{
  "best_metric": 0.3385751247406006,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.014178112538768276,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.089056269384139e-05,
      "grad_norm": 0.8523349165916443,
      "learning_rate": 1e-05,
      "loss": 0.7354,
      "step": 1
    },
    {
      "epoch": 7.089056269384139e-05,
      "eval_loss": 1.757895827293396,
      "eval_runtime": 1770.2655,
      "eval_samples_per_second": 13.421,
      "eval_steps_per_second": 3.355,
      "step": 1
    },
    {
      "epoch": 0.00014178112538768277,
      "grad_norm": 1.323467493057251,
      "learning_rate": 2e-05,
      "loss": 0.7794,
      "step": 2
    },
    {
      "epoch": 0.00021267168808152416,
      "grad_norm": 1.6836873292922974,
      "learning_rate": 3e-05,
      "loss": 0.9378,
      "step": 3
    },
    {
      "epoch": 0.00028356225077536554,
      "grad_norm": 1.7740553617477417,
      "learning_rate": 4e-05,
      "loss": 1.0128,
      "step": 4
    },
    {
      "epoch": 0.0003544528134692069,
      "grad_norm": 2.306671619415283,
      "learning_rate": 5e-05,
      "loss": 1.2748,
      "step": 5
    },
    {
      "epoch": 0.0004253433761630483,
      "grad_norm": 1.819011926651001,
      "learning_rate": 6e-05,
      "loss": 1.2096,
      "step": 6
    },
    {
      "epoch": 0.0004962339388568897,
      "grad_norm": 2.2308766841888428,
      "learning_rate": 7e-05,
      "loss": 1.3804,
      "step": 7
    },
    {
      "epoch": 0.0005671245015507311,
      "grad_norm": 1.9061588048934937,
      "learning_rate": 8e-05,
      "loss": 1.0324,
      "step": 8
    },
    {
      "epoch": 0.0006380150642445725,
      "grad_norm": 1.6470242738723755,
      "learning_rate": 9e-05,
      "loss": 0.8648,
      "step": 9
    },
    {
      "epoch": 0.0007089056269384139,
      "grad_norm": 1.5834276676177979,
      "learning_rate": 0.0001,
      "loss": 0.8482,
      "step": 10
    },
    {
      "epoch": 0.0007797961896322552,
      "grad_norm": 1.7377867698669434,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.7211,
      "step": 11
    },
    {
      "epoch": 0.0008506867523260966,
      "grad_norm": 1.5416024923324585,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.7497,
      "step": 12
    },
    {
      "epoch": 0.000921577315019938,
      "grad_norm": 1.1225073337554932,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.7273,
      "step": 13
    },
    {
      "epoch": 0.0009924678777137794,
      "grad_norm": 0.8795270323753357,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.5149,
      "step": 14
    },
    {
      "epoch": 0.0010633584404076207,
      "grad_norm": 0.7676340937614441,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.5692,
      "step": 15
    },
    {
      "epoch": 0.0011342490031014622,
      "grad_norm": 0.8031944632530212,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.5355,
      "step": 16
    },
    {
      "epoch": 0.0012051395657953034,
      "grad_norm": 0.8596481680870056,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.5862,
      "step": 17
    },
    {
      "epoch": 0.001276030128489145,
      "grad_norm": 0.7639876008033752,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.5911,
      "step": 18
    },
    {
      "epoch": 0.0013469206911829862,
      "grad_norm": 0.8159843683242798,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.5586,
      "step": 19
    },
    {
      "epoch": 0.0014178112538768277,
      "grad_norm": 0.7155534625053406,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.4336,
      "step": 20
    },
    {
      "epoch": 0.001488701816570669,
      "grad_norm": 0.7884729504585266,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.5175,
      "step": 21
    },
    {
      "epoch": 0.0015595923792645105,
      "grad_norm": 0.7705971598625183,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.497,
      "step": 22
    },
    {
      "epoch": 0.0016304829419583518,
      "grad_norm": 0.8776505589485168,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.5092,
      "step": 23
    },
    {
      "epoch": 0.0017013735046521932,
      "grad_norm": 0.775719940662384,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.4751,
      "step": 24
    },
    {
      "epoch": 0.0017722640673460345,
      "grad_norm": 0.7960324287414551,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4633,
      "step": 25
    },
    {
      "epoch": 0.001843154630039876,
      "grad_norm": 0.8504328727722168,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.4781,
      "step": 26
    },
    {
      "epoch": 0.0019140451927337173,
      "grad_norm": 0.79278165102005,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.4015,
      "step": 27
    },
    {
      "epoch": 0.001984935755427559,
      "grad_norm": 0.7221006155014038,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.4712,
      "step": 28
