{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.021174104070721508,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010587052035360753,
      "grad_norm": 3.7758225516881794e-05,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.00010587052035360753,
      "eval_loss": 11.5,
      "eval_runtime": 72.1135,
      "eval_samples_per_second": 220.597,
      "eval_steps_per_second": 55.149,
      "step": 1
    },
    {
      "epoch": 0.00021174104070721507,
      "grad_norm": 3.971419937442988e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0003176115610608226,
      "grad_norm": 3.637537520262413e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.00042348208141443014,
      "grad_norm": 3.887588536599651e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.0005293526017680377,
      "grad_norm": 4.2343250242993236e-05,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0006352231221216452,
      "grad_norm": 3.818485856754705e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0007410936424752528,
      "grad_norm": 3.684431794681586e-05,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.0008469641628288603,
      "grad_norm": 4.405047729960643e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.0009528346831824678,
      "grad_norm": 4.1015733586391434e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0010587052035360754,
      "grad_norm": 4.3070700485259295e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.001164575723889683,
      "grad_norm": 4.4531727326102555e-05,
      "learning_rate": 9.999316524962345e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.0012704462442432905,
      "grad_norm": 5.3285079047782347e-05,
      "learning_rate": 9.997266286704631e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.001376316764596898,
      "grad_norm": 5.0984035624423996e-05,
      "learning_rate": 9.993849845741524e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.0014821872849505055,
      "grad_norm": 5.58307183382567e-05,
      "learning_rate": 9.989068136093873e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.001588057805304113,
      "grad_norm": 5.934804357821122e-05,
      "learning_rate": 9.98292246503335e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.0016939283256577206,
      "grad_norm": 6.463150930358097e-05,
      "learning_rate": 9.975414512725057e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.001799798846011328,
      "grad_norm": 4.7909423301462084e-05,
      "learning_rate": 9.966546331768191e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.0019056693663649356,
      "grad_norm": 7.621497206855565e-05,
      "learning_rate": 9.956320346634876e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.0020115398867185433,
      "grad_norm": 6.396209209924564e-05,
      "learning_rate": 9.944739353007344e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.002117410407072151,
      "grad_norm": 6.801196286687627e-05,
      "learning_rate": 9.931806517013612e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.0022232809274257584,
      "grad_norm": 9.671619773143902e-05,
      "learning_rate": 9.917525374361912e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.002329151447779366,
      "grad_norm": 6.602923531318083e-05,
      "learning_rate": 9.901899829374047e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.0024350219681329734,
      "grad_norm": 6.1022692534606904e-05,
      "learning_rate": 9.884934153917997e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.002540892488486581,
      "grad_norm": 6.946302892174572e-05,
      "learning_rate": 9.86663298624003e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.0026467630088401885,
      "grad_norm": 7.02681572875008e-05,
      "learning_rate": 9.847001329696653e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.002752633529193796,
      "grad_norm": 7.992880273377523e-05,
      "learning_rate": 9.826044551386744e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.0028585040495474035,
      "grad_norm": 9.598107862984762e-05,
      "learning_rate": 9.803768380684242e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.002964374569901011,
      "grad_norm": 6.979780300753191e-05,
      "learning_rate": 9.780178907671789e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.0030702450902546185,
      "grad_norm": 8.061125845415518e-05,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.003176115610608226,
      "grad_norm": 6.121831393102184e-05,
      "learning_rate": 9.729086208503174e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.0032819861309618336,
      "grad_norm": 7.876812742324546e-05,
      "learning_rate": 9.701596950580806e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.003387856651315441,
