{
  "best_metric": 0.6153644323348999,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.1970928800197093,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009854644000985464,
      "grad_norm": 0.21368320286273956,
      "learning_rate": 5e-06,
      "loss": 0.0811,
      "step": 1
    },
    {
      "epoch": 0.0009854644000985464,
      "eval_loss": 0.8373544812202454,
      "eval_runtime": 66.3618,
      "eval_samples_per_second": 25.753,
      "eval_steps_per_second": 12.884,
      "step": 1
    },
    {
      "epoch": 0.001970928800197093,
      "grad_norm": 0.260768860578537,
      "learning_rate": 1e-05,
      "loss": 0.2399,
      "step": 2
    },
    {
      "epoch": 0.0029563932002956393,
      "grad_norm": 0.44264376163482666,
      "learning_rate": 1.5e-05,
      "loss": 0.364,
      "step": 3
    },
    {
      "epoch": 0.003941857600394186,
      "grad_norm": 0.5036729574203491,
      "learning_rate": 2e-05,
      "loss": 0.3749,
      "step": 4
    },
    {
      "epoch": 0.004927322000492732,
      "grad_norm": 0.45520466566085815,
      "learning_rate": 2.5e-05,
      "loss": 0.4327,
      "step": 5
    },
    {
      "epoch": 0.005912786400591279,
      "grad_norm": 0.43378737568855286,
      "learning_rate": 3e-05,
      "loss": 0.4906,
      "step": 6
    },
    {
      "epoch": 0.006898250800689825,
      "grad_norm": 0.29966574907302856,
      "learning_rate": 3.5e-05,
      "loss": 0.6722,
      "step": 7
    },
    {
      "epoch": 0.007883715200788372,
      "grad_norm": 0.288310706615448,
      "learning_rate": 4e-05,
      "loss": 0.7376,
      "step": 8
    },
    {
      "epoch": 0.008869179600886918,
      "grad_norm": 0.26541921496391296,
      "learning_rate": 4.5e-05,
      "loss": 0.7256,
      "step": 9
    },
    {
      "epoch": 0.009854644000985464,
      "grad_norm": 0.23990140855312347,
      "learning_rate": 5e-05,
      "loss": 0.8011,
      "step": 10
    },
    {
      "epoch": 0.01084010840108401,
      "grad_norm": 0.2725456655025482,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.7134,
      "step": 11
    },
    {
      "epoch": 0.011825572801182557,
      "grad_norm": 0.26453617215156555,
      "learning_rate": 6e-05,
      "loss": 0.817,
      "step": 12
    },
    {
      "epoch": 0.012811037201281104,
      "grad_norm": 0.25874823331832886,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.6065,
      "step": 13
    },
    {
      "epoch": 0.01379650160137965,
      "grad_norm": 0.2898238003253937,
      "learning_rate": 7e-05,
      "loss": 0.648,
      "step": 14
    },
    {
      "epoch": 0.014781966001478197,
      "grad_norm": 0.29036572575569153,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8054,
      "step": 15
    },
    {
      "epoch": 0.015767430401576743,
      "grad_norm": 0.2954308092594147,
      "learning_rate": 8e-05,
      "loss": 0.724,
      "step": 16
    },
    {
      "epoch": 0.01675289480167529,
      "grad_norm": 0.27134811878204346,
      "learning_rate": 8.5e-05,
      "loss": 0.6222,
      "step": 17
    },
    {
      "epoch": 0.017738359201773836,
      "grad_norm": 0.27076807618141174,
      "learning_rate": 9e-05,
      "loss": 0.6876,
      "step": 18
    },
    {
      "epoch": 0.018723823601872382,
      "grad_norm": 0.2982608675956726,
      "learning_rate": 9.5e-05,
      "loss": 0.7342,
      "step": 19
    },
    {
      "epoch": 0.01970928800197093,
      "grad_norm": 0.2779473066329956,
      "learning_rate": 0.0001,
      "loss": 0.7138,
      "step": 20
    },
    {
      "epoch": 0.020694752402069475,
      "grad_norm": 0.2604323625564575,
      "learning_rate": 9.999238475781957e-05,
      "loss": 0.6335,
      "step": 21
    },
    {
      "epoch": 0.02168021680216802,
      "grad_norm": 0.2886645495891571,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.6257,
      "step": 22
    },
    {
      "epoch": 0.022665681202266568,
      "grad_norm": 0.2738495469093323,
      "learning_rate": 9.99314767377287e-05,
      "loss": 0.6123,
      "step": 23
    },
    {
      "epoch": 0.023651145602365115,
      "grad_norm": 0.29884693026542664,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.7732,
      "step": 24
    },
    {
      "epoch": 0.02463661000246366,
      "grad_norm": 0.28413522243499756,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.737,
