{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10512023126450878,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00035040077088169594,
      "grad_norm": 6.5142412185668945,
      "learning_rate": 0.0,
      "loss": 5.324,
      "step": 1
    },
    {
      "epoch": 0.0007008015417633919,
      "grad_norm": 6.758334159851074,
      "learning_rate": 6.993006993006994e-07,
      "loss": 5.3405,
      "step": 2
    },
    {
      "epoch": 0.0014016030835267838,
      "grad_norm": 6.22674036026001,
      "learning_rate": 2.0979020979020983e-06,
      "loss": 5.3286,
      "step": 4
    },
    {
      "epoch": 0.0021024046252901755,
      "grad_norm": 5.438386917114258,
      "learning_rate": 3.496503496503497e-06,
      "loss": 5.25,
      "step": 6
    },
    {
      "epoch": 0.0028032061670535675,
      "grad_norm": 3.365504741668701,
      "learning_rate": 4.895104895104895e-06,
      "loss": 5.2821,
      "step": 8
    },
    {
      "epoch": 0.0035040077088169595,
      "grad_norm": 7.186147212982178,
      "learning_rate": 6.2937062937062944e-06,
      "loss": 5.21,
      "step": 10
    },
    {
      "epoch": 0.004204809250580351,
      "grad_norm": 4.960826396942139,
      "learning_rate": 7.692307692307694e-06,
      "loss": 5.0759,
      "step": 12
    },
    {
      "epoch": 0.004905610792343743,
      "grad_norm": 4.001464366912842,
      "learning_rate": 9.090909090909091e-06,
      "loss": 5.1092,
      "step": 14
    },
    {
      "epoch": 0.005606412334107135,
      "grad_norm": 3.2986342906951904,
      "learning_rate": 1.048951048951049e-05,
      "loss": 4.93,
      "step": 16
    },
    {
      "epoch": 0.006307213875870527,
      "grad_norm": 2.5407276153564453,
      "learning_rate": 1.188811188811189e-05,
      "loss": 4.8535,
      "step": 18
    },
    {
      "epoch": 0.007008015417633919,
      "grad_norm": 2.211754083633423,
      "learning_rate": 1.3286713286713287e-05,
      "loss": 4.74,
      "step": 20
    },
    {
      "epoch": 0.007708816959397311,
      "grad_norm": 1.6710195541381836,
      "learning_rate": 1.4685314685314686e-05,
      "loss": 4.609,
      "step": 22
    },
    {
      "epoch": 0.008409618501160702,
      "grad_norm": 1.280752182006836,
      "learning_rate": 1.6083916083916083e-05,
      "loss": 4.4879,
      "step": 24
    },
    {
      "epoch": 0.009110420042924094,
      "grad_norm": 1.312186598777771,
      "learning_rate": 1.7482517482517483e-05,
      "loss": 4.3995,
      "step": 26
    },
    {
      "epoch": 0.009811221584687486,
      "grad_norm": 1.3315190076828003,
      "learning_rate": 1.888111888111888e-05,
      "loss": 4.3005,
      "step": 28
    },
    {
      "epoch": 0.010512023126450878,
      "grad_norm": 1.3252590894699097,
      "learning_rate": 2.027972027972028e-05,
      "loss": 4.1952,
      "step": 30
    },
    {
      "epoch": 0.01121282466821427,
      "grad_norm": 1.3794758319854736,
      "learning_rate": 2.1678321678321677e-05,
      "loss": 4.1459,
      "step": 32
    },
    {
      "epoch": 0.011913626209977662,
      "grad_norm": 1.1808068752288818,
      "learning_rate": 2.307692307692308e-05,
      "loss": 4.034,
      "step": 34
    },
    {
      "epoch": 0.012614427751741054,
      "grad_norm": 1.31660795211792,
      "learning_rate": 2.4475524475524478e-05,
