{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01365280906546522,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001365280906546522,
      "grad_norm": 0.1318451166152954,
      "learning_rate": 1e-05,
      "loss": 1.2756,
      "step": 1
    },
    {
      "epoch": 0.0001365280906546522,
      "eval_loss": 1.1939568519592285,
      "eval_runtime": 244.769,
      "eval_samples_per_second": 25.199,
      "eval_steps_per_second": 3.15,
      "step": 1
    },
    {
      "epoch": 0.0002730561813093044,
      "grad_norm": 0.10672219097614288,
      "learning_rate": 2e-05,
      "loss": 1.1098,
      "step": 2
    },
    {
      "epoch": 0.00040958427196395656,
      "grad_norm": 0.10856203734874725,
      "learning_rate": 3e-05,
      "loss": 1.139,
      "step": 3
    },
    {
      "epoch": 0.0005461123626186088,
      "grad_norm": 0.15564854443073273,
      "learning_rate": 4e-05,
      "loss": 1.3985,
      "step": 4
    },
    {
      "epoch": 0.0006826404532732609,
      "grad_norm": 0.09477250277996063,
      "learning_rate": 5e-05,
      "loss": 1.0837,
      "step": 5
    },
    {
      "epoch": 0.0008191685439279131,
      "grad_norm": 0.10202593356370926,
      "learning_rate": 6e-05,
      "loss": 1.3073,
      "step": 6
    },
    {
      "epoch": 0.0009556966345825653,
      "grad_norm": 0.12491599470376968,
      "learning_rate": 7e-05,
      "loss": 1.1137,
      "step": 7
    },
    {
      "epoch": 0.0010922247252372176,
      "grad_norm": 0.13829798996448517,
      "learning_rate": 8e-05,
      "loss": 1.3621,
      "step": 8
    },
    {
      "epoch": 0.0012287528158918697,
      "grad_norm": 0.12090452760457993,
      "learning_rate": 9e-05,
      "loss": 1.2218,
      "step": 9
    },
    {
      "epoch": 0.0012287528158918697,
      "eval_loss": 1.188507318496704,
      "eval_runtime": 243.9103,
      "eval_samples_per_second": 25.288,
      "eval_steps_per_second": 3.161,
      "step": 9
    },
    {
      "epoch": 0.0013652809065465218,
      "grad_norm": 0.11588708311319351,
      "learning_rate": 0.0001,
      "loss": 1.2513,
      "step": 10
    },
    {
      "epoch": 0.0015018089972011742,
      "grad_norm": 0.1292330026626587,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.3059,
      "step": 11
    },
    {
      "epoch": 0.0016383370878558263,
      "grad_norm": 0.1201881468296051,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.2906,
      "step": 12
    },
    {
      "epoch": 0.0017748651785104786,
      "grad_norm": 0.10441885143518448,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.9956,
      "step": 13
    },
    {
      "epoch": 0.0019113932691651307,
      "grad_norm": 0.12657149136066437,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.201,
      "step": 14
    },
    {
      "epoch": 0.0020479213598197828,
      "grad_norm": 0.13582639396190643,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.1371,
      "step": 15
    },
    {
      "epoch": 0.0021844494504744353,
      "grad_norm": 0.17041465640068054,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.3096,
      "step": 16
    },
    {
      "epoch": 0.0023209775411290874,
      "grad_norm": 0.09900399297475815,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.022,
      "step": 17
    },
    {
      "epoch": 0.0024575056317837395,
      "grad_norm": 0.10686911642551422,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.1574,
      "step": 18
    },
    {
      "epoch": 0.0024575056317837395,
      "eval_loss": 1.1602661609649658,
      "eval_runtime": 243.8471,
      "eval_samples_per_second": 25.295,
      "eval_steps_per_second": 3.162,
      "step": 18
    },
    {
      "epoch": 0.0025940337224383916,
      "grad_norm": 0.13841882348060608,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3638,
      "step": 19
    },
    {
      "epoch": 0.0027305618130930437,
      "grad_norm": 0.1634441465139389,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.2489,
      "step": 20
    },
    {
      "epoch": 0.0028670899037476962,
      "grad_norm": 0.13136211037635803,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.2534,
      "step": 21
    },
    {
      "epoch": 0.0030036179944023483,
      "grad_norm": 0.14739690721035004,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.2986,
      "step": 22
    },
    {
      "epoch": 0.0031401460850570004,
      "grad_norm": 0.1394389420747757,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.1108,
      "step": 23
    },
    {
      "epoch": 0.0032766741757116525,
      "grad_norm": 0.20582497119903564,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.313,
      "step": 24
    },
    {
      "epoch": 0.003413202266366305,
      "grad_norm": 0.14224418997764587,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.0912,
      "step": 25
