[
  {
    "loss": 1.5751,
    "grad_norm": 5.8206610679626465,
    "learning_rate": 4.556962025316456e-05,
    "epoch": 0.012690355329949238,
    "step": 10
  },
  {
    "loss": 0.6817,
    "grad_norm": 2.4909415245056152,
    "learning_rate": 9.620253164556962e-05,
    "epoch": 0.025380710659898477,
    "step": 20
  },
  {
    "loss": 0.5317,
    "grad_norm": 2.0207533836364746,
    "learning_rate": 0.0001468354430379747,
    "epoch": 0.03807106598984772,
    "step": 30
  },
  {
    "loss": 0.4042,
    "grad_norm": 2.2393276691436768,
    "learning_rate": 0.00019746835443037975,
    "epoch": 0.050761421319796954,
    "step": 40
  },
  {
    "loss": 0.3339,
    "grad_norm": 1.3759368658065796,
    "learning_rate": 0.0002481012658227848,
    "epoch": 0.06345177664974619,
    "step": 50
  },
  {
    "loss": 0.2921,
    "grad_norm": 1.4795056581497192,
    "learning_rate": 0.0002987341772151899,
    "epoch": 0.07614213197969544,
    "step": 60
  },
  {
    "loss": 0.2594,
    "grad_norm": 1.5126503705978394,
    "learning_rate": 0.00034936708860759495,
    "epoch": 0.08883248730964467,
    "step": 70
  },
  {
    "loss": 0.2418,
    "grad_norm": 1.2799267768859863,
    "learning_rate": 0.0004,
    "epoch": 0.10152284263959391,
    "step": 80
  },
  {
    "loss": 0.2121,
    "grad_norm": 1.081551194190979,
    "learning_rate": 0.0003999559607204408,
    "epoch": 0.11421319796954314,
    "step": 90
  },
  {
    "loss": 0.1958,
    "grad_norm": 1.5507794618606567,
    "learning_rate": 0.0003998238622763449,
    "epoch": 0.12690355329949238,
    "step": 100
  },
  {
    "loss": 0.21,
    "grad_norm": 0.9705930352210999,
    "learning_rate": 0.0003996037628429151,
    "epoch": 0.13959390862944163,
    "step": 110
  },
  {
    "loss": 0.173,
    "grad_norm": 0.9663600325584412,
    "learning_rate": 0.00039929575935035633,
    "epoch": 0.15228426395939088,
    "step": 120
  },
  {
    "loss": 0.1662,
    "grad_norm": 1.1074914932250977,
    "learning_rate": 0.00039889998744118777,
    "epoch": 0.1649746192893401,
    "step": 130
  },
  {
    "loss": 0.1733,
    "grad_norm": 0.9759091734886169,
    "learning_rate": 0.00039841662141050683,
    "epoch": 0.17766497461928935,
    "step": 140
  },
  {
    "loss": 0.1646,
    "grad_norm": 0.8136119842529297,
    "learning_rate": 0.0003978458741292311,
    "epoch": 0.19035532994923857,
    "step": 150
  },
  {
    "eval_loss": 0.15786977112293243,
    "eval_runtime": 24.4689,
    "eval_samples_per_second": 54.232,
    "eval_steps_per_second": 13.568,
    "epoch": 0.19923857868020303,
    "step": 157
  },
  {
    "loss": 0.1468,
    "grad_norm": 0.8433499336242676,
    "learning_rate": 0.00039718799695035134,
    "epoch": 0.20304568527918782,
    "step": 160
  },
  {
    "loss": 0.1321,
    "grad_norm": 0.5848754644393921,
    "learning_rate": 0.0003964432795982376,
    "epoch": 0.21573604060913706,
    "step": 170
  },
  {
    "loss": 0.1427,
    "grad_norm": 0.7149267792701721,
    "learning_rate": 0.0003956120500410464,
    "epoch": 0.22842639593908629,
    "step": 180
  },
  {
    "loss": 0.1277,
    "grad_norm": 0.6142985224723816,
    "learning_rate": 0.0003946946743462862,
    "epoch": 0.24111675126903553,
    "step": 190
  },
  {
    "loss": 0.1355,
    "grad_norm": 0.5795847773551941,
    "learning_rate": 0.00039369155651960383,
    "epoch": 0.25380710659898476,
    "step": 200
  },
  {
    "loss": 0.1229,
