{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9996810207336523,
  "eval_steps": 500,
  "global_step": 1567,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006379585326953748,
      "grad_norm": 694.1307983398438,
      "learning_rate": 1.910828025477707e-06,
      "loss": 45.2944,
      "step": 1
    },
    {
      "epoch": 0.003189792663476874,
      "grad_norm": 503.5704345703125,
      "learning_rate": 9.554140127388534e-06,
      "loss": 45.6151,
      "step": 5
    },
    {
      "epoch": 0.006379585326953748,
      "grad_norm": 180.77162170410156,
      "learning_rate": 1.9108280254777068e-05,
      "loss": 33.1885,
      "step": 10
    },
    {
      "epoch": 0.009569377990430622,
      "grad_norm": 67.5441665649414,
      "learning_rate": 2.8662420382165606e-05,
      "loss": 23.199,
      "step": 15
    },
    {
      "epoch": 0.012759170653907496,
      "grad_norm": 18.643754959106445,
      "learning_rate": 3.8216560509554137e-05,
      "loss": 20.7118,
      "step": 20
    },
    {
      "epoch": 0.01594896331738437,
      "grad_norm": 10.430642127990723,
      "learning_rate": 4.777070063694267e-05,
      "loss": 19.5913,
      "step": 25
    },
    {
      "epoch": 0.019138755980861243,
      "grad_norm": 13.150680541992188,
      "learning_rate": 5.732484076433121e-05,
      "loss": 18.0748,
      "step": 30
    },
    {
      "epoch": 0.022328548644338118,
      "grad_norm": 34.60968017578125,
      "learning_rate": 6.687898089171974e-05,
      "loss": 15.8287,
      "step": 35
    },
    {
      "epoch": 0.025518341307814992,
      "grad_norm": 77.59700775146484,
      "learning_rate": 7.643312101910827e-05,
      "loss": 11.4445,
      "step": 40
    },
    {
      "epoch": 0.028708133971291867,
      "grad_norm": 14.57149600982666,
      "learning_rate": 8.59872611464968e-05,
      "loss": 3.2777,
      "step": 45
    },
    {
      "epoch": 0.03189792663476874,
      "grad_norm": 6.958239555358887,
      "learning_rate": 9.554140127388533e-05,
      "loss": 2.233,
      "step": 50
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 109.23677062988281,
      "learning_rate": 0.00010509554140127387,
      "loss": 1.8566,
      "step": 55
    },
    {
      "epoch": 0.03827751196172249,
      "grad_norm": 12.268388748168945,
      "learning_rate": 0.00011464968152866242,
      "loss": 1.7099,
      "step": 60
    },
    {
      "epoch": 0.04146730462519936,
      "grad_norm": 3.5562500953674316,
      "learning_rate": 0.00012420382165605095,
      "loss": 1.5828,
      "step": 65
    },
    {
      "epoch": 0.044657097288676235,
      "grad_norm": 2.0333609580993652,
      "learning_rate": 0.00013375796178343948,
      "loss": 1.4119,
      "step": 70
    },
    {
      "epoch": 0.04784688995215311,
      "grad_norm": 4.240214824676514,
      "learning_rate": 0.00014331210191082802,
      "loss": 1.3318,
      "step": 75
    },
    {
      "epoch": 0.051036682615629984,
      "grad_norm": 5.074183940887451,
      "learning_rate": 0.00015286624203821655,
      "loss": 1.2783,
      "step": 80
    },
    {
      "epoch": 0.05422647527910686,
      "grad_norm": 27.86067771911621,
      "learning_rate": 0.00016242038216560508,
      "loss": 1.2497,
      "step": 85
    },
    {
      "epoch": 0.05741626794258373,
      "grad_norm": 4.769386291503906,
      "learning_rate": 0.0001719745222929936,
      "loss": 1.2015,
      "step": 90
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 8.017805099487305,
      "learning_rate": 0.00018152866242038214,
      "loss": 1.1433,
      "step": 95
    },
    {
      "epoch": 0.06379585326953748,
      "grad_norm": 10.532003402709961,
      "learning_rate": 0.00019108280254777067,
      "loss": 1.1267,
      "step": 100
    },
    {
      "epoch": 0.06698564593301436,
      "grad_norm": 13.3386869430542,
      "learning_rate": 0.0002006369426751592,
      "loss": 1.1991,
      "step": 105
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 6.093812942504883,
      "learning_rate": 0.00021019108280254773,
      "loss": 1.1734,
      "step": 110
    },
    {
      "epoch": 0.0733652312599681,
      "grad_norm": 5.6636199951171875,
      "learning_rate": 0.00021974522292993626,
      "loss": 1.1269,
      "step": 115
    },
    {
      "epoch": 0.07655502392344497,
      "grad_norm": 3.0813510417938232,
      "learning_rate": 0.00022929936305732485,
      "loss": 1.1113,
      "step": 120
    },
    {
      "epoch": 0.07974481658692185,
      "grad_norm": 2.015939474105835,
      "learning_rate": 0.00023885350318471338,
      "loss": 1.0849,
      "step": 125
    },
    {
      "epoch": 0.08293460925039872,
      "grad_norm": 9.842239379882812,
      "learning_rate": 0.0002484076433121019,
      "loss": 1.1141,
      "step": 130
    },
    {
      "epoch": 0.0861244019138756,
      "grad_norm": 4.175192356109619,
      "learning_rate": 0.00025796178343949044,
      "loss": 1.0866,
      "step": 135
    },
    {
      "epoch": 0.08931419457735247,
      "grad_norm": 7.420131206512451,
      "learning_rate": 0.00026751592356687897,
      "loss": 1.053,
      "step": 140
    },
    {
      "epoch": 0.09250398724082935,
      "grad_norm": 20.004467010498047,
      "learning_rate": 0.0002770700636942675,
      "loss": 1.0895,
      "step": 145
    },
    {
      "epoch": 0.09569377990430622,
      "grad_norm": 16.957359313964844,
      "learning_rate": 0.00028662420382165603,
      "loss": 1.0669,
      "step": 150
    },
    {
      "epoch": 0.09888357256778309,
      "grad_norm": 3.6915156841278076,
      "learning_rate": 0.00029617834394904456,
      "loss": 1.0751,
      "step": 155
    },
    {
      "epoch": 0.10207336523125997,
      "grad_norm": 4.615033149719238,
      "learning_rate": 0.0002999966490829603,
      "loss": 1.0461,
      "step": 160
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 2.876262903213501,
      "learning_rate": 0.00029997617179878324,
      "loss": 1.0378,
      "step": 165
    },
    {
      "epoch": 0.10845295055821372,
      "grad_norm": 3.2917582988739014,
      "learning_rate": 0.0002999370813893047,
      "loss": 1.0302,
      "step": 170
    },
    {
      "epoch": 0.11164274322169059,
      "grad_norm": 7.9203715324401855,
      "learning_rate": 0.00029987938270592676,
      "loss": 1.067,
      "step": 175
    },
    {
      "epoch": 0.11483253588516747,
      "grad_norm": 4.65939474105835,
      "learning_rate": 0.0002998030829094724,
      "loss": 1.0646,
      "step": 180
    },
    {
      "epoch": 0.11802232854864433,
      "grad_norm": 1.8894805908203125,
      "learning_rate": 0.00029970819146929694,
      "loss": 1.0093,
      "step": 185
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 2.7538986206054688,
      "learning_rate": 0.0002995947201621131,
      "loss": 1.0402,
      "step": 190
    },
