{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.38095238095238093,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0038095238095238095,
      "grad_norm": 0.5346181988716125,
      "learning_rate": 1e-05,
      "loss": 0.4479,
      "step": 1
    },
    {
      "epoch": 0.0038095238095238095,
      "eval_loss": 0.3136264681816101,
      "eval_runtime": 38.0816,
      "eval_samples_per_second": 5.803,
      "eval_steps_per_second": 0.735,
      "step": 1
    },
    {
      "epoch": 0.007619047619047619,
      "grad_norm": 0.23544341325759888,
      "learning_rate": 2e-05,
      "loss": 0.3568,
      "step": 2
    },
    {
      "epoch": 0.011428571428571429,
      "grad_norm": 0.18332810699939728,
      "learning_rate": 3e-05,
      "loss": 0.3308,
      "step": 3
    },
    {
      "epoch": 0.015238095238095238,
      "grad_norm": 0.24650269746780396,
      "learning_rate": 4e-05,
      "loss": 0.4132,
      "step": 4
    },
    {
      "epoch": 0.01904761904761905,
      "grad_norm": 0.19837725162506104,
      "learning_rate": 5e-05,
      "loss": 0.2054,
      "step": 5
    },
    {
      "epoch": 0.022857142857142857,
      "grad_norm": 0.2519557476043701,
      "learning_rate": 6e-05,
      "loss": 0.4548,
      "step": 6
    },
    {
      "epoch": 0.02666666666666667,
      "grad_norm": 0.19431185722351074,
      "learning_rate": 7e-05,
      "loss": 0.1909,
      "step": 7
    },
    {
      "epoch": 0.030476190476190476,
      "grad_norm": 0.33615121245384216,
      "learning_rate": 8e-05,
      "loss": 0.3877,
      "step": 8
    },
    {
      "epoch": 0.03428571428571429,
      "grad_norm": 0.21951714158058167,
      "learning_rate": 9e-05,
      "loss": 0.2187,
      "step": 9
    },
    {
      "epoch": 0.03428571428571429,
      "eval_loss": 0.2572423219680786,
      "eval_runtime": 37.3961,
      "eval_samples_per_second": 5.91,
      "eval_steps_per_second": 0.749,
      "step": 9
    },
    {
      "epoch": 0.0380952380952381,
      "grad_norm": 0.2607838809490204,
      "learning_rate": 0.0001,
      "loss": 0.2781,
      "step": 10
    },
    {
      "epoch": 0.0419047619047619,
      "grad_norm": 0.16654881834983826,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.178,
      "step": 11
    },
    {
      "epoch": 0.045714285714285714,
      "grad_norm": 0.17344437539577484,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.1257,
      "step": 12
    },
    {
      "epoch": 0.049523809523809526,
      "grad_norm": 0.14956307411193848,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.0936,
      "step": 13
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 0.3537381887435913,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.4608,
      "step": 14
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 0.2508176267147064,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.2509,
      "step": 15
    },
    {
      "epoch": 0.06095238095238095,
      "grad_norm": 0.19386368989944458,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.1531,
      "step": 16
    },
    {
      "epoch": 0.06476190476190476,
      "grad_norm": 0.2557080090045929,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.3026,
      "step": 17
    },
    {
      "epoch": 0.06857142857142857,
      "grad_norm": 0.22005097568035126,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.1631,
      "step": 18
    },
    {
      "epoch": 0.06857142857142857,
      "eval_loss": 0.21302443742752075,
      "eval_runtime": 37.3539,
      "eval_samples_per_second": 5.916,
      "eval_steps_per_second": 0.75,
      "step": 18
    },
    {
      "epoch": 0.07238095238095238,
      "grad_norm": 0.24494941532611847,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2477,
      "step": 19
    },
    {
      "epoch": 0.0761904761904762,
      "grad_norm": 0.25652405619621277,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2687,
      "step": 20
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.2818816304206848,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.3878,
      "step": 21
    },
    {
      "epoch": 0.0838095238095238,
      "grad_norm": 0.22919946908950806,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.2388,
      "step": 22
    },
    {
      "epoch": 0.08761904761904762,
      "grad_norm": 0.18502135574817657,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.1765,
      "step": 23
    },
    {
      "epoch": 0.09142857142857143,
      "grad_norm": 0.2394161820411682,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.3521,
      "step": 24
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.04437919706106186,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0249,
