[
  {
    "loss": 2.6827,
    "grad_norm": 5.949710369110107,
    "learning_rate": 1.267605633802817e-05,
    "epoch": 0.007067137809187279,
    "step": 10
  },
  {
    "loss": 1.9991,
    "grad_norm": 1.8221319913864136,
    "learning_rate": 2.676056338028169e-05,
    "epoch": 0.014134275618374558,
    "step": 20
  },
  {
    "loss": 1.7179,
    "grad_norm": 0.8600999712944031,
    "learning_rate": 4.0845070422535214e-05,
    "epoch": 0.02120141342756184,
    "step": 30
  },
  {
    "loss": 1.6038,
    "grad_norm": 0.7585324048995972,
    "learning_rate": 5.492957746478874e-05,
    "epoch": 0.028268551236749116,
    "step": 40
  },
  {
    "loss": 1.4924,
    "grad_norm": 0.7620086669921875,
    "learning_rate": 6.901408450704226e-05,
    "epoch": 0.0353356890459364,
    "step": 50
  },
  {
    "loss": 1.4182,
    "grad_norm": 0.6350599527359009,
    "learning_rate": 8.309859154929578e-05,
    "epoch": 0.04240282685512368,
    "step": 60
  },
  {
    "loss": 1.386,
    "grad_norm": 0.7683842778205872,
    "learning_rate": 9.718309859154931e-05,
    "epoch": 0.04946996466431095,
    "step": 70
  },
  {
    "loss": 1.3652,
    "grad_norm": 0.7968618273735046,
    "learning_rate": 0.00011126760563380282,
    "epoch": 0.05653710247349823,
    "step": 80
  },
  {
    "loss": 1.348,
    "grad_norm": 0.7063258290290833,
    "learning_rate": 0.00012535211267605635,
    "epoch": 0.0636042402826855,
    "step": 90
  },
  {
    "loss": 1.322,
    "grad_norm": 0.8496018052101135,
    "learning_rate": 0.00013943661971830987,
    "epoch": 0.0706713780918728,
    "step": 100
  },
  {
    "loss": 1.3119,
    "grad_norm": 0.8192782998085022,
    "learning_rate": 0.00015352112676056339,
    "epoch": 0.07773851590106007,
    "step": 110
  },
  {
    "loss": 1.2765,
    "grad_norm": 0.8431249260902405,
    "learning_rate": 0.0001676056338028169,
    "epoch": 0.08480565371024736,
    "step": 120
  },
  {
    "loss": 1.2576,
    "grad_norm": 0.6553122997283936,
    "learning_rate": 0.00018169014084507045,
    "epoch": 0.09187279151943463,
    "step": 130
  },
  {
    "loss": 1.2482,
    "grad_norm": 0.6763297915458679,
    "learning_rate": 0.00019577464788732396,
    "epoch": 0.0989399293286219,
    "step": 140
  },
  {
    "loss": 1.228,
    "grad_norm": 0.6940188407897949,
    "learning_rate": 0.00019999665339174013,
    "epoch": 0.10600706713780919,
    "step": 150
  },
  {
    "loss": 1.2421,
    "grad_norm": 0.688686728477478,
    "learning_rate": 0.00019998026238030888,
    "epoch": 0.11307420494699646,
    "step": 160
  },
  {
    "loss": 1.2332,
    "grad_norm": 0.7205774784088135,
    "learning_rate": 0.00019995021451869546,
    "epoch": 0.12014134275618374,
    "step": 170
  },
  {
    "loss": 1.2164,
    "grad_norm": 0.6336075067520142,
    "learning_rate": 0.00019990651391130147,
    "epoch": 0.127208480565371,
    "step": 180
  },
  {
    "loss": 1.2046,
    "grad_norm": 0.5959163308143616,
    "learning_rate": 0.00019984916652743156,
    "epoch": 0.13427561837455831,
    "step": 190
  },
  {
    "loss": 1.224,
    "grad_norm": 0.6479778289794922,
    "learning_rate": 0.00019977818020047817,
    "epoch": 0.1413427561837456,
    "step": 200
  },
  {
    "loss": 1.1952,
    "grad_norm": 0.6542138457298279,
    "learning_rate": 0.00019969356462685146,
    "epoch": 0.14840989399293286,
    "step": 210
  },
  {
    "loss": 1.1933,
    "grad_norm": 0.605870246887207,
    "learning_rate": 0.0001995953313646548,
    "epoch": 0.15547703180212014,
    "step": 220
  },
  {
    "loss": 1.1723,
    "grad_norm": 0.6159653067588806,
    "learning_rate": 0.0001994834938321061,
    "epoch": 0.1625441696113074,
    "step": 230
  },
  {
    "loss": 1.1641,
    "grad_norm": 0.614716649055481,
    "learning_rate": 0.00019935806730570488,
    "epoch": 0.1696113074204947,
    "step": 240
  },
  {
    "loss": 1.1679,
    "grad_norm": 0.6723307967185974,
    "learning_rate": 0.00019921906891814551,
    "epoch": 0.17667844522968199,
    "step": 250
  },
  {
    "loss": 1.1699,
    "grad_norm": 0.5286707878112793,
    "learning_rate": 0.000199066517655977,
    "epoch": 0.18374558303886926,
    "step": 260
  },
  {
    "loss": 1.1488,
    "grad_norm": 0.6386291980743408,
    "learning_rate": 0.00019890043435700954,
    "epoch": 0.19081272084805653,
    "step": 270
  },
  {
    "loss": 1.155,
    "grad_norm": 0.5279228091239929,
    "learning_rate": 0.00019872084170746829,
    "epoch": 0.1978798586572438,
    "step": 280
  },
  {
    "eval_loss": 1.1403530836105347,
    "eval_runtime": 57.7627,
    "eval_samples_per_second": 41.238,
    "eval_steps_per_second": 10.318,
    "epoch": 0.19929328621908127,
    "step": 282
  },
  {
    "loss": 1.1519,
    "grad_norm": 0.5783646106719971,
    "learning_rate": 0.0001985277642388941,
    "epoch": 0.2049469964664311,
    "step": 290
  },
  {
    "loss": 1.1458,
    "grad_norm": 0.5709810853004456,
    "learning_rate": 0.00019832122832479326,
    "epoch": 0.21201413427561838,
    "step": 300
  },
  {
    "loss": 1.1386,
    "grad_norm": 0.6111096143722534,
    "learning_rate": 0.0001981012621770344,
    "epoch": 0.21908127208480566,
    "step": 310
  },
  {
    "loss": 1.13,
    "grad_norm": 0.6752498745918274,
    "learning_rate": 0.00019786789584199524,
    "epoch": 0.22614840989399293,
    "step": 320
  },
  {
    "loss": 1.1317,
    "grad_norm": 0.590641975402832,
    "learning_rate": 0.00019762116119645818,
    "epoch": 0.2332155477031802,
    "step": 330
  },
  {
    "loss": 1.1375,
    "grad_norm": 0.5161224603652954,
    "learning_rate": 0.00019736109194325635,
    "epoch": 0.24028268551236748,
    "step": 340
  },
  {
    "loss": 1.1317,
    "grad_norm": 0.5282869338989258,
    "learning_rate": 0.00019708772360666957,
    "epoch": 0.24734982332155478,
    "step": 350
  },
  {
    "loss": 1.0828,
    "grad_norm": 0.6267129778862,
    "learning_rate": 0.00019680109352757227,
    "epoch": 0.254416961130742,
