{
  "best_metric": 0.5091058611869812,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.1120919153706039,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005604595768530195,
      "grad_norm": 0.3677280843257904,
      "learning_rate": 1e-05,
      "loss": 0.8008,
      "step": 1
    },
    {
      "epoch": 0.0005604595768530195,
      "eval_loss": 0.7070078253746033,
      "eval_runtime": 51.8694,
      "eval_samples_per_second": 57.934,
      "eval_steps_per_second": 14.498,
      "step": 1
    },
    {
      "epoch": 0.001120919153706039,
      "grad_norm": 0.41068851947784424,
      "learning_rate": 2e-05,
      "loss": 0.74,
      "step": 2
    },
    {
      "epoch": 0.0016813787305590584,
      "grad_norm": 0.42486411333084106,
      "learning_rate": 3e-05,
      "loss": 0.6944,
      "step": 3
    },
    {
      "epoch": 0.002241838307412078,
      "grad_norm": 0.457768976688385,
      "learning_rate": 4e-05,
      "loss": 0.6118,
      "step": 4
    },
    {
      "epoch": 0.0028022978842650974,
      "grad_norm": 0.46679753065109253,
      "learning_rate": 5e-05,
      "loss": 0.7172,
      "step": 5
    },
    {
      "epoch": 0.003362757461118117,
      "grad_norm": 0.30219173431396484,
      "learning_rate": 6e-05,
      "loss": 0.6936,
      "step": 6
    },
    {
      "epoch": 0.003923217037971136,
      "grad_norm": 0.25852134823799133,
      "learning_rate": 7e-05,
      "loss": 0.7729,
      "step": 7
    },
    {
      "epoch": 0.004483676614824156,
      "grad_norm": 0.207831472158432,
      "learning_rate": 8e-05,
      "loss": 0.576,
      "step": 8
    },
    {
      "epoch": 0.005044136191677175,
      "grad_norm": 0.15584684908390045,
      "learning_rate": 9e-05,
      "loss": 0.6563,
      "step": 9
    },
    {
      "epoch": 0.005604595768530195,
      "grad_norm": 0.20175990462303162,
      "learning_rate": 0.0001,
      "loss": 0.757,
      "step": 10
    },
    {
      "epoch": 0.006165055345383214,
      "grad_norm": 0.1726260632276535,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.5433,
      "step": 11
    },
    {
      "epoch": 0.006725514922236234,
      "grad_norm": 0.18816137313842773,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.5361,
      "step": 12
    },
    {
      "epoch": 0.007285974499089253,
      "grad_norm": 0.2139499932527542,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.5815,
      "step": 13
    },
    {
      "epoch": 0.007846434075942273,
      "grad_norm": 0.19822777807712555,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.6024,
      "step": 14
    },
    {
      "epoch": 0.008406893652795292,
      "grad_norm": 0.1902790516614914,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.4765,
      "step": 15
    },
    {
      "epoch": 0.008967353229648312,
      "grad_norm": 0.13752365112304688,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.5302,
      "step": 16
    },
    {
      "epoch": 0.009527812806501331,
      "grad_norm": 0.141414612531662,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.5424,
      "step": 17
    },
    {
      "epoch": 0.01008827238335435,
      "grad_norm": 0.18285870552062988,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.7664,
      "step": 18
    },
    {
      "epoch": 0.01064873196020737,
      "grad_norm": 0.1193653792142868,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.4187,
      "step": 19
    },
    {
      "epoch": 0.01120919153706039,
      "grad_norm": 0.1328144520521164,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.5694,
      "step": 20
    },
    {
      "epoch": 0.011769651113913409,
      "grad_norm": 0.11352738738059998,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.428,
      "step": 21
    },
    {
      "epoch": 0.012330110690766428,
      "grad_norm": 0.12871421873569489,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.6375,
      "step": 22
    },
    {
      "epoch": 0.012890570267619448,
      "grad_norm": 0.10819278657436371,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.4676,
      "step": 23
    },
    {
      "epoch": 0.013451029844472467,
      "grad_norm": 0.09870828688144684,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.446,
      "step": 24
    },
    {
      "epoch": 0.014011489421325487,
      "grad_norm": 0.10254420340061188,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.3142,
      "step": 25
    },
    {
      "epoch": 0.014571948998178506,
      "grad_norm": 0.10862113535404205,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.5508,
      "step": 26
    },
    {
      "epoch": 0.015132408575031526,
      "grad_norm": 0.10733336955308914,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.4559,
      "step": 27
    },
    {
      "epoch": 0.015692868151884545,
      "grad_norm": 0.0958758294582367,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.3724,
      "step": 28