      "loss": 3.926,
      "step": 36
    },
    {
      "epoch": 0.013315229293504446,
      "grad_norm": 1.0347495079040527,
      "learning_rate": 2.5874125874125877e-05,
      "loss": 3.8812,
      "step": 38
    },
    {
      "epoch": 0.014016030835267838,
      "grad_norm": 1.050775408744812,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 3.7787,
      "step": 40
    },
    {
      "epoch": 0.01471683237703123,
      "grad_norm": 0.9461761713027954,
      "learning_rate": 2.8671328671328672e-05,
      "loss": 3.6738,
      "step": 42
    },
    {
      "epoch": 0.015417633918794622,
      "grad_norm": 1.0460454225540161,
      "learning_rate": 3.0069930069930068e-05,
      "loss": 3.6385,
      "step": 44
    },
    {
      "epoch": 0.016118435460558012,
      "grad_norm": 1.0687191486358643,
      "learning_rate": 3.146853146853147e-05,
      "loss": 3.5701,
      "step": 46
    },
    {
      "epoch": 0.016819237002321404,
      "grad_norm": 1.4722611904144287,
      "learning_rate": 3.2867132867132866e-05,
      "loss": 3.5438,
      "step": 48
    },
    {
      "epoch": 0.017520038544084796,
      "grad_norm": 1.1305724382400513,
      "learning_rate": 3.4265734265734265e-05,
      "loss": 3.4694,
      "step": 50
    },
    {
      "epoch": 0.018220840085848188,
      "grad_norm": 0.9322625994682312,
      "learning_rate": 3.566433566433567e-05,
      "loss": 3.4488,
      "step": 52
    },
    {
      "epoch": 0.01892164162761158,
      "grad_norm": 1.2441555261611938,
      "learning_rate": 3.7062937062937064e-05,
      "loss": 3.4289,
      "step": 54
    },
    {
      "epoch": 0.019622443169374972,
      "grad_norm": 0.9397731423377991,
      "learning_rate": 3.846153846153846e-05,
      "loss": 3.4021,
      "step": 56
    },
    {
      "epoch": 0.020323244711138364,
      "grad_norm": 1.3261164426803589,
      "learning_rate": 3.986013986013986e-05,
      "loss": 3.3575,
      "step": 58
    },
    {
      "epoch": 0.021024046252901756,
      "grad_norm": 1.08541738986969,
      "learning_rate": 4.125874125874126e-05,
      "loss": 3.3403,
      "step": 60
    },
    {
      "epoch": 0.021724847794665148,
      "grad_norm": 0.8626166582107544,
      "learning_rate": 4.265734265734266e-05,
      "loss": 3.3306,
      "step": 62
    },
    {
      "epoch": 0.02242564933642854,
      "grad_norm": 1.0596344470977783,
      "learning_rate": 4.405594405594406e-05,
      "loss": 3.2779,
      "step": 64
    },
    {
      "epoch": 0.023126450878191932,
      "grad_norm": 1.511917233467102,
      "learning_rate": 4.545454545454546e-05,
      "loss": 3.2759,
      "step": 66
    },
    {
      "epoch": 0.023827252419955324,
      "grad_norm": 1.2062046527862549,
      "learning_rate": 4.685314685314686e-05,
      "loss": 3.2545,
      "step": 68
    },
    {
      "epoch": 0.024528053961718716,
      "grad_norm": 1.1399930715560913,
      "learning_rate": 4.825174825174825e-05,
      "loss": 3.2235,
      "step": 70
    },
    {
      "epoch": 0.025228855503482108,
      "grad_norm": 0.8960133790969849,
      "learning_rate": 4.9650349650349656e-05,
      "loss": 3.2025,
      "step": 72
    },
    {
      "epoch": 0.0259296570452455,
      "grad_norm": 1.3042056560516357,
      "learning_rate": 5.1048951048951055e-05,
