{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01086484137331595,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001086484137331595,
      "grad_norm": 1.5099513530731201,
      "learning_rate": 1e-05,
      "loss": 10.4046,
      "step": 1
    },
    {
      "epoch": 0.0001086484137331595,
      "eval_loss": 10.412325859069824,
      "eval_runtime": 49.9215,
      "eval_samples_per_second": 155.264,
      "eval_steps_per_second": 19.41,
      "step": 1
    },
    {
      "epoch": 0.000217296827466319,
      "grad_norm": 1.6217904090881348,
      "learning_rate": 2e-05,
      "loss": 10.3875,
      "step": 2
    },
    {
      "epoch": 0.0003259452411994785,
      "grad_norm": 1.2565022706985474,
      "learning_rate": 3e-05,
      "loss": 10.4123,
      "step": 3
    },
    {
      "epoch": 0.000434593654932638,
      "grad_norm": 1.4051614999771118,
      "learning_rate": 4e-05,
      "loss": 10.3964,
      "step": 4
    },
    {
      "epoch": 0.0005432420686657974,
      "grad_norm": 1.3535511493682861,
      "learning_rate": 5e-05,
      "loss": 10.4142,
      "step": 5
    },
    {
      "epoch": 0.000651890482398957,
      "grad_norm": 1.4999443292617798,
      "learning_rate": 6e-05,
      "loss": 10.3977,
      "step": 6
    },
    {
      "epoch": 0.0007605388961321165,
      "grad_norm": 1.3049250841140747,
      "learning_rate": 7e-05,
      "loss": 10.432,
      "step": 7
    },
    {
      "epoch": 0.000869187309865276,
      "grad_norm": 1.4855458736419678,
      "learning_rate": 8e-05,
      "loss": 10.4005,
      "step": 8
    },
    {
      "epoch": 0.0009778357235984355,
      "grad_norm": 1.406107783317566,
      "learning_rate": 9e-05,
      "loss": 10.4181,
      "step": 9
    },
    {
      "epoch": 0.0009778357235984355,
      "eval_loss": 10.399271011352539,
      "eval_runtime": 51.0349,
      "eval_samples_per_second": 151.877,
      "eval_steps_per_second": 18.987,
      "step": 9
    },
    {
      "epoch": 0.0010864841373315949,
      "grad_norm": 1.486843466758728,
      "learning_rate": 0.0001,
      "loss": 10.3952,
      "step": 10
    },
    {
      "epoch": 0.0011951325510647544,
      "grad_norm": 1.6207181215286255,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3736,
      "step": 11
    },
    {
      "epoch": 0.001303780964797914,
      "grad_norm": 1.467222809791565,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3963,
      "step": 12
    },
    {
      "epoch": 0.0014124293785310734,
      "grad_norm": 1.4670981168746948,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.3987,
      "step": 13
    },
    {
      "epoch": 0.001521077792264233,
      "grad_norm": 1.519575834274292,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.373,
      "step": 14
    },
    {
      "epoch": 0.0016297262059973925,
      "grad_norm": 1.5052906274795532,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3953,
      "step": 15
    },
    {
      "epoch": 0.001738374619730552,
      "grad_norm": 1.284813404083252,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3941,
      "step": 16
    },
    {
      "epoch": 0.0018470230334637113,
      "grad_norm": 1.4351565837860107,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3775,
      "step": 17
    },
    {
      "epoch": 0.001955671447196871,
      "grad_norm": 1.5797349214553833,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3798,
      "step": 18
    },
    {
      "epoch": 0.001955671447196871,
      "eval_loss": 10.36672306060791,
      "eval_runtime": 50.7013,
      "eval_samples_per_second": 152.876,
      "eval_steps_per_second": 19.112,
      "step": 18
    },
    {
      "epoch": 0.0020643198609300306,
      "grad_norm": 1.5637619495391846,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3719,
      "step": 19
    },
    {
      "epoch": 0.0021729682746631897,
      "grad_norm": 1.66817045211792,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3421,
      "step": 20
    },
    {
      "epoch": 0.0022816166883963492,
      "grad_norm": 1.4857240915298462,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3808,
      "step": 21
    },
    {
      "epoch": 0.0023902651021295088,
      "grad_norm": 1.6014432907104492,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3393,
      "step": 22
    },
    {
      "epoch": 0.0024989135158626683,
      "grad_norm": 1.5560365915298462,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3411,
      "step": 23
    },
    {
      "epoch": 0.002607561929595828,
      "grad_norm": 1.60709547996521,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3514,
      "step": 24
    },
    {
      "epoch": 0.0027162103433289874,
      "grad_norm": 1.4551864862442017,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3411,
      "step": 25