    },
    {
      "epoch": 0.016253327728737565,
      "grad_norm": 0.11765323579311371,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6093,
      "step": 29
    },
    {
      "epoch": 0.016813787305590584,
      "grad_norm": 0.11290626972913742,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.5163,
      "step": 30
    },
    {
      "epoch": 0.017374246882443604,
      "grad_norm": 0.10655861347913742,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.5786,
      "step": 31
    },
    {
      "epoch": 0.017934706459296623,
      "grad_norm": 0.09757158160209656,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.3797,
      "step": 32
    },
    {
      "epoch": 0.018495166036149643,
      "grad_norm": 0.12417278438806534,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.5181,
      "step": 33
    },
    {
      "epoch": 0.019055625613002662,
      "grad_norm": 0.13819845020771027,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.4893,
      "step": 34
    },
    {
      "epoch": 0.01961608518985568,
      "grad_norm": 0.14043879508972168,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.5957,
      "step": 35
    },
    {
      "epoch": 0.0201765447667087,
      "grad_norm": 0.14535368978977203,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.5706,
      "step": 36
    },
    {
      "epoch": 0.02073700434356172,
      "grad_norm": 0.19944265484809875,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.5659,
      "step": 37
    },
    {
      "epoch": 0.02129746392041474,
      "grad_norm": 0.2089586853981018,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.5853,
      "step": 38
    },
    {
      "epoch": 0.02185792349726776,
      "grad_norm": 0.29936686158180237,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.8395,
      "step": 39
    },
    {
      "epoch": 0.02241838307412078,
      "grad_norm": 0.25824102759361267,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.5793,
      "step": 40
    },
    {
      "epoch": 0.0229788426509738,
      "grad_norm": 0.7873288989067078,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.1794,
      "step": 41
    },
    {
      "epoch": 0.023539302227826818,
      "grad_norm": 1.031481146812439,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.3254,
      "step": 42
    },
    {
      "epoch": 0.024099761804679837,
      "grad_norm": 0.22185416519641876,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.0622,
      "step": 43
    },
    {
      "epoch": 0.024660221381532857,
      "grad_norm": 0.1807919442653656,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.0666,
      "step": 44
    },
    {
      "epoch": 0.025220680958385876,
      "grad_norm": 0.2415287345647812,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.079,
      "step": 45
    },
    {
      "epoch": 0.025781140535238896,
      "grad_norm": 0.22567234933376312,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.0708,
      "step": 46
    },
    {
      "epoch": 0.026341600112091915,
      "grad_norm": 0.26517754793167114,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.084,
      "step": 47
    },
    {
      "epoch": 0.026902059688944935,
      "grad_norm": 0.28105413913726807,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0914,
      "step": 48
    },
    {
      "epoch": 0.027462519265797954,
      "grad_norm": 0.3662070631980896,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.1429,
      "step": 49
    },
    {
      "epoch": 0.028022978842650974,
      "grad_norm": 0.3930314779281616,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.1749,
      "step": 50
    },
    {
      "epoch": 0.028022978842650974,
      "eval_loss": 0.5723596811294556,
      "eval_runtime": 51.8133,
      "eval_samples_per_second": 57.997,
      "eval_steps_per_second": 14.514,
      "step": 50
    },
    {
      "epoch": 0.028583438419503993,
      "grad_norm": 0.44410592317581177,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.7213,
      "step": 51
    },
    {
      "epoch": 0.029143897996357013,
      "grad_norm": 0.38932937383651733,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.6611,
      "step": 52
    },
    {
      "epoch": 0.029704357573210032,
      "grad_norm": 0.42243826389312744,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.7757,
      "step": 53
    },
    {
      "epoch": 0.03026481715006305,
      "grad_norm": 0.3154599964618683,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.6941,
      "step": 54
    },
    {
      "epoch": 0.03082527672691607,
      "grad_norm": 0.27853474020957947,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.6648,
      "step": 55
    },
    {
      "epoch": 0.03138573630376909,
      "grad_norm": 0.264017790555954,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7467,
      "step": 56
    },
    {
      "epoch": 0.031946195880622114,