      "loss": 3.1475,
      "step": 74
    },
    {
      "epoch": 0.026630458587008892,
      "grad_norm": 1.186320424079895,
      "learning_rate": 5.244755244755245e-05,
      "loss": 3.1759,
      "step": 76
    },
    {
      "epoch": 0.027331260128772284,
      "grad_norm": 1.2691158056259155,
      "learning_rate": 5.384615384615385e-05,
      "loss": 3.1296,
      "step": 78
    },
    {
      "epoch": 0.028032061670535676,
      "grad_norm": 0.7816159129142761,
      "learning_rate": 5.524475524475524e-05,
      "loss": 3.1017,
      "step": 80
    },
    {
      "epoch": 0.028732863212299068,
      "grad_norm": 1.1489295959472656,
      "learning_rate": 5.664335664335665e-05,
      "loss": 3.1151,
      "step": 82
    },
    {
      "epoch": 0.02943366475406246,
      "grad_norm": 1.5686062574386597,
      "learning_rate": 5.8041958041958044e-05,
      "loss": 3.114,
      "step": 84
    },
    {
      "epoch": 0.030134466295825852,
      "grad_norm": 1.4421433210372925,
      "learning_rate": 5.944055944055944e-05,
      "loss": 3.0946,
      "step": 86
    },
    {
      "epoch": 0.030835267837589244,
      "grad_norm": 1.335250973701477,
      "learning_rate": 6.083916083916085e-05,
      "loss": 3.084,
      "step": 88
    },
    {
      "epoch": 0.03153606937935263,
      "grad_norm": 0.970507800579071,
      "learning_rate": 6.223776223776224e-05,
      "loss": 3.1163,
      "step": 90
    },
    {
      "epoch": 0.032236870921116025,
      "grad_norm": 1.2849407196044922,
      "learning_rate": 6.363636363636364e-05,
      "loss": 3.063,
      "step": 92
    },
    {
      "epoch": 0.032937672462879417,
      "grad_norm": 1.0378247499465942,
      "learning_rate": 6.503496503496504e-05,
      "loss": 3.0223,
      "step": 94
    },
    {
      "epoch": 0.03363847400464281,
      "grad_norm": 1.3139392137527466,
      "learning_rate": 6.643356643356644e-05,
      "loss": 3.0572,
      "step": 96
    },
    {
      "epoch": 0.0343392755464062,
      "grad_norm": 1.254752278327942,
      "learning_rate": 6.783216783216784e-05,
      "loss": 3.0408,
      "step": 98
    },
    {
      "epoch": 0.03504007708816959,
      "grad_norm": 1.3333168029785156,
      "learning_rate": 6.923076923076924e-05,
      "loss": 3.0185,
      "step": 100
    },
    {
      "epoch": 0.035740878629932984,
      "grad_norm": 1.2795464992523193,
      "learning_rate": 7.062937062937062e-05,
      "loss": 3.0328,
      "step": 102
    },
    {
      "epoch": 0.036441680171696376,
      "grad_norm": 1.2025645971298218,
      "learning_rate": 7.202797202797204e-05,
      "loss": 3.0303,
      "step": 104
    },
    {
      "epoch": 0.03714248171345977,
      "grad_norm": 1.1741266250610352,
      "learning_rate": 7.342657342657343e-05,
      "loss": 3.0252,
      "step": 106
    },
    {
      "epoch": 0.03784328325522316,
      "grad_norm": 1.2022653818130493,
      "learning_rate": 7.482517482517482e-05,
      "loss": 3.0183,
      "step": 108
    },
    {
      "epoch": 0.03854408479698655,
      "grad_norm": 1.1950666904449463,
      "learning_rate": 7.622377622377622e-05,
      "loss": 2.9804,
      "step": 110
    },
    {
      "epoch": 0.039244886338749944,
      "grad_norm": 1.5780822038650513,
      "learning_rate": 7.762237762237763e-05,