    "step": 360
  },
  {
    "loss": 1.1445,
    "grad_norm": 0.5746105313301086,
    "learning_rate": 0.0001965012408583327,
    "epoch": 0.26148409893992935,
    "step": 370
  },
  {
    "loss": 1.1146,
    "grad_norm": 0.6003304719924927,
    "learning_rate": 0.00019618820655746487,
    "epoch": 0.26855123674911663,
    "step": 380
  },
  {
    "loss": 1.1176,
    "grad_norm": 0.5761094689369202,
    "learning_rate": 0.0001958620333840339,
    "epoch": 0.2756183745583039,
    "step": 390
  },
  {
    "loss": 1.107,
    "grad_norm": 0.5851646661758423,
    "learning_rate": 0.00019552276589181522,
    "epoch": 0.2826855123674912,
    "step": 400
  },
  {
    "loss": 1.1305,
    "grad_norm": 0.603738009929657,
    "learning_rate": 0.00019517045042320892,
    "epoch": 0.28975265017667845,
    "step": 410
  },
  {
    "loss": 1.11,
    "grad_norm": 0.5267948508262634,
    "learning_rate": 0.00019480513510290934,
    "epoch": 0.2968197879858657,
    "step": 420
  },
  {
    "loss": 1.1154,
    "grad_norm": 0.569698691368103,
    "learning_rate": 0.00019442686983133168,
    "epoch": 0.303886925795053,
    "step": 430
  },
  {
    "loss": 1.0916,
    "grad_norm": 0.5906787514686584,
    "learning_rate": 0.0001940357062777956,
    "epoch": 0.31095406360424027,
    "step": 440
  },
  {
    "loss": 1.0965,
    "grad_norm": 0.563790500164032,
    "learning_rate": 0.0001936316978734676,
    "epoch": 0.31802120141342755,
    "step": 450
  },
  {
    "loss": 1.1157,
    "grad_norm": 0.5844557881355286,
    "learning_rate": 0.0001932148998040626,
    "epoch": 0.3250883392226148,
    "step": 460
  },
  {
    "loss": 1.0973,
    "grad_norm": 0.5148825645446777,
    "learning_rate": 0.00019278536900230563,
    "epoch": 0.3321554770318021,
    "step": 470
  },
  {
    "loss": 1.1128,
    "grad_norm": 0.5640899538993835,
    "learning_rate": 0.0001923431641401552,
    "epoch": 0.3392226148409894,
    "step": 480
  },
  {
    "loss": 1.1074,
    "grad_norm": 0.5463106036186218,
    "learning_rate": 0.00019188834562078902,
    "epoch": 0.3462897526501767,
    "step": 490
  },
  {
    "loss": 1.0837,
    "grad_norm": 0.5812387466430664,
    "learning_rate": 0.00019142097557035308,
    "epoch": 0.35335689045936397,
    "step": 500
  },
  {
    "loss": 1.0835,
    "grad_norm": 0.541191816329956,
    "learning_rate": 0.0001909411178294756,
    "epoch": 0.36042402826855124,
    "step": 510
  },
  {
    "loss": 1.0864,
    "grad_norm": 0.6021603941917419,
    "learning_rate": 0.0001904488379445466,
    "epoch": 0.3674911660777385,
    "step": 520
  },
  {
    "loss": 1.0724,
    "grad_norm": 0.6133444309234619,
    "learning_rate": 0.00018994420315876468,
    "epoch": 0.3745583038869258,
    "step": 530
  },
  {
    "loss": 1.0666,
    "grad_norm": 0.6168462038040161,
    "learning_rate": 0.0001894272824029518,
    "epoch": 0.38162544169611307,
    "step": 540
  },
  {
    "loss": 1.0812,
    "grad_norm": 0.5473210215568542,
    "learning_rate": 0.0001888981462861377,
    "epoch": 0.38869257950530034,
    "step": 550
  },
  {
    "loss": 1.0849,
    "grad_norm": 0.674217700958252,
    "learning_rate": 0.00018835686708591496,
    "epoch": 0.3957597173144876,
    "step": 560
  },
  {
    "eval_loss": 1.060619592666626,
    "eval_runtime": 43.4781,
    "eval_samples_per_second": 54.786,
    "eval_steps_per_second": 13.708,
    "epoch": 0.39858657243816253,
    "step": 564
  },
  {
    "loss": 1.0668,
    "grad_norm": 0.5787924528121948,
    "learning_rate": 0.00018780351873856627,
    "epoch": 0.4028268551236749,
    "step": 570
  },
  {
    "loss": 1.0726,
    "grad_norm": 0.564720869064331,
    "learning_rate": 0.00018723817682896515,
    "epoch": 0.4098939929328622,
    "step": 580
  },
  {
    "loss": 1.0729,
    "grad_norm": 0.5361018776893616,
    "learning_rate": 0.00018666091858025112,
    "epoch": 0.4169611307420495,
    "step": 590
  },
  {
    "loss": 1.0631,
    "grad_norm": 0.5667257905006409,
    "learning_rate": 0.0001860718228432817,
    "epoch": 0.42402826855123676,
    "step": 600
  },
  {
    "loss": 1.0603,
    "grad_norm": 0.5567010045051575,
    "learning_rate": 0.00018547097008586155,
    "epoch": 0.43109540636042404,
    "step": 610
  },
  {
    "loss": 1.0602,
    "grad_norm": 0.6078583002090454,
    "learning_rate": 0.00018485844238175095,
    "epoch": 0.4381625441696113,
    "step": 620
  },
  {
    "loss": 1.0553,
    "grad_norm": 0.5796458721160889,
    "learning_rate": 0.000184234323399455,
    "epoch": 0.4452296819787986,
    "step": 630
  },
  {
    "loss": 1.0742,
    "grad_norm": 0.5551220178604126,
    "learning_rate": 0.0001835986983907947,
    "epoch": 0.45229681978798586,
    "step": 640
  },
  {
    "loss": 1.0701,
    "grad_norm": 0.5546141862869263,
    "learning_rate": 0.00018295165417926207,
    "epoch": 0.45936395759717313,
    "step": 650
  },
  {
    "loss": 1.0495,
    "grad_norm": 0.752085268497467,
    "learning_rate": 0.00018229327914816052,
    "epoch": 0.4664310954063604,
    "step": 660
  },
  {
    "loss": 1.0539,
    "grad_norm": 0.514069676399231,
    "learning_rate": 0.00018162366322853191,
    "epoch": 0.4734982332155477,
    "step": 670
  },
  {
    "loss": 1.0476,
    "grad_norm": 0.545942485332489,
    "learning_rate": 0.00018094289788687245,
    "epoch": 0.48056537102473496,
    "step": 680
  },
  {
    "loss": 1.0412,
    "grad_norm": 0.5867109298706055,
    "learning_rate": 0.0001802510761126389,
    "epoch": 0.4876325088339223,
    "step": 690
  },
  {
    "loss": 1.0501,
    "grad_norm": 0.548149824142456,
    "learning_rate": 0.00017954829240554644,
    "epoch": 0.49469964664310956,
    "step": 700
  },
  {
    "loss": 1.0341,
    "grad_norm": 0.6045145988464355,
    "learning_rate": 0.00017883464276266064,
    "epoch": 0.5017667844522968,
    "step": 710
  },
  {
    "loss": 1.0359,
    "grad_norm": 0.5739872455596924,
    "learning_rate": 0.00017811022466528452,
    "epoch": 0.508833922261484,
