{
  "best_metric": 10.344660758972168,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.022583559168925023,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011291779584462511,
      "grad_norm": 0.04100991412997246,
      "learning_rate": 1e-05,
      "loss": 10.381,
      "step": 1
    },
    {
      "epoch": 0.00011291779584462511,
      "eval_loss": 10.381028175354004,
      "eval_runtime": 32.4558,
      "eval_samples_per_second": 459.547,
      "eval_steps_per_second": 114.895,
      "step": 1
    },
    {
      "epoch": 0.00022583559168925022,
      "grad_norm": 0.044040217995643616,
      "learning_rate": 2e-05,
      "loss": 10.3815,
      "step": 2
    },
    {
      "epoch": 0.00033875338753387534,
      "grad_norm": 0.052993159741163254,
      "learning_rate": 3e-05,
      "loss": 10.382,
      "step": 3
    },
    {
      "epoch": 0.00045167118337850043,
      "grad_norm": 0.04769936203956604,
      "learning_rate": 4e-05,
      "loss": 10.3801,
      "step": 4
    },
    {
      "epoch": 0.0005645889792231255,
      "grad_norm": 0.0484175905585289,
      "learning_rate": 5e-05,
      "loss": 10.3818,
      "step": 5
    },
    {
      "epoch": 0.0006775067750677507,
      "grad_norm": 0.05078798159956932,
      "learning_rate": 6e-05,
      "loss": 10.3807,
      "step": 6
    },
    {
      "epoch": 0.0007904245709123758,
      "grad_norm": 0.04868657514452934,
      "learning_rate": 7e-05,
      "loss": 10.3812,
      "step": 7
    },
    {
      "epoch": 0.0009033423667570009,
      "grad_norm": 0.045539066195487976,
      "learning_rate": 8e-05,
      "loss": 10.3802,
      "step": 8
    },
    {
      "epoch": 0.0010162601626016261,
      "grad_norm": 0.05046577751636505,
      "learning_rate": 9e-05,
      "loss": 10.3787,
      "step": 9
    },
    {
      "epoch": 0.001129177958446251,
      "grad_norm": 0.05890989676117897,
      "learning_rate": 0.0001,
      "loss": 10.3795,
      "step": 10
    },
    {
      "epoch": 0.0012420957542908762,
      "grad_norm": 0.052908070385456085,
      "learning_rate": 9.999316524962345e-05,
      "loss": 10.3803,
      "step": 11
    },
    {
      "epoch": 0.0013550135501355014,
      "grad_norm": 0.05563591048121452,
      "learning_rate": 9.997266286704631e-05,
      "loss": 10.3796,
      "step": 12
    },
    {
      "epoch": 0.0014679313459801265,
      "grad_norm": 0.06086162477731705,
      "learning_rate": 9.993849845741524e-05,
      "loss": 10.3784,
      "step": 13
    },
    {
      "epoch": 0.0015808491418247517,
      "grad_norm": 0.06735281646251678,
      "learning_rate": 9.989068136093873e-05,
      "loss": 10.3786,
      "step": 14
    },
    {
      "epoch": 0.0016937669376693768,
      "grad_norm": 0.0659685730934143,
      "learning_rate": 9.98292246503335e-05,
      "loss": 10.3783,
      "step": 15
    },
    {
      "epoch": 0.0018066847335140017,
      "grad_norm": 0.060501858592033386,
      "learning_rate": 9.975414512725057e-05,
      "loss": 10.3779,
      "step": 16
    },
    {
      "epoch": 0.0019196025293586269,
      "grad_norm": 0.0736258327960968,
      "learning_rate": 9.966546331768191e-05,
      "loss": 10.3771,
      "step": 17
    },
    {
      "epoch": 0.0020325203252032522,
      "grad_norm": 0.07797635346651077,
      "learning_rate": 9.956320346634876e-05,
      "loss": 10.3773,
      "step": 18
    },
    {
      "epoch": 0.002145438121047877,
      "grad_norm": 0.0858171358704567,
      "learning_rate": 9.944739353007344e-05,
      "loss": 10.3763,
      "step": 19
    },
    {
      "epoch": 0.002258355916892502,
      "grad_norm": 0.08906648308038712,
      "learning_rate": 9.931806517013612e-05,
      "loss": 10.3773,
      "step": 20
    },
    {
      "epoch": 0.0023712737127371273,
      "grad_norm": 0.11043969541788101,
      "learning_rate": 9.917525374361912e-05,
      "loss": 10.3753,
      "step": 21
    },
    {
      "epoch": 0.0024841915085817524,
      "grad_norm": 0.10496679693460464,
      "learning_rate": 9.901899829374047e-05,
      "loss": 10.374,
      "step": 22
    },
    {
      "epoch": 0.0025971093044263776,
      "grad_norm": 0.10960293561220169,
      "learning_rate": 9.884934153917997e-05,
      "loss": 10.3736,
      "step": 23
    },
    {
      "epoch": 0.0027100271002710027,
      "grad_norm": 0.11736557632684708,
      "learning_rate": 9.86663298624003e-05,
      "loss": 10.3751,
      "step": 24
    },
    {
      "epoch": 0.002822944896115628,
      "grad_norm": 0.12232089042663574,
