{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.999360204734485,
  "eval_steps": 500,
  "global_step": 781,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 11.76060723311326,
      "learning_rate": 2.5316455696202533e-07,
      "loss": 1.6822,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 15.75819587561109,
      "learning_rate": 1.2658227848101267e-06,
      "loss": 1.6642,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 11.381700092209451,
      "learning_rate": 2.5316455696202535e-06,
      "loss": 1.6269,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 3.940372481742168,
      "learning_rate": 3.7974683544303802e-06,
      "loss": 1.4696,
      "step": 15
    },
    {
      "epoch": 0.03,
      "grad_norm": 2.998284936315808,
      "learning_rate": 5.063291139240507e-06,
      "loss": 1.2737,
      "step": 20
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.4930912253553508,
      "learning_rate": 6.329113924050634e-06,
      "loss": 1.2514,
      "step": 25
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.5968427508980252,
      "learning_rate": 7.5949367088607605e-06,
      "loss": 1.2237,
      "step": 30
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.1919266894362968,
      "learning_rate": 8.860759493670886e-06,
      "loss": 1.1799,
      "step": 35
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.207968475527044,
      "learning_rate": 1.0126582278481014e-05,
      "loss": 1.155,
      "step": 40
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.1966812942254237,
      "learning_rate": 1.139240506329114e-05,
      "loss": 1.143,
      "step": 45
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.3885261269338125,
      "learning_rate": 1.2658227848101268e-05,
      "loss": 1.1694,
      "step": 50
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.0658475553487325,
      "learning_rate": 1.3924050632911395e-05,
      "loss": 1.1116,
      "step": 55
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.2195742201568416,
      "learning_rate": 1.5189873417721521e-05,
      "loss": 1.1111,
      "step": 60
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.1281565872746064,
      "learning_rate": 1.6455696202531647e-05,
      "loss": 1.1197,
      "step": 65
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.0428372909471566,
      "learning_rate": 1.7721518987341772e-05,
      "loss": 1.1046,
      "step": 70
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.1098623402342003,
      "learning_rate": 1.89873417721519e-05,
      "loss": 1.0803,
      "step": 75
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.02047373991112,
      "learning_rate": 1.999989986294826e-05,
      "loss": 1.1106,
      "step": 80
    },
    {
      "epoch": 0.11,
      "grad_norm": 1.1133871103761916,
      "learning_rate": 1.9996395276708856e-05,
      "loss": 1.0778,
      "step": 85
    },
    {
      "epoch": 0.12,
      "grad_norm": 1.067392872006611,
      "learning_rate": 1.9987885843187717e-05,
      "loss": 1.0884,
      "step": 90
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.9722703311148946,
      "learning_rate": 1.9974375822762117e-05,
      "loss": 1.0667,
      "step": 95
    },
    {
      "epoch": 0.13,
      "grad_norm": 1.0862367280314877,
      "learning_rate": 1.9955871979429188e-05,
      "loss": 1.0632,
      "step": 100
    },
    {
      "epoch": 0.13,
      "grad_norm": 1.2512571659408036,
      "learning_rate": 1.9932383577419432e-05,
      "loss": 1.0659,
      "step": 105
    },
    {
      "epoch": 0.14,
      "grad_norm": 1.1751369288993785,
      "learning_rate": 1.9903922376558432e-05,
      "loss": 1.0673,
      "step": 110
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.2199342074499273,
      "learning_rate": 1.9870502626379127e-05,
      "loss": 1.0412,
      "step": 115
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.0462278511220546,
      "learning_rate": 1.983214105898757e-05,
      "loss": 1.0417,
      "step": 120
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.1736617165184593,
      "learning_rate": 1.978885688068572e-05,
      "loss": 1.0533,
      "step": 125
    },
    {
      "epoch": 0.17,
      "grad_norm": 1.167836274508835,