    },
    {
      "epoch": 0.003549730357020957,
      "grad_norm": 0.10605136305093765,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.8729,
      "step": 26
    },
    {
      "epoch": 0.0036862584476756092,
      "grad_norm": 0.12778235971927643,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.2331,
      "step": 27
    },
    {
      "epoch": 0.0036862584476756092,
      "eval_loss": 1.1338000297546387,
      "eval_runtime": 244.0484,
      "eval_samples_per_second": 25.274,
      "eval_steps_per_second": 3.159,
      "step": 27
    },
    {
      "epoch": 0.0038227865383302613,
      "grad_norm": 0.1667197048664093,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.167,
      "step": 28
    },
    {
      "epoch": 0.003959314628984914,
      "grad_norm": 0.11533752828836441,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.1189,
      "step": 29
    },
    {
      "epoch": 0.0040958427196395655,
      "grad_norm": 0.13428707420825958,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.141,
      "step": 30
    },
    {
      "epoch": 0.004232370810294218,
      "grad_norm": 0.12984031438827515,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.081,
      "step": 31
    },
    {
      "epoch": 0.004368898900948871,
      "grad_norm": 0.123945452272892,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.0946,
      "step": 32
    },
    {
      "epoch": 0.004505426991603522,
      "grad_norm": 0.164602592587471,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.0671,
      "step": 33
    },
    {
      "epoch": 0.004641955082258175,
      "grad_norm": 0.1377650648355484,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.0508,
      "step": 34
    },
    {
      "epoch": 0.0047784831729128265,
      "grad_norm": 0.1623782217502594,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.0655,
      "step": 35
    },
    {
      "epoch": 0.004915011263567479,
      "grad_norm": 0.14126333594322205,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.0366,
      "step": 36
    },
    {
      "epoch": 0.004915011263567479,
      "eval_loss": 1.1166127920150757,
      "eval_runtime": 243.8018,
      "eval_samples_per_second": 25.299,
      "eval_steps_per_second": 3.162,
      "step": 36
    },
    {
      "epoch": 0.0050515393542221315,
      "grad_norm": 0.18974056839942932,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.315,
      "step": 37
    },
    {
      "epoch": 0.005188067444876783,
      "grad_norm": 0.1491367220878601,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.0972,
      "step": 38
    },
    {
      "epoch": 0.005324595535531436,
      "grad_norm": 0.14877454936504364,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.0623,
      "step": 39
    },
    {
      "epoch": 0.005461123626186087,
      "grad_norm": 0.12115084379911423,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.9672,
      "step": 40
    },
    {
      "epoch": 0.00559765171684074,
      "grad_norm": 0.17201928794384003,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.2131,
      "step": 41
    },
    {
      "epoch": 0.0057341798074953924,
      "grad_norm": 0.1561281681060791,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.0859,
      "step": 42
    },
    {
      "epoch": 0.005870707898150044,
      "grad_norm": 0.176400825381279,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.1378,
      "step": 43
    },
    {
      "epoch": 0.006007235988804697,
      "grad_norm": 0.14552244544029236,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.1543,
      "step": 44
    },
    {
      "epoch": 0.006143764079459349,
      "grad_norm": 0.16236838698387146,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.9699,
      "step": 45
    },
    {
      "epoch": 0.006143764079459349,
      "eval_loss": 1.1052995920181274,
      "eval_runtime": 243.7971,
      "eval_samples_per_second": 25.3,
      "eval_steps_per_second": 3.162,
      "step": 45
    },
    {
      "epoch": 0.006280292170114001,
      "grad_norm": 0.16507592797279358,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.1563,
      "step": 46
    },
    {
      "epoch": 0.006416820260768653,
      "grad_norm": 0.15362995862960815,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.0564,
      "step": 47
    },
    {
      "epoch": 0.006553348351423305,
      "grad_norm": 0.15471172332763672,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.0491,
      "step": 48
    },
    {
      "epoch": 0.0066898764420779576,
      "grad_norm": 0.1650945097208023,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.2523,
      "step": 49
    },
    {
      "epoch": 0.00682640453273261,
      "grad_norm": 0.14592431485652924,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.1442,
      "step": 50
    },
    {