      "step": 25
    },
    {
      "epoch": 0.025622074402562207,
      "grad_norm": 0.284929484128952,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.6115,
      "step": 26
    },
    {
      "epoch": 0.026607538802660754,
      "grad_norm": 0.3191145360469818,
      "learning_rate": 9.962730758206611e-05,
      "loss": 0.8331,
      "step": 27
    },
    {
      "epoch": 0.0275930032027593,
      "grad_norm": 0.288494348526001,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.6987,
      "step": 28
    },
    {
      "epoch": 0.028578467602857847,
      "grad_norm": 0.33966076374053955,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.787,
      "step": 29
    },
    {
      "epoch": 0.029563932002956393,
      "grad_norm": 0.29486000537872314,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.7766,
      "step": 30
    },
    {
      "epoch": 0.03054939640305494,
      "grad_norm": 0.3164560794830322,
      "learning_rate": 9.908135917238321e-05,
      "loss": 0.7605,
      "step": 31
    },
    {
      "epoch": 0.031534860803153486,
      "grad_norm": 0.3024621605873108,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.6868,
      "step": 32
    },
    {
      "epoch": 0.032520325203252036,
      "grad_norm": 0.31722673773765564,
      "learning_rate": 9.871850323926177e-05,
      "loss": 0.711,
      "step": 33
    },
    {
      "epoch": 0.03350578960335058,
      "grad_norm": 0.34064680337905884,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.7589,
      "step": 34
    },
    {
      "epoch": 0.03449125400344913,
      "grad_norm": 0.3236991763114929,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.6888,
      "step": 35
    },
    {
      "epoch": 0.03547671840354767,
      "grad_norm": 0.3362804055213928,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.7985,
      "step": 36
    },
    {
      "epoch": 0.03646218280364622,
      "grad_norm": 0.36856207251548767,
      "learning_rate": 9.781523779815179e-05,
      "loss": 0.8506,
      "step": 37
    },
    {
      "epoch": 0.037447647203744765,
      "grad_norm": 0.38532865047454834,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6945,
      "step": 38
    },
    {
      "epoch": 0.038433111603843315,
      "grad_norm": 0.3765904903411865,
      "learning_rate": 9.727592877996585e-05,
      "loss": 0.8341,
      "step": 39
    },
    {
      "epoch": 0.03941857600394186,
      "grad_norm": 0.3601222336292267,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.6398,
      "step": 40
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 0.40156570076942444,
      "learning_rate": 9.667902132486009e-05,
      "loss": 0.6301,
      "step": 41
    },
    {
      "epoch": 0.04138950480413895,
      "grad_norm": 0.4138280153274536,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.7974,
      "step": 42
    },
    {
      "epoch": 0.0423749692042375,
      "grad_norm": 0.4361515939235687,
      "learning_rate": 9.602524267262203e-05,
      "loss": 0.7225,
      "step": 43
    },
    {
      "epoch": 0.04336043360433604,
      "grad_norm": 0.4487519860267639,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.7484,
      "step": 44
    },
    {
      "epoch": 0.04434589800443459,
      "grad_norm": 0.43802666664123535,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.7125,
      "step": 45
    },
    {
      "epoch": 0.045331362404533136,
      "grad_norm": 0.4856754541397095,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.9,
      "step": 46
    },
    {
      "epoch": 0.046316826804631686,
      "grad_norm": 0.5210389494895935,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.9333,
      "step": 47
    },
    {
      "epoch": 0.04730229120473023,
      "grad_norm": 0.5823840498924255,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.7554,
      "step": 48
    },
    {
      "epoch": 0.04828775560482878,
      "grad_norm": 0.7275289297103882,
      "learning_rate": 9.373098535696979e-05,
      "loss": 0.9166,
      "step": 49
    },
    {
      "epoch": 0.04927322000492732,
      "grad_norm": 0.8048695921897888,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.9283,
      "step": 50
    },
    {
      "epoch": 0.04927322000492732,
      "eval_loss": 0.6464605927467346,
      "eval_runtime": 66.2868,
