{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.19745502413339183,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013163668275559457,
      "grad_norm": 1.1889708603566411,
      "learning_rate": 2e-05,
      "loss": 1.819,
      "step": 1
    },
    {
      "epoch": 0.0026327336551118913,
      "grad_norm": 1.2487402928615228,
      "learning_rate": 1.999777729859618e-05,
      "loss": 1.786,
      "step": 2
    },
    {
      "epoch": 0.003949100482667837,
      "grad_norm": 11.818568585279303,
      "learning_rate": 1.9991110182465032e-05,
      "loss": 2.1123,
      "step": 3
    },
    {
      "epoch": 0.005265467310223783,
      "grad_norm": 9.670771499171282,
      "learning_rate": 1.9980001615408228e-05,
      "loss": 2.1052,
      "step": 4
    },
    {
      "epoch": 0.006581834137779728,
      "grad_norm": 6.7296227669578945,
      "learning_rate": 1.9964456535631287e-05,
      "loss": 2.0417,
      "step": 5
    },
    {
      "epoch": 0.007898200965335674,
      "grad_norm": 2.9490730461911254,
      "learning_rate": 1.9944481853548335e-05,
      "loss": 1.9756,
      "step": 6
    },
    {
      "epoch": 0.009214567792891619,
      "grad_norm": 2.8814574350373383,
      "learning_rate": 1.9920086448710162e-05,
      "loss": 1.9305,
      "step": 7
    },
    {
      "epoch": 0.010530934620447565,
      "grad_norm": 2.360259343454192,
      "learning_rate": 1.9891281165856876e-05,
      "loss": 1.9001,
      "step": 8
    },
    {
      "epoch": 0.01184730144800351,
      "grad_norm": 1.6478415946047946,
      "learning_rate": 1.9858078810097004e-05,
      "loss": 1.9285,
      "step": 9
    },
    {
      "epoch": 0.013163668275559455,
      "grad_norm": 1.865513115308653,
      "learning_rate": 1.98204941412151e-05,
      "loss": 1.9158,
      "step": 10
    },
    {
      "epoch": 0.014480035103115402,
      "grad_norm": 1.2039798356530171,
      "learning_rate": 1.9778543867110428e-05,
      "loss": 1.9177,
      "step": 11
    },
    {
      "epoch": 0.015796401930671347,
      "grad_norm": 1.1202568182839863,
      "learning_rate": 1.9732246636369605e-05,
      "loss": 1.9124,
      "step": 12
    },
    {
      "epoch": 0.017112768758227294,
      "grad_norm": 0.9613691948096944,
      "learning_rate": 1.968162302997659e-05,
      "loss": 1.9048,
      "step": 13
    },
    {
      "epoch": 0.018429135585783237,
      "grad_norm": 0.893717907926126,
      "learning_rate": 1.962669555216358e-05,
      "loss": 1.8905,
      "step": 14
    },
    {
      "epoch": 0.019745502413339184,
      "grad_norm": 0.9042103319398382,
      "learning_rate": 1.9567488620406984e-05,
      "loss": 1.9179,
      "step": 15
    },
    {
      "epoch": 0.02106186924089513,
      "grad_norm": 0.8537257879688175,
      "learning_rate": 1.9504028554572865e-05,
      "loss": 1.8956,
      "step": 16
    },
    {
      "epoch": 0.022378236068451074,
      "grad_norm": 0.7723152246718353,
      "learning_rate": 1.943634356521671e-05,
      "loss": 1.9106,
      "step": 17
    },
    {
      "epoch": 0.02369460289600702,
      "grad_norm": 0.788599031919039,
      "learning_rate": 1.9364463741042694e-05,
      "loss": 1.8714,
      "step": 18
    },
    {
      "epoch": 0.025010969723562967,
      "grad_norm": 0.7138782811411121,
      "learning_rate": 1.928842103552803e-05,