      "learning_rate": 9.847001329696653e-05,
      "loss": 10.3723,
      "step": 25
    },
    {
      "epoch": 0.002935862691960253,
      "grad_norm": 0.15159954130649567,
      "learning_rate": 9.826044551386744e-05,
      "loss": 10.3695,
      "step": 26
    },
    {
      "epoch": 0.003048780487804878,
      "grad_norm": 0.15535123646259308,
      "learning_rate": 9.803768380684242e-05,
      "loss": 10.3693,
      "step": 27
    },
    {
      "epoch": 0.0031616982836495033,
      "grad_norm": 0.16011174023151398,
      "learning_rate": 9.780178907671789e-05,
      "loss": 10.3698,
      "step": 28
    },
    {
      "epoch": 0.0032746160794941285,
      "grad_norm": 0.17105847597122192,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.368,
      "step": 29
    },
    {
      "epoch": 0.0033875338753387536,
      "grad_norm": 0.16224470734596252,
      "learning_rate": 9.729086208503174e-05,
      "loss": 10.3677,
      "step": 30
    },
    {
      "epoch": 0.0035004516711833783,
      "grad_norm": 0.16979964077472687,
      "learning_rate": 9.701596950580806e-05,
      "loss": 10.3644,
      "step": 31
    },
    {
      "epoch": 0.0036133694670280035,
      "grad_norm": 0.1731005609035492,
      "learning_rate": 9.672822322997305e-05,
      "loss": 10.3652,
      "step": 32
    },
    {
      "epoch": 0.0037262872628726286,
      "grad_norm": 0.16660572588443756,
      "learning_rate": 9.642770192448536e-05,
      "loss": 10.3635,
      "step": 33
    },
    {
      "epoch": 0.0038392050587172538,
      "grad_norm": 0.1607976257801056,
      "learning_rate": 9.611448774886924e-05,
      "loss": 10.3616,
      "step": 34
    },
    {
      "epoch": 0.003952122854561879,
      "grad_norm": 0.1754891574382782,
      "learning_rate": 9.578866633275288e-05,
      "loss": 10.3607,
      "step": 35
    },
    {
      "epoch": 0.0040650406504065045,
      "grad_norm": 0.13825231790542603,
      "learning_rate": 9.545032675245813e-05,
      "loss": 10.3622,
      "step": 36
    },
    {
      "epoch": 0.004177958446251129,
      "grad_norm": 0.13528135418891907,
      "learning_rate": 9.509956150664796e-05,
      "loss": 10.3607,
      "step": 37
    },
    {
      "epoch": 0.004290876242095754,
      "grad_norm": 0.14247609674930573,
      "learning_rate": 9.473646649103818e-05,
      "loss": 10.3581,
      "step": 38
    },
    {
      "epoch": 0.004403794037940379,
      "grad_norm": 0.1414458453655243,
      "learning_rate": 9.43611409721806e-05,
      "loss": 10.3578,
      "step": 39
    },
    {
      "epoch": 0.004516711833785004,
      "grad_norm": 0.13390380144119263,
      "learning_rate": 9.397368756032445e-05,
      "loss": 10.3572,
      "step": 40
    },
    {
      "epoch": 0.004629629629629629,
      "grad_norm": 0.11491462588310242,
      "learning_rate": 9.357421218136386e-05,
      "loss": 10.3604,
      "step": 41
    },
    {
      "epoch": 0.0047425474254742545,
      "grad_norm": 0.1265956163406372,
      "learning_rate": 9.316282404787871e-05,
      "loss": 10.3558,
      "step": 42
    },
    {
      "epoch": 0.00485546522131888,
      "grad_norm": 0.1051797866821289,
      "learning_rate": 9.273963562927695e-05,
      "loss": 10.355,
      "step": 43
    },
    {
      "epoch": 0.004968383017163505,
      "grad_norm": 0.11701712757349014,
      "learning_rate": 9.230476262104677e-05,
      "loss": 10.354,
      "step": 44
    },
    {
      "epoch": 0.00508130081300813,
      "grad_norm": 0.1171548143029213,
      "learning_rate": 9.185832391312644e-05,
      "loss": 10.3544,
      "step": 45
    },
    {
      "epoch": 0.005194218608852755,
      "grad_norm": 0.10842075198888779,
      "learning_rate": 9.140044155740101e-05,
      "loss": 10.3529,
      "step": 46
    },
    {
      "epoch": 0.00530713640469738,
      "grad_norm": 0.13692361116409302,
      "learning_rate": 9.093124073433463e-05,
      "loss": 10.352,
      "step": 47
    },
    {
      "epoch": 0.005420054200542005,
      "grad_norm": 0.1399284452199936,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3489,
      "step": 48
    },
    {
      "epoch": 0.0055329719963866306,
      "grad_norm": 0.14620433747768402,
      "learning_rate": 8.995939984474624e-05,
      "loss": 10.3471,
      "step": 49
    },
    {
      "epoch": 0.005645889792231256,
      "grad_norm": 0.16134655475616455,
      "learning_rate": 8.945702546981969e-05,
      "loss": 10.344,
      "step": 50
    },
    {
