{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.984,
  "eval_steps": 500,
  "global_step": 124,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 6.260679721832275,
      "learning_rate": 0.0,
      "loss": 0.8916,
      "step": 1
    },
    {
      "epoch": 0.032,
      "grad_norm": 4.489860534667969,
      "learning_rate": 7.525749891599529e-06,
      "loss": 0.4733,
      "step": 2
    },
    {
      "epoch": 0.048,
      "grad_norm": 4.7128214836120605,
      "learning_rate": 1.192803136799156e-05,
      "loss": 0.4743,
      "step": 3
    },
    {
      "epoch": 0.064,
      "grad_norm": 2.6470186710357666,
      "learning_rate": 1.5051499783199057e-05,
      "loss": 0.359,
      "step": 4
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.181567907333374,
      "learning_rate": 1.7474250108400467e-05,
      "loss": 0.1721,
      "step": 5
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.8668755292892456,
      "learning_rate": 1.945378125959109e-05,
      "loss": 0.0896,
      "step": 6
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.5912112593650818,
      "learning_rate": 2.1127451000356418e-05,
      "loss": 0.0514,
      "step": 7
    },
    {
      "epoch": 0.128,
      "grad_norm": 1.9294259548187256,
      "learning_rate": 2.2577249674798584e-05,
      "loss": 0.0583,
      "step": 8
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.6033430099487305,
      "learning_rate": 2.385606273598312e-05,
      "loss": 0.0407,
      "step": 9
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.8109920620918274,
      "learning_rate": 2.4999999999999998e-05,
      "loss": 0.0421,
      "step": 10
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.6512332558631897,
      "learning_rate": 2.6034817128955623e-05,
      "loss": 0.0316,
      "step": 11
    },
    {
      "epoch": 0.192,
      "grad_norm": 1.0062273740768433,
      "learning_rate": 2.6979531151190617e-05,
      "loss": 0.0295,
      "step": 12
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.5179202556610107,
      "learning_rate": 2.7848583807670913e-05,
      "loss": 0.0206,
      "step": 13
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.5218726396560669,
      "learning_rate": 2.8653200891955945e-05,
      "loss": 0.0231,
      "step": 14
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.2781904637813568,
      "learning_rate": 2.940228147639203e-05,
      "loss": 0.0154,
      "step": 15
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.5812982320785522,
      "learning_rate": 3.0102999566398115e-05,
      "loss": 0.0162,
      "step": 16
    },
    {
      "epoch": 0.272,
      "grad_norm": 0.3600836396217346,
      "learning_rate": 3.076122303445685e-05,
      "loss": 0.0145,
      "step": 17
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.7257829904556274,
      "learning_rate": 3.1381812627582646e-05,
      "loss": 0.0138,
      "step": 18
    },
    {
      "epoch": 0.304,
      "grad_norm": 0.6328442692756653,
      "learning_rate": 3.1968840023820715e-05,
      "loss": 0.0157,
      "step": 19
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.6370071768760681,
      "learning_rate": 3.2525749891599525e-05,
      "loss": 0.0149,
      "step": 20
    },
    {
      "epoch": 0.336,
      "grad_norm": 3.0266289710998535,
      "learning_rate": 3.305548236834798e-05,
      "loss": 0.0409,
      "step": 21
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.6135730743408203,
      "learning_rate": 3.3560567020555153e-05,
      "loss": 0.0175,
      "step": 22
    },
    {
      "epoch": 0.368,
      "grad_norm": 0.2914888560771942,
      "learning_rate": 3.404319590043982e-05,
      "loss": 0.0106,
      "step": 23
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.400644451379776,
      "learning_rate": 3.450528104279015e-05,
      "loss": 0.0111,
      "step": 24
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.3323403000831604,
      "learning_rate": 3.4948500216800935e-05,
      "loss": 0.0062,
      "step": 25
