{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 456,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.6753363609313965,
      "learning_rate": 0.0,
      "loss": 2.7396,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.6047974824905396,
      "learning_rate": 4e-05,
      "loss": 2.6731,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.6591854095458984,
      "learning_rate": 8e-05,
      "loss": 2.8745,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.6128371953964233,
      "learning_rate": 0.00012,
      "loss": 2.4994,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.173621892929077,
      "learning_rate": 0.00016,
      "loss": 2.3746,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 1.9696063995361328,
      "learning_rate": 0.0002,
      "loss": 2.1932,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.2749128341674805,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.4674,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 2.679276943206787,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.6022,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.7713566422462463,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2462,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.2908493280410767,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.1527,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.8614892959594727,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.1237,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.6766211986541748,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.3264,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.582446813583374,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.2746,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.43136557936668396,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.9903,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5573680996894836,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.1572,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.4903632700443268,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.1907,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.5077425241470337,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.8689,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.45499491691589355,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.2908,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.3860357701778412,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.0414,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.42785316705703735,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.1843,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.34560921788215637,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.1635,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.33395230770111084,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.8594,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3725226819515228,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.146,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3196130096912384,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.0511,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.48426708579063416,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.9796,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3038801848888397,
      "learning_rate": 0.00019113082039911309,
      "loss": 1.0877,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.35030892491340637,
      "learning_rate": 0.00019068736141906876,
      "loss": 1.1521,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.2719012498855591,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.8538,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.33283811807632446,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.0535,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.32213294506073,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.9378,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.31899288296699524,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.9263,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3396363854408264,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.9406,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.38943594694137573,
      "learning_rate": 0.00018802660753880268,
      "loss": 1.0859,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.2910979092121124,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.045,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.6656845211982727,
      "learning_rate": 0.00018713968957871397,
      "loss": 1.0822,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.4086684286594391,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.8946,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.4486556351184845,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.1549,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.3533739745616913,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.0989,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 5.353644847869873,
      "learning_rate": 0.0001853658536585366,
      "loss": 1.0467,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.5463913679122925,
      "learning_rate": 0.00018492239467849224,
      "loss": 1.0308,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.30638256669044495,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.8587,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.42845618724823,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.9602,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.39537644386291504,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.9834,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.4424014389514923,
      "learning_rate": 0.00018314855875831487,
      "loss": 1.0509,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.45539534091949463,
      "learning_rate": 0.00018270509977827052,
      "loss": 1.0386,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.3145766854286194,
      "learning_rate": 0.00018226164079822616,
      "loss": 1.0802,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.3275849521160126,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.9166,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.569707453250885,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.1115,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.2998656928539276,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.8442,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.28205761313438416,
      "learning_rate": 0.0001804878048780488,
      "loss": 1.186,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.3158072829246521,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.1128,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.27256232500076294,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.8297,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.25822678208351135,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.816,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.4438026547431946,
      "learning_rate": 0.0001787139689578714,
      "loss": 1.062,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.40407776832580566,
      "learning_rate": 0.00017827050997782707,
      "loss": 1.0663,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.2808516025543213,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.1284,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.2991017997264862,
      "learning_rate": 0.00017738359201773839,
      "loss": 1.0279,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.2699621617794037,
      "learning_rate": 0.000176940133037694,
      "loss": 1.0439,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.36164867877960205,
      "learning_rate": 0.00017649667405764967,
      "loss": 1.1379,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.346542626619339,
      "learning_rate": 0.00017605321507760532,
      "loss": 1.052,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.2466624528169632,
      "learning_rate": 0.000175609756097561,
      "loss": 0.7292,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3952149748802185,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.9296,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.2705230116844177,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.9741,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.41347140073776245,