      "epoch": 0.005645889792231256,
      "eval_loss": 10.353063583374023,
      "eval_runtime": 32.3645,
      "eval_samples_per_second": 460.845,
      "eval_steps_per_second": 115.219,
      "step": 50
    },
    {
      "epoch": 0.005758807588075881,
      "grad_norm": 0.07836644351482391,
      "learning_rate": 8.894386393810563e-05,
      "loss": 10.3576,
      "step": 51
    },
    {
      "epoch": 0.005871725383920506,
      "grad_norm": 0.08972249180078506,
      "learning_rate": 8.842005554284296e-05,
      "loss": 10.3568,
      "step": 52
    },
    {
      "epoch": 0.005984643179765131,
      "grad_norm": 0.08503131568431854,
      "learning_rate": 8.788574348801675e-05,
      "loss": 10.3553,
      "step": 53
    },
    {
      "epoch": 0.006097560975609756,
      "grad_norm": 0.08864004164934158,
      "learning_rate": 8.73410738492077e-05,
      "loss": 10.356,
      "step": 54
    },
    {
      "epoch": 0.0062104787714543815,
      "grad_norm": 0.0987059623003006,
      "learning_rate": 8.678619553365659e-05,
      "loss": 10.3563,
      "step": 55
    },
    {
      "epoch": 0.006323396567299007,
      "grad_norm": 0.09272851049900055,
      "learning_rate": 8.622126023955446e-05,
      "loss": 10.3561,
      "step": 56
    },
    {
      "epoch": 0.006436314363143632,
      "grad_norm": 0.08075030148029327,
      "learning_rate": 8.564642241456986e-05,
      "loss": 10.3547,
      "step": 57
    },
    {
      "epoch": 0.006549232158988257,
      "grad_norm": 0.0814046636223793,
      "learning_rate": 8.506183921362443e-05,
      "loss": 10.3549,
      "step": 58
    },
    {
      "epoch": 0.006662149954832882,
      "grad_norm": 0.0711459070444107,
      "learning_rate": 8.44676704559283e-05,
      "loss": 10.3564,
      "step": 59
    },
    {
      "epoch": 0.006775067750677507,
      "grad_norm": 0.05498328059911728,
      "learning_rate": 8.386407858128706e-05,
      "loss": 10.3542,
      "step": 60
    },
    {
      "epoch": 0.0068879855465221315,
      "grad_norm": 0.06373993307352066,
      "learning_rate": 8.32512286056924e-05,
      "loss": 10.3543,
      "step": 61
    },
    {
      "epoch": 0.007000903342366757,
      "grad_norm": 0.05697491765022278,
      "learning_rate": 8.262928807620843e-05,
      "loss": 10.3522,
      "step": 62
    },
    {
      "epoch": 0.007113821138211382,
      "grad_norm": 0.0549735389649868,
      "learning_rate": 8.199842702516583e-05,
      "loss": 10.3528,
      "step": 63
    },
    {
      "epoch": 0.007226738934056007,
      "grad_norm": 0.056558676064014435,
      "learning_rate": 8.135881792367686e-05,
      "loss": 10.3524,
      "step": 64
    },
    {
      "epoch": 0.007339656729900632,
      "grad_norm": 0.04819077253341675,
      "learning_rate": 8.07106356344834e-05,
      "loss": 10.3533,
      "step": 65
    },
    {
      "epoch": 0.007452574525745257,
      "grad_norm": 0.052918169647455215,
      "learning_rate": 8.005405736415126e-05,
      "loss": 10.352,
      "step": 66
    },
    {
      "epoch": 0.007565492321589882,
      "grad_norm": 0.04404352232813835,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3511,
      "step": 67
    },
    {
      "epoch": 0.0076784101174345075,
      "grad_norm": 0.040255844593048096,
      "learning_rate": 7.871643313414718e-05,
      "loss": 10.3538,
      "step": 68
    },
    {
      "epoch": 0.007791327913279133,
      "grad_norm": 0.04346265643835068,
      "learning_rate": 7.803575286758364e-05,
      "loss": 10.352,
      "step": 69
    },
    {
      "epoch": 0.007904245709123759,
      "grad_norm": 0.04602336511015892,
      "learning_rate": 7.734740790612136e-05,
      "loss": 10.3483,
      "step": 70
    },
    {
      "epoch": 0.008017163504968384,
      "grad_norm": 0.04158735275268555,
      "learning_rate": 7.66515864363997e-05,
      "loss": 10.3512,
      "step": 71
    },
    {
      "epoch": 0.008130081300813009,
      "grad_norm": 0.053527139127254486,
      "learning_rate": 7.594847868906076e-05,
      "loss": 10.3524,
      "step": 72
    },
    {
      "epoch": 0.008242999096657632,
      "grad_norm": 0.04871845990419388,
      "learning_rate": 7.52382768867422e-05,
      "loss": 10.348,
      "step": 73
    },
    {
      "epoch": 0.008355916892502258,
      "grad_norm": 0.04520094394683838,
      "learning_rate": 7.452117519152542e-05,
      "loss": 10.349,
      "step": 74
    },
    {
      "epoch": 0.008468834688346883,
      "grad_norm": 0.047146353870630264,
