{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.998046875,
  "eval_steps": 500,
  "global_step": 1024,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001953125,
      "grad_norm": 2.2842363876082494,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.7076,
      "step": 1
    },
    {
      "epoch": 0.00390625,
      "grad_norm": 2.317015212334916,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.6296,
      "step": 2
    },
    {
      "epoch": 0.005859375,
      "grad_norm": 2.0835939653262883,
      "learning_rate": 3e-06,
      "loss": 1.5593,
      "step": 3
    },
    {
      "epoch": 0.0078125,
      "grad_norm": 2.1357657121975797,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.6713,
      "step": 4
    },
    {
      "epoch": 0.009765625,
      "grad_norm": 2.0362735997756847,
      "learning_rate": 5e-06,
      "loss": 1.5327,
      "step": 5
    },
    {
      "epoch": 0.01171875,
      "grad_norm": 2.1597413317388523,
      "learning_rate": 6e-06,
      "loss": 1.6435,
      "step": 6
    },
    {
      "epoch": 0.013671875,
      "grad_norm": 2.1354234831872616,
      "learning_rate": 7e-06,
      "loss": 1.539,
      "step": 7
    },
    {
      "epoch": 0.015625,
      "grad_norm": 2.0222980997885682,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.491,
      "step": 8
    },
    {
      "epoch": 0.017578125,
      "grad_norm": 1.8336578914749888,
      "learning_rate": 9e-06,
      "loss": 1.567,
      "step": 9
    },
    {
      "epoch": 0.01953125,
      "grad_norm": 1.7535364548043673,
      "learning_rate": 1e-05,
      "loss": 1.5181,
      "step": 10
    },
    {
      "epoch": 0.021484375,
      "grad_norm": 1.348232072077207,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 1.4633,
      "step": 11
    },
    {
      "epoch": 0.0234375,
      "grad_norm": 1.079057032053978,
      "learning_rate": 1.2e-05,
      "loss": 1.36,
      "step": 12
    },
    {
      "epoch": 0.025390625,
      "grad_norm": 0.7143765277543237,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.3195,
      "step": 13
    },
    {
      "epoch": 0.02734375,
      "grad_norm": 0.8120880164824964,
      "learning_rate": 1.4e-05,
      "loss": 1.3469,
      "step": 14
    },
    {
      "epoch": 0.029296875,
      "grad_norm": 0.6746494578904082,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.3626,
      "step": 15
    },
    {
      "epoch": 0.03125,
      "grad_norm": 0.9663545707089416,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.2772,
      "step": 16
    },
    {
      "epoch": 0.033203125,
      "grad_norm": 0.961439588523319,
      "learning_rate": 1.7e-05,
      "loss": 1.2911,
      "step": 17
    },
    {
      "epoch": 0.03515625,
      "grad_norm": 1.1738444068957379,
      "learning_rate": 1.8e-05,
      "loss": 1.3346,
      "step": 18
    },
    {
      "epoch": 0.037109375,
      "grad_norm": 1.2332387671295317,
      "learning_rate": 1.9e-05,
      "loss": 1.3761,
      "step": 19
    },
    {
      "epoch": 0.0390625,
      "grad_norm": 1.268714744941341,
      "learning_rate": 2e-05,
      "loss": 1.3042,
      "step": 20
    },
    {
      "epoch": 0.041015625,
      "grad_norm": 1.078415802927275,
      "learning_rate": 2.1000000000000002e-05,
      "loss": 1.2102,
      "step": 21
    },
    {
      "epoch": 0.04296875,
      "grad_norm": 1.330999136602917,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.2755,
      "step": 22
    },
    {
      "epoch": 0.044921875,
      "grad_norm": 0.7130882289363479,
      "learning_rate": 2.3e-05,
      "loss": 1.1706,
      "step": 23
    },
    {
      "epoch": 0.046875,
      "grad_norm": 0.5729960230193528,
      "learning_rate": 2.4e-05,
      "loss": 1.3215,
      "step": 24
    },
    {
      "epoch": 0.048828125,
      "grad_norm": 0.6125271472968751,
      "learning_rate": 2.5e-05,
      "loss": 1.3213,
      "step": 25
    },
    {
      "epoch": 0.05078125,
      "grad_norm": 0.6108864130655043,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.2865,
      "step": 26
    },
    {
      "epoch": 0.052734375,
      "grad_norm": 0.6479528408256864,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 1.3383,
      "step": 27
    },
    {
      "epoch": 0.0546875,
      "grad_norm": 0.8412108818700305,
      "learning_rate": 2.8e-05,
      "loss": 1.2763,
      "step": 28
    },
    {
      "epoch": 0.056640625,
      "grad_norm": 0.8629612077288169,
      "learning_rate": 2.9e-05,
      "loss": 1.3045,
      "step": 29
    },
    {
      "epoch": 0.05859375,
      "grad_norm": 0.7600858737745863,
      "learning_rate": 3.0000000000000004e-05,
      "loss": 1.2352,
      "step": 30
    },
    {
      "epoch": 0.060546875,
      "grad_norm": 0.7130629485255873,
      "learning_rate": 3.1e-05,
      "loss": 1.2299,
      "step": 31
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.5912964724458128,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.2234,
      "step": 32
    },
    {
      "epoch": 0.064453125,
      "grad_norm": 0.5368820032381596,
      "learning_rate": 3.3e-05,
      "loss": 1.1934,
      "step": 33
    },
    {
      "epoch": 0.06640625,
      "grad_norm": 0.5570421986755116,
      "learning_rate": 3.4e-05,
      "loss": 1.2581,
      "step": 34
    },
    {
      "epoch": 0.068359375,
      "grad_norm": 0.46598864760360764,
      "learning_rate": 3.5000000000000004e-05,
      "loss": 1.2535,
      "step": 35
    },
    {
      "epoch": 0.0703125,
      "grad_norm": 0.6392299897042107,
      "learning_rate": 3.6e-05,
      "loss": 1.2331,
      "step": 36
    },
    {
      "epoch": 0.072265625,
      "grad_norm": 0.49983937474417145,
      "learning_rate": 3.7000000000000005e-05,
      "loss": 1.2432,
      "step": 37
    },
    {
      "epoch": 0.07421875,
      "grad_norm": 0.652858138736506,
      "learning_rate": 3.8e-05,
      "loss": 1.2759,
      "step": 38
    },
    {
      "epoch": 0.076171875,
      "grad_norm": 0.5926189930170476,
      "learning_rate": 3.9e-05,
      "loss": 1.3016,
      "step": 39
    },
    {
      "epoch": 0.078125,
      "grad_norm": 0.6646763351870284,
      "learning_rate": 4e-05,
      "loss": 1.344,
      "step": 40
    },
    {
      "epoch": 0.080078125,
      "grad_norm": 0.6228429864196855,
      "learning_rate": 3.99998980683206e-05,
      "loss": 1.2794,
      "step": 41
    },
    {
      "epoch": 0.08203125,
      "grad_norm": 0.5633101870154669,
      "learning_rate": 3.9999592274321385e-05,
      "loss": 1.2931,
      "step": 42
    },
    {
      "epoch": 0.083984375,
      "grad_norm": 0.6866774046182069,
      "learning_rate": 3.999908262111937e-05,
      "loss": 1.2647,
      "step": 43
    },
    {
      "epoch": 0.0859375,
      "grad_norm": 0.5312790576505163,
      "learning_rate": 3.9998369113909555e-05,
      "loss": 1.2255,
      "step": 44
    },
    {
      "epoch": 0.087890625,
      "grad_norm": 0.5694229658922494,
      "learning_rate": 3.999745175996481e-05,
      "loss": 1.3104,
      "step": 45
    },
    {
      "epoch": 0.08984375,
      "grad_norm": 0.5068013674566277,
      "learning_rate": 3.999633056863589e-05,
      "loss": 1.1771,
      "step": 46
    },
    {
      "epoch": 0.091796875,
      "grad_norm": 0.5428027277075501,
      "learning_rate": 3.999500555135129e-05,
      "loss": 1.3508,
      "step": 47
    },
    {
      "epoch": 0.09375,
      "grad_norm": 0.4792441915562371,
      "learning_rate": 3.999347672161713e-05,
      "loss": 1.1144,
      "step": 48
    },
    {
      "epoch": 0.095703125,
      "grad_norm": 0.5033945174929487,
      "learning_rate": 3.999174409501703e-05,
      "loss": 1.1474,
      "step": 49
    },
    {
      "epoch": 0.09765625,
      "grad_norm": 0.5609150975698594,
      "learning_rate": 3.9989807689211946e-05,
      "loss": 1.2558,
      "step": 50
    },
    {
      "epoch": 0.099609375,
      "grad_norm": 0.5558707293914855,
      "learning_rate": 3.998766752393998e-05,
      "loss": 1.1411,
      "step": 51
    },
    {
      "epoch": 0.1015625,
      "grad_norm": 0.4429585853749615,
      "learning_rate": 3.99853236210162e-05,
      "loss": 1.1715,
      "step": 52
    },
    {
      "epoch": 0.103515625,
      "grad_norm": 0.5064052852591816,
      "learning_rate": 3.998277600433241e-05,
      "loss": 1.2018,
      "step": 53
    },
    {
      "epoch": 0.10546875,
      "grad_norm": 0.526020419983389,
      "learning_rate": 3.998002469985688e-05,
      "loss": 1.1164,
      "step": 54
    },
    {
      "epoch": 0.107421875,
      "grad_norm": 0.504222879676158,
      "learning_rate": 3.997706973563413e-05,
      "loss": 1.191,
      "step": 55
    },
    {
      "epoch": 0.109375,
      "grad_norm": 0.5614145336635687,
      "learning_rate": 3.9973911141784605e-05,
      "loss": 1.3011,
      "step": 56
    },
    {
      "epoch": 0.111328125,
      "grad_norm": 0.4391770801146478,
      "learning_rate": 3.997054895050437e-05,
      "loss": 1.2535,
      "step": 57
    },
    {
      "epoch": 0.11328125,
      "grad_norm": 0.5583307267784473,
      "learning_rate": 3.996698319606482e-05,
      "loss": 1.153,
      "step": 58
    },
    {
      "epoch": 0.115234375,
      "grad_norm": 0.4576133947689655,
      "learning_rate": 3.996321391481229e-05,
      "loss": 1.1564,
      "step": 59
    },
    {
      "epoch": 0.1171875,
      "grad_norm": 0.41970646962377184,
      "learning_rate": 3.995924114516769e-05,
      "loss": 1.1935,
      "step": 60
    },
    {
      "epoch": 0.119140625,
      "grad_norm": 0.44805324266797203,
      "learning_rate": 3.995506492762613e-05,
      "loss": 1.1339,
      "step": 61
    },
    {
      "epoch": 0.12109375,
      "grad_norm": 0.5208068893189155,
      "learning_rate": 3.9950685304756494e-05,
      "loss": 1.2092,
      "step": 62
    },
    {
      "epoch": 0.123046875,
      "grad_norm": 0.44195618774115664,
      "learning_rate": 3.994610232120101e-05,
      "loss": 1.1292,
      "step": 63
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.4514887790554273,
      "learning_rate": 3.994131602367481e-05,
      "loss": 1.1658,
      "step": 64
    },
    {
      "epoch": 0.126953125,
      "grad_norm": 0.5908686231033371,
      "learning_rate": 3.9936326460965423e-05,
      "loss": 1.2076,
      "step": 65
    },
    {
      "epoch": 0.12890625,
      "grad_norm": 0.46799815417666174,
      "learning_rate": 3.99311336839323e-05,
      "loss": 1.1889,
      "step": 66
    },
    {
      "epoch": 0.130859375,
      "grad_norm": 0.45939729407525115,
      "learning_rate": 3.992573774550629e-05,
      "loss": 1.1704,
      "step": 67
    },
    {
      "epoch": 0.1328125,
      "grad_norm": 0.4142175477343616,
      "learning_rate": 3.9920138700689095e-05,
      "loss": 1.1848,
      "step": 68
    },
    {
      "epoch": 0.134765625,
      "grad_norm": 0.37685838553537837,
      "learning_rate": 3.991433660655273e-05,
      "loss": 1.1041,
      "step": 69
    },
    {
      "epoch": 0.13671875,
      "grad_norm": 0.39832807246827023,
      "learning_rate": 3.99083315222389e-05,
      "loss": 1.2002,
      "step": 70
    },
    {
      "epoch": 0.138671875,
      "grad_norm": 0.43218323629933336,
      "learning_rate": 3.990212350895845e-05,
      "loss": 1.1487,
      "step": 71
    },
    {
      "epoch": 0.140625,
      "grad_norm": 0.43302460007599547,
      "learning_rate": 3.98957126299907e-05,
      "loss": 1.1638,
      "step": 72
    },
    {
      "epoch": 0.142578125,
      "grad_norm": 0.41150363252077565,
      "learning_rate": 3.988909895068281e-05,
      "loss": 1.1353,
      "step": 73
    },
    {
      "epoch": 0.14453125,
      "grad_norm": 0.4362254605938381,
      "learning_rate": 3.988228253844913e-05,
      "loss": 1.2202,
      "step": 74
    },
    {
      "epoch": 0.146484375,
      "grad_norm": 0.4696684841153936,
      "learning_rate": 3.987526346277049e-05,
      "loss": 1.1722,
      "step": 75
    },
    {
      "epoch": 0.1484375,
      "grad_norm": 0.42274900639715757,
      "learning_rate": 3.9868041795193505e-05,
      "loss": 1.179,
      "step": 76
    },
    {
      "epoch": 0.150390625,
      "grad_norm": 0.47381294364503707,
      "learning_rate": 3.9860617609329856e-05,
      "loss": 1.1978,
      "step": 77
    },
    {
      "epoch": 0.15234375,
      "grad_norm": 0.448192967722078,
      "learning_rate": 3.9852990980855505e-05,
      "loss": 1.2042,
      "step": 78
    },
    {
      "epoch": 0.154296875,
      "grad_norm": 0.388483486919693,
      "learning_rate": 3.984516198750997e-05,
      "loss": 1.148,
      "step": 79
    },
    {
      "epoch": 0.15625,
      "grad_norm": 0.4057112657252388,
      "learning_rate": 3.9837130709095475e-05,
      "loss": 1.1267,
      "step": 80
    },
    {
      "epoch": 0.158203125,
      "grad_norm": 0.5111257616377479,
      "learning_rate": 3.982889722747621e-05,
      "loss": 1.1992,
      "step": 81
    },
    {
      "epoch": 0.16015625,
      "grad_norm": 0.42800919524357695,
      "learning_rate": 3.9820461626577426e-05,
      "loss": 1.2214,
      "step": 82
    },
    {
      "epoch": 0.162109375,
      "grad_norm": 0.6604320971658805,
      "learning_rate": 3.981182399238462e-05,
      "loss": 1.1046,
      "step": 83
    },
    {
      "epoch": 0.1640625,
      "grad_norm": 0.4650529995861808,
      "learning_rate": 3.980298441294265e-05,
      "loss": 1.1485,
      "step": 84
    },
    {
      "epoch": 0.166015625,
      "grad_norm": 0.8247014006092652,
      "learning_rate": 3.9793942978354835e-05,
      "loss": 1.2345,
      "step": 85
    },
    {
      "epoch": 0.16796875,
      "grad_norm": 0.5111463246016623,
      "learning_rate": 3.978469978078203e-05,
      "loss": 1.1406,
      "step": 86
    },
    {
      "epoch": 0.169921875,
      "grad_norm": 0.3980549366997817,
      "learning_rate": 3.977525491444171e-05,
      "loss": 1.138,
      "step": 87
    },
    {
      "epoch": 0.171875,
      "grad_norm": 0.4500013345653544,
      "learning_rate": 3.976560847560697e-05,
      "loss": 1.1803,
      "step": 88
    },
    {
      "epoch": 0.173828125,
      "grad_norm": 0.6144879263096161,
      "learning_rate": 3.975576056260559e-05,
      "loss": 1.376,
      "step": 89
    },
    {
      "epoch": 0.17578125,
      "grad_norm": 0.45250166677505255,
      "learning_rate": 3.974571127581901e-05,
      "loss": 1.2616,
      "step": 90
    },
    {
      "epoch": 0.177734375,
      "grad_norm": 0.7260361194779941,
      "learning_rate": 3.973546071768128e-05,
      "loss": 1.207,
      "step": 91
    },
    {
      "epoch": 0.1796875,
      "grad_norm": 0.40590569325939646,
      "learning_rate": 3.972500899267807e-05,
      "loss": 1.1857,
      "step": 92
    },
    {
      "epoch": 0.181640625,
      "grad_norm": 0.7059204956983739,
      "learning_rate": 3.971435620734557e-05,
      "loss": 1.1629,
      "step": 93
    },
    {
      "epoch": 0.18359375,
      "grad_norm": 0.4166494769492577,
      "learning_rate": 3.97035024702694e-05,
      "loss": 1.2105,
      "step": 94
    },
    {
      "epoch": 0.185546875,
      "grad_norm": 0.4708428232528331,
      "learning_rate": 3.969244789208354e-05,
      "loss": 1.2074,
      "step": 95
    },
    {
      "epoch": 0.1875,
      "grad_norm": 0.46187395897944283,
      "learning_rate": 3.9681192585469146e-05,
      "loss": 1.2411,
      "step": 96
    },
    {
      "epoch": 0.189453125,
      "grad_norm": 0.40887786827875044,
      "learning_rate": 3.9669736665153455e-05,
      "loss": 1.181,
      "step": 97
    },
    {
      "epoch": 0.19140625,
      "grad_norm": 0.5783677933870661,
      "learning_rate": 3.96580802479086e-05,
      "loss": 1.2412,
      "step": 98
    },
    {
      "epoch": 0.193359375,
      "grad_norm": 0.46098155681455955,
      "learning_rate": 3.9646223452550374e-05,
      "loss": 1.0478,
      "step": 99
    },
    {
      "epoch": 0.1953125,
      "grad_norm": 0.4421189367731534,
      "learning_rate": 3.9634166399937104e-05,
      "loss": 1.1528,
      "step": 100
    },
    {
      "epoch": 0.197265625,
      "grad_norm": 0.44208897843282735,
      "learning_rate": 3.962190921296834e-05,
      "loss": 1.1294,
      "step": 101
    },
    {
      "epoch": 0.19921875,
      "grad_norm": 0.41115810620405063,
      "learning_rate": 3.9609452016583654e-05,
      "loss": 1.0787,
      "step": 102
    },
    {
      "epoch": 0.201171875,
      "grad_norm": 0.4592703963732682,
      "learning_rate": 3.959679493776134e-05,
      "loss": 1.2084,
      "step": 103
    },
    {
      "epoch": 0.203125,
      "grad_norm": 0.46514364761525706,
      "learning_rate": 3.9583938105517127e-05,
      "loss": 1.169,
      "step": 104
    },
    {
      "epoch": 0.205078125,
      "grad_norm": 0.5044144386089332,
      "learning_rate": 3.957088165090287e-05,
      "loss": 1.121,
      "step": 105
    },
    {
      "epoch": 0.20703125,
      "grad_norm": 0.4160320267546915,
      "learning_rate": 3.9557625707005185e-05,
      "loss": 1.1133,
      "step": 106
    },
    {
      "epoch": 0.208984375,
      "grad_norm": 0.46611013560363507,
      "learning_rate": 3.954417040894416e-05,
      "loss": 1.0846,
      "step": 107
    },
    {
      "epoch": 0.2109375,
      "grad_norm": 0.494489354902747,
      "learning_rate": 3.953051589387189e-05,
      "loss": 1.1762,
      "step": 108
    },
    {
      "epoch": 0.212890625,
      "grad_norm": 0.4226200871032249,
      "learning_rate": 3.951666230097115e-05,
      "loss": 1.0346,
      "step": 109
    },
    {
      "epoch": 0.21484375,
      "grad_norm": 0.4032354878018358,
      "learning_rate": 3.9502609771453934e-05,
      "loss": 1.1223,
      "step": 110
    },
    {
      "epoch": 0.216796875,
      "grad_norm": 0.4148468151686513,
      "learning_rate": 3.948835844856004e-05,
      "loss": 1.1581,
      "step": 111
    },
    {
      "epoch": 0.21875,
      "grad_norm": 0.4655201875464092,
      "learning_rate": 3.947390847755559e-05,
      "loss": 1.141,
      "step": 112
    },
    {
      "epoch": 0.220703125,
      "grad_norm": 0.44131202754652804,
      "learning_rate": 3.945926000573156e-05,
      "loss": 1.228,
      "step": 113
    },
    {
      "epoch": 0.22265625,
      "grad_norm": 0.4878464713519324,
      "learning_rate": 3.94444131824023e-05,
      "loss": 1.2023,
      "step": 114
    },
    {
      "epoch": 0.224609375,
      "grad_norm": 0.4433704308856408,
      "learning_rate": 3.942936815890396e-05,
      "loss": 1.2479,
      "step": 115
    },
    {
      "epoch": 0.2265625,
      "grad_norm": 0.4848454824446459,
      "learning_rate": 3.941412508859299e-05,
      "loss": 1.1269,
      "step": 116
    },
    {
      "epoch": 0.228515625,
      "grad_norm": 0.419630467357436,
      "learning_rate": 3.939868412684458e-05,
      "loss": 1.1806,
      "step": 117
    },
    {
      "epoch": 0.23046875,
      "grad_norm": 0.39683375502836515,
      "learning_rate": 3.938304543105104e-05,
      "loss": 1.1054,
      "step": 118
    },
    {
      "epoch": 0.232421875,
      "grad_norm": 0.4832371787668091,
      "learning_rate": 3.936720916062022e-05,
      "loss": 1.1174,
      "step": 119
    },
    {
      "epoch": 0.234375,
      "grad_norm": 0.5986867637436046,
      "learning_rate": 3.935117547697387e-05,
      "loss": 1.1791,
      "step": 120
    },
    {
      "epoch": 0.236328125,
      "grad_norm": 0.4150490343483682,
      "learning_rate": 3.933494454354605e-05,
      "loss": 1.2129,
      "step": 121
    },
    {
      "epoch": 0.23828125,
      "grad_norm": 0.4215588087170942,
      "learning_rate": 3.931851652578137e-05,
      "loss": 1.1414,
      "step": 122
    },
    {
      "epoch": 0.240234375,
      "grad_norm": 0.42515318009071157,
      "learning_rate": 3.9301891591133377e-05,
      "loss": 1.0854,
      "step": 123
    },
    {
      "epoch": 0.2421875,
      "grad_norm": 0.4488701042494301,
      "learning_rate": 3.928506990906282e-05,
      "loss": 1.0725,
      "step": 124
    },
    {
      "epoch": 0.244140625,
      "grad_norm": 0.41531581194897543,
      "learning_rate": 3.9268051651035944e-05,
      "loss": 1.0746,
      "step": 125
    },
    {
      "epoch": 0.24609375,
      "grad_norm": 0.46204021714125687,
      "learning_rate": 3.9250836990522685e-05,
      "loss": 1.2164,
      "step": 126
    },
    {
      "epoch": 0.248046875,
      "grad_norm": 0.6677384727690392,
      "learning_rate": 3.923342610299499e-05,
      "loss": 1.1834,
      "step": 127
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.4961785465516465,
      "learning_rate": 3.9215819165924956e-05,
      "loss": 1.2178,
      "step": 128
    },
    {
      "epoch": 0.251953125,
      "grad_norm": 0.4651476735438144,
      "learning_rate": 3.919801635878305e-05,
      "loss": 1.1005,
      "step": 129
    },
    {
      "epoch": 0.25390625,
      "grad_norm": 0.49434332973849215,
      "learning_rate": 3.918001786303627e-05,
      "loss": 1.1922,
      "step": 130
    },
    {
      "epoch": 0.255859375,
      "grad_norm": 0.45671514667179935,
      "learning_rate": 3.9161823862146297e-05,