    "grad_norm": 0.6075690984725952,
    "learning_rate": 0.0003926031383268634,
    "epoch": 0.26649746192893403,
    "step": 210
  },
  {
    "loss": 0.1307,
    "grad_norm": 0.5007538199424744,
    "learning_rate": 0.0003914298990995955,
    "epoch": 0.27918781725888325,
    "step": 220
  },
  {
    "loss": 0.1179,
    "grad_norm": 0.7290500402450562,
    "learning_rate": 0.00039017235552390333,
    "epoch": 0.2918781725888325,
    "step": 230
  },
  {
    "loss": 0.1097,
    "grad_norm": 0.5982555747032166,
    "learning_rate": 0.00038883106141291774,
    "epoch": 0.30456852791878175,
    "step": 240
  },
  {
    "loss": 0.1304,
    "grad_norm": 0.5894684195518494,
    "learning_rate": 0.000387406607462902,
    "epoch": 0.31725888324873097,
    "step": 250
  },
  {
    "loss": 0.1253,
    "grad_norm": 0.4741029441356659,
    "learning_rate": 0.00038589962099311336,
    "epoch": 0.3299492385786802,
    "step": 260
  },
  {
    "loss": 0.1252,
    "grad_norm": 0.5968972444534302,
    "learning_rate": 0.0003843107656695362,
    "epoch": 0.3426395939086294,
    "step": 270
  },
  {
    "loss": 0.1179,
    "grad_norm": 0.6765711307525635,
    "learning_rate": 0.00038264074121260817,
    "epoch": 0.3553299492385787,
    "step": 280
  },
  {
    "loss": 0.1245,
    "grad_norm": 0.531008243560791,
    "learning_rate": 0.0003808902830890687,
    "epoch": 0.3680203045685279,
    "step": 290
  },
  {
    "loss": 0.1166,
    "grad_norm": 0.6060107350349426,
    "learning_rate": 0.0003790601621880642,
    "epoch": 0.38071065989847713,
    "step": 300
  },
  {
    "loss": 0.1004,
    "grad_norm": 0.6947969198226929,
    "learning_rate": 0.0003771511844816547,
    "epoch": 0.3934010152284264,
    "step": 310
  },
  {
    "eval_loss": 0.1160828173160553,
    "eval_runtime": 9.5412,
    "eval_samples_per_second": 139.081,
    "eval_steps_per_second": 34.796,
    "epoch": 0.39847715736040606,
    "step": 314
  },
  {
    "loss": 0.1162,
    "grad_norm": 0.6814019083976746,
    "learning_rate": 0.0003751641906698689,
    "epoch": 0.40609137055837563,
    "step": 320
  },
  {
    "loss": 0.1209,
    "grad_norm": 0.6832170486450195,
    "learning_rate": 0.00037310005581046656,
    "epoch": 0.41878172588832485,
    "step": 330
  },
  {
    "loss": 0.1132,
    "grad_norm": 0.5093628764152527,
    "learning_rate": 0.00037095968893356875,
    "epoch": 0.43147208121827413,
    "step": 340
  },
  {
    "loss": 0.1072,
    "grad_norm": 0.6062504053115845,
    "learning_rate": 0.000368744032641328,
    "epoch": 0.44416243654822335,
    "step": 350
  },
  {
    "loss": 0.1056,
    "grad_norm": 0.4274779260158539,
    "learning_rate": 0.00036645406269281307,
    "epoch": 0.45685279187817257,
    "step": 360
  },
  {
    "loss": 0.1178,
    "grad_norm": 0.469860315322876,
    "learning_rate": 0.00036409078757429123,
    "epoch": 0.46954314720812185,
    "step": 370
  },
  {
    "loss": 0.1157,
    "grad_norm": 0.5052468776702881,
    "learning_rate": 0.0003616552480550987,
    "epoch": 0.48223350253807107,
    "step": 380
  },
  {
    "loss": 0.1052,
    "grad_norm": 0.6406036019325256,
    "learning_rate": 0.0003591485167292932,
    "epoch": 0.4949238578680203,
    "step": 390
  },
  {
    "loss": 0.1099,
    "grad_norm": 0.4725392162799835,
    "learning_rate": 0.000356571697543291,
    "epoch": 0.5076142131979695,
    "step": 400
  },
  {
    "loss": 0.0995,
    "grad_norm": 0.566696286201477,