      "grad_norm": 0.21072551608085632,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.6833,
      "step": 57
    },
    {
      "epoch": 0.03250665545747513,
      "grad_norm": 0.15394234657287598,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.6122,
      "step": 58
    },
    {
      "epoch": 0.03306711503432815,
      "grad_norm": 0.12989814579486847,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.6602,
      "step": 59
    },
    {
      "epoch": 0.03362757461118117,
      "grad_norm": 0.10766580700874329,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.5903,
      "step": 60
    },
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 0.10808862745761871,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6399,
      "step": 61
    },
    {
      "epoch": 0.03474849376488721,
      "grad_norm": 0.10216817259788513,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.5569,
      "step": 62
    },
    {
      "epoch": 0.03530895334174023,
      "grad_norm": 0.11299166828393936,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.5451,
      "step": 63
    },
    {
      "epoch": 0.035869412918593246,
      "grad_norm": 0.10453053563833237,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.567,
      "step": 64
    },
    {
      "epoch": 0.03642987249544627,
      "grad_norm": 0.11050667613744736,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.4774,
      "step": 65
    },
    {
      "epoch": 0.036990332072299285,
      "grad_norm": 0.10273489356040955,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.4623,
      "step": 66
    },
    {
      "epoch": 0.03755079164915231,
      "grad_norm": 0.11806432157754898,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.4694,
      "step": 67
    },
    {
      "epoch": 0.038111251226005324,
      "grad_norm": 0.11905335634946823,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.4483,
      "step": 68
    },
    {
      "epoch": 0.03867171080285835,
      "grad_norm": 0.1081826388835907,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.4317,
      "step": 69
    },
    {
      "epoch": 0.03923217037971136,
      "grad_norm": 0.12470875680446625,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.6757,
      "step": 70
    },
    {
      "epoch": 0.039792629956564386,
      "grad_norm": 0.10311262309551239,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.5085,
      "step": 71
    },
    {
      "epoch": 0.0403530895334174,
      "grad_norm": 0.09609906375408173,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.3204,
      "step": 72
    },
    {
      "epoch": 0.040913549110270425,
      "grad_norm": 0.1114426925778389,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.6135,
      "step": 73
    },
    {
      "epoch": 0.04147400868712344,
      "grad_norm": 0.11053726077079773,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.5591,
      "step": 74
    },
    {
      "epoch": 0.042034468263976464,
      "grad_norm": 0.09882042557001114,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.4849,
      "step": 75
    },
    {
      "epoch": 0.04259492784082948,
      "grad_norm": 0.09307467937469482,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.3876,
      "step": 76
    },
    {
      "epoch": 0.0431553874176825,
      "grad_norm": 0.10101637989282608,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.4171,
      "step": 77
    },
    {
      "epoch": 0.04371584699453552,
      "grad_norm": 0.09729183465242386,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.3159,
      "step": 78
    },
    {
      "epoch": 0.04427630657138854,
      "grad_norm": 0.10029616951942444,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.4379,
      "step": 79
    },
    {
      "epoch": 0.04483676614824156,
      "grad_norm": 0.10572826117277145,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.3283,
      "step": 80
    },
    {
      "epoch": 0.04539722572509458,
      "grad_norm": 0.11056410521268845,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.5298,
      "step": 81
    },
    {
      "epoch": 0.0459576853019476,
      "grad_norm": 0.10960118472576141,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.4963,
      "step": 82
    },
    {
      "epoch": 0.04651814487880062,
      "grad_norm": 0.11615201830863953,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.4284,
      "step": 83
    },
    {
      "epoch": 0.047078604455653636,
      "grad_norm": 0.13001911342144012,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.5505,
      "step": 84
    },
    {
      "epoch": 0.04763906403250666,
      "grad_norm": 0.16498185694217682,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.6697,
      "step": 85
    },
    {
      "epoch": 0.048199523609359675,
      "grad_norm": 0.14539735019207,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3698,
      "step": 86