      "step": 25
    },
    {
      "epoch": 0.09904761904761905,
      "grad_norm": 0.2186143547296524,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.2908,
      "step": 26
    },
    {
      "epoch": 0.10285714285714286,
      "grad_norm": 0.17146939039230347,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.186,
      "step": 27
    },
    {
      "epoch": 0.10285714285714286,
      "eval_loss": 0.2023545503616333,
      "eval_runtime": 37.3492,
      "eval_samples_per_second": 5.917,
      "eval_steps_per_second": 0.75,
      "step": 27
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 0.09047756344079971,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0744,
      "step": 28
    },
    {
      "epoch": 0.11047619047619048,
      "grad_norm": 0.21479760110378265,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.2477,
      "step": 29
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.16805769503116608,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.1779,
      "step": 30
    },
    {
      "epoch": 0.1180952380952381,
      "grad_norm": 0.19278070330619812,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.2138,
      "step": 31
    },
    {
      "epoch": 0.1219047619047619,
      "grad_norm": 0.2253497689962387,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.2077,
      "step": 32
    },
    {
      "epoch": 0.12571428571428572,
      "grad_norm": 0.32260391116142273,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.4862,
      "step": 33
    },
    {
      "epoch": 0.1295238095238095,
      "grad_norm": 0.22782167792320251,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.2701,
      "step": 34
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.19003619253635406,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.1678,
      "step": 35
    },
    {
      "epoch": 0.13714285714285715,
      "grad_norm": 0.28545764088630676,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.319,
      "step": 36
    },
    {
      "epoch": 0.13714285714285715,
      "eval_loss": 0.19705486297607422,
      "eval_runtime": 37.3319,
      "eval_samples_per_second": 5.92,
      "eval_steps_per_second": 0.75,
      "step": 36
    },
    {
      "epoch": 0.14095238095238094,
      "grad_norm": 0.25164854526519775,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.2585,
      "step": 37
    },
    {
      "epoch": 0.14476190476190476,
      "grad_norm": 0.23714573681354523,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.3039,
      "step": 38
    },
    {
      "epoch": 0.14857142857142858,
      "grad_norm": 0.16014249622821808,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.1471,
      "step": 39
    },
    {
      "epoch": 0.1523809523809524,
      "grad_norm": 0.24672310054302216,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2769,
      "step": 40
    },
    {
      "epoch": 0.15619047619047619,
      "grad_norm": 0.21812938153743744,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.262,
      "step": 41
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.26267993450164795,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.2592,
      "step": 42
    },
    {
      "epoch": 0.16380952380952382,
      "grad_norm": 0.17172189056873322,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.1519,
      "step": 43
    },
    {
      "epoch": 0.1676190476190476,
      "grad_norm": 0.23432576656341553,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.28,
      "step": 44
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.16116373240947723,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.1401,
      "step": 45
    },
    {
      "epoch": 0.17142857142857143,
      "eval_loss": 0.19408152997493744,
      "eval_runtime": 37.3399,
      "eval_samples_per_second": 5.919,
      "eval_steps_per_second": 0.75,
      "step": 45
    },
    {
      "epoch": 0.17523809523809525,
      "grad_norm": 0.23651473224163055,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3014,
      "step": 46
    },
    {
      "epoch": 0.17904761904761904,
      "grad_norm": 0.1395895928144455,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.1193,
      "step": 47
    },
    {
      "epoch": 0.18285714285714286,
      "grad_norm": 0.2189972996711731,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.2888,
      "step": 48
    },
    {
      "epoch": 0.18666666666666668,
      "grad_norm": 0.23274196684360504,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.2881,
      "step": 49
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.047817014157772064,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0335,
      "step": 50
    },
    {
      "epoch": 0.19428571428571428,