      "learning_rate": 0.00017427937915742792,
      "loss": 1.0694,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3015870451927185,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.8375,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3093418776988983,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.879,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.36475348472595215,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.8806,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.3609849810600281,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.9253,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.3079163730144501,
      "learning_rate": 0.00017206208425720623,
      "loss": 1.0338,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.2943955361843109,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.8379,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.34060949087142944,
      "learning_rate": 0.00017117516629711752,
      "loss": 1.0858,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.3115427792072296,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.8339,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.269108384847641,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8371,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3131944239139557,
      "learning_rate": 0.0001698447893569845,
      "loss": 1.1025,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.3371261656284332,
      "learning_rate": 0.00016940133037694015,
      "loss": 1.0874,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.30163106322288513,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.786,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.3672100007534027,
      "learning_rate": 0.00016851441241685144,
      "loss": 1.1546,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.360826313495636,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.8258,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.4466773271560669,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.9276,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.26879650354385376,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.8949,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.31472277641296387,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.8938,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.31833770871162415,
      "learning_rate": 0.00016629711751662974,
      "loss": 1.0621,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.35938823223114014,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.8929,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3366357684135437,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.8789,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.3333033621311188,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.9118,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.44680511951446533,
      "learning_rate": 0.00016452328159645234,
      "loss": 1.1072,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.3379020392894745,
      "learning_rate": 0.000164079822616408,
      "loss": 0.8427,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.3948090076446533,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.0534,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3617728650569916,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.8389,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.35040485858917236,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.8402,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.3581698536872864,
      "learning_rate": 0.0001623059866962306,
      "loss": 1.0025,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.3583804666996002,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.8797,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.2502649128437042,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.7932,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.37897902727127075,
      "learning_rate": 0.00016097560975609758,
      "loss": 1.0378,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.28588831424713135,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.8406,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.3307378590106964,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.6996,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.3762584924697876,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.959,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.27697858214378357,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.7913,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.30343618988990784,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.8215,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.3002854883670807,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.937,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.3340570330619812,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.8881,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.305184006690979,
      "learning_rate": 0.0001574279379157428,
      "loss": 1.0601,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.39571312069892883,
      "learning_rate": 0.00015698447893569846,
      "loss": 1.0448,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.3152364194393158,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.9556,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.30437639355659485,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.674,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.3132797181606293,
      "learning_rate": 0.00015565410199556542,
      "loss": 1.0324,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.3175605833530426,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.9323,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.33255118131637573,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.999,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.2968844473361969,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.8808,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.37689900398254395,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.8694,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.33357635140419006,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.951,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.31658682227134705,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.9183,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.41855478286743164,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.9948,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.2507818043231964,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.8021,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.5237794518470764,
      "learning_rate": 0.0001516629711751663,
      "loss": 1.0125,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.3374301493167877,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.9884,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.2544371783733368,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.8434,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.2930176556110382,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.9105,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.3695061504840851,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.9253,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.31878480315208435,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.7895,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.3489243984222412,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.8712,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.3055182993412018,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.8525,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.35498014092445374,
      "learning_rate": 0.00014811529933481154,
      "loss": 1.0891,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.2868698835372925,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.8646,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.34913045167922974,
      "learning_rate": 0.00014722838137472282,