    "learning_rate": 0.00035392592530969724,
    "epoch": 0.5203045685279187,
    "step": 410
  },
  {
    "loss": 0.1005,
    "grad_norm": 0.5996329188346863,
    "learning_rate": 0.0003512123652075423,
    "epoch": 0.5329949238578681,
    "step": 420
  },
  {
    "loss": 0.0991,
    "grad_norm": 0.529081404209137,
    "learning_rate": 0.00034843221226914565,
    "epoch": 0.5456852791878173,
    "step": 430
  },
  {
    "loss": 0.0992,
    "grad_norm": 0.49170249700546265,
    "learning_rate": 0.0003455866908538319,
    "epoch": 0.5583756345177665,
    "step": 440
  },
  {
    "loss": 0.1054,
    "grad_norm": 0.4307686388492584,
    "learning_rate": 0.0003426770541087322,
    "epoch": 0.5710659898477157,
    "step": 450
  },
  {
    "loss": 0.0999,
    "grad_norm": 0.42143514752388,
    "learning_rate": 0.00033970458341690677,
    "epoch": 0.583756345177665,
    "step": 460
  },
  {
    "loss": 0.091,
    "grad_norm": 0.49249398708343506,
    "learning_rate": 0.0003366705878330334,
    "epoch": 0.5964467005076142,
    "step": 470
  },
  {
    "eval_loss": 0.09394794702529907,
    "eval_runtime": 9.5472,
    "eval_samples_per_second": 138.993,
    "eval_steps_per_second": 34.774,
    "epoch": 0.5977157360406091,
    "step": 471
  },
  {
    "loss": 0.0934,
    "grad_norm": 0.5115765333175659,
    "learning_rate": 0.00033357640350690907,
    "epoch": 0.6091370558375635,
    "step": 480
  },
  {
    "loss": 0.0869,
    "grad_norm": 0.43772196769714355,
    "learning_rate": 0.00033042339309501936,
    "epoch": 0.6218274111675127,
    "step": 490
  },
  {
    "loss": 0.0887,
    "grad_norm": 0.4491313397884369,
    "learning_rate": 0.0003272129451604339,
    "epoch": 0.6345177664974619,
    "step": 500
  },
  {
    "loss": 0.0912,
    "grad_norm": 0.3995817303657532,
    "learning_rate": 0.00032394647356129394,
    "epoch": 0.6472081218274112,
    "step": 510
  },
  {
    "loss": 0.0923,
    "grad_norm": 0.3744134306907654,
    "learning_rate": 0.0003206254168281585,
    "epoch": 0.6598984771573604,
    "step": 520
  },
  {
    "loss": 0.1008,
    "grad_norm": 0.47935950756073,
    "learning_rate": 0.00031725123753048676,
    "epoch": 0.6725888324873096,
    "step": 530
  },
  {
    "loss": 0.0976,
    "grad_norm": 0.5493370294570923,
    "learning_rate": 0.0003138254216325324,
    "epoch": 0.6852791878172588,
    "step": 540
  },
  {
    "loss": 0.0972,
    "grad_norm": 0.5088523030281067,
    "learning_rate": 0.000310349477838936,
    "epoch": 0.6979695431472082,
    "step": 550
  },
  {
    "loss": 0.0974,
    "grad_norm": 0.4719524681568146,
    "learning_rate": 0.0003068249369303019,
    "epoch": 0.7106598984771574,
    "step": 560
  },
  {
    "loss": 0.0871,
    "grad_norm": 0.5160706043243408,
    "learning_rate": 0.0003032533510890542,
    "epoch": 0.7233502538071066,
    "step": 570
  },
  {
    "loss": 0.0883,
    "grad_norm": 0.42795512080192566,
    "learning_rate": 0.0002996362932158663,
    "epoch": 0.7360406091370558,
    "step": 580
  },
  {
    "loss": 0.0914,
    "grad_norm": 0.5042217969894409,
    "learning_rate": 0.0002959753562369666,
    "epoch": 0.748730964467005,
    "step": 590
  },
  {
    "loss": 0.0858,
    "grad_norm": 0.41944852471351624,
    "learning_rate": 0.0002922721524026259,
    "epoch": 0.7614213197969543,
    "step": 600
  },
  {
    "loss": 0.0784,
    "grad_norm": 0.3173629343509674,
    "learning_rate": 0.00028852831257713326,
