{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 215,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004651162790697674,
      "grad_norm": 19.55866050720215,
      "learning_rate": 0.0,
      "loss": 0.842,
      "mean_token_accuracy": 0.8234314918518066,
      "step": 1
    },
    {
      "epoch": 0.009302325581395349,
      "grad_norm": 21.536800384521484,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 0.8778,
      "mean_token_accuracy": 0.8231534361839294,
      "step": 2
    },
    {
      "epoch": 0.013953488372093023,
      "grad_norm": 19.168481826782227,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.8515,
      "mean_token_accuracy": 0.834034264087677,
      "step": 3
    },
    {
      "epoch": 0.018604651162790697,
      "grad_norm": 18.268512725830078,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 0.8173,
      "mean_token_accuracy": 0.8309476971626282,
      "step": 4
    },
    {
      "epoch": 0.023255813953488372,
      "grad_norm": 21.269716262817383,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.9329,
      "mean_token_accuracy": 0.8118487000465393,
      "step": 5
    },
    {
      "epoch": 0.027906976744186046,
      "grad_norm": 18.460010528564453,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.7823,
      "mean_token_accuracy": 0.828855574131012,
      "step": 6
    },
    {
      "epoch": 0.03255813953488372,
      "grad_norm": 16.87262535095215,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 0.8115,
      "mean_token_accuracy": 0.8283237814903259,
      "step": 7
    },
    {
      "epoch": 0.037209302325581395,
      "grad_norm": 10.028908729553223,
      "learning_rate": 3.181818181818182e-06,
      "loss": 0.6377,
      "mean_token_accuracy": 0.8507297039031982,
      "step": 8
    },
    {
      "epoch": 0.04186046511627907,
      "grad_norm": 8.71435260772705,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.5643,
      "mean_token_accuracy": 0.8626564145088196,
      "step": 9
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 9.083198547363281,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 0.4923,
      "mean_token_accuracy": 0.8710644841194153,
      "step": 10
    },
    {
      "epoch": 0.05116279069767442,
      "grad_norm": 8.942933082580566,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.4216,
      "mean_token_accuracy": 0.8911864161491394,
      "step": 11
    },
    {
      "epoch": 0.05581395348837209,
      "grad_norm": 7.374241352081299,
      "learning_rate": 5e-06,
      "loss": 0.4411,
      "mean_token_accuracy": 0.880411684513092,
      "step": 12
    },
    {
      "epoch": 0.06046511627906977,
      "grad_norm": 4.179415225982666,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.4198,
      "mean_token_accuracy": 0.8751418590545654,
      "step": 13
    },
    {
      "epoch": 0.06511627906976744,
      "grad_norm": 6.282081127166748,
      "learning_rate": 5.90909090909091e-06,
      "loss": 0.3647,
      "mean_token_accuracy": 0.888242781162262,
      "step": 14
    },
    {
      "epoch": 0.06976744186046512,
      "grad_norm": 3.4604814052581787,
      "learning_rate": 6.363636363636364e-06,
      "loss": 0.3436,
      "mean_token_accuracy": 0.8959692120552063,
      "step": 15
    },
    {
      "epoch": 0.07441860465116279,
      "grad_norm": 3.8495290279388428,
      "learning_rate": 6.818181818181818e-06,
      "loss": 0.3812,
      "mean_token_accuracy": 0.8860718607902527,
      "step": 16
    },
    {
      "epoch": 0.07906976744186046,
      "grad_norm": 3.0891449451446533,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.3327,
      "mean_token_accuracy": 0.902336597442627,
      "step": 17
    },
    {
      "epoch": 0.08372093023255814,
      "grad_norm": 3.0708651542663574,
      "learning_rate": 7.727272727272727e-06,
      "loss": 0.378,
      "mean_token_accuracy": 0.8839461207389832,
      "step": 18
    },
    {
      "epoch": 0.08837209302325581,
      "grad_norm": 3.3477752208709717,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.3839,
      "mean_token_accuracy": 0.8838277459144592,
      "step": 19
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 2.875257730484009,
      "learning_rate": 8.636363636363637e-06,
      "loss": 0.3514,
      "mean_token_accuracy": 0.8934681415557861,
      "step": 20
    },
    {
      "epoch": 0.09767441860465116,
      "grad_norm": 3.16715407371521,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.3999,
      "mean_token_accuracy": 0.8770043849945068,
      "step": 21
    },
    {
      "epoch": 0.10232558139534884,
      "grad_norm": 3.1992924213409424,
      "learning_rate": 9.545454545454547e-06,
      "loss": 0.3521,
      "mean_token_accuracy": 0.8836778998374939,
      "step": 22
    },
    {
      "epoch": 0.10697674418604651,
      "grad_norm": 3.009352207183838,
      "learning_rate": 1e-05,
      "loss": 0.3456,
      "mean_token_accuracy": 0.8959909677505493,
      "step": 23
    },
    {
      "epoch": 0.11162790697674418,
      "grad_norm": 3.262113332748413,
      "learning_rate": 9.999403846557509e-06,
      "loss": 0.371,
      "mean_token_accuracy": 0.8816819787025452,
      "step": 24
    },
    {
      "epoch": 0.11627906976744186,
      "grad_norm": 3.021036386489868,
      "learning_rate": 9.99761554418511e-06,
      "loss": 0.3332,
      "mean_token_accuracy": 0.8965391516685486,
      "step": 25
    },
    {
      "epoch": 0.12093023255813953,
      "grad_norm": 3.030052423477173,
      "learning_rate": 9.99463556670619e-06,
      "loss": 0.3347,
      "mean_token_accuracy": 0.897846519947052,
      "step": 26
    },
    {
      "epoch": 0.12558139534883722,
      "grad_norm": 3.1143341064453125,
      "learning_rate": 9.990464703686895e-06,
      "loss": 0.3637,
      "mean_token_accuracy": 0.8905608654022217,
      "step": 27
    },
    {
      "epoch": 0.13023255813953488,
      "grad_norm": 3.077057361602783,