      "loss": 1.0617,
      "step": 131
    },
    {
      "epoch": 0.2578125,
      "grad_norm": 0.49674226929417115,
      "learning_rate": 3.9143434541567654e-05,
      "loss": 1.2203,
      "step": 132
    },
    {
      "epoch": 0.259765625,
      "grad_norm": 0.5208683235687923,
      "learning_rate": 3.912485008874577e-05,
      "loss": 1.1587,
      "step": 133
    },
    {
      "epoch": 0.26171875,
      "grad_norm": 0.517022288962491,
      "learning_rate": 3.9106070693115087e-05,
      "loss": 1.1427,
      "step": 134
    },
    {
      "epoch": 0.263671875,
      "grad_norm": 0.38942661826422087,
      "learning_rate": 3.908709654609715e-05,
      "loss": 1.0629,
      "step": 135
    },
    {
      "epoch": 0.265625,
      "grad_norm": 0.4564236281556844,
      "learning_rate": 3.9067927841098614e-05,
      "loss": 1.0919,
      "step": 136
    },
    {
      "epoch": 0.267578125,
      "grad_norm": 0.4929559987928741,
      "learning_rate": 3.9048564773509314e-05,
      "loss": 1.1502,
      "step": 137
    },
    {
      "epoch": 0.26953125,
      "grad_norm": 0.48513251932309925,
      "learning_rate": 3.902900754070025e-05,
      "loss": 1.1158,
      "step": 138
    },
    {
      "epoch": 0.271484375,
      "grad_norm": 0.5349569441078609,
      "learning_rate": 3.900925634202158e-05,
      "loss": 1.1279,
      "step": 139
    },
    {
      "epoch": 0.2734375,
      "grad_norm": 0.47177459620840684,
      "learning_rate": 3.898931137880059e-05,
      "loss": 1.1595,
      "step": 140
    },
    {
      "epoch": 0.275390625,
      "grad_norm": 0.4904546697998669,
      "learning_rate": 3.896917285433964e-05,
      "loss": 1.2615,
      "step": 141
    },
    {
      "epoch": 0.27734375,
      "grad_norm": 0.5768180408665089,
      "learning_rate": 3.894884097391409e-05,
      "loss": 1.1688,
      "step": 142
    },
    {
      "epoch": 0.279296875,
      "grad_norm": 0.4362108519904031,
      "learning_rate": 3.892831594477021e-05,
      "loss": 1.0983,
      "step": 143
    },
    {
      "epoch": 0.28125,
      "grad_norm": 0.4570710320413065,
      "learning_rate": 3.890759797612307e-05,
      "loss": 1.3706,
      "step": 144
    },
    {
      "epoch": 0.283203125,
      "grad_norm": 0.4465318663671251,
      "learning_rate": 3.888668727915441e-05,
      "loss": 1.1377,
      "step": 145
    },
    {
      "epoch": 0.28515625,
      "grad_norm": 0.5047852656660148,
      "learning_rate": 3.886558406701046e-05,
      "loss": 1.0747,
      "step": 146
    },
    {
      "epoch": 0.287109375,
      "grad_norm": 0.4412295789497703,
      "learning_rate": 3.884428855479983e-05,
      "loss": 1.1261,
      "step": 147
    },
    {
      "epoch": 0.2890625,
      "grad_norm": 0.4476476539228374,
      "learning_rate": 3.8822800959591236e-05,
      "loss": 1.1769,
      "step": 148
    },
    {
      "epoch": 0.291015625,
      "grad_norm": 0.45924117326794117,
      "learning_rate": 3.880112150041134e-05,
      "loss": 1.1564,
      "step": 149
    },
    {
      "epoch": 0.29296875,
      "grad_norm": 0.43931168833110684,
      "learning_rate": 3.877925039824253e-05,
      "loss": 1.1682,
      "step": 150
    },
    {
      "epoch": 0.294921875,
      "grad_norm": 0.5438637955362605,
      "learning_rate": 3.8757187876020603e-05,
      "loss": 1.1448,
      "step": 151
    },
    {
      "epoch": 0.296875,
      "grad_norm": 0.42928963297461137,
      "learning_rate": 3.873493415863256e-05,
      "loss": 1.2078,
      "step": 152
    },
    {
      "epoch": 0.298828125,
      "grad_norm": 0.4381709802123583,
      "learning_rate": 3.8712489472914286e-05,
      "loss": 1.0604,
      "step": 153
    },
    {
      "epoch": 0.30078125,
      "grad_norm": 0.4988490117613772,
      "learning_rate": 3.8689854047648224e-05,
      "loss": 1.1424,
      "step": 154
    },
    {
      "epoch": 0.302734375,
      "grad_norm": 0.4257038437137218,
      "learning_rate": 3.866702811356107e-05,
      "loss": 1.0955,
      "step": 155
    },
    {
      "epoch": 0.3046875,
      "grad_norm": 0.4893472968930594,
      "learning_rate": 3.86440119033214e-05,
      "loss": 1.1854,
      "step": 156
    },
    {
      "epoch": 0.306640625,
      "grad_norm": 0.5731240348991923,
      "learning_rate": 3.862080565153731e-05,
      "loss": 1.2505,
      "step": 157
    },
    {
      "epoch": 0.30859375,
      "grad_norm": 0.4594995644663965,
      "learning_rate": 3.8597409594754025e-05,
      "loss": 1.1047,
      "step": 158
    },
    {
      "epoch": 0.310546875,
      "grad_norm": 0.3898970756217597,
      "learning_rate": 3.857382397145148e-05,
      "loss": 1.1728,
      "step": 159
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.5165759238716673,
      "learning_rate": 3.85500490220419e-05,
      "loss": 1.1232,
      "step": 160
    },
    {
      "epoch": 0.314453125,
      "grad_norm": 0.42169317869735606,
      "learning_rate": 3.852608498886732e-05,
      "loss": 1.1087,
      "step": 161
    },
    {
      "epoch": 0.31640625,
      "grad_norm": 0.4831766592421198,
      "learning_rate": 3.850193211619718e-05,
      "loss": 1.0902,
      "step": 162
    },
    {
      "epoch": 0.318359375,
      "grad_norm": 0.5168422003190449,
      "learning_rate": 3.8477590650225735e-05,
      "loss": 1.1979,
      "step": 163
    },
    {
      "epoch": 0.3203125,
      "grad_norm": 0.44267326014624,
      "learning_rate": 3.845306083906967e-05,
      "loss": 1.1311,
      "step": 164
    },
    {
      "epoch": 0.322265625,
      "grad_norm": 0.42634229457641887,
      "learning_rate": 3.842834293276545e-05,
      "loss": 1.1729,
      "step": 165
    },
    {
      "epoch": 0.32421875,
      "grad_norm": 0.40628491116146026,
      "learning_rate": 3.8403437183266834e-05,
      "loss": 1.0984,
      "step": 166
    },
    {
      "epoch": 0.326171875,
      "grad_norm": 0.4159045672550255,
      "learning_rate": 3.8378343844442344e-05,
      "loss": 1.1731,
      "step": 167
    },
    {
      "epoch": 0.328125,
      "grad_norm": 0.5968785135150301,
      "learning_rate": 3.8353063172072564e-05,
      "loss": 1.0247,
      "step": 168
    },
    {
      "epoch": 0.330078125,
      "grad_norm": 0.4649591605790638,
      "learning_rate": 3.8327595423847645e-05,
      "loss": 1.139,
      "step": 169
    },
    {
      "epoch": 0.33203125,
      "grad_norm": 0.48079030109724175,
      "learning_rate": 3.830194085936463e-05,
      "loss": 1.1268,
      "step": 170
    },
    {
      "epoch": 0.333984375,
      "grad_norm": 0.46348618416181137,
      "learning_rate": 3.8276099740124794e-05,
      "loss": 1.2004,
      "step": 171
    },
    {
      "epoch": 0.3359375,
      "grad_norm": 0.4832617358199499,
      "learning_rate": 3.8250072329531004e-05,
      "loss": 1.0743,
      "step": 172
    },
    {
      "epoch": 0.337890625,
      "grad_norm": 0.4420229534375586,
      "learning_rate": 3.822385889288503e-05,
      "loss": 1.141,
      "step": 173
    },
    {
      "epoch": 0.33984375,
      "grad_norm": 0.39752191495545935,
      "learning_rate": 3.819745969738484e-05,
      "loss": 1.0972,
      "step": 174
    },
    {
      "epoch": 0.341796875,
      "grad_norm": 0.4411421700040708,
      "learning_rate": 3.817087501212185e-05,
      "loss": 1.0233,
      "step": 175
    },
    {
      "epoch": 0.34375,
      "grad_norm": 0.4017237336736879,
      "learning_rate": 3.8144105108078246e-05,
      "loss": 1.1563,
      "step": 176
    },
    {
      "epoch": 0.345703125,
      "grad_norm": 0.686922962042273,
      "learning_rate": 3.8117150258124134e-05,
      "loss": 1.147,
      "step": 177
    },
    {
      "epoch": 0.34765625,
      "grad_norm": 0.4294357539370898,
      "learning_rate": 3.8090010737014836e-05,
      "loss": 1.1116,
      "step": 178
    },
    {
      "epoch": 0.349609375,
      "grad_norm": 0.41962832297995667,
      "learning_rate": 3.806268682138805e-05,
      "loss": 1.0827,
      "step": 179
    },
    {
      "epoch": 0.3515625,
      "grad_norm": 0.4413195950046206,
      "learning_rate": 3.803517878976103e-05,
      "loss": 1.0814,
      "step": 180
    },
    {
      "epoch": 0.353515625,
      "grad_norm": 0.45365068157119814,
      "learning_rate": 3.8007486922527774e-05,
      "loss": 1.0599,
      "step": 181
    },
    {
      "epoch": 0.35546875,
      "grad_norm": 0.5286445380979327,
      "learning_rate": 3.7979611501956124e-05,
      "loss": 1.2251,
      "step": 182
    },
    {
      "epoch": 0.357421875,
      "grad_norm": 0.38599209970455534,
      "learning_rate": 3.795155281218493e-05,
      "loss": 1.1676,
      "step": 183
    },
    {
      "epoch": 0.359375,
      "grad_norm": 0.44025531979392435,
      "learning_rate": 3.7923311139221114e-05,
      "loss": 1.0514,
      "step": 184
    },
    {
      "epoch": 0.361328125,
      "grad_norm": 0.42167205583593925,
      "learning_rate": 3.789488677093681e-05,
      "loss": 1.1002,
      "step": 185
    },
    {
      "epoch": 0.36328125,
      "grad_norm": 0.4466402130651366,
      "learning_rate": 3.786627999706638e-05,
      "loss": 1.1013,
      "step": 186
    },
    {
      "epoch": 0.365234375,
      "grad_norm": 0.496760952886551,
      "learning_rate": 3.783749110920345e-05,
      "loss": 1.1465,
      "step": 187
    },
    {
      "epoch": 0.3671875,
      "grad_norm": 0.4367613213432748,
      "learning_rate": 3.780852040079802e-05,
      "loss": 1.0657,
      "step": 188
    },
    {
      "epoch": 0.369140625,
      "grad_norm": 0.41447069424638583,
      "learning_rate": 3.777936816715336e-05,
      "loss": 1.116,
      "step": 189
    },
    {
      "epoch": 0.37109375,
      "grad_norm": 0.4361134375016492,
      "learning_rate": 3.7750034705423095e-05,
      "loss": 1.2767,
      "step": 190
    },
    {
      "epoch": 0.373046875,
      "grad_norm": 0.4066150259484398,
      "learning_rate": 3.772052031460812e-05,
      "loss": 1.0785,
      "step": 191
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.40407841923262816,
      "learning_rate": 3.769082529555359e-05,
      "loss": 1.1644,
      "step": 192
    },
    {
      "epoch": 0.376953125,
      "grad_norm": 0.44561296429853814,
      "learning_rate": 3.766094995094581e-05,
      "loss": 1.0663,
      "step": 193
    },
    {
      "epoch": 0.37890625,
      "grad_norm": 0.5352430776738828,
      "learning_rate": 3.7630894585309195e-05,
      "loss": 1.0209,
      "step": 194
    },
    {
      "epoch": 0.380859375,
      "grad_norm": 0.43636357529723163,
      "learning_rate": 3.7600659505003125e-05,
      "loss": 1.0621,
      "step": 195
    },
    {
      "epoch": 0.3828125,
      "grad_norm": 0.4264879021475797,
      "learning_rate": 3.757024501821885e-05,
      "loss": 1.1336,
      "step": 196
    },
    {
      "epoch": 0.384765625,
      "grad_norm": 0.3873402520476977,
      "learning_rate": 3.753965143497635e-05,
      "loss": 1.1378,
      "step": 197
    },
    {
      "epoch": 0.38671875,
      "grad_norm": 0.40092066811193233,
      "learning_rate": 3.750887906712115e-05,
      "loss": 1.0685,
      "step": 198
    },
    {
      "epoch": 0.388671875,
      "grad_norm": 0.43572366333630774,
      "learning_rate": 3.747792822832117e-05,
      "loss": 1.1723,
      "step": 199
    },
    {
      "epoch": 0.390625,
      "grad_norm": 0.37730662296410905,
      "learning_rate": 3.744679923406351e-05,
      "loss": 1.0823,
      "step": 200
    },
    {
      "epoch": 0.392578125,
      "grad_norm": 0.4578098403628755,
      "learning_rate": 3.741549240165122e-05,
      "loss": 1.1354,
      "step": 201
    },
    {
      "epoch": 0.39453125,
      "grad_norm": 0.4402925550279655,
      "learning_rate": 3.738400805020011e-05,
      "loss": 1.0921,
      "step": 202
    },
    {
      "epoch": 0.396484375,
      "grad_norm": 0.3814506298253285,
      "learning_rate": 3.7352346500635466e-05,
      "loss": 1.0813,
      "step": 203
    },
    {
      "epoch": 0.3984375,
      "grad_norm": 0.5352313284178145,
      "learning_rate": 3.732050807568878e-05,
      "loss": 1.2286,
      "step": 204
    },
    {
      "epoch": 0.400390625,
      "grad_norm": 0.4394941726895711,
      "learning_rate": 3.728849309989445e-05,
      "loss": 1.1362,
      "step": 205
    },
    {
      "epoch": 0.40234375,
      "grad_norm": 0.40009193940161264,
      "learning_rate": 3.7256301899586524e-05,
      "loss": 1.014,
      "step": 206
    },
    {
      "epoch": 0.404296875,
      "grad_norm": 0.4093033957375515,
      "learning_rate": 3.7223934802895294e-05,
      "loss": 1.0731,
      "step": 207
    },
    {
      "epoch": 0.40625,
      "grad_norm": 0.47801078784248796,
      "learning_rate": 3.719139213974403e-05,
      "loss": 1.2081,
      "step": 208
    },
    {
      "epoch": 0.408203125,
      "grad_norm": 0.5965083454407833,
      "learning_rate": 3.715867424184554e-05,
      "loss": 1.1495,
      "step": 209
    },
    {
      "epoch": 0.41015625,
      "grad_norm": 0.43672026913516004,
      "learning_rate": 3.712578144269887e-05,
      "loss": 1.1201,
      "step": 210
    },
    {
      "epoch": 0.412109375,
      "grad_norm": 0.5253144641112631,
      "learning_rate": 3.7092714077585836e-05,
      "loss": 1.2268,
      "step": 211
    },
    {
      "epoch": 0.4140625,
      "grad_norm": 0.4738073414405108,
      "learning_rate": 3.705947248356765e-05,
      "loss": 1.1188,
      "step": 212
    },
    {
      "epoch": 0.416015625,
      "grad_norm": 0.4477140058126639,
      "learning_rate": 3.7026056999481464e-05,
      "loss": 1.0571,
      "step": 213
    },
    {
      "epoch": 0.41796875,
      "grad_norm": 0.4471574730565842,
      "learning_rate": 3.699246796593692e-05,
      "loss": 1.0847,
      "step": 214
    },
    {
      "epoch": 0.419921875,
      "grad_norm": 0.41405988952981876,
      "learning_rate": 3.6958705725312655e-05,
      "loss": 1.1401,
      "step": 215
    },
    {
      "epoch": 0.421875,
      "grad_norm": 0.49370245896699827,
      "learning_rate": 3.692477062175289e-05,
      "loss": 1.0703,
      "step": 216
    },
    {
      "epoch": 0.423828125,
      "grad_norm": 0.4406399072344879,
      "learning_rate": 3.689066300116381e-05,
      "loss": 1.1793,
      "step": 217
    },
    {
      "epoch": 0.42578125,
      "grad_norm": 0.43483619180179833,
      "learning_rate": 3.6856383211210134e-05,
      "loss": 1.1305,
      "step": 218
    },
    {
      "epoch": 0.427734375,
      "grad_norm": 0.43256055966703133,
      "learning_rate": 3.682193160131152e-05,
      "loss": 1.0943,
      "step": 219
    },
    {
      "epoch": 0.4296875,
      "grad_norm": 0.5598257236379292,
      "learning_rate": 3.678730852263901e-05,
      "loss": 1.2309,
      "step": 220
    },
    {
      "epoch": 0.431640625,
      "grad_norm": 0.39045352547405415,
      "learning_rate": 3.675251432811144e-05,
      "loss": 1.0047,
      "step": 221
    },
    {
      "epoch": 0.43359375,
      "grad_norm": 0.44912102512870905,
      "learning_rate": 3.671754937239191e-05,
      "loss": 1.1087,
      "step": 222
    },
    {
      "epoch": 0.435546875,
      "grad_norm": 0.4174420596478436,
      "learning_rate": 3.668241401188407e-05,
      "loss": 1.0313,
      "step": 223
    },
    {
      "epoch": 0.4375,
      "grad_norm": 0.36458359932139156,
      "learning_rate": 3.6647108604728546e-05,
      "loss": 0.9782,
      "step": 224
    },
    {
      "epoch": 0.439453125,
      "grad_norm": 0.4419635662052487,
      "learning_rate": 3.661163351079929e-05,
      "loss": 1.1076,
      "step": 225
    },
    {
      "epoch": 0.44140625,
      "grad_norm": 0.4537093691655119,
      "learning_rate": 3.6575989091699895e-05,
      "loss": 1.1265,
      "step": 226
    },
    {
      "epoch": 0.443359375,
      "grad_norm": 0.4515222234083662,
      "learning_rate": 3.65401757107599e-05,
      "loss": 1.124,
      "step": 227
    },
    {
      "epoch": 0.4453125,
      "grad_norm": 0.4509933735945529,
      "learning_rate": 3.650419373303112e-05,
      "loss": 1.2212,
      "step": 228
    },
    {
      "epoch": 0.447265625,
      "grad_norm": 0.39315970041656184,
      "learning_rate": 3.646804352528389e-05,
      "loss": 1.1003,
      "step": 229
    },
    {
      "epoch": 0.44921875,
      "grad_norm": 0.583897939706095,
      "learning_rate": 3.643172545600336e-05,
      "loss": 1.0984,
      "step": 230
    },
    {
      "epoch": 0.451171875,
      "grad_norm": 0.5164803615434137,
      "learning_rate": 3.63952398953857e-05,
      "loss": 1.0738,
      "step": 231
    },
    {
      "epoch": 0.453125,
      "grad_norm": 0.4070265753872102,
      "learning_rate": 3.6358587215334355e-05,
      "loss": 1.034,
      "step": 232
    },
    {
      "epoch": 0.455078125,
      "grad_norm": 0.4101472350679783,
      "learning_rate": 3.632176778945626e-05,
      "loss": 1.1234,
      "step": 233
    },
    {
      "epoch": 0.45703125,
      "grad_norm": 0.410956088362877,
      "learning_rate": 3.628478199305799e-05,
      "loss": 1.1062,
      "step": 234
    },
    {
      "epoch": 0.458984375,
      "grad_norm": 0.42181972355385416,
      "learning_rate": 3.624763020314199e-05,
      "loss": 1.1848,
      "step": 235
    },
    {
      "epoch": 0.4609375,
      "grad_norm": 0.4069735981570203,
      "learning_rate": 3.62103127984027e-05,
      "loss": 1.1203,
      "step": 236
    },
    {
      "epoch": 0.462890625,
      "grad_norm": 0.4142934678480609,
      "learning_rate": 3.617283015922268e-05,
      "loss": 1.1044,
      "step": 237
    },
    {
      "epoch": 0.46484375,
      "grad_norm": 0.4697374307040272,
      "learning_rate": 3.6135182667668764e-05,
      "loss": 1.1947,
      "step": 238
    },
    {
      "epoch": 0.466796875,
      "grad_norm": 0.3985058819632944,
      "learning_rate": 3.6097370707488175e-05,
      "loss": 1.0906,
      "step": 239
    },
    {
      "epoch": 0.46875,
      "grad_norm": 0.40215610602620183,
      "learning_rate": 3.6059394664104554e-05,
      "loss": 1.1607,
      "step": 240
    },
    {
      "epoch": 0.470703125,
      "grad_norm": 0.3985665062059567,
      "learning_rate": 3.60212549246141e-05,
      "loss": 1.0787,
      "step": 241
    },
    {
      "epoch": 0.47265625,
      "grad_norm": 0.43711415007382576,
      "learning_rate": 3.598295187778158e-05,
      "loss": 1.1554,
      "step": 242
    },
    {
      "epoch": 0.474609375,
      "grad_norm": 0.4382023321095773,
      "learning_rate": 3.5944485914036384e-05,
      "loss": 1.0126,
      "step": 243
    },
    {
      "epoch": 0.4765625,
      "grad_norm": 0.37488265505774904,
      "learning_rate": 3.590585742546853e-05,
      "loss": 1.1054,
      "step": 244
    },
    {
      "epoch": 0.478515625,
      "grad_norm": 0.40930451172856447,
      "learning_rate": 3.586706680582471e-05,
      "loss": 1.0321,
      "step": 245
    },
    {
      "epoch": 0.48046875,
      "grad_norm": 0.5059310227059168,
      "learning_rate": 3.5828114450504205e-05,
      "loss": 1.1239,
      "step": 246
    },
    {
      "epoch": 0.482421875,
      "grad_norm": 0.45898297435796365,
      "learning_rate": 3.5789000756554927e-05,
      "loss": 1.0467,
      "step": 247
    },
    {
      "epoch": 0.484375,
      "grad_norm": 0.42551550838444063,
      "learning_rate": 3.5749726122669316e-05,
      "loss": 1.051,
      "step": 248
    },
    {
      "epoch": 0.486328125,
      "grad_norm": 0.4451344613451106,
      "learning_rate": 3.5710290949180325e-05,
      "loss": 1.1036,
      "step": 249
    },
    {
      "epoch": 0.48828125,
      "grad_norm": 0.43151805025113255,
      "learning_rate": 3.5670695638057285e-05,
      "loss": 1.1906,
      "step": 250
    },
    {
      "epoch": 0.490234375,
      "grad_norm": 0.492114391902568,
      "learning_rate": 3.563094059290186e-05,
      "loss": 1.1629,
      "step": 251
    },
    {
      "epoch": 0.4921875,
      "grad_norm": 0.4144331093915329,
      "learning_rate": 3.5591026218943905e-05,
      "loss": 1.1485,
      "step": 252
    },
    {
      "epoch": 0.494140625,
      "grad_norm": 0.4201461662795515,
      "learning_rate": 3.5550952923037337e-05,
      "loss": 1.1451,
      "step": 253
    },
    {
      "epoch": 0.49609375,
      "grad_norm": 0.41132936789582963,
      "learning_rate": 3.551072111365598e-05,
      "loss": 1.1216,
      "step": 254
    },
    {
      "epoch": 0.498046875,
      "grad_norm": 0.40892606177310264,
      "learning_rate": 3.547033120088943e-05,
      "loss": 1.0282,
      "step": 255
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.39721649148962185,
      "learning_rate": 3.5429783596438864e-05,
      "loss": 1.113,
      "step": 256
    },
    {
      "epoch": 0.501953125,
      "grad_norm": 0.41766348101220013,
      "learning_rate": 3.5389078713612806e-05,
      "loss": 1.0074,
      "step": 257
    },
    {
      "epoch": 0.50390625,
      "grad_norm": 0.4167567256329769,
      "learning_rate": 3.534821696732296e-05,
      "loss": 1.1494,
      "step": 258
    },
    {
      "epoch": 0.505859375,
      "grad_norm": 0.40290815531080393,
      "learning_rate": 3.5307198774079986e-05,