    "epoch": 0.7741116751269036,
    "step": 610
  },
  {
    "loss": 0.0899,
    "grad_norm": 0.5276319980621338,
    "learning_rate": 0.0002847454855205758,
    "epoch": 0.7868020304568528,
    "step": 620
  },
  {
    "eval_loss": 0.09238167852163315,
    "eval_runtime": 9.5377,
    "eval_samples_per_second": 139.132,
    "eval_steps_per_second": 34.809,
    "epoch": 0.7969543147208121,
    "step": 628
  },
  {
    "loss": 0.0868,
    "grad_norm": 0.5028842091560364,
    "learning_rate": 0.0002809253371627362,
    "epoch": 0.799492385786802,
    "step": 630
  },
  {
    "loss": 0.0834,
    "grad_norm": 0.40975555777549744,
    "learning_rate": 0.00027706954986942935,
    "epoch": 0.8121827411167513,
    "step": 640
  },
  {
    "loss": 0.0927,
    "grad_norm": 0.5146291851997375,
    "learning_rate": 0.0002731798217016005,
    "epoch": 0.8248730964467005,
    "step": 650
  },
  {
    "loss": 0.0813,
    "grad_norm": 0.3960341811180115,
    "learning_rate": 0.0002692578656675116,
    "epoch": 0.8375634517766497,
    "step": 660
  },
  {
    "loss": 0.0934,
    "grad_norm": 0.4789310693740845,
    "learning_rate": 0.00026530540896834467,
    "epoch": 0.850253807106599,
    "step": 670
  },
  {
    "loss": 0.0917,
    "grad_norm": 0.43943315744400024,
    "learning_rate": 0.00026132419223755493,
    "epoch": 0.8629441624365483,
    "step": 680
  },
  {
    "loss": 0.0862,
    "grad_norm": 0.5376535654067993,
    "learning_rate": 0.00025731596877430826,
    "epoch": 0.8756345177664975,
    "step": 690
  },
  {
    "loss": 0.088,
    "grad_norm": 0.452738493680954,
    "learning_rate": 0.0002532825037713411,
    "epoch": 0.8883248730964467,
    "step": 700
  },
  {
    "loss": 0.0819,
    "grad_norm": 0.4121873080730438,
    "learning_rate": 0.00024922557353758196,
    "epoch": 0.9010152284263959,
    "step": 710
  },
  {
    "loss": 0.0917,
    "grad_norm": 0.39808085560798645,
    "learning_rate": 0.00024514696471587794,
    "epoch": 0.9137055837563451,
    "step": 720
  },
  {
    "loss": 0.0802,
    "grad_norm": 0.43925586342811584,
    "learning_rate": 0.00024104847349617025,
    "epoch": 0.9263959390862944,
    "step": 730
  },
  {
    "loss": 0.0867,
    "grad_norm": 0.42966383695602417,
    "learning_rate": 0.00023693190482446493,
    "epoch": 0.9390862944162437,
    "step": 740
  },
  {
    "loss": 0.081,
    "grad_norm": 0.4360509514808655,
    "learning_rate": 0.00023279907160794733,
    "epoch": 0.9517766497461929,
    "step": 750
  },
  {
    "loss": 0.0943,
    "grad_norm": 0.4277612268924713,
    "learning_rate": 0.00022865179391659153,
    "epoch": 0.9644670050761421,
    "step": 760
  },
  {
    "loss": 0.0847,
    "grad_norm": 0.44837474822998047,
    "learning_rate": 0.00022449189818161407,
    "epoch": 0.9771573604060914,
    "step": 770
  },
  {
    "loss": 0.0857,
    "grad_norm": 0.4456328749656677,
    "learning_rate": 0.00022032121639112707,
    "epoch": 0.9898477157360406,
    "step": 780
  },
  {
    "eval_loss": 0.08206839114427567,
    "eval_runtime": 9.5084,
    "eval_samples_per_second": 139.561,
    "eval_steps_per_second": 34.917,
    "epoch": 0.9961928934010152,
    "step": 785
  },
  {
    "loss": 0.0885,
    "grad_norm": 0.3194786608219147,
    "learning_rate": 0.0002161415852833438,
    "epoch": 1.00253807106599,
    "step": 790
  },
  {
    "loss": 0.0613,
    "grad_norm": 0.3748820722103119,
