{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2857142857142857,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.379179924726486,
      "epoch": 0.002857142857142857,
      "grad_norm": 0.248466357588768,
      "learning_rate": 5.142857142857143e-06,
      "loss": 2.1112184524536133,
      "mean_token_accuracy": 0.521992451697588,
      "num_tokens": 490221.0,
      "step": 10
    },
    {
      "entropy": 2.275108999013901,
      "epoch": 0.005714285714285714,
      "grad_norm": 0.16482312977313995,
      "learning_rate": 1.0857142857142858e-05,
      "loss": 2.0270994186401365,
      "mean_token_accuracy": 0.5319361314177513,
      "num_tokens": 980654.0,
      "step": 20
    },
    {
      "entropy": 2.1243143171072005,
      "epoch": 0.008571428571428572,
      "grad_norm": 0.14482936263084412,
      "learning_rate": 1.657142857142857e-05,
      "loss": 1.947333526611328,
      "mean_token_accuracy": 0.5449633926153183,
      "num_tokens": 1471155.0,
      "step": 30
    },
    {
      "entropy": 2.0759591698646545,
      "epoch": 0.011428571428571429,
      "grad_norm": 0.13348551094532013,
      "learning_rate": 2.2285714285714287e-05,
      "loss": 1.8653924942016602,
      "mean_token_accuracy": 0.5575317889451981,
      "num_tokens": 1961803.0,
      "step": 40
    },
    {
      "entropy": 2.002236345410347,
      "epoch": 0.014285714285714285,
      "grad_norm": 0.12573261559009552,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.8171972274780273,
      "mean_token_accuracy": 0.5663816690444946,
      "num_tokens": 2451485.0,
      "step": 50
    },
    {
      "entropy": 1.9370298832654953,
      "epoch": 0.017142857142857144,
      "grad_norm": 0.12988947331905365,
      "learning_rate": 3.3714285714285716e-05,
      "loss": 1.7517566680908203,
      "mean_token_accuracy": 0.5784050762653351,
      "num_tokens": 2940490.0,
      "step": 60
    },
    {
      "entropy": 1.9337659150362014,
      "epoch": 0.02,
      "grad_norm": 0.1357634961605072,
      "learning_rate": 3.942857142857143e-05,
      "loss": 1.7462808609008789,
      "mean_token_accuracy": 0.578274418413639,
      "num_tokens": 3430891.0,
      "step": 70
    },
    {
      "entropy": 1.853649941086769,
      "epoch": 0.022857142857142857,
      "grad_norm": 0.14244548976421356,
      "learning_rate": 4.514285714285714e-05,
      "loss": 1.675507164001465,
      "mean_token_accuracy": 0.5902435079216957,
      "num_tokens": 3921132.0,
      "step": 80
    },
    {
      "entropy": 1.8723271518945694,
      "epoch": 0.025714285714285714,
      "grad_norm": 0.1481512039899826,
      "learning_rate": 5.085714285714286e-05,
      "loss": 1.7015415191650392,
      "mean_token_accuracy": 0.5883241996169091,
      "num_tokens": 4412262.0,
      "step": 90
    },
    {
      "entropy": 1.8528674066066741,
      "epoch": 0.02857142857142857,
      "grad_norm": 0.15897610783576965,
      "learning_rate": 5.6571428571428574e-05,
      "loss": 1.6771810531616211,
      "mean_token_accuracy": 0.5901058956980705,
      "num_tokens": 4902976.0,
      "step": 100
    },
    {
      "entropy": 1.8283027499914168,
      "epoch": 0.03142857142857143,
      "grad_norm": 0.15304645895957947,
      "learning_rate": 6.22857142857143e-05,
      "loss": 1.6524412155151367,
      "mean_token_accuracy": 0.5927876815199852,
      "num_tokens": 5393172.0,
      "step": 110
    },
    {
      "entropy": 1.8105649381875992,
      "epoch": 0.03428571428571429,
      "grad_norm": 0.1467505544424057,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.6439619064331055,
      "mean_token_accuracy": 0.5953322932124138,
      "num_tokens": 5883816.0,
      "step": 120
    },
    {
      "entropy": 1.8044609040021897,
      "epoch": 0.037142857142857144,