      "loss": 1.1173,
      "step": 259
    },
    {
      "epoch": 0.5078125,
      "grad_norm": 0.3993720783667527,
      "learning_rate": 3.52660245519892e-05,
      "loss": 1.0752,
      "step": 260
    },
    {
      "epoch": 0.509765625,
      "grad_norm": 0.42545000522760734,
      "learning_rate": 3.522469472074638e-05,
      "loss": 0.9948,
      "step": 261
    },
    {
      "epoch": 0.51171875,
      "grad_norm": 0.37379510205589955,
      "learning_rate": 3.518320970163341e-05,
      "loss": 1.0816,
      "step": 262
    },
    {
      "epoch": 0.513671875,
      "grad_norm": 0.38633279486112854,
      "learning_rate": 3.514156991751409e-05,
      "loss": 1.0954,
      "step": 263
    },
    {
      "epoch": 0.515625,
      "grad_norm": 0.40389091982968633,
      "learning_rate": 3.509977579282971e-05,
      "loss": 1.133,
      "step": 264
    },
    {
      "epoch": 0.517578125,
      "grad_norm": 0.4804041926173668,
      "learning_rate": 3.50578277535948e-05,
      "loss": 1.0541,
      "step": 265
    },
    {
      "epoch": 0.51953125,
      "grad_norm": 0.4012148619394628,
      "learning_rate": 3.501572622739278e-05,
      "loss": 1.1555,
      "step": 266
    },
    {
      "epoch": 0.521484375,
      "grad_norm": 0.3696526763975506,
      "learning_rate": 3.497347164337158e-05,
      "loss": 1.0857,
      "step": 267
    },
    {
      "epoch": 0.5234375,
      "grad_norm": 0.655745451392472,
      "learning_rate": 3.4931064432239256e-05,
      "loss": 1.1313,
      "step": 268
    },
    {
      "epoch": 0.525390625,
      "grad_norm": 0.37063711320152914,
      "learning_rate": 3.4888505026259644e-05,
      "loss": 1.0493,
      "step": 269
    },
    {
      "epoch": 0.52734375,
      "grad_norm": 0.6053650660031528,
      "learning_rate": 3.484579385924791e-05,
      "loss": 1.228,
      "step": 270
    },
    {
      "epoch": 0.529296875,
      "grad_norm": 0.4395843614703912,
      "learning_rate": 3.480293136656617e-05,
      "loss": 1.0371,
      "step": 271
    },
    {
      "epoch": 0.53125,
      "grad_norm": 0.4253433992305504,
      "learning_rate": 3.475991798511899e-05,
      "loss": 1.1542,
      "step": 272
    },
    {
      "epoch": 0.533203125,
      "grad_norm": 0.4192169579593461,
      "learning_rate": 3.471675415334899e-05,
      "loss": 1.119,
      "step": 273
    },
    {
      "epoch": 0.53515625,
      "grad_norm": 0.5125507615260523,
      "learning_rate": 3.467344031123237e-05,
      "loss": 1.0975,
      "step": 274
    },
    {
      "epoch": 0.537109375,
      "grad_norm": 0.4409386727934208,
      "learning_rate": 3.4629976900274396e-05,
      "loss": 1.0797,
      "step": 275
    },
    {
      "epoch": 0.5390625,
      "grad_norm": 0.4433870652840288,
      "learning_rate": 3.45863643635049e-05,
      "loss": 1.0765,
      "step": 276
    },
    {
      "epoch": 0.541015625,
      "grad_norm": 0.4369641917579842,
      "learning_rate": 3.454260314547381e-05,
      "loss": 1.1345,
      "step": 277
    },
    {
      "epoch": 0.54296875,
      "grad_norm": 0.4569220638166111,
      "learning_rate": 3.449869369224656e-05,
      "loss": 1.0484,
      "step": 278
    },
    {
      "epoch": 0.544921875,
      "grad_norm": 0.39807678444867833,
      "learning_rate": 3.445463645139959e-05,
      "loss": 1.1421,
      "step": 279
    },
    {
      "epoch": 0.546875,
      "grad_norm": 0.4053891646377848,
      "learning_rate": 3.441043187201574e-05,
      "loss": 1.0423,
      "step": 280
    },
    {
      "epoch": 0.548828125,
      "grad_norm": 0.3906910516461102,
      "learning_rate": 3.436608040467973e-05,
      "loss": 1.1273,
      "step": 281
    },
    {
      "epoch": 0.55078125,
      "grad_norm": 0.41346781105113967,
      "learning_rate": 3.432158250147351e-05,
      "loss": 1.0668,
      "step": 282
    },
    {
      "epoch": 0.552734375,
      "grad_norm": 0.4124283498849353,
      "learning_rate": 3.4276938615971664e-05,
      "loss": 1.0927,
      "step": 283
    },
    {
      "epoch": 0.5546875,
      "grad_norm": 0.43815431152188694,
      "learning_rate": 3.4232149203236836e-05,
      "loss": 1.1899,
      "step": 284
    },
    {
      "epoch": 0.556640625,
      "grad_norm": 0.3884560347509617,
      "learning_rate": 3.418721471981502e-05,
      "loss": 1.0609,
      "step": 285
    },
    {
      "epoch": 0.55859375,
      "grad_norm": 0.4232084968596145,
      "learning_rate": 3.4142135623730954e-05,
      "loss": 1.1084,
      "step": 286
    },
    {
      "epoch": 0.560546875,
      "grad_norm": 0.6358397558455653,
      "learning_rate": 3.409691237448343e-05,
      "loss": 1.029,
      "step": 287
    },
    {
      "epoch": 0.5625,
      "grad_norm": 0.45992194648645957,
      "learning_rate": 3.405154543304065e-05,
      "loss": 1.0849,
      "step": 288
    },
    {
      "epoch": 0.564453125,
      "grad_norm": 0.4818812993346098,
      "learning_rate": 3.400603526183542e-05,
      "loss": 0.943,
      "step": 289
    },
    {
      "epoch": 0.56640625,
      "grad_norm": 0.3765252982516796,
      "learning_rate": 3.3960382324760596e-05,
      "loss": 0.9954,
      "step": 290
    },
    {
      "epoch": 0.568359375,
      "grad_norm": 0.46990214773068983,
      "learning_rate": 3.391458708716422e-05,
      "loss": 1.0926,
      "step": 291
    },
    {
      "epoch": 0.5703125,
      "grad_norm": 0.3917178675223708,
      "learning_rate": 3.3868650015844835e-05,
      "loss": 1.0707,
      "step": 292
    },
    {
      "epoch": 0.572265625,
      "grad_norm": 0.41696024883927335,
      "learning_rate": 3.382257157904674e-05,
      "loss": 1.0687,
      "step": 293
    },
    {
      "epoch": 0.57421875,
      "grad_norm": 0.38807035050695815,
      "learning_rate": 3.377635224645515e-05,
      "loss": 1.1126,
      "step": 294
    },
    {
      "epoch": 0.576171875,
      "grad_norm": 0.406255734326262,
      "learning_rate": 3.3729992489191514e-05,
      "loss": 1.1278,
      "step": 295
    },
    {
      "epoch": 0.578125,
      "grad_norm": 0.39143009407102003,
      "learning_rate": 3.368349277980861e-05,
      "loss": 1.1409,
      "step": 296
    },
    {
      "epoch": 0.580078125,
      "grad_norm": 0.39325912719226885,
      "learning_rate": 3.363685359228579e-05,
      "loss": 1.0673,
      "step": 297
    },
    {
      "epoch": 0.58203125,
      "grad_norm": 0.4080744357399852,
      "learning_rate": 3.359007540202412e-05,
      "loss": 1.0569,
      "step": 298
    },
    {
      "epoch": 0.583984375,
      "grad_norm": 0.41221286181985456,
      "learning_rate": 3.354315868584155e-05,
      "loss": 1.0345,
      "step": 299
    },
    {
      "epoch": 0.5859375,
      "grad_norm": 0.408899231590681,
      "learning_rate": 3.349610392196804e-05,
      "loss": 1.1531,
      "step": 300
    },
    {
      "epoch": 0.587890625,
      "grad_norm": 0.40782751081372265,
      "learning_rate": 3.344891159004072e-05,
      "loss": 1.1214,
      "step": 301
    },
    {
      "epoch": 0.58984375,
      "grad_norm": 0.41491986698901345,
      "learning_rate": 3.340158217109895e-05,
      "loss": 1.102,
      "step": 302
    },
    {
      "epoch": 0.591796875,
      "grad_norm": 0.43560034237218315,
      "learning_rate": 3.335411614757942e-05,
      "loss": 1.0563,
      "step": 303
    },
    {
      "epoch": 0.59375,
      "grad_norm": 0.39300089945853034,
      "learning_rate": 3.3306514003311305e-05,
      "loss": 1.0941,
      "step": 304
    },
    {
      "epoch": 0.595703125,
      "grad_norm": 0.3993080209023848,
      "learning_rate": 3.3258776223511254e-05,
      "loss": 1.061,
      "step": 305
    },
    {
      "epoch": 0.59765625,
      "grad_norm": 0.4403361997874876,
      "learning_rate": 3.3210903294778476e-05,
      "loss": 1.059,
      "step": 306
    },
    {
      "epoch": 0.599609375,
      "grad_norm": 0.40839699507220767,
      "learning_rate": 3.3162895705089755e-05,
      "loss": 1.0646,
      "step": 307
    },
    {
      "epoch": 0.6015625,
      "grad_norm": 0.45190381917447386,
      "learning_rate": 3.311475394379454e-05,
      "loss": 1.0537,
      "step": 308
    },
    {
      "epoch": 0.603515625,
      "grad_norm": 0.4029154813389833,
      "learning_rate": 3.306647850160986e-05,
      "loss": 1.0964,
      "step": 309
    },
    {
      "epoch": 0.60546875,
      "grad_norm": 0.4202106517061233,
      "learning_rate": 3.301806987061543e-05,
      "loss": 1.0978,
      "step": 310
    },
    {
      "epoch": 0.607421875,
      "grad_norm": 0.4668232017003024,
      "learning_rate": 3.296952854424854e-05,
      "loss": 1.0437,
      "step": 311
    },
    {
      "epoch": 0.609375,
      "grad_norm": 0.39673723899015667,
      "learning_rate": 3.292085501729909e-05,
      "loss": 1.1046,
      "step": 312
    },
    {
      "epoch": 0.611328125,
      "grad_norm": 0.44958313468143707,
      "learning_rate": 3.287204978590451e-05,
      "loss": 1.1186,
      "step": 313
    },
    {
      "epoch": 0.61328125,
      "grad_norm": 0.4836454614853554,
      "learning_rate": 3.282311334754473e-05,
      "loss": 1.0877,
      "step": 314
    },
    {
      "epoch": 0.615234375,
      "grad_norm": 0.42606585670317537,
      "learning_rate": 3.277404620103707e-05,
      "loss": 1.1295,
      "step": 315
    },
    {
      "epoch": 0.6171875,
      "grad_norm": 0.390307353492261,
      "learning_rate": 3.27248488465312e-05,
      "loss": 1.1007,
      "step": 316
    },
    {
      "epoch": 0.619140625,
      "grad_norm": 0.3805925300751237,
      "learning_rate": 3.267552178550401e-05,
      "loss": 1.1001,
      "step": 317
    },
    {
      "epoch": 0.62109375,
      "grad_norm": 0.4035790500067785,
      "learning_rate": 3.262606552075454e-05,
      "loss": 1.1128,
      "step": 318
    },
    {
      "epoch": 0.623046875,
      "grad_norm": 0.4722955312249792,
      "learning_rate": 3.2576480556398786e-05,
      "loss": 1.1137,
      "step": 319
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.44165761079295995,
      "learning_rate": 3.2526767397864614e-05,
      "loss": 1.1454,
      "step": 320
    },
    {
      "epoch": 0.626953125,
      "grad_norm": 0.39553753160419564,
      "learning_rate": 3.2476926551886606e-05,
      "loss": 1.1166,
      "step": 321
    },
    {
      "epoch": 0.62890625,
      "grad_norm": 0.403965297853274,
      "learning_rate": 3.2426958526500865e-05,
      "loss": 1.0781,
      "step": 322
    },
    {
      "epoch": 0.630859375,
      "grad_norm": 0.3903234152596363,
      "learning_rate": 3.237686383103988e-05,
      "loss": 1.0549,
      "step": 323
    },
    {
      "epoch": 0.6328125,
      "grad_norm": 0.3927744347727879,
      "learning_rate": 3.232664297612727e-05,
      "loss": 1.1046,
      "step": 324
    },
    {
      "epoch": 0.634765625,
      "grad_norm": 0.3812149147814974,
      "learning_rate": 3.227629647367268e-05,
      "loss": 1.1601,
      "step": 325
    },
    {
      "epoch": 0.63671875,
      "grad_norm": 0.38396424698024334,
      "learning_rate": 3.2225824836866436e-05,
      "loss": 1.0004,
      "step": 326
    },
    {
      "epoch": 0.638671875,
      "grad_norm": 0.47563674580569204,
      "learning_rate": 3.217522858017442e-05,
      "loss": 1.0227,
      "step": 327
    },
    {
      "epoch": 0.640625,
      "grad_norm": 0.3935678660654307,
      "learning_rate": 3.212450821933277e-05,
      "loss": 1.0778,
      "step": 328
    },
    {
      "epoch": 0.642578125,
      "grad_norm": 0.37644343966319804,
      "learning_rate": 3.207366427134264e-05,
      "loss": 1.0786,
      "step": 329
    },
    {
      "epoch": 0.64453125,
      "grad_norm": 0.3901117853270985,
      "learning_rate": 3.2022697254464926e-05,
      "loss": 1.0559,
      "step": 330
    },
    {
      "epoch": 0.646484375,
      "grad_norm": 0.38427110510469054,
      "learning_rate": 3.1971607688215005e-05,
      "loss": 1.0164,
      "step": 331
    },
    {
      "epoch": 0.6484375,
      "grad_norm": 0.42177940077749226,
      "learning_rate": 3.19203960933574e-05,
      "loss": 1.0411,
      "step": 332
    },
    {
      "epoch": 0.650390625,
      "grad_norm": 0.4528297229069142,
      "learning_rate": 3.1869062991900496e-05,
      "loss": 1.1706,
      "step": 333
    },
    {
      "epoch": 0.65234375,
      "grad_norm": 0.3803445217139758,
      "learning_rate": 3.1817608907091216e-05,
      "loss": 1.0699,
      "step": 334
    },
    {
      "epoch": 0.654296875,
      "grad_norm": 0.41347538149417745,
      "learning_rate": 3.176603436340969e-05,
      "loss": 1.1955,
      "step": 335
    },
    {
      "epoch": 0.65625,
      "grad_norm": 0.3694910871081213,
      "learning_rate": 3.1714339886563896e-05,
      "loss": 0.9668,
      "step": 336
    },
    {
      "epoch": 0.658203125,
      "grad_norm": 0.3817019926131847,
      "learning_rate": 3.1662526003484336e-05,
      "loss": 0.9349,
      "step": 337
    },
    {
      "epoch": 0.66015625,
      "grad_norm": 0.4366158667650914,
      "learning_rate": 3.16105932423186e-05,
      "loss": 1.0995,
      "step": 338
    },
    {
      "epoch": 0.662109375,
      "grad_norm": 0.41958839201127524,
      "learning_rate": 3.155854213242606e-05,
      "loss": 0.9731,
      "step": 339
    },
    {
      "epoch": 0.6640625,
      "grad_norm": 0.47402698673401783,
      "learning_rate": 3.1506373204372414e-05,
      "loss": 1.147,
      "step": 340
    },
    {
      "epoch": 0.666015625,
      "grad_norm": 0.4827624577661964,
      "learning_rate": 3.145408698992431e-05,
      "loss": 1.0264,
      "step": 341
    },
    {
      "epoch": 0.66796875,
      "grad_norm": 0.4263534871906621,
      "learning_rate": 3.140168402204391e-05,
      "loss": 1.1036,
      "step": 342
    },
    {
      "epoch": 0.669921875,
      "grad_norm": 0.40773201005922843,
      "learning_rate": 3.134916483488347e-05,
      "loss": 1.0361,
      "step": 343
    },
    {
      "epoch": 0.671875,
      "grad_norm": 0.4066940928998629,
      "learning_rate": 3.129652996377987e-05,
      "loss": 1.1271,
      "step": 344
    },
    {
      "epoch": 0.673828125,
      "grad_norm": 0.4241747622419329,
      "learning_rate": 3.124377994524921e-05,
      "loss": 1.1259,
      "step": 345
    },
    {
      "epoch": 0.67578125,
      "grad_norm": 0.39662513220486106,
      "learning_rate": 3.1190915316981285e-05,
      "loss": 1.0236,
      "step": 346
    },
    {
      "epoch": 0.677734375,
      "grad_norm": 0.43948866331025493,
      "learning_rate": 3.1137936617834116e-05,
      "loss": 1.1076,
      "step": 347
    },
    {
      "epoch": 0.6796875,
      "grad_norm": 0.36237602577817707,
      "learning_rate": 3.10848443878285e-05,
      "loss": 1.033,
      "step": 348
    },
    {
      "epoch": 0.681640625,
      "grad_norm": 0.40357619022841135,
      "learning_rate": 3.103163916814243e-05,
      "loss": 1.1313,
      "step": 349
    },
    {
      "epoch": 0.68359375,
      "grad_norm": 0.4555883501566975,
      "learning_rate": 3.0978321501105666e-05,
      "loss": 1.0808,
      "step": 350
    },
    {
      "epoch": 0.685546875,
      "grad_norm": 0.35792704349676846,
      "learning_rate": 3.0924891930194135e-05,
      "loss": 1.0395,
      "step": 351
    },
    {
      "epoch": 0.6875,
      "grad_norm": 0.593623473361786,
      "learning_rate": 3.0871351000024425e-05,
      "loss": 1.0712,
      "step": 352
    },
    {
      "epoch": 0.689453125,
      "grad_norm": 0.4074422748367139,
      "learning_rate": 3.0817699256348225e-05,
      "loss": 0.9527,
      "step": 353
    },
    {
      "epoch": 0.69140625,
      "grad_norm": 0.4127817442760279,
      "learning_rate": 3.076393724604678e-05,
      "loss": 1.1954,
      "step": 354
    },
    {
      "epoch": 0.693359375,
      "grad_norm": 0.4946890107161909,
      "learning_rate": 3.071006551712528e-05,
      "loss": 1.0985,
      "step": 355
    },
    {
      "epoch": 0.6953125,
      "grad_norm": 0.44421056915788415,
      "learning_rate": 3.065608461870731e-05,
      "loss": 1.1738,
      "step": 356
    },
    {
      "epoch": 0.697265625,
      "grad_norm": 0.4556022988192606,
      "learning_rate": 3.0601995101029234e-05,
      "loss": 1.0996,
      "step": 357
    },
    {
      "epoch": 0.69921875,
      "grad_norm": 0.4589330478948055,
      "learning_rate": 3.054779751543459e-05,
      "loss": 1.1462,
      "step": 358
    },
    {
      "epoch": 0.701171875,
      "grad_norm": 0.8222210487787517,
      "learning_rate": 3.0493492414368467e-05,
      "loss": 1.0775,
      "step": 359
    },
    {
      "epoch": 0.703125,
      "grad_norm": 0.4588728539488581,
      "learning_rate": 3.0439080351371875e-05,
      "loss": 1.0424,
      "step": 360
    },
    {
      "epoch": 0.705078125,
      "grad_norm": 0.44719999962538626,
      "learning_rate": 3.0384561881076117e-05,
      "loss": 1.0759,
      "step": 361
    },
    {
      "epoch": 0.70703125,
      "grad_norm": 0.46357553715630206,
      "learning_rate": 3.0329937559197115e-05,
      "loss": 1.2382,
      "step": 362
    },
    {
      "epoch": 0.708984375,
      "grad_norm": 0.40336861309256355,
      "learning_rate": 3.0275207942529756e-05,
      "loss": 1.1079,
      "step": 363
    },
    {
      "epoch": 0.7109375,
      "grad_norm": 0.5144680446514719,
      "learning_rate": 3.022037358894221e-05,
      "loss": 1.0465,
      "step": 364
    },
    {
      "epoch": 0.712890625,
      "grad_norm": 0.4921289653271309,
      "learning_rate": 3.0165435057370263e-05,
      "loss": 1.0311,
      "step": 365
    },
    {
      "epoch": 0.71484375,
      "grad_norm": 0.4320225158526767,
      "learning_rate": 3.011039290781158e-05,
      "loss": 1.0595,
      "step": 366
    },
    {
      "epoch": 0.716796875,
      "grad_norm": 0.3810201922042623,
      "learning_rate": 3.005524770132004e-05,
      "loss": 0.9803,
      "step": 367
    },
    {
      "epoch": 0.71875,
      "grad_norm": 0.4495492407985583,
      "learning_rate": 3.0000000000000004e-05,
      "loss": 1.0729,
      "step": 368
    },
    {
      "epoch": 0.720703125,
      "grad_norm": 0.4152518634185682,
      "learning_rate": 2.9944650367000556e-05,
      "loss": 1.164,
      "step": 369
    },
    {
      "epoch": 0.72265625,
      "grad_norm": 0.46481518081956474,
      "learning_rate": 2.9889199366509807e-05,
      "loss": 1.0677,
      "step": 370
    },
    {
      "epoch": 0.724609375,
      "grad_norm": 0.36687791333329894,
      "learning_rate": 2.983364756374912e-05,
      "loss": 1.097,
      "step": 371
    },
    {
      "epoch": 0.7265625,
      "grad_norm": 0.4609623092360792,
      "learning_rate": 2.977799552496734e-05,
      "loss": 1.0742,
      "step": 372
    },
    {
      "epoch": 0.728515625,
      "grad_norm": 0.43485629130468156,
      "learning_rate": 2.9722243817435057e-05,
      "loss": 1.0596,
      "step": 373
    },
    {
      "epoch": 0.73046875,
      "grad_norm": 0.4308785423786187,
      "learning_rate": 2.9666393009438778e-05,
      "loss": 1.1025,
      "step": 374
    },
    {
      "epoch": 0.732421875,
      "grad_norm": 0.41425216636311923,
      "learning_rate": 2.9610443670275177e-05,
      "loss": 1.033,
      "step": 375
    },
    {
      "epoch": 0.734375,
      "grad_norm": 0.5209374726966056,
      "learning_rate": 2.955439637024526e-05,
      "loss": 1.0744,
      "step": 376
    },
    {
      "epoch": 0.736328125,
      "grad_norm": 0.7038228729760657,
      "learning_rate": 2.9498251680648572e-05,
      "loss": 1.0699,
      "step": 377
    },
    {
      "epoch": 0.73828125,
      "grad_norm": 0.38639106447314064,
      "learning_rate": 2.9442010173777355e-05,
      "loss": 1.0536,
      "step": 378
    },
    {
      "epoch": 0.740234375,
      "grad_norm": 0.5464755744132558,
      "learning_rate": 2.9385672422910746e-05,
      "loss": 1.1398,
      "step": 379
    },
    {
      "epoch": 0.7421875,
      "grad_norm": 0.37413132931711773,
      "learning_rate": 2.932923900230889e-05,
      "loss": 1.0285,
      "step": 380
    },
    {
      "epoch": 0.744140625,
      "grad_norm": 0.5155456583703741,
      "learning_rate": 2.9272710487207123e-05,
      "loss": 1.0657,
      "step": 381
    },
    {
      "epoch": 0.74609375,
      "grad_norm": 0.42610802775582945,
      "learning_rate": 2.92160874538101e-05,
      "loss": 1.0751,
      "step": 382
    },
    {
      "epoch": 0.748046875,
      "grad_norm": 0.37312053203898266,
      "learning_rate": 2.91593704792859e-05,
      "loss": 1.1236,
      "step": 383
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.3865778900367502,
      "learning_rate": 2.9102560141760178e-05,
      "loss": 1.0783,
      "step": 384
    },
    {
      "epoch": 0.751953125,
      "grad_norm": 0.44181257585885864,
      "learning_rate": 2.9045657020310245e-05,
      "loss": 1.096,
      "step": 385
    },
    {
      "epoch": 0.75390625,
      "grad_norm": 0.4355612014896031,
      "learning_rate": 2.898866169495916e-05,
      "loss": 1.1355,
      "step": 386
    },
    {
      "epoch": 0.755859375,
      "grad_norm": 0.43570244826557325,
