{
  "best_metric": 0.2940025329589844,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.01893849723024478,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.46924861512239e-05,
      "grad_norm": 2.454827070236206,
      "learning_rate": 5e-06,
      "loss": 1.218,
      "step": 1
    },
    {
      "epoch": 9.46924861512239e-05,
      "eval_loss": 1.7879356145858765,
      "eval_runtime": 1373.1479,
      "eval_samples_per_second": 12.953,
      "eval_steps_per_second": 6.477,
      "step": 1
    },
    {
      "epoch": 0.0001893849723024478,
      "grad_norm": 3.4767465591430664,
      "learning_rate": 1e-05,
      "loss": 1.1959,
      "step": 2
    },
    {
      "epoch": 0.0002840774584536717,
      "grad_norm": 4.736673355102539,
      "learning_rate": 1.5e-05,
      "loss": 1.3324,
      "step": 3
    },
    {
      "epoch": 0.0003787699446048956,
      "grad_norm": 3.548912763595581,
      "learning_rate": 2e-05,
      "loss": 1.2875,
      "step": 4
    },
    {
      "epoch": 0.0004734624307561195,
      "grad_norm": 2.0464327335357666,
      "learning_rate": 2.5e-05,
      "loss": 1.1956,
      "step": 5
    },
    {
      "epoch": 0.0005681549169073434,
      "grad_norm": 2.3961620330810547,
      "learning_rate": 3e-05,
      "loss": 1.1326,
      "step": 6
    },
    {
      "epoch": 0.0006628474030585673,
      "grad_norm": 1.7311418056488037,
      "learning_rate": 3.5e-05,
      "loss": 1.1647,
      "step": 7
    },
    {
      "epoch": 0.0007575398892097912,
      "grad_norm": 2.298950433731079,
      "learning_rate": 4e-05,
      "loss": 1.1572,
      "step": 8
    },
    {
      "epoch": 0.0008522323753610151,
      "grad_norm": 1.7803407907485962,
      "learning_rate": 4.5e-05,
      "loss": 1.144,
      "step": 9
    },
    {
      "epoch": 0.000946924861512239,
      "grad_norm": 1.5894001722335815,
      "learning_rate": 5e-05,
      "loss": 0.9952,
      "step": 10
    },
    {
      "epoch": 0.0010416173476634628,
      "grad_norm": 1.2197067737579346,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.6901,
      "step": 11
    },
    {
      "epoch": 0.0011363098338146868,
      "grad_norm": 1.7695541381835938,
      "learning_rate": 6e-05,
      "loss": 0.779,
      "step": 12
    },
    {
      "epoch": 0.0012310023199659107,
      "grad_norm": 1.0885900259017944,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.7552,
      "step": 13
    },
    {
      "epoch": 0.0013256948061171345,
      "grad_norm": 1.3367475271224976,
      "learning_rate": 7e-05,
      "loss": 0.754,
      "step": 14
    },
    {
      "epoch": 0.0014203872922683586,
      "grad_norm": 2.406761407852173,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.6969,
      "step": 15
    },
    {
      "epoch": 0.0015150797784195824,
      "grad_norm": 2.8892931938171387,
      "learning_rate": 8e-05,
      "loss": 0.6946,
      "step": 16
    },
    {
      "epoch": 0.0016097722645708062,
      "grad_norm": 2.041106939315796,
      "learning_rate": 8.5e-05,
      "loss": 0.6596,
      "step": 17
    },
    {
      "epoch": 0.0017044647507220303,
      "grad_norm": 1.3814897537231445,
      "learning_rate": 9e-05,
      "loss": 0.5348,
      "step": 18
    },
    {
      "epoch": 0.001799157236873254,
      "grad_norm": 0.7577526569366455,
      "learning_rate": 9.5e-05,
      "loss": 0.4126,
      "step": 19
    },
    {
      "epoch": 0.001893849723024478,
      "grad_norm": 1.5962600708007812,
      "learning_rate": 0.0001,
      "loss": 0.5226,
      "step": 20
    },
    {
      "epoch": 0.0019885422091757018,
      "grad_norm": 0.854233980178833,
      "learning_rate": 9.999238475781957e-05,
      "loss": 0.4707,
      "step": 21
    },
    {
      "epoch": 0.0020832346953269256,
      "grad_norm": 0.9870491027832031,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.4483,
      "step": 22
    },
    {
      "epoch": 0.00217792718147815,
      "grad_norm": 1.0716090202331543,
      "learning_rate": 9.99314767377287e-05,
      "loss": 0.4955,
      "step": 23
    },
    {
      "epoch": 0.0022726196676293737,
      "grad_norm": 1.1506928205490112,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.5013,
      "step": 24
    },
    {
      "epoch": 0.0023673121537805975,
      "grad_norm": 0.9374679327011108,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.351,