      "loss": 1.8805,
      "step": 19
    },
    {
      "epoch": 0.02632733655111891,
      "grad_norm": 0.6526275706400243,
      "learning_rate": 1.920824925271838e-05,
      "loss": 1.8992,
      "step": 20
    },
    {
      "epoch": 0.027643703378674857,
      "grad_norm": 0.7018291273940191,
      "learning_rate": 1.9123984032200586e-05,
      "loss": 1.8774,
      "step": 21
    },
    {
      "epoch": 0.028960070206230804,
      "grad_norm": 0.7136424568096796,
      "learning_rate": 1.9035662833259433e-05,
      "loss": 1.8978,
      "step": 22
    },
    {
      "epoch": 0.030276437033786747,
      "grad_norm": 0.7147862026041938,
      "learning_rate": 1.8943324918225495e-05,
      "loss": 1.8965,
      "step": 23
    },
    {
      "epoch": 0.031592803861342694,
      "grad_norm": 0.7049064442746601,
      "learning_rate": 1.8847011335021447e-05,
      "loss": 1.8831,
      "step": 24
    },
    {
      "epoch": 0.03290917068889864,
      "grad_norm": 0.6689369768605253,
      "learning_rate": 1.874676489891461e-05,
      "loss": 1.8881,
      "step": 25
    },
    {
      "epoch": 0.03422553751645459,
      "grad_norm": 0.6425593648258924,
      "learning_rate": 1.8642630173483832e-05,
      "loss": 1.889,
      "step": 26
    },
    {
      "epoch": 0.03554190434401053,
      "grad_norm": 0.6931260970545167,
      "learning_rate": 1.85346534508092e-05,
      "loss": 1.8936,
      "step": 27
    },
    {
      "epoch": 0.036858271171566474,
      "grad_norm": 0.5855894301604793,
      "learning_rate": 1.8422882730893323e-05,
      "loss": 1.9131,
      "step": 28
    },
    {
      "epoch": 0.03817463799912242,
      "grad_norm": 0.6403065763687231,
      "learning_rate": 1.8307367700323412e-05,
      "loss": 1.9104,
      "step": 29
    },
    {
      "epoch": 0.03949100482667837,
      "grad_norm": 0.667165710149791,
      "learning_rate": 1.8188159710183595e-05,
      "loss": 1.8807,
      "step": 30
    },
    {
      "epoch": 0.040807371654234315,
      "grad_norm": 0.601710689560651,
      "learning_rate": 1.8065311753227272e-05,
      "loss": 1.9261,
      "step": 31
    },
    {
      "epoch": 0.04212373848179026,
      "grad_norm": 0.6543848114887616,
      "learning_rate": 1.7938878440319722e-05,
      "loss": 1.9178,
      "step": 32
    },
    {
      "epoch": 0.0434401053093462,
      "grad_norm": 0.7216887863002542,
      "learning_rate": 1.7808915976161364e-05,
      "loss": 1.9212,
      "step": 33
    },
    {
      "epoch": 0.04475647213690215,
      "grad_norm": 0.6605220221485377,
      "learning_rate": 1.7675482134302503e-05,
      "loss": 1.9019,
      "step": 34
    },
    {
      "epoch": 0.046072838964458095,
      "grad_norm": 0.5651946270062499,
      "learning_rate": 1.753863623146066e-05,
      "loss": 1.9065,
      "step": 35
    },
    {
      "epoch": 0.04738920579201404,
      "grad_norm": 0.6283354866608959,
      "learning_rate": 1.7398439101151908e-05,
      "loss": 1.8926,
      "step": 36
    },
    {
      "epoch": 0.04870557261956999,
      "grad_norm": 0.591339280937863,
      "learning_rate": 1.7254953066647915e-05,
      "loss": 1.898,
      "step": 37
    },
    {
      "epoch": 0.050021939447125935,
      "grad_norm": 0.566891433067587,
      "learning_rate": 1.710824191327075e-05,
