{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 213,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014222222222222223,
      "grad_norm": 0.506786584854126,
      "learning_rate": 0.0,
      "loss": 1.1951476335525513,
      "step": 1
    },
    {
      "epoch": 0.028444444444444446,
      "grad_norm": 0.5440636277198792,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 1.2398298978805542,
      "step": 2
    },
    {
      "epoch": 0.042666666666666665,
      "grad_norm": 0.4429919421672821,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.9777733087539673,
      "step": 3
    },
    {
      "epoch": 0.05688888888888889,
      "grad_norm": 0.34922653436660767,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 0.8064044713973999,
      "step": 4
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 0.16975589096546173,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.5294505953788757,
      "step": 5
    },
    {
      "epoch": 0.08533333333333333,
      "grad_norm": 0.16188450157642365,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.636877179145813,
      "step": 6
    },
    {
      "epoch": 0.09955555555555555,
      "grad_norm": 0.11110807955265045,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 0.6087832450866699,
      "step": 7
    },
    {
      "epoch": 0.11377777777777778,
      "grad_norm": 0.0641367956995964,
      "learning_rate": 3.181818181818182e-06,
      "loss": 0.5258303880691528,
      "step": 8
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.052072592079639435,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.5444644689559937,
      "step": 9
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 0.0392303504049778,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 0.5337975025177002,
      "step": 10
    },
    {
      "epoch": 0.15644444444444444,
      "grad_norm": 0.028075236827135086,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.45043277740478516,
      "step": 11
    },
    {
      "epoch": 0.17066666666666666,
      "grad_norm": 0.02663014456629753,
      "learning_rate": 5e-06,
      "loss": 0.49355342984199524,
      "step": 12
    },
    {
      "epoch": 0.18488888888888888,
      "grad_norm": 0.028838366270065308,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.487549751996994,
      "step": 13
    },
    {
      "epoch": 0.1991111111111111,
      "grad_norm": 0.03057004138827324,
      "learning_rate": 5.90909090909091e-06,
      "loss": 0.500217616558075,
      "step": 14
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.028651155531406403,
      "learning_rate": 6.363636363636364e-06,
      "loss": 0.49628522992134094,
      "step": 15
    },
    {
      "epoch": 0.22755555555555557,
      "grad_norm": 0.028336627408862114,
      "learning_rate": 6.818181818181818e-06,
      "loss": 0.48170676827430725,
      "step": 16
    },
    {
      "epoch": 0.24177777777777779,
      "grad_norm": 0.019824286922812462,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.4609394073486328,
      "step": 17
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.02125639095902443,
      "learning_rate": 7.727272727272727e-06,
      "loss": 0.4759177565574646,
      "step": 18
    },
    {
      "epoch": 0.2702222222222222,
      "grad_norm": 0.025788351893424988,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.4962843060493469,
      "step": 19
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 0.033310867846012115,
      "learning_rate": 8.636363636363637e-06,
      "loss": 0.5028114318847656,
      "step": 20
    },
    {
      "epoch": 0.2986666666666667,
      "grad_norm": 0.020624130964279175,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.44575220346450806,
      "step": 21
    },
    {
      "epoch": 0.3128888888888889,
      "grad_norm": 0.020986203104257584,
      "learning_rate": 9.545454545454547e-06,
      "loss": 0.4755765199661255,
      "step": 22
    },
    {
      "epoch": 0.32711111111111113,
      "grad_norm": 2526660.75,
      "learning_rate": 1e-05,
      "loss": 0.4706365466117859,
      "step": 23
    },
    {
      "epoch": 0.3413333333333333,
      "grad_norm": 0.021011805161833763,
      "learning_rate": 9.999323662872998e-06,
      "loss": 0.4945886731147766,
      "step": 24
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.020573964342474937,
      "learning_rate": 9.99729483446475e-06,
      "loss": 0.4544343054294586,
      "step": 25
    },
    {
      "epoch": 0.36977777777777776,
      "grad_norm": 0.021116767078638077,
      "learning_rate": 9.993914063644053e-06,
      "loss": 0.4556806683540344,
      "step": 26
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.019978955388069153,
      "learning_rate": 9.989182265027232e-06,
      "loss": 0.4431076645851135,
      "step": 27
    },
    {
      "epoch": 0.3982222222222222,
      "grad_norm": 0.019631512463092804,
