{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.035229874933943986,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00035229874933943986,
      "grad_norm": 0.8301784992218018,
      "learning_rate": 1e-05,
      "loss": 1.0314,
      "step": 1
    },
    {
      "epoch": 0.00035229874933943986,
      "eval_loss": 1.0164258480072021,
      "eval_runtime": 513.2549,
      "eval_samples_per_second": 4.659,
      "eval_steps_per_second": 0.583,
      "step": 1
    },
    {
      "epoch": 0.0007045974986788797,
      "grad_norm": 0.81002277135849,
      "learning_rate": 2e-05,
      "loss": 1.0777,
      "step": 2
    },
    {
      "epoch": 0.0010568962480183195,
      "grad_norm": 0.8208487629890442,
      "learning_rate": 3e-05,
      "loss": 1.0731,
      "step": 3
    },
    {
      "epoch": 0.0014091949973577594,
      "grad_norm": 0.8213537931442261,
      "learning_rate": 4e-05,
      "loss": 1.0373,
      "step": 4
    },
    {
      "epoch": 0.0017614937466971991,
      "grad_norm": 0.7464555501937866,
      "learning_rate": 5e-05,
      "loss": 0.9352,
      "step": 5
    },
    {
      "epoch": 0.002113792496036639,
      "grad_norm": 0.8301072716712952,
      "learning_rate": 6e-05,
      "loss": 1.0056,
      "step": 6
    },
    {
      "epoch": 0.002466091245376079,
      "grad_norm": 0.7335529327392578,
      "learning_rate": 7e-05,
      "loss": 0.8623,
      "step": 7
    },
    {
      "epoch": 0.002818389994715519,
      "grad_norm": 0.8173276782035828,
      "learning_rate": 8e-05,
      "loss": 0.8475,
      "step": 8
    },
    {
      "epoch": 0.0031706887440549588,
      "grad_norm": 0.8094016313552856,
      "learning_rate": 9e-05,
      "loss": 0.699,
      "step": 9
    },
    {
      "epoch": 0.0031706887440549588,
      "eval_loss": 0.6605117321014404,
      "eval_runtime": 513.3371,
      "eval_samples_per_second": 4.658,
      "eval_steps_per_second": 0.582,
      "step": 9
    },
    {
      "epoch": 0.0035229874933943982,
      "grad_norm": 0.7788376212120056,
      "learning_rate": 0.0001,
      "loss": 0.6122,
      "step": 10
    },
    {
      "epoch": 0.003875286242733838,
      "grad_norm": 0.9470191597938538,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.6117,
      "step": 11
    },
    {
      "epoch": 0.004227584992073278,
      "grad_norm": 0.9317384362220764,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.5142,
      "step": 12
    },
    {
      "epoch": 0.004579883741412718,
      "grad_norm": 0.9516383409500122,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.4589,
      "step": 13
    },
    {
      "epoch": 0.004932182490752158,
      "grad_norm": 0.8068920373916626,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.3811,
      "step": 14
    },
    {
      "epoch": 0.005284481240091597,
      "grad_norm": 0.7357403635978699,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.3243,
      "step": 15
    },
    {
      "epoch": 0.005636779989431038,
      "grad_norm": 0.6929340958595276,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.2941,
      "step": 16
    },
    {
      "epoch": 0.005989078738770477,
      "grad_norm": 0.6850676536560059,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.2601,
      "step": 17
    },
    {
      "epoch": 0.0063413774881099175,
      "grad_norm": 0.5970450639724731,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.2616,
      "step": 18
    },
    {
      "epoch": 0.0063413774881099175,
      "eval_loss": 0.25062015652656555,
      "eval_runtime": 513.5983,
      "eval_samples_per_second": 4.655,
      "eval_steps_per_second": 0.582,
      "step": 18
    },
    {
      "epoch": 0.006693676237449357,
      "grad_norm": 0.5443854331970215,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2616,
      "step": 19
    },
    {
      "epoch": 0.0070459749867887965,
      "grad_norm": 0.5430485010147095,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.269,
      "step": 20
    },
    {
      "epoch": 0.007398273736128237,
      "grad_norm": 0.5432913303375244,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.2326,
      "step": 21
    },
    {
      "epoch": 0.007750572485467676,
      "grad_norm": 0.5930018424987793,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.2306,
      "step": 22
    },
    {
      "epoch": 0.008102871234807116,
      "grad_norm": 0.49449458718299866,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.2361,
      "step": 23
    },
    {
      "epoch": 0.008455169984146556,
      "grad_norm": 0.45944035053253174,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.2001,
      "step": 24
    },
    {
      "epoch": 0.008807468733485996,
      "grad_norm": 0.4323243200778961,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2244,
      "step": 25