      "loss": 2.9804,
      "step": 112
    },
    {
      "epoch": 0.039945687880513336,
      "grad_norm": 1.0478655099868774,
      "learning_rate": 7.902097902097903e-05,
      "loss": 2.9894,
      "step": 114
    },
    {
      "epoch": 0.04064648942227673,
      "grad_norm": 1.1782268285751343,
      "learning_rate": 8.041958041958042e-05,
      "loss": 2.9717,
      "step": 116
    },
    {
      "epoch": 0.04134729096404012,
      "grad_norm": 1.0321820974349976,
      "learning_rate": 8.181818181818183e-05,
      "loss": 2.9776,
      "step": 118
    },
    {
      "epoch": 0.04204809250580351,
      "grad_norm": 0.9697206020355225,
      "learning_rate": 8.321678321678323e-05,
      "loss": 2.9804,
      "step": 120
    },
    {
      "epoch": 0.042748894047566904,
      "grad_norm": 1.1984606981277466,
      "learning_rate": 8.461538461538461e-05,
      "loss": 2.9495,
      "step": 122
    },
    {
      "epoch": 0.043449695589330296,
      "grad_norm": 0.9830178618431091,
      "learning_rate": 8.601398601398601e-05,
      "loss": 2.9656,
      "step": 124
    },
    {
      "epoch": 0.04415049713109369,
      "grad_norm": 1.3105114698410034,
      "learning_rate": 8.741258741258743e-05,
      "loss": 2.9306,
      "step": 126
    },
    {
      "epoch": 0.04485129867285708,
      "grad_norm": 1.3499157428741455,
      "learning_rate": 8.881118881118881e-05,
      "loss": 2.9381,
      "step": 128
    },
    {
      "epoch": 0.04555210021462047,
      "grad_norm": 0.9977575540542603,
      "learning_rate": 9.020979020979021e-05,
      "loss": 2.907,
      "step": 130
    },
    {
      "epoch": 0.046252901756383864,
      "grad_norm": 1.2331498861312866,
      "learning_rate": 9.160839160839161e-05,
      "loss": 2.9224,
      "step": 132
    },
    {
      "epoch": 0.046953703298147256,
      "grad_norm": 1.451253890991211,
      "learning_rate": 9.300699300699301e-05,
      "loss": 2.9202,
      "step": 134
    },
    {
      "epoch": 0.04765450483991065,
      "grad_norm": 1.2146471738815308,
      "learning_rate": 9.440559440559441e-05,
      "loss": 2.9098,
      "step": 136
    },
    {
      "epoch": 0.04835530638167404,
      "grad_norm": 1.0873245000839233,
      "learning_rate": 9.580419580419581e-05,
      "loss": 2.9218,
      "step": 138
    },
    {
      "epoch": 0.04905610792343743,
      "grad_norm": 1.276413083076477,
      "learning_rate": 9.72027972027972e-05,
      "loss": 2.8947,
      "step": 140
    },
    {
      "epoch": 0.049756909465200824,
      "grad_norm": 1.126065731048584,
      "learning_rate": 9.86013986013986e-05,
      "loss": 2.8788,
      "step": 142
    },
    {
      "epoch": 0.050457711006964216,
      "grad_norm": 1.5177017450332642,
      "learning_rate": 0.0001,
      "loss": 2.9043,
      "step": 144
    },
    {
      "epoch": 0.05115851254872761,
      "grad_norm": 1.3744112253189087,
      "learning_rate": 9.99998657109765e-05,
      "loss": 2.888,
      "step": 146
    },
    {
      "epoch": 0.051859314090491,
      "grad_norm": 1.7921055555343628,
      "learning_rate": 9.999946284462733e-05,
      "loss": 2.8631,
      "step": 148
    },
    {
      "epoch": 0.05256011563225439,
      "grad_norm": 1.1755317449569702,
      "learning_rate": 9.999879140311652e-05,
      "loss": 2.8735,