    },
    {
      "epoch": 0.0487599831862127,
      "grad_norm": 0.15213927626609802,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.445,
      "step": 87
    },
    {
      "epoch": 0.049320442763065714,
      "grad_norm": 0.22662079334259033,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6716,
      "step": 88
    },
    {
      "epoch": 0.04988090233991874,
      "grad_norm": 0.2835257947444916,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.8111,
      "step": 89
    },
    {
      "epoch": 0.05044136191677175,
      "grad_norm": 0.24168755114078522,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.5775,
      "step": 90
    },
    {
      "epoch": 0.051001821493624776,
      "grad_norm": 0.16579575836658478,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.3765,
      "step": 91
    },
    {
      "epoch": 0.05156228107047779,
      "grad_norm": 0.4730679988861084,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.9374,
      "step": 92
    },
    {
      "epoch": 0.052122740647330815,
      "grad_norm": 0.4557138979434967,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.6752,
      "step": 93
    },
    {
      "epoch": 0.05268320022418383,
      "grad_norm": 0.07180450111627579,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0505,
      "step": 94
    },
    {
      "epoch": 0.053243659801036854,
      "grad_norm": 0.06586256623268127,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0194,
      "step": 95
    },
    {
      "epoch": 0.05380411937788987,
      "grad_norm": 0.09364598244428635,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.0313,
      "step": 96
    },
    {
      "epoch": 0.05436457895474289,
      "grad_norm": 0.07820381969213486,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.0252,
      "step": 97
    },
    {
      "epoch": 0.05492503853159591,
      "grad_norm": 0.09589055925607681,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0294,
      "step": 98
    },
    {
      "epoch": 0.05548549810844893,
      "grad_norm": 0.12185172736644745,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0399,
      "step": 99
    },
    {
      "epoch": 0.05604595768530195,
      "grad_norm": 0.19745580852031708,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0742,
      "step": 100
    },
    {
      "epoch": 0.05604595768530195,
      "eval_loss": 0.5517994165420532,
      "eval_runtime": 51.8155,
      "eval_samples_per_second": 57.994,
      "eval_steps_per_second": 14.513,
      "step": 100
    },
    {
      "epoch": 0.05660641726215497,
      "grad_norm": 0.2155827432870865,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.7762,
      "step": 101
    },
    {
      "epoch": 0.057166876839007986,
      "grad_norm": 0.20180773735046387,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5747,
      "step": 102
    },
    {
      "epoch": 0.05772733641586101,
      "grad_norm": 0.20370514690876007,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.6125,
      "step": 103
    },
    {
      "epoch": 0.058287795992714025,
      "grad_norm": 0.1845598667860031,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.5494,
      "step": 104
    },
    {
      "epoch": 0.05884825556956705,
      "grad_norm": 0.18556399643421173,
      "learning_rate": 5e-05,
      "loss": 0.6558,
      "step": 105
    },
    {
      "epoch": 0.059408715146420064,
      "grad_norm": 0.17830416560173035,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.6052,
      "step": 106
    },
    {
      "epoch": 0.05996917472327309,
      "grad_norm": 0.15088754892349243,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.6474,
      "step": 107
    },
    {
      "epoch": 0.0605296343001261,
      "grad_norm": 0.15237480401992798,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.7129,
      "step": 108
    },
    {
      "epoch": 0.061090093876979126,
      "grad_norm": 0.13710720837116241,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.6401,
      "step": 109
    },
    {
      "epoch": 0.06165055345383214,
      "grad_norm": 0.1370527446269989,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.6849,
      "step": 110
    },
    {
      "epoch": 0.062211013030685165,
      "grad_norm": 0.11326868087053299,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.6209,
      "step": 111
    },
    {
      "epoch": 0.06277147260753818,
      "grad_norm": 0.10983113944530487,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.6316,
      "step": 112
    },
    {
      "epoch": 0.0633319321843912,
      "grad_norm": 0.10251860320568085,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.5914,
      "step": 113
    },
    {
      "epoch": 0.06389239176124423,
      "grad_norm": 0.10766825824975967,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.6029,
      "step": 114
    },
    {
      "epoch": 0.06445285133809724,