      "step": 25
    },
    {
      "epoch": 0.0024620046399318214,
      "grad_norm": 1.4406720399856567,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.5091,
      "step": 26
    },
    {
      "epoch": 0.002556697126083045,
      "grad_norm": 0.7583168745040894,
      "learning_rate": 9.962730758206611e-05,
      "loss": 0.3653,
      "step": 27
    },
    {
      "epoch": 0.002651389612234269,
      "grad_norm": 0.706031322479248,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.4258,
      "step": 28
    },
    {
      "epoch": 0.0027460820983854933,
      "grad_norm": 0.5467961430549622,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.3124,
      "step": 29
    },
    {
      "epoch": 0.002840774584536717,
      "grad_norm": 1.217199444770813,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.482,
      "step": 30
    },
    {
      "epoch": 0.002935467070687941,
      "grad_norm": 0.8480075597763062,
      "learning_rate": 9.908135917238321e-05,
      "loss": 0.5182,
      "step": 31
    },
    {
      "epoch": 0.0030301595568391648,
      "grad_norm": 0.8619151711463928,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.3981,
      "step": 32
    },
    {
      "epoch": 0.0031248520429903886,
      "grad_norm": 0.684477686882019,
      "learning_rate": 9.871850323926177e-05,
      "loss": 0.3356,
      "step": 33
    },
    {
      "epoch": 0.0032195445291416124,
      "grad_norm": 0.6660991311073303,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.3082,
      "step": 34
    },
    {
      "epoch": 0.0033142370152928367,
      "grad_norm": 0.6820000410079956,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.2841,
      "step": 35
    },
    {
      "epoch": 0.0034089295014440605,
      "grad_norm": 1.5081778764724731,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.4676,
      "step": 36
    },
    {
      "epoch": 0.0035036219875952844,
      "grad_norm": 2.342919111251831,
      "learning_rate": 9.781523779815179e-05,
      "loss": 0.4332,
      "step": 37
    },
    {
      "epoch": 0.003598314473746508,
      "grad_norm": 0.7415688633918762,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.4409,
      "step": 38
    },
    {
      "epoch": 0.003693006959897732,
      "grad_norm": 0.5942909717559814,
      "learning_rate": 9.727592877996585e-05,
      "loss": 0.2993,
      "step": 39
    },
    {
      "epoch": 0.003787699446048956,
      "grad_norm": 0.581596851348877,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2952,
      "step": 40
    },
    {
      "epoch": 0.00388239193220018,
      "grad_norm": 0.924413800239563,
      "learning_rate": 9.667902132486009e-05,
      "loss": 0.3663,
      "step": 41
    },
    {
      "epoch": 0.0039770844183514035,
      "grad_norm": 0.7919589281082153,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.3553,
      "step": 42
    },
    {
      "epoch": 0.004071776904502627,
      "grad_norm": 0.5328347086906433,
      "learning_rate": 9.602524267262203e-05,
      "loss": 0.3145,
      "step": 43
    },
    {
      "epoch": 0.004166469390653851,
      "grad_norm": 0.7753825783729553,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.4335,
      "step": 44
    },
    {
      "epoch": 0.004261161876805076,
      "grad_norm": 0.8243319988250732,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.3628,
      "step": 45
    },
    {
      "epoch": 0.0043558543629563,
      "grad_norm": 0.6980270147323608,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.4811,
      "step": 46
    },
    {
      "epoch": 0.0044505468491075235,
      "grad_norm": 0.7640014290809631,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.3831,
      "step": 47
    },
    {
      "epoch": 0.004545239335258747,
      "grad_norm": 0.9565992951393127,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.437,
      "step": 48
    },
    {
      "epoch": 0.004639931821409971,
      "grad_norm": 0.6740021705627441,
      "learning_rate": 9.373098535696979e-05,
      "loss": 0.3222,
      "step": 49
    },
    {
      "epoch": 0.004734624307561195,
      "grad_norm": 1.1682296991348267,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.5101,
      "step": 50
    },
    {
      "epoch": 0.004734624307561195,
      "eval_loss": 0.3515163064002991,
      "eval_runtime": 1379.1591,