      "grad_norm": 0.20129097998142242,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.2356,
      "step": 51
    },
    {
      "epoch": 0.1980952380952381,
      "grad_norm": 0.07301297038793564,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0354,
      "step": 52
    },
    {
      "epoch": 0.2019047619047619,
      "grad_norm": 0.20672406256198883,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.2607,
      "step": 53
    },
    {
      "epoch": 0.2057142857142857,
      "grad_norm": 0.15599939227104187,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.122,
      "step": 54
    },
    {
      "epoch": 0.2057142857142857,
      "eval_loss": 0.1926814764738083,
      "eval_runtime": 37.3206,
      "eval_samples_per_second": 5.922,
      "eval_steps_per_second": 0.75,
      "step": 54
    },
    {
      "epoch": 0.20952380952380953,
      "grad_norm": 0.17496342957019806,
      "learning_rate": 5e-05,
      "loss": 0.1805,
      "step": 55
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.2164146900177002,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.2206,
      "step": 56
    },
    {
      "epoch": 0.21714285714285714,
      "grad_norm": 0.14042288064956665,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.1135,
      "step": 57
    },
    {
      "epoch": 0.22095238095238096,
      "grad_norm": 0.1861671507358551,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.1184,
      "step": 58
    },
    {
      "epoch": 0.22476190476190477,
      "grad_norm": 0.2806834578514099,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.4024,
      "step": 59
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.26244020462036133,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.3134,
      "step": 60
    },
    {
      "epoch": 0.23238095238095238,
      "grad_norm": 0.2721424698829651,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.3339,
      "step": 61
    },
    {
      "epoch": 0.2361904761904762,
      "grad_norm": 0.28071147203445435,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.316,
      "step": 62
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.25714853405952454,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.3324,
      "step": 63
    },
    {
      "epoch": 0.24,
      "eval_loss": 0.19057881832122803,
      "eval_runtime": 37.3668,
      "eval_samples_per_second": 5.914,
      "eval_steps_per_second": 0.749,
      "step": 63
    },
    {
      "epoch": 0.2438095238095238,
      "grad_norm": 0.17730502784252167,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1536,
      "step": 64
    },
    {
      "epoch": 0.24761904761904763,
      "grad_norm": 0.059574998915195465,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0332,
      "step": 65
    },
    {
      "epoch": 0.25142857142857145,
      "grad_norm": 0.14771728217601776,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0978,
      "step": 66
    },
    {
      "epoch": 0.25523809523809526,
      "grad_norm": 0.24020208418369293,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.2786,
      "step": 67
    },
    {
      "epoch": 0.259047619047619,
      "grad_norm": 0.32745540142059326,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.3115,
      "step": 68
    },
    {
      "epoch": 0.26285714285714284,
      "grad_norm": 0.17518901824951172,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.1652,
      "step": 69
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.23748300969600677,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2531,
      "step": 70
    },
    {
      "epoch": 0.2704761904761905,
      "grad_norm": 0.10380688309669495,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0509,
      "step": 71
    },
    {
      "epoch": 0.2742857142857143,
      "grad_norm": 0.190227672457695,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.1803,
      "step": 72
    },
    {
      "epoch": 0.2742857142857143,
      "eval_loss": 0.19022269546985626,
      "eval_runtime": 37.3611,
      "eval_samples_per_second": 5.915,
      "eval_steps_per_second": 0.749,
      "step": 72
    },
    {
      "epoch": 0.2780952380952381,
      "grad_norm": 0.19074185192584991,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1242,
      "step": 73
    },
    {
      "epoch": 0.2819047619047619,
      "grad_norm": 0.2084733545780182,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.2154,
      "step": 74
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.32112589478492737,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.4343,
      "step": 75
    },
    {
      "epoch": 0.2895238095238095,
