{
  "best_metric": 10.34481143951416,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 2.6936026936026938,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013468013468013467,
      "grad_norm": 0.04948703572154045,
      "learning_rate": 1e-05,
      "loss": 10.3779,
      "step": 1
    },
    {
      "epoch": 0.013468013468013467,
      "eval_loss": 10.373967170715332,
      "eval_runtime": 0.2823,
      "eval_samples_per_second": 442.792,
      "eval_steps_per_second": 113.355,
      "step": 1
    },
    {
      "epoch": 0.026936026936026935,
      "grad_norm": 0.04768728092312813,
      "learning_rate": 2e-05,
      "loss": 10.3794,
      "step": 2
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 0.04607202857732773,
      "learning_rate": 3e-05,
      "loss": 10.3769,
      "step": 3
    },
    {
      "epoch": 0.05387205387205387,
      "grad_norm": 0.045074257999658585,
      "learning_rate": 4e-05,
      "loss": 10.372,
      "step": 4
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 0.04999054595828056,
      "learning_rate": 5e-05,
      "loss": 10.3747,
      "step": 5
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 0.05577779933810234,
      "learning_rate": 6e-05,
      "loss": 10.3724,
      "step": 6
    },
    {
      "epoch": 0.09427609427609428,
      "grad_norm": 0.05278445780277252,
      "learning_rate": 7e-05,
      "loss": 10.3755,
      "step": 7
    },
    {
      "epoch": 0.10774410774410774,
      "grad_norm": 0.05606238171458244,
      "learning_rate": 8e-05,
      "loss": 10.374,
      "step": 8
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.05272321775555611,
      "learning_rate": 9e-05,
      "loss": 10.3749,
      "step": 9
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 0.061876486986875534,
      "learning_rate": 0.0001,
      "loss": 10.3744,
      "step": 10
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.05089195817708969,
      "learning_rate": 9.999316524962345e-05,
      "loss": 10.3699,
      "step": 11
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 0.06507832556962967,
      "learning_rate": 9.997266286704631e-05,
      "loss": 10.3741,
      "step": 12
    },
    {
      "epoch": 0.1750841750841751,
      "grad_norm": 0.05796496570110321,
      "learning_rate": 9.993849845741524e-05,
      "loss": 10.375,
      "step": 13
    },
    {
      "epoch": 0.18855218855218855,
      "grad_norm": 0.06485222280025482,
      "learning_rate": 9.989068136093873e-05,
      "loss": 10.3743,
      "step": 14
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 0.07092849165201187,
      "learning_rate": 9.98292246503335e-05,
      "loss": 10.3717,
      "step": 15
    },
    {
      "epoch": 0.21548821548821548,
      "grad_norm": 0.059462081640958786,
      "learning_rate": 9.975414512725057e-05,
      "loss": 10.3717,
      "step": 16
    },
    {
      "epoch": 0.22895622895622897,
      "grad_norm": 0.06747805327177048,
      "learning_rate": 9.966546331768191e-05,
      "loss": 10.3693,
      "step": 17
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.07929842174053192,
      "learning_rate": 9.956320346634876e-05,
      "loss": 10.3711,
      "step": 18
    },
    {
      "epoch": 0.2558922558922559,
      "grad_norm": 0.04987971484661102,
      "learning_rate": 9.944739353007344e-05,
      "loss": 10.3729,
      "step": 19
    },
    {
      "epoch": 0.26936026936026936,
      "grad_norm": 0.04955197870731354,
      "learning_rate": 9.931806517013612e-05,
      "loss": 10.3739,
      "step": 20
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 0.06165743246674538,
      "learning_rate": 9.917525374361912e-05,
      "loss": 10.3725,
      "step": 21
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.06283538788557053,
      "learning_rate": 9.901899829374047e-05,
      "loss": 10.3732,
      "step": 22
    },
    {
      "epoch": 0.30976430976430974,
      "grad_norm": 0.06416889280080795,
      "learning_rate": 9.884934153917997e-05,
      "loss": 10.3738,
      "step": 23
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 0.05778920277953148,
      "learning_rate": 9.86663298624003e-05,
      "loss": 10.3734,
      "step": 24
    },
    {
      "epoch": 0.3367003367003367,
      "grad_norm": 0.06930460780858994,
      "learning_rate": 9.847001329696653e-05,
      "loss": 10.3677,
      "step": 25