    {
      "epoch": 0.12440191387559808,
      "grad_norm": 2.2546260356903076,
      "learning_rate": 0.00029946268307052886,
      "loss": 1.0247,
      "step": 195
    },
    {
      "epoch": 0.12759170653907495,
      "grad_norm": 2.655927896499634,
      "learning_rate": 0.0002993120965813003,
      "loss": 0.9994,
      "step": 200
    },
    {
      "epoch": 0.13078149920255183,
      "grad_norm": 1.8121349811553955,
      "learning_rate": 0.0002991429793832975,
      "loss": 1.0279,
      "step": 205
    },
    {
      "epoch": 0.1339712918660287,
      "grad_norm": 1.38643217086792,
      "learning_rate": 0.00029895535246518524,
      "loss": 1.0534,
      "step": 210
    },
    {
      "epoch": 0.1371610845295056,
      "grad_norm": 4.24297571182251,
      "learning_rate": 0.0002987492391128182,
      "loss": 1.0622,
      "step": 215
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 2.3828201293945312,
      "learning_rate": 0.0002985246649063509,
      "loss": 1.0239,
      "step": 220
    },
    {
      "epoch": 0.14354066985645933,
      "grad_norm": 1.4523991346359253,
      "learning_rate": 0.0002982816577170631,
      "loss": 1.026,
      "step": 225
    },
    {
      "epoch": 0.1467304625199362,
      "grad_norm": 1.3892016410827637,
      "learning_rate": 0.00029802024770390087,
      "loss": 1.0298,
      "step": 230
    },
    {
      "epoch": 0.14992025518341306,
      "grad_norm": 3.4726333618164062,
      "learning_rate": 0.00029774046730973334,
      "loss": 1.0316,
      "step": 235
    },
    {
      "epoch": 0.15311004784688995,
      "grad_norm": 2.9531638622283936,
      "learning_rate": 0.00029744235125732664,
      "loss": 1.0196,
      "step": 240
    },
    {
      "epoch": 0.15629984051036683,
      "grad_norm": 1.494456171989441,
      "learning_rate": 0.0002971259365450344,
      "loss": 1.0245,
      "step": 245
    },
    {
      "epoch": 0.1594896331738437,
      "grad_norm": 3.462984323501587,
      "learning_rate": 0.00029679126244220596,
      "loss": 0.9657,
      "step": 250
    },
    {
      "epoch": 0.16267942583732056,
      "grad_norm": 2.6760306358337402,
      "learning_rate": 0.00029643837048431293,
      "loss": 0.9942,
      "step": 255
    },
    {
      "epoch": 0.16586921850079744,
      "grad_norm": 3.4000234603881836,
      "learning_rate": 0.0002960673044677939,
      "loss": 0.9955,
      "step": 260
    },
    {
      "epoch": 0.16905901116427433,
      "grad_norm": 2.6364219188690186,
      "learning_rate": 0.00029567811044461977,
      "loss": 0.966,
      "step": 265
    },
    {
      "epoch": 0.1722488038277512,
      "grad_norm": 10.39656925201416,
      "learning_rate": 0.00029527083671657746,
      "loss": 0.9989,
      "step": 270
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 2.5434165000915527,
      "learning_rate": 0.00029484553382927594,
      "loss": 0.9809,
      "step": 275
    },
    {
      "epoch": 0.17862838915470494,
      "grad_norm": 1.5303857326507568,
      "learning_rate": 0.000294402254565873,
      "loss": 1.0049,
      "step": 280
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 5.918676376342773,
      "learning_rate": 0.00029394105394052434,
      "loss": 0.995,
      "step": 285
    },
    {
      "epoch": 0.1850079744816587,
      "grad_norm": 1.4962425231933594,
      "learning_rate": 0.00029346198919155616,
      "loss": 1.0264,
      "step": 290
    },
    {
      "epoch": 0.18819776714513556,
      "grad_norm": 1.3401553630828857,
      "learning_rate": 0.00029296511977436107,
      "loss": 0.998,
      "step": 295
    },
    {
      "epoch": 0.19138755980861244,
      "grad_norm": 3.1120340824127197,
      "learning_rate": 0.0002924505073540198,
      "loss": 0.9931,
      "step": 300
    },
    {
      "epoch": 0.19457735247208932,
      "grad_norm": 2.893742561340332,
      "learning_rate": 0.0002919182157976476,
      "loss": 0.9924,
      "step": 305
    },
    {
      "epoch": 0.19776714513556617,
      "grad_norm": 3.6078243255615234,
      "learning_rate": 0.00029136831116646815,
      "loss": 0.9973,
      "step": 310
    },
    {
      "epoch": 0.20095693779904306,
      "grad_norm": 1.5071393251419067,
      "learning_rate": 0.000290800861707615,
      "loss": 0.9707,
      "step": 315
    },
    {
      "epoch": 0.20414673046251994,
      "grad_norm": 20.275678634643555,
      "learning_rate": 0.00029021593784566113,
      "loss": 0.9897,
      "step": 320
    },
    {
      "epoch": 0.20733652312599682,
      "grad_norm": 1.4310753345489502,
      "learning_rate": 0.0002896136121738793,
      "loss": 0.9855,
      "step": 325
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 2.6854515075683594,
      "learning_rate": 0.0002889939594452323,
      "loss": 0.9701,
      "step": 330
    },
    {
      "epoch": 0.21371610845295055,
      "grad_norm": 1.3763470649719238,
      "learning_rate": 0.00028835705656309583,
      "loss": 0.9812,
      "step": 335
    },
    {
      "epoch": 0.21690590111642744,
      "grad_norm": 1.8561792373657227,
      "learning_rate": 0.0002877029825717142,
      "loss": 0.9943,
      "step": 340
    },
    {
      "epoch": 0.22009569377990432,
      "grad_norm": 3.642995595932007,
      "learning_rate": 0.0002870318186463901,
      "loss": 0.9637,
      "step": 345
    },
    {
      "epoch": 0.22328548644338117,
      "grad_norm": 4.639859199523926,
      "learning_rate": 0.0002863436480834105,
      "loss": 0.9998,
      "step": 350
    },
    {
      "epoch": 0.22647527910685805,
      "grad_norm": 1.1026989221572876,
      "learning_rate": 0.00028563855628970886,
      "loss": 0.9777,
      "step": 355
    },
    {
      "epoch": 0.22966507177033493,
      "grad_norm": 1.1374722719192505,
      "learning_rate": 0.0002849166307722653,
      "loss": 1.0051,
      "step": 360
    },
    {
      "epoch": 0.23285486443381181,
      "grad_norm": 1.255344033241272,
      "learning_rate": 0.00028417796112724684,
      "loss": 1.009,
      "step": 365
    },
    {
      "epoch": 0.23604465709728867,
      "grad_norm": 1.4702554941177368,
      "learning_rate": 0.0002834226390288873,
      "loss": 0.9616,
      "step": 370
    },
    {
      "epoch": 0.23923444976076555,
      "grad_norm": 1.4822920560836792,
      "learning_rate": 0.0002826507582181103,
      "loss": 0.966,
      "step": 375
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 6.145591735839844,
      "learning_rate": 0.00028186241449089524,
      "loss": 0.9819,
      "step": 380
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 1.982974886894226,
      "learning_rate": 0.000281057705686388,
      "loss": 0.9766,
      "step": 385
    },
    {
      "epoch": 0.24880382775119617,
      "grad_norm": 1.2046759128570557,
      "learning_rate": 0.0002802367316747589,
      "loss": 0.9704,
      "step": 390
