{
  "best_metric": 1.9088218212127686,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.06705783738474434,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033528918692372173,
      "grad_norm": 2.992781162261963,
      "learning_rate": 5e-06,
      "loss": 2.5227,
      "step": 1
    },
    {
      "epoch": 0.00033528918692372173,
      "eval_loss": 4.411320209503174,
      "eval_runtime": 411.5379,
      "eval_samples_per_second": 12.205,
      "eval_steps_per_second": 6.104,
      "step": 1
    },
    {
      "epoch": 0.0006705783738474435,
      "grad_norm": 4.529913425445557,
      "learning_rate": 1e-05,
      "loss": 3.4584,
      "step": 2
    },
    {
      "epoch": 0.001005867560771165,
      "grad_norm": 4.515174388885498,
      "learning_rate": 1.5e-05,
      "loss": 3.235,
      "step": 3
    },
    {
      "epoch": 0.001341156747694887,
      "grad_norm": 5.1074395179748535,
      "learning_rate": 2e-05,
      "loss": 3.4917,
      "step": 4
    },
    {
      "epoch": 0.0016764459346186086,
      "grad_norm": 4.09510612487793,
      "learning_rate": 2.5e-05,
      "loss": 3.4111,
      "step": 5
    },
    {
      "epoch": 0.00201173512154233,
      "grad_norm": 4.380725860595703,
      "learning_rate": 3e-05,
      "loss": 3.9991,
      "step": 6
    },
    {
      "epoch": 0.002347024308466052,
      "grad_norm": 3.3854966163635254,
      "learning_rate": 3.5e-05,
      "loss": 2.8742,
      "step": 7
    },
    {
      "epoch": 0.002682313495389774,
      "grad_norm": 4.039089679718018,
      "learning_rate": 4e-05,
      "loss": 3.134,
      "step": 8
    },
    {
      "epoch": 0.0030176026823134955,
      "grad_norm": 4.565903663635254,
      "learning_rate": 4.5e-05,
      "loss": 2.6035,
      "step": 9
    },
    {
      "epoch": 0.003352891869237217,
      "grad_norm": 4.399992942810059,
      "learning_rate": 5e-05,
      "loss": 3.0781,
      "step": 10
    },
    {
      "epoch": 0.0036881810561609388,
      "grad_norm": 4.8409342765808105,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.3776,
      "step": 11
    },
    {
      "epoch": 0.00402347024308466,
      "grad_norm": 4.536879539489746,
      "learning_rate": 6e-05,
      "loss": 2.3365,
      "step": 12
    },
    {
      "epoch": 0.0043587594300083824,
      "grad_norm": 3.146723747253418,
      "learning_rate": 6.500000000000001e-05,
      "loss": 2.3901,
      "step": 13
    },
    {
      "epoch": 0.004694048616932104,
      "grad_norm": 3.6063036918640137,
      "learning_rate": 7e-05,
      "loss": 2.3625,
      "step": 14
    },
    {
      "epoch": 0.005029337803855826,
      "grad_norm": 3.854727029800415,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.063,
      "step": 15
    },
    {
      "epoch": 0.005364626990779548,
      "grad_norm": 3.5359508991241455,
      "learning_rate": 8e-05,
      "loss": 2.5032,
      "step": 16
    },
    {
      "epoch": 0.005699916177703269,
      "grad_norm": 3.1869733333587646,
      "learning_rate": 8.5e-05,
      "loss": 2.0691,
      "step": 17
    },
    {
      "epoch": 0.006035205364626991,
      "grad_norm": 6.3843865394592285,
      "learning_rate": 9e-05,
      "loss": 2.6971,
      "step": 18
    },
    {
      "epoch": 0.006370494551550712,
      "grad_norm": 2.90205717086792,
      "learning_rate": 9.5e-05,
      "loss": 2.2934,
      "step": 19
    },
    {
      "epoch": 0.006705783738474434,
      "grad_norm": 3.3418538570404053,
      "learning_rate": 0.0001,
      "loss": 2.4169,
      "step": 20
    },
    {
      "epoch": 0.007041072925398156,
      "grad_norm": 3.6200921535491943,
      "learning_rate": 9.999238475781957e-05,
      "loss": 2.492,
      "step": 21
    },
    {
      "epoch": 0.0073763621123218775,
      "grad_norm": 2.6384730339050293,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.1403,
      "step": 22
    },
    {
      "epoch": 0.0077116512992456,
      "grad_norm": 3.0785937309265137,
      "learning_rate": 9.99314767377287e-05,
      "loss": 2.3843,
      "step": 23
    },
    {
      "epoch": 0.00804694048616932,
      "grad_norm": 2.3972208499908447,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.143,
      "step": 24
    },
    {
      "epoch": 0.008382229673093043,
      "grad_norm": 2.129817008972168,
      "learning_rate": 9.980973490458728e-05,
      "loss": 2.145,