      "eval_samples_per_second": 25.782,
      "eval_steps_per_second": 12.899,
      "step": 50
    },
    {
      "epoch": 0.05025868440502587,
      "grad_norm": 0.12230159342288971,
      "learning_rate": 9.285836503510562e-05,
      "loss": 0.0571,
      "step": 51
    },
    {
      "epoch": 0.051244148805124415,
      "grad_norm": 0.11277984827756882,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.1799,
      "step": 52
    },
    {
      "epoch": 0.052229613205222965,
      "grad_norm": 0.1283257156610489,
      "learning_rate": 9.193352839727121e-05,
      "loss": 0.2379,
      "step": 53
    },
    {
      "epoch": 0.05321507760532151,
      "grad_norm": 0.1701822280883789,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.3356,
      "step": 54
    },
    {
      "epoch": 0.05420054200542006,
      "grad_norm": 0.20211534202098846,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.4511,
      "step": 55
    },
    {
      "epoch": 0.0551860064055186,
      "grad_norm": 0.20168742537498474,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.558,
      "step": 56
    },
    {
      "epoch": 0.05617147080561715,
      "grad_norm": 0.1796450912952423,
      "learning_rate": 8.993177550236464e-05,
      "loss": 0.5004,
      "step": 57
    },
    {
      "epoch": 0.057156935205715693,
      "grad_norm": 0.21156959235668182,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.6535,
      "step": 58
    },
    {
      "epoch": 0.05814239960581424,
      "grad_norm": 0.19509942829608917,
      "learning_rate": 8.885729807284856e-05,
      "loss": 0.5512,
      "step": 59
    },
    {
      "epoch": 0.059127864005912786,
      "grad_norm": 0.22828419506549835,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.8388,
      "step": 60
    },
    {
      "epoch": 0.060113328406011336,
      "grad_norm": 0.20433418452739716,
      "learning_rate": 8.773547901113862e-05,
      "loss": 0.5995,
      "step": 61
    },
    {
      "epoch": 0.06109879280610988,
      "grad_norm": 0.20512636005878448,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.6224,
      "step": 62
    },
    {
      "epoch": 0.06208425720620843,
      "grad_norm": 0.21725022792816162,
      "learning_rate": 8.656768508095853e-05,
      "loss": 0.6128,
      "step": 63
    },
    {
      "epoch": 0.06306972160630697,
      "grad_norm": 0.2174377739429474,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.6843,
      "step": 64
    },
    {
      "epoch": 0.06405518600640552,
      "grad_norm": 0.2236977070569992,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.6858,
      "step": 65
    },
    {
      "epoch": 0.06504065040650407,
      "grad_norm": 0.27690693736076355,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.9392,
      "step": 66
    },
    {
      "epoch": 0.06602611480660261,
      "grad_norm": 0.22860707342624664,
      "learning_rate": 8.409991800312493e-05,
      "loss": 0.7385,
      "step": 67
    },
    {
      "epoch": 0.06701157920670116,
      "grad_norm": 0.2298586070537567,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.7546,
      "step": 68
    },
    {
      "epoch": 0.0679970436067997,
      "grad_norm": 0.2377099245786667,
      "learning_rate": 8.280295144952536e-05,
      "loss": 0.6743,
      "step": 69
    },
    {
      "epoch": 0.06898250800689826,
      "grad_norm": 0.21426402032375336,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.5414,
      "step": 70
    },
    {
      "epoch": 0.0699679724069968,
      "grad_norm": 0.23989328742027283,
      "learning_rate": 8.146601955249188e-05,
      "loss": 0.606,
      "step": 71
    },
    {
      "epoch": 0.07095343680709534,
      "grad_norm": 0.2526426613330841,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.6877,
      "step": 72
    },
    {
      "epoch": 0.07193890120719389,
      "grad_norm": 0.25667741894721985,
      "learning_rate": 8.009075115760243e-05,
      "loss": 0.8371,
      "step": 73
    },
    {
      "epoch": 0.07292436560729244,
      "grad_norm": 0.2683584690093994,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.9071,
      "step": 74
    },
    {
      "epoch": 0.07390983000739099,
      "grad_norm": 0.2747768461704254,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.7603,
      "step": 75
    },
    {
