{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.17286084701815038,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001728608470181504,
      "grad_norm": 12.312000274658203,
      "learning_rate": 1e-05,
      "loss": 8.208,
      "step": 1
    },
    {
      "epoch": 0.001728608470181504,
      "eval_loss": 7.82079553604126,
      "eval_runtime": 59.4015,
      "eval_samples_per_second": 8.198,
      "eval_steps_per_second": 1.027,
      "step": 1
    },
    {
      "epoch": 0.003457216940363008,
      "grad_norm": 10.80457592010498,
      "learning_rate": 2e-05,
      "loss": 7.701,
      "step": 2
    },
    {
      "epoch": 0.005185825410544511,
      "grad_norm": 10.03779125213623,
      "learning_rate": 3e-05,
      "loss": 7.4742,
      "step": 3
    },
    {
      "epoch": 0.006914433880726016,
      "grad_norm": 10.799802780151367,
      "learning_rate": 4e-05,
      "loss": 7.8807,
      "step": 4
    },
    {
      "epoch": 0.00864304235090752,
      "grad_norm": 13.066155433654785,
      "learning_rate": 5e-05,
      "loss": 7.3703,
      "step": 5
    },
    {
      "epoch": 0.010371650821089023,
      "grad_norm": 12.932625770568848,
      "learning_rate": 6e-05,
      "loss": 7.3005,
      "step": 6
    },
    {
      "epoch": 0.012100259291270527,
      "grad_norm": 13.205818176269531,
      "learning_rate": 7e-05,
      "loss": 5.9246,
      "step": 7
    },
    {
      "epoch": 0.013828867761452032,
      "grad_norm": 10.532011032104492,
      "learning_rate": 8e-05,
      "loss": 4.607,
      "step": 8
    },
    {
      "epoch": 0.015557476231633534,
      "grad_norm": 9.597806930541992,
      "learning_rate": 9e-05,
      "loss": 3.3865,
      "step": 9
    },
    {
      "epoch": 0.015557476231633534,
      "eval_loss": 3.0007164478302,
      "eval_runtime": 59.9905,
      "eval_samples_per_second": 8.118,
      "eval_steps_per_second": 1.017,
      "step": 9
    },
    {
      "epoch": 0.01728608470181504,
      "grad_norm": 8.901469230651855,
      "learning_rate": 0.0001,
      "loss": 3.3019,
      "step": 10
    },
    {
      "epoch": 0.01901469317199654,
      "grad_norm": 8.612654685974121,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.0583,
      "step": 11
    },
    {
      "epoch": 0.020743301642178046,
      "grad_norm": 8.786474227905273,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.6476,
      "step": 12
    },
    {
      "epoch": 0.02247191011235955,
      "grad_norm": 12.150829315185547,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.7353,
      "step": 13
    },
    {
      "epoch": 0.024200518582541054,
      "grad_norm": 4.960375785827637,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.5344,
      "step": 14
    },
    {
      "epoch": 0.02592912705272256,
      "grad_norm": 5.48443603515625,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.4958,
      "step": 15
    },
    {
      "epoch": 0.027657735522904063,
      "grad_norm": 3.133187770843506,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.2864,
      "step": 16
    },
    {
      "epoch": 0.029386343993085567,
      "grad_norm": 11.571676254272461,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.4973,
      "step": 17
    },
    {
      "epoch": 0.03111495246326707,
      "grad_norm": 10.172198295593262,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.4595,
      "step": 18
    },
    {
      "epoch": 0.03111495246326707,
      "eval_loss": 0.2758592367172241,
      "eval_runtime": 59.9063,
      "eval_samples_per_second": 8.129,
      "eval_steps_per_second": 1.018,
      "step": 18
    },
    {
      "epoch": 0.032843560933448576,
      "grad_norm": 4.824380397796631,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2105,
      "step": 19
    },
    {
      "epoch": 0.03457216940363008,
      "grad_norm": 5.580054759979248,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2788,
      "step": 20
    },
    {
      "epoch": 0.036300777873811585,
      "grad_norm": 15.156196594238281,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.0478,
      "step": 21
    },
    {
      "epoch": 0.03802938634399308,
      "grad_norm": 11.11514949798584,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.7116,
      "step": 22
    },
    {
      "epoch": 0.03975799481417459,
      "grad_norm": 6.261142253875732,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.3382,
      "step": 23
    },
    {
      "epoch": 0.04148660328435609,
      "grad_norm": 1.7251250743865967,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.2252,
      "step": 24
    },
    {
      "epoch": 0.043215211754537596,
      "grad_norm": 4.312660217285156,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2501,
      "step": 25