      "loss": 1.0051,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.3663114011287689,
      "learning_rate": 0.0001467849223946785,
      "loss": 1.1822,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.4712967276573181,
      "learning_rate": 0.00014634146341463414,
      "loss": 1.26,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.3631509244441986,
      "learning_rate": 0.0001458980044345898,
      "loss": 1.1599,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.36662793159484863,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.8581,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.4787248969078064,
      "learning_rate": 0.00014501108647450113,
      "loss": 1.0785,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.4358362853527069,
      "learning_rate": 0.00014456762749445675,
      "loss": 1.0156,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.39556005597114563,
      "learning_rate": 0.00014412416851441242,
      "loss": 1.0267,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.35907939076423645,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.8823,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.26828625798225403,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.8673,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.3237515985965729,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.8641,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.2926613390445709,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.774,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.346812903881073,
      "learning_rate": 0.0001419068736141907,
      "loss": 1.0153,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.7879506349563599,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.899,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.355522096157074,
      "learning_rate": 0.000141019955654102,
      "loss": 0.8164,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.3531189262866974,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.8666,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.3663748502731323,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.8496,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.3735043704509735,
      "learning_rate": 0.00013968957871396897,
      "loss": 1.0068,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.3465340733528137,
      "learning_rate": 0.00013924611973392464,
      "loss": 1.0703,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.38539549708366394,
      "learning_rate": 0.00013880266075388026,
      "loss": 1.1036,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.37499338388442993,
      "learning_rate": 0.00013835920177383593,
      "loss": 1.0921,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.4159431457519531,
      "learning_rate": 0.00013791574279379157,
      "loss": 1.1292,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.3167089819908142,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.8512,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.3283349573612213,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.8751,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.3082846701145172,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.859,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.4045282304286957,
      "learning_rate": 0.00013614190687361418,
      "loss": 1.109,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.3488849103450775,
      "learning_rate": 0.00013569844789356985,
      "loss": 1.009,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3817792236804962,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.8929,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.32665708661079407,
      "learning_rate": 0.00013481152993348116,
      "loss": 1.1209,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.3800903856754303,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.8283,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.35179808735847473,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.8338,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.3269939124584198,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.7918,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.3475397527217865,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.8354,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.27860158681869507,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.7855,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.421125590801239,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.9002,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.36976537108421326,
      "learning_rate": 0.00013170731707317076,
      "loss": 1.0154,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.41473689675331116,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.9225,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.32284441590309143,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.9734,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.30496537685394287,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.8865,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.3334418535232544,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.7133,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.3436813950538635,
      "learning_rate": 0.000129490022172949,
      "loss": 0.7865,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.3677615821361542,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.8147,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.36466386914253235,
      "learning_rate": 0.00012860310421286032,
      "loss": 1.057,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.4074943959712982,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.8081,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.40346720814704895,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.9301,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.43556392192840576,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.8199,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.3291383385658264,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.8918,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.34331244230270386,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.8293,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.3715532422065735,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.7812,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.3675685226917267,
      "learning_rate": 0.00012549889135254989,
      "loss": 1.0022,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.3756179213523865,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.7981,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.4932439625263214,
      "learning_rate": 0.0001246119733924612,
      "loss": 1.0263,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.42718270421028137,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.953,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.38996610045433044,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.7133,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.40669193863868713,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.8002,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.4345385432243347,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.8379,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.3692195415496826,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.833,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.4574708044528961,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.8102,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.44225478172302246,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.859,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.47011590003967285,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.8564,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.361794114112854,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.6238,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.43486130237579346,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.811,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.3785902261734009,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.8675,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.411212295293808,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.799,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.41770684719085693,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.8747,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.45110413432121277,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.9518,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.43953660130500793,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.9383,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.4431529641151428,