      "epoch": 0.07489529440748953,
      "grad_norm": 0.2705404758453369,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.7255,
      "step": 76
    },
    {
      "epoch": 0.07588075880758807,
      "grad_norm": 0.2925010323524475,
      "learning_rate": 7.723195175075136e-05,
      "loss": 0.7684,
      "step": 77
    },
    {
      "epoch": 0.07686622320768663,
      "grad_norm": 0.2544151544570923,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.6322,
      "step": 78
    },
    {
      "epoch": 0.07785168760778517,
      "grad_norm": 0.27934426069259644,
      "learning_rate": 7.575190374550272e-05,
      "loss": 0.7391,
      "step": 79
    },
    {
      "epoch": 0.07883715200788372,
      "grad_norm": 0.3051762878894806,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.7494,
      "step": 80
    },
    {
      "epoch": 0.07982261640798226,
      "grad_norm": 0.28656357526779175,
      "learning_rate": 7.424048101231686e-05,
      "loss": 0.7278,
      "step": 81
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 0.3144802153110504,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.719,
      "step": 82
    },
    {
      "epoch": 0.08179354520817936,
      "grad_norm": 0.3164990246295929,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.7447,
      "step": 83
    },
    {
      "epoch": 0.0827790096082779,
      "grad_norm": 0.28684890270233154,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.7701,
      "step": 84
    },
    {
      "epoch": 0.08376447400837644,
      "grad_norm": 0.328673779964447,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.6504,
      "step": 85
    },
    {
      "epoch": 0.084749938408475,
      "grad_norm": 0.3479191064834595,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.816,
      "step": 86
    },
    {
      "epoch": 0.08573540280857354,
      "grad_norm": 0.30887213349342346,
      "learning_rate": 6.953655642446368e-05,
      "loss": 0.6048,
      "step": 87
    },
    {
      "epoch": 0.08672086720867209,
      "grad_norm": 0.3754432797431946,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.728,
      "step": 88
    },
    {
      "epoch": 0.08770633160877063,
      "grad_norm": 0.3510769009590149,
      "learning_rate": 6.7918397477265e-05,
      "loss": 0.7624,
      "step": 89
    },
    {
      "epoch": 0.08869179600886919,
      "grad_norm": 0.37762296199798584,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.6676,
      "step": 90
    },
    {
      "epoch": 0.08967726040896773,
      "grad_norm": 0.34411317110061646,
      "learning_rate": 6.627840772285784e-05,
      "loss": 0.6249,
      "step": 91
    },
    {
      "epoch": 0.09066272480906627,
      "grad_norm": 0.3781382739543915,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5981,
      "step": 92
    },
    {
      "epoch": 0.09164818920916482,
      "grad_norm": 0.4274924099445343,
      "learning_rate": 6.461858523613684e-05,
      "loss": 0.8801,
      "step": 93
    },
    {
      "epoch": 0.09263365360926337,
      "grad_norm": 0.4174174964427948,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.6756,
      "step": 94
    },
    {
      "epoch": 0.09361911800936192,
      "grad_norm": 0.47355586290359497,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.8179,
      "step": 95
    },
    {
      "epoch": 0.09460458240946046,
      "grad_norm": 0.4370453953742981,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.7869,
      "step": 96
    },
    {
      "epoch": 0.095590046809559,
      "grad_norm": 0.4838176667690277,
      "learning_rate": 6.124755271719325e-05,
      "loss": 0.8112,
      "step": 97
    },
    {
      "epoch": 0.09657551120965756,
      "grad_norm": 0.5100703835487366,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.7746,
      "step": 98
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.6169785261154175,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 0.8988,
      "step": 99
    },
    {
      "epoch": 0.09854644000985464,
      "grad_norm": 0.8071909546852112,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.6597,
      "step": 100
    },
    {
      "epoch": 0.09854644000985464,
      "eval_loss": 0.6289290189743042,
      "eval_runtime": 66.4133,
      "eval_samples_per_second": 25.733,
      "eval_steps_per_second": 12.874,