      "eval_samples_per_second": 12.897,
      "eval_steps_per_second": 6.449,
      "step": 50
    },
    {
      "epoch": 0.004829316793712419,
      "grad_norm": 0.6039596796035767,
      "learning_rate": 9.285836503510562e-05,
      "loss": 0.2464,
      "step": 51
    },
    {
      "epoch": 0.004924009279863643,
      "grad_norm": 0.7683883905410767,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.2204,
      "step": 52
    },
    {
      "epoch": 0.0050187017660148665,
      "grad_norm": 0.7136397361755371,
      "learning_rate": 9.193352839727121e-05,
      "loss": 0.3258,
      "step": 53
    },
    {
      "epoch": 0.00511339425216609,
      "grad_norm": 0.6061449646949768,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.3261,
      "step": 54
    },
    {
      "epoch": 0.005208086738317314,
      "grad_norm": 0.5305026769638062,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.4383,
      "step": 55
    },
    {
      "epoch": 0.005302779224468538,
      "grad_norm": 0.4076201319694519,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2777,
      "step": 56
    },
    {
      "epoch": 0.005397471710619763,
      "grad_norm": 0.4348657727241516,
      "learning_rate": 8.993177550236464e-05,
      "loss": 0.3071,
      "step": 57
    },
    {
      "epoch": 0.0054921641967709866,
      "grad_norm": 0.4837627708911896,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.2998,
      "step": 58
    },
    {
      "epoch": 0.00558685668292221,
      "grad_norm": 0.5451851487159729,
      "learning_rate": 8.885729807284856e-05,
      "loss": 0.3282,
      "step": 59
    },
    {
      "epoch": 0.005681549169073434,
      "grad_norm": 0.8234379291534424,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.3596,
      "step": 60
    },
    {
      "epoch": 0.005776241655224658,
      "grad_norm": 0.37643444538116455,
      "learning_rate": 8.773547901113862e-05,
      "loss": 0.2947,
      "step": 61
    },
    {
      "epoch": 0.005870934141375882,
      "grad_norm": 0.4549543261528015,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.4284,
      "step": 62
    },
    {
      "epoch": 0.005965626627527106,
      "grad_norm": 0.43117886781692505,
      "learning_rate": 8.656768508095853e-05,
      "loss": 0.3467,
      "step": 63
    },
    {
      "epoch": 0.0060603191136783295,
      "grad_norm": 0.5648695230484009,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.3844,
      "step": 64
    },
    {
      "epoch": 0.006155011599829553,
      "grad_norm": 0.3704398274421692,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.257,
      "step": 65
    },
    {
      "epoch": 0.006249704085980777,
      "grad_norm": 0.3764655292034149,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.3198,
      "step": 66
    },
    {
      "epoch": 0.006344396572132001,
      "grad_norm": 0.4212140738964081,
      "learning_rate": 8.409991800312493e-05,
      "loss": 0.2658,
      "step": 67
    },
    {
      "epoch": 0.006439089058283225,
      "grad_norm": 0.3406229615211487,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.2289,
      "step": 68
    },
    {
      "epoch": 0.006533781544434449,
      "grad_norm": 0.4278174340724945,
      "learning_rate": 8.280295144952536e-05,
      "loss": 0.3288,
      "step": 69
    },
    {
      "epoch": 0.006628474030585673,
      "grad_norm": 0.5700973868370056,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.3443,
      "step": 70
    },
    {
      "epoch": 0.006723166516736897,
      "grad_norm": 0.3512937128543854,
      "learning_rate": 8.146601955249188e-05,
      "loss": 0.2637,
      "step": 71
    },
    {
      "epoch": 0.006817859002888121,
      "grad_norm": 0.4744971990585327,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.3999,
      "step": 72
    },
    {
      "epoch": 0.006912551489039345,
      "grad_norm": 0.38957759737968445,
      "learning_rate": 8.009075115760243e-05,
      "loss": 0.3128,
      "step": 73
    },
    {
      "epoch": 0.007007243975190569,
      "grad_norm": 0.4311201274394989,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.3424,
      "step": 74
    },
    {
      "epoch": 0.0071019364613417926,
      "grad_norm": 0.42028185725212097,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.2738,
      "step": 75
    },
    {
      "epoch": 0.007196628947493016,
