{
  "best_metric": 1.0581001043319702,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.056589092452429796,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028294546226214896,
      "grad_norm": 0.16440449655056,
      "learning_rate": 1e-05,
      "loss": 1.2996,
      "step": 1
    },
    {
      "epoch": 0.00028294546226214896,
      "eval_loss": 1.2713711261749268,
      "eval_runtime": 842.935,
      "eval_samples_per_second": 7.062,
      "eval_steps_per_second": 1.766,
      "step": 1
    },
    {
      "epoch": 0.0005658909245242979,
      "grad_norm": 0.1700342893600464,
      "learning_rate": 2e-05,
      "loss": 1.3221,
      "step": 2
    },
    {
      "epoch": 0.0008488363867864469,
      "grad_norm": 0.6224064826965332,
      "learning_rate": 3e-05,
      "loss": 1.31,
      "step": 3
    },
    {
      "epoch": 0.0011317818490485959,
      "grad_norm": 0.17167212069034576,
      "learning_rate": 4e-05,
      "loss": 1.4168,
      "step": 4
    },
    {
      "epoch": 0.001414727311310745,
      "grad_norm": 0.17006374895572662,
      "learning_rate": 5e-05,
      "loss": 1.2778,
      "step": 5
    },
    {
      "epoch": 0.0016976727735728938,
      "grad_norm": 0.14817090332508087,
      "learning_rate": 6e-05,
      "loss": 1.359,
      "step": 6
    },
    {
      "epoch": 0.001980618235835043,
      "grad_norm": 0.14220255613327026,
      "learning_rate": 7e-05,
      "loss": 1.2903,
      "step": 7
    },
    {
      "epoch": 0.0022635636980971917,
      "grad_norm": 0.14943797886371613,
      "learning_rate": 8e-05,
      "loss": 1.4145,
      "step": 8
    },
    {
      "epoch": 0.0025465091603593406,
      "grad_norm": 0.15911582112312317,
      "learning_rate": 9e-05,
      "loss": 1.2543,
      "step": 9
    },
    {
      "epoch": 0.00282945462262149,
      "grad_norm": 0.2003304362297058,
      "learning_rate": 0.0001,
      "loss": 1.1865,
      "step": 10
    },
    {
      "epoch": 0.0031124000848836387,
      "grad_norm": 0.15105725824832916,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.2441,
      "step": 11
    },
    {
      "epoch": 0.0033953455471457876,
      "grad_norm": 0.18273615837097168,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.3079,
      "step": 12
    },
    {
      "epoch": 0.0036782910094079364,
      "grad_norm": 0.15067222714424133,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.1035,
      "step": 13
    },
    {
      "epoch": 0.003961236471670086,
      "grad_norm": 0.16023559868335724,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.1937,
      "step": 14
    },
    {
      "epoch": 0.004244181933932234,
      "grad_norm": 0.1322859674692154,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.1612,
      "step": 15
    },
    {
      "epoch": 0.0045271273961943834,
      "grad_norm": 0.13824763894081116,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.1877,
      "step": 16
    },
    {
      "epoch": 0.004810072858456533,
      "grad_norm": 0.1429131180047989,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.2191,
      "step": 17
    },
    {
      "epoch": 0.005093018320718681,
      "grad_norm": 0.14441147446632385,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.3544,
      "step": 18
    },
    {
      "epoch": 0.0053759637829808304,
      "grad_norm": 0.1360960155725479,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.3557,
      "step": 19
    },
    {
      "epoch": 0.00565890924524298,
      "grad_norm": 0.13308748602867126,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.2014,
      "step": 20
    },
    {
      "epoch": 0.005941854707505128,
      "grad_norm": 0.15097203850746155,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.1907,
      "step": 21
    },
    {
      "epoch": 0.0062248001697672774,
      "grad_norm": 0.13530918955802917,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.2768,
      "step": 22
    },
    {
      "epoch": 0.006507745632029427,
      "grad_norm": 0.13055387139320374,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.2202,
      "step": 23
    },
    {
      "epoch": 0.006790691094291575,
      "grad_norm": 0.1323249340057373,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.1482,
      "step": 24
    },
    {
      "epoch": 0.0070736365565537244,
      "grad_norm": 0.1272873729467392,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.1876,
      "step": 25
    },
    {
      "epoch": 0.007356582018815873,
      "grad_norm": 0.12506330013275146,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.1534,
      "step": 26
    },
    {
      "epoch": 0.007639527481078022,
      "grad_norm": 0.13982200622558594,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.2914,
      "step": 27
    },
    {
      "epoch": 0.007922472943340171,
      "grad_norm": 0.14281505346298218,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.309,
