{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6872852233676976,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006872852233676976,
      "grad_norm": 0.14803987741470337,
      "learning_rate": 1e-05,
      "loss": 1.1578,
      "step": 1
    },
    {
      "epoch": 0.006872852233676976,
      "eval_loss": 1.1710149049758911,
      "eval_runtime": 4.3328,
      "eval_samples_per_second": 113.091,
      "eval_steps_per_second": 3.693,
      "step": 1
    },
    {
      "epoch": 0.013745704467353952,
      "grad_norm": 0.15052220225334167,
      "learning_rate": 2e-05,
      "loss": 1.1513,
      "step": 2
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": 0.14369502663612366,
      "learning_rate": 3e-05,
      "loss": 1.1303,
      "step": 3
    },
    {
      "epoch": 0.027491408934707903,
      "grad_norm": 0.1555820256471634,
      "learning_rate": 4e-05,
      "loss": 1.1459,
      "step": 4
    },
    {
      "epoch": 0.03436426116838488,
      "grad_norm": 0.14590142667293549,
      "learning_rate": 5e-05,
      "loss": 1.149,
      "step": 5
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 0.1484256237745285,
      "learning_rate": 6e-05,
      "loss": 1.1649,
      "step": 6
    },
    {
      "epoch": 0.048109965635738834,
      "grad_norm": 0.15544907748699188,
      "learning_rate": 7e-05,
      "loss": 1.1709,
      "step": 7
    },
    {
      "epoch": 0.054982817869415807,
      "grad_norm": 0.1625906080007553,
      "learning_rate": 8e-05,
      "loss": 1.1258,
      "step": 8
    },
    {
      "epoch": 0.061855670103092786,
      "grad_norm": 0.1668718308210373,
      "learning_rate": 9e-05,
      "loss": 1.1921,
      "step": 9
    },
    {
      "epoch": 0.061855670103092786,
      "eval_loss": 1.143818736076355,
      "eval_runtime": 4.3318,
      "eval_samples_per_second": 113.118,
      "eval_steps_per_second": 3.694,
      "step": 9
    },
    {
      "epoch": 0.06872852233676977,
      "grad_norm": 0.15247748792171478,
      "learning_rate": 0.0001,
      "loss": 1.1609,
      "step": 10
    },
    {
      "epoch": 0.07560137457044673,
      "grad_norm": 0.1465996950864792,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.1556,
      "step": 11
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 0.14900223910808563,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.0948,
      "step": 12
    },
    {
      "epoch": 0.08934707903780069,
      "grad_norm": 0.14067278802394867,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.1131,
      "step": 13
    },
    {
      "epoch": 0.09621993127147767,
      "grad_norm": 0.1298786699771881,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.0848,
      "step": 14
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 0.13095682859420776,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.0686,
      "step": 15
    },
    {
      "epoch": 0.10996563573883161,
      "grad_norm": 0.1306569129228592,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.0594,
      "step": 16
    },
    {
      "epoch": 0.11683848797250859,
      "grad_norm": 0.1254565715789795,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.0832,
      "step": 17
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 0.12558577954769135,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.0305,
      "step": 18
    },
    {
      "epoch": 0.12371134020618557,
      "eval_loss": 1.0313658714294434,
      "eval_runtime": 4.3339,
      "eval_samples_per_second": 113.062,
      "eval_steps_per_second": 3.692,
      "step": 18
    },
    {
      "epoch": 0.13058419243986255,
      "grad_norm": 0.12779274582862854,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.0607,
      "step": 19
    },
    {
      "epoch": 0.13745704467353953,
      "grad_norm": 0.12421318143606186,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.0467,
      "step": 20
    },
    {
      "epoch": 0.14432989690721648,
      "grad_norm": 0.12824037671089172,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.0159,
      "step": 21
    },
    {
      "epoch": 0.15120274914089346,
      "grad_norm": 0.11996930092573166,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.0136,
      "step": 22
    },
    {
      "epoch": 0.15807560137457044,
      "grad_norm": 0.12454639375209808,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.9861,
      "step": 23
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 0.12318114191293716,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.9651,
      "step": 24
    },
    {
      "epoch": 0.1718213058419244,
      "grad_norm": 0.11891600489616394,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.9605,
      "step": 25
    },
    {
      "epoch": 0.17869415807560138,