      "learning_rate": 1.9740671762355548e-05,
      "loss": 1.043,
      "step": 130
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.9596104398511005,
      "learning_rate": 1.9687609828609156e-05,
      "loss": 1.0659,
      "step": 135
    },
    {
      "epoch": 0.18,
      "grad_norm": 1.089547455726339,
      "learning_rate": 1.9629697645710432e-05,
      "loss": 1.0285,
      "step": 140
    },
    {
      "epoch": 0.19,
      "grad_norm": 1.1072019428376578,
      "learning_rate": 1.9566964208274254e-05,
      "loss": 1.0263,
      "step": 145
    },
    {
      "epoch": 0.19,
      "grad_norm": 1.0354367364165142,
      "learning_rate": 1.9499440924749878e-05,
      "loss": 1.0864,
      "step": 150
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.0814026659538016,
      "learning_rate": 1.9427161601695833e-05,
      "loss": 1.0881,
      "step": 155
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.9888075369780667,
      "learning_rate": 1.9350162426854152e-05,
      "loss": 1.0016,
      "step": 160
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.1029714203666994,
      "learning_rate": 1.926848195103242e-05,
      "loss": 1.0316,
      "step": 165
    },
    {
      "epoch": 0.22,
      "grad_norm": 1.184388866021708,
      "learning_rate": 1.9182161068802742e-05,
      "loss": 1.038,
      "step": 170
    },
    {
      "epoch": 0.22,
      "grad_norm": 1.1210104018767146,
      "learning_rate": 1.909124299802724e-05,
      "loss": 1.03,
      "step": 175
    },
    {
      "epoch": 0.23,
      "grad_norm": 1.1599379220601473,
      "learning_rate": 1.8995773258220374e-05,
      "loss": 1.0362,
      "step": 180
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.9505042533934197,
      "learning_rate": 1.8895799647758912e-05,
      "loss": 1.0465,
      "step": 185
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.055130356572991,
      "learning_rate": 1.879137221995095e-05,
      "loss": 1.0302,
      "step": 190
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.188221794161717,
      "learning_rate": 1.868254325797594e-05,
      "loss": 1.0449,
      "step": 195
    },
    {
      "epoch": 0.26,
      "grad_norm": 1.24255219114766,
      "learning_rate": 1.8569367248708343e-05,
      "loss": 1.0453,
      "step": 200
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.9610325493923482,
      "learning_rate": 1.845190085543795e-05,
      "loss": 1.0736,
      "step": 205
    },
    {
      "epoch": 0.27,
      "grad_norm": 1.213521279472012,
      "learning_rate": 1.8330202889500518e-05,
      "loss": 1.07,
      "step": 210
    },
    {
      "epoch": 0.28,
      "grad_norm": 1.0901868382455668,
      "learning_rate": 1.8204334280833005e-05,
      "loss": 1.0185,
      "step": 215
    },
    {
      "epoch": 0.28,
      "grad_norm": 1.0577550693821212,
      "learning_rate": 1.807435804746807e-05,
      "loss": 1.0521,
      "step": 220
    },
    {
      "epoch": 0.29,
      "grad_norm": 1.1921950083382502,
      "learning_rate": 1.7940339263983112e-05,
      "loss": 1.0113,
      "step": 225
    },
    {
      "epoch": 0.29,
      "grad_norm": 1.1451176215596368,
      "learning_rate": 1.7802345028919728e-05,
      "loss": 1.0366,
      "step": 230
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.039996713908348,
      "learning_rate": 1.766044443118978e-05,
      "loss": 0.9962,
      "step": 235
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.9566229775736538,
      "learning_rate": 1.7514708515485002e-05,
      "loss": 1.0363,
      "step": 240
    },
    {
      "epoch": 0.31,
      "grad_norm": 1.4374877069036986,
      "learning_rate": 1.736521024670737e-05,
      "loss": 1.0319,
      "step": 245
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.02012945474932,
      "learning_rate": 1.7212024473438145e-05,
      "loss": 1.027,
      "step": 250
    },
    {
      "epoch": 0.33,
      "grad_norm": 1.1302434630373548,
      "learning_rate": 1.705522789046377e-05,
      "loss": 1.0065,
      "step": 255
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.9757055931379662,
      "learning_rate": 1.6894899000377462e-05,
      "loss": 1.0352,
      "step": 260
    },
    {
      "epoch": 0.34,
      "grad_norm": 1.049480995976599,
