{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0064524454768357204,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.45244547683572e-05,
      "grad_norm": 0.026197873055934906,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 10.3766,
      "step": 1
    },
    {
      "epoch": 6.45244547683572e-05,
      "eval_loss": 10.378262519836426,
      "eval_runtime": 93.5318,
      "eval_samples_per_second": 139.535,
      "eval_steps_per_second": 17.449,
      "step": 1
    },
    {
      "epoch": 0.0001290489095367144,
      "grad_norm": 0.026936905458569527,
      "learning_rate": 4.000000000000001e-06,
      "loss": 10.3761,
      "step": 2
    },
    {
      "epoch": 0.00019357336430507162,
      "grad_norm": 0.0278240405023098,
      "learning_rate": 6e-06,
      "loss": 10.3782,
      "step": 3
    },
    {
      "epoch": 0.0002580978190734288,
      "grad_norm": 0.028583543375134468,
      "learning_rate": 8.000000000000001e-06,
      "loss": 10.3782,
      "step": 4
    },
    {
      "epoch": 0.00032262227384178605,
      "grad_norm": 0.030367162078619003,
      "learning_rate": 1e-05,
      "loss": 10.3771,
      "step": 5
    },
    {
      "epoch": 0.00038714672861014324,
      "grad_norm": 0.027288779616355896,
      "learning_rate": 1.2e-05,
      "loss": 10.3795,
      "step": 6
    },
    {
      "epoch": 0.00045167118337850043,
      "grad_norm": 0.03344113379716873,
      "learning_rate": 1.4e-05,
      "loss": 10.3786,
      "step": 7
    },
    {
      "epoch": 0.0005161956381468576,
      "grad_norm": 0.037574075162410736,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 10.3806,
      "step": 8
    },
    {
      "epoch": 0.0005807200929152149,
      "grad_norm": 0.026230480521917343,
      "learning_rate": 1.8e-05,
      "loss": 10.3782,
      "step": 9
    },
    {
      "epoch": 0.0005807200929152149,
      "eval_loss": 10.378217697143555,
      "eval_runtime": 94.5352,
      "eval_samples_per_second": 138.054,
      "eval_steps_per_second": 17.263,
      "step": 9
    },
    {
      "epoch": 0.0006452445476835721,
      "grad_norm": 0.02515924535691738,
      "learning_rate": 2e-05,
      "loss": 10.3785,
      "step": 10
    },
    {
      "epoch": 0.0007097690024519292,
      "grad_norm": 0.02741788886487484,
      "learning_rate": 1.999390827019096e-05,
      "loss": 10.3806,
      "step": 11
    },
    {
      "epoch": 0.0007742934572202865,
      "grad_norm": 0.027379022911190987,
      "learning_rate": 1.9975640502598243e-05,
      "loss": 10.3799,
      "step": 12
    },
    {
      "epoch": 0.0008388179119886437,
      "grad_norm": 0.026748251169919968,
      "learning_rate": 1.9945218953682736e-05,
      "loss": 10.3798,
      "step": 13
    },
    {
      "epoch": 0.0009033423667570009,
      "grad_norm": 0.025931736454367638,
      "learning_rate": 1.9902680687415704e-05,
      "loss": 10.3773,
      "step": 14
    },
    {
      "epoch": 0.0009678668215253581,
      "grad_norm": 0.023032773286104202,
      "learning_rate": 1.9848077530122083e-05,
      "loss": 10.3758,
      "step": 15
    },
    {
      "epoch": 0.0010323912762937152,
      "grad_norm": 0.024977397173643112,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 10.3763,
      "step": 16
    },
    {
      "epoch": 0.0010969157310620726,
      "grad_norm": 0.027897605672478676,
      "learning_rate": 1.9702957262759964e-05,
      "loss": 10.3797,
      "step": 17
    },
    {
      "epoch": 0.0011614401858304297,
      "grad_norm": 0.030990947037935257,
      "learning_rate": 1.961261695938319e-05,
      "loss": 10.3765,
      "step": 18
    },
    {
      "epoch": 0.0011614401858304297,
      "eval_loss": 10.378108024597168,
      "eval_runtime": 94.5084,
      "eval_samples_per_second": 138.094,
      "eval_steps_per_second": 17.268,
      "step": 18
    },
    {
      "epoch": 0.0012259646405987869,
      "grad_norm": 0.026416031643748283,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 10.3783,
      "step": 19
    },
    {
      "epoch": 0.0012904890953671442,
