{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.28653295128939826,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0028653295128939827,
      "grad_norm": 0.18870845437049866,
      "learning_rate": 1e-05,
      "loss": 10.3647,
      "step": 1
    },
    {
      "epoch": 0.0028653295128939827,
      "eval_loss": 10.36025333404541,
      "eval_runtime": 1.0201,
      "eval_samples_per_second": 288.212,
      "eval_steps_per_second": 36.272,
      "step": 1
    },
    {
      "epoch": 0.0057306590257879654,
      "grad_norm": 0.21544590592384338,
      "learning_rate": 2e-05,
      "loss": 10.362,
      "step": 2
    },
    {
      "epoch": 0.008595988538681949,
      "grad_norm": 0.21012459695339203,
      "learning_rate": 3e-05,
      "loss": 10.3787,
      "step": 3
    },
    {
      "epoch": 0.011461318051575931,
      "grad_norm": 0.17221978306770325,
      "learning_rate": 4e-05,
      "loss": 10.3589,
      "step": 4
    },
    {
      "epoch": 0.014326647564469915,
      "grad_norm": 0.19953270256519318,
      "learning_rate": 5e-05,
      "loss": 10.3518,
      "step": 5
    },
    {
      "epoch": 0.017191977077363897,
      "grad_norm": 0.2154458910226822,
      "learning_rate": 6e-05,
      "loss": 10.3715,
      "step": 6
    },
    {
      "epoch": 0.02005730659025788,
      "grad_norm": 0.18448343873023987,
      "learning_rate": 7e-05,
      "loss": 10.3615,
      "step": 7
    },
    {
      "epoch": 0.022922636103151862,
      "grad_norm": 0.17267638444900513,
      "learning_rate": 8e-05,
      "loss": 10.3744,
      "step": 8
    },
    {
      "epoch": 0.025787965616045846,
      "grad_norm": 0.21264782547950745,
      "learning_rate": 9e-05,
      "loss": 10.3635,
      "step": 9
    },
    {
      "epoch": 0.025787965616045846,
      "eval_loss": 10.357918739318848,
      "eval_runtime": 1.0313,
      "eval_samples_per_second": 285.087,
      "eval_steps_per_second": 35.878,
      "step": 9
    },
    {
      "epoch": 0.02865329512893983,
      "grad_norm": 0.20090581476688385,
      "learning_rate": 0.0001,
      "loss": 10.3682,
      "step": 10
    },
    {
      "epoch": 0.03151862464183381,
      "grad_norm": 0.2009212225675583,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3545,
      "step": 11
    },
    {
      "epoch": 0.034383954154727794,
      "grad_norm": 0.17764975130558014,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3667,
      "step": 12
    },
    {
      "epoch": 0.03724928366762178,
      "grad_norm": 0.19756364822387695,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.3524,
      "step": 13
    },
    {
      "epoch": 0.04011461318051576,
      "grad_norm": 0.21011871099472046,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3613,
      "step": 14
    },
    {
      "epoch": 0.04297994269340974,
      "grad_norm": 0.20613764226436615,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3708,
      "step": 15
    },
    {
      "epoch": 0.045845272206303724,
      "grad_norm": 0.27395445108413696,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.347,
      "step": 16
    },
    {
      "epoch": 0.04871060171919771,
      "grad_norm": 0.20352178812026978,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3532,
      "step": 17
    },
    {
      "epoch": 0.05157593123209169,
      "grad_norm": 0.2129252851009369,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.354,
      "step": 18
    },
    {
      "epoch": 0.05157593123209169,
      "eval_loss": 10.35179328918457,
      "eval_runtime": 1.0103,
      "eval_samples_per_second": 290.994,
      "eval_steps_per_second": 36.622,
      "step": 18
    },
    {
      "epoch": 0.054441260744985676,
      "grad_norm": 0.1703406721353531,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3596,
      "step": 19
    },
    {
      "epoch": 0.05730659025787966,
      "grad_norm": 0.2214614599943161,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3457,
      "step": 20
    },
    {
      "epoch": 0.06017191977077364,
      "grad_norm": 0.2195059061050415,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3563,
      "step": 21
    },
    {
      "epoch": 0.06303724928366762,
      "grad_norm": 0.21687962114810944,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3525,
      "step": 22
    },
    {
      "epoch": 0.0659025787965616,
      "grad_norm": 0.20921839773654938,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3405,
      "step": 23
    },
    {
      "epoch": 0.06876790830945559,
      "grad_norm": 0.21130795776844025,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3536,
      "step": 24
    },
    {
      "epoch": 0.07163323782234957,
      "grad_norm": 0.22695602476596832,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3385,