      "learning_rate": 1.67311180742757e-05,
      "loss": 1.0326,
      "step": 265
    },
    {
      "epoch": 0.35,
      "grad_norm": 1.0192736067347892,
      "learning_rate": 1.65639671115693e-05,
      "loss": 0.9999,
      "step": 270
    },
    {
      "epoch": 0.35,
      "grad_norm": 1.1167809018301396,
      "learning_rate": 1.6393529798929103e-05,
      "loss": 1.0055,
      "step": 275
    },
    {
      "epoch": 0.36,
      "grad_norm": 1.0825619824653154,
      "learning_rate": 1.621989146838704e-05,
      "loss": 1.0233,
      "step": 280
    },
    {
      "epoch": 0.36,
      "grad_norm": 1.005770462178686,
      "learning_rate": 1.6043139054613326e-05,
      "loss": 1.0038,
      "step": 285
    },
    {
      "epoch": 0.37,
      "grad_norm": 1.098473406093216,
      "learning_rate": 1.586336105139127e-05,
      "loss": 0.9977,
      "step": 290
    },
    {
      "epoch": 0.38,
      "grad_norm": 1.0490431615668332,
      "learning_rate": 1.568064746731156e-05,
      "loss": 1.0061,
      "step": 295
    },
    {
      "epoch": 0.38,
      "grad_norm": 1.004305030186986,
      "learning_rate": 1.5495089780708062e-05,
      "loss": 0.9927,
      "step": 300
    },
    {
      "epoch": 0.39,
      "grad_norm": 1.0306996734289007,
      "learning_rate": 1.530678089385782e-05,
      "loss": 0.983,
      "step": 305
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.9423273242468014,
      "learning_rate": 1.5115815086468103e-05,
      "loss": 0.9799,
      "step": 310
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.1246961996346894,
      "learning_rate": 1.492228796847385e-05,
      "loss": 1.0154,
      "step": 315
    },
    {
      "epoch": 0.41,
      "grad_norm": 1.0747529887949312,
      "learning_rate": 1.4726296432169095e-05,
      "loss": 1.0162,
      "step": 320
    },
    {
      "epoch": 0.42,
      "grad_norm": 1.1471917674492866,
      "learning_rate": 1.4527938603696376e-05,
      "loss": 1.0363,
      "step": 325
    },
    {
      "epoch": 0.42,
      "grad_norm": 1.0505847496584861,
      "learning_rate": 1.4327313793918362e-05,
      "loss": 0.9627,
      "step": 330
    },
    {
      "epoch": 0.43,
      "grad_norm": 1.0262993815065058,
      "learning_rate": 1.4124522448696407e-05,
      "loss": 1.006,
      "step": 335
    },
    {
      "epoch": 0.44,
      "grad_norm": 1.044795548816788,
      "learning_rate": 1.3919666098600753e-05,
      "loss": 1.0076,
      "step": 340
    },
    {
      "epoch": 0.44,
      "grad_norm": 1.050133490357968,
      "learning_rate": 1.3712847308077737e-05,
      "loss": 1.021,
      "step": 345
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.1313342513320197,
      "learning_rate": 1.350416962409934e-05,
      "loss": 0.9964,
      "step": 350
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.0532665494275932,
      "learning_rate": 1.3293737524320798e-05,
      "loss": 1.0263,
      "step": 355
    },
    {
      "epoch": 0.46,
      "grad_norm": 1.1149778014746092,
      "learning_rate": 1.3081656364772308e-05,
      "loss": 0.9959,
      "step": 360
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.991705987820452,
      "learning_rate": 1.2868032327110904e-05,
      "loss": 1.0107,
      "step": 365
    },
    {
      "epoch": 0.47,
      "grad_norm": 1.1090968802518788,
      "learning_rate": 1.2652972365459008e-05,
      "loss": 1.015,
      "step": 370
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.0489892057222994,
      "learning_rate": 1.243658415285622e-05,
      "loss": 0.9843,
      "step": 375
    },
    {
      "epoch": 0.49,
      "grad_norm": 1.1053846068835982,
      "learning_rate": 1.2218976027351177e-05,
      "loss": 0.9901,
      "step": 380
    },
    {
      "epoch": 0.49,
      "grad_norm": 1.0419685500243974,
      "learning_rate": 1.2000256937760446e-05,
      "loss": 0.9755,
      "step": 385
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.9541231393070981,
      "learning_rate": 1.1780536389121668e-05,
      "loss": 0.9945,
      "step": 390
    },
    {
      "epoch": 0.51,
      "grad_norm": 1.0666176053825536,
      "learning_rate": 1.155992438786818e-05,
      "loss": 0.9917,
      "step": 395
    },
    {
      "epoch": 0.51,
