380952381,
      "grad_norm": 0.026687530800700188,
      "learning_rate": 0.022089863196015358,
      "loss": 2.409661293029785,
      "step": 14282
    },
    {
      "epoch": 0.6801904761904762,
      "grad_norm": 0.025254499167203903,
      "learning_rate": 0.022083288058638573,
      "loss": 2.396421432495117,
      "step": 14284
    },
    {
      "epoch": 0.6802857142857143,
      "grad_norm": 0.03022933006286621,
      "learning_rate": 0.022076711058616638,
      "loss": 2.388962507247925,
      "step": 14286
    },
    {
      "epoch": 0.6803809523809524,
      "grad_norm": 0.0307582039386034,
      "learning_rate": 0.022070137783885002,
      "loss": 2.398834705352783,
      "step": 14288
    },
    {
      "epoch": 0.6804761904761905,
      "grad_norm": 0.0290457084774971,
      "learning_rate": 0.022063560783863068,
      "loss": 2.4327034950256348,
      "step": 14290
    },
    {
      "epoch": 0.6805714285714286,
      "grad_norm": 0.02699536643922329,
      "learning_rate": 0.022056985646486282,
      "loss": 2.4164514541625977,
      "step": 14292
    },
    {
      "epoch": 0.6806666666666666,
      "grad_norm": 0.02589573711156845,
      "learning_rate": 0.022050410509109497,
      "loss": 2.4212918281555176,
      "step": 14294
    },
    {
      "epoch": 0.6807619047619048,
      "grad_norm": 0.02583828754723072,
      "learning_rate": 0.022043835371732712,
      "loss": 2.3624682426452637,
      "step": 14296
    },
    {
      "epoch": 0.6808571428571428,
      "grad_norm": 0.027167830616235733,
      "learning_rate": 0.022037260234355927,
      "loss": 2.4183242321014404,
      "step": 14298
    },
    {
      "epoch": 0.680952380952381,
      "grad_norm": 0.026475511491298676,
      "learning_rate": 0.02203068509697914,
      "loss": 2.399467945098877,
      "step": 14300
    },
    {
      "epoch": 0.681047619047619,
      "grad_norm": 0.025802485644817352,
      "learning_rate": 0.022024109959602356,
      "loss": 2.437802791595459,
      "step": 14302
    },
    {
      "epoch": 0.6811428571428572,
      "grad_norm": 0.02623749151825905,
      "learning_rate": 0.02201753482222557,
      "loss": 2.457392930984497,
      "step": 14304
    },
    {
      "epoch": 0.6812380952380952,
      "grad_norm": 0.026623068377375603,
      "learning_rate": 0.022010957822203636,
      "loss": 2.402958393096924,
      "step": 14306
    },
    {
      "epoch": 0.6813333333333333,
      "grad_norm": 0.028010301291942596,
      "learning_rate": 0.022004384547472,
      "loss": 2.441749095916748,
      "step": 14308
    },
    {
      "epoch": 0.6814285714285714,
      "grad_norm": 0.029308924451470375,
      "learning_rate": 0.021997809410095215,
      "loss": 2.436034679412842,
      "step": 14310
    },
    {
      "epoch": 0.6815238095238095,
      "grad_norm": 0.026763517409563065,
      "learning_rate": 0.02199123241007328,
      "loss": 2.45927357673645,
      "step": 14312
    },
    {
      "epoch": 0.6816190476190476,
      "grad_norm": 0.031089089810848236,
      "learning_rate": 0.021984659135341644,
      "loss": 2.4555768966674805,
      "step": 14314
    },
    {
      "epoch": 0.6817142857142857,
      "grad_norm": 0.02898036316037178,
      "learning_rate": 0.02197808213531971,
      "loss": 2.4297237396240234,
      "step": 14316
    },
    {
      "epoch": 0.6818095238095238,
      "grad_norm": 0.02564515545964241,
      "learning_rate": 0.021971506997942924,
      "loss": 2.394746780395508,
      "step": 14318
    },
    {
      "epoch": 0.6819047619047619,
      "grad_norm": 0.02700468711555004,
      "learning_rate": 0.02196493186056614,
      "loss": 2.4197678565979004,
      "step": 14320
    },
    {
      "epoch": 0.682,
      "grad_norm": 0.02571718767285347,
      "learning_rate": 0.021958356723189354,
      "loss": 2.4189515113830566,
      "step": 14322
    },
    {
      "epoch": 0.6820952380952381,
      "grad_norm": 0.02590649574995041,
      "learning_rate": 0.02195178158581257,
      "loss": 2.4208896160125732,
      "step": 14324
    },
    {
      "epoch": 0.6821904761904762,
      "grad_norm": 0.02553033083677292,
      "learning_rate": 0.021945206448435783,
      "loss": 2.485605239868164,
      "step": 14326
    },
    {
      "epoch": 0.6822857142857143,
      "grad_norm": 0.0329815074801445,
      "learning_rate": 0.02193862944841385,
      "loss": 2.4067459106445312,
      "step": 14328
    },
    {
      "epoch": 0.6823809523809524,
      "grad_norm": 0.026898540556430817,
      "learning_rate": 0.021932056173682213,
      "loss": 2.4341189861297607,
      "step": 14330
    },
    {
      "epoch": 0.6824761904761905,
      "grad_norm": 0.027871474623680115,
      "learning_rate": 0.02192547917366028,
      "loss": 2.432192802429199,
      "step": 14332
    },
    {
      "epoch": 0.6825714285714286,
      "grad_norm": 0.026132985949516296,
      "learning_rate": 0.021918905898928642,
      "loss": 2.4395804405212402,
      "step": 14334
    },
    {
      "epoch": 0.6826666666666666,
      "grad_norm": 0.024958323687314987,
      "learning_rate": 0.021912328898906708,
      "loss": 2.409780979156494,
      "step": 14336
    },
    {
      "epoch": 0.6827619047619048,
      "grad_norm": 0.026757871732115746,
      "learning_rate": 0.021905753761529922,
      "loss": 2.473374843597412,
      "step": 14338
    },
    {
      "epoch": 0.6828571428571428,
      "grad_norm": 0.02584773488342762,
      "learning_rate": 0.021899178624153137,
      "loss": 2.4597673416137695,
      "step": 14340
    },
    {
      "epoch": 0.682952380952381,
      "grad_norm": 0.026523733511567116,
      "learning_rate": 0.021892603486776352,
      "loss": 2.416377544403076,
      "step": 14342
    },
    {
      "epoch": 0.683047619047619,
      "grad_norm": 0.027639586478471756,
      "learning_rate": 0.021886028349399567,
      "loss": 2.4659852981567383,
      "step": 14344
    },
    {
      "epoch": 0.6831428571428572,
      "grad_norm": 0.02840779349207878,
      "learning_rate": 0.02187945321202278,
      "loss": 2.4775590896606445,
      "step": 14346
    },
    {
      "epoch": 0.6832380952380952,
      "grad_norm": 0.028200587257742882,
      "learning_rate": 0.021872876212000847,
      "loss": 2.510634183883667,
      "step": 14348
    },
    {
      "epoch": 0.6833333333333333,
      "grad_norm": 0.03174632042646408,
      "learning_rate": 0.02186630293726921,
      "loss": 2.444667339324951,
      "step": 14350
    },
    {
      "epoch": 0.6834285714285714,
      "grad_norm": 0.025868484750390053,
      "learning_rate": 0.021859725937247276,
      "loss": 2.476513385772705,
      "step": 14352
    },
    {
      "epoch": 0.6835238095238095,
      "grad_norm": 0.026175998151302338,
      "learning_rate": 0.02185315079987049,
      "loss": 2.4638843536376953,
      "step": 14354
    },
    {
      "epoch": 0.6836190476190476,
      "grad_norm": 0.027063759043812752,
      "learning_rate": 0.021846575662493706,
      "loss": 2.4731035232543945,
      "step": 14356
    },
    {
      "epoch": 0.6837142857142857,
      "grad_norm": 0.025788689032197,
      "learning_rate": 0.02184000052511692,
      "loss": 2.510831356048584,
      "step": 14358
    },
    {
      "epoch": 0.6838095238095238,
      "grad_norm": 0.026682864874601364,
      "learning_rate": 0.021833425387740135,
      "loss": 2.4634671211242676,
      "step": 14360
    },
    {
      "epoch": 0.6839047619047619,
      "grad_norm": 0.026866525411605835,
      "learning_rate": 0.02182685025036335,
      "loss": 2.486124277114868,
      "step": 14362
    },
    {
      "epoch": 0.684,
      "grad_norm": 0.02617553249001503,
      "learning_rate": 0.021820273250341415,
      "loss": 2.4758143424987793,
      "step": 14364
    },
    {
      "epoch": 0.6840952380952381,
      "grad_norm": 0.026921017095446587,
      "learning_rate": 0.02181369997560978,
      "loss": 2.4772210121154785,
      "step": 14366
    },
    {
      "epoch": 0.6841904761904762,
      "grad_norm": 0.026493124663829803,
      "learning_rate": 0.021807122975587845,
      "loss": 2.5057992935180664,
      "step": 14368
    },
    {
      "epoch": 0.6842857142857143,
      "grad_norm": 0.0257171168923378,
      "learning_rate": 0.02180054783821106,
      "loss": 2.5110838413238525,
      "step": 14370
    },
    {
      "epoch": 0.6843809523809524,
      "grad_norm": 0.026317063719034195,
      "learning_rate": 0.021793972700834274,
      "loss": 2.477952003479004,
      "step": 14372
    },
    {
      "epoch": 0.6844761904761905,
      "grad_norm": 0.029917581006884575,
      "learning_rate": 0.02178739756345749,
      "loss": 2.4533047676086426,
      "step": 14374
    },
    {
      "epoch": 0.6845714285714286,
      "grad_norm": 0.02744380198419094,
      "learning_rate": 0.021780822426080704,
      "loss": 2.4842727184295654,
      "step": 14376
    },
    {
      "epoch": 0.6846666666666666,
      "grad_norm": 0.02651776559650898,
      "learning_rate": 0.02177424728870392,
      "loss": 2.4573609828948975,
      "step": 14378
    },
    {
      "epoch": 0.6847619047619048,
      "grad_norm": 0.027664082124829292,
      "learning_rate": 0.021767672151327133,
      "loss": 2.472454071044922,
      "step": 14380
    },
    {
      "epoch": 0.6848571428571428,
      "grad_norm": 0.025912364944815636,
      "learning_rate": 0.021761097013950348,
      "loss": 2.467020034790039,
      "step": 14382
    },
    {
      "epoch": 0.684952380952381,
      "grad_norm": 0.02736453153192997,
      "learning_rate": 0.021754520013928413,
      "loss": 2.5155277252197266,
      "step": 14384
    },
    {
      "epoch": 0.685047619047619,
      "grad_norm": 0.027186498045921326,
      "learning_rate": 0.021747946739196777,
      "loss": 2.485295057296753,
      "step": 14386
    },
    {
      "epoch": 0.6851428571428572,
      "grad_norm": 0.027442874386906624,
      "learning_rate": 0.021741369739174843,
      "loss": 2.4860663414001465,
      "step": 14388
    },
    {
      "epoch": 0.6852380952380952,
      "grad_norm": 0.02808147855103016,
      "learning_rate": 0.021734794601798058,
      "loss": 2.478114604949951,
      "step": 14390
    },
    {
      "epoch": 0.6853333333333333,
      "grad_norm": 0.03156333044171333,
      "learning_rate": 0.021728219464421272,
      "loss": 2.4982268810272217,
      "step": 14392
    },
    {
      "epoch": 0.6854285714285714,
      "grad_norm": 0.027102423831820488,
      "learning_rate": 0.021721644327044487,
      "loss": 2.4731314182281494,
      "step": 14394
    },
    {
      "epoch": 0.6855238095238095,
      "grad_norm": 0.027780501171946526,
      "learning_rate": 0.0217150691896677,
      "loss": 2.4887125492095947,
      "step": 14396
    },
    {
      "epoch": 0.6856190476190476,
      "grad_norm": 0.0322355218231678,
      "learning_rate": 0.021708494052290916,
      "loss": 2.5231738090515137,
      "step": 14398
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.025297246873378754,
      "learning_rate": 0.021701917052268982,
      "loss": 2.4938037395477295,
      "step": 14400
    },
    {
      "epoch": 0.6858095238095238,
      "grad_norm": 0.026755668222904205,
      "learning_rate": 0.021695343777537346,
      "loss": 2.491833209991455,
      "step": 14402
    },
    {
      "epoch": 0.6859047619047619,
      "grad_norm": 0.026388071477413177,
      "learning_rate": 0.02168876677751541,
      "loss": 2.4873998165130615,
      "step": 14404
    },
    {
      "epoch": 0.686,
      "grad_norm": 0.02588014304637909,
      "learning_rate": 0.021682191640138626,
      "loss": 2.5016121864318848,
      "step": 14406
    },
    {
      "epoch": 0.6860952380952381,
      "grad_norm": 0.030544063076376915,
      "learning_rate": 0.02167561650276184,
      "loss": 2.5170769691467285,
      "step": 14408
    },
    {
      "epoch": 0.6861904761904762,
      "grad_norm": 0.026882056146860123,
      "learning_rate": 0.021669041365385056,
      "loss": 2.5012431144714355,
      "step": 14410
    },
    {
      "epoch": 0.6862857142857143,
      "grad_norm": 0.025865042582154274,
      "learning_rate": 0.02166246622800827,
      "loss": 2.5026803016662598,
      "step": 14412
    },
    {
      "epoch": 0.6863809523809524,
      "grad_norm": 0.02553933672606945,
      "learning_rate": 0.021655891090631485,
      "loss": 2.507570743560791,
      "step": 14414
    },
    {
      "epoch": 0.6864761904761905,
      "grad_norm": 0.02699315920472145,
      "learning_rate": 0.0216493159532547,
      "loss": 2.5128509998321533,
      "step": 14416
    },
    {
      "epoch": 0.6865714285714286,
      "grad_norm": 0.027075055986642838,
      "learning_rate": 0.021642740815877914,
      "loss": 2.5267462730407715,
      "step": 14418
    },
    {
      "epoch": 0.6866666666666666,
      "grad_norm": 0.02633160538971424,
      "learning_rate": 0.02163616381585598,
      "loss": 2.5350351333618164,
      "step": 14420
    },
    {
      "epoch": 0.6867619047619048,
      "grad_norm": 0.026895737275481224,
      "learning_rate": 0.021629590541124344,
      "loss": 2.5764830112457275,
      "step": 14422
    },
    {
      "epoch": 0.6868571428571428,
      "grad_norm": 0.02620691806077957,
      "learning_rate": 0.02162301354110241,
      "loss": 2.5129332542419434,
      "step": 14424
    },
    {
      "epoch": 0.686952380952381,
      "grad_norm": 0.026188381016254425,
      "learning_rate": 0.021616438403725624,
      "loss": 2.509998321533203,
      "step": 14426
    },
    {
      "epoch": 0.687047619047619,
      "grad_norm": 0.027325386181473732,
      "learning_rate": 0.02160986326634884,
      "loss": 2.5380911827087402,
      "step": 14428
    },
    {
      "epoch": 0.6871428571428572,
      "grad_norm": 0.026047343388199806,
      "learning_rate": 0.021603288128972054,
      "loss": 2.5024850368499756,
      "step": 14430
    },
    {
      "epoch": 0.6872380952380952,
      "grad_norm": 0.02661171182990074,
      "learning_rate": 0.021596712991595268,
      "loss": 2.510890245437622,
      "step": 14432
    },
    {
      "epoch": 0.6873333333333334,
      "grad_norm": 0.0272163487970829,
      "learning_rate": 0.021590137854218483,
      "loss": 2.5208826065063477,
      "step": 14434
    },
    {
      "epoch": 0.6874285714285714,
      "grad_norm": 0.03078778274357319,
      "learning_rate": 0.02158356085419655,
      "loss": 2.485194206237793,
      "step": 14436
    },
    {
      "epoch": 0.6875238095238095,
      "grad_norm": 0.02616221457719803,
      "learning_rate": 0.021576987579464912,
      "loss": 2.5186991691589355,
      "step": 14438
    },
    {
      "epoch": 0.6876190476190476,
      "grad_norm": 0.025739990174770355,
      "learning_rate": 0.021570410579442978,
      "loss": 2.5133700370788574,
      "step": 14440
    },
    {
      "epoch": 0.6877142857142857,
      "grad_norm": 0.02650393545627594,
      "learning_rate": 0.021563835442066193,
      "loss": 2.4936816692352295,
      "step": 14442
    },
    {
      "epoch": 0.6878095238095238,
      "grad_norm": 0.028089942410588264,
      "learning_rate": 0.021557260304689407,
      "loss": 2.4941787719726562,
      "step": 14444
    },
    {
      "epoch": 0.6879047619047619,
      "grad_norm": 0.026486651971936226,
      "learning_rate": 0.021550685167312622,
      "loss": 2.4993410110473633,
      "step": 14446
    },
    {
      "epoch": 0.688,
      "grad_norm": 0.03068563900887966,
      "learning_rate": 0.021544110029935837,
      "loss": 2.5324153900146484,
      "step": 14448
    },
    {
      "epoch": 0.6880952380952381,
      "grad_norm": 0.026739070191979408,
      "learning_rate": 0.02153753489255905,
      "loss": 2.5231122970581055,
      "step": 14450
    },
    {
      "epoch": 0.6881904761904762,
      "grad_norm": 0.0267905592918396,
      "learning_rate": 0.021530959755182266,
      "loss": 2.528949737548828,
      "step": 14452
    },
    {
      "epoch": 0.6882857142857143,
      "grad_norm": 0.025917910039424896,
      "learning_rate": 0.02152438461780548,
      "loss": 2.5158581733703613,
      "step": 14454
    },
    {
      "epoch": 0.6883809523809524,
      "grad_norm": 0.024836445227265358,
      "learning_rate": 0.021517807617783546,
      "loss": 2.4806480407714844,
      "step": 14456
    },
    {
      "epoch": 0.6884761904761905,
      "grad_norm": 0.02783723548054695,
      "learning_rate": 0.02151123434305191,
      "loss": 2.529407024383545,
      "step": 14458
    },
    {
      "epoch": 0.6885714285714286,
      "grad_norm": 0.026116373017430305,
      "learning_rate": 0.021504657343029976,
      "loss": 2.503361463546753,
      "step": 14460
    },
    {
      "epoch": 0.6886666666666666,
      "grad_norm": 0.027094736695289612,
      "learning_rate": 0.02149808220565319,
      "loss": 2.5524842739105225,
      "step": 14462
    },
    {
      "epoch": 0.6887619047619048,
      "grad_norm": 0.02640475519001484,
      "learning_rate": 0.021491507068276405,
      "loss": 2.5467276573181152,
      "step": 14464
    },
    {
      "epoch": 0.6888571428571428,