      "learning_rate": 9.985104060226937e-06,
      "loss": 0.353,
      "mean_token_accuracy": 0.89174485206604,
      "step": 28
    },
    {
      "epoch": 0.13488372093023257,
      "grad_norm": 2.9094748497009277,
      "learning_rate": 9.978555056666784e-06,
      "loss": 0.3761,
      "mean_token_accuracy": 0.879203736782074,
      "step": 29
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 3.0645463466644287,
      "learning_rate": 9.97081942821133e-06,
      "loss": 0.3706,
      "mean_token_accuracy": 0.8864420652389526,
      "step": 30
    },
    {
      "epoch": 0.14418604651162792,
      "grad_norm": 3.4396867752075195,
      "learning_rate": 9.961899224470146e-06,
      "loss": 0.3953,
      "mean_token_accuracy": 0.8805042505264282,
      "step": 31
    },
    {
      "epoch": 0.14883720930232558,
      "grad_norm": 3.069671154022217,
      "learning_rate": 9.95179680891442e-06,
      "loss": 0.3193,
      "mean_token_accuracy": 0.9063922762870789,
      "step": 32
    },
    {
      "epoch": 0.15348837209302327,
      "grad_norm": 3.6594560146331787,
      "learning_rate": 9.940514858250736e-06,
      "loss": 0.3566,
      "mean_token_accuracy": 0.8930913805961609,
      "step": 33
    },
    {
      "epoch": 0.15813953488372093,
      "grad_norm": 2.9152355194091797,
      "learning_rate": 9.928056361711854e-06,
      "loss": 0.3036,
      "mean_token_accuracy": 0.9053435325622559,
      "step": 34
    },
    {
      "epoch": 0.16279069767441862,
      "grad_norm": 2.9640631675720215,
      "learning_rate": 9.914424620264714e-06,
      "loss": 0.3576,
      "mean_token_accuracy": 0.8916776776313782,
      "step": 35
    },
    {
      "epoch": 0.16744186046511628,
      "grad_norm": 3.0034019947052,
      "learning_rate": 9.899623245735798e-06,
      "loss": 0.3279,
      "mean_token_accuracy": 0.8988348245620728,
      "step": 36
    },
    {
      "epoch": 0.17209302325581396,
      "grad_norm": 3.011780261993408,
      "learning_rate": 9.883656159854166e-06,
      "loss": 0.3172,
      "mean_token_accuracy": 0.9021276831626892,
      "step": 37
    },
    {
      "epoch": 0.17674418604651163,
      "grad_norm": 3.0025713443756104,
      "learning_rate": 9.866527593212355e-06,
      "loss": 0.3317,
      "mean_token_accuracy": 0.8996185660362244,
      "step": 38
    },
    {
      "epoch": 0.1813953488372093,
      "grad_norm": 3.0028834342956543,
      "learning_rate": 9.848242084145462e-06,
      "loss": 0.3201,
      "mean_token_accuracy": 0.901199221611023,
      "step": 39
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 2.8766064643859863,
      "learning_rate": 9.82880447752868e-06,
      "loss": 0.3381,
      "mean_token_accuracy": 0.892432451248169,
      "step": 40
    },
    {
      "epoch": 0.19069767441860466,
      "grad_norm": 2.992506742477417,
      "learning_rate": 9.808219923493606e-06,
      "loss": 0.3319,
      "mean_token_accuracy": 0.8978930115699768,
      "step": 41
    },
    {
      "epoch": 0.19534883720930232,
      "grad_norm": 3.164189577102661,
      "learning_rate": 9.786493876063685e-06,
      "loss": 0.3297,
      "mean_token_accuracy": 0.8960608243942261,
      "step": 42
    },
    {
      "epoch": 0.2,
      "grad_norm": 3.040355920791626,
      "learning_rate": 9.763632091709125e-06,
      "loss": 0.3098,
      "mean_token_accuracy": 0.8975339531898499,
      "step": 43
    },
    {
      "epoch": 0.20465116279069767,
      "grad_norm": 2.8777122497558594,
      "learning_rate": 9.739640627821678e-06,
      "loss": 0.3361,
      "mean_token_accuracy": 0.8984333872795105,
      "step": 44
    },
    {
      "epoch": 0.20930232558139536,
      "grad_norm": 3.248021125793457,
      "learning_rate": 9.714525841109697e-06,
      "loss": 0.2949,
      "mean_token_accuracy": 0.9033872485160828,
      "step": 45
    },
    {
      "epoch": 0.21395348837209302,
      "grad_norm": 3.1287307739257812,
      "learning_rate": 9.68829438591387e-06,
      "loss": 0.3029,
      "mean_token_accuracy": 0.899856686592102,
      "step": 46
    },
    {
      "epoch": 0.2186046511627907,
      "grad_norm": 3.0051000118255615,
      "learning_rate": 9.660953212444116e-06,
      "loss": 0.3143,
      "mean_token_accuracy": 0.8984231948852539,
      "step": 47
    },
    {
      "epoch": 0.22325581395348837,
      "grad_norm": 2.8489224910736084,
      "learning_rate": 9.632509564938073e-06,
      "loss": 0.3202,
      "mean_token_accuracy": 0.895948588848114,
      "step": 48
    },
    {
      "epoch": 0.22790697674418606,
      "grad_norm": 2.9875705242156982,
      "learning_rate": 9.60297097974169e-06,
      "loss": 0.3149,
      "mean_token_accuracy": 0.8959664106369019,
      "step": 49
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 2.847587823867798,
      "learning_rate": 9.572345283312407e-06,
      "loss": 0.316,
      "mean_token_accuracy": 0.8969941735267639,
      "step": 50
    },
    {
      "epoch": 0.2372093023255814,
      "grad_norm": 3.1370949745178223,
      "learning_rate": 9.540640590145496e-06,
      "loss": 0.3341,
      "mean_token_accuracy": 0.881118893623352,
      "step": 51
    },
    {
      "epoch": 0.24186046511627907,
      "grad_norm": 2.850233554840088,
      "learning_rate": 9.507865300624057e-06,
      "loss": 0.3356,
      "mean_token_accuracy": 0.887252688407898,
      "step": 52
    },
    {
      "epoch": 0.24651162790697675,
      "grad_norm": 2.9406354427337646,
      "learning_rate": 9.474028098793277e-06,
      "loss": 0.3124,
      "mean_token_accuracy": 0.8950287103652954,
      "step": 53
    },
    {
      "epoch": 0.25116279069767444,
      "grad_norm": 2.7969465255737305,
      "learning_rate": 9.439137950059539e-06,
      "loss": 0.3279,
      "mean_token_accuracy": 0.8895781636238098,
      "step": 54
    },
    {
      "epoch": 0.2558139534883721,
      "grad_norm": 2.7251291275024414,
      "learning_rate": 9.403204098814965e-06,
      "loss": 0.3283,