      "learning_rate": 2.8931574746669865e-05,
      "loss": 0.979,
      "step": 387
    },
    {
      "epoch": 0.7578125,
      "grad_norm": 0.4624097023644056,
      "learning_rate": 2.8874396757339197e-05,
      "loss": 1.1244,
      "step": 388
    },
    {
      "epoch": 0.759765625,
      "grad_norm": 0.43243927150243583,
      "learning_rate": 2.881712830979201e-05,
      "loss": 1.2005,
      "step": 389
    },
    {
      "epoch": 0.76171875,
      "grad_norm": 0.39334103281716926,
      "learning_rate": 2.875976998777521e-05,
      "loss": 1.1406,
      "step": 390
    },
    {
      "epoch": 0.763671875,
      "grad_norm": 0.41626592809859797,
      "learning_rate": 2.8702322375951808e-05,
      "loss": 1.0462,
      "step": 391
    },
    {
      "epoch": 0.765625,
      "grad_norm": 0.37844113633007853,
      "learning_rate": 2.864478605989494e-05,
      "loss": 0.9938,
      "step": 392
    },
    {
      "epoch": 0.767578125,
      "grad_norm": 0.38237298412290605,
      "learning_rate": 2.8587161626081963e-05,
      "loss": 1.1152,
      "step": 393
    },
    {
      "epoch": 0.76953125,
      "grad_norm": 0.457773179175426,
      "learning_rate": 2.8529449661888397e-05,
      "loss": 1.0211,
      "step": 394
    },
    {
      "epoch": 0.771484375,
      "grad_norm": 0.5451142296439877,
      "learning_rate": 2.8471650755581982e-05,
      "loss": 1.0347,
      "step": 395
    },
    {
      "epoch": 0.7734375,
      "grad_norm": 0.3748054383861272,
      "learning_rate": 2.8413765496316682e-05,
      "loss": 1.0349,
      "step": 396
    },
    {
      "epoch": 0.775390625,
      "grad_norm": 0.40348473462322654,
      "learning_rate": 2.8355794474126673e-05,
      "loss": 1.0827,
      "step": 397
    },
    {
      "epoch": 0.77734375,
      "grad_norm": 0.45778728826184956,
      "learning_rate": 2.8297738279920302e-05,
      "loss": 1.08,
      "step": 398
    },
    {
      "epoch": 0.779296875,
      "grad_norm": 0.416175722341481,
      "learning_rate": 2.8239597505474123e-05,
      "loss": 1.1477,
      "step": 399
    },
    {
      "epoch": 0.78125,
      "grad_norm": 0.4762205014497946,
      "learning_rate": 2.8181372743426805e-05,
      "loss": 1.1281,
      "step": 400
    },
    {
      "epoch": 0.783203125,
      "grad_norm": 0.38963452597451154,
      "learning_rate": 2.8123064587273123e-05,
      "loss": 1.1001,
      "step": 401
    },
    {
      "epoch": 0.78515625,
      "grad_norm": 0.37143930094659405,
      "learning_rate": 2.8064673631357914e-05,
      "loss": 1.1031,
      "step": 402
    },
    {
      "epoch": 0.787109375,
      "grad_norm": 0.37217736788218464,
      "learning_rate": 2.8006200470869996e-05,
      "loss": 1.0837,
      "step": 403
    },
    {
      "epoch": 0.7890625,
      "grad_norm": 0.4976469620168046,
      "learning_rate": 2.794764570183611e-05,
      "loss": 1.1485,
      "step": 404
    },
    {
      "epoch": 0.791015625,
      "grad_norm": 0.4118640178274368,
      "learning_rate": 2.788900992111485e-05,
      "loss": 1.0149,
      "step": 405
    },
    {
      "epoch": 0.79296875,
      "grad_norm": 0.4876334794131612,
      "learning_rate": 2.7830293726390584e-05,
      "loss": 1.0814,
      "step": 406
    },
    {
      "epoch": 0.794921875,
      "grad_norm": 0.39552602320591645,
      "learning_rate": 2.7771497716167334e-05,
      "loss": 1.0316,
      "step": 407
    },
    {
      "epoch": 0.796875,
      "grad_norm": 0.3666660618337925,
      "learning_rate": 2.771262248976272e-05,
      "loss": 1.1006,
      "step": 408
    },
    {
      "epoch": 0.798828125,
      "grad_norm": 0.4084835818544231,
      "learning_rate": 2.7653668647301797e-05,
      "loss": 1.1573,
      "step": 409
    },
    {
      "epoch": 0.80078125,
      "grad_norm": 0.42026908788757056,
      "learning_rate": 2.7594636789710992e-05,
      "loss": 1.1005,
      "step": 410
    },
    {
      "epoch": 0.802734375,
      "grad_norm": 0.4260753401631911,
      "learning_rate": 2.753552751871195e-05,
      "loss": 1.0693,
      "step": 411
    },
    {
      "epoch": 0.8046875,
      "grad_norm": 0.3638242310551269,
      "learning_rate": 2.7476341436815377e-05,
      "loss": 1.0464,
      "step": 412
    },
    {
      "epoch": 0.806640625,
      "grad_norm": 0.3709057452758752,
      "learning_rate": 2.7417079147314965e-05,
      "loss": 1.0302,
      "step": 413
    },
    {
      "epoch": 0.80859375,
      "grad_norm": 0.3881489168967299,
      "learning_rate": 2.735774125428117e-05,
      "loss": 1.0273,
      "step": 414
    },
    {
      "epoch": 0.810546875,
      "grad_norm": 0.3540248781421392,
      "learning_rate": 2.729832836255511e-05,
      "loss": 1.0526,
      "step": 415
    },
    {
      "epoch": 0.8125,
      "grad_norm": 0.4031356501380205,
      "learning_rate": 2.723884107774236e-05,
      "loss": 1.0392,
      "step": 416
    },
    {
      "epoch": 0.814453125,
      "grad_norm": 0.4213724427608797,
      "learning_rate": 2.717928000620681e-05,
      "loss": 1.1335,
      "step": 417
    },
    {
      "epoch": 0.81640625,
      "grad_norm": 0.38457290513987724,
      "learning_rate": 2.7119645755064468e-05,
      "loss": 1.1109,
      "step": 418
    },
    {
      "epoch": 0.818359375,
      "grad_norm": 0.3970191569510665,
      "learning_rate": 2.7059938932177264e-05,
      "loss": 1.1087,
      "step": 419
    },
    {
      "epoch": 0.8203125,
      "grad_norm": 0.42376486272155184,
      "learning_rate": 2.700016014614687e-05,
      "loss": 1.108,
      "step": 420
    },
    {
      "epoch": 0.822265625,
      "grad_norm": 0.4648805287473145,
      "learning_rate": 2.6940310006308502e-05,
      "loss": 1.1895,
      "step": 421
    },
    {
      "epoch": 0.82421875,
      "grad_norm": 0.4219670118710678,
      "learning_rate": 2.688038912272468e-05,
      "loss": 1.1492,
      "step": 422
    },
    {
      "epoch": 0.826171875,
      "grad_norm": 0.41710413834658855,
      "learning_rate": 2.682039810617903e-05,
      "loss": 1.1072,
      "step": 423
    },
    {
      "epoch": 0.828125,
      "grad_norm": 0.41979400770447894,
      "learning_rate": 2.6760337568170056e-05,
      "loss": 1.0904,
      "step": 424
    },
    {
      "epoch": 0.830078125,
      "grad_norm": 0.6395242461570778,
      "learning_rate": 2.6700208120904925e-05,
      "loss": 0.9924,
      "step": 425
    },
    {
      "epoch": 0.83203125,
      "grad_norm": 0.3633335504856954,
      "learning_rate": 2.6640010377293174e-05,
      "loss": 1.014,
      "step": 426
    },
    {
      "epoch": 0.833984375,
      "grad_norm": 0.4464511956431912,
      "learning_rate": 2.6579744950940514e-05,
      "loss": 1.0734,
      "step": 427
    },
    {
      "epoch": 0.8359375,
      "grad_norm": 0.4687781979743879,
      "learning_rate": 2.6519412456142572e-05,
      "loss": 1.0249,
      "step": 428
    },
    {
      "epoch": 0.837890625,
      "grad_norm": 0.49738564921372447,
      "learning_rate": 2.6459013507878588e-05,
      "loss": 1.0612,
      "step": 429
    },
    {
      "epoch": 0.83984375,
      "grad_norm": 0.4494079640359484,
      "learning_rate": 2.639854872180518e-05,
      "loss": 1.026,
      "step": 430
    },
    {
      "epoch": 0.841796875,
      "grad_norm": 0.39318026641514375,
      "learning_rate": 2.6338018714250084e-05,
      "loss": 0.9957,
      "step": 431
    },
    {
      "epoch": 0.84375,
      "grad_norm": 0.4142115852538159,
      "learning_rate": 2.6277424102205817e-05,
      "loss": 1.0505,
      "step": 432
    },
    {
      "epoch": 0.845703125,
      "grad_norm": 0.5472076626281186,
      "learning_rate": 2.6216765503323444e-05,
      "loss": 1.0888,
      "step": 433
    },
    {
      "epoch": 0.84765625,
      "grad_norm": 0.45879911363611803,
      "learning_rate": 2.615604353590625e-05,
      "loss": 1.2271,
      "step": 434
    },
    {
      "epoch": 0.849609375,
      "grad_norm": 0.3879148923020066,
      "learning_rate": 2.6095258818903443e-05,
      "loss": 1.0789,
      "step": 435
    },
    {
      "epoch": 0.8515625,
      "grad_norm": 0.3623048445133421,
      "learning_rate": 2.603441197190385e-05,
      "loss": 1.1001,
      "step": 436
    },
    {
      "epoch": 0.853515625,
      "grad_norm": 0.4034291862610704,
      "learning_rate": 2.5973503615129607e-05,
      "loss": 1.0657,
      "step": 437
    },
    {
      "epoch": 0.85546875,
      "grad_norm": 0.40641069832633525,
      "learning_rate": 2.591253436942982e-05,
      "loss": 1.0971,
      "step": 438
    },
    {
      "epoch": 0.857421875,
      "grad_norm": 0.4203758291885779,
      "learning_rate": 2.5851504856274252e-05,
      "loss": 1.0488,
      "step": 439
    },
    {
      "epoch": 0.859375,
      "grad_norm": 0.4126884109160508,
      "learning_rate": 2.5790415697746976e-05,
      "loss": 1.0095,
      "step": 440
    },
    {
      "epoch": 0.861328125,
      "grad_norm": 0.4078387530750107,
      "learning_rate": 2.572926751654005e-05,
      "loss": 1.0758,
      "step": 441
    },
    {
      "epoch": 0.86328125,
      "grad_norm": 0.3817629694236213,
      "learning_rate": 2.5668060935947144e-05,
      "loss": 1.1348,
      "step": 442
    },
    {
      "epoch": 0.865234375,
      "grad_norm": 0.409692718707719,
      "learning_rate": 2.5606796579857223e-05,
      "loss": 1.0567,
      "step": 443
    },
    {
      "epoch": 0.8671875,
      "grad_norm": 0.4701176256570698,
      "learning_rate": 2.554547507274816e-05,
      "loss": 1.0535,
      "step": 444
    },
    {
      "epoch": 0.869140625,
      "grad_norm": 0.4055365903869681,
      "learning_rate": 2.5484097039680364e-05,
      "loss": 1.0327,
      "step": 445
    },
    {
      "epoch": 0.87109375,
      "grad_norm": 0.4185308510496096,
      "learning_rate": 2.5422663106290446e-05,
      "loss": 1.0917,
      "step": 446
    },
    {
      "epoch": 0.873046875,
      "grad_norm": 0.35436315376257477,
      "learning_rate": 2.5361173898784793e-05,
      "loss": 0.9629,
      "step": 447
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.40368860473897683,
      "learning_rate": 2.529963004393324e-05,
      "loss": 1.1186,
      "step": 448
    },
    {
      "epoch": 0.876953125,
      "grad_norm": 0.41933105267599274,
      "learning_rate": 2.5238032169062615e-05,
      "loss": 1.0612,
      "step": 449
    },
    {
      "epoch": 0.87890625,
      "grad_norm": 0.3920136702588332,
      "learning_rate": 2.5176380902050418e-05,
      "loss": 1.0218,
      "step": 450
    },
    {
      "epoch": 0.880859375,
      "grad_norm": 0.3924826056587098,
      "learning_rate": 2.511467687131836e-05,
      "loss": 1.0235,
      "step": 451
    },
    {
      "epoch": 0.8828125,
      "grad_norm": 0.3713296557429479,
      "learning_rate": 2.505292070582599e-05,
      "loss": 1.031,
      "step": 452
    },
    {
      "epoch": 0.884765625,
      "grad_norm": 0.4144024885541483,
      "learning_rate": 2.4991113035064275e-05,
      "loss": 1.1098,
      "step": 453
    },
    {
      "epoch": 0.88671875,
      "grad_norm": 0.3953030954711052,
      "learning_rate": 2.492925448904919e-05,
      "loss": 1.0298,
      "step": 454
    },
    {
      "epoch": 0.888671875,
      "grad_norm": 0.40979901345360326,
      "learning_rate": 2.4867345698315264e-05,
      "loss": 1.087,
      "step": 455
    },
    {
      "epoch": 0.890625,
      "grad_norm": 0.42099406843050524,
      "learning_rate": 2.4805387293909214e-05,
      "loss": 1.0307,
      "step": 456
    },
    {
      "epoch": 0.892578125,
      "grad_norm": 0.4824392395386347,
      "learning_rate": 2.4743379907383466e-05,
      "loss": 1.0751,
      "step": 457
    },
    {
      "epoch": 0.89453125,
      "grad_norm": 0.43303194714488125,
      "learning_rate": 2.46813241707897e-05,
      "loss": 1.0852,
      "step": 458
    },
    {
      "epoch": 0.896484375,
      "grad_norm": 0.42139104734956734,
      "learning_rate": 2.4619220716672487e-05,
      "loss": 1.0121,
      "step": 459
    },
    {
      "epoch": 0.8984375,
      "grad_norm": 0.4037004594251964,
      "learning_rate": 2.4557070178062755e-05,
      "loss": 1.1123,
      "step": 460
    },
    {
      "epoch": 0.900390625,
      "grad_norm": 0.43814766094211854,
      "learning_rate": 2.4494873188471378e-05,
      "loss": 1.0854,
      "step": 461
    },
    {
      "epoch": 0.90234375,
      "grad_norm": 0.37549428576364635,
      "learning_rate": 2.443263038188272e-05,
      "loss": 1.021,
      "step": 462
    },
    {
      "epoch": 0.904296875,
      "grad_norm": 0.4601484439948765,
      "learning_rate": 2.437034239274816e-05,
      "loss": 1.0255,
      "step": 463
    },
    {
      "epoch": 0.90625,
      "grad_norm": 0.408442323524795,
      "learning_rate": 2.430800985597963e-05,
      "loss": 1.1535,
      "step": 464
    },
    {
      "epoch": 0.908203125,
      "grad_norm": 0.3770639784598037,
      "learning_rate": 2.4245633406943146e-05,
      "loss": 1.0092,
      "step": 465
    },
    {
      "epoch": 0.91015625,
      "grad_norm": 0.39632696571553727,
      "learning_rate": 2.418321368145234e-05,
      "loss": 1.0392,
      "step": 466
    },
    {
      "epoch": 0.912109375,
      "grad_norm": 0.3900617301120619,
      "learning_rate": 2.412075131576194e-05,
      "loss": 0.9926,
      "step": 467
    },
    {
      "epoch": 0.9140625,
      "grad_norm": 0.3942202959616746,
      "learning_rate": 2.4058246946561337e-05,
      "loss": 0.9972,
      "step": 468
    },
    {
      "epoch": 0.916015625,
      "grad_norm": 0.3509404351888746,
      "learning_rate": 2.3995701210968068e-05,
      "loss": 0.988,
      "step": 469
    },
    {
      "epoch": 0.91796875,
      "grad_norm": 0.4168690258420827,
      "learning_rate": 2.393311474652131e-05,
      "loss": 1.1025,
      "step": 470
    },
    {
      "epoch": 0.919921875,
      "grad_norm": 0.46200933426792423,
      "learning_rate": 2.3870488191175413e-05,
      "loss": 1.0633,
      "step": 471
    },
    {
      "epoch": 0.921875,
      "grad_norm": 0.35711987014827834,
      "learning_rate": 2.380782218329337e-05,
      "loss": 1.0525,
      "step": 472
    },
    {
      "epoch": 0.923828125,
      "grad_norm": 0.4031204434850072,
      "learning_rate": 2.3745117361640328e-05,
      "loss": 1.1179,
      "step": 473
    },
    {
      "epoch": 0.92578125,
      "grad_norm": 0.38258772862694423,
      "learning_rate": 2.3682374365377055e-05,
      "loss": 1.1029,
      "step": 474
    },
    {
      "epoch": 0.927734375,
      "grad_norm": 0.4045956763131697,
      "learning_rate": 2.361959383405346e-05,
      "loss": 1.1135,
      "step": 475
    },
    {
      "epoch": 0.9296875,
      "grad_norm": 0.39473113885867483,
      "learning_rate": 2.3556776407602038e-05,
      "loss": 0.9916,
      "step": 476
    },
    {
      "epoch": 0.931640625,
      "grad_norm": 0.38643556532939677,
      "learning_rate": 2.349392272633136e-05,
      "loss": 1.0741,
      "step": 477
    },
    {
      "epoch": 0.93359375,
      "grad_norm": 0.42567439419557046,
      "learning_rate": 2.343103343091957e-05,
      "loss": 0.9976,
      "step": 478
    },
    {
      "epoch": 0.935546875,
      "grad_norm": 0.3885877057479704,
      "learning_rate": 2.3368109162407802e-05,
      "loss": 1.0954,
      "step": 479
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.3684575524697125,
      "learning_rate": 2.33051505621937e-05,
      "loss": 1.1091,
      "step": 480
    },
    {
      "epoch": 0.939453125,
      "grad_norm": 0.4053221637918515,
      "learning_rate": 2.3242158272024852e-05,
      "loss": 1.0335,
      "step": 481
    },
    {
      "epoch": 0.94140625,
      "grad_norm": 0.3769352607947545,
      "learning_rate": 2.3179132933992247e-05,
      "loss": 1.0159,
      "step": 482
    },
    {
      "epoch": 0.943359375,
      "grad_norm": 0.3985369025141676,
      "learning_rate": 2.3116075190523736e-05,
      "loss": 1.09,
      "step": 483
    },
    {
      "epoch": 0.9453125,
      "grad_norm": 0.3935123859622257,
      "learning_rate": 2.305298568437749e-05,
      "loss": 0.9963,
      "step": 484
    },
    {
      "epoch": 0.947265625,
      "grad_norm": 0.4196014578008531,
      "learning_rate": 2.2989865058635452e-05,
      "loss": 1.0499,
      "step": 485
    },
    {
      "epoch": 0.94921875,
      "grad_norm": 0.419476500729373,
      "learning_rate": 2.2926713956696745e-05,
      "loss": 1.0371,
      "step": 486
    },
    {
      "epoch": 0.951171875,
      "grad_norm": 0.3808077428531366,
      "learning_rate": 2.2863533022271162e-05,
      "loss": 1.1248,
      "step": 487
    },
    {
      "epoch": 0.953125,
      "grad_norm": 0.3999093853366225,
      "learning_rate": 2.2800322899372586e-05,
      "loss": 1.064,
      "step": 488
    },
    {
      "epoch": 0.955078125,
      "grad_norm": 0.40587143499383244,
      "learning_rate": 2.2737084232312405e-05,
      "loss": 1.0637,
      "step": 489
    },
    {
      "epoch": 0.95703125,
      "grad_norm": 0.3789458557177568,
      "learning_rate": 2.267381766569297e-05,
      "loss": 0.9901,
      "step": 490
    },
    {
      "epoch": 0.958984375,
      "grad_norm": 0.3888268213746482,
      "learning_rate": 2.261052384440104e-05,
      "loss": 1.1481,
      "step": 491
    },
    {
      "epoch": 0.9609375,
      "grad_norm": 0.3560941746806575,
      "learning_rate": 2.254720341360114e-05,
      "loss": 1.0011,
      "step": 492
    },
    {
      "epoch": 0.962890625,
      "grad_norm": 0.4117369944130386,
      "learning_rate": 2.2483857018729066e-05,
      "loss": 1.0988,
      "step": 493
    },
    {
      "epoch": 0.96484375,
      "grad_norm": 0.3603669115916744,
      "learning_rate": 2.2420485305485264e-05,
      "loss": 1.0564,
      "step": 494
    },
    {
      "epoch": 0.966796875,
      "grad_norm": 0.45357516371473544,
      "learning_rate": 2.2357088919828243e-05,
      "loss": 1.1119,
      "step": 495
    },
    {
      "epoch": 0.96875,
      "grad_norm": 0.37884120057564985,
      "learning_rate": 2.2293668507968015e-05,
      "loss": 1.0883,
      "step": 496
    },
    {
      "epoch": 0.970703125,
      "grad_norm": 0.8383895359995993,
      "learning_rate": 2.2230224716359482e-05,
      "loss": 1.0815,
      "step": 497
    },
    {
      "epoch": 0.97265625,
      "grad_norm": 0.38866465119590105,
      "learning_rate": 2.2166758191695866e-05,
      "loss": 1.0174,
      "step": 498
    },
    {
      "epoch": 0.974609375,
      "grad_norm": 0.5709670798963341,
      "learning_rate": 2.210326958090212e-05,
      "loss": 1.0009,
      "step": 499
    },
    {
      "epoch": 0.9765625,
      "grad_norm": 0.3660396139993819,
      "learning_rate": 2.203975953112831e-05,
      "loss": 1.095,
      "step": 500
    },
    {
      "epoch": 0.978515625,
      "grad_norm": 0.3674603706471189,
      "learning_rate": 2.1976228689743044e-05,
      "loss": 0.9867,
      "step": 501
    },
    {
      "epoch": 0.98046875,
      "grad_norm": 0.9419848479362365,
      "learning_rate": 2.1912677704326847e-05,
      "loss": 1.2754,
      "step": 502
    },
    {
      "epoch": 0.982421875,
      "grad_norm": 0.3969899221243403,
      "learning_rate": 2.18491072226656e-05,
      "loss": 1.0077,
      "step": 503
    },
    {
      "epoch": 0.984375,
      "grad_norm": 0.4124566542707438,
      "learning_rate": 2.1785517892743887e-05,
      "loss": 1.0525,
      "step": 504
    },
    {
      "epoch": 0.986328125,
      "grad_norm": 0.41362237633561144,
      "learning_rate": 2.1721910362738438e-05,
      "loss": 1.0197,
      "step": 505
    },
    {
      "epoch": 0.98828125,
      "grad_norm": 0.4476968790164685,
      "learning_rate": 2.165828528101148e-05,
      "loss": 0.9919,
      "step": 506
    },
    {
      "epoch": 0.990234375,
      "grad_norm": 0.6290964144760007,
      "learning_rate": 2.1594643296104157e-05,
      "loss": 1.0917,
      "step": 507
    },
    {
      "epoch": 0.9921875,
      "grad_norm": 0.3973126449794871,
      "learning_rate": 2.153098505672992e-05,
      "loss": 1.1005,
      "step": 508
    },
    {
      "epoch": 0.994140625,
      "grad_norm": 0.4323540168560289,
      "learning_rate": 2.1467311211767873e-05,
      "loss": 1.0063,
      "step": 509
    },
    {
      "epoch": 0.99609375,
      "grad_norm": 0.5809974059109054,
      "learning_rate": 2.140362241025623e-05,
      "loss": 1.145,
      "step": 510
    },
    {
      "epoch": 0.998046875,
      "grad_norm": 0.38472241580582794,
      "learning_rate": 2.1339919301385636e-05,
      "loss": 0.9965,
      "step": 511
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.4053721417966819,
      "learning_rate": 2.1276202534492566e-05,
      "loss": 1.0342,
      "step": 512
    },
    {
      "epoch": 1.001953125,
      "grad_norm": 0.44179500630354,
      "learning_rate": 2.1212472759052747e-05,
      "loss": 1.0091,
      "step": 513
    },
    {
      "epoch": 1.001953125,
      "grad_norm": 0.446142731904768,
      "learning_rate": 2.114873062467447e-05,
      "loss": 1.0376,
      "step": 514
    },
    {
      "epoch": 1.00390625,
