{
  "best_metric": 0.7648534178733826,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.23344032681645754,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011672016340822876,
      "grad_norm": 0.46753478050231934,
      "learning_rate": 5e-06,
      "loss": 1.3161,
      "step": 1
    },
    {
      "epoch": 0.0011672016340822876,
      "eval_loss": 1.2134394645690918,
      "eval_runtime": 131.0537,
      "eval_samples_per_second": 11.011,
      "eval_steps_per_second": 5.509,
      "step": 1
    },
    {
      "epoch": 0.0023344032681645753,
      "grad_norm": 0.555250883102417,
      "learning_rate": 1e-05,
      "loss": 1.155,
      "step": 2
    },
    {
      "epoch": 0.0035016049022468633,
      "grad_norm": 0.6273149251937866,
      "learning_rate": 1.5e-05,
      "loss": 1.0917,
      "step": 3
    },
    {
      "epoch": 0.0046688065363291505,
      "grad_norm": 0.5431833863258362,
      "learning_rate": 2e-05,
      "loss": 1.198,
      "step": 4
    },
    {
      "epoch": 0.005836008170411439,
      "grad_norm": 0.5568272471427917,
      "learning_rate": 2.5e-05,
      "loss": 1.1327,
      "step": 5
    },
    {
      "epoch": 0.007003209804493727,
      "grad_norm": 0.5348870158195496,
      "learning_rate": 3e-05,
      "loss": 1.0018,
      "step": 6
    },
    {
      "epoch": 0.008170411438576015,
      "grad_norm": 0.5458340644836426,
      "learning_rate": 3.5e-05,
      "loss": 1.1215,
      "step": 7
    },
    {
      "epoch": 0.009337613072658301,
      "grad_norm": 0.5530060529708862,
      "learning_rate": 4e-05,
      "loss": 1.0996,
      "step": 8
    },
    {
      "epoch": 0.01050481470674059,
      "grad_norm": 0.4925542175769806,
      "learning_rate": 4.5e-05,
      "loss": 1.0459,
      "step": 9
    },
    {
      "epoch": 0.011672016340822877,
      "grad_norm": 0.42576614022254944,
      "learning_rate": 5e-05,
      "loss": 0.9905,
      "step": 10
    },
    {
      "epoch": 0.012839217974905165,
      "grad_norm": 0.4445820748806,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.0201,
      "step": 11
    },
    {
      "epoch": 0.014006419608987453,
      "grad_norm": 0.42280587553977966,
      "learning_rate": 6e-05,
      "loss": 0.9055,
      "step": 12
    },
    {
      "epoch": 0.01517362124306974,
      "grad_norm": 0.468988835811615,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.99,
      "step": 13
    },
    {
      "epoch": 0.01634082287715203,
      "grad_norm": 0.5269507169723511,
      "learning_rate": 7e-05,
      "loss": 1.004,
      "step": 14
    },
    {
      "epoch": 0.017508024511234316,
      "grad_norm": 0.599585235118866,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1302,
      "step": 15
    },
    {
      "epoch": 0.018675226145316602,
      "grad_norm": 0.6095326542854309,
      "learning_rate": 8e-05,
      "loss": 1.0333,
      "step": 16
    },
    {
      "epoch": 0.019842427779398892,
      "grad_norm": 0.6666775941848755,
      "learning_rate": 8.5e-05,
      "loss": 0.871,
      "step": 17
    },
    {
      "epoch": 0.02100962941348118,
      "grad_norm": 0.6163425445556641,
      "learning_rate": 9e-05,
      "loss": 0.8696,
      "step": 18
    },
    {
      "epoch": 0.022176831047563468,
      "grad_norm": 0.7333608865737915,
      "learning_rate": 9.5e-05,
      "loss": 0.8249,
      "step": 19
    },
    {
      "epoch": 0.023344032681645754,
      "grad_norm": 0.5166376829147339,
      "learning_rate": 0.0001,
      "loss": 0.8695,
      "step": 20
    },
    {
      "epoch": 0.02451123431572804,
      "grad_norm": 0.46006691455841064,
      "learning_rate": 9.999238475781957e-05,
      "loss": 0.8019,
      "step": 21
    },
    {
      "epoch": 0.02567843594981033,
      "grad_norm": 0.44337135553359985,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.8573,
      "step": 22
    },
    {
      "epoch": 0.026845637583892617,
      "grad_norm": 0.4858679175376892,
      "learning_rate": 9.99314767377287e-05,
      "loss": 0.9494,
      "step": 23
    },
    {
      "epoch": 0.028012839217974907,
      "grad_norm": 0.44925615191459656,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.7744,
      "step": 24
    },
    {
      "epoch": 0.029180040852057193,
      "grad_norm": 0.4528493881225586,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.8399,