      "loss": 1.9314,
      "step": 38
    },
    {
      "epoch": 0.051338306274681875,
      "grad_norm": 0.5036303737690743,
      "learning_rate": 1.695837086003772e-05,
      "loss": 1.908,
      "step": 39
    },
    {
      "epoch": 0.05265467310223782,
      "grad_norm": 0.5732998210738149,
      "learning_rate": 1.680540653066891e-05,
      "loss": 1.907,
      "step": 40
    },
    {
      "epoch": 0.05397103992979377,
      "grad_norm": 0.600054956243109,
      "learning_rate": 1.6649416923970248e-05,
      "loss": 1.908,
      "step": 41
    },
    {
      "epoch": 0.055287406757349715,
      "grad_norm": 0.5780718337975314,
      "learning_rate": 1.649047138360529e-05,
      "loss": 1.9006,
      "step": 42
    },
    {
      "epoch": 0.05660377358490566,
      "grad_norm": 0.5998379136280807,
      "learning_rate": 1.632864056726917e-05,
      "loss": 1.9023,
      "step": 43
    },
    {
      "epoch": 0.05792014041246161,
      "grad_norm": 0.630710242272472,
      "learning_rate": 1.6163996415278423e-05,
      "loss": 1.9284,
      "step": 44
    },
    {
      "epoch": 0.05923650724001755,
      "grad_norm": 0.5104566997273228,
      "learning_rate": 1.5996612118590604e-05,
      "loss": 1.9089,
      "step": 45
    },
    {
      "epoch": 0.060552874067573495,
      "grad_norm": 0.6521533677979531,
      "learning_rate": 1.5826562086267956e-05,
      "loss": 1.9285,
      "step": 46
    },
    {
      "epoch": 0.06186924089512944,
      "grad_norm": 0.5098826190359927,
      "learning_rate": 1.565392191239959e-05,
      "loss": 1.916,
      "step": 47
    },
    {
      "epoch": 0.06318560772268539,
      "grad_norm": 0.62515291794207,
      "learning_rate": 1.5478768342496872e-05,
      "loss": 1.9069,
      "step": 48
    },
    {
      "epoch": 0.06450197455024133,
      "grad_norm": 0.5918382830263713,
      "learning_rate": 1.5301179239376936e-05,
      "loss": 1.9224,
      "step": 49
    },
    {
      "epoch": 0.06581834137779728,
      "grad_norm": 0.6387295926323716,
      "learning_rate": 1.512123354854955e-05,
      "loss": 1.9022,
      "step": 50
    },
    {
      "epoch": 0.06713470820535322,
      "grad_norm": 0.5484211324952757,
      "learning_rate": 1.4939011263122635e-05,
      "loss": 1.9024,
      "step": 51
    },
    {
      "epoch": 0.06845107503290918,
      "grad_norm": 0.6838268591901047,
      "learning_rate": 1.4754593388242117e-05,
      "loss": 1.9133,
      "step": 52
    },
    {
      "epoch": 0.06976744186046512,
      "grad_norm": 0.49026244529365287,
      "learning_rate": 1.4568061905081874e-05,
      "loss": 1.9044,
      "step": 53
    },
    {
      "epoch": 0.07108380868802106,
      "grad_norm": 0.617101630668953,
      "learning_rate": 1.4379499734399797e-05,
      "loss": 1.9176,
      "step": 54
    },
    {
      "epoch": 0.07240017551557701,
      "grad_norm": 0.5185658207760714,
      "learning_rate": 1.4188990699676186e-05,
      "loss": 1.915,
      "step": 55
    },
    {
      "epoch": 0.07371654234313295,
      "grad_norm": 0.5509987613832577,
      "learning_rate": 1.3996619489850822e-05,
      "loss": 1.9282,
      "step": 56
    },
    {
      "epoch": 0.0750329091706889,
      "grad_norm": 0.5404326350759733,
      "learning_rate": 1.3802471621675337e-05,
      "loss": 1.9121,