    },
    {
      "epoch": 0.009159767482825437,
      "grad_norm": 0.5384598970413208,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.2247,
      "step": 26
    },
    {
      "epoch": 0.009512066232164875,
      "grad_norm": 0.4801414906978607,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.2245,
      "step": 27
    },
    {
      "epoch": 0.009512066232164875,
      "eval_loss": 0.21149218082427979,
      "eval_runtime": 514.5871,
      "eval_samples_per_second": 4.646,
      "eval_steps_per_second": 0.581,
      "step": 27
    },
    {
      "epoch": 0.009864364981504316,
      "grad_norm": 0.4523373246192932,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2384,
      "step": 28
    },
    {
      "epoch": 0.010216663730843756,
      "grad_norm": 0.5418875813484192,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.2223,
      "step": 29
    },
    {
      "epoch": 0.010568962480183195,
      "grad_norm": 0.32660040259361267,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.1959,
      "step": 30
    },
    {
      "epoch": 0.010921261229522635,
      "grad_norm": 0.3770998418331146,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.2069,
      "step": 31
    },
    {
      "epoch": 0.011273559978862075,
      "grad_norm": 0.43403732776641846,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.2017,
      "step": 32
    },
    {
      "epoch": 0.011625858728201514,
      "grad_norm": 0.4070363938808441,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.1932,
      "step": 33
    },
    {
      "epoch": 0.011978157477540954,
      "grad_norm": 0.3823421597480774,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.2066,
      "step": 34
    },
    {
      "epoch": 0.012330456226880395,
      "grad_norm": 0.4314517378807068,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.218,
      "step": 35
    },
    {
      "epoch": 0.012682754976219835,
      "grad_norm": 0.4176139533519745,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.2175,
      "step": 36
    },
    {
      "epoch": 0.012682754976219835,
      "eval_loss": 0.19645938277244568,
      "eval_runtime": 514.855,
      "eval_samples_per_second": 4.644,
      "eval_steps_per_second": 0.581,
      "step": 36
    },
    {
      "epoch": 0.013035053725559274,
      "grad_norm": 0.3173356354236603,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.183,
      "step": 37
    },
    {
      "epoch": 0.013387352474898714,
      "grad_norm": 0.3026830554008484,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.186,
      "step": 38
    },
    {
      "epoch": 0.013739651224238154,
      "grad_norm": 0.3605559170246124,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.2002,
      "step": 39
    },
    {
      "epoch": 0.014091949973577593,
      "grad_norm": 0.3413389325141907,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1627,
      "step": 40
    },
    {
      "epoch": 0.014444248722917033,
      "grad_norm": 0.32167595624923706,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.1775,
      "step": 41
    },
    {
      "epoch": 0.014796547472256474,
      "grad_norm": 0.36438509821891785,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.1923,
      "step": 42
    },
    {
      "epoch": 0.015148846221595914,
      "grad_norm": 0.2481244057416916,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.1915,
      "step": 43
    },
    {
      "epoch": 0.015501144970935353,
      "grad_norm": 0.3052941560745239,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.1897,
      "step": 44
    },
    {
      "epoch": 0.015853443720274793,
      "grad_norm": 0.5584444999694824,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.1886,
      "step": 45
    },
    {
      "epoch": 0.015853443720274793,
      "eval_loss": 0.18600860238075256,
      "eval_runtime": 513.9707,
      "eval_samples_per_second": 4.652,
      "eval_steps_per_second": 0.582,
      "step": 45
    },
    {
      "epoch": 0.01620574246961423,
      "grad_norm": 0.4166238605976105,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1965,
      "step": 46
    },
    {
      "epoch": 0.016558041218953674,
      "grad_norm": 0.42472735047340393,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.2044,
      "step": 47
    },
    {
      "epoch": 0.016910339968293112,
      "grad_norm": 0.3028751611709595,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.1708,
      "step": 48
    },
    {
      "epoch": 0.01726263871763255,
      "grad_norm": 0.335211843252182,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.192,
      "step": 49
    },
    {
      "epoch": 0.017614937466971993,
      "grad_norm": 0.3441692292690277,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.1761,
      "step": 50
    },
    {