    },
    {
      "epoch": 0.25199362041467305,
      "grad_norm": 1.5054329633712769,
      "learning_rate": 0.0002793995943448078,
      "loss": 0.9484,
      "step": 395
    },
    {
      "epoch": 0.2551834130781499,
      "grad_norm": 7.931117534637451,
      "learning_rate": 0.00027854639759131893,
      "loss": 0.9548,
      "step": 400
    },
    {
      "epoch": 0.2583732057416268,
      "grad_norm": 1.8060181140899658,
      "learning_rate": 0.00027767724730216696,
      "loss": 0.9946,
      "step": 405
    },
    {
      "epoch": 0.26156299840510366,
      "grad_norm": 2.3200082778930664,
      "learning_rate": 0.0002767922513451754,
      "loss": 0.9888,
      "step": 410
    },
    {
      "epoch": 0.2647527910685805,
      "grad_norm": 2.2360453605651855,
      "learning_rate": 0.00027589151955472965,
      "loss": 0.9588,
      "step": 415
    },
    {
      "epoch": 0.2679425837320574,
      "grad_norm": 1.594473123550415,
      "learning_rate": 0.00027497516371814543,
      "loss": 0.9547,
      "step": 420
    },
    {
      "epoch": 0.2711323763955343,
      "grad_norm": 3.532134532928467,
      "learning_rate": 0.00027404329756179537,
      "loss": 0.9589,
      "step": 425
    },
    {
      "epoch": 0.2743221690590112,
      "grad_norm": 2.1840810775756836,
      "learning_rate": 0.0002730960367369949,
      "loss": 1.017,
      "step": 430
    },
    {
      "epoch": 0.27751196172248804,
      "grad_norm": 1.9814718961715698,
      "learning_rate": 0.00027213349880564873,
      "loss": 0.9901,
      "step": 435
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 2.3927841186523438,
      "learning_rate": 0.0002711558032256607,
      "loss": 0.9715,
      "step": 440
    },
    {
      "epoch": 0.2838915470494418,
      "grad_norm": 1.501244306564331,
      "learning_rate": 0.0002701630713361085,
      "loss": 0.9621,
      "step": 445
    },
    {
      "epoch": 0.28708133971291866,
      "grad_norm": 1.6648037433624268,
      "learning_rate": 0.00026915542634218403,
      "loss": 0.9676,
      "step": 450
    },
    {
      "epoch": 0.2902711323763955,
      "grad_norm": 2.717752695083618,
      "learning_rate": 0.00026813299329990335,
      "loss": 0.9837,
      "step": 455
    },
    {
      "epoch": 0.2934609250398724,
      "grad_norm": 1.7805887460708618,
      "learning_rate": 0.0002670958991005859,
      "loss": 0.9635,
      "step": 460
    },
    {
      "epoch": 0.2966507177033493,
      "grad_norm": 2.2134859561920166,
      "learning_rate": 0.0002660442724551065,
      "loss": 0.9566,
      "step": 465
    },
    {
      "epoch": 0.29984051036682613,
      "grad_norm": 1.2682667970657349,
      "learning_rate": 0.00026497824387792146,
      "loss": 0.963,
      "step": 470
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 1.2729476690292358,
      "learning_rate": 0.00026389794567087085,
      "loss": 0.964,
      "step": 475
    },
    {
      "epoch": 0.3062200956937799,
      "grad_norm": 1.4577951431274414,
      "learning_rate": 0.0002628035119067586,
      "loss": 0.9487,
      "step": 480
    },
    {
      "epoch": 0.3094098883572568,
      "grad_norm": 1.637868881225586,
      "learning_rate": 0.0002616950784127135,
      "loss": 0.9453,
      "step": 485
    },
    {
      "epoch": 0.31259968102073366,
      "grad_norm": 1.3225361108779907,
      "learning_rate": 0.00026057278275333165,
      "loss": 0.9814,
      "step": 490
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 1.1870254278182983,
      "learning_rate": 0.00025943676421360395,
      "loss": 0.9555,
      "step": 495
    },
    {
      "epoch": 0.3189792663476874,
      "grad_norm": 2.6951119899749756,
      "learning_rate": 0.00025828716378163,
      "loss": 0.9657,
      "step": 500
    },
    {
      "epoch": 0.32216905901116427,
      "grad_norm": 2.149862766265869,
      "learning_rate": 0.00025712412413112006,
      "loss": 0.9697,
      "step": 505
    },
    {
      "epoch": 0.3253588516746411,
      "grad_norm": 1.2473626136779785,
      "learning_rate": 0.00025594778960368844,
      "loss": 0.9743,
      "step": 510
    },
    {
      "epoch": 0.32854864433811803,
      "grad_norm": 1.7699605226516724,
      "learning_rate": 0.0002547583061909396,
      "loss": 0.9564,
      "step": 515
    },
    {
      "epoch": 0.3317384370015949,
      "grad_norm": 2.645415782928467,
      "learning_rate": 0.00025355582151634956,
      "loss": 0.9812,
      "step": 520
    },
    {
      "epoch": 0.3349282296650718,
      "grad_norm": 1.1734089851379395,
      "learning_rate": 0.00025234048481694477,
      "loss": 0.9463,
      "step": 525
    },
    {
      "epoch": 0.33811802232854865,
      "grad_norm": 1.7658518552780151,
      "learning_rate": 0.0002511124469247809,
      "loss": 0.9547,
      "step": 530
    },
    {
      "epoch": 0.3413078149920255,
      "grad_norm": 1.289113163948059,
      "learning_rate": 0.00024987186024822295,
      "loss": 0.9426,
      "step": 535
    },
    {
      "epoch": 0.3444976076555024,
      "grad_norm": 10.93489933013916,
      "learning_rate": 0.0002486188787530309,
      "loss": 0.9476,
      "step": 540
    },
    {
      "epoch": 0.34768740031897927,
      "grad_norm": 1.6490458250045776,
      "learning_rate": 0.00024735365794325117,
      "loss": 0.976,
      "step": 545
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 1.1837722063064575,
      "learning_rate": 0.0002460763548419172,
      "loss": 0.9391,
      "step": 550
    },
    {
      "epoch": 0.35406698564593303,
      "grad_norm": 1.1305694580078125,
      "learning_rate": 0.0002447871279715624,
      "loss": 0.9555,
      "step": 555
    },
    {
      "epoch": 0.3572567783094099,
      "grad_norm": 1.6349717378616333,
      "learning_rate": 0.00024348613733454565,
      "loss": 0.9412,
      "step": 560
    },
    {
      "epoch": 0.36044657097288674,
      "grad_norm": 2.098814010620117,
      "learning_rate": 0.00024217354439319427,
      "loss": 0.9365,
      "step": 565
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 1.4904630184173584,
      "learning_rate": 0.00024084951204976528,
      "loss": 0.9243,
      "step": 570
    },
    {
      "epoch": 0.3668261562998405,
      "grad_norm": 2.3611807823181152,
      "learning_rate": 0.0002395142046262281,
      "loss": 0.9613,
      "step": 575
    },
    {
      "epoch": 0.3700159489633174,
      "grad_norm": 2.1644859313964844,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.942,
      "step": 580
    },
    {
      "epoch": 0.37320574162679426,
      "grad_norm": 1.9585081338882446,
      "learning_rate": 0.0002368104288027336,
      "loss": 0.9402,
      "step": 585
    },
    {
      "epoch": 0.3763955342902711,
      "grad_norm": 1.793800950050354,
      "learning_rate": 0.0002354422959608692,
      "loss": 0.9421,