    },
    {
      "epoch": 0.0020558263181214,
      "grad_norm": 0.6746979355812073,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.3633,
      "step": 29
    },
    {
      "epoch": 0.0021267168808152413,
      "grad_norm": 0.7011294364929199,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.4035,
      "step": 30
    },
    {
      "epoch": 0.002197607443509083,
      "grad_norm": 0.9637427926063538,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.5063,
      "step": 31
    },
    {
      "epoch": 0.0022684980062029243,
      "grad_norm": 0.8260793685913086,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.4903,
      "step": 32
    },
    {
      "epoch": 0.0023393885688967656,
      "grad_norm": 0.8451759219169617,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.5101,
      "step": 33
    },
    {
      "epoch": 0.002410279131590607,
      "grad_norm": 0.9071231484413147,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.5358,
      "step": 34
    },
    {
      "epoch": 0.0024811696942844486,
      "grad_norm": 0.8283616900444031,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.4872,
      "step": 35
    },
    {
      "epoch": 0.00255206025697829,
      "grad_norm": 0.6727207899093628,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.3844,
      "step": 36
    },
    {
      "epoch": 0.002622950819672131,
      "grad_norm": 0.6684113144874573,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.4779,
      "step": 37
    },
    {
      "epoch": 0.0026938413823659724,
      "grad_norm": 0.6834886074066162,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.4227,
      "step": 38
    },
    {
      "epoch": 0.0027647319450598137,
      "grad_norm": 0.6929678916931152,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.3783,
      "step": 39
    },
    {
      "epoch": 0.0028356225077536554,
      "grad_norm": 0.8095279335975647,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.4663,
      "step": 40
    },
    {
      "epoch": 0.0029065130704474967,
      "grad_norm": 0.6838681697845459,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.4228,
      "step": 41
    },
    {
      "epoch": 0.002977403633141338,
      "grad_norm": 0.6704063415527344,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.424,
      "step": 42
    },
    {
      "epoch": 0.0030482941958351792,
      "grad_norm": 0.6688175201416016,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.4395,
      "step": 43
    },
    {
      "epoch": 0.003119184758529021,
      "grad_norm": 0.6819213032722473,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.409,
      "step": 44
    },
    {
      "epoch": 0.0031900753212228622,
      "grad_norm": 0.7437801957130432,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.424,
      "step": 45
    },
    {
      "epoch": 0.0032609658839167035,
      "grad_norm": 0.6554301977157593,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.415,
      "step": 46
    },
    {
      "epoch": 0.0033318564466105448,
      "grad_norm": 0.8241038918495178,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.5095,
      "step": 47
    },
    {
      "epoch": 0.0034027470093043865,
      "grad_norm": 0.6540892124176025,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4263,
      "step": 48
    },
    {
      "epoch": 0.0034736375719982278,
      "grad_norm": 0.6774754524230957,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.3218,
      "step": 49
    },
    {
      "epoch": 0.003544528134692069,
      "grad_norm": 0.8738925457000732,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.4777,
      "step": 50
    },
    {
      "epoch": 0.003544528134692069,
      "eval_loss": 0.44972315430641174,
      "eval_runtime": 1780.5046,
      "eval_samples_per_second": 13.343,
      "eval_steps_per_second": 3.336,
      "step": 50
    },
    {
      "epoch": 0.0036154186973859103,
      "grad_norm": 2.26267409324646,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.5829,
      "step": 51
    },
    {
      "epoch": 0.003686309260079752,
      "grad_norm": 1.55825674533844,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.3442,
      "step": 52
    },
    {
      "epoch": 0.0037571998227735933,
      "grad_norm": 0.7894648909568787,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.3763,
      "step": 53
    },
    {
      "epoch": 0.0038280903854674346,
      "grad_norm": 0.49781158566474915,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.3286,
      "step": 54
    },
    {
      "epoch": 0.003898980948161276,
      "grad_norm": 4.833137035369873,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.5205,
      "step": 55
    },
    {
      "epoch": 0.003969871510855118,
      "grad_norm": 0.6314643025398254,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.4451,
      "step": 56
    },
    {
      "epoch": 0.004040762073548958,
