{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9990828492815653,
  "eval_steps": 500,
  "global_step": 817,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012228676245796392,
      "grad_norm": 1.6473579833541931,
      "learning_rate": 1.2195121951219513e-05,
      "loss": 1.3725,
      "step": 1
    },
    {
      "epoch": 0.006114338122898196,
      "grad_norm": 1.527729602912934,
      "learning_rate": 6.097560975609756e-05,
      "loss": 1.3787,
      "step": 5
    },
    {
      "epoch": 0.012228676245796393,
      "grad_norm": 1.5736263638617907,
      "learning_rate": 0.00012195121951219512,
      "loss": 1.3231,
      "step": 10
    },
    {
      "epoch": 0.01834301436869459,
      "grad_norm": 0.5769364715702556,
      "learning_rate": 0.00018292682926829268,
      "loss": 1.2224,
      "step": 15
    },
    {
      "epoch": 0.024457352491592785,
      "grad_norm": 0.4139930056267442,
      "learning_rate": 0.00024390243902439024,
      "loss": 1.1395,
      "step": 20
    },
    {
      "epoch": 0.03057169061449098,
      "grad_norm": 0.262099130716011,
      "learning_rate": 0.0003048780487804878,
      "loss": 1.0913,
      "step": 25
    },
    {
      "epoch": 0.03668602873738918,
      "grad_norm": 0.15253051567021142,
      "learning_rate": 0.00036585365853658537,
      "loss": 1.0795,
      "step": 30
    },
    {
      "epoch": 0.042800366860287375,
      "grad_norm": 0.1464835767250418,
      "learning_rate": 0.0004268292682926829,
      "loss": 1.0587,
      "step": 35
    },
    {
      "epoch": 0.04891470498318557,
      "grad_norm": 0.12891302801103366,
      "learning_rate": 0.0004878048780487805,
      "loss": 1.0502,
      "step": 40
    },
    {
      "epoch": 0.055029043106083766,
      "grad_norm": 0.1085934848109559,
      "learning_rate": 0.0005487804878048781,
      "loss": 1.0451,
      "step": 45
    },
    {
      "epoch": 0.06114338122898196,
      "grad_norm": 0.1226751965745002,
      "learning_rate": 0.0006097560975609756,
      "loss": 1.0181,
      "step": 50
    },
    {
      "epoch": 0.06725771935188016,
      "grad_norm": 0.1203151628753708,
      "learning_rate": 0.0006707317073170732,
      "loss": 1.0252,
      "step": 55
    },
    {
      "epoch": 0.07337205747477836,
      "grad_norm": 0.13789018529599276,
      "learning_rate": 0.0007317073170731707,
      "loss": 1.0093,
      "step": 60
    },
    {
      "epoch": 0.07948639559767655,
      "grad_norm": 0.12826204349422166,
      "learning_rate": 0.0007926829268292683,
      "loss": 1.0131,
      "step": 65
    },
    {
      "epoch": 0.08560073372057475,
      "grad_norm": 0.1364465428872305,
      "learning_rate": 0.0008536585365853659,
      "loss": 0.9985,
      "step": 70
    },
    {
      "epoch": 0.09171507184347294,
      "grad_norm": 0.14196429462926946,
      "learning_rate": 0.0009146341463414635,
      "loss": 0.9959,
      "step": 75
    },
    {
      "epoch": 0.09782940996637114,
      "grad_norm": 0.12106099937186893,
      "learning_rate": 0.000975609756097561,
      "loss": 1.0092,
      "step": 80
    },
    {
      "epoch": 0.10394374808926933,
      "grad_norm": 0.18450188337900664,
      "learning_rate": 0.0009999588943391596,
      "loss": 0.9995,
      "step": 85
    },
    {
      "epoch": 0.11005808621216753,
      "grad_norm": 0.14339050170878104,
      "learning_rate": 0.0009997077175540067,
      "loss": 0.9967,
      "step": 90
    },
    {
      "epoch": 0.11617242433506574,
      "grad_norm": 0.14026732631424904,
      "learning_rate": 0.0009992283150399447,
      "loss": 0.9929,
      "step": 95
    },
    {
      "epoch": 0.12228676245796392,
