{
  "best_metric": 0.6189942359924316,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.05988472191032263,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002994236095516131,
      "grad_norm": 1.5001531839370728,
      "learning_rate": 1e-05,
      "loss": 0.7045,
      "step": 1
    },
    {
      "epoch": 0.0002994236095516131,
      "eval_loss": 2.051914691925049,
      "eval_runtime": 422.224,
      "eval_samples_per_second": 13.322,
      "eval_steps_per_second": 3.332,
      "step": 1
    },
    {
      "epoch": 0.0005988472191032262,
      "grad_norm": 3.2409021854400635,
      "learning_rate": 2e-05,
      "loss": 1.2576,
      "step": 2
    },
    {
      "epoch": 0.0008982708286548395,
      "grad_norm": 3.3385164737701416,
      "learning_rate": 3e-05,
      "loss": 1.4342,
      "step": 3
    },
    {
      "epoch": 0.0011976944382064525,
      "grad_norm": 2.5048654079437256,
      "learning_rate": 4e-05,
      "loss": 1.2126,
      "step": 4
    },
    {
      "epoch": 0.0014971180477580657,
      "grad_norm": 2.4707694053649902,
      "learning_rate": 5e-05,
      "loss": 1.2135,
      "step": 5
    },
    {
      "epoch": 0.001796541657309679,
      "grad_norm": 2.2355294227600098,
      "learning_rate": 6e-05,
      "loss": 1.0944,
      "step": 6
    },
    {
      "epoch": 0.002095965266861292,
      "grad_norm": 2.022751808166504,
      "learning_rate": 7e-05,
      "loss": 1.1788,
      "step": 7
    },
    {
      "epoch": 0.002395388876412905,
      "grad_norm": 2.8048019409179688,
      "learning_rate": 8e-05,
      "loss": 1.131,
      "step": 8
    },
    {
      "epoch": 0.002694812485964518,
      "grad_norm": 1.797947645187378,
      "learning_rate": 9e-05,
      "loss": 0.9426,
      "step": 9
    },
    {
      "epoch": 0.0029942360955161314,
      "grad_norm": 1.7996845245361328,
      "learning_rate": 0.0001,
      "loss": 0.9091,
      "step": 10
    },
    {
      "epoch": 0.0032936597050677446,
      "grad_norm": 1.6557872295379639,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.8645,
      "step": 11
    },
    {
      "epoch": 0.003593083314619358,
      "grad_norm": 1.6052519083023071,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.6948,
      "step": 12
    },
    {
      "epoch": 0.003892506924170971,
      "grad_norm": 1.2952603101730347,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.5823,
      "step": 13
    },
    {
      "epoch": 0.004191930533722584,
      "grad_norm": 1.463269829750061,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.6292,
      "step": 14
    },
    {
      "epoch": 0.0044913541432741975,
      "grad_norm": 1.466579556465149,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.7209,
      "step": 15
    },
    {
      "epoch": 0.00479077775282581,
      "grad_norm": 1.2136961221694946,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.639,
      "step": 16
    },
    {
      "epoch": 0.005090201362377423,
      "grad_norm": 1.3666551113128662,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.6686,
      "step": 17
    },
    {
      "epoch": 0.005389624971929036,
      "grad_norm": 1.357208490371704,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.6592,
      "step": 18
    },
    {
      "epoch": 0.00568904858148065,
      "grad_norm": 1.077374815940857,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.5465,
      "step": 19
    },
    {
      "epoch": 0.005988472191032263,
      "grad_norm": 1.1113899946212769,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6283,
      "step": 20
    },
    {
      "epoch": 0.006287895800583876,
      "grad_norm": 1.1577091217041016,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.6512,
      "step": 21
    },
    {
      "epoch": 0.006587319410135489,
      "grad_norm": 1.234321117401123,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.7452,
      "step": 22
    },
    {
      "epoch": 0.0068867430196871025,
      "grad_norm": 1.0721598863601685,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.5771,
      "step": 23
    },
    {
      "epoch": 0.007186166629238716,
      "grad_norm": 1.0589637756347656,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.5554,
      "step": 24
    },
    {
      "epoch": 0.007485590238790329,
      "grad_norm": 1.0572690963745117,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.6028,
      "step": 25
    },
    {
      "epoch": 0.007785013848341942,
      "grad_norm": 1.1369898319244385,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7004,
      "step": 26
    },
    {
      "epoch": 0.008084437457893555,
      "grad_norm": 1.2353670597076416,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.7781,
      "step": 27
    },
    {
      "epoch": 0.008383861067445169,
      "grad_norm": 1.228273868560791,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.6891,
      "step": 28