      "step": 25
    },
    {
      "epoch": 0.03034724248613948,
      "grad_norm": 0.4085271656513214,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.9654,
      "step": 26
    },
    {
      "epoch": 0.031514444120221766,
      "grad_norm": 0.40491288900375366,
      "learning_rate": 9.962730758206611e-05,
      "loss": 0.8967,
      "step": 27
    },
    {
      "epoch": 0.03268164575430406,
      "grad_norm": 0.44310954213142395,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.9164,
      "step": 28
    },
    {
      "epoch": 0.033848847388386345,
      "grad_norm": 0.38083866238594055,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.8433,
      "step": 29
    },
    {
      "epoch": 0.03501604902246863,
      "grad_norm": 0.40849143266677856,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.8512,
      "step": 30
    },
    {
      "epoch": 0.03618325065655092,
      "grad_norm": 0.4501938223838806,
      "learning_rate": 9.908135917238321e-05,
      "loss": 0.8328,
      "step": 31
    },
    {
      "epoch": 0.037350452290633204,
      "grad_norm": 0.4410085082054138,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.902,
      "step": 32
    },
    {
      "epoch": 0.0385176539247155,
      "grad_norm": 0.48480021953582764,
      "learning_rate": 9.871850323926177e-05,
      "loss": 0.8779,
      "step": 33
    },
    {
      "epoch": 0.039684855558797784,
      "grad_norm": 0.4705844223499298,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.778,
      "step": 34
    },
    {
      "epoch": 0.04085205719288007,
      "grad_norm": 0.4460543990135193,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.9003,
      "step": 35
    },
    {
      "epoch": 0.04201925882696236,
      "grad_norm": 0.49308067560195923,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.9656,
      "step": 36
    },
    {
      "epoch": 0.04318646046104464,
      "grad_norm": 0.48300230503082275,
      "learning_rate": 9.781523779815179e-05,
      "loss": 0.8411,
      "step": 37
    },
    {
      "epoch": 0.044353662095126936,
      "grad_norm": 0.559090256690979,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8808,
      "step": 38
    },
    {
      "epoch": 0.04552086372920922,
      "grad_norm": 0.45826292037963867,
      "learning_rate": 9.727592877996585e-05,
      "loss": 0.8955,
      "step": 39
    },
    {
      "epoch": 0.04668806536329151,
      "grad_norm": 0.5036755204200745,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.7677,
      "step": 40
    },
    {
      "epoch": 0.047855266997373795,
      "grad_norm": 0.4597400426864624,
      "learning_rate": 9.667902132486009e-05,
      "loss": 0.8,
      "step": 41
    },
    {
      "epoch": 0.04902246863145608,
      "grad_norm": 0.4080221354961395,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.7653,
      "step": 42
    },
    {
      "epoch": 0.050189670265538375,
      "grad_norm": 0.3341499865055084,
      "learning_rate": 9.602524267262203e-05,
      "loss": 0.6779,
      "step": 43
    },
    {
      "epoch": 0.05135687189962066,
      "grad_norm": 0.33755984902381897,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.6499,
      "step": 44
    },
    {
      "epoch": 0.05252407353370295,
      "grad_norm": 0.3185901641845703,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.6571,
      "step": 45
    },
    {
      "epoch": 0.053691275167785234,
      "grad_norm": 0.3313101530075073,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.7173,
      "step": 46
    },
    {
      "epoch": 0.05485847680186752,
      "grad_norm": 0.33924600481987,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.7356,
      "step": 47
    },
    {
      "epoch": 0.05602567843594981,
      "grad_norm": 0.2959577739238739,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.6175,
      "step": 48
    },
    {
      "epoch": 0.0571928800700321,
      "grad_norm": 0.30051562190055847,
      "learning_rate": 9.373098535696979e-05,
      "loss": 0.7146,
      "step": 49
    },
    {
      "epoch": 0.058360081704114386,
      "grad_norm": 0.3311733901500702,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.6159,
      "step": 50
    },
    {
      "epoch": 0.058360081704114386,
      "eval_loss": 0.8087739944458008,
      "eval_runtime": 132.3214,