      "step": 100
    },
    {
      "epoch": 0.09953190440995319,
      "grad_norm": 0.06508608162403107,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.0293,
      "step": 101
    },
    {
      "epoch": 0.10051736881005174,
      "grad_norm": 0.10537426918745041,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.1911,
      "step": 102
    },
    {
      "epoch": 0.10150283321015029,
      "grad_norm": 0.10470440238714218,
      "learning_rate": 5.6093467170257374e-05,
      "loss": 0.2062,
      "step": 103
    },
    {
      "epoch": 0.10248829761024883,
      "grad_norm": 0.1329120248556137,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.2705,
      "step": 104
    },
    {
      "epoch": 0.10347376201034737,
      "grad_norm": 0.1280706822872162,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.2274,
      "step": 105
    },
    {
      "epoch": 0.10445922641044593,
      "grad_norm": 0.16757312417030334,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.4932,
      "step": 106
    },
    {
      "epoch": 0.10544469081054447,
      "grad_norm": 0.1751958429813385,
      "learning_rate": 5.26167978121472e-05,
      "loss": 0.5401,
      "step": 107
    },
    {
      "epoch": 0.10643015521064302,
      "grad_norm": 0.1717756688594818,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.6055,
      "step": 108
    },
    {
      "epoch": 0.10741561961074156,
      "grad_norm": 0.19734135270118713,
      "learning_rate": 5.0872620321864185e-05,
      "loss": 0.5538,
      "step": 109
    },
    {
      "epoch": 0.10840108401084012,
      "grad_norm": 0.18675287067890167,
      "learning_rate": 5e-05,
      "loss": 0.5751,
      "step": 110
    },
    {
      "epoch": 0.10938654841093866,
      "grad_norm": 0.19595959782600403,
      "learning_rate": 4.912737967813583e-05,
      "loss": 0.5783,
      "step": 111
    },
    {
      "epoch": 0.1103720128110372,
      "grad_norm": 0.20387478172779083,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.6778,
      "step": 112
    },
    {
      "epoch": 0.11135747721113574,
      "grad_norm": 0.19632427394390106,
      "learning_rate": 4.738320218785281e-05,
      "loss": 0.7262,
      "step": 113
    },
    {
      "epoch": 0.1123429416112343,
      "grad_norm": 0.22888943552970886,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.6576,
      "step": 114
    },
    {
      "epoch": 0.11332840601133284,
      "grad_norm": 0.21430076658725739,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.6493,
      "step": 115
    },
    {
      "epoch": 0.11431387041143139,
      "grad_norm": 0.20526853203773499,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.66,
      "step": 116
    },
    {
      "epoch": 0.11529933481152993,
      "grad_norm": 0.2236650139093399,
      "learning_rate": 4.390653282974264e-05,
      "loss": 0.6334,
      "step": 117
    },
    {
      "epoch": 0.11628479921162849,
      "grad_norm": 0.22159314155578613,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.7894,
      "step": 118
    },
    {
      "epoch": 0.11727026361172703,
      "grad_norm": 0.22929464280605316,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.6049,
      "step": 119
    },
    {
      "epoch": 0.11825572801182557,
      "grad_norm": 0.2338849902153015,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.685,
      "step": 120
    },
    {
      "epoch": 0.11924119241192412,
      "grad_norm": 0.2361065298318863,
      "learning_rate": 4.045955023117276e-05,
      "loss": 0.7811,
      "step": 121
    },
    {
      "epoch": 0.12022665681202267,
      "grad_norm": 0.23754455149173737,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.7872,
      "step": 122
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.2533068358898163,
      "learning_rate": 3.875244728280676e-05,
      "loss": 0.7897,
      "step": 123
    },
    {
      "epoch": 0.12219758561221976,
      "grad_norm": 0.25761741399765015,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.7821,
      "step": 124
    },
    {
      "epoch": 0.1231830500123183,
      "grad_norm": 0.262465238571167,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.8736,
      "step": 125
    },
    {
      "epoch": 0.12416851441241686,
      "grad_norm": 0.28506287932395935,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.7855,