      "learning_rate": 0.00011751662971175166,
      "loss": 1.0843,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.338666170835495,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.8364,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.5064515471458435,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.9109,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.5146324038505554,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.8605,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.39591801166534424,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.8311,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.4760957658290863,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.836,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.4155326187610626,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.9754,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.3706800937652588,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.8262,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.5003494024276733,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.9874,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.4487065076828003,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.8001,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.38692301511764526,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.8486,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.5101066827774048,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.9071,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.4823839068412781,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.8257,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.38172978162765503,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.7807,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.432370662689209,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.788,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.420469731092453,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.7141,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.5178762078285217,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.9078,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.4729172885417938,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.8345,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.4455544352531433,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.7944,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.4522795081138611,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.8394,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.4482082426548004,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.6586,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.4409103989601135,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.8638,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.4539140462875366,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.7618,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.538474977016449,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.8472,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.5380995869636536,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.9159,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.5771273970603943,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.9357,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.45590829849243164,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.8389,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.5439815521240234,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.8163,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.602954089641571,
      "learning_rate": 0.00010509977827050999,
      "loss": 1.0706,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.5096477270126343,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.7684,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.570733904838562,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.8946,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.4611380994319916,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.7623,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.4956399202346802,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.8614,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.47977501153945923,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.7984,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.5366384387016296,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.8089,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.47202619910240173,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.9272,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.48930907249450684,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.8406,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.5409417748451233,
      "learning_rate": 0.00010110864745011087,
      "loss": 1.0305,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.43893152475357056,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.7842,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.46009576320648193,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.6103,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.5462482571601868,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.8463,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.5006566047668457,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.857,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.5678414702415466,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.9244,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.5183091163635254,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.814,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.41302505135536194,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.739,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.5402347445487976,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.9331,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.4913271963596344,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.9823,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.4734552502632141,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.7932,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.5224055647850037,
      "learning_rate": 9.623059866962306e-05,
      "loss": 1.0228,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.5478543639183044,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.9807,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.4561575949192047,
      "learning_rate": 9.534368070953438e-05,
      "loss": 0.6793,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.43943655490875244,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.6919,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.5001429319381714,
      "learning_rate": 9.445676274944568e-05,
      "loss": 0.7689,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.5150021910667419,
      "learning_rate": 9.401330376940134e-05,
      "loss": 0.7762,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.4795988202095032,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.8051,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.5289055109024048,
      "learning_rate": 9.312638580931264e-05,
      "loss": 0.9534,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.5961309671401978,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.9041,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.5156664848327637,
      "learning_rate": 9.223946784922394e-05,
      "loss": 0.9927,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.4966232180595398,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.9447,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.5069417953491211,
