{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9995721009841677,
  "eval_steps": 876,
  "global_step": 1752,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "eval_loss": 2.8475096225738525,
      "eval_runtime": 103.0812,
      "eval_samples_per_second": 110.845,
      "eval_steps_per_second": 13.863,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 8.440493443386991,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.8492,
      "step": 10
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.9490346173447717,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.5819,
      "step": 20
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.600282990359268,
      "learning_rate": 6e-06,
      "loss": 2.368,
      "step": 30
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.5128342355183866,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.285,
      "step": 40
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.374859750679287,
      "learning_rate": 1e-05,
      "loss": 2.2456,
      "step": 50
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.5897286646420046,
      "learning_rate": 1.2e-05,
      "loss": 2.2245,
      "step": 60
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.5989674455070406,
      "learning_rate": 1.4e-05,
      "loss": 2.2195,
      "step": 70
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.5945958733352381,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.1831,
      "step": 80
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.694220003324143,
      "learning_rate": 1.8e-05,
      "loss": 2.1767,
      "step": 90
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.4554411206177154,
      "learning_rate": 2e-05,
      "loss": 2.1882,
      "step": 100
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.512788547176528,
      "learning_rate": 1.9998191841174705e-05,
      "loss": 2.1663,
      "step": 110
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.4884413661778526,
      "learning_rate": 1.999276801858648e-05,
      "loss": 2.1768,
      "step": 120
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.3566762491802051,
      "learning_rate": 1.998373049366187e-05,
      "loss": 2.1667,
      "step": 130
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.3202292242087335,
      "learning_rate": 1.9971082534656958e-05,
      "loss": 2.1643,
      "step": 140
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.5085528727448396,
      "learning_rate": 1.995482871547548e-05,
      "loss": 2.1487,
      "step": 150
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.5895534610050568,
      "learning_rate": 1.9934974914014765e-05,
      "loss": 2.1724,
      "step": 160
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.3805999898228127,
      "learning_rate": 1.9911528310040073e-05,
      "loss": 2.1537,
      "step": 170
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.4290062832106343,
      "learning_rate": 1.9884497382588185e-05,
      "loss": 2.1519,
      "step": 180
    },
    {
      "epoch": 0.11,
      "grad_norm": 1.3924244336208988,
      "learning_rate": 1.985389190690111e-05,
      "loss": 2.1671,
      "step": 190
    },
    {
      "epoch": 0.11,
      "grad_norm": 1.746424181546391,
      "learning_rate": 1.9819722950891034e-05,
      "loss": 2.1265,
      "step": 200
    },
    {
      "epoch": 0.12,
      "grad_norm": 1.487352260526166,
      "learning_rate": 1.9782002871137835e-05,
      "loss": 2.1444,
      "step": 210
    },
    {
      "epoch": 0.13,
      "grad_norm": 1.8190326103740864,
      "learning_rate": 1.974074530842053e-05,
      "loss": 2.1355,
      "step": 220
    },
    {
      "epoch": 0.13,
      "grad_norm": 1.714020487946669,
      "learning_rate": 1.9695965182784347e-05,
      "loss": 2.1142,
      "step": 230
    },
    {
      "epoch": 0.14,
      "grad_norm": 1.5433895344149444,
      "learning_rate": 1.9647678688145163e-05,
      "loss": 2.1351,
      "step": 240
    },
    {
      "epoch": 0.14,
      "grad_norm": 1.512497351400695,
      "learning_rate": 1.9595903286433256e-05,
