{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.06754474839581223,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033772374197906115,
      "grad_norm": 7.276058022398502e-05,
      "learning_rate": 5e-06,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.00033772374197906115,
      "eval_loss": 11.5,
      "eval_runtime": 38.7954,
      "eval_samples_per_second": 128.546,
      "eval_steps_per_second": 64.286,
      "step": 1
    },
    {
      "epoch": 0.0006754474839581223,
      "grad_norm": 5.878544470760971e-05,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0010131712259371835,
      "grad_norm": 0.00011510557669680566,
      "learning_rate": 1.5e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0013508949679162446,
      "grad_norm": 6.69136134092696e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.0016886187098953055,
      "grad_norm": 0.00010406153160147369,
      "learning_rate": 2.5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.002026342451874367,
      "grad_norm": 6.516464782180265e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.002364066193853428,
      "grad_norm": 0.00010503286466700956,
      "learning_rate": 3.5e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.002701789935832489,
      "grad_norm": 7.130981248337775e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.00303951367781155,
      "grad_norm": 0.00010857794404728338,
      "learning_rate": 4.5e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.003377237419790611,
      "grad_norm": 0.00010245521843899041,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.0037149611617696724,
      "grad_norm": 0.00011269093374721706,
      "learning_rate": 5.500000000000001e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.004052684903748734,
      "grad_norm": 0.00011142228322569281,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.004390408645727794,
      "grad_norm": 6.251192826312035e-05,
      "learning_rate": 6.500000000000001e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.004728132387706856,
      "grad_norm": 9.3655580712948e-05,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.005065856129685917,
      "grad_norm": 8.266478107543662e-05,
      "learning_rate": 7.500000000000001e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.005403579871664978,
      "grad_norm": 7.694377563893795e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.005741303613644039,
      "grad_norm": 0.00011045889550587162,
      "learning_rate": 8.5e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.0060790273556231,
      "grad_norm": 0.00016906291421037167,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.006416751097602162,
      "grad_norm": 9.80840195552446e-05,
      "learning_rate": 9.5e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.006754474839581222,
      "grad_norm": 0.00013097445480525494,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.0070921985815602835,
      "grad_norm": 0.0001700790598988533,
      "learning_rate": 9.999238475781957e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.007429922323539345,
      "grad_norm": 0.00012753397459164262,
      "learning_rate": 9.99695413509548e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.007767646065518406,
      "grad_norm": 0.00016159014194272459,
      "learning_rate": 9.99314767377287e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.008105369807497468,
      "grad_norm": 9.794745710678399e-05,
      "learning_rate": 9.987820251299122e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.008443093549476529,
      "grad_norm": 0.00014915158681105822,
      "learning_rate": 9.980973490458728e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.008780817291455589,
      "grad_norm": 0.00016512740694452077,
      "learning_rate": 9.972609476841367e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.00911854103343465,
      "grad_norm": 0.00016615127969998866,
      "learning_rate": 9.962730758206611e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.009456264775413711,
      "grad_norm": 0.00017522611597087234,
      "learning_rate": 9.951340343707852e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.009793988517392773,
      "grad_norm": 0.0001540362718515098,
      "learning_rate": 9.938441702975689e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.010131712259371834,
      "grad_norm": 0.00018813640053849667,
      "learning_rate": 9.924038765061042e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.010469436001350895,
      "grad_norm": 0.00017366709653288126,
      "learning_rate": 9.908135917238321e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.010807159743329957,
      "grad_norm": 0.0001967956923181191,