      "mean_token_accuracy": 0.8901644349098206,
      "step": 55
    },
    {
      "epoch": 0.26046511627906976,
      "grad_norm": 2.7642579078674316,
      "learning_rate": 9.366236065988053e-06,
      "loss": 0.3221,
      "mean_token_accuracy": 0.8957247138023376,
      "step": 56
    },
    {
      "epoch": 0.2651162790697674,
      "grad_norm": 2.3894405364990234,
      "learning_rate": 9.32824364652104e-06,
      "loss": 0.281,
      "mean_token_accuracy": 0.9091808199882507,
      "step": 57
    },
    {
      "epoch": 0.26976744186046514,
      "grad_norm": 2.4891464710235596,
      "learning_rate": 9.289236906774663e-06,
      "loss": 0.3109,
      "mean_token_accuracy": 0.8954732418060303,
      "step": 58
    },
    {
      "epoch": 0.2744186046511628,
      "grad_norm": 2.790039539337158,
      "learning_rate": 9.249226181861e-06,
      "loss": 0.2908,
      "mean_token_accuracy": 0.9037843346595764,
      "step": 59
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 2.580768585205078,
      "learning_rate": 9.208222072905113e-06,
      "loss": 0.3069,
      "mean_token_accuracy": 0.8923306465148926,
      "step": 60
    },
    {
      "epoch": 0.2837209302325581,
      "grad_norm": 2.7456512451171875,
      "learning_rate": 9.166235444236209e-06,
      "loss": 0.3416,
      "mean_token_accuracy": 0.8841578960418701,
      "step": 61
    },
    {
      "epoch": 0.28837209302325584,
      "grad_norm": 2.709031105041504,
      "learning_rate": 9.123277420509053e-06,
      "loss": 0.3347,
      "mean_token_accuracy": 0.8882771134376526,
      "step": 62
    },
    {
      "epoch": 0.2930232558139535,
      "grad_norm": 2.523022413253784,
      "learning_rate": 9.079359383756411e-06,
      "loss": 0.3129,
      "mean_token_accuracy": 0.8984159827232361,
      "step": 63
    },
    {
      "epoch": 0.29767441860465116,
      "grad_norm": 2.5372958183288574,
      "learning_rate": 9.034492970373305e-06,
      "loss": 0.309,
      "mean_token_accuracy": 0.8964273929595947,
      "step": 64
    },
    {
      "epoch": 0.3023255813953488,
      "grad_norm": 2.61922025680542,
      "learning_rate": 8.988690068033864e-06,
      "loss": 0.3333,
      "mean_token_accuracy": 0.890192985534668,
      "step": 65
    },
    {
      "epoch": 0.30697674418604654,
      "grad_norm": 2.3186187744140625,
      "learning_rate": 8.941962812541604e-06,
      "loss": 0.2997,
      "mean_token_accuracy": 0.894925057888031,
      "step": 66
    },
    {
      "epoch": 0.3116279069767442,
      "grad_norm": 2.499758005142212,
      "learning_rate": 8.894323584613951e-06,
      "loss": 0.3195,
      "mean_token_accuracy": 0.888198733329773,
      "step": 67
    },
    {
      "epoch": 0.31627906976744186,
      "grad_norm": 2.4142322540283203,
      "learning_rate": 8.845785006601898e-06,
      "loss": 0.2809,
      "mean_token_accuracy": 0.9037378430366516,
      "step": 68
    },
    {
      "epoch": 0.3209302325581395,
      "grad_norm": 2.5113420486450195,
      "learning_rate": 8.796359939145614e-06,
      "loss": 0.3085,
      "mean_token_accuracy": 0.8951073288917542,
      "step": 69
    },
    {
      "epoch": 0.32558139534883723,
      "grad_norm": 2.663149833679199,
      "learning_rate": 8.74606147776692e-06,
      "loss": 0.3094,
      "mean_token_accuracy": 0.8915014863014221,
      "step": 70
    },
    {
      "epoch": 0.3302325581395349,
      "grad_norm": 2.501584768295288,
      "learning_rate": 8.694902949399555e-06,
      "loss": 0.3077,
      "mean_token_accuracy": 0.8995984196662903,
      "step": 71
    },
    {
      "epoch": 0.33488372093023255,
      "grad_norm": 2.545039176940918,
      "learning_rate": 8.642897908858096e-06,
      "loss": 0.3109,
      "mean_token_accuracy": 0.8962626457214355,
      "step": 72
    },
    {
      "epoch": 0.3395348837209302,
      "grad_norm": 2.6288673877716064,
      "learning_rate": 8.590060135246516e-06,
      "loss": 0.3337,
      "mean_token_accuracy": 0.8833979368209839,
      "step": 73
    },
    {
      "epoch": 0.34418604651162793,
      "grad_norm": 2.310521125793457,
      "learning_rate": 8.53640362830732e-06,
      "loss": 0.2889,
      "mean_token_accuracy": 0.8993450403213501,
      "step": 74
    },
    {
      "epoch": 0.3488372093023256,
      "grad_norm": 2.6337504386901855,
      "learning_rate": 8.481942604712209e-06,
      "loss": 0.3167,
      "mean_token_accuracy": 0.8929409384727478,
      "step": 75
    },
    {
      "epoch": 0.35348837209302325,
      "grad_norm": 2.338621139526367,
      "learning_rate": 8.426691494295269e-06,
      "loss": 0.2867,
      "mean_token_accuracy": 0.9040859341621399,
      "step": 76
    },
    {
      "epoch": 0.3581395348837209,
      "grad_norm": 2.469846725463867,
      "learning_rate": 8.370664936229688e-06,
      "loss": 0.3127,
      "mean_token_accuracy": 0.8935756087303162,
      "step": 77
    },
    {
      "epoch": 0.3627906976744186,
      "grad_norm": 2.4656858444213867,
      "learning_rate": 8.313877775149009e-06,
      "loss": 0.2733,
      "mean_token_accuracy": 0.9058647155761719,
      "step": 78
    },
    {
      "epoch": 0.3674418604651163,
      "grad_norm": 2.7528796195983887,
      "learning_rate": 8.256345057213925e-06,
      "loss": 0.3141,
      "mean_token_accuracy": 0.8913813233375549,
      "step": 79
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 2.343507766723633,
      "learning_rate": 8.198082026125707e-06,
      "loss": 0.328,
      "mean_token_accuracy": 0.8872765898704529,
      "step": 80
    },
    {
      "epoch": 0.3767441860465116,
      "grad_norm": 2.487946033477783,
      "learning_rate": 8.139104119087265e-06,
      "loss": 0.2837,
      "mean_token_accuracy": 0.9029180407524109,
      "step": 81
    },
    {
      "epoch": 0.3813953488372093,
      "grad_norm": 2.4490132331848145,
      "learning_rate": 8.07942696271296e-06,
      "loss": 0.2809,
      "mean_token_accuracy": 0.9013158082962036,