      "step": 150
    },
    {
      "epoch": 0.053260917174017784,
      "grad_norm": 0.846362292766571,
      "learning_rate": 9.999785139005073e-05,
      "loss": 2.8768,
      "step": 152
    },
    {
      "epoch": 0.053961718715781176,
      "grad_norm": 0.9867280721664429,
      "learning_rate": 9.999664281047933e-05,
      "loss": 2.8859,
      "step": 154
    },
    {
      "epoch": 0.05466252025754457,
      "grad_norm": 0.9751666188240051,
      "learning_rate": 9.999516567089429e-05,
      "loss": 2.8497,
      "step": 156
    },
    {
      "epoch": 0.05536332179930796,
      "grad_norm": 1.0603703260421753,
      "learning_rate": 9.999341997923011e-05,
      "loss": 2.8404,
      "step": 158
    },
    {
      "epoch": 0.05606412334107135,
      "grad_norm": 1.0447975397109985,
      "learning_rate": 9.999140574486392e-05,
      "loss": 2.9092,
      "step": 160
    },
    {
      "epoch": 0.056764924882834744,
      "grad_norm": 1.3046443462371826,
      "learning_rate": 9.998912297861527e-05,
      "loss": 2.8971,
      "step": 162
    },
    {
      "epoch": 0.057465726424598136,
      "grad_norm": 1.1029243469238281,
      "learning_rate": 9.998657169274622e-05,
      "loss": 2.8834,
      "step": 164
    },
    {
      "epoch": 0.05816652796636153,
      "grad_norm": 0.8594210743904114,
      "learning_rate": 9.99837519009611e-05,
      "loss": 2.8361,
      "step": 166
    },
    {
      "epoch": 0.05886732950812492,
      "grad_norm": 0.8585363030433655,
      "learning_rate": 9.998066361840665e-05,
      "loss": 2.8782,
      "step": 168
    },
    {
      "epoch": 0.05956813104988831,
      "grad_norm": 0.693467378616333,
      "learning_rate": 9.997730686167173e-05,
      "loss": 2.8537,
      "step": 170
    },
    {
      "epoch": 0.060268932591651704,
      "grad_norm": 0.8418940305709839,
      "learning_rate": 9.997368164878738e-05,
      "loss": 2.8294,
      "step": 172
    },
    {
      "epoch": 0.060969734133415096,
      "grad_norm": 0.9938271045684814,
      "learning_rate": 9.996978799922665e-05,
      "loss": 2.8458,
      "step": 174
    },
    {
      "epoch": 0.06167053567517849,
      "grad_norm": 1.0347217321395874,
      "learning_rate": 9.99656259339045e-05,
      "loss": 2.8081,
      "step": 176
    },
    {
      "epoch": 0.06237133721694188,
      "grad_norm": 0.9216743111610413,
      "learning_rate": 9.996119547517775e-05,
      "loss": 2.8655,
      "step": 178
    },
    {
      "epoch": 0.06307213875870527,
      "grad_norm": 1.0579859018325806,
      "learning_rate": 9.995649664684486e-05,
      "loss": 2.823,
      "step": 180
    },
    {
      "epoch": 0.06377294030046866,
      "grad_norm": 0.9864194393157959,
      "learning_rate": 9.995152947414586e-05,
      "loss": 2.8081,
      "step": 182
    },
    {
      "epoch": 0.06447374184223205,
      "grad_norm": 0.8999143838882446,
      "learning_rate": 9.994629398376226e-05,
      "loss": 2.7947,
      "step": 184
    },
    {
      "epoch": 0.06517454338399545,
      "grad_norm": 0.9121315479278564,
      "learning_rate": 9.994079020381676e-05,
      "loss": 2.8253,
      "step": 186
    },
    {
      "epoch": 0.06587534492575883,
      "grad_norm": 0.8578842282295227,
      "learning_rate": 9.993501816387329e-05,
      "loss": 2.7548,