      "step": 28
    },
    {
      "epoch": 0.00820541840560232,
      "grad_norm": 0.13648371398448944,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.127,
      "step": 29
    },
    {
      "epoch": 0.008488363867864468,
      "grad_norm": 0.13310784101486206,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.0355,
      "step": 30
    },
    {
      "epoch": 0.008771309330126618,
      "grad_norm": 0.13640299439430237,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.1303,
      "step": 31
    },
    {
      "epoch": 0.009054254792388767,
      "grad_norm": 0.1537925750017166,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.1816,
      "step": 32
    },
    {
      "epoch": 0.009337200254650915,
      "grad_norm": 0.16159723699092865,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.1657,
      "step": 33
    },
    {
      "epoch": 0.009620145716913065,
      "grad_norm": 0.1593446135520935,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.1289,
      "step": 34
    },
    {
      "epoch": 0.009903091179175214,
      "grad_norm": 0.1702510118484497,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.1052,
      "step": 35
    },
    {
      "epoch": 0.010186036641437362,
      "grad_norm": 0.21495391428470612,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.0461,
      "step": 36
    },
    {
      "epoch": 0.010468982103699512,
      "grad_norm": 0.19715330004692078,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.08,
      "step": 37
    },
    {
      "epoch": 0.010751927565961661,
      "grad_norm": 0.21431279182434082,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.1049,
      "step": 38
    },
    {
      "epoch": 0.01103487302822381,
      "grad_norm": 0.23300930857658386,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.0301,
      "step": 39
    },
    {
      "epoch": 0.01131781849048596,
      "grad_norm": 0.25129327178001404,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.9851,
      "step": 40
    },
    {
      "epoch": 0.011600763952748108,
      "grad_norm": 0.25877508521080017,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.9413,
      "step": 41
    },
    {
      "epoch": 0.011883709415010256,
      "grad_norm": 0.26159363985061646,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.0129,
      "step": 42
    },
    {
      "epoch": 0.012166654877272406,
      "grad_norm": 0.29299482703208923,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.9863,
      "step": 43
    },
    {
      "epoch": 0.012449600339534555,
      "grad_norm": 0.3069484829902649,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.9243,
      "step": 44
    },
    {
      "epoch": 0.012732545801796703,
      "grad_norm": 0.31254783272743225,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.9245,
      "step": 45
    },
    {
      "epoch": 0.013015491264058853,
      "grad_norm": 0.37932831048965454,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.0717,
      "step": 46
    },
    {
      "epoch": 0.013298436726321002,
      "grad_norm": 0.32941412925720215,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.2149,
      "step": 47
    },
    {
      "epoch": 0.01358138218858315,
      "grad_norm": 0.32703065872192383,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.2114,
      "step": 48
    },
    {
      "epoch": 0.013864327650845299,
      "grad_norm": 0.3165903091430664,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.1123,
      "step": 49
    },
    {
      "epoch": 0.014147273113107449,
      "grad_norm": 0.3254237771034241,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.9885,
      "step": 50
    },
    {
      "epoch": 0.014147273113107449,
      "eval_loss": 1.1117700338363647,
      "eval_runtime": 850.2569,
      "eval_samples_per_second": 7.001,
      "eval_steps_per_second": 1.751,
      "step": 50
    },
    {
      "epoch": 0.014430218575369597,
      "grad_norm": 0.16385777294635773,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.2547,
      "step": 51
    },
    {
      "epoch": 0.014713164037631746,
      "grad_norm": 0.19642743468284607,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.2263,
      "step": 52
    },
    {
      "epoch": 0.014996109499893896,
      "grad_norm": 0.19041608273983002,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.2292,
      "step": 53
    },
    {
      "epoch": 0.015279054962156044,
      "grad_norm": 0.14180612564086914,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.2183,
      "step": 54
    },
    {
      "epoch": 0.015562000424418193,
      "grad_norm": 0.14292573928833008,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.1047,
      "step": 55
    },
    {
      "epoch": 0.015844945886680343,
      "grad_norm": 0.14870023727416992,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.1627,
      "step": 56
    },
    {
      "epoch": 0.01612789134894249,
