{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7936507936507936,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007936507936507936,
      "grad_norm": 0.5940561294555664,
      "learning_rate": 1e-05,
      "loss": 0.7819,
      "step": 1
    },
    {
      "epoch": 0.007936507936507936,
      "eval_loss": 0.7385377883911133,
      "eval_runtime": 12.4705,
      "eval_samples_per_second": 8.5,
      "eval_steps_per_second": 1.123,
      "step": 1
    },
    {
      "epoch": 0.015873015873015872,
      "grad_norm": 0.5844579339027405,
      "learning_rate": 2e-05,
      "loss": 0.5743,
      "step": 2
    },
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 0.6142908334732056,
      "learning_rate": 3e-05,
      "loss": 0.7856,
      "step": 3
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 1.1579065322875977,
      "learning_rate": 4e-05,
      "loss": 1.0332,
      "step": 4
    },
    {
      "epoch": 0.03968253968253968,
      "grad_norm": 0.6027746796607971,
      "learning_rate": 5e-05,
      "loss": 0.6717,
      "step": 5
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 0.9417018294334412,
      "learning_rate": 6e-05,
      "loss": 0.7161,
      "step": 6
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 0.8347136974334717,
      "learning_rate": 7e-05,
      "loss": 0.7583,
      "step": 7
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 1.023072361946106,
      "learning_rate": 8e-05,
      "loss": 0.5415,
      "step": 8
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.4929274022579193,
      "learning_rate": 9e-05,
      "loss": 0.4157,
      "step": 9
    },
    {
      "epoch": 0.07142857142857142,
      "eval_loss": 0.4522353708744049,
      "eval_runtime": 11.789,
      "eval_samples_per_second": 8.991,
      "eval_steps_per_second": 1.188,
      "step": 9
    },
    {
      "epoch": 0.07936507936507936,
      "grad_norm": 0.5577216148376465,
      "learning_rate": 0.0001,
      "loss": 0.4259,
      "step": 10
    },
    {
      "epoch": 0.0873015873015873,
      "grad_norm": 0.7210971117019653,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.4377,
      "step": 11
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.4076630473136902,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.3398,
      "step": 12
    },
    {
      "epoch": 0.10317460317460317,
      "grad_norm": 0.6704097986221313,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.3923,
      "step": 13
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.6116910576820374,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.2966,
      "step": 14
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 0.9248013496398926,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.3506,
      "step": 15
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 0.7895079851150513,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.2511,
      "step": 16
    },
    {
      "epoch": 0.1349206349206349,
      "grad_norm": 0.4172516167163849,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.2474,
      "step": 17
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.4765908718109131,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.2699,
      "step": 18
    },
    {
      "epoch": 0.14285714285714285,
      "eval_loss": 0.2643006443977356,
      "eval_runtime": 11.7881,
      "eval_samples_per_second": 8.992,
      "eval_steps_per_second": 1.188,
      "step": 18
    },
    {
      "epoch": 0.15079365079365079,
      "grad_norm": 0.5411407947540283,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2662,
      "step": 19
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 0.3574010729789734,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2805,
      "step": 20
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.7612572312355042,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.3236,
      "step": 21
    },
    {
      "epoch": 0.1746031746031746,
      "grad_norm": 0.3988335132598877,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.2418,
      "step": 22
    },
    {
      "epoch": 0.18253968253968253,
      "grad_norm": 0.39348870515823364,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.2039,
      "step": 23
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.6038708090782166,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.2575,
      "step": 24
    },
    {
      "epoch": 0.1984126984126984,
      "grad_norm": 0.6375281810760498,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2512,
      "step": 25
    },
    {
      "epoch": 0.20634920634920634,
      "grad_norm": 0.482608437538147,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.2392,
      "step": 26
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.35353580117225647,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.232,
      "step": 27
    },
    {
      "epoch": 0.21428571428571427,
      "eval_loss": 0.23887650668621063,
      "eval_runtime": 11.7951,
      "eval_samples_per_second": 8.987,
      "eval_steps_per_second": 1.187,
      "step": 27
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.5033824443817139,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2169,
      "step": 28
    },
    {
      "epoch": 0.23015873015873015,
      "grad_norm": 0.4087642431259155,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.2463,
      "step": 29
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.3605215549468994,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.2425,
      "step": 30
    },
    {
      "epoch": 0.24603174603174602,
      "grad_norm": 0.2426234781742096,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.2237,
      "step": 31
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 0.4276462197303772,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.263,
      "step": 32
    },
    {
      "epoch": 0.2619047619047619,
      "grad_norm": 0.3156845271587372,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.2098,
      "step": 33
    },
    {
      "epoch": 0.2698412698412698,
      "grad_norm": 0.22470353543758392,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.1993,