      "learning_rate": 9.98310071873072e-06,
      "loss": 0.4541151523590088,
      "step": 28
    },
    {
      "epoch": 0.41244444444444445,
      "grad_norm": 0.01977457106113434,
      "learning_rate": 9.975671070024741e-06,
      "loss": 0.4352927803993225,
      "step": 29
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.022281618788838387,
      "learning_rate": 9.966895328888195e-06,
      "loss": 0.5559179186820984,
      "step": 30
    },
    {
      "epoch": 0.4408888888888889,
      "grad_norm": 0.018352897837758064,
      "learning_rate": 9.956775869464901e-06,
      "loss": 0.42942947149276733,
      "step": 31
    },
    {
      "epoch": 0.45511111111111113,
      "grad_norm": 0.019121287390589714,
      "learning_rate": 9.945315429421307e-06,
      "loss": 0.45916861295700073,
      "step": 32
    },
    {
      "epoch": 0.4693333333333333,
      "grad_norm": 0.01712602935731411,
      "learning_rate": 9.932517109205849e-06,
      "loss": 0.4312085807323456,
      "step": 33
    },
    {
      "epoch": 0.48355555555555557,
      "grad_norm": 0.01892935112118721,
      "learning_rate": 9.918384371210178e-06,
      "loss": 0.5169366598129272,
      "step": 34
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 0.02034984715282917,
      "learning_rate": 9.902921038832456e-06,
      "loss": 0.49438145756721497,
      "step": 35
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.017887447029352188,
      "learning_rate": 9.886131295443003e-06,
      "loss": 0.4683716893196106,
      "step": 36
    },
    {
      "epoch": 0.5262222222222223,
      "grad_norm": 0.01887686364352703,
      "learning_rate": 9.868019683252543e-06,
      "loss": 0.46688079833984375,
      "step": 37
    },
    {
      "epoch": 0.5404444444444444,
      "grad_norm": 0.019363289698958397,
      "learning_rate": 9.848591102083375e-06,
      "loss": 0.4786224067211151,
      "step": 38
    },
    {
      "epoch": 0.5546666666666666,
      "grad_norm": 0.0201108418405056,
      "learning_rate": 9.82785080804381e-06,
      "loss": 0.47358086705207825,
      "step": 39
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 0.019631700590252876,
      "learning_rate": 9.805804412106197e-06,
      "loss": 0.585416316986084,
      "step": 40
    },
    {
      "epoch": 0.5831111111111111,
      "grad_norm": 0.01689487136900425,
      "learning_rate": 9.782457878588977e-06,
      "loss": 0.47205525636672974,
      "step": 41
    },
    {
      "epoch": 0.5973333333333334,
      "grad_norm": 0.01628926210105419,
      "learning_rate": 9.75781752354311e-06,
      "loss": 0.4348371624946594,
      "step": 42
    },
    {
      "epoch": 0.6115555555555555,
      "grad_norm": 0.01758437603712082,
      "learning_rate": 9.731890013043367e-06,
      "loss": 0.4891083538532257,
      "step": 43
    },
    {
      "epoch": 0.6257777777777778,
      "grad_norm": 0.017766334116458893,
      "learning_rate": 9.704682361384941e-06,
      "loss": 0.46330946683883667,
      "step": 44
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.017524050548672676,
      "learning_rate": 9.676201929185809e-06,
      "loss": 0.4083091914653778,
      "step": 45
    },
    {
      "epoch": 0.6542222222222223,
      "grad_norm": 0.017291702330112457,
      "learning_rate": 9.646456421395447e-06,
      "loss": 0.4653710126876831,
      "step": 46
    },
    {
      "epoch": 0.6684444444444444,
      "grad_norm": 0.017993608489632607,
      "learning_rate": 9.615453885210368e-06,
      "loss": 0.4626290202140808,
      "step": 47
    },
    {
      "epoch": 0.6826666666666666,
      "grad_norm": 0.017247265204787254,
      "learning_rate": 9.583202707897075e-06,
      "loss": 0.47964128851890564,
      "step": 48
    },
    {
      "epoch": 0.6968888888888889,
      "grad_norm": 0.017244094982743263,
      "learning_rate": 9.549711614523007e-06,
      "loss": 0.46718651056289673,
      "step": 49
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.01574530452489853,
      "learning_rate": 9.514989665596114e-06,
      "loss": 0.4456287622451782,
      "step": 50
    },
    {
      "epoch": 0.7111111111111111,
      "eval_loss": 0.4940151274204254,
      "eval_runtime": 6.2328,
      "eval_samples_per_second": 32.088,
      "eval_steps_per_second": 8.022,
      "step": 50
    },
    {
      "epoch": 0.7253333333333334,
      "grad_norm": 0.01783670485019684,
      "learning_rate": 9.479046254613673e-06,
      "loss": 0.45046865940093994,
      "step": 51
    },
    {
      "epoch": 0.7395555555555555,
      "grad_norm": 0.015281656756997108,
      "learning_rate": 9.441891105521005e-06,
      "loss": 0.43093934655189514,
      "step": 52
    },
    {
      "epoch": 0.7537777777777778,
      "grad_norm": 0.017853204160928726,
      "learning_rate": 9.40353427008083e-06,
      "loss": 0.4706975519657135,
      "step": 53