    },
    {
      "epoch": 0.3501683501683502,
      "grad_norm": 0.07306807488203049,
      "learning_rate": 9.826044551386744e-05,
      "loss": 10.3708,
      "step": 26
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.07593240588903427,
      "learning_rate": 9.803768380684242e-05,
      "loss": 10.3697,
      "step": 27
    },
    {
      "epoch": 0.3771043771043771,
      "grad_norm": 0.08581344038248062,
      "learning_rate": 9.780178907671789e-05,
      "loss": 10.372,
      "step": 28
    },
    {
      "epoch": 0.39057239057239057,
      "grad_norm": 0.09118858724832535,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3675,
      "step": 29
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 0.10562589764595032,
      "learning_rate": 9.729086208503174e-05,
      "loss": 10.367,
      "step": 30
    },
    {
      "epoch": 0.4175084175084175,
      "grad_norm": 0.09139563888311386,
      "learning_rate": 9.701596950580806e-05,
      "loss": 10.3678,
      "step": 31
    },
    {
      "epoch": 0.43097643097643096,
      "grad_norm": 0.09762820601463318,
      "learning_rate": 9.672822322997305e-05,
      "loss": 10.3664,
      "step": 32
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.12784236669540405,
      "learning_rate": 9.642770192448536e-05,
      "loss": 10.3682,
      "step": 33
    },
    {
      "epoch": 0.45791245791245794,
      "grad_norm": 0.10227736085653305,
      "learning_rate": 9.611448774886924e-05,
      "loss": 10.3674,
      "step": 34
    },
    {
      "epoch": 0.4713804713804714,
      "grad_norm": 0.12423071265220642,
      "learning_rate": 9.578866633275288e-05,
      "loss": 10.3654,
      "step": 35
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.11180764436721802,
      "learning_rate": 9.545032675245813e-05,
      "loss": 10.3683,
      "step": 36
    },
    {
      "epoch": 0.4983164983164983,
      "grad_norm": 0.09800101816654205,
      "learning_rate": 9.509956150664796e-05,
      "loss": 10.366,
      "step": 37
    },
    {
      "epoch": 0.5117845117845118,
      "grad_norm": 0.09123105555772781,
      "learning_rate": 9.473646649103818e-05,
      "loss": 10.368,
      "step": 38
    },
    {
      "epoch": 0.5252525252525253,
      "grad_norm": 0.1304626762866974,
      "learning_rate": 9.43611409721806e-05,
      "loss": 10.3681,
      "step": 39
    },
    {
      "epoch": 0.5387205387205387,
      "grad_norm": 0.10547351837158203,
      "learning_rate": 9.397368756032445e-05,
      "loss": 10.3665,
      "step": 40
    },
    {
      "epoch": 0.5521885521885522,
      "grad_norm": 0.11524995416402817,
      "learning_rate": 9.357421218136386e-05,
      "loss": 10.3608,
      "step": 41
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 0.122977614402771,
      "learning_rate": 9.316282404787871e-05,
      "loss": 10.3633,
      "step": 42
    },
    {
      "epoch": 0.5791245791245792,
      "grad_norm": 0.12059789150953293,
      "learning_rate": 9.273963562927695e-05,
      "loss": 10.3611,
      "step": 43
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.11756041646003723,
      "learning_rate": 9.230476262104677e-05,
      "loss": 10.3596,
      "step": 44
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.12892110645771027,
      "learning_rate": 9.185832391312644e-05,
      "loss": 10.3581,
      "step": 45
    },
    {
      "epoch": 0.6195286195286195,
      "grad_norm": 0.14496880769729614,
      "learning_rate": 9.140044155740101e-05,
      "loss": 10.3629,
      "step": 46
    },
    {
      "epoch": 0.632996632996633,
      "grad_norm": 0.11022935807704926,
      "learning_rate": 9.093124073433463e-05,
      "loss": 10.3637,
      "step": 47
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 0.11096550524234772,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3605,
      "step": 48
    },
    {
      "epoch": 0.6599326599326599,
      "grad_norm": 0.1276777684688568,
      "learning_rate": 8.995939984474624e-05,
      "loss": 10.3582,
      "step": 49
    },
    {
      "epoch": 0.6734006734006734,
      "grad_norm": 0.13111649453639984,
      "learning_rate": 8.945702546981969e-05,
      "loss": 10.3555,
      "step": 50
    },
    {
      "epoch": 0.6734006734006734,
      "eval_loss": 10.355432510375977,
      "eval_runtime": 0.276,
      "eval_samples_per_second": 452.841,