      "grad_norm": 0.5179358720779419,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.3937,
      "step": 57
    },
    {
      "epoch": 0.0041116526362428,
      "grad_norm": 0.5772222876548767,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.3653,
      "step": 58
    },
    {
      "epoch": 0.004182543198936642,
      "grad_norm": 0.5230809450149536,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.3794,
      "step": 59
    },
    {
      "epoch": 0.004253433761630483,
      "grad_norm": 0.5087058544158936,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.3957,
      "step": 60
    },
    {
      "epoch": 0.004324324324324324,
      "grad_norm": 0.4886504113674164,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.3961,
      "step": 61
    },
    {
      "epoch": 0.004395214887018166,
      "grad_norm": 0.47368374466896057,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.373,
      "step": 62
    },
    {
      "epoch": 0.004466105449712007,
      "grad_norm": 0.6237163543701172,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.3751,
      "step": 63
    },
    {
      "epoch": 0.004536996012405849,
      "grad_norm": 0.5442241430282593,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.4068,
      "step": 64
    },
    {
      "epoch": 0.0046078865750996895,
      "grad_norm": 0.6219522953033447,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.508,
      "step": 65
    },
    {
      "epoch": 0.004678777137793531,
      "grad_norm": 0.5011370778083801,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.2985,
      "step": 66
    },
    {
      "epoch": 0.004749667700487373,
      "grad_norm": 0.5422576069831848,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.3871,
      "step": 67
    },
    {
      "epoch": 0.004820558263181214,
      "grad_norm": 0.5588858127593994,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.4035,
      "step": 68
    },
    {
      "epoch": 0.0048914488258750555,
      "grad_norm": 0.5312881469726562,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3745,
      "step": 69
    },
    {
      "epoch": 0.004962339388568897,
      "grad_norm": 0.7475187182426453,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.5522,
      "step": 70
    },
    {
      "epoch": 0.005033229951262738,
      "grad_norm": 0.47773832082748413,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.3167,
      "step": 71
    },
    {
      "epoch": 0.00510412051395658,
      "grad_norm": 0.6200078129768372,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.4522,
      "step": 72
    },
    {
      "epoch": 0.005175011076650421,
      "grad_norm": 0.5681312680244446,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.3945,
      "step": 73
    },
    {
      "epoch": 0.005245901639344262,
      "grad_norm": 0.6025010943412781,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.3965,
      "step": 74
    },
    {
      "epoch": 0.005316792202038104,
      "grad_norm": 0.5036550760269165,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.3446,
      "step": 75
    },
    {
      "epoch": 0.005387682764731945,
      "grad_norm": 0.5747814774513245,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.3936,
      "step": 76
    },
    {
      "epoch": 0.0054585733274257866,
      "grad_norm": 0.6142371892929077,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.4408,
      "step": 77
    },
    {
      "epoch": 0.005529463890119627,
      "grad_norm": 0.5577287673950195,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.3285,
      "step": 78
    },
    {
      "epoch": 0.005600354452813469,
      "grad_norm": 0.5796722173690796,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.3367,
      "step": 79
    },
    {
      "epoch": 0.005671245015507311,
      "grad_norm": 0.5557568073272705,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.3138,
      "step": 80
    },
    {
      "epoch": 0.005742135578201152,
      "grad_norm": 0.5195022821426392,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.2951,
      "step": 81
    },
    {
      "epoch": 0.005813026140894993,
      "grad_norm": 0.565771222114563,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3469,
      "step": 82
    },
    {
      "epoch": 0.005883916703588835,
      "grad_norm": 0.707554817199707,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.3922,
      "step": 83
    },
    {
      "epoch": 0.005954807266282676,
      "grad_norm": 0.6795750856399536,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.4394,
      "step": 84
    },
    {
      "epoch": 0.006025697828976518,
      "grad_norm": 0.6365452408790588,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.4404,
      "step": 85
    },
    {
      "epoch": 0.0060965883916703585,
      "grad_norm": 0.6396660208702087,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3951,
      "step": 86
    },
    {