      "learning_rate": 9.890738003669029e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.011144883485309016,
      "grad_norm": 0.0001788329827832058,
      "learning_rate": 9.871850323926177e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.011482607227288078,
      "grad_norm": 0.0002920420956797898,
      "learning_rate": 9.851478631379982e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.01182033096926714,
      "grad_norm": 0.00025501628988422453,
      "learning_rate": 9.829629131445342e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.0121580547112462,
      "grad_norm": 0.00014368667325470597,
      "learning_rate": 9.806308479691595e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.012495778453225262,
      "grad_norm": 0.0003164131776429713,
      "learning_rate": 9.781523779815179e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.012833502195204323,
      "grad_norm": 0.000313744880259037,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.013171225937183385,
      "grad_norm": 0.00023910182062536478,
      "learning_rate": 9.727592877996585e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.013508949679162444,
      "grad_norm": 0.00023131851048674434,
      "learning_rate": 9.698463103929542e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.013846673421141506,
      "grad_norm": 0.00016217566735576838,
      "learning_rate": 9.667902132486009e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.014184397163120567,
      "grad_norm": 0.00025294432998634875,
      "learning_rate": 9.635919272833938e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.014522120905099628,
      "grad_norm": 0.0002531310892663896,
      "learning_rate": 9.602524267262203e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.01485984464707869,
      "grad_norm": 0.0001489182614022866,
      "learning_rate": 9.567727288213005e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.015197568389057751,
      "grad_norm": 0.00027500581927597523,
      "learning_rate": 9.53153893518325e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.015535292131036813,
      "grad_norm": 0.0002986603358294815,
      "learning_rate": 9.493970231495835e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.015873015873015872,
      "grad_norm": 0.0002843495167326182,
      "learning_rate": 9.45503262094184e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.016210739614994935,
      "grad_norm": 0.000245216564508155,
      "learning_rate": 9.414737964294636e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.016548463356973995,
      "grad_norm": 0.00024621959892101586,
      "learning_rate": 9.373098535696979e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.016886187098953058,
      "grad_norm": 0.0002581612498033792,
      "learning_rate": 9.330127018922194e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.016886187098953058,
      "eval_loss": 11.5,
      "eval_runtime": 38.9607,
      "eval_samples_per_second": 128.001,
      "eval_steps_per_second": 64.013,
      "step": 50
    },
    {
      "epoch": 0.017223910840932118,
      "grad_norm": 0.00047429301775991917,
      "learning_rate": 9.285836503510562e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.017561634582911177,
      "grad_norm": 0.0003680964873638004,
      "learning_rate": 9.24024048078213e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.01789935832489024,
      "grad_norm": 0.00042859482346102595,
      "learning_rate": 9.193352839727121e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.0182370820668693,
      "grad_norm": 0.0005228443769738078,
      "learning_rate": 9.145187862775209e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.018574805808848363,
      "grad_norm": 0.0005156008992344141,
      "learning_rate": 9.09576022144496e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.018912529550827423,
      "grad_norm": 0.0004643836582545191,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.019250253292806486,
      "grad_norm": 0.00040502825868315995,
      "learning_rate": 8.993177550236464e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.019587977034785545,
      "grad_norm": 0.0003081858449149877,
      "learning_rate": 8.940053768033609e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.019925700776764605,
      "grad_norm": 0.0004707358602900058,
      "learning_rate": 8.885729807284856e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.020263424518743668,
      "grad_norm": 0.0003463548782747239,
      "learning_rate": 8.83022221559489e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.020601148260722728,
      "grad_norm": 0.0004775702836923301,
