{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004824101209643378,
  "eval_steps": 10,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.412050604821689e-05,
      "grad_norm": 0.3311931788921356,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.3917,
      "step": 1
    },
    {
      "epoch": 4.824101209643378e-05,
      "grad_norm": 0.36366409063339233,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.4217,
      "step": 2
    },
    {
      "epoch": 7.236151814465067e-05,
      "grad_norm": 0.4242905378341675,
      "learning_rate": 1.5e-06,
      "loss": 0.4494,
      "step": 3
    },
    {
      "epoch": 9.648202419286756e-05,
      "grad_norm": 0.44046923518180847,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.467,
      "step": 4
    },
    {
      "epoch": 0.00012060253024108446,
      "grad_norm": 0.43109330534935,
      "learning_rate": 2.5e-06,
      "loss": 0.399,
      "step": 5
    },
    {
      "epoch": 0.00014472303628930135,
      "grad_norm": 0.37163135409355164,
      "learning_rate": 3e-06,
      "loss": 0.416,
      "step": 6
    },
    {
      "epoch": 0.00016884354233751825,
      "grad_norm": 0.397931307554245,
      "learning_rate": 3.5e-06,
      "loss": 0.4039,
      "step": 7
    },
    {
      "epoch": 0.00019296404838573512,
      "grad_norm": 0.36651691794395447,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.4518,
      "step": 8
    },
    {
      "epoch": 0.00021708455443395202,
      "grad_norm": 0.349309504032135,
      "learning_rate": 4.5e-06,
      "loss": 0.4782,
      "step": 9
    },
    {
      "epoch": 0.00024120506048216892,
      "grad_norm": 0.31746530532836914,
      "learning_rate": 5e-06,
      "loss": 0.3917,
      "step": 10
    },
    {
      "epoch": 0.00024120506048216892,
      "eval_loss": 0.45264774560928345,
      "eval_runtime": 657.2223,
      "eval_samples_per_second": 7.608,
      "eval_steps_per_second": 0.951,
      "step": 10
    },
    {
      "epoch": 0.0002653255665303858,
      "grad_norm": 0.34506547451019287,
      "learning_rate": 5.500000000000001e-06,
      "loss": 0.4271,
      "step": 11
    },
    {
      "epoch": 0.0002894460725786027,
      "grad_norm": 0.4447789788246155,
      "learning_rate": 6e-06,
      "loss": 0.5429,
      "step": 12
    },
    {
      "epoch": 0.00031356657862681957,
      "grad_norm": 0.34325507283210754,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 0.3699,
      "step": 13
    },
    {
      "epoch": 0.0003376870846750365,
      "grad_norm": 0.35941290855407715,
      "learning_rate": 7e-06,
      "loss": 0.4605,
      "step": 14
    },
    {
      "epoch": 0.00036180759072325337,
      "grad_norm": 0.38586971163749695,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.3847,
      "step": 15
    },
    {
      "epoch": 0.00038592809677147024,
      "grad_norm": 0.3841964304447174,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.411,
      "step": 16
    },
    {
      "epoch": 0.00041004860281968717,
      "grad_norm": 0.31548720598220825,
      "learning_rate": 8.5e-06,
      "loss": 0.4286,
      "step": 17
    },
    {
      "epoch": 0.00043416910886790404,
      "grad_norm": 0.42913171648979187,
      "learning_rate": 9e-06,
      "loss": 0.3874,
      "step": 18
    },
    {
      "epoch": 0.0004582896149161209,
      "grad_norm": 0.3180011212825775,
      "learning_rate": 9.5e-06,
      "loss": 0.4092,
      "step": 19
    },
    {
      "epoch": 0.00048241012096433784,
      "grad_norm": 0.4252677857875824,
      "learning_rate": 1e-05,
      "loss": 0.4409,
      "step": 20
    },
    {
      "epoch": 0.00048241012096433784,
      "eval_loss": 0.4525415897369385,
      "eval_runtime": 656.0202,
      "eval_samples_per_second": 7.622,
      "eval_steps_per_second": 0.953,
      "step": 20
    },
    {
      "epoch": 0.0005065306270125548,
      "grad_norm": 0.31288692355155945,
      "learning_rate": 9.999238475781957e-06,
      "loss": 0.3856,
      "step": 21
    },
    {
      "epoch": 0.0005306511330607716,
      "grad_norm": 0.3625168800354004,
      "learning_rate": 9.99695413509548e-06,
      "loss": 0.3992,
      "step": 22
    },
    {
      "epoch": 0.0005547716391089885,
      "grad_norm": 0.35107535123825073,
      "learning_rate": 9.993147673772869e-06,
      "loss": 0.3698,
      "step": 23
    },
    {
      "epoch": 0.0005788921451572054,
      "grad_norm": 0.33317747712135315,
      "learning_rate": 9.987820251299121e-06,
      "loss": 0.4249,
      "step": 24
    },
    {
      "epoch": 0.0006030126512054223,
      "grad_norm": 0.4086032807826996,
      "learning_rate": 9.980973490458728e-06,
      "loss": 0.4147,
      "step": 25
    },
    {
      "epoch": 0.0006271331572536391,
      "grad_norm": 0.33728134632110596,
      "learning_rate": 9.972609476841368e-06,
      "loss": 0.6989,
      "step": 26
    },
    {
      "epoch": 0.0006512536633018561,