      "epoch": 0.0061674789543642,
      "grad_norm": 0.5342606902122498,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.3531,
      "step": 87
    },
    {
      "epoch": 0.006238369517058042,
      "grad_norm": 0.604596734046936,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.4086,
      "step": 88
    },
    {
      "epoch": 0.006309260079751883,
      "grad_norm": 0.5136443972587585,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.3438,
      "step": 89
    },
    {
      "epoch": 0.0063801506424457245,
      "grad_norm": 0.5856671929359436,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.3713,
      "step": 90
    },
    {
      "epoch": 0.006451041205139566,
      "grad_norm": 0.5504666566848755,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.3081,
      "step": 91
    },
    {
      "epoch": 0.006521931767833407,
      "grad_norm": 0.5364263653755188,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.3002,
      "step": 92
    },
    {
      "epoch": 0.006592822330527249,
      "grad_norm": 0.5979559421539307,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4272,
      "step": 93
    },
    {
      "epoch": 0.0066637128932210896,
      "grad_norm": 0.5369541645050049,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.371,
      "step": 94
    },
    {
      "epoch": 0.006734603455914931,
      "grad_norm": 0.7055835723876953,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.4687,
      "step": 95
    },
    {
      "epoch": 0.006805494018608773,
      "grad_norm": 0.6241551637649536,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.4236,
      "step": 96
    },
    {
      "epoch": 0.006876384581302614,
      "grad_norm": 0.6014761924743652,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.3931,
      "step": 97
    },
    {
      "epoch": 0.0069472751439964555,
      "grad_norm": 0.5446456670761108,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.376,
      "step": 98
    },
    {
      "epoch": 0.007018165706690297,
      "grad_norm": 0.5127068758010864,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.289,
      "step": 99
    },
    {
      "epoch": 0.007089056269384138,
      "grad_norm": 0.6141975522041321,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.4337,
      "step": 100
    },
    {
      "epoch": 0.007089056269384138,
      "eval_loss": 0.3743059039115906,
      "eval_runtime": 1778.6043,
      "eval_samples_per_second": 13.358,
      "eval_steps_per_second": 3.34,
      "step": 100
    },
    {
      "epoch": 0.00715994683207798,
      "grad_norm": 1.1645331382751465,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.4339,
      "step": 101
    },
    {
      "epoch": 0.007230837394771821,
      "grad_norm": 0.8213737607002258,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.2394,
      "step": 102
    },
    {
      "epoch": 0.007301727957465662,
      "grad_norm": 0.3668546676635742,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.2523,
      "step": 103
    },
    {
      "epoch": 0.007372618520159504,
      "grad_norm": 0.4842718243598938,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.2477,
      "step": 104
    },
    {
      "epoch": 0.007443509082853345,
      "grad_norm": 0.5160728693008423,
      "learning_rate": 5e-05,
      "loss": 0.3465,
      "step": 105
    },
    {
      "epoch": 0.007514399645547187,
      "grad_norm": 0.5961820483207703,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.4104,
      "step": 106
    },
    {
      "epoch": 0.007585290208241028,
      "grad_norm": 0.5189549326896667,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.3775,
      "step": 107
    },
    {
      "epoch": 0.007656180770934869,
      "grad_norm": 0.5054015517234802,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.3492,
      "step": 108
    },
    {
      "epoch": 0.007727071333628711,
      "grad_norm": 0.5176796317100525,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.4417,
      "step": 109
    },
    {
      "epoch": 0.007797961896322552,
      "grad_norm": 0.4752146005630493,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.3667,
      "step": 110
    },
    {
      "epoch": 0.007868852459016393,
      "grad_norm": 0.5429568290710449,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.4323,
      "step": 111
    },
    {
      "epoch": 0.007939743021710235,
      "grad_norm": 0.4606378972530365,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.4042,
      "step": 112
    },
    {
      "epoch": 0.008010633584404077,
      "grad_norm": 0.4609495997428894,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.3588,
      "step": 113
    },
    {
      "epoch": 0.008081524147097917,
      "grad_norm": 0.4024210572242737,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.2539,
      "step": 114
    },
    {
      "epoch": 0.008152414709791759,