      "step": 590
    },
    {
      "epoch": 0.379585326953748,
      "grad_norm": 2.8529624938964844,
      "learning_rate": 0.00023406355911343717,
      "loss": 0.9688,
      "step": 595
    },
    {
      "epoch": 0.3827751196172249,
      "grad_norm": 1.6029831171035767,
      "learning_rate": 0.00023267438937163077,
      "loss": 0.9164,
      "step": 600
    },
    {
      "epoch": 0.38596491228070173,
      "grad_norm": 1.7395401000976562,
      "learning_rate": 0.00023127495914144051,
      "loss": 0.9409,
      "step": 605
    },
    {
      "epoch": 0.38915470494417864,
      "grad_norm": 1.7709709405899048,
      "learning_rate": 0.00022986544210225774,
      "loss": 0.9353,
      "step": 610
    },
    {
      "epoch": 0.3923444976076555,
      "grad_norm": 1.1406283378601074,
      "learning_rate": 0.00022844601318531955,
      "loss": 0.9163,
      "step": 615
    },
    {
      "epoch": 0.39553429027113235,
      "grad_norm": 1.617177963256836,
      "learning_rate": 0.00022701684855199857,
      "loss": 0.961,
      "step": 620
    },
    {
      "epoch": 0.39872408293460926,
      "grad_norm": 1.387049674987793,
      "learning_rate": 0.00022557812557194,
      "loss": 0.9273,
      "step": 625
    },
    {
      "epoch": 0.4019138755980861,
      "grad_norm": 1.331063151359558,
      "learning_rate": 0.00022413002280104915,
      "loss": 0.9132,
      "step": 630
    },
    {
      "epoch": 0.405103668261563,
      "grad_norm": 1.5018112659454346,
      "learning_rate": 0.00022267271995933074,
      "loss": 0.947,
      "step": 635
    },
    {
      "epoch": 0.4082934609250399,
      "grad_norm": 1.384469747543335,
      "learning_rate": 0.00022120639790858482,
      "loss": 0.9328,
      "step": 640
    },
    {
      "epoch": 0.41148325358851673,
      "grad_norm": 1.715080738067627,
      "learning_rate": 0.00021973123862996044,
      "loss": 0.9463,
      "step": 645
    },
    {
      "epoch": 0.41467304625199364,
      "grad_norm": 1.2330074310302734,
      "learning_rate": 0.00021824742520137026,
      "loss": 0.9391,
      "step": 650
    },
    {
      "epoch": 0.4178628389154705,
      "grad_norm": 1.498789668083191,
      "learning_rate": 0.00021675514177476945,
      "loss": 0.93,
      "step": 655
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 1.287414789199829,
      "learning_rate": 0.0002152545735533012,
      "loss": 0.9554,
      "step": 660
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 2.2374627590179443,
      "learning_rate": 0.00021374590676831136,
      "loss": 0.9394,
      "step": 665
    },
    {
      "epoch": 0.4274322169059011,
      "grad_norm": 1.494278073310852,
      "learning_rate": 0.00021222932865623605,
      "loss": 0.9463,
      "step": 670
    },
    {
      "epoch": 0.430622009569378,
      "grad_norm": 1.40542733669281,
      "learning_rate": 0.00021070502743536414,
      "loss": 0.9088,
      "step": 675
    },
    {
      "epoch": 0.43381180223285487,
      "grad_norm": 1.9738633632659912,
      "learning_rate": 0.00020917319228247805,
      "loss": 0.9089,
      "step": 680
    },
    {
      "epoch": 0.4370015948963317,
      "grad_norm": 2.0033769607543945,
      "learning_rate": 0.00020763401330937555,
      "loss": 0.9182,
      "step": 685
    },
    {
      "epoch": 0.44019138755980863,
      "grad_norm": 1.3576220273971558,
      "learning_rate": 0.00020608768153927546,
      "loss": 0.9269,
      "step": 690
    },
    {
      "epoch": 0.4433811802232855,
      "grad_norm": 1.2206989526748657,
      "learning_rate": 0.00020453438888311042,
      "loss": 0.9185,
      "step": 695
    },
    {
      "epoch": 0.44657097288676234,
      "grad_norm": 1.5050541162490845,
      "learning_rate": 0.00020297432811570916,
      "loss": 0.9287,
      "step": 700
    },
    {
      "epoch": 0.44976076555023925,
      "grad_norm": 1.3409852981567383,
      "learning_rate": 0.00020140769285187187,
      "loss": 0.9089,
      "step": 705
    },
    {
      "epoch": 0.4529505582137161,
      "grad_norm": 3.004441738128662,
      "learning_rate": 0.00019983467752234132,
      "loss": 0.8978,
      "step": 710
    },
    {
      "epoch": 0.45614035087719296,
      "grad_norm": 1.6164394617080688,
      "learning_rate": 0.0001982554773496723,
      "loss": 0.9464,
      "step": 715
    },
    {
      "epoch": 0.45933014354066987,
      "grad_norm": 1.1452794075012207,
      "learning_rate": 0.00019667028832400345,
      "loss": 0.8884,
      "step": 720
    },
    {
      "epoch": 0.4625199362041467,
      "grad_norm": 1.80891752243042,
      "learning_rate": 0.00019507930717873313,
      "loss": 0.9167,
      "step": 725
    },
    {
      "epoch": 0.46570972886762363,
      "grad_norm": 1.9527322053909302,
      "learning_rate": 0.00019348273136610364,
      "loss": 0.9182,
      "step": 730
    },
    {
      "epoch": 0.4688995215311005,
      "grad_norm": 1.8810184001922607,
      "learning_rate": 0.00019188075903269587,
      "loss": 0.9269,
      "step": 735
    },
    {
      "epoch": 0.47208931419457734,
      "grad_norm": 1.5535273551940918,
      "learning_rate": 0.00019027358899483776,
      "loss": 0.9048,
      "step": 740
    },
    {
      "epoch": 0.47527910685805425,
      "grad_norm": 1.7040493488311768,
      "learning_rate": 0.00018866142071393013,
      "loss": 0.9181,
      "step": 745
    },
    {
      "epoch": 0.4784688995215311,
      "grad_norm": 1.7220163345336914,
      "learning_rate": 0.00018704445427169156,
      "loss": 0.9242,
      "step": 750
    },
    {
      "epoch": 0.48165869218500795,
      "grad_norm": 1.5103449821472168,
      "learning_rate": 0.00018542289034532733,
      "loss": 0.9198,
      "step": 755
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 1.3625946044921875,
      "learning_rate": 0.00018379693018262349,
      "loss": 0.9253,
      "step": 760
    },
    {
      "epoch": 0.4880382775119617,
      "grad_norm": 1.1106137037277222,
      "learning_rate": 0.00018216677557697083,
      "loss": 0.9177,
      "step": 765
    },
    {
      "epoch": 0.49122807017543857,
      "grad_norm": 1.217457890510559,
      "learning_rate": 0.00018053262884232078,
      "loss": 0.9015,
      "step": 770
    },
    {
      "epoch": 0.4944178628389155,
      "grad_norm": 1.1275889873504639,
      "learning_rate": 0.0001788946927880768,
      "loss": 0.9088,
      "step": 775
    },
    {
      "epoch": 0.49760765550239233,
      "grad_norm": 1.321915864944458,
      "learning_rate": 0.00017725317069392418,
      "loss": 0.8997,
      "step": 780
    },
    {
      "epoch": 0.5007974481658692,
      "grad_norm": 1.509143590927124,
      "learning_rate": 0.00017560826628460182,
      "loss": 0.9071,
      "step": 785
    },
    {
      "epoch": 0.5039872408293461,
      "grad_norm": 2.1907105445861816,