      "eval_samples_per_second": 10.905,
      "eval_steps_per_second": 5.456,
      "step": 50
    },
    {
      "epoch": 0.05952728333819667,
      "grad_norm": 1.9488471746444702,
      "learning_rate": 9.285836503510562e-05,
      "loss": 1.1721,
      "step": 51
    },
    {
      "epoch": 0.06069448497227896,
      "grad_norm": 0.35117700695991516,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.8176,
      "step": 52
    },
    {
      "epoch": 0.06186168660636125,
      "grad_norm": 0.29183295369148254,
      "learning_rate": 9.193352839727121e-05,
      "loss": 0.8778,
      "step": 53
    },
    {
      "epoch": 0.06302888824044353,
      "grad_norm": 0.2742466926574707,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.8458,
      "step": 54
    },
    {
      "epoch": 0.06419608987452582,
      "grad_norm": 0.2707342803478241,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.9672,
      "step": 55
    },
    {
      "epoch": 0.06536329150860812,
      "grad_norm": 0.27765777707099915,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7322,
      "step": 56
    },
    {
      "epoch": 0.0665304931426904,
      "grad_norm": 0.2863132357597351,
      "learning_rate": 8.993177550236464e-05,
      "loss": 0.7149,
      "step": 57
    },
    {
      "epoch": 0.06769769477677269,
      "grad_norm": 0.3221801221370697,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.7915,
      "step": 58
    },
    {
      "epoch": 0.06886489641085497,
      "grad_norm": 0.2689799964427948,
      "learning_rate": 8.885729807284856e-05,
      "loss": 0.795,
      "step": 59
    },
    {
      "epoch": 0.07003209804493726,
      "grad_norm": 0.2634994089603424,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.7719,
      "step": 60
    },
    {
      "epoch": 0.07119929967901956,
      "grad_norm": 0.2534864544868469,
      "learning_rate": 8.773547901113862e-05,
      "loss": 0.7296,
      "step": 61
    },
    {
      "epoch": 0.07236650131310184,
      "grad_norm": 0.2511971890926361,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.6957,
      "step": 62
    },
    {
      "epoch": 0.07353370294718413,
      "grad_norm": 0.26438698172569275,
      "learning_rate": 8.656768508095853e-05,
      "loss": 0.7386,
      "step": 63
    },
    {
      "epoch": 0.07470090458126641,
      "grad_norm": 0.29938921332359314,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.8411,
      "step": 64
    },
    {
      "epoch": 0.0758681062153487,
      "grad_norm": 0.31056711077690125,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8485,
      "step": 65
    },
    {
      "epoch": 0.077035307849431,
      "grad_norm": 0.28200721740722656,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.7076,
      "step": 66
    },
    {
      "epoch": 0.07820250948351327,
      "grad_norm": 0.28061196208000183,
      "learning_rate": 8.409991800312493e-05,
      "loss": 0.8166,
      "step": 67
    },
    {
      "epoch": 0.07936971111759557,
      "grad_norm": 0.29691019654273987,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.8025,
      "step": 68
    },
    {
      "epoch": 0.08053691275167785,
      "grad_norm": 0.27255597710609436,
      "learning_rate": 8.280295144952536e-05,
      "loss": 0.7291,
      "step": 69
    },
    {
      "epoch": 0.08170411438576014,
      "grad_norm": 0.2795017659664154,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.7686,
      "step": 70
    },
    {
      "epoch": 0.08287131601984243,
      "grad_norm": 0.324293851852417,
      "learning_rate": 8.146601955249188e-05,
      "loss": 0.9809,
      "step": 71
    },
    {
      "epoch": 0.08403851765392471,
      "grad_norm": 0.3070826232433319,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.8348,
      "step": 72
    },
    {
      "epoch": 0.085205719288007,
      "grad_norm": 0.31788310408592224,
      "learning_rate": 8.009075115760243e-05,
      "loss": 0.8517,
      "step": 73
    },
    {
      "epoch": 0.08637292092208929,
      "grad_norm": 0.32753679156303406,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8604,
      "step": 74
    },
    {
      "epoch": 0.08754012255617158,
      "grad_norm": 0.3178713321685791,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.8283,
      "step": 75
    },
    {
      "epoch": 0.08870732419025387,