      "epoch": 0.01796723621631143,
      "grad_norm": 0.46626943349838257,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.1848,
      "step": 51
    },
    {
      "epoch": 0.018319534965650874,
      "grad_norm": 0.34437844157218933,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.1926,
      "step": 52
    },
    {
      "epoch": 0.018671833714990312,
      "grad_norm": 0.3511681854724884,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.1794,
      "step": 53
    },
    {
      "epoch": 0.01902413246432975,
      "grad_norm": 0.33112460374832153,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.2026,
      "step": 54
    },
    {
      "epoch": 0.01902413246432975,
      "eval_loss": 0.17996886372566223,
      "eval_runtime": 513.899,
      "eval_samples_per_second": 4.653,
      "eval_steps_per_second": 0.582,
      "step": 54
    },
    {
      "epoch": 0.019376431213669193,
      "grad_norm": 0.2823706269264221,
      "learning_rate": 5e-05,
      "loss": 0.1775,
      "step": 55
    },
    {
      "epoch": 0.01972872996300863,
      "grad_norm": 0.25659382343292236,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.1604,
      "step": 56
    },
    {
      "epoch": 0.02008102871234807,
      "grad_norm": 0.29731568694114685,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.1615,
      "step": 57
    },
    {
      "epoch": 0.020433327461687512,
      "grad_norm": 0.2573408782482147,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.1774,
      "step": 58
    },
    {
      "epoch": 0.02078562621102695,
      "grad_norm": 0.22935473918914795,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.1729,
      "step": 59
    },
    {
      "epoch": 0.02113792496036639,
      "grad_norm": 0.29212892055511475,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1824,
      "step": 60
    },
    {
      "epoch": 0.02149022370970583,
      "grad_norm": 0.25081226229667664,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.1566,
      "step": 61
    },
    {
      "epoch": 0.02184252245904527,
      "grad_norm": 0.27154645323753357,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.1992,
      "step": 62
    },
    {
      "epoch": 0.02219482120838471,
      "grad_norm": 0.29524990916252136,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.1807,
      "step": 63
    },
    {
      "epoch": 0.02219482120838471,
      "eval_loss": 0.17594482004642487,
      "eval_runtime": 513.854,
      "eval_samples_per_second": 4.653,
      "eval_steps_per_second": 0.582,
      "step": 63
    },
    {
      "epoch": 0.02254711995772415,
      "grad_norm": 0.2617270350456238,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1494,
      "step": 64
    },
    {
      "epoch": 0.02289941870706359,
      "grad_norm": 0.3561565577983856,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.2031,
      "step": 65
    },
    {
      "epoch": 0.023251717456403028,
      "grad_norm": 0.3045690357685089,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.1668,
      "step": 66
    },
    {
      "epoch": 0.02360401620574247,
      "grad_norm": 0.2725241184234619,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.1494,
      "step": 67
    },
    {
      "epoch": 0.02395631495508191,
      "grad_norm": 0.2796728312969208,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.1703,
      "step": 68
    },
    {
      "epoch": 0.02430861370442135,
      "grad_norm": 0.26963382959365845,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.1611,
      "step": 69
    },
    {
      "epoch": 0.02466091245376079,
      "grad_norm": 0.24480478465557098,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1655,
      "step": 70
    },
    {
      "epoch": 0.025013211203100228,
      "grad_norm": 0.2573697865009308,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.1594,
      "step": 71
    },
    {
      "epoch": 0.02536550995243967,
      "grad_norm": 0.2376534342765808,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.1667,
      "step": 72
    },
    {
      "epoch": 0.02536550995243967,
      "eval_loss": 0.17308475077152252,
      "eval_runtime": 513.9743,
      "eval_samples_per_second": 4.652,
      "eval_steps_per_second": 0.582,
      "step": 72
    },
    {
      "epoch": 0.02571780870177911,
      "grad_norm": 0.24161791801452637,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1814,
      "step": 73
    },
    {
      "epoch": 0.026070107451118547,
      "grad_norm": 0.21853087842464447,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.1654,
      "step": 74
    },
    {
      "epoch": 0.02642240620045799,
      "grad_norm": 0.31905707716941833,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.1668,
      "step": 75
    },
    {
      "epoch": 0.026774704949797428,
