{
  "best_metric": 0.7647904753684998,
  "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": 0.4645230174064636,
      "learning_rate": 5e-06,
      "loss": 1.3161,
      "step": 1
    },
    {
      "epoch": 0.0011672016340822876,
      "eval_loss": 1.2134394645690918,
      "eval_runtime": 129.7798,
      "eval_samples_per_second": 11.119,
      "eval_steps_per_second": 5.563,
      "step": 1
    },
    {
      "epoch": 0.0023344032681645753,
      "grad_norm": 0.5523867607116699,
      "learning_rate": 1e-05,
      "loss": 1.155,
      "step": 2
    },
    {
      "epoch": 0.0035016049022468633,
      "grad_norm": 0.6204341650009155,
      "learning_rate": 1.5e-05,
      "loss": 1.0916,
      "step": 3
    },
    {
      "epoch": 0.0046688065363291505,
      "grad_norm": 0.5389774441719055,
      "learning_rate": 2e-05,
      "loss": 1.1979,
      "step": 4
    },
    {
      "epoch": 0.005836008170411439,
      "grad_norm": 0.5569103956222534,
      "learning_rate": 2.5e-05,
      "loss": 1.1329,
      "step": 5
    },
    {
      "epoch": 0.007003209804493727,
      "grad_norm": 0.5306097865104675,
      "learning_rate": 3e-05,
      "loss": 1.0022,
      "step": 6
    },
    {
      "epoch": 0.008170411438576015,
      "grad_norm": 0.5503299832344055,
      "learning_rate": 3.5e-05,
      "loss": 1.1226,
      "step": 7
    },
    {
      "epoch": 0.009337613072658301,
      "grad_norm": 0.5780119299888611,
      "learning_rate": 4e-05,
      "loss": 1.0998,
      "step": 8
    },
    {
      "epoch": 0.01050481470674059,
      "grad_norm": 0.4954955577850342,
      "learning_rate": 4.5e-05,
      "loss": 1.0464,
      "step": 9
    },
    {
      "epoch": 0.011672016340822877,
      "grad_norm": 0.4273853003978729,
      "learning_rate": 5e-05,
      "loss": 0.9917,
      "step": 10
    },
    {
      "epoch": 0.012839217974905165,
      "grad_norm": 0.4458373785018921,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.0203,
      "step": 11
    },
    {
      "epoch": 0.014006419608987453,
      "grad_norm": 0.422532320022583,
      "learning_rate": 6e-05,
      "loss": 0.9054,
      "step": 12
    },
    {
      "epoch": 0.01517362124306974,
      "grad_norm": 0.466411828994751,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.9913,
      "step": 13
    },
    {
      "epoch": 0.01634082287715203,
      "grad_norm": 0.5178001523017883,
      "learning_rate": 7e-05,
      "loss": 1.0045,
      "step": 14
    },
    {
      "epoch": 0.017508024511234316,
      "grad_norm": 0.5916332602500916,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1295,
      "step": 15
    },
    {
      "epoch": 0.018675226145316602,
      "grad_norm": 0.5870257616043091,
      "learning_rate": 8e-05,
      "loss": 1.0357,
      "step": 16
    },
    {
      "epoch": 0.019842427779398892,
      "grad_norm": 0.6211600303649902,
      "learning_rate": 8.5e-05,
      "loss": 0.8712,
      "step": 17
    },
    {
      "epoch": 0.02100962941348118,
      "grad_norm": 0.5907412171363831,
      "learning_rate": 9e-05,
      "loss": 0.8706,
      "step": 18
    },
    {
      "epoch": 0.022176831047563468,
      "grad_norm": 0.6108558177947998,
      "learning_rate": 9.5e-05,
      "loss": 0.826,
      "step": 19
    },
    {
      "epoch": 0.023344032681645754,
      "grad_norm": 0.5364007949829102,
      "learning_rate": 0.0001,
      "loss": 0.8729,
      "step": 20
    },
    {
      "epoch": 0.02451123431572804,
      "grad_norm": 0.46780410408973694,
      "learning_rate": 9.999238475781957e-05,
      "loss": 0.8037,
      "step": 21
    },
    {
      "epoch": 0.02567843594981033,
      "grad_norm": 0.44036298990249634,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.8583,
      "step": 22
    },
    {
      "epoch": 0.026845637583892617,
      "grad_norm": 0.482135534286499,
      "learning_rate": 9.99314767377287e-05,
      "loss": 0.9498,
      "step": 23
    },
    {
      "epoch": 0.028012839217974907,
      "grad_norm": 0.433343768119812,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.7751,
      "step": 24
    },
    {
      "epoch": 0.029180040852057193,
      "grad_norm": 0.44726261496543884,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.8386,
      "step": 25
    },
    {
      "epoch": 0.03034724248613948,