      "epoch": 0.006962932623387262,
      "grad_norm": 0.14765486121177673,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.0828,
      "step": 51
    },
    {
      "epoch": 0.007099460714041914,
      "grad_norm": 0.15812382102012634,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.976,
      "step": 52
    },
    {
      "epoch": 0.007235988804696566,
      "grad_norm": 0.14823691546916962,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.031,
      "step": 53
    },
    {
      "epoch": 0.0073725168953512185,
      "grad_norm": 0.13323071599006653,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.1517,
      "step": 54
    },
    {
      "epoch": 0.0073725168953512185,
      "eval_loss": 1.0984772443771362,
      "eval_runtime": 243.9286,
      "eval_samples_per_second": 25.286,
      "eval_steps_per_second": 3.161,
      "step": 54
    },
    {
      "epoch": 0.007509044986005871,
      "grad_norm": 0.14095240831375122,
      "learning_rate": 5e-05,
      "loss": 0.9093,
      "step": 55
    },
    {
      "epoch": 0.007645573076660523,
      "grad_norm": 0.12879016995429993,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.0597,
      "step": 56
    },
    {
      "epoch": 0.007782101167315175,
      "grad_norm": 0.16116370260715485,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.0573,
      "step": 57
    },
    {
      "epoch": 0.007918629257969828,
      "grad_norm": 0.15659672021865845,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.054,
      "step": 58
    },
    {
      "epoch": 0.00805515734862448,
      "grad_norm": 0.1481948345899582,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.9419,
      "step": 59
    },
    {
      "epoch": 0.008191685439279131,
      "grad_norm": 0.12990693747997284,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.9434,
      "step": 60
    },
    {
      "epoch": 0.008328213529933784,
      "grad_norm": 0.1411079317331314,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.0028,
      "step": 61
    },
    {
      "epoch": 0.008464741620588436,
      "grad_norm": 0.1456051766872406,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.0792,
      "step": 62
    },
    {
      "epoch": 0.008601269711243089,
      "grad_norm": 0.16255994141101837,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.0684,
      "step": 63
    },
    {
      "epoch": 0.008601269711243089,
      "eval_loss": 1.0939992666244507,
      "eval_runtime": 243.8655,
      "eval_samples_per_second": 25.293,
      "eval_steps_per_second": 3.162,
      "step": 63
    },
    {
      "epoch": 0.008737797801897741,
      "grad_norm": 0.12971636652946472,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.0318,
      "step": 64
    },
    {
      "epoch": 0.008874325892552392,
      "grad_norm": 0.17562535405158997,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.0898,
      "step": 65
    },
    {
      "epoch": 0.009010853983207045,
      "grad_norm": 0.1497596651315689,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.0665,
      "step": 66
    },
    {
      "epoch": 0.009147382073861697,
      "grad_norm": 0.1735655665397644,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.1022,
      "step": 67
    },
    {
      "epoch": 0.00928391016451635,
      "grad_norm": 0.1332314908504486,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.0601,
      "step": 68
    },
    {
      "epoch": 0.009420438255171002,
      "grad_norm": 0.13418130576610565,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.0492,
      "step": 69
    },
    {
      "epoch": 0.009556966345825653,
      "grad_norm": 0.15565913915634155,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.0439,
      "step": 70
    },
    {
      "epoch": 0.009693494436480305,
      "grad_norm": 0.13962168991565704,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.206,
      "step": 71
    },
    {
      "epoch": 0.009830022527134958,
      "grad_norm": 0.18453654646873474,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.0785,
      "step": 72
    },
    {
      "epoch": 0.009830022527134958,
      "eval_loss": 1.0912525653839111,
      "eval_runtime": 243.7589,
      "eval_samples_per_second": 25.304,
      "eval_steps_per_second": 3.163,
      "step": 72
    },
    {
      "epoch": 0.00996655061778961,
      "grad_norm": 0.15799516439437866,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.9485,
      "step": 73
    },
    {
      "epoch": 0.010103078708444263,
      "grad_norm": 0.13663075864315033,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.0527,
      "step": 74
    },
    {
      "epoch": 0.010239606799098914,
      "grad_norm": 0.16008491814136505,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.1567,
      "step": 75
    },
    {
      "epoch": 0.010376134889753566,