      "grad_norm": 0.4490270046445201,
      "learning_rate": 2.1084976781092008e-05,
      "loss": 0.9437,
      "step": 515
    },
    {
      "epoch": 1.005859375,
      "grad_norm": 0.37465877776003104,
      "learning_rate": 2.102121187815901e-05,
      "loss": 0.9196,
      "step": 516
    },
    {
      "epoch": 1.0078125,
      "grad_norm": 0.34991615767421413,
      "learning_rate": 2.0957436565841843e-05,
      "loss": 0.9653,
      "step": 517
    },
    {
      "epoch": 1.009765625,
      "grad_norm": 0.39278293144349274,
      "learning_rate": 2.089365149421296e-05,
      "loss": 0.9918,
      "step": 518
    },
    {
      "epoch": 1.01171875,
      "grad_norm": 0.39892362114749175,
      "learning_rate": 2.0829857313444313e-05,
      "loss": 0.9659,
      "step": 519
    },
    {
      "epoch": 1.013671875,
      "grad_norm": 0.4102189057068763,
      "learning_rate": 2.076605467380071e-05,
      "loss": 0.9389,
      "step": 520
    },
    {
      "epoch": 1.015625,
      "grad_norm": 0.5558850845738904,
      "learning_rate": 2.0702244225633165e-05,
      "loss": 0.9213,
      "step": 521
    },
    {
      "epoch": 1.017578125,
      "grad_norm": 0.35399991541630493,
      "learning_rate": 2.063842661937229e-05,
      "loss": 0.9891,
      "step": 522
    },
    {
      "epoch": 1.01953125,
      "grad_norm": 0.39368262356876543,
      "learning_rate": 2.0574602505521667e-05,
      "loss": 0.9796,
      "step": 523
    },
    {
      "epoch": 1.021484375,
      "grad_norm": 0.34593091047515195,
      "learning_rate": 2.0510772534651205e-05,
      "loss": 0.9461,
      "step": 524
    },
    {
      "epoch": 1.0234375,
      "grad_norm": 0.35799560406545033,
      "learning_rate": 2.0446937357390516e-05,
      "loss": 0.9741,
      "step": 525
    },
    {
      "epoch": 1.025390625,
      "grad_norm": 0.41970672443083423,
      "learning_rate": 2.0383097624422287e-05,
      "loss": 0.9525,
      "step": 526
    },
    {
      "epoch": 1.02734375,
      "grad_norm": 0.4210263211317942,
      "learning_rate": 2.0319253986475633e-05,
      "loss": 0.9768,
      "step": 527
    },
    {
      "epoch": 1.029296875,
      "grad_norm": 0.4331623292323512,
      "learning_rate": 2.025540709431948e-05,
      "loss": 1.0205,
      "step": 528
    },
    {
      "epoch": 1.03125,
      "grad_norm": 0.3411476969036497,
      "learning_rate": 2.019155759875592e-05,
      "loss": 0.9341,
      "step": 529
    },
    {
      "epoch": 1.033203125,
      "grad_norm": 0.39467707038238026,
      "learning_rate": 2.0127706150613585e-05,
      "loss": 1.0076,
      "step": 530
    },
    {
      "epoch": 1.03515625,
      "grad_norm": 0.43562648997243625,
      "learning_rate": 2.0063853400741012e-05,
      "loss": 1.073,
      "step": 531
    },
    {
      "epoch": 1.037109375,
      "grad_norm": 0.44146731188131544,
      "learning_rate": 2e-05,
      "loss": 0.9488,
      "step": 532
    },
    {
      "epoch": 1.0390625,
      "grad_norm": 0.34113317020048084,
      "learning_rate": 1.9936146599258998e-05,
      "loss": 0.9615,
      "step": 533
    },
    {
      "epoch": 1.041015625,
      "grad_norm": 0.36276395278267437,
      "learning_rate": 1.987229384938642e-05,
      "loss": 0.9248,
      "step": 534
    },
    {
      "epoch": 1.04296875,
      "grad_norm": 0.36685985855164943,
      "learning_rate": 1.9808442401244084e-05,
      "loss": 0.9773,
      "step": 535
    },
    {
      "epoch": 1.044921875,
      "grad_norm": 0.41120951936023337,
      "learning_rate": 1.974459290568053e-05,
      "loss": 0.974,
      "step": 536
    },
    {
      "epoch": 1.046875,
      "grad_norm": 0.547454870376216,
      "learning_rate": 1.9680746013524374e-05,
      "loss": 0.9904,
      "step": 537
    },
    {
      "epoch": 1.048828125,
      "grad_norm": 0.5704830553650788,
      "learning_rate": 1.961690237557772e-05,
      "loss": 0.9134,
      "step": 538
    },
    {
      "epoch": 1.05078125,
      "grad_norm": 0.4876054172249476,
      "learning_rate": 1.9553062642609494e-05,
      "loss": 0.851,
      "step": 539
    },
    {
      "epoch": 1.052734375,
      "grad_norm": 0.40414171319597475,
      "learning_rate": 1.9489227465348802e-05,
      "loss": 1.0105,
      "step": 540
    },
    {
      "epoch": 1.0546875,
      "grad_norm": 0.58489484045902,
      "learning_rate": 1.9425397494478343e-05,
      "loss": 1.0032,
      "step": 541
    },
    {
      "epoch": 1.056640625,
      "grad_norm": 0.40245552903959203,
      "learning_rate": 1.936157338062772e-05,
      "loss": 0.9665,
      "step": 542
    },
    {
      "epoch": 1.05859375,
      "grad_norm": 0.36668575383716223,
      "learning_rate": 1.929775577436684e-05,
      "loss": 0.9187,
      "step": 543
    },
    {
      "epoch": 1.060546875,
      "grad_norm": 0.38605829094015137,
      "learning_rate": 1.9233945326199295e-05,
      "loss": 1.0292,
      "step": 544
    },
    {
      "epoch": 1.0625,
      "grad_norm": 0.4775647034665463,
      "learning_rate": 1.9170142686555694e-05,
      "loss": 0.8809,
      "step": 545
    },
    {
      "epoch": 1.064453125,
      "grad_norm": 0.3982312435094138,
      "learning_rate": 1.9106348505787044e-05,
      "loss": 1.0963,
      "step": 546
    },
    {
      "epoch": 1.06640625,
      "grad_norm": 0.40475239615772096,
      "learning_rate": 1.9042563434158164e-05,
      "loss": 1.0112,
      "step": 547
    },
    {
      "epoch": 1.068359375,
      "grad_norm": 0.35250493099402647,
      "learning_rate": 1.8978788121840993e-05,
      "loss": 0.8947,
      "step": 548
    },
    {
      "epoch": 1.0703125,
      "grad_norm": 0.41833732128026946,
      "learning_rate": 1.891502321890799e-05,
      "loss": 0.9575,
      "step": 549
    },
    {
      "epoch": 1.072265625,
      "grad_norm": 0.36694950012682076,
      "learning_rate": 1.8851269375325536e-05,
      "loss": 0.9706,
      "step": 550
    },
    {
      "epoch": 1.07421875,
      "grad_norm": 0.3634658637816904,
      "learning_rate": 1.878752724094726e-05,
      "loss": 0.9765,
      "step": 551
    },
    {
      "epoch": 1.076171875,
      "grad_norm": 0.35609629242033847,
      "learning_rate": 1.872379746550743e-05,
      "loss": 0.9522,
      "step": 552
    },
    {
      "epoch": 1.078125,
      "grad_norm": 0.3704199063139149,
      "learning_rate": 1.866008069861437e-05,
      "loss": 0.8662,
      "step": 553
    },
    {
      "epoch": 1.080078125,
      "grad_norm": 0.3591219461529281,
      "learning_rate": 1.8596377589743777e-05,
      "loss": 0.9324,
      "step": 554
    },
    {
      "epoch": 1.08203125,
      "grad_norm": 0.3595129819476128,
      "learning_rate": 1.8532688788232137e-05,
      "loss": 0.9492,
      "step": 555
    },
    {
      "epoch": 1.083984375,
      "grad_norm": 0.37634761093957714,
      "learning_rate": 1.8469014943270087e-05,
      "loss": 0.9186,
      "step": 556
    },
    {
      "epoch": 1.0859375,
      "grad_norm": 0.3878745382586326,
      "learning_rate": 1.8405356703895846e-05,
      "loss": 0.9845,
      "step": 557
    },
    {
      "epoch": 1.087890625,
      "grad_norm": 0.3565021555066516,
      "learning_rate": 1.834171471898853e-05,
      "loss": 0.944,
      "step": 558
    },
    {
      "epoch": 1.08984375,
      "grad_norm": 0.39945966259249516,
      "learning_rate": 1.827808963726157e-05,
      "loss": 0.9869,
      "step": 559
    },
    {
      "epoch": 1.091796875,
      "grad_norm": 0.3727767974429755,
      "learning_rate": 1.8214482107256117e-05,
      "loss": 0.9672,
      "step": 560
    },
    {
      "epoch": 1.09375,
      "grad_norm": 0.3999255506256679,
      "learning_rate": 1.815089277733441e-05,
      "loss": 1.1567,
      "step": 561
    },
    {
      "epoch": 1.095703125,
      "grad_norm": 0.38544867502151725,
      "learning_rate": 1.8087322295673156e-05,
      "loss": 1.1011,
      "step": 562
    },
    {
      "epoch": 1.09765625,
      "grad_norm": 0.36795897916133996,
      "learning_rate": 1.8023771310256967e-05,
      "loss": 0.938,
      "step": 563
    },
    {
      "epoch": 1.099609375,
      "grad_norm": 0.4085728847422467,
      "learning_rate": 1.79602404688717e-05,
      "loss": 1.01,
      "step": 564
    },
    {
      "epoch": 1.1015625,
      "grad_norm": 0.40428701633688546,
      "learning_rate": 1.7896730419097885e-05,
      "loss": 0.946,
      "step": 565
    },
    {
      "epoch": 1.103515625,
      "grad_norm": 0.3420045109324436,
      "learning_rate": 1.7833241808304137e-05,
      "loss": 0.9262,
      "step": 566
    },
    {
      "epoch": 1.10546875,
      "grad_norm": 0.32930758084261924,
      "learning_rate": 1.776977528364053e-05,
      "loss": 0.9337,
      "step": 567
    },
    {
      "epoch": 1.107421875,
      "grad_norm": 0.3728151943644151,
      "learning_rate": 1.7706331492031995e-05,
      "loss": 0.9862,
      "step": 568
    },
    {
      "epoch": 1.109375,
      "grad_norm": 0.3762462901429302,
      "learning_rate": 1.7642911080171764e-05,
      "loss": 1.0121,
      "step": 569
    },
    {
      "epoch": 1.111328125,
      "grad_norm": 0.34419819756856457,
      "learning_rate": 1.7579514694514746e-05,
      "loss": 0.9927,
      "step": 570
    },
    {
      "epoch": 1.11328125,
      "grad_norm": 0.361939909137465,
      "learning_rate": 1.7516142981270937e-05,
      "loss": 0.874,
      "step": 571
    },
    {
      "epoch": 1.115234375,
      "grad_norm": 0.359466280587838,
      "learning_rate": 1.745279658639887e-05,
      "loss": 0.9454,
      "step": 572
    },
    {
      "epoch": 1.1171875,
      "grad_norm": 0.4084703758968915,
      "learning_rate": 1.7389476155598974e-05,
      "loss": 0.9931,
      "step": 573
    },
    {
      "epoch": 1.119140625,
      "grad_norm": 0.3611109937308965,
      "learning_rate": 1.7326182334307032e-05,
      "loss": 0.9086,
      "step": 574
    },
    {
      "epoch": 1.12109375,
      "grad_norm": 0.37915013032154726,
      "learning_rate": 1.72629157676876e-05,
      "loss": 0.9992,
      "step": 575
    },
    {
      "epoch": 1.123046875,
      "grad_norm": 0.35895076602312803,
      "learning_rate": 1.7199677100627427e-05,
      "loss": 0.9962,
      "step": 576
    },
    {
      "epoch": 1.125,
      "grad_norm": 0.6928146195783631,
      "learning_rate": 1.713646697772884e-05,
      "loss": 0.8686,
      "step": 577
    },
    {
      "epoch": 1.126953125,
      "grad_norm": 0.4230864523593487,
      "learning_rate": 1.7073286043303258e-05,
      "loss": 0.9291,
      "step": 578
    },
    {
      "epoch": 1.12890625,
      "grad_norm": 0.350061579294634,
      "learning_rate": 1.701013494136456e-05,
      "loss": 0.9807,
      "step": 579
    },
    {
      "epoch": 1.130859375,
      "grad_norm": 0.48894395053828343,
      "learning_rate": 1.6947014315622508e-05,
      "loss": 0.9647,
      "step": 580
    },
    {
      "epoch": 1.1328125,
      "grad_norm": 0.6090161694868175,
      "learning_rate": 1.6883924809476267e-05,
      "loss": 0.9872,
      "step": 581
    },
    {
      "epoch": 1.134765625,
      "grad_norm": 0.38210311737856834,
      "learning_rate": 1.6820867066007763e-05,
      "loss": 0.9853,
      "step": 582
    },
    {
      "epoch": 1.13671875,
      "grad_norm": 0.38910736625758363,
      "learning_rate": 1.675784172797515e-05,
      "loss": 0.9278,
      "step": 583
    },
    {
      "epoch": 1.138671875,
      "grad_norm": 0.4133384990460752,
      "learning_rate": 1.6694849437806305e-05,
      "loss": 0.9109,
      "step": 584
    },
    {
      "epoch": 1.140625,
      "grad_norm": 0.37174192036951464,
      "learning_rate": 1.6631890837592204e-05,
      "loss": 0.9225,
      "step": 585
    },
    {
      "epoch": 1.142578125,
      "grad_norm": 0.40779602399318077,
      "learning_rate": 1.6568966569080435e-05,
      "loss": 1.0785,
      "step": 586
    },
    {
      "epoch": 1.14453125,
      "grad_norm": 0.425396243032134,
      "learning_rate": 1.6506077273668642e-05,
      "loss": 0.9913,
      "step": 587
    },
    {
      "epoch": 1.146484375,
      "grad_norm": 0.38512740005640106,
      "learning_rate": 1.644322359239797e-05,
      "loss": 0.9523,
      "step": 588
    },
    {
      "epoch": 1.1484375,
      "grad_norm": 0.33542250662600315,
      "learning_rate": 1.6380406165946544e-05,
      "loss": 0.9098,
      "step": 589
    },
    {
      "epoch": 1.150390625,
      "grad_norm": 0.4061483073935809,
      "learning_rate": 1.631762563462295e-05,
      "loss": 0.9948,
      "step": 590
    },
    {
      "epoch": 1.15234375,
      "grad_norm": 0.4255247042563437,
      "learning_rate": 1.6254882638359682e-05,
      "loss": 0.9073,
      "step": 591
    },
    {
      "epoch": 1.154296875,
      "grad_norm": 0.44428536040876276,
      "learning_rate": 1.619217781670663e-05,
      "loss": 0.9582,
      "step": 592
    },
    {
      "epoch": 1.15625,
      "grad_norm": 0.35993895058380465,
      "learning_rate": 1.612951180882459e-05,
      "loss": 0.9996,
      "step": 593
    },
    {
      "epoch": 1.158203125,
      "grad_norm": 0.41747531582822545,
      "learning_rate": 1.6066885253478695e-05,
      "loss": 1.096,
      "step": 594
    },
    {
      "epoch": 1.16015625,
      "grad_norm": 0.3331419574398452,
      "learning_rate": 1.6004298789031946e-05,
      "loss": 0.9544,
      "step": 595
    },
    {
      "epoch": 1.162109375,
      "grad_norm": 0.4354105941115212,
      "learning_rate": 1.5941753053438667e-05,
      "loss": 1.2018,
      "step": 596
    },
    {
      "epoch": 1.1640625,
      "grad_norm": 0.4222492510948584,
      "learning_rate": 1.5879248684238063e-05,
      "loss": 1.0028,
      "step": 597
    },
    {
      "epoch": 1.166015625,
      "grad_norm": 0.5967454884042651,
      "learning_rate": 1.581678631854767e-05,
      "loss": 1.0171,
      "step": 598
    },
    {
      "epoch": 1.16796875,
      "grad_norm": 0.3639266018682401,
      "learning_rate": 1.5754366593056857e-05,
      "loss": 0.9567,
      "step": 599
    },
    {
      "epoch": 1.169921875,
      "grad_norm": 0.34817512478040874,
      "learning_rate": 1.5691990144020376e-05,
      "loss": 0.9271,
      "step": 600
    },
    {
      "epoch": 1.171875,
      "grad_norm": 0.3853831454455573,
      "learning_rate": 1.562965760725185e-05,
      "loss": 0.8966,
      "step": 601
    },
    {
      "epoch": 1.173828125,
      "grad_norm": 0.410616258262907,
      "learning_rate": 1.5567369618117283e-05,
      "loss": 0.9331,
      "step": 602
    },
    {
      "epoch": 1.17578125,
      "grad_norm": 0.36657145792911333,
      "learning_rate": 1.5505126811528626e-05,
      "loss": 0.9319,
      "step": 603
    },
    {
      "epoch": 1.177734375,
      "grad_norm": 0.3807613916320253,
      "learning_rate": 1.5442929821937255e-05,
      "loss": 0.9849,
      "step": 604
    },
    {
      "epoch": 1.1796875,
      "grad_norm": 0.44687260138416424,
      "learning_rate": 1.5380779283327513e-05,
      "loss": 1.0827,
      "step": 605
    },
    {
      "epoch": 1.181640625,
      "grad_norm": 0.8043050725031463,
      "learning_rate": 1.5318675829210305e-05,
      "loss": 1.0632,
      "step": 606
    },
    {
      "epoch": 1.18359375,
      "grad_norm": 0.408384191928922,
      "learning_rate": 1.5256620092616544e-05,
      "loss": 1.0017,
      "step": 607
    },
    {
      "epoch": 1.185546875,
      "grad_norm": 0.4038587951285904,
      "learning_rate": 1.5194612706090786e-05,
      "loss": 0.9543,
      "step": 608
    },
    {
      "epoch": 1.1875,
      "grad_norm": 0.4011706051447064,
      "learning_rate": 1.5132654301684742e-05,
      "loss": 0.9959,
      "step": 609
    },
    {
      "epoch": 1.189453125,
      "grad_norm": 0.3852616434099168,
      "learning_rate": 1.5070745510950822e-05,
      "loss": 0.9561,
      "step": 610
    },
    {
      "epoch": 1.19140625,
      "grad_norm": 0.3809659064896749,
      "learning_rate": 1.5008886964935725e-05,
      "loss": 0.9787,
      "step": 611
    },
    {
      "epoch": 1.193359375,
      "grad_norm": 0.6528648150293458,
      "learning_rate": 1.4947079294174015e-05,
      "loss": 0.9937,
      "step": 612
    },
    {
      "epoch": 1.1953125,
      "grad_norm": 0.3775910426865845,
      "learning_rate": 1.4885323128681646e-05,
      "loss": 1.0041,
      "step": 613
    },
    {
      "epoch": 1.197265625,
      "grad_norm": 0.42775062168828504,
      "learning_rate": 1.4823619097949584e-05,
      "loss": 0.928,
      "step": 614
    },
    {
      "epoch": 1.19921875,
      "grad_norm": 0.3624221358959922,
      "learning_rate": 1.4761967830937392e-05,
      "loss": 0.905,
      "step": 615
    },
    {
      "epoch": 1.201171875,
      "grad_norm": 0.3771863313093266,
      "learning_rate": 1.4700369956066771e-05,
      "loss": 0.962,
      "step": 616
    },
    {
      "epoch": 1.203125,
      "grad_norm": 0.36974303903278527,
      "learning_rate": 1.4638826101215207e-05,
      "loss": 0.9689,
      "step": 617
    },
    {
      "epoch": 1.205078125,
      "grad_norm": 0.48031948584293677,
      "learning_rate": 1.4577336893709562e-05,
      "loss": 0.9551,
      "step": 618
    },
    {
      "epoch": 1.20703125,
      "grad_norm": 0.3596478876907126,
      "learning_rate": 1.451590296031964e-05,
      "loss": 1.0164,
      "step": 619
    },
    {
      "epoch": 1.208984375,
      "grad_norm": 0.37160113505489284,
      "learning_rate": 1.445452492725184e-05,
      "loss": 0.9918,
      "step": 620
    },
    {
      "epoch": 1.2109375,
      "grad_norm": 0.346400221979658,
      "learning_rate": 1.4393203420142778e-05,
      "loss": 0.9464,
      "step": 621
    },
    {
      "epoch": 1.212890625,
      "grad_norm": 0.35678900871020625,
      "learning_rate": 1.433193906405286e-05,
      "loss": 0.9269,
      "step": 622
    },
    {
      "epoch": 1.21484375,
      "grad_norm": 0.34241910026079136,
      "learning_rate": 1.4270732483459955e-05,
      "loss": 0.9588,
      "step": 623
    },
    {
      "epoch": 1.216796875,
      "grad_norm": 0.36833556801989115,
      "learning_rate": 1.420958430225303e-05,
      "loss": 1.0167,
      "step": 624
    },
    {
      "epoch": 1.21875,
      "grad_norm": 0.3430087997819356,
      "learning_rate": 1.4148495143725755e-05,
      "loss": 0.9506,
      "step": 625
    },
    {
      "epoch": 1.220703125,
      "grad_norm": 0.3587343448087659,
      "learning_rate": 1.4087465630570182e-05,
      "loss": 1.0706,
      "step": 626
    },
    {
      "epoch": 1.22265625,
      "grad_norm": 0.399468912947346,
      "learning_rate": 1.40264963848704e-05,
      "loss": 0.9162,
      "step": 627
    },
    {
      "epoch": 1.224609375,
      "grad_norm": 0.4188953495632537,
      "learning_rate": 1.3965588028096155e-05,
      "loss": 1.0427,
      "step": 628
    },
    {
      "epoch": 1.2265625,
      "grad_norm": 0.38249003229414436,
      "learning_rate": 1.3904741181096562e-05,
      "loss": 1.02,
      "step": 629
    },
    {
      "epoch": 1.228515625,
      "grad_norm": 0.3747562479454611,
      "learning_rate": 1.3843956464093756e-05,
      "loss": 0.9854,
      "step": 630
    },
    {
      "epoch": 1.23046875,
      "grad_norm": 0.39596682714642867,
      "learning_rate": 1.3783234496676564e-05,
      "loss": 0.9377,
      "step": 631
    },
    {
      "epoch": 1.232421875,
      "grad_norm": 0.37559710830126036,
      "learning_rate": 1.3722575897794181e-05,
      "loss": 1.0009,
      "step": 632
    },
    {
      "epoch": 1.234375,
      "grad_norm": 0.3602674698772576,
      "learning_rate": 1.366198128574992e-05,
      "loss": 1.0494,
      "step": 633
    },
    {
      "epoch": 1.236328125,
      "grad_norm": 0.35745878955476446,
      "learning_rate": 1.3601451278194823e-05,
      "loss": 1.0117,
      "step": 634
    },
    {
      "epoch": 1.23828125,
      "grad_norm": 0.43974743944299727,
      "learning_rate": 1.3540986492121424e-05,
      "loss": 0.9327,
      "step": 635
    },
    {
      "epoch": 1.240234375,
      "grad_norm": 0.3816381781834988,
      "learning_rate": 1.3480587543857433e-05,
      "loss": 0.9039,
      "step": 636
    },
    {
      "epoch": 1.2421875,
      "grad_norm": 0.3428616721943136,
      "learning_rate": 1.3420255049059492e-05,
      "loss": 0.9964,
      "step": 637
    },
    {
      "epoch": 1.244140625,
      "grad_norm": 0.40172160104662225,
      "learning_rate": 1.3359989622706838e-05,
      "loss": 0.9925,
      "step": 638
    },
    {
      "epoch": 1.24609375,
      "grad_norm": 0.3739741022796946,
      "learning_rate": 1.3299791879095084e-05,
      "loss": 0.949,
      "step": 639
    },
    {
      "epoch": 1.248046875,
      "grad_norm": 0.3863901644365365,
      "learning_rate": 1.3239662431829949e-05,
      "loss": 1.0132,
      "step": 640
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.4706045534030307,
      "learning_rate": 1.317960189382098e-05,
      "loss": 0.983,
      "step": 641
    },
    {
      "epoch": 1.251953125,
      "grad_norm": 0.4351589525257509,
      "learning_rate": 1.3119610877275326e-05,
      "loss": 0.9565,
      "step": 642
