{
  "best_metric": 4.439182758331299,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.012829353560947448,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.414676780473723e-05,
      "grad_norm": 1.6949574947357178,
      "learning_rate": 1e-05,
      "loss": 4.7768,
      "step": 1
    },
    {
      "epoch": 6.414676780473723e-05,
      "eval_loss": 5.596181392669678,
      "eval_runtime": 176.0356,
      "eval_samples_per_second": 149.152,
      "eval_steps_per_second": 37.288,
      "step": 1
    },
    {
      "epoch": 0.00012829353560947447,
      "grad_norm": 1.771706461906433,
      "learning_rate": 2e-05,
      "loss": 4.9218,
      "step": 2
    },
    {
      "epoch": 0.00019244030341421172,
      "grad_norm": 1.7616764307022095,
      "learning_rate": 3e-05,
      "loss": 4.8478,
      "step": 3
    },
    {
      "epoch": 0.00025658707121894894,
      "grad_norm": 1.7342147827148438,
      "learning_rate": 4e-05,
      "loss": 4.7419,
      "step": 4
    },
    {
      "epoch": 0.0003207338390236862,
      "grad_norm": 1.7335240840911865,
      "learning_rate": 5e-05,
      "loss": 4.976,
      "step": 5
    },
    {
      "epoch": 0.00038488060682842344,
      "grad_norm": 1.653656244277954,
      "learning_rate": 6e-05,
      "loss": 4.8041,
      "step": 6
    },
    {
      "epoch": 0.00044902737463316066,
      "grad_norm": 1.5152570009231567,
      "learning_rate": 7e-05,
      "loss": 4.9678,
      "step": 7
    },
    {
      "epoch": 0.0005131741424378979,
      "grad_norm": 1.231866478919983,
      "learning_rate": 8e-05,
      "loss": 4.8507,
      "step": 8
    },
    {
      "epoch": 0.0005773209102426352,
      "grad_norm": 1.267978310585022,
      "learning_rate": 9e-05,
      "loss": 4.8317,
      "step": 9
    },
    {
      "epoch": 0.0006414676780473724,
      "grad_norm": 1.1831883192062378,
      "learning_rate": 0.0001,
      "loss": 4.7916,
      "step": 10
    },
    {
      "epoch": 0.0007056144458521096,
      "grad_norm": 1.2578078508377075,
      "learning_rate": 9.999316524962345e-05,
      "loss": 4.843,
      "step": 11
    },
    {
      "epoch": 0.0007697612136568469,
      "grad_norm": 1.1221117973327637,
      "learning_rate": 9.997266286704631e-05,
      "loss": 4.6396,
      "step": 12
    },
    {
      "epoch": 0.0008339079814615841,
      "grad_norm": 1.0888439416885376,
      "learning_rate": 9.993849845741524e-05,
      "loss": 4.7944,
      "step": 13
    },
    {
      "epoch": 0.0008980547492663213,
      "grad_norm": 0.9830743670463562,
      "learning_rate": 9.989068136093873e-05,
      "loss": 4.8084,
      "step": 14
    },
    {
      "epoch": 0.0009622015170710586,
      "grad_norm": 1.1008315086364746,
      "learning_rate": 9.98292246503335e-05,
      "loss": 4.7347,
      "step": 15
    },
    {
      "epoch": 0.0010263482848757958,
      "grad_norm": 1.0735920667648315,
      "learning_rate": 9.975414512725057e-05,
      "loss": 4.6635,
      "step": 16
    },
    {
      "epoch": 0.001090495052680533,
      "grad_norm": 1.0329375267028809,
      "learning_rate": 9.966546331768191e-05,
      "loss": 4.6962,
      "step": 17
    },
    {
      "epoch": 0.0011546418204852703,
      "grad_norm": 1.0670247077941895,
      "learning_rate": 9.956320346634876e-05,
      "loss": 4.6574,
      "step": 18
    },
    {
      "epoch": 0.0012187885882900076,
      "grad_norm": 1.0531500577926636,
      "learning_rate": 9.944739353007344e-05,
      "loss": 4.6055,
      "step": 19
    },
    {
      "epoch": 0.0012829353560947449,
      "grad_norm": 1.0641534328460693,
      "learning_rate": 9.931806517013612e-05,
      "loss": 4.8328,
      "step": 20
    },
    {
      "epoch": 0.001347082123899482,
      "grad_norm": 1.0635719299316406,
      "learning_rate": 9.917525374361912e-05,
      "loss": 4.6629,
      "step": 21
    },
    {
      "epoch": 0.0014112288917042192,
      "grad_norm": 1.0062886476516724,
      "learning_rate": 9.901899829374047e-05,
      "loss": 4.6475,
      "step": 22
    },
    {
      "epoch": 0.0014753756595089565,
      "grad_norm": 1.0333250761032104,
      "learning_rate": 9.884934153917997e-05,
      "loss": 4.5601,
      "step": 23
    },
    {
      "epoch": 0.0015395224273136937,
      "grad_norm": 1.0814541578292847,
      "learning_rate": 9.86663298624003e-05,
      "loss": 4.588,
      "step": 24
    },
    {
      "epoch": 0.001603669195118431,
      "grad_norm": 1.0560483932495117,