      "grad_norm": 0.14967863261699677,
      "learning_rate": 7.371428571428572e-05,
      "loss": 1.6340011596679687,
      "mean_token_accuracy": 0.5963180974125862,
      "num_tokens": 6373950.0,
      "step": 130
    },
    {
      "entropy": 1.7858079195022583,
      "epoch": 0.04,
      "grad_norm": 0.16043871641159058,
      "learning_rate": 7.942857142857143e-05,
      "loss": 1.6211162567138673,
      "mean_token_accuracy": 0.5996491178870201,
      "num_tokens": 6864677.0,
      "step": 140
    },
    {
      "entropy": 1.7554930090904235,
      "epoch": 0.04285714285714286,
      "grad_norm": 0.17714525759220123,
      "learning_rate": 8.514285714285714e-05,
      "loss": 1.5993239402770996,
      "mean_token_accuracy": 0.6028685554862022,
      "num_tokens": 7354704.0,
      "step": 150
    },
    {
      "entropy": 1.7631021201610566,
      "epoch": 0.045714285714285714,
      "grad_norm": 0.1533629149198532,
      "learning_rate": 9.085714285714286e-05,
      "loss": 1.6020626068115233,
      "mean_token_accuracy": 0.6036920040845871,
      "num_tokens": 7844516.0,
      "step": 160
    },
    {
      "entropy": 1.7572406560182572,
      "epoch": 0.04857142857142857,
      "grad_norm": 0.13726936280727386,
      "learning_rate": 9.657142857142858e-05,
      "loss": 1.6002904891967773,
      "mean_token_accuracy": 0.6049441516399383,
      "num_tokens": 8335216.0,
      "step": 170
    },
    {
      "entropy": 1.7278330773115158,
      "epoch": 0.05142857142857143,
      "grad_norm": 0.1435551792383194,
      "learning_rate": 9.999964291145356e-05,
      "loss": 1.5778950691223144,
      "mean_token_accuracy": 0.6091306760907174,
      "num_tokens": 8825337.0,
      "step": 180
    },
    {
      "entropy": 1.7155232012271882,
      "epoch": 0.054285714285714284,
      "grad_norm": 0.12991751730442047,
      "learning_rate": 9.99956257238817e-05,
      "loss": 1.5530893325805664,
      "mean_token_accuracy": 0.6109549820423126,
      "num_tokens": 9315436.0,
      "step": 190
    },
    {
      "entropy": 1.7033455431461335,
      "epoch": 0.05714285714285714,
      "grad_norm": 0.12225023657083511,
      "learning_rate": 9.998714534787104e-05,
      "loss": 1.5497390747070312,
      "mean_token_accuracy": 0.6124480590224266,
      "num_tokens": 9806074.0,
      "step": 200
    },
    {
      "entropy": 1.704897478222847,
      "epoch": 0.06,
      "grad_norm": 0.13096989691257477,
      "learning_rate": 9.997420254047814e-05,
      "loss": 1.5562244415283204,
      "mean_token_accuracy": 0.6124653443694115,
      "num_tokens": 10296321.0,
      "step": 210
    },
    {
      "entropy": 1.687455916404724,
      "epoch": 0.06285714285714286,
      "grad_norm": 0.12014620006084442,
      "learning_rate": 9.995679845712782e-05,
      "loss": 1.5376283645629882,
      "mean_token_accuracy": 0.612839862704277,
      "num_tokens": 10786325.0,
      "step": 220
    },
    {
      "entropy": 1.6887607038021089,
      "epoch": 0.06571428571428571,
      "grad_norm": 0.1178581714630127,
      "learning_rate": 9.99349346515101e-05,
      "loss": 1.5371188163757323,
      "mean_token_accuracy": 0.6150592401623726,
      "num_tokens": 11276505.0,
      "step": 230
    },
    {
      "entropy": 1.6583371013402939,
      "epoch": 0.06857142857142857,
      "grad_norm": 0.12618421018123627,
      "learning_rate": 9.990861307544141e-05,
      "loss": 1.512394905090332,
      "mean_token_accuracy": 0.6184149146080017,
      "num_tokens": 11767090.0,
      "step": 240
    },
    {
      "entropy": 1.6633832812309266,
      "epoch": 0.07142857142857142,
      "grad_norm": 0.1347818523645401,
      "learning_rate": 9.987783607869043e-05,
      "loss": 1.5205227851867675,
      "mean_token_accuracy": 0.6188683018088341,
      "num_tokens": 12256334.0,