      "loss": 2.1321,
      "step": 250
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.5487574537580002,
      "learning_rate": 1.9540657701278536e-05,
      "loss": 2.1423,
      "step": 260
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.4010705826153367,
      "learning_rate": 1.948196191123948e-05,
      "loss": 2.1352,
      "step": 270
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.6179557586451234,
      "learning_rate": 1.9419837142578228e-05,
      "loss": 2.1248,
      "step": 280
    },
    {
      "epoch": 0.17,
      "grad_norm": 1.4561046353587423,
      "learning_rate": 1.9354305861584542e-05,
      "loss": 2.1301,
      "step": 290
    },
    {
      "epoch": 0.17,
      "grad_norm": 1.2669388875042749,
      "learning_rate": 1.928539176645122e-05,
      "loss": 2.1379,
      "step": 300
    },
    {
      "epoch": 0.18,
      "grad_norm": 1.341753008560977,
      "learning_rate": 1.921311977870413e-05,
      "loss": 2.1439,
      "step": 310
    },
    {
      "epoch": 0.18,
      "grad_norm": 1.3365022464568894,
      "learning_rate": 1.9137516034189768e-05,
      "loss": 2.1262,
      "step": 320
    },
    {
      "epoch": 0.19,
      "grad_norm": 1.2734810511458647,
      "learning_rate": 1.9058607873623697e-05,
      "loss": 2.1266,
      "step": 330
    },
    {
      "epoch": 0.19,
      "grad_norm": 1.3720854684658654,
      "learning_rate": 1.897642383270331e-05,
      "loss": 2.1343,
      "step": 340
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.121677779284525,
      "learning_rate": 1.8890993631788384e-05,
      "loss": 2.1352,
      "step": 350
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.189239436645775,
      "learning_rate": 1.880234816515326e-05,
      "loss": 2.0924,
      "step": 360
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.3089885528086298,
      "learning_rate": 1.8710519489814503e-05,
      "loss": 2.1121,
      "step": 370
    },
    {
      "epoch": 0.22,
      "grad_norm": 1.2381050831578697,
      "learning_rate": 1.8615540813938063e-05,
      "loss": 2.1225,
      "step": 380
    },
    {
      "epoch": 0.22,
      "grad_norm": 1.3316405801410958,
      "learning_rate": 1.851744648483014e-05,
      "loss": 2.1203,
      "step": 390
    },
    {
      "epoch": 0.23,
      "grad_norm": 1.1917580911147747,
      "learning_rate": 1.84162719765161e-05,
      "loss": 2.1079,
      "step": 400
    },
    {
      "epoch": 0.23,
      "grad_norm": 1.0924602070988052,
      "learning_rate": 1.831205387691198e-05,
      "loss": 2.111,
      "step": 410
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.4364738066604248,
      "learning_rate": 1.8204829874593083e-05,
      "loss": 2.0951,
      "step": 420
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.1895141642997293,
      "learning_rate": 1.809463874516462e-05,
      "loss": 2.104,
      "step": 430
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.0767130864233465,
      "learning_rate": 1.798152033723923e-05,
      "loss": 2.0951,
      "step": 440
    },
    {
      "epoch": 0.26,
      "grad_norm": 1.2427794223386772,
      "learning_rate": 1.786551555802643e-05,
      "loss": 2.1186,
      "step": 450
    },
    {
      "epoch": 0.26,
      "grad_norm": 1.2682001982680597,
      "learning_rate": 1.774666635853927e-05,
      "loss": 2.0969,
      "step": 460
    },
    {
      "epoch": 0.27,
      "grad_norm": 1.3411561694518368,
      "learning_rate": 1.762501571842355e-05,
      "loss": 2.0851,
      "step": 470
    },
    {
      "epoch": 0.27,
      "grad_norm": 1.1660818376097224,
      "learning_rate": 1.7500607630414973e-05,
      "loss": 2.0842,
      "step": 480
    },
    {
      "epoch": 0.28,
      "grad_norm": 26.782646263514767,
      "learning_rate": 1.7373487084429988e-05,
      "loss": 2.109,
      "step": 490
    },
    {
      "epoch": 0.29,
      "grad_norm": 1.0725118823204605,
      "learning_rate": 1.7243700051296016e-05,
      "loss": 2.1033,
      "step": 500
    },
    {
      "epoch": 0.29,
      "grad_norm": 1.1473544876658683,