      "grad_norm": 0.1432651360969384,
      "learning_rate": 0.000998520905748941,
      "loss": 0.9849,
      "step": 100
    },
    {
      "epoch": 0.12840110058086213,
      "grad_norm": 0.13147108970650698,
      "learning_rate": 0.0009975858127678633,
      "loss": 0.9883,
      "step": 105
    },
    {
      "epoch": 0.13451543870376031,
      "grad_norm": 0.12146848904095599,
      "learning_rate": 0.0009964234631709187,
      "loss": 0.985,
      "step": 110
    },
    {
      "epoch": 0.1406297768266585,
      "grad_norm": 0.15932664420891876,
      "learning_rate": 0.0009950343878246009,
      "loss": 0.983,
      "step": 115
    },
    {
      "epoch": 0.14674411494955672,
      "grad_norm": 0.13873375461481144,
      "learning_rate": 0.0009934192211452344,
      "loss": 0.98,
      "step": 120
    },
    {
      "epoch": 0.1528584530724549,
      "grad_norm": 0.1538004585641361,
      "learning_rate": 0.0009915787008092246,
      "loss": 0.9721,
      "step": 125
    },
    {
      "epoch": 0.1589727911953531,
      "grad_norm": 0.1382569798418763,
      "learning_rate": 0.0009895136674161465,
      "loss": 0.9741,
      "step": 130
    },
    {
      "epoch": 0.16508712931825129,
      "grad_norm": 0.15833788706187227,
      "learning_rate": 0.0009872250641048289,
      "loss": 0.9781,
      "step": 135
    },
    {
      "epoch": 0.1712014674411495,
      "grad_norm": 0.14959772029321822,
      "learning_rate": 0.0009847139361226047,
      "loss": 0.9804,
      "step": 140
    },
    {
      "epoch": 0.1773158055640477,
      "grad_norm": 0.15126558344190147,
      "learning_rate": 0.0009819814303479266,
      "loss": 0.9753,
      "step": 145
    },
    {
      "epoch": 0.18343014368694588,
      "grad_norm": 0.12558000003386655,
      "learning_rate": 0.0009790287947665682,
      "loss": 0.9753,
      "step": 150
    },
    {
      "epoch": 0.1895444818098441,
      "grad_norm": 0.15082368481634573,
      "learning_rate": 0.0009758573779016438,
      "loss": 0.9738,
      "step": 155
    },
    {
      "epoch": 0.19565881993274228,
      "grad_norm": 0.1436091644716082,
      "learning_rate": 0.0009724686281977146,
      "loss": 0.9721,
      "step": 160
    },
    {
      "epoch": 0.20177315805564047,
      "grad_norm": 0.13376422992258633,
      "learning_rate": 0.0009688640933592572,
      "loss": 0.9588,
      "step": 165
    },
    {
      "epoch": 0.20788749617853866,
      "grad_norm": 0.172820103639061,
      "learning_rate": 0.0009650454196437975,
      "loss": 0.9618,
      "step": 170
    },
    {
      "epoch": 0.21400183430143688,
      "grad_norm": 0.11027045474496103,
      "learning_rate": 0.0009610143511100353,
      "loss": 0.9663,
      "step": 175
    },
    {
      "epoch": 0.22011617242433507,
      "grad_norm": 0.12032276235435292,
      "learning_rate": 0.0009567727288213005,
      "loss": 0.9537,
      "step": 180
    },
    {
      "epoch": 0.22623051054723325,
      "grad_norm": 0.11615954231864511,
      "learning_rate": 0.0009523224900047051,
      "loss": 0.958,
      "step": 185
    },
    {
      "epoch": 0.23234484867013147,
      "grad_norm": 0.10504587748815435,
      "learning_rate": 0.0009476656671663766,
      "loss": 0.9604,
      "step": 190
    },
    {
      "epoch": 0.23845918679302966,
      "grad_norm": 0.13568715189393674,
      "learning_rate": 0.0009428043871631739,
      "loss": 0.9531,
      "step": 195
    },
    {
      "epoch": 0.24457352491592785,
      "grad_norm": 0.1447001714428606,
      "learning_rate": 0.0009377408702313137,
      "loss": 0.9462,
      "step": 200
    },
    {
      "epoch": 0.25068786303882606,
