{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2789400278940028,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002789400278940028,
      "grad_norm": 1.3559156656265259,
      "learning_rate": 1e-05,
      "loss": 2.2982,
      "step": 1
    },
    {
      "epoch": 0.002789400278940028,
      "eval_loss": 2.324856758117676,
      "eval_runtime": 52.9801,
      "eval_samples_per_second": 5.7,
      "eval_steps_per_second": 0.717,
      "step": 1
    },
    {
      "epoch": 0.005578800557880056,
      "grad_norm": 1.4949768781661987,
      "learning_rate": 2e-05,
      "loss": 2.3912,
      "step": 2
    },
    {
      "epoch": 0.008368200836820083,
      "grad_norm": 1.295521855354309,
      "learning_rate": 3e-05,
      "loss": 2.1321,
      "step": 3
    },
    {
      "epoch": 0.011157601115760111,
      "grad_norm": 1.3849579095840454,
      "learning_rate": 4e-05,
      "loss": 2.0892,
      "step": 4
    },
    {
      "epoch": 0.01394700139470014,
      "grad_norm": 1.410709261894226,
      "learning_rate": 5e-05,
      "loss": 2.1073,
      "step": 5
    },
    {
      "epoch": 0.016736401673640166,
      "grad_norm": 1.835424542427063,
      "learning_rate": 6e-05,
      "loss": 2.4634,
      "step": 6
    },
    {
      "epoch": 0.019525801952580194,
      "grad_norm": 1.9201370477676392,
      "learning_rate": 7e-05,
      "loss": 2.3361,
      "step": 7
    },
    {
      "epoch": 0.022315202231520222,
      "grad_norm": 1.8919646739959717,
      "learning_rate": 8e-05,
      "loss": 2.3183,
      "step": 8
    },
    {
      "epoch": 0.02510460251046025,
      "grad_norm": 2.5362789630889893,
      "learning_rate": 9e-05,
      "loss": 2.3376,
      "step": 9
    },
    {
      "epoch": 0.02510460251046025,
      "eval_loss": 1.8519941568374634,
      "eval_runtime": 52.8507,
      "eval_samples_per_second": 5.714,
      "eval_steps_per_second": 0.719,
      "step": 9
    },
    {
      "epoch": 0.02789400278940028,
      "grad_norm": 2.107351064682007,
      "learning_rate": 0.0001,
      "loss": 1.9185,
      "step": 10
    },
    {
      "epoch": 0.030683403068340307,
      "grad_norm": 1.8538174629211426,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.5435,
      "step": 11
    },
    {
      "epoch": 0.03347280334728033,
      "grad_norm": 1.4159091711044312,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.2372,
      "step": 12
    },
    {
      "epoch": 0.03626220362622036,
      "grad_norm": 2.1776630878448486,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.4526,
      "step": 13
    },
    {
      "epoch": 0.03905160390516039,
      "grad_norm": 1.743064284324646,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.2122,
      "step": 14
    },
    {
      "epoch": 0.04184100418410042,
      "grad_norm": 1.6609395742416382,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.0635,
      "step": 15
    },
    {
      "epoch": 0.044630404463040445,
      "grad_norm": 1.647965431213379,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.9718,
      "step": 16
    },
    {
      "epoch": 0.04741980474198047,
      "grad_norm": 1.6228158473968506,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.8951,
      "step": 17
    },
    {
      "epoch": 0.0502092050209205,
      "grad_norm": 1.300998330116272,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.8446,
      "step": 18
    },
    {
      "epoch": 0.0502092050209205,
      "eval_loss": 0.7097400426864624,
      "eval_runtime": 52.745,
      "eval_samples_per_second": 5.726,
      "eval_steps_per_second": 0.72,
      "step": 18
    },
    {
      "epoch": 0.05299860529986053,
      "grad_norm": 1.0316293239593506,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.665,
      "step": 19
    },
    {
      "epoch": 0.05578800557880056,
      "grad_norm": 0.992760181427002,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.707,
      "step": 20
    },
    {
      "epoch": 0.058577405857740586,
      "grad_norm": 1.0852915048599243,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.5554,
      "step": 21
    },
    {
      "epoch": 0.061366806136680614,
      "grad_norm": 1.189538598060608,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.5806,
      "step": 22
    },
    {
      "epoch": 0.06415620641562064,
      "grad_norm": 1.0849921703338623,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.5446,
      "step": 23
    },
    {
      "epoch": 0.06694560669456066,
      "grad_norm": 1.1741552352905273,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.5985,
      "step": 24
    },
    {
      "epoch": 0.0697350069735007,
      "grad_norm": 0.9880762100219727,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.4832,
      "step": 25
    },