    },
    {
      "epoch": 0.0449438202247191,
      "grad_norm": 1.7256615161895752,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.1944,
      "step": 26
    },
    {
      "epoch": 0.046672428694900604,
      "grad_norm": 3.2441158294677734,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.2636,
      "step": 27
    },
    {
      "epoch": 0.046672428694900604,
      "eval_loss": 0.23836037516593933,
      "eval_runtime": 59.8857,
      "eval_samples_per_second": 8.132,
      "eval_steps_per_second": 1.019,
      "step": 27
    },
    {
      "epoch": 0.04840103716508211,
      "grad_norm": 1.1730740070343018,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1172,
      "step": 28
    },
    {
      "epoch": 0.05012964563526361,
      "grad_norm": 4.2838616371154785,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.3228,
      "step": 29
    },
    {
      "epoch": 0.05185825410544512,
      "grad_norm": 2.63944411277771,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.2073,
      "step": 30
    },
    {
      "epoch": 0.05358686257562662,
      "grad_norm": 3.043018102645874,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.2092,
      "step": 31
    },
    {
      "epoch": 0.055315471045808126,
      "grad_norm": 6.101500034332275,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.3114,
      "step": 32
    },
    {
      "epoch": 0.05704407951598963,
      "grad_norm": 2.89831805229187,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.2246,
      "step": 33
    },
    {
      "epoch": 0.058772687986171135,
      "grad_norm": 3.855902910232544,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.2527,
      "step": 34
    },
    {
      "epoch": 0.06050129645635264,
      "grad_norm": 2.482206344604492,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.1879,
      "step": 35
    },
    {
      "epoch": 0.06222990492653414,
      "grad_norm": 2.551619529724121,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.2089,
      "step": 36
    },
    {
      "epoch": 0.06222990492653414,
      "eval_loss": 0.23016715049743652,
      "eval_runtime": 59.9334,
      "eval_samples_per_second": 8.126,
      "eval_steps_per_second": 1.018,
      "step": 36
    },
    {
      "epoch": 0.06395851339671564,
      "grad_norm": 3.615114450454712,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.3432,
      "step": 37
    },
    {
      "epoch": 0.06568712186689715,
      "grad_norm": 2.392651319503784,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.2407,
      "step": 38
    },
    {
      "epoch": 0.06741573033707865,
      "grad_norm": 2.1452417373657227,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.1913,
      "step": 39
    },
    {
      "epoch": 0.06914433880726016,
      "grad_norm": 3.030391216278076,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.216,
      "step": 40
    },
    {
      "epoch": 0.07087294727744166,
      "grad_norm": 1.4974638223648071,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.161,
      "step": 41
    },
    {
      "epoch": 0.07260155574762317,
      "grad_norm": 2.519773006439209,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.1837,
      "step": 42
    },
    {
      "epoch": 0.07433016421780467,
      "grad_norm": 3.8968756198883057,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.2215,
      "step": 43
    },
    {
      "epoch": 0.07605877268798616,
      "grad_norm": 2.4747507572174072,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.1623,
      "step": 44
    },
    {
      "epoch": 0.07778738115816768,
      "grad_norm": 1.3833476305007935,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.125,
      "step": 45
    },
    {
      "epoch": 0.07778738115816768,
      "eval_loss": 0.13616420328617096,
      "eval_runtime": 59.9742,
      "eval_samples_per_second": 8.12,
      "eval_steps_per_second": 1.017,
      "step": 45
    },
    {
      "epoch": 0.07951598962834917,
      "grad_norm": 2.1761486530303955,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1156,
      "step": 46
    },
    {
      "epoch": 0.08124459809853068,
      "grad_norm": 2.4008829593658447,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.1505,
      "step": 47
    },
    {
      "epoch": 0.08297320656871218,
      "grad_norm": 3.0325117111206055,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.1574,
      "step": 48
    },
    {
      "epoch": 0.0847018150388937,
      "grad_norm": 2.7544243335723877,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.1974,
      "step": 49
    },
    {
      "epoch": 0.08643042350907519,
      "grad_norm": 2.0129692554473877,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0959,
      "step": 50
    },
    {