      "grad_norm": 0.1241647609635287,
      "learning_rate": 0.0009324774289723468,
      "loss": 0.9443,
      "step": 205
    },
    {
      "epoch": 0.25680220116172425,
      "grad_norm": 0.1355644783905131,
      "learning_rate": 0.0009270164672969508,
      "loss": 0.9457,
      "step": 210
    },
    {
      "epoch": 0.26291653928462244,
      "grad_norm": 0.14124706011650312,
      "learning_rate": 0.0009213604793270196,
      "loss": 0.9492,
      "step": 215
    },
    {
      "epoch": 0.26903087740752063,
      "grad_norm": 0.14975483262187333,
      "learning_rate": 0.000915512048256552,
      "loss": 0.9364,
      "step": 220
    },
    {
      "epoch": 0.2751452155304188,
      "grad_norm": 0.1078100835280595,
      "learning_rate": 0.0009094738451718594,
      "loss": 0.9435,
      "step": 225
    },
    {
      "epoch": 0.281259553653317,
      "grad_norm": 0.12309862917298761,
      "learning_rate": 0.0009032486278316315,
      "loss": 0.9356,
      "step": 230
    },
    {
      "epoch": 0.28737389177621525,
      "grad_norm": 0.12723435610628442,
      "learning_rate": 0.0008968392394074163,
      "loss": 0.9378,
      "step": 235
    },
    {
      "epoch": 0.29348822989911344,
      "grad_norm": 0.10462231095819303,
      "learning_rate": 0.0008902486071850926,
      "loss": 0.9442,
      "step": 240
    },
    {
      "epoch": 0.29960256802201163,
      "grad_norm": 0.13925829008530255,
      "learning_rate": 0.0008834797412279236,
      "loss": 0.9334,
      "step": 245
    },
    {
      "epoch": 0.3057169061449098,
      "grad_norm": 0.1273487577497673,
      "learning_rate": 0.0008765357330018055,
      "loss": 0.931,
      "step": 250
    },
    {
      "epoch": 0.311831244267808,
      "grad_norm": 0.12116196314846202,
      "learning_rate": 0.0008694197539633384,
      "loss": 0.9383,
      "step": 255
    },
    {
      "epoch": 0.3179455823907062,
      "grad_norm": 0.1250843203236674,
      "learning_rate": 0.0008621350541113637,
      "loss": 0.9319,
      "step": 260
    },
    {
      "epoch": 0.3240599205136044,
      "grad_norm": 0.12080788537731575,
      "learning_rate": 0.0008546849605026289,
      "loss": 0.9285,
      "step": 265
    },
    {
      "epoch": 0.33017425863650257,
      "grad_norm": 0.17314003785998686,
      "learning_rate": 0.0008470728757322603,
      "loss": 0.9332,
      "step": 270
    },
    {
      "epoch": 0.3362885967594008,
      "grad_norm": 0.1431625193541668,
      "learning_rate": 0.0008393022763797346,
      "loss": 0.9318,
      "step": 275
    },
    {
      "epoch": 0.342402934882299,
      "grad_norm": 0.16735418777113265,
      "learning_rate": 0.0008313767114210615,
      "loss": 0.9323,
      "step": 280
    },
    {
      "epoch": 0.3485172730051972,
      "grad_norm": 0.1363188019161297,
      "learning_rate": 0.0008232998006078997,
      "loss": 0.935,
      "step": 285
    },
    {
      "epoch": 0.3546316111280954,
      "grad_norm": 0.11610423464025475,
      "learning_rate": 0.0008150752328143514,
      "loss": 0.9174,
      "step": 290
    },
    {
      "epoch": 0.36074594925099357,
      "grad_norm": 0.10924803560485702,
      "learning_rate": 0.0008067067643521834,
      "loss": 0.9118,
      "step": 295
    },
    {
      "epoch": 0.36686028737389176,
      "grad_norm": 0.10253606792051606,
      "learning_rate": 0.0007981982172552517,
      "loss": 0.9151,
      "step": 300
    },
    {
      "epoch": 0.37297462549678995,
      "grad_norm": 0.13982974888872052,
      "learning_rate": 0.0007895534775339084,
      "loss": 0.9255,
      "step": 305
    },
    {
      "epoch": 0.3790889636196882,
      "grad_norm": 0.09882318142435366,