    "learning_rate": 0.00021195484553769228,
    "epoch": 1.015228426395939,
    "step": 800
  },
  {
    "loss": 0.0608,
    "grad_norm": 0.4187680780887604,
    "learning_rate": 0.00020776284096419353,
    "epoch": 1.0279187817258884,
    "step": 810
  },
  {
    "loss": 0.0511,
    "grad_norm": 0.29912981390953064,
    "learning_rate": 0.0002035674176914609,
    "epoch": 1.0406091370558375,
    "step": 820
  },
  {
    "loss": 0.052,
    "grad_norm": 0.538901150226593,
    "learning_rate": 0.0001993704233536781,
    "epoch": 1.0532994923857868,
    "step": 830
  },
  {
    "loss": 0.0583,
    "grad_norm": 0.33813655376434326,
    "learning_rate": 0.00019517370627691454,
    "epoch": 1.0659898477157361,
    "step": 840
  },
  {
    "loss": 0.064,
    "grad_norm": 0.43808960914611816,
    "learning_rate": 0.00019097911466513606,
    "epoch": 1.0786802030456852,
    "step": 850
  },
  {
    "loss": 0.0644,
    "grad_norm": 0.34947964549064636,
    "learning_rate": 0.0001867884957862689,
    "epoch": 1.0913705583756346,
    "step": 860
  },
  {
    "loss": 0.0541,
    "grad_norm": 0.3377130627632141,
    "learning_rate": 0.0001826036951586764,
    "epoch": 1.1040609137055837,
    "step": 870
  },
  {
    "loss": 0.0585,
    "grad_norm": 0.5515534281730652,
    "learning_rate": 0.00017842655573840587,
    "epoch": 1.116751269035533,
    "step": 880
  },
  {
    "loss": 0.0499,
    "grad_norm": 0.37032851576805115,
    "learning_rate": 0.00017425891710756437,
    "epoch": 1.1294416243654823,
    "step": 890
  },
  {
    "loss": 0.0537,
    "grad_norm": 0.439820796251297,
    "learning_rate": 0.00017010261466417936,
    "epoch": 1.1421319796954315,
    "step": 900
  },
  {
    "loss": 0.053,
    "grad_norm": 0.47381657361984253,
    "learning_rate": 0.00016595947881390327,
    "epoch": 1.1548223350253808,
    "step": 910
  },
  {
    "loss": 0.0576,
    "grad_norm": 0.33624354004859924,
    "learning_rate": 0.00016183133416391573,
    "epoch": 1.16751269035533,
    "step": 920
  },
  {
    "loss": 0.0544,
    "grad_norm": 0.4324477016925812,
    "learning_rate": 0.00015771999871937964,
    "epoch": 1.1802030456852792,
    "step": 930
  },
  {
    "loss": 0.0562,
    "grad_norm": 0.48575344681739807,
    "learning_rate": 0.00015362728308280528,
    "epoch": 1.1928934010152283,
    "step": 940
  },
  {
    "eval_loss": 0.07984930276870728,
    "eval_runtime": 9.6222,
    "eval_samples_per_second": 137.91,
    "eval_steps_per_second": 34.504,
    "epoch": 1.1954314720812182,
    "step": 942
  },
  {
    "loss": 0.0556,
    "grad_norm": 0.3980204463005066,
    "learning_rate": 0.0001495549896566732,
    "epoch": 1.2055837563451777,
    "step": 950
  },
  {
    "loss": 0.0525,
    "grad_norm": 0.40248578786849976,
    "learning_rate": 0.00014550491184966985,
    "epoch": 1.218274111675127,
    "step": 960
  },
  {
    "loss": 0.0601,
    "grad_norm": 0.4088118076324463,
    "learning_rate": 0.00014147883328688305,
    "epoch": 1.2309644670050761,
    "step": 970
  },
  {
    "loss": 0.0561,
    "grad_norm": 0.49921339750289917,
    "learning_rate": 0.00013747852702430624,
    "epoch": 1.2436548223350254,
    "step": 980
  },
  {
    "loss": 0.0584,
    "grad_norm": 0.404526948928833,
    "learning_rate": 0.0001335057547679978,
    "epoch": 1.2563451776649746,
    "step": 990
  },
  {
    "loss": 0.0575,
    "grad_norm": 0.4947160482406616,
    "learning_rate": 0.00012956226609823771,