      "grad_norm": 0.8206042647361755,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.3201,
      "step": 76
    },
    {
      "epoch": 0.00729132143364424,
      "grad_norm": 0.5771775841712952,
      "learning_rate": 7.723195175075136e-05,
      "loss": 0.2649,
      "step": 77
    },
    {
      "epoch": 0.007386013919795464,
      "grad_norm": 0.5105963945388794,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.2409,
      "step": 78
    },
    {
      "epoch": 0.007480706405946688,
      "grad_norm": 0.6381076574325562,
      "learning_rate": 7.575190374550272e-05,
      "loss": 0.3571,
      "step": 79
    },
    {
      "epoch": 0.007575398892097912,
      "grad_norm": 0.6105549335479736,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.324,
      "step": 80
    },
    {
      "epoch": 0.0076700913782491355,
      "grad_norm": 0.5321648716926575,
      "learning_rate": 7.424048101231686e-05,
      "loss": 0.2994,
      "step": 81
    },
    {
      "epoch": 0.00776478386440036,
      "grad_norm": 0.5671144723892212,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.2814,
      "step": 82
    },
    {
      "epoch": 0.007859476350551583,
      "grad_norm": 0.46841391921043396,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.2263,
      "step": 83
    },
    {
      "epoch": 0.007954168836702807,
      "grad_norm": 0.5258737206459045,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.3163,
      "step": 84
    },
    {
      "epoch": 0.008048861322854031,
      "grad_norm": 0.5847420692443848,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.3243,
      "step": 85
    },
    {
      "epoch": 0.008143553809005255,
      "grad_norm": 0.3755183517932892,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.2863,
      "step": 86
    },
    {
      "epoch": 0.008238246295156479,
      "grad_norm": 0.5984253287315369,
      "learning_rate": 6.953655642446368e-05,
      "loss": 0.3218,
      "step": 87
    },
    {
      "epoch": 0.008332938781307702,
      "grad_norm": 0.8427244424819946,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.4936,
      "step": 88
    },
    {
      "epoch": 0.008427631267458928,
      "grad_norm": 0.5401929020881653,
      "learning_rate": 6.7918397477265e-05,
      "loss": 0.3244,
      "step": 89
    },
    {
      "epoch": 0.008522323753610152,
      "grad_norm": 0.5147351026535034,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.3014,
      "step": 90
    },
    {
      "epoch": 0.008617016239761376,
      "grad_norm": 0.9610792398452759,
      "learning_rate": 6.627840772285784e-05,
      "loss": 0.3499,
      "step": 91
    },
    {
      "epoch": 0.0087117087259126,
      "grad_norm": 0.5880213975906372,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3897,
      "step": 92
    },
    {
      "epoch": 0.008806401212063823,
      "grad_norm": 0.6239131689071655,
      "learning_rate": 6.461858523613684e-05,
      "loss": 0.3423,
      "step": 93
    },
    {
      "epoch": 0.008901093698215047,
      "grad_norm": 0.6501753926277161,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.2901,
      "step": 94
    },
    {
      "epoch": 0.008995786184366271,
      "grad_norm": 0.6097372174263,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.3358,
      "step": 95
    },
    {
      "epoch": 0.009090478670517495,
      "grad_norm": 0.48593440651893616,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.3299,
      "step": 96
    },
    {
      "epoch": 0.009185171156668719,
      "grad_norm": 0.5818943977355957,
      "learning_rate": 6.124755271719325e-05,
      "loss": 0.3705,
      "step": 97
    },
    {
      "epoch": 0.009279863642819942,
      "grad_norm": 0.5785600543022156,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.3194,
      "step": 98
    },
    {
      "epoch": 0.009374556128971166,
      "grad_norm": 0.5820888876914978,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 0.3804,
      "step": 99
    },
    {
      "epoch": 0.00946924861512239,
      "grad_norm": 0.8857993483543396,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.3766,
      "step": 100
    },
    {
      "epoch": 0.00946924861512239,
      "eval_loss": 0.3120051324367523,
      "eval_runtime": 1376.547,
      "eval_samples_per_second": 12.921,
      "eval_steps_per_second": 6.461,
      "step": 100
