{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 11,
  "global_step": 108,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009259259259259259,
      "grad_norm": 2.362648319863932,
      "learning_rate": 5e-06,
      "loss": 0.5807,
      "step": 1
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 2.136281230840684,
      "learning_rate": 1e-05,
      "loss": 0.534,
      "step": 2
    },
    {
      "epoch": 0.027777777777777776,
      "grad_norm": 2.2915803466254743,
      "learning_rate": 9.997804182543973e-06,
      "loss": 0.6069,
      "step": 3
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 1.817521417636344,
      "learning_rate": 9.991218658821609e-06,
      "loss": 0.5863,
      "step": 4
    },
    {
      "epoch": 0.046296296296296294,
      "grad_norm": 1.4406196993263543,
      "learning_rate": 9.980249213076085e-06,
      "loss": 0.5952,
      "step": 5
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 1.098132624881383,
      "learning_rate": 9.964905480067585e-06,
      "loss": 0.5384,
      "step": 6
    },
    {
      "epoch": 0.06481481481481481,
      "grad_norm": 1.2038829059152325,
      "learning_rate": 9.945200936610821e-06,
      "loss": 0.5779,
      "step": 7
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 1.1568981182086557,
      "learning_rate": 9.921152889737985e-06,
      "loss": 0.5487,
      "step": 8
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 1.009464783024193,
      "learning_rate": 9.892782461497521e-06,
      "loss": 0.5162,
      "step": 9
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 1.0403262733706924,
      "learning_rate": 9.860114570402055e-06,
      "loss": 0.4825,
      "step": 10
    },
    {
      "epoch": 0.10185185185185185,
      "grad_norm": 1.017871214392586,
      "learning_rate": 9.823177909541795e-06,
      "loss": 0.4962,
      "step": 11
    },
    {
      "epoch": 0.10185185185185185,
      "eval_loss": 0.5000379085540771,
      "eval_runtime": 7.2133,
      "eval_samples_per_second": 1.248,
      "eval_steps_per_second": 0.277,
      "step": 11
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 1.0511034662384473,
      "learning_rate": 9.782004921382612e-06,
      "loss": 0.4456,
      "step": 12
    },
    {
      "epoch": 0.12037037037037036,
      "grad_norm": 0.8657886515614241,
      "learning_rate": 9.736631769270958e-06,
      "loss": 0.4288,
      "step": 13
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 1.040741797545574,
      "learning_rate": 9.687098305670606e-06,
      "loss": 0.5855,
      "step": 14
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 1.3516228019504957,
      "learning_rate": 9.633448037159167e-06,
      "loss": 0.5184,
      "step": 15
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.9843907475003576,
      "learning_rate": 9.575728086215093e-06,
      "loss": 0.5568,
      "step": 16
    },
    {
      "epoch": 0.1574074074074074,
      "grad_norm": 0.8979836323930017,
      "learning_rate": 9.513989149828718e-06,
      "loss": 0.4272,
      "step": 17
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 1.1188974861045773,
      "learning_rate": 9.448285454973739e-06,
      "loss": 0.487,
      "step": 18
    },
    {
      "epoch": 0.17592592592592593,
      "grad_norm": 1.048669002845475,
      "learning_rate": 9.378674710978185e-06,
      "loss": 0.5321,
      "step": 19
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.2366432725685659,
      "learning_rate": 9.305218058836778e-06,
      "loss": 0.5396,
      "step": 20
    },
    {
      "epoch": 0.19444444444444445,
      "grad_norm": 1.0072812014692536,
      "learning_rate": 9.22798001750913e-06,
      "loss": 0.446,
      "step": 21
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 1.0654455593583398,
      "learning_rate": 9.14702842725101e-06,
      "loss": 0.5313,
      "step": 22
    },
    {
      "epoch": 0.2037037037037037,
      "eval_loss": 0.4791085124015808,
      "eval_runtime": 7.1652,
      "eval_samples_per_second": 1.256,
