{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.998551424432641,
  "eval_steps": 500,
  "global_step": 3105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009657170449058426,
      "grad_norm": 3.7852027137880246,
      "learning_rate": 5e-06,
      "loss": 0.6254,
      "step": 10
    },
    {
      "epoch": 0.01931434089811685,
      "grad_norm": 2.0620749606772866,
      "learning_rate": 5e-06,
      "loss": 0.5439,
      "step": 20
    },
    {
      "epoch": 0.028971511347175277,
      "grad_norm": 2.085747916186358,
      "learning_rate": 5e-06,
      "loss": 0.5216,
      "step": 30
    },
    {
      "epoch": 0.0386286817962337,
      "grad_norm": 1.8268450890377532,
      "learning_rate": 5e-06,
      "loss": 0.5097,
      "step": 40
    },
    {
      "epoch": 0.04828585224529213,
      "grad_norm": 2.0581630455526123,
      "learning_rate": 5e-06,
      "loss": 0.504,
      "step": 50
    },
    {
      "epoch": 0.05794302269435055,
      "grad_norm": 1.602128099496524,
      "learning_rate": 5e-06,
      "loss": 0.5013,
      "step": 60
    },
    {
      "epoch": 0.06760019314340898,
      "grad_norm": 1.6673623755384994,
      "learning_rate": 5e-06,
      "loss": 0.4878,
      "step": 70
    },
    {
      "epoch": 0.0772573635924674,
      "grad_norm": 1.8459613232584249,
      "learning_rate": 5e-06,
      "loss": 0.4878,
      "step": 80
    },
    {
      "epoch": 0.08691453404152583,
      "grad_norm": 1.93193366344165,
      "learning_rate": 5e-06,
      "loss": 0.4879,
      "step": 90
    },
    {
      "epoch": 0.09657170449058426,
      "grad_norm": 1.5465868737214155,
      "learning_rate": 5e-06,
      "loss": 0.4808,
      "step": 100
    },
    {
      "epoch": 0.10622887493964268,
      "grad_norm": 1.6271945980777192,
      "learning_rate": 5e-06,
      "loss": 0.4782,
      "step": 110
    },
    {
      "epoch": 0.1158860453887011,
      "grad_norm": 1.8402435224859226,
      "learning_rate": 5e-06,
      "loss": 0.4767,
      "step": 120
    },
    {
      "epoch": 0.12554321583775954,
      "grad_norm": 1.7618646649255147,
      "learning_rate": 5e-06,
      "loss": 0.4745,
      "step": 130
    },
    {
      "epoch": 0.13520038628681796,
      "grad_norm": 1.5315385028605073,
      "learning_rate": 5e-06,
      "loss": 0.4733,
      "step": 140
    },
    {
      "epoch": 0.14485755673587639,
      "grad_norm": 1.6814511784859512,
      "learning_rate": 5e-06,
      "loss": 0.4733,
      "step": 150
    },
    {
      "epoch": 0.1545147271849348,
      "grad_norm": 1.5271479672490604,
      "learning_rate": 5e-06,
      "loss": 0.4716,
      "step": 160
    },
    {
      "epoch": 0.16417189763399323,
      "grad_norm": 1.6777577770303629,
      "learning_rate": 5e-06,
      "loss": 0.471,
      "step": 170
    },
    {
      "epoch": 0.17382906808305165,
      "grad_norm": 1.5955962931770318,
      "learning_rate": 5e-06,
      "loss": 0.4733,
      "step": 180
    },
    {
      "epoch": 0.1834862385321101,
      "grad_norm": 1.6328687609928156,
      "learning_rate": 5e-06,
      "loss": 0.4711,
      "step": 190
    },
    {
      "epoch": 0.19314340898116852,
      "grad_norm": 1.6077537949384313,
      "learning_rate": 5e-06,
      "loss": 0.4669,
      "step": 200
    },
    {
      "epoch": 0.20280057943022695,
      "grad_norm": 1.5250866943562713,
      "learning_rate": 5e-06,
      "loss": 0.4647,
      "step": 210
    },
    {
      "epoch": 0.21245774987928537,
      "grad_norm": 1.4889880734895962,
      "learning_rate": 5e-06,
      "loss": 0.4585,
      "step": 220
    },
    {