      "grad_norm": 0.4052855968475342,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.9648,
      "step": 26
    },
    {
      "epoch": 0.031514444120221766,
      "grad_norm": 0.4005684554576874,
      "learning_rate": 9.962730758206611e-05,
      "loss": 0.8961,
      "step": 27
    },
    {
      "epoch": 0.03268164575430406,
      "grad_norm": 0.43962204456329346,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.9175,
      "step": 28
    },
    {
      "epoch": 0.033848847388386345,
      "grad_norm": 0.3778277039527893,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.8444,
      "step": 29
    },
    {
      "epoch": 0.03501604902246863,
      "grad_norm": 0.3987897038459778,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.8514,
      "step": 30
    },
    {
      "epoch": 0.03618325065655092,
      "grad_norm": 0.4220349192619324,
      "learning_rate": 9.908135917238321e-05,
      "loss": 0.8325,
      "step": 31
    },
    {
      "epoch": 0.037350452290633204,
      "grad_norm": 0.43536505103111267,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.9019,
      "step": 32
    },
    {
      "epoch": 0.0385176539247155,
      "grad_norm": 0.4588790535926819,
      "learning_rate": 9.871850323926177e-05,
      "loss": 0.8757,
      "step": 33
    },
    {
      "epoch": 0.039684855558797784,
      "grad_norm": 0.4669811427593231,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.7789,
      "step": 34
    },
    {
      "epoch": 0.04085205719288007,
      "grad_norm": 0.43914347887039185,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.9,
      "step": 35
    },
    {
      "epoch": 0.04201925882696236,
      "grad_norm": 0.4943505525588989,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.9662,
      "step": 36
    },
    {
      "epoch": 0.04318646046104464,
      "grad_norm": 0.47913798689842224,
      "learning_rate": 9.781523779815179e-05,
      "loss": 0.8431,
      "step": 37
    },
    {
      "epoch": 0.044353662095126936,
      "grad_norm": 0.5527225136756897,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8804,
      "step": 38
    },
    {
      "epoch": 0.04552086372920922,
      "grad_norm": 0.45204025506973267,
      "learning_rate": 9.727592877996585e-05,
      "loss": 0.8959,
      "step": 39
    },
    {
      "epoch": 0.04668806536329151,
      "grad_norm": 0.5248332619667053,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.77,
      "step": 40
    },
    {
      "epoch": 0.047855266997373795,
      "grad_norm": 0.4597388803958893,
      "learning_rate": 9.667902132486009e-05,
      "loss": 0.8016,
      "step": 41
    },
    {
      "epoch": 0.04902246863145608,
      "grad_norm": 0.42132359743118286,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.7668,
      "step": 42
    },
    {
      "epoch": 0.050189670265538375,
      "grad_norm": 0.333305299282074,
      "learning_rate": 9.602524267262203e-05,
      "loss": 0.6782,
      "step": 43
    },
    {
      "epoch": 0.05135687189962066,
      "grad_norm": 0.3380334973335266,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.651,
      "step": 44
    },
    {
      "epoch": 0.05252407353370295,
      "grad_norm": 0.31271177530288696,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.6561,
      "step": 45
    },
    {
      "epoch": 0.053691275167785234,
      "grad_norm": 0.32975664734840393,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.7163,
      "step": 46
    },
    {
      "epoch": 0.05485847680186752,
      "grad_norm": 0.34002843499183655,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.7353,
      "step": 47
    },
    {
      "epoch": 0.05602567843594981,
      "grad_norm": 0.2895605266094208,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.6177,
      "step": 48
    },
    {
      "epoch": 0.0571928800700321,
      "grad_norm": 0.29743078351020813,
      "learning_rate": 9.373098535696979e-05,
      "loss": 0.7147,
      "step": 49
    },
    {
      "epoch": 0.058360081704114386,
      "grad_norm": 0.32994723320007324,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.6151,
      "step": 50
    },
    {
      "epoch": 0.058360081704114386,
      "eval_loss": 0.8073924779891968,
      "eval_runtime": 131.3379,
      "eval_samples_per_second": 10.987,