      "step": 82
    },
    {
      "epoch": 0.386046511627907,
      "grad_norm": 2.332151174545288,
      "learning_rate": 8.019066368888222e-06,
      "loss": 0.2873,
      "mean_token_accuracy": 0.9034554362297058,
      "step": 83
    },
    {
      "epoch": 0.39069767441860465,
      "grad_norm": 2.451125383377075,
      "learning_rate": 7.958038330580067e-06,
      "loss": 0.3295,
      "mean_token_accuracy": 0.8829941749572754,
      "step": 84
    },
    {
      "epoch": 0.3953488372093023,
      "grad_norm": 2.379772186279297,
      "learning_rate": 7.89635901759967e-06,
      "loss": 0.297,
      "mean_token_accuracy": 0.8926709294319153,
      "step": 85
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.7636427879333496,
      "learning_rate": 7.834044772318033e-06,
      "loss": 0.3275,
      "mean_token_accuracy": 0.8930240273475647,
      "step": 86
    },
    {
      "epoch": 0.4046511627906977,
      "grad_norm": 2.4831793308258057,
      "learning_rate": 7.77111210533597e-06,
      "loss": 0.3006,
      "mean_token_accuracy": 0.8901177048683167,
      "step": 87
    },
    {
      "epoch": 0.40930232558139534,
      "grad_norm": 2.845695972442627,
      "learning_rate": 7.707577691109519e-06,
      "loss": 0.3559,
      "mean_token_accuracy": 0.8793193101882935,
      "step": 88
    },
    {
      "epoch": 0.413953488372093,
      "grad_norm": 2.25897479057312,
      "learning_rate": 7.6434583635319e-06,
      "loss": 0.3002,
      "mean_token_accuracy": 0.9035753011703491,
      "step": 89
    },
    {
      "epoch": 0.4186046511627907,
      "grad_norm": 2.267224073410034,
      "learning_rate": 7.578771111473276e-06,
      "loss": 0.2581,
      "mean_token_accuracy": 0.9115538001060486,
      "step": 90
    },
    {
      "epoch": 0.4232558139534884,
      "grad_norm": 2.3631324768066406,
      "learning_rate": 7.513533074279427e-06,
      "loss": 0.2676,
      "mean_token_accuracy": 0.9085960984230042,
      "step": 91
    },
    {
      "epoch": 0.42790697674418604,
      "grad_norm": 2.47088360786438,
      "learning_rate": 7.4477615372305545e-06,
      "loss": 0.3212,
      "mean_token_accuracy": 0.8931205868721008,
      "step": 92
    },
    {
      "epoch": 0.4325581395348837,
      "grad_norm": 2.367776393890381,
      "learning_rate": 7.3814739269614265e-06,
      "loss": 0.292,
      "mean_token_accuracy": 0.9006222486495972,
      "step": 93
    },
    {
      "epoch": 0.4372093023255814,
      "grad_norm": 2.3810348510742188,
      "learning_rate": 7.314687806844067e-06,
      "loss": 0.3059,
      "mean_token_accuracy": 0.8974854946136475,
      "step": 94
    },
    {
      "epoch": 0.4418604651162791,
      "grad_norm": 2.423929452896118,
      "learning_rate": 7.247420872334221e-06,
      "loss": 0.3003,
      "mean_token_accuracy": 0.8948303461074829,
      "step": 95
    },
    {
      "epoch": 0.44651162790697674,
      "grad_norm": 2.218552589416504,
      "learning_rate": 7.179690946282808e-06,
      "loss": 0.2809,
      "mean_token_accuracy": 0.9024173617362976,
      "step": 96
    },
    {
      "epoch": 0.4511627906976744,
      "grad_norm": 2.2407336235046387,
      "learning_rate": 7.111515974213639e-06,
      "loss": 0.2469,
      "mean_token_accuracy": 0.9117849469184875,
      "step": 97
    },
    {
      "epoch": 0.4558139534883721,
      "grad_norm": 2.3287737369537354,
      "learning_rate": 7.042914019568621e-06,
      "loss": 0.302,
      "mean_token_accuracy": 0.8931969404220581,
      "step": 98
    },
    {
      "epoch": 0.4604651162790698,
      "grad_norm": 2.180527687072754,
      "learning_rate": 6.973903258921719e-06,
      "loss": 0.2553,
      "mean_token_accuracy": 0.909423291683197,
      "step": 99
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 2.3433878421783447,
      "learning_rate": 6.904501977162949e-06,
      "loss": 0.3257,
      "mean_token_accuracy": 0.8879437446594238,
      "step": 100
    },
    {
      "epoch": 0.4697674418604651,
      "grad_norm": 2.3647921085357666,
      "learning_rate": 6.834728562653659e-06,
      "loss": 0.3094,
      "mean_token_accuracy": 0.8909768462181091,
      "step": 101
    },
    {
      "epoch": 0.4744186046511628,
      "grad_norm": 2.434654951095581,
      "learning_rate": 6.764601502354403e-06,
      "loss": 0.3045,
      "mean_token_accuracy": 0.8957603573799133,
      "step": 102
    },
    {
      "epoch": 0.4790697674418605,
      "grad_norm": 2.213092088699341,
      "learning_rate": 6.6941393769266995e-06,
      "loss": 0.2953,
      "mean_token_accuracy": 0.8990439176559448,
      "step": 103
    },
    {
      "epoch": 0.48372093023255813,
      "grad_norm": 2.135453701019287,
      "learning_rate": 6.6233608558099405e-06,
      "loss": 0.2752,
      "mean_token_accuracy": 0.9063274264335632,
      "step": 104
    },
    {
      "epoch": 0.4883720930232558,
      "grad_norm": 2.2655882835388184,
      "learning_rate": 6.552284692274803e-06,
      "loss": 0.3077,
      "mean_token_accuracy": 0.8922848701477051,
      "step": 105
    },
    {
      "epoch": 0.4930232558139535,
      "grad_norm": 2.3760480880737305,
      "learning_rate": 6.48092971845443e-06,
      "loss": 0.2796,
      "mean_token_accuracy": 0.9028503894805908,
      "step": 106
    },
    {
      "epoch": 0.49767441860465117,
      "grad_norm": 2.3789312839508057,
      "learning_rate": 6.409314840354724e-06,
      "loss": 0.3371,
      "mean_token_accuracy": 0.889424741268158,
      "step": 107
    },
    {
      "epoch": 0.5023255813953489,
      "grad_norm": 2.499450445175171,
      "learning_rate": 6.337459032845068e-06,
      "loss": 0.3151,
      "mean_token_accuracy": 0.8880661129951477,
      "step": 108
    },
    {
      "epoch": 0.5069767441860465,
      "grad_norm": 2.3901238441467285,
      "learning_rate": 6.2653813346308e-06,
      "loss": 0.2715,
      "mean_token_accuracy": 0.9052498936653137,