      "step": 126
    },
    {
      "epoch": 0.1251539788125154,
      "grad_norm": 0.2701311707496643,
      "learning_rate": 3.5381414763863166e-05,
      "loss": 0.6851,
      "step": 127
    },
    {
      "epoch": 0.12613944321261394,
      "grad_norm": 0.2602234184741974,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6349,
      "step": 128
    },
    {
      "epoch": 0.1271249076127125,
      "grad_norm": 0.26517555117607117,
      "learning_rate": 3.372159227714218e-05,
      "loss": 0.6741,
      "step": 129
    },
    {
      "epoch": 0.12811037201281103,
      "grad_norm": 0.2652198076248169,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.569,
      "step": 130
    },
    {
      "epoch": 0.1290958364129096,
      "grad_norm": 0.27912837266921997,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 0.7768,
      "step": 131
    },
    {
      "epoch": 0.13008130081300814,
      "grad_norm": 0.28829455375671387,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.6819,
      "step": 132
    },
    {
      "epoch": 0.13106676521310667,
      "grad_norm": 0.2873208522796631,
      "learning_rate": 3.046344357553632e-05,
      "loss": 0.8448,
      "step": 133
    },
    {
      "epoch": 0.13205222961320523,
      "grad_norm": 0.3321005702018738,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.8613,
      "step": 134
    },
    {
      "epoch": 0.13303769401330376,
      "grad_norm": 0.3113601505756378,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.757,
      "step": 135
    },
    {
      "epoch": 0.13402315841340232,
      "grad_norm": 0.3224503993988037,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.8078,
      "step": 136
    },
    {
      "epoch": 0.13500862281350087,
      "grad_norm": 0.3039480745792389,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.5903,
      "step": 137
    },
    {
      "epoch": 0.1359940872135994,
      "grad_norm": 0.3399895429611206,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.681,
      "step": 138
    },
    {
      "epoch": 0.13697955161369796,
      "grad_norm": 0.32148513197898865,
      "learning_rate": 2.575951898768315e-05,
      "loss": 0.6537,
      "step": 139
    },
    {
      "epoch": 0.13796501601379652,
      "grad_norm": 0.3466744124889374,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.7301,
      "step": 140
    },
    {
      "epoch": 0.13895048041389504,
      "grad_norm": 0.35640135407447815,
      "learning_rate": 2.4248096254497288e-05,
      "loss": 0.7172,
      "step": 141
    },
    {
      "epoch": 0.1399359448139936,
      "grad_norm": 0.38685786724090576,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.7447,
      "step": 142
    },
    {
      "epoch": 0.14092140921409213,
      "grad_norm": 0.3715401291847229,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 0.6587,
      "step": 143
    },
    {
      "epoch": 0.1419068736141907,
      "grad_norm": 0.41979506611824036,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.7954,
      "step": 144
    },
    {
      "epoch": 0.14289233801428924,
      "grad_norm": 0.4046609103679657,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.7503,
      "step": 145
    },
    {
      "epoch": 0.14387780241438777,
      "grad_norm": 0.4440525472164154,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8386,
      "step": 146
    },
    {
      "epoch": 0.14486326681448633,
      "grad_norm": 0.4576321542263031,
      "learning_rate": 1.9909248842397584e-05,
      "loss": 0.6455,
      "step": 147
    },
    {
      "epoch": 0.1458487312145849,
      "grad_norm": 0.5070066452026367,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.8399,
      "step": 148
    },
    {
      "epoch": 0.14683419561468342,
      "grad_norm": 0.5966192483901978,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 0.7003,
      "step": 149
    },
    {
      "epoch": 0.14781966001478197,
      "grad_norm": 0.7911564707756042,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.6801,
      "step": 150
    },
    {
      "epoch": 0.14781966001478197,
      "eval_loss": 0.6193792223930359,
      "eval_runtime": 66.3669,
      "eval_samples_per_second": 25.751,
      "eval_steps_per_second": 12.883,
      "step": 150
    },
    {
      "epoch": 0.1488051244148805,