      "grad_norm": 0.025560077279806137,
      "learning_rate": 0.02148493193089962,
      "loss": 2.52569317817688,
      "step": 14466
    },
    {
      "epoch": 0.688952380952381,
      "grad_norm": 0.02610349841415882,
      "learning_rate": 0.021478356793522835,
      "loss": 2.4870223999023438,
      "step": 14468
    },
    {
      "epoch": 0.689047619047619,
      "grad_norm": 0.026088973507285118,
      "learning_rate": 0.02147178165614605,
      "loss": 2.5371413230895996,
      "step": 14470
    },
    {
      "epoch": 0.6891428571428572,
      "grad_norm": 0.028223123401403427,
      "learning_rate": 0.021465204656124115,
      "loss": 2.498882293701172,
      "step": 14472
    },
    {
      "epoch": 0.6892380952380952,
      "grad_norm": 0.02862071432173252,
      "learning_rate": 0.02145863138139248,
      "loss": 2.5237646102905273,
      "step": 14474
    },
    {
      "epoch": 0.6893333333333334,
      "grad_norm": 0.02579565905034542,
      "learning_rate": 0.021452054381370544,
      "loss": 2.518064022064209,
      "step": 14476
    },
    {
      "epoch": 0.6894285714285714,
      "grad_norm": 0.02788950316607952,
      "learning_rate": 0.02144547924399376,
      "loss": 2.5035693645477295,
      "step": 14478
    },
    {
      "epoch": 0.6895238095238095,
      "grad_norm": 0.026234902441501617,
      "learning_rate": 0.021438904106616974,
      "loss": 2.522111177444458,
      "step": 14480
    },
    {
      "epoch": 0.6896190476190476,
      "grad_norm": 0.02667589671909809,
      "learning_rate": 0.02143232896924019,
      "loss": 2.4777445793151855,
      "step": 14482
    },
    {
      "epoch": 0.6897142857142857,
      "grad_norm": 0.02663242258131504,
      "learning_rate": 0.021425753831863403,
      "loss": 2.511826753616333,
      "step": 14484
    },
    {
      "epoch": 0.6898095238095238,
      "grad_norm": 0.02670823037624359,
      "learning_rate": 0.021419178694486618,
      "loss": 2.4945549964904785,
      "step": 14486
    },
    {
      "epoch": 0.6899047619047619,
      "grad_norm": 0.030884264037013054,
      "learning_rate": 0.021412601694464684,
      "loss": 2.5327811241149902,
      "step": 14488
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.034166306257247925,
      "learning_rate": 0.021406028419733047,
      "loss": 2.4992527961730957,
      "step": 14490
    },
    {
      "epoch": 0.6900952380952381,
      "grad_norm": 0.02955305390059948,
      "learning_rate": 0.021399451419711113,
      "loss": 2.52358341217041,
      "step": 14492
    },
    {
      "epoch": 0.6901904761904762,
      "grad_norm": 0.02889241836965084,
      "learning_rate": 0.021392878144979477,
      "loss": 2.502763271331787,
      "step": 14494
    },
    {
      "epoch": 0.6902857142857143,
      "grad_norm": 0.02886061742901802,
      "learning_rate": 0.021386301144957542,
      "loss": 2.4821791648864746,
      "step": 14496
    },
    {
      "epoch": 0.6903809523809524,
      "grad_norm": 0.025672340765595436,
      "learning_rate": 0.021379726007580757,
      "loss": 2.5150623321533203,
      "step": 14498
    },
    {
      "epoch": 0.6904761904761905,
      "grad_norm": 0.02639782801270485,
      "learning_rate": 0.021373150870203972,
      "loss": 2.4921810626983643,
      "step": 14500
    },
    {
      "epoch": 0.6905714285714286,
      "grad_norm": 0.026425331830978394,
      "learning_rate": 0.021366575732827187,
      "loss": 2.4665417671203613,
      "step": 14502
    },
    {
      "epoch": 0.6906666666666667,
      "grad_norm": 0.0264181699603796,
      "learning_rate": 0.0213600005954504,
      "loss": 2.5102055072784424,
      "step": 14504
    },
    {
      "epoch": 0.6907619047619048,
      "grad_norm": 0.026200270280241966,
      "learning_rate": 0.021353425458073616,
      "loss": 2.5381531715393066,
      "step": 14506
    },
    {
      "epoch": 0.6908571428571428,
      "grad_norm": 0.0274477768689394,
      "learning_rate": 0.02134684845805168,
      "loss": 2.508014440536499,
      "step": 14508
    },
    {
      "epoch": 0.690952380952381,
      "grad_norm": 0.026608731597661972,
      "learning_rate": 0.021340275183320045,
      "loss": 2.538602352142334,
      "step": 14510
    },
    {
      "epoch": 0.691047619047619,
      "grad_norm": 0.02725883387029171,
      "learning_rate": 0.02133369818329811,
      "loss": 2.5074362754821777,
      "step": 14512
    },
    {
      "epoch": 0.6911428571428572,
      "grad_norm": 0.028683673590421677,
      "learning_rate": 0.021327123045921326,
      "loss": 2.5001912117004395,
      "step": 14514
    },
    {
      "epoch": 0.6912380952380952,
      "grad_norm": 0.026495464146137238,
      "learning_rate": 0.02132054790854454,
      "loss": 2.5024147033691406,
      "step": 14516
    },
    {
      "epoch": 0.6913333333333334,
      "grad_norm": 0.02787492796778679,
      "learning_rate": 0.021313972771167755,
      "loss": 2.5106048583984375,
      "step": 14518
    },
    {
      "epoch": 0.6914285714285714,
      "grad_norm": 0.026119371876120567,
      "learning_rate": 0.02130739763379097,
      "loss": 2.5173349380493164,
      "step": 14520
    },
    {
      "epoch": 0.6915238095238095,
      "grad_norm": 0.025103632360696793,
      "learning_rate": 0.021300822496414185,
      "loss": 2.5435872077941895,
      "step": 14522
    },
    {
      "epoch": 0.6916190476190476,
      "grad_norm": 0.025919586420059204,
      "learning_rate": 0.02129424549639225,
      "loss": 2.5197906494140625,
      "step": 14524
    },
    {
      "epoch": 0.6917142857142857,
      "grad_norm": 0.026389971375465393,
      "learning_rate": 0.021287672221660614,
      "loss": 2.5411760807037354,
      "step": 14526
    },
    {
      "epoch": 0.6918095238095238,
      "grad_norm": 0.02538253925740719,
      "learning_rate": 0.02128109522163868,
      "loss": 2.525963068008423,
      "step": 14528
    },
    {
      "epoch": 0.6919047619047619,
      "grad_norm": 0.026247067376971245,
      "learning_rate": 0.021274521946907043,
      "loss": 2.507479190826416,
      "step": 14530
    },
    {
      "epoch": 0.692,
      "grad_norm": 0.02692943997681141,
      "learning_rate": 0.02126794494688511,
      "loss": 2.5075511932373047,
      "step": 14532
    },
    {
      "epoch": 0.6920952380952381,
      "grad_norm": 0.028877347707748413,
      "learning_rate": 0.021261369809508324,
      "loss": 2.5383219718933105,
      "step": 14534
    },
    {
      "epoch": 0.6921904761904762,
      "grad_norm": 0.028957856819033623,
      "learning_rate": 0.02125479467213154,
      "loss": 2.5175061225891113,
      "step": 14536
    },
    {
      "epoch": 0.6922857142857143,
      "grad_norm": 0.026154063642024994,
      "learning_rate": 0.021248219534754753,
      "loss": 2.5040440559387207,
      "step": 14538
    },
    {
      "epoch": 0.6923809523809524,
      "grad_norm": 0.028972141444683075,
      "learning_rate": 0.021241644397377968,
      "loss": 2.5212810039520264,
      "step": 14540
    },
    {
      "epoch": 0.6924761904761905,
      "grad_norm": 0.029285503551363945,
      "learning_rate": 0.021235069260001183,
      "loss": 2.5647873878479004,
      "step": 14542
    },
    {
      "epoch": 0.6925714285714286,
      "grad_norm": 0.02671969123184681,
      "learning_rate": 0.021228492259979248,
      "loss": 2.5056960582733154,
      "step": 14544
    },
    {
      "epoch": 0.6926666666666667,
      "grad_norm": 0.027942335233092308,
      "learning_rate": 0.021221918985247612,
      "loss": 2.540281295776367,
      "step": 14546
    },
    {
      "epoch": 0.6927619047619048,
      "grad_norm": 0.025368256494402885,
      "learning_rate": 0.021215341985225677,
      "loss": 2.4900155067443848,
      "step": 14548
    },
    {
      "epoch": 0.6928571428571428,
      "grad_norm": 0.026230528950691223,
      "learning_rate": 0.021208766847848892,
      "loss": 2.524752616882324,
      "step": 14550
    },
    {
      "epoch": 0.692952380952381,
      "grad_norm": 0.025077572092413902,
      "learning_rate": 0.021202191710472107,
      "loss": 2.4947080612182617,
      "step": 14552
    },
    {
      "epoch": 0.693047619047619,
      "grad_norm": 0.026252945885062218,
      "learning_rate": 0.02119561657309532,
      "loss": 2.518186330795288,
      "step": 14554
    },
    {
      "epoch": 0.6931428571428572,
      "grad_norm": 0.02932296134531498,
      "learning_rate": 0.021189041435718536,
      "loss": 2.476065158843994,
      "step": 14556
    },
    {
      "epoch": 0.6932380952380952,
      "grad_norm": 0.02610969915986061,
      "learning_rate": 0.02118246629834175,
      "loss": 2.4834985733032227,
      "step": 14558
    },
    {
      "epoch": 0.6933333333333334,
      "grad_norm": 0.0275430828332901,
      "learning_rate": 0.021175889298319817,
      "loss": 2.4986472129821777,
      "step": 14560
    },
    {
      "epoch": 0.6934285714285714,
      "grad_norm": 0.026103859767317772,
      "learning_rate": 0.02116931602358818,
      "loss": 2.547746181488037,
      "step": 14562
    },
    {
      "epoch": 0.6935238095238095,
      "grad_norm": 0.0278952457010746,
      "learning_rate": 0.021162739023566246,
      "loss": 2.6021852493286133,
      "step": 14564
    },
    {
      "epoch": 0.6936190476190476,
      "grad_norm": 0.026737507432699203,
      "learning_rate": 0.02115616574883461,
      "loss": 2.5392885208129883,
      "step": 14566
    },
    {
      "epoch": 0.6937142857142857,
      "grad_norm": 0.02593279629945755,
      "learning_rate": 0.021149588748812675,
      "loss": 2.5339198112487793,
      "step": 14568
    },
    {
      "epoch": 0.6938095238095238,
      "grad_norm": 0.02997896820306778,
      "learning_rate": 0.02114301361143589,
      "loss": 2.528355598449707,
      "step": 14570
    },
    {
      "epoch": 0.6939047619047619,
      "grad_norm": 0.029007168486714363,
      "learning_rate": 0.021136438474059105,
      "loss": 2.5482685565948486,
      "step": 14572
    },
    {
      "epoch": 0.694,
      "grad_norm": 0.03490349277853966,
      "learning_rate": 0.02112986333668232,
      "loss": 2.54689359664917,
      "step": 14574
    },
    {
      "epoch": 0.6940952380952381,
      "grad_norm": 0.031666599214076996,
      "learning_rate": 0.021123288199305534,
      "loss": 2.5045738220214844,
      "step": 14576
    },
    {
      "epoch": 0.6941904761904761,
      "grad_norm": 0.029333319514989853,
      "learning_rate": 0.02111671306192875,
      "loss": 2.508307456970215,
      "step": 14578
    },
    {
      "epoch": 0.6942857142857143,
      "grad_norm": 0.03230652958154678,
      "learning_rate": 0.021110136061906815,
      "loss": 2.507152557373047,
      "step": 14580
    },
    {
      "epoch": 0.6943809523809524,
      "grad_norm": 0.02691986784338951,
      "learning_rate": 0.02110356278717518,
      "loss": 2.5135295391082764,
      "step": 14582
    },
    {
      "epoch": 0.6944761904761905,
      "grad_norm": 0.028594354167580605,
      "learning_rate": 0.021096985787153244,
      "loss": 2.5378832817077637,
      "step": 14584
    },
    {
      "epoch": 0.6945714285714286,
      "grad_norm": 0.02735300548374653,
      "learning_rate": 0.02109041064977646,
      "loss": 2.5253496170043945,
      "step": 14586
    },
    {
      "epoch": 0.6946666666666667,
      "grad_norm": 0.03185562789440155,
      "learning_rate": 0.021083835512399673,
      "loss": 2.5570826530456543,
      "step": 14588
    },
    {
      "epoch": 0.6947619047619048,
      "grad_norm": 0.026325583457946777,
      "learning_rate": 0.021077260375022888,
      "loss": 2.5240161418914795,
      "step": 14590
    },
    {
      "epoch": 0.6948571428571428,
      "grad_norm": 0.029934845864772797,
      "learning_rate": 0.021070685237646103,
      "loss": 2.5226263999938965,
      "step": 14592
    },
    {
      "epoch": 0.694952380952381,
      "grad_norm": 0.0273821409791708,
      "learning_rate": 0.021064110100269318,
      "loss": 2.511660575866699,
      "step": 14594
    },
    {
      "epoch": 0.695047619047619,
      "grad_norm": 0.02660478465259075,
      "learning_rate": 0.021057533100247383,
      "loss": 2.5356764793395996,
      "step": 14596
    },
    {
      "epoch": 0.6951428571428572,
      "grad_norm": 0.026538651436567307,
      "learning_rate": 0.021050959825515747,
      "loss": 2.5073893070220947,
      "step": 14598
    },
    {
      "epoch": 0.6952380952380952,
      "grad_norm": 0.025758637115359306,
      "learning_rate": 0.021044382825493813,
      "loss": 2.5069642066955566,
      "step": 14600
    },
    {
      "epoch": 0.6953333333333334,
      "grad_norm": 0.027144264429807663,
      "learning_rate": 0.021037807688117027,
      "loss": 2.5115089416503906,
      "step": 14602
    },
    {
      "epoch": 0.6954285714285714,
      "grad_norm": 0.025766650214791298,
      "learning_rate": 0.021031232550740242,
      "loss": 2.464810371398926,
      "step": 14604
    },
    {
      "epoch": 0.6955238095238095,
      "grad_norm": 0.02697635255753994,
      "learning_rate": 0.021024657413363457,
      "loss": 2.530963897705078,
      "step": 14606
    },
    {
      "epoch": 0.6956190476190476,
      "grad_norm": 0.025838395580649376,
      "learning_rate": 0.02101808227598667,
      "loss": 2.4971041679382324,
      "step": 14608
    },
    {
      "epoch": 0.6957142857142857,
      "grad_norm": 0.025739748030900955,
      "learning_rate": 0.021011507138609886,
      "loss": 2.5004348754882812,
      "step": 14610
    },
    {
      "epoch": 0.6958095238095238,
      "grad_norm": 0.027137575671076775,
      "learning_rate": 0.0210049320012331,
      "loss": 2.5263466835021973,
      "step": 14612
    },
    {
      "epoch": 0.6959047619047619,
      "grad_norm": 0.026896720752120018,
      "learning_rate": 0.020998356863856316,
      "loss": 2.492546558380127,
      "step": 14614
    },
    {
      "epoch": 0.696,
      "grad_norm": 0.026811281219124794,
      "learning_rate": 0.02099177986383438,
      "loss": 2.5527234077453613,
      "step": 14616
    },
    {
      "epoch": 0.6960952380952381,
      "grad_norm": 0.025771405547857285,
      "learning_rate": 0.020985206589102745,
      "loss": 2.516263723373413,
      "step": 14618
    },
    {
      "epoch": 0.6961904761904761,
      "grad_norm": 0.025339940562844276,
      "learning_rate": 0.02097862958908081,
      "loss": 2.522724151611328,
      "step": 14620
    },
    {
      "epoch": 0.6962857142857143,
      "grad_norm": 0.025828110054135323,
      "learning_rate": 0.020972054451704025,
      "loss": 2.4817776679992676,
      "step": 14622
    },
    {
      "epoch": 0.6963809523809524,
      "grad_norm": 0.028312403708696365,
      "learning_rate": 0.02096547931432724,
      "loss": 2.498358726501465,
      "step": 14624
    },
    {
      "epoch": 0.6964761904761905,
      "grad_norm": 0.027928493916988373,
      "learning_rate": 0.020958904176950455,
      "loss": 2.49080228805542,
      "step": 14626
    },
    {
      "epoch": 0.6965714285714286,
      "grad_norm": 0.026526130735874176,
      "learning_rate": 0.02095232903957367,
      "loss": 2.5001049041748047,
      "step": 14628
    },
    {
      "epoch": 0.6966666666666667,
      "grad_norm": 0.0261798407882452,
      "learning_rate": 0.020945753902196884,
      "loss": 2.5447192192077637,
      "step": 14630
    },
    {
      "epoch": 0.6967619047619048,
      "grad_norm": 0.026707995682954788,
      "learning_rate": 0.02093917690217495,
      "loss": 2.5177066326141357,
      "step": 14632
    },
    {
      "epoch": 0.6968571428571428,
      "grad_norm": 0.02530074119567871,
      "learning_rate": 0.020932603627443314,
      "loss": 2.4831314086914062,
      "step": 14634
    },
    {
      "epoch": 0.696952380952381,
      "grad_norm": 0.02631053701043129,
      "learning_rate": 0.02092602662742138,
      "loss": 2.513397216796875,
      "step": 14636
    },
    {
      "epoch": 0.697047619047619,
      "grad_norm": 0.025417771190404892,
      "learning_rate": 0.020919451490044594,
      "loss": 2.4435079097747803,
      "step": 14638
    },
    {
      "epoch": 0.6971428571428572,
      "grad_norm": 0.027668830007314682,
      "learning_rate": 0.02091287635266781,
      "loss": 2.5301003456115723,
      "step": 14640
    },
    {
      "epoch": 0.6972380952380952,
      "grad_norm": 0.027569200843572617,
      "learning_rate": 0.020906301215291023,
      "loss": 2.5159215927124023,
      "step": 14642
    },
    {
      "epoch": 0.6973333333333334,
      "grad_norm": 0.03418632969260216,
      "learning_rate": 0.020899726077914238,
      "loss": 2.5296850204467773,
      "step": 14644
    },
    {
      "epoch": 0.6974285714285714,
      "grad_norm": 0.02758018486201763,
      "learning_rate": 0.020893150940537453,
      "loss": 2.513206958770752,
      "step": 14646
    },
    {
      "epoch": 0.6975238095238095,
      "grad_norm": 0.026554817333817482,
      "learning_rate": 0.020886575803160667,
      "loss": 2.4885988235473633,
      "step": 14648
    },
    {
      "epoch": 0.6976190476190476,