      "eval_steps_per_second": 0.279,
      "step": 22
    },
    {
      "epoch": 0.21296296296296297,
      "grad_norm": 1.0051504278398855,
      "learning_rate": 9.062434390028407e-06,
      "loss": 0.4983,
      "step": 23
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.9621751996571424,
      "learning_rate": 8.974272207066767e-06,
      "loss": 0.4642,
      "step": 24
    },
    {
      "epoch": 0.23148148148148148,
      "grad_norm": 0.9763151052182862,
      "learning_rate": 8.882619313590212e-06,
      "loss": 0.4832,
      "step": 25
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 0.934861026969845,
      "learning_rate": 8.787556210808101e-06,
      "loss": 0.441,
      "step": 26
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.0362041830687405,
      "learning_rate": 8.689166395208638e-06,
      "loss": 0.4489,
      "step": 27
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 0.9049359816184893,
      "learning_rate": 8.587536285221656e-06,
      "loss": 0.4971,
      "step": 28
    },
    {
      "epoch": 0.26851851851851855,
      "grad_norm": 0.9982959368756156,
      "learning_rate": 8.482755145314987e-06,
      "loss": 0.5289,
      "step": 29
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 2.050950638692456,
      "learning_rate": 8.374915007591053e-06,
      "loss": 0.5496,
      "step": 30
    },
    {
      "epoch": 0.28703703703703703,
      "grad_norm": 1.0501945401080932,
      "learning_rate": 8.264110590952609e-06,
      "loss": 0.5261,
      "step": 31
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.9229687907732845,
      "learning_rate": 8.150439217908557e-06,
      "loss": 0.4814,
      "step": 32
    },
    {
      "epoch": 0.3055555555555556,
      "grad_norm": 1.4319914933917381,
      "learning_rate": 8.034000729092967e-06,
      "loss": 0.4692,
      "step": 33
    },
    {
      "epoch": 0.3055555555555556,
      "eval_loss": 0.46850860118865967,
      "eval_runtime": 7.148,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.28,
      "step": 33
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 0.8881275342675574,
      "learning_rate": 7.914897395572362e-06,
      "loss": 0.4372,
      "step": 34
    },
    {
      "epoch": 0.32407407407407407,
      "grad_norm": 0.9840343978467488,
      "learning_rate": 7.793233829018263e-06,
      "loss": 0.5235,
      "step": 35
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.8470332819900018,
      "learning_rate": 7.669116889823955e-06,
      "loss": 0.4339,
      "step": 36
    },
    {
      "epoch": 0.3425925925925926,
      "grad_norm": 0.8893330836178615,
      "learning_rate": 7.542655593246103e-06,
      "loss": 0.4426,
      "step": 37
    },
    {
      "epoch": 0.35185185185185186,
      "grad_norm": 1.0550698950573756,
      "learning_rate": 7.413961013653725e-06,
      "loss": 0.5744,
      "step": 38
    },
    {
      "epoch": 0.3611111111111111,
      "grad_norm": 0.8784333801568516,
      "learning_rate": 7.283146186968566e-06,
      "loss": 0.3849,
      "step": 39
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.9142401659654863,
      "learning_rate": 7.1503260113826035e-06,
      "loss": 0.4057,
      "step": 40
    },
    {
      "epoch": 0.37962962962962965,
      "grad_norm": 0.8743924562233322,
      "learning_rate": 7.015617146439863e-06,
      "loss": 0.4149,
      "step": 41
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 0.9155700365107549,
      "learning_rate": 6.879137910571191e-06,
      "loss": 0.4557,
      "step": 42
    },
    {
      "epoch": 0.39814814814814814,
      "grad_norm": 0.9844599172183693,
      "learning_rate": 6.741008177171995e-06,
      "loss": 0.5052,
      "step": 43
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 0.8432119339426061,
      "learning_rate": 6.601349269314188e-06,
      "loss": 0.3876,
      "step": 44
    },
    {
      "epoch": 0.4074074074074074,
      "eval_loss": 0.4595443606376648,
      "eval_runtime": 7.1719,
      "eval_samples_per_second": 1.255,
      "eval_steps_per_second": 0.279,