      "grad_norm": 8.232305117417127e-05,
      "learning_rate": 9.672822322997305e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.0034937271716690486,
      "grad_norm": 0.00010647060844348744,
      "learning_rate": 9.642770192448536e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.003599597692022656,
      "grad_norm": 8.773127774475142e-05,
      "learning_rate": 9.611448774886924e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.0037054682123762637,
      "grad_norm": 8.684745262144133e-05,
      "learning_rate": 9.578866633275288e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.003811338732729871,
      "grad_norm": 0.0001693954545771703,
      "learning_rate": 9.545032675245813e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.003917209253083479,
      "grad_norm": 0.0002747740945778787,
      "learning_rate": 9.509956150664796e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.004023079773437087,
      "grad_norm": 0.00025078473845496774,
      "learning_rate": 9.473646649103818e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.004128950293790694,
      "grad_norm": 0.0008936162339523435,
      "learning_rate": 9.43611409721806e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.004234820814144302,
      "grad_norm": 0.0012688522692769766,
      "learning_rate": 9.397368756032445e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.004340691334497909,
      "grad_norm": 0.0010934964520856738,
      "learning_rate": 9.357421218136386e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.004446561854851517,
      "grad_norm": 0.0012208395637571812,
      "learning_rate": 9.316282404787871e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.004552432375205124,
      "grad_norm": 0.001099789165891707,
      "learning_rate": 9.273963562927695e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.004658302895558732,
      "grad_norm": 0.0013558148639276624,
      "learning_rate": 9.230476262104677e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.004764173415912339,
      "grad_norm": 0.0013746003387495875,
      "learning_rate": 9.185832391312644e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.004870043936265947,
      "grad_norm": 0.0014544494915753603,
      "learning_rate": 9.140044155740101e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.004975914456619554,
      "grad_norm": 0.0014375027967616916,
      "learning_rate": 9.093124073433463e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.005081784976973162,
      "grad_norm": 0.0014922708505764604,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.005187655497326769,
      "grad_norm": 0.0017685582861304283,
      "learning_rate": 8.995939984474624e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.005293526017680377,
      "grad_norm": 0.001406966825015843,
      "learning_rate": 8.945702546981969e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.005293526017680377,
      "eval_loss": 11.5,
      "eval_runtime": 72.0051,
      "eval_samples_per_second": 220.929,
      "eval_steps_per_second": 55.232,
      "step": 50
    },
    {
      "epoch": 0.0053993965380339844,
      "grad_norm": 0.00015319549129344523,
      "learning_rate": 8.894386393810563e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.005505267058387592,
      "grad_norm": 0.00019435409922152758,
      "learning_rate": 8.842005554284296e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.0056111375787411995,
      "grad_norm": 0.00020844223035965115,
      "learning_rate": 8.788574348801675e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.005717008099094807,
      "grad_norm": 0.00020513297931756824,
      "learning_rate": 8.73410738492077e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.0058228786194484145,
      "grad_norm": 0.0001638914691284299,
      "learning_rate": 8.678619553365659e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.005928749139802022,
      "grad_norm": 0.00020096043590456247,
      "learning_rate": 8.622126023955446e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.0060346196601556296,
      "grad_norm": 0.00023176470131147653,
      "learning_rate": 8.564642241456986e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.006140490180509237,
      "grad_norm": 0.0001855547889135778,
      "learning_rate": 8.506183921362443e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.006246360700862845,
      "grad_norm": 0.0001982215471798554,
      "learning_rate": 8.44676704559283e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.006352231221216452,
      "grad_norm": 0.0001941195223480463,
      "learning_rate": 8.386407858128706e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.00645810174157006,