      "grad_norm": 0.030617624521255493,
      "learning_rate": 0.020880000665783882,
      "loss": 2.491032361984253,
      "step": 14650
    },
    {
      "epoch": 0.6977142857142857,
      "grad_norm": 0.029850374907255173,
      "learning_rate": 0.020873423665761948,
      "loss": 2.4812893867492676,
      "step": 14652
    },
    {
      "epoch": 0.6978095238095238,
      "grad_norm": 0.026162857189774513,
      "learning_rate": 0.02086685039103031,
      "loss": 2.5203301906585693,
      "step": 14654
    },
    {
      "epoch": 0.6979047619047619,
      "grad_norm": 0.0289494339376688,
      "learning_rate": 0.020860273391008377,
      "loss": 2.4732978343963623,
      "step": 14656
    },
    {
      "epoch": 0.698,
      "grad_norm": 0.026381706818938255,
      "learning_rate": 0.020853698253631592,
      "loss": 2.4741268157958984,
      "step": 14658
    },
    {
      "epoch": 0.6980952380952381,
      "grad_norm": 0.026014214381575584,
      "learning_rate": 0.020847123116254807,
      "loss": 2.4805455207824707,
      "step": 14660
    },
    {
      "epoch": 0.6981904761904761,
      "grad_norm": 0.027585921809077263,
      "learning_rate": 0.02084054797887802,
      "loss": 2.4892024993896484,
      "step": 14662
    },
    {
      "epoch": 0.6982857142857143,
      "grad_norm": 0.03039766289293766,
      "learning_rate": 0.020833972841501236,
      "loss": 2.5107932090759277,
      "step": 14664
    },
    {
      "epoch": 0.6983809523809524,
      "grad_norm": 0.026342814788222313,
      "learning_rate": 0.02082739770412445,
      "loss": 2.4532217979431152,
      "step": 14666
    },
    {
      "epoch": 0.6984761904761905,
      "grad_norm": 0.025713760405778885,
      "learning_rate": 0.020820820704102516,
      "loss": 2.5040407180786133,
      "step": 14668
    },
    {
      "epoch": 0.6985714285714286,
      "grad_norm": 0.026002630591392517,
      "learning_rate": 0.02081424742937088,
      "loss": 2.4784140586853027,
      "step": 14670
    },
    {
      "epoch": 0.6986666666666667,
      "grad_norm": 0.025589942932128906,
      "learning_rate": 0.020807670429348946,
      "loss": 2.4511795043945312,
      "step": 14672
    },
    {
      "epoch": 0.6987619047619048,
      "grad_norm": 0.0255685243755579,
      "learning_rate": 0.02080109529197216,
      "loss": 2.4442567825317383,
      "step": 14674
    },
    {
      "epoch": 0.6988571428571428,
      "grad_norm": 0.025947902351617813,
      "learning_rate": 0.020794520154595375,
      "loss": 2.47658634185791,
      "step": 14676
    },
    {
      "epoch": 0.698952380952381,
      "grad_norm": 0.025507410988211632,
      "learning_rate": 0.02078794501721859,
      "loss": 2.4993395805358887,
      "step": 14678
    },
    {
      "epoch": 0.699047619047619,
      "grad_norm": 0.028277354314923286,
      "learning_rate": 0.020781369879841805,
      "loss": 2.521207809448242,
      "step": 14680
    },
    {
      "epoch": 0.6991428571428572,
      "grad_norm": 0.02533031813800335,
      "learning_rate": 0.02077479474246502,
      "loss": 2.4552698135375977,
      "step": 14682
    },
    {
      "epoch": 0.6992380952380952,
      "grad_norm": 0.029887719079852104,
      "learning_rate": 0.020768219605088234,
      "loss": 2.468930721282959,
      "step": 14684
    },
    {
      "epoch": 0.6993333333333334,
      "grad_norm": 0.025929300114512444,
      "learning_rate": 0.02076164446771145,
      "loss": 2.422050714492798,
      "step": 14686
    },
    {
      "epoch": 0.6994285714285714,
      "grad_norm": 0.025826334953308105,
      "learning_rate": 0.020755067467689514,
      "loss": 2.4445502758026123,
      "step": 14688
    },
    {
      "epoch": 0.6995238095238095,
      "grad_norm": 0.02789626456797123,
      "learning_rate": 0.020748494192957878,
      "loss": 2.5035085678100586,
      "step": 14690
    },
    {
      "epoch": 0.6996190476190476,
      "grad_norm": 0.02760200947523117,
      "learning_rate": 0.020741917192935944,
      "loss": 2.4989027976989746,
      "step": 14692
    },
    {
      "epoch": 0.6997142857142857,
      "grad_norm": 0.025426151230931282,
      "learning_rate": 0.02073534205555916,
      "loss": 2.472100257873535,
      "step": 14694
    },
    {
      "epoch": 0.6998095238095238,
      "grad_norm": 0.02559243142604828,
      "learning_rate": 0.020728766918182373,
      "loss": 2.4777169227600098,
      "step": 14696
    },
    {
      "epoch": 0.6999047619047619,
      "grad_norm": 0.02543334662914276,
      "learning_rate": 0.020722191780805588,
      "loss": 2.473095417022705,
      "step": 14698
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.02707161009311676,
      "learning_rate": 0.020715616643428802,
      "loss": 2.447995662689209,
      "step": 14700
    },
    {
      "epoch": 0.7000952380952381,
      "grad_norm": 0.027848724275827408,
      "learning_rate": 0.020709041506052017,
      "loss": 2.4494733810424805,
      "step": 14702
    },
    {
      "epoch": 0.7001904761904761,
      "grad_norm": 0.027495967224240303,
      "learning_rate": 0.020702464506030083,
      "loss": 2.4636495113372803,
      "step": 14704
    },
    {
      "epoch": 0.7002857142857143,
      "grad_norm": 0.02661939337849617,
      "learning_rate": 0.020695891231298447,
      "loss": 2.4535083770751953,
      "step": 14706
    },
    {
      "epoch": 0.7003809523809523,
      "grad_norm": 0.026650341227650642,
      "learning_rate": 0.020689314231276512,
      "loss": 2.4385886192321777,
      "step": 14708
    },
    {
      "epoch": 0.7004761904761905,
      "grad_norm": 0.02617066539824009,
      "learning_rate": 0.020682739093899727,
      "loss": 2.4547529220581055,
      "step": 14710
    },
    {
      "epoch": 0.7005714285714286,
      "grad_norm": 0.031457770615816116,
      "learning_rate": 0.02067616395652294,
      "loss": 2.478400468826294,
      "step": 14712
    },
    {
      "epoch": 0.7006666666666667,
      "grad_norm": 0.02738858014345169,
      "learning_rate": 0.020669588819146156,
      "loss": 2.4944252967834473,
      "step": 14714
    },
    {
      "epoch": 0.7007619047619048,
      "grad_norm": 0.027891816571354866,
      "learning_rate": 0.02066301368176937,
      "loss": 2.468693256378174,
      "step": 14716
    },
    {
      "epoch": 0.7008571428571428,
      "grad_norm": 0.02525424398481846,
      "learning_rate": 0.020656438544392586,
      "loss": 2.4543843269348145,
      "step": 14718
    },
    {
      "epoch": 0.700952380952381,
      "grad_norm": 0.02597595565021038,
      "learning_rate": 0.0206498634070158,
      "loss": 2.4470298290252686,
      "step": 14720
    },
    {
      "epoch": 0.701047619047619,
      "grad_norm": 0.026174940168857574,
      "learning_rate": 0.020643288269639015,
      "loss": 2.4793872833251953,
      "step": 14722
    },
    {
      "epoch": 0.7011428571428572,
      "grad_norm": 0.02627810835838318,
      "learning_rate": 0.02063671313226223,
      "loss": 2.4696269035339355,
      "step": 14724
    },
    {
      "epoch": 0.7012380952380952,
      "grad_norm": 0.02623147703707218,
      "learning_rate": 0.020630137994885445,
      "loss": 2.458425998687744,
      "step": 14726
    },
    {
      "epoch": 0.7013333333333334,
      "grad_norm": 0.0252494178712368,
      "learning_rate": 0.02062356285750866,
      "loss": 2.495882987976074,
      "step": 14728
    },
    {
      "epoch": 0.7014285714285714,
      "grad_norm": 0.025533637031912804,
      "learning_rate": 0.020616985857486725,
      "loss": 2.432713031768799,
      "step": 14730
    },
    {
      "epoch": 0.7015238095238095,
      "grad_norm": 0.02481916919350624,
      "learning_rate": 0.02061041258275509,
      "loss": 2.446664333343506,
      "step": 14732
    },
    {
      "epoch": 0.7016190476190476,
      "grad_norm": 0.028590362519025803,
      "learning_rate": 0.020603835582733154,
      "loss": 2.474175453186035,
      "step": 14734
    },
    {
      "epoch": 0.7017142857142857,
      "grad_norm": 0.025844819843769073,
      "learning_rate": 0.02059726044535637,
      "loss": 2.4432129859924316,
      "step": 14736
    },
    {
      "epoch": 0.7018095238095238,
      "grad_norm": 0.026831544935703278,
      "learning_rate": 0.020590685307979584,
      "loss": 2.465724229812622,
      "step": 14738
    },
    {
      "epoch": 0.7019047619047619,
      "grad_norm": 0.025947503745555878,
      "learning_rate": 0.0205841101706028,
      "loss": 2.467989444732666,
      "step": 14740
    },
    {
      "epoch": 0.702,
      "grad_norm": 0.027383267879486084,
      "learning_rate": 0.020577535033226013,
      "loss": 2.498831033706665,
      "step": 14742
    },
    {
      "epoch": 0.7020952380952381,
      "grad_norm": 0.02696104161441326,
      "learning_rate": 0.020570959895849228,
      "loss": 2.4423651695251465,
      "step": 14744
    },
    {
      "epoch": 0.7021904761904761,
      "grad_norm": 0.025981826707720757,
      "learning_rate": 0.020564382895827293,
      "loss": 2.4443511962890625,
      "step": 14746
    },
    {
      "epoch": 0.7022857142857143,
      "grad_norm": 0.03268289938569069,
      "learning_rate": 0.020557809621095657,
      "loss": 2.426682949066162,
      "step": 14748
    },
    {
      "epoch": 0.7023809523809523,
      "grad_norm": 0.026901239529252052,
      "learning_rate": 0.020551232621073723,
      "loss": 2.48661470413208,
      "step": 14750
    },
    {
      "epoch": 0.7024761904761905,
      "grad_norm": 0.02659415639936924,
      "learning_rate": 0.020544657483696938,
      "loss": 2.457679033279419,
      "step": 14752
    },
    {
      "epoch": 0.7025714285714286,
      "grad_norm": 0.026021037250757217,
      "learning_rate": 0.020538082346320152,
      "loss": 2.4638123512268066,
      "step": 14754
    },
    {
      "epoch": 0.7026666666666667,
      "grad_norm": 0.02905193716287613,
      "learning_rate": 0.020531507208943367,
      "loss": 2.428633213043213,
      "step": 14756
    },
    {
      "epoch": 0.7027619047619048,
      "grad_norm": 0.029797388240695,
      "learning_rate": 0.02052493207156658,
      "loss": 2.481541633605957,
      "step": 14758
    },
    {
      "epoch": 0.7028571428571428,
      "grad_norm": 0.026687024161219597,
      "learning_rate": 0.020518356934189796,
      "loss": 2.4576292037963867,
      "step": 14760
    },
    {
      "epoch": 0.702952380952381,
      "grad_norm": 0.02729600854218006,
      "learning_rate": 0.02051178179681301,
      "loss": 2.4269909858703613,
      "step": 14762
    },
    {
      "epoch": 0.703047619047619,
      "grad_norm": 0.025835195556282997,
      "learning_rate": 0.020505206659436226,
      "loss": 2.4774136543273926,
      "step": 14764
    },
    {
      "epoch": 0.7031428571428572,
      "grad_norm": 0.02574213594198227,
      "learning_rate": 0.02049862965941429,
      "loss": 2.44734525680542,
      "step": 14766
    },
    {
      "epoch": 0.7032380952380952,
      "grad_norm": 0.025931892916560173,
      "learning_rate": 0.020492056384682655,
      "loss": 2.4263641834259033,
      "step": 14768
    },
    {
      "epoch": 0.7033333333333334,
      "grad_norm": 0.025308262556791306,
      "learning_rate": 0.02048547938466072,
      "loss": 2.505408525466919,
      "step": 14770
    },
    {
      "epoch": 0.7034285714285714,
      "grad_norm": 0.026783842593431473,
      "learning_rate": 0.020478904247283936,
      "loss": 2.447723627090454,
      "step": 14772
    },
    {
      "epoch": 0.7035238095238096,
      "grad_norm": 0.02563503384590149,
      "learning_rate": 0.02047232910990715,
      "loss": 2.438994884490967,
      "step": 14774
    },
    {
      "epoch": 0.7036190476190476,
      "grad_norm": 0.02660524845123291,
      "learning_rate": 0.020465753972530365,
      "loss": 2.4511632919311523,
      "step": 14776
    },
    {
      "epoch": 0.7037142857142857,
      "grad_norm": 0.02808217518031597,
      "learning_rate": 0.02045917883515358,
      "loss": 2.4449353218078613,
      "step": 14778
    },
    {
      "epoch": 0.7038095238095238,
      "grad_norm": 0.02827282063663006,
      "learning_rate": 0.020452603697776794,
      "loss": 2.395031452178955,
      "step": 14780
    },
    {
      "epoch": 0.7039047619047619,
      "grad_norm": 0.03262253850698471,
      "learning_rate": 0.02044602669775486,
      "loss": 2.440002918243408,
      "step": 14782
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.03166159242391586,
      "learning_rate": 0.020439453423023224,
      "loss": 2.4259157180786133,
      "step": 14784
    },
    {
      "epoch": 0.7040952380952381,
      "grad_norm": 0.02597934380173683,
      "learning_rate": 0.02043287642300129,
      "loss": 2.4553470611572266,
      "step": 14786
    },
    {
      "epoch": 0.7041904761904761,
      "grad_norm": 0.026835324242711067,
      "learning_rate": 0.020426301285624504,
      "loss": 2.450976848602295,
      "step": 14788
    },
    {
      "epoch": 0.7042857142857143,
      "grad_norm": 0.027155041694641113,
      "learning_rate": 0.02041972614824772,
      "loss": 2.4217944145202637,
      "step": 14790
    },
    {
      "epoch": 0.7043809523809523,
      "grad_norm": 0.028210371732711792,
      "learning_rate": 0.020413151010870934,
      "loss": 2.440734386444092,
      "step": 14792
    },
    {
      "epoch": 0.7044761904761905,
      "grad_norm": 0.027099886909127235,
      "learning_rate": 0.020406575873494148,
      "loss": 2.45415997505188,
      "step": 14794
    },
    {
      "epoch": 0.7045714285714286,
      "grad_norm": 0.026945358142256737,
      "learning_rate": 0.020400000736117363,
      "loss": 2.4393014907836914,
      "step": 14796
    },
    {
      "epoch": 0.7046666666666667,
      "grad_norm": 0.028627930209040642,
      "learning_rate": 0.020393425598740578,
      "loss": 2.434840202331543,
      "step": 14798
    },
    {
      "epoch": 0.7047619047619048,
      "grad_norm": 0.02540714293718338,
      "learning_rate": 0.020386850461363792,
      "loss": 2.4150145053863525,
      "step": 14800
    },
    {
      "epoch": 0.7048571428571428,
      "grad_norm": 0.02633458934724331,
      "learning_rate": 0.020380273461341858,
      "loss": 2.4586877822875977,
      "step": 14802
    },
    {
      "epoch": 0.704952380952381,
      "grad_norm": 0.03218131884932518,
      "learning_rate": 0.020373700186610222,
      "loss": 2.4091782569885254,
      "step": 14804
    },
    {
      "epoch": 0.705047619047619,
      "grad_norm": 0.027163943275809288,
      "learning_rate": 0.020367123186588287,
      "loss": 2.4300336837768555,
      "step": 14806
    },
    {
      "epoch": 0.7051428571428572,
      "grad_norm": 0.025312574580311775,
      "learning_rate": 0.020360548049211502,
      "loss": 2.3841023445129395,
      "step": 14808
    },
    {
      "epoch": 0.7052380952380952,
      "grad_norm": 0.025460239499807358,
      "learning_rate": 0.020353972911834717,
      "loss": 2.412843704223633,
      "step": 14810
    },
    {
      "epoch": 0.7053333333333334,
      "grad_norm": 0.02500554732978344,
      "learning_rate": 0.02034739777445793,
      "loss": 2.433201789855957,
      "step": 14812
    },
    {
      "epoch": 0.7054285714285714,
      "grad_norm": 0.026306549087166786,
      "learning_rate": 0.020340822637081146,
      "loss": 2.4185237884521484,
      "step": 14814
    },
    {
      "epoch": 0.7055238095238096,
      "grad_norm": 0.02647777646780014,
      "learning_rate": 0.02033424749970436,
      "loss": 2.4215548038482666,
      "step": 14816
    },
    {
      "epoch": 0.7056190476190476,
      "grad_norm": 0.025681423023343086,
      "learning_rate": 0.020327670499682426,
      "loss": 2.440061569213867,
      "step": 14818
    },
    {
      "epoch": 0.7057142857142857,
      "grad_norm": 0.0266441497951746,
      "learning_rate": 0.02032109722495079,
      "loss": 2.449305534362793,
      "step": 14820
    },
    {
      "epoch": 0.7058095238095238,
      "grad_norm": 0.02470308728516102,
      "learning_rate": 0.020314520224928856,
      "loss": 2.446560859680176,
      "step": 14822
    },
    {
      "epoch": 0.7059047619047619,
      "grad_norm": 0.025740686804056168,
      "learning_rate": 0.02030794508755207,
      "loss": 2.4278671741485596,
      "step": 14824
    },
    {
      "epoch": 0.706,
      "grad_norm": 0.027313893660902977,
      "learning_rate": 0.020301369950175285,
      "loss": 2.415508270263672,
      "step": 14826
    },
    {
      "epoch": 0.7060952380952381,
      "grad_norm": 0.02591228298842907,
      "learning_rate": 0.0202947948127985,
      "loss": 2.397736072540283,
      "step": 14828
    },
    {
      "epoch": 0.7061904761904761,
      "grad_norm": 0.025931086391210556,
      "learning_rate": 0.020288219675421715,
      "loss": 2.428922653198242,
      "step": 14830
    },
    {
      "epoch": 0.7062857142857143,
      "grad_norm": 0.025482216849923134,
      "learning_rate": 0.02028164453804493,
      "loss": 2.393099308013916,
      "step": 14832
    },
    {
      "epoch": 0.7063809523809523,