      "step": 44
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 0.9547733839048285,
      "learning_rate": 6.46028385318488e-06,
      "loss": 0.4381,
      "step": 45
    },
    {
      "epoch": 0.42592592592592593,
      "grad_norm": 0.9165610947735227,
      "learning_rate": 6.3179358303453386e-06,
      "loss": 0.433,
      "step": 46
    },
    {
      "epoch": 0.4351851851851852,
      "grad_norm": 0.9276788988821667,
      "learning_rate": 6.17443022890492e-06,
      "loss": 0.4699,
      "step": 47
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.9408707549804078,
      "learning_rate": 6.029893093705492e-06,
      "loss": 0.4584,
      "step": 48
    },
    {
      "epoch": 0.4537037037037037,
      "grad_norm": 0.9822969953152866,
      "learning_rate": 5.884451375612865e-06,
      "loss": 0.5243,
      "step": 49
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 1.0689960747907674,
      "learning_rate": 5.738232820012407e-06,
      "loss": 0.4329,
      "step": 50
    },
    {
      "epoch": 0.4722222222222222,
      "grad_norm": 1.0494906655322942,
      "learning_rate": 5.591365854606829e-06,
      "loss": 0.5633,
      "step": 51
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 0.8987830176611722,
      "learning_rate": 5.443979476614674e-06,
      "loss": 0.445,
      "step": 52
    },
    {
      "epoch": 0.49074074074074076,
      "grad_norm": 0.8746204581445627,
      "learning_rate": 5.296203139468572e-06,
      "loss": 0.3809,
      "step": 53
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.8125477508425051,
      "learning_rate": 5.148166639112799e-06,
      "loss": 0.3964,
      "step": 54
    },
    {
      "epoch": 0.5092592592592593,
      "grad_norm": 0.907249706367073,
      "learning_rate": 5e-06,
      "loss": 0.4768,
      "step": 55
    },
    {
      "epoch": 0.5092592592592593,
      "eval_loss": 0.4542139768600464,
      "eval_runtime": 7.1716,
      "eval_samples_per_second": 1.255,
      "eval_steps_per_second": 0.279,
      "step": 55
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 0.8641393129712072,
      "learning_rate": 4.8518333608872015e-06,
      "loss": 0.4238,
      "step": 56
    },
    {
      "epoch": 0.5277777777777778,
      "grad_norm": 1.3038267949545501,
      "learning_rate": 4.703796860531429e-06,
      "loss": 0.5484,
      "step": 57
    },
    {
      "epoch": 0.5370370370370371,
      "grad_norm": 1.0286161889066556,
      "learning_rate": 4.556020523385326e-06,
      "loss": 0.397,
      "step": 58
    },
    {
      "epoch": 0.5462962962962963,
      "grad_norm": 0.8754084053422794,
      "learning_rate": 4.408634145393172e-06,
      "loss": 0.4452,
      "step": 59
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.935284958978312,
      "learning_rate": 4.261767179987595e-06,
      "loss": 0.4896,
      "step": 60
    },
    {
      "epoch": 0.5648148148148148,
      "grad_norm": 0.9674393986889579,
      "learning_rate": 4.115548624387136e-06,
      "loss": 0.4887,
      "step": 61
    },
    {
      "epoch": 0.5740740740740741,
      "grad_norm": 0.9724892358854195,
      "learning_rate": 3.970106906294509e-06,
      "loss": 0.4997,
      "step": 62
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 0.8794971763479272,
      "learning_rate": 3.825569771095082e-06,
      "loss": 0.417,
      "step": 63
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.8881388944091057,
      "learning_rate": 3.682064169654663e-06,
      "loss": 0.4504,
      "step": 64
    },
    {
      "epoch": 0.6018518518518519,
      "grad_norm": 0.9193120996402042,
      "learning_rate": 3.539716146815122e-06,
      "loss": 0.4694,
      "step": 65
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 1.0073500011381085,
      "learning_rate": 3.398650730685813e-06,
      "loss": 0.4985,
      "step": 66
    },
    {
      "epoch": 0.6111111111111112,
      "eval_loss": 0.4495806097984314,
      "eval_runtime": 7.1798,
      "eval_samples_per_second": 1.254,
      "eval_steps_per_second": 0.279,