      "eval_steps_per_second": 5.497,
      "step": 50
    },
    {
      "epoch": 0.05952728333819667,
      "grad_norm": 0.8547224402427673,
      "learning_rate": 9.285836503510562e-05,
      "loss": 1.1488,
      "step": 51
    },
    {
      "epoch": 0.06069448497227896,
      "grad_norm": 0.3317093551158905,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.8149,
      "step": 52
    },
    {
      "epoch": 0.06186168660636125,
      "grad_norm": 0.28299713134765625,
      "learning_rate": 9.193352839727121e-05,
      "loss": 0.8769,
      "step": 53
    },
    {
      "epoch": 0.06302888824044353,
      "grad_norm": 0.27979040145874023,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.8462,
      "step": 54
    },
    {
      "epoch": 0.06419608987452582,
      "grad_norm": 0.26757723093032837,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.9676,
      "step": 55
    },
    {
      "epoch": 0.06536329150860812,
      "grad_norm": 0.28088441491127014,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7332,
      "step": 56
    },
    {
      "epoch": 0.0665304931426904,
      "grad_norm": 0.2891692519187927,
      "learning_rate": 8.993177550236464e-05,
      "loss": 0.715,
      "step": 57
    },
    {
      "epoch": 0.06769769477677269,
      "grad_norm": 0.3234577775001526,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.7917,
      "step": 58
    },
    {
      "epoch": 0.06886489641085497,
      "grad_norm": 0.2690606415271759,
      "learning_rate": 8.885729807284856e-05,
      "loss": 0.7954,
      "step": 59
    },
    {
      "epoch": 0.07003209804493726,
      "grad_norm": 0.2573106288909912,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.7711,
      "step": 60
    },
    {
      "epoch": 0.07119929967901956,
      "grad_norm": 0.25576627254486084,
      "learning_rate": 8.773547901113862e-05,
      "loss": 0.7314,
      "step": 61
    },
    {
      "epoch": 0.07236650131310184,
      "grad_norm": 0.2450769990682602,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.6946,
      "step": 62
    },
    {
      "epoch": 0.07353370294718413,
      "grad_norm": 0.2636207640171051,
      "learning_rate": 8.656768508095853e-05,
      "loss": 0.7392,
      "step": 63
    },
    {
      "epoch": 0.07470090458126641,
      "grad_norm": 0.29346781969070435,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.8412,
      "step": 64
    },
    {
      "epoch": 0.0758681062153487,
      "grad_norm": 0.3023025095462799,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8481,
      "step": 65
    },
    {
      "epoch": 0.077035307849431,
      "grad_norm": 0.28165140748023987,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.7074,
      "step": 66
    },
    {
      "epoch": 0.07820250948351327,
      "grad_norm": 0.27901479601860046,
      "learning_rate": 8.409991800312493e-05,
      "loss": 0.8165,
      "step": 67
    },
    {
      "epoch": 0.07936971111759557,
      "grad_norm": 0.2872827351093292,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.8032,
      "step": 68
    },
    {
      "epoch": 0.08053691275167785,
      "grad_norm": 0.2825096845626831,
      "learning_rate": 8.280295144952536e-05,
      "loss": 0.7306,
      "step": 69
    },
    {
      "epoch": 0.08170411438576014,
      "grad_norm": 0.27829214930534363,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.7674,
      "step": 70
    },
    {
      "epoch": 0.08287131601984243,
      "grad_norm": 0.3277512490749359,
      "learning_rate": 8.146601955249188e-05,
      "loss": 0.9809,
      "step": 71
    },
    {
      "epoch": 0.08403851765392471,
      "grad_norm": 0.30526092648506165,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.8351,
      "step": 72
    },
    {
      "epoch": 0.085205719288007,
      "grad_norm": 0.3210103213787079,
      "learning_rate": 8.009075115760243e-05,
      "loss": 0.8512,
      "step": 73
    },
    {
      "epoch": 0.08637292092208929,
      "grad_norm": 0.3185954689979553,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8596,
      "step": 74
    },
    {
      "epoch": 0.08754012255617158,
      "grad_norm": 0.32168662548065186,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.8275,
      "step": 75
    },
    {
      "epoch": 0.08870732419025387,