      "grad_norm": 0.02576802857220173,
      "learning_rate": 0.020275067538022995,
      "loss": 2.4171557426452637,
      "step": 14834
    },
    {
      "epoch": 0.7064761904761905,
      "grad_norm": 0.02613390050828457,
      "learning_rate": 0.02026849426329136,
      "loss": 2.423222064971924,
      "step": 14836
    },
    {
      "epoch": 0.7065714285714285,
      "grad_norm": 0.029068078845739365,
      "learning_rate": 0.020261917263269424,
      "loss": 2.382845878601074,
      "step": 14838
    },
    {
      "epoch": 0.7066666666666667,
      "grad_norm": 0.025449445471167564,
      "learning_rate": 0.02025534398853779,
      "loss": 2.4598746299743652,
      "step": 14840
    },
    {
      "epoch": 0.7067619047619048,
      "grad_norm": 0.026635274291038513,
      "learning_rate": 0.020248766988515854,
      "loss": 2.3971073627471924,
      "step": 14842
    },
    {
      "epoch": 0.7068571428571429,
      "grad_norm": 0.025918681174516678,
      "learning_rate": 0.02024219185113907,
      "loss": 2.423346519470215,
      "step": 14844
    },
    {
      "epoch": 0.706952380952381,
      "grad_norm": 0.026046114042401314,
      "learning_rate": 0.020235616713762283,
      "loss": 2.3658883571624756,
      "step": 14846
    },
    {
      "epoch": 0.707047619047619,
      "grad_norm": 0.02893313765525818,
      "learning_rate": 0.020229041576385498,
      "loss": 2.413499116897583,
      "step": 14848
    },
    {
      "epoch": 0.7071428571428572,
      "grad_norm": 0.028921116143465042,
      "learning_rate": 0.020222466439008713,
      "loss": 2.4388222694396973,
      "step": 14850
    },
    {
      "epoch": 0.7072380952380952,
      "grad_norm": 0.027798078954219818,
      "learning_rate": 0.020215891301631927,
      "loss": 2.3828115463256836,
      "step": 14852
    },
    {
      "epoch": 0.7073333333333334,
      "grad_norm": 0.026878971606492996,
      "learning_rate": 0.020209314301609993,
      "loss": 2.443676710128784,
      "step": 14854
    },
    {
      "epoch": 0.7074285714285714,
      "grad_norm": 0.026369938626885414,
      "learning_rate": 0.020202741026878357,
      "loss": 2.4068403244018555,
      "step": 14856
    },
    {
      "epoch": 0.7075238095238096,
      "grad_norm": 0.027162546291947365,
      "learning_rate": 0.020196164026856422,
      "loss": 2.3921568393707275,
      "step": 14858
    },
    {
      "epoch": 0.7076190476190476,
      "grad_norm": 0.026257693767547607,
      "learning_rate": 0.020189588889479637,
      "loss": 2.388038158416748,
      "step": 14860
    },
    {
      "epoch": 0.7077142857142857,
      "grad_norm": 0.02788669429719448,
      "learning_rate": 0.020183013752102852,
      "loss": 2.447648048400879,
      "step": 14862
    },
    {
      "epoch": 0.7078095238095238,
      "grad_norm": 0.025882042944431305,
      "learning_rate": 0.020176438614726067,
      "loss": 2.3850831985473633,
      "step": 14864
    },
    {
      "epoch": 0.7079047619047619,
      "grad_norm": 0.031153997406363487,
      "learning_rate": 0.02016986347734928,
      "loss": 2.421598196029663,
      "step": 14866
    },
    {
      "epoch": 0.708,
      "grad_norm": 0.026668796315789223,
      "learning_rate": 0.020163288339972496,
      "loss": 2.370969295501709,
      "step": 14868
    },
    {
      "epoch": 0.7080952380952381,
      "grad_norm": 0.025908848270773888,
      "learning_rate": 0.02015671133995056,
      "loss": 2.426736354827881,
      "step": 14870
    },
    {
      "epoch": 0.7081904761904761,
      "grad_norm": 0.027479134500026703,
      "learning_rate": 0.020150138065218925,
      "loss": 2.4187445640563965,
      "step": 14872
    },
    {
      "epoch": 0.7082857142857143,
      "grad_norm": 0.027541236951947212,
      "learning_rate": 0.02014356106519699,
      "loss": 2.407979965209961,
      "step": 14874
    },
    {
      "epoch": 0.7083809523809523,
      "grad_norm": 0.02585376240313053,
      "learning_rate": 0.020136987790465355,
      "loss": 2.437450885772705,
      "step": 14876
    },
    {
      "epoch": 0.7084761904761905,
      "grad_norm": 0.026608433574438095,
      "learning_rate": 0.02013041079044342,
      "loss": 2.425913095474243,
      "step": 14878
    },
    {
      "epoch": 0.7085714285714285,
      "grad_norm": 0.028854571282863617,
      "learning_rate": 0.020123835653066635,
      "loss": 2.4328198432922363,
      "step": 14880
    },
    {
      "epoch": 0.7086666666666667,
      "grad_norm": 0.02642941288650036,
      "learning_rate": 0.02011726051568985,
      "loss": 2.4273645877838135,
      "step": 14882
    },
    {
      "epoch": 0.7087619047619048,
      "grad_norm": 0.026003146544098854,
      "learning_rate": 0.020110685378313065,
      "loss": 2.412534713745117,
      "step": 14884
    },
    {
      "epoch": 0.7088571428571429,
      "grad_norm": 0.026492854580283165,
      "learning_rate": 0.02010411024093628,
      "loss": 2.390758991241455,
      "step": 14886
    },
    {
      "epoch": 0.708952380952381,
      "grad_norm": 0.026660682633519173,
      "learning_rate": 0.020097535103559494,
      "loss": 2.44051194190979,
      "step": 14888
    },
    {
      "epoch": 0.709047619047619,
      "grad_norm": 0.026220116764307022,
      "learning_rate": 0.02009095810353756,
      "loss": 2.441074848175049,
      "step": 14890
    },
    {
      "epoch": 0.7091428571428572,
      "grad_norm": 0.025580501183867455,
      "learning_rate": 0.020084384828805923,
      "loss": 2.3902745246887207,
      "step": 14892
    },
    {
      "epoch": 0.7092380952380952,
      "grad_norm": 0.026442281901836395,
      "learning_rate": 0.02007780782878399,
      "loss": 2.3965463638305664,
      "step": 14894
    },
    {
      "epoch": 0.7093333333333334,
      "grad_norm": 0.02684585377573967,
      "learning_rate": 0.020071232691407204,
      "loss": 2.391150712966919,
      "step": 14896
    },
    {
      "epoch": 0.7094285714285714,
      "grad_norm": 0.025941668078303337,
      "learning_rate": 0.02006465755403042,
      "loss": 2.432293653488159,
      "step": 14898
    },
    {
      "epoch": 0.7095238095238096,
      "grad_norm": 0.024845406413078308,
      "learning_rate": 0.020058082416653633,
      "loss": 2.3958823680877686,
      "step": 14900
    },
    {
      "epoch": 0.7096190476190476,
      "grad_norm": 0.02674299292266369,
      "learning_rate": 0.020051507279276848,
      "loss": 2.383371353149414,
      "step": 14902
    },
    {
      "epoch": 0.7097142857142857,
      "grad_norm": 0.02570422925055027,
      "learning_rate": 0.020044932141900063,
      "loss": 2.376857280731201,
      "step": 14904
    },
    {
      "epoch": 0.7098095238095238,
      "grad_norm": 0.028513401746749878,
      "learning_rate": 0.020038355141878128,
      "loss": 2.4147846698760986,
      "step": 14906
    },
    {
      "epoch": 0.7099047619047619,
      "grad_norm": 0.027569271624088287,
      "learning_rate": 0.020031781867146492,
      "loss": 2.388996124267578,
      "step": 14908
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.027773048728704453,
      "learning_rate": 0.020025204867124557,
      "loss": 2.418844699859619,
      "step": 14910
    },
    {
      "epoch": 0.7100952380952381,
      "grad_norm": 0.02612140029668808,
      "learning_rate": 0.02001863159239292,
      "loss": 2.371701717376709,
      "step": 14912
    },
    {
      "epoch": 0.7101904761904761,
      "grad_norm": 0.028727296739816666,
      "learning_rate": 0.020012054592370987,
      "loss": 2.40533447265625,
      "step": 14914
    },
    {
      "epoch": 0.7102857142857143,
      "grad_norm": 0.02749863639473915,
      "learning_rate": 0.0200054794549942,
      "loss": 2.356374979019165,
      "step": 14916
    },
    {
      "epoch": 0.7103809523809523,
      "grad_norm": 0.0304914191365242,
      "learning_rate": 0.019998904317617416,
      "loss": 2.376025676727295,
      "step": 14918
    },
    {
      "epoch": 0.7104761904761905,
      "grad_norm": 0.02612967975437641,
      "learning_rate": 0.01999232918024063,
      "loss": 2.379204750061035,
      "step": 14920
    },
    {
      "epoch": 0.7105714285714285,
      "grad_norm": 0.02999177575111389,
      "learning_rate": 0.019985754042863846,
      "loss": 2.34993052482605,
      "step": 14922
    },
    {
      "epoch": 0.7106666666666667,
      "grad_norm": 0.029144538566470146,
      "learning_rate": 0.01997917890548706,
      "loss": 2.361457586288452,
      "step": 14924
    },
    {
      "epoch": 0.7107619047619048,
      "grad_norm": 0.026372693479061127,
      "learning_rate": 0.019972601905465126,
      "loss": 2.384807586669922,
      "step": 14926
    },
    {
      "epoch": 0.7108571428571429,
      "grad_norm": 0.02558102272450924,
      "learning_rate": 0.01996602863073349,
      "loss": 2.402895212173462,
      "step": 14928
    },
    {
      "epoch": 0.710952380952381,
      "grad_norm": 0.026863249018788338,
      "learning_rate": 0.019959451630711555,
      "loss": 2.366818428039551,
      "step": 14930
    },
    {
      "epoch": 0.711047619047619,
      "grad_norm": 0.033670712262392044,
      "learning_rate": 0.01995287649333477,
      "loss": 2.361891746520996,
      "step": 14932
    },
    {
      "epoch": 0.7111428571428572,
      "grad_norm": 0.02529686503112316,
      "learning_rate": 0.019946301355957985,
      "loss": 2.3881444931030273,
      "step": 14934
    },
    {
      "epoch": 0.7112380952380952,
      "grad_norm": 0.027151556685566902,
      "learning_rate": 0.0199397262185812,
      "loss": 2.352567434310913,
      "step": 14936
    },
    {
      "epoch": 0.7113333333333334,
      "grad_norm": 0.02554609254002571,
      "learning_rate": 0.019933151081204414,
      "loss": 2.371734142303467,
      "step": 14938
    },
    {
      "epoch": 0.7114285714285714,
      "grad_norm": 0.026667293161153793,
      "learning_rate": 0.01992657594382763,
      "loss": 2.3808164596557617,
      "step": 14940
    },
    {
      "epoch": 0.7115238095238096,
      "grad_norm": 0.028731796890497208,
      "learning_rate": 0.019919998943805695,
      "loss": 2.3731467723846436,
      "step": 14942
    },
    {
      "epoch": 0.7116190476190476,
      "grad_norm": 0.027497991919517517,
      "learning_rate": 0.01991342566907406,
      "loss": 2.400629997253418,
      "step": 14944
    },
    {
      "epoch": 0.7117142857142857,
      "grad_norm": 0.026669440791010857,
      "learning_rate": 0.019906848669052124,
      "loss": 2.386054515838623,
      "step": 14946
    },
    {
      "epoch": 0.7118095238095238,
      "grad_norm": 0.025070516392588615,
      "learning_rate": 0.01990027353167534,
      "loss": 2.397226333618164,
      "step": 14948
    },
    {
      "epoch": 0.7119047619047619,
      "grad_norm": 0.024595128372311592,
      "learning_rate": 0.019893698394298553,
      "loss": 2.4078052043914795,
      "step": 14950
    },
    {
      "epoch": 0.712,
      "grad_norm": 0.02522423304617405,
      "learning_rate": 0.019887123256921768,
      "loss": 2.341128349304199,
      "step": 14952
    },
    {
      "epoch": 0.7120952380952381,
      "grad_norm": 0.025554874911904335,
      "learning_rate": 0.019880548119544983,
      "loss": 2.3977179527282715,
      "step": 14954
    },
    {
      "epoch": 0.7121904761904762,
      "grad_norm": 0.025801749899983406,
      "learning_rate": 0.019873972982168198,
      "loss": 2.381911039352417,
      "step": 14956
    },
    {
      "epoch": 0.7122857142857143,
      "grad_norm": 0.025449909269809723,
      "learning_rate": 0.019867397844791412,
      "loss": 2.3392765522003174,
      "step": 14958
    },
    {
      "epoch": 0.7123809523809523,
      "grad_norm": 0.025686001405119896,
      "learning_rate": 0.019860822707414627,
      "loss": 2.3874855041503906,
      "step": 14960
    },
    {
      "epoch": 0.7124761904761905,
      "grad_norm": 0.02633265033364296,
      "learning_rate": 0.019854245707392693,
      "loss": 2.416311740875244,
      "step": 14962
    },
    {
      "epoch": 0.7125714285714285,
      "grad_norm": 0.027425741776823997,
      "learning_rate": 0.019847672432661057,
      "loss": 2.370887279510498,
      "step": 14964
    },
    {
      "epoch": 0.7126666666666667,
      "grad_norm": 0.0275392048060894,
      "learning_rate": 0.019841095432639122,
      "loss": 2.369263172149658,
      "step": 14966
    },
    {
      "epoch": 0.7127619047619047,
      "grad_norm": 0.02471034973859787,
      "learning_rate": 0.019834520295262337,
      "loss": 2.397378444671631,
      "step": 14968
    },
    {
      "epoch": 0.7128571428571429,
      "grad_norm": 0.025188611820340157,
      "learning_rate": 0.01982794515788555,
      "loss": 2.387019634246826,
      "step": 14970
    },
    {
      "epoch": 0.712952380952381,
      "grad_norm": 0.024481747299432755,
      "learning_rate": 0.019821370020508766,
      "loss": 2.353825569152832,
      "step": 14972
    },
    {
      "epoch": 0.713047619047619,
      "grad_norm": 0.02652350440621376,
      "learning_rate": 0.01981479488313198,
      "loss": 2.3326785564422607,
      "step": 14974
    },
    {
      "epoch": 0.7131428571428572,
      "grad_norm": 0.025368139147758484,
      "learning_rate": 0.019808219745755196,
      "loss": 2.351590633392334,
      "step": 14976
    },
    {
      "epoch": 0.7132380952380952,
      "grad_norm": 0.025594346225261688,
      "learning_rate": 0.01980164274573326,
      "loss": 2.4198453426361084,
      "step": 14978
    },
    {
      "epoch": 0.7133333333333334,
      "grad_norm": 0.028411658480763435,
      "learning_rate": 0.019795069471001625,
      "loss": 2.369096279144287,
      "step": 14980
    },
    {
      "epoch": 0.7134285714285714,
      "grad_norm": 0.026550300419330597,
      "learning_rate": 0.01978849247097969,
      "loss": 2.3685526847839355,
      "step": 14982
    },
    {
      "epoch": 0.7135238095238096,
      "grad_norm": 0.02620614692568779,
      "learning_rate": 0.019781917333602905,
      "loss": 2.373196601867676,
      "step": 14984
    },
    {
      "epoch": 0.7136190476190476,
      "grad_norm": 0.025834938511252403,
      "learning_rate": 0.01977534219622612,
      "loss": 2.357588768005371,
      "step": 14986
    },
    {
      "epoch": 0.7137142857142857,
      "grad_norm": 0.026975683867931366,
      "learning_rate": 0.019768767058849335,
      "loss": 2.349461078643799,
      "step": 14988
    },
    {
      "epoch": 0.7138095238095238,
      "grad_norm": 0.028899747878313065,
      "learning_rate": 0.01976219192147255,
      "loss": 2.315664768218994,
      "step": 14990
    },
    {
      "epoch": 0.7139047619047619,
      "grad_norm": 0.02764800935983658,
      "learning_rate": 0.019755616784095764,
      "loss": 2.3742799758911133,
      "step": 14992
    },
    {
      "epoch": 0.714,
      "grad_norm": 0.026885496452450752,
      "learning_rate": 0.01974904164671898,
      "loss": 2.364410161972046,
      "step": 14994
    },
    {
      "epoch": 0.7140952380952381,
      "grad_norm": 0.028645915910601616,
      "learning_rate": 0.019742466509342194,
      "loss": 2.3040106296539307,
      "step": 14996
    },
    {
      "epoch": 0.7141904761904762,
      "grad_norm": 0.02804999053478241,
      "learning_rate": 0.01973588950932026,
      "loss": 2.3601126670837402,
      "step": 14998
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.025633441284298897,
      "learning_rate": 0.019729316234588623,
      "loss": 2.340916633605957,
      "step": 15000
    },
    {
      "epoch": 0.7143809523809523,
      "grad_norm": 0.02800317481160164,
      "learning_rate": 0.01972273923456669,
      "loss": 2.3742449283599854,
      "step": 15002
    },
    {
      "epoch": 0.7144761904761905,
      "grad_norm": 0.027800509706139565,
      "learning_rate": 0.019716164097189903,
      "loss": 2.375584602355957,
      "step": 15004
    },
    {
      "epoch": 0.7145714285714285,
      "grad_norm": 0.02720266580581665,
      "learning_rate": 0.019709588959813118,
      "loss": 2.4019436836242676,
      "step": 15006
    },
    {
      "epoch": 0.7146666666666667,
      "grad_norm": 0.029274363070726395,
      "learning_rate": 0.019703013822436333,
      "loss": 2.380859851837158,
      "step": 15008
    },
    {
      "epoch": 0.7147619047619047,
      "grad_norm": 0.02899310737848282,
      "learning_rate": 0.019696438685059547,
      "loss": 2.337690830230713,
      "step": 15010
    },
    {
      "epoch": 0.7148571428571429,
      "grad_norm": 0.029514487832784653,
      "learning_rate": 0.019689863547682762,
      "loss": 2.4036459922790527,
      "step": 15012
    },
    {
      "epoch": 0.714952380952381,
      "grad_norm": 0.027826694771647453,
      "learning_rate": 0.019683286547660828,
      "loss": 2.3959908485412598,
      "step": 15014
    },
    {
      "epoch": 0.715047619047619,
      "grad_norm": 0.027102481573820114,
      "learning_rate": 0.01967671327292919,
      "loss": 2.3558616638183594,
      "step": 15016
    },
    {
      "epoch": 0.7151428571428572,
      "grad_norm": 0.02712608501315117,