      "grad_norm": 0.39848724007606506,
      "learning_rate": 9.962730758206612e-06,
      "loss": 0.4486,
      "step": 27
    },
    {
      "epoch": 0.000675374169350073,
      "grad_norm": 0.34975698590278625,
      "learning_rate": 9.951340343707852e-06,
      "loss": 0.3723,
      "step": 28
    },
    {
      "epoch": 0.0006994946753982899,
      "grad_norm": 0.3892325758934021,
      "learning_rate": 9.938441702975689e-06,
      "loss": 0.4762,
      "step": 29
    },
    {
      "epoch": 0.0007236151814465067,
      "grad_norm": 0.3921200633049011,
      "learning_rate": 9.924038765061042e-06,
      "loss": 0.4013,
      "step": 30
    },
    {
      "epoch": 0.0007236151814465067,
      "eval_loss": 0.452525794506073,
      "eval_runtime": 655.6748,
      "eval_samples_per_second": 7.626,
      "eval_steps_per_second": 0.953,
      "step": 30
    },
    {
      "epoch": 0.0007477356874947236,
      "grad_norm": 0.37671831250190735,
      "learning_rate": 9.908135917238321e-06,
      "loss": 0.3528,
      "step": 31
    },
    {
      "epoch": 0.0007718561935429405,
      "grad_norm": 0.34523534774780273,
      "learning_rate": 9.890738003669029e-06,
      "loss": 0.3735,
      "step": 32
    },
    {
      "epoch": 0.0007959766995911575,
      "grad_norm": 0.3326350152492523,
      "learning_rate": 9.871850323926178e-06,
      "loss": 0.4244,
      "step": 33
    },
    {
      "epoch": 0.0008200972056393743,
      "grad_norm": 0.37781861424446106,
      "learning_rate": 9.851478631379982e-06,
      "loss": 0.4553,
      "step": 34
    },
    {
      "epoch": 0.0008442177116875912,
      "grad_norm": 0.30233579874038696,
      "learning_rate": 9.829629131445342e-06,
      "loss": 0.4206,
      "step": 35
    },
    {
      "epoch": 0.0008683382177358081,
      "grad_norm": 0.3557078242301941,
      "learning_rate": 9.806308479691595e-06,
      "loss": 0.4207,
      "step": 36
    },
    {
      "epoch": 0.000892458723784025,
      "grad_norm": 0.3661990165710449,
      "learning_rate": 9.781523779815178e-06,
      "loss": 0.3499,
      "step": 37
    },
    {
      "epoch": 0.0009165792298322418,
      "grad_norm": 0.4143652021884918,
      "learning_rate": 9.755282581475769e-06,
      "loss": 0.4779,
      "step": 38
    },
    {
      "epoch": 0.0009406997358804588,
      "grad_norm": 0.36712220311164856,
      "learning_rate": 9.727592877996585e-06,
      "loss": 0.372,
      "step": 39
    },
    {
      "epoch": 0.0009648202419286757,
      "grad_norm": 0.3797116279602051,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.4588,
      "step": 40
    },
    {
      "epoch": 0.0009648202419286757,
      "eval_loss": 0.45261332392692566,
      "eval_runtime": 655.9483,
      "eval_samples_per_second": 7.623,
      "eval_steps_per_second": 0.953,
      "step": 40
    },
    {
      "epoch": 0.0009889407479768924,
      "grad_norm": 0.36112263798713684,
      "learning_rate": 9.667902132486009e-06,
      "loss": 0.4352,
      "step": 41
    },
    {
      "epoch": 0.0010130612540251095,
      "grad_norm": 0.3398573398590088,
      "learning_rate": 9.635919272833938e-06,
      "loss": 0.3985,
      "step": 42
    },
    {
      "epoch": 0.0010371817600733264,
      "grad_norm": 0.346431165933609,
      "learning_rate": 9.602524267262202e-06,
      "loss": 0.3879,
      "step": 43
    },
    {
      "epoch": 0.0010613022661215433,
      "grad_norm": 0.3009112775325775,
      "learning_rate": 9.567727288213005e-06,
      "loss": 0.3579,
      "step": 44
    },
    {
      "epoch": 0.0010854227721697602,
      "grad_norm": 0.4043431580066681,
      "learning_rate": 9.531538935183252e-06,
      "loss": 0.3802,
      "step": 45
    },
    {
      "epoch": 0.001109543278217977,
      "grad_norm": 0.4328388273715973,
      "learning_rate": 9.493970231495836e-06,
      "loss": 0.4506,
      "step": 46
    },
    {
      "epoch": 0.001133663784266194,
      "grad_norm": 0.36453568935394287,
      "learning_rate": 9.45503262094184e-06,
      "loss": 0.4507,
      "step": 47
    },
    {
      "epoch": 0.0011577842903144108,
      "grad_norm": 0.3751208484172821,
      "learning_rate": 9.414737964294636e-06,
      "loss": 0.3647,
      "step": 48
    },
    {
      "epoch": 0.0011819047963626276,
      "grad_norm": 0.3901105523109436,
      "learning_rate": 9.37309853569698e-06,
      "loss": 0.5013,
      "step": 49
    },
    {
      "epoch": 0.0012060253024108445,
      "grad_norm": 0.39861851930618286,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.4235,
      "step": 50
    },
    {
      "epoch": 0.0012060253024108445,
      "eval_loss": 0.4526110291481018,
      "eval_runtime": 656.5834,
      "eval_samples_per_second": 7.615,
      "eval_steps_per_second": 0.952,
      "step": 50
    },
    {
      "epoch": 0.0012301458084590614,
      "grad_norm": 0.35804349184036255,
      "learning_rate": 9.285836503510562e-06,