      "learning_rate": 7.379736965185368e-05,
      "loss": 10.349,
      "step": 75
    },
    {
      "epoch": 0.008581752484191508,
      "grad_norm": 0.05354265868663788,
      "learning_rate": 7.30670581489344e-05,
      "loss": 10.3499,
      "step": 76
    },
    {
      "epoch": 0.008694670280036133,
      "grad_norm": 0.04741924628615379,
      "learning_rate": 7.233044034264034e-05,
      "loss": 10.3516,
      "step": 77
    },
    {
      "epoch": 0.008807588075880758,
      "grad_norm": 0.036932554095983505,
      "learning_rate": 7.158771761692464e-05,
      "loss": 10.3521,
      "step": 78
    },
    {
      "epoch": 0.008920505871725383,
      "grad_norm": 0.034939613193273544,
      "learning_rate": 7.083909302476453e-05,
      "loss": 10.3496,
      "step": 79
    },
    {
      "epoch": 0.009033423667570008,
      "grad_norm": 0.04926309362053871,
      "learning_rate": 7.008477123264848e-05,
      "loss": 10.3476,
      "step": 80
    },
    {
      "epoch": 0.009146341463414634,
      "grad_norm": 0.040787048637866974,
      "learning_rate": 6.932495846462261e-05,
      "loss": 10.3503,
      "step": 81
    },
    {
      "epoch": 0.009259259259259259,
      "grad_norm": 0.0501272976398468,
      "learning_rate": 6.855986244591104e-05,
      "loss": 10.3485,
      "step": 82
    },
    {
      "epoch": 0.009372177055103884,
      "grad_norm": 0.0443388894200325,
      "learning_rate": 6.778969234612584e-05,
      "loss": 10.3481,
      "step": 83
    },
    {
      "epoch": 0.009485094850948509,
      "grad_norm": 0.04341081157326698,
      "learning_rate": 6.701465872208216e-05,
      "loss": 10.3471,
      "step": 84
    },
    {
      "epoch": 0.009598012646793134,
      "grad_norm": 0.03392558544874191,
      "learning_rate": 6.623497346023418e-05,
      "loss": 10.3477,
      "step": 85
    },
    {
      "epoch": 0.00971093044263776,
      "grad_norm": 0.0421648770570755,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3482,
      "step": 86
    },
    {
      "epoch": 0.009823848238482384,
      "grad_norm": 0.04103966802358627,
      "learning_rate": 6.466250186922325e-05,
      "loss": 10.3486,
      "step": 87
    },
    {
      "epoch": 0.00993676603432701,
      "grad_norm": 0.04064726456999779,
      "learning_rate": 6.387014543809223e-05,
      "loss": 10.3482,
      "step": 88
    },
    {
      "epoch": 0.010049683830171635,
      "grad_norm": 0.047337036579847336,
      "learning_rate": 6.307399704769099e-05,
      "loss": 10.3475,
      "step": 89
    },
    {
      "epoch": 0.01016260162601626,
      "grad_norm": 0.04175706207752228,
      "learning_rate": 6.227427435703997e-05,
      "loss": 10.3466,
      "step": 90
    },
    {
      "epoch": 0.010275519421860885,
      "grad_norm": 0.04183386638760567,
      "learning_rate": 6.147119600233758e-05,
      "loss": 10.3472,
      "step": 91
    },
    {
      "epoch": 0.01038843721770551,
      "grad_norm": 0.04434938728809357,
      "learning_rate": 6.066498153718735e-05,
      "loss": 10.349,
      "step": 92
    },
    {
      "epoch": 0.010501355013550135,
      "grad_norm": 0.03670772910118103,
      "learning_rate": 5.985585137257401e-05,
      "loss": 10.3475,
      "step": 93
    },
    {
      "epoch": 0.01061427280939476,
      "grad_norm": 0.042052727192640305,
      "learning_rate": 5.90440267166055e-05,
      "loss": 10.3464,
      "step": 94
    },
    {
      "epoch": 0.010727190605239386,
      "grad_norm": 0.05059920996427536,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 10.3461,
      "step": 95
    },
    {
      "epoch": 0.01084010840108401,
      "grad_norm": 0.05376601964235306,
      "learning_rate": 5.74131823855921e-05,
      "loss": 10.348,
      "step": 96
    },
    {
      "epoch": 0.010953026196928636,
      "grad_norm": 0.054171472787857056,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 10.3451,
      "step": 97
    },
    {
      "epoch": 0.011065943992773261,
      "grad_norm": 0.08600333333015442,
      "learning_rate": 5.577423184847932e-05,
      "loss": 10.3437,
      "step": 98
    },
    {
      "epoch": 0.011178861788617886,
      "grad_norm": 0.08800508081912994,
      "learning_rate": 5.495227651252315e-05,
      "loss": 10.3444,
      "step": 99
    },
    {
      "epoch": 0.011291779584462511,
      "grad_norm": 0.06499609351158142,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 10.3446,
      "step": 100
    },
    {
      "epoch": 0.011291779584462511,