      "grad_norm": 0.3042857348918915,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.8113,
      "step": 76
    },
    {
      "epoch": 0.08987452582433615,
      "grad_norm": 0.3086714446544647,
      "learning_rate": 7.723195175075136e-05,
      "loss": 0.775,
      "step": 77
    },
    {
      "epoch": 0.09104172745841844,
      "grad_norm": 0.337697297334671,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.8007,
      "step": 78
    },
    {
      "epoch": 0.09220892909250072,
      "grad_norm": 0.332986444234848,
      "learning_rate": 7.575190374550272e-05,
      "loss": 0.7799,
      "step": 79
    },
    {
      "epoch": 0.09337613072658302,
      "grad_norm": 0.3680335581302643,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8693,
      "step": 80
    },
    {
      "epoch": 0.09454333236066531,
      "grad_norm": 0.3400324881076813,
      "learning_rate": 7.424048101231686e-05,
      "loss": 0.8033,
      "step": 81
    },
    {
      "epoch": 0.09571053399474759,
      "grad_norm": 0.3480752110481262,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.8049,
      "step": 82
    },
    {
      "epoch": 0.09687773562882988,
      "grad_norm": 0.32390421628952026,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.8154,
      "step": 83
    },
    {
      "epoch": 0.09804493726291216,
      "grad_norm": 0.3939286768436432,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.8368,
      "step": 84
    },
    {
      "epoch": 0.09921213889699446,
      "grad_norm": 0.4093461036682129,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.825,
      "step": 85
    },
    {
      "epoch": 0.10037934053107675,
      "grad_norm": 0.3502061069011688,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.7531,
      "step": 86
    },
    {
      "epoch": 0.10154654216515903,
      "grad_norm": 0.4279065430164337,
      "learning_rate": 6.953655642446368e-05,
      "loss": 0.8631,
      "step": 87
    },
    {
      "epoch": 0.10271374379924132,
      "grad_norm": 0.389506995677948,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.905,
      "step": 88
    },
    {
      "epoch": 0.1038809454333236,
      "grad_norm": 0.353751540184021,
      "learning_rate": 6.7918397477265e-05,
      "loss": 0.8388,
      "step": 89
    },
    {
      "epoch": 0.1050481470674059,
      "grad_norm": 0.3757581114768982,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.7991,
      "step": 90
    },
    {
      "epoch": 0.10621534870148819,
      "grad_norm": 0.3809872567653656,
      "learning_rate": 6.627840772285784e-05,
      "loss": 0.8274,
      "step": 91
    },
    {
      "epoch": 0.10738255033557047,
      "grad_norm": 0.3491875231266022,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7432,
      "step": 92
    },
    {
      "epoch": 0.10854975196965276,
      "grad_norm": 0.30181223154067993,
      "learning_rate": 6.461858523613684e-05,
      "loss": 0.6283,
      "step": 93
    },
    {
      "epoch": 0.10971695360373504,
      "grad_norm": 0.31097540259361267,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.6898,
      "step": 94
    },
    {
      "epoch": 0.11088415523781733,
      "grad_norm": 0.3099660277366638,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.6467,
      "step": 95
    },
    {
      "epoch": 0.11205135687189963,
      "grad_norm": 0.2714497148990631,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.6564,
      "step": 96
    },
    {
      "epoch": 0.1132185585059819,
      "grad_norm": 0.2784051299095154,
      "learning_rate": 6.124755271719325e-05,
      "loss": 0.5751,
      "step": 97
    },
    {
      "epoch": 0.1143857601400642,
      "grad_norm": 0.2743142545223236,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.646,
      "step": 98
    },
    {
      "epoch": 0.11555296177414648,
      "grad_norm": 0.25440728664398193,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 0.552,
      "step": 99
    },
    {
      "epoch": 0.11672016340822877,
      "grad_norm": 0.31003862619400024,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.7203,
      "step": 100
    },
    {
      "epoch": 0.11672016340822877,
      "eval_loss": 0.7848469614982605,
      "eval_runtime": 132.5163,
      "eval_samples_per_second": 10.889,
      "eval_steps_per_second": 5.448,