      "epoch": 0.2221149203283438,
      "grad_norm": 1.6089621732620885,
      "learning_rate": 5e-06,
      "loss": 0.4578,
      "step": 230
    },
    {
      "epoch": 0.2317720907774022,
      "grad_norm": 1.4899292253368934,
      "learning_rate": 5e-06,
      "loss": 0.4555,
      "step": 240
    },
    {
      "epoch": 0.24142926122646063,
      "grad_norm": 1.5257308623369976,
      "learning_rate": 5e-06,
      "loss": 0.4663,
      "step": 250
    },
    {
      "epoch": 0.2510864316755191,
      "grad_norm": 1.8459225661699417,
      "learning_rate": 5e-06,
      "loss": 0.4588,
      "step": 260
    },
    {
      "epoch": 0.2607436021245775,
      "grad_norm": 1.723748524461411,
      "learning_rate": 5e-06,
      "loss": 0.4622,
      "step": 270
    },
    {
      "epoch": 0.27040077257363593,
      "grad_norm": 1.6111594714193933,
      "learning_rate": 5e-06,
      "loss": 0.4562,
      "step": 280
    },
    {
      "epoch": 0.2800579430226944,
      "grad_norm": 1.489881509289716,
      "learning_rate": 5e-06,
      "loss": 0.4632,
      "step": 290
    },
    {
      "epoch": 0.28971511347175277,
      "grad_norm": 1.7437076586484017,
      "learning_rate": 5e-06,
      "loss": 0.4498,
      "step": 300
    },
    {
      "epoch": 0.2993722839208112,
      "grad_norm": 1.5023208696211863,
      "learning_rate": 5e-06,
      "loss": 0.4547,
      "step": 310
    },
    {
      "epoch": 0.3090294543698696,
      "grad_norm": 1.47145559032755,
      "learning_rate": 5e-06,
      "loss": 0.448,
      "step": 320
    },
    {
      "epoch": 0.31868662481892807,
      "grad_norm": 1.493111331589544,
      "learning_rate": 5e-06,
      "loss": 0.4493,
      "step": 330
    },
    {
      "epoch": 0.32834379526798646,
      "grad_norm": 1.3731787738087704,
      "learning_rate": 5e-06,
      "loss": 0.4548,
      "step": 340
    },
    {
      "epoch": 0.3380009657170449,
      "grad_norm": 1.5097895917724191,
      "learning_rate": 5e-06,
      "loss": 0.4468,
      "step": 350
    },
    {
      "epoch": 0.3476581361661033,
      "grad_norm": 1.3977565649576211,
      "learning_rate": 5e-06,
      "loss": 0.4497,
      "step": 360
    },
    {
      "epoch": 0.35731530661516175,
      "grad_norm": 1.597963004052136,
      "learning_rate": 5e-06,
      "loss": 0.446,
      "step": 370
    },
    {
      "epoch": 0.3669724770642202,
      "grad_norm": 1.3464438194432793,
      "learning_rate": 5e-06,
      "loss": 0.4462,
      "step": 380
    },
    {
      "epoch": 0.3766296475132786,
      "grad_norm": 2.13016639276551,
      "learning_rate": 5e-06,
      "loss": 0.4471,
      "step": 390
    },
    {
      "epoch": 0.38628681796233705,
      "grad_norm": 1.459345081562004,
      "learning_rate": 5e-06,
      "loss": 0.4449,
      "step": 400
    },
    {
      "epoch": 0.39594398841139544,
      "grad_norm": 1.4268521503710732,
      "learning_rate": 5e-06,
      "loss": 0.4484,
      "step": 410
    },
    {
      "epoch": 0.4056011588604539,
      "grad_norm": 1.5213089527197126,
      "learning_rate": 5e-06,
      "loss": 0.442,
      "step": 420
    },
    {
      "epoch": 0.4152583293095123,
      "grad_norm": 1.4107454080123742,
      "learning_rate": 5e-06,
      "loss": 0.4471,
      "step": 430
    },
    {
      "epoch": 0.42491549975857074,
      "grad_norm": 1.4224146665144493,
      "learning_rate": 5e-06,
      "loss": 0.4421,
      "step": 440
    },
    {
      "epoch": 0.4345726702076292,
      "grad_norm": 1.339648419205393,
      "learning_rate": 5e-06,
      "loss": 0.4459,
      "step": 450
    },
    {