      "loss": 0.4019,
      "step": 51
    },
    {
      "epoch": 0.0012542663145072783,
      "grad_norm": 0.3577058017253876,
      "learning_rate": 9.24024048078213e-06,
      "loss": 0.5008,
      "step": 52
    },
    {
      "epoch": 0.0012783868205554954,
      "grad_norm": 0.3320634961128235,
      "learning_rate": 9.193352839727122e-06,
      "loss": 0.3664,
      "step": 53
    },
    {
      "epoch": 0.0013025073266037122,
      "grad_norm": 0.3395422101020813,
      "learning_rate": 9.145187862775208e-06,
      "loss": 0.4601,
      "step": 54
    },
    {
      "epoch": 0.001326627832651929,
      "grad_norm": 0.3735017776489258,
      "learning_rate": 9.09576022144496e-06,
      "loss": 0.3625,
      "step": 55
    },
    {
      "epoch": 0.001350748338700146,
      "grad_norm": 0.32877814769744873,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.4697,
      "step": 56
    },
    {
      "epoch": 0.0013748688447483629,
      "grad_norm": 0.49061062932014465,
      "learning_rate": 8.993177550236464e-06,
      "loss": 0.4022,
      "step": 57
    },
    {
      "epoch": 0.0013989893507965797,
      "grad_norm": 0.34869322180747986,
      "learning_rate": 8.94005376803361e-06,
      "loss": 0.3819,
      "step": 58
    },
    {
      "epoch": 0.0014231098568447966,
      "grad_norm": 0.351443886756897,
      "learning_rate": 8.885729807284855e-06,
      "loss": 0.4243,
      "step": 59
    },
    {
      "epoch": 0.0014472303628930135,
      "grad_norm": 0.48456260561943054,
      "learning_rate": 8.83022221559489e-06,
      "loss": 0.4152,
      "step": 60
    },
    {
      "epoch": 0.0014472303628930135,
      "eval_loss": 0.4525233507156372,
      "eval_runtime": 656.2728,
      "eval_samples_per_second": 7.619,
      "eval_steps_per_second": 0.952,
      "step": 60
    },
    {
      "epoch": 0.0014713508689412303,
      "grad_norm": 0.43146228790283203,
      "learning_rate": 8.773547901113862e-06,
      "loss": 0.4737,
      "step": 61
    },
    {
      "epoch": 0.0014954713749894472,
      "grad_norm": 0.35852473974227905,
      "learning_rate": 8.715724127386971e-06,
      "loss": 0.4752,
      "step": 62
    },
    {
      "epoch": 0.001519591881037664,
      "grad_norm": 0.3449285328388214,
      "learning_rate": 8.656768508095853e-06,
      "loss": 0.4155,
      "step": 63
    },
    {
      "epoch": 0.001543712387085881,
      "grad_norm": 0.35961848497390747,
      "learning_rate": 8.596699001693257e-06,
      "loss": 0.4416,
      "step": 64
    },
    {
      "epoch": 0.001567832893134098,
      "grad_norm": 0.36116358637809753,
      "learning_rate": 8.535533905932739e-06,
      "loss": 0.4277,
      "step": 65
    },
    {
      "epoch": 0.001591953399182315,
      "grad_norm": 0.4412328898906708,
      "learning_rate": 8.473291852294986e-06,
      "loss": 0.4025,
      "step": 66
    },
    {
      "epoch": 0.0016160739052305318,
      "grad_norm": 0.40739718079566956,
      "learning_rate": 8.409991800312493e-06,
      "loss": 0.5103,
      "step": 67
    },
    {
      "epoch": 0.0016401944112787487,
      "grad_norm": 0.3543914556503296,
      "learning_rate": 8.345653031794292e-06,
      "loss": 0.4714,
      "step": 68
    },
    {
      "epoch": 0.0016643149173269655,
      "grad_norm": 0.4757019877433777,
      "learning_rate": 8.280295144952537e-06,
      "loss": 0.5055,
      "step": 69
    },
    {
      "epoch": 0.0016884354233751824,
      "grad_norm": 0.40691736340522766,
      "learning_rate": 8.213938048432697e-06,
      "loss": 0.4448,
      "step": 70
    },
    {
      "epoch": 0.0016884354233751824,
      "eval_loss": 0.45241475105285645,
      "eval_runtime": 656.4012,
      "eval_samples_per_second": 7.617,
      "eval_steps_per_second": 0.952,
      "step": 70
    },
    {
      "epoch": 0.0017125559294233993,
      "grad_norm": 0.40699589252471924,
      "learning_rate": 8.146601955249187e-06,
      "loss": 0.4413,
      "step": 71
    },
    {
      "epoch": 0.0017366764354716162,
      "grad_norm": 0.3769061267375946,
      "learning_rate": 8.078307376628292e-06,
      "loss": 0.4598,
      "step": 72
    },
    {
      "epoch": 0.001760796941519833,
      "grad_norm": 0.4408392906188965,
      "learning_rate": 8.009075115760243e-06,
      "loss": 0.4181,
      "step": 73
    },
    {
      "epoch": 0.00178491744756805,
      "grad_norm": 0.3539417088031769,
      "learning_rate": 7.938926261462366e-06,
      "loss": 0.4573,
      "step": 74
    },
    {
      "epoch": 0.0018090379536162668,
      "grad_norm": 0.4681709110736847,
      "learning_rate": 7.86788218175523e-06,
      "loss": 0.528,
      "step": 75
    },
    {
      "epoch": 0.0018331584596644837,
      "grad_norm": 0.40181297063827515,
      "learning_rate": 7.795964517353734e-06,
      "loss": 0.4113,
      "step": 76
    },
    {
      "epoch": 0.0018572789657127007,
      "grad_norm": 0.3092106580734253,