      "epoch": 0.0881590319792567,
      "grad_norm": 2.1975345611572266,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.1515,
      "step": 51
    },
    {
      "epoch": 0.0898876404494382,
      "grad_norm": 2.3398613929748535,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0679,
      "step": 52
    },
    {
      "epoch": 0.09161624891961971,
      "grad_norm": 1.2971707582473755,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.1414,
      "step": 53
    },
    {
      "epoch": 0.09334485738980121,
      "grad_norm": 1.0790573358535767,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0444,
      "step": 54
    },
    {
      "epoch": 0.09334485738980121,
      "eval_loss": 0.08925344794988632,
      "eval_runtime": 59.9395,
      "eval_samples_per_second": 8.125,
      "eval_steps_per_second": 1.018,
      "step": 54
    },
    {
      "epoch": 0.09507346585998272,
      "grad_norm": 2.6760683059692383,
      "learning_rate": 5e-05,
      "loss": 0.1222,
      "step": 55
    },
    {
      "epoch": 0.09680207433016422,
      "grad_norm": 3.124195098876953,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0844,
      "step": 56
    },
    {
      "epoch": 0.09853068280034573,
      "grad_norm": 3.726902961730957,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.1026,
      "step": 57
    },
    {
      "epoch": 0.10025929127052723,
      "grad_norm": 1.8012640476226807,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0725,
      "step": 58
    },
    {
      "epoch": 0.10198789974070872,
      "grad_norm": 2.005619525909424,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0961,
      "step": 59
    },
    {
      "epoch": 0.10371650821089023,
      "grad_norm": 1.4710978269577026,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0591,
      "step": 60
    },
    {
      "epoch": 0.10544511668107173,
      "grad_norm": 3.6502554416656494,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.3019,
      "step": 61
    },
    {
      "epoch": 0.10717372515125324,
      "grad_norm": 0.946759045124054,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0566,
      "step": 62
    },
    {
      "epoch": 0.10890233362143474,
      "grad_norm": 5.641058444976807,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.1695,
      "step": 63
    },
    {
      "epoch": 0.10890233362143474,
      "eval_loss": 0.08094155043363571,
      "eval_runtime": 60.0007,
      "eval_samples_per_second": 8.117,
      "eval_steps_per_second": 1.017,
      "step": 63
    },
    {
      "epoch": 0.11063094209161625,
      "grad_norm": 2.45649790763855,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0992,
      "step": 64
    },
    {
      "epoch": 0.11235955056179775,
      "grad_norm": 1.054600477218628,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0354,
      "step": 65
    },
    {
      "epoch": 0.11408815903197926,
      "grad_norm": 2.082963466644287,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0499,
      "step": 66
    },
    {
      "epoch": 0.11581676750216076,
      "grad_norm": 2.0378904342651367,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.1216,
      "step": 67
    },
    {
      "epoch": 0.11754537597234227,
      "grad_norm": 3.01963472366333,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.1443,
      "step": 68
    },
    {
      "epoch": 0.11927398444252377,
      "grad_norm": 2.401992082595825,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.061,
      "step": 69
    },
    {
      "epoch": 0.12100259291270528,
      "grad_norm": 2.9330196380615234,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0719,
      "step": 70
    },
    {
      "epoch": 0.12273120138288678,
      "grad_norm": 2.8944931030273438,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.1496,
      "step": 71
    },
    {
      "epoch": 0.12445980985306827,
      "grad_norm": 2.2122907638549805,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0711,
      "step": 72
    },
    {
      "epoch": 0.12445980985306827,
      "eval_loss": 0.08498465269804001,
      "eval_runtime": 59.9709,
      "eval_samples_per_second": 8.121,
      "eval_steps_per_second": 1.017,
      "step": 72
    },
    {
      "epoch": 0.12618841832324978,
      "grad_norm": 0.5625259876251221,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0186,
      "step": 73
    },
    {
      "epoch": 0.12791702679343128,
      "grad_norm": 1.4233897924423218,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.04,
      "step": 74
    },
    {
      "epoch": 0.12964563526361278,
      "grad_norm": 2.205634355545044,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0768,
      "step": 75
    },
    {
      "epoch": 0.1313742437337943,