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.01542010996490717,
      "learning_rate": 9.3639861251539e-06,
      "loss": 0.4405261278152466,
      "step": 54
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 0.017832862213253975,
      "learning_rate": 9.323257369891702e-06,
      "loss": 0.47680750489234924,
      "step": 55
    },
    {
      "epoch": 0.7964444444444444,
      "grad_norm": 0.015628881752490997,
      "learning_rate": 9.281359022841966e-06,
      "loss": 0.42392900586128235,
      "step": 56
    },
    {
      "epoch": 0.8106666666666666,
      "grad_norm": 0.01757017895579338,
      "learning_rate": 9.238302418967757e-06,
      "loss": 0.48122283816337585,
      "step": 57
    },
    {
      "epoch": 0.8248888888888889,
      "grad_norm": 0.017186852172017097,
      "learning_rate": 9.194099206580981e-06,
      "loss": 0.5255264043807983,
      "step": 58
    },
    {
      "epoch": 0.8391111111111111,
      "grad_norm": 0.017161328345537186,
      "learning_rate": 9.14876134419111e-06,
      "loss": 0.4682884216308594,
      "step": 59
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.01665889099240303,
      "learning_rate": 9.102301097269974e-06,
      "loss": 0.5003230571746826,
      "step": 60
    },
    {
      "epoch": 0.8675555555555555,
      "grad_norm": 0.02079184167087078,
      "learning_rate": 9.05473103493355e-06,
      "loss": 0.45744988322257996,
      "step": 61
    },
    {
      "epoch": 0.8817777777777778,
      "grad_norm": 0.018035434186458588,
      "learning_rate": 9.006064026541549e-06,
      "loss": 0.5037047863006592,
      "step": 62
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.015980787575244904,
      "learning_rate": 8.956313238215824e-06,
      "loss": 0.4382043778896332,
      "step": 63
    },
    {
      "epoch": 0.9102222222222223,
      "grad_norm": 0.016865955665707588,
      "learning_rate": 8.905492129278478e-06,
      "loss": 0.44455963373184204,
      "step": 64
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 0.014777022413909435,
      "learning_rate": 8.85361444861063e-06,
      "loss": 0.4215100109577179,
      "step": 65
    },
    {
      "epoch": 0.9386666666666666,
      "grad_norm": 0.01814866065979004,
      "learning_rate": 8.800694230932885e-06,
      "loss": 0.48813939094543457,
      "step": 66
    },
    {
      "epoch": 0.9528888888888889,
      "grad_norm": 0.013353748247027397,
      "learning_rate": 8.74674579300843e-06,
      "loss": 3.263723850250244,
      "step": 67
    },
    {
      "epoch": 0.9671111111111111,
      "grad_norm": 0.014444677159190178,
      "learning_rate": 8.691783729769874e-06,
      "loss": 2.8557608127593994,
      "step": 68
    },
    {
      "epoch": 0.9813333333333333,
      "grad_norm": 0.01388335507363081,
      "learning_rate": 8.635822910370793e-06,
      "loss": 3.485170602798462,
      "step": 69
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 0.01357923075556755,
      "learning_rate": 8.578878474163115e-06,
      "loss": 3.1958985328674316,
      "step": 70
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.02305089496076107,
      "learning_rate": 8.520965826601394e-06,
      "loss": 2.678990364074707,
      "step": 71
    },
    {
      "epoch": 1.0142222222222221,
      "grad_norm": 0.014260848984122276,
      "learning_rate": 8.462100635075097e-06,
      "loss": 3.4466443061828613,
      "step": 72
    },
    {
      "epoch": 1.0284444444444445,
      "grad_norm": 0.014910527504980564,
      "learning_rate": 8.40229882467003e-06,
      "loss": 3.4718263149261475,
      "step": 73
    },
    {
      "epoch": 1.0426666666666666,
      "grad_norm": 0.013167285360395908,
      "learning_rate": 8.341576573860049e-06,
      "loss": 3.6029202938079834,
      "step": 74
    },
    {
      "epoch": 1.056888888888889,
      "grad_norm": 0.012767510488629341,
      "learning_rate": 8.279950310130218e-06,
      "loss": 4.018604755401611,
      "step": 75
    },
    {
      "epoch": 1.0711111111111111,
      "grad_norm": 0.013733700849115849,
      "learning_rate": 8.2174367055326e-06,
      "loss": 3.0605146884918213,
      "step": 76
    },
    {
      "epoch": 1.0853333333333333,
      "grad_norm": 0.011987799778580666,
      "learning_rate": 8.154052672175888e-06,
      "loss": 3.556879997253418,
      "step": 77
    },
    {
      "epoch": 1.0995555555555556,
      "grad_norm": 0.014038470573723316,
      "learning_rate": 8.08981535765009e-06,
      "loss": 3.7346572875976562,
      "step": 78
    },
    {
      "epoch": 1.1137777777777778,
      "grad_norm": 0.013301494531333447,
      "learning_rate": 8.024742140387506e-06,
      "loss": 3.2394087314605713,
      "step": 79
    },
    {
      "epoch": 1.1280000000000001,
      "grad_norm": 0.013333727605640888,
      "learning_rate": 7.95885062496126e-06,
      "loss": 3.625601053237915,
      "step": 80
    },