      "step": 109
    },
    {
      "epoch": 0.5116279069767442,
      "grad_norm": 2.2736220359802246,
      "learning_rate": 6.193100843208772e-06,
      "loss": 0.2802,
      "mean_token_accuracy": 0.8982987403869629,
      "step": 110
    },
    {
      "epoch": 0.5162790697674419,
      "grad_norm": 2.339315176010132,
      "learning_rate": 6.120636709807334e-06,
      "loss": 0.3087,
      "mean_token_accuracy": 0.8898224234580994,
      "step": 111
    },
    {
      "epoch": 0.5209302325581395,
      "grad_norm": 2.381701707839966,
      "learning_rate": 6.048008134312078e-06,
      "loss": 0.2888,
      "mean_token_accuracy": 0.8999055624008179,
      "step": 112
    },
    {
      "epoch": 0.5255813953488372,
      "grad_norm": 2.3778223991394043,
      "learning_rate": 5.975234360178698e-06,
      "loss": 0.3245,
      "mean_token_accuracy": 0.8921954035758972,
      "step": 113
    },
    {
      "epoch": 0.5302325581395348,
      "grad_norm": 2.1973538398742676,
      "learning_rate": 5.902334669334287e-06,
      "loss": 0.299,
      "mean_token_accuracy": 0.9011526107788086,
      "step": 114
    },
    {
      "epoch": 0.5348837209302325,
      "grad_norm": 2.4363880157470703,
      "learning_rate": 5.829328377068476e-06,
      "loss": 0.295,
      "mean_token_accuracy": 0.8934922218322754,
      "step": 115
    },
    {
      "epoch": 0.5395348837209303,
      "grad_norm": 2.4742653369903564,
      "learning_rate": 5.756234826915686e-06,
      "loss": 0.2994,
      "mean_token_accuracy": 0.9003058075904846,
      "step": 116
    },
    {
      "epoch": 0.5441860465116279,
      "grad_norm": 2.5611572265625,
      "learning_rate": 5.683073385529938e-06,
      "loss": 0.3118,
      "mean_token_accuracy": 0.8888066411018372,
      "step": 117
    },
    {
      "epoch": 0.5488372093023256,
      "grad_norm": 2.1916542053222656,
      "learning_rate": 5.60986343755352e-06,
      "loss": 0.2611,
      "mean_token_accuracy": 0.907447338104248,
      "step": 118
    },
    {
      "epoch": 0.5534883720930233,
      "grad_norm": 2.4621665477752686,
      "learning_rate": 5.536624380480878e-06,
      "loss": 0.2504,
      "mean_token_accuracy": 0.9125564694404602,
      "step": 119
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 2.305725336074829,
      "learning_rate": 5.4633756195191235e-06,
      "loss": 0.2594,
      "mean_token_accuracy": 0.909368097782135,
      "step": 120
    },
    {
      "epoch": 0.5627906976744186,
      "grad_norm": 2.0305423736572266,
      "learning_rate": 5.390136562446482e-06,
      "loss": 0.2259,
      "mean_token_accuracy": 0.9176449775695801,
      "step": 121
    },
    {
      "epoch": 0.5674418604651162,
      "grad_norm": 2.3692667484283447,
      "learning_rate": 5.316926614470063e-06,
      "loss": 0.3034,
      "mean_token_accuracy": 0.8940587043762207,
      "step": 122
    },
    {
      "epoch": 0.5720930232558139,
      "grad_norm": 2.6239306926727295,
      "learning_rate": 5.2437651730843165e-06,
      "loss": 0.3362,
      "mean_token_accuracy": 0.8789413571357727,
      "step": 123
    },
    {
      "epoch": 0.5767441860465117,
      "grad_norm": 2.5017409324645996,
      "learning_rate": 5.170671622931527e-06,
      "loss": 0.3094,
      "mean_token_accuracy": 0.8925363421440125,
      "step": 124
    },
    {
      "epoch": 0.5813953488372093,
      "grad_norm": 2.0600509643554688,
      "learning_rate": 5.097665330665714e-06,
      "loss": 0.2368,
      "mean_token_accuracy": 0.916695237159729,
      "step": 125
    },
    {
      "epoch": 0.586046511627907,
      "grad_norm": 2.5883283615112305,
      "learning_rate": 5.024765639821305e-06,
      "loss": 0.3191,
      "mean_token_accuracy": 0.894444465637207,
      "step": 126
    },
    {
      "epoch": 0.5906976744186047,
      "grad_norm": 2.050201654434204,
      "learning_rate": 4.951991865687923e-06,
      "loss": 0.2501,
      "mean_token_accuracy": 0.9178641438484192,
      "step": 127
    },
    {
      "epoch": 0.5953488372093023,
      "grad_norm": 2.357882499694824,
      "learning_rate": 4.879363290192667e-06,
      "loss": 0.2938,
      "mean_token_accuracy": 0.9023271799087524,
      "step": 128
    },
    {
      "epoch": 0.6,
      "grad_norm": 2.713916063308716,
      "learning_rate": 4.806899156791231e-06,
      "loss": 0.3558,
      "mean_token_accuracy": 0.8827831745147705,
      "step": 129
    },
    {
      "epoch": 0.6046511627906976,
      "grad_norm": 2.365781307220459,
      "learning_rate": 4.734618665369202e-06,
      "loss": 0.2804,
      "mean_token_accuracy": 0.8971909284591675,
      "step": 130
    },
    {
      "epoch": 0.6093023255813953,
      "grad_norm": 2.310689926147461,
      "learning_rate": 4.662540967154934e-06,
      "loss": 0.2656,
      "mean_token_accuracy": 0.9065172076225281,
      "step": 131
    },
    {
      "epoch": 0.6139534883720931,
      "grad_norm": 2.114121913909912,
      "learning_rate": 4.5906851596452765e-06,
      "loss": 0.2685,
      "mean_token_accuracy": 0.9042183756828308,
      "step": 132
    },
    {
      "epoch": 0.6186046511627907,
      "grad_norm": 2.287637948989868,
      "learning_rate": 4.519070281545571e-06,
      "loss": 0.3034,
      "mean_token_accuracy": 0.8936946392059326,
      "step": 133
    },
    {
      "epoch": 0.6232558139534884,
      "grad_norm": 2.266719341278076,
      "learning_rate": 4.447715307725197e-06,
      "loss": 0.3081,
      "mean_token_accuracy": 0.8978622555732727,
      "step": 134
    },
    {
      "epoch": 0.627906976744186,
      "grad_norm": 2.2800838947296143,
      "learning_rate": 4.376639144190061e-06,
      "loss": 0.2984,
      "mean_token_accuracy": 0.8969523310661316,
      "step": 135
    },
    {
      "epoch": 0.6325581395348837,
      "grad_norm": 2.5165393352508545,
      "learning_rate": 4.305860623073304e-06,
      "loss": 0.2959,
      "mean_token_accuracy": 0.898727536201477,
      "step": 136