      "learning_rate": 8.773547901113862e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.02093887200270179,
      "grad_norm": 0.0005734919104725122,
      "learning_rate": 8.715724127386972e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.02127659574468085,
      "grad_norm": 0.0006428358610719442,
      "learning_rate": 8.656768508095853e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.021614319486659914,
      "grad_norm": 0.0004899567575193942,
      "learning_rate": 8.596699001693255e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.021952043228638973,
      "grad_norm": 0.0005405608098953962,
      "learning_rate": 8.535533905932738e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.022289766970618033,
      "grad_norm": 0.0005998545093461871,
      "learning_rate": 8.473291852294987e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.022627490712597096,
      "grad_norm": 0.0006299249944277108,
      "learning_rate": 8.409991800312493e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.022965214454576156,
      "grad_norm": 0.0007823415799066424,
      "learning_rate": 8.345653031794292e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.02330293819655522,
      "grad_norm": 0.000636039359960705,
      "learning_rate": 8.280295144952536e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.02364066193853428,
      "grad_norm": 0.0006123732891865075,
      "learning_rate": 8.213938048432697e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.02397838568051334,
      "grad_norm": 0.0005400606314651668,
      "learning_rate": 8.146601955249188e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.0243161094224924,
      "grad_norm": 0.00047191730118356645,
      "learning_rate": 8.07830737662829e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.02465383316447146,
      "grad_norm": 0.0008023158297874033,
      "learning_rate": 8.009075115760243e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.024991556906450524,
      "grad_norm": 0.000606395595241338,
      "learning_rate": 7.938926261462366e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.025329280648429583,
      "grad_norm": 0.0006581166526302695,
      "learning_rate": 7.86788218175523e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.025667004390408647,
      "grad_norm": 0.0007552551105618477,
      "learning_rate": 7.795964517353735e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.026004728132387706,
      "grad_norm": 0.0007474394515156746,
      "learning_rate": 7.723195175075136e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.02634245187436677,
      "grad_norm": 0.0008201567106880248,
      "learning_rate": 7.649596321166024e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.02668017561634583,
      "grad_norm": 0.0009931371314451098,
      "learning_rate": 7.575190374550272e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.02701789935832489,
      "grad_norm": 0.0007147361757233739,
      "learning_rate": 7.500000000000001e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.02735562310030395,
      "grad_norm": 0.0008740099146962166,
      "learning_rate": 7.424048101231686e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.02769334684228301,
      "grad_norm": 0.0007939210627228022,
      "learning_rate": 7.347357813929454e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.028031070584262074,
      "grad_norm": 0.0006221792427822948,
      "learning_rate": 7.269952498697734e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.028368794326241134,
      "grad_norm": 0.000473547144792974,
      "learning_rate": 7.191855733945387e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.028706518068220197,
      "grad_norm": 0.0009338806266896427,
      "learning_rate": 7.113091308703498e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.029044241810199257,
      "grad_norm": 0.0006633476004935801,
      "learning_rate": 7.033683215379002e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.029381965552178316,
      "grad_norm": 0.0008773687877692282,
      "learning_rate": 6.953655642446368e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.02971968929415738,
      "grad_norm": 0.0007043882505968213,
      "learning_rate": 6.873032967079561e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.03005741303613644,
      "grad_norm": 0.0006674512987956405,
      "learning_rate": 6.7918397477265e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.030395136778115502,
      "grad_norm": 0.0008054351783357561,
      "learning_rate": 6.710100716628344e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.030732860520094562,
      "grad_norm": 0.0006025047623552382,
      "learning_rate": 6.627840772285784e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.031070584262073625,