      "step": 57
    },
    {
      "epoch": 0.07634927599824484,
      "grad_norm": 0.45194626257894893,
      "learning_rate": 1.3606633401697557e-05,
      "loss": 1.9348,
      "step": 58
    },
    {
      "epoch": 0.0776656428258008,
      "grad_norm": 0.44319095497602445,
      "learning_rate": 1.340919188789477e-05,
      "loss": 1.9162,
      "step": 59
    },
    {
      "epoch": 0.07898200965335674,
      "grad_norm": 0.45917008340300286,
      "learning_rate": 1.3210234850972966e-05,
      "loss": 1.9349,
      "step": 60
    },
    {
      "epoch": 0.08029837648091268,
      "grad_norm": 0.4397437065658123,
      "learning_rate": 1.300985073534919e-05,
      "loss": 1.9344,
      "step": 61
    },
    {
      "epoch": 0.08161474330846863,
      "grad_norm": 0.43586654360169025,
      "learning_rate": 1.280812861983446e-05,
      "loss": 1.9144,
      "step": 62
    },
    {
      "epoch": 0.08293111013602457,
      "grad_norm": 0.4334759261856198,
      "learning_rate": 1.2605158178034656e-05,
      "loss": 1.9202,
      "step": 63
    },
    {
      "epoch": 0.08424747696358052,
      "grad_norm": 0.41957147456515964,
      "learning_rate": 1.2401029638486952e-05,
      "loss": 1.8986,
      "step": 64
    },
    {
      "epoch": 0.08556384379113646,
      "grad_norm": 0.41703972877231255,
      "learning_rate": 1.219583374454963e-05,
      "loss": 1.9367,
      "step": 65
    },
    {
      "epoch": 0.0868802106186924,
      "grad_norm": 0.3885734477047593,
      "learning_rate": 1.1989661714063e-05,
      "loss": 1.9536,
      "step": 66
    },
    {
      "epoch": 0.08819657744624836,
      "grad_norm": 0.3629396674080558,
      "learning_rate": 1.1782605198799371e-05,
      "loss": 1.942,
      "step": 67
    },
    {
      "epoch": 0.0895129442738043,
      "grad_norm": 0.41851931328687847,
      "learning_rate": 1.157475624372018e-05,
      "loss": 1.9149,
      "step": 68
    },
    {
      "epoch": 0.09082931110136025,
      "grad_norm": 0.38254555542206087,
      "learning_rate": 1.1366207246058269e-05,
      "loss": 1.9258,
      "step": 69
    },
    {
      "epoch": 0.09214567792891619,
      "grad_norm": 0.3760396216126684,
      "learning_rate": 1.1157050914243614e-05,
      "loss": 1.9395,
      "step": 70
    },
    {
      "epoch": 0.09346204475647214,
      "grad_norm": 0.3802671210811049,
      "learning_rate": 1.0947380226690686e-05,
      "loss": 1.9354,
      "step": 71
    },
    {
      "epoch": 0.09477841158402808,
      "grad_norm": 0.346627059727759,
      "learning_rate": 1.0737288390465792e-05,
      "loss": 1.9259,
      "step": 72
    },
    {
      "epoch": 0.09609477841158402,
      "grad_norm": 0.3873365911679245,
      "learning_rate": 1.0526868799852797e-05,
      "loss": 1.9493,
      "step": 73
    },
    {
      "epoch": 0.09741114523913998,
      "grad_norm": 0.3805418724228647,
      "learning_rate": 1.031621499483559e-05,
      "loss": 1.9429,
      "step": 74
    },
    {
      "epoch": 0.09872751206669592,
      "grad_norm": 0.3477296159832507,
      "learning_rate": 1.0105420619515798e-05,
      "loss": 1.9348,
      "step": 75
    },
    {
      "epoch": 0.10004387889425187,
      "grad_norm": 0.36081350820036023,
      "learning_rate": 9.894579380484206e-06,
      "loss": 1.951,
      "step": 76
    },