      "epoch": 0.4442298406566876,
      "grad_norm": 1.541975682641463,
      "learning_rate": 5e-06,
      "loss": 0.4416,
      "step": 460
    },
    {
      "epoch": 0.45388701110574603,
      "grad_norm": 1.447132284857592,
      "learning_rate": 5e-06,
      "loss": 0.4529,
      "step": 470
    },
    {
      "epoch": 0.4635441815548044,
      "grad_norm": 1.385982642001702,
      "learning_rate": 5e-06,
      "loss": 0.4458,
      "step": 480
    },
    {
      "epoch": 0.4732013520038629,
      "grad_norm": 2.0640182165227428,
      "learning_rate": 5e-06,
      "loss": 0.4426,
      "step": 490
    },
    {
      "epoch": 0.48285852245292127,
      "grad_norm": 1.348125498390211,
      "learning_rate": 5e-06,
      "loss": 0.4329,
      "step": 500
    },
    {
      "epoch": 0.4925156929019797,
      "grad_norm": 1.509261123647944,
      "learning_rate": 5e-06,
      "loss": 0.4437,
      "step": 510
    },
    {
      "epoch": 0.5021728633510382,
      "grad_norm": 2.7536862793707493,
      "learning_rate": 5e-06,
      "loss": 0.4359,
      "step": 520
    },
    {
      "epoch": 0.5118300338000966,
      "grad_norm": 1.4717359737134839,
      "learning_rate": 5e-06,
      "loss": 0.4382,
      "step": 530
    },
    {
      "epoch": 0.521487204249155,
      "grad_norm": 1.442405927212471,
      "learning_rate": 5e-06,
      "loss": 0.4394,
      "step": 540
    },
    {
      "epoch": 0.5311443746982134,
      "grad_norm": 1.3948076832604182,
      "learning_rate": 5e-06,
      "loss": 0.4407,
      "step": 550
    },
    {
      "epoch": 0.5408015451472719,
      "grad_norm": 1.3948240431568104,
      "learning_rate": 5e-06,
      "loss": 0.4366,
      "step": 560
    },
    {
      "epoch": 0.5504587155963303,
      "grad_norm": 1.417839986279595,
      "learning_rate": 5e-06,
      "loss": 0.4369,
      "step": 570
    },
    {
      "epoch": 0.5601158860453888,
      "grad_norm": 1.5109506580715066,
      "learning_rate": 5e-06,
      "loss": 0.4353,
      "step": 580
    },
    {
      "epoch": 0.5697730564944471,
      "grad_norm": 1.4806935542579658,
      "learning_rate": 5e-06,
      "loss": 0.4378,
      "step": 590
    },
    {
      "epoch": 0.5794302269435055,
      "grad_norm": 1.5398960352117772,
      "learning_rate": 5e-06,
      "loss": 0.4352,
      "step": 600
    },
    {
      "epoch": 0.589087397392564,
      "grad_norm": 1.2925767785772035,
      "learning_rate": 5e-06,
      "loss": 0.4366,
      "step": 610
    },
    {
      "epoch": 0.5987445678416224,
      "grad_norm": 1.5201357387636154,
      "learning_rate": 5e-06,
      "loss": 0.4296,
      "step": 620
    },
    {
      "epoch": 0.6084017382906808,
      "grad_norm": 1.4717871703145071,
      "learning_rate": 5e-06,
      "loss": 0.431,
      "step": 630
    },
    {
      "epoch": 0.6180589087397392,
      "grad_norm": 1.3687678242722554,
      "learning_rate": 5e-06,
      "loss": 0.4345,
      "step": 640
    },
    {
      "epoch": 0.6277160791887977,
      "grad_norm": 1.3591593745283608,
      "learning_rate": 5e-06,
      "loss": 0.4313,
      "step": 650
    },
    {
      "epoch": 0.6373732496378561,
      "grad_norm": 1.4717658524480044,
      "learning_rate": 5e-06,
      "loss": 0.4291,
      "step": 660
    },
    {
      "epoch": 0.6470304200869146,
      "grad_norm": 1.398916059634764,
      "learning_rate": 5e-06,
      "loss": 0.4323,
      "step": 670
    },
    {
      "epoch": 0.6566875905359729,
      "grad_norm": 1.4300679905819138,
      "learning_rate": 5e-06,
      "loss": 0.4271,
      "step": 680
    },
    {