    "step": 720
  },
  {
    "loss": 1.0478,
    "grad_norm": 0.6167759299278259,
    "learning_rate": 0.0001773751370656431,
    "epoch": 0.5159010600706714,
    "step": 730
  },
  {
    "loss": 1.077,
    "grad_norm": 0.5697989463806152,
    "learning_rate": 0.0001766294803733671,
    "epoch": 0.5229681978798587,
    "step": 740
  },
  {
    "loss": 1.0321,
    "grad_norm": 0.5935072302818298,
    "learning_rate": 0.0001758733564417773,
    "epoch": 0.5300353356890459,
    "step": 750
  },
  {
    "loss": 1.0477,
    "grad_norm": 0.571767270565033,
    "learning_rate": 0.00017510686855397176,
    "epoch": 0.5371024734982333,
    "step": 760
  },
  {
    "loss": 1.0524,
    "grad_norm": 0.6030092239379883,
    "learning_rate": 0.00017433012140871811,
    "epoch": 0.5441696113074205,
    "step": 770
  },
  {
    "loss": 1.0298,
    "grad_norm": 0.6298210024833679,
    "learning_rate": 0.00017354322110615188,
    "epoch": 0.5512367491166078,
    "step": 780
  },
  {
    "loss": 1.0295,
    "grad_norm": 0.5458575487136841,
    "learning_rate": 0.00017274627513328385,
    "epoch": 0.558303886925795,
    "step": 790
  },
  {
    "loss": 1.0273,
    "grad_norm": 0.5203152298927307,
    "learning_rate": 0.00017193939234931777,
    "epoch": 0.5653710247349824,
    "step": 800
  },
  {
    "loss": 1.0368,
    "grad_norm": 0.6097717881202698,
    "learning_rate": 0.00017112268297078077,
    "epoch": 0.5724381625441696,
    "step": 810
  },
  {
    "loss": 1.0248,
    "grad_norm": 0.5902014374732971,
    "learning_rate": 0.0001702962585564681,
    "epoch": 0.5795053003533569,
    "step": 820
  },
  {
    "loss": 1.0522,
    "grad_norm": 0.5153626799583435,
    "learning_rate": 0.00016946023199220487,
    "epoch": 0.5865724381625441,
    "step": 830
  },
  {
    "loss": 1.0479,
    "grad_norm": 0.5805534720420837,
    "learning_rate": 0.0001686147174754263,
    "epoch": 0.5936395759717314,
    "step": 840
  },
  {
    "eval_loss": 1.0175507068634033,
    "eval_runtime": 43.4082,
    "eval_samples_per_second": 54.874,
    "eval_steps_per_second": 13.73,
    "epoch": 0.5978798586572438,
    "step": 846
  },
  {
    "loss": 1.0148,
    "grad_norm": 0.5587823390960693,
    "learning_rate": 0.00016775983049957887,
    "epoch": 0.6007067137809188,
    "step": 850
  },
  {
    "loss": 1.0049,
    "grad_norm": 0.5274335741996765,
    "learning_rate": 0.0001668956878383445,
    "epoch": 0.607773851590106,
    "step": 860
  },
  {
    "loss": 1.0066,
    "grad_norm": 0.5678777694702148,
    "learning_rate": 0.0001660224075296896,
    "epoch": 0.6148409893992933,
    "step": 870
  },
  {
    "loss": 1.0076,
    "grad_norm": 0.5417252779006958,
    "learning_rate": 0.00016514010885974184,
    "epoch": 0.6219081272084805,
    "step": 880
  },
  {
    "loss": 1.026,
    "grad_norm": 0.5451430678367615,
    "learning_rate": 0.00016424891234649618,
    "epoch": 0.6289752650176679,
    "step": 890
  },
  {
    "loss": 1.007,
    "grad_norm": 0.5552809834480286,
    "learning_rate": 0.00016334893972335247,
    "epoch": 0.6360424028268551,
    "step": 900
  },
  {
    "loss": 1.0216,
    "grad_norm": 0.5455328226089478,
    "learning_rate": 0.00016244031392248748,
    "epoch": 0.6431095406360424,
    "step": 910
  },
  {
    "loss": 1.0191,
    "grad_norm": 0.5708609223365784,
    "learning_rate": 0.00016152315905806268,
    "epoch": 0.6501766784452296,
    "step": 920
  },
  {
    "loss": 1.029,
    "grad_norm": 0.5028846859931946,
    "learning_rate": 0.00016059760040927103,
    "epoch": 0.657243816254417,
    "step": 930
  },
  {
    "loss": 1.0394,
    "grad_norm": 0.5415972471237183,
    "learning_rate": 0.0001596637644032242,
    "epoch": 0.6643109540636042,
    "step": 940
  },
  {
    "loss": 1.0208,
    "grad_norm": 0.5780535936355591,
    "learning_rate": 0.00015872177859768333,
    "epoch": 0.6713780918727915,
    "step": 950
  },
  {
    "loss": 1.006,
    "grad_norm": 0.585171103477478,
    "learning_rate": 0.00015777177166363527,
    "epoch": 0.6784452296819788,
    "step": 960
  },
  {
    "loss": 0.9989,
    "grad_norm": 0.5906310677528381,
    "learning_rate": 0.00015681387336771656,
    "epoch": 0.6855123674911661,
    "step": 970
  },
  {
    "loss": 1.0085,
    "grad_norm": 0.5665215849876404,
    "learning_rate": 0.0001558482145544879,
    "epoch": 0.6925795053003534,
    "step": 980
  },
  {
    "loss": 1.0169,
    "grad_norm": 0.5841283798217773,
    "learning_rate": 0.0001548749271285616,
    "epoch": 0.6996466431095406,
    "step": 990
  },
  {
    "loss": 1.0107,
    "grad_norm": 0.508304238319397,
    "learning_rate": 0.0001538941440365837,
    "epoch": 0.7067137809187279,
    "step": 1000
  },
  {
    "loss": 1.0042,
    "grad_norm": 0.5774527192115784,
    "learning_rate": 0.00015290599924907433,
    "epoch": 0.7137809187279152,
    "step": 1010
  },
  {
    "loss": 1.0105,
    "grad_norm": 0.6468122005462646,
    "learning_rate": 0.00015191062774212773,
    "epoch": 0.7208480565371025,
    "step": 1020
  },
  {
    "loss": 1.0069,
    "grad_norm": 0.6112880110740662,
    "learning_rate": 0.0001509081654789753,
    "epoch": 0.7279151943462897,
    "step": 1030
  },
  {
    "loss": 0.9936,
    "grad_norm": 0.7022767066955566,
    "learning_rate": 0.00014989874939141351,
    "epoch": 0.734982332155477,
    "step": 1040
  },
  {
    "loss": 1.0231,
    "grad_norm": 0.5384315848350525,
    "learning_rate": 0.0001488825173610997,
    "epoch": 0.7420494699646644,
    "step": 1050
  },
  {
    "loss": 0.9907,
    "grad_norm": 0.5737187266349792,
    "learning_rate": 0.0001478596082007181,
    "epoch": 0.7491166077738516,
    "step": 1060
  },
  {
    "loss": 1.0167,
    "grad_norm": 0.5474862456321716,
    "learning_rate": 0.00014683016163501855,
    "epoch": 0.7561837455830389,
    "step": 1070
  },
  {
    "loss": 0.9965,
    "grad_norm": 0.580353319644928,
    "learning_rate": 0.0001457943182817308,