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.32765913009643555,
      "learning_rate": 3.537433369927044e-05,
      "loss": 0.0082,
      "step": 26
    },
    {
      "epoch": 0.432,
      "grad_norm": 0.6343632340431213,
      "learning_rate": 3.578409410397468e-05,
      "loss": 0.0083,
      "step": 27
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.15722662210464478,
      "learning_rate": 3.6178950783555475e-05,
      "loss": 0.0045,
      "step": 28
    },
    {
      "epoch": 0.464,
      "grad_norm": 0.3368499279022217,
      "learning_rate": 3.65599499474739e-05,
      "loss": 0.0063,
      "step": 29
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.4413555860519409,
      "learning_rate": 3.6928031367991554e-05,
      "loss": 0.0103,
      "step": 30
    },
    {
      "epoch": 0.496,
      "grad_norm": 0.24060547351837158,
      "learning_rate": 3.728404234585681e-05,
      "loss": 0.0048,
      "step": 31
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.16296981275081635,
      "learning_rate": 3.762874945799765e-05,
      "loss": 0.0036,
      "step": 32
    },
    {
      "epoch": 0.528,
      "grad_norm": 0.23275071382522583,
      "learning_rate": 3.796284849694718e-05,
      "loss": 0.0034,
      "step": 33
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.1245385929942131,
      "learning_rate": 3.8286972926056376e-05,
      "loss": 0.0028,
      "step": 34
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.1135798767209053,
      "learning_rate": 3.8601701108756885e-05,
      "loss": 0.002,
      "step": 35
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.23044870793819427,
      "learning_rate": 3.890756251918218e-05,
      "loss": 0.0065,
      "step": 36
    },
    {
      "epoch": 0.592,
      "grad_norm": 0.5501028299331665,
      "learning_rate": 3.920504310167487e-05,
      "loss": 0.0046,
      "step": 37
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.23214226961135864,
      "learning_rate": 3.949458991542025e-05,
      "loss": 0.002,
      "step": 38
    },
    {
      "epoch": 0.624,
      "grad_norm": 0.05016089230775833,
      "learning_rate": 3.977661517566247e-05,
      "loss": 0.0005,
      "step": 39
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.3493764102458954,
      "learning_rate": 4.005149978319905e-05,
      "loss": 0.0039,
      "step": 40
    },
    {
      "epoch": 0.656,
      "grad_norm": 0.37873852252960205,
      "learning_rate": 4.031959641799338e-05,
      "loss": 0.0028,
      "step": 41
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.3247808814048767,
      "learning_rate": 4.058123225994751e-05,
      "loss": 0.0049,
      "step": 42
    },
    {
      "epoch": 0.688,
      "grad_norm": 0.3204132914543152,
      "learning_rate": 4.0836711389489654e-05,
      "loss": 0.0015,
      "step": 43
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.3880802094936371,
      "learning_rate": 4.108631691215468e-05,
      "loss": 0.0109,
      "step": 44
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.19677099585533142,
      "learning_rate": 4.133031284438358e-05,
      "loss": 0.0033,
      "step": 45
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.5502466559410095,
      "learning_rate": 4.156894579203935e-05,
      "loss": 0.009,
      "step": 46
    },
    {
      "epoch": 0.752,
      "grad_norm": 0.8511503338813782,
      "learning_rate": 4.180244644839293e-05,
      "loss": 0.0072,
      "step": 47
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.5488025546073914,
      "learning_rate": 4.203103093438968e-05,
      "loss": 0.0069,
      "step": 48
    },
    {
      "epoch": 0.784,
      "grad_norm": 0.13556785881519318,
      "learning_rate": 4.2254902000712836e-05,
      "loss": 0.003,
      "step": 49
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.13148938119411469,
      "learning_rate": 4.247425010840046e-05,
      "loss": 0.0016,
      "step": 50
    },
    {
      "epoch": 0.816,
      "grad_norm": 0.23687539994716644,