      "eval_steps_per_second": 115.927,
      "step": 50
    },
    {
      "epoch": 0.6868686868686869,
      "grad_norm": 0.1373024433851242,
      "learning_rate": 8.894386393810563e-05,
      "loss": 10.3611,
      "step": 51
    },
    {
      "epoch": 0.7003367003367004,
      "grad_norm": 0.1361517757177353,
      "learning_rate": 8.842005554284296e-05,
      "loss": 10.3588,
      "step": 52
    },
    {
      "epoch": 0.7138047138047138,
      "grad_norm": 0.11209013313055038,
      "learning_rate": 8.788574348801675e-05,
      "loss": 10.3566,
      "step": 53
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.14856919646263123,
      "learning_rate": 8.73410738492077e-05,
      "loss": 10.3578,
      "step": 54
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.09652044624090195,
      "learning_rate": 8.678619553365659e-05,
      "loss": 10.3567,
      "step": 55
    },
    {
      "epoch": 0.7542087542087542,
      "grad_norm": 0.09809385985136032,
      "learning_rate": 8.622126023955446e-05,
      "loss": 10.3558,
      "step": 56
    },
    {
      "epoch": 0.7676767676767676,
      "grad_norm": 0.10108034312725067,
      "learning_rate": 8.564642241456986e-05,
      "loss": 10.3579,
      "step": 57
    },
    {
      "epoch": 0.7811447811447811,
      "grad_norm": 0.08144769817590714,
      "learning_rate": 8.506183921362443e-05,
      "loss": 10.3539,
      "step": 58
    },
    {
      "epoch": 0.7946127946127947,
      "grad_norm": 0.08322631567716599,
      "learning_rate": 8.44676704559283e-05,
      "loss": 10.3594,
      "step": 59
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 0.08635346591472626,
      "learning_rate": 8.386407858128706e-05,
      "loss": 10.3538,
      "step": 60
    },
    {
      "epoch": 0.8215488215488216,
      "grad_norm": 0.10105765610933304,
      "learning_rate": 8.32512286056924e-05,
      "loss": 10.3502,
      "step": 61
    },
    {
      "epoch": 0.835016835016835,
      "grad_norm": 0.07694767415523529,
      "learning_rate": 8.262928807620843e-05,
      "loss": 10.3533,
      "step": 62
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 0.07848487049341202,
      "learning_rate": 8.199842702516583e-05,
      "loss": 10.3489,
      "step": 63
    },
    {
      "epoch": 0.8619528619528619,
      "grad_norm": 0.09165403246879578,
      "learning_rate": 8.135881792367686e-05,
      "loss": 10.3568,
      "step": 64
    },
    {
      "epoch": 0.8754208754208754,
      "grad_norm": 0.08877912163734436,
      "learning_rate": 8.07106356344834e-05,
      "loss": 10.3549,
      "step": 65
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.10322596877813339,
      "learning_rate": 8.005405736415126e-05,
      "loss": 10.3522,
      "step": 66
    },
    {
      "epoch": 0.9023569023569024,
      "grad_norm": 0.0847981721162796,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3565,
      "step": 67
    },
    {
      "epoch": 0.9158249158249159,
      "grad_norm": 0.11963289976119995,
      "learning_rate": 7.871643313414718e-05,
      "loss": 10.3542,
      "step": 68
    },
    {
      "epoch": 0.9292929292929293,
      "grad_norm": 0.12358040362596512,
      "learning_rate": 7.803575286758364e-05,
      "loss": 10.3528,
      "step": 69
    },
    {
      "epoch": 0.9427609427609428,
      "grad_norm": 0.11090252548456192,
      "learning_rate": 7.734740790612136e-05,
      "loss": 10.3595,
      "step": 70
    },
    {
      "epoch": 0.9562289562289562,
      "grad_norm": 0.12658852338790894,
      "learning_rate": 7.66515864363997e-05,
      "loss": 10.3576,
      "step": 71
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.2002861052751541,
      "learning_rate": 7.594847868906076e-05,
      "loss": 10.3626,
      "step": 72
    },
    {
      "epoch": 0.9831649831649831,
      "grad_norm": 0.07931201905012131,
      "learning_rate": 7.52382768867422e-05,
      "loss": 10.3509,
      "step": 73
    },
    {
      "epoch": 0.9966329966329966,
      "grad_norm": 0.07392469048500061,
      "learning_rate": 7.452117519152542e-05,
      "loss": 10.3544,
      "step": 74
    },
    {
      "epoch": 1.0101010101010102,
      "grad_norm": 0.2761108875274658,
      "learning_rate": 7.379736965185368e-05,
      "loss": 18.4303,
      "step": 75
    },
    {
      "epoch": 1.0235690235690236,
      "grad_norm": 0.06821335852146149,