    },
    {
      "epoch": 0.009563941101273614,
      "grad_norm": 0.4451744258403778,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.2185,
      "step": 101
    },
    {
      "epoch": 0.009658633587424838,
      "grad_norm": 0.393392950296402,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.2326,
      "step": 102
    },
    {
      "epoch": 0.009753326073576062,
      "grad_norm": 0.3935139775276184,
      "learning_rate": 5.6093467170257374e-05,
      "loss": 0.2376,
      "step": 103
    },
    {
      "epoch": 0.009848018559727285,
      "grad_norm": 0.49239593744277954,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.3127,
      "step": 104
    },
    {
      "epoch": 0.00994271104587851,
      "grad_norm": 0.5239997506141663,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.4293,
      "step": 105
    },
    {
      "epoch": 0.010037403532029733,
      "grad_norm": 0.4456406831741333,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.3016,
      "step": 106
    },
    {
      "epoch": 0.010132096018180957,
      "grad_norm": 0.40427473187446594,
      "learning_rate": 5.26167978121472e-05,
      "loss": 0.186,
      "step": 107
    },
    {
      "epoch": 0.01022678850433218,
      "grad_norm": 0.32894396781921387,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.2442,
      "step": 108
    },
    {
      "epoch": 0.010321480990483405,
      "grad_norm": 0.4474416971206665,
      "learning_rate": 5.0872620321864185e-05,
      "loss": 0.2203,
      "step": 109
    },
    {
      "epoch": 0.010416173476634628,
      "grad_norm": 0.4535369873046875,
      "learning_rate": 5e-05,
      "loss": 0.329,
      "step": 110
    },
    {
      "epoch": 0.010510865962785852,
      "grad_norm": 0.566321074962616,
      "learning_rate": 4.912737967813583e-05,
      "loss": 0.3164,
      "step": 111
    },
    {
      "epoch": 0.010605558448937076,
      "grad_norm": 0.33763089776039124,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.2745,
      "step": 112
    },
    {
      "epoch": 0.0107002509350883,
      "grad_norm": 0.37318381667137146,
      "learning_rate": 4.738320218785281e-05,
      "loss": 0.2406,
      "step": 113
    },
    {
      "epoch": 0.010794943421239525,
      "grad_norm": 0.35014447569847107,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.2285,
      "step": 114
    },
    {
      "epoch": 0.01088963590739075,
      "grad_norm": 0.3987157642841339,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.2837,
      "step": 115
    },
    {
      "epoch": 0.010984328393541973,
      "grad_norm": 0.36429470777511597,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.2372,
      "step": 116
    },
    {
      "epoch": 0.011079020879693197,
      "grad_norm": 0.4331720769405365,
      "learning_rate": 4.390653282974264e-05,
      "loss": 0.3545,
      "step": 117
    },
    {
      "epoch": 0.01117371336584442,
      "grad_norm": 0.32597437500953674,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.2248,
      "step": 118
    },
    {
      "epoch": 0.011268405851995645,
      "grad_norm": 0.32949554920196533,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.2144,
      "step": 119
    },
    {
      "epoch": 0.011363098338146868,
      "grad_norm": 0.5105450749397278,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.4314,
      "step": 120
    },
    {
      "epoch": 0.011457790824298092,
      "grad_norm": 0.37223193049430847,
      "learning_rate": 4.045955023117276e-05,
      "loss": 0.2877,
      "step": 121
    },
    {
      "epoch": 0.011552483310449316,
      "grad_norm": 0.33164238929748535,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.2723,
      "step": 122
    },
    {
      "epoch": 0.01164717579660054,
      "grad_norm": 0.37629207968711853,
      "learning_rate": 3.875244728280676e-05,
      "loss": 0.2631,
      "step": 123
    },
    {
      "epoch": 0.011741868282751764,
      "grad_norm": 0.4204508364200592,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.2915,
      "step": 124
    },
    {
      "epoch": 0.011836560768902988,
      "grad_norm": 0.49447402358055115,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.3062,
      "step": 125
    },
    {
      "epoch": 0.011931253255054211,
      "grad_norm": 0.38985031843185425,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.3535,