      "step": 250
    },
    {
      "entropy": 1.6662334859371186,
      "epoch": 0.07428571428571429,
      "grad_norm": 0.12107276916503906,
      "learning_rate": 9.984260640876821e-05,
      "loss": 1.5210847854614258,
      "mean_token_accuracy": 0.6181401565670968,
      "num_tokens": 12746242.0,
      "step": 260
    },
    {
      "entropy": 1.669426190853119,
      "epoch": 0.07714285714285714,
      "grad_norm": 0.13238908350467682,
      "learning_rate": 9.980292721068303e-05,
      "loss": 1.5255352020263673,
      "mean_token_accuracy": 0.6176877498626709,
      "num_tokens": 13236893.0,
      "step": 270
    },
    {
      "entropy": 1.6480093061923982,
      "epoch": 0.08,
      "grad_norm": 0.119101881980896,
      "learning_rate": 9.975880202665955e-05,
      "loss": 1.5022310256958007,
      "mean_token_accuracy": 0.6195305570960045,
      "num_tokens": 13727057.0,
      "step": 280
    },
    {
      "entropy": 1.6660549819469452,
      "epoch": 0.08285714285714285,
      "grad_norm": 0.12110637873411179,
      "learning_rate": 9.971023479582257e-05,
      "loss": 1.519071388244629,
      "mean_token_accuracy": 0.6170884057879448,
      "num_tokens": 14217233.0,
      "step": 290
    },
    {
      "entropy": 1.65420058965683,
      "epoch": 0.08571428571428572,
      "grad_norm": 0.1198863536119461,
      "learning_rate": 9.965722985384551e-05,
      "loss": 1.5074204444885253,
      "mean_token_accuracy": 0.6207710400223732,
      "num_tokens": 14706536.0,
      "step": 300
    },
    {
      "entropy": 1.653561717271805,
      "epoch": 0.08857142857142856,
      "grad_norm": 0.11553779989480972,
      "learning_rate": 9.959979193256321e-05,
      "loss": 1.503816509246826,
      "mean_token_accuracy": 0.620441184937954,
      "num_tokens": 15196956.0,
      "step": 310
    },
    {
      "entropy": 1.6494231253862381,
      "epoch": 0.09142857142857143,
      "grad_norm": 0.12458748370409012,
      "learning_rate": 9.953792615954956e-05,
      "loss": 1.5046157836914062,
      "mean_token_accuracy": 0.6211020454764367,
      "num_tokens": 15687053.0,
      "step": 320
    },
    {
      "entropy": 1.6357726126909256,
      "epoch": 0.09428571428571429,
      "grad_norm": 0.1191626638174057,
      "learning_rate": 9.94716380576598e-05,
      "loss": 1.4901004791259767,
      "mean_token_accuracy": 0.623300464451313,
      "num_tokens": 16177605.0,
      "step": 330
    },
    {
      "entropy": 1.6310274928808213,
      "epoch": 0.09714285714285714,
      "grad_norm": 0.1165379136800766,
      "learning_rate": 9.940093354453745e-05,
      "loss": 1.4859237670898438,
      "mean_token_accuracy": 0.6221878513693809,
      "num_tokens": 16668078.0,
      "step": 340
    },
    {
      "entropy": 1.6244249641895294,
      "epoch": 0.1,
      "grad_norm": 0.11486439406871796,
      "learning_rate": 9.932581893208602e-05,
      "loss": 1.4822301864624023,
      "mean_token_accuracy": 0.6249096423387528,
      "num_tokens": 17158239.0,
      "step": 350
    },
    {
      "entropy": 1.6261575251817704,
      "epoch": 0.10285714285714286,
      "grad_norm": 0.1269659847021103,
      "learning_rate": 9.924630092590552e-05,
      "loss": 1.4802236557006836,
      "mean_token_accuracy": 0.6244122132658958,
      "num_tokens": 17648337.0,
      "step": 360
    },
    {
      "entropy": 1.6262814104557037,
      "epoch": 0.10571428571428572,
      "grad_norm": 0.12204760313034058,
      "learning_rate": 9.916238662469393e-05,
      "loss": 1.4841039657592774,
      "mean_token_accuracy": 0.62349953353405,
      "num_tokens": 18139347.0,
      "step": 370
    },
    {
      "entropy": 1.6084025710821153,
      "epoch": 0.10857142857142857,
      "grad_norm": 0.11636750400066376,
      "learning_rate": 9.907408351961338e-05,
