{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.704225352112676,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007042253521126761,
      "grad_norm": 36.489925384521484,
      "learning_rate": 1e-05,
      "loss": 16.7418,
      "step": 1
    },
    {
      "epoch": 0.007042253521126761,
      "eval_loss": 8.365168571472168,
      "eval_runtime": 5.2379,
      "eval_samples_per_second": 22.91,
      "eval_steps_per_second": 2.864,
      "step": 1
    },
    {
      "epoch": 0.014084507042253521,
      "grad_norm": 54.84891128540039,
      "learning_rate": 2e-05,
      "loss": 15.7412,
      "step": 2
    },
    {
      "epoch": 0.02112676056338028,
      "grad_norm": 64.47398376464844,
      "learning_rate": 3e-05,
      "loss": 16.7694,
      "step": 3
    },
    {
      "epoch": 0.028169014084507043,
      "grad_norm": 16.057498931884766,
      "learning_rate": 4e-05,
      "loss": 16.2653,
      "step": 4
    },
    {
      "epoch": 0.035211267605633804,
      "grad_norm": 38.04544448852539,
      "learning_rate": 5e-05,
      "loss": 16.5994,
      "step": 5
    },
    {
      "epoch": 0.04225352112676056,
      "grad_norm": 32.003196716308594,
      "learning_rate": 6e-05,
      "loss": 16.4649,
      "step": 6
    },
    {
      "epoch": 0.04929577464788732,
      "grad_norm": 43.975486755371094,
      "learning_rate": 7e-05,
      "loss": 15.2708,
      "step": 7
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 23.013490676879883,
      "learning_rate": 8e-05,
      "loss": 15.9144,
      "step": 8
    },
    {
      "epoch": 0.06338028169014084,
      "grad_norm": 21.642526626586914,
      "learning_rate": 9e-05,
      "loss": 13.8646,
      "step": 9
    },
    {
      "epoch": 0.06338028169014084,
      "eval_loss": 5.608087539672852,
      "eval_runtime": 5.2413,
      "eval_samples_per_second": 22.895,
      "eval_steps_per_second": 2.862,
      "step": 9
    },
    {
      "epoch": 0.07042253521126761,
      "grad_norm": 20.63976287841797,
      "learning_rate": 0.0001,
      "loss": 11.0946,
      "step": 10
    },
    {
      "epoch": 0.07746478873239436,
      "grad_norm": 22.017879486083984,
      "learning_rate": 9.99695413509548e-05,
      "loss": 9.8704,
      "step": 11
    },
    {
      "epoch": 0.08450704225352113,
      "grad_norm": 25.062084197998047,
      "learning_rate": 9.987820251299122e-05,
      "loss": 6.6076,
      "step": 12
    },
    {
      "epoch": 0.09154929577464789,
      "grad_norm": 17.164138793945312,
      "learning_rate": 9.972609476841367e-05,
      "loss": 6.0168,
      "step": 13
    },
    {
      "epoch": 0.09859154929577464,
      "grad_norm": 11.223540306091309,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.8373,
      "step": 14
    },
    {
      "epoch": 0.1056338028169014,
      "grad_norm": 7.377206325531006,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.6019,
      "step": 15
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": 7.338124752044678,
      "learning_rate": 9.890738003669029e-05,
      "loss": 4.2857,
      "step": 16
    },
    {
      "epoch": 0.11971830985915492,
      "grad_norm": 6.844852447509766,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.2959,
      "step": 17
    },
    {
      "epoch": 0.1267605633802817,
      "grad_norm": 6.174362659454346,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.6541,
      "step": 18
    },
    {
      "epoch": 0.1267605633802817,
      "eval_loss": 1.0343117713928223,
      "eval_runtime": 5.2408,
      "eval_samples_per_second": 22.897,
      "eval_steps_per_second": 2.862,
      "step": 18
    },
    {
      "epoch": 0.13380281690140844,
      "grad_norm": 11.295928001403809,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.0969,
      "step": 19
    },
    {
      "epoch": 0.14084507042253522,
      "grad_norm": 5.165931224822998,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.1286,
      "step": 20
    },
    {
      "epoch": 0.14788732394366197,
      "grad_norm": 15.428300857543945,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.5216,
      "step": 21
    },
    {
      "epoch": 0.15492957746478872,
      "grad_norm": 15.729449272155762,
      "learning_rate": 9.567727288213005e-05,
      "loss": 3.2321,
      "step": 22
    },
    {
      "epoch": 0.1619718309859155,
      "grad_norm": 6.993392467498779,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.019,
      "step": 23
    },
    {
      "epoch": 0.16901408450704225,
      "grad_norm": 3.678471326828003,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.4714,
      "step": 24
    },
    {
      "epoch": 0.176056338028169,
      "grad_norm": 4.6879801750183105,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.449,