      "grad_norm": 0.1270134001970291,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.9527,
      "step": 26
    },
    {
      "epoch": 0.18556701030927836,
      "grad_norm": 0.12178168445825577,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.9732,
      "step": 27
    },
    {
      "epoch": 0.18556701030927836,
      "eval_loss": 0.9542049765586853,
      "eval_runtime": 4.3341,
      "eval_samples_per_second": 113.056,
      "eval_steps_per_second": 3.692,
      "step": 27
    },
    {
      "epoch": 0.19243986254295534,
      "grad_norm": 0.12120404094457626,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.9589,
      "step": 28
    },
    {
      "epoch": 0.19931271477663232,
      "grad_norm": 0.12348782271146774,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.8959,
      "step": 29
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 0.1340678483247757,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.9606,
      "step": 30
    },
    {
      "epoch": 0.21305841924398625,
      "grad_norm": 0.11195500940084457,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.9297,
      "step": 31
    },
    {
      "epoch": 0.21993127147766323,
      "grad_norm": 0.1213698610663414,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.9534,
      "step": 32
    },
    {
      "epoch": 0.2268041237113402,
      "grad_norm": 0.11941356956958771,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.9299,
      "step": 33
    },
    {
      "epoch": 0.23367697594501718,
      "grad_norm": 0.1208919808268547,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.9082,
      "step": 34
    },
    {
      "epoch": 0.24054982817869416,
      "grad_norm": 0.11267133802175522,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.9189,
      "step": 35
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": 0.10793629288673401,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.9211,
      "step": 36
    },
    {
      "epoch": 0.24742268041237114,
      "eval_loss": 0.9084511399269104,
      "eval_runtime": 4.3424,
      "eval_samples_per_second": 112.841,
      "eval_steps_per_second": 3.685,
      "step": 36
    },
    {
      "epoch": 0.2542955326460481,
      "grad_norm": 0.10952258110046387,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8865,
      "step": 37
    },
    {
      "epoch": 0.2611683848797251,
      "grad_norm": 0.11180167645215988,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.9032,
      "step": 38
    },
    {
      "epoch": 0.26804123711340205,
      "grad_norm": 0.10643989592790604,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.894,
      "step": 39
    },
    {
      "epoch": 0.27491408934707906,
      "grad_norm": 0.11159329861402512,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8972,
      "step": 40
    },
    {
      "epoch": 0.281786941580756,
      "grad_norm": 0.11082126200199127,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.8704,
      "step": 41
    },
    {
      "epoch": 0.28865979381443296,
      "grad_norm": 0.10907956957817078,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.8742,
      "step": 42
    },
    {
      "epoch": 0.29553264604810997,
      "grad_norm": 0.11652807146310806,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.8799,
      "step": 43
    },
    {
      "epoch": 0.3024054982817869,
      "grad_norm": 0.11712007969617844,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.9144,
      "step": 44
    },
    {
      "epoch": 0.30927835051546393,
      "grad_norm": 0.10531087219715118,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.902,
      "step": 45
    },
    {
      "epoch": 0.30927835051546393,
      "eval_loss": 0.8796476125717163,
      "eval_runtime": 4.322,
      "eval_samples_per_second": 113.374,
      "eval_steps_per_second": 3.702,
      "step": 45
    },
    {
      "epoch": 0.3161512027491409,
      "grad_norm": 0.10228931903839111,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8662,
      "step": 46
    },
    {
      "epoch": 0.3230240549828179,
      "grad_norm": 0.11387356370687485,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.85,
      "step": 47
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 0.10877646505832672,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.8655,
      "step": 48
    },
    {
      "epoch": 0.33676975945017185,
      "grad_norm": 0.10516759753227234,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.8635,
      "step": 49
    },
    {
      "epoch": 0.3436426116838488,
      "grad_norm": 0.10988269746303558,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.8839,
      "step": 50
    },
    {
      "epoch": 0.35051546391752575,