    "epoch": 1.2690355329949239,
    "step": 1000
  },
  {
    "loss": 0.0539,
    "grad_norm": 0.40267854928970337,
    "learning_rate": 0.0001256497976990259,
    "epoch": 1.281725888324873,
    "step": 1010
  },
  {
    "loss": 0.0571,
    "grad_norm": 0.4298776686191559,
    "learning_rate": 0.00012177007259325813,
    "epoch": 1.2944162436548223,
    "step": 1020
  },
  {
    "loss": 0.0472,
    "grad_norm": 0.4440214931964874,
    "learning_rate": 0.00011792479938391988,
    "epoch": 1.3071065989847717,
    "step": 1030
  },
  {
    "loss": 0.0557,
    "grad_norm": 0.4760426878929138,
    "learning_rate": 0.00011411567150162973,
    "epoch": 1.3197969543147208,
    "step": 1040
  },
  {
    "loss": 0.0525,
    "grad_norm": 0.38695594668388367,
    "learning_rate": 0.00011034436645886447,
    "epoch": 1.33248730964467,
    "step": 1050
  },
  {
    "loss": 0.0521,
    "grad_norm": 0.4604351222515106,
    "learning_rate": 0.00010661254511119501,
    "epoch": 1.3451776649746192,
    "step": 1060
  },
  {
    "loss": 0.0514,
    "grad_norm": 0.4119158089160919,
    "learning_rate": 0.00010292185092585709,
    "epoch": 1.3578680203045685,
    "step": 1070
  },
  {
    "loss": 0.0551,
    "grad_norm": 0.48942986130714417,
    "learning_rate": 9.92739092579808e-05,
    "epoch": 1.3705583756345177,
    "step": 1080
  },
  {
    "loss": 0.0507,
    "grad_norm": 0.34124505519866943,
    "learning_rate": 9.567032663479538e-05,
    "epoch": 1.383248730964467,
    "step": 1090
  },
  {
    "eval_loss": 0.07261822372674942,
    "eval_runtime": 9.4618,
    "eval_samples_per_second": 140.248,
    "eval_steps_per_second": 35.089,
    "epoch": 1.3946700507614214,
    "step": 1099
  },
  {
    "loss": 0.0521,
    "grad_norm": 0.37472787499427795,
    "learning_rate": 9.211269004812642e-05,
    "epoch": 1.3959390862944163,
    "step": 1100
  },
  {
    "loss": 0.0521,
    "grad_norm": 0.41362205147743225,
    "learning_rate": 8.860256625549608e-05,
    "epoch": 1.4086294416243654,
    "step": 1110
  },
  {
    "loss": 0.0502,
    "grad_norm": 0.41950875520706177,
    "learning_rate": 8.514150109013415e-05,
    "epoch": 1.4213197969543148,
    "step": 1120
  },
  {
    "loss": 0.0496,
    "grad_norm": 0.42962411046028137,
    "learning_rate": 8.173101878020454e-05,
    "epoch": 1.434010152284264,
    "step": 1130
  },
  {
    "loss": 0.0531,
    "grad_norm": 0.44318121671676636,
    "learning_rate": 7.837262127754609e-05,
    "epoch": 1.4467005076142132,
    "step": 1140
  },
  {
    "loss": 0.0521,
    "grad_norm": 0.4739588797092438,
    "learning_rate": 7.50677875962237e-05,
    "epoch": 1.4593908629441623,
    "step": 1150
  },
  {
    "loss": 0.0496,
    "grad_norm": 0.47502049803733826,
    "learning_rate": 7.181797316118124e-05,
    "epoch": 1.4720812182741116,
    "step": 1160
  },
  {
    "loss": 0.0489,
    "grad_norm": 0.41291266679763794,
    "learning_rate": 6.862460916728297e-05,
    "epoch": 1.484771573604061,
    "step": 1170
  },
  {
    "loss": 0.0477,
    "grad_norm": 0.3678615689277649,
    "learning_rate": 6.548910194902538e-05,
    "epoch": 1.49746192893401,
    "step": 1180
  },
  {
    "loss": 0.0539,
    "grad_norm": 0.4368578791618347,
    "learning_rate": 6.241283236119799e-05,
    "epoch": 1.5101522842639594,
    "step": 1190
  },
  {
    "loss": 0.0471,
    "grad_norm": 0.3706371784210205,
    "learning_rate": 5.9397155170764564e-05,