      "learning_rate": 4.2689254402448405e-05,
      "loss": 0.0042,
      "step": 51
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.17727361619472504,
      "learning_rate": 4.290008359086998e-05,
      "loss": 0.0019,
      "step": 52
    },
    {
      "epoch": 0.848,
      "grad_norm": 0.19355517625808716,
      "learning_rate": 4.310689674001973e-05,
      "loss": 0.0042,
      "step": 53
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.3897351622581482,
      "learning_rate": 4.330984399557421e-05,
      "loss": 0.0043,
      "step": 54
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.4540916979312897,
      "learning_rate": 4.350906723735609e-05,
      "loss": 0.0098,
      "step": 55
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.250455766916275,
      "learning_rate": 4.370470067515501e-05,
      "loss": 0.0024,
      "step": 56
    },
    {
      "epoch": 0.912,
      "grad_norm": 0.35260751843452454,
      "learning_rate": 4.3896871391812285e-05,
      "loss": 0.0058,
      "step": 57
    },
    {
      "epoch": 0.928,
      "grad_norm": 0.06356976181268692,
      "learning_rate": 4.408569983907343e-05,
      "loss": 0.001,
      "step": 58
    },
    {
      "epoch": 0.944,
      "grad_norm": 0.1714349240064621,
      "learning_rate": 4.42713002910536e-05,
      "loss": 0.0013,
      "step": 59
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.29726922512054443,
      "learning_rate": 4.445378125959108e-05,
      "loss": 0.0022,
      "step": 60
    },
    {
      "epoch": 0.976,
      "grad_norm": 0.08912788331508636,
      "learning_rate": 4.463324587526917e-05,
      "loss": 0.0019,
      "step": 61
    },
    {
      "epoch": 0.992,
      "grad_norm": 0.20514051616191864,
      "learning_rate": 4.4809792237456346e-05,
      "loss": 0.0025,
      "step": 62
    },
    {
      "epoch": 1.008,
      "grad_norm": 0.308870792388916,
      "learning_rate": 4.498351373633954e-05,
      "loss": 0.0016,
      "step": 63
    },
    {
      "epoch": 1.024,
      "grad_norm": 0.04065869003534317,
      "learning_rate": 4.515449934959717e-05,
      "loss": 0.0005,
      "step": 64
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.06654071062803268,
      "learning_rate": 4.532283391607138e-05,
      "loss": 0.0014,
      "step": 65
    },
    {
      "epoch": 1.056,
      "grad_norm": 0.012122690677642822,
      "learning_rate": 4.548859838854671e-05,
      "loss": 0.0002,
      "step": 66
    },
    {
      "epoch": 1.072,
      "grad_norm": 0.07316377013921738,
      "learning_rate": 4.565187006752065e-05,
      "loss": 0.0004,
      "step": 67
    },
    {
      "epoch": 1.088,
      "grad_norm": 0.09919071197509766,
      "learning_rate": 4.581272281765591e-05,
      "loss": 0.0005,
      "step": 68
    },
    {
      "epoch": 1.104,
      "grad_norm": 0.20175501704216003,
      "learning_rate": 4.597122726843138e-05,
      "loss": 0.0031,
      "step": 69
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.05414087697863579,
      "learning_rate": 4.612745100035642e-05,
      "loss": 0.0004,
      "step": 70
    },
    {
      "epoch": 1.1360000000000001,
      "grad_norm": 0.23636992275714874,
      "learning_rate": 4.628145871797688e-05,
      "loss": 0.0009,
      "step": 71
    },
    {
      "epoch": 1.152,
      "grad_norm": 0.030036162585020065,
      "learning_rate": 4.643331241078171e-05,
      "loss": 0.0002,
      "step": 72
    },
    {
      "epoch": 1.168,
      "grad_norm": 0.06486513465642929,
      "learning_rate": 4.658307150301139e-05,
      "loss": 0.0007,
      "step": 73
    },
    {
      "epoch": 1.184,
      "grad_norm": 0.3187963664531708,
      "learning_rate": 4.67307929932744e-05,
      "loss": 0.0007,
      "step": 74
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.08750700950622559,
      "learning_rate": 4.687653158479249e-05,
      "loss": 0.0005,
      "step": 75
    },
    {
      "epoch": 1.216,
      "grad_norm": 0.1704445630311966,
      "learning_rate": 4.702033980701978e-05,