      "step": 25
    },
    {
      "epoch": 0.07449856733524356,
      "grad_norm": 0.2284359186887741,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3517,
      "step": 26
    },
    {
      "epoch": 0.07736389684813753,
      "grad_norm": 0.22772260010242462,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3457,
      "step": 27
    },
    {
      "epoch": 0.07736389684813753,
      "eval_loss": 10.345144271850586,
      "eval_runtime": 1.0637,
      "eval_samples_per_second": 276.397,
      "eval_steps_per_second": 34.785,
      "step": 27
    },
    {
      "epoch": 0.08022922636103152,
      "grad_norm": 0.24294577538967133,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3317,
      "step": 28
    },
    {
      "epoch": 0.0830945558739255,
      "grad_norm": 0.2539214491844177,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3381,
      "step": 29
    },
    {
      "epoch": 0.08595988538681948,
      "grad_norm": 0.20477065443992615,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3582,
      "step": 30
    },
    {
      "epoch": 0.08882521489971347,
      "grad_norm": 0.21697883307933807,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3367,
      "step": 31
    },
    {
      "epoch": 0.09169054441260745,
      "grad_norm": 0.29203030467033386,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3243,
      "step": 32
    },
    {
      "epoch": 0.09455587392550144,
      "grad_norm": 0.23186412453651428,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3584,
      "step": 33
    },
    {
      "epoch": 0.09742120343839542,
      "grad_norm": 0.2152336984872818,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3469,
      "step": 34
    },
    {
      "epoch": 0.10028653295128939,
      "grad_norm": 0.2645852267742157,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3416,
      "step": 35
    },
    {
      "epoch": 0.10315186246418338,
      "grad_norm": 0.19434252381324768,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3436,
      "step": 36
    },
    {
      "epoch": 0.10315186246418338,
      "eval_loss": 10.338038444519043,
      "eval_runtime": 1.0423,
      "eval_samples_per_second": 282.056,
      "eval_steps_per_second": 35.497,
      "step": 36
    },
    {
      "epoch": 0.10601719197707736,
      "grad_norm": 0.2565288245677948,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3424,
      "step": 37
    },
    {
      "epoch": 0.10888252148997135,
      "grad_norm": 0.3266773819923401,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.3231,
      "step": 38
    },
    {
      "epoch": 0.11174785100286533,
      "grad_norm": 0.30517715215682983,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3282,
      "step": 39
    },
    {
      "epoch": 0.11461318051575932,
      "grad_norm": 0.213883176445961,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3301,
      "step": 40
    },
    {
      "epoch": 0.1174785100286533,
      "grad_norm": 0.23180383443832397,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.337,
      "step": 41
    },
    {
      "epoch": 0.12034383954154727,
      "grad_norm": 0.2547537088394165,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3492,
      "step": 42
    },
    {
      "epoch": 0.12320916905444126,
      "grad_norm": 0.3248274326324463,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.326,
      "step": 43
    },
    {
      "epoch": 0.12607449856733524,
      "grad_norm": 0.28297948837280273,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3352,
      "step": 44
    },
    {
      "epoch": 0.12893982808022922,
      "grad_norm": 0.2600502371788025,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3567,
      "step": 45
    },
    {
      "epoch": 0.12893982808022922,
      "eval_loss": 10.33073902130127,
      "eval_runtime": 1.0349,
      "eval_samples_per_second": 284.076,
      "eval_steps_per_second": 35.751,
      "step": 45
    },
    {
      "epoch": 0.1318051575931232,
      "grad_norm": 0.2766321301460266,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3338,
      "step": 46
    },
    {
      "epoch": 0.1346704871060172,
      "grad_norm": 0.2638920843601227,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.339,
      "step": 47
    },
    {
      "epoch": 0.13753581661891118,
      "grad_norm": 0.26153671741485596,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3352,
      "step": 48
    },
    {
      "epoch": 0.14040114613180515,
      "grad_norm": 0.27219700813293457,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.3293,
      "step": 49
    },
    {
      "epoch": 0.14326647564469913,
      "grad_norm": 0.2812553942203522,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3356,
      "step": 50
    },
    {