      "loss": 1.4650284767150878,
      "mean_token_accuracy": 0.6257219180464745,
      "num_tokens": 18629841.0,
      "step": 380
    },
    {
      "entropy": 1.6091126441955566,
      "epoch": 0.11142857142857143,
      "grad_norm": 0.12340579181909561,
      "learning_rate": 9.89813994936215e-05,
      "loss": 1.4654415130615235,
      "mean_token_accuracy": 0.627759400010109,
      "num_tokens": 19119573.0,
      "step": 390
    },
    {
      "entropy": 1.620647069811821,
      "epoch": 0.11428571428571428,
      "grad_norm": 0.1143694818019867,
      "learning_rate": 9.888434282076758e-05,
      "loss": 1.4784412384033203,
      "mean_token_accuracy": 0.6251529678702354,
      "num_tokens": 19609952.0,
      "step": 400
    },
    {
      "entropy": 1.6150473326444625,
      "epoch": 0.11714285714285715,
      "grad_norm": 0.11208155006170273,
      "learning_rate": 9.878292216545406e-05,
      "loss": 1.4707134246826172,
      "mean_token_accuracy": 0.6262766167521476,
      "num_tokens": 20100484.0,
      "step": 410
    },
    {
      "entropy": 1.6126654744148254,
      "epoch": 0.12,
      "grad_norm": 0.11389093846082687,
      "learning_rate": 9.867714658166294e-05,
      "loss": 1.4687725067138673,
      "mean_token_accuracy": 0.6262835577130318,
      "num_tokens": 20591061.0,
      "step": 420
    },
    {
      "entropy": 1.6087138205766678,
      "epoch": 0.12285714285714286,
      "grad_norm": 0.11683399975299835,
      "learning_rate": 9.856702551214758e-05,
      "loss": 1.4735491752624512,
      "mean_token_accuracy": 0.6256266921758652,
      "num_tokens": 21081884.0,
      "step": 430
    },
    {
      "entropy": 1.6129542291164398,
      "epoch": 0.12571428571428572,
      "grad_norm": 0.1123637780547142,
      "learning_rate": 9.84525687875897e-05,
      "loss": 1.4666884422302247,
      "mean_token_accuracy": 0.6269908130168915,
      "num_tokens": 21572985.0,
      "step": 440
    },
    {
      "entropy": 1.5876862674951553,
      "epoch": 0.12857142857142856,
      "grad_norm": 0.11302825808525085,
      "learning_rate": 9.833378662572183e-05,
      "loss": 1.44884033203125,
      "mean_token_accuracy": 0.6304112330079079,
      "num_tokens": 22062380.0,
      "step": 450
    },
    {
      "entropy": 1.6038869142532348,
      "epoch": 0.13142857142857142,
      "grad_norm": 0.11883237957954407,
      "learning_rate": 9.821068963041507e-05,
      "loss": 1.4640923500061036,
      "mean_token_accuracy": 0.6268730536103249,
      "num_tokens": 22553395.0,
      "step": 460
    },
    {
      "entropy": 1.616351565718651,
      "epoch": 0.13428571428571429,
      "grad_norm": 0.1148705706000328,
      "learning_rate": 9.808328879073251e-05,
      "loss": 1.4773920059204102,
      "mean_token_accuracy": 0.6249542534351349,
      "num_tokens": 23042805.0,
      "step": 470
    },
    {
      "entropy": 1.584571686387062,
      "epoch": 0.13714285714285715,
      "grad_norm": 0.12227737158536911,
      "learning_rate": 9.79515954799483e-05,
      "loss": 1.4490341186523437,
      "mean_token_accuracy": 0.6293571904301644,
      "num_tokens": 23532109.0,
      "step": 480
    },
    {
      "entropy": 1.5974321156740188,
      "epoch": 0.14,
      "grad_norm": 0.11681197583675385,
      "learning_rate": 9.781562145453212e-05,
      "loss": 1.458102035522461,
      "mean_token_accuracy": 0.6288253426551819,
      "num_tokens": 24022475.0,
      "step": 490
    },
    {
      "entropy": 1.5929092824459077,
      "epoch": 0.14285714285714285,
      "grad_norm": 0.11527484655380249,
      "learning_rate": 9.767537885309996e-05,
      "loss": 1.4527276039123536,
      "mean_token_accuracy": 0.6284167483448982,
      "num_tokens": 24512984.0,
      "step": 500
    },
    {
      "entropy": 1.5956292569637298,