      "grad_norm": 0.0008276731823571026,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.031408308004052685,
      "grad_norm": 0.0006977426237426698,
      "learning_rate": 6.461858523613684e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 0.0006919573643244803,
      "learning_rate": 6.378186779084995e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.032083755488010804,
      "grad_norm": 0.0006171864224597812,
      "learning_rate": 6.294095225512603e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.03242147922998987,
      "grad_norm": 0.0007080757059156895,
      "learning_rate": 6.209609477998338e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.03275920297196893,
      "grad_norm": 0.0006760466494597495,
      "learning_rate": 6.124755271719325e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.03309692671394799,
      "grad_norm": 0.0007032342837192118,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.03343465045592705,
      "grad_norm": 0.000764506752602756,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.033772374197906116,
      "grad_norm": 0.0009467988857068121,
      "learning_rate": 5.868240888334653e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.033772374197906116,
      "eval_loss": 11.5,
      "eval_runtime": 38.927,
      "eval_samples_per_second": 128.112,
      "eval_steps_per_second": 64.069,
      "step": 100
    },
    {
      "epoch": 0.034110097939885176,
      "grad_norm": 0.0007768378127366304,
      "learning_rate": 5.782172325201155e-05,
      "loss": 46.0,
      "step": 101
    },
    {
      "epoch": 0.034447821681864235,
      "grad_norm": 0.0011070900363847613,
      "learning_rate": 5.695865504800327e-05,
      "loss": 46.0,
      "step": 102
    },
    {
      "epoch": 0.034785545423843295,
      "grad_norm": 0.0008327396353706717,
      "learning_rate": 5.6093467170257374e-05,
      "loss": 46.0,
      "step": 103
    },
    {
      "epoch": 0.035123269165822354,
      "grad_norm": 0.0008931112824939191,
      "learning_rate": 5.522642316338268e-05,
      "loss": 46.0,
      "step": 104
    },
    {
      "epoch": 0.03546099290780142,
      "grad_norm": 0.0010443937499076128,
      "learning_rate": 5.435778713738292e-05,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 0.03579871664978048,
      "grad_norm": 0.0008864287519827485,
      "learning_rate": 5.348782368720626e-05,
      "loss": 46.0,
      "step": 106
    },
    {
      "epoch": 0.03613644039175954,
      "grad_norm": 0.0011207317002117634,
      "learning_rate": 5.26167978121472e-05,
      "loss": 46.0,
      "step": 107
    },
    {
      "epoch": 0.0364741641337386,
      "grad_norm": 0.0009042939636856318,
      "learning_rate": 5.174497483512506e-05,
      "loss": 46.0,
      "step": 108
    },
    {
      "epoch": 0.03681188787571766,
      "grad_norm": 0.001021576696075499,
      "learning_rate": 5.0872620321864185e-05,
      "loss": 46.0,
      "step": 109
    },
    {
      "epoch": 0.037149611617696726,
      "grad_norm": 0.0007057876791805029,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 0.037487335359675786,
      "grad_norm": 0.0011544162407517433,
      "learning_rate": 4.912737967813583e-05,
      "loss": 46.0,
      "step": 111
    },
    {
      "epoch": 0.037825059101654845,
      "grad_norm": 0.000699100608471781,
      "learning_rate": 4.825502516487497e-05,
      "loss": 46.0,
      "step": 112
    },
    {
      "epoch": 0.038162782843633905,
      "grad_norm": 0.0008428012952208519,
      "learning_rate": 4.738320218785281e-05,
      "loss": 46.0,
      "step": 113
    },
    {
      "epoch": 0.03850050658561297,
      "grad_norm": 0.0013961500953882933,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 46.0,
      "step": 114
    },
    {
      "epoch": 0.03883823032759203,
      "grad_norm": 0.001263579586520791,
      "learning_rate": 4.564221286261709e-05,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 0.03917595406957109,
      "grad_norm": 0.0009908132487908006,
      "learning_rate": 4.477357683661734e-05,
      "loss": 46.0,
      "step": 116
    },
    {
      "epoch": 0.03951367781155015,
      "grad_norm": 0.0009149489924311638,
      "learning_rate": 4.390653282974264e-05,
      "loss": 46.0,
      "step": 117
    },
    {
      "epoch": 0.03985140155352921,
      "grad_norm": 0.0012927039060741663,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 46.0,
      "step": 118
    },
    {
      "epoch": 0.04018912529550828,
      "grad_norm": 0.0017418642528355122,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 46.0,
      "step": 119
    },
    {
      "epoch": 0.040526849037487336,
      "grad_norm": 0.0006859771092422307,