      "step": 25
    },
    {
      "epoch": 0.008717518860016765,
      "grad_norm": 2.270543098449707,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.8986,
      "step": 26
    },
    {
      "epoch": 0.009052808046940487,
      "grad_norm": 2.55796217918396,
      "learning_rate": 9.962730758206611e-05,
      "loss": 2.1303,
      "step": 27
    },
    {
      "epoch": 0.009388097233864207,
      "grad_norm": 2.4456629753112793,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.1822,
      "step": 28
    },
    {
      "epoch": 0.00972338642078793,
      "grad_norm": 2.206874370574951,
      "learning_rate": 9.938441702975689e-05,
      "loss": 2.1543,
      "step": 29
    },
    {
      "epoch": 0.010058675607711651,
      "grad_norm": 2.635354995727539,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.0015,
      "step": 30
    },
    {
      "epoch": 0.010393964794635373,
      "grad_norm": 2.412721633911133,
      "learning_rate": 9.908135917238321e-05,
      "loss": 2.1105,
      "step": 31
    },
    {
      "epoch": 0.010729253981559096,
      "grad_norm": 1.984572410583496,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.094,
      "step": 32
    },
    {
      "epoch": 0.011064543168482816,
      "grad_norm": 2.202427625656128,
      "learning_rate": 9.871850323926177e-05,
      "loss": 2.2894,
      "step": 33
    },
    {
      "epoch": 0.011399832355406538,
      "grad_norm": 2.442368268966675,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.3403,
      "step": 34
    },
    {
      "epoch": 0.01173512154233026,
      "grad_norm": 2.77518367767334,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.1758,
      "step": 35
    },
    {
      "epoch": 0.012070410729253982,
      "grad_norm": 2.1861000061035156,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.4213,
      "step": 36
    },
    {
      "epoch": 0.012405699916177704,
      "grad_norm": 2.721886396408081,
      "learning_rate": 9.781523779815179e-05,
      "loss": 2.2233,
      "step": 37
    },
    {
      "epoch": 0.012740989103101424,
      "grad_norm": 3.1004526615142822,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.2733,
      "step": 38
    },
    {
      "epoch": 0.013076278290025146,
      "grad_norm": 1.9410390853881836,
      "learning_rate": 9.727592877996585e-05,
      "loss": 1.9792,
      "step": 39
    },
    {
      "epoch": 0.013411567476948869,
      "grad_norm": 2.257230758666992,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.2076,
      "step": 40
    },
    {
      "epoch": 0.01374685666387259,
      "grad_norm": 2.6516623497009277,
      "learning_rate": 9.667902132486009e-05,
      "loss": 2.0877,
      "step": 41
    },
    {
      "epoch": 0.014082145850796313,
      "grad_norm": 2.028968572616577,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.9033,
      "step": 42
    },
    {
      "epoch": 0.014417435037720033,
      "grad_norm": 2.28653621673584,
      "learning_rate": 9.602524267262203e-05,
      "loss": 2.2851,
      "step": 43
    },
    {
      "epoch": 0.014752724224643755,
      "grad_norm": 2.5327606201171875,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.4973,
      "step": 44
    },
    {
      "epoch": 0.015088013411567477,
      "grad_norm": 2.3178114891052246,
      "learning_rate": 9.53153893518325e-05,
      "loss": 2.2532,
      "step": 45
    },
    {
      "epoch": 0.0154233025984912,
      "grad_norm": 2.0378174781799316,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.2505,
      "step": 46
    },
    {
      "epoch": 0.01575859178541492,
      "grad_norm": 1.800331950187683,
      "learning_rate": 9.45503262094184e-05,
      "loss": 2.0703,
      "step": 47
    },
    {
      "epoch": 0.01609388097233864,
      "grad_norm": 1.7843546867370605,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.994,
      "step": 48
    },
    {
      "epoch": 0.016429170159262364,
      "grad_norm": 3.0077595710754395,
      "learning_rate": 9.373098535696979e-05,
      "loss": 2.0799,
      "step": 49
    },
    {
      "epoch": 0.016764459346186086,
      "grad_norm": 2.0977861881256104,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.1696,
      "step": 50
    },
    {
      "epoch": 0.016764459346186086,
      "eval_loss": 2.063823699951172,
      "eval_runtime": 413.5035,