      "step": 25
    },
    {
      "epoch": 0.18309859154929578,
      "grad_norm": 6.838872909545898,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.8043,
      "step": 26
    },
    {
      "epoch": 0.19014084507042253,
      "grad_norm": 7.476458549499512,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.0743,
      "step": 27
    },
    {
      "epoch": 0.19014084507042253,
      "eval_loss": 0.8306647539138794,
      "eval_runtime": 5.3176,
      "eval_samples_per_second": 22.567,
      "eval_steps_per_second": 2.821,
      "step": 27
    },
    {
      "epoch": 0.19718309859154928,
      "grad_norm": 7.009374141693115,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.2197,
      "step": 28
    },
    {
      "epoch": 0.20422535211267606,
      "grad_norm": 4.203879356384277,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.8692,
      "step": 29
    },
    {
      "epoch": 0.2112676056338028,
      "grad_norm": 2.9395430088043213,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.6414,
      "step": 30
    },
    {
      "epoch": 0.21830985915492956,
      "grad_norm": 4.54150915145874,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.6064,
      "step": 31
    },
    {
      "epoch": 0.22535211267605634,
      "grad_norm": 3.4813199043273926,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.5703,
      "step": 32
    },
    {
      "epoch": 0.2323943661971831,
      "grad_norm": 5.205654144287109,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.6502,
      "step": 33
    },
    {
      "epoch": 0.23943661971830985,
      "grad_norm": 6.046175956726074,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.8305,
      "step": 34
    },
    {
      "epoch": 0.24647887323943662,
      "grad_norm": 2.525583505630493,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.3965,
      "step": 35
    },
    {
      "epoch": 0.2535211267605634,
      "grad_norm": 7.969776630401611,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.1048,
      "step": 36
    },
    {
      "epoch": 0.2535211267605634,
      "eval_loss": 0.7210001349449158,
      "eval_runtime": 5.2587,
      "eval_samples_per_second": 22.819,
      "eval_steps_per_second": 2.852,
      "step": 36
    },
    {
      "epoch": 0.2605633802816901,
      "grad_norm": 2.2472925186157227,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.3476,
      "step": 37
    },
    {
      "epoch": 0.2676056338028169,
      "grad_norm": 3.452265739440918,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.7696,
      "step": 38
    },
    {
      "epoch": 0.2746478873239437,
      "grad_norm": 2.057129144668579,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.4384,
      "step": 39
    },
    {
      "epoch": 0.28169014084507044,
      "grad_norm": 2.932300090789795,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3321,
      "step": 40
    },
    {
      "epoch": 0.2887323943661972,
      "grad_norm": 1.8168283700942993,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.4552,
      "step": 41
    },
    {
      "epoch": 0.29577464788732394,
      "grad_norm": 1.3311522006988525,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.4102,
      "step": 42
    },
    {
      "epoch": 0.3028169014084507,
      "grad_norm": 3.1506192684173584,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.5,
      "step": 43
    },
    {
      "epoch": 0.30985915492957744,
      "grad_norm": 4.003086090087891,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.4761,
      "step": 44
    },
    {
      "epoch": 0.31690140845070425,
      "grad_norm": 3.40531063079834,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.5122,
      "step": 45
    },
    {
      "epoch": 0.31690140845070425,
      "eval_loss": 0.7483626008033752,
      "eval_runtime": 5.2389,
      "eval_samples_per_second": 22.905,
      "eval_steps_per_second": 2.863,
      "step": 45
    },
    {
      "epoch": 0.323943661971831,
      "grad_norm": 2.6020545959472656,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.3895,
      "step": 46
    },
    {
      "epoch": 0.33098591549295775,
      "grad_norm": 2.6481332778930664,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.4633,
      "step": 47
    },
    {
      "epoch": 0.3380281690140845,
      "grad_norm": 2.3728225231170654,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.7675,
      "step": 48
    },
    {
      "epoch": 0.34507042253521125,
      "grad_norm": 2.0442349910736084,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.3868,
      "step": 49
    },
    {
      "epoch": 0.352112676056338,
      "grad_norm": 1.7789822816848755,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.4195,
      "step": 50
    },
