{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3184713375796178,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0031847133757961785,
      "grad_norm": 1.115488052368164,
      "learning_rate": 1e-05,
      "loss": 0.8923,
      "step": 1
    },
    {
      "epoch": 0.0031847133757961785,
      "eval_loss": 0.6753442883491516,
      "eval_runtime": 28.5505,
      "eval_samples_per_second": 9.282,
      "eval_steps_per_second": 1.191,
      "step": 1
    },
    {
      "epoch": 0.006369426751592357,
      "grad_norm": 0.697792649269104,
      "learning_rate": 2e-05,
      "loss": 0.5385,
      "step": 2
    },
    {
      "epoch": 0.009554140127388535,
      "grad_norm": 0.9180307984352112,
      "learning_rate": 3e-05,
      "loss": 0.7585,
      "step": 3
    },
    {
      "epoch": 0.012738853503184714,
      "grad_norm": 0.708147406578064,
      "learning_rate": 4e-05,
      "loss": 0.5962,
      "step": 4
    },
    {
      "epoch": 0.01592356687898089,
      "grad_norm": 0.7137494683265686,
      "learning_rate": 5e-05,
      "loss": 0.5324,
      "step": 5
    },
    {
      "epoch": 0.01910828025477707,
      "grad_norm": 0.8869802951812744,
      "learning_rate": 6e-05,
      "loss": 0.644,
      "step": 6
    },
    {
      "epoch": 0.022292993630573247,
      "grad_norm": 0.6279322504997253,
      "learning_rate": 7e-05,
      "loss": 0.4582,
      "step": 7
    },
    {
      "epoch": 0.025477707006369428,
      "grad_norm": 0.6124541163444519,
      "learning_rate": 8e-05,
      "loss": 0.45,
      "step": 8
    },
    {
      "epoch": 0.028662420382165606,
      "grad_norm": 0.5748103857040405,
      "learning_rate": 9e-05,
      "loss": 0.4067,
      "step": 9
    },
    {
      "epoch": 0.028662420382165606,
      "eval_loss": 0.4189354181289673,
      "eval_runtime": 27.738,
      "eval_samples_per_second": 9.554,
      "eval_steps_per_second": 1.226,
      "step": 9
    },
    {
      "epoch": 0.03184713375796178,
      "grad_norm": 0.5088583827018738,
      "learning_rate": 0.0001,
      "loss": 0.3514,
      "step": 10
    },
    {
      "epoch": 0.03503184713375796,
      "grad_norm": 0.5462948083877563,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.3517,
      "step": 11
    },
    {
      "epoch": 0.03821656050955414,
      "grad_norm": 0.5087607502937317,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.2668,
      "step": 12
    },
    {
      "epoch": 0.041401273885350316,
      "grad_norm": 0.7763290405273438,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.3746,
      "step": 13
    },
    {
      "epoch": 0.044585987261146494,
      "grad_norm": 0.5589542984962463,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.1791,
      "step": 14
    },
    {
      "epoch": 0.04777070063694268,
      "grad_norm": 0.709544837474823,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.1798,
      "step": 15
    },
    {
      "epoch": 0.050955414012738856,
      "grad_norm": 0.6173073053359985,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.1308,
      "step": 16
    },
    {
      "epoch": 0.054140127388535034,
      "grad_norm": 0.810734748840332,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.1134,
      "step": 17
    },
    {
      "epoch": 0.05732484076433121,
      "grad_norm": 0.7491536140441895,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.1201,
      "step": 18
    },
    {
      "epoch": 0.05732484076433121,
      "eval_loss": 0.11272910982370377,
      "eval_runtime": 27.8759,
      "eval_samples_per_second": 9.506,
      "eval_steps_per_second": 1.22,
      "step": 18
    },
    {
      "epoch": 0.06050955414012739,
      "grad_norm": 0.471101313829422,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0994,
      "step": 19
    },
    {
      "epoch": 0.06369426751592357,
      "grad_norm": 0.5923621654510498,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1055,
      "step": 20
    },
    {
      "epoch": 0.06687898089171974,
      "grad_norm": 0.44465842843055725,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.099,
      "step": 21
    },
    {
      "epoch": 0.07006369426751592,
      "grad_norm": 0.41296958923339844,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0914,
      "step": 22
    },
    {
      "epoch": 0.0732484076433121,
      "grad_norm": 0.30696362257003784,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.0614,
      "step": 23
    },
    {
      "epoch": 0.07643312101910828,
      "grad_norm": 0.5171131491661072,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0645,
      "step": 24
    },
    {
      "epoch": 0.07961783439490445,
      "grad_norm": 0.44935065507888794,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0587,
      "step": 25