      "learning_rate": 7.30670581489344e-05,
      "loss": 10.0565,
      "step": 76
    },
    {
      "epoch": 1.037037037037037,
      "grad_norm": 0.07589493691921234,
      "learning_rate": 7.233044034264034e-05,
      "loss": 10.2522,
      "step": 77
    },
    {
      "epoch": 1.0505050505050506,
      "grad_norm": 0.07571856677532196,
      "learning_rate": 7.158771761692464e-05,
      "loss": 10.413,
      "step": 78
    },
    {
      "epoch": 1.063973063973064,
      "grad_norm": 0.11319424211978912,
      "learning_rate": 7.083909302476453e-05,
      "loss": 10.5229,
      "step": 79
    },
    {
      "epoch": 1.0774410774410774,
      "grad_norm": 0.06916380673646927,
      "learning_rate": 7.008477123264848e-05,
      "loss": 10.3141,
      "step": 80
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.06370759755373001,
      "learning_rate": 6.932495846462261e-05,
      "loss": 10.1791,
      "step": 81
    },
    {
      "epoch": 1.1043771043771045,
      "grad_norm": 0.07580740749835968,
      "learning_rate": 6.855986244591104e-05,
      "loss": 10.3441,
      "step": 82
    },
    {
      "epoch": 1.1178451178451179,
      "grad_norm": 0.11109385639429092,
      "learning_rate": 6.778969234612584e-05,
      "loss": 10.5073,
      "step": 83
    },
    {
      "epoch": 1.1313131313131313,
      "grad_norm": 0.08346983045339584,
      "learning_rate": 6.701465872208216e-05,
      "loss": 10.3391,
      "step": 84
    },
    {
      "epoch": 1.144781144781145,
      "grad_norm": 0.08446172624826431,
      "learning_rate": 6.623497346023418e-05,
      "loss": 10.3035,
      "step": 85
    },
    {
      "epoch": 1.1582491582491583,
      "grad_norm": 0.08403271436691284,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3233,
      "step": 86
    },
    {
      "epoch": 1.1717171717171717,
      "grad_norm": 0.06150268763303757,
      "learning_rate": 6.466250186922325e-05,
      "loss": 10.3903,
      "step": 87
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.13861966133117676,
      "learning_rate": 6.387014543809223e-05,
      "loss": 10.4917,
      "step": 88
    },
    {
      "epoch": 1.1986531986531987,
      "grad_norm": 0.1120426207780838,
      "learning_rate": 6.307399704769099e-05,
      "loss": 10.3469,
      "step": 89
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 0.1144438087940216,
      "learning_rate": 6.227427435703997e-05,
      "loss": 10.3083,
      "step": 90
    },
    {
      "epoch": 1.2255892255892256,
      "grad_norm": 0.10067962855100632,
      "learning_rate": 6.147119600233758e-05,
      "loss": 10.208,
      "step": 91
    },
    {
      "epoch": 1.239057239057239,
      "grad_norm": 0.12961308658123016,
      "learning_rate": 6.066498153718735e-05,
      "loss": 10.5601,
      "step": 92
    },
    {
      "epoch": 1.2525252525252526,
      "grad_norm": 0.07210229337215424,
      "learning_rate": 5.985585137257401e-05,
      "loss": 10.3754,
      "step": 93
    },
    {
      "epoch": 1.265993265993266,
      "grad_norm": 0.06851514428853989,
      "learning_rate": 5.90440267166055e-05,
      "loss": 10.1755,
      "step": 94
    },
    {
      "epoch": 1.2794612794612794,
      "grad_norm": 0.06954556703567505,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 10.3431,
      "step": 95
    },
    {
      "epoch": 1.2929292929292928,
      "grad_norm": 0.10277853906154633,
      "learning_rate": 5.74131823855921e-05,
      "loss": 10.396,
      "step": 96
    },
    {
      "epoch": 1.3063973063973064,
      "grad_norm": 0.06646107137203217,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 10.3533,
      "step": 97
    },
    {
      "epoch": 1.3198653198653199,
      "grad_norm": 0.08708590269088745,
      "learning_rate": 5.577423184847932e-05,
      "loss": 10.3263,
      "step": 98
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.06862103193998337,
      "learning_rate": 5.495227651252315e-05,
      "loss": 10.5241,
      "step": 99
    },
    {
      "epoch": 1.3468013468013469,
      "grad_norm": 0.0658043622970581,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 10.1345,
      "step": 100
    },
    {
      "epoch": 1.3468013468013469,
      "eval_loss": 10.347537994384766,
      "eval_runtime": 0.2778,
      "eval_samples_per_second": 449.981,
      "eval_steps_per_second": 115.195,