    },
    {
      "epoch": 0.6372093023255814,
      "grad_norm": 2.1377274990081787,
      "learning_rate": 4.2353984976456e-06,
      "loss": 0.2779,
      "mean_token_accuracy": 0.9044293165206909,
      "step": 137
    },
    {
      "epoch": 0.641860465116279,
      "grad_norm": 2.179332971572876,
      "learning_rate": 4.1652714373463435e-06,
      "loss": 0.2864,
      "mean_token_accuracy": 0.9005101919174194,
      "step": 138
    },
    {
      "epoch": 0.6465116279069767,
      "grad_norm": 2.23024320602417,
      "learning_rate": 4.095498022837051e-06,
      "loss": 0.2712,
      "mean_token_accuracy": 0.9082063436508179,
      "step": 139
    },
    {
      "epoch": 0.6511627906976745,
      "grad_norm": 2.311195135116577,
      "learning_rate": 4.026096741078281e-06,
      "loss": 0.3099,
      "mean_token_accuracy": 0.8930677175521851,
      "step": 140
    },
    {
      "epoch": 0.6558139534883721,
      "grad_norm": 2.3037424087524414,
      "learning_rate": 3.957085980431382e-06,
      "loss": 0.3041,
      "mean_token_accuracy": 0.8964273929595947,
      "step": 141
    },
    {
      "epoch": 0.6604651162790698,
      "grad_norm": 2.166527509689331,
      "learning_rate": 3.888484025786364e-06,
      "loss": 0.2771,
      "mean_token_accuracy": 0.9047784209251404,
      "step": 142
    },
    {
      "epoch": 0.6651162790697674,
      "grad_norm": 2.092200756072998,
      "learning_rate": 3.820309053717195e-06,
      "loss": 0.2628,
      "mean_token_accuracy": 0.9099807739257812,
      "step": 143
    },
    {
      "epoch": 0.6697674418604651,
      "grad_norm": 2.402787446975708,
      "learning_rate": 3.75257912766578e-06,
      "loss": 0.3491,
      "mean_token_accuracy": 0.8836612701416016,
      "step": 144
    },
    {
      "epoch": 0.6744186046511628,
      "grad_norm": 2.40132737159729,
      "learning_rate": 3.6853121931559334e-06,
      "loss": 0.3185,
      "mean_token_accuracy": 0.8895066976547241,
      "step": 145
    },
    {
      "epoch": 0.6790697674418604,
      "grad_norm": 2.2350831031799316,
      "learning_rate": 3.618526073038574e-06,
      "loss": 0.3344,
      "mean_token_accuracy": 0.8823676109313965,
      "step": 146
    },
    {
      "epoch": 0.6837209302325581,
      "grad_norm": 2.335584878921509,
      "learning_rate": 3.552238462769446e-06,
      "loss": 0.2788,
      "mean_token_accuracy": 0.8992438912391663,
      "step": 147
    },
    {
      "epoch": 0.6883720930232559,
      "grad_norm": 2.4658241271972656,
      "learning_rate": 3.4864669257205745e-06,
      "loss": 0.2697,
      "mean_token_accuracy": 0.9067319631576538,
      "step": 148
    },
    {
      "epoch": 0.6930232558139535,
      "grad_norm": 2.318817377090454,
      "learning_rate": 3.4212288885267246e-06,
      "loss": 0.3142,
      "mean_token_accuracy": 0.8924602270126343,
      "step": 149
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 2.45670223236084,
      "learning_rate": 3.3565416364681016e-06,
      "loss": 0.2819,
      "mean_token_accuracy": 0.8985480070114136,
      "step": 150
    },
    {
      "epoch": 0.7023255813953488,
      "grad_norm": 2.082231044769287,
      "learning_rate": 3.2924223088904816e-06,
      "loss": 0.2731,
      "mean_token_accuracy": 0.9048190712928772,
      "step": 151
    },
    {
      "epoch": 0.7069767441860465,
      "grad_norm": 2.509894847869873,
      "learning_rate": 3.228887894664029e-06,
      "loss": 0.3314,
      "mean_token_accuracy": 0.8872409462928772,
      "step": 152
    },
    {
      "epoch": 0.7116279069767442,
      "grad_norm": 2.383643388748169,
      "learning_rate": 3.1659552276819693e-06,
      "loss": 0.3066,
      "mean_token_accuracy": 0.892098069190979,
      "step": 153
    },
    {
      "epoch": 0.7162790697674418,
      "grad_norm": 2.2269604206085205,
      "learning_rate": 3.1036409824003324e-06,
      "loss": 0.2792,
      "mean_token_accuracy": 0.9020003080368042,
      "step": 154
    },
    {
      "epoch": 0.7209302325581395,
      "grad_norm": 2.065215826034546,
      "learning_rate": 3.0419616694199327e-06,
      "loss": 0.2585,
      "mean_token_accuracy": 0.9109966158866882,
      "step": 155
    },
    {
      "epoch": 0.7255813953488373,
      "grad_norm": 2.148339033126831,
      "learning_rate": 2.98093363111178e-06,
      "loss": 0.236,
      "mean_token_accuracy": 0.9179540872573853,
      "step": 156
    },
    {
      "epoch": 0.7302325581395349,
      "grad_norm": 2.51432204246521,
      "learning_rate": 2.92057303728704e-06,
      "loss": 0.2938,
      "mean_token_accuracy": 0.8990790247917175,
      "step": 157
    },
    {
      "epoch": 0.7348837209302326,
      "grad_norm": 2.2039244174957275,
      "learning_rate": 2.860895880912735e-06,
      "loss": 0.279,
      "mean_token_accuracy": 0.9065436720848083,
      "step": 158
    },
    {
      "epoch": 0.7395348837209302,
      "grad_norm": 2.268071174621582,
      "learning_rate": 2.801917973874294e-06,
      "loss": 0.2978,
      "mean_token_accuracy": 0.8923124074935913,
      "step": 159
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 2.350569248199463,
      "learning_rate": 2.7436549427860766e-06,
      "loss": 0.3165,
      "mean_token_accuracy": 0.8912504315376282,
      "step": 160
    },
    {
      "epoch": 0.7488372093023256,
      "grad_norm": 2.0372023582458496,
      "learning_rate": 2.6861222248509926e-06,
      "loss": 0.2444,
      "mean_token_accuracy": 0.9146341681480408,
      "step": 161
    },
    {
      "epoch": 0.7534883720930232,
      "grad_norm": 2.0885045528411865,
      "learning_rate": 2.6293350637703123e-06,
      "loss": 0.2747,
      "mean_token_accuracy": 0.9104732871055603,
      "step": 162
    },
    {
      "epoch": 0.7581395348837209,
      "grad_norm": 2.4233343601226807,
      "learning_rate": 2.5733085057047325e-06,
      "loss": 0.2845,
      "mean_token_accuracy": 0.9028448462486267,
      "step": 163