    {
      "epoch": 1.1422222222222222,
      "grad_norm": 0.013422077521681786,
      "learning_rate": 7.892158637322647e-06,
      "loss": 3.3379783630371094,
      "step": 81
    },
    {
      "epoch": 1.1564444444444444,
      "grad_norm": 0.012368597090244293,
      "learning_rate": 7.824684219978591e-06,
      "loss": 3.502805471420288,
      "step": 82
    },
    {
      "epoch": 1.1706666666666667,
      "grad_norm": 0.013034222647547722,
      "learning_rate": 7.756445627110523e-06,
      "loss": 3.362370729446411,
      "step": 83
    },
    {
      "epoch": 1.1848888888888889,
      "grad_norm": 0.014766803942620754,
      "learning_rate": 7.68746131963598e-06,
      "loss": 3.1864588260650635,
      "step": 84
    },
    {
      "epoch": 1.199111111111111,
      "grad_norm": 0.012399553321301937,
      "learning_rate": 7.6177499602143e-06,
      "loss": 3.4393932819366455,
      "step": 85
    },
    {
      "epoch": 1.2133333333333334,
      "grad_norm": 0.014413993805646896,
      "learning_rate": 7.547330408197695e-06,
      "loss": 3.76263689994812,
      "step": 86
    },
    {
      "epoch": 1.2275555555555555,
      "grad_norm": 0.014122135005891323,
      "learning_rate": 7.476221714529167e-06,
      "loss": 3.3016631603240967,
      "step": 87
    },
    {
      "epoch": 1.2417777777777779,
      "grad_norm": 0.015857728198170662,
      "learning_rate": 7.404443116588548e-06,
      "loss": 2.8077316284179688,
      "step": 88
    },
    {
      "epoch": 1.256,
      "grad_norm": 0.013196472078561783,
      "learning_rate": 7.332014032988123e-06,
      "loss": 3.496107816696167,
      "step": 89
    },
    {
      "epoch": 1.2702222222222221,
      "grad_norm": 0.01415536180138588,
      "learning_rate": 7.2589540583192165e-06,
      "loss": 3.4046881198883057,
      "step": 90
    },
    {
      "epoch": 1.2844444444444445,
      "grad_norm": 0.01354147121310234,
      "learning_rate": 7.185282957851175e-06,
      "loss": 3.3288354873657227,
      "step": 91
    },
    {
      "epoch": 1.2986666666666666,
      "grad_norm": 0.013861758634448051,
      "learning_rate": 7.111020662184174e-06,
      "loss": 3.573462963104248,
      "step": 92
    },
    {
      "epoch": 1.3128888888888888,
      "grad_norm": 0.01368795894086361,
      "learning_rate": 7.036187261857289e-06,
      "loss": 3.4570071697235107,
      "step": 93
    },
    {
      "epoch": 1.3271111111111111,
      "grad_norm": 0.014616986736655235,
      "learning_rate": 6.960803001913315e-06,
      "loss": 3.511754274368286,
      "step": 94
    },
    {
      "epoch": 1.3413333333333333,
      "grad_norm": 0.01352851465344429,
      "learning_rate": 6.884888276421766e-06,
      "loss": 4.017252445220947,
      "step": 95
    },
    {
      "epoch": 1.3555555555555556,
      "grad_norm": 0.013078316114842892,
      "learning_rate": 6.8084636229615786e-06,
      "loss": 3.5670371055603027,
      "step": 96
    },
    {
      "epoch": 1.3697777777777778,
      "grad_norm": 0.012880469672381878,
      "learning_rate": 6.731549717064975e-06,
      "loss": 4.055681228637695,
      "step": 97
    },
    {
      "epoch": 1.384,
      "grad_norm": 0.013766918331384659,
      "learning_rate": 6.654167366624009e-06,
      "loss": 3.303616762161255,
      "step": 98
    },
    {
      "epoch": 1.3982222222222223,
      "grad_norm": 0.015087485313415527,
      "learning_rate": 6.576337506261314e-06,
      "loss": 2.8152995109558105,
      "step": 99
    },
    {
      "epoch": 1.4124444444444444,
      "grad_norm": 0.013361976481974125,
      "learning_rate": 6.498081191666549e-06,
      "loss": 3.3619225025177,
      "step": 100
    },
    {
      "epoch": 1.4124444444444444,
      "eval_loss": 3.694061279296875,
      "eval_runtime": 5.8211,
      "eval_samples_per_second": 34.358,
      "eval_steps_per_second": 8.589,
      "step": 100
    },
    {
      "epoch": 1.4266666666666667,
      "grad_norm": 0.013033254072070122,
      "learning_rate": 6.419419593900109e-06,
      "loss": 3.0373668670654297,
      "step": 101
    },
    {
      "epoch": 1.4408888888888889,
      "grad_norm": 0.012533189728856087,
      "learning_rate": 6.340373993665607e-06,
      "loss": 3.642394542694092,
      "step": 102
    },
    {
      "epoch": 1.455111111111111,
      "grad_norm": 0.013018937781453133,
      "learning_rate": 6.2609657755527135e-06,
      "loss": 3.3127541542053223,
      "step": 103
    },
    {
      "epoch": 1.4693333333333334,
      "grad_norm": 0.014089098200201988,
      "learning_rate": 6.1812164222518626e-06,
      "loss": 3.500901937484741,
      "step": 104
    },
    {
      "epoch": 1.4835555555555555,
      "grad_norm": 0.0140894316136837,
      "learning_rate": 6.101147508742456e-06,
      "loss": 3.4911036491394043,
      "step": 105
    },
    {
      "epoch": 1.4977777777777779,
      "grad_norm": 0.014050478115677834,