    },
    {
      "epoch": 0.008683284676996781,
      "grad_norm": 1.5415000915527344,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6284,
      "step": 29
    },
    {
      "epoch": 0.008982708286548395,
      "grad_norm": 1.2694517374038696,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7427,
      "step": 30
    },
    {
      "epoch": 0.009282131896100007,
      "grad_norm": 1.0838075876235962,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.6549,
      "step": 31
    },
    {
      "epoch": 0.00958155550565162,
      "grad_norm": 1.1120599508285522,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.5431,
      "step": 32
    },
    {
      "epoch": 0.009880979115203234,
      "grad_norm": 1.1518739461898804,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.5033,
      "step": 33
    },
    {
      "epoch": 0.010180402724754846,
      "grad_norm": 1.096585988998413,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.5161,
      "step": 34
    },
    {
      "epoch": 0.01047982633430646,
      "grad_norm": 1.4382801055908203,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.9635,
      "step": 35
    },
    {
      "epoch": 0.010779249943858073,
      "grad_norm": 1.3973444700241089,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.7488,
      "step": 36
    },
    {
      "epoch": 0.011078673553409687,
      "grad_norm": 1.7564913034439087,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.7366,
      "step": 37
    },
    {
      "epoch": 0.0113780971629613,
      "grad_norm": 2.130863666534424,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.9292,
      "step": 38
    },
    {
      "epoch": 0.011677520772512913,
      "grad_norm": 1.659516453742981,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.9802,
      "step": 39
    },
    {
      "epoch": 0.011976944382064526,
      "grad_norm": 1.8587124347686768,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.8617,
      "step": 40
    },
    {
      "epoch": 0.01227636799161614,
      "grad_norm": 1.5178453922271729,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.7172,
      "step": 41
    },
    {
      "epoch": 0.012575791601167752,
      "grad_norm": 2.470705270767212,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8211,
      "step": 42
    },
    {
      "epoch": 0.012875215210719364,
      "grad_norm": 1.578737497329712,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8244,
      "step": 43
    },
    {
      "epoch": 0.013174638820270979,
      "grad_norm": 3.1308135986328125,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7703,
      "step": 44
    },
    {
      "epoch": 0.013474062429822591,
      "grad_norm": 1.7756150960922241,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8427,
      "step": 45
    },
    {
      "epoch": 0.013773486039374205,
      "grad_norm": 2.1269168853759766,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7262,
      "step": 46
    },
    {
      "epoch": 0.014072909648925817,
      "grad_norm": 1.8117233514785767,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.722,
      "step": 47
    },
    {
      "epoch": 0.014372333258477431,
      "grad_norm": 2.315007448196411,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7214,
      "step": 48
    },
    {
      "epoch": 0.014671756868029044,
      "grad_norm": 2.204045057296753,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.5963,
      "step": 49
    },
    {
      "epoch": 0.014971180477580658,
      "grad_norm": 2.364506483078003,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7147,
      "step": 50
    },
    {
      "epoch": 0.014971180477580658,
      "eval_loss": 0.6820001602172852,
      "eval_runtime": 425.4327,
      "eval_samples_per_second": 13.222,
      "eval_steps_per_second": 3.307,
      "step": 50
    },
    {
      "epoch": 0.01527060408713227,
      "grad_norm": 0.49941274523735046,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.4138,
      "step": 51
    },
    {
      "epoch": 0.015570027696683884,
      "grad_norm": 0.8532990217208862,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.6634,
      "step": 52
    },
    {
      "epoch": 0.015869451306235495,
      "grad_norm": 0.7567525506019592,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.5103,
      "step": 53
    },
    {
      "epoch": 0.01616887491578711,
      "grad_norm": 0.830200731754303,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.5727,
      "step": 54
    },
    {
      "epoch": 0.016468298525338723,
      "grad_norm": 0.8407249450683594,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.5468,
      "step": 55
    },
    {
      "epoch": 0.016767722134890337,
      "grad_norm": 0.8793759346008301,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.6098,
      "step": 56
    },
    {
      "epoch": 0.017067145744441948,