      "grad_norm": 0.0965939313173294,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.4778,
      "step": 115
    },
    {
      "epoch": 0.06501331091495026,
      "grad_norm": 0.07469344139099121,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.393,
      "step": 116
    },
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 0.07472770661115646,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.4454,
      "step": 117
    },
    {
      "epoch": 0.0661342300686563,
      "grad_norm": 0.08290337026119232,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.4298,
      "step": 118
    },
    {
      "epoch": 0.06669468964550931,
      "grad_norm": 0.08237549662590027,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.5801,
      "step": 119
    },
    {
      "epoch": 0.06725514922236234,
      "grad_norm": 0.08433205634355545,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.5189,
      "step": 120
    },
    {
      "epoch": 0.06781560879921536,
      "grad_norm": 0.08241920918226242,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.5882,
      "step": 121
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.07750262320041656,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.4329,
      "step": 122
    },
    {
      "epoch": 0.06893652795292139,
      "grad_norm": 0.09360496699810028,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.4498,
      "step": 123
    },
    {
      "epoch": 0.06949698752977441,
      "grad_norm": 0.07918721437454224,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.4436,
      "step": 124
    },
    {
      "epoch": 0.07005744710662744,
      "grad_norm": 0.07802974432706833,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.4385,
      "step": 125
    },
    {
      "epoch": 0.07061790668348046,
      "grad_norm": 0.07684274017810822,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.3796,
      "step": 126
    },
    {
      "epoch": 0.07117836626033347,
      "grad_norm": 0.08179648965597153,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.23,
      "step": 127
    },
    {
      "epoch": 0.07173882583718649,
      "grad_norm": 0.09350673854351044,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.4804,
      "step": 128
    },
    {
      "epoch": 0.07229928541403952,
      "grad_norm": 0.10113374143838882,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.5466,
      "step": 129
    },
    {
      "epoch": 0.07285974499089254,
      "grad_norm": 0.10080043971538544,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.5033,
      "step": 130
    },
    {
      "epoch": 0.07342020456774555,
      "grad_norm": 0.10606753826141357,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.5129,
      "step": 131
    },
    {
      "epoch": 0.07398066414459857,
      "grad_norm": 0.10032961517572403,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.432,
      "step": 132
    },
    {
      "epoch": 0.0745411237214516,
      "grad_norm": 0.12103240191936493,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.5362,
      "step": 133
    },
    {
      "epoch": 0.07510158329830462,
      "grad_norm": 0.1325491964817047,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.5433,
      "step": 134
    },
    {
      "epoch": 0.07566204287515763,
      "grad_norm": 0.10120103508234024,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.3614,
      "step": 135
    },
    {
      "epoch": 0.07622250245201065,
      "grad_norm": 0.14613452553749084,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.4622,
      "step": 136
    },
    {
      "epoch": 0.07678296202886367,
      "grad_norm": 0.21499399840831757,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.5762,
      "step": 137
    },
    {
      "epoch": 0.0773434216057167,
      "grad_norm": 0.18698327243328094,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.4825,
      "step": 138
    },
    {
      "epoch": 0.0779038811825697,
      "grad_norm": 0.38714802265167236,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.86,
      "step": 139
    },
    {
      "epoch": 0.07846434075942273,
      "grad_norm": 0.2595014274120331,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.5248,
      "step": 140
    },
    {
      "epoch": 0.07902480033627575,
      "grad_norm": 0.2457626461982727,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.3919,
      "step": 141
    },
    {
      "epoch": 0.07958525991312877,
      "grad_norm": 0.596648633480072,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.8573,
      "step": 142
    },
    {
      "epoch": 0.08014571948998178,
      "grad_norm": 0.10801538825035095,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0945,
      "step": 143
    },
    {
      "epoch": 0.0807061790668348,
      "grad_norm": 0.06797955185174942,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.0213,
      "step": 144
    },