      "learning_rate": 9.847001329696653e-05,
      "loss": 4.7663,
      "step": 25
    },
    {
      "epoch": 0.0016678159629231683,
      "grad_norm": 1.0555614233016968,
      "learning_rate": 9.826044551386744e-05,
      "loss": 4.6834,
      "step": 26
    },
    {
      "epoch": 0.0017319627307279054,
      "grad_norm": 1.0532069206237793,
      "learning_rate": 9.803768380684242e-05,
      "loss": 4.7581,
      "step": 27
    },
    {
      "epoch": 0.0017961094985326426,
      "grad_norm": 1.0774611234664917,
      "learning_rate": 9.780178907671789e-05,
      "loss": 4.5798,
      "step": 28
    },
    {
      "epoch": 0.00186025626633738,
      "grad_norm": 1.1202058792114258,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.5658,
      "step": 29
    },
    {
      "epoch": 0.0019244030341421172,
      "grad_norm": 1.1507009267807007,
      "learning_rate": 9.729086208503174e-05,
      "loss": 4.6534,
      "step": 30
    },
    {
      "epoch": 0.0019885498019468545,
      "grad_norm": 1.150127649307251,
      "learning_rate": 9.701596950580806e-05,
      "loss": 4.5972,
      "step": 31
    },
    {
      "epoch": 0.0020526965697515915,
      "grad_norm": 1.4034016132354736,
      "learning_rate": 9.672822322997305e-05,
      "loss": 4.5515,
      "step": 32
    },
    {
      "epoch": 0.002116843337556329,
      "grad_norm": 1.5375943183898926,
      "learning_rate": 9.642770192448536e-05,
      "loss": 4.7035,
      "step": 33
    },
    {
      "epoch": 0.002180990105361066,
      "grad_norm": 1.7135989665985107,
      "learning_rate": 9.611448774886924e-05,
      "loss": 4.6596,
      "step": 34
    },
    {
      "epoch": 0.0022451368731658036,
      "grad_norm": 1.2220253944396973,
      "learning_rate": 9.578866633275288e-05,
      "loss": 4.7419,
      "step": 35
    },
    {
      "epoch": 0.0023092836409705406,
      "grad_norm": 1.2686922550201416,
      "learning_rate": 9.545032675245813e-05,
      "loss": 4.5849,
      "step": 36
    },
    {
      "epoch": 0.0023734304087752777,
      "grad_norm": 1.23640775680542,
      "learning_rate": 9.509956150664796e-05,
      "loss": 4.612,
      "step": 37
    },
    {
      "epoch": 0.002437577176580015,
      "grad_norm": 1.568307638168335,
      "learning_rate": 9.473646649103818e-05,
      "loss": 4.7548,
      "step": 38
    },
    {
      "epoch": 0.0025017239443847522,
      "grad_norm": 1.517473816871643,
      "learning_rate": 9.43611409721806e-05,
      "loss": 4.7243,
      "step": 39
    },
    {
      "epoch": 0.0025658707121894897,
      "grad_norm": 1.313269019126892,
      "learning_rate": 9.397368756032445e-05,
      "loss": 4.6087,
      "step": 40
    },
    {
      "epoch": 0.0026300174799942268,
      "grad_norm": 2.2595510482788086,
      "learning_rate": 9.357421218136386e-05,
      "loss": 4.743,
      "step": 41
    },
    {
      "epoch": 0.002694164247798964,
      "grad_norm": 3.3371033668518066,
      "learning_rate": 9.316282404787871e-05,
      "loss": 4.5435,
      "step": 42
    },
    {
      "epoch": 0.0027583110156037013,
      "grad_norm": 1.8085966110229492,
      "learning_rate": 9.273963562927695e-05,
      "loss": 4.5709,
      "step": 43
    },
    {
      "epoch": 0.0028224577834084384,
      "grad_norm": 1.8736380338668823,
      "learning_rate": 9.230476262104677e-05,
      "loss": 4.9747,
      "step": 44
    },
    {
      "epoch": 0.002886604551213176,
      "grad_norm": 2.1571285724639893,
      "learning_rate": 9.185832391312644e-05,
      "loss": 5.0479,
      "step": 45
    },
    {
      "epoch": 0.002950751319017913,
      "grad_norm": 2.30226731300354,
      "learning_rate": 9.140044155740101e-05,
      "loss": 5.0239,
      "step": 46
    },
    {
      "epoch": 0.0030148980868226504,
      "grad_norm": 2.3104941844940186,
      "learning_rate": 9.093124073433463e-05,
      "loss": 5.1189,
      "step": 47
    },
    {
      "epoch": 0.0030790448546273875,
      "grad_norm": 2.460177421569824,
      "learning_rate": 9.045084971874738e-05,
      "loss": 4.9984,
      "step": 48
    },
    {
      "epoch": 0.0031431916224321245,
      "grad_norm": 2.32393479347229,
      "learning_rate": 8.995939984474624e-05,
      "loss": 5.1342,
      "step": 49
    },
    {
      "epoch": 0.003207338390236862,
      "grad_norm": 3.8427116870880127,
      "learning_rate": 8.945702546981969e-05,
      "loss": 5.7603,
      "step": 50
    },
    {