      "grad_norm": 0.6687417030334473,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.4783,
      "step": 57
    },
    {
      "epoch": 0.017366569353993562,
      "grad_norm": 0.8845154643058777,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.6648,
      "step": 58
    },
    {
      "epoch": 0.017665992963545176,
      "grad_norm": 1.135591745376587,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.7689,
      "step": 59
    },
    {
      "epoch": 0.01796541657309679,
      "grad_norm": 0.9716898202896118,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.7,
      "step": 60
    },
    {
      "epoch": 0.0182648401826484,
      "grad_norm": 0.9164270162582397,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6189,
      "step": 61
    },
    {
      "epoch": 0.018564263792200015,
      "grad_norm": 0.9437540769577026,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.7042,
      "step": 62
    },
    {
      "epoch": 0.01886368740175163,
      "grad_norm": 0.8639401197433472,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.6033,
      "step": 63
    },
    {
      "epoch": 0.01916311101130324,
      "grad_norm": 0.9677025675773621,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.7053,
      "step": 64
    },
    {
      "epoch": 0.019462534620854854,
      "grad_norm": 0.7951339483261108,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.5071,
      "step": 65
    },
    {
      "epoch": 0.019761958230406468,
      "grad_norm": 0.8249769806861877,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.5557,
      "step": 66
    },
    {
      "epoch": 0.020061381839958082,
      "grad_norm": 0.8557410836219788,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6183,
      "step": 67
    },
    {
      "epoch": 0.020360805449509693,
      "grad_norm": 0.7307040691375732,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.5188,
      "step": 68
    },
    {
      "epoch": 0.020660229059061307,
      "grad_norm": 0.7995737791061401,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.5171,
      "step": 69
    },
    {
      "epoch": 0.02095965266861292,
      "grad_norm": 1.0233532190322876,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.6083,
      "step": 70
    },
    {
      "epoch": 0.021259076278164535,
      "grad_norm": 0.9353818297386169,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.6521,
      "step": 71
    },
    {
      "epoch": 0.021558499887716145,
      "grad_norm": 0.9416821599006653,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.6472,
      "step": 72
    },
    {
      "epoch": 0.02185792349726776,
      "grad_norm": 1.0074691772460938,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7213,
      "step": 73
    },
    {
      "epoch": 0.022157347106819374,
      "grad_norm": 0.9756485819816589,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.6098,
      "step": 74
    },
    {
      "epoch": 0.022456770716370984,
      "grad_norm": 1.0886120796203613,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.679,
      "step": 75
    },
    {
      "epoch": 0.0227561943259226,
      "grad_norm": 1.0123395919799805,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7678,
      "step": 76
    },
    {
      "epoch": 0.023055617935474212,
      "grad_norm": 0.8262513279914856,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.5881,
      "step": 77
    },
    {
      "epoch": 0.023355041545025827,
      "grad_norm": 1.0379709005355835,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.5532,
      "step": 78
    },
    {
      "epoch": 0.023654465154577437,
      "grad_norm": 1.0266590118408203,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7198,
      "step": 79
    },
    {
      "epoch": 0.02395388876412905,
      "grad_norm": 1.062197208404541,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.4714,
      "step": 80
    },
    {
      "epoch": 0.024253312373680665,
      "grad_norm": 0.997150719165802,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.5731,
      "step": 81
    },
    {
      "epoch": 0.02455273598323228,
      "grad_norm": 1.1995980739593506,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.8221,
      "step": 82
    },
    {
      "epoch": 0.02485215959278389,
      "grad_norm": 0.8821386098861694,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.4972,
      "step": 83
    },
    {
      "epoch": 0.025151583202335504,
      "grad_norm": 1.1449307203292847,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.6011,
      "step": 84
    },
    {
      "epoch": 0.02545100681188712,
      "grad_norm": 1.2733798027038574,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.6991,
      "step": 85
    },
    {
      "epoch": 0.02575043042143873,
      "grad_norm": 0.9108691215515137,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4796,
      "step": 86
    },
    {