      "grad_norm": 0.02477899007499218,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 10.3752,
      "step": 20
    },
    {
      "epoch": 0.0013550135501355014,
      "grad_norm": 0.028769120573997498,
      "learning_rate": 1.9271838545667876e-05,
      "loss": 10.3786,
      "step": 21
    },
    {
      "epoch": 0.0014195380049038585,
      "grad_norm": 0.02721049264073372,
      "learning_rate": 1.913545457642601e-05,
      "loss": 10.3762,
      "step": 22
    },
    {
      "epoch": 0.0014840624596722158,
      "grad_norm": 0.02645275555551052,
      "learning_rate": 1.8987940462991673e-05,
      "loss": 10.3782,
      "step": 23
    },
    {
      "epoch": 0.001548586914440573,
      "grad_norm": 0.02513984404504299,
      "learning_rate": 1.8829475928589272e-05,
      "loss": 10.3774,
      "step": 24
    },
    {
      "epoch": 0.0016131113692089301,
      "grad_norm": 0.030071387067437172,
      "learning_rate": 1.866025403784439e-05,
      "loss": 10.3753,
      "step": 25
    },
    {
      "epoch": 0.0016776358239772875,
      "grad_norm": 0.030626939609646797,
      "learning_rate": 1.848048096156426e-05,
      "loss": 10.3774,
      "step": 26
    },
    {
      "epoch": 0.0017421602787456446,
      "grad_norm": 0.027455894276499748,
      "learning_rate": 1.8290375725550417e-05,
      "loss": 10.3808,
      "step": 27
    },
    {
      "epoch": 0.0017421602787456446,
      "eval_loss": 10.378000259399414,
      "eval_runtime": 94.0472,
      "eval_samples_per_second": 138.771,
      "eval_steps_per_second": 17.353,
      "step": 27
    },
    {
      "epoch": 0.0018066847335140017,
      "grad_norm": 0.02224784530699253,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 10.3797,
      "step": 28
    },
    {
      "epoch": 0.001871209188282359,
      "grad_norm": 0.02824169397354126,
      "learning_rate": 1.788010753606722e-05,
      "loss": 10.3793,
      "step": 29
    },
    {
      "epoch": 0.0019357336430507162,
      "grad_norm": 0.02937052957713604,
      "learning_rate": 1.766044443118978e-05,
      "loss": 10.3789,
      "step": 30
    },
    {
      "epoch": 0.0020002580978190736,
      "grad_norm": 0.028946861624717712,
      "learning_rate": 1.7431448254773943e-05,
      "loss": 10.3751,
      "step": 31
    },
    {
      "epoch": 0.0020647825525874305,
      "grad_norm": 0.027421152219176292,
      "learning_rate": 1.7193398003386514e-05,
      "loss": 10.3778,
      "step": 32
    },
    {
      "epoch": 0.002129307007355788,
      "grad_norm": 0.030297035351395607,
      "learning_rate": 1.6946583704589973e-05,
      "loss": 10.3787,
      "step": 33
    },
    {
      "epoch": 0.002193831462124145,
      "grad_norm": 0.025568794459104538,
      "learning_rate": 1.6691306063588583e-05,
      "loss": 10.377,
      "step": 34
    },
    {
      "epoch": 0.002258355916892502,
      "grad_norm": 0.028658976778388023,
      "learning_rate": 1.6427876096865394e-05,
      "loss": 10.3789,
      "step": 35
    },
    {
      "epoch": 0.0023228803716608595,
      "grad_norm": 0.0332128070294857,
      "learning_rate": 1.6156614753256583e-05,
      "loss": 10.3776,
      "step": 36
    },
    {
      "epoch": 0.0023228803716608595,
      "eval_loss": 10.377901077270508,
      "eval_runtime": 94.4464,
      "eval_samples_per_second": 138.184,
      "eval_steps_per_second": 17.28,
      "step": 36
    },
    {
      "epoch": 0.002387404826429217,
      "grad_norm": 0.027265075594186783,
      "learning_rate": 1.5877852522924733e-05,
      "loss": 10.3761,
      "step": 37
    },
    {
      "epoch": 0.0024519292811975737,
      "grad_norm": 0.025722986087203026,
      "learning_rate": 1.5591929034707468e-05,
      "loss": 10.3782,
      "step": 38
    },
    {
      "epoch": 0.002516453735965931,
      "grad_norm": 0.0297780092805624,
      "learning_rate": 1.529919264233205e-05,
      "loss": 10.3761,
      "step": 39
    },
    {
      "epoch": 0.0025809781907342884,
      "grad_norm": 0.02702772617340088,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 10.3811,