    {
      "epoch": 0.07252440725244072,
      "grad_norm": 1.2720280885696411,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.5232,
      "step": 26
    },
    {
      "epoch": 0.07531380753138076,
      "grad_norm": 0.8770483732223511,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.5127,
      "step": 27
    },
    {
      "epoch": 0.07531380753138076,
      "eval_loss": 0.4544554054737091,
      "eval_runtime": 52.7242,
      "eval_samples_per_second": 5.728,
      "eval_steps_per_second": 0.721,
      "step": 27
    },
    {
      "epoch": 0.07810320781032078,
      "grad_norm": 1.0763133764266968,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4893,
      "step": 28
    },
    {
      "epoch": 0.08089260808926081,
      "grad_norm": 4.231393337249756,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.5389,
      "step": 29
    },
    {
      "epoch": 0.08368200836820083,
      "grad_norm": 2.0894691944122314,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.5256,
      "step": 30
    },
    {
      "epoch": 0.08647140864714087,
      "grad_norm": 0.9810737371444702,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.4633,
      "step": 31
    },
    {
      "epoch": 0.08926080892608089,
      "grad_norm": 0.6633622050285339,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.3574,
      "step": 32
    },
    {
      "epoch": 0.09205020920502092,
      "grad_norm": 0.9858479499816895,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.4049,
      "step": 33
    },
    {
      "epoch": 0.09483960948396095,
      "grad_norm": 0.8702887892723083,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.3425,
      "step": 34
    },
    {
      "epoch": 0.09762900976290098,
      "grad_norm": 0.8333115577697754,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.3372,
      "step": 35
    },
    {
      "epoch": 0.100418410041841,
      "grad_norm": 0.7566404938697815,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.33,
      "step": 36
    },
    {
      "epoch": 0.100418410041841,
      "eval_loss": 0.3604300320148468,
      "eval_runtime": 52.7348,
      "eval_samples_per_second": 5.727,
      "eval_steps_per_second": 0.721,
      "step": 36
    },
    {
      "epoch": 0.10320781032078104,
      "grad_norm": 0.7114524841308594,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.2738,
      "step": 37
    },
    {
      "epoch": 0.10599721059972106,
      "grad_norm": 0.6801817417144775,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.3377,
      "step": 38
    },
    {
      "epoch": 0.1087866108786611,
      "grad_norm": 0.72431480884552,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.2961,
      "step": 39
    },
    {
      "epoch": 0.11157601115760112,
      "grad_norm": 0.9961448907852173,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.3979,
      "step": 40
    },
    {
      "epoch": 0.11436541143654114,
      "grad_norm": 0.7426677346229553,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.304,
      "step": 41
    },
    {
      "epoch": 0.11715481171548117,
      "grad_norm": 0.634848952293396,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.2814,
      "step": 42
    },
    {
      "epoch": 0.1199442119944212,
      "grad_norm": 0.7828645706176758,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.3165,
      "step": 43
    },
    {
      "epoch": 0.12273361227336123,
      "grad_norm": 0.9621155261993408,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.3042,
      "step": 44
    },
    {
      "epoch": 0.12552301255230125,
      "grad_norm": 0.7523605823516846,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.3727,
      "step": 45
    },
    {
      "epoch": 0.12552301255230125,
      "eval_loss": 0.3056940734386444,
      "eval_runtime": 52.7202,
      "eval_samples_per_second": 5.728,
      "eval_steps_per_second": 0.721,
      "step": 45
    },
    {
      "epoch": 0.12831241283124128,
      "grad_norm": 0.7485724091529846,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2883,
      "step": 46
    },
    {
      "epoch": 0.13110181311018132,
      "grad_norm": 0.6190716028213501,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.2932,
      "step": 47
    },
    {
      "epoch": 0.13389121338912133,
      "grad_norm": 0.8940878510475159,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.3347,
      "step": 48
    },
    {
      "epoch": 0.13668061366806136,
      "grad_norm": 0.7823814749717712,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.2572,
      "step": 49
    },
    {
      "epoch": 0.1394700139470014,
      "grad_norm": 0.7668711543083191,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.3296,
      "step": 50
    },
    {
      "epoch": 0.14225941422594143,