      "grad_norm": 0.00019479637558106333,
      "learning_rate": 8.32512286056924e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.006563972261923667,
      "grad_norm": 0.0001838829048210755,
      "learning_rate": 8.262928807620843e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.006669842782277275,
      "grad_norm": 0.00016903660434763879,
      "learning_rate": 8.199842702516583e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.006775713302630882,
      "grad_norm": 0.00019123349920846522,
      "learning_rate": 8.135881792367686e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.00688158382298449,
      "grad_norm": 0.0002044424181804061,
      "learning_rate": 8.07106356344834e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.006987454343338097,
      "grad_norm": 0.00026173770311288536,
      "learning_rate": 8.005405736415126e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.007093324863691705,
      "grad_norm": 0.00011461394024081528,
      "learning_rate": 7.938926261462366e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.007199195384045312,
      "grad_norm": 0.0001901618525153026,
      "learning_rate": 7.871643313414718e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.00730506590439892,
      "grad_norm": 0.00021410213958006352,
      "learning_rate": 7.803575286758364e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.007410936424752527,
      "grad_norm": 0.00018753486801870167,
      "learning_rate": 7.734740790612136e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.007516806945106135,
      "grad_norm": 0.0002480893163010478,
      "learning_rate": 7.66515864363997e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.007622677465459742,
      "grad_norm": 0.0002523521543480456,
      "learning_rate": 7.594847868906076e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.00772854798581335,
      "grad_norm": 0.00020747345115523785,
      "learning_rate": 7.52382768867422e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.007834418506166958,
      "grad_norm": 0.00020068875164724886,
      "learning_rate": 7.452117519152542e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.007940289026520565,
      "grad_norm": 0.00020946303266100585,
      "learning_rate": 7.379736965185368e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.008046159546874173,
      "grad_norm": 0.00015278464707080275,
      "learning_rate": 7.30670581489344e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.00815203006722778,
      "grad_norm": 0.00016136947670020163,
      "learning_rate": 7.233044034264034e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.008257900587581388,
      "grad_norm": 0.0001631510822335258,
      "learning_rate": 7.158771761692464e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.008363771107934995,
      "grad_norm": 0.0001458908518543467,
      "learning_rate": 7.083909302476453e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.008469641628288603,
      "grad_norm": 0.00016608608711976558,
      "learning_rate": 7.008477123264848e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.00857551214864221,
      "grad_norm": 0.00013964880781713873,
      "learning_rate": 6.932495846462261e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.008681382668995818,
      "grad_norm": 0.00013575328921433538,
      "learning_rate": 6.855986244591104e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.008787253189349425,
      "grad_norm": 0.00019137118943035603,
      "learning_rate": 6.778969234612584e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.008893123709703033,
      "grad_norm": 0.00020755836158059537,
      "learning_rate": 6.701465872208216e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.00899899423005664,
      "grad_norm": 0.00029875306063331664,
      "learning_rate": 6.623497346023418e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.009104864750410249,
      "grad_norm": 0.0003985251532867551,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.009210735270763855,
      "grad_norm": 0.0007180428947322071,
      "learning_rate": 6.466250186922325e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.009316605791117464,
      "grad_norm": 0.002547956071794033,
      "learning_rate": 6.387014543809223e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.00942247631147107,
      "grad_norm": 0.002583778463304043,
      "learning_rate": 6.307399704769099e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.009528346831824679,
      "grad_norm": 0.0024923228193074465,
      "learning_rate": 6.227427435703997e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.009634217352178285,
      "grad_norm": 0.0021992200054228306,