      "epoch": 0.003207338390236862,
      "eval_loss": 5.226949214935303,
      "eval_runtime": 175.9293,
      "eval_samples_per_second": 149.242,
      "eval_steps_per_second": 37.31,
      "step": 50
    },
    {
      "epoch": 0.003271485158041599,
      "grad_norm": 16.735816955566406,
      "learning_rate": 8.894386393810563e-05,
      "loss": 5.1462,
      "step": 51
    },
    {
      "epoch": 0.0033356319258463366,
      "grad_norm": 16.28045654296875,
      "learning_rate": 8.842005554284296e-05,
      "loss": 5.132,
      "step": 52
    },
    {
      "epoch": 0.0033997786936510736,
      "grad_norm": 14.842843055725098,
      "learning_rate": 8.788574348801675e-05,
      "loss": 5.0758,
      "step": 53
    },
    {
      "epoch": 0.0034639254614558107,
      "grad_norm": 10.867883682250977,
      "learning_rate": 8.73410738492077e-05,
      "loss": 4.6109,
      "step": 54
    },
    {
      "epoch": 0.003528072229260548,
      "grad_norm": 6.1834397315979,
      "learning_rate": 8.678619553365659e-05,
      "loss": 4.4568,
      "step": 55
    },
    {
      "epoch": 0.0035922189970652853,
      "grad_norm": 2.2811717987060547,
      "learning_rate": 8.622126023955446e-05,
      "loss": 4.1773,
      "step": 56
    },
    {
      "epoch": 0.0036563657648700227,
      "grad_norm": 1.0003621578216553,
      "learning_rate": 8.564642241456986e-05,
      "loss": 4.3889,
      "step": 57
    },
    {
      "epoch": 0.00372051253267476,
      "grad_norm": 1.2055577039718628,
      "learning_rate": 8.506183921362443e-05,
      "loss": 4.3058,
      "step": 58
    },
    {
      "epoch": 0.0037846593004794973,
      "grad_norm": 1.120505690574646,
      "learning_rate": 8.44676704559283e-05,
      "loss": 4.1976,
      "step": 59
    },
    {
      "epoch": 0.0038488060682842344,
      "grad_norm": 1.160064935684204,
      "learning_rate": 8.386407858128706e-05,
      "loss": 4.307,
      "step": 60
    },
    {
      "epoch": 0.003912952836088971,
      "grad_norm": 1.234038233757019,
      "learning_rate": 8.32512286056924e-05,
      "loss": 4.3807,
      "step": 61
    },
    {
      "epoch": 0.003977099603893709,
      "grad_norm": 1.2030341625213623,
      "learning_rate": 8.262928807620843e-05,
      "loss": 4.2994,
      "step": 62
    },
    {
      "epoch": 0.004041246371698446,
      "grad_norm": 1.1614115238189697,
      "learning_rate": 8.199842702516583e-05,
      "loss": 4.4704,
      "step": 63
    },
    {
      "epoch": 0.004105393139503183,
      "grad_norm": 1.0668236017227173,
      "learning_rate": 8.135881792367686e-05,
      "loss": 4.4356,
      "step": 64
    },
    {
      "epoch": 0.0041695399073079205,
      "grad_norm": 0.966719925403595,
      "learning_rate": 8.07106356344834e-05,
      "loss": 4.3505,
      "step": 65
    },
    {
      "epoch": 0.004233686675112658,
      "grad_norm": 1.089863896369934,
      "learning_rate": 8.005405736415126e-05,
      "loss": 4.4084,
      "step": 66
    },
    {
      "epoch": 0.004297833442917395,
      "grad_norm": 0.957463264465332,
      "learning_rate": 7.938926261462366e-05,
      "loss": 4.3484,
      "step": 67
    },
    {
      "epoch": 0.004361980210722132,
      "grad_norm": 0.9310042858123779,
      "learning_rate": 7.871643313414718e-05,
      "loss": 4.3054,
      "step": 68
    },
    {
      "epoch": 0.00442612697852687,
      "grad_norm": 1.0095648765563965,
      "learning_rate": 7.803575286758364e-05,
      "loss": 4.1342,
      "step": 69
    },
    {
      "epoch": 0.004490273746331607,
      "grad_norm": 1.1456671953201294,
      "learning_rate": 7.734740790612136e-05,
      "loss": 4.5236,
      "step": 70
    },
    {
      "epoch": 0.004554420514136344,
      "grad_norm": 1.506197452545166,
      "learning_rate": 7.66515864363997e-05,
      "loss": 4.4159,
      "step": 71
    },
    {
      "epoch": 0.004618567281941081,
      "grad_norm": 1.6366878747940063,
      "learning_rate": 7.594847868906076e-05,
      "loss": 4.3043,
      "step": 72
    },
    {
      "epoch": 0.004682714049745819,
      "grad_norm": 1.4405200481414795,
      "learning_rate": 7.52382768867422e-05,
      "loss": 4.3536,
      "step": 73
    },
    {
      "epoch": 0.004746860817550555,
      "grad_norm": 1.1504731178283691,
      "learning_rate": 7.452117519152542e-05,
      "loss": 4.4886,
      "step": 74
    },
    {
      "epoch": 0.004811007585355293,
      "grad_norm": 1.0585530996322632,