      "learning_rate": 7.723195175075136e-06,
      "loss": 0.3763,
      "step": 77
    },
    {
      "epoch": 0.0018813994717609176,
      "grad_norm": 0.35467004776000977,
      "learning_rate": 7.649596321166024e-06,
      "loss": 0.382,
      "step": 78
    },
    {
      "epoch": 0.0019055199778091345,
      "grad_norm": 0.38216719031333923,
      "learning_rate": 7.575190374550272e-06,
      "loss": 0.4819,
      "step": 79
    },
    {
      "epoch": 0.0019296404838573514,
      "grad_norm": 0.3604303002357483,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.4073,
      "step": 80
    },
    {
      "epoch": 0.0019296404838573514,
      "eval_loss": 0.45228177309036255,
      "eval_runtime": 656.4261,
      "eval_samples_per_second": 7.617,
      "eval_steps_per_second": 0.952,
      "step": 80
    },
    {
      "epoch": 0.0019537609899055682,
      "grad_norm": 0.44827160239219666,
      "learning_rate": 7.424048101231687e-06,
      "loss": 0.4619,
      "step": 81
    },
    {
      "epoch": 0.001977881495953785,
      "grad_norm": 0.3786572217941284,
      "learning_rate": 7.347357813929455e-06,
      "loss": 0.4302,
      "step": 82
    },
    {
      "epoch": 0.002002002002002002,
      "grad_norm": 0.35757017135620117,
      "learning_rate": 7.269952498697734e-06,
      "loss": 0.3991,
      "step": 83
    },
    {
      "epoch": 0.002026122508050219,
      "grad_norm": 0.3329964578151703,
      "learning_rate": 7.191855733945388e-06,
      "loss": 0.4032,
      "step": 84
    },
    {
      "epoch": 0.0020502430140984357,
      "grad_norm": 0.4239315390586853,
      "learning_rate": 7.113091308703498e-06,
      "loss": 0.3927,
      "step": 85
    },
    {
      "epoch": 0.002074363520146653,
      "grad_norm": 0.30143341422080994,
      "learning_rate": 7.033683215379002e-06,
      "loss": 0.3472,
      "step": 86
    },
    {
      "epoch": 0.0020984840261948695,
      "grad_norm": 0.43596914410591125,
      "learning_rate": 6.953655642446368e-06,
      "loss": 0.4735,
      "step": 87
    },
    {
      "epoch": 0.0021226045322430866,
      "grad_norm": 0.3773175776004791,
      "learning_rate": 6.873032967079562e-06,
      "loss": 0.369,
      "step": 88
    },
    {
      "epoch": 0.0021467250382913032,
      "grad_norm": 0.34213048219680786,
      "learning_rate": 6.7918397477265e-06,
      "loss": 0.3906,
      "step": 89
    },
    {
      "epoch": 0.0021708455443395203,
      "grad_norm": 0.3846489489078522,
      "learning_rate": 6.710100716628345e-06,
      "loss": 0.3817,
      "step": 90
    },
    {
      "epoch": 0.0021708455443395203,
      "eval_loss": 0.45225536823272705,
      "eval_runtime": 656.8503,
      "eval_samples_per_second": 7.612,
      "eval_steps_per_second": 0.952,
      "step": 90
    },
    {
      "epoch": 0.002194966050387737,
      "grad_norm": 0.3564792275428772,
      "learning_rate": 6.627840772285784e-06,
      "loss": 0.3358,
      "step": 91
    },
    {
      "epoch": 0.002219086556435954,
      "grad_norm": 0.40026184916496277,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.473,
      "step": 92
    },
    {
      "epoch": 0.0022432070624841707,
      "grad_norm": 0.4029349088668823,
      "learning_rate": 6.461858523613684e-06,
      "loss": 0.4073,
      "step": 93
    },
    {
      "epoch": 0.002267327568532388,
      "grad_norm": 0.39364010095596313,
      "learning_rate": 6.378186779084996e-06,
      "loss": 0.4213,
      "step": 94
    },
    {
      "epoch": 0.002291448074580605,
      "grad_norm": 0.3491790294647217,
      "learning_rate": 6.294095225512604e-06,
      "loss": 0.4252,
      "step": 95
    },
    {
      "epoch": 0.0023155685806288216,
      "grad_norm": 0.39630284905433655,
      "learning_rate": 6.209609477998339e-06,
      "loss": 0.4484,
      "step": 96
    },
    {
      "epoch": 0.0023396890866770386,
      "grad_norm": 0.38778364658355713,
      "learning_rate": 6.124755271719326e-06,
      "loss": 0.4152,
      "step": 97
    },
    {
      "epoch": 0.0023638095927252553,
      "grad_norm": 0.3973414897918701,
      "learning_rate": 6.039558454088796e-06,
      "loss": 0.5188,
      "step": 98
    },
    {
      "epoch": 0.0023879300987734724,
      "grad_norm": 0.3545883893966675,
      "learning_rate": 5.954044976882725e-06,
      "loss": 0.3939,
      "step": 99
    },
    {
      "epoch": 0.002412050604821689,
      "grad_norm": 0.377933144569397,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 0.3927,
      "step": 100
    },
    {
      "epoch": 0.002412050604821689,
      "eval_loss": 0.4522687494754791,
      "eval_runtime": 656.1353,
      "eval_samples_per_second": 7.62,
      "eval_steps_per_second": 0.953,
      "step": 100
    },
    {
      "epoch": 0.002436171110869906,
      "grad_norm": 0.405863493680954,
      "learning_rate": 5.782172325201155e-06,
      "loss": 0.4153,
      "step": 101
    },