      "learning_rate": 6.147119600233758e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.009740087872531894,
      "grad_norm": 0.001998371910303831,
      "learning_rate": 6.066498153718735e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.0098459583928855,
      "grad_norm": 0.002456718124449253,
      "learning_rate": 5.985585137257401e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.009951828913239109,
      "grad_norm": 0.0027659297920763493,
      "learning_rate": 5.90440267166055e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.010057699433592715,
      "grad_norm": 0.002772964769974351,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.010163569953946324,
      "grad_norm": 0.0028121722862124443,
      "learning_rate": 5.74131823855921e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.01026944047429993,
      "grad_norm": 0.002786785364151001,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.010375310994653539,
      "grad_norm": 0.0026966389268636703,
      "learning_rate": 5.577423184847932e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.010481181515007145,
      "grad_norm": 0.003058412577956915,
      "learning_rate": 5.495227651252315e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.010587052035360754,
      "grad_norm": 0.0024895125534385443,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.010587052035360754,
      "eval_loss": 11.5,
      "eval_runtime": 72.0658,
      "eval_samples_per_second": 220.743,
      "eval_steps_per_second": 55.186,
      "step": 100
    },
    {
      "epoch": 0.01069292255571436,
      "grad_norm": 0.0003552868729457259,
      "learning_rate": 5.330452921628497e-05,
      "loss": 46.0,
      "step": 101
    },
    {
      "epoch": 0.010798793076067969,
      "grad_norm": 0.0003323951968923211,
      "learning_rate": 5.247918773366112e-05,
      "loss": 46.0,
      "step": 102
    },
    {
      "epoch": 0.010904663596421577,
      "grad_norm": 0.0002966799074783921,
      "learning_rate": 5.165316846586541e-05,
      "loss": 46.0,
      "step": 103
    },
    {
      "epoch": 0.011010534116775184,
      "grad_norm": 0.0003673431056085974,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 46.0,
      "step": 104
    },
    {
      "epoch": 0.011116404637128792,
      "grad_norm": 0.00031036778818815947,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 0.011222275157482399,
      "grad_norm": 0.00028706042212434113,
      "learning_rate": 4.917330276168208e-05,
      "loss": 46.0,
      "step": 106
    },
    {
      "epoch": 0.011328145677836007,
      "grad_norm": 0.0002792067243717611,
      "learning_rate": 4.834683153413459e-05,
      "loss": 46.0,
      "step": 107
    },
    {
      "epoch": 0.011434016198189614,
      "grad_norm": 0.00030040412093512714,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 46.0,
      "step": 108
    },
    {
      "epoch": 0.011539886718543222,
      "grad_norm": 0.00028762564761564136,
      "learning_rate": 4.669547078371504e-05,
      "loss": 46.0,
      "step": 109
    },
    {
      "epoch": 0.011645757238896829,
      "grad_norm": 0.0003190697461832315,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 0.011751627759250437,
      "grad_norm": 0.0003825913299806416,
      "learning_rate": 4.504772348747687e-05,
      "loss": 46.0,
      "step": 111
    },
    {
      "epoch": 0.011857498279604044,
      "grad_norm": 0.0003889522049576044,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 46.0,
      "step": 112
    },
    {
      "epoch": 0.011963368799957652,
      "grad_norm": 0.000495815824251622,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 46.0,
      "step": 113
    },
    {
      "epoch": 0.012069239320311259,
      "grad_norm": 0.0003524029743857682,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 46.0,
      "step": 114
    },
    {
      "epoch": 0.012175109840664868,
      "grad_norm": 0.0003622378862928599,
      "learning_rate": 4.17702704859633e-05,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 0.012280980361018474,
      "grad_norm": 0.00025719942641444504,
      "learning_rate": 4.095597328339452e-05,
      "loss": 46.0,
      "step": 116
    },
    {
      "epoch": 0.012386850881372083,
      "grad_norm": 0.0003259727091062814,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 46.0,
      "step": 117
    },
    {
      "epoch": 0.01249272140172569,
      "grad_norm": 0.0002925765002146363,
      "learning_rate": 3.933501846281267e-05,
      "loss": 46.0,
      "step": 118
    },
    {
      "epoch": 0.012598591922079298,
      "grad_norm": 0.0003228446585126221,
      "learning_rate": 3.852880399766243e-05,
      "loss": 46.0,
      "step": 119
    },
    {
      "epoch": 0.012704462442432904,