    {
      "epoch": 0.08126663864368783,
      "grad_norm": 0.08374099433422089,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.0245,
      "step": 145
    },
    {
      "epoch": 0.08182709822054085,
      "grad_norm": 0.08725516498088837,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.0266,
      "step": 146
    },
    {
      "epoch": 0.08238755779739386,
      "grad_norm": 0.09196209907531738,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0286,
      "step": 147
    },
    {
      "epoch": 0.08294801737424688,
      "grad_norm": 0.10627547651529312,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.0324,
      "step": 148
    },
    {
      "epoch": 0.0835084769510999,
      "grad_norm": 0.12337683141231537,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.0474,
      "step": 149
    },
    {
      "epoch": 0.08406893652795293,
      "grad_norm": 0.2357434630393982,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0874,
      "step": 150
    },
    {
      "epoch": 0.08406893652795293,
      "eval_loss": 0.5263974070549011,
      "eval_runtime": 51.8794,
      "eval_samples_per_second": 57.923,
      "eval_steps_per_second": 14.495,
      "step": 150
    },
    {
      "epoch": 0.08462939610480594,
      "grad_norm": 0.0901440903544426,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.543,
      "step": 151
    },
    {
      "epoch": 0.08518985568165896,
      "grad_norm": 0.0969991385936737,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.5639,
      "step": 152
    },
    {
      "epoch": 0.08575031525851198,
      "grad_norm": 0.09385892748832703,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.5533,
      "step": 153
    },
    {
      "epoch": 0.086310774835365,
      "grad_norm": 0.0925811156630516,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.5487,
      "step": 154
    },
    {
      "epoch": 0.08687123441221802,
      "grad_norm": 0.10227348655462265,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.5814,
      "step": 155
    },
    {
      "epoch": 0.08743169398907104,
      "grad_norm": 0.0962430089712143,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.5488,
      "step": 156
    },
    {
      "epoch": 0.08799215356592406,
      "grad_norm": 0.09839499741792679,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.606,
      "step": 157
    },
    {
      "epoch": 0.08855261314277708,
      "grad_norm": 0.09578869491815567,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.6249,
      "step": 158
    },
    {
      "epoch": 0.0891130727196301,
      "grad_norm": 0.09709734469652176,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.5996,
      "step": 159
    },
    {
      "epoch": 0.08967353229648312,
      "grad_norm": 0.10046759992837906,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.659,
      "step": 160
    },
    {
      "epoch": 0.09023399187333614,
      "grad_norm": 0.09015260636806488,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.5788,
      "step": 161
    },
    {
      "epoch": 0.09079445145018916,
      "grad_norm": 0.08255616575479507,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.5354,
      "step": 162
    },
    {
      "epoch": 0.09135491102704217,
      "grad_norm": 0.07470031827688217,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.4842,
      "step": 163
    },
    {
      "epoch": 0.0919153706038952,
      "grad_norm": 0.0882846936583519,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.5403,
      "step": 164
    },
    {
      "epoch": 0.09247583018074822,
      "grad_norm": 0.08571461588144302,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.5694,
      "step": 165
    },
    {
      "epoch": 0.09303628975760124,
      "grad_norm": 0.08566728979349136,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.5365,
      "step": 166
    },
    {
      "epoch": 0.09359674933445425,
      "grad_norm": 0.07061930000782013,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.3471,
      "step": 167
    },
    {
      "epoch": 0.09415720891130727,
      "grad_norm": 0.07187210023403168,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.3464,
      "step": 168
    },
    {
      "epoch": 0.0947176684881603,
      "grad_norm": 0.07516112178564072,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.4436,
      "step": 169
    },
    {
      "epoch": 0.09527812806501332,
      "grad_norm": 0.06667198985815048,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.3392,
      "step": 170
    },
    {
      "epoch": 0.09583858764186633,
      "grad_norm": 0.07135532051324844,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.3911,
      "step": 171
    },
    {
      "epoch": 0.09639904721871935,
      "grad_norm": 0.0793675035238266,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.4653,
      "step": 172
    },
    {
      "epoch": 0.09695950679557237,