    {
      "epoch": 0.002460291616918123,
      "grad_norm": 0.3857528567314148,
      "learning_rate": 5.695865504800328e-06,
      "loss": 0.4545,
      "step": 102
    },
    {
      "epoch": 0.00248441212296634,
      "grad_norm": 0.3878491520881653,
      "learning_rate": 5.609346717025738e-06,
      "loss": 0.4443,
      "step": 103
    },
    {
      "epoch": 0.0025085326290145565,
      "grad_norm": 0.34467750787734985,
      "learning_rate": 5.522642316338268e-06,
      "loss": 0.4375,
      "step": 104
    },
    {
      "epoch": 0.0025326531350627736,
      "grad_norm": 0.45316892862319946,
      "learning_rate": 5.435778713738292e-06,
      "loss": 0.5197,
      "step": 105
    },
    {
      "epoch": 0.0025567736411109907,
      "grad_norm": 0.4341200888156891,
      "learning_rate": 5.348782368720627e-06,
      "loss": 0.3831,
      "step": 106
    },
    {
      "epoch": 0.0025808941471592074,
      "grad_norm": 0.35221683979034424,
      "learning_rate": 5.2616797812147205e-06,
      "loss": 0.3923,
      "step": 107
    },
    {
      "epoch": 0.0026050146532074245,
      "grad_norm": 0.3838233947753906,
      "learning_rate": 5.174497483512506e-06,
      "loss": 0.356,
      "step": 108
    },
    {
      "epoch": 0.002629135159255641,
      "grad_norm": 0.41011756658554077,
      "learning_rate": 5.087262032186418e-06,
      "loss": 0.5793,
      "step": 109
    },
    {
      "epoch": 0.002653255665303858,
      "grad_norm": 0.36588796973228455,
      "learning_rate": 5e-06,
      "loss": 0.4389,
      "step": 110
    },
    {
      "epoch": 0.002653255665303858,
      "eval_loss": 0.4522809088230133,
      "eval_runtime": 656.6352,
      "eval_samples_per_second": 7.615,
      "eval_steps_per_second": 0.952,
      "step": 110
    },
    {
      "epoch": 0.002677376171352075,
      "grad_norm": 0.4244416058063507,
      "learning_rate": 4.9127379678135825e-06,
      "loss": 0.4446,
      "step": 111
    },
    {
      "epoch": 0.002701496677400292,
      "grad_norm": 0.2862201929092407,
      "learning_rate": 4.825502516487497e-06,
      "loss": 0.3354,
      "step": 112
    },
    {
      "epoch": 0.0027256171834485086,
      "grad_norm": 0.3602610230445862,
      "learning_rate": 4.738320218785281e-06,
      "loss": 0.3866,
      "step": 113
    },
    {
      "epoch": 0.0027497376894967257,
      "grad_norm": 0.37873271107673645,
      "learning_rate": 4.651217631279374e-06,
      "loss": 0.3666,
      "step": 114
    },
    {
      "epoch": 0.0027738581955449424,
      "grad_norm": 0.34318113327026367,
      "learning_rate": 4.564221286261709e-06,
      "loss": 0.3987,
      "step": 115
    },
    {
      "epoch": 0.0027979787015931594,
      "grad_norm": 0.4408251643180847,
      "learning_rate": 4.477357683661734e-06,
      "loss": 0.3931,
      "step": 116
    },
    {
      "epoch": 0.002822099207641376,
      "grad_norm": 0.3661717474460602,
      "learning_rate": 4.390653282974264e-06,
      "loss": 0.3798,
      "step": 117
    },
    {
      "epoch": 0.002846219713689593,
      "grad_norm": 0.32164856791496277,
      "learning_rate": 4.304134495199675e-06,
      "loss": 0.4482,
      "step": 118
    },
    {
      "epoch": 0.0028703402197378103,
      "grad_norm": 0.3605085015296936,
      "learning_rate": 4.217827674798845e-06,
      "loss": 0.4035,
      "step": 119
    },
    {
      "epoch": 0.002894460725786027,
      "grad_norm": 0.37207821011543274,
      "learning_rate": 4.131759111665349e-06,
      "loss": 0.3745,
      "step": 120
    },
    {
      "epoch": 0.002894460725786027,
      "eval_loss": 0.4523176848888397,
      "eval_runtime": 655.8999,
      "eval_samples_per_second": 7.623,
      "eval_steps_per_second": 0.953,
      "step": 120
    },
    {
      "epoch": 0.002918581231834244,
      "grad_norm": 0.37908729910850525,
      "learning_rate": 4.045955023117276e-06,
      "loss": 0.4563,
      "step": 121
    },
    {
      "epoch": 0.0029427017378824607,
      "grad_norm": 0.3790426254272461,
      "learning_rate": 3.960441545911205e-06,
      "loss": 0.4842,
      "step": 122
    },
    {
      "epoch": 0.0029668222439306778,
      "grad_norm": 0.41289275884628296,
      "learning_rate": 3.875244728280676e-06,
      "loss": 0.4354,
      "step": 123
    },
    {
      "epoch": 0.0029909427499788944,
      "grad_norm": 0.42376378178596497,
      "learning_rate": 3.790390522001662e-06,
      "loss": 0.4343,
      "step": 124
    },
    {
      "epoch": 0.0030150632560271115,
      "grad_norm": 0.3424387276172638,
      "learning_rate": 3.705904774487396e-06,
      "loss": 0.4985,
      "step": 125
    },
    {
      "epoch": 0.003039183762075328,
      "grad_norm": 0.36581212282180786,
      "learning_rate": 3.6218132209150047e-06,
      "loss": 0.3527,
      "step": 126
    },
    {
      "epoch": 0.0030633042681235453,
      "grad_norm": 0.38337764143943787,