      "grad_norm": 0.30243968963623047,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.8111,
      "step": 76
    },
    {
      "epoch": 0.08987452582433615,
      "grad_norm": 0.3073781132698059,
      "learning_rate": 7.723195175075136e-05,
      "loss": 0.774,
      "step": 77
    },
    {
      "epoch": 0.09104172745841844,
      "grad_norm": 0.33538374304771423,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.8025,
      "step": 78
    },
    {
      "epoch": 0.09220892909250072,
      "grad_norm": 0.32899773120880127,
      "learning_rate": 7.575190374550272e-05,
      "loss": 0.7792,
      "step": 79
    },
    {
      "epoch": 0.09337613072658302,
      "grad_norm": 0.353575199842453,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8698,
      "step": 80
    },
    {
      "epoch": 0.09454333236066531,
      "grad_norm": 0.3382454216480255,
      "learning_rate": 7.424048101231686e-05,
      "loss": 0.8027,
      "step": 81
    },
    {
      "epoch": 0.09571053399474759,
      "grad_norm": 0.3465535640716553,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.804,
      "step": 82
    },
    {
      "epoch": 0.09687773562882988,
      "grad_norm": 0.32555699348449707,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.8145,
      "step": 83
    },
    {
      "epoch": 0.09804493726291216,
      "grad_norm": 0.3700169622898102,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.8366,
      "step": 84
    },
    {
      "epoch": 0.09921213889699446,
      "grad_norm": 0.4031713604927063,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.8251,
      "step": 85
    },
    {
      "epoch": 0.10037934053107675,
      "grad_norm": 0.34600454568862915,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.7523,
      "step": 86
    },
    {
      "epoch": 0.10154654216515903,
      "grad_norm": 0.4239829182624817,
      "learning_rate": 6.953655642446368e-05,
      "loss": 0.8653,
      "step": 87
    },
    {
      "epoch": 0.10271374379924132,
      "grad_norm": 0.364509642124176,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.9048,
      "step": 88
    },
    {
      "epoch": 0.1038809454333236,
      "grad_norm": 0.3522888422012329,
      "learning_rate": 6.7918397477265e-05,
      "loss": 0.8411,
      "step": 89
    },
    {
      "epoch": 0.1050481470674059,
      "grad_norm": 0.3662375509738922,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.7989,
      "step": 90
    },
    {
      "epoch": 0.10621534870148819,
      "grad_norm": 0.3740469813346863,
      "learning_rate": 6.627840772285784e-05,
      "loss": 0.8273,
      "step": 91
    },
    {
      "epoch": 0.10738255033557047,
      "grad_norm": 0.34407129883766174,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7439,
      "step": 92
    },
    {
      "epoch": 0.10854975196965276,
      "grad_norm": 0.301419198513031,
      "learning_rate": 6.461858523613684e-05,
      "loss": 0.628,
      "step": 93
    },
    {
      "epoch": 0.10971695360373504,
      "grad_norm": 0.304275244474411,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.6889,
      "step": 94
    },
    {
      "epoch": 0.11088415523781733,
      "grad_norm": 0.3066118657588959,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.6458,
      "step": 95
    },
    {
      "epoch": 0.11205135687189963,
      "grad_norm": 0.26829689741134644,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.6544,
      "step": 96
    },
    {
      "epoch": 0.1132185585059819,
      "grad_norm": 0.2772735059261322,
      "learning_rate": 6.124755271719325e-05,
      "loss": 0.5729,
      "step": 97
    },
    {
      "epoch": 0.1143857601400642,
      "grad_norm": 0.27392178773880005,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.6469,
      "step": 98
    },
    {
      "epoch": 0.11555296177414648,
      "grad_norm": 0.25070396065711975,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 0.5527,
      "step": 99
    },
    {
      "epoch": 0.11672016340822877,
      "grad_norm": 0.3061893582344055,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.7178,
      "step": 100
    },
    {
      "epoch": 0.11672016340822877,
      "eval_loss": 0.7844517230987549,
      "eval_runtime": 131.5352,
      "eval_samples_per_second": 10.97,
      "eval_steps_per_second": 5.489,
      "step": 100
    },