      "learning_rate": 0.00017396018370461808,
      "loss": 0.924,
      "step": 790
    },
    {
      "epoch": 0.507177033492823,
      "grad_norm": 3.8603427410125732,
      "learning_rate": 0.00017230912749291547,
      "loss": 0.9352,
      "step": 795
    },
    {
      "epoch": 0.5103668261562998,
      "grad_norm": 1.6749746799468994,
      "learning_rate": 0.00017065530255748557,
      "loss": 0.9218,
      "step": 800
    },
    {
      "epoch": 0.5135566188197768,
      "grad_norm": 1.847925066947937,
      "learning_rate": 0.00016899891414993854,
      "loss": 0.9171,
      "step": 805
    },
    {
      "epoch": 0.5167464114832536,
      "grad_norm": 1.3573256731033325,
      "learning_rate": 0.00016734016784002994,
      "loss": 0.9178,
      "step": 810
    },
    {
      "epoch": 0.5199362041467305,
      "grad_norm": 1.2376315593719482,
      "learning_rate": 0.000165679269490148,
      "loss": 0.8975,
      "step": 815
    },
    {
      "epoch": 0.5231259968102073,
      "grad_norm": 1.7870066165924072,
      "learning_rate": 0.0001640164252297648,
      "loss": 0.9074,
      "step": 820
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 1.1662150621414185,
      "learning_rate": 0.00016235184142985367,
      "loss": 0.894,
      "step": 825
    },
    {
      "epoch": 0.529505582137161,
      "grad_norm": 1.8673336505889893,
      "learning_rate": 0.00016068572467727762,
      "loss": 0.9195,
      "step": 830
    },
    {
      "epoch": 0.532695374800638,
      "grad_norm": 1.196296215057373,
      "learning_rate": 0.00015901828174915005,
      "loss": 0.9135,
      "step": 835
    },
    {
      "epoch": 0.5358851674641149,
      "grad_norm": 2.296478509902954,
      "learning_rate": 0.00015734971958717228,
      "loss": 0.9105,
      "step": 840
    },
    {
      "epoch": 0.5390749601275917,
      "grad_norm": 1.0914058685302734,
      "learning_rate": 0.00015568024527195067,
      "loss": 0.9211,
      "step": 845
    },
    {
      "epoch": 0.5422647527910686,
      "grad_norm": 1.104638934135437,
      "learning_rate": 0.0001540100659972963,
      "loss": 0.8852,
      "step": 850
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 1.2603851556777954,
      "learning_rate": 0.000152339389044511,
      "loss": 0.9166,
      "step": 855
    },
    {
      "epoch": 0.5486443381180224,
      "grad_norm": 1.6585578918457031,
      "learning_rate": 0.00015066842175666186,
      "loss": 0.9094,
      "step": 860
    },
    {
      "epoch": 0.5518341307814992,
      "grad_norm": 1.1676634550094604,
      "learning_rate": 0.0001489973715128487,
      "loss": 0.8908,
      "step": 865
    },
    {
      "epoch": 0.5550239234449761,
      "grad_norm": 3.5736377239227295,
      "learning_rate": 0.00014732644570246675,
      "loss": 0.8909,
      "step": 870
    },
    {
      "epoch": 0.5582137161084529,
      "grad_norm": 1.4160521030426025,
      "learning_rate": 0.00014565585169946824,
      "loss": 0.9092,
      "step": 875
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 1.3239599466323853,
      "learning_rate": 0.0001439857968366256,
      "loss": 0.9054,
      "step": 880
    },
    {
      "epoch": 0.5645933014354066,
      "grad_norm": 1.075803518295288,
      "learning_rate": 0.00014231648837980022,
      "loss": 0.8836,
      "step": 885
    },
    {
      "epoch": 0.5677830940988836,
      "grad_norm": 1.0712918043136597,
      "learning_rate": 0.00014064813350221894,
      "loss": 0.9306,
      "step": 890
    },
    {
      "epoch": 0.5709728867623605,
      "grad_norm": 1.9769309759140015,
      "learning_rate": 0.00013898093925876267,
      "loss": 0.8789,
      "step": 895
    },
    {
      "epoch": 0.5741626794258373,
      "grad_norm": 3.4712631702423096,
      "learning_rate": 0.00013731511256026913,
      "loss": 0.8883,
      "step": 900
    },
    {
      "epoch": 0.5773524720893142,
      "grad_norm": 1.1367384195327759,
      "learning_rate": 0.00013565086014785406,
      "loss": 0.908,
      "step": 905
    },
    {
      "epoch": 0.580542264752791,
      "grad_norm": 2.3845860958099365,
      "learning_rate": 0.00013398838856725257,
      "loss": 0.8968,
      "step": 910
    },
    {
      "epoch": 0.583732057416268,
      "grad_norm": 1.257691502571106,
      "learning_rate": 0.00013232790414318608,
      "loss": 0.8906,
      "step": 915
    },
    {
      "epoch": 0.5869218500797448,
      "grad_norm": 1.0229823589324951,
      "learning_rate": 0.0001306696129537553,
      "loss": 0.9062,
      "step": 920
    },
    {
      "epoch": 0.5901116427432217,
      "grad_norm": 1.5208640098571777,
      "learning_rate": 0.00012901372080486472,
      "loss": 0.8854,
      "step": 925
    },
    {
      "epoch": 0.5933014354066986,
      "grad_norm": 1.2354867458343506,
      "learning_rate": 0.00012736043320468073,
      "loss": 0.8775,
      "step": 930
    },
    {
      "epoch": 0.5964912280701754,
      "grad_norm": 1.5079673528671265,
      "learning_rate": 0.0001257099553381262,
      "loss": 0.8893,
      "step": 935
    },
    {
      "epoch": 0.5996810207336523,
      "grad_norm": 0.9733923673629761,
      "learning_rate": 0.00012406249204141603,
      "loss": 0.89,
      "step": 940
    },
    {
      "epoch": 0.6028708133971292,
      "grad_norm": 1.3117018938064575,
      "learning_rate": 0.000122418247776635,
      "loss": 0.8945,
      "step": 945
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.251587152481079,
      "learning_rate": 0.00012077742660636299,
      "loss": 0.8909,
      "step": 950
    },
    {
      "epoch": 0.6092503987240829,
      "grad_norm": 1.1672098636627197,
      "learning_rate": 0.00011914023216834904,
      "loss": 0.8688,
      "step": 955
    },
    {
      "epoch": 0.6124401913875598,
      "grad_norm": 1.3299888372421265,
      "learning_rate": 0.0001175068676502386,
      "loss": 0.8639,
      "step": 960
    },
    {
      "epoch": 0.6156299840510366,
      "grad_norm": 1.0402354001998901,
      "learning_rate": 0.00011587753576435634,
      "loss": 0.8688,
      "step": 965
    },
    {
      "epoch": 0.6188197767145136,
      "grad_norm": 1.5155375003814697,
      "learning_rate": 0.00011425243872254835,
      "loss": 0.8738,
      "step": 970
    },
    {
      "epoch": 0.6220095693779905,
      "grad_norm": 1.1635366678237915,
      "learning_rate": 0.00011263177821108573,
      "loss": 0.8845,
      "step": 975
    },
    {
      "epoch": 0.6251993620414673,
      "grad_norm": 1.1347579956054688,
      "learning_rate": 0.00011101575536563433,
      "loss": 0.8801,
      "step": 980
    },
    {
      "epoch": 0.6283891547049442,
      "grad_norm": 1.443695306777954,
      "learning_rate": 0.00010940457074629217,
      "loss": 0.8773,
      "step": 985
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 1.2533496618270874,