      "grad_norm": 1.0564637749960983,
      "learning_rate": 1.1338531386752618e-05,
      "loss": 0.9821,
      "step": 400
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.1667820924248677,
      "learning_rate": 1.1116468229547079e-05,
      "loss": 0.9557,
      "step": 405
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.2270496171271985,
      "learning_rate": 1.0893846095547493e-05,
      "loss": 0.9876,
      "step": 410
    },
    {
      "epoch": 0.53,
      "grad_norm": 1.0509829176213852,
      "learning_rate": 1.0670776443910024e-05,
      "loss": 0.9705,
      "step": 415
    },
    {
      "epoch": 0.54,
      "grad_norm": 1.031556959390347,
      "learning_rate": 1.0447370957847343e-05,
      "loss": 0.9956,
      "step": 420
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.9782347943874674,
      "learning_rate": 1.0223741488712732e-05,
      "loss": 1.0016,
      "step": 425
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.1997141162620377,
      "learning_rate": 1e-05,
      "loss": 0.9926,
      "step": 430
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.0406139514481398,
      "learning_rate": 9.776258511287271e-06,
      "loss": 0.9863,
      "step": 435
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.8886020594570727,
      "learning_rate": 9.55262904215266e-06,
      "loss": 0.974,
      "step": 440
    },
    {
      "epoch": 0.57,
      "grad_norm": 1.0655688286549563,
      "learning_rate": 9.329223556089976e-06,
      "loss": 0.9757,
      "step": 445
    },
    {
      "epoch": 0.58,
      "grad_norm": 1.0923191593800243,
      "learning_rate": 9.10615390445251e-06,
      "loss": 0.9713,
      "step": 450
    },
    {
      "epoch": 0.58,
      "grad_norm": 1.076596518914256,
      "learning_rate": 8.883531770452924e-06,
      "loss": 0.9654,
      "step": 455
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.8916672807364537,
      "learning_rate": 8.661468613247387e-06,
      "loss": 1.0012,
      "step": 460
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.874231994609429,
      "learning_rate": 8.440075612131823e-06,
      "loss": 0.9935,
      "step": 465
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.0720988215903333,
      "learning_rate": 8.219463610878336e-06,
      "loss": 1.0012,
      "step": 470
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.9880422724089176,
      "learning_rate": 7.999743062239557e-06,
      "loss": 0.9978,
      "step": 475
    },
    {
      "epoch": 0.61,
      "grad_norm": 1.1188809925235335,
      "learning_rate": 7.781023972648826e-06,
      "loss": 1.0149,
      "step": 480
    },
    {
      "epoch": 0.62,
      "grad_norm": 1.0471236576275667,
      "learning_rate": 7.563415847143782e-06,
      "loss": 0.9488,
      "step": 485
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.9980906565809108,
      "learning_rate": 7.347027634540993e-06,
      "loss": 0.9909,
      "step": 490
    },
    {
      "epoch": 0.63,
      "grad_norm": 1.0442475148255606,
      "learning_rate": 7.131967672889101e-06,
      "loss": 0.9747,
      "step": 495
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.1002478336061363,
      "learning_rate": 6.918343635227694e-06,
      "loss": 0.9745,
      "step": 500
    },
    {
      "epoch": 0.65,
      "grad_norm": 1.136505991571122,
      "learning_rate": 6.706262475679205e-06,
      "loss": 0.9962,
      "step": 505
    },
    {
      "epoch": 0.65,
      "grad_norm": 1.018960782583497,
      "learning_rate": 6.495830375900665e-06,
      "loss": 0.9551,
      "step": 510
    },
    {
      "epoch": 0.66,
      "grad_norm": 1.1144991763692194,
      "learning_rate": 6.287152691922264e-06,
      "loss": 0.9995,
      "step": 515
    },
    {
      "epoch": 0.67,
      "grad_norm": 1.02967918390761,
      "learning_rate": 6.080333901399252e-06,
      "loss": 0.9789,
      "step": 520
    },
    {
      "epoch": 0.67,
      "grad_norm": 1.0324482375798092,
      "learning_rate": 5.875477551303596e-06,
      "loss": 0.99,
      "step": 525
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.9742298498254184,
      "learning_rate": 5.672686206081638e-06,
      "loss": 0.992,
      "step": 530