      "learning_rate": 4.131759111665349e-05,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 0.040864572779466396,
      "grad_norm": 0.0011371650034561753,
      "learning_rate": 4.045955023117276e-05,
      "loss": 46.0,
      "step": 121
    },
    {
      "epoch": 0.041202296521445456,
      "grad_norm": 0.0007151041645556688,
      "learning_rate": 3.960441545911204e-05,
      "loss": 46.0,
      "step": 122
    },
    {
      "epoch": 0.04154002026342452,
      "grad_norm": 0.001328582176938653,
      "learning_rate": 3.875244728280676e-05,
      "loss": 46.0,
      "step": 123
    },
    {
      "epoch": 0.04187774400540358,
      "grad_norm": 0.0012535835849121213,
      "learning_rate": 3.790390522001662e-05,
      "loss": 46.0,
      "step": 124
    },
    {
      "epoch": 0.04221546774738264,
      "grad_norm": 0.0010161892278119922,
      "learning_rate": 3.705904774487396e-05,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 0.0425531914893617,
      "grad_norm": 0.000856311060488224,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 46.0,
      "step": 126
    },
    {
      "epoch": 0.04289091523134076,
      "grad_norm": 0.0013442924246191978,
      "learning_rate": 3.5381414763863166e-05,
      "loss": 46.0,
      "step": 127
    },
    {
      "epoch": 0.04322863897331983,
      "grad_norm": 0.0012326273135840893,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 46.0,
      "step": 128
    },
    {
      "epoch": 0.04356636271529889,
      "grad_norm": 0.0009677083580754697,
      "learning_rate": 3.372159227714218e-05,
      "loss": 46.0,
      "step": 129
    },
    {
      "epoch": 0.04390408645727795,
      "grad_norm": 0.0011392139131203294,
      "learning_rate": 3.289899283371657e-05,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 0.044241810199257006,
      "grad_norm": 0.0012129353126510978,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 46.0,
      "step": 131
    },
    {
      "epoch": 0.044579533941236066,
      "grad_norm": 0.0009816366946324706,
      "learning_rate": 3.12696703292044e-05,
      "loss": 46.0,
      "step": 132
    },
    {
      "epoch": 0.04491725768321513,
      "grad_norm": 0.0010957185877487063,
      "learning_rate": 3.046344357553632e-05,
      "loss": 46.0,
      "step": 133
    },
    {
      "epoch": 0.04525498142519419,
      "grad_norm": 0.0010009566321969032,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 46.0,
      "step": 134
    },
    {
      "epoch": 0.04559270516717325,
      "grad_norm": 0.0010443383362144232,
      "learning_rate": 2.886908691296504e-05,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 0.04593042890915231,
      "grad_norm": 0.0010585614945739508,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 46.0,
      "step": 136
    },
    {
      "epoch": 0.04626815265113138,
      "grad_norm": 0.0008764097583480179,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 46.0,
      "step": 137
    },
    {
      "epoch": 0.04660587639311044,
      "grad_norm": 0.0013279024278745055,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 46.0,
      "step": 138
    },
    {
      "epoch": 0.0469436001350895,
      "grad_norm": 0.0010183140402659774,
      "learning_rate": 2.575951898768315e-05,
      "loss": 46.0,
      "step": 139
    },
    {
      "epoch": 0.04728132387706856,
      "grad_norm": 0.0008116578683257103,
      "learning_rate": 2.500000000000001e-05,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 0.001265092520043254,
      "learning_rate": 2.4248096254497288e-05,
      "loss": 46.0,
      "step": 141
    },
    {
      "epoch": 0.04795677136102668,
      "grad_norm": 0.0011083990102633834,
      "learning_rate": 2.350403678833976e-05,
      "loss": 46.0,
      "step": 142
    },
    {
      "epoch": 0.04829449510300574,
      "grad_norm": 0.0008676938596181571,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 46.0,
      "step": 143
    },
    {
      "epoch": 0.0486322188449848,
      "grad_norm": 0.000770486134570092,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 46.0,
      "step": 144
    },
    {
      "epoch": 0.04896994258696386,
      "grad_norm": 0.0009965162025764585,
      "learning_rate": 2.132117818244771e-05,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 0.04930766632894292,
      "grad_norm": 0.0011302151251584291,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 146
    },
    {
      "epoch": 0.04964539007092199,
      "grad_norm": 0.0011233602417632937,
      "learning_rate": 1.9909248842397584e-05,
      "loss": 46.0,
      "step": 147
    },
    {
      "epoch": 0.04998311381290105,
      "grad_norm": 0.0008180382428690791,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 46.0,