      "grad_norm": 0.10523088276386261,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.8789,
      "step": 51
    },
    {
      "epoch": 0.35738831615120276,
      "grad_norm": 0.10412962734699249,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.8665,
      "step": 52
    },
    {
      "epoch": 0.3642611683848797,
      "grad_norm": 0.11392374336719513,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.8501,
      "step": 53
    },
    {
      "epoch": 0.3711340206185567,
      "grad_norm": 0.11030527204275131,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.8674,
      "step": 54
    },
    {
      "epoch": 0.3711340206185567,
      "eval_loss": 0.8610700368881226,
      "eval_runtime": 4.3247,
      "eval_samples_per_second": 113.301,
      "eval_steps_per_second": 3.7,
      "step": 54
    },
    {
      "epoch": 0.37800687285223367,
      "grad_norm": 0.11474549025297165,
      "learning_rate": 5e-05,
      "loss": 0.8763,
      "step": 55
    },
    {
      "epoch": 0.3848797250859107,
      "grad_norm": 0.1175265684723854,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.8834,
      "step": 56
    },
    {
      "epoch": 0.3917525773195876,
      "grad_norm": 0.11283692717552185,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.8477,
      "step": 57
    },
    {
      "epoch": 0.39862542955326463,
      "grad_norm": 0.11457814276218414,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.8508,
      "step": 58
    },
    {
      "epoch": 0.4054982817869416,
      "grad_norm": 0.11225730925798416,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.8609,
      "step": 59
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": 0.11168105155229568,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.8532,
      "step": 60
    },
    {
      "epoch": 0.41924398625429554,
      "grad_norm": 0.1141161248087883,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.8122,
      "step": 61
    },
    {
      "epoch": 0.4261168384879725,
      "grad_norm": 0.10743686556816101,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.8289,
      "step": 62
    },
    {
      "epoch": 0.4329896907216495,
      "grad_norm": 0.11766848713159561,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.8581,
      "step": 63
    },
    {
      "epoch": 0.4329896907216495,
      "eval_loss": 0.848796010017395,
      "eval_runtime": 4.3343,
      "eval_samples_per_second": 113.052,
      "eval_steps_per_second": 3.692,
      "step": 63
    },
    {
      "epoch": 0.43986254295532645,
      "grad_norm": 0.11746356636285782,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8677,
      "step": 64
    },
    {
      "epoch": 0.44673539518900346,
      "grad_norm": 0.12862779200077057,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.8654,
      "step": 65
    },
    {
      "epoch": 0.4536082474226804,
      "grad_norm": 0.11820956319570541,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.8095,
      "step": 66
    },
    {
      "epoch": 0.46048109965635736,
      "grad_norm": 0.12124162167310715,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.8402,
      "step": 67
    },
    {
      "epoch": 0.46735395189003437,
      "grad_norm": 0.12057328224182129,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.8651,
      "step": 68
    },
    {
      "epoch": 0.4742268041237113,
      "grad_norm": 0.11911960691213608,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.8275,
      "step": 69
    },
    {
      "epoch": 0.48109965635738833,
      "grad_norm": 0.11372791975736618,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.8372,
      "step": 70
    },
    {
      "epoch": 0.4879725085910653,
      "grad_norm": 0.11872468143701553,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.8532,
      "step": 71
    },
    {
      "epoch": 0.4948453608247423,
      "grad_norm": 0.11730431020259857,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.8477,
      "step": 72
    },
    {
      "epoch": 0.4948453608247423,
      "eval_loss": 0.8410154581069946,
      "eval_runtime": 4.3081,
      "eval_samples_per_second": 113.74,
      "eval_steps_per_second": 3.714,
      "step": 72
    },
    {
      "epoch": 0.5017182130584192,
      "grad_norm": 0.11617182940244675,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8222,
      "step": 73
    },
    {
      "epoch": 0.5085910652920962,
      "grad_norm": 0.11658919602632523,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.8416,
      "step": 74
    },
    {
      "epoch": 0.5154639175257731,
      "grad_norm": 0.11968255788087845,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.8421,
      "step": 75
    },
    {
      "epoch": 0.5223367697594502,