      "step": 40
    },
    {
      "epoch": 0.0026455026455026454,
      "grad_norm": 0.025780929252505302,
      "learning_rate": 1.469471562785891e-05,
      "loss": 10.3787,
      "step": 41
    },
    {
      "epoch": 0.0027100271002710027,
      "grad_norm": 0.03268590196967125,
      "learning_rate": 1.4383711467890776e-05,
      "loss": 10.3757,
      "step": 42
    },
    {
      "epoch": 0.00277455155503936,
      "grad_norm": 0.03610847145318985,
      "learning_rate": 1.4067366430758004e-05,
      "loss": 10.3788,
      "step": 43
    },
    {
      "epoch": 0.002839076009807717,
      "grad_norm": 0.02523721195757389,
      "learning_rate": 1.3746065934159123e-05,
      "loss": 10.378,
      "step": 44
    },
    {
      "epoch": 0.0029036004645760743,
      "grad_norm": 0.026593849062919617,
      "learning_rate": 1.342020143325669e-05,
      "loss": 10.3777,
      "step": 45
    },
    {
      "epoch": 0.0029036004645760743,
      "eval_loss": 10.377813339233398,
      "eval_runtime": 94.5001,
      "eval_samples_per_second": 138.106,
      "eval_steps_per_second": 17.27,
      "step": 45
    },
    {
      "epoch": 0.0029681249193444317,
      "grad_norm": 0.02478192001581192,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 10.3776,
      "step": 46
    },
    {
      "epoch": 0.0030326493741127886,
      "grad_norm": 0.031417760998010635,
      "learning_rate": 1.2756373558169992e-05,
      "loss": 10.3794,
      "step": 47
    },
    {
      "epoch": 0.003097173828881146,
      "grad_norm": 0.037823840975761414,
      "learning_rate": 1.2419218955996677e-05,
      "loss": 10.3782,
      "step": 48
    },
    {
      "epoch": 0.0031616982836495033,
      "grad_norm": 0.020790569484233856,
      "learning_rate": 1.2079116908177592e-05,
      "loss": 10.3787,
      "step": 49
    },
    {
      "epoch": 0.0032262227384178602,
      "grad_norm": 0.02425728552043438,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 10.3792,
      "step": 50
    },
    {
      "epoch": 0.0032907471931862176,
      "grad_norm": 0.02828303538262844,
      "learning_rate": 1.1391731009600655e-05,
      "loss": 10.3772,
      "step": 51
    },
    {
      "epoch": 0.003355271647954575,
      "grad_norm": 0.028103332966566086,
      "learning_rate": 1.1045284632676535e-05,
      "loss": 10.3762,
      "step": 52
    },
    {
      "epoch": 0.003419796102722932,
      "grad_norm": 0.03077799640595913,
      "learning_rate": 1.0697564737441254e-05,
      "loss": 10.3766,
      "step": 53
    },
    {
      "epoch": 0.003484320557491289,
      "grad_norm": 0.03291391581296921,
      "learning_rate": 1.0348994967025012e-05,
      "loss": 10.3748,
      "step": 54
    },
    {
      "epoch": 0.003484320557491289,
      "eval_loss": 10.377745628356934,
      "eval_runtime": 94.035,
      "eval_samples_per_second": 138.789,
      "eval_steps_per_second": 17.355,
      "step": 54
    },
    {
      "epoch": 0.0035488450122596465,
      "grad_norm": 0.03468142822384834,
      "learning_rate": 1e-05,
      "loss": 10.3785,
      "step": 55
    },
    {
      "epoch": 0.0036133694670280035,
      "grad_norm": 0.03757575526833534,
      "learning_rate": 9.651005032974994e-06,
      "loss": 10.3761,
      "step": 56
    },
    {
      "epoch": 0.003677893921796361,
      "grad_norm": 0.03238731622695923,
      "learning_rate": 9.302435262558748e-06,
      "loss": 10.378,
      "step": 57
    },
    {
      "epoch": 0.003742418376564718,
      "grad_norm": 0.03340912610292435,
      "learning_rate": 8.954715367323468e-06,
      "loss": 10.3801,
      "step": 58
    },
    {
      "epoch": 0.003806942831333075,
      "grad_norm": 0.027483763173222542,
      "learning_rate": 8.60826899039935e-06,
      "loss": 10.3769,
      "step": 59
    },
    {
      "epoch": 0.0038714672861014324,
      "grad_norm": 0.022548139095306396,
      "learning_rate": 8.263518223330698e-06,
      "loss": 10.3806,
      "step": 60
    },
    {
      "epoch": 0.00393599174086979,
      "grad_norm": 0.025931406766176224,