      "learning_rate": 7.379736965185368e-05,
      "loss": 4.3503,
      "step": 75
    },
    {
      "epoch": 0.00487515435316003,
      "grad_norm": 0.9902110695838928,
      "learning_rate": 7.30670581489344e-05,
      "loss": 4.3448,
      "step": 76
    },
    {
      "epoch": 0.004939301120964767,
      "grad_norm": 1.1550136804580688,
      "learning_rate": 7.233044034264034e-05,
      "loss": 4.3835,
      "step": 77
    },
    {
      "epoch": 0.0050034478887695044,
      "grad_norm": 1.2284083366394043,
      "learning_rate": 7.158771761692464e-05,
      "loss": 4.2892,
      "step": 78
    },
    {
      "epoch": 0.005067594656574242,
      "grad_norm": 1.1169049739837646,
      "learning_rate": 7.083909302476453e-05,
      "loss": 4.3988,
      "step": 79
    },
    {
      "epoch": 0.0051317414243789794,
      "grad_norm": 1.257652997970581,
      "learning_rate": 7.008477123264848e-05,
      "loss": 4.4614,
      "step": 80
    },
    {
      "epoch": 0.005195888192183716,
      "grad_norm": 1.1160391569137573,
      "learning_rate": 6.932495846462261e-05,
      "loss": 4.557,
      "step": 81
    },
    {
      "epoch": 0.0052600349599884536,
      "grad_norm": 1.0872268676757812,
      "learning_rate": 6.855986244591104e-05,
      "loss": 4.514,
      "step": 82
    },
    {
      "epoch": 0.005324181727793191,
      "grad_norm": 1.0650984048843384,
      "learning_rate": 6.778969234612584e-05,
      "loss": 4.7157,
      "step": 83
    },
    {
      "epoch": 0.005388328495597928,
      "grad_norm": 1.1006252765655518,
      "learning_rate": 6.701465872208216e-05,
      "loss": 4.4739,
      "step": 84
    },
    {
      "epoch": 0.005452475263402665,
      "grad_norm": 1.0449990034103394,
      "learning_rate": 6.623497346023418e-05,
      "loss": 4.5417,
      "step": 85
    },
    {
      "epoch": 0.005516622031207403,
      "grad_norm": 1.1591130495071411,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.4075,
      "step": 86
    },
    {
      "epoch": 0.00558076879901214,
      "grad_norm": 1.1175400018692017,
      "learning_rate": 6.466250186922325e-05,
      "loss": 4.5812,
      "step": 87
    },
    {
      "epoch": 0.005644915566816877,
      "grad_norm": 1.0931376218795776,
      "learning_rate": 6.387014543809223e-05,
      "loss": 4.4844,
      "step": 88
    },
    {
      "epoch": 0.005709062334621614,
      "grad_norm": 1.115383267402649,
      "learning_rate": 6.307399704769099e-05,
      "loss": 4.3342,
      "step": 89
    },
    {
      "epoch": 0.005773209102426352,
      "grad_norm": 1.5079224109649658,
      "learning_rate": 6.227427435703997e-05,
      "loss": 4.3492,
      "step": 90
    },
    {
      "epoch": 0.005837355870231088,
      "grad_norm": 1.4159773588180542,
      "learning_rate": 6.147119600233758e-05,
      "loss": 4.6671,
      "step": 91
    },
    {
      "epoch": 0.005901502638035826,
      "grad_norm": 1.5043301582336426,
      "learning_rate": 6.066498153718735e-05,
      "loss": 4.7477,
      "step": 92
    },
    {
      "epoch": 0.005965649405840563,
      "grad_norm": 1.5698325634002686,
      "learning_rate": 5.985585137257401e-05,
      "loss": 4.5902,
      "step": 93
    },
    {
      "epoch": 0.006029796173645301,
      "grad_norm": 1.6872855424880981,
      "learning_rate": 5.90440267166055e-05,
      "loss": 4.6308,
      "step": 94
    },
    {
      "epoch": 0.0060939429414500375,
      "grad_norm": 1.6496694087982178,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 4.8072,
      "step": 95
    },
    {
      "epoch": 0.006158089709254775,
      "grad_norm": 1.8149094581604004,
      "learning_rate": 5.74131823855921e-05,
      "loss": 4.7701,
      "step": 96
    },
    {
      "epoch": 0.0062222364770595125,
      "grad_norm": 1.871055245399475,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 4.7448,
      "step": 97
    },
    {
      "epoch": 0.006286383244864249,
      "grad_norm": 2.1074602603912354,
      "learning_rate": 5.577423184847932e-05,
      "loss": 5.2005,
      "step": 98
    },
    {
      "epoch": 0.006350530012668987,
      "grad_norm": 2.565190553665161,
      "learning_rate": 5.495227651252315e-05,
      "loss": 5.2087,
      "step": 99
    },
    {
      "epoch": 0.006414676780473724,
      "grad_norm": 4.073370456695557,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 5.3805,
      "step": 100
    },
    {
      "epoch": 0.006414676780473724,