      "grad_norm": 0.4307248890399933,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1825,
      "step": 76
    },
    {
      "epoch": 0.027127003699136867,
      "grad_norm": 0.5884014964103699,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.1886,
      "step": 77
    },
    {
      "epoch": 0.02747930244847631,
      "grad_norm": 0.4084033668041229,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.1692,
      "step": 78
    },
    {
      "epoch": 0.027831601197815747,
      "grad_norm": 0.29296913743019104,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.1631,
      "step": 79
    },
    {
      "epoch": 0.028183899947155186,
      "grad_norm": 0.29117217659950256,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.1875,
      "step": 80
    },
    {
      "epoch": 0.028536198696494628,
      "grad_norm": 0.24767440557479858,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.177,
      "step": 81
    },
    {
      "epoch": 0.028536198696494628,
      "eval_loss": 0.17174069583415985,
      "eval_runtime": 513.728,
      "eval_samples_per_second": 4.654,
      "eval_steps_per_second": 0.582,
      "step": 81
    },
    {
      "epoch": 0.028888497445834067,
      "grad_norm": 0.2397385835647583,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1677,
      "step": 82
    },
    {
      "epoch": 0.02924079619517351,
      "grad_norm": 0.3177073299884796,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.1818,
      "step": 83
    },
    {
      "epoch": 0.029593094944512947,
      "grad_norm": 0.40429046750068665,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.1904,
      "step": 84
    },
    {
      "epoch": 0.029945393693852386,
      "grad_norm": 0.3296579420566559,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.155,
      "step": 85
    },
    {
      "epoch": 0.030297692443191828,
      "grad_norm": 0.2939475476741791,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.1764,
      "step": 86
    },
    {
      "epoch": 0.030649991192531267,
      "grad_norm": 0.2700442671775818,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.1719,
      "step": 87
    },
    {
      "epoch": 0.031002289941870705,
      "grad_norm": 0.27427229285240173,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.1837,
      "step": 88
    },
    {
      "epoch": 0.03135458869121015,
      "grad_norm": 0.2285013496875763,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.1587,
      "step": 89
    },
    {
      "epoch": 0.031706887440549586,
      "grad_norm": 0.25230032205581665,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.185,
      "step": 90
    },
    {
      "epoch": 0.031706887440549586,
      "eval_loss": 0.17110635340213776,
      "eval_runtime": 513.5332,
      "eval_samples_per_second": 4.656,
      "eval_steps_per_second": 0.582,
      "step": 90
    },
    {
      "epoch": 0.032059186189889025,
      "grad_norm": 0.42755863070487976,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.1821,
      "step": 91
    },
    {
      "epoch": 0.03241148493922846,
      "grad_norm": 0.23349186778068542,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.158,
      "step": 92
    },
    {
      "epoch": 0.03276378368856791,
      "grad_norm": 0.31822070479393005,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.1498,
      "step": 93
    },
    {
      "epoch": 0.03311608243790735,
      "grad_norm": 0.257592111825943,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.1809,
      "step": 94
    },
    {
      "epoch": 0.033468381187246786,
      "grad_norm": 0.3682272434234619,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.2006,
      "step": 95
    },
    {
      "epoch": 0.033820679936586225,
      "grad_norm": 0.25005558133125305,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.1924,
      "step": 96
    },
    {
      "epoch": 0.03417297868592566,
      "grad_norm": 0.23438604176044464,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.1602,
      "step": 97
    },
    {
      "epoch": 0.0345252774352651,
      "grad_norm": 0.2923586666584015,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.1988,
      "step": 98
    },
    {
      "epoch": 0.03487757618460455,
      "grad_norm": 0.652924656867981,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.1429,
      "step": 99
    },
    {
      "epoch": 0.03487757618460455,
      "eval_loss": 0.1709044873714447,
      "eval_runtime": 513.0575,
      "eval_samples_per_second": 4.66,
      "eval_steps_per_second": 0.583,
      "step": 99
    },
    {
      "epoch": 0.035229874933943986,
      "grad_norm": 0.28639668226242065,
      "learning_rate": 0.0,
      "loss": 0.1806,
      "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": 1.4392613301072691e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}