      "eval_samples_per_second": 12.147,
      "eval_steps_per_second": 6.075,
      "step": 50
    },
    {
      "epoch": 0.017099748533109808,
      "grad_norm": 2.62034010887146,
      "learning_rate": 9.285836503510562e-05,
      "loss": 1.3636,
      "step": 51
    },
    {
      "epoch": 0.01743503772003353,
      "grad_norm": 2.527620315551758,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.9578,
      "step": 52
    },
    {
      "epoch": 0.017770326906957252,
      "grad_norm": 1.6442492008209229,
      "learning_rate": 9.193352839727121e-05,
      "loss": 1.6767,
      "step": 53
    },
    {
      "epoch": 0.018105616093880974,
      "grad_norm": 1.4458750486373901,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.686,
      "step": 54
    },
    {
      "epoch": 0.018440905280804692,
      "grad_norm": 1.7364954948425293,
      "learning_rate": 9.09576022144496e-05,
      "loss": 1.6665,
      "step": 55
    },
    {
      "epoch": 0.018776194467728415,
      "grad_norm": 1.7776877880096436,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.9963,
      "step": 56
    },
    {
      "epoch": 0.019111483654652137,
      "grad_norm": 2.0100560188293457,
      "learning_rate": 8.993177550236464e-05,
      "loss": 1.9905,
      "step": 57
    },
    {
      "epoch": 0.01944677284157586,
      "grad_norm": 1.632913589477539,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.6513,
      "step": 58
    },
    {
      "epoch": 0.01978206202849958,
      "grad_norm": 1.4831138849258423,
      "learning_rate": 8.885729807284856e-05,
      "loss": 1.6766,
      "step": 59
    },
    {
      "epoch": 0.020117351215423303,
      "grad_norm": 1.9989702701568604,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.1606,
      "step": 60
    },
    {
      "epoch": 0.020452640402347025,
      "grad_norm": 1.4675123691558838,
      "learning_rate": 8.773547901113862e-05,
      "loss": 1.6553,
      "step": 61
    },
    {
      "epoch": 0.020787929589270747,
      "grad_norm": 1.6913825273513794,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.7686,
      "step": 62
    },
    {
      "epoch": 0.02112321877619447,
      "grad_norm": 1.5257123708724976,
      "learning_rate": 8.656768508095853e-05,
      "loss": 1.7896,
      "step": 63
    },
    {
      "epoch": 0.02145850796311819,
      "grad_norm": 1.544580340385437,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.5592,
      "step": 64
    },
    {
      "epoch": 0.02179379715004191,
      "grad_norm": 1.672667384147644,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.8603,
      "step": 65
    },
    {
      "epoch": 0.02212908633696563,
      "grad_norm": 2.002145767211914,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.0322,
      "step": 66
    },
    {
      "epoch": 0.022464375523889354,
      "grad_norm": 1.8057658672332764,
      "learning_rate": 8.409991800312493e-05,
      "loss": 1.9131,
      "step": 67
    },
    {
      "epoch": 0.022799664710813076,
      "grad_norm": 1.672799825668335,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.8299,
      "step": 68
    },
    {
      "epoch": 0.023134953897736798,
      "grad_norm": 1.944652795791626,
      "learning_rate": 8.280295144952536e-05,
      "loss": 1.9988,
      "step": 69
    },
    {
      "epoch": 0.02347024308466052,
      "grad_norm": 1.6608362197875977,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.5165,
      "step": 70
    },
    {
      "epoch": 0.023805532271584242,
      "grad_norm": 1.6543148756027222,
      "learning_rate": 8.146601955249188e-05,
      "loss": 1.9441,
      "step": 71
    },
    {
      "epoch": 0.024140821458507964,
      "grad_norm": 2.1947410106658936,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.0615,
      "step": 72
    },
    {
      "epoch": 0.024476110645431686,
      "grad_norm": 1.912451148033142,
      "learning_rate": 8.009075115760243e-05,
      "loss": 2.2494,
      "step": 73
    },
    {
      "epoch": 0.024811399832355408,
      "grad_norm": 1.6554523706436157,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.7974,
      "step": 74
    },
    {
      "epoch": 0.025146689019279127,
      "grad_norm": 1.7719614505767822,
      "learning_rate": 7.86788218175523e-05,
      "loss": 1.9316,
      "step": 75
    },
    {
      "epoch": 0.02548197820620285,