      "epoch": 0.026049854030990343,
      "grad_norm": 1.111510157585144,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.5695,
      "step": 87
    },
    {
      "epoch": 0.026349277640541957,
      "grad_norm": 1.2187892198562622,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.741,
      "step": 88
    },
    {
      "epoch": 0.02664870125009357,
      "grad_norm": 1.1394623517990112,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.4894,
      "step": 89
    },
    {
      "epoch": 0.026948124859645182,
      "grad_norm": 1.1562232971191406,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.5802,
      "step": 90
    },
    {
      "epoch": 0.027247548469196796,
      "grad_norm": 1.6421946287155151,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.8678,
      "step": 91
    },
    {
      "epoch": 0.02754697207874841,
      "grad_norm": 1.4353466033935547,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7584,
      "step": 92
    },
    {
      "epoch": 0.027846395688300024,
      "grad_norm": 1.6679998636245728,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.685,
      "step": 93
    },
    {
      "epoch": 0.028145819297851635,
      "grad_norm": 2.0447373390197754,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.8782,
      "step": 94
    },
    {
      "epoch": 0.02844524290740325,
      "grad_norm": 1.5540831089019775,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6548,
      "step": 95
    },
    {
      "epoch": 0.028744666516954863,
      "grad_norm": 1.827242374420166,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.8822,
      "step": 96
    },
    {
      "epoch": 0.029044090126506474,
      "grad_norm": 1.7200450897216797,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7237,
      "step": 97
    },
    {
      "epoch": 0.029343513736058088,
      "grad_norm": 1.8981895446777344,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.5728,
      "step": 98
    },
    {
      "epoch": 0.0296429373456097,
      "grad_norm": 2.032804489135742,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.7954,
      "step": 99
    },
    {
      "epoch": 0.029942360955161316,
      "grad_norm": 2.4046475887298584,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.9076,
      "step": 100
    },
    {
      "epoch": 0.029942360955161316,
      "eval_loss": 0.6560322046279907,
      "eval_runtime": 425.2173,
      "eval_samples_per_second": 13.229,
      "eval_steps_per_second": 3.309,
      "step": 100
    },
    {
      "epoch": 0.030241784564712926,
      "grad_norm": 0.5754131078720093,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.4107,
      "step": 101
    },
    {
      "epoch": 0.03054120817426454,
      "grad_norm": 0.8198177218437195,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5759,
      "step": 102
    },
    {
      "epoch": 0.030840631783816155,
      "grad_norm": 0.8692825436592102,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.6836,
      "step": 103
    },
    {
      "epoch": 0.03114005539336777,
      "grad_norm": 0.9244077801704407,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.6715,
      "step": 104
    },
    {
      "epoch": 0.03143947900291938,
      "grad_norm": 0.7085159420967102,
      "learning_rate": 5e-05,
      "loss": 0.4922,
      "step": 105
    },
    {
      "epoch": 0.03173890261247099,
      "grad_norm": 0.8054493069648743,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.512,
      "step": 106
    },
    {
      "epoch": 0.03203832622202261,
      "grad_norm": 0.8640458583831787,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.6612,
      "step": 107
    },
    {
      "epoch": 0.03233774983157422,
      "grad_norm": 0.771088182926178,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.5367,
      "step": 108
    },
    {
      "epoch": 0.032637173441125836,
      "grad_norm": 0.7910268306732178,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.5723,
      "step": 109
    },
    {
      "epoch": 0.032936597050677446,
      "grad_norm": 0.7257114052772522,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.4949,
      "step": 110
    },
    {
      "epoch": 0.03323602066022906,
      "grad_norm": 1.22477126121521,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.5706,
      "step": 111
    },
    {
      "epoch": 0.033535444269780675,
      "grad_norm": 0.7681582570075989,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.5562,
      "step": 112
    },
    {
      "epoch": 0.033834867879332285,
      "grad_norm": 0.923491358757019,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.6285,
      "step": 113
    },
    {
      "epoch": 0.034134291488883896,
      "grad_norm": 0.7958170175552368,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.5698,
      "step": 114
    },
    {
      "epoch": 0.03443371509843551,
