{
  "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": 1.6684012713309793,
      "learning_rate": 2e-05,
      "loss": 1.7198,
      "step": 1
    },
    {
      "epoch": 0.0026327336551118913,
      "grad_norm": 1.7544839656507987,
      "learning_rate": 1.999777729859618e-05,
      "loss": 1.6832,
      "step": 2
    },
    {
      "epoch": 0.003949100482667837,
      "grad_norm": 7.313399140560638,
      "learning_rate": 1.9991110182465032e-05,
      "loss": 2.0103,
      "step": 3
    },
    {
      "epoch": 0.005265467310223783,
      "grad_norm": 6.615638069530941,
      "learning_rate": 1.9980001615408228e-05,
      "loss": 1.9925,
      "step": 4
    },
    {
      "epoch": 0.006581834137779728,
      "grad_norm": 3.912217609735039,
      "learning_rate": 1.9964456535631287e-05,
      "loss": 1.9331,
      "step": 5
    },
    {
      "epoch": 0.007898200965335674,
      "grad_norm": 3.505541055937303,
      "learning_rate": 1.9944481853548335e-05,
      "loss": 1.9008,
      "step": 6
    },
    {
      "epoch": 0.009214567792891619,
      "grad_norm": 2.0274344017789416,
      "learning_rate": 1.9920086448710162e-05,
      "loss": 1.8566,
      "step": 7
    },
    {
      "epoch": 0.010530934620447565,
      "grad_norm": 1.5126632146257974,
      "learning_rate": 1.9891281165856876e-05,
      "loss": 1.8102,
      "step": 8
    },
    {
      "epoch": 0.01184730144800351,
      "grad_norm": 1.312875076480979,
      "learning_rate": 1.9858078810097004e-05,
      "loss": 1.8242,
      "step": 9
    },
    {
      "epoch": 0.013163668275559455,
      "grad_norm": 1.1063432185415227,
      "learning_rate": 1.98204941412151e-05,
      "loss": 1.8192,
      "step": 10
    },
    {
      "epoch": 0.014480035103115402,
      "grad_norm": 0.9766272868563541,
      "learning_rate": 1.9778543867110428e-05,
      "loss": 1.8161,
      "step": 11
    },
    {
      "epoch": 0.015796401930671347,
      "grad_norm": 0.8570691019482384,
      "learning_rate": 1.9732246636369605e-05,
      "loss": 1.8071,
      "step": 12
    },
    {
      "epoch": 0.017112768758227294,
      "grad_norm": 0.8840923444422949,
      "learning_rate": 1.968162302997659e-05,
      "loss": 1.8045,
      "step": 13
    },
    {
      "epoch": 0.018429135585783237,
      "grad_norm": 0.8290075073741686,
      "learning_rate": 1.962669555216358e-05,
      "loss": 1.7914,
      "step": 14
    },
    {
      "epoch": 0.019745502413339184,
      "grad_norm": 0.8281599801788184,
      "learning_rate": 1.9567488620406984e-05,
      "loss": 1.8224,
      "step": 15
    },
    {
      "epoch": 0.02106186924089513,
      "grad_norm": 0.8797179311493277,
      "learning_rate": 1.9504028554572865e-05,
      "loss": 1.8054,
      "step": 16
    },
    {
      "epoch": 0.022378236068451074,
      "grad_norm": 0.783529765175221,
      "learning_rate": 1.943634356521671e-05,
      "loss": 1.8188,
      "step": 17
    },
    {
      "epoch": 0.02369460289600702,
      "grad_norm": 0.77442943945218,
      "learning_rate": 1.9364463741042694e-05,
      "loss": 1.7848,
      "step": 18
    },
    {
      "epoch": 0.025010969723562967,
      "grad_norm": 0.8082444535492397,
      "learning_rate": 1.928842103552803e-05,
      "loss": 1.7943,
      "step": 19
    },
    {