      "grad_norm": 0.13285201787948608,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.2005,
      "step": 57
    },
    {
      "epoch": 0.01641083681120464,
      "grad_norm": 0.1282941997051239,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.2194,
      "step": 58
    },
    {
      "epoch": 0.016693782273466788,
      "grad_norm": 0.1225777268409729,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.1638,
      "step": 59
    },
    {
      "epoch": 0.016976727735728937,
      "grad_norm": 0.1255250722169876,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.1653,
      "step": 60
    },
    {
      "epoch": 0.01725967319799109,
      "grad_norm": 0.12213602662086487,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.2027,
      "step": 61
    },
    {
      "epoch": 0.017542618660253237,
      "grad_norm": 0.13007181882858276,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.2544,
      "step": 62
    },
    {
      "epoch": 0.017825564122515385,
      "grad_norm": 0.11928606033325195,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.112,
      "step": 63
    },
    {
      "epoch": 0.018108509584777534,
      "grad_norm": 0.1263105273246765,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.2461,
      "step": 64
    },
    {
      "epoch": 0.018391455047039682,
      "grad_norm": 0.10763184726238251,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.1281,
      "step": 65
    },
    {
      "epoch": 0.01867440050930183,
      "grad_norm": 0.11457965523004532,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.2477,
      "step": 66
    },
    {
      "epoch": 0.018957345971563982,
      "grad_norm": 0.11507471650838852,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.248,
      "step": 67
    },
    {
      "epoch": 0.01924029143382613,
      "grad_norm": 0.12245697528123856,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.0905,
      "step": 68
    },
    {
      "epoch": 0.01952323689608828,
      "grad_norm": 0.1169041246175766,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.1617,
      "step": 69
    },
    {
      "epoch": 0.019806182358350428,
      "grad_norm": 0.1343025416135788,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.2809,
      "step": 70
    },
    {
      "epoch": 0.020089127820612576,
      "grad_norm": 0.1181471198797226,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.207,
      "step": 71
    },
    {
      "epoch": 0.020372073282874725,
      "grad_norm": 0.11915626376867294,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.1163,
      "step": 72
    },
    {
      "epoch": 0.020655018745136876,
      "grad_norm": 0.1203724816441536,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.2107,
      "step": 73
    },
    {
      "epoch": 0.020937964207399025,
      "grad_norm": 0.13024255633354187,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.1557,
      "step": 74
    },
    {
      "epoch": 0.021220909669661173,
      "grad_norm": 0.13673028349876404,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.2181,
      "step": 75
    },
    {
      "epoch": 0.021503855131923322,
      "grad_norm": 0.11701218038797379,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.0944,
      "step": 76
    },
    {
      "epoch": 0.02178680059418547,
      "grad_norm": 0.11889658868312836,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.1794,
      "step": 77
    },
    {
      "epoch": 0.02206974605644762,
      "grad_norm": 0.12679612636566162,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.2172,
      "step": 78
    },
    {
      "epoch": 0.022352691518709767,
      "grad_norm": 0.12585391104221344,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.2081,
      "step": 79
    },
    {
      "epoch": 0.02263563698097192,
      "grad_norm": 0.1325233280658722,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.1304,
      "step": 80
    },
    {
      "epoch": 0.022918582443234067,
      "grad_norm": 0.11568166315555573,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.0704,
      "step": 81
    },
    {
      "epoch": 0.023201527905496216,
      "grad_norm": 0.12443523854017258,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.1205,
      "step": 82
    },
    {
      "epoch": 0.023484473367758364,
      "grad_norm": 0.11627588421106339,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.0525,
      "step": 83
    },
    {
      "epoch": 0.023767418830020513,
      "grad_norm": 0.1464812159538269,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.0965,
      "step": 84
    },
    {
      "epoch": 0.02405036429228266,
      "grad_norm": 0.1542767584323883,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.0639,
      "step": 85
    },
    {
      "epoch": 0.024333309754544813,
      "grad_norm": 0.15702028572559357,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0808,
      "step": 86