      "grad_norm": 0.13075454533100128,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.0036,
      "step": 76
    },
    {
      "epoch": 0.010512662980408219,
      "grad_norm": 0.1945352852344513,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.2375,
      "step": 77
    },
    {
      "epoch": 0.010649191071062871,
      "grad_norm": 0.1744111329317093,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.0812,
      "step": 78
    },
    {
      "epoch": 0.010785719161717524,
      "grad_norm": 0.15505953133106232,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.1332,
      "step": 79
    },
    {
      "epoch": 0.010922247252372175,
      "grad_norm": 0.1417454183101654,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.0222,
      "step": 80
    },
    {
      "epoch": 0.011058775343026827,
      "grad_norm": 0.1598300337791443,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.0383,
      "step": 81
    },
    {
      "epoch": 0.011058775343026827,
      "eval_loss": 1.0898100137710571,
      "eval_runtime": 243.897,
      "eval_samples_per_second": 25.289,
      "eval_steps_per_second": 3.161,
      "step": 81
    },
    {
      "epoch": 0.01119530343368148,
      "grad_norm": 0.17551879584789276,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.0462,
      "step": 82
    },
    {
      "epoch": 0.011331831524336132,
      "grad_norm": 0.13904789090156555,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.0482,
      "step": 83
    },
    {
      "epoch": 0.011468359614990785,
      "grad_norm": 0.17219290137290955,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.25,
      "step": 84
    },
    {
      "epoch": 0.011604887705645437,
      "grad_norm": 0.20321820676326752,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.097,
      "step": 85
    },
    {
      "epoch": 0.011741415796300088,
      "grad_norm": 0.1325589269399643,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.9449,
      "step": 86
    },
    {
      "epoch": 0.01187794388695474,
      "grad_norm": 0.16319213807582855,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.2643,
      "step": 87
    },
    {
      "epoch": 0.012014471977609393,
      "grad_norm": 0.15970468521118164,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.9925,
      "step": 88
    },
    {
      "epoch": 0.012151000068264046,
      "grad_norm": 0.17611786723136902,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.1965,
      "step": 89
    },
    {
      "epoch": 0.012287528158918698,
      "grad_norm": 0.15889012813568115,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.9813,
      "step": 90
    },
    {
      "epoch": 0.012287528158918698,
      "eval_loss": 1.0891379117965698,
      "eval_runtime": 244.0249,
      "eval_samples_per_second": 25.276,
      "eval_steps_per_second": 3.16,
      "step": 90
    },
    {
      "epoch": 0.012424056249573349,
      "grad_norm": 0.17122295498847961,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.0401,
      "step": 91
    },
    {
      "epoch": 0.012560584340228002,
      "grad_norm": 0.14136753976345062,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.858,
      "step": 92
    },
    {
      "epoch": 0.012697112430882654,
      "grad_norm": 0.16805991530418396,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.0906,
      "step": 93
    },
    {
      "epoch": 0.012833640521537307,
      "grad_norm": 0.17546240985393524,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.0872,
      "step": 94
    },
    {
      "epoch": 0.01297016861219196,
      "grad_norm": 0.16446717083454132,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.1252,
      "step": 95
    },
    {
      "epoch": 0.01310669670284661,
      "grad_norm": 0.16491715610027313,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.2288,
      "step": 96
    },
    {
      "epoch": 0.013243224793501263,
      "grad_norm": 0.1417722851037979,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.002,
      "step": 97
    },
    {
      "epoch": 0.013379752884155915,
      "grad_norm": 0.14609864354133606,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.1695,
      "step": 98
    },
    {
      "epoch": 0.013516280974810568,
      "grad_norm": 0.18153584003448486,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.0607,
      "step": 99
    },
    {
      "epoch": 0.013516280974810568,
      "eval_loss": 1.0889930725097656,
      "eval_runtime": 243.8388,
      "eval_samples_per_second": 25.295,
      "eval_steps_per_second": 3.162,
      "step": 99
    },
    {
      "epoch": 0.01365280906546522,
      "grad_norm": 0.15827305614948273,
      "learning_rate": 0.0,
      "loss": 1.1212,
      "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": 1.338179403644928e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}