      "epoch": 0.6663447609850314,
      "grad_norm": 1.4886395606416152,
      "learning_rate": 5e-06,
      "loss": 0.4297,
      "step": 690
    },
    {
      "epoch": 0.6760019314340898,
      "grad_norm": 1.5034980432589369,
      "learning_rate": 5e-06,
      "loss": 0.4272,
      "step": 700
    },
    {
      "epoch": 0.6856591018831483,
      "grad_norm": 1.5962520697846152,
      "learning_rate": 5e-06,
      "loss": 0.4316,
      "step": 710
    },
    {
      "epoch": 0.6953162723322066,
      "grad_norm": 1.5447138904473863,
      "learning_rate": 5e-06,
      "loss": 0.4324,
      "step": 720
    },
    {
      "epoch": 0.7049734427812651,
      "grad_norm": 1.3937453432394886,
      "learning_rate": 5e-06,
      "loss": 0.4311,
      "step": 730
    },
    {
      "epoch": 0.7146306132303235,
      "grad_norm": 1.3011464123427467,
      "learning_rate": 5e-06,
      "loss": 0.4292,
      "step": 740
    },
    {
      "epoch": 0.724287783679382,
      "grad_norm": 1.4931973618415784,
      "learning_rate": 5e-06,
      "loss": 0.4295,
      "step": 750
    },
    {
      "epoch": 0.7339449541284404,
      "grad_norm": 1.3582576932610695,
      "learning_rate": 5e-06,
      "loss": 0.4322,
      "step": 760
    },
    {
      "epoch": 0.7436021245774987,
      "grad_norm": 1.5128036261098081,
      "learning_rate": 5e-06,
      "loss": 0.4306,
      "step": 770
    },
    {
      "epoch": 0.7532592950265572,
      "grad_norm": 1.3047038324570048,
      "learning_rate": 5e-06,
      "loss": 0.43,
      "step": 780
    },
    {
      "epoch": 0.7629164654756156,
      "grad_norm": 1.3637121209115217,
      "learning_rate": 5e-06,
      "loss": 0.4273,
      "step": 790
    },
    {
      "epoch": 0.7725736359246741,
      "grad_norm": 1.3919305669020587,
      "learning_rate": 5e-06,
      "loss": 0.4314,
      "step": 800
    },
    {
      "epoch": 0.7822308063737325,
      "grad_norm": 1.3941190921525122,
      "learning_rate": 5e-06,
      "loss": 0.4255,
      "step": 810
    },
    {
      "epoch": 0.7918879768227909,
      "grad_norm": 1.362917573056491,
      "learning_rate": 5e-06,
      "loss": 0.4333,
      "step": 820
    },
    {
      "epoch": 0.8015451472718493,
      "grad_norm": 1.415609597869972,
      "learning_rate": 5e-06,
      "loss": 0.4225,
      "step": 830
    },
    {
      "epoch": 0.8112023177209078,
      "grad_norm": 1.489818925031249,
      "learning_rate": 5e-06,
      "loss": 0.425,
      "step": 840
    },
    {
      "epoch": 0.8208594881699662,
      "grad_norm": 1.4658100940320271,
      "learning_rate": 5e-06,
      "loss": 0.4304,
      "step": 850
    },
    {
      "epoch": 0.8305166586190246,
      "grad_norm": 1.3385021753495208,
      "learning_rate": 5e-06,
      "loss": 0.4263,
      "step": 860
    },
    {
      "epoch": 0.840173829068083,
      "grad_norm": 1.4519295448528378,
      "learning_rate": 5e-06,
      "loss": 0.4274,
      "step": 870
    },
    {
      "epoch": 0.8498309995171415,
      "grad_norm": 1.5271445690200918,
      "learning_rate": 5e-06,
      "loss": 0.4244,
      "step": 880
    },
    {
      "epoch": 0.8594881699661999,
      "grad_norm": 9.54446637099851,
      "learning_rate": 5e-06,
      "loss": 0.4294,
      "step": 890
    },
    {
      "epoch": 0.8691453404152584,
      "grad_norm": 1.4822497861334036,
      "learning_rate": 5e-06,
      "loss": 0.4206,
      "step": 900
    },
    {
      "epoch": 0.8788025108643167,
      "grad_norm": 1.295865945244785,
      "learning_rate": 5e-06,
      "loss": 0.4223,
      "step": 910
    },
    {
      "epoch": 0.8884596813133752,