      "grad_norm": 0.12416433542966843,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.8257,
      "step": 76
    },
    {
      "epoch": 0.5292096219931272,
      "grad_norm": 0.12016404420137405,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.7842,
      "step": 77
    },
    {
      "epoch": 0.5360824742268041,
      "grad_norm": 0.11930861324071884,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.8309,
      "step": 78
    },
    {
      "epoch": 0.5429553264604811,
      "grad_norm": 0.11690670996904373,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.8424,
      "step": 79
    },
    {
      "epoch": 0.5498281786941581,
      "grad_norm": 0.12800775468349457,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.8533,
      "step": 80
    },
    {
      "epoch": 0.5567010309278351,
      "grad_norm": 0.11666473746299744,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.8122,
      "step": 81
    },
    {
      "epoch": 0.5567010309278351,
      "eval_loss": 0.8369756937026978,
      "eval_runtime": 4.3476,
      "eval_samples_per_second": 112.707,
      "eval_steps_per_second": 3.68,
      "step": 81
    },
    {
      "epoch": 0.563573883161512,
      "grad_norm": 0.11748181283473969,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8442,
      "step": 82
    },
    {
      "epoch": 0.570446735395189,
      "grad_norm": 0.12347516417503357,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.8251,
      "step": 83
    },
    {
      "epoch": 0.5773195876288659,
      "grad_norm": 0.12434191256761551,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.8409,
      "step": 84
    },
    {
      "epoch": 0.584192439862543,
      "grad_norm": 0.1248202845454216,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.8637,
      "step": 85
    },
    {
      "epoch": 0.5910652920962199,
      "grad_norm": 0.1126582995057106,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.8198,
      "step": 86
    },
    {
      "epoch": 0.5979381443298969,
      "grad_norm": 0.11644302308559418,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.8159,
      "step": 87
    },
    {
      "epoch": 0.6048109965635738,
      "grad_norm": 0.1160711720585823,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.8351,
      "step": 88
    },
    {
      "epoch": 0.6116838487972509,
      "grad_norm": 0.12403754889965057,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.8231,
      "step": 89
    },
    {
      "epoch": 0.6185567010309279,
      "grad_norm": 0.12182094901800156,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.812,
      "step": 90
    },
    {
      "epoch": 0.6185567010309279,
      "eval_loss": 0.8352839350700378,
      "eval_runtime": 4.331,
      "eval_samples_per_second": 113.139,
      "eval_steps_per_second": 3.694,
      "step": 90
    },
    {
      "epoch": 0.6254295532646048,
      "grad_norm": 0.11822124570608139,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.8052,
      "step": 91
    },
    {
      "epoch": 0.6323024054982818,
      "grad_norm": 0.11817607283592224,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.8182,
      "step": 92
    },
    {
      "epoch": 0.6391752577319587,
      "grad_norm": 0.11649473011493683,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.786,
      "step": 93
    },
    {
      "epoch": 0.6460481099656358,
      "grad_norm": 0.12507495284080505,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.7984,
      "step": 94
    },
    {
      "epoch": 0.6529209621993127,
      "grad_norm": 0.12664298713207245,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.8451,
      "step": 95
    },
    {
      "epoch": 0.6597938144329897,
      "grad_norm": 0.11847827583551407,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.8363,
      "step": 96
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.11604692786931992,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.8365,
      "step": 97
    },
    {
      "epoch": 0.6735395189003437,
      "grad_norm": 0.1193615198135376,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.8042,
      "step": 98
    },
    {
      "epoch": 0.6804123711340206,
      "grad_norm": 0.1261865496635437,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.8423,
      "step": 99
    },
    {
      "epoch": 0.6804123711340206,
      "eval_loss": 0.8349943161010742,
      "eval_runtime": 4.3286,
      "eval_samples_per_second": 113.2,
      "eval_steps_per_second": 3.696,
      "step": 99
    },
    {
      "epoch": 0.6872852233676976,
      "grad_norm": 0.127155140042305,
      "learning_rate": 0.0,
      "loss": 0.8032,
      "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": 8.23495017627648e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}