      "eval_loss": 10.348467826843262,
      "eval_runtime": 32.3394,
      "eval_samples_per_second": 461.203,
      "eval_steps_per_second": 115.308,
      "step": 100
    },
    {
      "epoch": 0.011404697380307137,
      "grad_norm": 0.04080375283956528,
      "learning_rate": 5.330452921628497e-05,
      "loss": 10.3538,
      "step": 101
    },
    {
      "epoch": 0.011517615176151762,
      "grad_norm": 0.04966358095407486,
      "learning_rate": 5.247918773366112e-05,
      "loss": 10.354,
      "step": 102
    },
    {
      "epoch": 0.011630532971996387,
      "grad_norm": 0.05560516193509102,
      "learning_rate": 5.165316846586541e-05,
      "loss": 10.3519,
      "step": 103
    },
    {
      "epoch": 0.011743450767841012,
      "grad_norm": 0.04882074147462845,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 10.352,
      "step": 104
    },
    {
      "epoch": 0.011856368563685637,
      "grad_norm": 0.05872456356883049,
      "learning_rate": 5e-05,
      "loss": 10.3513,
      "step": 105
    },
    {
      "epoch": 0.011969286359530262,
      "grad_norm": 0.062215276062488556,
      "learning_rate": 4.917330276168208e-05,
      "loss": 10.3515,
      "step": 106
    },
    {
      "epoch": 0.012082204155374887,
      "grad_norm": 0.05737992003560066,
      "learning_rate": 4.834683153413459e-05,
      "loss": 10.3508,
      "step": 107
    },
    {
      "epoch": 0.012195121951219513,
      "grad_norm": 0.05156635865569115,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 10.3517,
      "step": 108
    },
    {
      "epoch": 0.012308039747064138,
      "grad_norm": 0.06305219978094101,
      "learning_rate": 4.669547078371504e-05,
      "loss": 10.353,
      "step": 109
    },
    {
      "epoch": 0.012420957542908763,
      "grad_norm": 0.03509973734617233,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 10.3503,
      "step": 110
    },
    {
      "epoch": 0.012533875338753388,
      "grad_norm": 0.043863292783498764,
      "learning_rate": 4.504772348747687e-05,
      "loss": 10.3507,
      "step": 111
    },
    {
      "epoch": 0.012646793134598013,
      "grad_norm": 0.04563123360276222,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 10.3509,
      "step": 112
    },
    {
      "epoch": 0.012759710930442638,
      "grad_norm": 0.04611482843756676,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 10.3502,
      "step": 113
    },
    {
      "epoch": 0.012872628726287264,
      "grad_norm": 0.03914660960435867,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 10.349,
      "step": 114
    },
    {
      "epoch": 0.012985546522131889,
      "grad_norm": 0.048438526690006256,
      "learning_rate": 4.17702704859633e-05,
      "loss": 10.3498,
      "step": 115
    },
    {
      "epoch": 0.013098464317976514,
      "grad_norm": 0.03755532205104828,
      "learning_rate": 4.095597328339452e-05,
      "loss": 10.3492,
      "step": 116
    },
    {
      "epoch": 0.013211382113821139,
      "grad_norm": 0.03352291136980057,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 10.349,
      "step": 117
    },
    {
      "epoch": 0.013324299909665764,
      "grad_norm": 0.034118108451366425,
      "learning_rate": 3.933501846281267e-05,
      "loss": 10.3484,
      "step": 118
    },
    {
      "epoch": 0.01343721770551039,
      "grad_norm": 0.026466088369488716,
      "learning_rate": 3.852880399766243e-05,
      "loss": 10.3507,
      "step": 119
    },
    {
      "epoch": 0.013550135501355014,
      "grad_norm": 0.032075125724077225,
      "learning_rate": 3.772572564296005e-05,
      "loss": 10.3469,
      "step": 120
    },
    {
      "epoch": 0.013663053297199638,
      "grad_norm": 0.03435631841421127,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 10.3479,
      "step": 121
    },
    {
      "epoch": 0.013775971093044263,
      "grad_norm": 0.03220003843307495,
      "learning_rate": 3.612985456190778e-05,
      "loss": 10.3467,
      "step": 122
    },
    {
      "epoch": 0.013888888888888888,
      "grad_norm": 0.04220530763268471,
      "learning_rate": 3.533749813077677e-05,
      "loss": 10.3464,
      "step": 123
    },
    {
      "epoch": 0.014001806684733513,
      "grad_norm": 0.03280406817793846,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3459,
      "step": 124
    },
    {
      "epoch": 0.014114724480578138,
      "grad_norm": 0.0477244071662426,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 10.3464,
      "step": 125
    },
    {