    {
      "epoch": 0.11788736504231107,
      "grad_norm": 0.27881744503974915,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.9024,
      "step": 101
    },
    {
      "epoch": 0.11905456667639334,
      "grad_norm": 0.2848488688468933,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.8755,
      "step": 102
    },
    {
      "epoch": 0.12022176831047564,
      "grad_norm": 0.2713146507740021,
      "learning_rate": 5.6093467170257374e-05,
      "loss": 0.8695,
      "step": 103
    },
    {
      "epoch": 0.12138896994455792,
      "grad_norm": 0.25380441546440125,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.8603,
      "step": 104
    },
    {
      "epoch": 0.12255617157864021,
      "grad_norm": 0.2523921728134155,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.766,
      "step": 105
    },
    {
      "epoch": 0.1237233732127225,
      "grad_norm": 0.23555214703083038,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.8138,
      "step": 106
    },
    {
      "epoch": 0.12489057484680478,
      "grad_norm": 0.2412918657064438,
      "learning_rate": 5.26167978121472e-05,
      "loss": 0.9006,
      "step": 107
    },
    {
      "epoch": 0.12605777648088706,
      "grad_norm": 0.23593959212303162,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.8237,
      "step": 108
    },
    {
      "epoch": 0.12722497811496936,
      "grad_norm": 0.23072870075702667,
      "learning_rate": 5.0872620321864185e-05,
      "loss": 0.7662,
      "step": 109
    },
    {
      "epoch": 0.12839217974905165,
      "grad_norm": 0.24987874925136566,
      "learning_rate": 5e-05,
      "loss": 0.7334,
      "step": 110
    },
    {
      "epoch": 0.12955938138313394,
      "grad_norm": 0.2619277834892273,
      "learning_rate": 4.912737967813583e-05,
      "loss": 0.8111,
      "step": 111
    },
    {
      "epoch": 0.13072658301721624,
      "grad_norm": 0.25728732347488403,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.8008,
      "step": 112
    },
    {
      "epoch": 0.1318937846512985,
      "grad_norm": 0.2542027235031128,
      "learning_rate": 4.738320218785281e-05,
      "loss": 0.6894,
      "step": 113
    },
    {
      "epoch": 0.1330609862853808,
      "grad_norm": 0.25486239790916443,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.7197,
      "step": 114
    },
    {
      "epoch": 0.1342281879194631,
      "grad_norm": 0.2670009434223175,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.7636,
      "step": 115
    },
    {
      "epoch": 0.13539538955354538,
      "grad_norm": 0.27421027421951294,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.781,
      "step": 116
    },
    {
      "epoch": 0.13656259118762767,
      "grad_norm": 0.2642095386981964,
      "learning_rate": 4.390653282974264e-05,
      "loss": 0.7648,
      "step": 117
    },
    {
      "epoch": 0.13772979282170994,
      "grad_norm": 0.28716525435447693,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.7874,
      "step": 118
    },
    {
      "epoch": 0.13889699445579223,
      "grad_norm": 0.29199421405792236,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.8243,
      "step": 119
    },
    {
      "epoch": 0.14006419608987453,
      "grad_norm": 0.2674504518508911,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.7611,
      "step": 120
    },
    {
      "epoch": 0.14123139772395682,
      "grad_norm": 0.2917780876159668,
      "learning_rate": 4.045955023117276e-05,
      "loss": 0.7462,
      "step": 121
    },
    {
      "epoch": 0.1423985993580391,
      "grad_norm": 0.3149389624595642,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.754,
      "step": 122
    },
    {
      "epoch": 0.14356580099212138,
      "grad_norm": 0.3116993308067322,
      "learning_rate": 3.875244728280676e-05,
      "loss": 0.8438,
      "step": 123
    },
    {
      "epoch": 0.14473300262620367,
      "grad_norm": 0.3052745461463928,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.8313,
      "step": 124
    },
    {
      "epoch": 0.14590020426028597,
      "grad_norm": 0.3292216360569,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.8778,
      "step": 125
    },
    {
      "epoch": 0.14706740589436826,
      "grad_norm": 0.3010333478450775,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.8251,