      "step": 66
    },
    {
      "epoch": 0.6203703703703703,
      "grad_norm": 0.824519734053682,
      "learning_rate": 3.258991822828007e-06,
      "loss": 0.4104,
      "step": 67
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 0.9368830049136432,
      "learning_rate": 3.1208620894288105e-06,
      "loss": 0.4926,
      "step": 68
    },
    {
      "epoch": 0.6388888888888888,
      "grad_norm": 1.1454803265014575,
      "learning_rate": 2.98438285356014e-06,
      "loss": 0.4655,
      "step": 69
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 0.8964782710358511,
      "learning_rate": 2.8496739886173994e-06,
      "loss": 0.4535,
      "step": 70
    },
    {
      "epoch": 0.6574074074074074,
      "grad_norm": 0.9529134597913587,
      "learning_rate": 2.716853813031435e-06,
      "loss": 0.5186,
      "step": 71
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.963788290306135,
      "learning_rate": 2.5860389863462765e-06,
      "loss": 0.522,
      "step": 72
    },
    {
      "epoch": 0.6759259259259259,
      "grad_norm": 0.8411162085924286,
      "learning_rate": 2.457344406753899e-06,
      "loss": 0.4245,
      "step": 73
    },
    {
      "epoch": 0.6851851851851852,
      "grad_norm": 0.8871221033397801,
      "learning_rate": 2.330883110176049e-06,
      "loss": 0.4806,
      "step": 74
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 0.9550800145418555,
      "learning_rate": 2.2067661709817384e-06,
      "loss": 0.5149,
      "step": 75
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 0.8501908519121222,
      "learning_rate": 2.0851026044276405e-06,
      "loss": 0.4107,
      "step": 76
    },
    {
      "epoch": 0.7129629629629629,
      "grad_norm": 0.8678719046436287,
      "learning_rate": 1.9659992709070346e-06,
      "loss": 0.4687,
      "step": 77
    },
    {
      "epoch": 0.7129629629629629,
      "eval_loss": 0.44653645157814026,
      "eval_runtime": 7.1486,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.28,
      "step": 77
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 0.876245605736801,
      "learning_rate": 1.8495607820914451e-06,
      "loss": 0.4197,
      "step": 78
    },
    {
      "epoch": 0.7314814814814815,
      "grad_norm": 0.7970757955872202,
      "learning_rate": 1.7358894090473928e-06,
      "loss": 0.3619,
      "step": 79
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.7955115388136204,
      "learning_rate": 1.6250849924089485e-06,
      "loss": 0.3587,
      "step": 80
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.7782242902212891,
      "learning_rate": 1.5172448546850166e-06,
      "loss": 0.3391,
      "step": 81
    },
    {
      "epoch": 0.7592592592592593,
      "grad_norm": 0.9995473034082181,
      "learning_rate": 1.4124637147783431e-06,
      "loss": 0.5386,
      "step": 82
    },
    {
      "epoch": 0.7685185185185185,
      "grad_norm": 0.8444693019666363,
      "learning_rate": 1.3108336047913633e-06,
      "loss": 0.4069,
      "step": 83
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.8808187390006551,
      "learning_rate": 1.2124437891918995e-06,
      "loss": 0.4371,
      "step": 84
    },
    {
      "epoch": 0.7870370370370371,
      "grad_norm": 0.9813077333772956,
      "learning_rate": 1.1173806864097885e-06,
      "loss": 0.4374,
      "step": 85
    },
    {
      "epoch": 0.7962962962962963,
      "grad_norm": 0.8064326056384253,
      "learning_rate": 1.0257277929332332e-06,
      "loss": 0.3986,
      "step": 86
    },
    {
      "epoch": 0.8055555555555556,
      "grad_norm": 0.8710631137320209,
      "learning_rate": 9.375656099715935e-07,
      "loss": 0.4473,
      "step": 87
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 0.887311644170428,
      "learning_rate": 8.529715727489912e-07,
      "loss": 0.4484,
      "step": 88
    },
    {
      "epoch": 0.8148148148148148,
      "eval_loss": 0.4449349045753479,
      "eval_runtime": 7.1634,
      "eval_samples_per_second": 1.256,
      "eval_steps_per_second": 0.279,