      "epoch": 0.02632733655111891,
      "grad_norm": 0.6939415823196081,
      "learning_rate": 1.920824925271838e-05,
      "loss": 1.8149,
      "step": 20
    },
    {
      "epoch": 0.027643703378674857,
      "grad_norm": 0.8146240036119807,
      "learning_rate": 1.9123984032200586e-05,
      "loss": 1.7921,
      "step": 21
    },
    {
      "epoch": 0.028960070206230804,
      "grad_norm": 0.6713466387915797,
      "learning_rate": 1.9035662833259433e-05,
      "loss": 1.8127,
      "step": 22
    },
    {
      "epoch": 0.030276437033786747,
      "grad_norm": 0.8083685421986408,
      "learning_rate": 1.8943324918225495e-05,
      "loss": 1.8117,
      "step": 23
    },
    {
      "epoch": 0.031592803861342694,
      "grad_norm": 0.7947188479489032,
      "learning_rate": 1.8847011335021447e-05,
      "loss": 1.7992,
      "step": 24
    },
    {
      "epoch": 0.03290917068889864,
      "grad_norm": 0.7258709677626598,
      "learning_rate": 1.874676489891461e-05,
      "loss": 1.8069,
      "step": 25
    },
    {
      "epoch": 0.03422553751645459,
      "grad_norm": 0.8703532331587269,
      "learning_rate": 1.8642630173483832e-05,
      "loss": 1.8097,
      "step": 26
    },
    {
      "epoch": 0.03554190434401053,
      "grad_norm": 0.7994103203896015,
      "learning_rate": 1.85346534508092e-05,
      "loss": 1.8159,
      "step": 27
    },
    {
      "epoch": 0.036858271171566474,
      "grad_norm": 0.8900812525717379,
      "learning_rate": 1.8422882730893323e-05,
      "loss": 1.8371,
      "step": 28
    },
    {
      "epoch": 0.03817463799912242,
      "grad_norm": 0.9063306081170588,
      "learning_rate": 1.8307367700323412e-05,
      "loss": 1.835,
      "step": 29
    },
    {
      "epoch": 0.03949100482667837,
      "grad_norm": 0.7890748419439795,
      "learning_rate": 1.8188159710183595e-05,
      "loss": 1.8074,
      "step": 30
    },
    {
      "epoch": 0.040807371654234315,
      "grad_norm": 0.8559042359307617,
      "learning_rate": 1.8065311753227272e-05,
      "loss": 1.8525,
      "step": 31
    },
    {
      "epoch": 0.04212373848179026,
      "grad_norm": 0.6480169512923297,
      "learning_rate": 1.7938878440319722e-05,
      "loss": 1.8449,
      "step": 32
    },
    {
      "epoch": 0.0434401053093462,
      "grad_norm": 0.7335113483791531,
      "learning_rate": 1.7808915976161364e-05,
      "loss": 1.8505,
      "step": 33
    },
    {
      "epoch": 0.04475647213690215,
      "grad_norm": 0.6886290754184599,
      "learning_rate": 1.7675482134302503e-05,
      "loss": 1.832,
      "step": 34
    },
    {
      "epoch": 0.046072838964458095,
      "grad_norm": 0.7124527820528233,
      "learning_rate": 1.753863623146066e-05,
      "loss": 1.8381,
      "step": 35
    },
    {
      "epoch": 0.04738920579201404,
      "grad_norm": 0.7718175859961022,
      "learning_rate": 1.7398439101151908e-05,
      "loss": 1.8251,
      "step": 36
    },
    {
      "epoch": 0.04870557261956999,
      "grad_norm": 0.7568743189389296,
      "learning_rate": 1.7254953066647915e-05,
      "loss": 1.8314,
      "step": 37
    },
    {
      "epoch": 0.050021939447125935,
      "grad_norm": 1.044057176793069,
      "learning_rate": 1.710824191327075e-05,
      "loss": 1.8642,
      "step": 38