    },
    {
      "epoch": 0.08280254777070063,
      "grad_norm": 0.34924501180648804,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0661,
      "step": 26
    },
    {
      "epoch": 0.08598726114649681,
      "grad_norm": 0.259950190782547,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0526,
      "step": 27
    },
    {
      "epoch": 0.08598726114649681,
      "eval_loss": 0.06498026102781296,
      "eval_runtime": 27.8621,
      "eval_samples_per_second": 9.511,
      "eval_steps_per_second": 1.22,
      "step": 27
    },
    {
      "epoch": 0.08917197452229299,
      "grad_norm": 0.37740960717201233,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0482,
      "step": 28
    },
    {
      "epoch": 0.09235668789808917,
      "grad_norm": 0.44652295112609863,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.0672,
      "step": 29
    },
    {
      "epoch": 0.09554140127388536,
      "grad_norm": 0.5386968851089478,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0627,
      "step": 30
    },
    {
      "epoch": 0.09872611464968153,
      "grad_norm": 0.3329814672470093,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0536,
      "step": 31
    },
    {
      "epoch": 0.10191082802547771,
      "grad_norm": 0.3999462127685547,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.042,
      "step": 32
    },
    {
      "epoch": 0.10509554140127389,
      "grad_norm": 0.4074510931968689,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0858,
      "step": 33
    },
    {
      "epoch": 0.10828025477707007,
      "grad_norm": 0.4060448706150055,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0629,
      "step": 34
    },
    {
      "epoch": 0.11146496815286625,
      "grad_norm": 0.33128824830055237,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0467,
      "step": 35
    },
    {
      "epoch": 0.11464968152866242,
      "grad_norm": 0.28124168515205383,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0336,
      "step": 36
    },
    {
      "epoch": 0.11464968152866242,
      "eval_loss": 0.051190927624702454,
      "eval_runtime": 27.7522,
      "eval_samples_per_second": 9.549,
      "eval_steps_per_second": 1.225,
      "step": 36
    },
    {
      "epoch": 0.1178343949044586,
      "grad_norm": 0.3602929711341858,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0288,
      "step": 37
    },
    {
      "epoch": 0.12101910828025478,
      "grad_norm": 0.3745328187942505,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0501,
      "step": 38
    },
    {
      "epoch": 0.12420382165605096,
      "grad_norm": 0.48710617423057556,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0662,
      "step": 39
    },
    {
      "epoch": 0.12738853503184713,
      "grad_norm": 0.3970116078853607,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0437,
      "step": 40
    },
    {
      "epoch": 0.1305732484076433,
      "grad_norm": 0.36601918935775757,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0836,
      "step": 41
    },
    {
      "epoch": 0.1337579617834395,
      "grad_norm": 0.37417304515838623,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0498,
      "step": 42
    },
    {
      "epoch": 0.13694267515923567,
      "grad_norm": 0.3792519271373749,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0598,
      "step": 43
    },
    {
      "epoch": 0.14012738853503184,
      "grad_norm": 0.24354057013988495,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0391,
      "step": 44
    },
    {
      "epoch": 0.14331210191082802,
      "grad_norm": 0.24774585664272308,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0373,
      "step": 45
    },
    {
      "epoch": 0.14331210191082802,
      "eval_loss": 0.04600941762328148,
      "eval_runtime": 27.6949,
      "eval_samples_per_second": 9.569,
      "eval_steps_per_second": 1.228,
      "step": 45
    },
    {
      "epoch": 0.1464968152866242,
      "grad_norm": 0.2508378028869629,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0423,
      "step": 46
    },
    {
      "epoch": 0.14968152866242038,
      "grad_norm": 0.16944631934165955,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0247,
      "step": 47
    },
    {
      "epoch": 0.15286624203821655,
      "grad_norm": 0.40228548645973206,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.044,
      "step": 48
    },
    {
      "epoch": 0.15605095541401273,
      "grad_norm": 0.2818053364753723,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0372,
      "step": 49
    },
    {
      "epoch": 0.1592356687898089,
      "grad_norm": 0.6381693482398987,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0544,
      "step": 50
    },
    {