      "learning_rate": 9.135254988913526e-05,
      "loss": 0.8577,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.5083569884300232,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.9604,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.4884309470653534,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.6828,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.493662565946579,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.7775,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.5201241374015808,
      "learning_rate": 8.957871396895788e-05,
      "loss": 0.973,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.4902701675891876,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.7453,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.7000847458839417,
      "learning_rate": 8.869179600886919e-05,
      "loss": 0.9973,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.572896420955658,
      "learning_rate": 8.824833702882484e-05,
      "loss": 0.9429,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.561058759689331,
      "learning_rate": 8.78048780487805e-05,
      "loss": 1.0176,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.5121408700942993,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.7407,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.5502723455429077,
      "learning_rate": 8.69179600886918e-05,
      "loss": 0.8722,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.5121498703956604,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.9213,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.4571462869644165,
      "learning_rate": 8.603104212860311e-05,
      "loss": 0.7,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.5703877806663513,
      "learning_rate": 8.558758314855876e-05,
      "loss": 0.8466,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.5442690253257751,
      "learning_rate": 8.514412416851442e-05,
      "loss": 0.6839,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.56926429271698,
      "learning_rate": 8.470066518847007e-05,
      "loss": 1.0205,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.5426958799362183,
      "learning_rate": 8.425720620842572e-05,
      "loss": 0.6528,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.6180535554885864,
      "learning_rate": 8.381374722838138e-05,
      "loss": 0.8412,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.6664066910743713,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.8329,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.5359776020050049,
      "learning_rate": 8.292682926829268e-05,
      "loss": 0.9421,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.5313830971717834,
      "learning_rate": 8.248337028824834e-05,
      "loss": 0.7066,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.503743052482605,
      "learning_rate": 8.2039911308204e-05,
      "loss": 0.9682,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.5591855049133301,
      "learning_rate": 8.159645232815965e-05,
      "loss": 0.8621,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.5927342772483826,
      "learning_rate": 8.11529933481153e-05,
      "loss": 0.8845,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.5871875882148743,
      "learning_rate": 8.070953436807095e-05,
      "loss": 0.9288,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.4816722571849823,
      "learning_rate": 8.026607538802661e-05,
      "loss": 0.7302,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.5300981998443604,
      "learning_rate": 7.982261640798227e-05,
      "loss": 0.8035,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.5308715105056763,
      "learning_rate": 7.937915742793793e-05,
      "loss": 0.7536,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.538088858127594,
      "learning_rate": 7.893569844789357e-05,
      "loss": 0.8246,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.5808150172233582,
      "learning_rate": 7.849223946784923e-05,
      "loss": 0.9631,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.5283225178718567,
      "learning_rate": 7.804878048780489e-05,
      "loss": 0.7806,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.43234360218048096,
      "learning_rate": 7.760532150776053e-05,
      "loss": 0.7491,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.5764623880386353,
      "learning_rate": 7.716186252771619e-05,
      "loss": 0.8128,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.5183278918266296,
      "learning_rate": 7.671840354767185e-05,
      "loss": 0.6958,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.5421848297119141,
      "learning_rate": 7.627494456762749e-05,
      "loss": 0.8658,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.5530264973640442,
      "learning_rate": 7.583148558758315e-05,
      "loss": 0.807,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.5575171709060669,
      "learning_rate": 7.538802660753881e-05,
      "loss": 0.864,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.45418375730514526,
      "learning_rate": 7.494456762749445e-05,
      "loss": 0.7912,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.5195934176445007,
      "learning_rate": 7.450110864745011e-05,
      "loss": 0.7601,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.526201069355011,
      "learning_rate": 7.405764966740577e-05,
      "loss": 0.7973,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.5117388963699341,
      "learning_rate": 7.361419068736141e-05,
      "loss": 0.6847,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.5242432355880737,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.7498,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.620801568031311,
      "learning_rate": 7.272727272727273e-05,
      "loss": 1.0201,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.5436952710151672,
      "learning_rate": 7.228381374722837e-05,
      "loss": 0.7587,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.5160356163978577,
      "learning_rate": 7.184035476718403e-05,
      "loss": 0.6658,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.6170647144317627,
      "learning_rate": 7.139689578713969e-05,
      "loss": 0.8197,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.5294138789176941,
      "learning_rate": 7.095343680709535e-05,
      "loss": 0.8264,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.5055113434791565,
      "learning_rate": 7.0509977827051e-05,
      "loss": 0.8255,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.51408451795578,
      "learning_rate": 7.006651884700666e-05,
      "loss": 0.9478,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.726474404335022,
      "learning_rate": 6.962305986696232e-05,
      "loss": 0.868,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.6018652319908142,
      "learning_rate": 6.917960088691796e-05,
      "loss": 0.8678,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.5645736455917358,
      "learning_rate": 6.873614190687362e-05,
      "loss": 0.9267,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.5721924304962158,
      "learning_rate": 6.829268292682928e-05,
      "loss": 0.9286,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9521707892417908,
      "learning_rate": 6.784922394678492e-05,
      "loss": 1.0017,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.5080501437187195,
      "learning_rate": 6.740576496674058e-05,
      "loss": 0.5844,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.5562191605567932,
      "learning_rate": 6.696230598669624e-05,
      "loss": 0.7353,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.6108002662658691,
      "learning_rate": 6.651884700665188e-05,
      "loss": 0.7662,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.6404972672462463,
      "learning_rate": 6.607538802660754e-05,
      "loss": 0.6951,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.5950292944908142,
      "learning_rate": 6.56319290465632e-05,
      "loss": 0.8436,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.5857701897621155,
      "learning_rate": 6.518847006651884e-05,
      "loss": 0.9945,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.4862763583660126,
