{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.11757789535567313,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005878894767783657,
      "grad_norm": 1.2200881428725552e-05,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0005878894767783657,
      "eval_loss": 11.5,
      "eval_runtime": 14.7203,
      "eval_samples_per_second": 194.63,
      "eval_steps_per_second": 48.708,
      "step": 1
    },
    {
      "epoch": 0.0011757789535567313,
      "grad_norm": 1.7827886040322483e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.001763668430335097,
      "grad_norm": 2.2101048671174794e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0023515579071134627,
      "grad_norm": 1.0840062714123633e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.0029394473838918285,
      "grad_norm": 1.330858049186645e-05,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.003527336860670194,
      "grad_norm": 1.1974941116932314e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.00411522633744856,
      "grad_norm": 1.4702818589285016e-05,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.004703115814226925,
      "grad_norm": 1.117567444453016e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.005291005291005291,
      "grad_norm": 1.4747185559826903e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.005878894767783657,
      "grad_norm": 1.419016371073667e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.006466784244562022,
      "grad_norm": 1.6711815987946466e-05,
      "learning_rate": 9.999316524962345e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.007054673721340388,
      "grad_norm": 2.282014611409977e-05,
      "learning_rate": 9.997266286704631e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.007642563198118754,
      "grad_norm": 2.0610854335245676e-05,
      "learning_rate": 9.993849845741524e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.00823045267489712,
      "grad_norm": 2.4417717213509604e-05,
      "learning_rate": 9.989068136093873e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.008818342151675485,
      "grad_norm": 2.1419642507680692e-05,
      "learning_rate": 9.98292246503335e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.00940623162845385,
      "grad_norm": 2.7986092391074635e-05,
      "learning_rate": 9.975414512725057e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.009994121105232217,
      "grad_norm": 2.714978836593218e-05,
      "learning_rate": 9.966546331768191e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.010582010582010581,
      "grad_norm": 2.6022331439889967e-05,
      "learning_rate": 9.956320346634876e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.011169900058788948,
      "grad_norm": 3.4786058677127585e-05,
      "learning_rate": 9.944739353007344e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.011757789535567314,
      "grad_norm": 3.197040132363327e-05,
      "learning_rate": 9.931806517013612e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.012345679012345678,
      "grad_norm": 2.781535658868961e-05,
      "learning_rate": 9.917525374361912e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.012933568489124045,
      "grad_norm": 3.9784859836800024e-05,
      "learning_rate": 9.901899829374047e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.01352145796590241,
      "grad_norm": 3.073911648243666e-05,
      "learning_rate": 9.884934153917997e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.014109347442680775,
      "grad_norm": 2.9768023523502052e-05,
      "learning_rate": 9.86663298624003e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.014697236919459141,
      "grad_norm": 4.239286499796435e-05,
      "learning_rate": 9.847001329696653e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.015285126396237508,
      "grad_norm": 3.544949140632525e-05,
      "learning_rate": 9.826044551386744e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.015873015873015872,
      "grad_norm": 3.475979247014038e-05,
      "learning_rate": 9.803768380684242e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.01646090534979424,
      "grad_norm": 4.99827328894753e-05,
      "learning_rate": 9.780178907671789e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.017048794826572605,
      "grad_norm": 5.652049003401771e-05,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.01763668430335097,
      "grad_norm": 6.812476931372657e-05,
      "learning_rate": 9.729086208503174e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.018224573780129337,
      "grad_norm": 5.2008861530339345e-05,