      "epoch": 0.014227642276422764,
      "grad_norm": 0.03582311421632767,
      "learning_rate": 3.298534127791785e-05,
      "loss": 10.3473,
      "step": 126
    },
    {
      "epoch": 0.014340560072267389,
      "grad_norm": 0.03447744622826576,
      "learning_rate": 3.221030765387417e-05,
      "loss": 10.346,
      "step": 127
    },
    {
      "epoch": 0.014453477868112014,
      "grad_norm": 0.040054451674222946,
      "learning_rate": 3.144013755408895e-05,
      "loss": 10.3476,
      "step": 128
    },
    {
      "epoch": 0.014566395663956639,
      "grad_norm": 0.04340576007962227,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 10.3445,
      "step": 129
    },
    {
      "epoch": 0.014679313459801264,
      "grad_norm": 0.038768261671066284,
      "learning_rate": 2.991522876735154e-05,
      "loss": 10.3468,
      "step": 130
    },
    {
      "epoch": 0.01479223125564589,
      "grad_norm": 0.04203769564628601,
      "learning_rate": 2.916090697523549e-05,
      "loss": 10.3459,
      "step": 131
    },
    {
      "epoch": 0.014905149051490514,
      "grad_norm": 0.05311080068349838,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 10.3467,
      "step": 132
    },
    {
      "epoch": 0.01501806684733514,
      "grad_norm": 0.042701371014118195,
      "learning_rate": 2.766955965735968e-05,
      "loss": 10.3453,
      "step": 133
    },
    {
      "epoch": 0.015130984643179765,
      "grad_norm": 0.045268937945365906,
      "learning_rate": 2.693294185106562e-05,
      "loss": 10.3467,
      "step": 134
    },
    {
      "epoch": 0.01524390243902439,
      "grad_norm": 0.043085936456918716,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 10.3451,
      "step": 135
    },
    {
      "epoch": 0.015356820234869015,
      "grad_norm": 0.044772304594516754,
      "learning_rate": 2.547882480847461e-05,
      "loss": 10.3449,
      "step": 136
    },
    {
      "epoch": 0.01546973803071364,
      "grad_norm": 0.04884057864546776,
      "learning_rate": 2.476172311325783e-05,
      "loss": 10.3445,
      "step": 137
    },
    {
      "epoch": 0.015582655826558265,
      "grad_norm": 0.05156552419066429,
      "learning_rate": 2.405152131093926e-05,
      "loss": 10.3419,
      "step": 138
    },
    {
      "epoch": 0.01569557362240289,
      "grad_norm": 0.04518983140587807,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 10.3454,
      "step": 139
    },
    {
      "epoch": 0.015808491418247517,
      "grad_norm": 0.052372559905052185,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 10.3427,
      "step": 140
    },
    {
      "epoch": 0.01592140921409214,
      "grad_norm": 0.04336490109562874,
      "learning_rate": 2.196424713241637e-05,
      "loss": 10.345,
      "step": 141
    },
    {
      "epoch": 0.016034327009936768,
      "grad_norm": 0.05480709299445152,
      "learning_rate": 2.128356686585282e-05,
      "loss": 10.3455,
      "step": 142
    },
    {
      "epoch": 0.01614724480578139,
      "grad_norm": 0.04925680160522461,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3438,
      "step": 143
    },
    {
      "epoch": 0.016260162601626018,
      "grad_norm": 0.046634964644908905,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 10.3426,
      "step": 144
    },
    {
      "epoch": 0.01637308039747064,
      "grad_norm": 0.05420253798365593,
      "learning_rate": 1.928936436551661e-05,
      "loss": 10.3446,
      "step": 145
    },
    {
      "epoch": 0.016485998193315265,
      "grad_norm": 0.0552377849817276,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 10.3462,
      "step": 146
    },
    {
      "epoch": 0.01659891598915989,
      "grad_norm": 0.07975079119205475,
      "learning_rate": 1.800157297483417e-05,
      "loss": 10.3427,
      "step": 147
    },
    {
      "epoch": 0.016711833785004515,
      "grad_norm": 0.08498017489910126,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 10.3412,
      "step": 148
    },
    {
      "epoch": 0.016824751580849142,
      "grad_norm": 0.10630565881729126,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 10.3409,
      "step": 149
    },
    {
      "epoch": 0.016937669376693765,
      "grad_norm": 0.09660294651985168,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 10.3409,
      "step": 150
    },
    {
      "epoch": 0.016937669376693765,
      "eval_loss": 10.345593452453613,
      "eval_runtime": 32.2951,
      "eval_samples_per_second": 461.834,