      "learning_rate": 6.47450110864745e-05,
      "loss": 0.6349,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.5508712530136108,
      "learning_rate": 6.430155210643016e-05,
      "loss": 0.6629,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.6336526870727539,
      "learning_rate": 6.38580931263858e-05,
      "loss": 0.8338,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.5567284226417542,
      "learning_rate": 6.341463414634146e-05,
      "loss": 0.6402,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.5753811597824097,
      "learning_rate": 6.297117516629712e-05,
      "loss": 0.7471,
      "step": 315
    },
    {
      "epoch": 2.0791208791208793,
      "grad_norm": 0.6722463369369507,
      "learning_rate": 6.252771618625277e-05,
      "loss": 0.805,
      "step": 316
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.6304366588592529,
      "learning_rate": 6.208425720620842e-05,
      "loss": 0.7077,
      "step": 317
    },
    {
      "epoch": 2.0923076923076924,
      "grad_norm": 0.5530065894126892,
      "learning_rate": 6.164079822616408e-05,
      "loss": 0.755,
      "step": 318
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.6075183749198914,
      "learning_rate": 6.119733924611974e-05,
      "loss": 0.7062,
      "step": 319
    },
    {
      "epoch": 2.1054945054945056,
      "grad_norm": 0.5700207352638245,
      "learning_rate": 6.075388026607539e-05,
      "loss": 0.8415,
      "step": 320
    },
    {
      "epoch": 2.112087912087912,
      "grad_norm": 0.5903488397598267,
      "learning_rate": 6.031042128603105e-05,
      "loss": 0.7171,
      "step": 321
    },
    {
      "epoch": 2.1186813186813187,
      "grad_norm": 0.6823955774307251,
      "learning_rate": 5.98669623059867e-05,
      "loss": 0.8024,
      "step": 322
    },
    {
      "epoch": 2.1252747252747253,
      "grad_norm": 0.590376079082489,
      "learning_rate": 5.942350332594236e-05,
      "loss": 0.7671,
      "step": 323
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.6151862740516663,
      "learning_rate": 5.898004434589801e-05,
      "loss": 0.5782,
      "step": 324
    },
    {
      "epoch": 2.1384615384615384,
      "grad_norm": 0.5370686650276184,
      "learning_rate": 5.853658536585366e-05,
      "loss": 0.5983,
      "step": 325
    },
    {
      "epoch": 2.145054945054945,
      "grad_norm": 0.6067591309547424,
      "learning_rate": 5.809312638580932e-05,
      "loss": 0.8142,
      "step": 326
    },
    {
      "epoch": 2.1516483516483516,
      "grad_norm": 0.6914520263671875,
      "learning_rate": 5.7649667405764975e-05,
      "loss": 0.7526,
      "step": 327
    },
    {
      "epoch": 2.158241758241758,
      "grad_norm": 0.7216525673866272,
      "learning_rate": 5.720620842572062e-05,
      "loss": 0.8612,
      "step": 328
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 0.7188699841499329,
      "learning_rate": 5.676274944567628e-05,
      "loss": 0.8917,
      "step": 329
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.7169713377952576,
      "learning_rate": 5.6319290465631935e-05,
      "loss": 0.7069,
      "step": 330
    },
    {
      "epoch": 2.178021978021978,
      "grad_norm": 0.5513160228729248,
      "learning_rate": 5.587583148558758e-05,
      "loss": 0.6421,
      "step": 331
    },
    {
      "epoch": 2.184615384615385,
      "grad_norm": 0.5431884527206421,
      "learning_rate": 5.543237250554324e-05,
      "loss": 0.6776,
      "step": 332
    },
    {
      "epoch": 2.1912087912087914,
      "grad_norm": 0.6243288516998291,
      "learning_rate": 5.4988913525498895e-05,
      "loss": 0.6749,
      "step": 333
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.7112690210342407,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.6938,
      "step": 334
    },
    {
      "epoch": 2.2043956043956046,
      "grad_norm": 0.6238105893135071,
      "learning_rate": 5.4101995565410204e-05,
      "loss": 0.5502,
      "step": 335
    },
    {
      "epoch": 2.210989010989011,
      "grad_norm": 0.6335462927818298,
      "learning_rate": 5.365853658536586e-05,
      "loss": 0.6563,
      "step": 336
    },
    {
      "epoch": 2.2175824175824177,
      "grad_norm": 0.6057775020599365,
      "learning_rate": 5.3215077605321506e-05,
      "loss": 0.6975,
      "step": 337
    },
    {
      "epoch": 2.2241758241758243,
      "grad_norm": 0.6290048360824585,
      "learning_rate": 5.2771618625277164e-05,
      "loss": 0.745,
      "step": 338
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.5167511701583862,
      "learning_rate": 5.232815964523282e-05,
      "loss": 0.6588,
      "step": 339
    },
    {
      "epoch": 2.2373626373626374,
      "grad_norm": 0.6949765682220459,
      "learning_rate": 5.1884700665188466e-05,
      "loss": 0.7472,
      "step": 340
    },
    {
      "epoch": 2.243956043956044,
      "grad_norm": 0.7215961217880249,
      "learning_rate": 5.1441241685144124e-05,
      "loss": 0.6612,
      "step": 341
    },
    {
      "epoch": 2.2505494505494505,
      "grad_norm": 0.510892927646637,
      "learning_rate": 5.099778270509978e-05,
      "loss": 0.6527,
      "step": 342
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 0.731456995010376,
      "learning_rate": 5.0554323725055433e-05,
      "loss": 0.7226,
      "step": 343
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 0.6512704491615295,
      "learning_rate": 5.011086474501109e-05,
      "loss": 0.6743,
      "step": 344
    },
    {
      "epoch": 2.2703296703296703,
      "grad_norm": 0.651498556137085,
      "learning_rate": 4.966740576496674e-05,
      "loss": 0.7466,
      "step": 345
    },
    {
      "epoch": 2.276923076923077,
      "grad_norm": 0.5663884282112122,
      "learning_rate": 4.92239467849224e-05,
      "loss": 0.5927,
      "step": 346
    },
    {
      "epoch": 2.2835164835164834,
      "grad_norm": 0.674555778503418,
      "learning_rate": 4.878048780487805e-05,
      "loss": 0.8744,
      "step": 347
    },
    {
      "epoch": 2.29010989010989,
      "grad_norm": 0.7060825228691101,
      "learning_rate": 4.833702882483371e-05,
      "loss": 0.6693,
      "step": 348
    },
    {
      "epoch": 2.2967032967032965,
      "grad_norm": 0.7182577252388,
      "learning_rate": 4.789356984478936e-05,
      "loss": 0.5812,
      "step": 349
    },
    {
      "epoch": 2.303296703296703,
      "grad_norm": 0.6156234741210938,
      "learning_rate": 4.745011086474501e-05,
      "loss": 0.7247,
      "step": 350
    },
    {
      "epoch": 2.3098901098901097,
      "grad_norm": 0.6124761700630188,
      "learning_rate": 4.700665188470067e-05,
      "loss": 0.5423,
      "step": 351
    },
    {
      "epoch": 2.3164835164835162,
      "grad_norm": 0.6417215466499329,
      "learning_rate": 4.656319290465632e-05,
      "loss": 0.8036,
      "step": 352
    },
    {
      "epoch": 2.3230769230769233,
      "grad_norm": 0.7024691700935364,
      "learning_rate": 4.611973392461197e-05,
      "loss": 0.7742,
      "step": 353
    },
    {
      "epoch": 2.32967032967033,
      "grad_norm": 0.7200444936752319,
      "learning_rate": 4.567627494456763e-05,
      "loss": 0.7953,
      "step": 354
    },
    {
      "epoch": 2.3362637362637364,
      "grad_norm": 0.6519104838371277,
      "learning_rate": 4.523281596452328e-05,
      "loss": 0.8102,
      "step": 355
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 0.7219530344009399,
      "learning_rate": 4.478935698447894e-05,
      "loss": 0.7355,
      "step": 356
    },
    {
      "epoch": 2.3494505494505495,
      "grad_norm": 0.7919983863830566,
      "learning_rate": 4.4345898004434597e-05,
      "loss": 0.8659,
      "step": 357
    },
    {
      "epoch": 2.356043956043956,
      "grad_norm": 0.756294846534729,
      "learning_rate": 4.390243902439025e-05,
      "loss": 0.7903,
      "step": 358
    },
    {
      "epoch": 2.3626373626373627,
      "grad_norm": 0.7363466024398804,
      "learning_rate": 4.34589800443459e-05,
      "loss": 0.6673,
      "step": 359
    },
    {
      "epoch": 2.3692307692307693,
      "grad_norm": 0.4577414095401764,
      "learning_rate": 4.301552106430156e-05,
      "loss": 0.4714,
      "step": 360