      "grad_norm": 0.05842919647693634,
      "learning_rate": 1.7197048550474643e-05,
      "loss": 0.0392,
      "step": 151
    },
    {
      "epoch": 0.14979058881497906,
      "grad_norm": 0.10516805201768875,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1793,
      "step": 152
    },
    {
      "epoch": 0.15077605321507762,
      "grad_norm": 0.11005867272615433,
      "learning_rate": 1.5900081996875083e-05,
      "loss": 0.2707,
      "step": 153
    },
    {
      "epoch": 0.15176151761517614,
      "grad_norm": 0.11866780370473862,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.3616,
      "step": 154
    },
    {
      "epoch": 0.1527469820152747,
      "grad_norm": 0.15852022171020508,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.5022,
      "step": 155
    },
    {
      "epoch": 0.15373244641537326,
      "grad_norm": 0.1865692287683487,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.6785,
      "step": 156
    },
    {
      "epoch": 0.1547179108154718,
      "grad_norm": 0.13659554719924927,
      "learning_rate": 1.3432314919041478e-05,
      "loss": 0.3663,
      "step": 157
    },
    {
      "epoch": 0.15570337521557034,
      "grad_norm": 0.17033393681049347,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.5578,
      "step": 158
    },
    {
      "epoch": 0.15668883961566887,
      "grad_norm": 0.17408299446105957,
      "learning_rate": 1.22645209888614e-05,
      "loss": 0.5313,
      "step": 159
    },
    {
      "epoch": 0.15767430401576743,
      "grad_norm": 0.18068967759609222,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.6492,
      "step": 160
    },
    {
      "epoch": 0.158659768415866,
      "grad_norm": 0.18489249050617218,
      "learning_rate": 1.1142701927151456e-05,
      "loss": 0.6622,
      "step": 161
    },
    {
      "epoch": 0.15964523281596452,
      "grad_norm": 0.19225475192070007,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.6331,
      "step": 162
    },
    {
      "epoch": 0.16063069721606307,
      "grad_norm": 0.17949078977108002,
      "learning_rate": 1.006822449763537e-05,
      "loss": 0.5526,
      "step": 163
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 0.20066401362419128,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.6809,
      "step": 164
    },
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 0.19776208698749542,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.626,
      "step": 165
    },
    {
      "epoch": 0.16358709041635872,
      "grad_norm": 0.20371097326278687,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.6395,
      "step": 166
    },
    {
      "epoch": 0.16457255481645724,
      "grad_norm": 0.20566946268081665,
      "learning_rate": 8.066471602728803e-06,
      "loss": 0.6099,
      "step": 167
    },
    {
      "epoch": 0.1655580192165558,
      "grad_norm": 0.2198767364025116,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.7695,
      "step": 168
    },
    {
      "epoch": 0.16654348361665436,
      "grad_norm": 0.21261905133724213,
      "learning_rate": 7.1416349648943894e-06,
      "loss": 0.7628,
      "step": 169
    },
    {
      "epoch": 0.1675289480167529,
      "grad_norm": 0.2710641920566559,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.814,
      "step": 170
    },
    {
      "epoch": 0.16851441241685144,
      "grad_norm": 0.2244243621826172,
      "learning_rate": 6.269014643030213e-06,
      "loss": 0.6744,
      "step": 171
    },
    {
      "epoch": 0.16949987681695,
      "grad_norm": 0.2463361620903015,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.7145,
      "step": 172
    },
    {
      "epoch": 0.17048534121704853,
      "grad_norm": 0.25145378708839417,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.6732,
      "step": 173
    },
    {
      "epoch": 0.1714708056171471,
      "grad_norm": 0.24809202551841736,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.7062,
      "step": 174
    },
    {
      "epoch": 0.17245627001724562,
      "grad_norm": 0.26336124539375305,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.8605,
      "step": 175
    },
    {
      "epoch": 0.17344173441734417,
      "grad_norm": 0.2400476485490799,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.6193,
      "step": 176
    },
    {