      "step": 100
    },
    {
      "epoch": 0.11788736504231107,
      "grad_norm": 0.2813931107521057,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.903,
      "step": 101
    },
    {
      "epoch": 0.11905456667639334,
      "grad_norm": 0.28414005041122437,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.8748,
      "step": 102
    },
    {
      "epoch": 0.12022176831047564,
      "grad_norm": 0.2646597921848297,
      "learning_rate": 5.6093467170257374e-05,
      "loss": 0.8695,
      "step": 103
    },
    {
      "epoch": 0.12138896994455792,
      "grad_norm": 0.2558835744857788,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.8611,
      "step": 104
    },
    {
      "epoch": 0.12255617157864021,
      "grad_norm": 0.2555631101131439,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.7667,
      "step": 105
    },
    {
      "epoch": 0.1237233732127225,
      "grad_norm": 0.23551872372627258,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.8148,
      "step": 106
    },
    {
      "epoch": 0.12489057484680478,
      "grad_norm": 0.24096406996250153,
      "learning_rate": 5.26167978121472e-05,
      "loss": 0.9008,
      "step": 107
    },
    {
      "epoch": 0.12605777648088706,
      "grad_norm": 0.2395971566438675,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.8232,
      "step": 108
    },
    {
      "epoch": 0.12722497811496936,
      "grad_norm": 0.24123628437519073,
      "learning_rate": 5.0872620321864185e-05,
      "loss": 0.7684,
      "step": 109
    },
    {
      "epoch": 0.12839217974905165,
      "grad_norm": 0.24901266396045685,
      "learning_rate": 5e-05,
      "loss": 0.7346,
      "step": 110
    },
    {
      "epoch": 0.12955938138313394,
      "grad_norm": 0.26431071758270264,
      "learning_rate": 4.912737967813583e-05,
      "loss": 0.8108,
      "step": 111
    },
    {
      "epoch": 0.13072658301721624,
      "grad_norm": 0.2600049376487732,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.8016,
      "step": 112
    },
    {
      "epoch": 0.1318937846512985,
      "grad_norm": 0.2589147388935089,
      "learning_rate": 4.738320218785281e-05,
      "loss": 0.692,
      "step": 113
    },
    {
      "epoch": 0.1330609862853808,
      "grad_norm": 0.25345081090927124,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.7195,
      "step": 114
    },
    {
      "epoch": 0.1342281879194631,
      "grad_norm": 0.27083754539489746,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.764,
      "step": 115
    },
    {
      "epoch": 0.13539538955354538,
      "grad_norm": 0.2684639096260071,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.7806,
      "step": 116
    },
    {
      "epoch": 0.13656259118762767,
      "grad_norm": 0.26421883702278137,
      "learning_rate": 4.390653282974264e-05,
      "loss": 0.7648,
      "step": 117
    },
    {
      "epoch": 0.13772979282170994,
      "grad_norm": 0.2725983262062073,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.7857,
      "step": 118
    },
    {
      "epoch": 0.13889699445579223,
      "grad_norm": 0.2822451591491699,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.8243,
      "step": 119
    },
    {
      "epoch": 0.14006419608987453,
      "grad_norm": 0.2686375081539154,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.7614,
      "step": 120
    },
    {
      "epoch": 0.14123139772395682,
      "grad_norm": 0.28960907459259033,
      "learning_rate": 4.045955023117276e-05,
      "loss": 0.7475,
      "step": 121
    },
    {
      "epoch": 0.1423985993580391,
      "grad_norm": 0.30722492933273315,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.7529,
      "step": 122
    },
    {
      "epoch": 0.14356580099212138,
      "grad_norm": 0.317967027425766,
      "learning_rate": 3.875244728280676e-05,
      "loss": 0.8443,
      "step": 123
    },
    {
      "epoch": 0.14473300262620367,
      "grad_norm": 0.3088550269603729,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.8311,
      "step": 124
    },
    {
      "epoch": 0.14590020426028597,
      "grad_norm": 0.3324052393436432,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.8801,
      "step": 125
    },
    {
      "epoch": 0.14706740589436826,
      "grad_norm": 0.29917237162590027,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.8246,