    },
    {
      "epoch": 2.375824175824176,
      "grad_norm": 0.6378329992294312,
      "learning_rate": 4.257206208425721e-05,
      "loss": 0.5701,
      "step": 361
    },
    {
      "epoch": 2.3824175824175824,
      "grad_norm": 0.7127747535705566,
      "learning_rate": 4.212860310421286e-05,
      "loss": 0.6576,
      "step": 362
    },
    {
      "epoch": 2.389010989010989,
      "grad_norm": 0.7423340678215027,
      "learning_rate": 4.168514412416852e-05,
      "loss": 0.702,
      "step": 363
    },
    {
      "epoch": 2.3956043956043955,
      "grad_norm": 0.6840337514877319,
      "learning_rate": 4.124168514412417e-05,
      "loss": 0.7787,
      "step": 364
    },
    {
      "epoch": 2.402197802197802,
      "grad_norm": 0.6408001780509949,
      "learning_rate": 4.0798226164079826e-05,
      "loss": 0.8465,
      "step": 365
    },
    {
      "epoch": 2.4087912087912087,
      "grad_norm": 0.7359005808830261,
      "learning_rate": 4.035476718403548e-05,
      "loss": 0.6091,
      "step": 366
    },
    {
      "epoch": 2.4153846153846152,
      "grad_norm": 0.6782566905021667,
      "learning_rate": 3.9911308203991135e-05,
      "loss": 0.7427,
      "step": 367
    },
    {
      "epoch": 2.421978021978022,
      "grad_norm": 0.6211289763450623,
      "learning_rate": 3.9467849223946786e-05,
      "loss": 0.7191,
      "step": 368
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.7456162571907043,
      "learning_rate": 3.9024390243902444e-05,
      "loss": 0.6316,
      "step": 369
    },
    {
      "epoch": 2.4351648351648354,
      "grad_norm": 0.76494300365448,
      "learning_rate": 3.8580931263858095e-05,
      "loss": 0.9598,
      "step": 370
    },
    {
      "epoch": 2.441758241758242,
      "grad_norm": 0.699178159236908,
      "learning_rate": 3.8137472283813746e-05,
      "loss": 0.6878,
      "step": 371
    },
    {
      "epoch": 2.4483516483516485,
      "grad_norm": 0.6407485008239746,
      "learning_rate": 3.7694013303769404e-05,
      "loss": 0.7074,
      "step": 372
    },
    {
      "epoch": 2.454945054945055,
      "grad_norm": 0.5461326241493225,
      "learning_rate": 3.7250554323725055e-05,
      "loss": 0.632,
      "step": 373
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.8245248198509216,
      "learning_rate": 3.6807095343680706e-05,
      "loss": 0.7632,
      "step": 374
    },
    {
      "epoch": 2.4681318681318682,
      "grad_norm": 0.7752164602279663,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.8062,
      "step": 375
    },
    {
      "epoch": 2.474725274725275,
      "grad_norm": 0.6900202631950378,
      "learning_rate": 3.5920177383592015e-05,
      "loss": 0.689,
      "step": 376
    },
    {
      "epoch": 2.4813186813186814,
      "grad_norm": 0.6894698739051819,
      "learning_rate": 3.547671840354767e-05,
      "loss": 0.685,
      "step": 377
    },
    {
      "epoch": 2.487912087912088,
      "grad_norm": 0.743312418460846,
      "learning_rate": 3.503325942350333e-05,
      "loss": 0.6954,
      "step": 378
    },
    {
      "epoch": 2.4945054945054945,
      "grad_norm": 0.7428473234176636,
      "learning_rate": 3.458980044345898e-05,
      "loss": 0.6586,
      "step": 379
    },
    {
      "epoch": 2.501098901098901,
      "grad_norm": 0.6857025027275085,
      "learning_rate": 3.414634146341464e-05,
      "loss": 0.659,
      "step": 380
    },
    {
      "epoch": 2.5076923076923077,
      "grad_norm": 0.691189169883728,
      "learning_rate": 3.370288248337029e-05,
      "loss": 0.7909,
      "step": 381
    },
    {
      "epoch": 2.5142857142857142,
      "grad_norm": 0.7529495358467102,
      "learning_rate": 3.325942350332594e-05,
      "loss": 0.6971,
      "step": 382
    },
    {
      "epoch": 2.520879120879121,
      "grad_norm": 0.8102642297744751,
      "learning_rate": 3.28159645232816e-05,
      "loss": 0.7354,
      "step": 383
    },
    {
      "epoch": 2.5274725274725274,
      "grad_norm": 0.6831857562065125,
      "learning_rate": 3.237250554323725e-05,
      "loss": 0.6553,
      "step": 384
    },
    {
      "epoch": 2.534065934065934,
      "grad_norm": 0.7702910304069519,
      "learning_rate": 3.19290465631929e-05,
      "loss": 0.5866,
      "step": 385
    },
    {
      "epoch": 2.5406593406593405,
      "grad_norm": 0.7641969323158264,
      "learning_rate": 3.148558758314856e-05,
      "loss": 0.7697,
      "step": 386
    },
    {
      "epoch": 2.547252747252747,
      "grad_norm": 0.6161828637123108,
      "learning_rate": 3.104212860310421e-05,
      "loss": 0.6594,
      "step": 387
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.6707410216331482,
      "learning_rate": 3.059866962305987e-05,
      "loss": 0.7081,
      "step": 388
    },
    {
      "epoch": 2.5604395604395602,
      "grad_norm": 0.7885312438011169,
      "learning_rate": 3.0155210643015524e-05,
      "loss": 0.7696,
      "step": 389
    },
    {
      "epoch": 2.567032967032967,
      "grad_norm": 0.7820473909378052,
      "learning_rate": 2.971175166297118e-05,
      "loss": 0.6843,
      "step": 390
    },
    {
      "epoch": 2.5736263736263734,
      "grad_norm": 0.7199775576591492,
      "learning_rate": 2.926829268292683e-05,
      "loss": 0.869,
      "step": 391
    },
    {
      "epoch": 2.5802197802197804,
      "grad_norm": 0.7974603772163391,
      "learning_rate": 2.8824833702882487e-05,
      "loss": 0.7899,
      "step": 392
    },
    {
      "epoch": 2.586813186813187,
      "grad_norm": 0.6653918623924255,
      "learning_rate": 2.838137472283814e-05,
      "loss": 0.6094,
      "step": 393
    },
    {
      "epoch": 2.5934065934065935,
      "grad_norm": 0.6833547949790955,
      "learning_rate": 2.793791574279379e-05,
      "loss": 0.6213,
      "step": 394
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.6442340016365051,
      "learning_rate": 2.7494456762749448e-05,
      "loss": 0.6882,
      "step": 395
    },
    {
      "epoch": 2.6065934065934067,
      "grad_norm": 0.7573860883712769,
      "learning_rate": 2.7050997782705102e-05,
      "loss": 0.5794,
      "step": 396
    },
    {
      "epoch": 2.6131868131868132,
      "grad_norm": 0.755738377571106,
      "learning_rate": 2.6607538802660753e-05,
      "loss": 0.7129,
      "step": 397
    },
    {
      "epoch": 2.61978021978022,
      "grad_norm": 0.6064629554748535,
      "learning_rate": 2.616407982261641e-05,
      "loss": 0.5524,
      "step": 398
    },
    {
      "epoch": 2.6263736263736264,
      "grad_norm": 0.7285276651382446,
      "learning_rate": 2.5720620842572062e-05,
      "loss": 0.6526,
      "step": 399
    },
    {
      "epoch": 2.632967032967033,
      "grad_norm": 0.711154043674469,
      "learning_rate": 2.5277161862527717e-05,
      "loss": 0.7591,
      "step": 400
    },
    {
      "epoch": 2.6395604395604395,
      "grad_norm": 0.6310650110244751,
      "learning_rate": 2.483370288248337e-05,
      "loss": 0.5711,
      "step": 401
    },
    {
      "epoch": 2.646153846153846,
      "grad_norm": 0.6208779811859131,
      "learning_rate": 2.4390243902439026e-05,
      "loss": 0.5996,
      "step": 402
    },
    {
      "epoch": 2.6527472527472526,
      "grad_norm": 0.7026847004890442,
      "learning_rate": 2.394678492239468e-05,
      "loss": 0.7114,
      "step": 403
    },
    {
      "epoch": 2.659340659340659,
      "grad_norm": 0.7767087817192078,
      "learning_rate": 2.3503325942350335e-05,
      "loss": 0.7036,
      "step": 404
    },
    {
      "epoch": 2.665934065934066,
      "grad_norm": 0.7058011889457703,
      "learning_rate": 2.3059866962305986e-05,
      "loss": 0.7313,
      "step": 405
    },
    {
      "epoch": 2.672527472527473,
      "grad_norm": 0.7921257019042969,
      "learning_rate": 2.261640798226164e-05,
      "loss": 0.6598,
      "step": 406
    },
    {
      "epoch": 2.6791208791208794,
      "grad_norm": 0.8462347984313965,
      "learning_rate": 2.2172949002217298e-05,
      "loss": 0.7092,
      "step": 407
    },
    {
      "epoch": 2.685714285714286,
      "grad_norm": 0.8546882271766663,
      "learning_rate": 2.172949002217295e-05,
      "loss": 0.7527,
      "step": 408
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.6981221437454224,