      "grad_norm": 0.508936882019043,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.3056,
      "step": 115
    },
    {
      "epoch": 0.0082233052724856,
      "grad_norm": 0.4702116847038269,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.3446,
      "step": 116
    },
    {
      "epoch": 0.008294195835179442,
      "grad_norm": 0.48911041021347046,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.3549,
      "step": 117
    },
    {
      "epoch": 0.008365086397873284,
      "grad_norm": 0.47224682569503784,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.3649,
      "step": 118
    },
    {
      "epoch": 0.008435976960567124,
      "grad_norm": 0.5375878810882568,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.3898,
      "step": 119
    },
    {
      "epoch": 0.008506867523260965,
      "grad_norm": 0.5839834809303284,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.3996,
      "step": 120
    },
    {
      "epoch": 0.008577758085954807,
      "grad_norm": 0.5372905731201172,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.3944,
      "step": 121
    },
    {
      "epoch": 0.008648648648648649,
      "grad_norm": 0.5804446339607239,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.4677,
      "step": 122
    },
    {
      "epoch": 0.00871953921134249,
      "grad_norm": 0.6173442006111145,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.4097,
      "step": 123
    },
    {
      "epoch": 0.008790429774036332,
      "grad_norm": 0.5606793165206909,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.345,
      "step": 124
    },
    {
      "epoch": 0.008861320336730172,
      "grad_norm": 0.5558311939239502,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.3834,
      "step": 125
    },
    {
      "epoch": 0.008932210899424014,
      "grad_norm": 0.5951129794120789,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.3602,
      "step": 126
    },
    {
      "epoch": 0.009003101462117856,
      "grad_norm": 0.4856142997741699,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.3103,
      "step": 127
    },
    {
      "epoch": 0.009073992024811697,
      "grad_norm": 0.4996812343597412,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.3682,
      "step": 128
    },
    {
      "epoch": 0.009144882587505539,
      "grad_norm": 0.5909815430641174,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.4107,
      "step": 129
    },
    {
      "epoch": 0.009215773150199379,
      "grad_norm": 0.44087570905685425,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.3221,
      "step": 130
    },
    {
      "epoch": 0.00928666371289322,
      "grad_norm": 0.5540933609008789,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.3438,
      "step": 131
    },
    {
      "epoch": 0.009357554275587062,
      "grad_norm": 0.5242694616317749,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.2932,
      "step": 132
    },
    {
      "epoch": 0.009428444838280904,
      "grad_norm": 0.45764636993408203,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.244,
      "step": 133
    },
    {
      "epoch": 0.009499335400974746,
      "grad_norm": 0.5010474324226379,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.2954,
      "step": 134
    },
    {
      "epoch": 0.009570225963668586,
      "grad_norm": 0.6669395565986633,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.4188,
      "step": 135
    },
    {
      "epoch": 0.009641116526362428,
      "grad_norm": 0.5768990516662598,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.3828,
      "step": 136
    },
    {
      "epoch": 0.00971200708905627,
      "grad_norm": 0.5708727836608887,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.2528,
      "step": 137
    },
    {
      "epoch": 0.009782897651750111,
      "grad_norm": 0.644628643989563,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.3636,
      "step": 138
    },
    {
      "epoch": 0.009853788214443953,
      "grad_norm": 0.6101208329200745,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.346,
      "step": 139
    },
    {
      "epoch": 0.009924678777137794,
      "grad_norm": 0.5933841466903687,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.3744,
      "step": 140
    },
    {
      "epoch": 0.009995569339831634,
      "grad_norm": 0.6101102232933044,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.393,
      "step": 141
    },
    {
      "epoch": 0.010066459902525476,
      "grad_norm": 0.5287688374519348,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.3131,
      "step": 142
    },
    {
      "epoch": 0.010137350465219318,
      "grad_norm": 0.6600167155265808,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.37,
      "step": 143
    },
    {
      "epoch": 0.01020824102791316,
      "grad_norm": 0.5290716886520386,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.3381,
      "step": 144
    },
    {