    {
      "epoch": 0.3591549295774648,
      "grad_norm": 2.0427401065826416,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.6343,
      "step": 51
    },
    {
      "epoch": 0.36619718309859156,
      "grad_norm": 3.6951797008514404,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.7408,
      "step": 52
    },
    {
      "epoch": 0.3732394366197183,
      "grad_norm": 3.672791004180908,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.524,
      "step": 53
    },
    {
      "epoch": 0.38028169014084506,
      "grad_norm": 4.061415672302246,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.5609,
      "step": 54
    },
    {
      "epoch": 0.38028169014084506,
      "eval_loss": 0.7512367963790894,
      "eval_runtime": 5.2814,
      "eval_samples_per_second": 22.721,
      "eval_steps_per_second": 2.84,
      "step": 54
    },
    {
      "epoch": 0.3873239436619718,
      "grad_norm": 2.5772194862365723,
      "learning_rate": 5e-05,
      "loss": 1.4108,
      "step": 55
    },
    {
      "epoch": 0.39436619718309857,
      "grad_norm": 1.6014587879180908,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.365,
      "step": 56
    },
    {
      "epoch": 0.4014084507042254,
      "grad_norm": 2.9118096828460693,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.7301,
      "step": 57
    },
    {
      "epoch": 0.4084507042253521,
      "grad_norm": 4.28907585144043,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.7773,
      "step": 58
    },
    {
      "epoch": 0.4154929577464789,
      "grad_norm": 3.053123712539673,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.6367,
      "step": 59
    },
    {
      "epoch": 0.4225352112676056,
      "grad_norm": 3.9312641620635986,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.5563,
      "step": 60
    },
    {
      "epoch": 0.4295774647887324,
      "grad_norm": 4.716941833496094,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.5059,
      "step": 61
    },
    {
      "epoch": 0.43661971830985913,
      "grad_norm": 1.2284787893295288,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.3866,
      "step": 62
    },
    {
      "epoch": 0.44366197183098594,
      "grad_norm": 1.6609184741973877,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.3671,
      "step": 63
    },
    {
      "epoch": 0.44366197183098594,
      "eval_loss": 0.7309496402740479,
      "eval_runtime": 5.2546,
      "eval_samples_per_second": 22.837,
      "eval_steps_per_second": 2.855,
      "step": 63
    },
    {
      "epoch": 0.4507042253521127,
      "grad_norm": 2.3474254608154297,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.6455,
      "step": 64
    },
    {
      "epoch": 0.45774647887323944,
      "grad_norm": 3.384629726409912,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.5113,
      "step": 65
    },
    {
      "epoch": 0.4647887323943662,
      "grad_norm": 2.769561290740967,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.0072,
      "step": 66
    },
    {
      "epoch": 0.47183098591549294,
      "grad_norm": 1.6377378702163696,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.378,
      "step": 67
    },
    {
      "epoch": 0.4788732394366197,
      "grad_norm": 2.9717202186584473,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.9511,
      "step": 68
    },
    {
      "epoch": 0.4859154929577465,
      "grad_norm": 1.5930095911026,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.6474,
      "step": 69
    },
    {
      "epoch": 0.49295774647887325,
      "grad_norm": 2.147733688354492,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.5024,
      "step": 70
    },
    {
      "epoch": 0.5,
      "grad_norm": 2.3971445560455322,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.4185,
      "step": 71
    },
    {
      "epoch": 0.5070422535211268,
      "grad_norm": 2.334181308746338,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.4944,
      "step": 72
    },
    {
      "epoch": 0.5070422535211268,
      "eval_loss": 0.7280327677726746,
      "eval_runtime": 5.2593,
      "eval_samples_per_second": 22.817,
      "eval_steps_per_second": 2.852,
      "step": 72
    },
    {
      "epoch": 0.5140845070422535,
      "grad_norm": 2.140132427215576,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.4209,
      "step": 73
    },
    {
      "epoch": 0.5211267605633803,
      "grad_norm": 1.595037817955017,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.6229,
      "step": 74
    },
    {
      "epoch": 0.528169014084507,
      "grad_norm": 3.3290388584136963,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.4053,
      "step": 75
    },
    {
      "epoch": 0.5352112676056338,