    },
    {
      "epoch": 0.02461625521680696,
      "grad_norm": 0.15997888147830963,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.9567,
      "step": 87
    },
    {
      "epoch": 0.02489920067906911,
      "grad_norm": 0.19944031536579132,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.0556,
      "step": 88
    },
    {
      "epoch": 0.025182146141331258,
      "grad_norm": 0.197474867105484,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.8529,
      "step": 89
    },
    {
      "epoch": 0.025465091603593407,
      "grad_norm": 0.18544484674930573,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.8967,
      "step": 90
    },
    {
      "epoch": 0.025748037065855555,
      "grad_norm": 0.2609814405441284,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.8961,
      "step": 91
    },
    {
      "epoch": 0.026030982528117707,
      "grad_norm": 0.21465229988098145,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.8638,
      "step": 92
    },
    {
      "epoch": 0.026313927990379855,
      "grad_norm": 0.22472678124904633,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.9798,
      "step": 93
    },
    {
      "epoch": 0.026596873452642004,
      "grad_norm": 0.24460439383983612,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.9558,
      "step": 94
    },
    {
      "epoch": 0.026879818914904152,
      "grad_norm": 0.26187804341316223,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.839,
      "step": 95
    },
    {
      "epoch": 0.0271627643771663,
      "grad_norm": 0.26067283749580383,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7627,
      "step": 96
    },
    {
      "epoch": 0.02744570983942845,
      "grad_norm": 0.276324987411499,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.0388,
      "step": 97
    },
    {
      "epoch": 0.027728655301690597,
      "grad_norm": 0.2537800371646881,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.9669,
      "step": 98
    },
    {
      "epoch": 0.02801160076395275,
      "grad_norm": 0.2540218234062195,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.9093,
      "step": 99
    },
    {
      "epoch": 0.028294546226214898,
      "grad_norm": 0.3037388026714325,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.9567,
      "step": 100
    },
    {
      "epoch": 0.028294546226214898,
      "eval_loss": 1.0753511190414429,
      "eval_runtime": 850.163,
      "eval_samples_per_second": 7.002,
      "eval_steps_per_second": 1.751,
      "step": 100
    },
    {
      "epoch": 0.028577491688477046,
      "grad_norm": 0.13434098660945892,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.2111,
      "step": 101
    },
    {
      "epoch": 0.028860437150739195,
      "grad_norm": 0.1525864452123642,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.2108,
      "step": 102
    },
    {
      "epoch": 0.029143382613001343,
      "grad_norm": 0.1402004510164261,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.1543,
      "step": 103
    },
    {
      "epoch": 0.02942632807526349,
      "grad_norm": 0.1261124312877655,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.1264,
      "step": 104
    },
    {
      "epoch": 0.029709273537525643,
      "grad_norm": 0.1095128059387207,
      "learning_rate": 5e-05,
      "loss": 1.2259,
      "step": 105
    },
    {
      "epoch": 0.029992218999787792,
      "grad_norm": 0.11906921118497849,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.1716,
      "step": 106
    },
    {
      "epoch": 0.03027516446204994,
      "grad_norm": 0.11580817401409149,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.277,
      "step": 107
    },
    {
      "epoch": 0.03055810992431209,
      "grad_norm": 0.13293761014938354,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.2011,
      "step": 108
    },
    {
      "epoch": 0.030841055386574237,
      "grad_norm": 0.12140903621912003,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.1304,
      "step": 109
    },
    {
      "epoch": 0.031124000848836385,
      "grad_norm": 0.12187553197145462,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.0988,
      "step": 110
    },
    {
      "epoch": 0.031406946311098534,
      "grad_norm": 0.12612001597881317,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.1944,
      "step": 111
    },
    {
      "epoch": 0.031689891773360686,
      "grad_norm": 0.13121286034584045,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.2021,
      "step": 112
    },
    {
      "epoch": 0.03197283723562283,
      "grad_norm": 0.1161508858203888,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.1636,
      "step": 113
    },
    {
      "epoch": 0.03225578269788498,
      "grad_norm": 0.12370994687080383,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.2789,
      "step": 114
    },
    {
      "epoch": 0.032538728160147135,