      "grad_norm": 1.7786928415298462,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1886,
      "step": 76
    },
    {
      "epoch": 0.1331028522039758,
      "grad_norm": 2.8164985179901123,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0808,
      "step": 77
    },
    {
      "epoch": 0.1348314606741573,
      "grad_norm": 3.44098162651062,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0864,
      "step": 78
    },
    {
      "epoch": 0.1365600691443388,
      "grad_norm": 2.6552727222442627,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.1229,
      "step": 79
    },
    {
      "epoch": 0.13828867761452032,
      "grad_norm": 2.736898899078369,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.143,
      "step": 80
    },
    {
      "epoch": 0.14001728608470182,
      "grad_norm": 1.184891700744629,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0516,
      "step": 81
    },
    {
      "epoch": 0.14001728608470182,
      "eval_loss": 0.08963877707719803,
      "eval_runtime": 59.9126,
      "eval_samples_per_second": 8.129,
      "eval_steps_per_second": 1.018,
      "step": 81
    },
    {
      "epoch": 0.14174589455488332,
      "grad_norm": 1.8975074291229248,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1537,
      "step": 82
    },
    {
      "epoch": 0.14347450302506481,
      "grad_norm": 3.9329543113708496,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.2281,
      "step": 83
    },
    {
      "epoch": 0.14520311149524634,
      "grad_norm": 6.52722692489624,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.2079,
      "step": 84
    },
    {
      "epoch": 0.14693171996542784,
      "grad_norm": 1.6043305397033691,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0877,
      "step": 85
    },
    {
      "epoch": 0.14866032843560933,
      "grad_norm": 2.5400655269622803,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0965,
      "step": 86
    },
    {
      "epoch": 0.15038893690579083,
      "grad_norm": 1.2767246961593628,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0712,
      "step": 87
    },
    {
      "epoch": 0.15211754537597233,
      "grad_norm": 2.5262181758880615,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0671,
      "step": 88
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 1.2105026245117188,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0602,
      "step": 89
    },
    {
      "epoch": 0.15557476231633535,
      "grad_norm": 2.1266372203826904,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2097,
      "step": 90
    },
    {
      "epoch": 0.15557476231633535,
      "eval_loss": 0.0771675556898117,
      "eval_runtime": 59.9224,
      "eval_samples_per_second": 8.127,
      "eval_steps_per_second": 1.018,
      "step": 90
    },
    {
      "epoch": 0.15730337078651685,
      "grad_norm": 2.3782505989074707,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0881,
      "step": 91
    },
    {
      "epoch": 0.15903197925669835,
      "grad_norm": 1.4200860261917114,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0975,
      "step": 92
    },
    {
      "epoch": 0.16076058772687987,
      "grad_norm": 0.5721936821937561,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0205,
      "step": 93
    },
    {
      "epoch": 0.16248919619706137,
      "grad_norm": 3.5002877712249756,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0394,
      "step": 94
    },
    {
      "epoch": 0.16421780466724287,
      "grad_norm": 2.611619234085083,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0684,
      "step": 95
    },
    {
      "epoch": 0.16594641313742436,
      "grad_norm": 2.6668496131896973,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.1992,
      "step": 96
    },
    {
      "epoch": 0.1676750216076059,
      "grad_norm": 1.5637649297714233,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.1031,
      "step": 97
    },
    {
      "epoch": 0.1694036300777874,
      "grad_norm": 1.752373218536377,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0992,
      "step": 98
    },
    {
      "epoch": 0.17113223854796888,
      "grad_norm": 2.568974018096924,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.1165,
      "step": 99
    },
    {
      "epoch": 0.17113223854796888,
      "eval_loss": 0.07640420645475388,
      "eval_runtime": 59.9181,
      "eval_samples_per_second": 8.128,
      "eval_steps_per_second": 1.018,
      "step": 99
    },
    {
      "epoch": 0.17286084701815038,
      "grad_norm": 2.4552574157714844,
      "learning_rate": 0.0,
      "loss": 0.1097,
      "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": 7.41887283560448e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}