      "epoch": 0.1457142857142857,
      "grad_norm": 0.11178956925868988,
      "learning_rate": 9.75308801953302e-05,
      "loss": 1.4558266639709472,
      "mean_token_accuracy": 0.628529217839241,
      "num_tokens": 25003761.0,
      "step": 510
    },
    {
      "entropy": 1.5775458842515946,
      "epoch": 0.14857142857142858,
      "grad_norm": 0.11768428981304169,
      "learning_rate": 9.738213838084621e-05,
      "loss": 1.4407743453979491,
      "mean_token_accuracy": 0.6300915256142616,
      "num_tokens": 25493579.0,
      "step": 520
    },
    {
      "entropy": 1.5778144687414168,
      "epoch": 0.15142857142857144,
      "grad_norm": 0.11278413981199265,
      "learning_rate": 9.722916668806454e-05,
      "loss": 1.4403908729553223,
      "mean_token_accuracy": 0.6314086809754371,
      "num_tokens": 25984228.0,
      "step": 530
    },
    {
      "entropy": 1.570985835790634,
      "epoch": 0.15428571428571428,
      "grad_norm": 0.1122731938958168,
      "learning_rate": 9.707197877300974e-05,
      "loss": 1.426032543182373,
      "mean_token_accuracy": 0.6325461342930794,
      "num_tokens": 26473677.0,
      "step": 540
    },
    {
      "entropy": 1.5796766877174377,
      "epoch": 0.15714285714285714,
      "grad_norm": 0.11975421756505966,
      "learning_rate": 9.691058866809514e-05,
      "loss": 1.4357484817504882,
      "mean_token_accuracy": 0.6324031576514244,
      "num_tokens": 26964375.0,
      "step": 550
    },
    {
      "entropy": 1.5689537853002549,
      "epoch": 0.16,
      "grad_norm": 0.11165549606084824,
      "learning_rate": 9.674501078087018e-05,
      "loss": 1.4325990676879883,
      "mean_token_accuracy": 0.6315152242779731,
      "num_tokens": 27454872.0,
      "step": 560
    },
    {
      "entropy": 1.5615802317857743,
      "epoch": 0.16285714285714287,
      "grad_norm": 0.11403413116931915,
      "learning_rate": 9.657525989273428e-05,
      "loss": 1.424344253540039,
      "mean_token_accuracy": 0.6343739420175553,
      "num_tokens": 27945254.0,
      "step": 570
    },
    {
      "entropy": 1.568941941857338,
      "epoch": 0.1657142857142857,
      "grad_norm": 0.11258367449045181,
      "learning_rate": 9.640135115761721e-05,
      "loss": 1.4347594261169434,
      "mean_token_accuracy": 0.6329293712973595,
      "num_tokens": 28435475.0,
      "step": 580
    },
    {
      "entropy": 1.5669189006090165,
      "epoch": 0.16857142857142857,
      "grad_norm": 0.1104324460029602,
      "learning_rate": 9.622330010062632e-05,
      "loss": 1.4304702758789063,
      "mean_token_accuracy": 0.6331642985343933,
      "num_tokens": 28925167.0,
      "step": 590
    },
    {
      "entropy": 1.574634400010109,
      "epoch": 0.17142857142857143,
      "grad_norm": 0.11263342946767807,
      "learning_rate": 9.604112261666054e-05,
      "loss": 1.436413288116455,
      "mean_token_accuracy": 0.6318994089961052,
      "num_tokens": 29415502.0,
      "step": 600
    },
    {
      "entropy": 1.56950443983078,
      "epoch": 0.1742857142857143,
      "grad_norm": 0.11262984573841095,
      "learning_rate": 9.58548349689915e-05,
      "loss": 1.424701976776123,
      "mean_token_accuracy": 0.6350988477468491,
      "num_tokens": 29906208.0,
      "step": 610
    },
    {
      "entropy": 1.5514621257781982,
      "epoch": 0.17714285714285713,
      "grad_norm": 0.11094693094491959,
      "learning_rate": 9.566445378781162e-05,
      "loss": 1.4180520057678223,
      "mean_token_accuracy": 0.6351837337017059,
      "num_tokens": 30396946.0,
      "step": 620
    },
    {
      "entropy": 1.5565964162349701,
      "epoch": 0.18,
      "grad_norm": 0.110066719353199,
      "learning_rate": 9.546999606874947e-05,
      "loss": 1.4229997634887694,
      "mean_token_accuracy": 0.6346639677882194,