      "grad_norm": 0.9093762636184692,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.6797,
      "step": 115
    },
    {
      "epoch": 0.034733138707987124,
      "grad_norm": 0.7690200805664062,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.5806,
      "step": 116
    },
    {
      "epoch": 0.035032562317538735,
      "grad_norm": 0.8075854778289795,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.5311,
      "step": 117
    },
    {
      "epoch": 0.03533198592709035,
      "grad_norm": 0.9249498248100281,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.715,
      "step": 118
    },
    {
      "epoch": 0.03563140953664196,
      "grad_norm": 0.8106542825698853,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.5219,
      "step": 119
    },
    {
      "epoch": 0.03593083314619358,
      "grad_norm": 0.9355509281158447,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.6899,
      "step": 120
    },
    {
      "epoch": 0.03623025675574519,
      "grad_norm": 0.7863615155220032,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.4937,
      "step": 121
    },
    {
      "epoch": 0.0365296803652968,
      "grad_norm": 0.7703730463981628,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.5174,
      "step": 122
    },
    {
      "epoch": 0.03682910397484842,
      "grad_norm": 1.0717506408691406,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.79,
      "step": 123
    },
    {
      "epoch": 0.03712852758440003,
      "grad_norm": 0.8717485070228577,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.5848,
      "step": 124
    },
    {
      "epoch": 0.03742795119395164,
      "grad_norm": 0.8647756576538086,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.518,
      "step": 125
    },
    {
      "epoch": 0.03772737480350326,
      "grad_norm": 0.8701774477958679,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.6327,
      "step": 126
    },
    {
      "epoch": 0.03802679841305487,
      "grad_norm": 0.7016443014144897,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.4864,
      "step": 127
    },
    {
      "epoch": 0.03832622202260648,
      "grad_norm": 1.012001872062683,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.6002,
      "step": 128
    },
    {
      "epoch": 0.0386256456321581,
      "grad_norm": 0.9274682402610779,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.7767,
      "step": 129
    },
    {
      "epoch": 0.03892506924170971,
      "grad_norm": 0.8704296350479126,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.6129,
      "step": 130
    },
    {
      "epoch": 0.039224492851261325,
      "grad_norm": 0.7325119376182556,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.4274,
      "step": 131
    },
    {
      "epoch": 0.039523916460812936,
      "grad_norm": 1.1247433423995972,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.6026,
      "step": 132
    },
    {
      "epoch": 0.039823340070364546,
      "grad_norm": 0.9354616403579712,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7108,
      "step": 133
    },
    {
      "epoch": 0.040122763679916164,
      "grad_norm": 1.1834038496017456,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.6703,
      "step": 134
    },
    {
      "epoch": 0.040422187289467774,
      "grad_norm": 1.0683410167694092,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.6567,
      "step": 135
    },
    {
      "epoch": 0.040721610899019385,
      "grad_norm": 1.1029707193374634,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.6895,
      "step": 136
    },
    {
      "epoch": 0.041021034508571,
      "grad_norm": 1.0247859954833984,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.6219,
      "step": 137
    },
    {
      "epoch": 0.04132045811812261,
      "grad_norm": 0.9446123838424683,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.5425,
      "step": 138
    },
    {
      "epoch": 0.041619881727674224,
      "grad_norm": 1.3057301044464111,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.7612,
      "step": 139
    },
    {
      "epoch": 0.04191930533722584,
      "grad_norm": 1.2749944925308228,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.702,
      "step": 140
    },
    {
      "epoch": 0.04221872894677745,
      "grad_norm": 1.2318137884140015,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.604,
      "step": 141
    },
    {
      "epoch": 0.04251815255632907,
      "grad_norm": 1.245090126991272,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.5922,
      "step": 142
    },
    {
      "epoch": 0.04281757616588068,
      "grad_norm": 1.3600701093673706,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6315,
      "step": 143
    },
    {
      "epoch": 0.04311699977543229,
      "grad_norm": 1.9873156547546387,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.5642,
      "step": 144