      "step": 126
    },
    {
      "epoch": 0.14823460752845055,
      "grad_norm": 0.3386470675468445,
      "learning_rate": 3.5381414763863166e-05,
      "loss": 0.8236,
      "step": 127
    },
    {
      "epoch": 0.14940180916253282,
      "grad_norm": 0.33097153902053833,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8059,
      "step": 128
    },
    {
      "epoch": 0.1505690107966151,
      "grad_norm": 0.32120153307914734,
      "learning_rate": 3.372159227714218e-05,
      "loss": 0.7842,
      "step": 129
    },
    {
      "epoch": 0.1517362124306974,
      "grad_norm": 0.36916086077690125,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.8031,
      "step": 130
    },
    {
      "epoch": 0.1529034140647797,
      "grad_norm": 0.32527828216552734,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 0.8087,
      "step": 131
    },
    {
      "epoch": 0.154070615698862,
      "grad_norm": 0.3791372776031494,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.8672,
      "step": 132
    },
    {
      "epoch": 0.15523781733294426,
      "grad_norm": 0.3701271712779999,
      "learning_rate": 3.046344357553632e-05,
      "loss": 0.7371,
      "step": 133
    },
    {
      "epoch": 0.15640501896702655,
      "grad_norm": 0.3659634590148926,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.8235,
      "step": 134
    },
    {
      "epoch": 0.15757222060110884,
      "grad_norm": 0.4024992287158966,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.9173,
      "step": 135
    },
    {
      "epoch": 0.15873942223519114,
      "grad_norm": 0.42308032512664795,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.9053,
      "step": 136
    },
    {
      "epoch": 0.15990662386927343,
      "grad_norm": 0.40175530314445496,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.8113,
      "step": 137
    },
    {
      "epoch": 0.1610738255033557,
      "grad_norm": 0.36555033922195435,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.8684,
      "step": 138
    },
    {
      "epoch": 0.162241027137438,
      "grad_norm": 0.3812856078147888,
      "learning_rate": 2.575951898768315e-05,
      "loss": 0.8385,
      "step": 139
    },
    {
      "epoch": 0.16340822877152028,
      "grad_norm": 0.4847084879875183,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.0403,
      "step": 140
    },
    {
      "epoch": 0.16457543040560257,
      "grad_norm": 0.35007935762405396,
      "learning_rate": 2.4248096254497288e-05,
      "loss": 0.7455,
      "step": 141
    },
    {
      "epoch": 0.16574263203968487,
      "grad_norm": 0.41641098260879517,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.7863,
      "step": 142
    },
    {
      "epoch": 0.16690983367376713,
      "grad_norm": 0.27946096658706665,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 0.6836,
      "step": 143
    },
    {
      "epoch": 0.16807703530784943,
      "grad_norm": 0.2813800573348999,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.5916,
      "step": 144
    },
    {
      "epoch": 0.16924423694193172,
      "grad_norm": 0.24183239042758942,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.6092,
      "step": 145
    },
    {
      "epoch": 0.170411438576014,
      "grad_norm": 0.2797646224498749,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.5887,
      "step": 146
    },
    {
      "epoch": 0.1715786402100963,
      "grad_norm": 0.27872341871261597,
      "learning_rate": 1.9909248842397584e-05,
      "loss": 0.6105,
      "step": 147
    },
    {
      "epoch": 0.17274584184417857,
      "grad_norm": 0.2950071394443512,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.6768,
      "step": 148
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.24491213262081146,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 0.6329,
      "step": 149
    },
    {
      "epoch": 0.17508024511234316,
      "grad_norm": 0.3210446536540985,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.661,
      "step": 150
    },
    {
      "epoch": 0.17508024511234316,
      "eval_loss": 0.7759228944778442,
      "eval_runtime": 131.4518,
      "eval_samples_per_second": 10.977,
      "eval_steps_per_second": 5.493,
      "step": 150
    },
    {
      "epoch": 0.17624744674642545,