      "learning_rate": 9.701596950580806e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.0188124632569077,
      "grad_norm": 4.9285401473753154e-05,
      "learning_rate": 9.672822322997305e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.019400352733686066,
      "grad_norm": 5.389636862673797e-05,
      "learning_rate": 9.642770192448536e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.019988242210464434,
      "grad_norm": 3.948846278944984e-05,
      "learning_rate": 9.611448774886924e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.0205761316872428,
      "grad_norm": 6.24753229203634e-05,
      "learning_rate": 9.578866633275288e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.021164021164021163,
      "grad_norm": 5.562061051023193e-05,
      "learning_rate": 9.545032675245813e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.02175191064079953,
      "grad_norm": 5.352373773348518e-05,
      "learning_rate": 9.509956150664796e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.022339800117577895,
      "grad_norm": 7.429166726069525e-05,
      "learning_rate": 9.473646649103818e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.02292768959435626,
      "grad_norm": 8.258564048446715e-05,
      "learning_rate": 9.43611409721806e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.023515579071134628,
      "grad_norm": 6.324872811092064e-05,
      "learning_rate": 9.397368756032445e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.024103468547912992,
      "grad_norm": 5.442733890959062e-05,
      "learning_rate": 9.357421218136386e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 7.162464316934347e-05,
      "learning_rate": 9.316282404787871e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.025279247501469725,
      "grad_norm": 8.010022429516539e-05,
      "learning_rate": 9.273963562927695e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.02586713697824809,
      "grad_norm": 7.225250010378659e-05,
      "learning_rate": 9.230476262104677e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.026455026455026454,
      "grad_norm": 6.659435166511685e-05,
      "learning_rate": 9.185832391312644e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.02704291593180482,
      "grad_norm": 8.050394535530359e-05,
      "learning_rate": 9.140044155740101e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.027630805408583186,
      "grad_norm": 7.825119973858818e-05,
      "learning_rate": 9.093124073433463e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.02821869488536155,
      "grad_norm": 0.00010891531564993784,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.02880658436213992,
      "grad_norm": 9.231964213540778e-05,
      "learning_rate": 8.995939984474624e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.029394473838918283,
      "grad_norm": 0.0001537384232506156,
      "learning_rate": 8.945702546981969e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.029394473838918283,
      "eval_loss": 11.5,
      "eval_runtime": 14.6834,
      "eval_samples_per_second": 195.118,
      "eval_steps_per_second": 48.831,
      "step": 50
    },
    {
      "epoch": 0.029982363315696647,
      "grad_norm": 8.368275302927941e-05,
      "learning_rate": 8.894386393810563e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.030570252792475015,
      "grad_norm": 6.684993422823027e-05,
      "learning_rate": 8.842005554284296e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.03115814226925338,
      "grad_norm": 9.400331327924505e-05,
      "learning_rate": 8.788574348801675e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 7.778815779602155e-05,
      "learning_rate": 8.73410738492077e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.03233392122281011,
      "grad_norm": 8.927400631364435e-05,
      "learning_rate": 8.678619553365659e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.03292181069958848,
      "grad_norm": 6.915492849657312e-05,
      "learning_rate": 8.622126023955446e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.03350970017636684,
      "grad_norm": 9.622250945540145e-05,
      "learning_rate": 8.564642241456986e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.03409758965314521,
      "grad_norm": 7.83871510066092e-05,
      "learning_rate": 8.506183921362443e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.03468547912992358,
      "grad_norm": 9.540237806504592e-05,
      "learning_rate": 8.44676704559283e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.03527336860670194,
      "grad_norm": 9.246560512110591e-05,
      "learning_rate": 8.386407858128706e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.035861258083480306,