    },
    {
      "epoch": 0.002824858757062147,
      "grad_norm": 1.67805016040802,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3366,
      "step": 26
    },
    {
      "epoch": 0.0029335071707953064,
      "grad_norm": 1.5231330394744873,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3398,
      "step": 27
    },
    {
      "epoch": 0.0029335071707953064,
      "eval_loss": 10.332958221435547,
      "eval_runtime": 50.6164,
      "eval_samples_per_second": 153.132,
      "eval_steps_per_second": 19.144,
      "step": 27
    },
    {
      "epoch": 0.003042155584528466,
      "grad_norm": 1.7659465074539185,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.331,
      "step": 28
    },
    {
      "epoch": 0.0031508039982616255,
      "grad_norm": 1.6914821863174438,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3354,
      "step": 29
    },
    {
      "epoch": 0.003259452411994785,
      "grad_norm": 1.7179479598999023,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3135,
      "step": 30
    },
    {
      "epoch": 0.0033681008257279445,
      "grad_norm": 1.6100873947143555,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3158,
      "step": 31
    },
    {
      "epoch": 0.003476749239461104,
      "grad_norm": 1.5977933406829834,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3014,
      "step": 32
    },
    {
      "epoch": 0.003585397653194263,
      "grad_norm": 1.5835942029953003,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3178,
      "step": 33
    },
    {
      "epoch": 0.0036940460669274227,
      "grad_norm": 1.5189638137817383,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.317,
      "step": 34
    },
    {
      "epoch": 0.003802694480660582,
      "grad_norm": 1.5402252674102783,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3151,
      "step": 35
    },
    {
      "epoch": 0.003911342894393742,
      "grad_norm": 1.6104727983474731,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.2874,
      "step": 36
    },
    {
      "epoch": 0.003911342894393742,
      "eval_loss": 10.299212455749512,
      "eval_runtime": 50.866,
      "eval_samples_per_second": 152.381,
      "eval_steps_per_second": 19.05,
      "step": 36
    },
    {
      "epoch": 0.004019991308126901,
      "grad_norm": 1.610350251197815,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3047,
      "step": 37
    },
    {
      "epoch": 0.004128639721860061,
      "grad_norm": 1.5481282472610474,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.2996,
      "step": 38
    },
    {
      "epoch": 0.00423728813559322,
      "grad_norm": 1.247719168663025,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3214,
      "step": 39
    },
    {
      "epoch": 0.004345936549326379,
      "grad_norm": 1.5715504884719849,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3132,
      "step": 40
    },
    {
      "epoch": 0.004454584963059539,
      "grad_norm": 1.5834615230560303,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.2998,
      "step": 41
    },
    {
      "epoch": 0.0045632333767926985,
      "grad_norm": 1.3792880773544312,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3017,
      "step": 42
    },
    {
      "epoch": 0.0046718817905258584,
      "grad_norm": 1.5816736221313477,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.2933,
      "step": 43
    },
    {
      "epoch": 0.0047805302042590175,
      "grad_norm": 1.5913182497024536,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.2781,
      "step": 44
    },
    {
      "epoch": 0.0048891786179921775,
      "grad_norm": 1.6335688829421997,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.2657,
      "step": 45
    },
    {
      "epoch": 0.0048891786179921775,
      "eval_loss": 10.27038288116455,
      "eval_runtime": 50.9692,
      "eval_samples_per_second": 152.072,
      "eval_steps_per_second": 19.011,
      "step": 45
    },
    {
      "epoch": 0.004997827031725337,
      "grad_norm": 1.475588321685791,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.2898,
      "step": 46
    },
    {
      "epoch": 0.0051064754454584966,
      "grad_norm": 1.5345820188522339,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.2616,
      "step": 47
    },
    {
      "epoch": 0.005215123859191656,
      "grad_norm": 1.508804440498352,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.2893,
      "step": 48
    },
    {
      "epoch": 0.005323772272924816,
      "grad_norm": 1.4398443698883057,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.2821,
      "step": 49
    },
    {
      "epoch": 0.005432420686657975,
      "grad_norm": 1.4615792036056519,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.2633,
      "step": 50
    },
    {