      "learning_rate": 1.7111293466126938e-05,
      "loss": 2.1067,
      "step": 510
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.1233164996213143,
      "learning_rate": 1.6976315211349848e-05,
      "loss": 2.1005,
      "step": 520
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.6171587137595458,
      "learning_rate": 1.6838814099389268e-05,
      "loss": 2.1043,
      "step": 530
    },
    {
      "epoch": 0.31,
      "grad_norm": 1.372813395267995,
      "learning_rate": 1.669883985501501e-05,
      "loss": 2.1002,
      "step": 540
    },
    {
      "epoch": 0.31,
      "grad_norm": 1.1127836389394197,
      "learning_rate": 1.6556443097360136e-05,
      "loss": 2.0851,
      "step": 550
    },
    {
      "epoch": 0.32,
      "grad_norm": 2.717610258588088,
      "learning_rate": 1.641167532161545e-05,
      "loss": 2.0845,
      "step": 560
    },
    {
      "epoch": 0.33,
      "grad_norm": 1.5653769104194137,
      "learning_rate": 1.6264588880407218e-05,
      "loss": 2.0724,
      "step": 570
    },
    {
      "epoch": 0.33,
      "grad_norm": 1.2316818487469028,
      "learning_rate": 1.6115236964864798e-05,
      "loss": 2.078,
      "step": 580
    },
    {
      "epoch": 0.34,
      "grad_norm": 1.1213742181427604,
      "learning_rate": 1.5963673585385016e-05,
      "loss": 2.0748,
      "step": 590
    },
    {
      "epoch": 0.34,
      "grad_norm": 1.1502465686154286,
      "learning_rate": 1.580995355210031e-05,
      "loss": 2.093,
      "step": 600
    },
    {
      "epoch": 0.35,
      "grad_norm": 1.0993269956575817,
      "learning_rate": 1.565413245505765e-05,
      "loss": 2.0444,
      "step": 610
    },
    {
      "epoch": 0.35,
      "grad_norm": 1.2751286594255482,
      "learning_rate": 1.5496266644115386e-05,
      "loss": 2.0861,
      "step": 620
    },
    {
      "epoch": 0.36,
      "grad_norm": 2.446189093106462,
      "learning_rate": 1.5336413208565373e-05,
      "loss": 2.0779,
      "step": 630
    },
    {
      "epoch": 0.37,
      "grad_norm": 1.2051699362872939,
      "learning_rate": 1.5174629956487659e-05,
      "loss": 2.0606,
      "step": 640
    },
    {
      "epoch": 0.37,
      "grad_norm": 1.1973773050996088,
      "learning_rate": 1.5010975393845257e-05,
      "loss": 2.053,
      "step": 650
    },
    {
      "epoch": 0.38,
      "grad_norm": 1.1884541045802726,
      "learning_rate": 1.4845508703326504e-05,
      "loss": 2.0756,
      "step": 660
    },
    {
      "epoch": 0.38,
      "grad_norm": 1.073704568611228,
      "learning_rate": 1.4678289722942757e-05,
      "loss": 2.1002,
      "step": 670
    },
    {
      "epoch": 0.39,
      "grad_norm": 1.2085026626189295,
      "learning_rate": 1.4509378924389044e-05,
      "loss": 2.0443,
      "step": 680
    },
    {
      "epoch": 0.39,
      "grad_norm": 1.120124358877359,
      "learning_rate": 1.4338837391175582e-05,
      "loss": 2.0861,
      "step": 690
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.1688083159685203,
      "learning_rate": 1.4166726796538044e-05,
      "loss": 2.0521,
      "step": 700
    },
    {
      "epoch": 0.41,
      "grad_norm": 1.1839022965360089,
      "learning_rate": 1.3993109381134553e-05,
      "loss": 2.0825,
      "step": 710
    },
    {
      "epoch": 0.41,
      "grad_norm": 1.204413246457808,
      "learning_rate": 1.3818047930537491e-05,
      "loss": 2.0638,
      "step": 720
    },
    {
      "epoch": 0.42,
      "grad_norm": 1.0984747546501181,
      "learning_rate": 1.3641605752528225e-05,
      "loss": 2.0668,
      "step": 730
    },
    {
      "epoch": 0.42,
      "grad_norm": 1.2424062933194955,
      "learning_rate": 1.3463846654203021e-05,
      "loss": 2.0704,
      "step": 740
    },
    {
      "epoch": 0.43,
      "grad_norm": 1.2287388164827397,
      "learning_rate": 1.3284834918898362e-05,
      "loss": 2.0604,
      "step": 750
    },
    {
      "epoch": 0.43,
      "grad_norm": 1.2727536904439012,
      "learning_rate": 1.3104635282944054e-05,
      "loss": 2.062,
      "step": 760
    },