      "learning_rate": 6.020780696456059e-06,
      "loss": 3.375718116760254,
      "step": 106
    },
    {
      "epoch": 1.512,
      "grad_norm": 0.013563934713602066,
      "learning_rate": 5.940137727416247e-06,
      "loss": 3.340306282043457,
      "step": 107
    },
    {
      "epoch": 1.5262222222222221,
      "grad_norm": 0.013330376707017422,
      "learning_rate": 5.859240418356614e-06,
      "loss": 3.5164387226104736,
      "step": 108
    },
    {
      "epoch": 1.5404444444444443,
      "grad_norm": 0.013517254032194614,
      "learning_rate": 5.778110654818602e-06,
      "loss": 3.955772876739502,
      "step": 109
    },
    {
      "epoch": 1.5546666666666666,
      "grad_norm": 0.014757441356778145,
      "learning_rate": 5.696770385230679e-06,
      "loss": 3.425647020339966,
      "step": 110
    },
    {
      "epoch": 1.568888888888889,
      "grad_norm": 0.014494120143353939,
      "learning_rate": 5.615241614970546e-06,
      "loss": 3.219924211502075,
      "step": 111
    },
    {
      "epoch": 1.5831111111111111,
      "grad_norm": 0.012901407666504383,
      "learning_rate": 5.533546400411899e-06,
      "loss": 3.3812978267669678,
      "step": 112
    },
    {
      "epoch": 1.5973333333333333,
      "grad_norm": 0.013786875642836094,
      "learning_rate": 5.4517068429574215e-06,
      "loss": 3.7506139278411865,
      "step": 113
    },
    {
      "epoch": 1.6115555555555554,
      "grad_norm": 0.012589235790073872,
      "learning_rate": 5.3697450830595775e-06,
      "loss": 3.259803295135498,
      "step": 114
    },
    {
      "epoch": 1.6257777777777778,
      "grad_norm": 0.01369628868997097,
      "learning_rate": 5.287683294230855e-06,
      "loss": 2.8727362155914307,
      "step": 115
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.012632690370082855,
      "learning_rate": 5.20554367704505e-06,
      "loss": 3.628926992416382,
      "step": 116
    },
    {
      "epoch": 1.6542222222222223,
      "grad_norm": 0.014506797306239605,
      "learning_rate": 5.123348453131242e-06,
      "loss": 3.236464023590088,
      "step": 117
    },
    {
      "epoch": 1.6684444444444444,
      "grad_norm": 0.014436502009630203,
      "learning_rate": 5.041119859162068e-06,
      "loss": 2.888354778289795,
      "step": 118
    },
    {
      "epoch": 1.6826666666666665,
      "grad_norm": 0.014416320249438286,
      "learning_rate": 4.958880140837934e-06,
      "loss": 3.105433702468872,
      "step": 119
    },
    {
      "epoch": 1.696888888888889,
      "grad_norm": 0.014613285660743713,
      "learning_rate": 4.876651546868759e-06,
      "loss": 3.2962746620178223,
      "step": 120
    },
    {
      "epoch": 1.7111111111111112,
      "grad_norm": 0.014369661919772625,
      "learning_rate": 4.794456322954953e-06,
      "loss": 3.451850414276123,
      "step": 121
    },
    {
      "epoch": 1.7253333333333334,
      "grad_norm": 0.013792592100799084,
      "learning_rate": 4.7123167057691446e-06,
      "loss": 3.6925525665283203,
      "step": 122
    },
    {
      "epoch": 1.7395555555555555,
      "grad_norm": 0.013583365827798843,
      "learning_rate": 4.630254916940424e-06,
      "loss": 4.191713333129883,
      "step": 123
    },
    {
      "epoch": 1.7537777777777777,
      "grad_norm": 0.014320321381092072,
      "learning_rate": 4.548293157042581e-06,
      "loss": 2.8300790786743164,
      "step": 124
    },
    {
      "epoch": 1.768,
      "grad_norm": 0.013430479913949966,
      "learning_rate": 4.466453599588103e-06,
      "loss": 3.5787062644958496,
      "step": 125
    },
    {
      "epoch": 1.7822222222222224,
      "grad_norm": 0.012813941575586796,
      "learning_rate": 4.384758385029457e-06,
      "loss": 2.687720537185669,
      "step": 126
    },
    {
      "epoch": 1.7964444444444445,
      "grad_norm": 0.014274616725742817,
      "learning_rate": 4.3032296147693225e-06,
      "loss": 3.221151113510132,
      "step": 127
    },
    {
      "epoch": 1.8106666666666666,
      "grad_norm": 0.013514580205082893,
      "learning_rate": 4.2218893451814005e-06,
      "loss": 3.415364980697632,
      "step": 128
    },
    {
      "epoch": 1.8248888888888888,
      "grad_norm": 0.01293711643666029,
      "learning_rate": 4.140759581643386e-06,
      "loss": 3.2137668132781982,
      "step": 129
    },
    {
      "epoch": 1.8391111111111111,
      "grad_norm": 0.013326463289558887,
      "learning_rate": 4.059862272583755e-06,
      "loss": 2.874941349029541,
      "step": 130
    },
    {
      "epoch": 1.8533333333333335,
      "grad_norm": 0.013346531428396702,
      "learning_rate": 3.979219303543942e-06,
      "loss": 3.6437442302703857,
      "step": 131
    },
    {
      "epoch": 1.8675555555555556,
      "grad_norm": 0.013448791578412056,
      "learning_rate": 3.898852491257547e-06,
      "loss": 3.262843370437622,