      "num_tokens": 30887292.0,
      "step": 630
    },
    {
      "entropy": 1.5571098238229752,
      "epoch": 0.18285714285714286,
      "grad_norm": 0.11187391728162766,
      "learning_rate": 9.527147917135265e-05,
      "loss": 1.4242905616760253,
      "mean_token_accuracy": 0.634743233025074,
      "num_tokens": 31377366.0,
      "step": 640
    },
    {
      "entropy": 1.5575890451669694,
      "epoch": 0.18571428571428572,
      "grad_norm": 0.12017875164747238,
      "learning_rate": 9.5068920817538e-05,
      "loss": 1.4210159301757812,
      "mean_token_accuracy": 0.6346415132284164,
      "num_tokens": 31867728.0,
      "step": 650
    },
    {
      "entropy": 1.5610258907079697,
      "epoch": 0.18857142857142858,
      "grad_norm": 0.11284279823303223,
      "learning_rate": 9.486233909000957e-05,
      "loss": 1.4286124229431152,
      "mean_token_accuracy": 0.633992238342762,
      "num_tokens": 32357951.0,
      "step": 660
    },
    {
      "entropy": 1.570546704530716,
      "epoch": 0.19142857142857142,
      "grad_norm": 0.11221849918365479,
      "learning_rate": 9.465175243064428e-05,
      "loss": 1.427887535095215,
      "mean_token_accuracy": 0.6341994881629944,
      "num_tokens": 32848000.0,
      "step": 670
    },
    {
      "entropy": 1.5625760078430175,
      "epoch": 0.19428571428571428,
      "grad_norm": 0.11504076421260834,
      "learning_rate": 9.443717963884569e-05,
      "loss": 1.4254456520080567,
      "mean_token_accuracy": 0.6330446928739548,
      "num_tokens": 33338988.0,
      "step": 680
    },
    {
      "entropy": 1.5441237717866898,
      "epoch": 0.19714285714285715,
      "grad_norm": 0.11827517300844193,
      "learning_rate": 9.42186398698657e-05,
      "loss": 1.409364604949951,
      "mean_token_accuracy": 0.6384268119931221,
      "num_tokens": 33829458.0,
      "step": 690
    },
    {
      "entropy": 1.5519202262163163,
      "epoch": 0.2,
      "grad_norm": 0.11421947181224823,
      "learning_rate": 9.399615263309448e-05,
      "loss": 1.4179234504699707,
      "mean_token_accuracy": 0.6360488340258599,
      "num_tokens": 34319687.0,
      "step": 700
    },
    {
      "entropy": 1.5406184524297715,
      "epoch": 0.20285714285714285,
      "grad_norm": 0.11246901750564575,
      "learning_rate": 9.37697377903189e-05,
      "loss": 1.4044339179992675,
      "mean_token_accuracy": 0.6360796883702278,
      "num_tokens": 34810861.0,
      "step": 710
    },
    {
      "entropy": 1.5405683517456055,
      "epoch": 0.2057142857142857,
      "grad_norm": 0.10953953862190247,
      "learning_rate": 9.353941555394946e-05,
      "loss": 1.4075803756713867,
      "mean_token_accuracy": 0.6373428180813789,
      "num_tokens": 35301651.0,
      "step": 720
    },
    {
      "entropy": 1.5303823828697205,
      "epoch": 0.20857142857142857,
      "grad_norm": 0.11503418534994125,
      "learning_rate": 9.330520648521581e-05,
      "loss": 1.3944478034973145,
      "mean_token_accuracy": 0.6395626902580261,
      "num_tokens": 35792660.0,
      "step": 730
    },
    {
      "entropy": 1.546586701273918,
      "epoch": 0.21142857142857144,
      "grad_norm": 0.11355750262737274,
      "learning_rate": 9.306713149233126e-05,
      "loss": 1.4133389472961426,
      "mean_token_accuracy": 0.6359729379415512,
      "num_tokens": 36283021.0,
      "step": 740
    },
    {
      "entropy": 1.5666495472192765,
      "epoch": 0.21428571428571427,
      "grad_norm": 0.11290405690670013,
      "learning_rate": 9.282521182862629e-05,
      "loss": 1.4316218376159668,
      "mean_token_accuracy": 0.6324604853987694,
      "num_tokens": 36773401.0,
      "step": 750
    },
    {
      "entropy": 1.5476279586553574,
      "epoch": 0.21714285714285714,