      "grad_norm": 0.00011721053306246176,
      "learning_rate": 8.32512286056924e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.036449147560258674,
      "grad_norm": 0.00012698338832706213,
      "learning_rate": 8.262928807620843e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 0.00011470681783976033,
      "learning_rate": 8.199842702516583e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.0376249265138154,
      "grad_norm": 0.00010416519216960296,
      "learning_rate": 8.135881792367686e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.03821281599059377,
      "grad_norm": 0.00010567618301138282,
      "learning_rate": 8.07106356344834e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.03880070546737213,
      "grad_norm": 0.00011028368317056447,
      "learning_rate": 8.005405736415126e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.0393885949441505,
      "grad_norm": 0.00010800146264955401,
      "learning_rate": 7.938926261462366e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.03997648442092887,
      "grad_norm": 0.00012027574121020734,
      "learning_rate": 7.871643313414718e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.04056437389770723,
      "grad_norm": 0.00010102101077791303,
      "learning_rate": 7.803575286758364e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.0411522633744856,
      "grad_norm": 9.868204506346956e-05,
      "learning_rate": 7.734740790612136e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.041740152851263965,
      "grad_norm": 0.0001290036889258772,
      "learning_rate": 7.66515864363997e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.042328042328042326,
      "grad_norm": 0.00013819633750244975,
      "learning_rate": 7.594847868906076e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.042915931804820694,
      "grad_norm": 0.00011861192615469918,
      "learning_rate": 7.52382768867422e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.04350382128159906,
      "grad_norm": 0.00012252737360540777,
      "learning_rate": 7.452117519152542e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.04409171075837742,
      "grad_norm": 0.00012786111619789153,
      "learning_rate": 7.379736965185368e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.04467960023515579,
      "grad_norm": 0.00013507521362043917,
      "learning_rate": 7.30670581489344e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.04526748971193416,
      "grad_norm": 0.00013448945537675172,
      "learning_rate": 7.233044034264034e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.04585537918871252,
      "grad_norm": 0.00015985369100235403,
      "learning_rate": 7.158771761692464e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.04644326866549089,
      "grad_norm": 0.0002274230937473476,
      "learning_rate": 7.083909302476453e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.047031158142269255,
      "grad_norm": 0.00018909748177975416,
      "learning_rate": 7.008477123264848e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 0.00018354748317506164,
      "learning_rate": 6.932495846462261e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.048206937095825984,
      "grad_norm": 0.00021790298342239112,
      "learning_rate": 6.855986244591104e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.04879482657260435,
      "grad_norm": 0.00019040610641241074,
      "learning_rate": 6.778969234612584e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 0.00013821803440805525,
      "learning_rate": 6.701465872208216e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.04997060552616108,
      "grad_norm": 0.00014293193817138672,
      "learning_rate": 6.623497346023418e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.05055849500293945,
      "grad_norm": 0.00016535299073439091,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.05114638447971781,
      "grad_norm": 0.0001693520462140441,
      "learning_rate": 6.466250186922325e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.05173427395649618,
      "grad_norm": 0.00013024566578678787,
      "learning_rate": 6.387014543809223e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.052322163433274546,
      "grad_norm": 0.0001873626169981435,
      "learning_rate": 6.307399704769099e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.05291005291005291,
      "grad_norm": 0.00022204006381798536,
      "learning_rate": 6.227427435703997e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.053497942386831275,
      "grad_norm": 0.0002036402584053576,
      "learning_rate": 6.147119600233758e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.05408583186360964,