      "step": 132
    },
    {
      "epoch": 1.8817777777777778,
      "grad_norm": 0.013963771052658558,
      "learning_rate": 3.818783577748138e-06,
      "loss": 2.763110637664795,
      "step": 133
    },
    {
      "epoch": 1.896,
      "grad_norm": 0.01534951850771904,
      "learning_rate": 3.7390342244472886e-06,
      "loss": 2.978278160095215,
      "step": 134
    },
    {
      "epoch": 1.9102222222222223,
      "grad_norm": 0.014479058794677258,
      "learning_rate": 3.659626006334395e-06,
      "loss": 2.9288432598114014,
      "step": 135
    },
    {
      "epoch": 1.9244444444444444,
      "grad_norm": 0.01563713327050209,
      "learning_rate": 3.5805804060998926e-06,
      "loss": 3.158463954925537,
      "step": 136
    },
    {
      "epoch": 1.9386666666666668,
      "grad_norm": 0.01603933610022068,
      "learning_rate": 3.501918808333453e-06,
      "loss": 2.699950933456421,
      "step": 137
    },
    {
      "epoch": 1.952888888888889,
      "grad_norm": 0.014355695806443691,
      "learning_rate": 3.4236624937386874e-06,
      "loss": 3.840054512023926,
      "step": 138
    },
    {
      "epoch": 1.967111111111111,
      "grad_norm": 0.013930619694292545,
      "learning_rate": 3.3458326333759927e-06,
      "loss": 2.972839832305908,
      "step": 139
    },
    {
      "epoch": 1.9813333333333332,
      "grad_norm": 0.015130864456295967,
      "learning_rate": 3.268450282935026e-06,
      "loss": 2.8588995933532715,
      "step": 140
    },
    {
      "epoch": 1.9955555555555555,
      "grad_norm": 0.013637659139931202,
      "learning_rate": 3.1915363770384223e-06,
      "loss": 3.6230926513671875,
      "step": 141
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.023099087178707123,
      "learning_rate": 3.1151117235782346e-06,
      "loss": 2.1066107749938965,
      "step": 142
    },
    {
      "epoch": 2.014222222222222,
      "grad_norm": 0.014238209463655949,
      "learning_rate": 3.0391969980866874e-06,
      "loss": 3.128911256790161,
      "step": 143
    },
    {
      "epoch": 2.0284444444444443,
      "grad_norm": 0.012874635867774487,
      "learning_rate": 2.963812738142713e-06,
      "loss": 3.2379772663116455,
      "step": 144
    },
    {
      "epoch": 2.042666666666667,
      "grad_norm": 0.013502821326255798,
      "learning_rate": 2.8889793378158284e-06,
      "loss": 3.2959132194519043,
      "step": 145
    },
    {
      "epoch": 2.056888888888889,
      "grad_norm": 0.013256440870463848,
      "learning_rate": 2.814717042148827e-06,
      "loss": 3.3406944274902344,
      "step": 146
    },
    {
      "epoch": 2.071111111111111,
      "grad_norm": 0.013458102941513062,
      "learning_rate": 2.7410459416807856e-06,
      "loss": 3.3720455169677734,
      "step": 147
    },
    {
      "epoch": 2.0853333333333333,
      "grad_norm": 0.01476226095110178,
      "learning_rate": 2.6679859670118785e-06,
      "loss": 3.153254508972168,
      "step": 148
    },
    {
      "epoch": 2.0995555555555554,
      "grad_norm": 0.013766537420451641,
      "learning_rate": 2.5955568834114523e-06,
      "loss": 2.9255833625793457,
      "step": 149
    },
    {
      "epoch": 2.113777777777778,
      "grad_norm": 0.012672817334532738,
      "learning_rate": 2.523778285470835e-06,
      "loss": 3.385373115539551,
      "step": 150
    },
    {
      "epoch": 2.113777777777778,
      "eval_loss": 3.694100856781006,
      "eval_runtime": 6.2397,
      "eval_samples_per_second": 32.053,
      "eval_steps_per_second": 8.013,
      "step": 150
    },
    {
      "epoch": 2.128,
      "grad_norm": 0.013193093240261078,
      "learning_rate": 2.452669591802307e-06,
      "loss": 2.953336238861084,
      "step": 151
    },
    {
      "epoch": 2.1422222222222222,
      "grad_norm": 0.012676793150603771,
      "learning_rate": 2.3822500397857016e-06,
      "loss": 3.4797470569610596,
      "step": 152
    },
    {
      "epoch": 2.1564444444444444,
      "grad_norm": 0.013178958557546139,
      "learning_rate": 2.3125386803640188e-06,
      "loss": 3.766719341278076,
      "step": 153
    },
    {
      "epoch": 2.1706666666666665,
      "grad_norm": 0.013044048100709915,
      "learning_rate": 2.243554372889479e-06,
      "loss": 3.105588436126709,
      "step": 154
    },
    {
      "epoch": 2.1848888888888887,
      "grad_norm": 0.01274812500923872,
      "learning_rate": 2.1753157800214107e-06,
      "loss": 3.7258148193359375,
      "step": 155
    },
    {
      "epoch": 2.1991111111111112,
      "grad_norm": 0.014226537197828293,
      "learning_rate": 2.1078413626773547e-06,
      "loss": 3.2563636302948,
      "step": 156
    },
    {
      "epoch": 2.2133333333333334,
      "grad_norm": 0.013875821605324745,
      "learning_rate": 2.0411493750387423e-06,
      "loss": 3.6285147666931152,
      "step": 157
    },
    {
      "epoch": 2.2275555555555555,