      "eval_steps_per_second": 115.466,
      "step": 150
    },
    {
      "epoch": 0.017050587172538392,
      "grad_norm": 0.05264096334576607,
      "learning_rate": 1.553232954407171e-05,
      "loss": 10.352,
      "step": 151
    },
    {
      "epoch": 0.017163504968383016,
      "grad_norm": 0.05680564418435097,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 10.35,
      "step": 152
    },
    {
      "epoch": 0.017276422764227643,
      "grad_norm": 0.07362597435712814,
      "learning_rate": 1.435357758543015e-05,
      "loss": 10.3496,
      "step": 153
    },
    {
      "epoch": 0.017389340560072266,
      "grad_norm": 0.07560759782791138,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 10.3486,
      "step": 154
    },
    {
      "epoch": 0.017502258355916893,
      "grad_norm": 0.06887754797935486,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 10.3494,
      "step": 155
    },
    {
      "epoch": 0.017615176151761516,
      "grad_norm": 0.0513104610145092,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 10.3495,
      "step": 156
    },
    {
      "epoch": 0.017728093947606143,
      "grad_norm": 0.0641750618815422,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 10.3479,
      "step": 157
    },
    {
      "epoch": 0.017841011743450767,
      "grad_norm": 0.06762168556451797,
      "learning_rate": 1.157994445715706e-05,
      "loss": 10.349,
      "step": 158
    },
    {
      "epoch": 0.017953929539295393,
      "grad_norm": 0.05303732678294182,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 10.3491,
      "step": 159
    },
    {
      "epoch": 0.018066847335140017,
      "grad_norm": 0.06499285995960236,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 10.3474,
      "step": 160
    },
    {
      "epoch": 0.018179765130984644,
      "grad_norm": 0.05941135808825493,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 10.3495,
      "step": 161
    },
    {
      "epoch": 0.018292682926829267,
      "grad_norm": 0.06241150200366974,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3469,
      "step": 162
    },
    {
      "epoch": 0.018405600722673894,
      "grad_norm": 0.04952944815158844,
      "learning_rate": 9.068759265665384e-06,
      "loss": 10.3482,
      "step": 163
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 0.04664451256394386,
      "learning_rate": 8.599558442598998e-06,
      "loss": 10.3465,
      "step": 164
    },
    {
      "epoch": 0.018631436314363144,
      "grad_norm": 0.04972931742668152,
      "learning_rate": 8.141676086873572e-06,
      "loss": 10.3473,
      "step": 165
    },
    {
      "epoch": 0.018744354110207768,
      "grad_norm": 0.04423098266124725,
      "learning_rate": 7.695237378953223e-06,
      "loss": 10.3493,
      "step": 166
    },
    {
      "epoch": 0.018857271906052395,
      "grad_norm": 0.0514768622815609,
      "learning_rate": 7.260364370723044e-06,
      "loss": 10.3466,
      "step": 167
    },
    {
      "epoch": 0.018970189701897018,
      "grad_norm": 0.04833725094795227,
      "learning_rate": 6.837175952121306e-06,
      "loss": 10.3475,
      "step": 168
    },
    {
      "epoch": 0.019083107497741645,
      "grad_norm": 0.05269399285316467,
      "learning_rate": 6.425787818636131e-06,
      "loss": 10.3447,
      "step": 169
    },
    {
      "epoch": 0.01919602529358627,
      "grad_norm": 0.051521141082048416,
      "learning_rate": 6.026312439675552e-06,
      "loss": 10.3448,
      "step": 170
    },
    {
      "epoch": 0.019308943089430895,
      "grad_norm": 0.0535459890961647,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 10.3458,
      "step": 171
    },
    {
      "epoch": 0.01942186088527552,
      "grad_norm": 0.04571601375937462,
      "learning_rate": 5.263533508961827e-06,
      "loss": 10.3447,
      "step": 172
    },
    {
      "epoch": 0.019534778681120146,
      "grad_norm": 0.05001677945256233,
      "learning_rate": 4.900438493352055e-06,
      "loss": 10.344,
      "step": 173
    },
    {
      "epoch": 0.01964769647696477,
      "grad_norm": 0.05242624878883362,
      "learning_rate": 4.549673247541875e-06,
      "loss": 10.3439,
      "step": 174
    },
    {
      "epoch": 0.019760614272809396,
      "grad_norm": 0.04885996878147125,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 10.3447,
      "step": 175
    },
    {
      "epoch": 0.01987353206865402,
      "grad_norm": 0.050185222178697586,
      "learning_rate": 3.885512251130763e-06,