      "loss": 0.0043,
      "step": 76
    },
    {
      "epoch": 1.232,
      "grad_norm": 0.05070444941520691,
      "learning_rate": 4.716226812931204e-05,
      "loss": 0.0002,
      "step": 77
    },
    {
      "epoch": 1.248,
      "grad_norm": 0.16684693098068237,
      "learning_rate": 4.7302365067262006e-05,
      "loss": 0.0005,
      "step": 78
    },
    {
      "epoch": 1.264,
      "grad_norm": 0.1785346418619156,
      "learning_rate": 4.744067728226103e-05,
      "loss": 0.0015,
      "step": 79
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.11600260436534882,
      "learning_rate": 4.757724967479858e-05,
      "loss": 0.0002,
      "step": 80
    },
    {
      "epoch": 1.296,
      "grad_norm": 0.11261828243732452,
      "learning_rate": 4.771212547196624e-05,
      "loss": 0.0014,
      "step": 81
    },
    {
      "epoch": 1.312,
      "grad_norm": 0.14189577102661133,
      "learning_rate": 4.7845346309592914e-05,
      "loss": 0.0022,
      "step": 82
    },
    {
      "epoch": 1.328,
      "grad_norm": 0.03923390433192253,
      "learning_rate": 4.7976952309401844e-05,
      "loss": 0.0003,
      "step": 83
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 0.18425288796424866,
      "learning_rate": 4.810698215154703e-05,
      "loss": 0.0016,
      "step": 84
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.030996577814221382,
      "learning_rate": 4.823547314285732e-05,
      "loss": 0.0003,
      "step": 85
    },
    {
      "epoch": 1.376,
      "grad_norm": 0.0935090109705925,
      "learning_rate": 4.836246128108918e-05,
      "loss": 0.0002,
      "step": 86
    },
    {
      "epoch": 1.392,
      "grad_norm": 0.06287915259599686,
      "learning_rate": 4.8487981315465456e-05,
      "loss": 0.0004,
      "step": 87
    },
    {
      "epoch": 1.408,
      "grad_norm": 0.2098032534122467,
      "learning_rate": 4.8612066803754214e-05,
      "loss": 0.0027,
      "step": 88
    },
    {
      "epoch": 1.424,
      "grad_norm": 0.33795973658561707,
      "learning_rate": 4.873475016612281e-05,
      "loss": 0.0016,
      "step": 89
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.0037344074808061123,
      "learning_rate": 4.885606273598312e-05,
      "loss": 0.0001,
      "step": 90
    },
    {
      "epoch": 1.456,
      "grad_norm": 0.063005730509758,
      "learning_rate": 4.897603480802733e-05,
      "loss": 0.0004,
      "step": 91
    },
    {
      "epoch": 1.472,
      "grad_norm": 0.22439338266849518,
      "learning_rate": 4.909469568363888e-05,
      "loss": 0.0012,
      "step": 92
    },
    {
      "epoch": 1.488,
      "grad_norm": 0.1571952849626541,
      "learning_rate": 4.9212073713848375e-05,
      "loss": 0.0022,
      "step": 93
    },
    {
      "epoch": 1.504,
      "grad_norm": 0.05777396634221077,
      "learning_rate": 4.932819633999246e-05,
      "loss": 0.0002,
      "step": 94
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.2547585070133209,
      "learning_rate": 4.9443090132221186e-05,
      "loss": 0.0017,
      "step": 95
    },
    {
      "epoch": 1.536,
      "grad_norm": 0.18122625350952148,
      "learning_rate": 4.9556780825989205e-05,
      "loss": 0.0009,
      "step": 96
    },
    {
      "epoch": 1.552,
      "grad_norm": 0.1862194538116455,
      "learning_rate": 4.9669293356656114e-05,
      "loss": 0.0034,
      "step": 97
    },
    {
      "epoch": 1.568,
      "grad_norm": 0.07604966312646866,
      "learning_rate": 4.978065189231237e-05,
      "loss": 0.0005,
      "step": 98
    },
    {
      "epoch": 1.584,
      "grad_norm": 0.30250972509384155,
      "learning_rate": 4.989087986493874e-05,
      "loss": 0.0012,
      "step": 99
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.24614813923835754,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 0.0039,
      "step": 100
    },
    {
      "epoch": 1.616,
      "grad_norm": 0.5879510045051575,
      "learning_rate": 5e-05,
      "loss": 0.0013,
      "step": 101
    },
    {