      "step": 126
    },
    {
      "epoch": 0.14823460752845055,
      "grad_norm": 0.3261500597000122,
      "learning_rate": 3.5381414763863166e-05,
      "loss": 0.8245,
      "step": 127
    },
    {
      "epoch": 0.14940180916253282,
      "grad_norm": 0.32705891132354736,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8063,
      "step": 128
    },
    {
      "epoch": 0.1505690107966151,
      "grad_norm": 0.32474347949028015,
      "learning_rate": 3.372159227714218e-05,
      "loss": 0.7836,
      "step": 129
    },
    {
      "epoch": 0.1517362124306974,
      "grad_norm": 0.35860228538513184,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.8029,
      "step": 130
    },
    {
      "epoch": 0.1529034140647797,
      "grad_norm": 0.3252365291118622,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 0.8088,
      "step": 131
    },
    {
      "epoch": 0.154070615698862,
      "grad_norm": 0.3829883933067322,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.8673,
      "step": 132
    },
    {
      "epoch": 0.15523781733294426,
      "grad_norm": 0.3726121783256531,
      "learning_rate": 3.046344357553632e-05,
      "loss": 0.7388,
      "step": 133
    },
    {
      "epoch": 0.15640501896702655,
      "grad_norm": 0.3640628457069397,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.8213,
      "step": 134
    },
    {
      "epoch": 0.15757222060110884,
      "grad_norm": 0.4049950838088989,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.9175,
      "step": 135
    },
    {
      "epoch": 0.15873942223519114,
      "grad_norm": 0.4239923655986786,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.906,
      "step": 136
    },
    {
      "epoch": 0.15990662386927343,
      "grad_norm": 0.3672682046890259,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.8127,
      "step": 137
    },
    {
      "epoch": 0.1610738255033557,
      "grad_norm": 0.3689378798007965,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.867,
      "step": 138
    },
    {
      "epoch": 0.162241027137438,
      "grad_norm": 0.3810284435749054,
      "learning_rate": 2.575951898768315e-05,
      "loss": 0.839,
      "step": 139
    },
    {
      "epoch": 0.16340822877152028,
      "grad_norm": 0.4596632122993469,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.0415,
      "step": 140
    },
    {
      "epoch": 0.16457543040560257,
      "grad_norm": 0.35170069336891174,
      "learning_rate": 2.4248096254497288e-05,
      "loss": 0.7468,
      "step": 141
    },
    {
      "epoch": 0.16574263203968487,
      "grad_norm": 0.4190421402454376,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.7845,
      "step": 142
    },
    {
      "epoch": 0.16690983367376713,
      "grad_norm": 0.28160279989242554,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 0.684,
      "step": 143
    },
    {
      "epoch": 0.16807703530784943,
      "grad_norm": 0.28425997495651245,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.5931,
      "step": 144
    },
    {
      "epoch": 0.16924423694193172,
      "grad_norm": 0.24034002423286438,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.6104,
      "step": 145
    },
    {
      "epoch": 0.170411438576014,
      "grad_norm": 0.2798788845539093,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.5888,
      "step": 146
    },
    {
      "epoch": 0.1715786402100963,
      "grad_norm": 0.2780373692512512,
      "learning_rate": 1.9909248842397584e-05,
      "loss": 0.6114,
      "step": 147
    },
    {
      "epoch": 0.17274584184417857,
      "grad_norm": 0.2934766709804535,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.6771,
      "step": 148
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.2454727590084076,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 0.6322,
      "step": 149
    },
    {
      "epoch": 0.17508024511234316,
      "grad_norm": 0.3195655643939972,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.663,
      "step": 150
    },
    {
      "epoch": 0.17508024511234316,
      "eval_loss": 0.7762418389320374,
      "eval_runtime": 132.6232,
      "eval_samples_per_second": 10.88,
      "eval_steps_per_second": 5.444,
      "step": 150
    },
    {
      "epoch": 0.17624744674642545,
      "grad_norm": 2.268336296081543,