      "grad_norm": 1.6777218580245972,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.5162,
      "step": 76
    },
    {
      "epoch": 0.5422535211267606,
      "grad_norm": 2.207165479660034,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.4367,
      "step": 77
    },
    {
      "epoch": 0.5492957746478874,
      "grad_norm": 2.791753053665161,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.5284,
      "step": 78
    },
    {
      "epoch": 0.5563380281690141,
      "grad_norm": 2.0597660541534424,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.4983,
      "step": 79
    },
    {
      "epoch": 0.5633802816901409,
      "grad_norm": 2.1963610649108887,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.469,
      "step": 80
    },
    {
      "epoch": 0.5704225352112676,
      "grad_norm": 1.8355844020843506,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.6337,
      "step": 81
    },
    {
      "epoch": 0.5704225352112676,
      "eval_loss": 0.7295297980308533,
      "eval_runtime": 5.2947,
      "eval_samples_per_second": 22.664,
      "eval_steps_per_second": 2.833,
      "step": 81
    },
    {
      "epoch": 0.5774647887323944,
      "grad_norm": 2.3852171897888184,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.3641,
      "step": 82
    },
    {
      "epoch": 0.5845070422535211,
      "grad_norm": 2.421605110168457,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.4797,
      "step": 83
    },
    {
      "epoch": 0.5915492957746479,
      "grad_norm": 1.8228073120117188,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.5467,
      "step": 84
    },
    {
      "epoch": 0.5985915492957746,
      "grad_norm": 3.43153977394104,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.4331,
      "step": 85
    },
    {
      "epoch": 0.6056338028169014,
      "grad_norm": 1.7456953525543213,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.341,
      "step": 86
    },
    {
      "epoch": 0.6126760563380281,
      "grad_norm": 1.962058663368225,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.5015,
      "step": 87
    },
    {
      "epoch": 0.6197183098591549,
      "grad_norm": 4.884045600891113,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.6106,
      "step": 88
    },
    {
      "epoch": 0.6267605633802817,
      "grad_norm": 1.6915897130966187,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.4477,
      "step": 89
    },
    {
      "epoch": 0.6338028169014085,
      "grad_norm": 1.18873131275177,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.3877,
      "step": 90
    },
    {
      "epoch": 0.6338028169014085,
      "eval_loss": 0.7244928479194641,
      "eval_runtime": 5.2601,
      "eval_samples_per_second": 22.813,
      "eval_steps_per_second": 2.852,
      "step": 90
    },
    {
      "epoch": 0.6408450704225352,
      "grad_norm": 2.745110273361206,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.3234,
      "step": 91
    },
    {
      "epoch": 0.647887323943662,
      "grad_norm": 1.5612205266952515,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.3812,
      "step": 92
    },
    {
      "epoch": 0.6549295774647887,
      "grad_norm": 1.651207447052002,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.6955,
      "step": 93
    },
    {
      "epoch": 0.6619718309859155,
      "grad_norm": 1.4542431831359863,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.4568,
      "step": 94
    },
    {
      "epoch": 0.6690140845070423,
      "grad_norm": 2.2859489917755127,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.4368,
      "step": 95
    },
    {
      "epoch": 0.676056338028169,
      "grad_norm": 2.264481544494629,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.7259,
      "step": 96
    },
    {
      "epoch": 0.6830985915492958,
      "grad_norm": 3.839521646499634,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.663,
      "step": 97
    },
    {
      "epoch": 0.6901408450704225,
      "grad_norm": 1.972511649131775,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.4722,
      "step": 98
    },
    {
      "epoch": 0.6971830985915493,
      "grad_norm": 1.8594896793365479,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.6764,
      "step": 99
    },
    {
      "epoch": 0.6971830985915493,
      "eval_loss": 0.7270611524581909,
      "eval_runtime": 5.2604,
      "eval_samples_per_second": 22.812,
      "eval_steps_per_second": 2.851,
      "step": 99
    },
    {
      "epoch": 0.704225352112676,
      "grad_norm": 1.3822779655456543,
      "learning_rate": 0.0,
      "loss": 1.4299,
      "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": 6.53464644354048e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}