      "grad_norm": 1.4498222196547434,
      "learning_rate": 5e-06,
      "loss": 0.4222,
      "step": 920
    },
    {
      "epoch": 0.8981168517624336,
      "grad_norm": 1.4109015353277008,
      "learning_rate": 5e-06,
      "loss": 0.424,
      "step": 930
    },
    {
      "epoch": 0.9077740222114921,
      "grad_norm": 1.3782840436535198,
      "learning_rate": 5e-06,
      "loss": 0.4224,
      "step": 940
    },
    {
      "epoch": 0.9174311926605505,
      "grad_norm": 1.3492925117698618,
      "learning_rate": 5e-06,
      "loss": 0.4209,
      "step": 950
    },
    {
      "epoch": 0.9270883631096088,
      "grad_norm": 1.3072263370484556,
      "learning_rate": 5e-06,
      "loss": 0.419,
      "step": 960
    },
    {
      "epoch": 0.9367455335586673,
      "grad_norm": 1.3359087020152296,
      "learning_rate": 5e-06,
      "loss": 0.4213,
      "step": 970
    },
    {
      "epoch": 0.9464027040077257,
      "grad_norm": 1.4027836366902715,
      "learning_rate": 5e-06,
      "loss": 0.4264,
      "step": 980
    },
    {
      "epoch": 0.9560598744567842,
      "grad_norm": 1.3083915796128625,
      "learning_rate": 5e-06,
      "loss": 0.4213,
      "step": 990
    },
    {
      "epoch": 0.9657170449058425,
      "grad_norm": 1.283807856099459,
      "learning_rate": 5e-06,
      "loss": 0.4226,
      "step": 1000
    },
    {
      "epoch": 0.975374215354901,
      "grad_norm": 1.318305259783526,
      "learning_rate": 5e-06,
      "loss": 0.4177,
      "step": 1010
    },
    {
      "epoch": 0.9850313858039594,
      "grad_norm": 1.351081315674525,
      "learning_rate": 5e-06,
      "loss": 0.4184,
      "step": 1020
    },
    {
      "epoch": 0.9946885562530179,
      "grad_norm": 1.286367123540384,
      "learning_rate": 5e-06,
      "loss": 0.417,
      "step": 1030
    },
    {
      "epoch": 0.9995171414775471,
      "eval_loss": 0.4186817705631256,
      "eval_runtime": 178.2472,
      "eval_samples_per_second": 156.541,
      "eval_steps_per_second": 0.612,
      "step": 1035
    },
    {
      "epoch": 1.0043457267020763,
      "grad_norm": 2.083458671261006,
      "learning_rate": 5e-06,
      "loss": 0.3804,
      "step": 1040
    },
    {
      "epoch": 1.0140028971511348,
      "grad_norm": 1.6710464918103058,
      "learning_rate": 5e-06,
      "loss": 0.3159,
      "step": 1050
    },
    {
      "epoch": 1.0236600676001932,
      "grad_norm": 1.365743230792304,
      "learning_rate": 5e-06,
      "loss": 0.3138,
      "step": 1060
    },
    {
      "epoch": 1.0333172380492515,
      "grad_norm": 1.39749368883128,
      "learning_rate": 5e-06,
      "loss": 0.3146,
      "step": 1070
    },
    {
      "epoch": 1.04297440849831,
      "grad_norm": 1.5821963324713015,
      "learning_rate": 5e-06,
      "loss": 0.3101,
      "step": 1080
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 1.6454840741114403,
      "learning_rate": 5e-06,
      "loss": 0.3152,
      "step": 1090
    },
    {
      "epoch": 1.0622887493964268,
      "grad_norm": 1.4356941510220327,
      "learning_rate": 5e-06,
      "loss": 0.3211,
      "step": 1100
    },
    {
      "epoch": 1.0719459198454853,
      "grad_norm": 1.421015975147645,
      "learning_rate": 5e-06,
      "loss": 0.3185,
      "step": 1110
    },
    {
      "epoch": 1.0816030902945437,
      "grad_norm": 1.3637757751998314,
      "learning_rate": 5e-06,
      "loss": 0.3177,
      "step": 1120
    },
    {
      "epoch": 1.0912602607436022,
      "grad_norm": 1.4492110772881415,
      "learning_rate": 5e-06,
      "loss": 0.319,