    {
      "epoch": 0.10136024572180781,
      "grad_norm": 0.3603157658181124,
      "learning_rate": 9.683785005164412e-06,
      "loss": 1.9568,
      "step": 77
    },
    {
      "epoch": 0.10267661254936375,
      "grad_norm": 0.3344964866298326,
      "learning_rate": 9.473131200147205e-06,
      "loss": 1.9635,
      "step": 78
    },
    {
      "epoch": 0.1039929793769197,
      "grad_norm": 0.3577372410086672,
      "learning_rate": 9.262711609534211e-06,
      "loss": 1.9493,
      "step": 79
    },
    {
      "epoch": 0.10530934620447564,
      "grad_norm": 0.32166763062706677,
      "learning_rate": 9.052619773309318e-06,
      "loss": 1.9416,
      "step": 80
    },
    {
      "epoch": 0.1066257130320316,
      "grad_norm": 0.3642098555682263,
      "learning_rate": 8.842949085756389e-06,
      "loss": 1.9375,
      "step": 81
    },
    {
      "epoch": 0.10794207985958754,
      "grad_norm": 0.31313176156525635,
      "learning_rate": 8.633792753941733e-06,
      "loss": 1.9482,
      "step": 82
    },
    {
      "epoch": 0.10925844668714349,
      "grad_norm": 0.32357294734122866,
      "learning_rate": 8.425243756279824e-06,
      "loss": 1.9274,
      "step": 83
    },
    {
      "epoch": 0.11057481351469943,
      "grad_norm": 0.3149933190799516,
      "learning_rate": 8.217394801200632e-06,
      "loss": 1.9494,
      "step": 84
    },
    {
      "epoch": 0.11189118034225537,
      "grad_norm": 0.3145273258487357,
      "learning_rate": 8.010338285937006e-06,
      "loss": 1.9383,
      "step": 85
    },
    {
      "epoch": 0.11320754716981132,
      "grad_norm": 0.3293525045662984,
      "learning_rate": 7.804166255450372e-06,
      "loss": 1.9438,
      "step": 86
    },
    {
      "epoch": 0.11452391399736726,
      "grad_norm": 0.29338737195487413,
      "learning_rate": 7.598970361513052e-06,
      "loss": 1.9486,
      "step": 87
    },
    {
      "epoch": 0.11584028082492322,
      "grad_norm": 0.3103457426467627,
      "learning_rate": 7.394841821965345e-06,
      "loss": 1.9274,
      "step": 88
    },
    {
      "epoch": 0.11715664765247916,
      "grad_norm": 0.3143049571743679,
      "learning_rate": 7.191871380165538e-06,
      "loss": 1.9524,
      "step": 89
    },
    {
      "epoch": 0.1184730144800351,
      "grad_norm": 0.29504032042698036,
      "learning_rate": 6.990149264650814e-06,
      "loss": 1.9445,
      "step": 90
    },
    {
      "epoch": 0.11978938130759105,
      "grad_norm": 0.3210704673929567,
      "learning_rate": 6.789765149027039e-06,
      "loss": 1.9515,
      "step": 91
    },
    {
      "epoch": 0.12110574813514699,
      "grad_norm": 0.28621542114599363,
      "learning_rate": 6.590808112105232e-06,
      "loss": 1.969,
      "step": 92
    },
    {
      "epoch": 0.12242211496270294,
      "grad_norm": 0.2882677076447023,
      "learning_rate": 6.3933665983024465e-06,
      "loss": 1.954,
      "step": 93
    },
    {
      "epoch": 0.12373848179025888,
      "grad_norm": 0.287930909134049,
      "learning_rate": 6.197528378324664e-06,
      "loss": 1.9313,
      "step": 94
    },
    {
      "epoch": 0.12505484861781482,
      "grad_norm": 0.31023728939120476,
      "learning_rate": 6.003380510149179e-06,
      "loss": 1.9602,
      "step": 95
    },
    {
      "epoch": 0.12637121544537078,