      "learning_rate": 1.7197048550474643e-05,
      "loss": 1.0756,
      "step": 151
    },
    {
      "epoch": 0.17741464838050774,
      "grad_norm": 0.3209622800350189,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.8104,
      "step": 152
    },
    {
      "epoch": 0.17858185001459,
      "grad_norm": 0.34762123227119446,
      "learning_rate": 1.5900081996875083e-05,
      "loss": 1.0414,
      "step": 153
    },
    {
      "epoch": 0.1797490516486723,
      "grad_norm": 0.29948487877845764,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.7971,
      "step": 154
    },
    {
      "epoch": 0.1809162532827546,
      "grad_norm": 0.28894099593162537,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.7501,
      "step": 155
    },
    {
      "epoch": 0.1820834549168369,
      "grad_norm": 0.29133960604667664,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.8022,
      "step": 156
    },
    {
      "epoch": 0.18325065655091918,
      "grad_norm": 0.2916227877140045,
      "learning_rate": 1.3432314919041478e-05,
      "loss": 0.8677,
      "step": 157
    },
    {
      "epoch": 0.18441785818500145,
      "grad_norm": 0.2980591356754303,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.8069,
      "step": 158
    },
    {
      "epoch": 0.18558505981908374,
      "grad_norm": 0.26787444949150085,
      "learning_rate": 1.22645209888614e-05,
      "loss": 0.8179,
      "step": 159
    },
    {
      "epoch": 0.18675226145316604,
      "grad_norm": 0.262446790933609,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.9099,
      "step": 160
    },
    {
      "epoch": 0.18791946308724833,
      "grad_norm": 0.26893505454063416,
      "learning_rate": 1.1142701927151456e-05,
      "loss": 0.7464,
      "step": 161
    },
    {
      "epoch": 0.18908666472133062,
      "grad_norm": 0.25039032101631165,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.7374,
      "step": 162
    },
    {
      "epoch": 0.1902538663554129,
      "grad_norm": 0.2451329231262207,
      "learning_rate": 1.006822449763537e-05,
      "loss": 0.7186,
      "step": 163
    },
    {
      "epoch": 0.19142106798949518,
      "grad_norm": 0.26940593123435974,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8439,
      "step": 164
    },
    {
      "epoch": 0.19258826962357747,
      "grad_norm": 0.26144108176231384,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.7798,
      "step": 165
    },
    {
      "epoch": 0.19375547125765977,
      "grad_norm": 0.26482659578323364,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.6827,
      "step": 166
    },
    {
      "epoch": 0.19492267289174206,
      "grad_norm": 0.2691318988800049,
      "learning_rate": 8.066471602728803e-06,
      "loss": 0.7502,
      "step": 167
    },
    {
      "epoch": 0.19608987452582433,
      "grad_norm": 0.30980005860328674,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.879,
      "step": 168
    },
    {
      "epoch": 0.19725707615990662,
      "grad_norm": 0.2952917814254761,
      "learning_rate": 7.1416349648943894e-06,
      "loss": 0.8698,
      "step": 169
    },
    {
      "epoch": 0.1984242777939889,
      "grad_norm": 0.29962897300720215,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.817,
      "step": 170
    },
    {
      "epoch": 0.1995914794280712,
      "grad_norm": 0.27048513293266296,
      "learning_rate": 6.269014643030213e-06,
      "loss": 0.7231,
      "step": 171
    },
    {
      "epoch": 0.2007586810621535,
      "grad_norm": 0.29043522477149963,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.8186,
      "step": 172
    },
    {
      "epoch": 0.20192588269623576,
      "grad_norm": 0.2933797240257263,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.8125,
      "step": 173
    },
    {
      "epoch": 0.20309308433031806,
      "grad_norm": 0.30532306432724,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.7502,
      "step": 174
    },
    {
      "epoch": 0.20426028596440035,
      "grad_norm": 0.319522500038147,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.8628,
      "step": 175
    },
    {
      "epoch": 0.20542748759848264,
      "grad_norm": 0.2974447011947632,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.8006,
      "step": 176
    },
    {
      "epoch": 0.20659468923256494,