      "epoch": 0.005541069100391135,
      "grad_norm": 1.425754189491272,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.254,
      "step": 51
    },
    {
      "epoch": 0.005649717514124294,
      "grad_norm": 1.575873851776123,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.2354,
      "step": 52
    },
    {
      "epoch": 0.005758365927857453,
      "grad_norm": 1.4261200428009033,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.2575,
      "step": 53
    },
    {
      "epoch": 0.005867014341590613,
      "grad_norm": 1.4143245220184326,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.2419,
      "step": 54
    },
    {
      "epoch": 0.005867014341590613,
      "eval_loss": 10.2475004196167,
      "eval_runtime": 50.3307,
      "eval_samples_per_second": 154.002,
      "eval_steps_per_second": 19.253,
      "step": 54
    },
    {
      "epoch": 0.005975662755323772,
      "grad_norm": 1.402956485748291,
      "learning_rate": 5e-05,
      "loss": 10.244,
      "step": 55
    },
    {
      "epoch": 0.006084311169056932,
      "grad_norm": 1.4193462133407593,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.2596,
      "step": 56
    },
    {
      "epoch": 0.006192959582790091,
      "grad_norm": 1.451875925064087,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.2356,
      "step": 57
    },
    {
      "epoch": 0.006301607996523251,
      "grad_norm": 1.4304717779159546,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.2335,
      "step": 58
    },
    {
      "epoch": 0.00641025641025641,
      "grad_norm": 1.2412749528884888,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.2883,
      "step": 59
    },
    {
      "epoch": 0.00651890482398957,
      "grad_norm": 1.3596646785736084,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.2176,
      "step": 60
    },
    {
      "epoch": 0.006627553237722729,
      "grad_norm": 1.325228214263916,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.2421,
      "step": 61
    },
    {
      "epoch": 0.006736201651455889,
      "grad_norm": 1.3296804428100586,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.2198,
      "step": 62
    },
    {
      "epoch": 0.006844850065189048,
      "grad_norm": 1.313968539237976,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.2505,
      "step": 63
    },
    {
      "epoch": 0.006844850065189048,
      "eval_loss": 10.231610298156738,
      "eval_runtime": 50.925,
      "eval_samples_per_second": 152.204,
      "eval_steps_per_second": 19.028,
      "step": 63
    },
    {
      "epoch": 0.006953498478922208,
      "grad_norm": 1.3507755994796753,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.2458,
      "step": 64
    },
    {
      "epoch": 0.007062146892655367,
      "grad_norm": 1.4658613204956055,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.2765,
      "step": 65
    },
    {
      "epoch": 0.007170795306388526,
      "grad_norm": 1.410145878791809,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.2188,
      "step": 66
    },
    {
      "epoch": 0.007279443720121686,
      "grad_norm": 1.3317679166793823,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.2431,
      "step": 67
    },
    {
      "epoch": 0.007388092133854845,
      "grad_norm": 1.3417940139770508,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.2381,
      "step": 68
    },
    {
      "epoch": 0.007496740547588005,
      "grad_norm": 1.2955317497253418,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.2199,
      "step": 69
    },
    {
      "epoch": 0.007605388961321164,
      "grad_norm": 1.2896071672439575,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.2168,
      "step": 70
    },
    {
      "epoch": 0.007714037375054324,
      "grad_norm": 1.2548023462295532,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.2155,
      "step": 71
    },
    {
      "epoch": 0.007822685788787484,
      "grad_norm": 1.2902367115020752,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.2043,
      "step": 72
    },
    {
      "epoch": 0.007822685788787484,
      "eval_loss": 10.221445083618164,
      "eval_runtime": 51.0101,
      "eval_samples_per_second": 151.95,
      "eval_steps_per_second": 18.996,
      "step": 72
    },
    {
      "epoch": 0.007931334202520643,
      "grad_norm": 1.3279486894607544,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.2459,
      "step": 73
    },
    {
      "epoch": 0.008039982616253803,
      "grad_norm": 1.2856497764587402,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.2218,
      "step": 74
    },
    {
      "epoch": 0.008148631029986962,
      "grad_norm": 1.2557402849197388,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.2338,
      "step": 75
    },
    {
      "epoch": 0.008257279443720122,