      "grad_norm": 0.0003316564834676683,
      "learning_rate": 3.772572564296005e-05,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 0.012810332962786513,
      "grad_norm": 0.0002721836499404162,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 46.0,
      "step": 121
    },
    {
      "epoch": 0.01291620348314012,
      "grad_norm": 0.00028851881506852806,
      "learning_rate": 3.612985456190778e-05,
      "loss": 46.0,
      "step": 122
    },
    {
      "epoch": 0.013022074003493728,
      "grad_norm": 0.0002666217915248126,
      "learning_rate": 3.533749813077677e-05,
      "loss": 46.0,
      "step": 123
    },
    {
      "epoch": 0.013127944523847334,
      "grad_norm": 0.000259630149230361,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 46.0,
      "step": 124
    },
    {
      "epoch": 0.013233815044200943,
      "grad_norm": 0.0003889918443746865,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 0.01333968556455455,
      "grad_norm": 0.0003328875172883272,
      "learning_rate": 3.298534127791785e-05,
      "loss": 46.0,
      "step": 126
    },
    {
      "epoch": 0.013445556084908158,
      "grad_norm": 0.00018043341697193682,
      "learning_rate": 3.221030765387417e-05,
      "loss": 46.0,
      "step": 127
    },
    {
      "epoch": 0.013551426605261764,
      "grad_norm": 0.0003149941621813923,
      "learning_rate": 3.144013755408895e-05,
      "loss": 46.0,
      "step": 128
    },
    {
      "epoch": 0.013657297125615373,
      "grad_norm": 0.00025322509463876486,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 46.0,
      "step": 129
    },
    {
      "epoch": 0.01376316764596898,
      "grad_norm": 0.00027760243392549455,
      "learning_rate": 2.991522876735154e-05,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 0.013869038166322588,
      "grad_norm": 0.00023040082305669785,
      "learning_rate": 2.916090697523549e-05,
      "loss": 46.0,
      "step": 131
    },
    {
      "epoch": 0.013974908686676194,
      "grad_norm": 0.0002616914571262896,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 46.0,
      "step": 132
    },
    {
      "epoch": 0.014080779207029803,
      "grad_norm": 0.00021648740221280605,
      "learning_rate": 2.766955965735968e-05,
      "loss": 46.0,
      "step": 133
    },
    {
      "epoch": 0.01418664972738341,
      "grad_norm": 0.00030988408252596855,
      "learning_rate": 2.693294185106562e-05,
      "loss": 46.0,
      "step": 134
    },
    {
      "epoch": 0.014292520247737018,
      "grad_norm": 0.000268768664682284,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 0.014398390768090625,
      "grad_norm": 0.0004775602137669921,
      "learning_rate": 2.547882480847461e-05,
      "loss": 46.0,
      "step": 136
    },
    {
      "epoch": 0.014504261288444233,
      "grad_norm": 0.0006808377802371979,
      "learning_rate": 2.476172311325783e-05,
      "loss": 46.0,
      "step": 137
    },
    {
      "epoch": 0.01461013180879784,
      "grad_norm": 0.0011323445942252874,
      "learning_rate": 2.405152131093926e-05,
      "loss": 46.0,
      "step": 138
    },
    {
      "epoch": 0.014716002329151448,
      "grad_norm": 0.00297493115067482,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 46.0,
      "step": 139
    },
    {
      "epoch": 0.014821872849505055,
      "grad_norm": 0.0038632601499557495,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 0.014927743369858663,
      "grad_norm": 0.003049037652090192,
      "learning_rate": 2.196424713241637e-05,
      "loss": 46.0,
      "step": 141
    },
    {
      "epoch": 0.01503361389021227,
      "grad_norm": 0.004032890312373638,
      "learning_rate": 2.128356686585282e-05,
      "loss": 46.0,
      "step": 142
    },
    {
      "epoch": 0.015139484410565878,
      "grad_norm": 0.003995910286903381,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 143
    },
    {
      "epoch": 0.015245354930919485,
      "grad_norm": 0.003903838573023677,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 46.0,
      "step": 144
    },
    {
      "epoch": 0.015351225451273093,
      "grad_norm": 0.0038895534817129374,
      "learning_rate": 1.928936436551661e-05,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 0.0154570959716267,
      "grad_norm": 0.003806990571320057,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 46.0,
      "step": 146
    },
    {
      "epoch": 0.015562966491980308,
      "grad_norm": 0.003817790187895298,
      "learning_rate": 1.800157297483417e-05,
      "loss": 46.0,
      "step": 147
    },
    {
      "epoch": 0.015668837012333917,
      "grad_norm": 0.003742322325706482,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 46.0,