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.132108415071919,
      "learning_rate": 5.47206139630363e-06,
      "loss": 1.0074,
      "step": 535
    },
    {
      "epoch": 0.69,
      "grad_norm": 1.0995283960956674,
      "learning_rate": 5.273703567830908e-06,
      "loss": 0.977,
      "step": 540
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.0441789439099798,
      "learning_rate": 5.077712031526153e-06,
      "loss": 1.0189,
      "step": 545
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.981986385580179,
      "learning_rate": 4.8841849135319015e-06,
      "loss": 0.9531,
      "step": 550
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.9434471380481197,
      "learning_rate": 4.693219106142186e-06,
      "loss": 0.9845,
      "step": 555
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.0743211447236112,
      "learning_rate": 4.504910219291941e-06,
      "loss": 0.9544,
      "step": 560
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.9538980158325512,
      "learning_rate": 4.319352532688444e-06,
      "loss": 0.9834,
      "step": 565
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.9654411881427548,
      "learning_rate": 4.13663894860873e-06,
      "loss": 0.9788,
      "step": 570
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.993405896499914,
      "learning_rate": 3.956860945386677e-06,
      "loss": 1.0042,
      "step": 575
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.9704739668364883,
      "learning_rate": 3.7801085316129615e-06,
      "loss": 0.9868,
      "step": 580
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.977366110513439,
      "learning_rate": 3.606470201070904e-06,
      "loss": 0.9468,
      "step": 585
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.9579638698628271,
      "learning_rate": 3.4360328884307058e-06,
      "loss": 0.9635,
      "step": 590
    },
    {
      "epoch": 0.76,
      "grad_norm": 1.106753292275808,
      "learning_rate": 3.2688819257242963e-06,
      "loss": 0.9617,
      "step": 595
    },
    {
      "epoch": 0.77,
      "grad_norm": 1.1425286371389305,
      "learning_rate": 3.1051009996225434e-06,
      "loss": 0.9692,
      "step": 600
    },
    {
      "epoch": 0.77,
      "grad_norm": 1.1364557782660365,
      "learning_rate": 2.9447721095362325e-06,
      "loss": 0.9744,
      "step": 605
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.9406598524967239,
      "learning_rate": 2.7879755265618558e-06,
      "loss": 0.9925,
      "step": 610
    },
    {
      "epoch": 0.79,
      "grad_norm": 1.0664629358580562,
      "learning_rate": 2.6347897532926293e-06,
      "loss": 0.9588,
      "step": 615
    },
    {
      "epoch": 0.79,
      "grad_norm": 1.0139901204102686,
      "learning_rate": 2.485291484515e-06,
      "loss": 0.9769,
      "step": 620
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.8650137198761167,
      "learning_rate": 2.339555568810221e-06,
      "loss": 0.9957,
      "step": 625
    },
    {
      "epoch": 0.81,
      "grad_norm": 1.0370421826033083,
      "learning_rate": 2.1976549710802754e-06,
      "loss": 0.992,
      "step": 630
    },
    {
      "epoch": 0.81,
      "grad_norm": 1.0397841541534047,
      "learning_rate": 2.0596607360168897e-06,
      "loss": 0.9804,
      "step": 635
    },
    {
      "epoch": 0.82,
      "grad_norm": 1.2468139771235325,
      "learning_rate": 1.9256419525319316e-06,
      "loss": 0.9528,
      "step": 640
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.9006093150032681,
      "learning_rate": 1.7956657191669969e-06,
      "loss": 0.9388,
      "step": 645
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.0317668957030404,
      "learning_rate": 1.6697971104994847e-06,
      "loss": 0.9781,
      "step": 650
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.0387479722065127,
      "learning_rate": 1.5480991445620541e-06,
      "loss": 0.9917,
      "step": 655
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.9754842911312599,
      "learning_rate": 1.4306327512916574e-06,
      "loss": 0.9696,
      "step": 660
    },
    {
      "epoch": 0.85,
      "grad_norm": 1.0363013030380983,
      "learning_rate": 1.3174567420240647e-06,
      "loss": 0.9658,
      "step": 665