      "eval_loss": 5.076630592346191,
      "eval_runtime": 175.8418,
      "eval_samples_per_second": 149.316,
      "eval_steps_per_second": 37.329,
      "step": 100
    },
    {
      "epoch": 0.006478823548278461,
      "grad_norm": 14.903026580810547,
      "learning_rate": 5.330452921628497e-05,
      "loss": 5.0655,
      "step": 101
    },
    {
      "epoch": 0.006542970316083198,
      "grad_norm": 16.69548988342285,
      "learning_rate": 5.247918773366112e-05,
      "loss": 5.304,
      "step": 102
    },
    {
      "epoch": 0.006607117083887936,
      "grad_norm": 15.94449234008789,
      "learning_rate": 5.165316846586541e-05,
      "loss": 5.1495,
      "step": 103
    },
    {
      "epoch": 0.006671263851692673,
      "grad_norm": 14.320172309875488,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 5.1239,
      "step": 104
    },
    {
      "epoch": 0.00673541061949741,
      "grad_norm": 12.876553535461426,
      "learning_rate": 5e-05,
      "loss": 4.8099,
      "step": 105
    },
    {
      "epoch": 0.006799557387302147,
      "grad_norm": 10.945818901062012,
      "learning_rate": 4.917330276168208e-05,
      "loss": 4.6354,
      "step": 106
    },
    {
      "epoch": 0.006863704155106885,
      "grad_norm": 7.846940994262695,
      "learning_rate": 4.834683153413459e-05,
      "loss": 4.6015,
      "step": 107
    },
    {
      "epoch": 0.006927850922911621,
      "grad_norm": 5.602920055389404,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 4.4204,
      "step": 108
    },
    {
      "epoch": 0.006991997690716359,
      "grad_norm": 3.3654377460479736,
      "learning_rate": 4.669547078371504e-05,
      "loss": 4.3534,
      "step": 109
    },
    {
      "epoch": 0.007056144458521096,
      "grad_norm": 1.380203366279602,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 4.2598,
      "step": 110
    },
    {
      "epoch": 0.007120291226325834,
      "grad_norm": 0.8914572596549988,
      "learning_rate": 4.504772348747687e-05,
      "loss": 4.3893,
      "step": 111
    },
    {
      "epoch": 0.0071844379941305705,
      "grad_norm": 1.0553282499313354,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 4.3207,
      "step": 112
    },
    {
      "epoch": 0.007248584761935308,
      "grad_norm": 1.182533860206604,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 4.2244,
      "step": 113
    },
    {
      "epoch": 0.0073127315297400455,
      "grad_norm": 1.2025384902954102,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 4.3037,
      "step": 114
    },
    {
      "epoch": 0.007376878297544782,
      "grad_norm": 1.20087730884552,
      "learning_rate": 4.17702704859633e-05,
      "loss": 4.2187,
      "step": 115
    },
    {
      "epoch": 0.00744102506534952,
      "grad_norm": 1.2578917741775513,
      "learning_rate": 4.095597328339452e-05,
      "loss": 4.1639,
      "step": 116
    },
    {
      "epoch": 0.007505171833154257,
      "grad_norm": 1.2138766050338745,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 4.298,
      "step": 117
    },
    {
      "epoch": 0.007569318600958995,
      "grad_norm": 1.3775701522827148,
      "learning_rate": 3.933501846281267e-05,
      "loss": 4.3557,
      "step": 118
    },
    {
      "epoch": 0.007633465368763731,
      "grad_norm": 1.1817946434020996,
      "learning_rate": 3.852880399766243e-05,
      "loss": 4.2795,
      "step": 119
    },
    {
      "epoch": 0.007697612136568469,
      "grad_norm": 1.2066301107406616,
      "learning_rate": 3.772572564296005e-05,
      "loss": 4.4205,
      "step": 120
    },
    {
      "epoch": 0.007761758904373206,
      "grad_norm": 1.200325846672058,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 4.4474,
      "step": 121
    },
    {
      "epoch": 0.007825905672177943,
      "grad_norm": 1.2479723691940308,
      "learning_rate": 3.612985456190778e-05,
      "loss": 4.3991,
      "step": 122
    },
    {
      "epoch": 0.00789005243998268,
      "grad_norm": 1.1213867664337158,
      "learning_rate": 3.533749813077677e-05,
      "loss": 4.364,
      "step": 123
    },
    {
      "epoch": 0.007954199207787418,
      "grad_norm": 1.1056736707687378,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 4.4023,
      "step": 124
    },
    {
      "epoch": 0.008018345975592155,
      "grad_norm": 1.0023938417434692,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 4.414,
      "step": 125
    },
    {