      "grad_norm": 1.7867423295974731,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.9377,
      "step": 76
    },
    {
      "epoch": 0.02581726739312657,
      "grad_norm": 1.5760337114334106,
      "learning_rate": 7.723195175075136e-05,
      "loss": 1.8641,
      "step": 77
    },
    {
      "epoch": 0.026152556580050293,
      "grad_norm": 1.8237406015396118,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.9964,
      "step": 78
    },
    {
      "epoch": 0.026487845766974015,
      "grad_norm": 1.855748176574707,
      "learning_rate": 7.575190374550272e-05,
      "loss": 2.0663,
      "step": 79
    },
    {
      "epoch": 0.026823134953897737,
      "grad_norm": 1.6799901723861694,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.2576,
      "step": 80
    },
    {
      "epoch": 0.02715842414082146,
      "grad_norm": 1.7999197244644165,
      "learning_rate": 7.424048101231686e-05,
      "loss": 2.0209,
      "step": 81
    },
    {
      "epoch": 0.02749371332774518,
      "grad_norm": 1.7967363595962524,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.174,
      "step": 82
    },
    {
      "epoch": 0.027829002514668903,
      "grad_norm": 1.8757990598678589,
      "learning_rate": 7.269952498697734e-05,
      "loss": 2.0941,
      "step": 83
    },
    {
      "epoch": 0.028164291701592625,
      "grad_norm": 1.780026912689209,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.2014,
      "step": 84
    },
    {
      "epoch": 0.028499580888516344,
      "grad_norm": 1.827178716659546,
      "learning_rate": 7.113091308703498e-05,
      "loss": 2.2593,
      "step": 85
    },
    {
      "epoch": 0.028834870075440066,
      "grad_norm": 2.0073418617248535,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.033,
      "step": 86
    },
    {
      "epoch": 0.029170159262363788,
      "grad_norm": 1.819101333618164,
      "learning_rate": 6.953655642446368e-05,
      "loss": 1.8496,
      "step": 87
    },
    {
      "epoch": 0.02950544844928751,
      "grad_norm": 2.141103744506836,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.0383,
      "step": 88
    },
    {
      "epoch": 0.029840737636211232,
      "grad_norm": 1.9048711061477661,
      "learning_rate": 6.7918397477265e-05,
      "loss": 2.1003,
      "step": 89
    },
    {
      "epoch": 0.030176026823134954,
      "grad_norm": 1.8321547508239746,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.9953,
      "step": 90
    },
    {
      "epoch": 0.030511316010058676,
      "grad_norm": 2.1996445655822754,
      "learning_rate": 6.627840772285784e-05,
      "loss": 2.1625,
      "step": 91
    },
    {
      "epoch": 0.0308466051969824,
      "grad_norm": 1.961883544921875,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1395,
      "step": 92
    },
    {
      "epoch": 0.03118189438390612,
      "grad_norm": 2.2218706607818604,
      "learning_rate": 6.461858523613684e-05,
      "loss": 2.3638,
      "step": 93
    },
    {
      "epoch": 0.03151718357082984,
      "grad_norm": 1.862480878829956,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.0408,
      "step": 94
    },
    {
      "epoch": 0.03185247275775356,
      "grad_norm": 1.9635447263717651,
      "learning_rate": 6.294095225512603e-05,
      "loss": 2.3324,
      "step": 95
    },
    {
      "epoch": 0.03218776194467728,
      "grad_norm": 1.7687016725540161,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.0399,
      "step": 96
    },
    {
      "epoch": 0.032523051131601005,
      "grad_norm": 1.6486884355545044,
      "learning_rate": 6.124755271719325e-05,
      "loss": 1.9136,
      "step": 97
    },
    {
      "epoch": 0.03285834031852473,
      "grad_norm": 1.6339043378829956,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.1181,
      "step": 98
    },
    {
      "epoch": 0.03319362950544845,
      "grad_norm": 1.6916457414627075,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 1.9995,
      "step": 99
    },
    {
      "epoch": 0.03352891869237217,
      "grad_norm": 2.411832809448242,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.2204,
      "step": 100
    },
    {
      "epoch": 0.03352891869237217,
      "eval_loss": 1.973891019821167,
      "eval_runtime": 413.6173,
      "eval_samples_per_second": 12.144,
      "eval_steps_per_second": 6.073,
      "step": 100
    },