      "step": 100
    },
    {
      "epoch": 1.3602693602693603,
      "grad_norm": 0.09986591339111328,
      "learning_rate": 5.330452921628497e-05,
      "loss": 10.3085,
      "step": 101
    },
    {
      "epoch": 1.3737373737373737,
      "grad_norm": 0.07463264465332031,
      "learning_rate": 5.247918773366112e-05,
      "loss": 10.624,
      "step": 102
    },
    {
      "epoch": 1.387205387205387,
      "grad_norm": 0.08060763031244278,
      "learning_rate": 5.165316846586541e-05,
      "loss": 10.2899,
      "step": 103
    },
    {
      "epoch": 1.4006734006734007,
      "grad_norm": 0.10077881813049316,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 10.135,
      "step": 104
    },
    {
      "epoch": 1.4141414141414141,
      "grad_norm": 0.07200150191783905,
      "learning_rate": 5e-05,
      "loss": 10.5765,
      "step": 105
    },
    {
      "epoch": 1.4276094276094276,
      "grad_norm": 0.08930617570877075,
      "learning_rate": 4.917330276168208e-05,
      "loss": 10.2447,
      "step": 106
    },
    {
      "epoch": 1.4410774410774412,
      "grad_norm": 0.13597853481769562,
      "learning_rate": 4.834683153413459e-05,
      "loss": 10.2787,
      "step": 107
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.13182705640792847,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 10.2947,
      "step": 108
    },
    {
      "epoch": 1.468013468013468,
      "grad_norm": 0.12229684740304947,
      "learning_rate": 4.669547078371504e-05,
      "loss": 10.4704,
      "step": 109
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 0.1501709371805191,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 10.3998,
      "step": 110
    },
    {
      "epoch": 1.494949494949495,
      "grad_norm": 0.09399032592773438,
      "learning_rate": 4.504772348747687e-05,
      "loss": 10.3866,
      "step": 111
    },
    {
      "epoch": 1.5084175084175084,
      "grad_norm": 0.0846509113907814,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 10.2691,
      "step": 112
    },
    {
      "epoch": 1.5218855218855218,
      "grad_norm": 0.09290160238742828,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 10.289,
      "step": 113
    },
    {
      "epoch": 1.5353535353535355,
      "grad_norm": 0.10921469330787659,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 10.3383,
      "step": 114
    },
    {
      "epoch": 1.5488215488215489,
      "grad_norm": 0.0893743485212326,
      "learning_rate": 4.17702704859633e-05,
      "loss": 10.3919,
      "step": 115
    },
    {
      "epoch": 1.5622895622895623,
      "grad_norm": 0.07425656914710999,
      "learning_rate": 4.095597328339452e-05,
      "loss": 10.2941,
      "step": 116
    },
    {
      "epoch": 1.5757575757575757,
      "grad_norm": 0.09040941298007965,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 10.418,
      "step": 117
    },
    {
      "epoch": 1.589225589225589,
      "grad_norm": 0.08472064137458801,
      "learning_rate": 3.933501846281267e-05,
      "loss": 10.5199,
      "step": 118
    },
    {
      "epoch": 1.6026936026936027,
      "grad_norm": 0.11523989588022232,
      "learning_rate": 3.852880399766243e-05,
      "loss": 10.1027,
      "step": 119
    },
    {
      "epoch": 1.6161616161616161,
      "grad_norm": 0.08889497071504593,
      "learning_rate": 3.772572564296005e-05,
      "loss": 10.3929,
      "step": 120
    },
    {
      "epoch": 1.6296296296296298,
      "grad_norm": 0.06373216956853867,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 10.3361,
      "step": 121
    },
    {
      "epoch": 1.6430976430976432,
      "grad_norm": 0.10492755472660065,
      "learning_rate": 3.612985456190778e-05,
      "loss": 10.4105,
      "step": 122
    },
    {
      "epoch": 1.6565656565656566,
      "grad_norm": 0.11437976360321045,
      "learning_rate": 3.533749813077677e-05,
      "loss": 10.2215,
      "step": 123
    },
    {
      "epoch": 1.67003367003367,
      "grad_norm": 0.10444636642932892,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.527,
      "step": 124
    },
    {
      "epoch": 1.6835016835016834,
      "grad_norm": 0.10957822948694229,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 10.132,
      "step": 125
    },
    {
      "epoch": 1.696969696969697,
      "grad_norm": 0.09705518186092377,
      "learning_rate": 3.298534127791785e-05,