      "grad_norm": 0.2752773114898817,
      "learning_rate": 5.8110093003238175e-06,
      "loss": 1.9831,
      "step": 96
    },
    {
      "epoch": 0.12768758227292673,
      "grad_norm": 0.2972076509810327,
      "learning_rate": 5.620500265600206e-06,
      "loss": 1.9562,
      "step": 97
    },
    {
      "epoch": 0.12900394910048266,
      "grad_norm": 0.28344306622056237,
      "learning_rate": 5.431938094918132e-06,
      "loss": 1.9679,
      "step": 98
    },
    {
      "epoch": 0.1303203159280386,
      "grad_norm": 0.27862896188615965,
      "learning_rate": 5.245406611757882e-06,
      "loss": 1.9667,
      "step": 99
    },
    {
      "epoch": 0.13163668275559456,
      "grad_norm": 0.2775069903986726,
      "learning_rate": 5.060988736877366e-06,
      "loss": 1.9486,
      "step": 100
    },
    {
      "epoch": 0.13295304958315052,
      "grad_norm": 0.2750571862770337,
      "learning_rate": 4.878766451450451e-06,
      "loss": 1.9557,
      "step": 101
    },
    {
      "epoch": 0.13426941641070644,
      "grad_norm": 0.2680704001161532,
      "learning_rate": 4.698820760623064e-06,
      "loss": 1.9506,
      "step": 102
    },
    {
      "epoch": 0.1355857832382624,
      "grad_norm": 0.2782630531024094,
      "learning_rate": 4.5212316575031325e-06,
      "loss": 1.9639,
      "step": 103
    },
    {
      "epoch": 0.13690215006581835,
      "grad_norm": 0.25617683357697074,
      "learning_rate": 4.346078087600411e-06,
      "loss": 1.9683,
      "step": 104
    },
    {
      "epoch": 0.13821851689337428,
      "grad_norm": 0.2444943371569369,
      "learning_rate": 4.173437913732048e-06,
      "loss": 1.9659,
      "step": 105
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 0.2597397835336073,
      "learning_rate": 4.003387881409397e-06,
      "loss": 1.9704,
      "step": 106
    },
    {
      "epoch": 0.14085125054848618,
      "grad_norm": 0.26063366143876027,
      "learning_rate": 3.836003584721577e-06,
      "loss": 1.97,
      "step": 107
    },
    {
      "epoch": 0.1421676173760421,
      "grad_norm": 0.23235593032133328,
      "learning_rate": 3.6713594327308343e-06,
      "loss": 1.9554,
      "step": 108
    },
    {
      "epoch": 0.14348398420359806,
      "grad_norm": 0.22701215505987368,
      "learning_rate": 3.509528616394716e-06,
      "loss": 1.9737,
      "step": 109
    },
    {
      "epoch": 0.14480035103115402,
      "grad_norm": 0.24108913765275466,
      "learning_rate": 3.3505830760297543e-06,
      "loss": 1.9699,
      "step": 110
    },
    {
      "epoch": 0.14611671785870997,
      "grad_norm": 0.24405476026520742,
      "learning_rate": 3.1945934693310897e-06,
      "loss": 1.9767,
      "step": 111
    },
    {
      "epoch": 0.1474330846862659,
      "grad_norm": 0.23175867510438058,
      "learning_rate": 3.0416291399622834e-06,
      "loss": 2.0023,
      "step": 112
    },
    {
      "epoch": 0.14874945151382185,
      "grad_norm": 0.22596129228759587,
      "learning_rate": 2.891758086729253e-06,
      "loss": 1.955,
      "step": 113
    },
    {
      "epoch": 0.1500658183413778,
      "grad_norm": 0.24851949999567013,
      "learning_rate": 2.7450469333520856e-06,
      "loss": 1.9611,
      "step": 114
    },
    {
      "epoch": 0.15138218516893373,