      "grad_norm": 0.013328024186193943,
      "learning_rate": 1.9752578596124955e-06,
      "loss": 3.4809606075286865,
      "step": 158
    },
    {
      "epoch": 2.2417777777777776,
      "grad_norm": 0.014153145253658295,
      "learning_rate": 1.9101846423499113e-06,
      "loss": 3.331500768661499,
      "step": 159
    },
    {
      "epoch": 2.2560000000000002,
      "grad_norm": 0.013629083521664143,
      "learning_rate": 1.8459473278241125e-06,
      "loss": 3.103165626525879,
      "step": 160
    },
    {
      "epoch": 2.2702222222222224,
      "grad_norm": 0.013135570101439953,
      "learning_rate": 1.7825632944674016e-06,
      "loss": 2.949009656906128,
      "step": 161
    },
    {
      "epoch": 2.2844444444444445,
      "grad_norm": 0.015113947913050652,
      "learning_rate": 1.7200496898697832e-06,
      "loss": 3.8803815841674805,
      "step": 162
    },
    {
      "epoch": 2.2986666666666666,
      "grad_norm": 0.01285882480442524,
      "learning_rate": 1.6584234261399535e-06,
      "loss": 3.3277387619018555,
      "step": 163
    },
    {
      "epoch": 2.3128888888888888,
      "grad_norm": 0.013268567621707916,
      "learning_rate": 1.5977011753299726e-06,
      "loss": 3.04113507270813,
      "step": 164
    },
    {
      "epoch": 2.327111111111111,
      "grad_norm": 0.015572321601212025,
      "learning_rate": 1.5378993649249053e-06,
      "loss": 3.1088926792144775,
      "step": 165
    },
    {
      "epoch": 2.3413333333333335,
      "grad_norm": 0.013958935625851154,
      "learning_rate": 1.4790341733986085e-06,
      "loss": 2.9704766273498535,
      "step": 166
    },
    {
      "epoch": 2.3555555555555556,
      "grad_norm": 0.01262224093079567,
      "learning_rate": 1.4211215258368866e-06,
      "loss": 2.666156053543091,
      "step": 167
    },
    {
      "epoch": 2.3697777777777778,
      "grad_norm": 0.01445838063955307,
      "learning_rate": 1.3641770896292083e-06,
      "loss": 3.5968339443206787,
      "step": 168
    },
    {
      "epoch": 2.384,
      "grad_norm": 0.013657037168741226,
      "learning_rate": 1.3082162702301276e-06,
      "loss": 3.576735496520996,
      "step": 169
    },
    {
      "epoch": 2.398222222222222,
      "grad_norm": 0.014326483011245728,
      "learning_rate": 1.2532542069915722e-06,
      "loss": 3.0840680599212646,
      "step": 170
    },
    {
      "epoch": 2.4124444444444446,
      "grad_norm": 0.014063039794564247,
      "learning_rate": 1.1993057690671174e-06,
      "loss": 3.7334625720977783,
      "step": 171
    },
    {
      "epoch": 2.4266666666666667,
      "grad_norm": 0.012410550378262997,
      "learning_rate": 1.1463855513893695e-06,
      "loss": 4.4254841804504395,
      "step": 172
    },
    {
      "epoch": 2.440888888888889,
      "grad_norm": 0.012715302407741547,
      "learning_rate": 1.0945078707215224e-06,
      "loss": 3.775759696960449,
      "step": 173
    },
    {
      "epoch": 2.455111111111111,
      "grad_norm": 0.014594604261219501,
      "learning_rate": 1.0436867617841768e-06,
      "loss": 2.9598851203918457,
      "step": 174
    },
    {
      "epoch": 2.469333333333333,
      "grad_norm": 0.013803915120661259,
      "learning_rate": 9.939359734584552e-07,
      "loss": 2.9934566020965576,
      "step": 175
    },
    {
      "epoch": 2.4835555555555557,
      "grad_norm": 0.013807227835059166,
      "learning_rate": 9.452689650664515e-07,
      "loss": 3.3066673278808594,
      "step": 176
    },
    {
      "epoch": 2.497777777777778,
      "grad_norm": 0.013583092018961906,
      "learning_rate": 8.976989027300265e-07,
      "loss": 2.8772518634796143,
      "step": 177
    },
    {
      "epoch": 2.512,
      "grad_norm": NaN,
      "learning_rate": 8.512386558088919e-07,
      "loss": 0.2714032232761383,
      "step": 178
    },
    {
      "epoch": 2.526222222222222,
      "grad_norm": NaN,
      "learning_rate": 8.059007934190194e-07,
      "loss": 0.0,
      "step": 179
    },
    {
      "epoch": 2.5404444444444443,
      "grad_norm": NaN,
      "learning_rate": 7.61697581032243e-07,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 2.554666666666667,
      "grad_norm": NaN,
      "learning_rate": 7.186409771580355e-07,
      "loss": 0.0,
      "step": 181
    },
    {
      "epoch": 2.568888888888889,
      "grad_norm": NaN,
      "learning_rate": 6.76742630108298e-07,
      "loss": 0.0,
      "step": 182
    },
    {
      "epoch": 2.583111111111111,
      "grad_norm": NaN,
      "learning_rate": 6.360138748461015e-07,
      "loss": 0.0,
      "step": 183
    },
    {
      "epoch": 2.5973333333333333,
      "grad_norm": NaN,
      "learning_rate": 5.964657299191712e-07,
      "loss": 0.0,
      "step": 184
    },
    {
      "epoch": 2.6115555555555554,
      "grad_norm": NaN,
      "learning_rate": 5.581088944789953e-07,
      "loss": 0.0,