      "grad_norm": 2.9876537322998047,
      "learning_rate": 1.7197048550474643e-05,
      "loss": 1.0861,
      "step": 151
    },
    {
      "epoch": 0.17741464838050774,
      "grad_norm": 0.3166830539703369,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.8093,
      "step": 152
    },
    {
      "epoch": 0.17858185001459,
      "grad_norm": 0.3454245626926422,
      "learning_rate": 1.5900081996875083e-05,
      "loss": 1.0401,
      "step": 153
    },
    {
      "epoch": 0.1797490516486723,
      "grad_norm": 0.2986275255680084,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.7968,
      "step": 154
    },
    {
      "epoch": 0.1809162532827546,
      "grad_norm": 0.28862103819847107,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.7489,
      "step": 155
    },
    {
      "epoch": 0.1820834549168369,
      "grad_norm": 0.29491740465164185,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.8023,
      "step": 156
    },
    {
      "epoch": 0.18325065655091918,
      "grad_norm": 0.29212015867233276,
      "learning_rate": 1.3432314919041478e-05,
      "loss": 0.8676,
      "step": 157
    },
    {
      "epoch": 0.18441785818500145,
      "grad_norm": 0.2891896069049835,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.8065,
      "step": 158
    },
    {
      "epoch": 0.18558505981908374,
      "grad_norm": 0.2665817439556122,
      "learning_rate": 1.22645209888614e-05,
      "loss": 0.8174,
      "step": 159
    },
    {
      "epoch": 0.18675226145316604,
      "grad_norm": 0.26441434025764465,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.9098,
      "step": 160
    },
    {
      "epoch": 0.18791946308724833,
      "grad_norm": 0.2736872136592865,
      "learning_rate": 1.1142701927151456e-05,
      "loss": 0.7467,
      "step": 161
    },
    {
      "epoch": 0.18908666472133062,
      "grad_norm": 0.25108665227890015,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.7381,
      "step": 162
    },
    {
      "epoch": 0.1902538663554129,
      "grad_norm": 0.2441488355398178,
      "learning_rate": 1.006822449763537e-05,
      "loss": 0.7181,
      "step": 163
    },
    {
      "epoch": 0.19142106798949518,
      "grad_norm": 0.27161863446235657,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8432,
      "step": 164
    },
    {
      "epoch": 0.19258826962357747,
      "grad_norm": 0.2643083930015564,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.78,
      "step": 165
    },
    {
      "epoch": 0.19375547125765977,
      "grad_norm": 0.2586856484413147,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.6824,
      "step": 166
    },
    {
      "epoch": 0.19492267289174206,
      "grad_norm": 0.2640346884727478,
      "learning_rate": 8.066471602728803e-06,
      "loss": 0.7481,
      "step": 167
    },
    {
      "epoch": 0.19608987452582433,
      "grad_norm": 0.30174580216407776,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.8775,
      "step": 168
    },
    {
      "epoch": 0.19725707615990662,
      "grad_norm": 0.29615455865859985,
      "learning_rate": 7.1416349648943894e-06,
      "loss": 0.8692,
      "step": 169
    },
    {
      "epoch": 0.1984242777939889,
      "grad_norm": 0.2982340157032013,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.8168,
      "step": 170
    },
    {
      "epoch": 0.1995914794280712,
      "grad_norm": 0.26757344603538513,
      "learning_rate": 6.269014643030213e-06,
      "loss": 0.7225,
      "step": 171
    },
    {
      "epoch": 0.2007586810621535,
      "grad_norm": 0.29791203141212463,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.8185,
      "step": 172
    },
    {
      "epoch": 0.20192588269623576,
      "grad_norm": 0.28804895281791687,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.8119,
      "step": 173
    },
    {
      "epoch": 0.20309308433031806,
      "grad_norm": 0.3093741238117218,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.7504,
      "step": 174
    },
    {
      "epoch": 0.20426028596440035,
      "grad_norm": 0.3644060790538788,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.8599,
      "step": 175
    },
    {
      "epoch": 0.20542748759848264,
      "grad_norm": 0.2981199026107788,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.8009,