      "grad_norm": 0.7000058889389038,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.2693,
      "step": 51
    },
    {
      "epoch": 0.14504881450488144,
      "grad_norm": 0.6057772636413574,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.2903,
      "step": 52
    },
    {
      "epoch": 0.14783821478382148,
      "grad_norm": 0.5921920537948608,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.239,
      "step": 53
    },
    {
      "epoch": 0.1506276150627615,
      "grad_norm": 0.750872015953064,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.2087,
      "step": 54
    },
    {
      "epoch": 0.1506276150627615,
      "eval_loss": 0.27080443501472473,
      "eval_runtime": 52.711,
      "eval_samples_per_second": 5.729,
      "eval_steps_per_second": 0.721,
      "step": 54
    },
    {
      "epoch": 0.15341701534170155,
      "grad_norm": 0.8061081767082214,
      "learning_rate": 5e-05,
      "loss": 0.267,
      "step": 55
    },
    {
      "epoch": 0.15620641562064155,
      "grad_norm": 0.6060543656349182,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.222,
      "step": 56
    },
    {
      "epoch": 0.1589958158995816,
      "grad_norm": 0.6406531929969788,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.2602,
      "step": 57
    },
    {
      "epoch": 0.16178521617852162,
      "grad_norm": 1.3150423765182495,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.3005,
      "step": 58
    },
    {
      "epoch": 0.16457461645746166,
      "grad_norm": 0.6370297074317932,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.2092,
      "step": 59
    },
    {
      "epoch": 0.16736401673640167,
      "grad_norm": 0.6858253479003906,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1646,
      "step": 60
    },
    {
      "epoch": 0.1701534170153417,
      "grad_norm": 0.8348706960678101,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.2604,
      "step": 61
    },
    {
      "epoch": 0.17294281729428174,
      "grad_norm": 0.7750731706619263,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.2594,
      "step": 62
    },
    {
      "epoch": 0.17573221757322174,
      "grad_norm": 0.5308626294136047,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.2119,
      "step": 63
    },
    {
      "epoch": 0.17573221757322174,
      "eval_loss": 0.25027772784233093,
      "eval_runtime": 52.7494,
      "eval_samples_per_second": 5.725,
      "eval_steps_per_second": 0.72,
      "step": 63
    },
    {
      "epoch": 0.17852161785216178,
      "grad_norm": 0.635723888874054,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2522,
      "step": 64
    },
    {
      "epoch": 0.18131101813110181,
      "grad_norm": 0.6576067805290222,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.2243,
      "step": 65
    },
    {
      "epoch": 0.18410041841004185,
      "grad_norm": 0.6761228442192078,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.2236,
      "step": 66
    },
    {
      "epoch": 0.18688981868898186,
      "grad_norm": 0.6696838736534119,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.2044,
      "step": 67
    },
    {
      "epoch": 0.1896792189679219,
      "grad_norm": 0.6317145824432373,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.1486,
      "step": 68
    },
    {
      "epoch": 0.19246861924686193,
      "grad_norm": 0.9569390416145325,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.6536,
      "step": 69
    },
    {
      "epoch": 0.19525801952580196,
      "grad_norm": 0.7576932907104492,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2566,
      "step": 70
    },
    {
      "epoch": 0.19804741980474197,
      "grad_norm": 1.474607229232788,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.3012,
      "step": 71
    },
    {
      "epoch": 0.200836820083682,
      "grad_norm": 0.6508307456970215,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.2188,
      "step": 72
    },
    {
      "epoch": 0.200836820083682,
      "eval_loss": 0.2393614649772644,
      "eval_runtime": 52.7336,
      "eval_samples_per_second": 5.727,
      "eval_steps_per_second": 0.721,
      "step": 72
    },
    {
      "epoch": 0.20362622036262204,
      "grad_norm": 0.6299262642860413,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1672,
      "step": 73
    },
    {
      "epoch": 0.20641562064156208,
      "grad_norm": 0.5372329354286194,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.1438,
      "step": 74
    },
    {
      "epoch": 0.20920502092050208,
      "grad_norm": 0.844080924987793,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.213,
      "step": 75
    },
    {
      "epoch": 0.21199442119944212,