      "learning_rate": 3.538141476386317e-06,
      "loss": 0.3984,
      "step": 127
    },
    {
      "epoch": 0.003087424774171762,
      "grad_norm": 0.40349331498146057,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.4642,
      "step": 128
    },
    {
      "epoch": 0.003111545280219979,
      "grad_norm": 0.4810910224914551,
      "learning_rate": 3.372159227714218e-06,
      "loss": 0.3634,
      "step": 129
    },
    {
      "epoch": 0.003135665786268196,
      "grad_norm": 0.3497662842273712,
      "learning_rate": 3.289899283371657e-06,
      "loss": 0.4154,
      "step": 130
    },
    {
      "epoch": 0.003135665786268196,
      "eval_loss": 0.4523341655731201,
      "eval_runtime": 655.5944,
      "eval_samples_per_second": 7.627,
      "eval_steps_per_second": 0.953,
      "step": 130
    },
    {
      "epoch": 0.0031597862923164128,
      "grad_norm": 0.386590838432312,
      "learning_rate": 3.2081602522734987e-06,
      "loss": 0.4812,
      "step": 131
    },
    {
      "epoch": 0.00318390679836463,
      "grad_norm": 0.4523124098777771,
      "learning_rate": 3.12696703292044e-06,
      "loss": 0.4677,
      "step": 132
    },
    {
      "epoch": 0.0032080273044128465,
      "grad_norm": 0.3832690715789795,
      "learning_rate": 3.0463443575536324e-06,
      "loss": 0.463,
      "step": 133
    },
    {
      "epoch": 0.0032321478104610636,
      "grad_norm": 0.3430319130420685,
      "learning_rate": 2.966316784621e-06,
      "loss": 0.4157,
      "step": 134
    },
    {
      "epoch": 0.0032562683165092803,
      "grad_norm": 0.3613578975200653,
      "learning_rate": 2.886908691296504e-06,
      "loss": 0.4374,
      "step": 135
    },
    {
      "epoch": 0.0032803888225574973,
      "grad_norm": 0.3682035505771637,
      "learning_rate": 2.8081442660546126e-06,
      "loss": 0.4025,
      "step": 136
    },
    {
      "epoch": 0.003304509328605714,
      "grad_norm": 0.39483726024627686,
      "learning_rate": 2.7300475013022666e-06,
      "loss": 0.4197,
      "step": 137
    },
    {
      "epoch": 0.003328629834653931,
      "grad_norm": 0.43622323870658875,
      "learning_rate": 2.6526421860705474e-06,
      "loss": 0.4006,
      "step": 138
    },
    {
      "epoch": 0.0033527503407021477,
      "grad_norm": 0.3498108685016632,
      "learning_rate": 2.5759518987683154e-06,
      "loss": 0.4095,
      "step": 139
    },
    {
      "epoch": 0.003376870846750365,
      "grad_norm": 0.39195385575294495,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.39,
      "step": 140
    },
    {
      "epoch": 0.003376870846750365,
      "eval_loss": 0.4523204565048218,
      "eval_runtime": 656.4586,
      "eval_samples_per_second": 7.617,
      "eval_steps_per_second": 0.952,
      "step": 140
    },
    {
      "epoch": 0.003400991352798582,
      "grad_norm": 0.3237302303314209,
      "learning_rate": 2.424809625449729e-06,
      "loss": 0.46,
      "step": 141
    },
    {
      "epoch": 0.0034251118588467986,
      "grad_norm": 0.4392617344856262,
      "learning_rate": 2.3504036788339763e-06,
      "loss": 0.4872,
      "step": 142
    },
    {
      "epoch": 0.0034492323648950157,
      "grad_norm": 0.45489931106567383,
      "learning_rate": 2.2768048249248648e-06,
      "loss": 0.4423,
      "step": 143
    },
    {
      "epoch": 0.0034733528709432323,
      "grad_norm": 0.31627240777015686,
      "learning_rate": 2.204035482646267e-06,
      "loss": 0.4867,
      "step": 144
    },
    {
      "epoch": 0.0034974733769914494,
      "grad_norm": 0.3952763080596924,
      "learning_rate": 2.132117818244771e-06,
      "loss": 0.3602,
      "step": 145
    },
    {
      "epoch": 0.003521593883039666,
      "grad_norm": 0.38230791687965393,
      "learning_rate": 2.061073738537635e-06,
      "loss": 0.3765,
      "step": 146
    },
    {
      "epoch": 0.003545714389087883,
      "grad_norm": 0.35084497928619385,
      "learning_rate": 1.990924884239758e-06,
      "loss": 0.4487,
      "step": 147
    },
    {
      "epoch": 0.0035698348951361,
      "grad_norm": 0.43376678228378296,
      "learning_rate": 1.9216926233717087e-06,
      "loss": 0.3875,
      "step": 148
    },
    {
      "epoch": 0.003593955401184317,
      "grad_norm": 0.3624168336391449,
      "learning_rate": 1.8533980447508138e-06,
      "loss": 0.3496,
      "step": 149
    },
    {
      "epoch": 0.0036180759072325336,
      "grad_norm": 0.3335222601890564,
      "learning_rate": 1.7860619515673034e-06,
      "loss": 0.3329,
      "step": 150
    },
    {
      "epoch": 0.0036180759072325336,
      "eval_loss": 0.45227569341659546,
      "eval_runtime": 655.6445,
      "eval_samples_per_second": 7.626,
      "eval_steps_per_second": 0.953,
      "step": 150
    },
    {
      "epoch": 0.0036421964132807507,
      "grad_norm": 0.39886796474456787,
      "learning_rate": 1.7197048550474643e-06,
      "loss": 0.4374,
      "step": 151