      "learning_rate": 0.019670136272907257,
      "loss": 2.3816885948181152,
      "step": 15018
    },
    {
      "epoch": 0.7152380952380952,
      "grad_norm": 0.02554384432733059,
      "learning_rate": 0.019663561135530472,
      "loss": 2.369047164916992,
      "step": 15020
    },
    {
      "epoch": 0.7153333333333334,
      "grad_norm": 0.02522895485162735,
      "learning_rate": 0.019656985998153687,
      "loss": 2.361952304840088,
      "step": 15022
    },
    {
      "epoch": 0.7154285714285714,
      "grad_norm": 0.026136798784136772,
      "learning_rate": 0.0196504108607769,
      "loss": 2.369077444076538,
      "step": 15024
    },
    {
      "epoch": 0.7155238095238096,
      "grad_norm": 0.025469938293099403,
      "learning_rate": 0.019643835723400116,
      "loss": 2.3305726051330566,
      "step": 15026
    },
    {
      "epoch": 0.7156190476190476,
      "grad_norm": 0.02517659217119217,
      "learning_rate": 0.01963726058602333,
      "loss": 2.2993264198303223,
      "step": 15028
    },
    {
      "epoch": 0.7157142857142857,
      "grad_norm": 0.024530239403247833,
      "learning_rate": 0.019630685448646545,
      "loss": 2.3427467346191406,
      "step": 15030
    },
    {
      "epoch": 0.7158095238095238,
      "grad_norm": 0.026664065197110176,
      "learning_rate": 0.01962411031126976,
      "loss": 2.3880913257598877,
      "step": 15032
    },
    {
      "epoch": 0.7159047619047619,
      "grad_norm": 0.025874387472867966,
      "learning_rate": 0.019617533311247826,
      "loss": 2.3666815757751465,
      "step": 15034
    },
    {
      "epoch": 0.716,
      "grad_norm": 0.02533714845776558,
      "learning_rate": 0.01961096003651619,
      "loss": 2.3821568489074707,
      "step": 15036
    },
    {
      "epoch": 0.7160952380952381,
      "grad_norm": 0.025477126240730286,
      "learning_rate": 0.019604383036494255,
      "loss": 2.3420257568359375,
      "step": 15038
    },
    {
      "epoch": 0.7161904761904762,
      "grad_norm": 0.025824973359704018,
      "learning_rate": 0.01959780789911747,
      "loss": 2.3465864658355713,
      "step": 15040
    },
    {
      "epoch": 0.7162857142857143,
      "grad_norm": 0.025827759876847267,
      "learning_rate": 0.019591232761740685,
      "loss": 2.3493459224700928,
      "step": 15042
    },
    {
      "epoch": 0.7163809523809523,
      "grad_norm": 0.026343556120991707,
      "learning_rate": 0.0195846576243639,
      "loss": 2.390183687210083,
      "step": 15044
    },
    {
      "epoch": 0.7164761904761905,
      "grad_norm": 0.026261623948812485,
      "learning_rate": 0.019578082486987114,
      "loss": 2.338191509246826,
      "step": 15046
    },
    {
      "epoch": 0.7165714285714285,
      "grad_norm": 0.025530602782964706,
      "learning_rate": 0.01957150734961033,
      "loss": 2.357668876647949,
      "step": 15048
    },
    {
      "epoch": 0.7166666666666667,
      "grad_norm": 0.02969994768500328,
      "learning_rate": 0.019564930349588394,
      "loss": 2.3351666927337646,
      "step": 15050
    },
    {
      "epoch": 0.7167619047619047,
      "grad_norm": 0.026466840878129005,
      "learning_rate": 0.019558357074856758,
      "loss": 2.381925344467163,
      "step": 15052
    },
    {
      "epoch": 0.7168571428571429,
      "grad_norm": 0.02657860331237316,
      "learning_rate": 0.019551780074834824,
      "loss": 2.402562141418457,
      "step": 15054
    },
    {
      "epoch": 0.716952380952381,
      "grad_norm": 0.02918262593448162,
      "learning_rate": 0.01954520493745804,
      "loss": 2.3778810501098633,
      "step": 15056
    },
    {
      "epoch": 0.717047619047619,
      "grad_norm": 0.02623538300395012,
      "learning_rate": 0.019538629800081253,
      "loss": 2.3486320972442627,
      "step": 15058
    },
    {
      "epoch": 0.7171428571428572,
      "grad_norm": 0.025874536484479904,
      "learning_rate": 0.019532054662704468,
      "loss": 2.3394083976745605,
      "step": 15060
    },
    {
      "epoch": 0.7172380952380952,
      "grad_norm": 0.02623477391898632,
      "learning_rate": 0.019525479525327682,
      "loss": 2.366846799850464,
      "step": 15062
    },
    {
      "epoch": 0.7173333333333334,
      "grad_norm": 0.027533384039998055,
      "learning_rate": 0.019518904387950897,
      "loss": 2.366143226623535,
      "step": 15064
    },
    {
      "epoch": 0.7174285714285714,
      "grad_norm": 0.03212916478514671,
      "learning_rate": 0.019512327387928963,
      "loss": 2.297041654586792,
      "step": 15066
    },
    {
      "epoch": 0.7175238095238096,
      "grad_norm": 0.025744281709194183,
      "learning_rate": 0.019505754113197327,
      "loss": 2.3422083854675293,
      "step": 15068
    },
    {
      "epoch": 0.7176190476190476,
      "grad_norm": 0.025394855067133904,
      "learning_rate": 0.019499177113175392,
      "loss": 2.363295555114746,
      "step": 15070
    },
    {
      "epoch": 0.7177142857142857,
      "grad_norm": 0.027946067973971367,
      "learning_rate": 0.019492603838443756,
      "loss": 2.3629074096679688,
      "step": 15072
    },
    {
      "epoch": 0.7178095238095238,
      "grad_norm": 0.025905989110469818,
      "learning_rate": 0.01948602683842182,
      "loss": 2.4174933433532715,
      "step": 15074
    },
    {
      "epoch": 0.7179047619047619,
      "grad_norm": 0.025882558897137642,
      "learning_rate": 0.019479451701045036,
      "loss": 2.362771987915039,
      "step": 15076
    },
    {
      "epoch": 0.718,
      "grad_norm": 0.027264676988124847,
      "learning_rate": 0.01947287656366825,
      "loss": 2.3604178428649902,
      "step": 15078
    },
    {
      "epoch": 0.7180952380952381,
      "grad_norm": 0.025587594136595726,
      "learning_rate": 0.019466301426291466,
      "loss": 2.3631155490875244,
      "step": 15080
    },
    {
      "epoch": 0.7181904761904762,
      "grad_norm": 0.03127032145857811,
      "learning_rate": 0.01945972628891468,
      "loss": 2.3598601818084717,
      "step": 15082
    },
    {
      "epoch": 0.7182857142857143,
      "grad_norm": 0.03245281055569649,
      "learning_rate": 0.019453151151537895,
      "loss": 2.3755760192871094,
      "step": 15084
    },
    {
      "epoch": 0.7183809523809523,
      "grad_norm": 0.02561723254621029,
      "learning_rate": 0.01944657415151596,
      "loss": 2.3582077026367188,
      "step": 15086
    },
    {
      "epoch": 0.7184761904761905,
      "grad_norm": 0.027132652699947357,
      "learning_rate": 0.019440000876784325,
      "loss": 2.3988380432128906,
      "step": 15088
    },
    {
      "epoch": 0.7185714285714285,
      "grad_norm": 0.025796808302402496,
      "learning_rate": 0.01943342387676239,
      "loss": 2.4079766273498535,
      "step": 15090
    },
    {
      "epoch": 0.7186666666666667,
      "grad_norm": 0.02662590891122818,
      "learning_rate": 0.019426848739385605,
      "loss": 2.3486552238464355,
      "step": 15092
    },
    {
      "epoch": 0.7187619047619047,
      "grad_norm": 0.025438962504267693,
      "learning_rate": 0.01942027360200882,
      "loss": 2.3575451374053955,
      "step": 15094
    },
    {
      "epoch": 0.7188571428571429,
      "grad_norm": 0.026874015107750893,
      "learning_rate": 0.019413698464632034,
      "loss": 2.3410110473632812,
      "step": 15096
    },
    {
      "epoch": 0.7189523809523809,
      "grad_norm": 0.028343312442302704,
      "learning_rate": 0.01940712332725525,
      "loss": 2.313406229019165,
      "step": 15098
    },
    {
      "epoch": 0.719047619047619,
      "grad_norm": 0.026611439883708954,
      "learning_rate": 0.019400548189878464,
      "loss": 2.353070020675659,
      "step": 15100
    },
    {
      "epoch": 0.7191428571428572,
      "grad_norm": 0.02587355673313141,
      "learning_rate": 0.01939397118985653,
      "loss": 2.328432321548462,
      "step": 15102
    },
    {
      "epoch": 0.7192380952380952,
      "grad_norm": 0.02696993574500084,
      "learning_rate": 0.019387397915124893,
      "loss": 2.3398475646972656,
      "step": 15104
    },
    {
      "epoch": 0.7193333333333334,
      "grad_norm": 0.025522474199533463,
      "learning_rate": 0.01938082091510296,
      "loss": 2.3886914253234863,
      "step": 15106
    },
    {
      "epoch": 0.7194285714285714,
      "grad_norm": 0.027092069387435913,
      "learning_rate": 0.019374247640371323,
      "loss": 2.3856375217437744,
      "step": 15108
    },
    {
      "epoch": 0.7195238095238096,
      "grad_norm": 0.02791188657283783,
      "learning_rate": 0.019367670640349388,
      "loss": 2.388169288635254,
      "step": 15110
    },
    {
      "epoch": 0.7196190476190476,
      "grad_norm": 0.026186030358076096,
      "learning_rate": 0.019361095502972603,
      "loss": 2.3651366233825684,
      "step": 15112
    },
    {
      "epoch": 0.7197142857142858,
      "grad_norm": 0.026590384542942047,
      "learning_rate": 0.019354520365595818,
      "loss": 2.3676371574401855,
      "step": 15114
    },
    {
      "epoch": 0.7198095238095238,
      "grad_norm": 0.026089467108249664,
      "learning_rate": 0.019347945228219032,
      "loss": 2.411494731903076,
      "step": 15116
    },
    {
      "epoch": 0.7199047619047619,
      "grad_norm": 0.02560073882341385,
      "learning_rate": 0.019341370090842247,
      "loss": 2.386552333831787,
      "step": 15118
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.02677053026854992,
      "learning_rate": 0.01933479495346546,
      "loss": 2.3700127601623535,
      "step": 15120
    },
    {
      "epoch": 0.7200952380952381,
      "grad_norm": 0.02518317475914955,
      "learning_rate": 0.019328219816088676,
      "loss": 2.381269931793213,
      "step": 15122
    },
    {
      "epoch": 0.7201904761904762,
      "grad_norm": 0.027076879516243935,
      "learning_rate": 0.01932164467871189,
      "loss": 2.3995347023010254,
      "step": 15124
    },
    {
      "epoch": 0.7202857142857143,
      "grad_norm": 0.027925478294491768,
      "learning_rate": 0.019315069541335106,
      "loss": 2.385711669921875,
      "step": 15126
    },
    {
      "epoch": 0.7203809523809523,
      "grad_norm": 0.026285843923687935,
      "learning_rate": 0.01930849254131317,
      "loss": 2.3702797889709473,
      "step": 15128
    },
    {
      "epoch": 0.7204761904761905,
      "grad_norm": 0.02596811018884182,
      "learning_rate": 0.019301919266581535,
      "loss": 2.323136329650879,
      "step": 15130
    },
    {
      "epoch": 0.7205714285714285,
      "grad_norm": 0.026843121275305748,
      "learning_rate": 0.0192953422665596,
      "loss": 2.371209144592285,
      "step": 15132
    },
    {
      "epoch": 0.7206666666666667,
      "grad_norm": 0.025846078991889954,
      "learning_rate": 0.019288767129182816,
      "loss": 2.3854970932006836,
      "step": 15134
    },
    {
      "epoch": 0.7207619047619047,
      "grad_norm": 0.02617582306265831,
      "learning_rate": 0.01928219199180603,
      "loss": 2.4090566635131836,
      "step": 15136
    },
    {
      "epoch": 0.7208571428571429,
      "grad_norm": 0.025867028161883354,
      "learning_rate": 0.019275616854429245,
      "loss": 2.3554186820983887,
      "step": 15138
    },
    {
      "epoch": 0.7209523809523809,
      "grad_norm": 0.027322279289364815,
      "learning_rate": 0.01926904171705246,
      "loss": 2.3527023792266846,
      "step": 15140
    },
    {
      "epoch": 0.721047619047619,
      "grad_norm": 0.025838598608970642,
      "learning_rate": 0.019262466579675674,
      "loss": 2.3722236156463623,
      "step": 15142
    },
    {
      "epoch": 0.7211428571428572,
      "grad_norm": 0.025581803172826767,
      "learning_rate": 0.01925589144229889,
      "loss": 2.368626117706299,
      "step": 15144
    },
    {
      "epoch": 0.7212380952380952,
      "grad_norm": 0.025134757161140442,
      "learning_rate": 0.019249316304922104,
      "loss": 2.3542633056640625,
      "step": 15146
    },
    {
      "epoch": 0.7213333333333334,
      "grad_norm": 0.026113692671060562,
      "learning_rate": 0.01924273930490017,
      "loss": 2.385822296142578,
      "step": 15148
    },
    {
      "epoch": 0.7214285714285714,
      "grad_norm": 0.026744598522782326,
      "learning_rate": 0.019236166030168533,
      "loss": 2.3841559886932373,
      "step": 15150
    },
    {
      "epoch": 0.7215238095238096,
      "grad_norm": 0.025854814797639847,
      "learning_rate": 0.0192295890301466,
      "loss": 2.436155319213867,
      "step": 15152
    },
    {
      "epoch": 0.7216190476190476,
      "grad_norm": 0.02726590633392334,
      "learning_rate": 0.019223013892769814,
      "loss": 2.3761343955993652,
      "step": 15154
    },
    {
      "epoch": 0.7217142857142858,
      "grad_norm": 0.026066027581691742,
      "learning_rate": 0.019216438755393028,
      "loss": 2.3527603149414062,
      "step": 15156
    },
    {
      "epoch": 0.7218095238095238,
      "grad_norm": 0.025994453579187393,
      "learning_rate": 0.019209863618016243,
      "loss": 2.344118595123291,
      "step": 15158
    },
    {
      "epoch": 0.7219047619047619,
      "grad_norm": 0.02608698606491089,
      "learning_rate": 0.019203288480639458,
      "loss": 2.388861656188965,
      "step": 15160
    },
    {
      "epoch": 0.722,
      "grad_norm": 0.027722882106900215,
      "learning_rate": 0.019196713343262672,
      "loss": 2.3554329872131348,
      "step": 15162
    },
    {
      "epoch": 0.7220952380952381,
      "grad_norm": 0.030190544202923775,
      "learning_rate": 0.019190136343240738,
      "loss": 2.406351089477539,
      "step": 15164
    },
    {
      "epoch": 0.7221904761904762,
      "grad_norm": 0.02588650956749916,
      "learning_rate": 0.019183563068509102,
      "loss": 2.354224681854248,
      "step": 15166
    },
    {
      "epoch": 0.7222857142857143,
      "grad_norm": 0.026674646884202957,
      "learning_rate": 0.019176986068487167,
      "loss": 2.3712873458862305,
      "step": 15168
    },
    {
      "epoch": 0.7223809523809523,
      "grad_norm": 0.025483274832367897,
      "learning_rate": 0.019170410931110382,
      "loss": 2.3746416568756104,
      "step": 15170
    },
    {
      "epoch": 0.7224761904761905,
      "grad_norm": 0.02614513970911503,
      "learning_rate": 0.019163835793733597,
      "loss": 2.3678135871887207,
      "step": 15172
    },
    {
      "epoch": 0.7225714285714285,
      "grad_norm": 0.02492862567305565,
      "learning_rate": 0.01915726065635681,
      "loss": 2.361236095428467,
      "step": 15174
    },
    {
      "epoch": 0.7226666666666667,
      "grad_norm": 0.025383593514561653,
      "learning_rate": 0.019150685518980026,
      "loss": 2.3607916831970215,
      "step": 15176
    },
    {
      "epoch": 0.7227619047619047,
      "grad_norm": 0.028080327436327934,
      "learning_rate": 0.01914411038160324,
      "loss": 2.3487820625305176,
      "step": 15178
    },
    {
      "epoch": 0.7228571428571429,
      "grad_norm": 0.02729123830795288,
      "learning_rate": 0.019137533381581306,
      "loss": 2.3665521144866943,
      "step": 15180
    },
    {
      "epoch": 0.7229523809523809,
      "grad_norm": 0.027587443590164185,
      "learning_rate": 0.01913096010684967,
      "loss": 2.384793281555176,
      "step": 15182
    },
    {
      "epoch": 0.723047619047619,
      "grad_norm": 0.02724936231970787,
      "learning_rate": 0.019124383106827736,
      "loss": 2.3424105644226074,
      "step": 15184
    },
    {
      "epoch": 0.7231428571428572,
      "grad_norm": 0.024827072396874428,
      "learning_rate": 0.0191178098320961,
      "loss": 2.3319473266601562,
      "step": 15186
    },
    {
      "epoch": 0.7232380952380952,
      "grad_norm": 0.027130398899316788,
      "learning_rate": 0.019111232832074165,
      "loss": 2.4101438522338867,
      "step": 15188
    },
    {
      "epoch": 0.7233333333333334,
      "grad_norm": 0.02750711888074875,
      "learning_rate": 0.01910465769469738,
      "loss": 2.3653171062469482,
      "step": 15190
    },
    {
      "epoch": 0.7234285714285714,
      "grad_norm": 0.02773682214319706,
      "learning_rate": 0.019098082557320595,
      "loss": 2.3753271102905273,
      "step": 15192
    },
    {
      "epoch": 0.7235238095238096,
      "grad_norm": 0.026956750079989433,
      "learning_rate": 0.01909150741994381,
      "loss": 2.4087109565734863,
      "step": 15194
    },
    {
      "epoch": 0.7236190476190476,
      "grad_norm": 0.025770237669348717,
      "learning_rate": 0.019084932282567024,
      "loss": 2.32291316986084,
      "step": 15196
    },
    {
      "epoch": 0.7237142857142858,
      "grad_norm": 0.0261429101228714,
      "learning_rate": 0.01907835714519024,
      "loss": 2.41044545173645,
      "step": 15198
    },
    {
      "epoch": 0.7238095238095238,
      "grad_norm": 0.026039518415927887,
      "learning_rate": 0.019071780145168304,
      "loss": 2.3975987434387207,
      "step": 15200
    },
    {
      "epoch": 0.7239047619047619,