      "loss": 10.3553,
      "step": 126
    },
    {
      "epoch": 1.7104377104377104,
      "grad_norm": 0.11563467234373093,
      "learning_rate": 3.221030765387417e-05,
      "loss": 10.5727,
      "step": 127
    },
    {
      "epoch": 1.723905723905724,
      "grad_norm": 0.15855231881141663,
      "learning_rate": 3.144013755408895e-05,
      "loss": 10.6883,
      "step": 128
    },
    {
      "epoch": 1.7373737373737375,
      "grad_norm": 0.07911287993192673,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 9.9991,
      "step": 129
    },
    {
      "epoch": 1.7508417508417509,
      "grad_norm": 0.07733754813671112,
      "learning_rate": 2.991522876735154e-05,
      "loss": 10.244,
      "step": 130
    },
    {
      "epoch": 1.7643097643097643,
      "grad_norm": 0.08639588952064514,
      "learning_rate": 2.916090697523549e-05,
      "loss": 10.1512,
      "step": 131
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.0744738057255745,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 10.5696,
      "step": 132
    },
    {
      "epoch": 1.791245791245791,
      "grad_norm": 0.07286791503429413,
      "learning_rate": 2.766955965735968e-05,
      "loss": 10.4254,
      "step": 133
    },
    {
      "epoch": 1.8047138047138047,
      "grad_norm": 0.09132079035043716,
      "learning_rate": 2.693294185106562e-05,
      "loss": 10.3155,
      "step": 134
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.09164854884147644,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 10.0967,
      "step": 135
    },
    {
      "epoch": 1.8316498316498318,
      "grad_norm": 0.10320233553647995,
      "learning_rate": 2.547882480847461e-05,
      "loss": 10.558,
      "step": 136
    },
    {
      "epoch": 1.8451178451178452,
      "grad_norm": 0.07293586432933807,
      "learning_rate": 2.476172311325783e-05,
      "loss": 10.3638,
      "step": 137
    },
    {
      "epoch": 1.8585858585858586,
      "grad_norm": 0.08990565687417984,
      "learning_rate": 2.405152131093926e-05,
      "loss": 10.3105,
      "step": 138
    },
    {
      "epoch": 1.872053872053872,
      "grad_norm": 0.08296056091785431,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 10.339,
      "step": 139
    },
    {
      "epoch": 1.8855218855218854,
      "grad_norm": 0.08532875031232834,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 10.2263,
      "step": 140
    },
    {
      "epoch": 1.898989898989899,
      "grad_norm": 0.07990080863237381,
      "learning_rate": 2.196424713241637e-05,
      "loss": 10.5779,
      "step": 141
    },
    {
      "epoch": 1.9124579124579124,
      "grad_norm": 0.08947526663541794,
      "learning_rate": 2.128356686585282e-05,
      "loss": 10.2954,
      "step": 142
    },
    {
      "epoch": 1.925925925925926,
      "grad_norm": 0.11442378163337708,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.4064,
      "step": 143
    },
    {
      "epoch": 1.9393939393939394,
      "grad_norm": 0.08506354689598083,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 10.3984,
      "step": 144
    },
    {
      "epoch": 1.9528619528619529,
      "grad_norm": 0.12100011110305786,
      "learning_rate": 1.928936436551661e-05,
      "loss": 10.2733,
      "step": 145
    },
    {
      "epoch": 1.9663299663299663,
      "grad_norm": 0.10722660273313522,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 10.5923,
      "step": 146
    },
    {
      "epoch": 1.9797979797979797,
      "grad_norm": 0.07393872737884521,
      "learning_rate": 1.800157297483417e-05,
      "loss": 10.5143,
      "step": 147
    },
    {
      "epoch": 1.9932659932659933,
      "grad_norm": 0.06809595972299576,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 10.3846,
      "step": 148
    },
    {
      "epoch": 2.006734006734007,
      "grad_norm": 0.34508776664733887,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 18.0587,
      "step": 149
    },
    {
      "epoch": 2.0202020202020203,
      "grad_norm": 0.08044521510601044,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 9.8434,
      "step": 150
    },
    {
      "epoch": 2.0202020202020203,
      "eval_loss": 10.345002174377441,
      "eval_runtime": 0.2761,
      "eval_samples_per_second": 452.655,
      "eval_steps_per_second": 115.88,
      "step": 150
    },
    {