      "grad_norm": 0.11210077255964279,
      "learning_rate": 9.25794690906512e-05,
      "loss": 1.4119671821594237,
      "mean_token_accuracy": 0.6370165795087814,
      "num_tokens": 37263273.0,
      "step": 760
    },
    {
      "entropy": 1.5502693444490432,
      "epoch": 0.22,
      "grad_norm": 0.1148453801870346,
      "learning_rate": 9.23299252162482e-05,
      "loss": 1.4147866249084473,
      "mean_token_accuracy": 0.636229844391346,
      "num_tokens": 37753396.0,
      "step": 770
    },
    {
      "entropy": 1.5336053550243378,
      "epoch": 0.22285714285714286,
      "grad_norm": 0.12296847254037857,
      "learning_rate": 9.20766024825929e-05,
      "loss": 1.4014326095581056,
      "mean_token_accuracy": 0.6389749109745025,
      "num_tokens": 38243813.0,
      "step": 780
    },
    {
      "entropy": 1.5418373078107834,
      "epoch": 0.2257142857142857,
      "grad_norm": 0.11040552705526352,
      "learning_rate": 9.181952350420568e-05,
      "loss": 1.408182144165039,
      "mean_token_accuracy": 0.6375694692134857,
      "num_tokens": 38734087.0,
      "step": 790
    },
    {
      "entropy": 1.540384903550148,
      "epoch": 0.22857142857142856,
      "grad_norm": 0.11459089070558548,
      "learning_rate": 9.15587112309328e-05,
      "loss": 1.4076971054077148,
      "mean_token_accuracy": 0.6367619827389717,
      "num_tokens": 39223587.0,
      "step": 800
    },
    {
      "entropy": 1.5353645473718642,
      "epoch": 0.23142857142857143,
      "grad_norm": 0.10925675183534622,
      "learning_rate": 9.129418894589765e-05,
      "loss": 1.4029156684875488,
      "mean_token_accuracy": 0.6391762167215347,
      "num_tokens": 39713378.0,
      "step": 810
    },
    {
      "entropy": 1.537180870771408,
      "epoch": 0.2342857142857143,
      "grad_norm": 0.11116520315408707,
      "learning_rate": 9.102598026342224e-05,
      "loss": 1.4027939796447755,
      "mean_token_accuracy": 0.6384590819478035,
      "num_tokens": 40204035.0,
      "step": 820
    },
    {
      "entropy": 1.5364642143249512,
      "epoch": 0.23714285714285716,
      "grad_norm": 0.11325648427009583,
      "learning_rate": 9.075410912691907e-05,
      "loss": 1.4042522430419921,
      "mean_token_accuracy": 0.6376483544707299,
      "num_tokens": 40693853.0,
      "step": 830
    },
    {
      "entropy": 1.5172248750925064,
      "epoch": 0.24,
      "grad_norm": 0.11164099723100662,
      "learning_rate": 9.04785998067537e-05,
      "loss": 1.38507022857666,
      "mean_token_accuracy": 0.6411049708724021,
      "num_tokens": 41184741.0,
      "step": 840
    },
    {
      "entropy": 1.5312542200088501,
      "epoch": 0.24285714285714285,
      "grad_norm": 0.11361584812402725,
      "learning_rate": 9.019947689807812e-05,
      "loss": 1.401794147491455,
      "mean_token_accuracy": 0.6388043731451034,
      "num_tokens": 41675456.0,
      "step": 850
    },
    {
      "entropy": 1.5356624484062196,
      "epoch": 0.24571428571428572,
      "grad_norm": 0.1110292598605156,
      "learning_rate": 8.991676531863508e-05,
      "loss": 1.398195171356201,
      "mean_token_accuracy": 0.6395324870944024,
      "num_tokens": 42165958.0,
      "step": 860
    },
    {
      "entropy": 1.5131745964288712,
      "epoch": 0.24857142857142858,
      "grad_norm": 0.11180949956178665,
      "learning_rate": 8.963049030653357e-05,
      "loss": 1.386609935760498,
      "mean_token_accuracy": 0.6415100902318954,
      "num_tokens": 42655563.0,
      "step": 870
    },
    {
      "entropy": 1.5264964669942855,
      "epoch": 0.25142857142857145,
      "grad_norm": 0.11161798238754272,
      "learning_rate": 8.934067741799588e-05,
      "loss": 1.3911283493041993,
      "mean_token_accuracy": 0.6405024617910385,
      "num_tokens": 43145690.0,