      "learning_rate": 0.0007807764934001874,
      "loss": 0.9177,
      "step": 310
    },
    {
      "epoch": 0.3852033017425864,
      "grad_norm": 0.10319437561877241,
      "learning_rate": 0.000771871273464585,
      "loss": 0.9094,
      "step": 315
    },
    {
      "epoch": 0.39131763986548457,
      "grad_norm": 0.11417378850578246,
      "learning_rate": 0.0007628418849052523,
      "loss": 0.9096,
      "step": 320
    },
    {
      "epoch": 0.39743197798838276,
      "grad_norm": 0.12295800667011886,
      "learning_rate": 0.0007536924516104411,
      "loss": 0.9095,
      "step": 325
    },
    {
      "epoch": 0.40354631611128094,
      "grad_norm": 0.11159190643662502,
      "learning_rate": 0.0007444271522950469,
      "loss": 0.9021,
      "step": 330
    },
    {
      "epoch": 0.40966065423417913,
      "grad_norm": 0.1252629153454932,
      "learning_rate": 0.0007350502185921132,
      "loss": 0.9076,
      "step": 335
    },
    {
      "epoch": 0.4157749923570773,
      "grad_norm": 0.11464728685850215,
      "learning_rate": 0.0007255659331201672,
      "loss": 0.9113,
      "step": 340
    },
    {
      "epoch": 0.42188933047997557,
      "grad_norm": 0.13306027654586686,
      "learning_rate": 0.0007159786275272686,
      "loss": 0.9104,
      "step": 345
    },
    {
      "epoch": 0.42800366860287375,
      "grad_norm": 0.1187107905375174,
      "learning_rate": 0.0007062926805126653,
      "loss": 0.9164,
      "step": 350
    },
    {
      "epoch": 0.43411800672577194,
      "grad_norm": 0.12255410907403633,
      "learning_rate": 0.0006965125158269618,
      "loss": 0.8986,
      "step": 355
    },
    {
      "epoch": 0.44023234484867013,
      "grad_norm": 0.09613158587511622,
      "learning_rate": 0.0006866426002517105,
      "loss": 0.9009,
      "step": 360
    },
    {
      "epoch": 0.4463466829715683,
      "grad_norm": 0.1169754004784448,
      "learning_rate": 0.0006766874415593496,
      "loss": 0.909,
      "step": 365
    },
    {
      "epoch": 0.4524610210944665,
      "grad_norm": 0.11351098683885749,
      "learning_rate": 0.0006666515864544209,
      "loss": 0.9019,
      "step": 370
    },
    {
      "epoch": 0.4585753592173647,
      "grad_norm": 0.12147663137303133,
      "learning_rate": 0.0006565396184970059,
      "loss": 0.9042,
      "step": 375
    },
    {
      "epoch": 0.46468969734026294,
      "grad_norm": 0.1114287532695913,
      "learning_rate": 0.0006463561560093292,
      "loss": 0.9007,
      "step": 380
    },
    {
      "epoch": 0.47080403546316113,
      "grad_norm": 0.10708526766281388,
      "learning_rate": 0.0006361058499664855,
      "loss": 0.8949,
      "step": 385
    },
    {
      "epoch": 0.4769183735860593,
      "grad_norm": 0.10655002270489923,
      "learning_rate": 0.0006257933818722543,
      "loss": 0.8998,
      "step": 390
    },
    {
      "epoch": 0.4830327117089575,
      "grad_norm": 0.1016499106218396,
      "learning_rate": 0.0006154234616209693,
      "loss": 0.887,
      "step": 395
    },
    {
      "epoch": 0.4891470498318557,
      "grad_norm": 0.10775455001043291,
      "learning_rate": 0.0006050008253464246,
      "loss": 0.8892,
      "step": 400
    },
    {
      "epoch": 0.4952613879547539,
      "grad_norm": 0.09438287053968446,
      "learning_rate": 0.0005945302332587938,
      "loss": 0.886,
      "step": 405
    },
    {
      "epoch": 0.5013757260776521,
      "grad_norm": 0.10561263991422343,
      "learning_rate": 0.0005840164674705543,
      "loss": 0.8904,
      "step": 410
    },
    {
      "epoch": 0.5074900642005503,
      "grad_norm": 0.15358893461343107,