      "grad_norm": 0.00021583128545898944,
      "learning_rate": 6.066498153718735e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.054673721340388004,
      "grad_norm": 0.00017304472567047924,
      "learning_rate": 5.985585137257401e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.05526161081716637,
      "grad_norm": 0.00022401580645237118,
      "learning_rate": 5.90440267166055e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.05584950029394474,
      "grad_norm": 0.0001782601175364107,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.0564373897707231,
      "grad_norm": 0.00014753256982658058,
      "learning_rate": 5.74131823855921e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.05702527924750147,
      "grad_norm": 0.0002095407253364101,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.05761316872427984,
      "grad_norm": 0.0002310619893250987,
      "learning_rate": 5.577423184847932e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.0582010582010582,
      "grad_norm": 0.00017526566807646304,
      "learning_rate": 5.495227651252315e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.058788947677836566,
      "grad_norm": 0.00036505848402157426,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.058788947677836566,
      "eval_loss": 11.5,
      "eval_runtime": 14.7262,
      "eval_samples_per_second": 194.552,
      "eval_steps_per_second": 48.689,
      "step": 100
    },
    {
      "epoch": 0.059376837154614934,
      "grad_norm": 0.00023663064348511398,
      "learning_rate": 5.330452921628497e-05,
      "loss": 46.0,
      "step": 101
    },
    {
      "epoch": 0.059964726631393295,
      "grad_norm": 0.0002004673151532188,
      "learning_rate": 5.247918773366112e-05,
      "loss": 46.0,
      "step": 102
    },
    {
      "epoch": 0.06055261610817166,
      "grad_norm": 0.00018475911929272115,
      "learning_rate": 5.165316846586541e-05,
      "loss": 46.0,
      "step": 103
    },
    {
      "epoch": 0.06114050558495003,
      "grad_norm": 0.0001679732813499868,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 46.0,
      "step": 104
    },
    {
      "epoch": 0.06172839506172839,
      "grad_norm": 0.00015846949827391654,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 0.06231628453850676,
      "grad_norm": 0.00020989541371818632,
      "learning_rate": 4.917330276168208e-05,
      "loss": 46.0,
      "step": 106
    },
    {
      "epoch": 0.06290417401528513,
      "grad_norm": 0.00017476950597483665,
      "learning_rate": 4.834683153413459e-05,
      "loss": 46.0,
      "step": 107
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 0.00022384320618584752,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 46.0,
      "step": 108
    },
    {
      "epoch": 0.06407995296884186,
      "grad_norm": 0.0002436400973238051,
      "learning_rate": 4.669547078371504e-05,
      "loss": 46.0,
      "step": 109
    },
    {
      "epoch": 0.06466784244562022,
      "grad_norm": 0.0002316598256584257,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 0.06525573192239859,
      "grad_norm": 0.00023956299992278218,
      "learning_rate": 4.504772348747687e-05,
      "loss": 46.0,
      "step": 111
    },
    {
      "epoch": 0.06584362139917696,
      "grad_norm": 0.00025115429889410734,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 46.0,
      "step": 112
    },
    {
      "epoch": 0.06643151087595532,
      "grad_norm": 0.00024121768365148455,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 46.0,
      "step": 113
    },
    {
      "epoch": 0.06701940035273368,
      "grad_norm": 0.0002561850706115365,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 46.0,
      "step": 114
    },
    {
      "epoch": 0.06760728982951206,
      "grad_norm": 0.0003116210864391178,
      "learning_rate": 4.17702704859633e-05,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 0.06819517930629042,
      "grad_norm": 0.0002619897713884711,
      "learning_rate": 4.095597328339452e-05,
      "loss": 46.0,
      "step": 116
    },
    {
      "epoch": 0.06878306878306878,
      "grad_norm": 0.00030647803214378655,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 46.0,
      "step": 117
    },
    {
      "epoch": 0.06937095825984715,
      "grad_norm": 0.00034101519850082695,
      "learning_rate": 3.933501846281267e-05,
      "loss": 46.0,
      "step": 118
    },
    {
      "epoch": 0.06995884773662552,
      "grad_norm": 0.0002878307132050395,
      "learning_rate": 3.852880399766243e-05,
      "loss": 46.0,
      "step": 119
    },
    {
      "epoch": 0.07054673721340388,