      "step": 176
    },
    {
      "epoch": 0.20659468923256494,
      "grad_norm": 0.31050100922584534,
      "learning_rate": 3.974757327377981e-06,
      "loss": 0.7389,
      "step": 177
    },
    {
      "epoch": 0.2077618908666472,
      "grad_norm": 0.36374491453170776,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.7974,
      "step": 178
    },
    {
      "epoch": 0.2089290925007295,
      "grad_norm": 0.35834863781929016,
      "learning_rate": 3.3209786751399187e-06,
      "loss": 0.8731,
      "step": 179
    },
    {
      "epoch": 0.2100962941348118,
      "grad_norm": 0.34159740805625916,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.7632,
      "step": 180
    },
    {
      "epoch": 0.21126349576889408,
      "grad_norm": 0.3954731225967407,
      "learning_rate": 2.724071220034158e-06,
      "loss": 0.7966,
      "step": 181
    },
    {
      "epoch": 0.21243069740297638,
      "grad_norm": 0.3321947455406189,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.8209,
      "step": 182
    },
    {
      "epoch": 0.21359789903705864,
      "grad_norm": 0.40751057863235474,
      "learning_rate": 2.1847622018482283e-06,
      "loss": 0.9554,
      "step": 183
    },
    {
      "epoch": 0.21476510067114093,
      "grad_norm": 0.3630269169807434,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.7975,
      "step": 184
    },
    {
      "epoch": 0.21593230230522323,
      "grad_norm": 0.3335731029510498,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.7557,
      "step": 185
    },
    {
      "epoch": 0.21709950393930552,
      "grad_norm": 0.41817012429237366,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.8555,
      "step": 186
    },
    {
      "epoch": 0.21826670557338781,
      "grad_norm": 0.44638216495513916,
      "learning_rate": 1.2814967607382432e-06,
      "loss": 0.9116,
      "step": 187
    },
    {
      "epoch": 0.21943390720747008,
      "grad_norm": 0.3788118064403534,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.8128,
      "step": 188
    },
    {
      "epoch": 0.22060110884155237,
      "grad_norm": 0.4116956293582916,
      "learning_rate": 9.186408276168013e-07,
      "loss": 0.7983,
      "step": 189
    },
    {
      "epoch": 0.22176831047563467,
      "grad_norm": 0.4356229305267334,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.8469,
      "step": 190
    },
    {
      "epoch": 0.22293551210971696,
      "grad_norm": 0.4859538972377777,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.8661,
      "step": 191
    },
    {
      "epoch": 0.22410271374379925,
      "grad_norm": 0.36541688442230225,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.7258,
      "step": 192
    },
    {
      "epoch": 0.22526991537788152,
      "grad_norm": 0.2873554527759552,
      "learning_rate": 3.7269241793390085e-07,
      "loss": 0.5465,
      "step": 193
    },
    {
      "epoch": 0.2264371170119638,
      "grad_norm": 0.2782743573188782,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.6742,
      "step": 194
    },
    {
      "epoch": 0.2276043186460461,
      "grad_norm": 0.2942681312561035,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.6396,
      "step": 195
    },
    {
      "epoch": 0.2287715202801284,
      "grad_norm": 0.2656351625919342,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.6217,
      "step": 196
    },
    {
      "epoch": 0.2299387219142107,
      "grad_norm": 0.2713199257850647,
      "learning_rate": 6.852326227130834e-08,
      "loss": 0.6669,
      "step": 197
    },
    {
      "epoch": 0.23110592354829296,
      "grad_norm": 0.26152923703193665,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.5913,
      "step": 198
    },
    {
      "epoch": 0.23227312518237525,
      "grad_norm": 0.252290815114975,
      "learning_rate": 7.615242180436522e-09,
      "loss": 0.5732,
      "step": 199
    },
    {
      "epoch": 0.23344032681645754,
      "grad_norm": 0.2770606279373169,
      "learning_rate": 0.0,
      "loss": 0.623,
      "step": 200
    },
    {
      "epoch": 0.23344032681645754,
      "eval_loss": 0.7647904753684998,
      "eval_runtime": 131.3901,
      "eval_samples_per_second": 10.983,
      "eval_steps_per_second": 5.495,
      "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
}