      "epoch": 0.010279131590607001,
      "grad_norm": 0.5473757982254028,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.3352,
      "step": 145
    },
    {
      "epoch": 0.010350022153300841,
      "grad_norm": 0.5812906622886658,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.2937,
      "step": 146
    },
    {
      "epoch": 0.010420912715994683,
      "grad_norm": 0.5383227467536926,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.3403,
      "step": 147
    },
    {
      "epoch": 0.010491803278688525,
      "grad_norm": 0.5573107600212097,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.3672,
      "step": 148
    },
    {
      "epoch": 0.010562693841382366,
      "grad_norm": 0.5898846983909607,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.3701,
      "step": 149
    },
    {
      "epoch": 0.010633584404076208,
      "grad_norm": 0.6166815757751465,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.4691,
      "step": 150
    },
    {
      "epoch": 0.010633584404076208,
      "eval_loss": 0.35101068019866943,
      "eval_runtime": 1780.1453,
      "eval_samples_per_second": 13.346,
      "eval_steps_per_second": 3.337,
      "step": 150
    },
    {
      "epoch": 0.010704474966770048,
      "grad_norm": 1.2775356769561768,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.5215,
      "step": 151
    },
    {
      "epoch": 0.01077536552946389,
      "grad_norm": 1.6608169078826904,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.4586,
      "step": 152
    },
    {
      "epoch": 0.010846256092157731,
      "grad_norm": 0.9321173429489136,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.2503,
      "step": 153
    },
    {
      "epoch": 0.010917146654851573,
      "grad_norm": 0.22683802247047424,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.1947,
      "step": 154
    },
    {
      "epoch": 0.010988037217545415,
      "grad_norm": 0.5026242136955261,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.4189,
      "step": 155
    },
    {
      "epoch": 0.011058927780239255,
      "grad_norm": 0.5351672768592834,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.3454,
      "step": 156
    },
    {
      "epoch": 0.011129818342933097,
      "grad_norm": 0.4625988304615021,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.3385,
      "step": 157
    },
    {
      "epoch": 0.011200708905626938,
      "grad_norm": 0.47665536403656006,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.3369,
      "step": 158
    },
    {
      "epoch": 0.01127159946832078,
      "grad_norm": 0.45336824655532837,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.3144,
      "step": 159
    },
    {
      "epoch": 0.011342490031014622,
      "grad_norm": 0.5424633026123047,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.4535,
      "step": 160
    },
    {
      "epoch": 0.011413380593708463,
      "grad_norm": 0.5455241203308105,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.3757,
      "step": 161
    },
    {
      "epoch": 0.011484271156402303,
      "grad_norm": 0.44789063930511475,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.3254,
      "step": 162
    },
    {
      "epoch": 0.011555161719096145,
      "grad_norm": 0.5109904408454895,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.4503,
      "step": 163
    },
    {
      "epoch": 0.011626052281789987,
      "grad_norm": 0.49336186051368713,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.307,
      "step": 164
    },
    {
      "epoch": 0.011696942844483828,
      "grad_norm": 0.4530882239341736,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.3065,
      "step": 165
    },
    {
      "epoch": 0.01176783340717767,
      "grad_norm": 0.47018206119537354,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.344,
      "step": 166
    },
    {
      "epoch": 0.01183872396987151,
      "grad_norm": 0.5175123810768127,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.2736,
      "step": 167
    },
    {
      "epoch": 0.011909614532565352,
      "grad_norm": 0.4692923128604889,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.2944,
      "step": 168
    },
    {
      "epoch": 0.011980505095259194,
      "grad_norm": 0.5630585551261902,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.3187,
      "step": 169
    },
    {
      "epoch": 0.012051395657953035,
      "grad_norm": 0.5216619968414307,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.3036,
      "step": 170
    },
    {
      "epoch": 0.012122286220646877,
      "grad_norm": 0.6745107769966125,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.4632,
      "step": 171
    },
    {
      "epoch": 0.012193176783340717,
      "grad_norm": 0.4953429698944092,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.3427,
      "step": 172
    },
    {
      "epoch": 0.012264067346034559,