    {
      "epoch": 0.44,
      "grad_norm": 1.2445619190644972,
      "learning_rate": 1.2923312912252509e-05,
      "loss": 2.0675,
      "step": 770
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.209175703891303,
      "learning_rate": 1.2740933378752685e-05,
      "loss": 2.0813,
      "step": 780
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.05801221856849,
      "learning_rate": 1.2557562636677195e-05,
      "loss": 2.0291,
      "step": 790
    },
    {
      "epoch": 0.46,
      "grad_norm": 1.2744525431893252,
      "learning_rate": 1.2373266998711152e-05,
      "loss": 2.07,
      "step": 800
    },
    {
      "epoch": 0.46,
      "grad_norm": 1.1119947967102999,
      "learning_rate": 1.2188113112011407e-05,
      "loss": 2.0593,
      "step": 810
    },
    {
      "epoch": 0.47,
      "grad_norm": 1.0106196828749796,
      "learning_rate": 1.2002167934104815e-05,
      "loss": 2.0631,
      "step": 820
    },
    {
      "epoch": 0.47,
      "grad_norm": 1.0010665987533642,
      "learning_rate": 1.1815498708674266e-05,
      "loss": 2.0714,
      "step": 830
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.2516027979222362,
      "learning_rate": 1.162817294124124e-05,
      "loss": 2.0464,
      "step": 840
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.0156082708830316,
      "learning_rate": 1.144025837475365e-05,
      "loss": 2.0557,
      "step": 850
    },
    {
      "epoch": 0.49,
      "grad_norm": 1.1250221739850519,
      "learning_rate": 1.1251822965087856e-05,
      "loss": 2.0496,
      "step": 860
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.2672537523919118,
      "learning_rate": 1.1062934856473655e-05,
      "loss": 2.0448,
      "step": 870
    },
    {
      "epoch": 0.5,
      "eval_loss": 2.0418317317962646,
      "eval_runtime": 103.7763,
      "eval_samples_per_second": 110.102,
      "eval_steps_per_second": 13.77,
      "step": 876
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.1236822586139523,
      "learning_rate": 1.0873662356851164e-05,
      "loss": 2.0371,
      "step": 880
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.992435580318823,
      "learning_rate": 1.0684073913168502e-05,
      "loss": 2.0444,
      "step": 890
    },
    {
      "epoch": 0.51,
      "grad_norm": 1.102811565572559,
      "learning_rate": 1.0494238086629184e-05,
      "loss": 2.0619,
      "step": 900
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.1541097046897795,
      "learning_rate": 1.0304223527898244e-05,
      "loss": 2.0344,
      "step": 910
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.0366360190903774,
      "learning_rate": 1.0114098952275935e-05,
      "loss": 2.0665,
      "step": 920
    },
    {
      "epoch": 0.53,
      "grad_norm": 1.0161399852210633,
      "learning_rate": 9.923933114848125e-06,
      "loss": 2.036,
      "step": 930
    },
    {
      "epoch": 0.54,
      "grad_norm": 1.24836412296511,
      "learning_rate": 9.733794785622254e-06,
      "loss": 2.0575,
      "step": 940
    },
    {
      "epoch": 0.54,
      "grad_norm": 1.1159767378128298,
      "learning_rate": 9.543752724657924e-06,
      "loss": 2.0264,
      "step": 950
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.089755633213397,
      "learning_rate": 9.353875657201084e-06,
      "loss": 2.0253,
      "step": 960
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.106234215385007,
      "learning_rate": 9.164232248830777e-06,
      "loss": 2.0188,
      "step": 970
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.0275698738246675,
      "learning_rate": 8.974891080627504e-06,
      "loss": 2.0551,
      "step": 980
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.1622793874021287,
      "learning_rate": 8.785920624372122e-06,
      "loss": 2.036,
      "step": 990
    },
    {
      "epoch": 0.57,
      "grad_norm": 1.1956825372131208,
      "learning_rate": 8.597389217784268e-06,
      "loss": 2.0121,
      "step": 1000
    },
    {
      "epoch": 0.58,
      "grad_norm": 1.1603630656961061,