      "step": 88
    },
    {
      "epoch": 0.8240740740740741,
      "grad_norm": 0.7647806015755853,
      "learning_rate": 7.720199824908692e-07,
      "loss": 0.3425,
      "step": 89
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.8976917694082569,
      "learning_rate": 6.947819411632223e-07,
      "loss": 0.4269,
      "step": 90
    },
    {
      "epoch": 0.8425925925925926,
      "grad_norm": 0.9316801386853545,
      "learning_rate": 6.213252890218163e-07,
      "loss": 0.5674,
      "step": 91
    },
    {
      "epoch": 0.8518518518518519,
      "grad_norm": 0.8870482831956321,
      "learning_rate": 5.517145450262639e-07,
      "loss": 0.454,
      "step": 92
    },
    {
      "epoch": 0.8611111111111112,
      "grad_norm": 0.7768323848063172,
      "learning_rate": 4.860108501712824e-07,
      "loss": 0.3412,
      "step": 93
    },
    {
      "epoch": 0.8703703703703703,
      "grad_norm": 0.8658069877384894,
      "learning_rate": 4.242719137849077e-07,
      "loss": 0.4292,
      "step": 94
    },
    {
      "epoch": 0.8796296296296297,
      "grad_norm": 0.9112502068381936,
      "learning_rate": 3.665519628408332e-07,
      "loss": 0.4765,
      "step": 95
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.8505617937603335,
      "learning_rate": 3.1290169432939556e-07,
      "loss": 0.428,
      "step": 96
    },
    {
      "epoch": 0.8981481481481481,
      "grad_norm": 0.8868085158482631,
      "learning_rate": 2.6336823072904305e-07,
      "loss": 0.4488,
      "step": 97
    },
    {
      "epoch": 0.9074074074074074,
      "grad_norm": 0.8291365248164002,
      "learning_rate": 2.179950786173879e-07,
      "loss": 0.3881,
      "step": 98
    },
    {
      "epoch": 0.9166666666666666,
      "grad_norm": 0.9100636810782011,
      "learning_rate": 1.7682209045820687e-07,
      "loss": 0.4809,
      "step": 99
    },
    {
      "epoch": 0.9166666666666666,
      "eval_loss": 0.4441840946674347,
      "eval_runtime": 7.1692,
      "eval_samples_per_second": 1.255,
      "eval_steps_per_second": 0.279,
      "step": 99
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 0.8985637565061618,
      "learning_rate": 1.3988542959794627e-07,
      "loss": 0.4533,
      "step": 100
    },
    {
      "epoch": 0.9351851851851852,
      "grad_norm": 0.9612580974302548,
      "learning_rate": 1.0721753850247984e-07,
      "loss": 0.5236,
      "step": 101
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 0.8120796428633341,
      "learning_rate": 7.884711026201586e-08,
      "loss": 0.3763,
      "step": 102
    },
    {
      "epoch": 0.9537037037037037,
      "grad_norm": 0.8644849276991213,
      "learning_rate": 5.479906338917984e-08,
      "loss": 0.4101,
      "step": 103
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 0.8946182268462048,
      "learning_rate": 3.5094519932415417e-08,
      "loss": 0.4942,
      "step": 104
    },
    {
      "epoch": 0.9722222222222222,
      "grad_norm": 0.9166159846522884,
      "learning_rate": 1.975078692391552e-08,
      "loss": 0.4778,
      "step": 105
    },
    {
      "epoch": 0.9814814814814815,
      "grad_norm": 0.9473852601201989,
      "learning_rate": 8.781341178393244e-09,
      "loss": 0.4537,
      "step": 106
    },
    {
      "epoch": 0.9907407407407407,
      "grad_norm": 0.8895854364679423,
      "learning_rate": 2.19581745602826e-09,
      "loss": 0.4192,
      "step": 107
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.7849733548858487,
      "learning_rate": 0.0,
      "loss": 0.3589,
      "step": 108
    },
    {
      "epoch": 1.0,
      "step": 108,
      "total_flos": 17851226259456.0,
      "train_loss": 0.46821982275556634,
      "train_runtime": 1249.8096,
      "train_samples_per_second": 0.69,
      "train_steps_per_second": 0.086
    }
  ],
  "logging_steps": 1,
  "max_steps": 108,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 108,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 17851226259456.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}