      "grad_norm": 0.5791112780570984,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.3428,
      "step": 173
    },
    {
      "epoch": 0.0123349579087284,
      "grad_norm": 0.4678581953048706,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.2533,
      "step": 174
    },
    {
      "epoch": 0.012405848471422242,
      "grad_norm": 0.5255546569824219,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.3473,
      "step": 175
    },
    {
      "epoch": 0.012476739034116084,
      "grad_norm": 0.5590485334396362,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.3772,
      "step": 176
    },
    {
      "epoch": 0.012547629596809926,
      "grad_norm": 0.5010048151016235,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.3034,
      "step": 177
    },
    {
      "epoch": 0.012618520159503765,
      "grad_norm": 0.5139868259429932,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.3668,
      "step": 178
    },
    {
      "epoch": 0.012689410722197607,
      "grad_norm": 0.5235176682472229,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.3343,
      "step": 179
    },
    {
      "epoch": 0.012760301284891449,
      "grad_norm": 0.5011683106422424,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.265,
      "step": 180
    },
    {
      "epoch": 0.01283119184758529,
      "grad_norm": 0.5358313322067261,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.329,
      "step": 181
    },
    {
      "epoch": 0.012902082410279132,
      "grad_norm": 0.5778741836547852,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.3384,
      "step": 182
    },
    {
      "epoch": 0.012972972972972972,
      "grad_norm": 0.6553307175636292,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.3791,
      "step": 183
    },
    {
      "epoch": 0.013043863535666814,
      "grad_norm": 0.5440935492515564,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.3068,
      "step": 184
    },
    {
      "epoch": 0.013114754098360656,
      "grad_norm": 0.6319936513900757,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.3238,
      "step": 185
    },
    {
      "epoch": 0.013185644661054497,
      "grad_norm": 0.6062104105949402,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.3742,
      "step": 186
    },
    {
      "epoch": 0.01325653522374834,
      "grad_norm": 0.5926635265350342,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.3504,
      "step": 187
    },
    {
      "epoch": 0.013327425786442179,
      "grad_norm": 0.6781738996505737,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.3701,
      "step": 188
    },
    {
      "epoch": 0.01339831634913602,
      "grad_norm": 0.5442988872528076,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.2929,
      "step": 189
    },
    {
      "epoch": 0.013469206911829863,
      "grad_norm": 0.6574541926383972,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.3655,
      "step": 190
    },
    {
      "epoch": 0.013540097474523704,
      "grad_norm": 0.5230603218078613,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.2877,
      "step": 191
    },
    {
      "epoch": 0.013610988037217546,
      "grad_norm": 0.6173690557479858,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.3354,
      "step": 192
    },
    {
      "epoch": 0.013681878599911386,
      "grad_norm": 0.5953249335289001,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.4004,
      "step": 193
    },
    {
      "epoch": 0.013752769162605228,
      "grad_norm": 0.5658497214317322,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.3764,
      "step": 194
    },
    {
      "epoch": 0.01382365972529907,
      "grad_norm": 0.5230283737182617,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.2946,
      "step": 195
    },
    {
      "epoch": 0.013894550287992911,
      "grad_norm": 0.6644552946090698,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.3506,
      "step": 196
    },
    {
      "epoch": 0.013965440850686753,
      "grad_norm": 0.6267344951629639,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.3829,
      "step": 197
    },
    {
      "epoch": 0.014036331413380594,
      "grad_norm": 0.5537121891975403,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.3182,
      "step": 198
    },
    {
      "epoch": 0.014107221976074434,
      "grad_norm": 0.6501596570014954,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.3424,
      "step": 199
    },
    {
      "epoch": 0.014178112538768276,
      "grad_norm": 0.692003607749939,
      "learning_rate": 0.0,
      "loss": 0.402,
      "step": 200
    },
    {
      "epoch": 0.014178112538768276,
      "eval_loss": 0.3385751247406006,
      "eval_runtime": 1779.6264,
      "eval_samples_per_second": 13.35,
      "eval_steps_per_second": 3.338,
      "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": 2.75545916964864e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}