      "epoch": 1.6320000000000001,
      "grad_norm": 0.22871676087379456,
      "learning_rate": 4.791666666666667e-05,
      "loss": 0.0028,
      "step": 102
    },
    {
      "epoch": 1.6480000000000001,
      "grad_norm": 0.707224428653717,
      "learning_rate": 4.5833333333333334e-05,
      "loss": 0.0189,
      "step": 103
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 0.4451245367527008,
      "learning_rate": 4.375e-05,
      "loss": 0.012,
      "step": 104
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.4289276599884033,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.0172,
      "step": 105
    },
    {
      "epoch": 1.696,
      "grad_norm": 0.16858172416687012,
      "learning_rate": 3.958333333333333e-05,
      "loss": 0.0054,
      "step": 106
    },
    {
      "epoch": 1.712,
      "grad_norm": 0.6743901371955872,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.018,
      "step": 107
    },
    {
      "epoch": 1.728,
      "grad_norm": 0.12994635105133057,
      "learning_rate": 3.541666666666667e-05,
      "loss": 0.0028,
      "step": 108
    },
    {
      "epoch": 1.744,
      "grad_norm": 0.23073440790176392,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0066,
      "step": 109
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.2053990364074707,
      "learning_rate": 3.125e-05,
      "loss": 0.0062,
      "step": 110
    },
    {
      "epoch": 1.776,
      "grad_norm": 0.21822550892829895,
      "learning_rate": 2.916666666666667e-05,
      "loss": 0.0048,
      "step": 111
    },
    {
      "epoch": 1.792,
      "grad_norm": 0.23637858033180237,
      "learning_rate": 2.7083333333333332e-05,
      "loss": 0.008,
      "step": 112
    },
    {
      "epoch": 1.808,
      "grad_norm": 0.16311441361904144,
      "learning_rate": 2.5e-05,
      "loss": 0.0046,
      "step": 113
    },
    {
      "epoch": 1.8239999999999998,
      "grad_norm": 0.22796936333179474,
      "learning_rate": 2.2916666666666667e-05,
      "loss": 0.0059,
      "step": 114
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.10936176776885986,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 0.0032,
      "step": 115
    },
    {
      "epoch": 1.8559999999999999,
      "grad_norm": 0.0829433873295784,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 0.0022,
      "step": 116
    },
    {
      "epoch": 1.8719999999999999,
      "grad_norm": 0.06876740604639053,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0017,
      "step": 117
    },
    {
      "epoch": 1.888,
      "grad_norm": 0.1515437364578247,
      "learning_rate": 1.4583333333333335e-05,
      "loss": 0.0027,
      "step": 118
    },
    {
      "epoch": 1.904,
      "grad_norm": 0.1485004723072052,
      "learning_rate": 1.25e-05,
      "loss": 0.0021,
      "step": 119
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.07808104157447815,
      "learning_rate": 1.0416666666666668e-05,
      "loss": 0.0026,
      "step": 120
    },
    {
      "epoch": 1.936,
      "grad_norm": 0.08884049206972122,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.0026,
      "step": 121
    },
    {
      "epoch": 1.952,
      "grad_norm": 0.19903910160064697,
      "learning_rate": 6.25e-06,
      "loss": 0.0016,
      "step": 122
    },
    {
      "epoch": 1.968,
      "grad_norm": 0.05246974900364876,
      "learning_rate": 4.166666666666667e-06,
      "loss": 0.0023,
      "step": 123
    },
    {
      "epoch": 1.984,
      "grad_norm": 0.0979187935590744,
      "learning_rate": 2.0833333333333334e-06,
      "loss": 0.0025,
      "step": 124
    },
    {
      "epoch": 1.984,
      "step": 124,
      "total_flos": 5304362532864.0,
      "train_loss": 0.026456003524682244,
      "train_runtime": 11520.9946,
      "train_samples_per_second": 0.347,
      "train_steps_per_second": 0.011
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 124,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5304362532864.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}