    "epoch": 0.7632508833922261,
    "step": 1080
  },
  {
    "loss": 1.02,
    "grad_norm": 0.5732952952384949,
    "learning_rate": 0.00014475221963235687,
    "epoch": 0.7703180212014135,
    "step": 1090
  },
  {
    "loss": 1.0026,
    "grad_norm": 0.5824176669120789,
    "learning_rate": 0.00014370400803284374,
    "epoch": 0.7773851590106007,
    "step": 1100
  },
  {
    "loss": 1.0063,
    "grad_norm": 0.5431606769561768,
    "learning_rate": 0.00014264982666413958,
    "epoch": 0.784452296819788,
    "step": 1110
  },
  {
    "loss": 1.0196,
    "grad_norm": 0.5714312791824341,
    "learning_rate": 0.00014158981952263608,
    "epoch": 0.7915194346289752,
    "step": 1120
  },
  {
    "eval_loss": 0.9868658185005188,
    "eval_runtime": 43.5605,
    "eval_samples_per_second": 54.683,
    "eval_steps_per_second": 13.682,
    "epoch": 0.7971731448763251,
    "step": 1128
  },
  {
    "loss": 1.0083,
    "grad_norm": 0.5832623839378357,
    "learning_rate": 0.000140524131400499,
    "epoch": 0.7985865724381626,
    "step": 1130
  },
  {
    "loss": 1.0142,
    "grad_norm": 0.5128731727600098,
    "learning_rate": 0.00013945290786589027,
    "epoch": 0.8056537102473498,
    "step": 1140
  },
  {
    "loss": 0.9984,
    "grad_norm": 0.5578513145446777,
    "learning_rate": 0.00013837629524308408,
    "epoch": 0.8127208480565371,
    "step": 1150
  },
  {
    "loss": 0.9849,
    "grad_norm": 0.6349474191665649,
    "learning_rate": 0.00013729444059247954,
    "epoch": 0.8197879858657244,
    "step": 1160
  },
  {
    "loss": 1.0082,
    "grad_norm": 0.5942397713661194,
    "learning_rate": 0.00013620749169051307,
    "epoch": 0.8268551236749117,
    "step": 1170
  },
  {
    "loss": 0.9698,
    "grad_norm": 0.5328270196914673,
    "learning_rate": 0.00013511559700947264,
    "epoch": 0.833922261484099,
    "step": 1180
  },
  {
    "loss": 1.0041,
    "grad_norm": 0.5367234945297241,
    "learning_rate": 0.00013401890569721725,
    "epoch": 0.8409893992932862,
    "step": 1190
  },
  {
    "loss": 0.9784,
    "grad_norm": 0.5053948163986206,
    "learning_rate": 0.00013291756755680388,
    "epoch": 0.8480565371024735,
    "step": 1200
  },
  {
    "loss": 0.9821,
    "grad_norm": 0.6247851252555847,
    "learning_rate": 0.00013181173302602528,
    "epoch": 0.8551236749116607,
    "step": 1210
  },
  {
    "loss": 0.9842,
    "grad_norm": 0.6302320957183838,
    "learning_rate": 0.0001307015531568606,
    "epoch": 0.8621908127208481,
    "step": 1220
  },
  {
    "loss": 0.9794,
    "grad_norm": 0.48732852935791016,
    "learning_rate": 0.00012958717959484254,
    "epoch": 0.8692579505300353,
    "step": 1230
  },
  {
    "loss": 1.0007,
    "grad_norm": 0.5459453463554382,
    "learning_rate": 0.0001284687645583432,
    "epoch": 0.8763250883392226,
    "step": 1240
  },
  {
    "loss": 0.978,
    "grad_norm": 0.6455541253089905,
    "learning_rate": 0.0001273464608177818,
    "epoch": 0.8833922261484098,
    "step": 1250
  },
  {
    "loss": 0.9907,
    "grad_norm": 0.5769440531730652,
    "learning_rate": 0.00012622042167475693,
    "epoch": 0.8904593639575972,
    "step": 1260
  },
  {
    "loss": 0.9888,
    "grad_norm": 0.5793958306312561,
    "learning_rate": 0.00012509080094110604,
    "epoch": 0.8975265017667845,
    "step": 1270
  },
  {
    "loss": 0.983,
    "grad_norm": 0.5198792815208435,
    "learning_rate": 0.00012395775291789568,
    "epoch": 0.9045936395759717,
    "step": 1280
  },
  {
    "loss": 1.0023,
    "grad_norm": 0.5861442685127258,
    "learning_rate": 0.00012282143237434478,
    "epoch": 0.911660777385159,
    "step": 1290
  },
  {
    "loss": 0.9725,
    "grad_norm": 0.594825029373169,
    "learning_rate": 0.00012168199452668341,
    "epoch": 0.9187279151943463,
    "step": 1300
  },
  {
    "loss": 0.987,
    "grad_norm": 0.5613613128662109,
    "learning_rate": 0.00012053959501695145,
    "epoch": 0.9257950530035336,
    "step": 1310
  },
  {
    "loss": 0.9891,
    "grad_norm": 0.5798191428184509,
    "learning_rate": 0.00011939438989173828,
    "epoch": 0.9328621908127208,
    "step": 1320
  },
  {
    "loss": 0.9891,
    "grad_norm": 0.5428863763809204,
    "learning_rate": 0.00011824653558086769,
    "epoch": 0.9399293286219081,
    "step": 1330
  },
  {
    "loss": 0.9865,
    "grad_norm": 0.5526650547981262,
    "learning_rate": 0.00011709618887603014,
    "epoch": 0.9469964664310954,
    "step": 1340
  },
  {
    "loss": 0.958,
    "grad_norm": 0.6232343316078186,
    "learning_rate": 0.00011594350690936581,
    "epoch": 0.9540636042402827,
    "step": 1350
  },
  {
    "loss": 1.0113,
    "grad_norm": 0.6425083875656128,
    "learning_rate": 0.00011478864713200113,
    "epoch": 0.9611307420494699,
    "step": 1360
  },
  {
    "loss": 0.9683,
    "grad_norm": 0.5667459964752197,
    "learning_rate": 0.00011363176729254146,
    "epoch": 0.9681978798586572,
    "step": 1370
  },
  {
    "loss": 0.9884,
    "grad_norm": 0.5597785115242004,
    "learning_rate": 0.00011247302541552359,
    "epoch": 0.9752650176678446,
    "step": 1380
  },
  {
    "loss": 0.9724,
    "grad_norm": 0.538309633731842,
    "learning_rate": 0.00011131257977983014,
    "epoch": 0.9823321554770318,
    "step": 1390
  },
  {
    "loss": 0.9734,
    "grad_norm": 0.5398442149162292,
    "learning_rate": 0.00011015058889706942,
    "epoch": 0.9893992932862191,
    "step": 1400
  },
  {
    "loss": 0.9643,
    "grad_norm": 0.5224325656890869,
    "learning_rate": 0.00010898721148992351,
    "epoch": 0.9964664310954063,
    "step": 1410
  },
  {
    "eval_loss": 0.9602861404418945,
    "eval_runtime": 43.2203,
    "eval_samples_per_second": 55.113,
    "eval_steps_per_second": 13.79,
    "epoch": 0.9964664310954063,
    "step": 1410
  },
  {
    "loss": 0.937,
    "grad_norm": 0.5699999928474426,
    "learning_rate": 0.00010782260647046742,
    "epoch": 1.0035335689045937,
    "step": 1420
  },
  {
    "loss": 0.8954,
