{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013522650439486139,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001352265043948614,
      "grad_norm": 0.13028183579444885,
      "learning_rate": 1e-05,
      "loss": 10.367,
      "step": 1
    },
    {
      "epoch": 0.0001352265043948614,
      "eval_loss": 10.374638557434082,
      "eval_runtime": 39.838,
      "eval_samples_per_second": 156.333,
      "eval_steps_per_second": 19.554,
      "step": 1
    },
    {
      "epoch": 0.0002704530087897228,
      "grad_norm": 0.10174716264009476,
      "learning_rate": 2e-05,
      "loss": 10.3809,
      "step": 2
    },
    {
      "epoch": 0.00040567951318458417,
      "grad_norm": 0.0866115540266037,
      "learning_rate": 3e-05,
      "loss": 10.373,
      "step": 3
    },
    {
      "epoch": 0.0005409060175794456,
      "grad_norm": 0.06329571455717087,
      "learning_rate": 4e-05,
      "loss": 10.3767,
      "step": 4
    },
    {
      "epoch": 0.000676132521974307,
      "grad_norm": 0.10207287222146988,
      "learning_rate": 5e-05,
      "loss": 10.3819,
      "step": 5
    },
    {
      "epoch": 0.0008113590263691683,
      "grad_norm": 0.14628176391124725,
      "learning_rate": 6e-05,
      "loss": 10.3764,
      "step": 6
    },
    {
      "epoch": 0.0009465855307640297,
      "grad_norm": 0.06459755450487137,
      "learning_rate": 7e-05,
      "loss": 10.3845,
      "step": 7
    },
    {
      "epoch": 0.0010818120351588911,
      "grad_norm": 0.06547542661428452,
      "learning_rate": 8e-05,
      "loss": 10.3759,
      "step": 8
    },
    {
      "epoch": 0.0012170385395537525,
      "grad_norm": 0.10897202789783478,
      "learning_rate": 9e-05,
      "loss": 10.378,
      "step": 9
    },
    {
      "epoch": 0.0012170385395537525,
      "eval_loss": 10.37391185760498,
      "eval_runtime": 41.1364,
      "eval_samples_per_second": 151.399,
      "eval_steps_per_second": 18.937,
      "step": 9
    },
    {
      "epoch": 0.001352265043948614,
      "grad_norm": 0.1761985719203949,
      "learning_rate": 0.0001,
      "loss": 10.3579,
      "step": 10
    },
    {
      "epoch": 0.0014874915483434753,
      "grad_norm": 0.0966603010892868,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3665,
      "step": 11
    },
    {
      "epoch": 0.0016227180527383367,
      "grad_norm": 0.11158464848995209,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3696,
      "step": 12
    },
    {
      "epoch": 0.001757944557133198,
      "grad_norm": 0.14970263838768005,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.37,
      "step": 13
    },
    {
      "epoch": 0.0018931710615280595,
      "grad_norm": 0.10012516379356384,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3647,
      "step": 14
    },
    {
      "epoch": 0.002028397565922921,
      "grad_norm": 0.1887078732252121,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3722,
      "step": 15
    },
    {
      "epoch": 0.0021636240703177823,
      "grad_norm": 0.1151905506849289,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3691,
      "step": 16
    },
    {
      "epoch": 0.0022988505747126436,
      "grad_norm": 0.08883685618638992,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3667,
      "step": 17
    },
    {
      "epoch": 0.002434077079107505,
      "grad_norm": 0.09848842024803162,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3694,
      "step": 18
    },
    {
      "epoch": 0.002434077079107505,
      "eval_loss": 10.371732711791992,
      "eval_runtime": 40.9155,
      "eval_samples_per_second": 152.216,
      "eval_steps_per_second": 19.039,
      "step": 18
    },
    {
      "epoch": 0.0025693035835023664,
      "grad_norm": 0.19662371277809143,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3869,
      "step": 19
    },
    {
      "epoch": 0.002704530087897228,
      "grad_norm": 0.12802760303020477,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3803,
      "step": 20
    },
    {
      "epoch": 0.002839756592292089,
      "grad_norm": 0.15228529274463654,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3695,
      "step": 21
    },
    {
      "epoch": 0.0029749830966869506,
      "grad_norm": 0.09475445747375488,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3693,
      "step": 22
    },
    {
      "epoch": 0.003110209601081812,
      "grad_norm": 0.10489476472139359,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.364,
      "step": 23
    },
    {
      "epoch": 0.0032454361054766734,
      "grad_norm": 0.03964424505829811,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3695,
      "step": 24
    },
    {
      "epoch": 0.0033806626098715348,
      "grad_norm": 0.09453272819519043,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3699,