      "grad_norm": 0.1902702897787094,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1552,
      "step": 76
    },
    {
      "epoch": 0.29333333333333333,
      "grad_norm": 0.2693329453468323,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.2737,
      "step": 77
    },
    {
      "epoch": 0.29714285714285715,
      "grad_norm": 0.31123238801956177,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.3605,
      "step": 78
    },
    {
      "epoch": 0.30095238095238097,
      "grad_norm": 0.2944278120994568,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.3841,
      "step": 79
    },
    {
      "epoch": 0.3047619047619048,
      "grad_norm": 0.16294506192207336,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.1595,
      "step": 80
    },
    {
      "epoch": 0.30857142857142855,
      "grad_norm": 0.2932952344417572,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.4475,
      "step": 81
    },
    {
      "epoch": 0.30857142857142855,
      "eval_loss": 0.1896044760942459,
      "eval_runtime": 37.3867,
      "eval_samples_per_second": 5.911,
      "eval_steps_per_second": 0.749,
      "step": 81
    },
    {
      "epoch": 0.31238095238095237,
      "grad_norm": 0.15527942776679993,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1089,
      "step": 82
    },
    {
      "epoch": 0.3161904761904762,
      "grad_norm": 0.21412207186222076,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.2528,
      "step": 83
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.19277051091194153,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.1487,
      "step": 84
    },
    {
      "epoch": 0.3238095238095238,
      "grad_norm": 0.2552787959575653,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.2528,
      "step": 85
    },
    {
      "epoch": 0.32761904761904764,
      "grad_norm": 0.2055615782737732,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.2111,
      "step": 86
    },
    {
      "epoch": 0.3314285714285714,
      "grad_norm": 0.19458648562431335,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.1901,
      "step": 87
    },
    {
      "epoch": 0.3352380952380952,
      "grad_norm": 0.163802832365036,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.1408,
      "step": 88
    },
    {
      "epoch": 0.33904761904761904,
      "grad_norm": 0.2166626900434494,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.2437,
      "step": 89
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.21965087950229645,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.1838,
      "step": 90
    },
    {
      "epoch": 0.34285714285714286,
      "eval_loss": 0.18933163583278656,
      "eval_runtime": 37.33,
      "eval_samples_per_second": 5.92,
      "eval_steps_per_second": 0.75,
      "step": 90
    },
    {
      "epoch": 0.3466666666666667,
      "grad_norm": 0.24209770560264587,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.206,
      "step": 91
    },
    {
      "epoch": 0.3504761904761905,
      "grad_norm": 0.1948838084936142,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.1765,
      "step": 92
    },
    {
      "epoch": 0.35428571428571426,
      "grad_norm": 0.2708851993083954,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.3214,
      "step": 93
    },
    {
      "epoch": 0.3580952380952381,
      "grad_norm": 0.2648138701915741,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.3246,
      "step": 94
    },
    {
      "epoch": 0.3619047619047619,
      "grad_norm": 0.14957250654697418,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.1071,
      "step": 95
    },
    {
      "epoch": 0.3657142857142857,
      "grad_norm": 0.22787782549858093,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.2352,
      "step": 96
    },
    {
      "epoch": 0.36952380952380953,
      "grad_norm": 0.20865921676158905,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.1892,
      "step": 97
    },
    {
      "epoch": 0.37333333333333335,
      "grad_norm": 0.1268477588891983,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0761,
      "step": 98
    },
    {
      "epoch": 0.37714285714285717,
      "grad_norm": 0.18190668523311615,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.1698,
      "step": 99
    },
    {
      "epoch": 0.37714285714285717,
      "eval_loss": 0.18927593529224396,
      "eval_runtime": 37.3443,
      "eval_samples_per_second": 5.918,
      "eval_steps_per_second": 0.75,
      "step": 99
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.20865972340106964,
      "learning_rate": 0.0,
      "loss": 0.2133,
      "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": 1.1684724716077056e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}