      "step": 34
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 0.23595388233661652,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.2161,
      "step": 35
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.3054620325565338,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.2123,
      "step": 36
    },
    {
      "epoch": 0.2857142857142857,
      "eval_loss": 0.22184596955776215,
      "eval_runtime": 11.7876,
      "eval_samples_per_second": 8.993,
      "eval_steps_per_second": 1.188,
      "step": 36
    },
    {
      "epoch": 0.29365079365079366,
      "grad_norm": 0.42485561966896057,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.2481,
      "step": 37
    },
    {
      "epoch": 0.30158730158730157,
      "grad_norm": 0.25488778948783875,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.2089,
      "step": 38
    },
    {
      "epoch": 0.30952380952380953,
      "grad_norm": 0.22732485830783844,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.2151,
      "step": 39
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 0.569657027721405,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1922,
      "step": 40
    },
    {
      "epoch": 0.3253968253968254,
      "grad_norm": 0.27273625135421753,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.2203,
      "step": 41
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.547612726688385,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.2446,
      "step": 42
    },
    {
      "epoch": 0.3412698412698413,
      "grad_norm": 0.3911803364753723,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.2097,
      "step": 43
    },
    {
      "epoch": 0.3492063492063492,
      "grad_norm": 0.34991058707237244,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.1864,
      "step": 44
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.41730400919914246,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.2209,
      "step": 45
    },
    {
      "epoch": 0.35714285714285715,
      "eval_loss": 0.2063593566417694,
      "eval_runtime": 11.7486,
      "eval_samples_per_second": 9.022,
      "eval_steps_per_second": 1.192,
      "step": 45
    },
    {
      "epoch": 0.36507936507936506,
      "grad_norm": 0.48006361722946167,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2276,
      "step": 46
    },
    {
      "epoch": 0.373015873015873,
      "grad_norm": 0.3670620322227478,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.2313,
      "step": 47
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.29657959938049316,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.2078,
      "step": 48
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 0.40728524327278137,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.1976,
      "step": 49
    },
    {
      "epoch": 0.3968253968253968,
      "grad_norm": 0.3712082803249359,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2026,
      "step": 50
    },
    {
      "epoch": 0.40476190476190477,
      "grad_norm": 0.4507344961166382,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.2318,
      "step": 51
    },
    {
      "epoch": 0.4126984126984127,
      "grad_norm": 0.590757429599762,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.2108,
      "step": 52
    },
    {
      "epoch": 0.42063492063492064,
      "grad_norm": 0.45648106932640076,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.2281,
      "step": 53
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.46647682785987854,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.2243,
      "step": 54
    },
    {
      "epoch": 0.42857142857142855,
      "eval_loss": 0.20285502076148987,
      "eval_runtime": 11.786,
      "eval_samples_per_second": 8.994,
      "eval_steps_per_second": 1.188,
      "step": 54
    },
    {
      "epoch": 0.4365079365079365,
      "grad_norm": 0.840855598449707,
      "learning_rate": 5e-05,
      "loss": 0.2236,
      "step": 55
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.40392041206359863,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.2201,
      "step": 56
    },
    {
      "epoch": 0.4523809523809524,
      "grad_norm": 0.37353482842445374,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.1772,
      "step": 57
    },
    {
      "epoch": 0.4603174603174603,
      "grad_norm": 0.4607539474964142,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.1891,
      "step": 58
    },
    {
      "epoch": 0.46825396825396826,
      "grad_norm": 0.7805458903312683,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.2134,
      "step": 59
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.40825238823890686,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.2109,
      "step": 60
    },
    {
      "epoch": 0.48412698412698413,
      "grad_norm": 0.39922696352005005,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.2057,
      "step": 61
    },
    {
      "epoch": 0.49206349206349204,
      "grad_norm": 0.585004985332489,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.2046,
      "step": 62
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.4767926335334778,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.2239,
      "step": 63
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.19394847750663757,
      "eval_runtime": 11.7443,
      "eval_samples_per_second": 9.026,
      "eval_steps_per_second": 1.192,
      "step": 63
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 0.49406272172927856,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2034,
      "step": 64
    },
    {
      "epoch": 0.5158730158730159,
      "grad_norm": 0.298798531293869,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.1868,
      "step": 65
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 0.3498222231864929,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.1837,
      "step": 66
    },
    {
      "epoch": 0.5317460317460317,
      "grad_norm": 0.6188130378723145,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.2095,
      "step": 67
    },
    {
      "epoch": 0.5396825396825397,