      "grad_norm": 0.3108435571193695,
      "learning_rate": 3.974757327377981e-06,
      "loss": 0.74,
      "step": 177
    },
    {
      "epoch": 0.2077618908666472,
      "grad_norm": 0.3974533975124359,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.7976,
      "step": 178
    },
    {
      "epoch": 0.2089290925007295,
      "grad_norm": 0.3614056408405304,
      "learning_rate": 3.3209786751399187e-06,
      "loss": 0.8718,
      "step": 179
    },
    {
      "epoch": 0.2100962941348118,
      "grad_norm": 0.34091833233833313,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.7613,
      "step": 180
    },
    {
      "epoch": 0.21126349576889408,
      "grad_norm": 0.39933404326438904,
      "learning_rate": 2.724071220034158e-06,
      "loss": 0.7969,
      "step": 181
    },
    {
      "epoch": 0.21243069740297638,
      "grad_norm": 0.3371112644672394,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.8209,
      "step": 182
    },
    {
      "epoch": 0.21359789903705864,
      "grad_norm": 0.4095701575279236,
      "learning_rate": 2.1847622018482283e-06,
      "loss": 0.9561,
      "step": 183
    },
    {
      "epoch": 0.21476510067114093,
      "grad_norm": 0.36004993319511414,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.7986,
      "step": 184
    },
    {
      "epoch": 0.21593230230522323,
      "grad_norm": 0.3452329635620117,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.7562,
      "step": 185
    },
    {
      "epoch": 0.21709950393930552,
      "grad_norm": 0.411942720413208,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.8564,
      "step": 186
    },
    {
      "epoch": 0.21826670557338781,
      "grad_norm": 0.4416041374206543,
      "learning_rate": 1.2814967607382432e-06,
      "loss": 0.9108,
      "step": 187
    },
    {
      "epoch": 0.21943390720747008,
      "grad_norm": 0.37889963388442993,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.8114,
      "step": 188
    },
    {
      "epoch": 0.22060110884155237,
      "grad_norm": 0.4028225541114807,
      "learning_rate": 9.186408276168013e-07,
      "loss": 0.8,
      "step": 189
    },
    {
      "epoch": 0.22176831047563467,
      "grad_norm": 0.4361197352409363,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.8465,
      "step": 190
    },
    {
      "epoch": 0.22293551210971696,
      "grad_norm": 0.49626660346984863,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.8675,
      "step": 191
    },
    {
      "epoch": 0.22410271374379925,
      "grad_norm": 0.36257416009902954,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.7252,
      "step": 192
    },
    {
      "epoch": 0.22526991537788152,
      "grad_norm": 0.29285672307014465,
      "learning_rate": 3.7269241793390085e-07,
      "loss": 0.5469,
      "step": 193
    },
    {
      "epoch": 0.2264371170119638,
      "grad_norm": 0.2791464030742645,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.675,
      "step": 194
    },
    {
      "epoch": 0.2276043186460461,
      "grad_norm": 0.29202139377593994,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.6398,
      "step": 195
    },
    {
      "epoch": 0.2287715202801284,
      "grad_norm": 0.263590008020401,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.6208,
      "step": 196
    },
    {
      "epoch": 0.2299387219142107,
      "grad_norm": 0.2701646387577057,
      "learning_rate": 6.852326227130834e-08,
      "loss": 0.6671,
      "step": 197
    },
    {
      "epoch": 0.23110592354829296,
      "grad_norm": 0.26873281598091125,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.592,
      "step": 198
    },
    {
      "epoch": 0.23227312518237525,
      "grad_norm": 0.25243112444877625,
      "learning_rate": 7.615242180436522e-09,
      "loss": 0.5726,
      "step": 199
    },
    {
      "epoch": 0.23344032681645754,
      "grad_norm": 0.27846142649650574,
      "learning_rate": 0.0,
      "loss": 0.6234,
      "step": 200
    },
    {
      "epoch": 0.23344032681645754,
      "eval_loss": 0.7648534178733826,
      "eval_runtime": 132.5779,
      "eval_samples_per_second": 10.884,
      "eval_steps_per_second": 5.446,
      "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": 2.1369082990087373e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}