      "step": 188
    },
    {
      "epoch": 0.06657614646752223,
      "grad_norm": 0.8564820289611816,
      "learning_rate": 9.992897789493672e-05,
      "loss": 2.8361,
      "step": 190
    },
    {
      "epoch": 0.06727694800928562,
      "grad_norm": 0.8013344407081604,
      "learning_rate": 9.992266942945269e-05,
      "loss": 2.8606,
      "step": 192
    },
    {
      "epoch": 0.06797774955104902,
      "grad_norm": 0.7343975901603699,
      "learning_rate": 9.991609280130752e-05,
      "loss": 2.7947,
      "step": 194
    },
    {
      "epoch": 0.0686785510928124,
      "grad_norm": 0.7338536381721497,
      "learning_rate": 9.990924804582797e-05,
      "loss": 2.7492,
      "step": 196
    },
    {
      "epoch": 0.0693793526345758,
      "grad_norm": 0.828781008720398,
      "learning_rate": 9.990213519978109e-05,
      "loss": 2.8013,
      "step": 198
    },
    {
      "epoch": 0.07008015417633918,
      "grad_norm": 0.7156624794006348,
      "learning_rate": 9.989475430137391e-05,
      "loss": 2.7943,
      "step": 200
    },
    {
      "epoch": 0.07078095571810258,
      "grad_norm": 0.6014353632926941,
      "learning_rate": 9.988710539025341e-05,
      "loss": 2.8099,
      "step": 202
    },
    {
      "epoch": 0.07148175725986597,
      "grad_norm": 0.6569661498069763,
      "learning_rate": 9.987918850750619e-05,
      "loss": 2.8125,
      "step": 204
    },
    {
      "epoch": 0.07218255880162937,
      "grad_norm": 0.6558775305747986,
      "learning_rate": 9.987100369565825e-05,
      "loss": 2.7487,
      "step": 206
    },
    {
      "epoch": 0.07288336034339275,
      "grad_norm": 0.6454245448112488,
      "learning_rate": 9.986255099867481e-05,
      "loss": 2.7648,
      "step": 208
    },
    {
      "epoch": 0.07358416188515615,
      "grad_norm": 0.5741921067237854,
      "learning_rate": 9.985383046196004e-05,
      "loss": 2.7743,
      "step": 210
    },
    {
      "epoch": 0.07428496342691954,
      "grad_norm": 0.5875937938690186,
      "learning_rate": 9.984484213235685e-05,
      "loss": 2.7728,
      "step": 212
    },
    {
      "epoch": 0.07498576496868294,
      "grad_norm": 0.6638422012329102,
      "learning_rate": 9.98355860581466e-05,
      "loss": 2.7504,
      "step": 214
    },
    {
      "epoch": 0.07568656651044632,
      "grad_norm": 1.1614341735839844,
      "learning_rate": 9.982606228904884e-05,
      "loss": 2.7923,
      "step": 216
    },
    {
      "epoch": 0.07638736805220972,
      "grad_norm": 1.005254864692688,
      "learning_rate": 9.981627087622108e-05,
      "loss": 2.76,
      "step": 218
    },
    {
      "epoch": 0.0770881695939731,
      "grad_norm": 0.7738555669784546,
      "learning_rate": 9.980621187225852e-05,
      "loss": 2.7866,
      "step": 220
    },
    {
      "epoch": 0.0777889711357365,
      "grad_norm": 0.9469527006149292,
      "learning_rate": 9.979588533119367e-05,
      "loss": 2.8012,
      "step": 222
    },
    {
      "epoch": 0.07848977267749989,
      "grad_norm": 0.9031473398208618,
      "learning_rate": 9.978529130849619e-05,
      "loss": 2.7522,
      "step": 224
    },
    {
      "epoch": 0.07919057421926329,
      "grad_norm": 0.9450514912605286,
      "learning_rate": 9.977442986107252e-05,
      "loss": 2.7791,