    },
    {
      "epoch": 1.25390625,
      "grad_norm": 0.378547110136832,
      "learning_rate": 1.3059689993691503e-05,
      "loss": 0.9055,
      "step": 643
    },
    {
      "epoch": 1.255859375,
      "grad_norm": 0.37731581451077806,
      "learning_rate": 1.2999839853853132e-05,
      "loss": 1.0063,
      "step": 644
    },
    {
      "epoch": 1.2578125,
      "grad_norm": 0.47116357786388924,
      "learning_rate": 1.2940061067822738e-05,
      "loss": 0.9509,
      "step": 645
    },
    {
      "epoch": 1.259765625,
      "grad_norm": 0.358578648154698,
      "learning_rate": 1.2880354244935539e-05,
      "loss": 1.0252,
      "step": 646
    },
    {
      "epoch": 1.26171875,
      "grad_norm": 0.399649490009225,
      "learning_rate": 1.2820719993793192e-05,
      "loss": 1.0575,
      "step": 647
    },
    {
      "epoch": 1.263671875,
      "grad_norm": 0.34667184960412123,
      "learning_rate": 1.276115892225764e-05,
      "loss": 1.0346,
      "step": 648
    },
    {
      "epoch": 1.265625,
      "grad_norm": 0.3855021796248961,
      "learning_rate": 1.2701671637444898e-05,
      "loss": 1.065,
      "step": 649
    },
    {
      "epoch": 1.267578125,
      "grad_norm": 0.35585972324157916,
      "learning_rate": 1.2642258745718836e-05,
      "loss": 0.9794,
      "step": 650
    },
    {
      "epoch": 1.26953125,
      "grad_norm": 0.3710316437527253,
      "learning_rate": 1.2582920852685038e-05,
      "loss": 0.899,
      "step": 651
    },
    {
      "epoch": 1.271484375,
      "grad_norm": 0.4822855478874204,
      "learning_rate": 1.2523658563184626e-05,
      "loss": 0.9789,
      "step": 652
    },
    {
      "epoch": 1.2734375,
      "grad_norm": 0.3433031737220971,
      "learning_rate": 1.2464472481288058e-05,
      "loss": 1.052,
      "step": 653
    },
    {
      "epoch": 1.275390625,
      "grad_norm": 0.3577526653316302,
      "learning_rate": 1.2405363210289006e-05,
      "loss": 0.9669,
      "step": 654
    },
    {
      "epoch": 1.27734375,
      "grad_norm": 0.3495929504958208,
      "learning_rate": 1.2346331352698206e-05,
      "loss": 1.014,
      "step": 655
    },
    {
      "epoch": 1.279296875,
      "grad_norm": 0.3915135488607845,
      "learning_rate": 1.2287377510237293e-05,
      "loss": 0.9608,
      "step": 656
    },
    {
      "epoch": 1.28125,
      "grad_norm": 0.35515321624360285,
      "learning_rate": 1.222850228383267e-05,
      "loss": 0.9398,
      "step": 657
    },
    {
      "epoch": 1.283203125,
      "grad_norm": 0.3737209255071266,
      "learning_rate": 1.2169706273609422e-05,
      "loss": 0.9554,
      "step": 658
    },
    {
      "epoch": 1.28515625,
      "grad_norm": 0.33848697946301126,
      "learning_rate": 1.2110990078885158e-05,
      "loss": 0.8591,
      "step": 659
    },
    {
      "epoch": 1.287109375,
      "grad_norm": 0.46452694835714037,
      "learning_rate": 1.2052354298163898e-05,
      "loss": 0.9381,
      "step": 660
    },
    {
      "epoch": 1.2890625,
      "grad_norm": 0.3703189613266902,
      "learning_rate": 1.199379952913001e-05,
      "loss": 1.0022,
      "step": 661
    },
    {
      "epoch": 1.291015625,
      "grad_norm": 0.38909547645130305,
      "learning_rate": 1.1935326368642095e-05,
      "loss": 0.9006,
      "step": 662
    },
    {
      "epoch": 1.29296875,
      "grad_norm": 0.4545249467882348,
      "learning_rate": 1.1876935412726882e-05,
      "loss": 1.0168,
      "step": 663
    },
    {
      "epoch": 1.294921875,
      "grad_norm": 0.4249249523099954,
      "learning_rate": 1.1818627256573203e-05,
      "loss": 0.9715,
      "step": 664
    },
    {
      "epoch": 1.296875,
      "grad_norm": 0.39567387420683053,
      "learning_rate": 1.1760402494525889e-05,
      "loss": 0.9387,
      "step": 665
    },
    {
      "epoch": 1.298828125,
      "grad_norm": 0.38001946826349847,
      "learning_rate": 1.1702261720079701e-05,
      "loss": 1.022,
      "step": 666
    },
    {
      "epoch": 1.30078125,
      "grad_norm": 0.3982258638160227,
      "learning_rate": 1.1644205525873334e-05,
      "loss": 1.0828,
      "step": 667
    },
    {
      "epoch": 1.302734375,
      "grad_norm": 0.4403809407388327,
      "learning_rate": 1.1586234503683318e-05,
      "loss": 1.0013,
      "step": 668
    },
    {
      "epoch": 1.3046875,
      "grad_norm": 0.401181571463019,
      "learning_rate": 1.1528349244418018e-05,
      "loss": 0.9632,
      "step": 669
    },
    {
      "epoch": 1.306640625,
      "grad_norm": 0.3526813740920086,
      "learning_rate": 1.1470550338111605e-05,
      "loss": 0.8926,
      "step": 670
    },
    {
      "epoch": 1.30859375,
      "grad_norm": 0.3671467469487214,
      "learning_rate": 1.141283837391804e-05,
      "loss": 0.985,
      "step": 671
    },
    {
      "epoch": 1.310546875,
      "grad_norm": 0.3518561693775614,
      "learning_rate": 1.135521394010506e-05,
      "loss": 0.9088,
      "step": 672
    },
    {
      "epoch": 1.3125,
      "grad_norm": 0.45986260985481126,
      "learning_rate": 1.12976776240482e-05,
      "loss": 1.0078,
      "step": 673
    },
    {
      "epoch": 1.314453125,
      "grad_norm": 0.3142685458435685,
      "learning_rate": 1.1240230012224793e-05,
      "loss": 0.9212,
      "step": 674
    },
    {
      "epoch": 1.31640625,
      "grad_norm": 0.36375897949504293,
      "learning_rate": 1.1182871690207992e-05,
      "loss": 0.9803,
      "step": 675
    },
    {
      "epoch": 1.318359375,
      "grad_norm": 0.41209305654187706,
      "learning_rate": 1.1125603242660805e-05,
      "loss": 0.9444,
      "step": 676
    },
    {
      "epoch": 1.3203125,
      "grad_norm": 0.3214000338736702,
      "learning_rate": 1.106842525333014e-05,
      "loss": 0.9534,
      "step": 677
    },
    {
      "epoch": 1.322265625,
      "grad_norm": 0.35318281920874656,
      "learning_rate": 1.101133830504085e-05,
      "loss": 0.9632,
      "step": 678
    },
    {
      "epoch": 1.32421875,
      "grad_norm": 0.37878097687262124,
      "learning_rate": 1.0954342979689763e-05,
      "loss": 1.0109,
      "step": 679
    },
    {
      "epoch": 1.326171875,
      "grad_norm": 0.367073940535207,
      "learning_rate": 1.0897439858239832e-05,
      "loss": 0.9491,
      "step": 680
    },
    {
      "epoch": 1.328125,
      "grad_norm": 0.3381887531812055,
      "learning_rate": 1.0840629520714108e-05,
      "loss": 0.9328,
      "step": 681
    },
    {
      "epoch": 1.330078125,
      "grad_norm": 0.3101804754722931,
      "learning_rate": 1.0783912546189904e-05,
      "loss": 0.9204,
      "step": 682
    },
    {
      "epoch": 1.33203125,
      "grad_norm": 0.40170172498897927,
      "learning_rate": 1.0727289512792884e-05,
      "loss": 1.0038,
      "step": 683
    },
    {
      "epoch": 1.333984375,
      "grad_norm": 0.35337666164492343,
      "learning_rate": 1.0670760997691118e-05,
      "loss": 0.9408,
      "step": 684
    },
    {
      "epoch": 1.3359375,
      "grad_norm": 0.3903287148433341,
      "learning_rate": 1.061432757708926e-05,
      "loss": 0.939,
      "step": 685
    },
    {
      "epoch": 1.337890625,
      "grad_norm": 0.44691174956650226,
      "learning_rate": 1.0557989826222652e-05,
      "loss": 1.0306,
      "step": 686
    },
    {
      "epoch": 1.33984375,
      "grad_norm": 0.3906780223611621,
      "learning_rate": 1.0501748319351438e-05,
      "loss": 0.9426,
      "step": 687
    },
    {
      "epoch": 1.341796875,
      "grad_norm": 0.5748081954728778,
      "learning_rate": 1.044560362975474e-05,
      "loss": 1.1097,
      "step": 688
    },
    {
      "epoch": 1.34375,
      "grad_norm": 0.34913594643718227,
      "learning_rate": 1.038955632972483e-05,
      "loss": 0.9763,
      "step": 689
    },
    {
      "epoch": 1.345703125,
      "grad_norm": 0.6410459781843788,
      "learning_rate": 1.0333606990561229e-05,
      "loss": 1.0008,
      "step": 690
    },
    {
      "epoch": 1.34765625,
      "grad_norm": 0.3668964116256979,
      "learning_rate": 1.0277756182564944e-05,
      "loss": 0.9721,
      "step": 691
    },
    {
      "epoch": 1.349609375,
      "grad_norm": 0.3975419995528479,
      "learning_rate": 1.0222004475032667e-05,
      "loss": 1.0274,
      "step": 692
    },
    {
      "epoch": 1.3515625,
      "grad_norm": 0.38154000085398126,
      "learning_rate": 1.016635243625089e-05,
      "loss": 0.9495,
      "step": 693
    },
    {
      "epoch": 1.353515625,
      "grad_norm": 0.3844134294953614,
      "learning_rate": 1.0110800633490191e-05,
      "loss": 0.8829,
      "step": 694
    },
    {
      "epoch": 1.35546875,
      "grad_norm": 0.39215706974188513,
      "learning_rate": 1.0055349632999452e-05,
      "loss": 0.9935,
      "step": 695
    },
    {
      "epoch": 1.357421875,
      "grad_norm": 0.3788537180880118,
      "learning_rate": 1.0000000000000006e-05,
      "loss": 1.0289,
      "step": 696
    },
    {
      "epoch": 1.359375,
      "grad_norm": 0.33728979789374863,
      "learning_rate": 9.944752298679955e-06,
      "loss": 0.9736,
      "step": 697
    },
    {
      "epoch": 1.361328125,
      "grad_norm": 0.3509226536442889,
      "learning_rate": 9.889607092188428e-06,
      "loss": 0.9335,
      "step": 698
    },
    {
      "epoch": 1.36328125,
      "grad_norm": 0.3796758040595075,
      "learning_rate": 9.834564942629747e-06,
      "loss": 1.1153,
      "step": 699
    },
    {
      "epoch": 1.365234375,
      "grad_norm": 0.39386927498826957,
      "learning_rate": 9.77962641105779e-06,
      "loss": 0.9694,
      "step": 700
    },
    {
      "epoch": 1.3671875,
      "grad_norm": 0.38556852083696624,
      "learning_rate": 9.724792057470254e-06,
      "loss": 0.9725,
      "step": 701
    },
    {
      "epoch": 1.369140625,
      "grad_norm": 0.3852806743502684,
      "learning_rate": 9.670062440802895e-06,
      "loss": 0.8915,
      "step": 702
    },
    {
      "epoch": 1.37109375,
      "grad_norm": 0.3754981704696039,
      "learning_rate": 9.615438118923885e-06,
      "loss": 0.9795,
      "step": 703
    },
    {
      "epoch": 1.373046875,
      "grad_norm": 0.38519930255753826,
      "learning_rate": 9.560919648628133e-06,
      "loss": 0.7423,
      "step": 704
    },
    {
      "epoch": 1.375,
      "grad_norm": 0.3678480156445294,
      "learning_rate": 9.506507585631543e-06,
      "loss": 0.9625,
      "step": 705
    },
    {
      "epoch": 1.376953125,
      "grad_norm": 0.46825623680966244,
      "learning_rate": 9.452202484565416e-06,
      "loss": 0.9712,
      "step": 706
    },
    {
      "epoch": 1.37890625,
      "grad_norm": 0.40615557628969196,
      "learning_rate": 9.398004898970768e-06,
      "loss": 0.9375,
      "step": 707
    },
    {
      "epoch": 1.380859375,
      "grad_norm": 0.37193760769831974,
      "learning_rate": 9.343915381292689e-06,
      "loss": 0.9105,
      "step": 708
    },
    {
      "epoch": 1.3828125,
      "grad_norm": 0.35389181630380073,
      "learning_rate": 9.28993448287472e-06,
      "loss": 0.9551,
      "step": 709
    },
    {
      "epoch": 1.384765625,
      "grad_norm": 0.34654926842170286,
      "learning_rate": 9.23606275395322e-06,
      "loss": 1.0028,
      "step": 710
    },
    {
      "epoch": 1.38671875,
      "grad_norm": 0.33815647223994644,
      "learning_rate": 9.182300743651775e-06,
      "loss": 0.8881,
      "step": 711
    },
    {
      "epoch": 1.388671875,
      "grad_norm": 0.3941538419262175,
      "learning_rate": 9.12864899997558e-06,
      "loss": 0.9378,
      "step": 712
    },
    {
      "epoch": 1.390625,
      "grad_norm": 0.3609485819384754,
      "learning_rate": 9.07510806980587e-06,
      "loss": 0.9296,
      "step": 713
    },
    {
      "epoch": 1.392578125,
      "grad_norm": 0.3355616357239785,
      "learning_rate": 9.021678498894337e-06,
      "loss": 0.9502,
      "step": 714
    },
    {
      "epoch": 1.39453125,
      "grad_norm": 0.36657409109596417,
      "learning_rate": 8.968360831857572e-06,
      "loss": 0.8878,
      "step": 715
    },
    {
      "epoch": 1.396484375,
      "grad_norm": 0.34140611240627566,
      "learning_rate": 8.915155612171508e-06,
      "loss": 0.889,
      "step": 716
    },
    {
      "epoch": 1.3984375,
      "grad_norm": 0.3515167932682012,
      "learning_rate": 8.862063382165887e-06,
      "loss": 0.9671,
      "step": 717
    },
    {
      "epoch": 1.400390625,
      "grad_norm": 0.4049728482000477,
      "learning_rate": 8.80908468301872e-06,
      "loss": 1.0124,
      "step": 718
    },
    {
      "epoch": 1.40234375,
      "grad_norm": 0.37691212884914266,
      "learning_rate": 8.756220054750792e-06,
      "loss": 1.0017,
      "step": 719
    },
    {
      "epoch": 1.404296875,
      "grad_norm": 0.3417579870636361,
      "learning_rate": 8.703470036220132e-06,
      "loss": 0.9785,
      "step": 720
    },
    {
      "epoch": 1.40625,
      "grad_norm": 0.3793995910078198,
      "learning_rate": 8.65083516511654e-06,
      "loss": 0.8911,
      "step": 721
    },
    {
      "epoch": 1.408203125,
      "grad_norm": 0.39483705765810345,
      "learning_rate": 8.598315977956095e-06,
      "loss": 1.1062,
      "step": 722
    },
    {
      "epoch": 1.41015625,
      "grad_norm": 0.3721977004688327,
      "learning_rate": 8.545913010075695e-06,
      "loss": 0.9196,
      "step": 723
    },
    {
      "epoch": 1.412109375,
      "grad_norm": 0.3731612176360843,
      "learning_rate": 8.493626795627589e-06,
      "loss": 0.916,
      "step": 724
    },
    {
      "epoch": 1.4140625,
      "grad_norm": 0.34431704326817825,
      "learning_rate": 8.441457867573943e-06,
      "loss": 0.9619,
      "step": 725
    },
    {
      "epoch": 1.416015625,
      "grad_norm": 0.35430006429746574,
      "learning_rate": 8.389406757681403e-06,
      "loss": 0.8805,
      "step": 726
    },
    {
      "epoch": 1.41796875,
      "grad_norm": 0.41844830277198886,
      "learning_rate": 8.33747399651567e-06,
      "loss": 0.9841,
      "step": 727
    },
    {
      "epoch": 1.419921875,
      "grad_norm": 0.44066175458551077,
      "learning_rate": 8.285660113436104e-06,
      "loss": 0.9264,
      "step": 728
    },
    {
      "epoch": 1.421875,
      "grad_norm": 0.364606957035922,
      "learning_rate": 8.233965636590316e-06,
      "loss": 0.9524,
      "step": 729
    },
    {
      "epoch": 1.423828125,
      "grad_norm": 0.3687107482636316,
      "learning_rate": 8.182391092908796e-06,
      "loss": 0.9566,
      "step": 730
    },
    {
      "epoch": 1.42578125,
      "grad_norm": 0.36546146068159463,
      "learning_rate": 8.130937008099509e-06,
      "loss": 0.9953,
      "step": 731
    },
    {
      "epoch": 1.427734375,
      "grad_norm": 0.5718029668283694,
      "learning_rate": 8.079603906642604e-06,
      "loss": 1.0813,
      "step": 732
    },
    {
      "epoch": 1.4296875,
      "grad_norm": 0.3699733978166363,
      "learning_rate": 8.028392311785005e-06,
      "loss": 1.051,
      "step": 733
    },
    {
      "epoch": 1.431640625,
      "grad_norm": 0.3794408196537551,
      "learning_rate": 7.977302745535076e-06,
      "loss": 0.962,
      "step": 734
    },
    {
      "epoch": 1.43359375,
      "grad_norm": 0.37312317670980216,
      "learning_rate": 7.926335728657369e-06,
      "loss": 0.906,
      "step": 735
    },
    {
      "epoch": 1.435546875,
      "grad_norm": 0.3875766940986475,
      "learning_rate": 7.875491780667246e-06,
      "loss": 0.8935,
      "step": 736
    },
    {
      "epoch": 1.4375,
      "grad_norm": 0.4678258586681586,
      "learning_rate": 7.824771419825588e-06,
      "loss": 0.9714,
      "step": 737
    },
    {
      "epoch": 1.439453125,
      "grad_norm": 0.3889435532263294,
      "learning_rate": 7.774175163133568e-06,
      "loss": 0.9753,
      "step": 738
    },
    {
      "epoch": 1.44140625,
      "grad_norm": 0.38174992024546406,
      "learning_rate": 7.72370352632733e-06,
      "loss": 1.0371,
      "step": 739
    },
    {
      "epoch": 1.443359375,
      "grad_norm": 0.3929329137219644,
      "learning_rate": 7.673357023872725e-06,
      "loss": 1.0676,
      "step": 740
    },
    {
      "epoch": 1.4453125,
      "grad_norm": 0.37452210269342173,
      "learning_rate": 7.623136168960128e-06,
      "loss": 0.9165,
      "step": 741
    },
    {
      "epoch": 1.447265625,
      "grad_norm": 0.33086498134420034,
      "learning_rate": 7.573041473499143e-06,
      "loss": 0.8272,
      "step": 742
    },
    {
      "epoch": 1.44921875,
      "grad_norm": 0.3554442637209336,
      "learning_rate": 7.5230734481133985e-06,
      "loss": 0.9984,
      "step": 743
    },
    {
      "epoch": 1.451171875,
      "grad_norm": 0.34001703972425806,
      "learning_rate": 7.473232602135387e-06,
      "loss": 0.9616,
      "step": 744
    },
    {
      "epoch": 1.453125,
      "grad_norm": 0.3691991307110838,
      "learning_rate": 7.423519443601221e-06,
      "loss": 0.9775,
      "step": 745
    },
    {
      "epoch": 1.455078125,
      "grad_norm": 0.5155066793110128,
      "learning_rate": 7.373934479245457e-06,
      "loss": 0.9478,
      "step": 746
    },
    {
      "epoch": 1.45703125,
      "grad_norm": 0.37558189262490166,
      "learning_rate": 7.3244782144959826e-06,
      "loss": 0.9281,
      "step": 747
    },
    {
      "epoch": 1.458984375,
      "grad_norm": 0.3339730173329286,
      "learning_rate": 7.275151153468809e-06,
      "loss": 0.9177,
      "step": 748
    },
    {
      "epoch": 1.4609375,
      "grad_norm": 0.3347580421964363,
      "learning_rate": 7.225953798962933e-06,
      "loss": 0.9648,
      "step": 749
    },
    {
      "epoch": 1.462890625,
      "grad_norm": 0.3449124080760216,
      "learning_rate": 7.176886652455275e-06,
      "loss": 0.9614,
      "step": 750
    },
    {
      "epoch": 1.46484375,
      "grad_norm": 0.3304697539797901,
      "learning_rate": 7.1279502140954956e-06,
      "loss": 0.8518,
      "step": 751
    },
    {
      "epoch": 1.466796875,
      "grad_norm": 0.3536512330604111,
      "learning_rate": 7.079144982700909e-06,
      "loss": 1.0054,
      "step": 752
    },
    {
      "epoch": 1.46875,
      "grad_norm": 0.3454832950461163,
      "learning_rate": 7.03047145575146e-06,
      "loss": 1.0113,
      "step": 753
    },
    {
      "epoch": 1.470703125,
      "grad_norm": 0.3385697048920916,
      "learning_rate": 6.98193012938458e-06,
      "loss": 0.9532,
      "step": 754
    },
    {
      "epoch": 1.47265625,
      "grad_norm": 0.32561540449598936,
      "learning_rate": 6.933521498390141e-06,
      "loss": 0.9007,
      "step": 755
    },
    {
      "epoch": 1.474609375,
      "grad_norm": 0.33412754710587733,
      "learning_rate": 6.885246056205475e-06,
      "loss": 0.9348,
      "step": 756
    },
    {
      "epoch": 1.4765625,
      "grad_norm": 0.38261099176566454,
      "learning_rate": 6.83710429491025e-06,
      "loss": 0.9563,
      "step": 757
    },
    {
      "epoch": 1.478515625,
      "grad_norm": 0.3762099157849163,
      "learning_rate": 6.789096705221534e-06,
      "loss": 0.9444,
      "step": 758
    },
    {
      "epoch": 1.48046875,
      "grad_norm": 0.37699479460630525,
      "learning_rate": 6.741223776488748e-06,
      "loss": 0.9428,
      "step": 759
    },
    {
      "epoch": 1.482421875,
      "grad_norm": 0.3403641467287786,
      "learning_rate": 6.693485996688695e-06,
      "loss": 0.948,
      "step": 760
    },
    {
      "epoch": 1.484375,
      "grad_norm": 0.34165243631197845,
      "learning_rate": 6.6458838524205845e-06,
      "loss": 0.9809,
      "step": 761
    },
    {
      "epoch": 1.486328125,
      "grad_norm": 0.30705290128480056,
      "learning_rate": 6.598417828901064e-06,
      "loss": 0.8477,
      "step": 762
    },
    {
      "epoch": 1.48828125,
      "grad_norm": 0.4009203333596796,
      "learning_rate": 6.551088409959286e-06,
      "loss": 1.0243,
      "step": 763
    },
    {
      "epoch": 1.490234375,
      "grad_norm": 0.39474889196372004,
      "learning_rate": 6.503896078031961e-06,
      "loss": 0.9163,
      "step": 764
    },
    {
      "epoch": 1.4921875,
      "grad_norm": 0.4223027556435545,
      "learning_rate": 6.45684131415846e-06,
      "loss": 0.9923,
      "step": 765
    },
    {
      "epoch": 1.494140625,
      "grad_norm": 0.42701075773956493,
      "learning_rate": 6.409924597975889e-06,
      "loss": 0.9305,
      "step": 766
    },
    {
      "epoch": 1.49609375,
      "grad_norm": 0.3187861529505421,
      "learning_rate": 6.363146407714218e-06,
      "loss": 0.8849,
      "step": 767
    },
    {
      "epoch": 1.498046875,
      "grad_norm": 0.38922984189716714,
      "learning_rate": 6.316507220191395e-06,
      "loss": 0.9225,
      "step": 768
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.37676390533925286,
      "learning_rate": 6.270007510808489e-06,
      "loss": 0.9302,
      "step": 769
    },
    {
      "epoch": 1.501953125,
      "grad_norm": 0.3909810454840726,
      "learning_rate": 6.223647753544852e-06,
      "loss": 0.9326,