    },
    {
      "epoch": 0.051338306274681875,
      "grad_norm": 0.7226585088265222,
      "learning_rate": 1.695837086003772e-05,
      "loss": 1.8426,
      "step": 39
    },
    {
      "epoch": 0.05265467310223782,
      "grad_norm": 0.8828829990259817,
      "learning_rate": 1.680540653066891e-05,
      "loss": 1.8426,
      "step": 40
    },
    {
      "epoch": 0.05397103992979377,
      "grad_norm": 0.7611059525763374,
      "learning_rate": 1.6649416923970248e-05,
      "loss": 1.844,
      "step": 41
    },
    {
      "epoch": 0.055287406757349715,
      "grad_norm": 0.8796203524459953,
      "learning_rate": 1.649047138360529e-05,
      "loss": 1.8379,
      "step": 42
    },
    {
      "epoch": 0.05660377358490566,
      "grad_norm": 0.7459045440144071,
      "learning_rate": 1.632864056726917e-05,
      "loss": 1.8403,
      "step": 43
    },
    {
      "epoch": 0.05792014041246161,
      "grad_norm": 0.7361343990919398,
      "learning_rate": 1.6163996415278423e-05,
      "loss": 1.8678,
      "step": 44
    },
    {
      "epoch": 0.05923650724001755,
      "grad_norm": 0.7208530063457853,
      "learning_rate": 1.5996612118590604e-05,
      "loss": 1.8506,
      "step": 45
    },
    {
      "epoch": 0.060552874067573495,
      "grad_norm": 0.653453604456369,
      "learning_rate": 1.5826562086267956e-05,
      "loss": 1.8697,
      "step": 46
    },
    {
      "epoch": 0.06186924089512944,
      "grad_norm": 0.7840182754073093,
      "learning_rate": 1.565392191239959e-05,
      "loss": 1.8591,
      "step": 47
    },
    {
      "epoch": 0.06318560772268539,
      "grad_norm": 0.7436769579872637,
      "learning_rate": 1.5478768342496872e-05,
      "loss": 1.851,
      "step": 48
    },
    {
      "epoch": 0.06450197455024133,
      "grad_norm": 0.813592253139494,
      "learning_rate": 1.5301179239376936e-05,
      "loss": 1.8671,
      "step": 49
    },
    {
      "epoch": 0.06581834137779728,
      "grad_norm": 0.7903412649668103,
      "learning_rate": 1.512123354854955e-05,
      "loss": 1.8479,
      "step": 50
    },
    {
      "epoch": 0.06713470820535322,
      "grad_norm": 0.8465778396135325,
      "learning_rate": 1.4939011263122635e-05,
      "loss": 1.8485,
      "step": 51
    },
    {
      "epoch": 0.06845107503290918,
      "grad_norm": 0.6998918029233343,
      "learning_rate": 1.4754593388242117e-05,
      "loss": 1.8603,
      "step": 52
    },
    {
      "epoch": 0.06976744186046512,
      "grad_norm": 0.7054493381944434,
      "learning_rate": 1.4568061905081874e-05,
      "loss": 1.8518,
      "step": 53
    },
    {
      "epoch": 0.07108380868802106,
      "grad_norm": 0.580554939433495,
      "learning_rate": 1.4379499734399797e-05,
      "loss": 1.8653,
      "step": 54
    },
    {
      "epoch": 0.07240017551557701,
      "grad_norm": 0.5591128325722674,
      "learning_rate": 1.4188990699676186e-05,
      "loss": 1.8638,
      "step": 55
    },
    {
      "epoch": 0.07371654234313295,
      "grad_norm": 0.5314535281722449,
      "learning_rate": 1.3996619489850822e-05,
      "loss": 1.8777,
      "step": 56
    },
    {
      "epoch": 0.0750329091706889,
      "grad_norm": 0.572853737923918,
      "learning_rate": 1.3802471621675337e-05,
      "loss": 1.863,