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.8960305658205177,
      "learning_rate": 1.2086277800490554e-06,
      "loss": 0.9595,
      "step": 670
    },
    {
      "epoch": 0.86,
      "grad_norm": 1.179228433134159,
      "learning_rate": 1.1042003522410882e-06,
      "loss": 0.9688,
      "step": 675
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.9413992615815986,
      "learning_rate": 1.0042267417796292e-06,
      "loss": 0.989,
      "step": 680
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.9758806517342423,
      "learning_rate": 9.08757001972762e-07,
      "loss": 0.9629,
      "step": 685
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.1736698700435968,
      "learning_rate": 8.178389311972612e-07,
      "loss": 0.9557,
      "step": 690
    },
    {
      "epoch": 0.89,
      "grad_norm": 1.0617448240010183,
      "learning_rate": 7.315180489675822e-07,
      "loss": 0.9637,
      "step": 695
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.9621374315918411,
      "learning_rate": 6.498375731458529e-07,
      "loss": 0.987,
      "step": 700
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.9896147163255197,
      "learning_rate": 5.728383983041696e-07,
      "loss": 0.9728,
      "step": 705
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.9188541096678722,
      "learning_rate": 5.005590752501244e-07,
      "loss": 1.0125,
      "step": 710
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.99532325879258,
      "learning_rate": 4.3303579172574884e-07,
      "loss": 0.969,
      "step": 715
    },
    {
      "epoch": 0.92,
      "grad_norm": 1.0242423087799273,
      "learning_rate": 3.7030235428956895e-07,
      "loss": 0.9804,
      "step": 720
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.9934143231160297,
      "learning_rate": 3.1239017139084725e-07,
      "loss": 0.9665,
      "step": 725
    },
    {
      "epoch": 0.93,
      "grad_norm": 1.1181836954053048,
      "learning_rate": 2.593282376444539e-07,
      "loss": 0.9763,
      "step": 730
    },
    {
      "epoch": 0.94,
      "grad_norm": 1.092994710465261,
      "learning_rate": 2.11143119314281e-07,
      "loss": 0.9634,
      "step": 735
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.9598027605106688,
      "learning_rate": 1.6785894101243205e-07,
      "loss": 1.0029,
      "step": 740
    },
    {
      "epoch": 0.95,
      "grad_norm": 1.0352713808102656,
      "learning_rate": 1.2949737362087156e-07,
      "loss": 0.9645,
      "step": 745
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.9639150803887012,
      "learning_rate": 9.607762344156946e-08,
      "loss": 0.9461,
      "step": 750
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.9466905218851684,
      "learning_rate": 6.761642258056977e-08,
      "loss": 0.9829,
      "step": 755
    },
    {
      "epoch": 0.97,
      "grad_norm": 1.0617099395887875,
      "learning_rate": 4.412802057081278e-08,
      "loss": 0.9796,
      "step": 760
    },
    {
      "epoch": 0.98,
      "grad_norm": 1.020436800278922,
      "learning_rate": 2.5624177237884017e-08,
      "loss": 0.9529,
      "step": 765
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.8998248978192732,
      "learning_rate": 1.2114156812284006e-08,
      "loss": 0.9831,
      "step": 770
    },
    {
      "epoch": 0.99,
      "grad_norm": 1.216227728570802,
      "learning_rate": 3.6047232911462506e-09,
      "loss": 0.985,
      "step": 775
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9463439407790857,
      "learning_rate": 1.0013705174061195e-10,
      "loss": 0.9774,
      "step": 780
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.9624356627464294,
      "eval_runtime": 1769.185,
      "eval_samples_per_second": 55.649,
      "eval_steps_per_second": 1.739,
      "step": 781
    },
    {
      "epoch": 1.0,
      "step": 781,
      "total_flos": 113044957102080.0,
      "train_loss": 1.0241747791574798,
      "train_runtime": 9230.502,
      "train_samples_per_second": 10.834,
      "train_steps_per_second": 0.085
    }
  ],
  "logging_steps": 5,
  "max_steps": 781,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 113044957102080.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}