      "grad_norm": 0.00020418080384843051,
      "learning_rate": 3.772572564296005e-05,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 0.07113462669018225,
      "grad_norm": 0.00023136381059885025,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 46.0,
      "step": 121
    },
    {
      "epoch": 0.07172251616696061,
      "grad_norm": 0.0002736892201937735,
      "learning_rate": 3.612985456190778e-05,
      "loss": 46.0,
      "step": 122
    },
    {
      "epoch": 0.07231040564373897,
      "grad_norm": 0.0002745291276369244,
      "learning_rate": 3.533749813077677e-05,
      "loss": 46.0,
      "step": 123
    },
    {
      "epoch": 0.07289829512051735,
      "grad_norm": 0.00038284220499917865,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 46.0,
      "step": 124
    },
    {
      "epoch": 0.07348618459729571,
      "grad_norm": 0.0003141397319268435,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.00026097806403413415,
      "learning_rate": 3.298534127791785e-05,
      "loss": 46.0,
      "step": 126
    },
    {
      "epoch": 0.07466196355085244,
      "grad_norm": 0.0003224723623134196,
      "learning_rate": 3.221030765387417e-05,
      "loss": 46.0,
      "step": 127
    },
    {
      "epoch": 0.0752498530276308,
      "grad_norm": 0.0002900491817854345,
      "learning_rate": 3.144013755408895e-05,
      "loss": 46.0,
      "step": 128
    },
    {
      "epoch": 0.07583774250440917,
      "grad_norm": 0.0003029312065336853,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 46.0,
      "step": 129
    },
    {
      "epoch": 0.07642563198118754,
      "grad_norm": 0.000258547137491405,
      "learning_rate": 2.991522876735154e-05,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 0.0770135214579659,
      "grad_norm": 0.00037054592394270003,
      "learning_rate": 2.916090697523549e-05,
      "loss": 46.0,
      "step": 131
    },
    {
      "epoch": 0.07760141093474426,
      "grad_norm": 0.00021082180319353938,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 46.0,
      "step": 132
    },
    {
      "epoch": 0.07818930041152264,
      "grad_norm": 0.0003058281436096877,
      "learning_rate": 2.766955965735968e-05,
      "loss": 46.0,
      "step": 133
    },
    {
      "epoch": 0.078777189888301,
      "grad_norm": 0.000300654792226851,
      "learning_rate": 2.693294185106562e-05,
      "loss": 46.0,
      "step": 134
    },
    {
      "epoch": 0.07936507936507936,
      "grad_norm": 0.00030618489836342633,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 0.07995296884185774,
      "grad_norm": 0.00027653935831040144,
      "learning_rate": 2.547882480847461e-05,
      "loss": 46.0,
      "step": 136
    },
    {
      "epoch": 0.0805408583186361,
      "grad_norm": 0.0002095149247907102,
      "learning_rate": 2.476172311325783e-05,
      "loss": 46.0,
      "step": 137
    },
    {
      "epoch": 0.08112874779541446,
      "grad_norm": 0.0002489014295861125,
      "learning_rate": 2.405152131093926e-05,
      "loss": 46.0,
      "step": 138
    },
    {
      "epoch": 0.08171663727219283,
      "grad_norm": 0.0003460674488451332,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 46.0,
      "step": 139
    },
    {
      "epoch": 0.0823045267489712,
      "grad_norm": 0.00029815846937708557,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 0.08289241622574955,
      "grad_norm": 0.00037956913001835346,
      "learning_rate": 2.196424713241637e-05,
      "loss": 46.0,
      "step": 141
    },
    {
      "epoch": 0.08348030570252793,
      "grad_norm": 0.0003765831352211535,
      "learning_rate": 2.128356686585282e-05,
      "loss": 46.0,
      "step": 142
    },
    {
      "epoch": 0.08406819517930629,
      "grad_norm": 0.00026469153817743063,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 143
    },
    {
      "epoch": 0.08465608465608465,
      "grad_norm": 0.00020272209076210856,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 46.0,
      "step": 144
    },
    {
      "epoch": 0.08524397413286303,
      "grad_norm": 0.00046419556019827724,
      "learning_rate": 1.928936436551661e-05,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 0.08583186360964139,
      "grad_norm": 0.0002875496866181493,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 46.0,
      "step": 146
    },
    {
      "epoch": 0.08641975308641975,
      "grad_norm": 0.00029781847842969,
      "learning_rate": 1.800157297483417e-05,
      "loss": 46.0,
      "step": 147
    },
    {
      "epoch": 0.08700764256319812,
      "grad_norm": 0.000376311712898314,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 46.0,