    {
      "epoch": 0.03386420787929589,
      "grad_norm": 2.4231576919555664,
      "learning_rate": 5.782172325201155e-05,
      "loss": 1.6551,
      "step": 101
    },
    {
      "epoch": 0.034199497066219615,
      "grad_norm": 2.900712251663208,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.0897,
      "step": 102
    },
    {
      "epoch": 0.03453478625314334,
      "grad_norm": 1.7243603467941284,
      "learning_rate": 5.6093467170257374e-05,
      "loss": 1.5175,
      "step": 103
    },
    {
      "epoch": 0.03487007544006706,
      "grad_norm": 1.6598199605941772,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.7261,
      "step": 104
    },
    {
      "epoch": 0.03520536462699078,
      "grad_norm": 1.80154287815094,
      "learning_rate": 5.435778713738292e-05,
      "loss": 1.5605,
      "step": 105
    },
    {
      "epoch": 0.035540653813914504,
      "grad_norm": 1.6656845808029175,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.5951,
      "step": 106
    },
    {
      "epoch": 0.035875943000838226,
      "grad_norm": 1.8260254859924316,
      "learning_rate": 5.26167978121472e-05,
      "loss": 1.8052,
      "step": 107
    },
    {
      "epoch": 0.03621123218776195,
      "grad_norm": 1.9387423992156982,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.9528,
      "step": 108
    },
    {
      "epoch": 0.03654652137468566,
      "grad_norm": 1.7920228242874146,
      "learning_rate": 5.0872620321864185e-05,
      "loss": 1.7059,
      "step": 109
    },
    {
      "epoch": 0.036881810561609385,
      "grad_norm": 1.5748786926269531,
      "learning_rate": 5e-05,
      "loss": 1.6674,
      "step": 110
    },
    {
      "epoch": 0.03721709974853311,
      "grad_norm": 1.4134800434112549,
      "learning_rate": 4.912737967813583e-05,
      "loss": 1.5574,
      "step": 111
    },
    {
      "epoch": 0.03755238893545683,
      "grad_norm": 1.574621558189392,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.4027,
      "step": 112
    },
    {
      "epoch": 0.03788767812238055,
      "grad_norm": 1.5440373420715332,
      "learning_rate": 4.738320218785281e-05,
      "loss": 1.6197,
      "step": 113
    },
    {
      "epoch": 0.03822296730930427,
      "grad_norm": 1.5774800777435303,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.9142,
      "step": 114
    },
    {
      "epoch": 0.038558256496227995,
      "grad_norm": 1.7833162546157837,
      "learning_rate": 4.564221286261709e-05,
      "loss": 1.8281,
      "step": 115
    },
    {
      "epoch": 0.03889354568315172,
      "grad_norm": 1.6017940044403076,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.7815,
      "step": 116
    },
    {
      "epoch": 0.03922883487007544,
      "grad_norm": 1.4744386672973633,
      "learning_rate": 4.390653282974264e-05,
      "loss": 1.7268,
      "step": 117
    },
    {
      "epoch": 0.03956412405699916,
      "grad_norm": 1.2313249111175537,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.5412,
      "step": 118
    },
    {
      "epoch": 0.039899413243922884,
      "grad_norm": 1.5644769668579102,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 1.9018,
      "step": 119
    },
    {
      "epoch": 0.040234702430846606,
      "grad_norm": 1.3826490640640259,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.677,
      "step": 120
    },
    {
      "epoch": 0.04056999161777033,
      "grad_norm": 1.734617829322815,
      "learning_rate": 4.045955023117276e-05,
      "loss": 1.806,
      "step": 121
    },
    {
      "epoch": 0.04090528080469405,
      "grad_norm": 1.5642307996749878,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.9275,
      "step": 122
    },
    {
      "epoch": 0.04124056999161777,
      "grad_norm": 1.308278203010559,
      "learning_rate": 3.875244728280676e-05,
      "loss": 1.5416,
      "step": 123
    },
    {
      "epoch": 0.041575859178541494,
      "grad_norm": 1.59608793258667,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.7504,
      "step": 124
    },
    {
      "epoch": 0.041911148365465216,
      "grad_norm": 1.3959640264511108,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.8318,
      "step": 125
    },
    {
      "epoch": 0.04224643755238894,
      "grad_norm": 1.539931058883667,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.8151,