      "step": 185
    },
    {
      "epoch": 2.6257777777777775,
      "grad_norm": NaN,
      "learning_rate": 5.20953745386329e-07,
      "loss": 0.0,
      "step": 186
    },
    {
      "epoch": 2.64,
      "grad_norm": NaN,
      "learning_rate": 4.850103344038853e-07,
      "loss": 0.0,
      "step": 187
    },
    {
      "epoch": 2.6542222222222223,
      "grad_norm": NaN,
      "learning_rate": 4.502883854769935e-07,
      "loss": 0.0,
      "step": 188
    },
    {
      "epoch": 2.6684444444444444,
      "grad_norm": NaN,
      "learning_rate": 4.167972921029262e-07,
      "loss": 0.0,
      "step": 189
    },
    {
      "epoch": 2.6826666666666665,
      "grad_norm": NaN,
      "learning_rate": 3.8454611478963235e-07,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 2.696888888888889,
      "grad_norm": NaN,
      "learning_rate": 3.535435786045538e-07,
      "loss": 0.0,
      "step": 191
    },
    {
      "epoch": 2.7111111111111112,
      "grad_norm": NaN,
      "learning_rate": 3.237980708141919e-07,
      "loss": 0.0,
      "step": 192
    },
    {
      "epoch": 2.7253333333333334,
      "grad_norm": NaN,
      "learning_rate": 2.9531763861505967e-07,
      "loss": 0.0,
      "step": 193
    },
    {
      "epoch": 2.7395555555555555,
      "grad_norm": NaN,
      "learning_rate": 2.681099869566328e-07,
      "loss": 0.0,
      "step": 194
    },
    {
      "epoch": 2.7537777777777777,
      "grad_norm": NaN,
      "learning_rate": 2.4218247645689306e-07,
      "loss": 0.0,
      "step": 195
    },
    {
      "epoch": 2.768,
      "grad_norm": NaN,
      "learning_rate": 2.175421214110235e-07,
      "loss": 0.0,
      "step": 196
    },
    {
      "epoch": 2.7822222222222224,
      "grad_norm": NaN,
      "learning_rate": 1.941955878938029e-07,
      "loss": 0.0,
      "step": 197
    },
    {
      "epoch": 2.7964444444444445,
      "grad_norm": NaN,
      "learning_rate": 1.721491919561913e-07,
      "loss": 0.0,
      "step": 198
    },
    {
      "epoch": 2.8106666666666666,
      "grad_norm": NaN,
      "learning_rate": 1.514088979166256e-07,
      "loss": 0.0,
      "step": 199
    },
    {
      "epoch": 2.824888888888889,
      "grad_norm": NaN,
      "learning_rate": 1.3198031674745814e-07,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 2.824888888888889,
      "eval_loss": NaN,
      "eval_runtime": 5.5777,
      "eval_samples_per_second": 35.857,
      "eval_steps_per_second": 8.964,
      "step": 200
    },
    {
      "epoch": 2.8391111111111114,
      "grad_norm": NaN,
      "learning_rate": 1.138687045569975e-07,
      "loss": 0.0,
      "step": 201
    },
    {
      "epoch": 2.8533333333333335,
      "grad_norm": NaN,
      "learning_rate": 9.70789611675449e-08,
      "loss": 0.0,
      "step": 202
    },
    {
      "epoch": 2.8675555555555556,
      "grad_norm": NaN,
      "learning_rate": 8.161562878982399e-08,
      "loss": 0.0,
      "step": 203
    },
    {
      "epoch": 2.8817777777777778,
      "grad_norm": NaN,
      "learning_rate": 6.74828907941516e-08,
      "loss": 0.0,
      "step": 204
    },
    {
      "epoch": 2.896,
      "grad_norm": NaN,
      "learning_rate": 5.468457057869358e-08,
      "loss": 0.0,
      "step": 205
    },
    {
      "epoch": 2.910222222222222,
      "grad_norm": NaN,
      "learning_rate": 4.322413053509944e-08,
      "loss": 0.0,
      "step": 206
    },
    {
      "epoch": 2.924444444444444,
      "grad_norm": NaN,
      "learning_rate": 3.31046711118066e-08,
      "loss": 0.0,
      "step": 207
    },
    {
      "epoch": 2.9386666666666668,
      "grad_norm": NaN,
      "learning_rate": 2.4328929975260262e-08,
      "loss": 0.0,
      "step": 208
    },
    {
      "epoch": 2.952888888888889,
      "grad_norm": NaN,
      "learning_rate": 1.6899281269279756e-08,
      "loss": 0.0,
      "step": 209
    },
    {
      "epoch": 2.967111111111111,
      "grad_norm": NaN,
      "learning_rate": 1.0817734972768946e-08,
      "loss": 0.0,
      "step": 210
    },
    {
      "epoch": 2.981333333333333,
      "grad_norm": NaN,
      "learning_rate": 6.085936355947897e-09,
      "loss": 0.0,
      "step": 211
    },
    {
      "epoch": 2.9955555555555557,
      "grad_norm": NaN,
      "learning_rate": 2.7051655352494654e-09,
      "loss": 0.0,
      "step": 212
    },
    {
      "epoch": 3.0,
      "grad_norm": NaN,
      "learning_rate": 6.763371270035457e-10,
      "loss": 0.0,
      "step": 213
    },
    {
      "epoch": 3.0,
      "step": 213,
      "total_flos": 1.0308479847759872e+17,
      "train_loss": 1.8930653027245696,
      "train_runtime": 5673.0769,
      "train_samples_per_second": 9.519,
      "train_steps_per_second": 0.038
    }
  ],
  "logging_steps": 1,
  "max_steps": 213,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0308479847759872e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}