    "grad_norm": 0.5502023100852966,
    "learning_rate": 0.00010665693291846244,
    "epoch": 1.010600706713781,
    "step": 1430
  },
  {
    "loss": 0.9035,
    "grad_norm": 0.5710829496383667,
    "learning_rate": 0.00010549035005962653,
    "epoch": 1.017667844522968,
    "step": 1440
  },
  {
    "loss": 0.9071,
    "grad_norm": 0.5481554865837097,
    "learning_rate": 0.00010432301724388485,
    "epoch": 1.0247349823321554,
    "step": 1450
  },
  {
    "loss": 0.9024,
    "grad_norm": 0.5516000986099243,
    "learning_rate": 0.0001031550939236033,
    "epoch": 1.0318021201413428,
    "step": 1460
  },
  {
    "loss": 0.912,
    "grad_norm": 0.5710824728012085,
    "learning_rate": 0.00010198673963180796,
    "epoch": 1.03886925795053,
    "step": 1470
  },
  {
    "loss": 0.883,
    "grad_norm": 0.5751714110374451,
    "learning_rate": 0.00010081811396039373,
    "epoch": 1.0459363957597174,
    "step": 1480
  },
  {
    "loss": 0.8968,
    "grad_norm": 0.6338666081428528,
    "learning_rate": 9.964937653832468e-05,
    "epoch": 1.0530035335689045,
    "step": 1490
  },
  {
    "loss": 0.9077,
    "grad_norm": 0.5074037313461304,
    "learning_rate": 9.848068700982955e-05,
    "epoch": 1.0600706713780919,
    "step": 1500
  },
  {
    "loss": 0.908,
    "grad_norm": 0.5829271674156189,
    "learning_rate": 9.731220501259501e-05,
    "epoch": 1.0671378091872792,
    "step": 1510
  },
  {
    "loss": 0.8943,
    "grad_norm": 0.5685243606567383,
    "learning_rate": 9.614409015595995e-05,
    "epoch": 1.0742049469964665,
    "step": 1520
  },
  {
    "loss": 0.8869,
    "grad_norm": 0.5944189429283142,
    "learning_rate": 9.497650199911341e-05,
    "epoch": 1.0812720848056536,
    "step": 1530
  },
  {
    "loss": 0.9062,
    "grad_norm": 0.5707447528839111,
    "learning_rate": 9.380960002929979e-05,
    "epoch": 1.088339222614841,
    "step": 1540
  },
  {
    "loss": 0.8912,
    "grad_norm": 0.5999617576599121,
    "learning_rate": 9.264354364003327e-05,
    "epoch": 1.0954063604240283,
    "step": 1550
  },
  {
    "loss": 0.9002,
    "grad_norm": 0.5612591505050659,
    "learning_rate": 9.147849210932571e-05,
    "epoch": 1.1024734982332156,
    "step": 1560
  },
  {
    "loss": 0.9025,
    "grad_norm": 0.6082556247711182,
    "learning_rate": 9.031460457792982e-05,
    "epoch": 1.1095406360424027,
    "step": 1570
  },
  {
    "loss": 0.9286,
    "grad_norm": 0.562528133392334,
    "learning_rate": 8.915204002760122e-05,
    "epoch": 1.11660777385159,
    "step": 1580
  },
  {
    "loss": 0.9022,
    "grad_norm": 0.5675996541976929,
    "learning_rate": 8.799095725938243e-05,
    "epoch": 1.1236749116607774,
    "step": 1590
  },
  {
    "loss": 0.8905,
    "grad_norm": 0.577520489692688,
    "learning_rate": 8.68315148719111e-05,
    "epoch": 1.1307420494699647,
    "step": 1600
  },
  {
    "loss": 0.9199,
    "grad_norm": 0.557808518409729,
    "learning_rate": 8.567387123975648e-05,
    "epoch": 1.137809187279152,
    "step": 1610
  },
  {
    "loss": 0.8856,
    "grad_norm": 0.6074324250221252,
    "learning_rate": 8.451818449178591e-05,
    "epoch": 1.1448763250883391,
    "step": 1620
  },
  {
    "loss": 0.8989,
    "grad_norm": 0.5722407102584839,
    "learning_rate": 8.336461248956522e-05,
    "epoch": 1.1519434628975265,
    "step": 1630
  },
  {
    "loss": 0.8872,
    "grad_norm": 0.5413146615028381,
    "learning_rate": 8.221331280579564e-05,
    "epoch": 1.1590106007067138,
    "step": 1640
  },
  {
    "loss": 0.8896,
    "grad_norm": 0.569531261920929,
    "learning_rate": 8.106444270278999e-05,
    "epoch": 1.1660777385159011,
    "step": 1650
  },
  {
    "loss": 0.905,
    "grad_norm": 0.5654504299163818,
    "learning_rate": 7.991815911099126e-05,
    "epoch": 1.1731448763250882,
    "step": 1660
  },
  {
    "loss": 0.9112,
    "grad_norm": 0.5890611410140991,
    "learning_rate": 7.877461860753697e-05,
    "epoch": 1.1802120141342756,
    "step": 1670
  },
  {
    "loss": 0.8988,
    "grad_norm": 0.5833044052124023,
    "learning_rate": 7.763397739487098e-05,
    "epoch": 1.187279151943463,
    "step": 1680
  },
  {
    "loss": 0.9063,
    "grad_norm": 0.6019202470779419,
    "learning_rate": 7.649639127940735e-05,
    "epoch": 1.1943462897526502,
    "step": 1690
  },
  {
    "eval_loss": 0.947350263595581,
    "eval_runtime": 43.7059,
    "eval_samples_per_second": 54.501,
    "eval_steps_per_second": 13.637,
    "epoch": 1.1957597173144876,
    "step": 1692
  },
  {
    "loss": 0.8976,
    "grad_norm": 0.5837628841400146,
    "learning_rate": 7.536201565024767e-05,
    "epoch": 1.2014134275618376,
    "step": 1700
  },
  {
    "loss": 0.8992,
    "grad_norm": 0.8743357062339783,
    "learning_rate": 7.423100545795565e-05,
    "epoch": 1.2084805653710247,
    "step": 1710
  },
  {
    "loss": 0.8933,
    "grad_norm": 0.6327987313270569,
    "learning_rate": 7.310351519339165e-05,
    "epoch": 1.215547703180212,
    "step": 1720
  },
  {
    "loss": 0.9088,
    "grad_norm": 0.5537572503089905,
    "learning_rate": 7.197969886660984e-05,
    "epoch": 1.2226148409893993,
    "step": 1730
  },
  {
    "loss": 0.8975,
    "grad_norm": 0.5983340740203857,
    "learning_rate": 7.085970998582112e-05,
    "epoch": 1.2296819787985867,
    "step": 1740
  },
  {
    "loss": 0.9015,
    "grad_norm": 0.5243608355522156,
    "learning_rate": 6.974370153642468e-05,
    "epoch": 1.2367491166077738,
    "step": 1750
  },
  {
    "loss": 0.8847,
    "grad_norm": 0.5976786017417908,
    "learning_rate": 6.863182596011087e-05,
    "epoch": 1.243816254416961,
    "step": 1760
  },
  {
    "loss": 0.8904,
    "grad_norm": 0.5367252826690674,
    "learning_rate": 6.752423513403824e-05,
    "epoch": 1.2508833922261484,
    "step": 1770
  },
  {
    "loss": 0.9066,
    "grad_norm": 0.5782431960105896,
    "learning_rate": 6.642108035008803e-05,
    "epoch": 1.2579505300353357,
    "step": 1780
  },
  {