      "grad_norm": 0.6184529662132263,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1864,
      "step": 76
    },
    {
      "epoch": 0.21478382147838215,
      "grad_norm": 0.8859326839447021,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.37,
      "step": 77
    },
    {
      "epoch": 0.2175732217573222,
      "grad_norm": 0.6930046677589417,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.2325,
      "step": 78
    },
    {
      "epoch": 0.2203626220362622,
      "grad_norm": 0.6587538719177246,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.2372,
      "step": 79
    },
    {
      "epoch": 0.22315202231520223,
      "grad_norm": 0.5163601636886597,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.1806,
      "step": 80
    },
    {
      "epoch": 0.22594142259414227,
      "grad_norm": 0.7977961301803589,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.2736,
      "step": 81
    },
    {
      "epoch": 0.22594142259414227,
      "eval_loss": 0.23303189873695374,
      "eval_runtime": 52.7206,
      "eval_samples_per_second": 5.728,
      "eval_steps_per_second": 0.721,
      "step": 81
    },
    {
      "epoch": 0.22873082287308227,
      "grad_norm": 1.0265192985534668,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.3048,
      "step": 82
    },
    {
      "epoch": 0.2315202231520223,
      "grad_norm": 0.7465397715568542,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.2165,
      "step": 83
    },
    {
      "epoch": 0.23430962343096234,
      "grad_norm": 0.7663724422454834,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.2594,
      "step": 84
    },
    {
      "epoch": 0.23709902370990238,
      "grad_norm": 0.858521580696106,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.2692,
      "step": 85
    },
    {
      "epoch": 0.2398884239888424,
      "grad_norm": 0.5936315059661865,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.2348,
      "step": 86
    },
    {
      "epoch": 0.24267782426778242,
      "grad_norm": 0.5714499354362488,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.187,
      "step": 87
    },
    {
      "epoch": 0.24546722454672246,
      "grad_norm": 0.7403538823127747,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.1411,
      "step": 88
    },
    {
      "epoch": 0.2482566248256625,
      "grad_norm": 0.9827370047569275,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.2321,
      "step": 89
    },
    {
      "epoch": 0.2510460251046025,
      "grad_norm": 0.9658119678497314,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.241,
      "step": 90
    },
    {
      "epoch": 0.2510460251046025,
      "eval_loss": 0.2301451861858368,
      "eval_runtime": 52.756,
      "eval_samples_per_second": 5.724,
      "eval_steps_per_second": 0.72,
      "step": 90
    },
    {
      "epoch": 0.25383542538354253,
      "grad_norm": 0.5446522235870361,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.1993,
      "step": 91
    },
    {
      "epoch": 0.25662482566248257,
      "grad_norm": 0.6010146737098694,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.179,
      "step": 92
    },
    {
      "epoch": 0.2594142259414226,
      "grad_norm": 0.695270836353302,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.1544,
      "step": 93
    },
    {
      "epoch": 0.26220362622036264,
      "grad_norm": 0.5995609164237976,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.2263,
      "step": 94
    },
    {
      "epoch": 0.2649930264993027,
      "grad_norm": 0.9947669506072998,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.2255,
      "step": 95
    },
    {
      "epoch": 0.26778242677824265,
      "grad_norm": 0.6095288991928101,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.1982,
      "step": 96
    },
    {
      "epoch": 0.2705718270571827,
      "grad_norm": 0.7338091731071472,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.1718,
      "step": 97
    },
    {
      "epoch": 0.2733612273361227,
      "grad_norm": 1.0805656909942627,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.3113,
      "step": 98
    },
    {
      "epoch": 0.27615062761506276,
      "grad_norm": 0.7472536563873291,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.2833,
      "step": 99
    },
    {
      "epoch": 0.27615062761506276,
      "eval_loss": 0.2296682894229889,
      "eval_runtime": 52.738,
      "eval_samples_per_second": 5.726,
      "eval_steps_per_second": 0.721,
      "step": 99
    },
    {
      "epoch": 0.2789400278940028,
      "grad_norm": 0.7433314919471741,
      "learning_rate": 0.0,
      "loss": 0.2479,
      "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": 1.301297403789312e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}