      "step": 770
    },
    {
      "epoch": 1.50390625,
      "grad_norm": 0.39037072614279755,
      "learning_rate": 6.177428420953271e-06,
      "loss": 1.0468,
      "step": 771
    },
    {
      "epoch": 1.505859375,
      "grad_norm": 0.3479509260011028,
      "learning_rate": 6.131349984155168e-06,
      "loss": 0.9802,
      "step": 772
    },
    {
      "epoch": 1.5078125,
      "grad_norm": 0.36044446837345395,
      "learning_rate": 6.0854129128357865e-06,
      "loss": 0.8788,
      "step": 773
    },
    {
      "epoch": 1.509765625,
      "grad_norm": 0.3963406354206991,
      "learning_rate": 6.039617675239408e-06,
      "loss": 1.0214,
      "step": 774
    },
    {
      "epoch": 1.51171875,
      "grad_norm": 0.323076597180957,
      "learning_rate": 5.993964738164581e-06,
      "loss": 0.9156,
      "step": 775
    },
    {
      "epoch": 1.513671875,
      "grad_norm": 0.36027921967078824,
      "learning_rate": 5.948454566959363e-06,
      "loss": 0.9673,
      "step": 776
    },
    {
      "epoch": 1.515625,
      "grad_norm": 0.40632355344666676,
      "learning_rate": 5.903087625516568e-06,
      "loss": 1.0218,
      "step": 777
    },
    {
      "epoch": 1.517578125,
      "grad_norm": 0.36886422171724675,
      "learning_rate": 5.857864376269051e-06,
      "loss": 0.9713,
      "step": 778
    },
    {
      "epoch": 1.51953125,
      "grad_norm": 0.34047449363141336,
      "learning_rate": 5.812785280184987e-06,
      "loss": 0.9897,
      "step": 779
    },
    {
      "epoch": 1.521484375,
      "grad_norm": 0.3677381676995354,
      "learning_rate": 5.76785079676317e-06,
      "loss": 0.9514,
      "step": 780
    },
    {
      "epoch": 1.5234375,
      "grad_norm": 0.34518523015006153,
      "learning_rate": 5.723061384028339e-06,
      "loss": 0.9355,
      "step": 781
    },
    {
      "epoch": 1.525390625,
      "grad_norm": 0.38782877502733815,
      "learning_rate": 5.678417498526501e-06,
      "loss": 0.9023,
      "step": 782
    },
    {
      "epoch": 1.52734375,
      "grad_norm": 0.3690231117458861,
      "learning_rate": 5.633919595320274e-06,
      "loss": 0.9779,
      "step": 783
    },
    {
      "epoch": 1.529296875,
      "grad_norm": 0.37690613650557625,
      "learning_rate": 5.5895681279842615e-06,
      "loss": 0.9721,
      "step": 784
    },
    {
      "epoch": 1.53125,
      "grad_norm": 0.3481749800424234,
      "learning_rate": 5.545363548600417e-06,
      "loss": 0.9055,
      "step": 785
    },
    {
      "epoch": 1.533203125,
      "grad_norm": 0.35445594195661845,
      "learning_rate": 5.501306307753442e-06,
      "loss": 1.0125,
      "step": 786
    },
    {
      "epoch": 1.53515625,
      "grad_norm": 0.33642034404228005,
      "learning_rate": 5.457396854526193e-06,
      "loss": 0.9464,
      "step": 787
    },
    {
      "epoch": 1.537109375,
      "grad_norm": 0.3640433443158337,
      "learning_rate": 5.413635636495103e-06,
      "loss": 1.011,
      "step": 788
    },
    {
      "epoch": 1.5390625,
      "grad_norm": 0.33618666315109463,
      "learning_rate": 5.370023099725609e-06,
      "loss": 0.8597,
      "step": 789
    },
    {
      "epoch": 1.541015625,
      "grad_norm": 0.36749374513850036,
      "learning_rate": 5.32655968876763e-06,
      "loss": 0.9858,
      "step": 790
    },
    {
      "epoch": 1.54296875,
      "grad_norm": 0.3880453291066791,
      "learning_rate": 5.28324584665101e-06,
      "loss": 0.9341,
      "step": 791
    },
    {
      "epoch": 1.544921875,
      "grad_norm": 0.35821804618375047,
      "learning_rate": 5.240082014881016e-06,
      "loss": 1.037,
      "step": 792
    },
    {
      "epoch": 1.546875,
      "grad_norm": 0.36665993295487526,
      "learning_rate": 5.197068633433835e-06,
      "loss": 1.0014,
      "step": 793
    },
    {
      "epoch": 1.548828125,
      "grad_norm": 0.3550548699585417,
      "learning_rate": 5.154206140752087e-06,
      "loss": 1.0134,
      "step": 794
    },
    {
      "epoch": 1.55078125,
      "grad_norm": 0.33158675091184703,
      "learning_rate": 5.111494973740359e-06,
      "loss": 0.948,
      "step": 795
    },
    {
      "epoch": 1.552734375,
      "grad_norm": 0.3399950347590982,
      "learning_rate": 5.068935567760746e-06,
      "loss": 0.9196,
      "step": 796
    },
    {
      "epoch": 1.5546875,
      "grad_norm": 0.31979105809261354,
      "learning_rate": 5.0265283566284265e-06,
      "loss": 0.9635,
      "step": 797
    },
    {
      "epoch": 1.556640625,
      "grad_norm": 0.3381243740156393,
      "learning_rate": 4.984273772607222e-06,
      "loss": 1.0639,
      "step": 798
    },
    {
      "epoch": 1.55859375,
      "grad_norm": 0.3397294220936685,
      "learning_rate": 4.942172246405204e-06,
      "loss": 0.9273,
      "step": 799
    },
    {
      "epoch": 1.560546875,
      "grad_norm": 0.31882547867178535,
      "learning_rate": 4.900224207170299e-06,
      "loss": 0.9297,
      "step": 800
    },
    {
      "epoch": 1.5625,
      "grad_norm": 0.35668461558856696,
      "learning_rate": 4.858430082485923e-06,
      "loss": 0.9548,
      "step": 801
    },
    {
      "epoch": 1.564453125,
      "grad_norm": 0.7367144273899422,
      "learning_rate": 4.8167902983665895e-06,
      "loss": 0.9501,
      "step": 802
    },
    {
      "epoch": 1.56640625,
      "grad_norm": 0.34638768137374404,
      "learning_rate": 4.775305279253635e-06,
      "loss": 0.9729,
      "step": 803
    },
    {
      "epoch": 1.568359375,
      "grad_norm": 0.5412994654989381,
      "learning_rate": 4.733975448010808e-06,
      "loss": 0.9202,
      "step": 804
    },
    {
      "epoch": 1.5703125,
      "grad_norm": 0.3304722151941945,
      "learning_rate": 4.692801225920018e-06,
      "loss": 0.9078,
      "step": 805
    },
    {
      "epoch": 1.572265625,
      "grad_norm": 0.35617977127829975,
      "learning_rate": 4.6517830326770465e-06,
      "loss": 0.9908,
      "step": 806
    },
    {
      "epoch": 1.57421875,
      "grad_norm": 0.3549693585436051,
      "learning_rate": 4.610921286387206e-06,
      "loss": 0.9802,
      "step": 807
    },
    {
      "epoch": 1.576171875,
      "grad_norm": 0.3170150608843284,
      "learning_rate": 4.570216403561141e-06,
      "loss": 0.9258,
      "step": 808
    },
    {
      "epoch": 1.578125,
      "grad_norm": 0.33286645409949284,
      "learning_rate": 4.529668799110572e-06,
      "loss": 0.9749,
      "step": 809
    },
    {
      "epoch": 1.580078125,
      "grad_norm": 0.33696830778752673,
      "learning_rate": 4.489278886344026e-06,
      "loss": 0.978,
      "step": 810
    },
    {
      "epoch": 1.58203125,
      "grad_norm": 0.36361281108701393,
      "learning_rate": 4.449047076962667e-06,
      "loss": 1.0201,
      "step": 811
    },
    {
      "epoch": 1.583984375,
      "grad_norm": 0.4057622791778849,
      "learning_rate": 4.408973781056101e-06,
      "loss": 0.9955,
      "step": 812
    },
    {
      "epoch": 1.5859375,
      "grad_norm": 0.3501850340995405,
      "learning_rate": 4.369059407098144e-06,
      "loss": 1.0435,
      "step": 813
    },
    {
      "epoch": 1.587890625,
      "grad_norm": 0.4062014736955811,
      "learning_rate": 4.329304361942717e-06,
      "loss": 1.0266,
      "step": 814
    },
    {
      "epoch": 1.58984375,
      "grad_norm": 0.38790766719298647,
      "learning_rate": 4.289709050819686e-06,
      "loss": 0.9973,
      "step": 815
    },
    {
      "epoch": 1.591796875,
      "grad_norm": 0.36417631869963496,
      "learning_rate": 4.250273877330691e-06,
      "loss": 0.9248,
      "step": 816
    },
    {
      "epoch": 1.59375,
      "grad_norm": 0.3615478167180576,
      "learning_rate": 4.210999243445078e-06,
      "loss": 0.8756,
      "step": 817
    },
    {
      "epoch": 1.595703125,
      "grad_norm": 0.36034880891002974,
      "learning_rate": 4.171885549495802e-06,
      "loss": 0.9262,
      "step": 818
    },
    {
      "epoch": 1.59765625,
      "grad_norm": 0.5624070786466386,
      "learning_rate": 4.132933194175299e-06,
      "loss": 1.0473,
      "step": 819
    },
    {
      "epoch": 1.599609375,
      "grad_norm": 0.32899804672895744,
      "learning_rate": 4.09414257453147e-06,
      "loss": 1.0036,
      "step": 820
    },
    {
      "epoch": 1.6015625,
      "grad_norm": 0.36745496029706165,
      "learning_rate": 4.055514085963626e-06,
      "loss": 1.023,
      "step": 821
    },
    {
      "epoch": 1.603515625,
      "grad_norm": 0.3685732843637604,
      "learning_rate": 4.0170481222184275e-06,
      "loss": 0.9776,
      "step": 822
    },
    {
      "epoch": 1.60546875,
      "grad_norm": 0.42396302210154263,
      "learning_rate": 3.978745075385901e-06,
      "loss": 1.0278,
      "step": 823
    },
    {
      "epoch": 1.607421875,
      "grad_norm": 0.415378306356566,
      "learning_rate": 3.940605335895451e-06,
      "loss": 1.0019,
      "step": 824
    },
    {
      "epoch": 1.609375,
      "grad_norm": 0.35054709129129163,
      "learning_rate": 3.902629292511833e-06,
      "loss": 1.0493,
      "step": 825
    },
    {
      "epoch": 1.611328125,
      "grad_norm": 0.37472276736217736,
      "learning_rate": 3.864817332331234e-06,
      "loss": 1.005,
      "step": 826
    },
    {
      "epoch": 1.61328125,
      "grad_norm": 0.337218801148979,
      "learning_rate": 3.827169840777329e-06,
      "loss": 0.9658,
      "step": 827
    },
    {
      "epoch": 1.615234375,
      "grad_norm": 0.3433098736021148,
      "learning_rate": 3.78968720159731e-06,
      "loss": 0.9709,
      "step": 828
    },
    {
      "epoch": 1.6171875,
      "grad_norm": 0.3315860623471969,
      "learning_rate": 3.752369796858013e-06,
      "loss": 0.9917,
      "step": 829
    },
    {
      "epoch": 1.619140625,
      "grad_norm": 0.3672941427985792,
      "learning_rate": 3.715218006942014e-06,
      "loss": 1.0749,
      "step": 830
    },
    {
      "epoch": 1.62109375,
      "grad_norm": 0.39465414039795116,
      "learning_rate": 3.6782322105437485e-06,
      "loss": 0.9324,
      "step": 831
    },
    {
      "epoch": 1.623046875,
      "grad_norm": 0.36209819062866505,
      "learning_rate": 3.641412784665648e-06,
      "loss": 1.0281,
      "step": 832
    },
    {
      "epoch": 1.625,
      "grad_norm": 0.3686114995168954,
      "learning_rate": 3.6047601046143067e-06,
      "loss": 0.8755,
      "step": 833
    },
    {
      "epoch": 1.626953125,
      "grad_norm": 0.33211664620835185,
      "learning_rate": 3.568274543996646e-06,
      "loss": 0.9919,
      "step": 834
    },
    {
      "epoch": 1.62890625,
      "grad_norm": 0.6420016250272645,
      "learning_rate": 3.531956474716112e-06,
      "loss": 0.9875,
      "step": 835
    },
    {
      "epoch": 1.630859375,
      "grad_norm": 0.34331434259424204,
      "learning_rate": 3.4958062669688843e-06,
      "loss": 0.963,
      "step": 836
    },
    {
      "epoch": 1.6328125,
      "grad_norm": 0.3842961637718067,
      "learning_rate": 3.4598242892401036e-06,
      "loss": 0.9728,
      "step": 837
    },
    {
      "epoch": 1.634765625,
      "grad_norm": 0.3913761839243788,
      "learning_rate": 3.4240109083001105e-06,
      "loss": 0.9672,
      "step": 838
    },
    {
      "epoch": 1.63671875,
      "grad_norm": 0.37089539683495437,
      "learning_rate": 3.3883664892007116e-06,
      "loss": 1.0419,
      "step": 839
    },
    {
      "epoch": 1.638671875,
      "grad_norm": 0.3544073274448587,
      "learning_rate": 3.3528913952714558e-06,
      "loss": 0.914,
      "step": 840
    },
    {
      "epoch": 1.640625,
      "grad_norm": 0.4858314718332949,
      "learning_rate": 3.3175859881159366e-06,
      "loss": 1.0508,
      "step": 841
    },
    {
      "epoch": 1.642578125,
      "grad_norm": 0.3528574764725793,
      "learning_rate": 3.2824506276080935e-06,
      "loss": 0.9296,
      "step": 842
    },
    {
      "epoch": 1.64453125,
      "grad_norm": 0.3282207252025308,
      "learning_rate": 3.2474856718885617e-06,
      "loss": 0.9588,
      "step": 843
    },
    {
      "epoch": 1.646484375,
      "grad_norm": 0.32780167281036593,
      "learning_rate": 3.212691477361001e-06,
      "loss": 0.9598,
      "step": 844
    },
    {
      "epoch": 1.6484375,
      "grad_norm": 0.3400905574028211,
      "learning_rate": 3.1780683986884854e-06,
      "loss": 0.8936,
      "step": 845
    },
    {
      "epoch": 1.650390625,
      "grad_norm": 0.3676258265986709,
      "learning_rate": 3.1436167887898673e-06,
      "loss": 1.0108,
      "step": 846
    },
    {
      "epoch": 1.65234375,
      "grad_norm": 0.36849264473138216,
      "learning_rate": 3.1093369988361945e-06,
      "loss": 1.0383,
      "step": 847
    },
    {
      "epoch": 1.654296875,
      "grad_norm": 0.39037402775860364,
      "learning_rate": 3.07522937824712e-06,
      "loss": 1.0594,
      "step": 848
    },
    {
      "epoch": 1.65625,
      "grad_norm": 0.3379744299009819,
      "learning_rate": 3.0412942746873496e-06,
      "loss": 0.939,
      "step": 849
    },
    {
      "epoch": 1.658203125,
      "grad_norm": 0.33153311729525337,
      "learning_rate": 3.007532034063094e-06,
      "loss": 0.9059,
      "step": 850
    },
    {
      "epoch": 1.66015625,
      "grad_norm": 0.3455087844328493,
      "learning_rate": 2.9739430005185423e-06,
      "loss": 0.9024,
      "step": 851
    },
    {
      "epoch": 1.662109375,
      "grad_norm": 0.33464725279433777,
      "learning_rate": 2.9405275164323522e-06,
      "loss": 1.0108,
      "step": 852
    },
    {
      "epoch": 1.6640625,
      "grad_norm": 0.3168080558994273,
      "learning_rate": 2.907285922414169e-06,
      "loss": 0.8989,
      "step": 853
    },
    {
      "epoch": 1.666015625,
      "grad_norm": 0.3904579046215014,
      "learning_rate": 2.874218557301134e-06,
      "loss": 1.0257,
      "step": 854
    },
    {
      "epoch": 1.66796875,
      "grad_norm": 0.3352509751343241,
      "learning_rate": 2.841325758154463e-06,
      "loss": 1.0504,
      "step": 855
    },
    {
      "epoch": 1.669921875,
      "grad_norm": 0.3592514342735571,
      "learning_rate": 2.808607860255981e-06,
      "loss": 0.9691,
      "step": 856
    },
    {
      "epoch": 1.671875,
      "grad_norm": 0.3267155984018539,
      "learning_rate": 2.776065197104705e-06,
      "loss": 0.937,
      "step": 857
    },
    {
      "epoch": 1.673828125,
      "grad_norm": 0.3399489260646595,
      "learning_rate": 2.7436981004134787e-06,
      "loss": 0.9498,
      "step": 858
    },
    {
      "epoch": 1.67578125,
      "grad_norm": 0.4369890889938006,
      "learning_rate": 2.7115069001055537e-06,
      "loss": 0.9906,
      "step": 859
    },
    {
      "epoch": 1.677734375,
      "grad_norm": 0.35875793467083805,
      "learning_rate": 2.679491924311226e-06,
      "loss": 1.0105,
      "step": 860
    },
    {
      "epoch": 1.6796875,
      "grad_norm": 0.33042544575832233,
      "learning_rate": 2.6476534993645376e-06,
      "loss": 0.9808,
      "step": 861
    },
    {
      "epoch": 1.681640625,
      "grad_norm": 0.3489192710172102,
      "learning_rate": 2.615991949799899e-06,
      "loss": 0.9476,
      "step": 862
    },
    {
      "epoch": 1.68359375,
      "grad_norm": 0.3807700126806633,
      "learning_rate": 2.584507598348787e-06,
      "loss": 0.9574,
      "step": 863
    },
    {
      "epoch": 1.685546875,
      "grad_norm": 0.36964219200316595,
      "learning_rate": 2.553200765936501e-06,
      "loss": 0.9024,
      "step": 864
    },
    {
      "epoch": 1.6875,
      "grad_norm": 0.3556627106992668,
      "learning_rate": 2.5220717716788378e-06,
      "loss": 0.8687,
      "step": 865
    },
    {
      "epoch": 1.689453125,
      "grad_norm": 0.3322000884756514,
      "learning_rate": 2.49112093287885e-06,
      "loss": 0.9504,
      "step": 866
    },
    {
      "epoch": 1.69140625,
      "grad_norm": 0.3701519677509065,
      "learning_rate": 2.4603485650236537e-06,
      "loss": 1.004,
      "step": 867
    },
    {
      "epoch": 1.693359375,
      "grad_norm": 0.3312692727132356,
      "learning_rate": 2.4297549817811563e-06,
      "loss": 0.9421,
      "step": 868
    },
    {
      "epoch": 1.6953125,
      "grad_norm": 0.35199112164506446,
      "learning_rate": 2.39934049499688e-06,
      "loss": 0.9679,
      "step": 869
    },
    {
      "epoch": 1.697265625,
      "grad_norm": 0.3287351697470824,
      "learning_rate": 2.369105414690809e-06,
      "loss": 0.9465,
      "step": 870
    },
    {
      "epoch": 1.69921875,
      "grad_norm": 0.35633887076765347,
      "learning_rate": 2.3390500490541925e-06,
      "loss": 1.0397,
      "step": 871
    },
    {
      "epoch": 1.701171875,
      "grad_norm": 0.39988446660063875,
      "learning_rate": 2.309174704446411e-06,
      "loss": 1.0082,
      "step": 872
    },
    {
      "epoch": 1.703125,
      "grad_norm": 0.43025629592798453,
      "learning_rate": 2.2794796853918788e-06,
      "loss": 0.953,
      "step": 873
    },
    {
      "epoch": 1.705078125,
      "grad_norm": 0.40102992479060373,
      "learning_rate": 2.2499652945769147e-06,
      "loss": 0.8468,
      "step": 874
    },
    {
      "epoch": 1.70703125,
      "grad_norm": 0.35165212028343795,
      "learning_rate": 2.220631832846645e-06,
      "loss": 0.966,
      "step": 875
    },
    {
      "epoch": 1.708984375,
      "grad_norm": 0.4106731353899637,
      "learning_rate": 2.1914795992019868e-06,
      "loss": 0.9705,
      "step": 876
    },
    {
      "epoch": 1.7109375,
      "grad_norm": 0.3496212858723693,
      "learning_rate": 2.162508890796553e-06,
      "loss": 0.9674,
      "step": 877
    },
    {
      "epoch": 1.712890625,
      "grad_norm": 0.3602824894553474,
      "learning_rate": 2.133720002933626e-06,
      "loss": 0.8979,
      "step": 878
    },
    {
      "epoch": 1.71484375,
      "grad_norm": 0.4041833737547774,
      "learning_rate": 2.1051132290631937e-06,
      "loss": 0.9509,
      "step": 879
    },
    {
      "epoch": 1.716796875,
      "grad_norm": 0.36192746263411507,
      "learning_rate": 2.0766888607788906e-06,
      "loss": 0.9679,
      "step": 880
    },
    {
      "epoch": 1.71875,
      "grad_norm": 0.3159102288573728,
      "learning_rate": 2.0484471878150815e-06,
      "loss": 0.893,
      "step": 881
    },
    {
      "epoch": 1.720703125,
      "grad_norm": 0.3519058283518318,
      "learning_rate": 2.0203884980438837e-06,
      "loss": 0.8964,
      "step": 882
    },
    {
      "epoch": 1.72265625,
      "grad_norm": 0.381383120077412,
      "learning_rate": 1.9925130774722335e-06,
      "loss": 0.9382,
      "step": 883
    },
    {
      "epoch": 1.724609375,
      "grad_norm": 0.3613546886340017,
      "learning_rate": 1.964821210238972e-06,
      "loss": 0.9693,
      "step": 884
    },
    {
      "epoch": 1.7265625,
      "grad_norm": 0.3942760369804237,
      "learning_rate": 1.937313178611955e-06,
      "loss": 1.0356,
      "step": 885
    },
    {
      "epoch": 1.728515625,
      "grad_norm": 0.39895407706308134,
      "learning_rate": 1.909989262985168e-06,
      "loss": 0.876,
      "step": 886
    },
    {
      "epoch": 1.73046875,
      "grad_norm": 0.35383654897625144,
      "learning_rate": 1.8828497418758718e-06,
      "loss": 0.9972,
      "step": 887
    },
    {
      "epoch": 1.732421875,
      "grad_norm": 0.38377632481048274,
      "learning_rate": 1.8558948919217612e-06,
      "loss": 1.0044,
      "step": 888
    },
    {
      "epoch": 1.734375,
      "grad_norm": 0.3461773876079714,
      "learning_rate": 1.8291249878781526e-06,
      "loss": 0.9876,
      "step": 889
    },
    {
      "epoch": 1.736328125,
      "grad_norm": 0.4346566256511891,
      "learning_rate": 1.8025403026151678e-06,
      "loss": 0.9602,
      "step": 890
    },
    {
      "epoch": 1.73828125,
      "grad_norm": 0.3574146419881523,
      "learning_rate": 1.7761411071149747e-06,
      "loss": 0.9682,
      "step": 891
    },
    {
      "epoch": 1.740234375,
      "grad_norm": 0.3519065226822375,
      "learning_rate": 1.7499276704690004e-06,
      "loss": 0.9614,
      "step": 892
    },
    {
      "epoch": 1.7421875,
      "grad_norm": 0.3496145800331222,
      "learning_rate": 1.723900259875213e-06,
      "loss": 1.0102,
      "step": 893
    },
    {
      "epoch": 1.744140625,
      "grad_norm": 0.3514071507159642,
      "learning_rate": 1.6980591406353752e-06,
      "loss": 0.8867,
      "step": 894
    },
    {
      "epoch": 1.74609375,
      "grad_norm": 0.3905828203906191,
      "learning_rate": 1.6724045761523555e-06,
      "loss": 1.0476,
      "step": 895
    },
    {
      "epoch": 1.748046875,
      "grad_norm": 0.35225299605349136,
      "learning_rate": 1.646936827927441e-06,
      "loss": 0.9368,
      "step": 896
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.32804229261746376,
      "learning_rate": 1.6216561555576648e-06,
      "loss": 0.9623,
      "step": 897
    },
    {
      "epoch": 1.751953125,
      "grad_norm": 0.3312493132322017,
      "learning_rate": 1.596562816733165e-06,