      "step": 148
    },
    {
      "epoch": 0.05032083755488011,
      "grad_norm": 0.0007508528069593012,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 46.0,
      "step": 149
    },
    {
      "epoch": 0.05065856129685917,
      "grad_norm": 0.0010786211350932717,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 0.05065856129685917,
      "eval_loss": 11.5,
      "eval_runtime": 38.8856,
      "eval_samples_per_second": 128.248,
      "eval_steps_per_second": 64.137,
      "step": 150
    },
    {
      "epoch": 0.050996285038838234,
      "grad_norm": 0.0010216847294941545,
      "learning_rate": 1.7197048550474643e-05,
      "loss": 46.0,
      "step": 151
    },
    {
      "epoch": 0.05133400878081729,
      "grad_norm": 0.0012289107544347644,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 46.0,
      "step": 152
    },
    {
      "epoch": 0.05167173252279635,
      "grad_norm": 0.0008682836778461933,
      "learning_rate": 1.5900081996875083e-05,
      "loss": 46.0,
      "step": 153
    },
    {
      "epoch": 0.05200945626477541,
      "grad_norm": 0.0011643536854535341,
      "learning_rate": 1.526708147705013e-05,
      "loss": 46.0,
      "step": 154
    },
    {
      "epoch": 0.05234718000675447,
      "grad_norm": 0.0012115777935832739,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 46.0,
      "step": 155
    },
    {
      "epoch": 0.05268490374873354,
      "grad_norm": 0.0007694285595789552,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 46.0,
      "step": 156
    },
    {
      "epoch": 0.0530226274907126,
      "grad_norm": 0.0010046809911727905,
      "learning_rate": 1.3432314919041478e-05,
      "loss": 46.0,
      "step": 157
    },
    {
      "epoch": 0.05336035123269166,
      "grad_norm": 0.0010704821906983852,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 46.0,
      "step": 158
    },
    {
      "epoch": 0.05369807497467072,
      "grad_norm": 0.0011834176257252693,
      "learning_rate": 1.22645209888614e-05,
      "loss": 46.0,
      "step": 159
    },
    {
      "epoch": 0.05403579871664978,
      "grad_norm": 0.0011986505705863237,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 46.0,
      "step": 160
    },
    {
      "epoch": 0.054373522458628844,
      "grad_norm": 0.0012326020514592528,
      "learning_rate": 1.1142701927151456e-05,
      "loss": 46.0,
      "step": 161
    },
    {
      "epoch": 0.0547112462006079,
      "grad_norm": 0.0012002837611362338,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 46.0,
      "step": 162
    },
    {
      "epoch": 0.05504896994258696,
      "grad_norm": 0.000992245739325881,
      "learning_rate": 1.006822449763537e-05,
      "loss": 46.0,
      "step": 163
    },
    {
      "epoch": 0.05538669368456602,
      "grad_norm": 0.0011888997396454215,
      "learning_rate": 9.549150281252633e-06,
      "loss": 46.0,
      "step": 164
    },
    {
      "epoch": 0.05572441742654509,
      "grad_norm": 0.0010090389987453818,
      "learning_rate": 9.042397785550405e-06,
      "loss": 46.0,
      "step": 165
    },
    {
      "epoch": 0.05606214116852415,
      "grad_norm": 0.0015678474446758628,
      "learning_rate": 8.548121372247918e-06,
      "loss": 46.0,
      "step": 166
    },
    {
      "epoch": 0.05639986491050321,
      "grad_norm": 0.001133469631895423,
      "learning_rate": 8.066471602728803e-06,
      "loss": 46.0,
      "step": 167
    },
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 0.0012654394377022982,
      "learning_rate": 7.597595192178702e-06,
      "loss": 46.0,
      "step": 168
    },
    {
      "epoch": 0.05707531239446133,
      "grad_norm": 0.001259388169273734,
      "learning_rate": 7.1416349648943894e-06,
      "loss": 46.0,
      "step": 169
    },
    {
      "epoch": 0.057413036136440394,
      "grad_norm": 0.0010654539801180363,
      "learning_rate": 6.698729810778065e-06,
      "loss": 46.0,
      "step": 170
    },
    {
      "epoch": 0.057750759878419454,
      "grad_norm": 0.0011588961351662874,
      "learning_rate": 6.269014643030213e-06,
      "loss": 46.0,
      "step": 171
    },
    {
      "epoch": 0.058088483620398514,
      "grad_norm": 0.0008982659783214331,
      "learning_rate": 5.852620357053651e-06,
      "loss": 46.0,
      "step": 172
    },
    {
      "epoch": 0.05842620736237757,
      "grad_norm": 0.0010412945412099361,
      "learning_rate": 5.449673790581611e-06,
      "loss": 46.0,
      "step": 173
    },
    {
      "epoch": 0.05876393110435663,
      "grad_norm": 0.0010980138322338462,
      "learning_rate": 5.060297685041659e-06,
      "loss": 46.0,
      "step": 174
    },
    {
      "epoch": 0.0591016548463357,