      "epoch": 0.14613180515759314,
      "grad_norm": 0.26205867528915405,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3289,
      "step": 51
    },
    {
      "epoch": 0.1489971346704871,
      "grad_norm": 0.2941390573978424,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.3359,
      "step": 52
    },
    {
      "epoch": 0.1518624641833811,
      "grad_norm": 0.30991968512535095,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3291,
      "step": 53
    },
    {
      "epoch": 0.15472779369627507,
      "grad_norm": 0.26404446363449097,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.324,
      "step": 54
    },
    {
      "epoch": 0.15472779369627507,
      "eval_loss": 10.3239107131958,
      "eval_runtime": 1.0645,
      "eval_samples_per_second": 276.186,
      "eval_steps_per_second": 34.758,
      "step": 54
    },
    {
      "epoch": 0.15759312320916904,
      "grad_norm": 0.23177841305732727,
      "learning_rate": 5e-05,
      "loss": 10.3431,
      "step": 55
    },
    {
      "epoch": 0.16045845272206305,
      "grad_norm": 0.2693847715854645,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3345,
      "step": 56
    },
    {
      "epoch": 0.16332378223495703,
      "grad_norm": 0.315563827753067,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3337,
      "step": 57
    },
    {
      "epoch": 0.166189111747851,
      "grad_norm": 0.2582322955131531,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3285,
      "step": 58
    },
    {
      "epoch": 0.16905444126074498,
      "grad_norm": 0.38031986355781555,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.307,
      "step": 59
    },
    {
      "epoch": 0.17191977077363896,
      "grad_norm": 0.33206507563591003,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3213,
      "step": 60
    },
    {
      "epoch": 0.17478510028653296,
      "grad_norm": 0.2936471402645111,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3271,
      "step": 61
    },
    {
      "epoch": 0.17765042979942694,
      "grad_norm": 0.320385217666626,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3251,
      "step": 62
    },
    {
      "epoch": 0.18051575931232092,
      "grad_norm": 0.3414050340652466,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3106,
      "step": 63
    },
    {
      "epoch": 0.18051575931232092,
      "eval_loss": 10.318222999572754,
      "eval_runtime": 1.0447,
      "eval_samples_per_second": 281.419,
      "eval_steps_per_second": 35.417,
      "step": 63
    },
    {
      "epoch": 0.1833810888252149,
      "grad_norm": 0.29449090361595154,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3208,
      "step": 64
    },
    {
      "epoch": 0.18624641833810887,
      "grad_norm": 0.318759560585022,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.327,
      "step": 65
    },
    {
      "epoch": 0.18911174785100288,
      "grad_norm": 0.32590019702911377,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3242,
      "step": 66
    },
    {
      "epoch": 0.19197707736389685,
      "grad_norm": 0.3307969570159912,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3131,
      "step": 67
    },
    {
      "epoch": 0.19484240687679083,
      "grad_norm": 0.270192950963974,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3285,
      "step": 68
    },
    {
      "epoch": 0.1977077363896848,
      "grad_norm": 0.3431764245033264,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3281,
      "step": 69
    },
    {
      "epoch": 0.20057306590257878,
      "grad_norm": 0.27470043301582336,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3218,
      "step": 70
    },
    {
      "epoch": 0.2034383954154728,
      "grad_norm": 0.29296571016311646,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.3186,
      "step": 71
    },
    {
      "epoch": 0.20630372492836677,
      "grad_norm": 0.335977166891098,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.3168,
      "step": 72
    },
    {
      "epoch": 0.20630372492836677,
      "eval_loss": 10.314079284667969,
      "eval_runtime": 1.025,
      "eval_samples_per_second": 286.826,
      "eval_steps_per_second": 36.097,
      "step": 72
    },
    {
      "epoch": 0.20916905444126074,
      "grad_norm": 0.3692624270915985,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3224,
      "step": 73
    },
    {
      "epoch": 0.21203438395415472,
      "grad_norm": 0.31396710872650146,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3251,
      "step": 74
    },
    {
      "epoch": 0.2148997134670487,
      "grad_norm": 0.32838553190231323,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3128,
      "step": 75
    },
    {
      "epoch": 0.2177650429799427,