      "step": 57
    },
    {
      "epoch": 0.07634927599824484,
      "grad_norm": 0.5525984688937411,
      "learning_rate": 1.3606633401697557e-05,
      "loss": 1.8856,
      "step": 58
    },
    {
      "epoch": 0.0776656428258008,
      "grad_norm": 0.5814361735639326,
      "learning_rate": 1.340919188789477e-05,
      "loss": 1.8686,
      "step": 59
    },
    {
      "epoch": 0.07898200965335674,
      "grad_norm": 0.5635297476244343,
      "learning_rate": 1.3210234850972966e-05,
      "loss": 1.888,
      "step": 60
    },
    {
      "epoch": 0.08029837648091268,
      "grad_norm": 0.5953206518543657,
      "learning_rate": 1.300985073534919e-05,
      "loss": 1.8881,
      "step": 61
    },
    {
      "epoch": 0.08161474330846863,
      "grad_norm": 0.5230925552300961,
      "learning_rate": 1.280812861983446e-05,
      "loss": 1.8686,
      "step": 62
    },
    {
      "epoch": 0.08293111013602457,
      "grad_norm": 0.5273527537624487,
      "learning_rate": 1.2605158178034656e-05,
      "loss": 1.8758,
      "step": 63
    },
    {
      "epoch": 0.08424747696358052,
      "grad_norm": 0.49217542550349164,
      "learning_rate": 1.2401029638486952e-05,
      "loss": 1.8553,
      "step": 64
    },
    {
      "epoch": 0.08556384379113646,
      "grad_norm": 0.48015663835520717,
      "learning_rate": 1.219583374454963e-05,
      "loss": 1.8948,
      "step": 65
    },
    {
      "epoch": 0.0868802106186924,
      "grad_norm": 0.4346637015375099,
      "learning_rate": 1.1989661714063e-05,
      "loss": 1.9116,
      "step": 66
    },
    {
      "epoch": 0.08819657744624836,
      "grad_norm": 0.4158039859056577,
      "learning_rate": 1.1782605198799371e-05,
      "loss": 1.9012,
      "step": 67
    },
    {
      "epoch": 0.0895129442738043,
      "grad_norm": 0.45476021793950305,
      "learning_rate": 1.157475624372018e-05,
      "loss": 1.8749,
      "step": 68
    },
    {
      "epoch": 0.09082931110136025,
      "grad_norm": 0.4243248902319673,
      "learning_rate": 1.1366207246058269e-05,
      "loss": 1.8862,
      "step": 69
    },
    {
      "epoch": 0.09214567792891619,
      "grad_norm": 0.3974626586399554,
      "learning_rate": 1.1157050914243614e-05,
      "loss": 1.9018,
      "step": 70
    },
    {
      "epoch": 0.09346204475647214,
      "grad_norm": 0.4159112066894095,
      "learning_rate": 1.0947380226690686e-05,
      "loss": 1.8984,
      "step": 71
    },
    {
      "epoch": 0.09477841158402808,
      "grad_norm": 0.40954357145514375,
      "learning_rate": 1.0737288390465792e-05,
      "loss": 1.8898,
      "step": 72
    },
    {
      "epoch": 0.09609477841158402,
      "grad_norm": 0.3946167930030394,
      "learning_rate": 1.0526868799852797e-05,
      "loss": 1.9133,
      "step": 73
    },
    {
      "epoch": 0.09741114523913998,
      "grad_norm": 0.38898816697214444,
      "learning_rate": 1.031621499483559e-05,
      "loss": 1.9076,
      "step": 74
    },
    {
      "epoch": 0.09872751206669592,
      "grad_norm": 0.3821435248986923,
      "learning_rate": 1.0105420619515798e-05,
      "loss": 1.9011,
      "step": 75
    },
    {
      "epoch": 0.10004387889425187,
      "grad_norm": 0.3631502961117549,
      "learning_rate": 9.894579380484206e-06,
      "loss": 1.9175,