      "grad_norm": 0.1287892609834671,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.152,
      "step": 115
    },
    {
      "epoch": 0.03282167362240928,
      "grad_norm": 0.12575651705265045,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.1705,
      "step": 116
    },
    {
      "epoch": 0.03310461908467143,
      "grad_norm": 0.11825452744960785,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.0457,
      "step": 117
    },
    {
      "epoch": 0.033387564546933576,
      "grad_norm": 0.1207413449883461,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.1076,
      "step": 118
    },
    {
      "epoch": 0.03367051000919573,
      "grad_norm": 0.12669555842876434,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.2526,
      "step": 119
    },
    {
      "epoch": 0.03395345547145787,
      "grad_norm": 0.12330494821071625,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.1822,
      "step": 120
    },
    {
      "epoch": 0.034236400933720025,
      "grad_norm": 0.13075558841228485,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.1815,
      "step": 121
    },
    {
      "epoch": 0.03451934639598218,
      "grad_norm": 0.1124318316578865,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.071,
      "step": 122
    },
    {
      "epoch": 0.03480229185824432,
      "grad_norm": 0.1311994343996048,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.1701,
      "step": 123
    },
    {
      "epoch": 0.035085237320506474,
      "grad_norm": 0.11577284336090088,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.03,
      "step": 124
    },
    {
      "epoch": 0.03536818278276862,
      "grad_norm": 0.12342160940170288,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.1701,
      "step": 125
    },
    {
      "epoch": 0.03565112824503077,
      "grad_norm": 0.13422353565692902,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.1936,
      "step": 126
    },
    {
      "epoch": 0.03593407370729292,
      "grad_norm": 0.13389138877391815,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.357,
      "step": 127
    },
    {
      "epoch": 0.03621701916955507,
      "grad_norm": 0.13625678420066833,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.235,
      "step": 128
    },
    {
      "epoch": 0.03649996463181722,
      "grad_norm": 0.13449987769126892,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.1568,
      "step": 129
    },
    {
      "epoch": 0.036782910094079364,
      "grad_norm": 0.13607105612754822,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.1194,
      "step": 130
    },
    {
      "epoch": 0.037065855556341516,
      "grad_norm": 0.13287802040576935,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.2005,
      "step": 131
    },
    {
      "epoch": 0.03734880101860366,
      "grad_norm": 0.16337142884731293,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.1008,
      "step": 132
    },
    {
      "epoch": 0.03763174648086581,
      "grad_norm": 0.1378541737794876,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.0721,
      "step": 133
    },
    {
      "epoch": 0.037914691943127965,
      "grad_norm": 0.14839281141757965,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.0573,
      "step": 134
    },
    {
      "epoch": 0.03819763740539011,
      "grad_norm": 0.16162434220314026,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.0275,
      "step": 135
    },
    {
      "epoch": 0.03848058286765226,
      "grad_norm": 0.15635748207569122,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.9669,
      "step": 136
    },
    {
      "epoch": 0.03876352832991441,
      "grad_norm": 0.21240057051181793,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.93,
      "step": 137
    },
    {
      "epoch": 0.03904647379217656,
      "grad_norm": 0.1887265294790268,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.0255,
      "step": 138
    },
    {
      "epoch": 0.039329419254438704,
      "grad_norm": 0.2102651447057724,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.7748,
      "step": 139
    },
    {
      "epoch": 0.039612364716700856,
      "grad_norm": 0.21125148236751556,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.866,
      "step": 140
    },
    {
      "epoch": 0.03989531017896301,
      "grad_norm": 0.2356061488389969,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.9828,
      "step": 141
    },
    {
      "epoch": 0.04017825564122515,
      "grad_norm": 0.2363680750131607,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.8121,
      "step": 142
    },
    {
      "epoch": 0.040461201103487304,
      "grad_norm": 0.24148066341876984,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.9703,
      "step": 143
    },
    {
      "epoch": 0.04074414656574945,
      "grad_norm": 0.25656065344810486,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.0935,
      "step": 144