      "step": 126
    },
    {
      "epoch": 0.012025945741205435,
      "grad_norm": 0.393546462059021,
      "learning_rate": 3.5381414763863166e-05,
      "loss": 0.3109,
      "step": 127
    },
    {
      "epoch": 0.012120638227356659,
      "grad_norm": 0.4812166690826416,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2909,
      "step": 128
    },
    {
      "epoch": 0.012215330713507883,
      "grad_norm": 0.4680134952068329,
      "learning_rate": 3.372159227714218e-05,
      "loss": 0.3586,
      "step": 129
    },
    {
      "epoch": 0.012310023199659107,
      "grad_norm": 0.30080264806747437,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.2044,
      "step": 130
    },
    {
      "epoch": 0.01240471568581033,
      "grad_norm": 0.3511880338191986,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 0.2577,
      "step": 131
    },
    {
      "epoch": 0.012499408171961554,
      "grad_norm": 0.482510507106781,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.3746,
      "step": 132
    },
    {
      "epoch": 0.012594100658112778,
      "grad_norm": 0.4897306263446808,
      "learning_rate": 3.046344357553632e-05,
      "loss": 0.2549,
      "step": 133
    },
    {
      "epoch": 0.012688793144264002,
      "grad_norm": 0.48270678520202637,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.2571,
      "step": 134
    },
    {
      "epoch": 0.012783485630415226,
      "grad_norm": 0.7660849094390869,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.3252,
      "step": 135
    },
    {
      "epoch": 0.01287817811656645,
      "grad_norm": 0.34716224670410156,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.2741,
      "step": 136
    },
    {
      "epoch": 0.012972870602717674,
      "grad_norm": 0.41306325793266296,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.2623,
      "step": 137
    },
    {
      "epoch": 0.013067563088868897,
      "grad_norm": 0.47318580746650696,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.309,
      "step": 138
    },
    {
      "epoch": 0.013162255575020123,
      "grad_norm": 0.537813663482666,
      "learning_rate": 2.575951898768315e-05,
      "loss": 0.3915,
      "step": 139
    },
    {
      "epoch": 0.013256948061171347,
      "grad_norm": 0.5747792720794678,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.3346,
      "step": 140
    },
    {
      "epoch": 0.01335164054732257,
      "grad_norm": 0.5642172694206238,
      "learning_rate": 2.4248096254497288e-05,
      "loss": 0.3576,
      "step": 141
    },
    {
      "epoch": 0.013446333033473794,
      "grad_norm": 0.725172758102417,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.4239,
      "step": 142
    },
    {
      "epoch": 0.013541025519625018,
      "grad_norm": 0.6283183097839355,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 0.3412,
      "step": 143
    },
    {
      "epoch": 0.013635718005776242,
      "grad_norm": 0.5846209526062012,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.3374,
      "step": 144
    },
    {
      "epoch": 0.013730410491927466,
      "grad_norm": 0.7421755194664001,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.3344,
      "step": 145
    },
    {
      "epoch": 0.01382510297807869,
      "grad_norm": 0.5736775994300842,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.215,
      "step": 146
    },
    {
      "epoch": 0.013919795464229914,
      "grad_norm": 0.5754392743110657,
      "learning_rate": 1.9909248842397584e-05,
      "loss": 0.2971,
      "step": 147
    },
    {
      "epoch": 0.014014487950381137,
      "grad_norm": 0.5859729051589966,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.3441,
      "step": 148
    },
    {
      "epoch": 0.014109180436532361,
      "grad_norm": 0.6326302886009216,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 0.3143,
      "step": 149
    },
    {
      "epoch": 0.014203872922683585,
      "grad_norm": 0.47283610701560974,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.3032,
      "step": 150
    },
    {
      "epoch": 0.014203872922683585,
      "eval_loss": 0.3101840913295746,
      "eval_runtime": 1378.4955,
      "eval_samples_per_second": 12.903,
      "eval_steps_per_second": 6.452,
      "step": 150
    },
    {
      "epoch": 0.014298565408834809,