      "epoch": 0.1624203821656051,
      "grad_norm": 0.18308870494365692,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0305,
      "step": 51
    },
    {
      "epoch": 0.16560509554140126,
      "grad_norm": 0.24834081530570984,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0314,
      "step": 52
    },
    {
      "epoch": 0.16878980891719744,
      "grad_norm": 0.21828560531139374,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0258,
      "step": 53
    },
    {
      "epoch": 0.17197452229299362,
      "grad_norm": 0.3777863681316376,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0447,
      "step": 54
    },
    {
      "epoch": 0.17197452229299362,
      "eval_loss": 0.04182341694831848,
      "eval_runtime": 27.7076,
      "eval_samples_per_second": 9.564,
      "eval_steps_per_second": 1.227,
      "step": 54
    },
    {
      "epoch": 0.1751592356687898,
      "grad_norm": 0.385259211063385,
      "learning_rate": 5e-05,
      "loss": 0.0427,
      "step": 55
    },
    {
      "epoch": 0.17834394904458598,
      "grad_norm": 0.25352638959884644,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0449,
      "step": 56
    },
    {
      "epoch": 0.18152866242038215,
      "grad_norm": 0.2799479365348816,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0334,
      "step": 57
    },
    {
      "epoch": 0.18471337579617833,
      "grad_norm": 0.10697340220212936,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0164,
      "step": 58
    },
    {
      "epoch": 0.18789808917197454,
      "grad_norm": 0.2636820077896118,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0199,
      "step": 59
    },
    {
      "epoch": 0.1910828025477707,
      "grad_norm": 0.29948464035987854,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.043,
      "step": 60
    },
    {
      "epoch": 0.1942675159235669,
      "grad_norm": 0.3402281105518341,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0361,
      "step": 61
    },
    {
      "epoch": 0.19745222929936307,
      "grad_norm": 0.2752113342285156,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.033,
      "step": 62
    },
    {
      "epoch": 0.20063694267515925,
      "grad_norm": 0.2980349659919739,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0295,
      "step": 63
    },
    {
      "epoch": 0.20063694267515925,
      "eval_loss": 0.04023485630750656,
      "eval_runtime": 27.7042,
      "eval_samples_per_second": 9.565,
      "eval_steps_per_second": 1.227,
      "step": 63
    },
    {
      "epoch": 0.20382165605095542,
      "grad_norm": 0.2337586134672165,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0252,
      "step": 64
    },
    {
      "epoch": 0.2070063694267516,
      "grad_norm": 0.29516276717185974,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0445,
      "step": 65
    },
    {
      "epoch": 0.21019108280254778,
      "grad_norm": 0.170352503657341,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0264,
      "step": 66
    },
    {
      "epoch": 0.21337579617834396,
      "grad_norm": 0.298715204000473,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0481,
      "step": 67
    },
    {
      "epoch": 0.21656050955414013,
      "grad_norm": 0.4538519084453583,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0405,
      "step": 68
    },
    {
      "epoch": 0.2197452229299363,
      "grad_norm": 0.2287202924489975,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0264,
      "step": 69
    },
    {
      "epoch": 0.2229299363057325,
      "grad_norm": 0.272175669670105,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0388,
      "step": 70
    },
    {
      "epoch": 0.22611464968152867,
      "grad_norm": 0.415954053401947,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0372,
      "step": 71
    },
    {
      "epoch": 0.22929936305732485,
      "grad_norm": 0.3850722312927246,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0499,
      "step": 72
    },
    {
      "epoch": 0.22929936305732485,
      "eval_loss": 0.038790568709373474,
      "eval_runtime": 27.693,
      "eval_samples_per_second": 9.569,
      "eval_steps_per_second": 1.228,
      "step": 72
    },
    {
      "epoch": 0.23248407643312102,
      "grad_norm": 0.5190379023551941,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.039,
      "step": 73
    },
    {
      "epoch": 0.2356687898089172,
      "grad_norm": 0.24570351839065552,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0401,
      "step": 74
    },
    {
      "epoch": 0.23885350318471338,
      "grad_norm": 0.26611748337745667,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0358,
      "step": 75
    },
    {
      "epoch": 0.24203821656050956,