    "epoch": 1.5228426395939088,
    "step": 1200
  },
  {
    "loss": 0.0546,
    "grad_norm": 0.48822730779647827,
    "learning_rate": 5.644339846023359e-05,
    "epoch": 1.5355329949238579,
    "step": 1210
  },
  {
    "loss": 0.0458,
    "grad_norm": 0.3171629011631012,
    "learning_rate": 5.35528630427804e-05,
    "epoch": 1.548223350253807,
    "step": 1220
  },
  {
    "loss": 0.0524,
    "grad_norm": 0.5258194208145142,
    "learning_rate": 5.072682188937812e-05,
    "epoch": 1.5609137055837563,
    "step": 1230
  },
  {
    "loss": 0.0439,
    "grad_norm": 0.40187448263168335,
    "learning_rate": 4.796651956819078e-05,
    "epoch": 1.5736040609137056,
    "step": 1240
  },
  {
    "loss": 0.0488,
    "grad_norm": 0.5225071310997009,
    "learning_rate": 4.527317169647434e-05,
    "epoch": 1.5862944162436547,
    "step": 1250
  },
  {
    "eval_loss": 0.06903357803821564,
    "eval_runtime": 9.4791,
    "eval_samples_per_second": 139.992,
    "eval_steps_per_second": 35.024,
    "epoch": 1.5939086294416245,
    "step": 1256
  },
  {
    "loss": 0.0469,
    "grad_norm": 0.37204620242118835,
    "learning_rate": 4.264796440522747e-05,
    "epoch": 1.598984771573604,
    "step": 1260
  },
  {
    "loss": 0.045,
    "grad_norm": 0.40722259879112244,
    "learning_rate": 4.009205381682828e-05,
    "epoch": 1.6116751269035534,
    "step": 1270
  },
  {
    "loss": 0.05,
    "grad_norm": 0.4333907663822174,
    "learning_rate": 3.760656553588591e-05,
    "epoch": 1.6243654822335025,
    "step": 1280
  },
  {
    "loss": 0.0408,
    "grad_norm": 0.3389703631401062,
    "learning_rate": 3.519259415353291e-05,
    "epoch": 1.6370558375634516,
    "step": 1290
  },
  {
    "loss": 0.0478,
    "grad_norm": 0.43472781777381897,
    "learning_rate": 3.285120276537481e-05,
    "epoch": 1.649746192893401,
    "step": 1300
  },
  {
    "loss": 0.0449,
    "grad_norm": 0.35716742277145386,
    "learning_rate": 3.058342250331063e-05,
    "epoch": 1.6624365482233503,
    "step": 1310
  },
  {
    "loss": 0.0455,
    "grad_norm": 0.419575959444046,
    "learning_rate": 2.83902520814298e-05,
    "epoch": 1.6751269035532994,
    "step": 1320
  },
  {
    "loss": 0.044,
    "grad_norm": 0.29724448919296265,
    "learning_rate": 2.627265735618549e-05,
    "epoch": 1.6878172588832487,
    "step": 1330
  },
  {
    "loss": 0.0469,
    "grad_norm": 0.4269305169582367,
    "learning_rate": 2.4231570901038868e-05,
    "epoch": 1.700507614213198,
    "step": 1340
  },
  {
    "loss": 0.0459,
    "grad_norm": 0.5313772559165955,
    "learning_rate": 2.2267891595759816e-05,
    "epoch": 1.7131979695431472,
    "step": 1350
  },
  {
    "loss": 0.0418,
    "grad_norm": 0.4228779077529907,
    "learning_rate": 2.03824842305673e-05,
    "epoch": 1.7258883248730963,
    "step": 1360
  },
  {
    "loss": 0.0476,
    "grad_norm": 0.42005908489227295,
    "learning_rate": 1.8576179125281688e-05,
    "epoch": 1.7385786802030458,
    "step": 1370
  },
  {
    "loss": 0.0477,
    "grad_norm": 0.40062543749809265,
    "learning_rate": 1.684977176365794e-05,
    "epoch": 1.751269035532995,
    "step": 1380
  },
  {
    "loss": 0.0475,
    "grad_norm": 0.4797188639640808,
    "learning_rate": 1.5204022443060472e-05,
    "epoch": 1.763959390862944,
    "step": 1390
  },
  {
    "loss": 0.0468,
    "grad_norm": 0.391634076833725,
    "learning_rate": 1.3639655939633323e-05,