      "step": 226
    },
    {
      "epoch": 0.07989137576102667,
      "grad_norm": 0.7259206771850586,
      "learning_rate": 9.97633010472656e-05,
      "loss": 2.7237,
      "step": 228
    },
    {
      "epoch": 0.08059217730279007,
      "grad_norm": 0.6595309972763062,
      "learning_rate": 9.975190492685451e-05,
      "loss": 2.7284,
      "step": 230
    },
    {
      "epoch": 0.08129297884455346,
      "grad_norm": 0.7696382999420166,
      "learning_rate": 9.974024156105422e-05,
      "loss": 2.7631,
      "step": 232
    },
    {
      "epoch": 0.08199378038631686,
      "grad_norm": 0.7305110096931458,
      "learning_rate": 9.972831101251521e-05,
      "loss": 2.7793,
      "step": 234
    },
    {
      "epoch": 0.08269458192808024,
      "grad_norm": 0.6039514541625977,
      "learning_rate": 9.971611334532314e-05,
      "loss": 2.7669,
      "step": 236
    },
    {
      "epoch": 0.08339538346984364,
      "grad_norm": 0.5824711918830872,
      "learning_rate": 9.970364862499852e-05,
      "loss": 2.7476,
      "step": 238
    },
    {
      "epoch": 0.08409618501160702,
      "grad_norm": 0.6831758618354797,
      "learning_rate": 9.969091691849637e-05,
      "loss": 2.7098,
      "step": 240
    },
    {
      "epoch": 0.08479698655337042,
      "grad_norm": 0.6469074487686157,
      "learning_rate": 9.967791829420581e-05,
      "loss": 2.7609,
      "step": 242
    },
    {
      "epoch": 0.08549778809513381,
      "grad_norm": 0.5876832604408264,
      "learning_rate": 9.966465282194976e-05,
      "loss": 2.7306,
      "step": 244
    },
    {
      "epoch": 0.08619858963689721,
      "grad_norm": 0.6310129761695862,
      "learning_rate": 9.965112057298451e-05,
      "loss": 2.7283,
      "step": 246
    },
    {
      "epoch": 0.08689939117866059,
      "grad_norm": 0.6113069653511047,
      "learning_rate": 9.963732161999935e-05,
      "loss": 2.7274,
      "step": 248
    },
    {
      "epoch": 0.08760019272042399,
      "grad_norm": 1.0655111074447632,
      "learning_rate": 9.96232560371162e-05,
      "loss": 2.7022,
      "step": 250
    },
    {
      "epoch": 0.08830099426218738,
      "grad_norm": 0.8412613272666931,
      "learning_rate": 9.960892389988918e-05,
      "loss": 2.7213,
      "step": 252
    },
    {
      "epoch": 0.08900179580395078,
      "grad_norm": 0.7329776883125305,
      "learning_rate": 9.959432528530428e-05,
      "loss": 2.7343,
      "step": 254
    },
    {
      "epoch": 0.08970259734571416,
      "grad_norm": 0.702498197555542,
      "learning_rate": 9.95794602717788e-05,
      "loss": 2.7642,
      "step": 256
    },
    {
      "epoch": 0.09040339888747755,
      "grad_norm": 0.6936408281326294,
      "learning_rate": 9.95643289391611e-05,
      "loss": 2.7081,
      "step": 258
    },
    {
      "epoch": 0.09110420042924094,
      "grad_norm": 0.664743959903717,
      "learning_rate": 9.954893136873005e-05,
      "loss": 2.7054,
      "step": 260
    },
    {
      "epoch": 0.09180500197100433,
      "grad_norm": 0.5716791152954102,
      "learning_rate": 9.953326764319463e-05,
      "loss": 2.6751,
      "step": 262
    },
    {
      "epoch": 0.09250580351276773,
      "grad_norm": 0.6207195520401001,
      "learning_rate": 9.95173378466935e-05,
      "loss": 2.6945,