      "learning_rate": 8.409365039809282e-06,
      "loss": 2.0522,
      "step": 1010
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.9807193257053537,
      "learning_rate": 8.221916085962511e-06,
      "loss": 2.0383,
      "step": 1020
    },
    {
      "epoch": 0.59,
      "grad_norm": 1.1576541284187967,
      "learning_rate": 8.03511014374e-06,
      "loss": 2.0338,
      "step": 1030
    },
    {
      "epoch": 0.59,
      "grad_norm": 1.058077247137416,
      "learning_rate": 7.849014768104354e-06,
      "loss": 2.0087,
      "step": 1040
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.0492342153111835,
      "learning_rate": 7.663697257054736e-06,
      "loss": 2.0375,
      "step": 1050
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.0607146652851884,
      "learning_rate": 7.479224627289765e-06,
      "loss": 2.027,
      "step": 1060
    },
    {
      "epoch": 0.61,
      "grad_norm": 1.0606337357914948,
      "learning_rate": 7.295663589972139e-06,
      "loss": 2.0304,
      "step": 1070
    },
    {
      "epoch": 0.62,
      "grad_norm": 1.2458990385743096,
      "learning_rate": 7.113080526603793e-06,
      "loss": 2.0247,
      "step": 1080
    },
    {
      "epoch": 0.62,
      "grad_norm": 1.0520000264708274,
      "learning_rate": 6.93154146502019e-06,
      "loss": 2.0347,
      "step": 1090
    },
    {
      "epoch": 0.63,
      "grad_norm": 1.0190764685112967,
      "learning_rate": 6.7511120555126055e-06,
      "loss": 2.0245,
      "step": 1100
    },
    {
      "epoch": 0.63,
      "grad_norm": 1.0288266074715982,
      "learning_rate": 6.571857547086864e-06,
      "loss": 2.0269,
      "step": 1110
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.0406522209538531,
      "learning_rate": 6.393842763867248e-06,
      "loss": 2.0148,
      "step": 1120
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.9707392990243359,
      "learning_rate": 6.2171320816540144e-06,
      "loss": 2.0242,
      "step": 1130
    },
    {
      "epoch": 0.65,
      "grad_norm": 1.0459965944310712,
      "learning_rate": 6.041789404643078e-06,
      "loss": 2.0217,
      "step": 1140
    },
    {
      "epoch": 0.66,
      "grad_norm": 1.1477415350002944,
      "learning_rate": 5.867878142316221e-06,
      "loss": 2.0396,
      "step": 1150
    },
    {
      "epoch": 0.66,
      "grad_norm": 1.02016191198618,
      "learning_rate": 5.695461186510194e-06,
      "loss": 2.01,
      "step": 1160
    },
    {
      "epoch": 0.67,
      "grad_norm": 1.0555922529805126,
      "learning_rate": 5.524600888673058e-06,
      "loss": 2.0279,
      "step": 1170
    },
    {
      "epoch": 0.67,
      "grad_norm": 1.047057359776084,
      "learning_rate": 5.355359037315893e-06,
      "loss": 2.0288,
      "step": 1180
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.2084733042646434,
      "learning_rate": 5.187796835668137e-06,
      "loss": 2.0069,
      "step": 1190
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.0679386080767506,
      "learning_rate": 5.021974879544522e-06,
      "loss": 2.0239,
      "step": 1200
    },
    {
      "epoch": 0.69,
      "grad_norm": 1.1309906953604523,
      "learning_rate": 4.857953135431723e-06,
      "loss": 1.9917,
      "step": 1210
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.0606942502452434,
      "learning_rate": 4.695790918802577e-06,
      "loss": 2.0103,
      "step": 1220
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.222543190695613,
      "learning_rate": 4.535546872665707e-06,
      "loss": 2.0211,
      "step": 1230
    },
    {
      "epoch": 0.71,
      "grad_norm": 1.1395641397720997,
      "learning_rate": 4.377278946358363e-06,
      "loss": 2.0281,
      "step": 1240
    },
    {
      "epoch": 0.71,
      "grad_norm": 1.2221683190418635,
      "learning_rate": 4.2210443745900806e-06,
      "loss": 1.9907,
      "step": 1250
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.080522060394201,
      "learning_rate": 4.066899656744816e-06,
      "loss": 1.9982,
      "step": 1260