      "learning_rate": 2.1286031042128604e-05,
      "loss": 0.798,
      "step": 409
    },
    {
      "epoch": 2.698901098901099,
      "grad_norm": 0.6834746599197388,
      "learning_rate": 2.084257206208426e-05,
      "loss": 0.6623,
      "step": 410
    },
    {
      "epoch": 2.7054945054945057,
      "grad_norm": 0.7084916234016418,
      "learning_rate": 2.0399113082039913e-05,
      "loss": 0.6304,
      "step": 411
    },
    {
      "epoch": 2.7120879120879122,
      "grad_norm": 0.6562837958335876,
      "learning_rate": 1.9955654101995567e-05,
      "loss": 0.7604,
      "step": 412
    },
    {
      "epoch": 2.718681318681319,
      "grad_norm": 0.7399200201034546,
      "learning_rate": 1.9512195121951222e-05,
      "loss": 0.7445,
      "step": 413
    },
    {
      "epoch": 2.7252747252747254,
      "grad_norm": 0.7633038759231567,
      "learning_rate": 1.9068736141906873e-05,
      "loss": 0.6965,
      "step": 414
    },
    {
      "epoch": 2.731868131868132,
      "grad_norm": 0.6780048608779907,
      "learning_rate": 1.8625277161862528e-05,
      "loss": 0.7226,
      "step": 415
    },
    {
      "epoch": 2.7384615384615385,
      "grad_norm": 0.7924910187721252,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.6453,
      "step": 416
    },
    {
      "epoch": 2.745054945054945,
      "grad_norm": 0.8024608492851257,
      "learning_rate": 1.7738359201773837e-05,
      "loss": 0.7223,
      "step": 417
    },
    {
      "epoch": 2.7516483516483516,
      "grad_norm": 0.6756635308265686,
      "learning_rate": 1.729490022172949e-05,
      "loss": 0.7092,
      "step": 418
    },
    {
      "epoch": 2.758241758241758,
      "grad_norm": 0.7710825800895691,
      "learning_rate": 1.6851441241685146e-05,
      "loss": 0.6941,
      "step": 419
    },
    {
      "epoch": 2.764835164835165,
      "grad_norm": 0.7406888008117676,
      "learning_rate": 1.64079822616408e-05,
      "loss": 0.7118,
      "step": 420
    },
    {
      "epoch": 2.7714285714285714,
      "grad_norm": 0.9230878353118896,
      "learning_rate": 1.596452328159645e-05,
      "loss": 0.6651,
      "step": 421
    },
    {
      "epoch": 2.778021978021978,
      "grad_norm": 0.813704252243042,
      "learning_rate": 1.5521064301552106e-05,
      "loss": 0.7587,
      "step": 422
    },
    {
      "epoch": 2.7846153846153845,
      "grad_norm": 0.656252920627594,
      "learning_rate": 1.5077605321507762e-05,
      "loss": 0.6469,
      "step": 423
    },
    {
      "epoch": 2.791208791208791,
      "grad_norm": 0.8923037648200989,
      "learning_rate": 1.4634146341463415e-05,
      "loss": 0.8542,
      "step": 424
    },
    {
      "epoch": 2.7978021978021976,
      "grad_norm": 0.8174076676368713,
      "learning_rate": 1.419068736141907e-05,
      "loss": 0.8131,
      "step": 425
    },
    {
      "epoch": 2.804395604395604,
      "grad_norm": 0.7854478359222412,
      "learning_rate": 1.3747228381374724e-05,
      "loss": 0.7304,
      "step": 426
    },
    {
      "epoch": 2.8109890109890108,
      "grad_norm": 0.8396859169006348,
      "learning_rate": 1.3303769401330377e-05,
      "loss": 0.7908,
      "step": 427
    },
    {
      "epoch": 2.8175824175824173,
      "grad_norm": 0.7249636650085449,
      "learning_rate": 1.2860310421286031e-05,
      "loss": 0.7164,
      "step": 428
    },
    {
      "epoch": 2.824175824175824,
      "grad_norm": 0.6814908981323242,
      "learning_rate": 1.2416851441241686e-05,
      "loss": 0.5167,
      "step": 429
    },
    {
      "epoch": 2.830769230769231,
      "grad_norm": 0.6904162168502808,
      "learning_rate": 1.197339246119734e-05,
      "loss": 0.7017,
      "step": 430
    },
    {
      "epoch": 2.8373626373626375,
      "grad_norm": 0.8621271848678589,
      "learning_rate": 1.1529933481152993e-05,
      "loss": 0.6564,
      "step": 431
    },
    {
      "epoch": 2.843956043956044,
      "grad_norm": 0.7942920327186584,
      "learning_rate": 1.1086474501108649e-05,
      "loss": 0.7986,
      "step": 432
    },
    {
      "epoch": 2.8505494505494506,
      "grad_norm": 0.8235623836517334,
      "learning_rate": 1.0643015521064302e-05,
      "loss": 0.8021,
      "step": 433
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.8427809476852417,
      "learning_rate": 1.0199556541019956e-05,
      "loss": 0.7267,
      "step": 434
    },
    {
      "epoch": 2.8637362637362638,
      "grad_norm": 0.7525250315666199,
      "learning_rate": 9.756097560975611e-06,
      "loss": 0.7237,
      "step": 435
    },
    {
      "epoch": 2.8703296703296703,
      "grad_norm": 0.786842942237854,
      "learning_rate": 9.312638580931264e-06,
      "loss": 0.7819,
      "step": 436
    },
    {
      "epoch": 2.876923076923077,
      "grad_norm": 0.708014965057373,
      "learning_rate": 8.869179600886918e-06,
      "loss": 0.7342,
      "step": 437
    },
    {
      "epoch": 2.8835164835164835,
      "grad_norm": 0.6295266151428223,
      "learning_rate": 8.425720620842573e-06,
      "loss": 0.6041,
      "step": 438
    },
    {
      "epoch": 2.89010989010989,
      "grad_norm": 0.7611504197120667,
      "learning_rate": 7.982261640798226e-06,
      "loss": 0.6615,
      "step": 439
    },
    {
      "epoch": 2.8967032967032966,
      "grad_norm": 0.759299099445343,
      "learning_rate": 7.538802660753881e-06,
      "loss": 0.7634,
      "step": 440
    },
    {
      "epoch": 2.903296703296703,
      "grad_norm": 0.6968246102333069,
      "learning_rate": 7.095343680709535e-06,
      "loss": 0.8211,
      "step": 441
    },
    {
      "epoch": 2.9098901098901098,
      "grad_norm": 0.886398434638977,
      "learning_rate": 6.651884700665188e-06,
      "loss": 0.829,
      "step": 442
    },
    {
      "epoch": 2.9164835164835163,
      "grad_norm": 0.6937124729156494,
      "learning_rate": 6.208425720620843e-06,
      "loss": 0.6515,
      "step": 443
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.7284226417541504,
      "learning_rate": 5.7649667405764965e-06,
      "loss": 0.7449,
      "step": 444
    },
    {
      "epoch": 2.92967032967033,
      "grad_norm": 0.8096718192100525,
      "learning_rate": 5.321507760532151e-06,
      "loss": 0.8422,
      "step": 445
    },
    {
      "epoch": 2.9362637362637365,
      "grad_norm": 0.6692107915878296,
      "learning_rate": 4.8780487804878055e-06,
      "loss": 0.7686,
      "step": 446
    },
    {
      "epoch": 2.942857142857143,
      "grad_norm": 0.764277458190918,
      "learning_rate": 4.434589800443459e-06,
      "loss": 0.7234,
      "step": 447
    },
    {
      "epoch": 2.9494505494505496,
      "grad_norm": 0.7769583463668823,
      "learning_rate": 3.991130820399113e-06,
      "loss": 0.7756,
      "step": 448
    },
    {
      "epoch": 2.956043956043956,
      "grad_norm": 0.8534997701644897,
      "learning_rate": 3.5476718403547673e-06,
      "loss": 0.7584,
      "step": 449
    },
    {
      "epoch": 2.9626373626373628,
      "grad_norm": 0.8344732522964478,
      "learning_rate": 3.1042128603104214e-06,
      "loss": 0.6661,
      "step": 450
    },
    {
      "epoch": 2.9692307692307693,
      "grad_norm": 0.795549750328064,
      "learning_rate": 2.6607538802660755e-06,
      "loss": 0.8384,
      "step": 451
    },
    {
      "epoch": 2.975824175824176,
      "grad_norm": 0.8564179539680481,
      "learning_rate": 2.2172949002217296e-06,
      "loss": 0.7071,
      "step": 452
    },
    {
      "epoch": 2.9824175824175825,
      "grad_norm": 0.8729435205459595,
      "learning_rate": 1.7738359201773837e-06,
      "loss": 0.6735,
      "step": 453
    },
    {
      "epoch": 2.989010989010989,
      "grad_norm": 0.7816163897514343,
      "learning_rate": 1.3303769401330377e-06,
      "loss": 0.7315,
      "step": 454
    },
    {
      "epoch": 2.9956043956043956,
      "grad_norm": 0.8512691259384155,
      "learning_rate": 8.869179600886918e-07,
      "loss": 0.718,
      "step": 455
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.1011788845062256,
      "learning_rate": 4.434589800443459e-07,
      "loss": 0.7783,
      "step": 456
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.28802532318249e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}