      "grad_norm": 0.07511810958385468,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.4429,
      "step": 173
    },
    {
      "epoch": 0.0975199663724254,
      "grad_norm": 0.08126147091388702,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.4487,
      "step": 174
    },
    {
      "epoch": 0.0980804259492784,
      "grad_norm": 0.08286601305007935,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.4705,
      "step": 175
    },
    {
      "epoch": 0.09864088552613143,
      "grad_norm": 0.07838480919599533,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.3966,
      "step": 176
    },
    {
      "epoch": 0.09920134510298445,
      "grad_norm": 0.09499913454055786,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.5837,
      "step": 177
    },
    {
      "epoch": 0.09976180467983747,
      "grad_norm": 0.09032324701547623,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.4116,
      "step": 178
    },
    {
      "epoch": 0.10032226425669048,
      "grad_norm": 0.08511090278625488,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.4243,
      "step": 179
    },
    {
      "epoch": 0.1008827238335435,
      "grad_norm": 0.09722740203142166,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.4873,
      "step": 180
    },
    {
      "epoch": 0.10144318341039653,
      "grad_norm": 0.1047426238656044,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.5064,
      "step": 181
    },
    {
      "epoch": 0.10200364298724955,
      "grad_norm": 0.10460769385099411,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.4993,
      "step": 182
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.12271469831466675,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.6215,
      "step": 183
    },
    {
      "epoch": 0.10312456214095558,
      "grad_norm": 0.08913122862577438,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.2827,
      "step": 184
    },
    {
      "epoch": 0.1036850217178086,
      "grad_norm": 0.1290159374475479,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.5769,
      "step": 185
    },
    {
      "epoch": 0.10424548129466163,
      "grad_norm": 0.1382816880941391,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.4667,
      "step": 186
    },
    {
      "epoch": 0.10480594087151464,
      "grad_norm": 0.2082459032535553,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.6412,
      "step": 187
    },
    {
      "epoch": 0.10536640044836766,
      "grad_norm": 0.17582543194293976,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.5639,
      "step": 188
    },
    {
      "epoch": 0.10592686002522068,
      "grad_norm": 0.13624028861522675,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.3429,
      "step": 189
    },
    {
      "epoch": 0.10648731960207371,
      "grad_norm": 0.16022244095802307,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.3135,
      "step": 190
    },
    {
      "epoch": 0.10704777917892672,
      "grad_norm": 0.3089972734451294,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.4147,
      "step": 191
    },
    {
      "epoch": 0.10760823875577974,
      "grad_norm": 0.5554230213165283,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.7216,
      "step": 192
    },
    {
      "epoch": 0.10816869833263276,
      "grad_norm": 0.06168578937649727,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.0151,
      "step": 193
    },
    {
      "epoch": 0.10872915790948579,
      "grad_norm": 0.060312360525131226,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0198,
      "step": 194
    },
    {
      "epoch": 0.1092896174863388,
      "grad_norm": 0.059499192982912064,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0178,
      "step": 195
    },
    {
      "epoch": 0.10985007706319182,
      "grad_norm": 0.08455067873001099,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.022,
      "step": 196
    },
    {
      "epoch": 0.11041053664004484,
      "grad_norm": 0.07464565336704254,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.0266,
      "step": 197
    },
    {
      "epoch": 0.11097099621689786,
      "grad_norm": 0.10879623144865036,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0334,
      "step": 198
    },
    {
      "epoch": 0.11153145579375087,
      "grad_norm": 0.11358213424682617,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.0354,
      "step": 199
    },
    {
      "epoch": 0.1120919153706039,
      "grad_norm": 0.17541155219078064,
      "learning_rate": 0.0,
      "loss": 0.0566,
      "step": 200
    },
    {
      "epoch": 0.1120919153706039,
      "eval_loss": 0.5091058611869812,
      "eval_runtime": 51.8351,
      "eval_samples_per_second": 57.972,
      "eval_steps_per_second": 14.508,
      "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": 9147051367464960.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}