      "step": 1130
    },
    {
      "epoch": 1.1009174311926606,
      "grad_norm": 1.4113019794162502,
      "learning_rate": 5e-06,
      "loss": 0.3183,
      "step": 1140
    },
    {
      "epoch": 1.110574601641719,
      "grad_norm": 1.4617901618486682,
      "learning_rate": 5e-06,
      "loss": 0.3206,
      "step": 1150
    },
    {
      "epoch": 1.1202317720907775,
      "grad_norm": 1.4362393573916201,
      "learning_rate": 5e-06,
      "loss": 0.3161,
      "step": 1160
    },
    {
      "epoch": 1.1298889425398357,
      "grad_norm": 1.480531545050256,
      "learning_rate": 5e-06,
      "loss": 0.3176,
      "step": 1170
    },
    {
      "epoch": 1.1395461129888942,
      "grad_norm": 1.4429791008774708,
      "learning_rate": 5e-06,
      "loss": 0.3206,
      "step": 1180
    },
    {
      "epoch": 1.1492032834379526,
      "grad_norm": 1.580292399548444,
      "learning_rate": 5e-06,
      "loss": 0.3189,
      "step": 1190
    },
    {
      "epoch": 1.158860453887011,
      "grad_norm": 1.4710472342154686,
      "learning_rate": 5e-06,
      "loss": 0.3176,
      "step": 1200
    },
    {
      "epoch": 1.1685176243360695,
      "grad_norm": 1.5510111053127804,
      "learning_rate": 5e-06,
      "loss": 0.3256,
      "step": 1210
    },
    {
      "epoch": 1.178174794785128,
      "grad_norm": 1.479606545432114,
      "learning_rate": 5e-06,
      "loss": 0.3194,
      "step": 1220
    },
    {
      "epoch": 1.1878319652341864,
      "grad_norm": 1.4470509715427249,
      "learning_rate": 5e-06,
      "loss": 0.315,
      "step": 1230
    },
    {
      "epoch": 1.1974891356832449,
      "grad_norm": 1.688180637289201,
      "learning_rate": 5e-06,
      "loss": 0.3203,
      "step": 1240
    },
    {
      "epoch": 1.2071463061323033,
      "grad_norm": 1.4261984744846448,
      "learning_rate": 5e-06,
      "loss": 0.3182,
      "step": 1250
    },
    {
      "epoch": 1.2168034765813616,
      "grad_norm": 1.5604626368447907,
      "learning_rate": 5e-06,
      "loss": 0.3204,
      "step": 1260
    },
    {
      "epoch": 1.22646064703042,
      "grad_norm": 1.5055974462561796,
      "learning_rate": 5e-06,
      "loss": 0.3194,
      "step": 1270
    },
    {
      "epoch": 1.2361178174794785,
      "grad_norm": 1.472413847791833,
      "learning_rate": 5e-06,
      "loss": 0.3164,
      "step": 1280
    },
    {
      "epoch": 1.245774987928537,
      "grad_norm": 1.4227053664977902,
      "learning_rate": 5e-06,
      "loss": 0.3195,
      "step": 1290
    },
    {
      "epoch": 1.2554321583775954,
      "grad_norm": 1.4555119482883845,
      "learning_rate": 5e-06,
      "loss": 0.3206,
      "step": 1300
    },
    {
      "epoch": 1.2650893288266538,
      "grad_norm": 1.3939863833537502,
      "learning_rate": 5e-06,
      "loss": 0.3174,
      "step": 1310
    },
    {
      "epoch": 1.2747464992757123,
      "grad_norm": 1.6503658733951097,
      "learning_rate": 5e-06,
      "loss": 0.3212,
      "step": 1320
    },
    {
      "epoch": 1.2844036697247707,
      "grad_norm": 1.5193288982909279,
      "learning_rate": 5e-06,
      "loss": 0.3185,
      "step": 1330
    },
    {
      "epoch": 1.2940608401738292,
      "grad_norm": 1.8992907121697116,
      "learning_rate": 5e-06,
      "loss": 0.3195,
      "step": 1340
    },
    {
      "epoch": 1.3037180106228874,
      "grad_norm": 1.462324131369204,
      "learning_rate": 5e-06,
      "loss": 0.3181,
      "step": 1350
    },
    {
      "epoch": 1.3133751810719458,
      "grad_norm": 1.5578779143588841,
      "learning_rate": 5e-06,
      "loss": 0.3203,