      "step": 25
    },
    {
      "epoch": 0.003515889114266396,
      "grad_norm": 0.07760817557573318,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3778,
      "step": 26
    },
    {
      "epoch": 0.0036511156186612576,
      "grad_norm": 0.12330657988786697,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3614,
      "step": 27
    },
    {
      "epoch": 0.0036511156186612576,
      "eval_loss": 10.369364738464355,
      "eval_runtime": 40.853,
      "eval_samples_per_second": 152.449,
      "eval_steps_per_second": 19.068,
      "step": 27
    },
    {
      "epoch": 0.003786342123056119,
      "grad_norm": 0.2079092264175415,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3696,
      "step": 28
    },
    {
      "epoch": 0.00392156862745098,
      "grad_norm": 0.19546237587928772,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3679,
      "step": 29
    },
    {
      "epoch": 0.004056795131845842,
      "grad_norm": 0.1694408506155014,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3609,
      "step": 30
    },
    {
      "epoch": 0.004192021636240703,
      "grad_norm": 0.07508226484060287,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3676,
      "step": 31
    },
    {
      "epoch": 0.0043272481406355645,
      "grad_norm": 0.12029743939638138,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3714,
      "step": 32
    },
    {
      "epoch": 0.004462474645030426,
      "grad_norm": 0.16662153601646423,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3706,
      "step": 33
    },
    {
      "epoch": 0.004597701149425287,
      "grad_norm": 0.06308508664369583,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3701,
      "step": 34
    },
    {
      "epoch": 0.004732927653820149,
      "grad_norm": 0.11743340641260147,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3745,
      "step": 35
    },
    {
      "epoch": 0.00486815415821501,
      "grad_norm": 0.09249456971883774,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3673,
      "step": 36
    },
    {
      "epoch": 0.00486815415821501,
      "eval_loss": 10.366896629333496,
      "eval_runtime": 41.0089,
      "eval_samples_per_second": 151.869,
      "eval_steps_per_second": 18.996,
      "step": 36
    },
    {
      "epoch": 0.0050033806626098715,
      "grad_norm": 0.24108552932739258,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3796,
      "step": 37
    },
    {
      "epoch": 0.005138607167004733,
      "grad_norm": 0.11644657701253891,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.377,
      "step": 38
    },
    {
      "epoch": 0.005273833671399594,
      "grad_norm": 0.0865534096956253,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3657,
      "step": 39
    },
    {
      "epoch": 0.005409060175794456,
      "grad_norm": 0.21966713666915894,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3647,
      "step": 40
    },
    {
      "epoch": 0.005544286680189317,
      "grad_norm": 0.0750628337264061,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3614,
      "step": 41
    },
    {
      "epoch": 0.005679513184584178,
      "grad_norm": 0.14090754091739655,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3662,
      "step": 42
    },
    {
      "epoch": 0.00581473968897904,
      "grad_norm": 0.10155241936445236,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.3634,
      "step": 43
    },
    {
      "epoch": 0.005949966193373901,
      "grad_norm": 0.0886780321598053,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3604,
      "step": 44
    },
    {
      "epoch": 0.006085192697768763,
      "grad_norm": 0.2659003436565399,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3539,
      "step": 45
    },
    {
      "epoch": 0.006085192697768763,
      "eval_loss": 10.364371299743652,
      "eval_runtime": 41.0033,
      "eval_samples_per_second": 151.89,
      "eval_steps_per_second": 18.998,
      "step": 45
    },
    {
      "epoch": 0.006220419202163624,
      "grad_norm": 0.18210439383983612,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3612,
      "step": 46
    },
    {
      "epoch": 0.006355645706558485,
      "grad_norm": 0.0754951685667038,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3693,
      "step": 47
    },
    {
      "epoch": 0.006490872210953347,
      "grad_norm": 0.08908693492412567,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3614,
      "step": 48
    },
    {
      "epoch": 0.006626098715348208,
      "grad_norm": 0.10534809529781342,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.372,
      "step": 49
    },
    {
      "epoch": 0.0067613252197430695,
      "grad_norm": 0.11808033287525177,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.366,
      "step": 50