      "step": 880
    },
    {
      "entropy": 1.5238522559404373,
      "epoch": 0.2542857142857143,
      "grad_norm": 0.11398132890462875,
      "learning_rate": 8.90473525250761e-05,
      "loss": 1.3967710494995118,
      "mean_token_accuracy": 0.6410051316022873,
      "num_tokens": 43636186.0,
      "step": 890
    },
    {
      "entropy": 1.5147892564535141,
      "epoch": 0.2571428571428571,
      "grad_norm": 0.1122528463602066,
      "learning_rate": 8.875054181335054e-05,
      "loss": 1.3884020805358888,
      "mean_token_accuracy": 0.6408766448497772,
      "num_tokens": 44126324.0,
      "step": 900
    },
    {
      "entropy": 1.51045164167881,
      "epoch": 0.26,
      "grad_norm": 0.11045881360769272,
      "learning_rate": 8.845027177958e-05,
      "loss": 1.3785322189331055,
      "mean_token_accuracy": 0.6415310442447663,
      "num_tokens": 44616075.0,
      "step": 910
    },
    {
      "entropy": 1.5210172832012177,
      "epoch": 0.26285714285714284,
      "grad_norm": 0.10973014682531357,
      "learning_rate": 8.814656922934445e-05,
      "loss": 1.3884805679321288,
      "mean_token_accuracy": 0.6404986321926117,
      "num_tokens": 45106497.0,
      "step": 920
    },
    {
      "entropy": 1.5296362102031709,
      "epoch": 0.26571428571428574,
      "grad_norm": 0.11496967822313309,
      "learning_rate": 8.783946127465001e-05,
      "loss": 1.3945645332336425,
      "mean_token_accuracy": 0.6402764439582824,
      "num_tokens": 45597040.0,
      "step": 930
    },
    {
      "entropy": 1.5171466410160064,
      "epoch": 0.26857142857142857,
      "grad_norm": 0.11463408172130585,
      "learning_rate": 8.752897533150868e-05,
      "loss": 1.387949275970459,
      "mean_token_accuracy": 0.6412890180945396,
      "num_tokens": 46087347.0,
      "step": 940
    },
    {
      "entropy": 1.5124164909124374,
      "epoch": 0.2714285714285714,
      "grad_norm": 0.11042758822441101,
      "learning_rate": 8.721513911749073e-05,
      "loss": 1.3821532249450683,
      "mean_token_accuracy": 0.6414273202419281,
      "num_tokens": 46577723.0,
      "step": 950
    },
    {
      "entropy": 1.5339836180210114,
      "epoch": 0.2742857142857143,
      "grad_norm": 0.115251325070858,
      "learning_rate": 8.689798064925049e-05,
      "loss": 1.4023088455200194,
      "mean_token_accuracy": 0.6390077367424964,
      "num_tokens": 47067566.0,
      "step": 960
    },
    {
      "entropy": 1.4907908529043197,
      "epoch": 0.27714285714285714,
      "grad_norm": 0.10888004302978516,
      "learning_rate": 8.657752824002512e-05,
      "loss": 1.3607192993164063,
      "mean_token_accuracy": 0.6449671313166618,
      "num_tokens": 47557094.0,
      "step": 970
    },
    {
      "entropy": 1.5133179754018784,
      "epoch": 0.28,
      "grad_norm": 0.10961966216564178,
      "learning_rate": 8.625381049710711e-05,
      "loss": 1.387069320678711,
      "mean_token_accuracy": 0.6418288230895997,
      "num_tokens": 48047288.0,
      "step": 980
    },
    {
      "entropy": 1.5235115170478821,
      "epoch": 0.28285714285714286,
      "grad_norm": 0.11490974575281143,
      "learning_rate": 8.592685631929041e-05,
      "loss": 1.3894145011901855,
      "mean_token_accuracy": 0.6398768693208694,
      "num_tokens": 48537707.0,
      "step": 990
    },
    {
      "entropy": 1.5072008579969407,
      "epoch": 0.2857142857142857,
      "grad_norm": 0.11175917088985443,
      "learning_rate": 8.55966948942907e-05,
      "loss": 1.3789593696594238,
      "mean_token_accuracy": 0.6438135176897049,
      "num_tokens": 49027502.0,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 3500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.73130249895936e+17,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}