    },
    {
      "epoch": 0.7627906976744186,
      "grad_norm": 2.1531500816345215,
      "learning_rate": 2.518057395287792e-06,
      "loss": 0.2964,
      "mean_token_accuracy": 0.8945344090461731,
      "step": 164
    },
    {
      "epoch": 0.7674418604651163,
      "grad_norm": 2.34539532661438,
      "learning_rate": 2.463596371692681e-06,
      "loss": 0.2939,
      "mean_token_accuracy": 0.8953551650047302,
      "step": 165
    },
    {
      "epoch": 0.772093023255814,
      "grad_norm": 2.0955286026000977,
      "learning_rate": 2.409939864753487e-06,
      "loss": 0.2916,
      "mean_token_accuracy": 0.898024320602417,
      "step": 166
    },
    {
      "epoch": 0.7767441860465116,
      "grad_norm": 2.1634206771850586,
      "learning_rate": 2.3571020911419067e-06,
      "loss": 0.2789,
      "mean_token_accuracy": 0.9082539677619934,
      "step": 167
    },
    {
      "epoch": 0.7813953488372093,
      "grad_norm": 2.386928081512451,
      "learning_rate": 2.3050970506004463e-06,
      "loss": 0.3075,
      "mean_token_accuracy": 0.8937572240829468,
      "step": 168
    },
    {
      "epoch": 0.786046511627907,
      "grad_norm": 2.380465030670166,
      "learning_rate": 2.2539385222330797e-06,
      "loss": 0.2494,
      "mean_token_accuracy": 0.9121189117431641,
      "step": 169
    },
    {
      "epoch": 0.7906976744186046,
      "grad_norm": 2.232485055923462,
      "learning_rate": 2.203640060854387e-06,
      "loss": 0.2626,
      "mean_token_accuracy": 0.9113078117370605,
      "step": 170
    },
    {
      "epoch": 0.7953488372093023,
      "grad_norm": 2.1620066165924072,
      "learning_rate": 2.1542149933981014e-06,
      "loss": 0.2955,
      "mean_token_accuracy": 0.899713933467865,
      "step": 171
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.135443925857544,
      "learning_rate": 2.10567641538605e-06,
      "loss": 0.2718,
      "mean_token_accuracy": 0.9112734794616699,
      "step": 172
    },
    {
      "epoch": 0.8046511627906977,
      "grad_norm": 2.0903422832489014,
      "learning_rate": 2.058037187458398e-06,
      "loss": 0.285,
      "mean_token_accuracy": 0.9051055312156677,
      "step": 173
    },
    {
      "epoch": 0.8093023255813954,
      "grad_norm": 2.3708086013793945,
      "learning_rate": 2.011309931966136e-06,
      "loss": 0.2787,
      "mean_token_accuracy": 0.904355525970459,
      "step": 174
    },
    {
      "epoch": 0.813953488372093,
      "grad_norm": 2.1600074768066406,
      "learning_rate": 1.965507029626695e-06,
      "loss": 0.2869,
      "mean_token_accuracy": 0.8876973390579224,
      "step": 175
    },
    {
      "epoch": 0.8186046511627907,
      "grad_norm": 2.169403314590454,
      "learning_rate": 1.920640616243589e-06,
      "loss": 0.2556,
      "mean_token_accuracy": 0.9110191464424133,
      "step": 176
    },
    {
      "epoch": 0.8232558139534883,
      "grad_norm": 2.4098989963531494,
      "learning_rate": 1.8767225794909484e-06,
      "loss": 0.3099,
      "mean_token_accuracy": 0.8926380276679993,
      "step": 177
    },
    {
      "epoch": 0.827906976744186,
      "grad_norm": 2.0924203395843506,
      "learning_rate": 1.8337645557637929e-06,
      "loss": 0.2685,
      "mean_token_accuracy": 0.9054539203643799,
      "step": 178
    },
    {
      "epoch": 0.8325581395348837,
      "grad_norm": 2.10318660736084,
      "learning_rate": 1.7917779270948887e-06,
      "loss": 0.287,
      "mean_token_accuracy": 0.9022500514984131,
      "step": 179
    },
    {
      "epoch": 0.8372093023255814,
      "grad_norm": 2.266540288925171,
      "learning_rate": 1.7507738181390027e-06,
      "loss": 0.2751,
      "mean_token_accuracy": 0.9026884436607361,
      "step": 180
    },
    {
      "epoch": 0.8418604651162791,
      "grad_norm": 2.2889575958251953,
      "learning_rate": 1.7107630932253383e-06,
      "loss": 0.2791,
      "mean_token_accuracy": 0.9028925895690918,
      "step": 181
    },
    {
      "epoch": 0.8465116279069768,
      "grad_norm": 2.204096555709839,
      "learning_rate": 1.6717563534789594e-06,
      "loss": 0.2856,
      "mean_token_accuracy": 0.9041808843612671,
      "step": 182
    },
    {
      "epoch": 0.8511627906976744,
      "grad_norm": 2.236905097961426,
      "learning_rate": 1.6337639340119476e-06,
      "loss": 0.2896,
      "mean_token_accuracy": 0.8966881632804871,
      "step": 183
    },
    {
      "epoch": 0.8558139534883721,
      "grad_norm": 2.307908296585083,
      "learning_rate": 1.596795901185037e-06,
      "loss": 0.2973,
      "mean_token_accuracy": 0.8991920948028564,
      "step": 184
    },
    {
      "epoch": 0.8604651162790697,
      "grad_norm": 1.9844419956207275,
      "learning_rate": 1.5608620499404628e-06,
      "loss": 0.2689,
      "mean_token_accuracy": 0.9050772786140442,
      "step": 185
    },
    {
      "epoch": 0.8651162790697674,
      "grad_norm": 2.2421247959136963,
      "learning_rate": 1.5259719012067249e-06,
      "loss": 0.299,
      "mean_token_accuracy": 0.8975785374641418,
      "step": 186
    },
    {
      "epoch": 0.8697674418604651,
      "grad_norm": 2.2404239177703857,
      "learning_rate": 1.4921346993759453e-06,
      "loss": 0.2618,
      "mean_token_accuracy": 0.905358612537384,
      "step": 187
    },
    {
      "epoch": 0.8744186046511628,
      "grad_norm": 2.1030170917510986,
      "learning_rate": 1.459359409854505e-06,
      "loss": 0.2777,
      "mean_token_accuracy": 0.9086073637008667,
      "step": 188
    },
    {
      "epoch": 0.8790697674418605,
      "grad_norm": 2.15631365776062,
      "learning_rate": 1.4276547166875946e-06,
      "loss": 0.2572,
      "mean_token_accuracy": 0.9099292159080505,
      "step": 189
    },
    {
      "epoch": 0.8837209302325582,
      "grad_norm": 2.330944299697876,
      "learning_rate": 1.397029020258313e-06,
      "loss": 0.2763,
      "mean_token_accuracy": 0.8994728922843933,
      "step": 190