      "grad_norm": 0.0011544724693521857,
      "learning_rate": 4.684610648167503e-06,
      "loss": 46.0,
      "step": 175
    },
    {
      "epoch": 0.05943937858831476,
      "grad_norm": 0.0010008839890360832,
      "learning_rate": 4.322727117869951e-06,
      "loss": 46.0,
      "step": 176
    },
    {
      "epoch": 0.05977710233029382,
      "grad_norm": 0.0009903137106448412,
      "learning_rate": 3.974757327377981e-06,
      "loss": 46.0,
      "step": 177
    },
    {
      "epoch": 0.06011482607227288,
      "grad_norm": 0.00108939444180578,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 46.0,
      "step": 178
    },
    {
      "epoch": 0.060452549814251945,
      "grad_norm": 0.0009730703313834965,
      "learning_rate": 3.3209786751399187e-06,
      "loss": 46.0,
      "step": 179
    },
    {
      "epoch": 0.060790273556231005,
      "grad_norm": 0.0014580844435840845,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 46.0,
      "step": 180
    },
    {
      "epoch": 0.061127997298210064,
      "grad_norm": 0.0012510529486462474,
      "learning_rate": 2.724071220034158e-06,
      "loss": 46.0,
      "step": 181
    },
    {
      "epoch": 0.061465721040189124,
      "grad_norm": 0.0013135881163179874,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 46.0,
      "step": 182
    },
    {
      "epoch": 0.06180344478216818,
      "grad_norm": 0.0009398313704878092,
      "learning_rate": 2.1847622018482283e-06,
      "loss": 46.0,
      "step": 183
    },
    {
      "epoch": 0.06214116852414725,
      "grad_norm": 0.0014489085879176855,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 46.0,
      "step": 184
    },
    {
      "epoch": 0.06247889226612631,
      "grad_norm": 0.0009700249647721648,
      "learning_rate": 1.70370868554659e-06,
      "loss": 46.0,
      "step": 185
    },
    {
      "epoch": 0.06281661600810537,
      "grad_norm": 0.0010533477179706097,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 46.0,
      "step": 186
    },
    {
      "epoch": 0.06315433975008443,
      "grad_norm": 0.001313917338848114,
      "learning_rate": 1.2814967607382432e-06,
      "loss": 46.0,
      "step": 187
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 0.0012558267917484045,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 46.0,
      "step": 188
    },
    {
      "epoch": 0.06382978723404255,
      "grad_norm": 0.0010105348192155361,
      "learning_rate": 9.186408276168013e-07,
      "loss": 46.0,
      "step": 189
    },
    {
      "epoch": 0.06416751097602161,
      "grad_norm": 0.0014234244590625167,
      "learning_rate": 7.596123493895991e-07,
      "loss": 46.0,
      "step": 190
    },
    {
      "epoch": 0.06450523471800068,
      "grad_norm": 0.0008752213325351477,
      "learning_rate": 6.15582970243117e-07,
      "loss": 46.0,
      "step": 191
    },
    {
      "epoch": 0.06484295845997974,
      "grad_norm": 0.0007266063475981355,
      "learning_rate": 4.865965629214819e-07,
      "loss": 46.0,
      "step": 192
    },
    {
      "epoch": 0.0651806822019588,
      "grad_norm": 0.001014669775031507,
      "learning_rate": 3.7269241793390085e-07,
      "loss": 46.0,
      "step": 193
    },
    {
      "epoch": 0.06551840594393786,
      "grad_norm": 0.0008748005493544042,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 46.0,
      "step": 194
    },
    {
      "epoch": 0.06585612968591692,
      "grad_norm": 0.0008451690664514899,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 46.0,
      "step": 195
    },
    {
      "epoch": 0.06619385342789598,
      "grad_norm": 0.0010732212103903294,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 46.0,
      "step": 196
    },
    {
      "epoch": 0.06653157716987504,
      "grad_norm": 0.000886994821485132,
      "learning_rate": 6.852326227130834e-08,
      "loss": 46.0,
      "step": 197
    },
    {
      "epoch": 0.0668693009118541,
      "grad_norm": 0.0010644092690199614,
      "learning_rate": 3.04586490452119e-08,
      "loss": 46.0,
      "step": 198
    },
    {
      "epoch": 0.06720702465383316,
      "grad_norm": 0.0013122831005603075,
      "learning_rate": 7.615242180436522e-09,
      "loss": 46.0,
      "step": 199
    },
    {
      "epoch": 0.06754474839581223,
      "grad_norm": 0.001323534408584237,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 200
    },
    {
      "epoch": 0.06754474839581223,
      "eval_loss": 11.5,
      "eval_runtime": 38.9507,
      "eval_samples_per_second": 128.034,
      "eval_steps_per_second": 64.03,
      "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": 46026799841280.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}