      "learning_rate": 0.00010779842431269843,
      "loss": 0.8851,
      "step": 990
    },
    {
      "epoch": 0.6347687400318979,
      "grad_norm": 1.0504379272460938,
      "learning_rate": 0.0001061975153992172,
      "loss": 0.869,
      "step": 995
    },
    {
      "epoch": 0.6379585326953748,
      "grad_norm": 1.9185314178466797,
      "learning_rate": 0.00010460204269019829,
      "loss": 0.8623,
      "step": 1000
    },
    {
      "epoch": 0.6411483253588517,
      "grad_norm": 1.520933747291565,
      "learning_rate": 0.0001030122041953196,
      "loss": 0.8854,
      "step": 1005
    },
    {
      "epoch": 0.6443381180223285,
      "grad_norm": 1.1053557395935059,
      "learning_rate": 0.0001014281972250121,
      "loss": 0.881,
      "step": 1010
    },
    {
      "epoch": 0.6475279106858054,
      "grad_norm": 1.258350133895874,
      "learning_rate": 9.985021836597273e-05,
      "loss": 0.8561,
      "step": 1015
    },
    {
      "epoch": 0.6507177033492823,
      "grad_norm": 1.004818081855774,
      "learning_rate": 9.827846345676614e-05,
      "loss": 0.8673,
      "step": 1020
    },
    {
      "epoch": 0.6539074960127592,
      "grad_norm": 1.3916617631912231,
      "learning_rate": 9.671312756351998e-05,
      "loss": 0.8673,
      "step": 1025
    },
    {
      "epoch": 0.6570972886762361,
      "grad_norm": 1.0740200281143188,
      "learning_rate": 9.515440495571569e-05,
      "loss": 0.8678,
      "step": 1030
    },
    {
      "epoch": 0.6602870813397129,
      "grad_norm": 1.025354266166687,
      "learning_rate": 9.360248908207813e-05,
      "loss": 0.8611,
      "step": 1035
    },
    {
      "epoch": 0.6634768740031898,
      "grad_norm": 1.2619115114212036,
      "learning_rate": 9.205757254656755e-05,
      "loss": 0.8485,
      "step": 1040
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.9425147771835327,
      "learning_rate": 9.05198470844756e-05,
      "loss": 0.8534,
      "step": 1045
    },
    {
      "epoch": 0.6698564593301436,
      "grad_norm": 1.214699149131775,
      "learning_rate": 8.898950353862998e-05,
      "loss": 0.8739,
      "step": 1050
    },
    {
      "epoch": 0.6730462519936204,
      "grad_norm": 1.2433393001556396,
      "learning_rate": 8.746673183570923e-05,
      "loss": 0.8703,
      "step": 1055
    },
    {
      "epoch": 0.6762360446570973,
      "grad_norm": 1.4109057188034058,
      "learning_rate": 8.595172096267157e-05,
      "loss": 0.9019,
      "step": 1060
    },
    {
      "epoch": 0.6794258373205742,
      "grad_norm": 1.2065266370773315,
      "learning_rate": 8.444465894330024e-05,
      "loss": 0.8465,
      "step": 1065
    },
    {
      "epoch": 0.682615629984051,
      "grad_norm": 0.994489848613739,
      "learning_rate": 8.294573281486828e-05,
      "loss": 0.8654,
      "step": 1070
    },
    {
      "epoch": 0.6858054226475279,
      "grad_norm": 1.036932110786438,
      "learning_rate": 8.145512860492596e-05,
      "loss": 0.8509,
      "step": 1075
    },
    {
      "epoch": 0.6889952153110048,
      "grad_norm": 1.1829875707626343,
      "learning_rate": 7.997303130821362e-05,
      "loss": 0.8726,
      "step": 1080
    },
    {
      "epoch": 0.6921850079744817,
      "grad_norm": 1.0227490663528442,
      "learning_rate": 7.849962486370206e-05,
      "loss": 0.8623,
      "step": 1085
    },
    {
      "epoch": 0.6953748006379585,
      "grad_norm": 1.0316836833953857,
      "learning_rate": 7.703509213176451e-05,
      "loss": 0.8762,
      "step": 1090
    },
    {
      "epoch": 0.6985645933014354,
      "grad_norm": 1.1211485862731934,
      "learning_rate": 7.557961487148272e-05,
      "loss": 0.8824,
      "step": 1095
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 1.0168806314468384,
      "learning_rate": 7.413337371808884e-05,
      "loss": 0.8582,
      "step": 1100
    },
    {
      "epoch": 0.7049441786283892,
      "grad_norm": 1.244272232055664,
      "learning_rate": 7.269654816054756e-05,
      "loss": 0.8563,
      "step": 1105
    },
    {
      "epoch": 0.7081339712918661,
      "grad_norm": 1.1271004676818848,
      "learning_rate": 7.126931651928012e-05,
      "loss": 0.8538,
      "step": 1110
    },
    {
      "epoch": 0.7113237639553429,
      "grad_norm": 1.1314244270324707,
      "learning_rate": 6.985185592403367e-05,
      "loss": 0.8716,
      "step": 1115
    },
    {
      "epoch": 0.7145135566188198,
      "grad_norm": 1.212408423423767,
      "learning_rate": 6.844434229189787e-05,
      "loss": 0.8624,
      "step": 1120
    },
    {
      "epoch": 0.7177033492822966,
      "grad_norm": 1.4100135564804077,
      "learning_rate": 6.704695030547252e-05,
      "loss": 0.8428,
      "step": 1125
    },
    {
      "epoch": 0.7208931419457735,
      "grad_norm": 1.6255112886428833,
      "learning_rate": 6.56598533911881e-05,
      "loss": 0.8553,
      "step": 1130
    },
    {
      "epoch": 0.7240829346092504,
      "grad_norm": 1.0644069910049438,
      "learning_rate": 6.428322369778254e-05,
      "loss": 0.8703,
      "step": 1135
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.9541735053062439,
      "learning_rate": 6.291723207493577e-05,
      "loss": 0.8334,
      "step": 1140
    },
    {
      "epoch": 0.7304625199362041,
      "grad_norm": 1.1123586893081665,
      "learning_rate": 6.15620480520666e-05,
      "loss": 0.8521,
      "step": 1145
    },
    {
      "epoch": 0.733652312599681,
      "grad_norm": 1.3636609315872192,
      "learning_rate": 6.0217839817292765e-05,
      "loss": 0.84,
      "step": 1150
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 1.311625599861145,
      "learning_rate": 5.888477419655733e-05,
      "loss": 0.8592,
      "step": 1155
    },
    {
      "epoch": 0.7400318979266348,
      "grad_norm": 1.0517165660858154,
      "learning_rate": 5.7563016632924555e-05,
      "loss": 0.8403,
      "step": 1160
    },
    {
      "epoch": 0.7432216905901117,
      "grad_norm": 1.1106277704238892,
      "learning_rate": 5.625273116604728e-05,
      "loss": 0.8828,
      "step": 1165
    },
    {
      "epoch": 0.7464114832535885,
      "grad_norm": 1.4360631704330444,
      "learning_rate": 5.495408041180829e-05,
      "loss": 0.8732,
      "step": 1170
    },
    {
      "epoch": 0.7496012759170654,
      "grad_norm": 1.226717233657837,
      "learning_rate": 5.3667225542138507e-05,
      "loss": 0.8268,
      "step": 1175
    },
    {
      "epoch": 0.7527910685805422,
      "grad_norm": 1.013719916343689,
      "learning_rate": 5.239232626501464e-05,
      "loss": 0.8775,
      "step": 1180
    },
    {
      "epoch": 0.7559808612440191,
      "grad_norm": 1.9293391704559326,
      "learning_rate": 5.1129540804637906e-05,
      "loss": 0.8578,
      "step": 1185
    },
    {
      "epoch": 0.759170653907496,