      "grad_norm": 0.02910463698208332,
      "learning_rate": 0.01906520687043667,
      "loss": 2.4152209758758545,
      "step": 15202
    },
    {
      "epoch": 0.724,
      "grad_norm": 0.026574622839689255,
      "learning_rate": 0.019058629870414734,
      "loss": 2.3398470878601074,
      "step": 15204
    },
    {
      "epoch": 0.7240952380952381,
      "grad_norm": 0.026588501408696175,
      "learning_rate": 0.01905205473303795,
      "loss": 2.3941524028778076,
      "step": 15206
    },
    {
      "epoch": 0.7241904761904762,
      "grad_norm": 0.026031406596302986,
      "learning_rate": 0.019045479595661163,
      "loss": 2.357435941696167,
      "step": 15208
    },
    {
      "epoch": 0.7242857142857143,
      "grad_norm": 0.027828345075249672,
      "learning_rate": 0.019038904458284378,
      "loss": 2.378911018371582,
      "step": 15210
    },
    {
      "epoch": 0.7243809523809523,
      "grad_norm": 0.02619311958551407,
      "learning_rate": 0.019032329320907593,
      "loss": 2.4048757553100586,
      "step": 15212
    },
    {
      "epoch": 0.7244761904761905,
      "grad_norm": 0.02821364626288414,
      "learning_rate": 0.019025754183530807,
      "loss": 2.426086902618408,
      "step": 15214
    },
    {
      "epoch": 0.7245714285714285,
      "grad_norm": 0.0250778179615736,
      "learning_rate": 0.019019177183508873,
      "loss": 2.355103015899658,
      "step": 15216
    },
    {
      "epoch": 0.7246666666666667,
      "grad_norm": 0.025161664932966232,
      "learning_rate": 0.019012603908777237,
      "loss": 2.366468906402588,
      "step": 15218
    },
    {
      "epoch": 0.7247619047619047,
      "grad_norm": 0.02769194357097149,
      "learning_rate": 0.019006026908755302,
      "loss": 2.382730007171631,
      "step": 15220
    },
    {
      "epoch": 0.7248571428571429,
      "grad_norm": 0.02611970156431198,
      "learning_rate": 0.018999453634023666,
      "loss": 2.365675210952759,
      "step": 15222
    },
    {
      "epoch": 0.7249523809523809,
      "grad_norm": 0.02595735341310501,
      "learning_rate": 0.018992876634001732,
      "loss": 2.3610057830810547,
      "step": 15224
    },
    {
      "epoch": 0.725047619047619,
      "grad_norm": 0.02594320848584175,
      "learning_rate": 0.018986301496624947,
      "loss": 2.3859572410583496,
      "step": 15226
    },
    {
      "epoch": 0.7251428571428571,
      "grad_norm": 0.025332635268568993,
      "learning_rate": 0.01897972635924816,
      "loss": 2.4027457237243652,
      "step": 15228
    },
    {
      "epoch": 0.7252380952380952,
      "grad_norm": 0.024790486320853233,
      "learning_rate": 0.018973151221871376,
      "loss": 2.3800926208496094,
      "step": 15230
    },
    {
      "epoch": 0.7253333333333334,
      "grad_norm": 0.030299417674541473,
      "learning_rate": 0.01896657608449459,
      "loss": 2.3915200233459473,
      "step": 15232
    },
    {
      "epoch": 0.7254285714285714,
      "grad_norm": 0.02622968703508377,
      "learning_rate": 0.018960000947117805,
      "loss": 2.4062957763671875,
      "step": 15234
    },
    {
      "epoch": 0.7255238095238096,
      "grad_norm": 0.02652839571237564,
      "learning_rate": 0.01895342394709587,
      "loss": 2.352564811706543,
      "step": 15236
    },
    {
      "epoch": 0.7256190476190476,
      "grad_norm": 0.02752676047384739,
      "learning_rate": 0.018946850672364235,
      "loss": 2.3439879417419434,
      "step": 15238
    },
    {
      "epoch": 0.7257142857142858,
      "grad_norm": 0.025600465014576912,
      "learning_rate": 0.0189402736723423,
      "loss": 2.3665194511413574,
      "step": 15240
    },
    {
      "epoch": 0.7258095238095238,
      "grad_norm": 0.025393683463335037,
      "learning_rate": 0.018933698534965515,
      "loss": 2.3781654834747314,
      "step": 15242
    },
    {
      "epoch": 0.7259047619047619,
      "grad_norm": 0.026340622454881668,
      "learning_rate": 0.01892712339758873,
      "loss": 2.3609371185302734,
      "step": 15244
    },
    {
      "epoch": 0.726,
      "grad_norm": 0.025212280452251434,
      "learning_rate": 0.018920548260211945,
      "loss": 2.3539066314697266,
      "step": 15246
    },
    {
      "epoch": 0.7260952380952381,
      "grad_norm": 0.025481095537543297,
      "learning_rate": 0.01891397312283516,
      "loss": 2.3538413047790527,
      "step": 15248
    },
    {
      "epoch": 0.7261904761904762,
      "grad_norm": 0.02523799240589142,
      "learning_rate": 0.018907397985458374,
      "loss": 2.358488082885742,
      "step": 15250
    },
    {
      "epoch": 0.7262857142857143,
      "grad_norm": 0.02542700059711933,
      "learning_rate": 0.01890082098543644,
      "loss": 2.366429328918457,
      "step": 15252
    },
    {
      "epoch": 0.7263809523809523,
      "grad_norm": 0.025170888751745224,
      "learning_rate": 0.018894247710704803,
      "loss": 2.405271530151367,
      "step": 15254
    },
    {
      "epoch": 0.7264761904761905,
      "grad_norm": 0.02888454683125019,
      "learning_rate": 0.01888767071068287,
      "loss": 2.3885974884033203,
      "step": 15256
    },
    {
      "epoch": 0.7265714285714285,
      "grad_norm": 0.02677515707910061,
      "learning_rate": 0.018881097435951233,
      "loss": 2.355015993118286,
      "step": 15258
    },
    {
      "epoch": 0.7266666666666667,
      "grad_norm": 0.02633916214108467,
      "learning_rate": 0.0188745204359293,
      "loss": 2.364135265350342,
      "step": 15260
    },
    {
      "epoch": 0.7267619047619047,
      "grad_norm": 0.02672755718231201,
      "learning_rate": 0.018867945298552513,
      "loss": 2.3996496200561523,
      "step": 15262
    },
    {
      "epoch": 0.7268571428571429,
      "grad_norm": 0.025831835344433784,
      "learning_rate": 0.018861370161175728,
      "loss": 2.3986635208129883,
      "step": 15264
    },
    {
      "epoch": 0.7269523809523809,
      "grad_norm": 0.026527198031544685,
      "learning_rate": 0.018854795023798943,
      "loss": 2.3962652683258057,
      "step": 15266
    },
    {
      "epoch": 0.727047619047619,
      "grad_norm": 0.0278646070510149,
      "learning_rate": 0.018848219886422157,
      "loss": 2.373182773590088,
      "step": 15268
    },
    {
      "epoch": 0.7271428571428571,
      "grad_norm": 0.026290493085980415,
      "learning_rate": 0.018841644749045372,
      "loss": 2.3597848415374756,
      "step": 15270
    },
    {
      "epoch": 0.7272380952380952,
      "grad_norm": 0.02793416567146778,
      "learning_rate": 0.018835067749023438,
      "loss": 2.358440637588501,
      "step": 15272
    },
    {
      "epoch": 0.7273333333333334,
      "grad_norm": 0.025540918111801147,
      "learning_rate": 0.0188284944742918,
      "loss": 2.3604464530944824,
      "step": 15274
    },
    {
      "epoch": 0.7274285714285714,
      "grad_norm": 0.030248254537582397,
      "learning_rate": 0.018821917474269867,
      "loss": 2.426537275314331,
      "step": 15276
    },
    {
      "epoch": 0.7275238095238096,
      "grad_norm": 0.027517782524228096,
      "learning_rate": 0.01881534233689308,
      "loss": 2.4142308235168457,
      "step": 15278
    },
    {
      "epoch": 0.7276190476190476,
      "grad_norm": 0.02641669102013111,
      "learning_rate": 0.018808767199516296,
      "loss": 2.3754019737243652,
      "step": 15280
    },
    {
      "epoch": 0.7277142857142858,
      "grad_norm": 0.024802766740322113,
      "learning_rate": 0.01880219206213951,
      "loss": 2.3995003700256348,
      "step": 15282
    },
    {
      "epoch": 0.7278095238095238,
      "grad_norm": 0.02572629041969776,
      "learning_rate": 0.018795616924762726,
      "loss": 2.3884096145629883,
      "step": 15284
    },
    {
      "epoch": 0.7279047619047619,
      "grad_norm": 0.025614337995648384,
      "learning_rate": 0.01878904178738594,
      "loss": 2.36983060836792,
      "step": 15286
    },
    {
      "epoch": 0.728,
      "grad_norm": 0.026690956205129623,
      "learning_rate": 0.018782464787364006,
      "loss": 2.36472225189209,
      "step": 15288
    },
    {
      "epoch": 0.7280952380952381,
      "grad_norm": 0.026669664308428764,
      "learning_rate": 0.01877589151263237,
      "loss": 2.4027202129364014,
      "step": 15290
    },
    {
      "epoch": 0.7281904761904762,
      "grad_norm": 0.024892352521419525,
      "learning_rate": 0.018769314512610435,
      "loss": 2.3895626068115234,
      "step": 15292
    },
    {
      "epoch": 0.7282857142857143,
      "grad_norm": 0.025380335748195648,
      "learning_rate": 0.01876273937523365,
      "loss": 2.362504005432129,
      "step": 15294
    },
    {
      "epoch": 0.7283809523809524,
      "grad_norm": 0.025349317118525505,
      "learning_rate": 0.018756164237856865,
      "loss": 2.3979625701904297,
      "step": 15296
    },
    {
      "epoch": 0.7284761904761905,
      "grad_norm": 0.028007224202156067,
      "learning_rate": 0.01874958910048008,
      "loss": 2.3432817459106445,
      "step": 15298
    },
    {
      "epoch": 0.7285714285714285,
      "grad_norm": 0.025343144312500954,
      "learning_rate": 0.018743013963103294,
      "loss": 2.383787155151367,
      "step": 15300
    },
    {
      "epoch": 0.7286666666666667,
      "grad_norm": 0.02610095590353012,
      "learning_rate": 0.01873643882572651,
      "loss": 2.3993163108825684,
      "step": 15302
    },
    {
      "epoch": 0.7287619047619047,
      "grad_norm": 0.02834979072213173,
      "learning_rate": 0.018729863688349724,
      "loss": 2.4102182388305664,
      "step": 15304
    },
    {
      "epoch": 0.7288571428571429,
      "grad_norm": 0.028444720432162285,
      "learning_rate": 0.01872328855097294,
      "loss": 2.431774139404297,
      "step": 15306
    },
    {
      "epoch": 0.7289523809523809,
      "grad_norm": 0.02867240458726883,
      "learning_rate": 0.018716711550951004,
      "loss": 2.3626339435577393,
      "step": 15308
    },
    {
      "epoch": 0.729047619047619,
      "grad_norm": 0.026156583800911903,
      "learning_rate": 0.018710138276219368,
      "loss": 2.3690438270568848,
      "step": 15310
    },
    {
      "epoch": 0.7291428571428571,
      "grad_norm": 0.02542552351951599,
      "learning_rate": 0.018703561276197433,
      "loss": 2.347487688064575,
      "step": 15312
    },
    {
      "epoch": 0.7292380952380952,
      "grad_norm": 0.029663661494851112,
      "learning_rate": 0.018696986138820648,
      "loss": 2.3770551681518555,
      "step": 15314
    },
    {
      "epoch": 0.7293333333333333,
      "grad_norm": 0.03129972517490387,
      "learning_rate": 0.018690411001443863,
      "loss": 2.382101535797119,
      "step": 15316
    },
    {
      "epoch": 0.7294285714285714,
      "grad_norm": 0.025644171983003616,
      "learning_rate": 0.018683835864067078,
      "loss": 2.378249168395996,
      "step": 15318
    },
    {
      "epoch": 0.7295238095238096,
      "grad_norm": 0.02765338309109211,
      "learning_rate": 0.018677260726690292,
      "loss": 2.3457717895507812,
      "step": 15320
    },
    {
      "epoch": 0.7296190476190476,
      "grad_norm": 0.026862457394599915,
      "learning_rate": 0.018670685589313507,
      "loss": 2.397500991821289,
      "step": 15322
    },
    {
      "epoch": 0.7297142857142858,
      "grad_norm": 0.025465495884418488,
      "learning_rate": 0.018664108589291573,
      "loss": 2.3701553344726562,
      "step": 15324
    },
    {
      "epoch": 0.7298095238095238,
      "grad_norm": 0.02730472944676876,
      "learning_rate": 0.018657535314559937,
      "loss": 2.363633632659912,
      "step": 15326
    },
    {
      "epoch": 0.729904761904762,
      "grad_norm": 0.027047080919146538,
      "learning_rate": 0.018650958314538002,
      "loss": 2.4203298091888428,
      "step": 15328
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.02582465671002865,
      "learning_rate": 0.018644383177161217,
      "loss": 2.374755859375,
      "step": 15330
    },
    {
      "epoch": 0.7300952380952381,
      "grad_norm": 0.03266439214348793,
      "learning_rate": 0.01863780803978443,
      "loss": 2.368558645248413,
      "step": 15332
    },
    {
      "epoch": 0.7301904761904762,
      "grad_norm": 0.02613827958703041,
      "learning_rate": 0.018631232902407646,
      "loss": 2.3933534622192383,
      "step": 15334
    },
    {
      "epoch": 0.7302857142857143,
      "grad_norm": 0.028849581256508827,
      "learning_rate": 0.01862465776503086,
      "loss": 2.3790063858032227,
      "step": 15336
    },
    {
      "epoch": 0.7303809523809524,
      "grad_norm": 0.027398420497775078,
      "learning_rate": 0.018618082627654076,
      "loss": 2.3959295749664307,
      "step": 15338
    },
    {
      "epoch": 0.7304761904761905,
      "grad_norm": 0.028846068307757378,
      "learning_rate": 0.01861150749027729,
      "loss": 2.399057626724243,
      "step": 15340
    },
    {
      "epoch": 0.7305714285714285,
      "grad_norm": 0.025816602632403374,
      "learning_rate": 0.018604932352900505,
      "loss": 2.399055004119873,
      "step": 15342
    },
    {
      "epoch": 0.7306666666666667,
      "grad_norm": 0.027379939332604408,
      "learning_rate": 0.01859835535287857,
      "loss": 2.370433807373047,
      "step": 15344
    },
    {
      "epoch": 0.7307619047619047,
      "grad_norm": 0.029091008007526398,
      "learning_rate": 0.018591782078146935,
      "loss": 2.3861892223358154,
      "step": 15346
    },
    {
      "epoch": 0.7308571428571429,
      "grad_norm": 0.028706377372145653,
      "learning_rate": 0.018585205078125,
      "loss": 2.3736205101013184,
      "step": 15348
    },
    {
      "epoch": 0.7309523809523809,
      "grad_norm": 0.026885556057095528,
      "learning_rate": 0.018578629940748215,
      "loss": 2.3927223682403564,
      "step": 15350
    },
    {
      "epoch": 0.7310476190476191,
      "grad_norm": 0.026686998084187508,
      "learning_rate": 0.01857205480337143,
      "loss": 2.430769443511963,
      "step": 15352
    },
    {
      "epoch": 0.7311428571428571,
      "grad_norm": 0.028046920895576477,
      "learning_rate": 0.018565479665994644,
      "loss": 2.389317035675049,
      "step": 15354
    },
    {
      "epoch": 0.7312380952380952,
      "grad_norm": 0.029130665585398674,
      "learning_rate": 0.01855890452861786,
      "loss": 2.422238826751709,
      "step": 15356
    },
    {
      "epoch": 0.7313333333333333,
      "grad_norm": 0.027769677340984344,
      "learning_rate": 0.018552329391241074,
      "loss": 2.380801200866699,
      "step": 15358
    },
    {
      "epoch": 0.7314285714285714,
      "grad_norm": 0.027684735134243965,
      "learning_rate": 0.01854575239121914,
      "loss": 2.3585495948791504,
      "step": 15360
    },
    {
      "epoch": 0.7315238095238096,
      "grad_norm": 0.02603060193359852,
      "learning_rate": 0.018539179116487503,
      "loss": 2.4010541439056396,
      "step": 15362
    },
    {
      "epoch": 0.7316190476190476,
      "grad_norm": 0.026965122669935226,
      "learning_rate": 0.01853260211646557,
      "loss": 2.3451766967773438,
      "step": 15364
    },
    {
      "epoch": 0.7317142857142858,
      "grad_norm": 0.02599172480404377,
      "learning_rate": 0.018526026979088783,
      "loss": 2.3914995193481445,
      "step": 15366
    },
    {
      "epoch": 0.7318095238095238,
      "grad_norm": 0.026203887537121773,
      "learning_rate": 0.018519451841711998,
      "loss": 2.390079975128174,
      "step": 15368
    },
    {
      "epoch": 0.731904761904762,
      "grad_norm": 0.028142716735601425,
      "learning_rate": 0.018512876704335213,
      "loss": 2.3558130264282227,
      "step": 15370
    },
    {
      "epoch": 0.732,
      "grad_norm": 0.026295457035303116,
      "learning_rate": 0.018506301566958427,
      "loss": 2.3454535007476807,
      "step": 15372
    },
    {
      "epoch": 0.7320952380952381,
      "grad_norm": 0.025547729805111885,
      "learning_rate": 0.018499726429581642,
      "loss": 2.36720609664917,
      "step": 15374
    },
    {
      "epoch": 0.7321904761904762,
      "grad_norm": 0.025338895618915558,
      "learning_rate": 0.018493151292204857,
      "loss": 2.3472912311553955,
      "step": 15376
    },
    {
      "epoch": 0.7322857142857143,
      "grad_norm": 0.0277293398976326,
      "learning_rate": 0.01848657615482807,
      "loss": 2.3775739669799805,
      "step": 15378
    },
    {
      "epoch": 0.7323809523809524,
      "grad_norm": 0.026738733053207397,
      "learning_rate": 0.018479999154806137,
      "loss": 2.3740074634552,
      "step": 15380
    },
    {
      "epoch": 0.7324761904761905,
      "grad_norm": 0.025275427848100662,
      "learning_rate": 0.0184734258800745,
      "loss": 2.362675666809082,
      "step": 15382
    },
    {
      "epoch": 0.7325714285714285,
      "grad_norm": 0.02684083767235279,
      "learning_rate": 0.018466848880052567,
      "loss": 2.3951191902160645,
      "step": 15384
    },
    {
      "epoch": 0.7326666666666667,
      "grad_norm": 0.024970771744847298,