    "loss": 0.8915,
    "grad_norm": 0.6352420449256897,
    "learning_rate": 6.53225122941981e-05,
    "epoch": 1.265017667844523,
    "step": 1790
  },
  {
    "loss": 0.8916,
    "grad_norm": 0.6211472749710083,
    "learning_rate": 6.422868102578018e-05,
    "epoch": 1.2720848056537102,
    "step": 1800
  },
  {
    "loss": 0.8769,
    "grad_norm": 0.5358094573020935,
    "learning_rate": 6.31397359572223e-05,
    "epoch": 1.2791519434628975,
    "step": 1810
  },
  {
    "loss": 0.8657,
    "grad_norm": 0.5707045197486877,
    "learning_rate": 6.205582583347974e-05,
    "epoch": 1.2862190812720848,
    "step": 1820
  },
  {
    "loss": 0.873,
    "grad_norm": 0.6060373187065125,
    "learning_rate": 6.097709871175723e-05,
    "epoch": 1.293286219081272,
    "step": 1830
  },
  {
    "loss": 0.8954,
    "grad_norm": 0.5479307174682617,
    "learning_rate": 5.990370194128479e-05,
    "epoch": 1.3003533568904593,
    "step": 1840
  },
  {
    "loss": 0.8849,
    "grad_norm": 0.5866280794143677,
    "learning_rate": 5.88357821431908e-05,
    "epoch": 1.3074204946996466,
    "step": 1850
  },
  {
    "loss": 0.882,
    "grad_norm": 0.6369838714599609,
    "learning_rate": 5.7773485190474044e-05,
    "epoch": 1.314487632508834,
    "step": 1860
  },
  {
    "loss": 0.8863,
    "grad_norm": 0.5785922408103943,
    "learning_rate": 5.671695618807802e-05,
    "epoch": 1.3215547703180213,
    "step": 1870
  },
  {
    "loss": 0.9007,
    "grad_norm": 0.6535210609436035,
    "learning_rate": 5.566633945307052e-05,
    "epoch": 1.3286219081272086,
    "step": 1880
  },
  {
    "loss": 0.8863,
    "grad_norm": 0.5599955320358276,
    "learning_rate": 5.4621778494930397e-05,
    "epoch": 1.3356890459363957,
    "step": 1890
  },
  {
    "loss": 0.8949,
    "grad_norm": 0.6138301491737366,
    "learning_rate": 5.358341599594483e-05,
    "epoch": 1.342756183745583,
    "step": 1900
  },
  {
    "loss": 0.8629,
    "grad_norm": 0.5357041358947754,
    "learning_rate": 5.255139379171967e-05,
    "epoch": 1.3498233215547704,
    "step": 1910
  },
  {
    "loss": 0.8977,
    "grad_norm": 0.5802581310272217,
    "learning_rate": 5.152585285180517e-05,
    "epoch": 1.3568904593639575,
    "step": 1920
  },
  {
    "loss": 0.8614,
    "grad_norm": 0.6308375597000122,
    "learning_rate": 5.050693326044036e-05,
    "epoch": 1.3639575971731448,
    "step": 1930
  },
  {
    "loss": 0.8656,
    "grad_norm": 0.6286219358444214,
    "learning_rate": 4.949477419741814e-05,
    "epoch": 1.3710247349823321,
    "step": 1940
  },
  {
    "loss": 0.8775,
    "grad_norm": 0.5799056887626648,
    "learning_rate": 4.848951391907377e-05,
    "epoch": 1.3780918727915195,
    "step": 1950
  },
  {
    "loss": 0.8773,
    "grad_norm": 0.5816202163696289,
    "learning_rate": 4.749128973940001e-05,
    "epoch": 1.3851590106007068,
    "step": 1960
  },
  {
    "loss": 0.9143,
    "grad_norm": 0.540955126285553,
    "learning_rate": 4.6500238011290295e-05,
    "epoch": 1.3922261484098941,
    "step": 1970
  },
  {
    "eval_loss": 0.931702196598053,
    "eval_runtime": 43.3565,
    "eval_samples_per_second": 54.94,
    "eval_steps_per_second": 13.747,
    "epoch": 1.3950530035335689,
    "step": 1974
  },
  {
    "loss": 0.8762,
    "grad_norm": 0.577583372592926,
    "learning_rate": 4.551649410791384e-05,
    "epoch": 1.3992932862190812,
    "step": 1980
  },
  {
    "loss": 0.8779,
    "grad_norm": 0.5985121130943298,
    "learning_rate": 4.454019240422412e-05,
    "epoch": 1.4063604240282686,
    "step": 1990
  },
  {
    "loss": 0.8721,
    "grad_norm": 0.6050156354904175,
    "learning_rate": 4.357146625860391e-05,
    "epoch": 1.4134275618374559,
    "step": 2000
  },
  {
    "loss": 0.9011,
    "grad_norm": 0.5412665605545044,
    "learning_rate": 4.261044799464915e-05,
    "epoch": 1.420494699646643,
    "step": 2010
  },
  {
    "loss": 0.8794,
    "grad_norm": 0.5395935773849487,
    "learning_rate": 4.165726888309402e-05,
    "epoch": 1.4275618374558303,
    "step": 2020
  },
  {
    "loss": 0.9012,
    "grad_norm": 0.5516586899757385,
    "learning_rate": 4.0712059123880155e-05,
    "epoch": 1.4346289752650176,
    "step": 2030
  },
  {
    "loss": 0.874,
    "grad_norm": 0.5666341781616211,
    "learning_rate": 3.977494782837182e-05,
    "epoch": 1.441696113074205,
    "step": 2040
  },
  {
    "loss": 0.8642,
    "grad_norm": 0.6185910701751709,
    "learning_rate": 3.884606300171979e-05,
    "epoch": 1.4487632508833923,
    "step": 2050
  },
  {
    "loss": 0.8902,
    "grad_norm": 0.5560716390609741,
    "learning_rate": 3.7925531525376623e-05,
    "epoch": 1.4558303886925796,
    "step": 2060
  },
  {
    "loss": 0.8892,
    "grad_norm": 0.6083916425704956,
    "learning_rate": 3.7013479139765115e-05,
    "epoch": 1.4628975265017667,
    "step": 2070
  },
  {
    "loss": 0.8664,
    "grad_norm": 0.5855932235717773,
    "learning_rate": 3.611003042710266e-05,
    "epoch": 1.469964664310954,
    "step": 2080
  },
  {
    "loss": 0.8864,
    "grad_norm": 0.5607093572616577,
    "learning_rate": 3.521530879438407e-05,
    "epoch": 1.4770318021201414,
    "step": 2090
  },
  {
    "loss": 0.8797,
    "grad_norm": 0.6089926958084106,
    "learning_rate": 3.432943645652453e-05,
    "epoch": 1.4840989399293285,
    "step": 2100
  },
  {
    "loss": 0.8788,
    "grad_norm": 0.5762563347816467,
    "learning_rate": 3.345253441966579e-05,
    "epoch": 1.4911660777385158,
    "step": 2110
  },
  {
    "loss": 0.8829,
    "grad_norm": 0.6184695959091187,
    "learning_rate": 3.258472246464717e-05,
    "epoch": 1.4982332155477032,
    "step": 2120
  },
  {
    "loss": 0.886,
    "grad_norm": 0.6246795058250427,
    "learning_rate": 3.172611913064402e-05,
    "epoch": 1.5053003533568905,
    "step": 2130
  },
  {
    "loss": 0.8844,
    "grad_norm": 0.5603175759315491,
    "learning_rate": 3.087684169897588e-05,
    "epoch": 1.5123674911660778,
    "step": 2140