      "epoch": 0.008082492743396893,
      "grad_norm": 1.0224699974060059,
      "learning_rate": 3.298534127791785e-05,
      "loss": 4.553,
      "step": 126
    },
    {
      "epoch": 0.008146639511201629,
      "grad_norm": 0.979837954044342,
      "learning_rate": 3.221030765387417e-05,
      "loss": 4.3103,
      "step": 127
    },
    {
      "epoch": 0.008210786279006366,
      "grad_norm": 1.0487502813339233,
      "learning_rate": 3.144013755408895e-05,
      "loss": 4.509,
      "step": 128
    },
    {
      "epoch": 0.008274933046811104,
      "grad_norm": 1.158705711364746,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 4.3335,
      "step": 129
    },
    {
      "epoch": 0.008339079814615841,
      "grad_norm": 1.2162866592407227,
      "learning_rate": 2.991522876735154e-05,
      "loss": 4.4842,
      "step": 130
    },
    {
      "epoch": 0.008403226582420579,
      "grad_norm": 1.1114434003829956,
      "learning_rate": 2.916090697523549e-05,
      "loss": 4.4306,
      "step": 131
    },
    {
      "epoch": 0.008467373350225316,
      "grad_norm": 1.156044363975525,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 4.5508,
      "step": 132
    },
    {
      "epoch": 0.008531520118030054,
      "grad_norm": 1.1695888042449951,
      "learning_rate": 2.766955965735968e-05,
      "loss": 4.372,
      "step": 133
    },
    {
      "epoch": 0.00859566688583479,
      "grad_norm": 1.2924425601959229,
      "learning_rate": 2.693294185106562e-05,
      "loss": 4.3554,
      "step": 134
    },
    {
      "epoch": 0.008659813653639527,
      "grad_norm": 1.12234628200531,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 4.3713,
      "step": 135
    },
    {
      "epoch": 0.008723960421444264,
      "grad_norm": 1.1108462810516357,
      "learning_rate": 2.547882480847461e-05,
      "loss": 4.4748,
      "step": 136
    },
    {
      "epoch": 0.008788107189249002,
      "grad_norm": 1.1847881078720093,
      "learning_rate": 2.476172311325783e-05,
      "loss": 4.3121,
      "step": 137
    },
    {
      "epoch": 0.00885225395705374,
      "grad_norm": 1.1697601079940796,
      "learning_rate": 2.405152131093926e-05,
      "loss": 4.4152,
      "step": 138
    },
    {
      "epoch": 0.008916400724858477,
      "grad_norm": 1.3349449634552002,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 4.5931,
      "step": 139
    },
    {
      "epoch": 0.008980547492663214,
      "grad_norm": 1.27959144115448,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 4.345,
      "step": 140
    },
    {
      "epoch": 0.00904469426046795,
      "grad_norm": 1.5184048414230347,
      "learning_rate": 2.196424713241637e-05,
      "loss": 4.4866,
      "step": 141
    },
    {
      "epoch": 0.009108841028272687,
      "grad_norm": 1.5085785388946533,
      "learning_rate": 2.128356686585282e-05,
      "loss": 4.6932,
      "step": 142
    },
    {
      "epoch": 0.009172987796077425,
      "grad_norm": 1.8742656707763672,
      "learning_rate": 2.061073738537635e-05,
      "loss": 4.7292,
      "step": 143
    },
    {
      "epoch": 0.009237134563882162,
      "grad_norm": 1.8291269540786743,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 4.6561,
      "step": 144
    },
    {
      "epoch": 0.0093012813316869,
      "grad_norm": 1.8334598541259766,
      "learning_rate": 1.928936436551661e-05,
      "loss": 4.6796,
      "step": 145
    },
    {
      "epoch": 0.009365428099491637,
      "grad_norm": 2.19795298576355,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 4.431,
      "step": 146
    },
    {
      "epoch": 0.009429574867296375,
      "grad_norm": 2.974046230316162,
      "learning_rate": 1.800157297483417e-05,
      "loss": 4.917,
      "step": 147
    },
    {
      "epoch": 0.00949372163510111,
      "grad_norm": 3.4350974559783936,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 5.173,
      "step": 148
    },
    {
      "epoch": 0.009557868402905848,
      "grad_norm": 3.8057234287261963,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 5.1518,
      "step": 149
    },
    {
      "epoch": 0.009622015170710586,
      "grad_norm": 5.24576473236084,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 5.3034,
      "step": 150
    },
    {
      "epoch": 0.009622015170710586,
      "eval_loss": 4.562685966491699,
      "eval_runtime": 175.5812,
      "eval_samples_per_second": 149.538,
      "eval_steps_per_second": 37.384,