      "epoch": 0.17442719881744273,
      "grad_norm": 0.2559741735458374,
      "learning_rate": 3.974757327377981e-06,
      "loss": 0.7645,
      "step": 177
    },
    {
      "epoch": 0.17541266321754126,
      "grad_norm": 0.2447197139263153,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.7348,
      "step": 178
    },
    {
      "epoch": 0.17639812761763982,
      "grad_norm": 0.259756475687027,
      "learning_rate": 3.3209786751399187e-06,
      "loss": 0.7928,
      "step": 179
    },
    {
      "epoch": 0.17738359201773837,
      "grad_norm": 0.2761157751083374,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.7365,
      "step": 180
    },
    {
      "epoch": 0.1783690564178369,
      "grad_norm": 0.2338065654039383,
      "learning_rate": 2.724071220034158e-06,
      "loss": 0.4513,
      "step": 181
    },
    {
      "epoch": 0.17935452081793546,
      "grad_norm": 0.29236283898353577,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7673,
      "step": 182
    },
    {
      "epoch": 0.180339985218034,
      "grad_norm": 0.2648184299468994,
      "learning_rate": 2.1847622018482283e-06,
      "loss": 0.5189,
      "step": 183
    },
    {
      "epoch": 0.18132544961813254,
      "grad_norm": 0.3015969693660736,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.7121,
      "step": 184
    },
    {
      "epoch": 0.1823109140182311,
      "grad_norm": 0.280955970287323,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.63,
      "step": 185
    },
    {
      "epoch": 0.18329637841832963,
      "grad_norm": 0.2971841096878052,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.6638,
      "step": 186
    },
    {
      "epoch": 0.1842818428184282,
      "grad_norm": 0.33108440041542053,
      "learning_rate": 1.2814967607382432e-06,
      "loss": 0.69,
      "step": 187
    },
    {
      "epoch": 0.18526730721852674,
      "grad_norm": 0.3237815201282501,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.6172,
      "step": 188
    },
    {
      "epoch": 0.18625277161862527,
      "grad_norm": 0.33323925733566284,
      "learning_rate": 9.186408276168013e-07,
      "loss": 0.7341,
      "step": 189
    },
    {
      "epoch": 0.18723823601872383,
      "grad_norm": 0.37207913398742676,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.6773,
      "step": 190
    },
    {
      "epoch": 0.18822370041882236,
      "grad_norm": 0.3713732957839966,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.7245,
      "step": 191
    },
    {
      "epoch": 0.18920916481892092,
      "grad_norm": 0.40831276774406433,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.7629,
      "step": 192
    },
    {
      "epoch": 0.19019462921901947,
      "grad_norm": 0.3399887979030609,
      "learning_rate": 3.7269241793390085e-07,
      "loss": 0.5719,
      "step": 193
    },
    {
      "epoch": 0.191180093619118,
      "grad_norm": 0.3936917185783386,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.8063,
      "step": 194
    },
    {
      "epoch": 0.19216555801921656,
      "grad_norm": 0.42481428384780884,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.8021,
      "step": 195
    },
    {
      "epoch": 0.19315102241931512,
      "grad_norm": 0.4348626136779785,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.8341,
      "step": 196
    },
    {
      "epoch": 0.19413648681941365,
      "grad_norm": 0.564532995223999,
      "learning_rate": 6.852326227130834e-08,
      "loss": 0.962,
      "step": 197
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.4802018404006958,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.7501,
      "step": 198
    },
    {
      "epoch": 0.19610741561961073,
      "grad_norm": 0.5178065299987793,
      "learning_rate": 7.615242180436522e-09,
      "loss": 0.726,
      "step": 199
    },
    {
      "epoch": 0.1970928800197093,
      "grad_norm": 0.6739293336868286,
      "learning_rate": 0.0,
      "loss": 0.7251,
      "step": 200
    },
    {
      "epoch": 0.1970928800197093,
      "eval_loss": 0.6153644323348999,
      "eval_runtime": 66.3312,
      "eval_samples_per_second": 25.765,
      "eval_steps_per_second": 12.89,
      "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": 6.177685386559488e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}