      "loss": 10.3448,
      "step": 176
    },
    {
      "epoch": 0.019986449864498646,
      "grad_norm": 0.05446929857134819,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 10.3446,
      "step": 177
    },
    {
      "epoch": 0.02009936766034327,
      "grad_norm": 0.047627102583646774,
      "learning_rate": 3.271776770026963e-06,
      "loss": 10.3473,
      "step": 178
    },
    {
      "epoch": 0.020212285456187896,
      "grad_norm": 0.05602965131402016,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 10.3441,
      "step": 179
    },
    {
      "epoch": 0.02032520325203252,
      "grad_norm": 0.047643404453992844,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 10.3427,
      "step": 180
    },
    {
      "epoch": 0.020438121047877147,
      "grad_norm": 0.04618468135595322,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3436,
      "step": 181
    },
    {
      "epoch": 0.02055103884372177,
      "grad_norm": 0.05832911655306816,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 10.3445,
      "step": 182
    },
    {
      "epoch": 0.020663956639566397,
      "grad_norm": 0.050765261054039,
      "learning_rate": 1.962316193157593e-06,
      "loss": 10.3441,
      "step": 183
    },
    {
      "epoch": 0.02077687443541102,
      "grad_norm": 0.052007660269737244,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 10.3409,
      "step": 184
    },
    {
      "epoch": 0.020889792231255647,
      "grad_norm": 0.05720518156886101,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 10.3425,
      "step": 185
    },
    {
      "epoch": 0.02100271002710027,
      "grad_norm": 0.049611642956733704,
      "learning_rate": 1.333670137599713e-06,
      "loss": 10.3432,
      "step": 186
    },
    {
      "epoch": 0.021115627822944898,
      "grad_norm": 0.05184567719697952,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 10.3426,
      "step": 187
    },
    {
      "epoch": 0.02122854561878952,
      "grad_norm": 0.05349419265985489,
      "learning_rate": 9.810017062595322e-07,
      "loss": 10.3423,
      "step": 188
    },
    {
      "epoch": 0.021341463414634148,
      "grad_norm": 0.05556259676814079,
      "learning_rate": 8.247462563808817e-07,
      "loss": 10.3423,
      "step": 189
    },
    {
      "epoch": 0.02145438121047877,
      "grad_norm": 0.05646717548370361,
      "learning_rate": 6.819348298638839e-07,
      "loss": 10.3407,
      "step": 190
    },
    {
      "epoch": 0.021567299006323398,
      "grad_norm": 0.06285367161035538,
      "learning_rate": 5.526064699265753e-07,
      "loss": 10.3417,
      "step": 191
    },
    {
      "epoch": 0.02168021680216802,
      "grad_norm": 0.05729836970567703,
      "learning_rate": 4.367965336512403e-07,
      "loss": 10.3409,
      "step": 192
    },
    {
      "epoch": 0.021793134598012645,
      "grad_norm": 0.04995645582675934,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 10.3414,
      "step": 193
    },
    {
      "epoch": 0.021906052393857272,
      "grad_norm": 0.05906350538134575,
      "learning_rate": 2.458548727494292e-07,
      "loss": 10.3399,
      "step": 194
    },
    {
      "epoch": 0.022018970189701895,
      "grad_norm": 0.05778375640511513,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 10.3429,
      "step": 195
    },
    {
      "epoch": 0.022131887985546522,
      "grad_norm": 0.06676250696182251,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 10.3428,
      "step": 196
    },
    {
      "epoch": 0.022244805781391146,
      "grad_norm": 0.0736616998910904,
      "learning_rate": 6.150154258476315e-08,
      "loss": 10.3412,
      "step": 197
    },
    {
      "epoch": 0.022357723577235773,
      "grad_norm": 0.0833023265004158,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 10.3394,
      "step": 198
    },
    {
      "epoch": 0.022470641373080396,
      "grad_norm": 0.09651142358779907,
      "learning_rate": 6.834750376549792e-09,
      "loss": 10.34,
      "step": 199
    },
    {
      "epoch": 0.022583559168925023,
      "grad_norm": 0.1050083190202713,
      "learning_rate": 0.0,
      "loss": 10.3394,
      "step": 200
    },
    {
      "epoch": 0.022583559168925023,
      "eval_loss": 10.344660758972168,
      "eval_runtime": 32.5364,
      "eval_samples_per_second": 458.41,
      "eval_steps_per_second": 114.61,
      "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": 22338019786752.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}