      "grad_norm": 0.6273069381713867,
      "learning_rate": 1.7197048550474643e-05,
      "loss": 0.2193,
      "step": 151
    },
    {
      "epoch": 0.014393257894986033,
      "grad_norm": 0.5617712140083313,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.2056,
      "step": 152
    },
    {
      "epoch": 0.014487950381137257,
      "grad_norm": 0.7072075009346008,
      "learning_rate": 1.5900081996875083e-05,
      "loss": 0.3089,
      "step": 153
    },
    {
      "epoch": 0.01458264286728848,
      "grad_norm": 0.6112410426139832,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.2099,
      "step": 154
    },
    {
      "epoch": 0.014677335353439704,
      "grad_norm": 0.6010673642158508,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.4229,
      "step": 155
    },
    {
      "epoch": 0.014772027839590928,
      "grad_norm": 0.5914064049720764,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.1822,
      "step": 156
    },
    {
      "epoch": 0.014866720325742152,
      "grad_norm": 0.6139535307884216,
      "learning_rate": 1.3432314919041478e-05,
      "loss": 0.2749,
      "step": 157
    },
    {
      "epoch": 0.014961412811893376,
      "grad_norm": 0.4070436954498291,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.2948,
      "step": 158
    },
    {
      "epoch": 0.0150561052980446,
      "grad_norm": 0.5271391868591309,
      "learning_rate": 1.22645209888614e-05,
      "loss": 0.255,
      "step": 159
    },
    {
      "epoch": 0.015150797784195823,
      "grad_norm": 0.5544912219047546,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.3203,
      "step": 160
    },
    {
      "epoch": 0.015245490270347047,
      "grad_norm": 0.4444845914840698,
      "learning_rate": 1.1142701927151456e-05,
      "loss": 0.2705,
      "step": 161
    },
    {
      "epoch": 0.015340182756498271,
      "grad_norm": 0.3598558306694031,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.2842,
      "step": 162
    },
    {
      "epoch": 0.015434875242649495,
      "grad_norm": 0.42015647888183594,
      "learning_rate": 1.006822449763537e-05,
      "loss": 0.3233,
      "step": 163
    },
    {
      "epoch": 0.01552956772880072,
      "grad_norm": 0.33955568075180054,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2131,
      "step": 164
    },
    {
      "epoch": 0.015624260214951944,
      "grad_norm": 0.3296820819377899,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.2057,
      "step": 165
    },
    {
      "epoch": 0.015718952701103166,
      "grad_norm": 0.40896186232566833,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.2299,
      "step": 166
    },
    {
      "epoch": 0.01581364518725439,
      "grad_norm": 0.5911323428153992,
      "learning_rate": 8.066471602728803e-06,
      "loss": 0.2567,
      "step": 167
    },
    {
      "epoch": 0.015908337673405614,
      "grad_norm": 0.469912052154541,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.3262,
      "step": 168
    },
    {
      "epoch": 0.016003030159556838,
      "grad_norm": 0.3689268231391907,
      "learning_rate": 7.1416349648943894e-06,
      "loss": 0.3411,
      "step": 169
    },
    {
      "epoch": 0.016097722645708062,
      "grad_norm": 0.5381249189376831,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.3265,
      "step": 170
    },
    {
      "epoch": 0.016192415131859286,
      "grad_norm": 0.42854657769203186,
      "learning_rate": 6.269014643030213e-06,
      "loss": 0.26,
      "step": 171
    },
    {
      "epoch": 0.01628710761801051,
      "grad_norm": 0.4198633134365082,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.2319,
      "step": 172
    },
    {
      "epoch": 0.016381800104161733,
      "grad_norm": 0.7672091126441956,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.3694,
      "step": 173
    },
    {
      "epoch": 0.016476492590312957,
      "grad_norm": 0.4732285737991333,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.3039,
      "step": 174
    },
    {
      "epoch": 0.01657118507646418,
      "grad_norm": 0.3932953178882599,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.2077,
      "step": 175
    },
    {
      "epoch": 0.016665877562615405,
      "grad_norm": 0.42570826411247253,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.2604,
      "step": 176
    },
    {