      "step": 126
    },
    {
      "epoch": 0.04258172673931266,
      "grad_norm": 1.9125542640686035,
      "learning_rate": 3.5381414763863166e-05,
      "loss": 2.1793,
      "step": 127
    },
    {
      "epoch": 0.04291701592623638,
      "grad_norm": 1.8889496326446533,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.041,
      "step": 128
    },
    {
      "epoch": 0.0432523051131601,
      "grad_norm": 1.9471142292022705,
      "learning_rate": 3.372159227714218e-05,
      "loss": 1.9827,
      "step": 129
    },
    {
      "epoch": 0.04358759430008382,
      "grad_norm": 1.873214602470398,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.8718,
      "step": 130
    },
    {
      "epoch": 0.04392288348700754,
      "grad_norm": 1.711531400680542,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 1.8252,
      "step": 131
    },
    {
      "epoch": 0.04425817267393126,
      "grad_norm": 1.5534932613372803,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.7072,
      "step": 132
    },
    {
      "epoch": 0.044593461860854985,
      "grad_norm": 1.7707465887069702,
      "learning_rate": 3.046344357553632e-05,
      "loss": 1.7909,
      "step": 133
    },
    {
      "epoch": 0.04492875104777871,
      "grad_norm": 2.0942959785461426,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.2297,
      "step": 134
    },
    {
      "epoch": 0.04526404023470243,
      "grad_norm": 1.8636870384216309,
      "learning_rate": 2.886908691296504e-05,
      "loss": 1.9661,
      "step": 135
    },
    {
      "epoch": 0.04559932942162615,
      "grad_norm": 1.750473141670227,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.9891,
      "step": 136
    },
    {
      "epoch": 0.045934618608549874,
      "grad_norm": 1.7958630323410034,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 2.246,
      "step": 137
    },
    {
      "epoch": 0.046269907795473596,
      "grad_norm": 1.7150790691375732,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.0096,
      "step": 138
    },
    {
      "epoch": 0.04660519698239732,
      "grad_norm": 1.850218415260315,
      "learning_rate": 2.575951898768315e-05,
      "loss": 2.0812,
      "step": 139
    },
    {
      "epoch": 0.04694048616932104,
      "grad_norm": 1.802883267402649,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.0021,
      "step": 140
    },
    {
      "epoch": 0.04727577535624476,
      "grad_norm": 1.8256604671478271,
      "learning_rate": 2.4248096254497288e-05,
      "loss": 1.806,
      "step": 141
    },
    {
      "epoch": 0.047611064543168484,
      "grad_norm": 1.7722952365875244,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.0219,
      "step": 142
    },
    {
      "epoch": 0.047946353730092206,
      "grad_norm": 1.784156084060669,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 2.0517,
      "step": 143
    },
    {
      "epoch": 0.04828164291701593,
      "grad_norm": 1.9192204475402832,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.2254,
      "step": 144
    },
    {
      "epoch": 0.04861693210393965,
      "grad_norm": 1.7217282056808472,
      "learning_rate": 2.132117818244771e-05,
      "loss": 2.035,
      "step": 145
    },
    {
      "epoch": 0.04895222129086337,
      "grad_norm": 1.7334017753601074,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.037,
      "step": 146
    },
    {
      "epoch": 0.049287510477787094,
      "grad_norm": 2.0734338760375977,
      "learning_rate": 1.9909248842397584e-05,
      "loss": 2.1014,
      "step": 147
    },
    {
      "epoch": 0.049622799664710816,
      "grad_norm": 1.4909307956695557,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.8301,
      "step": 148
    },
    {
      "epoch": 0.04995808885163453,
      "grad_norm": 1.5050811767578125,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 1.9028,
      "step": 149
    },
    {
      "epoch": 0.050293378038558254,
      "grad_norm": 1.7747118473052979,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.9659,
      "step": 150
    },
    {
      "epoch": 0.050293378038558254,
      "eval_loss": 1.919277548789978,
      "eval_runtime": 414.0216,
      "eval_samples_per_second": 12.132,
      "eval_steps_per_second": 6.067,
      "step": 150
    },
    {
      "epoch": 0.050628667225481976,
      "grad_norm": 1.75709867477417,