      "grad_norm": 1.105729103088379,
      "learning_rate": 4.9879025881797466e-05,
      "loss": 0.8443,
      "step": 1190
    },
    {
      "epoch": 0.7623604465709729,
      "grad_norm": 1.0743812322616577,
      "learning_rate": 4.8640936694420245e-05,
      "loss": 0.8406,
      "step": 1195
    },
    {
      "epoch": 0.7655502392344498,
      "grad_norm": 1.0439478158950806,
      "learning_rate": 4.7415426898309704e-05,
      "loss": 0.8281,
      "step": 1200
    },
    {
      "epoch": 0.7687400318979266,
      "grad_norm": 1.1847258806228638,
      "learning_rate": 4.62026485880761e-05,
      "loss": 0.845,
      "step": 1205
    },
    {
      "epoch": 0.7719298245614035,
      "grad_norm": 1.4025248289108276,
      "learning_rate": 4.50027522782603e-05,
      "loss": 0.8456,
      "step": 1210
    },
    {
      "epoch": 0.7751196172248804,
      "grad_norm": 1.398414134979248,
      "learning_rate": 4.3815886884654136e-05,
      "loss": 0.8367,
      "step": 1215
    },
    {
      "epoch": 0.7783094098883573,
      "grad_norm": 1.4555211067199707,
      "learning_rate": 4.264219970581854e-05,
      "loss": 0.8594,
      "step": 1220
    },
    {
      "epoch": 0.7814992025518341,
      "grad_norm": 1.2245261669158936,
      "learning_rate": 4.148183640480293e-05,
      "loss": 0.8622,
      "step": 1225
    },
    {
      "epoch": 0.784688995215311,
      "grad_norm": 1.0004338026046753,
      "learning_rate": 4.0334940991067276e-05,
      "loss": 0.8619,
      "step": 1230
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 0.9635859131813049,
      "learning_rate": 3.920165580260973e-05,
      "loss": 0.8596,
      "step": 1235
    },
    {
      "epoch": 0.7910685805422647,
      "grad_norm": 1.0776612758636475,
      "learning_rate": 3.808212148830095e-05,
      "loss": 0.839,
      "step": 1240
    },
    {
      "epoch": 0.7942583732057417,
      "grad_norm": 1.1850311756134033,
      "learning_rate": 3.697647699042918e-05,
      "loss": 0.8347,
      "step": 1245
    },
    {
      "epoch": 0.7974481658692185,
      "grad_norm": 1.168291449546814,
      "learning_rate": 3.5884859527455995e-05,
      "loss": 0.8513,
      "step": 1250
    },
    {
      "epoch": 0.8006379585326954,
      "grad_norm": 1.0602375268936157,
      "learning_rate": 3.48074045769868e-05,
      "loss": 0.8521,
      "step": 1255
    },
    {
      "epoch": 0.8038277511961722,
      "grad_norm": 1.074064016342163,
      "learning_rate": 3.3744245858956967e-05,
      "loss": 0.877,
      "step": 1260
    },
    {
      "epoch": 0.8070175438596491,
      "grad_norm": 1.0063201189041138,
      "learning_rate": 3.2695515319036186e-05,
      "loss": 0.8549,
      "step": 1265
    },
    {
      "epoch": 0.810207336523126,
      "grad_norm": 0.9187350273132324,
      "learning_rate": 3.1661343112253304e-05,
      "loss": 0.8439,
      "step": 1270
    },
    {
      "epoch": 0.8133971291866029,
      "grad_norm": 1.0719003677368164,
      "learning_rate": 3.064185758684265e-05,
      "loss": 0.829,
      "step": 1275
    },
    {
      "epoch": 0.8165869218500797,
      "grad_norm": 0.9533995985984802,
      "learning_rate": 2.96371852683157e-05,
      "loss": 0.8492,
      "step": 1280
    },
    {
      "epoch": 0.8197767145135566,
      "grad_norm": 1.3275169134140015,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 0.8587,
      "step": 1285
    },
    {
      "epoch": 0.8229665071770335,
      "grad_norm": 1.1175739765167236,
      "learning_rate": 2.7672777146354246e-05,
      "loss": 0.8505,
      "step": 1290
    },
    {
      "epoch": 0.8261562998405104,
      "grad_norm": 1.0937777757644653,
      "learning_rate": 2.6713285140144802e-05,
      "loss": 0.8624,
      "step": 1295
    },
    {
      "epoch": 0.8293460925039873,
      "grad_norm": 1.5751278400421143,
      "learning_rate": 2.5769093905012333e-05,
      "loss": 0.8406,
      "step": 1300
    },
    {
      "epoch": 0.8325358851674641,
      "grad_norm": 0.9947794079780579,
      "learning_rate": 2.4840320621903253e-05,
      "loss": 0.8374,
      "step": 1305
    },
    {
      "epoch": 0.835725677830941,
      "grad_norm": 1.0281869173049927,
      "learning_rate": 2.392708055828495e-05,
      "loss": 0.8417,
      "step": 1310
    },
    {
      "epoch": 0.8389154704944178,
      "grad_norm": 1.0307683944702148,
      "learning_rate": 2.3029487053840295e-05,
      "loss": 0.8379,
      "step": 1315
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.9527477025985718,
      "learning_rate": 2.214765150640108e-05,
      "loss": 0.8518,
      "step": 1320
    },
    {
      "epoch": 0.8452950558213717,
      "grad_norm": 1.0322529077529907,
      "learning_rate": 2.1281683358122996e-05,
      "loss": 0.8398,
      "step": 1325
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 0.9636293053627014,
      "learning_rate": 2.043169008190289e-05,
      "loss": 0.859,
      "step": 1330
    },
    {
      "epoch": 0.8516746411483254,
      "grad_norm": 0.946626603603363,
      "learning_rate": 1.9597777168040872e-05,
      "loss": 0.8586,
      "step": 1335
    },
    {
      "epoch": 0.8548644338118022,
      "grad_norm": 0.9317569136619568,
      "learning_rate": 1.8780048111147776e-05,
      "loss": 0.8587,
      "step": 1340
    },
    {
      "epoch": 0.8580542264752791,
      "grad_norm": 1.0601786375045776,
      "learning_rate": 1.797860439730126e-05,
      "loss": 0.8097,
      "step": 1345
    },
    {
      "epoch": 0.861244019138756,
      "grad_norm": 0.9538899064064026,
      "learning_rate": 1.7193545491450183e-05,
      "loss": 0.8533,
      "step": 1350
    },
    {
      "epoch": 0.8644338118022329,
      "grad_norm": 0.9394316077232361,
      "learning_rate": 1.6424968825070567e-05,
      "loss": 0.8271,
      "step": 1355
    },
    {
      "epoch": 0.8676236044657097,
      "grad_norm": 1.0136967897415161,
      "learning_rate": 1.567296978407353e-05,
      "loss": 0.8378,
      "step": 1360
    },
    {
      "epoch": 0.8708133971291866,
      "grad_norm": 0.9502097964286804,
      "learning_rate": 1.4937641696967245e-05,
      "loss": 0.8568,
      "step": 1365
    },
    {
      "epoch": 0.8740031897926634,
      "grad_norm": 0.9635610580444336,
      "learning_rate": 1.4219075823274251e-05,
      "loss": 0.8426,
      "step": 1370
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 0.9333298206329346,
      "learning_rate": 1.3517361342205295e-05,
      "loss": 0.8346,
      "step": 1375
    },
    {
      "epoch": 0.8803827751196173,
      "grad_norm": 0.874499499797821,
      "learning_rate": 1.2832585341591844e-05,
      "loss": 0.8138,
      "step": 1380
    },
    {
      "epoch": 0.8835725677830941,
      "grad_norm": 1.1882647275924683,
      "learning_rate": 1.2164832807077585e-05,
      "loss": 0.8446,
      "step": 1385
    },
    {