      "learning_rate": 0.000573464329812409,
      "loss": 0.8992,
      "step": 415
    },
    {
      "epoch": 0.5136044023234485,
      "grad_norm": 0.10760823616000371,
      "learning_rate": 0.0005628786396402013,
      "loss": 0.8919,
      "step": 420
    },
    {
      "epoch": 0.5197187404463467,
      "grad_norm": 0.0983532065047366,
      "learning_rate": 0.0005522642316338268,
      "loss": 0.8873,
      "step": 425
    },
    {
      "epoch": 0.5258330785692449,
      "grad_norm": 0.10566645548622697,
      "learning_rate": 0.0005416259535891447,
      "loss": 0.8985,
      "step": 430
    },
    {
      "epoch": 0.5319474166921431,
      "grad_norm": 0.09400617437059618,
      "learning_rate": 0.0005309686642039016,
      "loss": 0.8855,
      "step": 435
    },
    {
      "epoch": 0.5380617548150413,
      "grad_norm": 0.10458511844644205,
      "learning_rate": 0.0005202972308586735,
      "loss": 0.8805,
      "step": 440
    },
    {
      "epoch": 0.5441760929379394,
      "grad_norm": 0.1069055482540605,
      "learning_rate": 0.0005096165273938436,
      "loss": 0.8743,
      "step": 445
    },
    {
      "epoch": 0.5502904310608376,
      "grad_norm": 0.09403124483054168,
      "learning_rate": 0.0004989314318836302,
      "loss": 0.8794,
      "step": 450
    },
    {
      "epoch": 0.5564047691837358,
      "grad_norm": 0.10699257109922651,
      "learning_rate": 0.00048824682440817927,
      "loss": 0.8806,
      "step": 455
    },
    {
      "epoch": 0.562519107306634,
      "grad_norm": 0.09985948385062245,
      "learning_rate": 0.0004775675848247427,
      "loss": 0.8813,
      "step": 460
    },
    {
      "epoch": 0.5686334454295322,
      "grad_norm": 0.105036623631725,
      "learning_rate": 0.0004668985905389563,
      "loss": 0.887,
      "step": 465
    },
    {
      "epoch": 0.5747477835524305,
      "grad_norm": 0.11080094841828096,
      "learning_rate": 0.0004562447142772404,
      "loss": 0.8744,
      "step": 470
    },
    {
      "epoch": 0.5808621216753287,
      "grad_norm": 0.1250806107949013,
      "learning_rate": 0.0004456108218613346,
      "loss": 0.8698,
      "step": 475
    },
    {
      "epoch": 0.5869764597982269,
      "grad_norm": 0.0972143382654124,
      "learning_rate": 0.00043500176998598775,
      "loss": 0.8805,
      "step": 480
    },
    {
      "epoch": 0.5930907979211251,
      "grad_norm": 0.11219773661945918,
      "learning_rate": 0.0004244224040008156,
      "loss": 0.8801,
      "step": 485
    },
    {
      "epoch": 0.5992051360440233,
      "grad_norm": 0.14071498565703944,
      "learning_rate": 0.00041387755569734057,
      "loss": 0.8807,
      "step": 490
    },
    {
      "epoch": 0.6053194741669214,
      "grad_norm": 0.10783176136023623,
      "learning_rate": 0.0004033720411022235,
      "loss": 0.8697,
      "step": 495
    },
    {
      "epoch": 0.6114338122898196,
      "grad_norm": 0.09520310912796215,
      "learning_rate": 0.00039291065827769484,
      "loss": 0.8777,
      "step": 500
    },
    {
      "epoch": 0.6175481504127178,
      "grad_norm": 0.09620451010405635,
      "learning_rate": 0.0003824981851301924,
      "loss": 0.8723,
      "step": 505
    },
    {
      "epoch": 0.623662488535616,
      "grad_norm": 0.08307849142839015,
      "learning_rate": 0.0003721393772282022,
      "loss": 0.8678,
      "step": 510
    },
    {
      "epoch": 0.6297768266585142,
      "grad_norm": 0.09253756305585324,
      "learning_rate": 0.00036183896563030295,
      "loss": 0.8799,
      "step": 515
    },
    {
      "epoch": 0.6358911647814124,
      "grad_norm": 0.08933396229258163,