      "step": 150
    },
    {
      "epoch": 0.009686161938515323,
      "grad_norm": 6.747333526611328,
      "learning_rate": 1.553232954407171e-05,
      "loss": 4.6423,
      "step": 151
    },
    {
      "epoch": 0.00975030870632006,
      "grad_norm": 7.345855236053467,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 4.4016,
      "step": 152
    },
    {
      "epoch": 0.009814455474124798,
      "grad_norm": 7.83561897277832,
      "learning_rate": 1.435357758543015e-05,
      "loss": 4.4795,
      "step": 153
    },
    {
      "epoch": 0.009878602241929534,
      "grad_norm": 8.044681549072266,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 4.6148,
      "step": 154
    },
    {
      "epoch": 0.009942749009734271,
      "grad_norm": 8.439257621765137,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 4.4925,
      "step": 155
    },
    {
      "epoch": 0.010006895777539009,
      "grad_norm": 7.490894317626953,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 4.5371,
      "step": 156
    },
    {
      "epoch": 0.010071042545343746,
      "grad_norm": 7.207547187805176,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 4.6755,
      "step": 157
    },
    {
      "epoch": 0.010135189313148484,
      "grad_norm": 7.033567428588867,
      "learning_rate": 1.157994445715706e-05,
      "loss": 4.5547,
      "step": 158
    },
    {
      "epoch": 0.010199336080953221,
      "grad_norm": 6.314227104187012,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 4.5327,
      "step": 159
    },
    {
      "epoch": 0.010263482848757959,
      "grad_norm": 5.745182037353516,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 4.2416,
      "step": 160
    },
    {
      "epoch": 0.010327629616562695,
      "grad_norm": 5.671355247497559,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 4.4693,
      "step": 161
    },
    {
      "epoch": 0.010391776384367432,
      "grad_norm": 4.737553596496582,
      "learning_rate": 9.549150281252633e-06,
      "loss": 4.3237,
      "step": 162
    },
    {
      "epoch": 0.01045592315217217,
      "grad_norm": 4.091307163238525,
      "learning_rate": 9.068759265665384e-06,
      "loss": 4.4015,
      "step": 163
    },
    {
      "epoch": 0.010520069919976907,
      "grad_norm": 3.5185821056365967,
      "learning_rate": 8.599558442598998e-06,
      "loss": 4.3101,
      "step": 164
    },
    {
      "epoch": 0.010584216687781645,
      "grad_norm": 2.9012203216552734,
      "learning_rate": 8.141676086873572e-06,
      "loss": 4.3895,
      "step": 165
    },
    {
      "epoch": 0.010648363455586382,
      "grad_norm": 2.7300195693969727,
      "learning_rate": 7.695237378953223e-06,
      "loss": 4.1931,
      "step": 166
    },
    {
      "epoch": 0.01071251022339112,
      "grad_norm": 2.3747920989990234,
      "learning_rate": 7.260364370723044e-06,
      "loss": 4.4433,
      "step": 167
    },
    {
      "epoch": 0.010776656991195855,
      "grad_norm": 2.079371690750122,
      "learning_rate": 6.837175952121306e-06,
      "loss": 4.3543,
      "step": 168
    },
    {
      "epoch": 0.010840803759000593,
      "grad_norm": 1.4814141988754272,
      "learning_rate": 6.425787818636131e-06,
      "loss": 4.3045,
      "step": 169
    },
    {
      "epoch": 0.01090495052680533,
      "grad_norm": 1.343712329864502,
      "learning_rate": 6.026312439675552e-06,
      "loss": 4.3258,
      "step": 170
    },
    {
      "epoch": 0.010969097294610068,
      "grad_norm": 1.111197590827942,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 4.454,
      "step": 171
    },
    {
      "epoch": 0.011033244062414805,
      "grad_norm": 1.142809510231018,
      "learning_rate": 5.263533508961827e-06,
      "loss": 4.1421,
      "step": 172
    },
    {
      "epoch": 0.011097390830219543,
      "grad_norm": 1.0003230571746826,
      "learning_rate": 4.900438493352055e-06,
      "loss": 4.2493,
      "step": 173
    },
    {
      "epoch": 0.01116153759802428,
      "grad_norm": 0.9974198937416077,
      "learning_rate": 4.549673247541875e-06,
      "loss": 4.3759,
      "step": 174
    },
    {
      "epoch": 0.011225684365829016,
      "grad_norm": 0.9607443809509277,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 4.3765,
      "step": 175
    },
    {
      "epoch": 0.011289831133633754,
      "grad_norm": 0.9585141539573669,
      "learning_rate": 3.885512251130763e-06,