      "grad_norm": 0.3307073712348938,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.199,
      "step": 68
    },
    {
      "epoch": 0.5476190476190477,
      "grad_norm": 0.4896056056022644,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.2065,
      "step": 69
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.2844799757003784,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1642,
      "step": 70
    },
    {
      "epoch": 0.5634920634920635,
      "grad_norm": 0.34150537848472595,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.1686,
      "step": 71
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.41576912999153137,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.1663,
      "step": 72
    },
    {
      "epoch": 0.5714285714285714,
      "eval_loss": 0.18488213419914246,
      "eval_runtime": 11.758,
      "eval_samples_per_second": 9.015,
      "eval_steps_per_second": 1.191,
      "step": 72
    },
    {
      "epoch": 0.5793650793650794,
      "grad_norm": 0.3610566556453705,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1656,
      "step": 73
    },
    {
      "epoch": 0.5873015873015873,
      "grad_norm": 0.5242999196052551,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.2121,
      "step": 74
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 0.3753286898136139,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.1943,
      "step": 75
    },
    {
      "epoch": 0.6031746031746031,
      "grad_norm": 0.31328487396240234,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1619,
      "step": 76
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 0.37601473927497864,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.2007,
      "step": 77
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 0.371862530708313,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.1739,
      "step": 78
    },
    {
      "epoch": 0.626984126984127,
      "grad_norm": 0.45121678709983826,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.1895,
      "step": 79
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 0.46577611565589905,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.2122,
      "step": 80
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 0.4364396035671234,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.1786,
      "step": 81
    },
    {
      "epoch": 0.6428571428571429,
      "eval_loss": 0.181279718875885,
      "eval_runtime": 11.7965,
      "eval_samples_per_second": 8.986,
      "eval_steps_per_second": 1.187,
      "step": 81
    },
    {
      "epoch": 0.6507936507936508,
      "grad_norm": 0.35893717408180237,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1865,
      "step": 82
    },
    {
      "epoch": 0.6587301587301587,
      "grad_norm": 0.470602810382843,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.194,
      "step": 83
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.381485253572464,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.1805,
      "step": 84
    },
    {
      "epoch": 0.6746031746031746,
      "grad_norm": 0.40939468145370483,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.1736,
      "step": 85
    },
    {
      "epoch": 0.6825396825396826,
      "grad_norm": 0.4633791744709015,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.1653,
      "step": 86
    },
    {
      "epoch": 0.6904761904761905,
      "grad_norm": 0.47274208068847656,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.2001,
      "step": 87
    },
    {
      "epoch": 0.6984126984126984,
      "grad_norm": 0.38420310616493225,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.1879,
      "step": 88
    },
    {
      "epoch": 0.7063492063492064,
      "grad_norm": 0.5543503761291504,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.2209,
      "step": 89
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.3958447277545929,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2045,
      "step": 90
    },
    {
      "epoch": 0.7142857142857143,
      "eval_loss": 0.17844752967357635,
      "eval_runtime": 11.7617,
      "eval_samples_per_second": 9.012,
      "eval_steps_per_second": 1.19,
      "step": 90
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 0.5378851294517517,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2005,
      "step": 91
    },
    {
      "epoch": 0.7301587301587301,
      "grad_norm": 0.7305738925933838,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.253,
      "step": 92
    },
    {
      "epoch": 0.7380952380952381,
      "grad_norm": 0.35247576236724854,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.1845,
      "step": 93
    },
    {
      "epoch": 0.746031746031746,
      "grad_norm": 0.3374378979206085,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.1605,
      "step": 94
    },
    {
      "epoch": 0.753968253968254,
      "grad_norm": 0.49339020252227783,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.2133,
      "step": 95
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.5759761333465576,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.2141,
      "step": 96
    },
    {
      "epoch": 0.7698412698412699,
      "grad_norm": 0.4132503271102905,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.1785,
      "step": 97
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.41149216890335083,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.1676,
      "step": 98
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 0.35065194964408875,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.1859,
      "step": 99
    },
    {
      "epoch": 0.7857142857142857,
      "eval_loss": 0.1782868206501007,
      "eval_runtime": 11.759,
      "eval_samples_per_second": 9.014,
      "eval_steps_per_second": 1.191,
      "step": 99
    },
    {
      "epoch": 0.7936507936507936,
      "grad_norm": 0.31834158301353455,
      "learning_rate": 0.0,
      "loss": 0.1843,
      "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": 7.641439020672614e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}