      "step": 148
    },
    {
      "epoch": 0.01577470753268752,
      "grad_norm": 0.0038418227341026068,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 46.0,
      "step": 149
    },
    {
      "epoch": 0.01588057805304113,
      "grad_norm": 0.0033004693686962128,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 0.01588057805304113,
      "eval_loss": 11.5,
      "eval_runtime": 72.372,
      "eval_samples_per_second": 219.809,
      "eval_steps_per_second": 54.952,
      "step": 150
    },
    {
      "epoch": 0.015986448573394738,
      "grad_norm": 0.0003055637062061578,
      "learning_rate": 1.553232954407171e-05,
      "loss": 46.0,
      "step": 151
    },
    {
      "epoch": 0.016092319093748347,
      "grad_norm": 0.0003770513867493719,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 46.0,
      "step": 152
    },
    {
      "epoch": 0.016198189614101955,
      "grad_norm": 0.0003364474105183035,
      "learning_rate": 1.435357758543015e-05,
      "loss": 46.0,
      "step": 153
    },
    {
      "epoch": 0.01630406013445556,
      "grad_norm": 0.0003832425572909415,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 46.0,
      "step": 154
    },
    {
      "epoch": 0.01640993065480917,
      "grad_norm": 0.00033884920412674546,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 46.0,
      "step": 155
    },
    {
      "epoch": 0.016515801175162777,
      "grad_norm": 0.0003470079100225121,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 46.0,
      "step": 156
    },
    {
      "epoch": 0.016621671695516385,
      "grad_norm": 0.000391679466702044,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 46.0,
      "step": 157
    },
    {
      "epoch": 0.01672754221586999,
      "grad_norm": 0.0003146318776998669,
      "learning_rate": 1.157994445715706e-05,
      "loss": 46.0,
      "step": 158
    },
    {
      "epoch": 0.0168334127362236,
      "grad_norm": 0.0004575755156110972,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 46.0,
      "step": 159
    },
    {
      "epoch": 0.016939283256577207,
      "grad_norm": 0.00035353205748833716,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 46.0,
      "step": 160
    },
    {
      "epoch": 0.017045153776930815,
      "grad_norm": 0.0004495004832278937,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 46.0,
      "step": 161
    },
    {
      "epoch": 0.01715102429728442,
      "grad_norm": 0.0004749736108351499,
      "learning_rate": 9.549150281252633e-06,
      "loss": 46.0,
      "step": 162
    },
    {
      "epoch": 0.01725689481763803,
      "grad_norm": 0.00045031620538793504,
      "learning_rate": 9.068759265665384e-06,
      "loss": 46.0,
      "step": 163
    },
    {
      "epoch": 0.017362765337991637,
      "grad_norm": 0.0004341602907516062,
      "learning_rate": 8.599558442598998e-06,
      "loss": 46.0,
      "step": 164
    },
    {
      "epoch": 0.017468635858345245,
      "grad_norm": 0.00039324010140262544,
      "learning_rate": 8.141676086873572e-06,
      "loss": 46.0,
      "step": 165
    },
    {
      "epoch": 0.01757450637869885,
      "grad_norm": 0.00040012571844272316,
      "learning_rate": 7.695237378953223e-06,
      "loss": 46.0,
      "step": 166
    },
    {
      "epoch": 0.01768037689905246,
      "grad_norm": 0.0004905827809125185,
      "learning_rate": 7.260364370723044e-06,
      "loss": 46.0,
      "step": 167
    },
    {
      "epoch": 0.017786247419406067,
      "grad_norm": 0.0003093832347076386,
      "learning_rate": 6.837175952121306e-06,
      "loss": 46.0,
      "step": 168
    },
    {
      "epoch": 0.017892117939759675,
      "grad_norm": 0.0004072758601978421,
      "learning_rate": 6.425787818636131e-06,
      "loss": 46.0,
      "step": 169
    },
    {
      "epoch": 0.01799798846011328,
      "grad_norm": 0.00039729507989250124,
      "learning_rate": 6.026312439675552e-06,
      "loss": 46.0,
      "step": 170
    },
    {
      "epoch": 0.01810385898046689,
      "grad_norm": 0.00039634527638554573,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 46.0,
      "step": 171
    },
    {
      "epoch": 0.018209729500820497,
      "grad_norm": 0.00036778414505533874,
      "learning_rate": 5.263533508961827e-06,
      "loss": 46.0,
      "step": 172
    },
    {
      "epoch": 0.018315600021174105,
      "grad_norm": 0.00030700594652444124,
      "learning_rate": 4.900438493352055e-06,
      "loss": 46.0,
      "step": 173
    },
    {
      "epoch": 0.01842147054152771,
      "grad_norm": 0.00028865691274404526,
      "learning_rate": 4.549673247541875e-06,
      "loss": 46.0,
      "step": 174
    },
    {
      "epoch": 0.01852734106188132,