      "grad_norm": 0.22293156665441605,
      "learning_rate": 2.6015608988480956e-06,
      "loss": 1.9658,
      "step": 115
    },
    {
      "epoch": 0.15269855199648968,
      "grad_norm": 0.21616202749444716,
      "learning_rate": 2.4613637685393433e-06,
      "loss": 1.9753,
      "step": 116
    },
    {
      "epoch": 0.15401491882404564,
      "grad_norm": 0.22185470586350384,
      "learning_rate": 2.324517865697501e-06,
      "loss": 1.9495,
      "step": 117
    },
    {
      "epoch": 0.1553312856516016,
      "grad_norm": 0.21722679538918865,
      "learning_rate": 2.19108402383864e-06,
      "loss": 1.9628,
      "step": 118
    },
    {
      "epoch": 0.15664765247915752,
      "grad_norm": 0.21205900012695214,
      "learning_rate": 2.06112155968028e-06,
      "loss": 1.9823,
      "step": 119
    },
    {
      "epoch": 0.15796401930671347,
      "grad_norm": 0.2182253662134732,
      "learning_rate": 1.9346882467727323e-06,
      "loss": 1.9875,
      "step": 120
    },
    {
      "epoch": 0.15928038613426942,
      "grad_norm": 0.22007111443224736,
      "learning_rate": 1.811840289816409e-06,
      "loss": 1.9805,
      "step": 121
    },
    {
      "epoch": 0.16059675296182535,
      "grad_norm": 0.20406970469647664,
      "learning_rate": 1.6926322996765899e-06,
      "loss": 1.9818,
      "step": 122
    },
    {
      "epoch": 0.1619131197893813,
      "grad_norm": 0.2024904864715853,
      "learning_rate": 1.5771172691066793e-06,
      "loss": 1.9859,
      "step": 123
    },
    {
      "epoch": 0.16322948661693726,
      "grad_norm": 0.20299971001174535,
      "learning_rate": 1.4653465491908003e-06,
      "loss": 2.0096,
      "step": 124
    },
    {
      "epoch": 0.1645458534444932,
      "grad_norm": 0.21516178859981677,
      "learning_rate": 1.3573698265161683e-06,
      "loss": 1.9654,
      "step": 125
    },
    {
      "epoch": 0.16586222027204914,
      "grad_norm": 0.20722629324747893,
      "learning_rate": 1.2532351010853916e-06,
      "loss": 1.9708,
      "step": 126
    },
    {
      "epoch": 0.1671785870996051,
      "grad_norm": 0.21213871178644442,
      "learning_rate": 1.152988664978556e-06,
      "loss": 1.9787,
      "step": 127
    },
    {
      "epoch": 0.16849495392716105,
      "grad_norm": 0.20023503307538396,
      "learning_rate": 1.0566750817745076e-06,
      "loss": 1.9858,
      "step": 128
    },
    {
      "epoch": 0.16981132075471697,
      "grad_norm": 0.1924700263570635,
      "learning_rate": 9.6433716674057e-07,
      "loss": 1.9781,
      "step": 129
    },
    {
      "epoch": 0.17112768758227292,
      "grad_norm": 0.20779051083187167,
      "learning_rate": 8.760159677994174e-07,
      "loss": 1.9827,
      "step": 130
    },
    {
      "epoch": 0.17244405440982888,
      "grad_norm": 0.20230044677950978,
      "learning_rate": 7.91750747281621e-07,
      "loss": 1.9741,
      "step": 131
    },
    {
      "epoch": 0.1737604212373848,
      "grad_norm": 0.19683020520485797,
      "learning_rate": 7.115789644719728e-07,
      "loss": 1.9949,
      "step": 132
    },
    {
      "epoch": 0.17507678806494076,
      "grad_norm": 0.19524340774257554,
      "learning_rate": 6.355362589573078e-07,
      "loss": 1.9762,
      "step": 133
    },
    {
      "epoch": 0.1763931548924967,