      "step": 76
    },
    {
      "epoch": 0.10136024572180781,
      "grad_norm": 0.3563001673448401,
      "learning_rate": 9.683785005164412e-06,
      "loss": 1.9246,
      "step": 77
    },
    {
      "epoch": 0.10267661254936375,
      "grad_norm": 0.37215129181973333,
      "learning_rate": 9.473131200147205e-06,
      "loss": 1.9316,
      "step": 78
    },
    {
      "epoch": 0.1039929793769197,
      "grad_norm": 0.3645960930127108,
      "learning_rate": 9.262711609534211e-06,
      "loss": 1.9177,
      "step": 79
    },
    {
      "epoch": 0.10530934620447564,
      "grad_norm": 0.3449113791721328,
      "learning_rate": 9.052619773309318e-06,
      "loss": 1.9115,
      "step": 80
    },
    {
      "epoch": 0.1066257130320316,
      "grad_norm": 0.32178936350113957,
      "learning_rate": 8.842949085756389e-06,
      "loss": 1.9077,
      "step": 81
    },
    {
      "epoch": 0.10794207985958754,
      "grad_norm": 0.36036929592193934,
      "learning_rate": 8.633792753941733e-06,
      "loss": 1.9196,
      "step": 82
    },
    {
      "epoch": 0.10925844668714349,
      "grad_norm": 0.3374942561935641,
      "learning_rate": 8.425243756279824e-06,
      "loss": 1.8994,
      "step": 83
    },
    {
      "epoch": 0.11057481351469943,
      "grad_norm": 0.32381338156360456,
      "learning_rate": 8.217394801200632e-06,
      "loss": 1.9223,
      "step": 84
    },
    {
      "epoch": 0.11189118034225537,
      "grad_norm": 0.3426489465260607,
      "learning_rate": 8.010338285937006e-06,
      "loss": 1.9117,
      "step": 85
    },
    {
      "epoch": 0.11320754716981132,
      "grad_norm": 0.3573967434382005,
      "learning_rate": 7.804166255450372e-06,
      "loss": 1.9175,
      "step": 86
    },
    {
      "epoch": 0.11452391399736726,
      "grad_norm": 0.2980247994867231,
      "learning_rate": 7.598970361513052e-06,
      "loss": 1.9236,
      "step": 87
    },
    {
      "epoch": 0.11584028082492322,
      "grad_norm": 0.32946390372633017,
      "learning_rate": 7.394841821965345e-06,
      "loss": 1.9033,
      "step": 88
    },
    {
      "epoch": 0.11715664765247916,
      "grad_norm": 0.31860708919636743,
      "learning_rate": 7.191871380165538e-06,
      "loss": 1.9292,
      "step": 89
    },
    {
      "epoch": 0.1184730144800351,
      "grad_norm": 0.2902687504254022,
      "learning_rate": 6.990149264650814e-06,
      "loss": 1.922,
      "step": 90
    },
    {
      "epoch": 0.11978938130759105,
      "grad_norm": 0.2995049576957932,
      "learning_rate": 6.789765149027039e-06,
      "loss": 1.9293,
      "step": 91
    },
    {
      "epoch": 0.12110574813514699,
      "grad_norm": 0.29877438224934777,
      "learning_rate": 6.590808112105232e-06,
      "loss": 1.948,
      "step": 92
    },
    {
      "epoch": 0.12242211496270294,
      "grad_norm": 0.30536668388843324,
      "learning_rate": 6.3933665983024465e-06,
      "loss": 1.9335,
      "step": 93
    },
    {
      "epoch": 0.12373848179025888,
      "grad_norm": 0.29191583397715043,
      "learning_rate": 6.197528378324664e-06,
      "loss": 1.911,
      "step": 94
    },
    {
      "epoch": 0.12505484861781482,
      "grad_norm": 0.2745385727758564,
      "learning_rate": 6.003380510149179e-06,
      "loss": 1.9412,