      "learning_rate": 1.7197048550474643e-05,
      "loss": 1.616,
      "step": 151
    },
    {
      "epoch": 0.0509639564124057,
      "grad_norm": 1.6926578283309937,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.812,
      "step": 152
    },
    {
      "epoch": 0.05129924559932942,
      "grad_norm": 1.6195133924484253,
      "learning_rate": 1.5900081996875083e-05,
      "loss": 1.9274,
      "step": 153
    },
    {
      "epoch": 0.05163453478625314,
      "grad_norm": 1.6469265222549438,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.0456,
      "step": 154
    },
    {
      "epoch": 0.051969823973176864,
      "grad_norm": 1.4841623306274414,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.5657,
      "step": 155
    },
    {
      "epoch": 0.052305113160100586,
      "grad_norm": 1.2378308773040771,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.2767,
      "step": 156
    },
    {
      "epoch": 0.05264040234702431,
      "grad_norm": 1.5727970600128174,
      "learning_rate": 1.3432314919041478e-05,
      "loss": 1.8513,
      "step": 157
    },
    {
      "epoch": 0.05297569153394803,
      "grad_norm": 1.5331429243087769,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.6441,
      "step": 158
    },
    {
      "epoch": 0.05331098072087175,
      "grad_norm": 1.4793914556503296,
      "learning_rate": 1.22645209888614e-05,
      "loss": 1.8016,
      "step": 159
    },
    {
      "epoch": 0.053646269907795474,
      "grad_norm": 1.377514362335205,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.6343,
      "step": 160
    },
    {
      "epoch": 0.053981559094719196,
      "grad_norm": 1.5226294994354248,
      "learning_rate": 1.1142701927151456e-05,
      "loss": 1.6647,
      "step": 161
    },
    {
      "epoch": 0.05431684828164292,
      "grad_norm": 1.5354899168014526,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.8415,
      "step": 162
    },
    {
      "epoch": 0.05465213746856664,
      "grad_norm": 1.9512042999267578,
      "learning_rate": 1.006822449763537e-05,
      "loss": 1.7546,
      "step": 163
    },
    {
      "epoch": 0.05498742665549036,
      "grad_norm": 1.6189467906951904,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.7584,
      "step": 164
    },
    {
      "epoch": 0.055322715842414084,
      "grad_norm": 1.5202131271362305,
      "learning_rate": 9.042397785550405e-06,
      "loss": 1.8023,
      "step": 165
    },
    {
      "epoch": 0.055658005029337806,
      "grad_norm": 1.607535481452942,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.8869,
      "step": 166
    },
    {
      "epoch": 0.05599329421626153,
      "grad_norm": 1.742763638496399,
      "learning_rate": 8.066471602728803e-06,
      "loss": 1.9203,
      "step": 167
    },
    {
      "epoch": 0.05632858340318525,
      "grad_norm": 1.82354736328125,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.8802,
      "step": 168
    },
    {
      "epoch": 0.056663872590108966,
      "grad_norm": 1.465013861656189,
      "learning_rate": 7.1416349648943894e-06,
      "loss": 1.6293,
      "step": 169
    },
    {
      "epoch": 0.05699916177703269,
      "grad_norm": 1.4326895475387573,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.6423,
      "step": 170
    },
    {
      "epoch": 0.05733445096395641,
      "grad_norm": 1.6752136945724487,
      "learning_rate": 6.269014643030213e-06,
      "loss": 1.8577,
      "step": 171
    },
    {
      "epoch": 0.05766974015088013,
      "grad_norm": 1.7337913513183594,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.979,
      "step": 172
    },
    {
      "epoch": 0.058005029337803854,
      "grad_norm": 1.7008464336395264,
      "learning_rate": 5.449673790581611e-06,
      "loss": 2.0092,
      "step": 173
    },
    {
      "epoch": 0.058340318524727576,
      "grad_norm": 1.747277855873108,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.0613,
      "step": 174
    },
    {
      "epoch": 0.0586756077116513,
      "grad_norm": 1.6014654636383057,
      "learning_rate": 4.684610648167503e-06,
      "loss": 2.0041,
      "step": 175
    },
    {
      "epoch": 0.05901089689857502,
      "grad_norm": 1.7131054401397705,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.8981,
      "step": 176
    },
    {
      "epoch": 0.05934618608549874,