      "grad_norm": 0.34741511940956116,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0311,
      "step": 76
    },
    {
      "epoch": 0.24522292993630573,
      "grad_norm": 0.1831596940755844,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0318,
      "step": 77
    },
    {
      "epoch": 0.2484076433121019,
      "grad_norm": 0.21395991742610931,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.03,
      "step": 78
    },
    {
      "epoch": 0.2515923566878981,
      "grad_norm": 0.2382720559835434,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0478,
      "step": 79
    },
    {
      "epoch": 0.25477707006369427,
      "grad_norm": 0.32946422696113586,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0283,
      "step": 80
    },
    {
      "epoch": 0.25796178343949044,
      "grad_norm": 0.1543850153684616,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0235,
      "step": 81
    },
    {
      "epoch": 0.25796178343949044,
      "eval_loss": 0.036795035004615784,
      "eval_runtime": 27.6977,
      "eval_samples_per_second": 9.568,
      "eval_steps_per_second": 1.228,
      "step": 81
    },
    {
      "epoch": 0.2611464968152866,
      "grad_norm": 0.21874427795410156,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.037,
      "step": 82
    },
    {
      "epoch": 0.2643312101910828,
      "grad_norm": 0.21999911963939667,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0226,
      "step": 83
    },
    {
      "epoch": 0.267515923566879,
      "grad_norm": 0.23353098332881927,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0273,
      "step": 84
    },
    {
      "epoch": 0.27070063694267515,
      "grad_norm": 0.29108190536499023,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0485,
      "step": 85
    },
    {
      "epoch": 0.27388535031847133,
      "grad_norm": 0.19980104267597198,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0213,
      "step": 86
    },
    {
      "epoch": 0.2770700636942675,
      "grad_norm": 0.31934672594070435,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0301,
      "step": 87
    },
    {
      "epoch": 0.2802547770700637,
      "grad_norm": 0.2646752893924713,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.022,
      "step": 88
    },
    {
      "epoch": 0.28343949044585987,
      "grad_norm": 0.36101585626602173,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.039,
      "step": 89
    },
    {
      "epoch": 0.28662420382165604,
      "grad_norm": 0.2735932469367981,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0373,
      "step": 90
    },
    {
      "epoch": 0.28662420382165604,
      "eval_loss": 0.036771975457668304,
      "eval_runtime": 27.7037,
      "eval_samples_per_second": 9.566,
      "eval_steps_per_second": 1.227,
      "step": 90
    },
    {
      "epoch": 0.2898089171974522,
      "grad_norm": 0.31893447041511536,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0418,
      "step": 91
    },
    {
      "epoch": 0.2929936305732484,
      "grad_norm": 0.34668245911598206,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0366,
      "step": 92
    },
    {
      "epoch": 0.2961783439490446,
      "grad_norm": 0.3424743711948395,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0445,
      "step": 93
    },
    {
      "epoch": 0.29936305732484075,
      "grad_norm": 0.14717084169387817,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0287,
      "step": 94
    },
    {
      "epoch": 0.30254777070063693,
      "grad_norm": 0.25211742520332336,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0387,
      "step": 95
    },
    {
      "epoch": 0.3057324840764331,
      "grad_norm": 0.1929836869239807,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0201,
      "step": 96
    },
    {
      "epoch": 0.3089171974522293,
      "grad_norm": 0.19661644101142883,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.031,
      "step": 97
    },
    {
      "epoch": 0.31210191082802546,
      "grad_norm": 0.47783294320106506,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0203,
      "step": 98
    },
    {
      "epoch": 0.31528662420382164,
      "grad_norm": 0.2048252671957016,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0236,
      "step": 99
    },
    {
      "epoch": 0.31528662420382164,
      "eval_loss": 0.03640306740999222,
      "eval_runtime": 27.7053,
      "eval_samples_per_second": 9.565,
      "eval_steps_per_second": 1.227,
      "step": 99
    },
    {
      "epoch": 0.3184713375796178,
      "grad_norm": 0.2546924352645874,
      "learning_rate": 0.0,
      "loss": 0.04,
      "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": 6.643995874689024e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}