      "step": 95
    },
    {
      "epoch": 0.12637121544537078,
      "grad_norm": 0.26985309520565787,
      "learning_rate": 5.8110093003238175e-06,
      "loss": 1.9644,
      "step": 96
    },
    {
      "epoch": 0.12768758227292673,
      "grad_norm": 0.2974824581704979,
      "learning_rate": 5.620500265600206e-06,
      "loss": 1.9381,
      "step": 97
    },
    {
      "epoch": 0.12900394910048266,
      "grad_norm": 0.27773093312757435,
      "learning_rate": 5.431938094918132e-06,
      "loss": 1.9507,
      "step": 98
    },
    {
      "epoch": 0.1303203159280386,
      "grad_norm": 0.26094471936037056,
      "learning_rate": 5.245406611757882e-06,
      "loss": 1.95,
      "step": 99
    },
    {
      "epoch": 0.13163668275559456,
      "grad_norm": 0.2545114698358054,
      "learning_rate": 5.060988736877366e-06,
      "loss": 1.9327,
      "step": 100
    },
    {
      "epoch": 0.13295304958315052,
      "grad_norm": 0.2681769857889081,
      "learning_rate": 4.878766451450451e-06,
      "loss": 1.94,
      "step": 101
    },
    {
      "epoch": 0.13426941641070644,
      "grad_norm": 0.2675750488582007,
      "learning_rate": 4.698820760623064e-06,
      "loss": 1.9358,
      "step": 102
    },
    {
      "epoch": 0.1355857832382624,
      "grad_norm": 0.23198118609030557,
      "learning_rate": 4.5212316575031325e-06,
      "loss": 1.95,
      "step": 103
    },
    {
      "epoch": 0.13690215006581835,
      "grad_norm": 0.23737089588805418,
      "learning_rate": 4.346078087600411e-06,
      "loss": 1.9547,
      "step": 104
    },
    {
      "epoch": 0.13821851689337428,
      "grad_norm": 0.2395968040151698,
      "learning_rate": 4.173437913732048e-06,
      "loss": 1.9531,
      "step": 105
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 0.24897537697162153,
      "learning_rate": 4.003387881409397e-06,
      "loss": 1.9579,
      "step": 106
    },
    {
      "epoch": 0.14085125054848618,
      "grad_norm": 0.23457194149971583,
      "learning_rate": 3.836003584721577e-06,
      "loss": 1.9583,
      "step": 107
    },
    {
      "epoch": 0.1421676173760421,
      "grad_norm": 0.2304739790046877,
      "learning_rate": 3.6713594327308343e-06,
      "loss": 1.9439,
      "step": 108
    },
    {
      "epoch": 0.14348398420359806,
      "grad_norm": 0.23634489167745804,
      "learning_rate": 3.509528616394716e-06,
      "loss": 1.9632,
      "step": 109
    },
    {
      "epoch": 0.14480035103115402,
      "grad_norm": 0.2299306346634024,
      "learning_rate": 3.3505830760297543e-06,
      "loss": 1.9596,
      "step": 110
    },
    {
      "epoch": 0.14611671785870997,
      "grad_norm": 0.22638974340841073,
      "learning_rate": 3.1945934693310897e-06,
      "loss": 1.967,
      "step": 111
    },
    {
      "epoch": 0.1474330846862659,
      "grad_norm": 0.22622679583224486,
      "learning_rate": 3.0416291399622834e-06,
      "loss": 1.9931,
      "step": 112
    },
    {
      "epoch": 0.14874945151382185,
      "grad_norm": 0.22548168760119114,
      "learning_rate": 2.891758086729253e-06,
      "loss": 1.9464,
      "step": 113
    },
    {
      "epoch": 0.1500658183413778,
      "grad_norm": 0.24305295514121497,
      "learning_rate": 2.7450469333520856e-06,