      "step": 148
    },
    {
      "epoch": 0.08759553203997648,
      "grad_norm": 0.0004443646757863462,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 46.0,
      "step": 149
    },
    {
      "epoch": 0.08818342151675485,
      "grad_norm": 0.0007552163442596793,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 0.08818342151675485,
      "eval_loss": 11.5,
      "eval_runtime": 14.7297,
      "eval_samples_per_second": 194.505,
      "eval_steps_per_second": 48.677,
      "step": 150
    },
    {
      "epoch": 0.08877131099353322,
      "grad_norm": 0.0003553929564077407,
      "learning_rate": 1.553232954407171e-05,
      "loss": 46.0,
      "step": 151
    },
    {
      "epoch": 0.08935920047031158,
      "grad_norm": 0.00027716203476302326,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 46.0,
      "step": 152
    },
    {
      "epoch": 0.08994708994708994,
      "grad_norm": 0.00019364635227248073,
      "learning_rate": 1.435357758543015e-05,
      "loss": 46.0,
      "step": 153
    },
    {
      "epoch": 0.09053497942386832,
      "grad_norm": 0.0002733284782152623,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 46.0,
      "step": 154
    },
    {
      "epoch": 0.09112286890064668,
      "grad_norm": 0.00025294398074038327,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 46.0,
      "step": 155
    },
    {
      "epoch": 0.09171075837742504,
      "grad_norm": 0.0002934844815172255,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 46.0,
      "step": 156
    },
    {
      "epoch": 0.09229864785420341,
      "grad_norm": 0.0001922444353112951,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 46.0,
      "step": 157
    },
    {
      "epoch": 0.09288653733098177,
      "grad_norm": 0.0002667148073669523,
      "learning_rate": 1.157994445715706e-05,
      "loss": 46.0,
      "step": 158
    },
    {
      "epoch": 0.09347442680776014,
      "grad_norm": 0.000411880697356537,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 46.0,
      "step": 159
    },
    {
      "epoch": 0.09406231628453851,
      "grad_norm": 0.0003312369517516345,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 46.0,
      "step": 160
    },
    {
      "epoch": 0.09465020576131687,
      "grad_norm": 0.00036445181467570364,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 46.0,
      "step": 161
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.00036645587533712387,
      "learning_rate": 9.549150281252633e-06,
      "loss": 46.0,
      "step": 162
    },
    {
      "epoch": 0.09582598471487361,
      "grad_norm": 0.00028862638282589614,
      "learning_rate": 9.068759265665384e-06,
      "loss": 46.0,
      "step": 163
    },
    {
      "epoch": 0.09641387419165197,
      "grad_norm": 0.00028140039648860693,
      "learning_rate": 8.599558442598998e-06,
      "loss": 46.0,
      "step": 164
    },
    {
      "epoch": 0.09700176366843033,
      "grad_norm": 0.00041429486009292305,
      "learning_rate": 8.141676086873572e-06,
      "loss": 46.0,
      "step": 165
    },
    {
      "epoch": 0.0975896531452087,
      "grad_norm": 0.00025987005210481584,
      "learning_rate": 7.695237378953223e-06,
      "loss": 46.0,
      "step": 166
    },
    {
      "epoch": 0.09817754262198707,
      "grad_norm": 0.0003932338731829077,
      "learning_rate": 7.260364370723044e-06,
      "loss": 46.0,
      "step": 167
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 0.0002543106966186315,
      "learning_rate": 6.837175952121306e-06,
      "loss": 46.0,
      "step": 168
    },
    {
      "epoch": 0.0993533215755438,
      "grad_norm": 0.0004230441409163177,
      "learning_rate": 6.425787818636131e-06,
      "loss": 46.0,
      "step": 169
    },
    {
      "epoch": 0.09994121105232216,
      "grad_norm": 0.0003758452949114144,
      "learning_rate": 6.026312439675552e-06,
      "loss": 46.0,
      "step": 170
    },
    {
      "epoch": 0.10052910052910052,
      "grad_norm": 0.0003121093614026904,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 46.0,
      "step": 171
    },
    {
      "epoch": 0.1011169900058789,
      "grad_norm": 0.00045456658699549735,
      "learning_rate": 5.263533508961827e-06,
      "loss": 46.0,
      "step": 172
    },
    {
      "epoch": 0.10170487948265726,
      "grad_norm": 0.00031664478592574596,
      "learning_rate": 4.900438493352055e-06,
      "loss": 46.0,
      "step": 173
    },
    {
      "epoch": 0.10229276895943562,
      "grad_norm": 0.00028027768712490797,
      "learning_rate": 4.549673247541875e-06,
      "loss": 46.0,
      "step": 174
    },
    {
      "epoch": 0.102880658436214,