      "grad_norm": 0.20098123761556075,
      "learning_rate": 5.636564347832907e-07,
      "loss": 1.9818,
      "step": 134
    },
    {
      "epoch": 0.17770952172005267,
      "grad_norm": 0.18935262395702177,
      "learning_rate": 4.95971445427137e-07,
      "loss": 1.983,
      "step": 135
    },
    {
      "epoch": 0.1790258885476086,
      "grad_norm": 0.1906817912560046,
      "learning_rate": 4.3251137959302023e-07,
      "loss": 1.9708,
      "step": 136
    },
    {
      "epoch": 0.18034225537516455,
      "grad_norm": 0.19470612058115894,
      "learning_rate": 3.733044478364234e-07,
      "loss": 1.967,
      "step": 137
    },
    {
      "epoch": 0.1816586222027205,
      "grad_norm": 0.18636115957247928,
      "learning_rate": 3.1837697002341293e-07,
      "loss": 1.9791,
      "step": 138
    },
    {
      "epoch": 0.18297498903027642,
      "grad_norm": 0.18877431556550928,
      "learning_rate": 2.677533636303964e-07,
      "loss": 1.9694,
      "step": 139
    },
    {
      "epoch": 0.18429135585783238,
      "grad_norm": 0.1955087203028538,
      "learning_rate": 2.214561328895748e-07,
      "loss": 1.9741,
      "step": 140
    },
    {
      "epoch": 0.18560772268538833,
      "grad_norm": 0.196549286904382,
      "learning_rate": 1.7950585878489856e-07,
      "loss": 1.979,
      "step": 141
    },
    {
      "epoch": 0.18692408951294429,
      "grad_norm": 0.19224460294869852,
      "learning_rate": 1.419211899029971e-07,
      "loss": 1.9707,
      "step": 142
    },
    {
      "epoch": 0.1882404563405002,
      "grad_norm": 0.18853581462437616,
      "learning_rate": 1.0871883414312778e-07,
      "loss": 1.981,
      "step": 143
    },
    {
      "epoch": 0.18955682316805617,
      "grad_norm": 0.1838928559361403,
      "learning_rate": 7.99135512898408e-08,
      "loss": 1.9731,
      "step": 144
    },
    {
      "epoch": 0.19087318999561212,
      "grad_norm": 0.190162401461088,
      "learning_rate": 5.55181464516652e-08,
      "loss": 1.975,
      "step": 145
    },
    {
      "epoch": 0.19218955682316805,
      "grad_norm": 0.19003523312950812,
      "learning_rate": 3.554346436871581e-08,
      "loss": 1.9704,
      "step": 146
    },
    {
      "epoch": 0.193505923650724,
      "grad_norm": 0.19021539316010605,
      "learning_rate": 1.9998384591773945e-08,
      "loss": 1.979,
      "step": 147
    },
    {
      "epoch": 0.19482229047827995,
      "grad_norm": 0.18754432655782285,
      "learning_rate": 8.889817534969425e-09,
      "loss": 1.9867,
      "step": 148
    },
    {
      "epoch": 0.1961386573058359,
      "grad_norm": 0.1897467195961825,
      "learning_rate": 2.222701403818972e-09,
      "loss": 1.9756,
      "step": 149
    },
    {
      "epoch": 0.19745502413339183,
      "grad_norm": 0.20302937860642753,
      "learning_rate": 0.0,
      "loss": 1.9877,
      "step": 150
    },
    {
      "epoch": 0.19745502413339183,
      "step": 150,
      "total_flos": 349677715193856.0,
      "train_loss": 1.9421729667981467,
      "train_runtime": 5209.8016,
      "train_samples_per_second": 58.044,
      "train_steps_per_second": 0.029
    }
  ],
  "logging_steps": 1,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 349677715193856.0,
  "train_batch_size": 42,
  "trial_name": null,
  "trial_params": null
}