    },
    {
      "epoch": 0.006896551724137931,
      "grad_norm": 0.2752968370914459,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3447,
      "step": 51
    },
    {
      "epoch": 0.007031778228532792,
      "grad_norm": 0.14523477852344513,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.3655,
      "step": 52
    },
    {
      "epoch": 0.007167004732927654,
      "grad_norm": 0.1733541488647461,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3647,
      "step": 53
    },
    {
      "epoch": 0.007302231237322515,
      "grad_norm": 0.1748340129852295,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3705,
      "step": 54
    },
    {
      "epoch": 0.007302231237322515,
      "eval_loss": 10.36203384399414,
      "eval_runtime": 40.7225,
      "eval_samples_per_second": 152.938,
      "eval_steps_per_second": 19.129,
      "step": 54
    },
    {
      "epoch": 0.0074374577417173765,
      "grad_norm": 0.12748098373413086,
      "learning_rate": 5e-05,
      "loss": 10.3647,
      "step": 55
    },
    {
      "epoch": 0.007572684246112238,
      "grad_norm": 0.23120729625225067,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3612,
      "step": 56
    },
    {
      "epoch": 0.007707910750507099,
      "grad_norm": 0.08134011179208755,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3731,
      "step": 57
    },
    {
      "epoch": 0.00784313725490196,
      "grad_norm": 0.2719850540161133,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3667,
      "step": 58
    },
    {
      "epoch": 0.007978363759296822,
      "grad_norm": 0.1496485471725464,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.3562,
      "step": 59
    },
    {
      "epoch": 0.008113590263691683,
      "grad_norm": 0.16650433838367462,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3546,
      "step": 60
    },
    {
      "epoch": 0.008248816768086545,
      "grad_norm": 0.15551519393920898,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3711,
      "step": 61
    },
    {
      "epoch": 0.008384043272481406,
      "grad_norm": 0.1664876788854599,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3558,
      "step": 62
    },
    {
      "epoch": 0.008519269776876268,
      "grad_norm": 0.22050045430660248,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3618,
      "step": 63
    },
    {
      "epoch": 0.008519269776876268,
      "eval_loss": 10.359942436218262,
      "eval_runtime": 40.9328,
      "eval_samples_per_second": 152.152,
      "eval_steps_per_second": 19.031,
      "step": 63
    },
    {
      "epoch": 0.008654496281271129,
      "grad_norm": 0.19365984201431274,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3598,
      "step": 64
    },
    {
      "epoch": 0.00878972278566599,
      "grad_norm": 0.13088227808475494,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.3575,
      "step": 65
    },
    {
      "epoch": 0.008924949290060852,
      "grad_norm": 0.3167434334754944,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3557,
      "step": 66
    },
    {
      "epoch": 0.009060175794455713,
      "grad_norm": 0.12147484719753265,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3661,
      "step": 67
    },
    {
      "epoch": 0.009195402298850575,
      "grad_norm": 0.36501771211624146,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3538,
      "step": 68
    },
    {
      "epoch": 0.009330628803245436,
      "grad_norm": 0.24930152297019958,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3536,
      "step": 69
    },
    {
      "epoch": 0.009465855307640297,
      "grad_norm": 0.1812044084072113,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3599,
      "step": 70
    },
    {
      "epoch": 0.009601081812035159,
      "grad_norm": 0.2339591383934021,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.3605,
      "step": 71
    },
    {
      "epoch": 0.00973630831643002,
      "grad_norm": 0.23646140098571777,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.3559,
      "step": 72
    },
    {
      "epoch": 0.00973630831643002,
      "eval_loss": 10.358288764953613,
      "eval_runtime": 40.9322,
      "eval_samples_per_second": 152.154,
      "eval_steps_per_second": 19.031,
      "step": 72
    },
    {
      "epoch": 0.009871534820824882,
      "grad_norm": 0.15088936686515808,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3794,
      "step": 73
    },
    {
      "epoch": 0.010006761325219743,
      "grad_norm": 0.15647698938846588,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3718,
      "step": 74
    },
    {
      "epoch": 0.010141987829614604,
      "grad_norm": 0.3020474910736084,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3613,
      "step": 75
    },
    {