      "learning_rate": 0.01846027374267578,
      "loss": 2.4005684852600098,
      "step": 15386
    },
    {
      "epoch": 0.7327619047619047,
      "grad_norm": 0.025690244510769844,
      "learning_rate": 0.018453698605298996,
      "loss": 2.3801286220550537,
      "step": 15388
    },
    {
      "epoch": 0.7328571428571429,
      "grad_norm": 0.030914129689335823,
      "learning_rate": 0.01844712346792221,
      "loss": 2.3713841438293457,
      "step": 15390
    },
    {
      "epoch": 0.7329523809523809,
      "grad_norm": 0.027420494705438614,
      "learning_rate": 0.018440548330545425,
      "loss": 2.3492565155029297,
      "step": 15392
    },
    {
      "epoch": 0.7330476190476191,
      "grad_norm": 0.027036022394895554,
      "learning_rate": 0.01843397319316864,
      "loss": 2.3786826133728027,
      "step": 15394
    },
    {
      "epoch": 0.7331428571428571,
      "grad_norm": 0.025963103398680687,
      "learning_rate": 0.018427396193146706,
      "loss": 2.3669376373291016,
      "step": 15396
    },
    {
      "epoch": 0.7332380952380952,
      "grad_norm": 0.0263023991137743,
      "learning_rate": 0.01842082291841507,
      "loss": 2.3827404975891113,
      "step": 15398
    },
    {
      "epoch": 0.7333333333333333,
      "grad_norm": 0.026546403765678406,
      "learning_rate": 0.018414245918393135,
      "loss": 2.3861284255981445,
      "step": 15400
    },
    {
      "epoch": 0.7334285714285714,
      "grad_norm": 0.025618407875299454,
      "learning_rate": 0.01840767078101635,
      "loss": 2.40620756149292,
      "step": 15402
    },
    {
      "epoch": 0.7335238095238096,
      "grad_norm": 0.026574790477752686,
      "learning_rate": 0.018401095643639565,
      "loss": 2.3783841133117676,
      "step": 15404
    },
    {
      "epoch": 0.7336190476190476,
      "grad_norm": 0.0251972246915102,
      "learning_rate": 0.01839452050626278,
      "loss": 2.4136428833007812,
      "step": 15406
    },
    {
      "epoch": 0.7337142857142858,
      "grad_norm": 0.025837894529104233,
      "learning_rate": 0.018387945368885994,
      "loss": 2.3634467124938965,
      "step": 15408
    },
    {
      "epoch": 0.7338095238095238,
      "grad_norm": 0.02684752084314823,
      "learning_rate": 0.01838137023150921,
      "loss": 2.4119598865509033,
      "step": 15410
    },
    {
      "epoch": 0.733904761904762,
      "grad_norm": 0.025651197880506516,
      "learning_rate": 0.018374795094132423,
      "loss": 2.373897075653076,
      "step": 15412
    },
    {
      "epoch": 0.734,
      "grad_norm": 0.025938594713807106,
      "learning_rate": 0.018368219956755638,
      "loss": 2.3681435585021973,
      "step": 15414
    },
    {
      "epoch": 0.7340952380952381,
      "grad_norm": 0.026270130649209023,
      "learning_rate": 0.018361642956733704,
      "loss": 2.348132848739624,
      "step": 15416
    },
    {
      "epoch": 0.7341904761904762,
      "grad_norm": 0.025986403226852417,
      "learning_rate": 0.018355069682002068,
      "loss": 2.332057476043701,
      "step": 15418
    },
    {
      "epoch": 0.7342857142857143,
      "grad_norm": 0.026202933862805367,
      "learning_rate": 0.018348492681980133,
      "loss": 2.3675220012664795,
      "step": 15420
    },
    {
      "epoch": 0.7343809523809524,
      "grad_norm": 0.026841996237635612,
      "learning_rate": 0.018341917544603348,
      "loss": 2.325416088104248,
      "step": 15422
    },
    {
      "epoch": 0.7344761904761905,
      "grad_norm": 0.025805678218603134,
      "learning_rate": 0.018335342407226562,
      "loss": 2.3587794303894043,
      "step": 15424
    },
    {
      "epoch": 0.7345714285714285,
      "grad_norm": 0.026292894035577774,
      "learning_rate": 0.018328767269849777,
      "loss": 2.3425426483154297,
      "step": 15426
    },
    {
      "epoch": 0.7346666666666667,
      "grad_norm": 0.02649039588868618,
      "learning_rate": 0.018322192132472992,
      "loss": 2.3979504108428955,
      "step": 15428
    },
    {
      "epoch": 0.7347619047619047,
      "grad_norm": 0.028186645358800888,
      "learning_rate": 0.018315616995096207,
      "loss": 2.368335008621216,
      "step": 15430
    },
    {
      "epoch": 0.7348571428571429,
      "grad_norm": 0.027124974876642227,
      "learning_rate": 0.018309039995074272,
      "loss": 2.3270816802978516,
      "step": 15432
    },
    {
      "epoch": 0.7349523809523809,
      "grad_norm": 0.026396509259939194,
      "learning_rate": 0.018302466720342636,
      "loss": 2.347776412963867,
      "step": 15434
    },
    {
      "epoch": 0.7350476190476191,
      "grad_norm": 0.025079233571887016,
      "learning_rate": 0.0182958897203207,
      "loss": 2.3425240516662598,
      "step": 15436
    },
    {
      "epoch": 0.7351428571428571,
      "grad_norm": 0.02568703517317772,
      "learning_rate": 0.018289314582943916,
      "loss": 2.3250651359558105,
      "step": 15438
    },
    {
      "epoch": 0.7352380952380952,
      "grad_norm": 0.02804923802614212,
      "learning_rate": 0.01828273944556713,
      "loss": 2.348559856414795,
      "step": 15440
    },
    {
      "epoch": 0.7353333333333333,
      "grad_norm": 0.029926897957921028,
      "learning_rate": 0.018276164308190346,
      "loss": 2.3646650314331055,
      "step": 15442
    },
    {
      "epoch": 0.7354285714285714,
      "grad_norm": 0.03155452758073807,
      "learning_rate": 0.01826958917081356,
      "loss": 2.365105152130127,
      "step": 15444
    },
    {
      "epoch": 0.7355238095238095,
      "grad_norm": 0.026557469740509987,
      "learning_rate": 0.018263014033436775,
      "loss": 2.337434768676758,
      "step": 15446
    },
    {
      "epoch": 0.7356190476190476,
      "grad_norm": 0.026180610060691833,
      "learning_rate": 0.01825643703341484,
      "loss": 2.365389347076416,
      "step": 15448
    },
    {
      "epoch": 0.7357142857142858,
      "grad_norm": 0.024962229654192924,
      "learning_rate": 0.018249863758683205,
      "loss": 2.337594985961914,
      "step": 15450
    },
    {
      "epoch": 0.7358095238095238,
      "grad_norm": 0.025834988802671432,
      "learning_rate": 0.01824328675866127,
      "loss": 2.337247848510742,
      "step": 15452
    },
    {
      "epoch": 0.735904761904762,
      "grad_norm": 0.024887770414352417,
      "learning_rate": 0.018236713483929634,
      "loss": 2.370060682296753,
      "step": 15454
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.02693953365087509,
      "learning_rate": 0.0182301364839077,
      "loss": 2.374703884124756,
      "step": 15456
    },
    {
      "epoch": 0.7360952380952381,
      "grad_norm": 0.026177743449807167,
      "learning_rate": 0.018223561346530914,
      "loss": 2.36273193359375,
      "step": 15458
    },
    {
      "epoch": 0.7361904761904762,
      "grad_norm": 0.025637397542595863,
      "learning_rate": 0.01821698620915413,
      "loss": 2.355320453643799,
      "step": 15460
    },
    {
      "epoch": 0.7362857142857143,
      "grad_norm": 0.025522558018565178,
      "learning_rate": 0.018210411071777344,
      "loss": 2.3607234954833984,
      "step": 15462
    },
    {
      "epoch": 0.7363809523809524,
      "grad_norm": 0.025990338996052742,
      "learning_rate": 0.01820383593440056,
      "loss": 2.3650240898132324,
      "step": 15464
    },
    {
      "epoch": 0.7364761904761905,
      "grad_norm": 0.02626601792871952,
      "learning_rate": 0.018197260797023773,
      "loss": 2.360414981842041,
      "step": 15466
    },
    {
      "epoch": 0.7365714285714285,
      "grad_norm": 0.025338027626276016,
      "learning_rate": 0.01819068379700184,
      "loss": 2.333975315093994,
      "step": 15468
    },
    {
      "epoch": 0.7366666666666667,
      "grad_norm": 0.026090111583471298,
      "learning_rate": 0.018184110522270203,
      "loss": 2.3561692237854004,
      "step": 15470
    },
    {
      "epoch": 0.7367619047619047,
      "grad_norm": 0.0265871062874794,
      "learning_rate": 0.018177533522248268,
      "loss": 2.3327770233154297,
      "step": 15472
    },
    {
      "epoch": 0.7368571428571429,
      "grad_norm": 0.025207186117768288,
      "learning_rate": 0.018170958384871483,
      "loss": 2.3810951709747314,
      "step": 15474
    },
    {
      "epoch": 0.7369523809523809,
      "grad_norm": 0.02802153490483761,
      "learning_rate": 0.018164383247494698,
      "loss": 2.3261585235595703,
      "step": 15476
    },
    {
      "epoch": 0.7370476190476191,
      "grad_norm": 0.026032522320747375,
      "learning_rate": 0.018157808110117912,
      "loss": 2.374445676803589,
      "step": 15478
    },
    {
      "epoch": 0.7371428571428571,
      "grad_norm": 0.024956760928034782,
      "learning_rate": 0.018151232972741127,
      "loss": 2.3311667442321777,
      "step": 15480
    },
    {
      "epoch": 0.7372380952380952,
      "grad_norm": 0.029985038563609123,
      "learning_rate": 0.018144657835364342,
      "loss": 2.3467915058135986,
      "step": 15482
    },
    {
      "epoch": 0.7373333333333333,
      "grad_norm": 0.03466275706887245,
      "learning_rate": 0.018138080835342407,
      "loss": 2.3583219051361084,
      "step": 15484
    },
    {
      "epoch": 0.7374285714285714,
      "grad_norm": 0.028474224731326103,
      "learning_rate": 0.01813150756061077,
      "loss": 2.365318775177002,
      "step": 15486
    },
    {
      "epoch": 0.7375238095238095,
      "grad_norm": 0.025433536618947983,
      "learning_rate": 0.018124930560588837,
      "loss": 2.328592300415039,
      "step": 15488
    },
    {
      "epoch": 0.7376190476190476,
      "grad_norm": 0.026312559843063354,
      "learning_rate": 0.0181183572858572,
      "loss": 2.3362984657287598,
      "step": 15490
    },
    {
      "epoch": 0.7377142857142858,
      "grad_norm": 0.02632959745824337,
      "learning_rate": 0.018111780285835266,
      "loss": 2.3491628170013428,
      "step": 15492
    },
    {
      "epoch": 0.7378095238095238,
      "grad_norm": 0.02643604762852192,
      "learning_rate": 0.01810520514845848,
      "loss": 2.3690783977508545,
      "step": 15494
    },
    {
      "epoch": 0.737904761904762,
      "grad_norm": 0.026177145540714264,
      "learning_rate": 0.018098630011081696,
      "loss": 2.3959383964538574,
      "step": 15496
    },
    {
      "epoch": 0.738,
      "grad_norm": 0.02577868476510048,
      "learning_rate": 0.01809205487370491,
      "loss": 2.3120603561401367,
      "step": 15498
    },
    {
      "epoch": 0.7380952380952381,
      "grad_norm": 0.026492565870285034,
      "learning_rate": 0.018085479736328125,
      "loss": 2.3557052612304688,
      "step": 15500
    },
    {
      "epoch": 0.7381904761904762,
      "grad_norm": 0.025387611240148544,
      "learning_rate": 0.01807890459895134,
      "loss": 2.3480210304260254,
      "step": 15502
    },
    {
      "epoch": 0.7382857142857143,
      "grad_norm": 0.026227280497550964,
      "learning_rate": 0.018072327598929405,
      "loss": 2.380622386932373,
      "step": 15504
    },
    {
      "epoch": 0.7383809523809524,
      "grad_norm": 0.026438741013407707,
      "learning_rate": 0.01806575432419777,
      "loss": 2.337888717651367,
      "step": 15506
    },
    {
      "epoch": 0.7384761904761905,
      "grad_norm": 0.0300892423838377,
      "learning_rate": 0.018059177324175835,
      "loss": 2.3222532272338867,
      "step": 15508
    },
    {
      "epoch": 0.7385714285714285,
      "grad_norm": 0.025763535872101784,
      "learning_rate": 0.01805260218679905,
      "loss": 2.3574514389038086,
      "step": 15510
    },
    {
      "epoch": 0.7386666666666667,
      "grad_norm": 0.025381341576576233,
      "learning_rate": 0.018046027049422264,
      "loss": 2.366950035095215,
      "step": 15512
    },
    {
      "epoch": 0.7387619047619047,
      "grad_norm": 0.025321854278445244,
      "learning_rate": 0.01803945191204548,
      "loss": 2.3520684242248535,
      "step": 15514
    },
    {
      "epoch": 0.7388571428571429,
      "grad_norm": 0.02527572773396969,
      "learning_rate": 0.018032876774668694,
      "loss": 2.3530097007751465,
      "step": 15516
    },
    {
      "epoch": 0.7389523809523809,
      "grad_norm": 0.026988815516233444,
      "learning_rate": 0.018026301637291908,
      "loss": 2.3326668739318848,
      "step": 15518
    },
    {
      "epoch": 0.7390476190476191,
      "grad_norm": 0.025999439880251884,
      "learning_rate": 0.018019724637269974,
      "loss": 2.3460378646850586,
      "step": 15520
    },
    {
      "epoch": 0.7391428571428571,
      "grad_norm": 0.025522805750370026,
      "learning_rate": 0.018013151362538338,
      "loss": 2.328484296798706,
      "step": 15522
    },
    {
      "epoch": 0.7392380952380952,
      "grad_norm": 0.026413394138216972,
      "learning_rate": 0.018006574362516403,
      "loss": 2.358071804046631,
      "step": 15524
    },
    {
      "epoch": 0.7393333333333333,
      "grad_norm": 0.02646331861615181,
      "learning_rate": 0.017999999225139618,
      "loss": 2.347684860229492,
      "step": 15526
    },
    {
      "epoch": 0.7394285714285714,
      "grad_norm": 0.026081789284944534,
      "learning_rate": 0.017993425950407982,
      "loss": 2.329948902130127,
      "step": 15528
    },
    {
      "epoch": 0.7395238095238095,
      "grad_norm": 0.02496488206088543,
      "learning_rate": 0.017986848950386047,
      "loss": 2.3554697036743164,
      "step": 15530
    },
    {
      "epoch": 0.7396190476190476,
      "grad_norm": 0.027289673686027527,
      "learning_rate": 0.01798027567565441,
      "loss": 2.402756690979004,
      "step": 15532
    },
    {
      "epoch": 0.7397142857142858,
      "grad_norm": 0.025630872696638107,
      "learning_rate": 0.017973698675632477,
      "loss": 2.339308738708496,
      "step": 15534
    },
    {
      "epoch": 0.7398095238095238,
      "grad_norm": 0.02780371531844139,
      "learning_rate": 0.01796712353825569,
      "loss": 2.3338005542755127,
      "step": 15536
    },
    {
      "epoch": 0.739904761904762,
      "grad_norm": 0.03231804072856903,
      "learning_rate": 0.017960548400878906,
      "loss": 2.3687350749969482,
      "step": 15538
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.02597762458026409,
      "learning_rate": 0.01795397326350212,
      "loss": 2.3198928833007812,
      "step": 15540
    },
    {
      "epoch": 0.7400952380952381,
      "grad_norm": 0.024800289422273636,
      "learning_rate": 0.017947398126125336,
      "loss": 2.354149103164673,
      "step": 15542
    },
    {
      "epoch": 0.7401904761904762,
      "grad_norm": 0.02641119994223118,
      "learning_rate": 0.01794082298874855,
      "loss": 2.352957248687744,
      "step": 15544
    },
    {
      "epoch": 0.7402857142857143,
      "grad_norm": 0.026838308200240135,
      "learning_rate": 0.017934245988726616,
      "loss": 2.309941291809082,
      "step": 15546
    },
    {
      "epoch": 0.7403809523809524,
      "grad_norm": 0.02619113028049469,
      "learning_rate": 0.01792767271399498,
      "loss": 2.3251538276672363,
      "step": 15548
    },
    {
      "epoch": 0.7404761904761905,
      "grad_norm": 0.026309343054890633,
      "learning_rate": 0.017921095713973045,
      "loss": 2.3199567794799805,
      "step": 15550
    },
    {
      "epoch": 0.7405714285714285,
      "grad_norm": 0.027828708291053772,
      "learning_rate": 0.01791452057659626,
      "loss": 2.3380002975463867,
      "step": 15552
    },
    {
      "epoch": 0.7406666666666667,
      "grad_norm": 0.02610698528587818,
      "learning_rate": 0.017907945439219475,
      "loss": 2.327108860015869,
      "step": 15554
    },
    {
      "epoch": 0.7407619047619047,
      "grad_norm": 0.025202888995409012,
      "learning_rate": 0.01790137030184269,
      "loss": 2.305941104888916,
      "step": 15556
    },
    {
      "epoch": 0.7408571428571429,
      "grad_norm": 0.028123941272497177,
      "learning_rate": 0.017894795164465904,
      "loss": 2.3469228744506836,
      "step": 15558
    },
    {
      "epoch": 0.7409523809523809,
      "grad_norm": 0.02756907232105732,
      "learning_rate": 0.01788822002708912,
      "loss": 2.342402935028076,
      "step": 15560
    },
    {
      "epoch": 0.7410476190476191,
      "grad_norm": 0.025955915451049805,
      "learning_rate": 0.017881643027067184,
      "loss": 2.344564437866211,
      "step": 15562
    },
    {
      "epoch": 0.7411428571428571,
      "grad_norm": 0.025975707918405533,
      "learning_rate": 0.01787506975233555,
      "loss": 2.345348358154297,
      "step": 15564
    },
    {
      "epoch": 0.7412380952380953,
      "grad_norm": 0.026285624131560326,
      "learning_rate": 0.017868492752313614,
      "loss": 2.3173465728759766,
      "step": 15566
    },
    {
      "epoch": 0.7413333333333333,
      "grad_norm": 0.026878802105784416,
      "learning_rate": 0.017861919477581978,
      "loss": 2.3525912761688232,
      "step": 15568
    },
    {
      "epoch": 0.7414285714285714,