    "epoch": 1.7766497461928934,
    "step": 1400
  },
  {
    "loss": 0.0489,
    "grad_norm": 0.42081767320632935,
    "learning_rate": 1.2157361189114325e-05,
    "epoch": 1.7893401015228427,
    "step": 1410
  },
  {
    "eval_loss": 0.0661860853433609,
    "eval_runtime": 9.5602,
    "eval_samples_per_second": 138.805,
    "eval_steps_per_second": 34.727,
    "epoch": 1.7931472081218274,
    "step": 1413
  },
  {
    "loss": 0.0454,
    "grad_norm": 0.46962904930114746,
    "learning_rate": 1.075779098343257e-05,
    "epoch": 1.8020304568527918,
    "step": 1420
  },
  {
    "loss": 0.0441,
    "grad_norm": 0.4605846405029297,
    "learning_rate": 9.441561683223476e-06,
    "epoch": 1.8147208121827412,
    "step": 1430
  },
  {
    "loss": 0.0414,
    "grad_norm": 0.41056081652641296,
    "learning_rate": 8.209252946388302e-06,
    "epoch": 1.8274111675126905,
    "step": 1440
  },
  {
    "loss": 0.0376,
    "grad_norm": 0.4158293902873993,
    "learning_rate": 7.0614074728166506e-06,
    "epoch": 1.8401015228426396,
    "step": 1450
  },
  {
    "loss": 0.0466,
    "grad_norm": 0.5301814675331116,
    "learning_rate": 5.9985307653855016e-06,
    "epoch": 1.8527918781725887,
    "step": 1460
  },
  {
    "loss": 0.0458,
    "grad_norm": 0.44248396158218384,
    "learning_rate": 5.021090907339488e-06,
    "epoch": 1.865482233502538,
    "step": 1470
  },
  {
    "loss": 0.0454,
    "grad_norm": 0.32068517804145813,
    "learning_rate": 4.12951835615012e-06,
    "epoch": 1.8781725888324874,
    "step": 1480
  },
  {
    "loss": 0.0453,
    "grad_norm": 0.5575969815254211,
    "learning_rate": 3.324205753945764e-06,
    "epoch": 1.8908629441624365,
    "step": 1490
  },
  {
    "loss": 0.0404,
    "grad_norm": 0.3342937231063843,
    "learning_rate": 2.605507754594605e-06,
    "epoch": 1.9035532994923858,
    "step": 1500
  },
  {
    "loss": 0.0452,
    "grad_norm": 0.516743004322052,
    "learning_rate": 1.9737408675177594e-06,
    "epoch": 1.9162436548223352,
    "step": 1510
  },
  {
    "loss": 0.0438,
    "grad_norm": 0.4447910487651825,
    "learning_rate": 1.4291833183008196e-06,
    "epoch": 1.9289340101522843,
    "step": 1520
  },
  {
    "loss": 0.0523,
    "grad_norm": 0.46259304881095886,
    "learning_rate": 9.720749261652007e-07,
    "epoch": 1.9416243654822334,
    "step": 1530
  },
  {
    "loss": 0.0463,
    "grad_norm": 0.4858075678348541,
    "learning_rate": 6.026169983536223e-07,
    "epoch": 1.9543147208121827,
    "step": 1540
  },
  {
    "loss": 0.0486,
    "grad_norm": 0.43060243129730225,
    "learning_rate": 3.209722414757588e-07,
    "epoch": 1.967005076142132,
    "step": 1550
  },
  {
    "loss": 0.0416,
    "grad_norm": 0.4320192337036133,
    "learning_rate": 1.2726468985349015e-07,
    "epoch": 1.9796954314720812,
    "step": 1560
  },
  {
    "loss": 0.0368,
    "grad_norm": 0.38553470373153687,
    "learning_rate": 2.1579650896952354e-08,
    "epoch": 1.9923857868020305,
    "step": 1570
  },
  {
    "eval_loss": 0.06596987694501877,
    "eval_runtime": 9.5315,
    "eval_samples_per_second": 139.222,
    "eval_steps_per_second": 34.832,
    "epoch": 1.9923857868020305,
    "step": 1570
  },
  {
    "train_runtime": 366.7473,
    "train_samples_per_second": 137.435,
    "train_steps_per_second": 4.297,
    "total_flos": 9515820530880000.0,
    "train_loss": 0.10226353834652659,
    "epoch": 2.0,
    "step": 1576
  }
]