      "grad_norm": 1.5840563774108887,
      "learning_rate": 3.974757327377981e-06,
      "loss": 1.7876,
      "step": 177
    },
    {
      "epoch": 0.059681475272422464,
      "grad_norm": 1.8875409364700317,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.0019,
      "step": 178
    },
    {
      "epoch": 0.060016764459346186,
      "grad_norm": 1.597502589225769,
      "learning_rate": 3.3209786751399187e-06,
      "loss": 1.8282,
      "step": 179
    },
    {
      "epoch": 0.06035205364626991,
      "grad_norm": 2.0686233043670654,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.0876,
      "step": 180
    },
    {
      "epoch": 0.06068734283319363,
      "grad_norm": 1.970877766609192,
      "learning_rate": 2.724071220034158e-06,
      "loss": 2.0983,
      "step": 181
    },
    {
      "epoch": 0.06102263202011735,
      "grad_norm": 1.7997721433639526,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.7738,
      "step": 182
    },
    {
      "epoch": 0.061357921207041075,
      "grad_norm": 1.7016370296478271,
      "learning_rate": 2.1847622018482283e-06,
      "loss": 2.0017,
      "step": 183
    },
    {
      "epoch": 0.0616932103939648,
      "grad_norm": 2.033308744430542,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.1012,
      "step": 184
    },
    {
      "epoch": 0.06202849958088852,
      "grad_norm": 1.65354323387146,
      "learning_rate": 1.70370868554659e-06,
      "loss": 2.0865,
      "step": 185
    },
    {
      "epoch": 0.06236378876781224,
      "grad_norm": 1.7829906940460205,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.1552,
      "step": 186
    },
    {
      "epoch": 0.06269907795473596,
      "grad_norm": 1.7008651494979858,
      "learning_rate": 1.2814967607382432e-06,
      "loss": 2.2325,
      "step": 187
    },
    {
      "epoch": 0.06303436714165968,
      "grad_norm": 1.867773413658142,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.1546,
      "step": 188
    },
    {
      "epoch": 0.0633696563285834,
      "grad_norm": 1.5875962972640991,
      "learning_rate": 9.186408276168013e-07,
      "loss": 1.9401,
      "step": 189
    },
    {
      "epoch": 0.06370494551550712,
      "grad_norm": 1.7697455883026123,
      "learning_rate": 7.596123493895991e-07,
      "loss": 2.1524,
      "step": 190
    },
    {
      "epoch": 0.06404023470243085,
      "grad_norm": 1.833638072013855,
      "learning_rate": 6.15582970243117e-07,
      "loss": 2.0173,
      "step": 191
    },
    {
      "epoch": 0.06437552388935457,
      "grad_norm": 1.6446995735168457,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.8198,
      "step": 192
    },
    {
      "epoch": 0.0647108130762783,
      "grad_norm": 1.7010647058486938,
      "learning_rate": 3.7269241793390085e-07,
      "loss": 1.767,
      "step": 193
    },
    {
      "epoch": 0.06504610226320201,
      "grad_norm": 1.7113988399505615,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.974,
      "step": 194
    },
    {
      "epoch": 0.06538139145012574,
      "grad_norm": 1.8768165111541748,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 2.0782,
      "step": 195
    },
    {
      "epoch": 0.06571668063704945,
      "grad_norm": 1.672215461730957,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.0222,
      "step": 196
    },
    {
      "epoch": 0.06605196982397318,
      "grad_norm": 2.0398664474487305,
      "learning_rate": 6.852326227130834e-08,
      "loss": 2.3799,
      "step": 197
    },
    {
      "epoch": 0.0663872590108969,
      "grad_norm": 1.9088635444641113,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.8721,
      "step": 198
    },
    {
      "epoch": 0.06672254819782061,
      "grad_norm": 1.7489848136901855,
      "learning_rate": 7.615242180436522e-09,
      "loss": 2.0907,
      "step": 199
    },
    {
      "epoch": 0.06705783738474434,
      "grad_norm": 1.9194645881652832,
      "learning_rate": 0.0,
      "loss": 2.0171,
      "step": 200
    },
    {
      "epoch": 0.06705783738474434,
      "eval_loss": 1.9088218212127686,
      "eval_runtime": 414.3409,
      "eval_samples_per_second": 12.123,
      "eval_steps_per_second": 6.063,
      "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": 3.017027157491712e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}