    },
    {
      "epoch": 0.04341642338498391,
      "grad_norm": 1.6253494024276733,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7893,
      "step": 145
    },
    {
      "epoch": 0.04371584699453552,
      "grad_norm": 2.223517417907715,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.7117,
      "step": 146
    },
    {
      "epoch": 0.04401527060408713,
      "grad_norm": 1.4891387224197388,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.6886,
      "step": 147
    },
    {
      "epoch": 0.04431469421363875,
      "grad_norm": 1.8988481760025024,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.6511,
      "step": 148
    },
    {
      "epoch": 0.04461411782319036,
      "grad_norm": 1.9879004955291748,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6608,
      "step": 149
    },
    {
      "epoch": 0.04491354143274197,
      "grad_norm": 3.114546775817871,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.0648,
      "step": 150
    },
    {
      "epoch": 0.04491354143274197,
      "eval_loss": 0.62343829870224,
      "eval_runtime": 425.8771,
      "eval_samples_per_second": 13.208,
      "eval_steps_per_second": 3.304,
      "step": 150
    },
    {
      "epoch": 0.045212965042293586,
      "grad_norm": 0.43147456645965576,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.4138,
      "step": 151
    },
    {
      "epoch": 0.0455123886518452,
      "grad_norm": 0.7259081602096558,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.5588,
      "step": 152
    },
    {
      "epoch": 0.045811812261396814,
      "grad_norm": 0.7420914173126221,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.6171,
      "step": 153
    },
    {
      "epoch": 0.046111235870948425,
      "grad_norm": 0.7084308862686157,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.5414,
      "step": 154
    },
    {
      "epoch": 0.046410659480500036,
      "grad_norm": 0.7758296728134155,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.6016,
      "step": 155
    },
    {
      "epoch": 0.04671008309005165,
      "grad_norm": 0.8064884543418884,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.6663,
      "step": 156
    },
    {
      "epoch": 0.047009506699603264,
      "grad_norm": 0.702960193157196,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.5676,
      "step": 157
    },
    {
      "epoch": 0.047308930309154874,
      "grad_norm": 0.7341101169586182,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.6173,
      "step": 158
    },
    {
      "epoch": 0.04760835391870649,
      "grad_norm": 0.7270143032073975,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.572,
      "step": 159
    },
    {
      "epoch": 0.0479077775282581,
      "grad_norm": 0.8354920744895935,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.6034,
      "step": 160
    },
    {
      "epoch": 0.04820720113780971,
      "grad_norm": 0.7022597193717957,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.5522,
      "step": 161
    },
    {
      "epoch": 0.04850662474736133,
      "grad_norm": 0.8673229217529297,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.6279,
      "step": 162
    },
    {
      "epoch": 0.04880604835691294,
      "grad_norm": 0.6902653574943542,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.3885,
      "step": 163
    },
    {
      "epoch": 0.04910547196646456,
      "grad_norm": 0.8798882961273193,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.7099,
      "step": 164
    },
    {
      "epoch": 0.04940489557601617,
      "grad_norm": 0.8040981292724609,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.6171,
      "step": 165
    },
    {
      "epoch": 0.04970431918556778,
      "grad_norm": 0.9544451832771301,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.8003,
      "step": 166
    },
    {
      "epoch": 0.0500037427951194,
      "grad_norm": 0.732454776763916,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.4933,
      "step": 167
    },
    {
      "epoch": 0.05030316640467101,
      "grad_norm": 0.7949601411819458,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.5855,
      "step": 168
    },
    {
      "epoch": 0.05060259001422262,
      "grad_norm": 0.8372290730476379,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.575,
      "step": 169
    },
    {
      "epoch": 0.05090201362377424,
      "grad_norm": 0.767195463180542,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.5396,
      "step": 170
    },
    {
      "epoch": 0.05120143723332585,
      "grad_norm": 0.8188921213150024,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.5139,
      "step": 171
    },
    {
      "epoch": 0.05150086084287746,
      "grad_norm": 1.0281224250793457,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.7038,
      "step": 172
    },
    {
      "epoch": 0.051800284452429075,