      "grad_norm": 1.230995535850525,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.24,
      "step": 76
    },
    {
      "epoch": 0.00836592785745328,
      "grad_norm": 1.2729625701904297,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.2335,
      "step": 77
    },
    {
      "epoch": 0.00847457627118644,
      "grad_norm": 1.2476736307144165,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.2116,
      "step": 78
    },
    {
      "epoch": 0.0085832246849196,
      "grad_norm": 1.2497066259384155,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.222,
      "step": 79
    },
    {
      "epoch": 0.008691873098652759,
      "grad_norm": 1.2957948446273804,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.1891,
      "step": 80
    },
    {
      "epoch": 0.008800521512385919,
      "grad_norm": 1.2511223554611206,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.2187,
      "step": 81
    },
    {
      "epoch": 0.008800521512385919,
      "eval_loss": 10.216525077819824,
      "eval_runtime": 50.3835,
      "eval_samples_per_second": 153.84,
      "eval_steps_per_second": 19.232,
      "step": 81
    },
    {
      "epoch": 0.008909169926119079,
      "grad_norm": 1.133992314338684,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.2158,
      "step": 82
    },
    {
      "epoch": 0.009017818339852239,
      "grad_norm": 1.1790755987167358,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.2158,
      "step": 83
    },
    {
      "epoch": 0.009126466753585397,
      "grad_norm": 1.2124773263931274,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.2046,
      "step": 84
    },
    {
      "epoch": 0.009235115167318557,
      "grad_norm": 1.2567768096923828,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.2164,
      "step": 85
    },
    {
      "epoch": 0.009343763581051717,
      "grad_norm": 1.2171235084533691,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.2074,
      "step": 86
    },
    {
      "epoch": 0.009452411994784877,
      "grad_norm": 1.239092230796814,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.2059,
      "step": 87
    },
    {
      "epoch": 0.009561060408518035,
      "grad_norm": 1.2312257289886475,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.2176,
      "step": 88
    },
    {
      "epoch": 0.009669708822251195,
      "grad_norm": 1.2067418098449707,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.2194,
      "step": 89
    },
    {
      "epoch": 0.009778357235984355,
      "grad_norm": 1.205758810043335,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.2083,
      "step": 90
    },
    {
      "epoch": 0.009778357235984355,
      "eval_loss": 10.214375495910645,
      "eval_runtime": 50.8288,
      "eval_samples_per_second": 152.492,
      "eval_steps_per_second": 19.064,
      "step": 90
    },
    {
      "epoch": 0.009887005649717515,
      "grad_norm": 1.233474612236023,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.2168,
      "step": 91
    },
    {
      "epoch": 0.009995654063450673,
      "grad_norm": 1.2249033451080322,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.2072,
      "step": 92
    },
    {
      "epoch": 0.010104302477183833,
      "grad_norm": 1.2261874675750732,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.2294,
      "step": 93
    },
    {
      "epoch": 0.010212950890916993,
      "grad_norm": 1.2400648593902588,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.2298,
      "step": 94
    },
    {
      "epoch": 0.010321599304650151,
      "grad_norm": 1.2564033269882202,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.1955,
      "step": 95
    },
    {
      "epoch": 0.010430247718383311,
      "grad_norm": 1.2460192441940308,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.2174,
      "step": 96
    },
    {
      "epoch": 0.010538896132116471,
      "grad_norm": 1.2550164461135864,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.2145,
      "step": 97
    },
    {
      "epoch": 0.010647544545849631,
      "grad_norm": 1.2537856101989746,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.2281,
      "step": 98
    },
    {
      "epoch": 0.01075619295958279,
      "grad_norm": 1.248205304145813,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.2172,
      "step": 99
    },
    {
      "epoch": 0.01075619295958279,
      "eval_loss": 10.214019775390625,
      "eval_runtime": 51.002,
      "eval_samples_per_second": 151.974,
      "eval_steps_per_second": 18.999,
      "step": 99
    },
    {
      "epoch": 0.01086484137331595,
      "grad_norm": 1.2180185317993164,
      "learning_rate": 0.0,
      "loss": 10.2542,
      "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": 5230244659200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}