  },
  {
    "loss": 0.8683,
    "grad_norm": 0.584713876247406,
    "learning_rate": 3.0037006177086346e-05,
    "epoch": 1.5194346289752652,
    "step": 2150
  },
  {
    "loss": 0.8423,
    "grad_norm": 0.588035523891449,
    "learning_rate": 2.920672728269692e-05,
    "epoch": 1.5265017667844523,
    "step": 2160
  },
  {
    "loss": 0.8753,
    "grad_norm": 0.7277367115020752,
    "learning_rate": 2.8386118428137254e-05,
    "epoch": 1.5335689045936396,
    "step": 2170
  },
  {
    "loss": 0.8689,
    "grad_norm": 0.7008647322654724,
    "learning_rate": 2.7575291704853323e-05,
    "epoch": 1.5406360424028267,
    "step": 2180
  },
  {
    "loss": 0.8794,
    "grad_norm": 0.6551691293716431,
    "learning_rate": 2.6774357868096432e-05,
    "epoch": 1.547703180212014,
    "step": 2190
  },
  {
    "loss": 0.8603,
    "grad_norm": 0.6580778360366821,
    "learning_rate": 2.5983426321794502e-05,
    "epoch": 1.5547703180212014,
    "step": 2200
  },
  {
    "loss": 0.8857,
    "grad_norm": 0.5846377611160278,
    "learning_rate": 2.5202605103607835e-05,
    "epoch": 1.5618374558303887,
    "step": 2210
  },
  {
    "loss": 0.8651,
    "grad_norm": 0.6134793162345886,
    "learning_rate": 2.443200087017192e-05,
    "epoch": 1.568904593639576,
    "step": 2220
  },
  {
    "loss": 0.8777,
    "grad_norm": 0.5883351564407349,
    "learning_rate": 2.3671718882528437e-05,
    "epoch": 1.5759717314487633,
    "step": 2230
  },
  {
    "loss": 0.8675,
    "grad_norm": 0.623563289642334,
    "learning_rate": 2.292186299174712e-05,
    "epoch": 1.5830388692579507,
    "step": 2240
  },
  {
    "loss": 0.8723,
    "grad_norm": 0.641573965549469,
    "learning_rate": 2.218253562474023e-05,
    "epoch": 1.5901060070671378,
    "step": 2250
  },
  {
    "eval_loss": 0.9208451509475708,
    "eval_runtime": 43.8208,
    "eval_samples_per_second": 54.358,
    "eval_steps_per_second": 13.601,
    "epoch": 1.5943462897526501,
    "step": 2256
  },
  {
    "loss": 0.8811,
    "grad_norm": 0.5773902535438538,
    "learning_rate": 2.1453837770271334e-05,
    "epoch": 1.5971731448763251,
    "step": 2260
  },
  {
    "loss": 0.8775,
    "grad_norm": 0.5559404492378235,
    "learning_rate": 2.0735868965160953e-05,
    "epoch": 1.6042402826855122,
    "step": 2270
  },
  {
    "loss": 0.8719,
    "grad_norm": 0.5846749544143677,
    "learning_rate": 2.0028727280690107e-05,
    "epoch": 1.6113074204946995,
    "step": 2280
  },
  {
    "loss": 0.8721,
    "grad_norm": 0.6338834166526794,
    "learning_rate": 1.9332509309204183e-05,
    "epoch": 1.6183745583038869,
    "step": 2290
  },
  {
    "loss": 0.8764,
    "grad_norm": 0.5955981016159058,
    "learning_rate": 1.8647310150919083e-05,
    "epoch": 1.6254416961130742,
    "step": 2300
  },
  {
    "loss": 0.8706,
    "grad_norm": 0.5912985801696777,
    "learning_rate": 1.797322340093067e-05,
    "epoch": 1.6325088339222615,
    "step": 2310
  },
  {
    "loss": 0.8508,
    "grad_norm": 0.649738073348999,
    "learning_rate": 1.7310341136430385e-05,
    "epoch": 1.6395759717314489,
    "step": 2320
  },
  {
    "loss": 0.8796,
    "grad_norm": 0.6230898499488831,
    "learning_rate": 1.6658753904127734e-05,
    "epoch": 1.6466431095406362,
    "step": 2330
  },
  {
    "loss": 0.8691,
    "grad_norm": 0.6647538542747498,
    "learning_rate": 1.6018550707882062e-05,
    "epoch": 1.6537102473498233,
    "step": 2340
  },
  {
    "loss": 0.8804,
    "grad_norm": 0.6123314499855042,
    "learning_rate": 1.538981899654508e-05,
    "epoch": 1.6607773851590106,
    "step": 2350
  },
  {
    "loss": 0.87,
    "grad_norm": 0.6355293393135071,
    "learning_rate": 1.477264465201572e-05,
    "epoch": 1.6678445229681977,
    "step": 2360
  },
  {
    "loss": 0.8661,
    "grad_norm": 0.5558314323425293,
    "learning_rate": 1.4167111977508973e-05,
    "epoch": 1.674911660777385,
    "step": 2370
  },
  {
    "loss": 0.8525,
    "grad_norm": 0.5967123508453369,
    "learning_rate": 1.3573303686040628e-05,
    "epoch": 1.6819787985865724,
    "step": 2380
  },
  {
    "loss": 0.8647,
    "grad_norm": 0.5779529213905334,
    "learning_rate": 1.2991300889128866e-05,
    "epoch": 1.6890459363957597,
    "step": 2390
  },
  {
    "loss": 0.8794,
    "grad_norm": 0.5755199790000916,
    "learning_rate": 1.2421183085714927e-05,
    "epoch": 1.696113074204947,
    "step": 2400
  },
  {
    "loss": 0.861,
    "grad_norm": 0.5797527432441711,
    "learning_rate": 1.1863028151303879e-05,
    "epoch": 1.7031802120141344,
    "step": 2410
  },
  {
    "loss": 0.8714,
    "grad_norm": 0.5963758826255798,
    "learning_rate": 1.13169123273271e-05,
    "epoch": 1.7102473498233217,
    "step": 2420
  },
  {
    "loss": 0.8771,
    "grad_norm": 0.5919273495674133,
    "learning_rate": 1.078291021072817e-05,
    "epoch": 1.7173144876325088,
    "step": 2430
  },
  {
    "loss": 0.8706,
    "grad_norm": 0.5632163882255554,
    "learning_rate": 1.0261094743773203e-05,
    "epoch": 1.7243816254416962,
    "step": 2440
  },
  {
    "loss": 0.8718,
    "grad_norm": 0.5939465761184692,
    "learning_rate": 9.751537204087258e-06,
    "epoch": 1.7314487632508833,
    "step": 2450
  },
  {
    "loss": 0.8648,
    "grad_norm": 0.5735843777656555,
    "learning_rate": 9.254307194918144e-06,
    "epoch": 1.7385159010600706,
    "step": 2460
  },
  {
    "loss": 0.8638,
    "grad_norm": 0.5408446192741394,
    "learning_rate": 8.769472635628905e-06,
    "epoch": 1.745583038869258,
    "step": 2470
  },
  {
    "loss": 0.8692,
    "grad_norm": 0.5887193083763123,
    "learning_rate": 8.297099752420446e-06,
    "epoch": 1.7526501766784452,
    "step": 2480
  },
  {
    "loss": 0.8852,
    "grad_norm": 0.5828359127044678,
    "learning_rate": 7.837253069285234e-06,
    "epoch": 1.7597173144876326,
    "step": 2490
  },
  {
    "loss": 0.8688,
    "grad_norm": 0.5949276685714722,
    "learning_rate": 7.389995399193595e-06,