      "learning_rate": 0.0003516016547244047,
      "loss": 0.8705,
      "step": 520
    },
    {
      "epoch": 0.6420055029043106,
      "grad_norm": 0.10619698692809078,
      "learning_rate": 0.00034143212007916793,
      "loss": 0.8619,
      "step": 525
    },
    {
      "epoch": 0.6481198410272088,
      "grad_norm": 0.09349371215537762,
      "learning_rate": 0.00033133500630858504,
      "loss": 0.881,
      "step": 530
    },
    {
      "epoch": 0.654234179150107,
      "grad_norm": 0.09046629782340958,
      "learning_rate": 0.0003213149249506997,
      "loss": 0.8696,
      "step": 535
    },
    {
      "epoch": 0.6603485172730051,
      "grad_norm": 0.09293695191807286,
      "learning_rate": 0.00031137645236143204,
      "loss": 0.872,
      "step": 540
    },
    {
      "epoch": 0.6664628553959034,
      "grad_norm": 0.09042774606106192,
      "learning_rate": 0.0003015241276244729,
      "loss": 0.866,
      "step": 545
    },
    {
      "epoch": 0.6725771935188016,
      "grad_norm": 0.08943853887177049,
      "learning_rate": 0.00029176245047820063,
      "loss": 0.8663,
      "step": 550
    },
    {
      "epoch": 0.6786915316416998,
      "grad_norm": 0.10703770717270873,
      "learning_rate": 0.0002820958792605669,
      "loss": 0.8676,
      "step": 555
    },
    {
      "epoch": 0.684805869764598,
      "grad_norm": 0.08492021626424746,
      "learning_rate": 0.00027252882887289287,
      "loss": 0.8554,
      "step": 560
    },
    {
      "epoch": 0.6909202078874962,
      "grad_norm": 0.10407953654970142,
      "learning_rate": 0.0002630656687635007,
      "loss": 0.8583,
      "step": 565
    },
    {
      "epoch": 0.6970345460103944,
      "grad_norm": 0.0824461160121573,
      "learning_rate": 0.0002537107209321074,
      "loss": 0.8628,
      "step": 570
    },
    {
      "epoch": 0.7031488841332926,
      "grad_norm": 0.10428889280009748,
      "learning_rate": 0.0002444682579558872,
      "loss": 0.8535,
      "step": 575
    },
    {
      "epoch": 0.7092632222561908,
      "grad_norm": 0.07965447039376655,
      "learning_rate": 0.00023534250103810628,
      "loss": 0.8545,
      "step": 580
    },
    {
      "epoch": 0.715377560379089,
      "grad_norm": 0.0928006027867118,
      "learning_rate": 0.00022633761808022273,
      "loss": 0.8524,
      "step": 585
    },
    {
      "epoch": 0.7214918985019871,
      "grad_norm": 0.08872667637386111,
      "learning_rate": 0.00021745772177832756,
      "loss": 0.8512,
      "step": 590
    },
    {
      "epoch": 0.7276062366248853,
      "grad_norm": 0.1079467742979241,
      "learning_rate": 0.00020870686774480197,
      "loss": 0.8599,
      "step": 595
    },
    {
      "epoch": 0.7337205747477835,
      "grad_norm": 0.09888079366817214,
      "learning_rate": 0.00020008905265604316,
      "loss": 0.858,
      "step": 600
    },
    {
      "epoch": 0.7398349128706817,
      "grad_norm": 0.1058830999608511,
      "learning_rate": 0.00019160821242710958,
      "loss": 0.8602,
      "step": 605
    },
    {
      "epoch": 0.7459492509935799,
      "grad_norm": 0.08962748847918732,
      "learning_rate": 0.00018326822041411523,
      "loss": 0.8671,
      "step": 610
    },
    {
      "epoch": 0.7520635891164782,
      "grad_norm": 0.09399010413130322,
      "learning_rate": 0.00017507288564519647,
      "loss": 0.8526,
      "step": 615
    },
    {
      "epoch": 0.7581779272393764,
      "grad_norm": 0.08270084851060709,
      "learning_rate": 0.00016702595108085945,
      "loss": 0.8624,
      "step": 620
    },
    {
      "epoch": 0.7642922653622746,
      "grad_norm": 0.09980027261787928,