      "epoch": 0.010277214334009466,
      "grad_norm": 0.342067152261734,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.3582,
      "step": 76
    },
    {
      "epoch": 0.010412440838404327,
      "grad_norm": 0.3511400818824768,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3546,
      "step": 77
    },
    {
      "epoch": 0.010547667342799188,
      "grad_norm": 0.2721881568431854,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.3608,
      "step": 78
    },
    {
      "epoch": 0.01068289384719405,
      "grad_norm": 0.3455629348754883,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.3484,
      "step": 79
    },
    {
      "epoch": 0.010818120351588911,
      "grad_norm": 0.327305406332016,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3572,
      "step": 80
    },
    {
      "epoch": 0.010953346855983773,
      "grad_norm": 0.18577629327774048,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.3567,
      "step": 81
    },
    {
      "epoch": 0.010953346855983773,
      "eval_loss": 10.357199668884277,
      "eval_runtime": 40.778,
      "eval_samples_per_second": 152.729,
      "eval_steps_per_second": 19.103,
      "step": 81
    },
    {
      "epoch": 0.011088573360378634,
      "grad_norm": 0.11704239249229431,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3635,
      "step": 82
    },
    {
      "epoch": 0.011223799864773495,
      "grad_norm": 0.19233828783035278,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.3677,
      "step": 83
    },
    {
      "epoch": 0.011359026369168357,
      "grad_norm": 0.07823574542999268,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.3695,
      "step": 84
    },
    {
      "epoch": 0.011494252873563218,
      "grad_norm": 0.13713940978050232,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3596,
      "step": 85
    },
    {
      "epoch": 0.01162947937795808,
      "grad_norm": 0.18941013514995575,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.3583,
      "step": 86
    },
    {
      "epoch": 0.011764705882352941,
      "grad_norm": 0.30075106024742126,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3597,
      "step": 87
    },
    {
      "epoch": 0.011899932386747802,
      "grad_norm": 0.10994397848844528,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.3648,
      "step": 88
    },
    {
      "epoch": 0.012035158891142664,
      "grad_norm": 0.13853776454925537,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.3724,
      "step": 89
    },
    {
      "epoch": 0.012170385395537525,
      "grad_norm": 0.191994771361351,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3556,
      "step": 90
    },
    {
      "epoch": 0.012170385395537525,
      "eval_loss": 10.356754302978516,
      "eval_runtime": 40.9895,
      "eval_samples_per_second": 151.941,
      "eval_steps_per_second": 19.005,
      "step": 90
    },
    {
      "epoch": 0.012305611899932387,
      "grad_norm": 0.10114133358001709,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3638,
      "step": 91
    },
    {
      "epoch": 0.012440838404327248,
      "grad_norm": 0.22643674910068512,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3453,
      "step": 92
    },
    {
      "epoch": 0.01257606490872211,
      "grad_norm": 0.18599919974803925,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.3606,
      "step": 93
    },
    {
      "epoch": 0.01271129141311697,
      "grad_norm": 0.4384092092514038,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.3458,
      "step": 94
    },
    {
      "epoch": 0.012846517917511832,
      "grad_norm": 0.1412304788827896,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.3518,
      "step": 95
    },
    {
      "epoch": 0.012981744421906694,
      "grad_norm": 0.20670315623283386,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.3595,
      "step": 96
    },
    {
      "epoch": 0.013116970926301555,
      "grad_norm": 0.15490083396434784,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.3575,
      "step": 97
    },
    {
      "epoch": 0.013252197430696416,
      "grad_norm": 0.19258053600788116,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.349,
      "step": 98
    },
    {
      "epoch": 0.013387423935091278,
      "grad_norm": 0.15515723824501038,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3637,
      "step": 99
    },
    {
      "epoch": 0.013387423935091278,
      "eval_loss": 10.356693267822266,
      "eval_runtime": 40.9088,
      "eval_samples_per_second": 152.241,
      "eval_steps_per_second": 19.042,
      "step": 99
    },
    {
      "epoch": 0.013522650439486139,
      "grad_norm": 0.2686675488948822,
      "learning_rate": 0.0,
      "loss": 10.3569,
      "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
}