      "grad_norm": 0.00037024260382167995,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 46.0,
      "step": 175
    },
    {
      "epoch": 0.018633211582234927,
      "grad_norm": 0.00036190252285450697,
      "learning_rate": 3.885512251130763e-06,
      "loss": 46.0,
      "step": 176
    },
    {
      "epoch": 0.018739082102588536,
      "grad_norm": 0.00022930241539143026,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 46.0,
      "step": 177
    },
    {
      "epoch": 0.01884495262294214,
      "grad_norm": 0.0003324221761431545,
      "learning_rate": 3.271776770026963e-06,
      "loss": 46.0,
      "step": 178
    },
    {
      "epoch": 0.01895082314329575,
      "grad_norm": 0.00042887942981906235,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 46.0,
      "step": 179
    },
    {
      "epoch": 0.019056693663649357,
      "grad_norm": 0.0003296059148851782,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 46.0,
      "step": 180
    },
    {
      "epoch": 0.019162564184002966,
      "grad_norm": 0.0002851575263775885,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 46.0,
      "step": 181
    },
    {
      "epoch": 0.01926843470435657,
      "grad_norm": 0.0001940513902809471,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 46.0,
      "step": 182
    },
    {
      "epoch": 0.01937430522471018,
      "grad_norm": 0.0003125584335066378,
      "learning_rate": 1.962316193157593e-06,
      "loss": 46.0,
      "step": 183
    },
    {
      "epoch": 0.019480175745063787,
      "grad_norm": 0.0002611489035189152,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 46.0,
      "step": 184
    },
    {
      "epoch": 0.019586046265417396,
      "grad_norm": 0.00031425541965290904,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 46.0,
      "step": 185
    },
    {
      "epoch": 0.019691916785771,
      "grad_norm": 0.0006939004524610937,
      "learning_rate": 1.333670137599713e-06,
      "loss": 46.0,
      "step": 186
    },
    {
      "epoch": 0.01979778730612461,
      "grad_norm": 0.000857637554872781,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 46.0,
      "step": 187
    },
    {
      "epoch": 0.019903657826478217,
      "grad_norm": 0.0011133542284369469,
      "learning_rate": 9.810017062595322e-07,
      "loss": 46.0,
      "step": 188
    },
    {
      "epoch": 0.020009528346831826,
      "grad_norm": 0.003940091468393803,
      "learning_rate": 8.247462563808817e-07,
      "loss": 46.0,
      "step": 189
    },
    {
      "epoch": 0.02011539886718543,
      "grad_norm": 0.004161616321653128,
      "learning_rate": 6.819348298638839e-07,
      "loss": 46.0,
      "step": 190
    },
    {
      "epoch": 0.02022126938753904,
      "grad_norm": 0.003415259998291731,
      "learning_rate": 5.526064699265753e-07,
      "loss": 46.0,
      "step": 191
    },
    {
      "epoch": 0.020327139907892647,
      "grad_norm": 0.0036220657639205456,
      "learning_rate": 4.367965336512403e-07,
      "loss": 46.0,
      "step": 192
    },
    {
      "epoch": 0.020433010428246256,
      "grad_norm": 0.00391359580680728,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 46.0,
      "step": 193
    },
    {
      "epoch": 0.02053888094859986,
      "grad_norm": 0.004199817311018705,
      "learning_rate": 2.458548727494292e-07,
      "loss": 46.0,
      "step": 194
    },
    {
      "epoch": 0.02064475146895347,
      "grad_norm": 0.004004967398941517,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 46.0,
      "step": 195
    },
    {
      "epoch": 0.020750621989307078,
      "grad_norm": 0.004130095709115267,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 46.0,
      "step": 196
    },
    {
      "epoch": 0.020856492509660686,
      "grad_norm": 0.0036113057285547256,
      "learning_rate": 6.150154258476315e-08,
      "loss": 46.0,
      "step": 197
    },
    {
      "epoch": 0.02096236303001429,
      "grad_norm": 0.0042992583476006985,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 46.0,
      "step": 198
    },
    {
      "epoch": 0.0210682335503679,
      "grad_norm": 0.004452473483979702,
      "learning_rate": 6.834750376549792e-09,
      "loss": 46.0,
      "step": 199
    },
    {
      "epoch": 0.021174104070721508,
      "grad_norm": 0.0033008004538714886,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 200
    },
    {
      "epoch": 0.021174104070721508,
      "eval_loss": 11.5,
      "eval_runtime": 72.0373,
      "eval_samples_per_second": 220.83,
      "eval_steps_per_second": 55.208,
      "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": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 32319255085056.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}