      "loss": 4.3566,
      "step": 176
    },
    {
      "epoch": 0.011353977901438491,
      "grad_norm": 0.9915074110031128,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 4.3127,
      "step": 177
    },
    {
      "epoch": 0.011418124669243229,
      "grad_norm": 1.0069830417633057,
      "learning_rate": 3.271776770026963e-06,
      "loss": 4.4462,
      "step": 178
    },
    {
      "epoch": 0.011482271437047966,
      "grad_norm": 1.0191423892974854,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 4.4001,
      "step": 179
    },
    {
      "epoch": 0.011546418204852704,
      "grad_norm": 1.1447769403457642,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 4.5136,
      "step": 180
    },
    {
      "epoch": 0.011610564972657441,
      "grad_norm": 1.2010947465896606,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 4.5089,
      "step": 181
    },
    {
      "epoch": 0.011674711740462177,
      "grad_norm": 1.1182702779769897,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 4.3512,
      "step": 182
    },
    {
      "epoch": 0.011738858508266914,
      "grad_norm": 1.3424458503723145,
      "learning_rate": 1.962316193157593e-06,
      "loss": 4.5034,
      "step": 183
    },
    {
      "epoch": 0.011803005276071652,
      "grad_norm": 1.2088637351989746,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 4.7073,
      "step": 184
    },
    {
      "epoch": 0.01186715204387639,
      "grad_norm": 1.2827458381652832,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 4.4968,
      "step": 185
    },
    {
      "epoch": 0.011931298811681127,
      "grad_norm": 1.411598801612854,
      "learning_rate": 1.333670137599713e-06,
      "loss": 4.4289,
      "step": 186
    },
    {
      "epoch": 0.011995445579485864,
      "grad_norm": 1.4446345567703247,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 4.5778,
      "step": 187
    },
    {
      "epoch": 0.012059592347290602,
      "grad_norm": 1.4703569412231445,
      "learning_rate": 9.810017062595322e-07,
      "loss": 4.5659,
      "step": 188
    },
    {
      "epoch": 0.012123739115095337,
      "grad_norm": 1.5508967638015747,
      "learning_rate": 8.247462563808817e-07,
      "loss": 4.4926,
      "step": 189
    },
    {
      "epoch": 0.012187885882900075,
      "grad_norm": 1.6261972188949585,
      "learning_rate": 6.819348298638839e-07,
      "loss": 4.2867,
      "step": 190
    },
    {
      "epoch": 0.012252032650704812,
      "grad_norm": 1.7402580976486206,
      "learning_rate": 5.526064699265753e-07,
      "loss": 4.5234,
      "step": 191
    },
    {
      "epoch": 0.01231617941850955,
      "grad_norm": 2.0115389823913574,
      "learning_rate": 4.367965336512403e-07,
      "loss": 4.7659,
      "step": 192
    },
    {
      "epoch": 0.012380326186314287,
      "grad_norm": 2.0737099647521973,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 4.5599,
      "step": 193
    },
    {
      "epoch": 0.012444472954119025,
      "grad_norm": 2.5929040908813477,
      "learning_rate": 2.458548727494292e-07,
      "loss": 4.398,
      "step": 194
    },
    {
      "epoch": 0.012508619721923762,
      "grad_norm": 2.7410614490509033,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 4.7292,
      "step": 195
    },
    {
      "epoch": 0.012572766489728498,
      "grad_norm": 3.4124248027801514,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 4.8734,
      "step": 196
    },
    {
      "epoch": 0.012636913257533236,
      "grad_norm": 3.6188454627990723,
      "learning_rate": 6.150154258476315e-08,
      "loss": 4.9895,
      "step": 197
    },
    {
      "epoch": 0.012701060025337973,
      "grad_norm": 3.626702308654785,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 4.9788,
      "step": 198
    },
    {
      "epoch": 0.01276520679314271,
      "grad_norm": 4.390501499176025,
      "learning_rate": 6.834750376549792e-09,
      "loss": 5.1407,
      "step": 199
    },
    {
      "epoch": 0.012829353560947448,
      "grad_norm": 6.542236804962158,
      "learning_rate": 0.0,
      "loss": 5.7452,
      "step": 200
    },
    {
      "epoch": 0.012829353560947448,
      "eval_loss": 4.439182758331299,
      "eval_runtime": 175.5774,
      "eval_samples_per_second": 149.541,
      "eval_steps_per_second": 37.385,
      "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": 5953579646976000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}