      "loss": 1.9527,
      "step": 114
    },
    {
      "epoch": 0.15138218516893373,
      "grad_norm": 0.22168251746782325,
      "learning_rate": 2.6015608988480956e-06,
      "loss": 1.9582,
      "step": 115
    },
    {
      "epoch": 0.15269855199648968,
      "grad_norm": 0.21869031387995932,
      "learning_rate": 2.4613637685393433e-06,
      "loss": 1.9677,
      "step": 116
    },
    {
      "epoch": 0.15401491882404564,
      "grad_norm": 0.21598506720102095,
      "learning_rate": 2.324517865697501e-06,
      "loss": 1.9423,
      "step": 117
    },
    {
      "epoch": 0.1553312856516016,
      "grad_norm": 0.21451123257968752,
      "learning_rate": 2.19108402383864e-06,
      "loss": 1.9562,
      "step": 118
    },
    {
      "epoch": 0.15664765247915752,
      "grad_norm": 0.20577415266502194,
      "learning_rate": 2.06112155968028e-06,
      "loss": 1.9761,
      "step": 119
    },
    {
      "epoch": 0.15796401930671347,
      "grad_norm": 0.21127510307084235,
      "learning_rate": 1.9346882467727323e-06,
      "loss": 1.9815,
      "step": 120
    },
    {
      "epoch": 0.15928038613426942,
      "grad_norm": 0.22179968946911885,
      "learning_rate": 1.811840289816409e-06,
      "loss": 1.9752,
      "step": 121
    },
    {
      "epoch": 0.16059675296182535,
      "grad_norm": 0.20762279005669518,
      "learning_rate": 1.6926322996765899e-06,
      "loss": 1.9767,
      "step": 122
    },
    {
      "epoch": 0.1619131197893813,
      "grad_norm": 0.2119830743130354,
      "learning_rate": 1.5771172691066793e-06,
      "loss": 1.981,
      "step": 123
    },
    {
      "epoch": 0.16322948661693726,
      "grad_norm": 0.21033783732526593,
      "learning_rate": 1.4653465491908003e-06,
      "loss": 2.0054,
      "step": 124
    },
    {
      "epoch": 0.1645458534444932,
      "grad_norm": 0.2172243067325937,
      "learning_rate": 1.3573698265161683e-06,
      "loss": 1.9613,
      "step": 125
    },
    {
      "epoch": 0.16586222027204914,
      "grad_norm": 0.20606192679997118,
      "learning_rate": 1.2532351010853916e-06,
      "loss": 1.9671,
      "step": 126
    },
    {
      "epoch": 0.1671785870996051,
      "grad_norm": 0.21435566532117142,
      "learning_rate": 1.152988664978556e-06,
      "loss": 1.9753,
      "step": 127
    },
    {
      "epoch": 0.16849495392716105,
      "grad_norm": 0.2069790226984845,
      "learning_rate": 1.0566750817745076e-06,
      "loss": 1.9825,
      "step": 128
    },
    {
      "epoch": 0.16981132075471697,
      "grad_norm": 0.2005697488355136,
      "learning_rate": 9.6433716674057e-07,
      "loss": 1.9752,
      "step": 129
    },
    {
      "epoch": 0.17112768758227292,
      "grad_norm": 0.2110796873927842,
      "learning_rate": 8.760159677994174e-07,
      "loss": 1.9799,
      "step": 130
    },
    {
      "epoch": 0.17244405440982888,
      "grad_norm": 0.2101037777585019,
      "learning_rate": 7.91750747281621e-07,
      "loss": 1.9715,
      "step": 131
    },
    {
      "epoch": 0.1737604212373848,
      "grad_norm": 0.2073031435527084,
      "learning_rate": 7.115789644719728e-07,
      "loss": 1.9927,
      "step": 132
    },
    {
      "epoch": 0.17507678806494076,
      "grad_norm": 0.20153461101886738,
      "learning_rate": 6.355362589573078e-07,