      "loss": 0.9307,
      "step": 898
    },
    {
      "epoch": 1.75390625,
      "grad_norm": 0.32655605665351745,
      "learning_rate": 1.5716570672345599e-06,
      "loss": 0.9805,
      "step": 899
    },
    {
      "epoch": 1.755859375,
      "grad_norm": 0.394094204087187,
      "learning_rate": 1.5469391609303386e-06,
      "loss": 0.9867,
      "step": 900
    },
    {
      "epoch": 1.7578125,
      "grad_norm": 0.32363394136809587,
      "learning_rate": 1.5224093497742654e-06,
      "loss": 1.0091,
      "step": 901
    },
    {
      "epoch": 1.759765625,
      "grad_norm": 0.33359362155581607,
      "learning_rate": 1.4980678838028294e-06,
      "loss": 0.9636,
      "step": 902
    },
    {
      "epoch": 1.76171875,
      "grad_norm": 0.3560754852478311,
      "learning_rate": 1.4739150111326827e-06,
      "loss": 1.0249,
      "step": 903
    },
    {
      "epoch": 1.763671875,
      "grad_norm": 0.5059736614922816,
      "learning_rate": 1.4499509779581078e-06,
      "loss": 0.9624,
      "step": 904
    },
    {
      "epoch": 1.765625,
      "grad_norm": 0.36879000558906166,
      "learning_rate": 1.4261760285485227e-06,
      "loss": 0.9457,
      "step": 905
    },
    {
      "epoch": 1.767578125,
      "grad_norm": 0.40169930844289076,
      "learning_rate": 1.4025904052459783e-06,
      "loss": 0.9372,
      "step": 906
    },
    {
      "epoch": 1.76953125,
      "grad_norm": 0.3971684344921998,
      "learning_rate": 1.3791943484626935e-06,
      "loss": 0.9173,
      "step": 907
    },
    {
      "epoch": 1.771484375,
      "grad_norm": 0.3290786813649836,
      "learning_rate": 1.3559880966786066e-06,
      "loss": 0.9332,
      "step": 908
    },
    {
      "epoch": 1.7734375,
      "grad_norm": 0.4487234199517543,
      "learning_rate": 1.3329718864389364e-06,
      "loss": 1.0483,
      "step": 909
    },
    {
      "epoch": 1.775390625,
      "grad_norm": 0.3261700993090167,
      "learning_rate": 1.3101459523517802e-06,
      "loss": 0.904,
      "step": 910
    },
    {
      "epoch": 1.77734375,
      "grad_norm": 0.37305788722713606,
      "learning_rate": 1.2875105270857203e-06,
      "loss": 0.9332,
      "step": 911
    },
    {
      "epoch": 1.779296875,
      "grad_norm": 0.4031564738205153,
      "learning_rate": 1.2650658413674434e-06,
      "loss": 0.9172,
      "step": 912
    },
    {
      "epoch": 1.78125,
      "grad_norm": 0.37246733947996924,
      "learning_rate": 1.2428121239794022e-06,
      "loss": 0.9825,
      "step": 913
    },
    {
      "epoch": 1.783203125,
      "grad_norm": 0.3411964092280633,
      "learning_rate": 1.220749601757476e-06,
      "loss": 0.953,
      "step": 914
    },
    {
      "epoch": 1.78515625,
      "grad_norm": 0.32950822196807084,
      "learning_rate": 1.1988784995886605e-06,
      "loss": 0.972,
      "step": 915
    },
    {
      "epoch": 1.787109375,
      "grad_norm": 0.3345103309155423,
      "learning_rate": 1.1771990404087697e-06,
      "loss": 0.9273,
      "step": 916
    },
    {
      "epoch": 1.7890625,
      "grad_norm": 0.3680835951271046,
      "learning_rate": 1.1557114452001716e-06,
      "loss": 0.95,
      "step": 917
    },
    {
      "epoch": 1.791015625,
      "grad_norm": 0.39148860179503037,
      "learning_rate": 1.1344159329895366e-06,
      "loss": 1.0437,
      "step": 918
    },
    {
      "epoch": 1.79296875,
      "grad_norm": 0.7376168908589766,
      "learning_rate": 1.113312720845594e-06,
      "loss": 1.0732,
      "step": 919
    },
    {
      "epoch": 1.794921875,
      "grad_norm": 0.44262816913005554,
      "learning_rate": 1.092402023876933e-06,
      "loss": 0.9735,
      "step": 920
    },
    {
      "epoch": 1.796875,
      "grad_norm": 0.39038238402245246,
      "learning_rate": 1.0716840552297936e-06,
      "loss": 0.9807,
      "step": 921
    },
    {
      "epoch": 1.798828125,
      "grad_norm": 0.3882601298817771,
      "learning_rate": 1.051159026085915e-06,
      "loss": 0.8839,
      "step": 922
    },
    {
      "epoch": 1.80078125,
      "grad_norm": 0.3528934515469854,
      "learning_rate": 1.0308271456603624e-06,
      "loss": 1.0511,
      "step": 923
    },
    {
      "epoch": 1.802734375,
      "grad_norm": 0.3564523740726362,
      "learning_rate": 1.0106886211994138e-06,
      "loss": 0.9455,
      "step": 924
    },
    {
      "epoch": 1.8046875,
      "grad_norm": 0.31762683416349985,
      "learning_rate": 9.907436579784213e-07,
      "loss": 0.9697,
      "step": 925
    },
    {
      "epoch": 1.806640625,
      "grad_norm": 0.3801429314092011,
      "learning_rate": 9.709924592997533e-07,
      "loss": 1.0966,
      "step": 926
    },
    {
      "epoch": 1.80859375,
      "grad_norm": 0.3493058369345675,
      "learning_rate": 9.514352264906889e-07,
      "loss": 0.9326,
      "step": 927
    },
    {
      "epoch": 1.810546875,
      "grad_norm": 0.369099099833458,
      "learning_rate": 9.320721589013892e-07,
      "loss": 0.9134,
      "step": 928
    },
    {
      "epoch": 1.8125,
      "grad_norm": 0.3808182307879033,
      "learning_rate": 9.12903453902858e-07,
      "loss": 0.9125,
      "step": 929
    },
    {
      "epoch": 1.814453125,
      "grad_norm": 0.3456329419721695,
      "learning_rate": 8.939293068849175e-07,
      "loss": 0.9139,
      "step": 930
    },
    {
      "epoch": 1.81640625,
      "grad_norm": 0.3406485979562886,
      "learning_rate": 8.751499112542339e-07,
      "loss": 1.0243,
      "step": 931
    },
    {
      "epoch": 1.818359375,
      "grad_norm": 0.3210764100001583,
      "learning_rate": 8.565654584323524e-07,
      "loss": 0.9829,
      "step": 932
    },
    {
      "epoch": 1.8203125,
      "grad_norm": 0.3668512562159964,
      "learning_rate": 8.381761378537101e-07,
      "loss": 0.9069,
      "step": 933
    },
    {
      "epoch": 1.822265625,
      "grad_norm": 0.3431074822383598,
      "learning_rate": 8.199821369637396e-07,
      "loss": 1.0002,
      "step": 934
    },
    {
      "epoch": 1.82421875,
      "grad_norm": 0.3509693664918606,
      "learning_rate": 8.019836412169591e-07,
      "loss": 0.9178,
      "step": 935
    },
    {
      "epoch": 1.826171875,
      "grad_norm": 0.3597622454227097,
      "learning_rate": 7.841808340750478e-07,
      "loss": 0.9432,
      "step": 936
    },
    {
      "epoch": 1.828125,
      "grad_norm": 0.35263808129070756,
      "learning_rate": 7.665738970050096e-07,
      "loss": 0.8751,
      "step": 937
    },
    {
      "epoch": 1.830078125,
      "grad_norm": 0.3454514728467226,
      "learning_rate": 7.491630094773161e-07,
      "loss": 0.939,
      "step": 938
    },
    {
      "epoch": 1.83203125,
      "grad_norm": 0.3476148078880441,
      "learning_rate": 7.319483489640644e-07,
      "loss": 1.0074,
      "step": 939
    },
    {
      "epoch": 1.833984375,
      "grad_norm": 0.3558611979420541,
      "learning_rate": 7.149300909371804e-07,
      "loss": 0.9998,
      "step": 940
    },
    {
      "epoch": 1.8359375,
      "grad_norm": 0.4231834967840788,
      "learning_rate": 6.98108408866629e-07,
      "loss": 1.0532,
      "step": 941
    },
    {
      "epoch": 1.837890625,
      "grad_norm": 0.3701247171483504,
      "learning_rate": 6.814834742186361e-07,
      "loss": 1.0818,
      "step": 942
    },
    {
      "epoch": 1.83984375,
      "grad_norm": 0.33100418558525796,
      "learning_rate": 6.650554564539513e-07,
      "loss": 0.9281,
      "step": 943
    },
    {
      "epoch": 1.841796875,
      "grad_norm": 0.34943114450428675,
      "learning_rate": 6.488245230261281e-07,
      "loss": 1.0304,
      "step": 944
    },
    {
      "epoch": 1.84375,
      "grad_norm": 0.3358226439459799,
      "learning_rate": 6.327908393797888e-07,
      "loss": 0.9208,
      "step": 945
    },
    {
      "epoch": 1.845703125,
      "grad_norm": 0.3692754510302509,
      "learning_rate": 6.16954568948962e-07,
      "loss": 0.9613,
      "step": 946
    },
    {
      "epoch": 1.84765625,
      "grad_norm": 0.3548678948914393,
      "learning_rate": 6.013158731554192e-07,
      "loss": 0.9335,
      "step": 947
    },
    {
      "epoch": 1.849609375,
      "grad_norm": 0.4916960462161901,
      "learning_rate": 5.858749114070073e-07,
      "loss": 0.9665,
      "step": 948
    },
    {
      "epoch": 1.8515625,
      "grad_norm": 0.34562512537565865,
      "learning_rate": 5.706318410960432e-07,
      "loss": 0.9405,
      "step": 949
    },
    {
      "epoch": 1.853515625,
      "grad_norm": 0.35337073583126055,
      "learning_rate": 5.555868175977064e-07,
      "loss": 1.018,
      "step": 950
    },
    {
      "epoch": 1.85546875,
      "grad_norm": 0.34922835367393223,
      "learning_rate": 5.407399942684443e-07,
      "loss": 1.0477,
      "step": 951
    },
    {
      "epoch": 1.857421875,
      "grad_norm": 0.32669028671164363,
      "learning_rate": 5.260915224444207e-07,
      "loss": 0.9258,
      "step": 952
    },
    {
      "epoch": 1.859375,
      "grad_norm": 0.38688056790403885,
      "learning_rate": 5.116415514399697e-07,
      "loss": 0.965,
      "step": 953
    },
    {
      "epoch": 1.861328125,
      "grad_norm": 0.3583271400252034,
      "learning_rate": 4.973902285460708e-07,
      "loss": 0.9039,
      "step": 954
    },
    {
      "epoch": 1.86328125,
      "grad_norm": 0.3763517309634589,
      "learning_rate": 4.833376990288541e-07,
      "loss": 0.8942,
      "step": 955
    },
    {
      "epoch": 1.865234375,
      "grad_norm": 0.41840327278473965,
      "learning_rate": 4.69484106128113e-07,
      "loss": 0.9217,
      "step": 956
    },
    {
      "epoch": 1.8671875,
      "grad_norm": 0.48189210935319654,
      "learning_rate": 4.558295910558452e-07,
      "loss": 0.9726,
      "step": 957
    },
    {
      "epoch": 1.869140625,
      "grad_norm": 0.4024561076162549,
      "learning_rate": 4.4237429299481824e-07,
      "loss": 0.9467,
      "step": 958
    },
    {
      "epoch": 1.87109375,
      "grad_norm": 0.3404000507177348,
      "learning_rate": 4.2911834909713955e-07,
      "loss": 0.9324,
      "step": 959
    },
    {
      "epoch": 1.873046875,
      "grad_norm": 0.37944809731106327,
      "learning_rate": 4.1606189448287757e-07,
      "loss": 0.9185,
      "step": 960
    },
    {
      "epoch": 1.875,
      "grad_norm": 0.347161508627164,
      "learning_rate": 4.0320506223866297e-07,
      "loss": 1.0618,
      "step": 961
    },
    {
      "epoch": 1.876953125,
      "grad_norm": 0.39568336372075197,
      "learning_rate": 3.9054798341634947e-07,
      "loss": 0.9308,
      "step": 962
    },
    {
      "epoch": 1.87890625,
      "grad_norm": 0.3988571408933023,
      "learning_rate": 3.780907870316641e-07,
      "loss": 0.9526,
      "step": 963
    },
    {
      "epoch": 1.880859375,
      "grad_norm": 0.398371414984607,
      "learning_rate": 3.658336000629015e-07,
      "loss": 0.9956,
      "step": 964
    },
    {
      "epoch": 1.8828125,
      "grad_norm": 0.3438799621684331,
      "learning_rate": 3.5377654744962907e-07,
      "loss": 1.0687,
      "step": 965
    },
    {
      "epoch": 1.884765625,
      "grad_norm": 0.39699246512526676,
      "learning_rate": 3.419197520914086e-07,
      "loss": 1.1627,
      "step": 966
    },
    {
      "epoch": 1.88671875,
      "grad_norm": 0.35201200812493444,
      "learning_rate": 3.302633348465434e-07,
      "loss": 0.9449,
      "step": 967
    },
    {
      "epoch": 1.888671875,
      "grad_norm": 0.32877578712250805,
      "learning_rate": 3.188074145308573e-07,
      "loss": 0.9075,
      "step": 968
    },
    {
      "epoch": 1.890625,
      "grad_norm": 0.32981575777312694,
      "learning_rate": 3.075521079164667e-07,
      "loss": 1.0126,
      "step": 969
    },
    {
      "epoch": 1.892578125,
      "grad_norm": 0.33641211411571265,
      "learning_rate": 2.964975297306016e-07,
      "loss": 0.8823,
      "step": 970
    },
    {
      "epoch": 1.89453125,
      "grad_norm": 0.344062591745831,
      "learning_rate": 2.8564379265443534e-07,
      "loss": 0.9042,
      "step": 971
    },
    {
      "epoch": 1.896484375,
      "grad_norm": 0.3382258898282539,
      "learning_rate": 2.74991007321932e-07,
      "loss": 0.9539,
      "step": 972
    },
    {
      "epoch": 1.8984375,
      "grad_norm": 0.34408359316566367,
      "learning_rate": 2.645392823187209e-07,
      "loss": 0.937,
      "step": 973
    },
    {
      "epoch": 1.900390625,
      "grad_norm": 0.40252450642423426,
      "learning_rate": 2.5428872418099327e-07,
      "loss": 0.9623,
      "step": 974
    },
    {
      "epoch": 1.90234375,
      "grad_norm": 0.32650087303943487,
      "learning_rate": 2.442394373944068e-07,
      "loss": 0.8756,
      "step": 975
    },
    {
      "epoch": 1.904296875,
      "grad_norm": 0.3841664877636987,
      "learning_rate": 2.343915243930317e-07,
      "loss": 0.9259,
      "step": 976
    },
    {
      "epoch": 1.90625,
      "grad_norm": 0.3669917581544276,
      "learning_rate": 2.2474508555829332e-07,
      "loss": 0.8973,
      "step": 977
    },
    {
      "epoch": 1.908203125,
      "grad_norm": 0.3752187875781994,
      "learning_rate": 2.1530021921797096e-07,
      "loss": 0.9675,
      "step": 978
    },
    {
      "epoch": 1.91015625,
      "grad_norm": 0.3550010185294928,
      "learning_rate": 2.060570216451674e-07,
      "loss": 1.02,
      "step": 979
    },
    {
      "epoch": 1.912109375,
      "grad_norm": 0.3297340190628814,
      "learning_rate": 1.970155870573498e-07,
      "loss": 0.9498,
      "step": 980
    },
    {
      "epoch": 1.9140625,
      "grad_norm": 0.3667116318991766,
      "learning_rate": 1.8817600761537936e-07,
      "loss": 0.9487,
      "step": 981
    },
    {
      "epoch": 1.916015625,
      "grad_norm": 0.3800544584048625,
      "learning_rate": 1.795383734225764e-07,
      "loss": 0.9872,
      "step": 982
    },
    {
      "epoch": 1.91796875,
      "grad_norm": 0.32522748254279055,
      "learning_rate": 1.7110277252379238e-07,
      "loss": 0.9104,
      "step": 983
    },
    {
      "epoch": 1.919921875,
      "grad_norm": 0.3806646553505043,
      "learning_rate": 1.6286929090452596e-07,
      "loss": 0.9088,
      "step": 984
    },
    {
      "epoch": 1.921875,
      "grad_norm": 0.42299442292566575,
      "learning_rate": 1.548380124900395e-07,
      "loss": 0.9698,
      "step": 985
    },
    {
      "epoch": 1.923828125,
      "grad_norm": 0.34014932945727216,
      "learning_rate": 1.470090191444973e-07,
      "loss": 0.9067,
      "step": 986
    },
    {
      "epoch": 1.92578125,
      "grad_norm": 0.41114569125901435,
      "learning_rate": 1.3938239067014857e-07,
      "loss": 0.969,
      "step": 987
    },
    {
      "epoch": 1.927734375,
      "grad_norm": 0.37110257385407536,
      "learning_rate": 1.3195820480649935e-07,
      "loss": 1.0695,
      "step": 988
    },
    {
      "epoch": 1.9296875,
      "grad_norm": 0.3617094624401443,
      "learning_rate": 1.247365372295173e-07,
      "loss": 0.9954,
      "step": 989
    },
    {
      "epoch": 1.931640625,
      "grad_norm": 0.34807116363173835,
      "learning_rate": 1.1771746155087693e-07,
      "loss": 0.9222,
      "step": 990
    },
    {
      "epoch": 1.93359375,
      "grad_norm": 0.39088454537964334,
      "learning_rate": 1.1090104931719581e-07,
      "loss": 0.9922,
      "step": 991
    },
    {
      "epoch": 1.935546875,
      "grad_norm": 0.3334913612888957,
      "learning_rate": 1.042873700093061e-07,
      "loss": 0.9096,
      "step": 992
    },
    {
      "epoch": 1.9375,
      "grad_norm": 0.34050635233379445,
      "learning_rate": 9.787649104155306e-08,
      "loss": 0.944,
      "step": 993
    },
    {
      "epoch": 1.939453125,
      "grad_norm": 0.3522177990721162,
      "learning_rate": 9.16684777611021e-08,
      "loss": 0.9781,
      "step": 994
    },
    {
      "epoch": 1.94140625,
      "grad_norm": 0.38001892994954917,
      "learning_rate": 8.566339344727503e-08,
      "loss": 0.9112,
      "step": 995
    },
    {
      "epoch": 1.943359375,
      "grad_norm": 0.3549451702379671,
      "learning_rate": 7.98612993109038e-08,
      "loss": 0.9705,
      "step": 996
    },
    {
      "epoch": 1.9453125,
      "grad_norm": 0.3642736748873916,
      "learning_rate": 7.426225449371327e-08,
      "loss": 0.9518,
      "step": 997
    },
    {
      "epoch": 1.947265625,
      "grad_norm": 0.38525054768493344,
      "learning_rate": 6.886631606770166e-08,
      "loss": 1.0151,
      "step": 998
    },
    {
      "epoch": 1.94921875,
      "grad_norm": 0.4598184227586954,
      "learning_rate": 6.367353903457663e-08,
      "loss": 0.946,
      "step": 999
    },
    {
      "epoch": 1.951171875,
      "grad_norm": 0.38596680800637123,
      "learning_rate": 5.8683976325191185e-08,
      "loss": 1.063,
      "step": 1000
    },
    {
      "epoch": 1.953125,
      "grad_norm": 0.390077956276957,
      "learning_rate": 5.389767879899088e-08,
      "loss": 0.9386,
      "step": 1001
    },
    {
      "epoch": 1.955078125,
      "grad_norm": 0.32728559348396596,
      "learning_rate": 4.9314695243511954e-08,
      "loss": 0.9607,
      "step": 1002
    },
    {
      "epoch": 1.95703125,
      "grad_norm": 0.441727742998025,
      "learning_rate": 4.4935072373875064e-08,
      "loss": 0.9577,
      "step": 1003
    },
    {
      "epoch": 1.958984375,
      "grad_norm": 0.4109803780015982,
      "learning_rate": 4.075885483231234e-08,
      "loss": 0.9053,
      "step": 1004
    },
    {
      "epoch": 1.9609375,
      "grad_norm": 0.32819067827041765,
      "learning_rate": 3.6786085187709985e-08,
      "loss": 0.9701,
      "step": 1005
    },
    {
      "epoch": 1.962890625,
      "grad_norm": 0.4022840812080156,
      "learning_rate": 3.3016803935177476e-08,
      "loss": 0.9256,
      "step": 1006
    },
    {
      "epoch": 1.96484375,
      "grad_norm": 0.3297886055261517,
      "learning_rate": 2.9451049495630158e-08,
      "loss": 0.9672,
      "step": 1007
    },
    {
      "epoch": 1.966796875,
      "grad_norm": 0.40315004880040545,
      "learning_rate": 2.6088858215400638e-08,
      "loss": 1.0058,
      "step": 1008
    },
    {
      "epoch": 1.96875,
      "grad_norm": 0.3925529234153025,
      "learning_rate": 2.2930264365872423e-08,
      "loss": 0.9561,
      "step": 1009
    },
    {
      "epoch": 1.970703125,
      "grad_norm": 0.33235657315352346,
      "learning_rate": 1.9975300143122434e-08,
      "loss": 0.9334,
      "step": 1010
    },
    {
      "epoch": 1.97265625,
      "grad_norm": 0.3959865485662931,
      "learning_rate": 1.7223995667594584e-08,
      "loss": 0.9249,
      "step": 1011
    },
    {
      "epoch": 1.974609375,
      "grad_norm": 0.37245443190696986,
      "learning_rate": 1.4676378983800032e-08,
      "loss": 0.9304,
      "step": 1012
    },
    {
      "epoch": 1.9765625,
      "grad_norm": 0.37105753989780677,
      "learning_rate": 1.2332476060021858e-08,
      "loss": 0.9794,
      "step": 1013
    },
    {
      "epoch": 1.978515625,
      "grad_norm": 0.6903119510996225,
      "learning_rate": 1.0192310788057492e-08,
      "loss": 1.1607,
      "step": 1014
    },
    {
      "epoch": 1.98046875,
      "grad_norm": 0.3825801188749438,
      "learning_rate": 8.25590498297224e-09,
      "loss": 0.984,
      "step": 1015
    },
    {
      "epoch": 1.982421875,
      "grad_norm": 0.4895558883231159,
      "learning_rate": 6.523278382872811e-09,
      "loss": 0.9504,
      "step": 1016
    },
    {
      "epoch": 1.984375,
      "grad_norm": 0.34211278378628385,
      "learning_rate": 4.994448648714123e-09,
      "loss": 1.0692,
      "step": 1017
    },
    {
      "epoch": 1.986328125,
      "grad_norm": 0.36207507500151775,
      "learning_rate": 3.6694313641127967e-09,
      "loss": 0.8947,
      "step": 1018
    },
    {
      "epoch": 1.98828125,
      "grad_norm": 0.33104333759748333,
      "learning_rate": 2.548240035196159e-09,
      "loss": 0.9328,
      "step": 1019
    },
    {
      "epoch": 1.990234375,
      "grad_norm": 0.3485900038914914,
      "learning_rate": 1.6308860904534762e-09,
      "loss": 0.9528,
      "step": 1020
    },
    {
      "epoch": 1.9921875,
      "grad_norm": 0.3194620455365908,
      "learning_rate": 9.173788806293715e-10,
      "loss": 0.9578,
      "step": 1021
    },
    {
      "epoch": 1.994140625,
      "grad_norm": 0.34696746753308005,
      "learning_rate": 4.0772567861946387e-10,
      "loss": 0.9731,
      "step": 1022
    },
    {
      "epoch": 1.99609375,
      "grad_norm": 0.3679482895309835,
      "learning_rate": 1.0193167940597549e-10,
      "loss": 0.9267,
      "step": 1023
    },
    {
      "epoch": 1.998046875,
      "grad_norm": 0.35355310524306177,
      "learning_rate": 0.0,
      "loss": 0.9811,
      "step": 1024
    }
  ],
  "logging_steps": 1,
  "max_steps": 1024,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 256,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2124256464863232.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}