      "grad_norm": 0.025844309478998184,
      "learning_rate": 0.017855342477560043,
      "loss": 2.341384172439575,
      "step": 15570
    },
    {
      "epoch": 0.7415238095238095,
      "grad_norm": 0.026279469951987267,
      "learning_rate": 0.017848767340183258,
      "loss": 2.3185031414031982,
      "step": 15572
    },
    {
      "epoch": 0.7416190476190476,
      "grad_norm": 0.02552093379199505,
      "learning_rate": 0.017842192202806473,
      "loss": 2.332857370376587,
      "step": 15574
    },
    {
      "epoch": 0.7417142857142857,
      "grad_norm": 0.024680597707629204,
      "learning_rate": 0.017835617065429688,
      "loss": 2.327584743499756,
      "step": 15576
    },
    {
      "epoch": 0.7418095238095238,
      "grad_norm": 0.030557727441191673,
      "learning_rate": 0.017829041928052902,
      "loss": 2.3169448375701904,
      "step": 15578
    },
    {
      "epoch": 0.741904761904762,
      "grad_norm": 0.02772785909473896,
      "learning_rate": 0.017822466790676117,
      "loss": 2.361814022064209,
      "step": 15580
    },
    {
      "epoch": 0.742,
      "grad_norm": 0.025353379547595978,
      "learning_rate": 0.017815889790654182,
      "loss": 2.3341922760009766,
      "step": 15582
    },
    {
      "epoch": 0.7420952380952381,
      "grad_norm": 0.02637895755469799,
      "learning_rate": 0.017809316515922546,
      "loss": 2.3278346061706543,
      "step": 15584
    },
    {
      "epoch": 0.7421904761904762,
      "grad_norm": 0.026542482897639275,
      "learning_rate": 0.017802739515900612,
      "loss": 2.3315510749816895,
      "step": 15586
    },
    {
      "epoch": 0.7422857142857143,
      "grad_norm": 0.02661876007914543,
      "learning_rate": 0.017796164378523827,
      "loss": 2.3526439666748047,
      "step": 15588
    },
    {
      "epoch": 0.7423809523809524,
      "grad_norm": 0.02696835622191429,
      "learning_rate": 0.01778958924114704,
      "loss": 2.3332533836364746,
      "step": 15590
    },
    {
      "epoch": 0.7424761904761905,
      "grad_norm": 0.024904955178499222,
      "learning_rate": 0.017783014103770256,
      "loss": 2.3030877113342285,
      "step": 15592
    },
    {
      "epoch": 0.7425714285714285,
      "grad_norm": 0.02643158845603466,
      "learning_rate": 0.01777643896639347,
      "loss": 2.3559577465057373,
      "step": 15594
    },
    {
      "epoch": 0.7426666666666667,
      "grad_norm": 0.02787517011165619,
      "learning_rate": 0.017769863829016685,
      "loss": 2.2801733016967773,
      "step": 15596
    },
    {
      "epoch": 0.7427619047619047,
      "grad_norm": 0.027094339951872826,
      "learning_rate": 0.01776328682899475,
      "loss": 2.2730023860931396,
      "step": 15598
    },
    {
      "epoch": 0.7428571428571429,
      "grad_norm": 0.028016643598675728,
      "learning_rate": 0.017756713554263115,
      "loss": 2.317416191101074,
      "step": 15600
    },
    {
      "epoch": 0.7429523809523809,
      "grad_norm": 0.025573773309588432,
      "learning_rate": 0.01775013655424118,
      "loss": 2.3057284355163574,
      "step": 15602
    },
    {
      "epoch": 0.7430476190476191,
      "grad_norm": 0.025539245456457138,
      "learning_rate": 0.017743563279509544,
      "loss": 2.311638355255127,
      "step": 15604
    },
    {
      "epoch": 0.7431428571428571,
      "grad_norm": 0.027940969914197922,
      "learning_rate": 0.01773698627948761,
      "loss": 2.3007876873016357,
      "step": 15606
    },
    {
      "epoch": 0.7432380952380953,
      "grad_norm": 0.03341735899448395,
      "learning_rate": 0.017730411142110825,
      "loss": 2.3369052410125732,
      "step": 15608
    },
    {
      "epoch": 0.7433333333333333,
      "grad_norm": 0.028901206329464912,
      "learning_rate": 0.01772383600473404,
      "loss": 2.3507888317108154,
      "step": 15610
    },
    {
      "epoch": 0.7434285714285714,
      "grad_norm": 0.027818255126476288,
      "learning_rate": 0.017717260867357254,
      "loss": 2.3169541358947754,
      "step": 15612
    },
    {
      "epoch": 0.7435238095238095,
      "grad_norm": 0.025007903575897217,
      "learning_rate": 0.01771068572998047,
      "loss": 2.3707547187805176,
      "step": 15614
    },
    {
      "epoch": 0.7436190476190476,
      "grad_norm": 0.027196960523724556,
      "learning_rate": 0.017704110592603683,
      "loss": 2.3037190437316895,
      "step": 15616
    },
    {
      "epoch": 0.7437142857142857,
      "grad_norm": 0.026002032682299614,
      "learning_rate": 0.01769753359258175,
      "loss": 2.3338780403137207,
      "step": 15618
    },
    {
      "epoch": 0.7438095238095238,
      "grad_norm": 0.025685282424092293,
      "learning_rate": 0.017690960317850113,
      "loss": 2.3259117603302,
      "step": 15620
    },
    {
      "epoch": 0.743904761904762,
      "grad_norm": 0.029291940852999687,
      "learning_rate": 0.01768438331782818,
      "loss": 2.3070497512817383,
      "step": 15622
    },
    {
      "epoch": 0.744,
      "grad_norm": 0.025454513728618622,
      "learning_rate": 0.017677808180451393,
      "loss": 2.3352341651916504,
      "step": 15624
    },
    {
      "epoch": 0.7440952380952381,
      "grad_norm": 0.02763959765434265,
      "learning_rate": 0.017671233043074608,
      "loss": 2.289316177368164,
      "step": 15626
    },
    {
      "epoch": 0.7441904761904762,
      "grad_norm": 0.025107964873313904,
      "learning_rate": 0.017664657905697823,
      "loss": 2.300992965698242,
      "step": 15628
    },
    {
      "epoch": 0.7442857142857143,
      "grad_norm": 0.025980591773986816,
      "learning_rate": 0.017658082768321037,
      "loss": 2.2867579460144043,
      "step": 15630
    },
    {
      "epoch": 0.7443809523809524,
      "grad_norm": 0.028337927535176277,
      "learning_rate": 0.017651507630944252,
      "loss": 2.2816200256347656,
      "step": 15632
    },
    {
      "epoch": 0.7444761904761905,
      "grad_norm": 0.025092434138059616,
      "learning_rate": 0.017644930630922318,
      "loss": 2.3408336639404297,
      "step": 15634
    },
    {
      "epoch": 0.7445714285714286,
      "grad_norm": 0.02689722739160061,
      "learning_rate": 0.01763835735619068,
      "loss": 2.3111696243286133,
      "step": 15636
    },
    {
      "epoch": 0.7446666666666667,
      "grad_norm": 0.02591930702328682,
      "learning_rate": 0.017631780356168747,
      "loss": 2.353759765625,
      "step": 15638
    },
    {
      "epoch": 0.7447619047619047,
      "grad_norm": 0.026604680344462395,
      "learning_rate": 0.01762520521879196,
      "loss": 2.3260655403137207,
      "step": 15640
    },
    {
      "epoch": 0.7448571428571429,
      "grad_norm": 0.025254525244235992,
      "learning_rate": 0.017618630081415176,
      "loss": 2.30930757522583,
      "step": 15642
    },
    {
      "epoch": 0.7449523809523809,
      "grad_norm": 0.028750525787472725,
      "learning_rate": 0.01761205494403839,
      "loss": 2.31941556930542,
      "step": 15644
    },
    {
      "epoch": 0.7450476190476191,
      "grad_norm": 0.025785226374864578,
      "learning_rate": 0.017605479806661606,
      "loss": 2.328462839126587,
      "step": 15646
    },
    {
      "epoch": 0.7451428571428571,
      "grad_norm": 0.02694571204483509,
      "learning_rate": 0.01759890466928482,
      "loss": 2.3318099975585938,
      "step": 15648
    },
    {
      "epoch": 0.7452380952380953,
      "grad_norm": 0.02823738008737564,
      "learning_rate": 0.017592329531908035,
      "loss": 2.3128108978271484,
      "step": 15650
    },
    {
      "epoch": 0.7453333333333333,
      "grad_norm": 0.027523033320903778,
      "learning_rate": 0.01758575439453125,
      "loss": 2.2967193126678467,
      "step": 15652
    },
    {
      "epoch": 0.7454285714285714,
      "grad_norm": 0.025206640362739563,
      "learning_rate": 0.017579177394509315,
      "loss": 2.349384069442749,
      "step": 15654
    },
    {
      "epoch": 0.7455238095238095,
      "grad_norm": 0.025826087221503258,
      "learning_rate": 0.01757260411977768,
      "loss": 2.3311996459960938,
      "step": 15656
    },
    {
      "epoch": 0.7456190476190476,
      "grad_norm": 0.025308458134531975,
      "learning_rate": 0.017566027119755745,
      "loss": 2.315877914428711,
      "step": 15658
    },
    {
      "epoch": 0.7457142857142857,
      "grad_norm": 0.024982865899801254,
      "learning_rate": 0.01755945198237896,
      "loss": 2.3292622566223145,
      "step": 15660
    },
    {
      "epoch": 0.7458095238095238,
      "grad_norm": 0.02726987935602665,
      "learning_rate": 0.017552876845002174,
      "loss": 2.292407512664795,
      "step": 15662
    },
    {
      "epoch": 0.745904761904762,
      "grad_norm": 0.02603534609079361,
      "learning_rate": 0.01754630170762539,
      "loss": 2.3198719024658203,
      "step": 15664
    },
    {
      "epoch": 0.746,
      "grad_norm": 0.025060297921299934,
      "learning_rate": 0.017539726570248604,
      "loss": 2.2778306007385254,
      "step": 15666
    },
    {
      "epoch": 0.7460952380952381,
      "grad_norm": 0.025332637131214142,
      "learning_rate": 0.01753315143287182,
      "loss": 2.3153865337371826,
      "step": 15668
    },
    {
      "epoch": 0.7461904761904762,
      "grad_norm": 0.02595061995089054,
      "learning_rate": 0.017526574432849884,
      "loss": 2.3036351203918457,
      "step": 15670
    },
    {
      "epoch": 0.7462857142857143,
      "grad_norm": 0.026319460943341255,
      "learning_rate": 0.017520001158118248,
      "loss": 2.3079161643981934,
      "step": 15672
    },
    {
      "epoch": 0.7463809523809524,
      "grad_norm": 0.02661813236773014,
      "learning_rate": 0.017513424158096313,
      "loss": 2.3358192443847656,
      "step": 15674
    },
    {
      "epoch": 0.7464761904761905,
      "grad_norm": 0.026765845715999603,
      "learning_rate": 0.017506849020719528,
      "loss": 2.368149518966675,
      "step": 15676
    },
    {
      "epoch": 0.7465714285714286,
      "grad_norm": 0.025871483609080315,
      "learning_rate": 0.017500273883342743,
      "loss": 2.3330066204071045,
      "step": 15678
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 0.025812484323978424,
      "learning_rate": 0.017493698745965958,
      "loss": 2.3020691871643066,
      "step": 15680
    },
    {
      "epoch": 0.7467619047619047,
      "grad_norm": 0.025462981313467026,
      "learning_rate": 0.017487123608589172,
      "loss": 2.3113908767700195,
      "step": 15682
    },
    {
      "epoch": 0.7468571428571429,
      "grad_norm": 0.026074349880218506,
      "learning_rate": 0.017480548471212387,
      "loss": 2.3012642860412598,
      "step": 15684
    },
    {
      "epoch": 0.7469523809523809,
      "grad_norm": 0.02581758052110672,
      "learning_rate": 0.017473973333835602,
      "loss": 2.3721771240234375,
      "step": 15686
    },
    {
      "epoch": 0.7470476190476191,
      "grad_norm": 0.02651822380721569,
      "learning_rate": 0.017467398196458817,
      "loss": 2.3386192321777344,
      "step": 15688
    },
    {
      "epoch": 0.7471428571428571,
      "grad_norm": 0.029550235718488693,
      "learning_rate": 0.017460821196436882,
      "loss": 2.3528077602386475,
      "step": 15690
    },
    {
      "epoch": 0.7472380952380953,
      "grad_norm": 0.02518484555184841,
      "learning_rate": 0.017454247921705246,
      "loss": 2.311462879180908,
      "step": 15692
    },
    {
      "epoch": 0.7473333333333333,
      "grad_norm": 0.025168655440211296,
      "learning_rate": 0.01744767092168331,
      "loss": 2.29652738571167,
      "step": 15694
    },
    {
      "epoch": 0.7474285714285714,
      "grad_norm": 0.026097258552908897,
      "learning_rate": 0.017441095784306526,
      "loss": 2.308227062225342,
      "step": 15696
    },
    {
      "epoch": 0.7475238095238095,
      "grad_norm": 0.026120008900761604,
      "learning_rate": 0.01743452064692974,
      "loss": 2.292232036590576,
      "step": 15698
    },
    {
      "epoch": 0.7476190476190476,
      "grad_norm": 0.024850936606526375,
      "learning_rate": 0.017427945509552956,
      "loss": 2.2931203842163086,
      "step": 15700
    },
    {
      "epoch": 0.7477142857142857,
      "grad_norm": 0.025767646729946136,
      "learning_rate": 0.01742137037217617,
      "loss": 2.3148651123046875,
      "step": 15702
    },
    {
      "epoch": 0.7478095238095238,
      "grad_norm": 0.02588091790676117,
      "learning_rate": 0.017414795234799385,
      "loss": 2.329885482788086,
      "step": 15704
    },
    {
      "epoch": 0.7479047619047619,
      "grad_norm": 0.025512296706438065,
      "learning_rate": 0.01740821823477745,
      "loss": 2.3152451515197754,
      "step": 15706
    },
    {
      "epoch": 0.748,
      "grad_norm": 0.02626778744161129,
      "learning_rate": 0.017401644960045815,
      "loss": 2.3046584129333496,
      "step": 15708
    },
    {
      "epoch": 0.7480952380952381,
      "grad_norm": 0.02582602947950363,
      "learning_rate": 0.01739506796002388,
      "loss": 2.297856092453003,
      "step": 15710
    },
    {
      "epoch": 0.7481904761904762,
      "grad_norm": 0.026222407817840576,
      "learning_rate": 0.017388492822647095,
      "loss": 2.3093080520629883,
      "step": 15712
    },
    {
      "epoch": 0.7482857142857143,
      "grad_norm": 0.026395166292786598,
      "learning_rate": 0.01738191768527031,
      "loss": 2.3238277435302734,
      "step": 15714
    },
    {
      "epoch": 0.7483809523809524,
      "grad_norm": 0.026226164773106575,
      "learning_rate": 0.017375342547893524,
      "loss": 2.3006796836853027,
      "step": 15716
    },
    {
      "epoch": 0.7484761904761905,
      "grad_norm": 0.02697596326470375,
      "learning_rate": 0.01736876741051674,
      "loss": 2.3389341831207275,
      "step": 15718
    },
    {
      "epoch": 0.7485714285714286,
      "grad_norm": 0.02642185613512993,
      "learning_rate": 0.017362192273139954,
      "loss": 2.3074889183044434,
      "step": 15720
    },
    {
      "epoch": 0.7486666666666667,
      "grad_norm": 0.02782079018652439,
      "learning_rate": 0.01735561713576317,
      "loss": 2.328770160675049,
      "step": 15722
    },
    {
      "epoch": 0.7487619047619047,
      "grad_norm": 0.029526278376579285,
      "learning_rate": 0.017349041998386383,
      "loss": 2.264914035797119,
      "step": 15724
    },
    {
      "epoch": 0.7488571428571429,
      "grad_norm": 0.027077285572886467,
      "learning_rate": 0.01734246499836445,
      "loss": 2.3192410469055176,
      "step": 15726
    },
    {
      "epoch": 0.7489523809523809,
      "grad_norm": 0.028856394812464714,
      "learning_rate": 0.017335891723632812,
      "loss": 2.3326239585876465,
      "step": 15728
    },
    {
      "epoch": 0.7490476190476191,
      "grad_norm": 0.02852701209485531,
      "learning_rate": 0.017329314723610878,
      "loss": 2.308624029159546,
      "step": 15730
    },
    {
      "epoch": 0.7491428571428571,
      "grad_norm": 0.026169560849666595,
      "learning_rate": 0.017322739586234093,
      "loss": 2.316768169403076,
      "step": 15732
    },
    {
      "epoch": 0.7492380952380953,
      "grad_norm": 0.02709086425602436,
      "learning_rate": 0.017316164448857307,
      "loss": 2.3272228240966797,
      "step": 15734
    },
    {
      "epoch": 0.7493333333333333,
      "grad_norm": 0.027657698839902878,
      "learning_rate": 0.017309589311480522,
      "loss": 2.3079776763916016,
      "step": 15736
    },
    {
      "epoch": 0.7494285714285714,
      "grad_norm": 0.02516268379986286,
      "learning_rate": 0.017303014174103737,
      "loss": 2.3612399101257324,
      "step": 15738
    },
    {
      "epoch": 0.7495238095238095,
      "grad_norm": 0.026182102039456367,
      "learning_rate": 0.01729643903672695,
      "loss": 2.305617094039917,
      "step": 15740
    },
    {
      "epoch": 0.7496190476190476,
      "grad_norm": 0.02609368972480297,
      "learning_rate": 0.017289862036705017,
      "loss": 2.312685489654541,
      "step": 15742
    },
    {
      "epoch": 0.7497142857142857,
      "grad_norm": 0.026187218725681305,
      "learning_rate": 0.01728328876197338,
      "loss": 2.309286117553711,
      "step": 15744
    },
    {
      "epoch": 0.7498095238095238,
      "grad_norm": 0.029577380046248436,
      "learning_rate": 0.017276711761951447,
      "loss": 2.3096208572387695,
      "step": 15746
    },
    {
      "epoch": 0.7499047619047619,
      "grad_norm": 0.02641557902097702,
      "learning_rate": 0.01727013662457466,
      "loss": 2.314117431640625,
      "step": 15748
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.029240325093269348,
      "learning_rate": 0.017263561487197876,
      "loss": 2.3062260150909424,
      "step": 15750
    }
  ],
  "logging_steps": 2,
  "max_steps": 21000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 1050,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.287197266138471e+19,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}