      "learning_rate": 0.0001591310919045003,
      "loss": 0.8612,
      "step": 625
    },
    {
      "epoch": 0.7704066034851728,
      "grad_norm": 0.09445752377399474,
      "learning_rate": 0.00015139191384388095,
      "loss": 0.8619,
      "step": 630
    },
    {
      "epoch": 0.776520941608071,
      "grad_norm": 0.09149316315284103,
      "learning_rate": 0.00014381195152432768,
      "loss": 0.8569,
      "step": 635
    },
    {
      "epoch": 0.7826352797309691,
      "grad_norm": 0.10490270600046576,
      "learning_rate": 0.00013639466685440134,
      "loss": 0.8603,
      "step": 640
    },
    {
      "epoch": 0.7887496178538673,
      "grad_norm": 0.08352199090543881,
      "learning_rate": 0.00012914344744478112,
      "loss": 0.863,
      "step": 645
    },
    {
      "epoch": 0.7948639559767655,
      "grad_norm": 0.1037013152834401,
      "learning_rate": 0.0001220616050610791,
      "loss": 0.8465,
      "step": 650
    },
    {
      "epoch": 0.8009782940996637,
      "grad_norm": 0.08763593791016736,
      "learning_rate": 0.00011515237411129698,
      "loss": 0.8504,
      "step": 655
    },
    {
      "epoch": 0.8070926322225619,
      "grad_norm": 0.08445574275325193,
      "learning_rate": 0.00010841891016861154,
      "loss": 0.8623,
      "step": 660
    },
    {
      "epoch": 0.8132069703454601,
      "grad_norm": 0.08168853426345901,
      "learning_rate": 0.00010186428853016605,
      "loss": 0.8615,
      "step": 665
    },
    {
      "epoch": 0.8193213084683583,
      "grad_norm": 0.09147819158262574,
      "learning_rate": 9.549150281252633e-05,
      "loss": 0.8567,
      "step": 670
    },
    {
      "epoch": 0.8254356465912565,
      "grad_norm": 0.10248465777136823,
      "learning_rate": 8.930346358443952e-05,
      "loss": 0.8619,
      "step": 675
    },
    {
      "epoch": 0.8315499847141546,
      "grad_norm": 0.08649839904042995,
      "learning_rate": 8.330299703752498e-05,
      "loss": 0.8465,
      "step": 680
    },
    {
      "epoch": 0.8376643228370529,
      "grad_norm": 0.0952129204342795,
      "learning_rate": 7.749284369549953e-05,
      "loss": 0.8524,
      "step": 685
    },
    {
      "epoch": 0.8437786609599511,
      "grad_norm": 0.08211788402495825,
      "learning_rate": 7.187565716252992e-05,
      "loss": 0.8509,
      "step": 690
    },
    {
      "epoch": 0.8498929990828493,
      "grad_norm": 0.08571973496189347,
      "learning_rate": 6.645400291128356e-05,
      "loss": 0.8577,
      "step": 695
    },
    {
      "epoch": 0.8560073372057475,
      "grad_norm": 0.08082502620292945,
      "learning_rate": 6.123035711122859e-05,
      "loss": 0.8476,
      "step": 700
    },
    {
      "epoch": 0.8621216753286457,
      "grad_norm": 0.07815053165759356,
      "learning_rate": 5.6207105497722956e-05,
      "loss": 0.8363,
      "step": 705
    },
    {
      "epoch": 0.8682360134515439,
      "grad_norm": 0.08165596121429411,
      "learning_rate": 5.138654228240425e-05,
      "loss": 0.838,
      "step": 710
    },
    {
      "epoch": 0.8743503515744421,
      "grad_norm": 0.08037559269668637,
      "learning_rate": 4.677086910538092e-05,
      "loss": 0.8466,
      "step": 715
    },
    {
      "epoch": 0.8804646896973403,
      "grad_norm": 0.08019657403458592,
      "learning_rate": 4.236219402970326e-05,
      "loss": 0.858,
      "step": 720
    },
    {
      "epoch": 0.8865790278202385,
      "grad_norm": 0.08867793444411678,
      "learning_rate": 3.816253057857144e-05,
      "loss": 0.8427,
      "step": 725
    },
    {
      "epoch": 0.8926933659431366,
      "grad_norm": 0.08359801409970409,
      "learning_rate": 3.417379681572297e-05,