    "epoch": 1.76678445229682,
    "step": 2500
  },
  {
    "loss": 0.8574,
    "grad_norm": 0.5560010075569153,
    "learning_rate": 6.9553878355138936e-06,
    "epoch": 1.773851590106007,
    "step": 2510
  },
  {
    "loss": 0.8739,
    "grad_norm": 0.6576620936393738,
    "learning_rate": 6.5334897436672535e-06,
    "epoch": 1.7809187279151943,
    "step": 2520
  },
  {
    "loss": 0.8664,
    "grad_norm": 0.6786220669746399,
    "learning_rate": 6.124358753018689e-06,
    "epoch": 1.7879858657243817,
    "step": 2530
  },
  {
    "eval_loss": 0.9149619936943054,
    "eval_runtime": 46.9648,
    "eval_samples_per_second": 50.719,
    "eval_steps_per_second": 12.69,
    "epoch": 1.7936395759717314,
    "step": 2538
  },
  {
    "loss": 0.8505,
    "grad_norm": 0.5556807518005371,
    "learning_rate": 5.7280507490050985e-06,
    "epoch": 1.7950530035335688,
    "step": 2540
  },
  {
    "loss": 0.8581,
    "grad_norm": 0.6154960989952087,
    "learning_rate": 5.3446198655015765e-06,
    "epoch": 1.802120141342756,
    "step": 2550
  },
  {
    "loss": 0.8708,
    "grad_norm": 0.6271000504493713,
    "learning_rate": 4.974118477426992e-06,
    "epoch": 1.8091872791519434,
    "step": 2560
  },
  {
    "loss": 0.8619,
    "grad_norm": 0.718324601650238,
    "learning_rate": 4.616597193589833e-06,
    "epoch": 1.8162544169611308,
    "step": 2570
  },
  {
    "loss": 0.8619,
    "grad_norm": 0.5940812230110168,
    "learning_rate": 4.272104849775216e-06,
    "epoch": 1.823321554770318,
    "step": 2580
  },
  {
    "loss": 0.8621,
    "grad_norm": 0.539251983165741,
    "learning_rate": 3.940688502074186e-06,
    "epoch": 1.8303886925795054,
    "step": 2590
  },
  {
    "loss": 0.8574,
    "grad_norm": 0.6987637281417847,
    "learning_rate": 3.622393420456016e-06,
    "epoch": 1.8374558303886925,
    "step": 2600
  },
  {
    "loss": 0.8659,
    "grad_norm": 0.5573965311050415,
    "learning_rate": 3.3172630825846095e-06,
    "epoch": 1.8445229681978799,
    "step": 2610
  },
  {
    "loss": 0.8674,
    "grad_norm": 0.5907488465309143,
    "learning_rate": 3.025339167879615e-06,
    "epoch": 1.851590106007067,
    "step": 2620
  },
  {
    "loss": 0.8551,
    "grad_norm": 0.6165907382965088,
    "learning_rate": 2.7466615518231486e-06,
    "epoch": 1.8586572438162543,
    "step": 2630
  },
  {
    "loss": 0.8617,
    "grad_norm": 0.5819846391677856,
    "learning_rate": 2.4812683005130843e-06,
    "epoch": 1.8657243816254416,
    "step": 2640
  },
  {
    "loss": 0.8544,
    "grad_norm": 0.5709139108657837,
    "learning_rate": 2.229195665463324e-06,
    "epoch": 1.872791519434629,
    "step": 2650
  },
  {
    "loss": 0.8475,
    "grad_norm": 0.687758207321167,
    "learning_rate": 1.990478078652047e-06,
    "epoch": 1.8798586572438163,
    "step": 2660
  },
  {
    "loss": 0.8617,
    "grad_norm": 0.5966079831123352,
    "learning_rate": 1.7651481478184296e-06,
    "epoch": 1.8869257950530036,
    "step": 2670
  },
  {
    "loss": 0.8681,
    "grad_norm": 0.5431429743766785,
    "learning_rate": 1.553236652008605e-06,
    "epoch": 1.893992932862191,
    "step": 2680
  },
  {
    "loss": 0.8618,
    "grad_norm": 0.6142215728759766,
    "learning_rate": 1.3547725373713405e-06,
    "epoch": 1.901060070671378,
    "step": 2690
  },
  {
    "loss": 0.8654,
    "grad_norm": 0.5876252055168152,
    "learning_rate": 1.169782913204176e-06,
    "epoch": 1.9081272084805654,
    "step": 2700
  },
  {
    "loss": 0.8492,
    "grad_norm": 0.5388440489768982,
    "learning_rate": 9.98293048250376e-07,
    "epoch": 1.9151943462897525,
    "step": 2710
  },
  {
    "loss": 0.8666,
    "grad_norm": 0.6419453620910645,
    "learning_rate": 8.403263672473793e-07,
    "epoch": 1.9222614840989398,
    "step": 2720
  },
  {
    "loss": 0.8654,
    "grad_norm": 0.5551348328590393,
    "learning_rate": 6.959044477270138e-07,
    "epoch": 1.9293286219081272,
    "step": 2730
  },
  {
    "loss": 0.8681,
    "grad_norm": 0.5783069133758545,
    "learning_rate": 5.650470170681876e-07,
    "epoch": 1.9363957597173145,
    "step": 2740
  },
  {
    "loss": 0.8661,
    "grad_norm": 0.579828143119812,
    "learning_rate": 4.477719498021782e-07,
    "epoch": 1.9434628975265018,
    "step": 2750
  },
  {
    "loss": 0.8518,
    "grad_norm": 0.6109597682952881,
    "learning_rate": 3.440952651710072e-07,
    "epoch": 1.9505300353356891,
    "step": 2760
  },
  {
    "loss": 0.8649,
    "grad_norm": 0.5834357738494873,
    "learning_rate": 2.540311249393912e-07,
    "epoch": 1.9575971731448765,
    "step": 2770
  },
  {
    "loss": 0.8595,
    "grad_norm": 0.5844215750694275,
    "learning_rate": 1.7759183146021096e-07,
    "epoch": 1.9646643109540636,
    "step": 2780
  },
  {
    "loss": 0.8602,
    "grad_norm": 0.6017207503318787,
    "learning_rate": 1.1478782599411153e-07,
    "epoch": 1.971731448763251,
    "step": 2790
  },
  {
    "loss": 0.8555,
    "grad_norm": 0.60943603515625,
    "learning_rate": 6.562768728327618e-08,
    "epoch": 1.978798586572438,
    "step": 2800
  },
  {
    "loss": 0.86,
    "grad_norm": 0.5658397078514099,
    "learning_rate": 3.0118130379575005e-08,
    "epoch": 1.9858657243816253,
    "step": 2810
  },
  {
    "loss": 0.8591,
    "grad_norm": 0.5758052468299866,
    "learning_rate": 8.2640057273764e-09,
    "epoch": 1.9929328621908127,
    "step": 2820
  },
  {
    "eval_loss": 0.9138538241386414,
    "eval_runtime": 43.3799,
    "eval_samples_per_second": 54.91,
    "eval_steps_per_second": 13.739,
    "epoch": 1.9929328621908127,
    "step": 2820
  },
  {
    "loss": 0.8452,
    "grad_norm": 1.4162325859069824,
    "learning_rate": 6.829850092149315e-11,
    "epoch": 2.0,
    "step": 2830
  },
  {
    "train_runtime": 3925.8146,
    "train_samples_per_second": 23.055,
    "train_steps_per_second": 0.721,
    "total_flos": 4.463337713824443e+17,
    "train_loss": 0.9908652207876684,
    "epoch": 2.0,
    "step": 2830
  }
]