      "grad_norm": 0.9781774878501892,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.5737,
      "step": 173
    },
    {
      "epoch": 0.052099708061980686,
      "grad_norm": 0.8292896747589111,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.4803,
      "step": 174
    },
    {
      "epoch": 0.052399131671532304,
      "grad_norm": 0.7253761291503906,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.4819,
      "step": 175
    },
    {
      "epoch": 0.052698555281083914,
      "grad_norm": 0.8768001794815063,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.6017,
      "step": 176
    },
    {
      "epoch": 0.052997978890635525,
      "grad_norm": 0.9723128080368042,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.564,
      "step": 177
    },
    {
      "epoch": 0.05329740250018714,
      "grad_norm": 0.8739854097366333,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.5993,
      "step": 178
    },
    {
      "epoch": 0.05359682610973875,
      "grad_norm": 0.9704213738441467,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.6152,
      "step": 179
    },
    {
      "epoch": 0.053896249719290364,
      "grad_norm": 0.8975372910499573,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.5783,
      "step": 180
    },
    {
      "epoch": 0.05419567332884198,
      "grad_norm": 0.8953799605369568,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.5749,
      "step": 181
    },
    {
      "epoch": 0.05449509693839359,
      "grad_norm": 0.9258882403373718,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.4968,
      "step": 182
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 2.0587058067321777,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.5865,
      "step": 183
    },
    {
      "epoch": 0.05509394415749682,
      "grad_norm": 0.9230641722679138,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.5685,
      "step": 184
    },
    {
      "epoch": 0.05539336776704843,
      "grad_norm": 0.9448370933532715,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.4236,
      "step": 185
    },
    {
      "epoch": 0.05569279137660005,
      "grad_norm": 0.9470467567443848,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.5651,
      "step": 186
    },
    {
      "epoch": 0.05599221498615166,
      "grad_norm": 1.1695692539215088,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.7204,
      "step": 187
    },
    {
      "epoch": 0.05629163859570327,
      "grad_norm": 1.2620238065719604,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6593,
      "step": 188
    },
    {
      "epoch": 0.05659106220525489,
      "grad_norm": 1.5011035203933716,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.6295,
      "step": 189
    },
    {
      "epoch": 0.0568904858148065,
      "grad_norm": 1.45396888256073,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.6497,
      "step": 190
    },
    {
      "epoch": 0.05718990942435811,
      "grad_norm": 1.3384662866592407,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.6432,
      "step": 191
    },
    {
      "epoch": 0.057489333033909726,
      "grad_norm": 1.5185068845748901,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.5154,
      "step": 192
    },
    {
      "epoch": 0.057788756643461336,
      "grad_norm": 1.317029356956482,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.6862,
      "step": 193
    },
    {
      "epoch": 0.05808818025301295,
      "grad_norm": 1.4526642560958862,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.6542,
      "step": 194
    },
    {
      "epoch": 0.058387603862564565,
      "grad_norm": 1.2908947467803955,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.6585,
      "step": 195
    },
    {
      "epoch": 0.058687027472116175,
      "grad_norm": 1.4427117109298706,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.5863,
      "step": 196
    },
    {
      "epoch": 0.05898645108166779,
      "grad_norm": 1.4706379175186157,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6085,
      "step": 197
    },
    {
      "epoch": 0.0592858746912194,
      "grad_norm": 2.0276565551757812,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.7309,
      "step": 198
    },
    {
      "epoch": 0.059585298300771014,
      "grad_norm": 1.7853847742080688,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.5928,
      "step": 199
    },
    {
      "epoch": 0.05988472191032263,
      "grad_norm": 3.0589098930358887,
      "learning_rate": 0.0,
      "loss": 0.7103,
      "step": 200
    },
    {
      "epoch": 0.05988472191032263,
      "eval_loss": 0.6189942359924316,
      "eval_runtime": 425.7069,
      "eval_samples_per_second": 13.213,
      "eval_steps_per_second": 3.305,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.0321122932791706e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}