    },
    {
      "epoch": 0.0036663169193289673,
      "grad_norm": 0.36089280247688293,
      "learning_rate": 1.6543469682057105e-06,
      "loss": 0.4437,
      "step": 152
    },
    {
      "epoch": 0.0036904374253771844,
      "grad_norm": 0.4028494954109192,
      "learning_rate": 1.5900081996875083e-06,
      "loss": 0.4092,
      "step": 153
    },
    {
      "epoch": 0.0037145579314254015,
      "grad_norm": 0.34552139043807983,
      "learning_rate": 1.5267081477050132e-06,
      "loss": 0.4125,
      "step": 154
    },
    {
      "epoch": 0.003738678437473618,
      "grad_norm": 0.3772471845149994,
      "learning_rate": 1.4644660940672628e-06,
      "loss": 0.3705,
      "step": 155
    },
    {
      "epoch": 0.0037627989435218352,
      "grad_norm": 0.3887017071247101,
      "learning_rate": 1.4033009983067454e-06,
      "loss": 0.3919,
      "step": 156
    },
    {
      "epoch": 0.003786919449570052,
      "grad_norm": 0.41117388010025024,
      "learning_rate": 1.3432314919041478e-06,
      "loss": 0.427,
      "step": 157
    },
    {
      "epoch": 0.003811039955618269,
      "grad_norm": 0.5241091847419739,
      "learning_rate": 1.2842758726130283e-06,
      "loss": 0.4188,
      "step": 158
    },
    {
      "epoch": 0.0038351604616664856,
      "grad_norm": 0.36033713817596436,
      "learning_rate": 1.22645209888614e-06,
      "loss": 0.5107,
      "step": 159
    },
    {
      "epoch": 0.0038592809677147027,
      "grad_norm": 0.39244335889816284,
      "learning_rate": 1.1697777844051105e-06,
      "loss": 0.4801,
      "step": 160
    },
    {
      "epoch": 0.0038592809677147027,
      "eval_loss": 0.4522644877433777,
      "eval_runtime": 656.1739,
      "eval_samples_per_second": 7.62,
      "eval_steps_per_second": 0.952,
      "step": 160
    },
    {
      "epoch": 0.0038834014737629194,
      "grad_norm": 0.3368006944656372,
      "learning_rate": 1.1142701927151456e-06,
      "loss": 0.455,
      "step": 161
    },
    {
      "epoch": 0.0039075219798111365,
      "grad_norm": 0.3198925256729126,
      "learning_rate": 1.0599462319663906e-06,
      "loss": 0.4003,
      "step": 162
    },
    {
      "epoch": 0.003931642485859354,
      "grad_norm": 0.41680222749710083,
      "learning_rate": 1.006822449763537e-06,
      "loss": 0.5181,
      "step": 163
    },
    {
      "epoch": 0.00395576299190757,
      "grad_norm": 0.4605503976345062,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.4181,
      "step": 164
    },
    {
      "epoch": 0.003979883497955787,
      "grad_norm": 0.3941374719142914,
      "learning_rate": 9.042397785550405e-07,
      "loss": 0.4428,
      "step": 165
    },
    {
      "epoch": 0.004004004004004004,
      "grad_norm": 0.3564678132534027,
      "learning_rate": 8.54812137224792e-07,
      "loss": 0.3859,
      "step": 166
    },
    {
      "epoch": 0.004028124510052221,
      "grad_norm": 0.405307799577713,
      "learning_rate": 8.066471602728804e-07,
      "loss": 0.44,
      "step": 167
    },
    {
      "epoch": 0.004052245016100438,
      "grad_norm": 0.35025468468666077,
      "learning_rate": 7.597595192178702e-07,
      "loss": 0.4707,
      "step": 168
    },
    {
      "epoch": 0.004076365522148654,
      "grad_norm": 0.4460391700267792,
      "learning_rate": 7.141634964894389e-07,
      "loss": 0.4446,
      "step": 169
    },
    {
      "epoch": 0.0041004860281968715,
      "grad_norm": 0.3382282853126526,
      "learning_rate": 6.698729810778065e-07,
      "loss": 0.4604,
      "step": 170
    },
    {
      "epoch": 0.0041004860281968715,
      "eval_loss": 0.45224910974502563,
      "eval_runtime": 655.6744,
      "eval_samples_per_second": 7.626,
      "eval_steps_per_second": 0.953,
      "step": 170
    },
    {
      "epoch": 0.0041246065342450886,
      "grad_norm": 0.3316885828971863,
      "learning_rate": 6.269014643030214e-07,
      "loss": 0.39,
      "step": 171
    },
    {
      "epoch": 0.004148727040293306,
      "grad_norm": 0.37666186690330505,
      "learning_rate": 5.852620357053651e-07,
      "loss": 0.3344,
      "step": 172
    },
    {
      "epoch": 0.004172847546341522,
      "grad_norm": 0.311280220746994,
      "learning_rate": 5.449673790581611e-07,
      "loss": 0.3873,
      "step": 173
    },
    {
      "epoch": 0.004196968052389739,
      "grad_norm": 0.3799581825733185,
      "learning_rate": 5.06029768504166e-07,
      "loss": 0.468,
      "step": 174
    },
    {
      "epoch": 0.004221088558437956,
      "grad_norm": 0.347642183303833,
      "learning_rate": 4.6846106481675035e-07,
      "loss": 0.4674,
      "step": 175
    },
    {
      "epoch": 0.004245209064486173,
      "grad_norm": 0.3709600865840912,
      "learning_rate": 4.322727117869951e-07,
      "loss": 0.5441,
      "step": 176
    },
    {
      "epoch": 0.00426932957053439,
      "grad_norm": 0.3888307809829712,