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.9711133864519806,
      "learning_rate": 3.914900536448959e-06,
      "loss": 1.9983,
      "step": 1270
    },
    {
      "epoch": 0.73,
      "grad_norm": 1.1380541178528216,
      "learning_rate": 3.7651019814126656e-06,
      "loss": 2.0097,
      "step": 1280
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.9633220950938465,
      "learning_rate": 3.617558163551802e-06,
      "loss": 1.986,
      "step": 1290
    },
    {
      "epoch": 0.74,
      "grad_norm": 1.0500879776289904,
      "learning_rate": 3.4723224393976353e-06,
      "loss": 2.0258,
      "step": 1300
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.064203126844793,
      "learning_rate": 3.329447330801455e-06,
      "loss": 2.03,
      "step": 1310
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.9922208622268893,
      "learning_rate": 3.1889845059409552e-06,
      "loss": 2.0059,
      "step": 1320
    },
    {
      "epoch": 0.76,
      "grad_norm": 1.153139782016341,
      "learning_rate": 3.0509847606354215e-06,
      "loss": 2.024,
      "step": 1330
    },
    {
      "epoch": 0.76,
      "grad_norm": 1.4479646282996403,
      "learning_rate": 2.91549799997632e-06,
      "loss": 1.996,
      "step": 1340
    },
    {
      "epoch": 0.77,
      "grad_norm": 1.0338025335111782,
      "learning_rate": 2.782573220280055e-06,
      "loss": 2.0027,
      "step": 1350
    },
    {
      "epoch": 0.78,
      "grad_norm": 1.063732584831313,
      "learning_rate": 2.6522584913693295e-06,
      "loss": 1.999,
      "step": 1360
    },
    {
      "epoch": 0.78,
      "grad_norm": 1.18151388005813,
      "learning_rate": 2.5246009391895665e-06,
      "loss": 2.0197,
      "step": 1370
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.96078239213874,
      "learning_rate": 2.3996467287666914e-06,
      "loss": 1.9811,
      "step": 1380
    },
    {
      "epoch": 0.79,
      "grad_norm": 1.2378184274393051,
      "learning_rate": 2.277441047512361e-06,
      "loss": 2.0001,
      "step": 1390
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.0558611234794726,
      "learning_rate": 2.1580280888828e-06,
      "loss": 1.9939,
      "step": 1400
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.9611056812337401,
      "learning_rate": 2.041451036397002e-06,
      "loss": 1.9958,
      "step": 1410
    },
    {
      "epoch": 0.81,
      "grad_norm": 1.031950356244068,
      "learning_rate": 1.9277520480202205e-06,
      "loss": 2.0299,
      "step": 1420
    },
    {
      "epoch": 0.82,
      "grad_norm": 1.2064256312461334,
      "learning_rate": 1.81697224091831e-06,
      "loss": 1.9985,
      "step": 1430
    },
    {
      "epoch": 0.82,
      "grad_norm": 1.06230601717853,
      "learning_rate": 1.7091516765884464e-06,
      "loss": 2.0173,
      "step": 1440
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.2012632430707513,
      "learning_rate": 1.6043293463716202e-06,
      "loss": 2.0259,
      "step": 1450
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.0228988400529624,
      "learning_rate": 1.5025431573521209e-06,
      "loss": 2.0066,
      "step": 1460
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.0275759044730708,
      "learning_rate": 1.4038299186491444e-06,
      "loss": 2.0044,
      "step": 1470
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.0956109756099108,
      "learning_rate": 1.308225328105439e-06,
      "loss": 1.9951,
      "step": 1480
    },
    {
      "epoch": 0.85,
      "grad_norm": 1.5121064882610806,
      "learning_rate": 1.215763959377827e-06,
      "loss": 1.9667,
      "step": 1490
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.9788828191357646,
      "learning_rate": 1.1264792494342858e-06,
      "loss": 2.0037,
      "step": 1500
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.9967966044408001,
      "learning_rate": 1.0404034864620605e-06,
      "loss": 1.9866,
      "step": 1510
    },
    {
      "epoch": 0.87,
      "grad_norm": 1.0099926855076669,
      "learning_rate": 9.575677981912457e-07,
      "loss": 1.9836,