      "step": 264
    },
    {
      "epoch": 0.09320660505453111,
      "grad_norm": 0.6572092771530151,
      "learning_rate": 9.950114206479453e-05,
      "loss": 2.6989,
      "step": 266
    },
    {
      "epoch": 0.09390740659629451,
      "grad_norm": 0.7676830887794495,
      "learning_rate": 9.948468038449435e-05,
      "loss": 2.7613,
      "step": 268
    },
    {
      "epoch": 0.0946082081380579,
      "grad_norm": 0.5810503959655762,
      "learning_rate": 9.946795289421787e-05,
      "loss": 2.7234,
      "step": 270
    },
    {
      "epoch": 0.0953090096798213,
      "grad_norm": 0.6459682583808899,
      "learning_rate": 9.945095968381784e-05,
      "loss": 2.717,
      "step": 272
    },
    {
      "epoch": 0.09600981122158468,
      "grad_norm": 0.6498464345932007,
      "learning_rate": 9.94337008445743e-05,
      "loss": 2.7389,
      "step": 274
    },
    {
      "epoch": 0.09671061276334808,
      "grad_norm": 0.6287350654602051,
      "learning_rate": 9.941617646919421e-05,
      "loss": 2.681,
      "step": 276
    },
    {
      "epoch": 0.09741141430511147,
      "grad_norm": 0.7516258955001831,
      "learning_rate": 9.939838665181076e-05,
      "loss": 2.6696,
      "step": 278
    },
    {
      "epoch": 0.09811221584687486,
      "grad_norm": 0.6962350606918335,
      "learning_rate": 9.938033148798307e-05,
      "loss": 2.6971,
      "step": 280
    },
    {
      "epoch": 0.09881301738863825,
      "grad_norm": 0.6605144739151001,
      "learning_rate": 9.936201107469555e-05,
      "loss": 2.6999,
      "step": 282
    },
    {
      "epoch": 0.09951381893040165,
      "grad_norm": 0.5991240739822388,
      "learning_rate": 9.93434255103574e-05,
      "loss": 2.6936,
      "step": 284
    },
    {
      "epoch": 0.10021462047216503,
      "grad_norm": 0.5660961866378784,
      "learning_rate": 9.932457489480213e-05,
      "loss": 2.686,
      "step": 286
    },
    {
      "epoch": 0.10091542201392843,
      "grad_norm": 0.690290093421936,
      "learning_rate": 9.930545932928698e-05,
      "loss": 2.6809,
      "step": 288
    },
    {
      "epoch": 0.10161622355569182,
      "grad_norm": 0.7119167447090149,
      "learning_rate": 9.928607891649234e-05,
      "loss": 2.7221,
      "step": 290
    },
    {
      "epoch": 0.10231702509745522,
      "grad_norm": 0.7049365639686584,
      "learning_rate": 9.926643376052131e-05,
      "loss": 2.6569,
      "step": 292
    },
    {
      "epoch": 0.1030178266392186,
      "grad_norm": 0.6691743731498718,
      "learning_rate": 9.924652396689902e-05,
      "loss": 2.6751,
      "step": 294
    },
    {
      "epoch": 0.103718628180982,
      "grad_norm": 0.5533433556556702,
      "learning_rate": 9.922634964257215e-05,
      "loss": 2.7064,
      "step": 296
    },
    {
      "epoch": 0.10441942972274539,
      "grad_norm": 0.6669672727584839,
      "learning_rate": 9.920591089590831e-05,
      "loss": 2.687,
      "step": 298
    },
    {
      "epoch": 0.10512023126450878,
      "grad_norm": 0.8539720773696899,
      "learning_rate": 9.918520783669549e-05,
      "loss": 2.6968,
      "step": 300
    }
  ],
  "logging_steps": 2,
  "max_steps": 2854,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.377550336196608e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}