      "epoch": 0.886762360446571,
      "grad_norm": 1.0986793041229248,
      "learning_rate": 1.151418661157122e-05,
      "loss": 0.8343,
      "step": 1390
    },
    {
      "epoch": 0.8899521531100478,
      "grad_norm": 0.930297315120697,
      "learning_rate": 1.0880727504961339e-05,
      "loss": 0.8307,
      "step": 1395
    },
    {
      "epoch": 0.8931419457735247,
      "grad_norm": 0.9573615193367004,
      "learning_rate": 1.0264534104094812e-05,
      "loss": 0.8423,
      "step": 1400
    },
    {
      "epoch": 0.8963317384370016,
      "grad_norm": 0.976313591003418,
      "learning_rate": 9.665682883019732e-06,
      "loss": 0.833,
      "step": 1405
    },
    {
      "epoch": 0.8995215311004785,
      "grad_norm": 0.9044297337532043,
      "learning_rate": 9.084248163494511e-06,
      "loss": 0.838,
      "step": 1410
    },
    {
      "epoch": 0.9027113237639554,
      "grad_norm": 0.9953575134277344,
      "learning_rate": 8.520302105764148e-06,
      "loss": 0.8357,
      "step": 1415
    },
    {
      "epoch": 0.9059011164274322,
      "grad_norm": 1.0662360191345215,
      "learning_rate": 7.973914699604367e-06,
      "loss": 0.8355,
      "step": 1420
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.9103978276252747,
      "learning_rate": 7.445153755635569e-06,
      "loss": 0.8451,
      "step": 1425
    },
    {
      "epoch": 0.9122807017543859,
      "grad_norm": 0.9437443614006042,
      "learning_rate": 6.934084896906983e-06,
      "loss": 0.8431,
      "step": 1430
    },
    {
      "epoch": 0.9154704944178629,
      "grad_norm": 1.0551937818527222,
      "learning_rate": 6.440771550752377e-06,
      "loss": 0.8508,
      "step": 1435
    },
    {
      "epoch": 0.9186602870813397,
      "grad_norm": 0.9969338178634644,
      "learning_rate": 5.965274940918274e-06,
      "loss": 0.84,
      "step": 1440
    },
    {
      "epoch": 0.9218500797448166,
      "grad_norm": 0.9045847654342651,
      "learning_rate": 5.507654079965612e-06,
      "loss": 0.8169,
      "step": 1445
    },
    {
      "epoch": 0.9250398724082934,
      "grad_norm": 1.1404656171798706,
      "learning_rate": 5.067965761945869e-06,
      "loss": 0.8529,
      "step": 1450
    },
    {
      "epoch": 0.9282296650717703,
      "grad_norm": 0.9272449016571045,
      "learning_rate": 4.646264555352586e-06,
      "loss": 0.8292,
      "step": 1455
    },
    {
      "epoch": 0.9314194577352473,
      "grad_norm": 1.0107725858688354,
      "learning_rate": 4.242602796348915e-06,
      "loss": 0.8219,
      "step": 1460
    },
    {
      "epoch": 0.9346092503987241,
      "grad_norm": 1.1535266637802124,
      "learning_rate": 3.857030582272369e-06,
      "loss": 0.8254,
      "step": 1465
    },
    {
      "epoch": 0.937799043062201,
      "grad_norm": 1.0003602504730225,
      "learning_rate": 3.489595765417441e-06,
      "loss": 0.7996,
      "step": 1470
    },
    {
      "epoch": 0.9409888357256778,
      "grad_norm": 0.9239038228988647,
      "learning_rate": 3.140343947096624e-06,
      "loss": 0.8079,
      "step": 1475
    },
    {
      "epoch": 0.9441786283891547,
      "grad_norm": 0.9535396695137024,
      "learning_rate": 2.80931847198117e-06,
      "loss": 0.861,
      "step": 1480
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 1.0079741477966309,
      "learning_rate": 2.4965604227215774e-06,
      "loss": 0.844,
      "step": 1485
    },
    {
      "epoch": 0.9505582137161085,
      "grad_norm": 0.9593281149864197,
      "learning_rate": 2.202108614848885e-06,
      "loss": 0.8295,
      "step": 1490
    },
    {
      "epoch": 0.9537480063795853,
      "grad_norm": 0.8958705067634583,
      "learning_rate": 1.925999591957561e-06,
      "loss": 0.8235,
      "step": 1495
    },
    {
      "epoch": 0.9569377990430622,
      "grad_norm": 0.9902259707450867,
      "learning_rate": 1.6682676211700107e-06,
      "loss": 0.8371,
      "step": 1500
    },
    {
      "epoch": 0.960127591706539,
      "grad_norm": 0.906568706035614,
      "learning_rate": 1.4289446888838652e-06,
      "loss": 0.8421,
      "step": 1505
    },
    {
      "epoch": 0.9633173843700159,
      "grad_norm": 1.0222581624984741,
      "learning_rate": 1.2080604968022378e-06,
      "loss": 0.8104,
      "step": 1510
    },
    {
      "epoch": 0.9665071770334929,
      "grad_norm": 0.9215661883354187,
      "learning_rate": 1.0056424582474575e-06,
      "loss": 0.8266,
      "step": 1515
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.9094756245613098,
      "learning_rate": 8.217156947590064e-07,
      "loss": 0.8195,
      "step": 1520
    },
    {
      "epoch": 0.9728867623604466,
      "grad_norm": 0.9477907419204712,
      "learning_rate": 6.563030329755969e-07,
      "loss": 0.807,
      "step": 1525
    },
    {
      "epoch": 0.9760765550239234,
      "grad_norm": 1.0699169635772705,
      "learning_rate": 5.094250018023715e-07,
      "loss": 0.8512,
      "step": 1530
    },
    {
      "epoch": 0.9792663476874003,
      "grad_norm": 0.9320189952850342,
      "learning_rate": 3.8109982986300747e-07,
      "loss": 0.8457,
      "step": 1535
    },
    {
      "epoch": 0.9824561403508771,
      "grad_norm": 0.9529619812965393,
      "learning_rate": 2.7134344323747616e-07,
      "loss": 0.8232,
      "step": 1540
    },
    {
      "epoch": 0.9856459330143541,
      "grad_norm": 0.9721714854240417,
      "learning_rate": 1.801694634854578e-07,
      "loss": 0.8438,
      "step": 1545
    },
    {
      "epoch": 0.988835725677831,
      "grad_norm": 1.0308058261871338,
      "learning_rate": 1.075892059558603e-07,
      "loss": 0.8509,
      "step": 1550
    },
    {
      "epoch": 0.9920255183413078,
      "grad_norm": 0.9877679347991943,
      "learning_rate": 5.3611678382442516e-08,
      "loss": 0.8327,
      "step": 1555
    },
    {
      "epoch": 0.9952153110047847,
      "grad_norm": 0.987597644329071,
      "learning_rate": 1.824357976594193e-08,
      "loss": 0.8036,
      "step": 1560
    },
    {
      "epoch": 0.9984051036682615,
      "grad_norm": 1.006822943687439,
      "learning_rate": 1.4892995426396548e-09,
      "loss": 0.8301,
      "step": 1565
    },
    {
      "epoch": 0.9996810207336523,
      "eval_loss": 2.3456168174743652,
      "eval_runtime": 2.9374,
      "eval_samples_per_second": 3.404,
      "eval_steps_per_second": 0.681,
      "step": 1567
    },
    {
      "epoch": 0.9996810207336523,
      "step": 1567,
      "total_flos": 6.008617478547046e+17,
      "train_loss": 1.5171029353948178,
      "train_runtime": 9750.6774,
      "train_samples_per_second": 1.286,
      "train_steps_per_second": 0.161
    }
  ],
  "logging_steps": 5,
  "max_steps": 1567,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.008617478547046e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}