      "step": 1520
    },
    {
      "epoch": 0.87,
      "grad_norm": 1.002362361634915,
      "learning_rate": 8.780021406380012e-07,
      "loss": 1.9983,
      "step": 1530
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.9435464306765974,
      "learning_rate": 8.017352872715078e-07,
      "loss": 1.9797,
      "step": 1540
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.999977176523449,
      "learning_rate": 7.287948186085614e-07,
      "loss": 2.0142,
      "step": 1550
    },
    {
      "epoch": 0.89,
      "grad_norm": 1.152097320833946,
      "learning_rate": 6.592071122395849e-07,
      "loss": 2.0097,
      "step": 1560
    },
    {
      "epoch": 0.9,
      "grad_norm": 1.0857203698752966,
      "learning_rate": 5.929973332896677e-07,
      "loss": 2.0183,
      "step": 1570
    },
    {
      "epoch": 0.9,
      "grad_norm": 1.0543333030471254,
      "learning_rate": 5.301894253180295e-07,
      "loss": 1.985,
      "step": 1580
    },
    {
      "epoch": 0.91,
      "grad_norm": 1.0212489054938816,
      "learning_rate": 4.708061016592924e-07,
      "loss": 1.9888,
      "step": 1590
    },
    {
      "epoch": 0.91,
      "grad_norm": 1.2687381408479979,
      "learning_rate": 4.1486883720960436e-07,
      "loss": 1.997,
      "step": 1600
    },
    {
      "epoch": 0.92,
      "grad_norm": 1.0473866672283625,
      "learning_rate": 3.6239786066064264e-07,
      "loss": 2.0062,
      "step": 1610
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.9105990124075911,
      "learning_rate": 3.1341214718426885e-07,
      "loss": 1.999,
      "step": 1620
    },
    {
      "epoch": 0.93,
      "grad_norm": 1.0250683907923996,
      "learning_rate": 2.6792941157051446e-07,
      "loss": 1.9727,
      "step": 1630
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.9011974189916996,
      "learning_rate": 2.2596610182133328e-07,
      "loss": 1.998,
      "step": 1640
    },
    {
      "epoch": 0.94,
      "grad_norm": 1.0603603261183756,
      "learning_rate": 1.8753739320250153e-07,
      "loss": 2.0138,
      "step": 1650
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.9978845922018089,
      "learning_rate": 1.5265718275574658e-07,
      "loss": 1.9968,
      "step": 1660
    },
    {
      "epoch": 0.95,
      "grad_norm": 1.092063001361788,
      "learning_rate": 1.2133808427313486e-07,
      "loss": 2.011,
      "step": 1670
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.0628189984992609,
      "learning_rate": 9.359142373553287e-08,
      "loss": 2.0037,
      "step": 1680
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.9584594600500118,
      "learning_rate": 6.942723521676465e-08,
      "loss": 1.9823,
      "step": 1690
    },
    {
      "epoch": 0.97,
      "grad_norm": 1.0728091649423657,
      "learning_rate": 4.88542572549755e-08,
      "loss": 1.9732,
      "step": 1700
    },
    {
      "epoch": 0.98,
      "grad_norm": 1.0209005535735403,
      "learning_rate": 3.187992969249876e-08,
      "loss": 2.0,
      "step": 1710
    },
    {
      "epoch": 0.98,
      "grad_norm": 1.0849633622627997,
      "learning_rate": 1.851039098537122e-08,
      "loss": 1.9958,
      "step": 1720
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.9962734868875971,
      "learning_rate": 8.750475983472228e-09,
      "loss": 1.9992,
      "step": 1730
    },
    {
      "epoch": 0.99,
      "grad_norm": 1.083369781103426,
      "learning_rate": 2.6037141820933752e-09,
      "loss": 1.9757,
      "step": 1740
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9782925803672103,
      "learning_rate": 7.232844555282725e-11,
      "loss": 1.9782,
      "step": 1750
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.987204909324646,
      "eval_runtime": 103.685,
      "eval_samples_per_second": 110.199,
      "eval_steps_per_second": 13.782,
      "step": 1752
    }
  ],
  "logging_steps": 10,
  "max_steps": 1752,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 876,
  "total_flos": 366806984294400.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}