      "grad_norm": 0.3165194094181061,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.3204,
      "step": 76
    },
    {
      "epoch": 0.22063037249283668,
      "grad_norm": 0.3308541476726532,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3179,
      "step": 77
    },
    {
      "epoch": 0.22349570200573066,
      "grad_norm": 0.3327239453792572,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.312,
      "step": 78
    },
    {
      "epoch": 0.22636103151862463,
      "grad_norm": 0.3000035583972931,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.3087,
      "step": 79
    },
    {
      "epoch": 0.22922636103151864,
      "grad_norm": 0.32877233624458313,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3161,
      "step": 80
    },
    {
      "epoch": 0.23209169054441262,
      "grad_norm": 0.3862011730670929,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.3023,
      "step": 81
    },
    {
      "epoch": 0.23209169054441262,
      "eval_loss": 10.311718940734863,
      "eval_runtime": 1.0872,
      "eval_samples_per_second": 270.408,
      "eval_steps_per_second": 34.031,
      "step": 81
    },
    {
      "epoch": 0.2349570200573066,
      "grad_norm": 0.33126261830329895,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3185,
      "step": 82
    },
    {
      "epoch": 0.23782234957020057,
      "grad_norm": 0.29596734046936035,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.3169,
      "step": 83
    },
    {
      "epoch": 0.24068767908309455,
      "grad_norm": 0.32354721426963806,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.3139,
      "step": 84
    },
    {
      "epoch": 0.24355300859598855,
      "grad_norm": 0.32435595989227295,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3234,
      "step": 85
    },
    {
      "epoch": 0.24641833810888253,
      "grad_norm": 0.3075031340122223,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.3194,
      "step": 86
    },
    {
      "epoch": 0.2492836676217765,
      "grad_norm": 0.38141223788261414,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3027,
      "step": 87
    },
    {
      "epoch": 0.2521489971346705,
      "grad_norm": 0.3392947018146515,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.3089,
      "step": 88
    },
    {
      "epoch": 0.25501432664756446,
      "grad_norm": 0.3004538118839264,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.3138,
      "step": 89
    },
    {
      "epoch": 0.25787965616045844,
      "grad_norm": 0.3904876410961151,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3068,
      "step": 90
    },
    {
      "epoch": 0.25787965616045844,
      "eval_loss": 10.310718536376953,
      "eval_runtime": 1.0615,
      "eval_samples_per_second": 276.979,
      "eval_steps_per_second": 34.858,
      "step": 90
    },
    {
      "epoch": 0.2607449856733524,
      "grad_norm": 0.3297453224658966,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3213,
      "step": 91
    },
    {
      "epoch": 0.2636103151862464,
      "grad_norm": 0.35301482677459717,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3242,
      "step": 92
    },
    {
      "epoch": 0.2664756446991404,
      "grad_norm": 0.37583693861961365,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.3206,
      "step": 93
    },
    {
      "epoch": 0.2693409742120344,
      "grad_norm": 0.4035826623439789,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.2922,
      "step": 94
    },
    {
      "epoch": 0.2722063037249284,
      "grad_norm": 0.33306726813316345,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.314,
      "step": 95
    },
    {
      "epoch": 0.27507163323782235,
      "grad_norm": 0.38546448945999146,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.3188,
      "step": 96
    },
    {
      "epoch": 0.27793696275071633,
      "grad_norm": 0.3463270962238312,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.3203,
      "step": 97
    },
    {
      "epoch": 0.2808022922636103,
      "grad_norm": 0.33884936571121216,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.3175,
      "step": 98
    },
    {
      "epoch": 0.2836676217765043,
      "grad_norm": 0.34364816546440125,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3123,
      "step": 99
    },
    {
      "epoch": 0.2836676217765043,
      "eval_loss": 10.31053352355957,
      "eval_runtime": 1.029,
      "eval_samples_per_second": 285.719,
      "eval_steps_per_second": 35.958,
      "step": 99
    },
    {
      "epoch": 0.28653295128939826,
      "grad_norm": 0.3673644959926605,
      "learning_rate": 0.0,
      "loss": 10.3042,
      "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": 5256395882496.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}