      "learning_rate": 3.9747573273779816e-07,
      "loss": 0.5416,
      "step": 177
    },
    {
      "epoch": 0.0042934500765826064,
      "grad_norm": 0.37339866161346436,
      "learning_rate": 3.6408072716606346e-07,
      "loss": 0.4391,
      "step": 178
    },
    {
      "epoch": 0.0043175705826308235,
      "grad_norm": 0.3653758466243744,
      "learning_rate": 3.320978675139919e-07,
      "loss": 0.5056,
      "step": 179
    },
    {
      "epoch": 0.004341691088679041,
      "grad_norm": 0.3997964560985565,
      "learning_rate": 3.015368960704584e-07,
      "loss": 0.3809,
      "step": 180
    },
    {
      "epoch": 0.004341691088679041,
      "eval_loss": 0.45224234461784363,
      "eval_runtime": 656.2617,
      "eval_samples_per_second": 7.619,
      "eval_steps_per_second": 0.952,
      "step": 180
    },
    {
      "epoch": 0.004365811594727258,
      "grad_norm": 0.31695839762687683,
      "learning_rate": 2.724071220034158e-07,
      "loss": 0.4538,
      "step": 181
    },
    {
      "epoch": 0.004389932100775474,
      "grad_norm": 0.35246968269348145,
      "learning_rate": 2.447174185242324e-07,
      "loss": 0.4292,
      "step": 182
    },
    {
      "epoch": 0.004414052606823691,
      "grad_norm": 0.3488803505897522,
      "learning_rate": 2.1847622018482283e-07,
      "loss": 0.412,
      "step": 183
    },
    {
      "epoch": 0.004438173112871908,
      "grad_norm": 0.3700258135795593,
      "learning_rate": 1.9369152030840553e-07,
      "loss": 0.375,
      "step": 184
    },
    {
      "epoch": 0.004462293618920125,
      "grad_norm": 0.3783937990665436,
      "learning_rate": 1.7037086855465902e-07,
      "loss": 0.4448,
      "step": 185
    },
    {
      "epoch": 0.004486414124968341,
      "grad_norm": 0.3575262725353241,
      "learning_rate": 1.4852136862001766e-07,
      "loss": 0.3898,
      "step": 186
    },
    {
      "epoch": 0.0045105346310165585,
      "grad_norm": 0.3567143380641937,
      "learning_rate": 1.2814967607382433e-07,
      "loss": 0.4076,
      "step": 187
    },
    {
      "epoch": 0.004534655137064776,
      "grad_norm": 0.3481285572052002,
      "learning_rate": 1.0926199633097156e-07,
      "loss": 0.3369,
      "step": 188
    },
    {
      "epoch": 0.004558775643112993,
      "grad_norm": 0.3537425100803375,
      "learning_rate": 9.186408276168012e-08,
      "loss": 0.4935,
      "step": 189
    },
    {
      "epoch": 0.00458289614916121,
      "grad_norm": 0.44966480135917664,
      "learning_rate": 7.59612349389599e-08,
      "loss": 0.4258,
      "step": 190
    },
    {
      "epoch": 0.00458289614916121,
      "eval_loss": 0.45223602652549744,
      "eval_runtime": 656.4102,
      "eval_samples_per_second": 7.617,
      "eval_steps_per_second": 0.952,
      "step": 190
    },
    {
      "epoch": 0.004607016655209426,
      "grad_norm": 0.361909419298172,
      "learning_rate": 6.15582970243117e-08,
      "loss": 0.4188,
      "step": 191
    },
    {
      "epoch": 0.004631137161257643,
      "grad_norm": 0.39177781343460083,
      "learning_rate": 4.865965629214819e-08,
      "loss": 0.4596,
      "step": 192
    },
    {
      "epoch": 0.00465525766730586,
      "grad_norm": 0.35150718688964844,
      "learning_rate": 3.726924179339009e-08,
      "loss": 0.715,
      "step": 193
    },
    {
      "epoch": 0.004679378173354077,
      "grad_norm": 0.36558404564857483,
      "learning_rate": 2.7390523158633552e-08,
      "loss": 0.3912,
      "step": 194
    },
    {
      "epoch": 0.0047034986794022935,
      "grad_norm": 0.4544391632080078,
      "learning_rate": 1.9026509541272276e-08,
      "loss": 0.4655,
      "step": 195
    },
    {
      "epoch": 0.004727619185450511,
      "grad_norm": 0.34412747621536255,
      "learning_rate": 1.2179748700879013e-08,
      "loss": 0.4681,
      "step": 196
    },
    {
      "epoch": 0.004751739691498728,
      "grad_norm": 0.38506874442100525,
      "learning_rate": 6.852326227130835e-09,
      "loss": 0.4185,
      "step": 197
    },
    {
      "epoch": 0.004775860197546945,
      "grad_norm": 0.33594921231269836,
      "learning_rate": 3.0458649045211897e-09,
      "loss": 0.4004,
      "step": 198
    },
    {
      "epoch": 0.004799980703595161,
      "grad_norm": 0.4446846842765808,
      "learning_rate": 7.615242180436521e-10,
      "loss": 0.461,
      "step": 199
    },
    {
      "epoch": 0.004824101209643378,
      "grad_norm": 0.358017235994339,
      "learning_rate": 0.0,
      "loss": 0.4165,
      "step": 200
    },
    {
      "epoch": 0.004824101209643378,
      "eval_loss": 0.45223602652549744,
      "eval_runtime": 657.1445,
      "eval_samples_per_second": 7.609,
      "eval_steps_per_second": 0.951,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "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": 1.059439567662121e+17,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}