      "epoch": 2.0336700336700337,
      "grad_norm": 0.09060797840356827,
      "learning_rate": 1.553232954407171e-05,
      "loss": 10.431,
      "step": 151
    },
    {
      "epoch": 2.047138047138047,
      "grad_norm": 0.09153641760349274,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 10.4801,
      "step": 152
    },
    {
      "epoch": 2.0606060606060606,
      "grad_norm": 0.08559516817331314,
      "learning_rate": 1.435357758543015e-05,
      "loss": 10.3074,
      "step": 153
    },
    {
      "epoch": 2.074074074074074,
      "grad_norm": 0.08177684992551804,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 10.3372,
      "step": 154
    },
    {
      "epoch": 2.0875420875420874,
      "grad_norm": 0.0665111318230629,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 10.2295,
      "step": 155
    },
    {
      "epoch": 2.101010101010101,
      "grad_norm": 0.08716362714767456,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 10.6088,
      "step": 156
    },
    {
      "epoch": 2.1144781144781146,
      "grad_norm": 0.06661536544561386,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 10.4011,
      "step": 157
    },
    {
      "epoch": 2.127946127946128,
      "grad_norm": 0.08193931728601456,
      "learning_rate": 1.157994445715706e-05,
      "loss": 10.182,
      "step": 158
    },
    {
      "epoch": 2.1414141414141414,
      "grad_norm": 0.10440803319215775,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 10.4073,
      "step": 159
    },
    {
      "epoch": 2.154882154882155,
      "grad_norm": 0.08257047832012177,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 10.3952,
      "step": 160
    },
    {
      "epoch": 2.1683501683501682,
      "grad_norm": 0.06713279336690903,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 10.0706,
      "step": 161
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.05952250957489014,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.4215,
      "step": 162
    },
    {
      "epoch": 2.1952861952861955,
      "grad_norm": 0.06925564259290695,
      "learning_rate": 9.068759265665384e-06,
      "loss": 10.4482,
      "step": 163
    },
    {
      "epoch": 2.208754208754209,
      "grad_norm": 0.12750621140003204,
      "learning_rate": 8.599558442598998e-06,
      "loss": 10.3108,
      "step": 164
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.09073226153850555,
      "learning_rate": 8.141676086873572e-06,
      "loss": 10.5142,
      "step": 165
    },
    {
      "epoch": 2.2356902356902357,
      "grad_norm": 0.12167255580425262,
      "learning_rate": 7.695237378953223e-06,
      "loss": 10.4292,
      "step": 166
    },
    {
      "epoch": 2.249158249158249,
      "grad_norm": 0.06686627119779587,
      "learning_rate": 7.260364370723044e-06,
      "loss": 10.0645,
      "step": 167
    },
    {
      "epoch": 2.2626262626262625,
      "grad_norm": 0.07000602036714554,
      "learning_rate": 6.837175952121306e-06,
      "loss": 10.5307,
      "step": 168
    },
    {
      "epoch": 2.276094276094276,
      "grad_norm": 0.059983570128679276,
      "learning_rate": 6.425787818636131e-06,
      "loss": 10.2922,
      "step": 169
    },
    {
      "epoch": 2.28956228956229,
      "grad_norm": 0.06469827145338058,
      "learning_rate": 6.026312439675552e-06,
      "loss": 10.3114,
      "step": 170
    },
    {
      "epoch": 2.303030303030303,
      "grad_norm": 0.06783290952444077,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 10.5604,
      "step": 171
    },
    {
      "epoch": 2.3164983164983166,
      "grad_norm": 0.0824701189994812,
      "learning_rate": 5.263533508961827e-06,
      "loss": 10.0696,
      "step": 172
    },
    {
      "epoch": 2.32996632996633,
      "grad_norm": 0.08239365369081497,
      "learning_rate": 4.900438493352055e-06,
      "loss": 10.4696,
      "step": 173
    },
    {
      "epoch": 2.3434343434343434,
      "grad_norm": 0.08829548954963684,
      "learning_rate": 4.549673247541875e-06,
      "loss": 10.2398,
      "step": 174
    },
    {
      "epoch": 2.356902356902357,
      "grad_norm": 0.09629055857658386,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 10.2048,
      "step": 175
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.07236671447753906,
      "learning_rate": 3.885512251130763e-06,
      "loss": 10.2993,