      "loss": 1.974,
      "step": 133
    },
    {
      "epoch": 0.1763931548924967,
      "grad_norm": 0.20998390792827068,
      "learning_rate": 5.636564347832907e-07,
      "loss": 1.9797,
      "step": 134
    },
    {
      "epoch": 0.17770952172005267,
      "grad_norm": 0.20078622953607106,
      "learning_rate": 4.95971445427137e-07,
      "loss": 1.9812,
      "step": 135
    },
    {
      "epoch": 0.1790258885476086,
      "grad_norm": 0.20339808928794587,
      "learning_rate": 4.3251137959302023e-07,
      "loss": 1.9692,
      "step": 136
    },
    {
      "epoch": 0.18034225537516455,
      "grad_norm": 0.20627429081407878,
      "learning_rate": 3.733044478364234e-07,
      "loss": 1.9652,
      "step": 137
    },
    {
      "epoch": 0.1816586222027205,
      "grad_norm": 0.20321443113928203,
      "learning_rate": 3.1837697002341293e-07,
      "loss": 1.9776,
      "step": 138
    },
    {
      "epoch": 0.18297498903027642,
      "grad_norm": 0.19781262257649188,
      "learning_rate": 2.677533636303964e-07,
      "loss": 1.9681,
      "step": 139
    },
    {
      "epoch": 0.18429135585783238,
      "grad_norm": 0.20077922644328586,
      "learning_rate": 2.214561328895748e-07,
      "loss": 1.9727,
      "step": 140
    },
    {
      "epoch": 0.18560772268538833,
      "grad_norm": 0.2083473030555337,
      "learning_rate": 1.7950585878489856e-07,
      "loss": 1.9778,
      "step": 141
    },
    {
      "epoch": 0.18692408951294429,
      "grad_norm": 0.20761426168347388,
      "learning_rate": 1.419211899029971e-07,
      "loss": 1.9694,
      "step": 142
    },
    {
      "epoch": 0.1882404563405002,
      "grad_norm": 0.20428193433533662,
      "learning_rate": 1.0871883414312778e-07,
      "loss": 1.9805,
      "step": 143
    },
    {
      "epoch": 0.18955682316805617,
      "grad_norm": 0.19799699957898195,
      "learning_rate": 7.99135512898408e-08,
      "loss": 1.9721,
      "step": 144
    },
    {
      "epoch": 0.19087318999561212,
      "grad_norm": 0.1949656470521933,
      "learning_rate": 5.55181464516652e-08,
      "loss": 1.9737,
      "step": 145
    },
    {
      "epoch": 0.19218955682316805,
      "grad_norm": 0.20400087106043757,
      "learning_rate": 3.554346436871581e-08,
      "loss": 1.9697,
      "step": 146
    },
    {
      "epoch": 0.193505923650724,
      "grad_norm": 0.2040243897683087,
      "learning_rate": 1.9998384591773945e-08,
      "loss": 1.9782,
      "step": 147
    },
    {
      "epoch": 0.19482229047827995,
      "grad_norm": 0.1993711508133477,
      "learning_rate": 8.889817534969425e-09,
      "loss": 1.986,
      "step": 148
    },
    {
      "epoch": 0.1961386573058359,
      "grad_norm": 0.2030943995914907,
      "learning_rate": 2.222701403818972e-09,
      "loss": 1.9748,
      "step": 149
    },
    {
      "epoch": 0.19745502413339183,
      "grad_norm": 0.21707727728816964,
      "learning_rate": 0.0,
      "loss": 1.9865,
      "step": 150
    },
    {
      "epoch": 0.19745502413339183,
      "step": 150,
      "total_flos": 349677715193856.0,
      "train_loss": 1.9023579597473144,
      "train_runtime": 5206.9725,
      "train_samples_per_second": 58.076,
      "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
}