    },
    {
      "epoch": 0.0410270920280116,
      "grad_norm": 0.25884708762168884,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.9618,
      "step": 145
    },
    {
      "epoch": 0.04131003749027375,
      "grad_norm": 0.3108620047569275,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.0156,
      "step": 146
    },
    {
      "epoch": 0.0415929829525359,
      "grad_norm": 0.29481470584869385,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.0081,
      "step": 147
    },
    {
      "epoch": 0.04187592841479805,
      "grad_norm": 0.25957190990448,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.6641,
      "step": 148
    },
    {
      "epoch": 0.042158873877060195,
      "grad_norm": 0.27256420254707336,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.8801,
      "step": 149
    },
    {
      "epoch": 0.04244181933932235,
      "grad_norm": 0.2954092025756836,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.0305,
      "step": 150
    },
    {
      "epoch": 0.04244181933932235,
      "eval_loss": 1.0615785121917725,
      "eval_runtime": 849.3578,
      "eval_samples_per_second": 7.009,
      "eval_steps_per_second": 1.753,
      "step": 150
    },
    {
      "epoch": 0.04272476480158449,
      "grad_norm": 0.12533512711524963,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.0599,
      "step": 151
    },
    {
      "epoch": 0.043007710263846644,
      "grad_norm": 0.13720209896564484,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.1079,
      "step": 152
    },
    {
      "epoch": 0.043290655726108795,
      "grad_norm": 0.13644611835479736,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.2152,
      "step": 153
    },
    {
      "epoch": 0.04357360118837094,
      "grad_norm": 0.12521038949489594,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.1266,
      "step": 154
    },
    {
      "epoch": 0.04385654665063309,
      "grad_norm": 0.1390223205089569,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.0935,
      "step": 155
    },
    {
      "epoch": 0.04413949211289524,
      "grad_norm": 0.1307298094034195,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.1593,
      "step": 156
    },
    {
      "epoch": 0.04442243757515739,
      "grad_norm": 0.12621790170669556,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.0882,
      "step": 157
    },
    {
      "epoch": 0.044705383037419534,
      "grad_norm": 0.1250780075788498,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.1732,
      "step": 158
    },
    {
      "epoch": 0.044988328499681686,
      "grad_norm": 0.13175423443317413,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.0934,
      "step": 159
    },
    {
      "epoch": 0.04527127396194384,
      "grad_norm": 0.11663813889026642,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.1498,
      "step": 160
    },
    {
      "epoch": 0.04555421942420598,
      "grad_norm": 0.12064314633607864,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.1383,
      "step": 161
    },
    {
      "epoch": 0.045837164886468135,
      "grad_norm": 0.1287967413663864,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.1635,
      "step": 162
    },
    {
      "epoch": 0.04612011034873028,
      "grad_norm": 0.1258004605770111,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.2445,
      "step": 163
    },
    {
      "epoch": 0.04640305581099243,
      "grad_norm": 0.11661669611930847,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.1039,
      "step": 164
    },
    {
      "epoch": 0.04668600127325458,
      "grad_norm": 0.11886816471815109,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.2234,
      "step": 165
    },
    {
      "epoch": 0.04696894673551673,
      "grad_norm": 0.11847767978906631,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.1436,
      "step": 166
    },
    {
      "epoch": 0.04725189219777888,
      "grad_norm": 0.11583325266838074,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.0854,
      "step": 167
    },
    {
      "epoch": 0.047534837660041025,
      "grad_norm": 0.12116571515798569,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.1634,
      "step": 168
    },
    {
      "epoch": 0.04781778312230318,
      "grad_norm": 0.11252746731042862,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.142,
      "step": 169
    },
    {
      "epoch": 0.04810072858456532,
      "grad_norm": 0.1247907280921936,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.2008,
      "step": 170
    },
    {
      "epoch": 0.048383674046827474,
      "grad_norm": 0.13404998183250427,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.2174,
      "step": 171
    },
    {
      "epoch": 0.048666619509089626,
      "grad_norm": 0.1351357400417328,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.1554,
      "step": 172
    },
    {
      "epoch": 0.04894956497135177,