    },
    {
      "epoch": 0.8883720930232558,
      "grad_norm": 2.309465169906616,
      "learning_rate": 1.367490435061928e-06,
      "loss": 0.3225,
      "mean_token_accuracy": 0.886062741279602,
      "step": 191
    },
    {
      "epoch": 0.8930232558139535,
      "grad_norm": 2.127525806427002,
      "learning_rate": 1.3390467875558855e-06,
      "loss": 0.2417,
      "mean_token_accuracy": 0.9141114950180054,
      "step": 192
    },
    {
      "epoch": 0.8976744186046511,
      "grad_norm": 2.108126640319824,
      "learning_rate": 1.3117056140861317e-06,
      "loss": 0.2816,
      "mean_token_accuracy": 0.9047395586967468,
      "step": 193
    },
    {
      "epoch": 0.9023255813953488,
      "grad_norm": 2.094708204269409,
      "learning_rate": 1.285474158890304e-06,
      "loss": 0.2558,
      "mean_token_accuracy": 0.9168649911880493,
      "step": 194
    },
    {
      "epoch": 0.9069767441860465,
      "grad_norm": 2.037085771560669,
      "learning_rate": 1.2603593721783219e-06,
      "loss": 0.2597,
      "mean_token_accuracy": 0.9116804599761963,
      "step": 195
    },
    {
      "epoch": 0.9116279069767442,
      "grad_norm": 2.141491413116455,
      "learning_rate": 1.2363679082908766e-06,
      "loss": 0.2917,
      "mean_token_accuracy": 0.9007202982902527,
      "step": 196
    },
    {
      "epoch": 0.9162790697674419,
      "grad_norm": 2.208596706390381,
      "learning_rate": 1.2135061239363161e-06,
      "loss": 0.2499,
      "mean_token_accuracy": 0.9134494662284851,
      "step": 197
    },
    {
      "epoch": 0.9209302325581395,
      "grad_norm": 2.2450554370880127,
      "learning_rate": 1.1917800765063954e-06,
      "loss": 0.2626,
      "mean_token_accuracy": 0.9065197706222534,
      "step": 198
    },
    {
      "epoch": 0.9255813953488372,
      "grad_norm": 2.408583879470825,
      "learning_rate": 1.1711955224713209e-06,
      "loss": 0.2875,
      "mean_token_accuracy": 0.9005586504936218,
      "step": 199
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 2.1336426734924316,
      "learning_rate": 1.1517579158545386e-06,
      "loss": 0.2615,
      "mean_token_accuracy": 0.9102848172187805,
      "step": 200
    },
    {
      "epoch": 0.9348837209302325,
      "grad_norm": 2.3364694118499756,
      "learning_rate": 1.1334724067876463e-06,
      "loss": 0.2908,
      "mean_token_accuracy": 0.9005729556083679,
      "step": 201
    },
    {
      "epoch": 0.9395348837209302,
      "grad_norm": 2.078341007232666,
      "learning_rate": 1.1163438401458358e-06,
      "loss": 0.2576,
      "mean_token_accuracy": 0.9106926918029785,
      "step": 202
    },
    {
      "epoch": 0.9441860465116279,
      "grad_norm": 2.2890896797180176,
      "learning_rate": 1.1003767542642021e-06,
      "loss": 0.2759,
      "mean_token_accuracy": 0.9083694219589233,
      "step": 203
    },
    {
      "epoch": 0.9488372093023256,
      "grad_norm": 2.0735230445861816,
      "learning_rate": 1.0855753797352868e-06,
      "loss": 0.2423,
      "mean_token_accuracy": 0.9119083881378174,
      "step": 204
    },
    {
      "epoch": 0.9534883720930233,
      "grad_norm": 2.030658006668091,
      "learning_rate": 1.0719436382881466e-06,
      "loss": 0.2534,
      "mean_token_accuracy": 0.9100484848022461,
      "step": 205
    },
    {
      "epoch": 0.958139534883721,
      "grad_norm": 2.127164363861084,
      "learning_rate": 1.0594851417492665e-06,
      "loss": 0.2728,
      "mean_token_accuracy": 0.9037346839904785,
      "step": 206
    },
    {
      "epoch": 0.9627906976744186,
      "grad_norm": 2.3576440811157227,
      "learning_rate": 1.0482031910855804e-06,
      "loss": 0.293,
      "mean_token_accuracy": 0.8944464921951294,
      "step": 207
    },
    {
      "epoch": 0.9674418604651163,
      "grad_norm": 2.2039594650268555,
      "learning_rate": 1.0381007755298547e-06,
      "loss": 0.2671,
      "mean_token_accuracy": 0.9105979800224304,
      "step": 208
    },
    {
      "epoch": 0.9720930232558139,
      "grad_norm": 2.1151583194732666,
      "learning_rate": 1.029180571788672e-06,
      "loss": 0.2481,
      "mean_token_accuracy": 0.9147457480430603,
      "step": 209
    },
    {
      "epoch": 0.9767441860465116,
      "grad_norm": 1.9925205707550049,
      "learning_rate": 1.021444943333218e-06,
      "loss": 0.2566,
      "mean_token_accuracy": 0.9106199145317078,
      "step": 210
    },
    {
      "epoch": 0.9813953488372092,
      "grad_norm": 2.154791831970215,
      "learning_rate": 1.0148959397730637e-06,
      "loss": 0.2524,
      "mean_token_accuracy": 0.9126606583595276,
      "step": 211
    },
    {
      "epoch": 0.986046511627907,
      "grad_norm": 2.046583890914917,
      "learning_rate": 1.0095352963131057e-06,
      "loss": 0.2764,
      "mean_token_accuracy": 0.9061299562454224,
      "step": 212
    },
    {
      "epoch": 0.9906976744186047,
      "grad_norm": 2.164486885070801,
      "learning_rate": 1.0053644332938118e-06,
      "loss": 0.2457,
      "mean_token_accuracy": 0.9103270769119263,
      "step": 213
    },
    {
      "epoch": 0.9953488372093023,
      "grad_norm": 2.152712345123291,
      "learning_rate": 1.0023844558148912e-06,
      "loss": 0.2898,
      "mean_token_accuracy": 0.8999999761581421,
      "step": 214
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.9525059461593628,
      "learning_rate": 1.0005961534424925e-06,
      "loss": 0.2203,
      "mean_token_accuracy": 0.9142746329307556,
      "step": 215
    },
    {
      "epoch": 1.0,
      "step": 215,
      "total_flos": 2.0144468407196058e+17,
      "train_loss": 0.32296112443125524,
      "train_runtime": 757.3407,
      "train_samples_per_second": 9.046,
      "train_steps_per_second": 0.284
    }
  ],
  "logging_steps": 1,
  "max_steps": 215,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0144468407196058e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}