      "epoch": 0.016760570048766632,
      "grad_norm": 0.583980143070221,
      "learning_rate": 3.974757327377981e-06,
      "loss": 0.4246,
      "step": 177
    },
    {
      "epoch": 0.016855262534917856,
      "grad_norm": 0.3952184021472931,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.3048,
      "step": 178
    },
    {
      "epoch": 0.01694995502106908,
      "grad_norm": 0.46545296907424927,
      "learning_rate": 3.3209786751399187e-06,
      "loss": 0.3136,
      "step": 179
    },
    {
      "epoch": 0.017044647507220304,
      "grad_norm": 0.5798347592353821,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.3032,
      "step": 180
    },
    {
      "epoch": 0.017139339993371527,
      "grad_norm": 0.4284912943840027,
      "learning_rate": 2.724071220034158e-06,
      "loss": 0.3,
      "step": 181
    },
    {
      "epoch": 0.01723403247952275,
      "grad_norm": 0.49665868282318115,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.384,
      "step": 182
    },
    {
      "epoch": 0.017328724965673975,
      "grad_norm": 0.4045867621898651,
      "learning_rate": 2.1847622018482283e-06,
      "loss": 0.2759,
      "step": 183
    },
    {
      "epoch": 0.0174234174518252,
      "grad_norm": 0.38050130009651184,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.2523,
      "step": 184
    },
    {
      "epoch": 0.017518109937976423,
      "grad_norm": 0.5833321213722229,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.2836,
      "step": 185
    },
    {
      "epoch": 0.017612802424127647,
      "grad_norm": 0.45387473702430725,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.2927,
      "step": 186
    },
    {
      "epoch": 0.01770749491027887,
      "grad_norm": 0.47009631991386414,
      "learning_rate": 1.2814967607382432e-06,
      "loss": 0.264,
      "step": 187
    },
    {
      "epoch": 0.017802187396430094,
      "grad_norm": 0.4835204482078552,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.1906,
      "step": 188
    },
    {
      "epoch": 0.017896879882581318,
      "grad_norm": 0.6437592506408691,
      "learning_rate": 9.186408276168013e-07,
      "loss": 0.331,
      "step": 189
    },
    {
      "epoch": 0.017991572368732542,
      "grad_norm": 0.5117820501327515,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.3278,
      "step": 190
    },
    {
      "epoch": 0.018086264854883766,
      "grad_norm": 0.5106391310691833,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.4103,
      "step": 191
    },
    {
      "epoch": 0.01818095734103499,
      "grad_norm": 0.5827416777610779,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.3457,
      "step": 192
    },
    {
      "epoch": 0.018275649827186213,
      "grad_norm": 0.40404656529426575,
      "learning_rate": 3.7269241793390085e-07,
      "loss": 0.3005,
      "step": 193
    },
    {
      "epoch": 0.018370342313337437,
      "grad_norm": 0.5825130939483643,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.429,
      "step": 194
    },
    {
      "epoch": 0.01846503479948866,
      "grad_norm": 0.7986671328544617,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.379,
      "step": 195
    },
    {
      "epoch": 0.018559727285639885,
      "grad_norm": 0.9346861839294434,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.4103,
      "step": 196
    },
    {
      "epoch": 0.01865441977179111,
      "grad_norm": 0.7575134634971619,
      "learning_rate": 6.852326227130834e-08,
      "loss": 0.2874,
      "step": 197
    },
    {
      "epoch": 0.018749112257942332,
      "grad_norm": 0.6524055600166321,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.4532,
      "step": 198
    },
    {
      "epoch": 0.018843804744093556,
      "grad_norm": 0.813246488571167,
      "learning_rate": 7.615242180436522e-09,
      "loss": 0.4367,
      "step": 199
    },
    {
      "epoch": 0.01893849723024478,
      "grad_norm": 0.8081971406936646,
      "learning_rate": 0.0,
      "loss": 0.3835,
      "step": 200
    },
    {
      "epoch": 0.01893849723024478,
      "eval_loss": 0.2940025329589844,
      "eval_runtime": 1376.3415,
      "eval_samples_per_second": 12.923,
      "eval_steps_per_second": 6.462,
      "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": 2.660991548522496e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}