      "learning_rate": 7.92088309182241e-06,
      "loss": 10.3782,
      "step": 61
    },
    {
      "epoch": 0.004000516195638147,
      "grad_norm": 0.030363237485289574,
      "learning_rate": 7.580781044003324e-06,
      "loss": 10.3783,
      "step": 62
    },
    {
      "epoch": 0.0040650406504065045,
      "grad_norm": 0.027962248772382736,
      "learning_rate": 7.243626441830009e-06,
      "loss": 10.3784,
      "step": 63
    },
    {
      "epoch": 0.0040650406504065045,
      "eval_loss": 10.377690315246582,
      "eval_runtime": 94.4322,
      "eval_samples_per_second": 138.205,
      "eval_steps_per_second": 17.282,
      "step": 63
    },
    {
      "epoch": 0.004129565105174861,
      "grad_norm": 0.033061280846595764,
      "learning_rate": 6.909830056250527e-06,
      "loss": 10.3794,
      "step": 64
    },
    {
      "epoch": 0.004194089559943218,
      "grad_norm": 0.03424518555402756,
      "learning_rate": 6.579798566743314e-06,
      "loss": 10.3809,
      "step": 65
    },
    {
      "epoch": 0.004258614014711576,
      "grad_norm": 0.02736547961831093,
      "learning_rate": 6.25393406584088e-06,
      "loss": 10.375,
      "step": 66
    },
    {
      "epoch": 0.004323138469479933,
      "grad_norm": 0.02246510423719883,
      "learning_rate": 5.932633569242e-06,
      "loss": 10.38,
      "step": 67
    },
    {
      "epoch": 0.00438766292424829,
      "grad_norm": 0.026952644810080528,
      "learning_rate": 5.616288532109225e-06,
      "loss": 10.3753,
      "step": 68
    },
    {
      "epoch": 0.004452187379016648,
      "grad_norm": 0.02410932444036007,
      "learning_rate": 5.305284372141095e-06,
      "loss": 10.3783,
      "step": 69
    },
    {
      "epoch": 0.004516711833785004,
      "grad_norm": 0.021015537902712822,
      "learning_rate": 5.000000000000003e-06,
      "loss": 10.3784,
      "step": 70
    },
    {
      "epoch": 0.004581236288553362,
      "grad_norm": 0.028286607936024666,
      "learning_rate": 4.700807357667953e-06,
      "loss": 10.3785,
      "step": 71
    },
    {
      "epoch": 0.004645760743321719,
      "grad_norm": 0.02780069038271904,
      "learning_rate": 4.408070965292534e-06,
      "loss": 10.3771,
      "step": 72
    },
    {
      "epoch": 0.004645760743321719,
      "eval_loss": 10.377655029296875,
      "eval_runtime": 94.3929,
      "eval_samples_per_second": 138.262,
      "eval_steps_per_second": 17.289,
      "step": 72
    },
    {
      "epoch": 0.004710285198090076,
      "grad_norm": 0.02527373470366001,
      "learning_rate": 4.12214747707527e-06,
      "loss": 10.3751,
      "step": 73
    },
    {
      "epoch": 0.004774809652858434,
      "grad_norm": 0.030667316168546677,
      "learning_rate": 3.8433852467434175e-06,
      "loss": 10.3789,
      "step": 74
    },
    {
      "epoch": 0.004839334107626791,
      "grad_norm": 0.024445723742246628,
      "learning_rate": 3.5721239031346067e-06,
      "loss": 10.3765,
      "step": 75
    },
    {
      "epoch": 0.0049038585623951475,
      "grad_norm": 0.027317577973008156,
      "learning_rate": 3.308693936411421e-06,
      "loss": 10.3783,
      "step": 76
    },
    {
      "epoch": 0.004968383017163505,
      "grad_norm": 0.025673918426036835,
      "learning_rate": 3.0534162954100264e-06,
      "loss": 10.3762,
      "step": 77
    },
    {
      "epoch": 0.005032907471931862,
      "grad_norm": 0.02838023565709591,
      "learning_rate": 2.8066019966134907e-06,
      "loss": 10.3741,
      "step": 78
    },
    {
      "epoch": 0.0050974319267002195,
      "grad_norm": 0.033573299646377563,
      "learning_rate": 2.5685517452260566e-06,
      "loss": 10.3773,
      "step": 79
    },
    {
      "epoch": 0.005161956381468577,
      "grad_norm": 0.025929216295480728,
      "learning_rate": 2.339555568810221e-06,
      "loss": 10.3751,
      "step": 80
    },
    {
      "epoch": 0.005226480836236934,
      "grad_norm": 0.033958472311496735,
      "learning_rate": 2.119892463932781e-06,
      "loss": 10.3768,
      "step": 81
    },
    {