      "grad_norm": 0.11428412795066833,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.1791,
      "step": 173
    },
    {
      "epoch": 0.04923251043361392,
      "grad_norm": 0.12799057364463806,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.1846,
      "step": 174
    },
    {
      "epoch": 0.04951545589587607,
      "grad_norm": 0.12541352212429047,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.1304,
      "step": 175
    },
    {
      "epoch": 0.04979840135813822,
      "grad_norm": 0.14077579975128174,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.2332,
      "step": 176
    },
    {
      "epoch": 0.050081346820400365,
      "grad_norm": 0.1404252052307129,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.094,
      "step": 177
    },
    {
      "epoch": 0.050364292282662516,
      "grad_norm": 0.127461239695549,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.2235,
      "step": 178
    },
    {
      "epoch": 0.05064723774492467,
      "grad_norm": 0.13746525347232819,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.1474,
      "step": 179
    },
    {
      "epoch": 0.05093018320718681,
      "grad_norm": 0.1321931630373001,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.1411,
      "step": 180
    },
    {
      "epoch": 0.051213128669448965,
      "grad_norm": 0.1274341642856598,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.143,
      "step": 181
    },
    {
      "epoch": 0.05149607413171111,
      "grad_norm": 0.12655508518218994,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.9722,
      "step": 182
    },
    {
      "epoch": 0.05177901959397326,
      "grad_norm": 0.14023424685001373,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.1595,
      "step": 183
    },
    {
      "epoch": 0.052061965056235414,
      "grad_norm": 0.1564980447292328,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.1376,
      "step": 184
    },
    {
      "epoch": 0.05234491051849756,
      "grad_norm": 0.1588853895664215,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.9301,
      "step": 185
    },
    {
      "epoch": 0.05262785598075971,
      "grad_norm": 0.14725466072559357,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.9275,
      "step": 186
    },
    {
      "epoch": 0.052910801443021856,
      "grad_norm": 0.18655529618263245,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.9885,
      "step": 187
    },
    {
      "epoch": 0.05319374690528401,
      "grad_norm": 0.1960240751504898,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.9353,
      "step": 188
    },
    {
      "epoch": 0.05347669236754615,
      "grad_norm": 0.22216826677322388,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.9963,
      "step": 189
    },
    {
      "epoch": 0.053759637829808304,
      "grad_norm": 0.2207292914390564,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.9103,
      "step": 190
    },
    {
      "epoch": 0.054042583292070456,
      "grad_norm": 0.21293385326862335,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.7813,
      "step": 191
    },
    {
      "epoch": 0.0543255287543326,
      "grad_norm": 0.22293995320796967,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.8966,
      "step": 192
    },
    {
      "epoch": 0.05460847421659475,
      "grad_norm": 0.24725447595119476,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.8331,
      "step": 193
    },
    {
      "epoch": 0.0548914196788569,
      "grad_norm": 0.2699107527732849,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.7815,
      "step": 194
    },
    {
      "epoch": 0.05517436514111905,
      "grad_norm": 0.26064953207969666,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.9104,
      "step": 195
    },
    {
      "epoch": 0.055457310603381195,
      "grad_norm": 0.3105829954147339,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.885,
      "step": 196
    },
    {
      "epoch": 0.05574025606564335,
      "grad_norm": 0.27669769525527954,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.8055,
      "step": 197
    },
    {
      "epoch": 0.0560232015279055,
      "grad_norm": 0.2636876106262207,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.0784,
      "step": 198
    },
    {
      "epoch": 0.056306146990167644,
      "grad_norm": 0.2587314248085022,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.9319,
      "step": 199
    },
    {
      "epoch": 0.056589092452429796,
      "grad_norm": 0.29389357566833496,
      "learning_rate": 0.0,
      "loss": 1.0633,
      "step": 200
    },
    {
      "epoch": 0.056589092452429796,
      "eval_loss": 1.0581001043319702,
      "eval_runtime": 849.0634,
      "eval_samples_per_second": 7.011,
      "eval_steps_per_second": 1.754,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 5.258784547767583e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}