      "loss": 0.8602,
      "step": 730
    },
    {
      "epoch": 0.8988077040660348,
      "grad_norm": 0.07709654354498045,
      "learning_rate": 3.0397814469416973e-05,
      "loss": 0.8478,
      "step": 735
    },
    {
      "epoch": 0.904922042188933,
      "grad_norm": 0.08504934863051679,
      "learning_rate": 2.683630810041787e-05,
      "loss": 0.8522,
      "step": 740
    },
    {
      "epoch": 0.9110363803118312,
      "grad_norm": 0.08097550153449702,
      "learning_rate": 2.349090431435641e-05,
      "loss": 0.855,
      "step": 745
    },
    {
      "epoch": 0.9171507184347294,
      "grad_norm": 0.07983590236151124,
      "learning_rate": 2.0363131018828753e-05,
      "loss": 0.8503,
      "step": 750
    },
    {
      "epoch": 0.9232650565576276,
      "grad_norm": 0.08750545593776848,
      "learning_rate": 1.7454416725573353e-05,
      "loss": 0.8439,
      "step": 755
    },
    {
      "epoch": 0.9293793946805259,
      "grad_norm": 0.08281156948532688,
      "learning_rate": 1.4766089898042678e-05,
      "loss": 0.8457,
      "step": 760
    },
    {
      "epoch": 0.9354937328034241,
      "grad_norm": 0.08034480195198145,
      "learning_rate": 1.2299378344669988e-05,
      "loss": 0.8474,
      "step": 765
    },
    {
      "epoch": 0.9416080709263223,
      "grad_norm": 0.07959517933222772,
      "learning_rate": 1.0055408658106447e-05,
      "loss": 0.8493,
      "step": 770
    },
    {
      "epoch": 0.9477224090492204,
      "grad_norm": 0.07800509939986551,
      "learning_rate": 8.035205700685167e-06,
      "loss": 0.8397,
      "step": 775
    },
    {
      "epoch": 0.9538367471721186,
      "grad_norm": 0.0826449021240808,
      "learning_rate": 6.239692136348285e-06,
      "loss": 0.8467,
      "step": 780
    },
    {
      "epoch": 0.9599510852950168,
      "grad_norm": 0.07635093172829255,
      "learning_rate": 4.669688009248607e-06,
      "loss": 0.8435,
      "step": 785
    },
    {
      "epoch": 0.966065423417915,
      "grad_norm": 0.0793118068228326,
      "learning_rate": 3.325910369220975e-06,
      "loss": 0.8465,
      "step": 790
    },
    {
      "epoch": 0.9721797615408132,
      "grad_norm": 0.07689348809541706,
      "learning_rate": 2.20897294429212e-06,
      "loss": 0.8475,
      "step": 795
    },
    {
      "epoch": 0.9782940996637114,
      "grad_norm": 0.07630687024952551,
      "learning_rate": 1.3193858603794961e-06,
      "loss": 0.8565,
      "step": 800
    },
    {
      "epoch": 0.9844084377866096,
      "grad_norm": 0.08756903255033648,
      "learning_rate": 6.575554083078084e-07,
      "loss": 0.86,
      "step": 805
    },
    {
      "epoch": 0.9905227759095078,
      "grad_norm": 0.08038874760992833,
      "learning_rate": 2.2378385824833868e-07,
      "loss": 0.8346,
      "step": 810
    },
    {
      "epoch": 0.996637114032406,
      "grad_norm": 0.09307333259332833,
      "learning_rate": 1.8269321666375404e-08,
      "loss": 0.8459,
      "step": 815
    },
    {
      "epoch": 0.9990828492815653,
      "eval_loss": 1.2038620710372925,
      "eval_runtime": 112.7414,
      "eval_samples_per_second": 185.832,
      "eval_steps_per_second": 5.81,
      "step": 817
    },
    {
      "epoch": 0.9990828492815653,
      "step": 817,
      "total_flos": 80161328332800.0,
      "train_loss": 0.9149785230034276,
      "train_runtime": 1861.2659,
      "train_samples_per_second": 56.226,
      "train_steps_per_second": 0.439
    }
  ],
  "logging_steps": 5,
  "max_steps": 817,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 80161328332800.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}