      "grad_norm": 0.0004479677591007203,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 46.0,
      "step": 175
    },
    {
      "epoch": 0.10346854791299236,
      "grad_norm": 0.0003130917903035879,
      "learning_rate": 3.885512251130763e-06,
      "loss": 46.0,
      "step": 176
    },
    {
      "epoch": 0.10405643738977072,
      "grad_norm": 0.000290354568278417,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 46.0,
      "step": 177
    },
    {
      "epoch": 0.10464432686654909,
      "grad_norm": 0.0004163481935393065,
      "learning_rate": 3.271776770026963e-06,
      "loss": 46.0,
      "step": 178
    },
    {
      "epoch": 0.10523221634332745,
      "grad_norm": 0.0003034559777006507,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 46.0,
      "step": 179
    },
    {
      "epoch": 0.10582010582010581,
      "grad_norm": 0.0003527678200043738,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 46.0,
      "step": 180
    },
    {
      "epoch": 0.10640799529688419,
      "grad_norm": 0.0003999746113549918,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 46.0,
      "step": 181
    },
    {
      "epoch": 0.10699588477366255,
      "grad_norm": 0.00046493555419147015,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 46.0,
      "step": 182
    },
    {
      "epoch": 0.10758377425044091,
      "grad_norm": 0.0003394379746168852,
      "learning_rate": 1.962316193157593e-06,
      "loss": 46.0,
      "step": 183
    },
    {
      "epoch": 0.10817166372721929,
      "grad_norm": 0.00029489657026715577,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 46.0,
      "step": 184
    },
    {
      "epoch": 0.10875955320399765,
      "grad_norm": 0.000345588952768594,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 46.0,
      "step": 185
    },
    {
      "epoch": 0.10934744268077601,
      "grad_norm": 0.00036880935658700764,
      "learning_rate": 1.333670137599713e-06,
      "loss": 46.0,
      "step": 186
    },
    {
      "epoch": 0.10993533215755438,
      "grad_norm": 0.00037571301800198853,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 46.0,
      "step": 187
    },
    {
      "epoch": 0.11052322163433274,
      "grad_norm": 0.0003209378046449274,
      "learning_rate": 9.810017062595322e-07,
      "loss": 46.0,
      "step": 188
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.0003390021447557956,
      "learning_rate": 8.247462563808817e-07,
      "loss": 46.0,
      "step": 189
    },
    {
      "epoch": 0.11169900058788948,
      "grad_norm": 0.0003676283813547343,
      "learning_rate": 6.819348298638839e-07,
      "loss": 46.0,
      "step": 190
    },
    {
      "epoch": 0.11228689006466784,
      "grad_norm": 0.00031735040829516947,
      "learning_rate": 5.526064699265753e-07,
      "loss": 46.0,
      "step": 191
    },
    {
      "epoch": 0.1128747795414462,
      "grad_norm": 0.00026506275753490627,
      "learning_rate": 4.367965336512403e-07,
      "loss": 46.0,
      "step": 192
    },
    {
      "epoch": 0.11346266901822458,
      "grad_norm": 0.0003598119365051389,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 46.0,
      "step": 193
    },
    {
      "epoch": 0.11405055849500294,
      "grad_norm": 0.0003071975370403379,
      "learning_rate": 2.458548727494292e-07,
      "loss": 46.0,
      "step": 194
    },
    {
      "epoch": 0.1146384479717813,
      "grad_norm": 0.0003063932526856661,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 46.0,
      "step": 195
    },
    {
      "epoch": 0.11522633744855967,
      "grad_norm": 0.00032924365950748324,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 46.0,
      "step": 196
    },
    {
      "epoch": 0.11581422692533803,
      "grad_norm": 0.0003192869480699301,
      "learning_rate": 6.150154258476315e-08,
      "loss": 46.0,
      "step": 197
    },
    {
      "epoch": 0.1164021164021164,
      "grad_norm": 0.00035585826844908297,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 46.0,
      "step": 198
    },
    {
      "epoch": 0.11699000587889477,
      "grad_norm": 0.00043484813068062067,
      "learning_rate": 6.834750376549792e-09,
      "loss": 46.0,
      "step": 199
    },
    {
      "epoch": 0.11757789535567313,
      "grad_norm": 0.0003695202758535743,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 200
    },
    {
      "epoch": 0.11757789535567313,
      "eval_loss": 11.5,
      "eval_runtime": 14.6882,
      "eval_samples_per_second": 195.055,
      "eval_steps_per_second": 48.815,
      "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": 36982232186880.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}