      "step": 176
    },
    {
      "epoch": 2.3838383838383836,
      "grad_norm": 0.06139844283461571,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 10.5182,
      "step": 177
    },
    {
      "epoch": 2.3973063973063975,
      "grad_norm": 0.08017696440219879,
      "learning_rate": 3.271776770026963e-06,
      "loss": 10.3754,
      "step": 178
    },
    {
      "epoch": 2.410774410774411,
      "grad_norm": 0.08598282933235168,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 10.3943,
      "step": 179
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 0.11197204142808914,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 10.1814,
      "step": 180
    },
    {
      "epoch": 2.4377104377104377,
      "grad_norm": 0.10275253653526306,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.5342,
      "step": 181
    },
    {
      "epoch": 2.451178451178451,
      "grad_norm": 0.0896286740899086,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 10.3003,
      "step": 182
    },
    {
      "epoch": 2.4646464646464645,
      "grad_norm": 0.12249773740768433,
      "learning_rate": 1.962316193157593e-06,
      "loss": 10.1865,
      "step": 183
    },
    {
      "epoch": 2.478114478114478,
      "grad_norm": 0.15416379272937775,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 10.6468,
      "step": 184
    },
    {
      "epoch": 2.4915824915824913,
      "grad_norm": 0.07922852039337158,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 10.4257,
      "step": 185
    },
    {
      "epoch": 2.505050505050505,
      "grad_norm": 0.06210814043879509,
      "learning_rate": 1.333670137599713e-06,
      "loss": 10.1629,
      "step": 186
    },
    {
      "epoch": 2.5185185185185186,
      "grad_norm": 0.06594108790159225,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 10.3995,
      "step": 187
    },
    {
      "epoch": 2.531986531986532,
      "grad_norm": 0.0927363857626915,
      "learning_rate": 9.810017062595322e-07,
      "loss": 10.0206,
      "step": 188
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.08485542982816696,
      "learning_rate": 8.247462563808817e-07,
      "loss": 10.4953,
      "step": 189
    },
    {
      "epoch": 2.558922558922559,
      "grad_norm": 0.07645878195762634,
      "learning_rate": 6.819348298638839e-07,
      "loss": 10.4868,
      "step": 190
    },
    {
      "epoch": 2.5723905723905722,
      "grad_norm": 0.06822597235441208,
      "learning_rate": 5.526064699265753e-07,
      "loss": 10.1223,
      "step": 191
    },
    {
      "epoch": 2.5858585858585856,
      "grad_norm": 0.09703625738620758,
      "learning_rate": 4.367965336512403e-07,
      "loss": 10.3798,
      "step": 192
    },
    {
      "epoch": 2.5993265993265995,
      "grad_norm": 0.08330526947975159,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 10.3073,
      "step": 193
    },
    {
      "epoch": 2.612794612794613,
      "grad_norm": 0.0737113356590271,
      "learning_rate": 2.458548727494292e-07,
      "loss": 10.5479,
      "step": 194
    },
    {
      "epoch": 2.6262626262626263,
      "grad_norm": 0.08518735319375992,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 10.501,
      "step": 195
    },
    {
      "epoch": 2.6397306397306397,
      "grad_norm": 0.08353786915540695,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 10.0576,
      "step": 196
    },
    {
      "epoch": 2.653198653198653,
      "grad_norm": 0.07031574100255966,
      "learning_rate": 6.150154258476315e-08,
      "loss": 10.5087,
      "step": 197
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.061461467295885086,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 10.238,
      "step": 198
    },
    {
      "epoch": 2.68013468013468,
      "grad_norm": 0.12415464222431183,
      "learning_rate": 6.834750376549792e-09,
      "loss": 10.3836,
      "step": 199
    },
    {
      "epoch": 2.6936026936026938,
      "grad_norm": 0.14063477516174316,
      "learning_rate": 0.0,
      "loss": 10.3726,
      "step": 200
    },
    {
      "epoch": 2.6936026936026938,
      "eval_loss": 10.34481143951416,
      "eval_runtime": 0.2727,
      "eval_samples_per_second": 458.421,
      "eval_steps_per_second": 117.356,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 22282244456448.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}