      "epoch": 0.005226480836236934,
      "eval_loss": 10.377635955810547,
      "eval_runtime": 93.9485,
      "eval_samples_per_second": 138.917,
      "eval_steps_per_second": 17.371,
      "step": 81
    },
    {
      "epoch": 0.005291005291005291,
      "grad_norm": 0.02693011797964573,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 10.375,
      "step": 82
    },
    {
      "epoch": 0.005355529745773648,
      "grad_norm": 0.03208151459693909,
      "learning_rate": 1.709624274449584e-06,
      "loss": 10.3803,
      "step": 83
    },
    {
      "epoch": 0.005420054200542005,
      "grad_norm": 0.028754878789186478,
      "learning_rate": 1.5195190384357405e-06,
      "loss": 10.3747,
      "step": 84
    },
    {
      "epoch": 0.005484578655310363,
      "grad_norm": 0.025995273143053055,
      "learning_rate": 1.339745962155613e-06,
      "loss": 10.3748,
      "step": 85
    },
    {
      "epoch": 0.00554910311007872,
      "grad_norm": 0.026898324489593506,
      "learning_rate": 1.1705240714107301e-06,
      "loss": 10.378,
      "step": 86
    },
    {
      "epoch": 0.0056136275648470775,
      "grad_norm": 0.02781934104859829,
      "learning_rate": 1.012059537008332e-06,
      "loss": 10.3788,
      "step": 87
    },
    {
      "epoch": 0.005678152019615434,
      "grad_norm": 0.03010799176990986,
      "learning_rate": 8.645454235739903e-07,
      "loss": 10.3764,
      "step": 88
    },
    {
      "epoch": 0.005742676474383791,
      "grad_norm": 0.02704032137989998,
      "learning_rate": 7.281614543321269e-07,
      "loss": 10.3737,
      "step": 89
    },
    {
      "epoch": 0.005807200929152149,
      "grad_norm": 0.02597571723163128,
      "learning_rate": 6.030737921409169e-07,
      "loss": 10.3775,
      "step": 90
    },
    {
      "epoch": 0.005807200929152149,
      "eval_loss": 10.377629280090332,
      "eval_runtime": 94.4816,
      "eval_samples_per_second": 138.133,
      "eval_steps_per_second": 17.273,
      "step": 90
    },
    {
      "epoch": 0.005871725383920506,
      "grad_norm": 0.03344319388270378,
      "learning_rate": 4.894348370484648e-07,
      "loss": 10.3786,
      "step": 91
    },
    {
      "epoch": 0.005936249838688863,
      "grad_norm": 0.025218836963176727,
      "learning_rate": 3.8738304061681107e-07,
      "loss": 10.3796,
      "step": 92
    },
    {
      "epoch": 0.006000774293457221,
      "grad_norm": 0.03514518216252327,
      "learning_rate": 2.970427372400353e-07,
      "loss": 10.3775,
      "step": 93
    },
    {
      "epoch": 0.006065298748225577,
      "grad_norm": 0.03037307597696781,
      "learning_rate": 2.1852399266194312e-07,
      "loss": 10.3771,
      "step": 94
    },
    {
      "epoch": 0.0061298232029939346,
      "grad_norm": 0.025971580296754837,
      "learning_rate": 1.519224698779198e-07,
      "loss": 10.3797,
      "step": 95
    },
    {
      "epoch": 0.006194347657762292,
      "grad_norm": 0.027631748467683792,
      "learning_rate": 9.731931258429638e-08,
      "loss": 10.3774,
      "step": 96
    },
    {
      "epoch": 0.006258872112530649,
      "grad_norm": 0.02829601615667343,
      "learning_rate": 5.4781046317267103e-08,
      "loss": 10.3786,
      "step": 97
    },
    {
      "epoch": 0.006323396567299007,
      "grad_norm": 0.032121721655130386,
      "learning_rate": 2.4359497401758026e-08,
      "loss": 10.3746,
      "step": 98
    },
    {
      "epoch": 0.006387921022067364,
      "grad_norm": 0.033310312777757645,
      "learning_rate": 6.091729809042379e-09,
      "loss": 10.3775,
      "step": 99
    },
    {
      "epoch": 0.006387921022067364,
      "eval_loss": 10.377626419067383,
      "eval_runtime": 94.5259,
      "eval_samples_per_second": 138.068,
      "eval_steps_per_second": 17.265,
      "step": 99
    },
    {
      "epoch": 0.0064524454768357204,
      "grad_norm": 0.03267132118344307,
      "learning_rate": 0.0,
      "loss": 10.3777,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5387151998976.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}