      "step": 1360
    },
    {
      "epoch": 1.3230323515210043,
      "grad_norm": 1.5253185582586557,
      "learning_rate": 5e-06,
      "loss": 0.3226,
      "step": 1370
    },
    {
      "epoch": 1.3326895219700627,
      "grad_norm": 1.598448718585017,
      "learning_rate": 5e-06,
      "loss": 0.3237,
      "step": 1380
    },
    {
      "epoch": 1.3423466924191212,
      "grad_norm": 1.4405857624240854,
      "learning_rate": 5e-06,
      "loss": 0.3223,
      "step": 1390
    },
    {
      "epoch": 1.3520038628681796,
      "grad_norm": 1.517684638613212,
      "learning_rate": 5e-06,
      "loss": 0.3231,
      "step": 1400
    },
    {
      "epoch": 1.361661033317238,
      "grad_norm": 1.483051649435277,
      "learning_rate": 5e-06,
      "loss": 0.3239,
      "step": 1410
    },
    {
      "epoch": 1.3713182037662965,
      "grad_norm": 1.5390732079855134,
      "learning_rate": 5e-06,
      "loss": 0.3218,
      "step": 1420
    },
    {
      "epoch": 1.380975374215355,
      "grad_norm": 1.5122394104164938,
      "learning_rate": 5e-06,
      "loss": 0.322,
      "step": 1430
    },
    {
      "epoch": 1.3906325446644132,
      "grad_norm": 1.5432820441426014,
      "learning_rate": 5e-06,
      "loss": 0.3145,
      "step": 1440
    },
    {
      "epoch": 1.4002897151134719,
      "grad_norm": 1.4643744673012662,
      "learning_rate": 5e-06,
      "loss": 0.3178,
      "step": 1450
    },
    {
      "epoch": 1.4099468855625301,
      "grad_norm": 1.4925264181574245,
      "learning_rate": 5e-06,
      "loss": 0.3243,
      "step": 1460
    },
    {
      "epoch": 1.4196040560115886,
      "grad_norm": 1.4092376086387746,
      "learning_rate": 5e-06,
      "loss": 0.3211,
      "step": 1470
    },
    {
      "epoch": 1.429261226460647,
      "grad_norm": 1.4232165437715756,
      "learning_rate": 5e-06,
      "loss": 0.3221,
      "step": 1480
    },
    {
      "epoch": 1.4389183969097055,
      "grad_norm": 1.4049090252857714,
      "learning_rate": 5e-06,
      "loss": 0.3259,
      "step": 1490
    },
    {
      "epoch": 1.448575567358764,
      "grad_norm": 1.5709064686147567,
      "learning_rate": 5e-06,
      "loss": 0.3192,
      "step": 1500
    },
    {
      "epoch": 1.4582327378078224,
      "grad_norm": 1.530143106655807,
      "learning_rate": 5e-06,
      "loss": 0.3198,
      "step": 1510
    },
    {
      "epoch": 1.4678899082568808,
      "grad_norm": 1.4642072322356405,
      "learning_rate": 5e-06,
      "loss": 0.3242,
      "step": 1520
    },
    {
      "epoch": 1.477547078705939,
      "grad_norm": 1.5078287858320247,
      "learning_rate": 5e-06,
      "loss": 0.3229,
      "step": 1530
    },
    {
      "epoch": 1.4872042491549977,
      "grad_norm": 1.6543135999245175,
      "learning_rate": 5e-06,
      "loss": 0.3258,
      "step": 1540
    },
    {
      "epoch": 1.496861419604056,
      "grad_norm": 1.4353311149318353,
      "learning_rate": 5e-06,
      "loss": 0.3218,
      "step": 1550
    },
    {
      "epoch": 1.5065185900531144,
      "grad_norm": 1.427362675163451,
      "learning_rate": 5e-06,
      "loss": 0.3203,
      "step": 1560
    },
    {
      "epoch": 1.5161757605021728,
      "grad_norm": 1.469685263972175,
      "learning_rate": 5e-06,
      "loss": 0.3233,
      "step": 1570
    },
    {
      "epoch": 1.5258329309512313,
      "grad_norm": 1.3556540711826985,
      "learning_rate": 5e-06,
      "loss": 0.32,
      "step": 1580
    },
    {
      "epoch": 1.5354901014002897,
      "grad_norm": 1.7785146026384562,
      "learning_rate": 5e-06,
      "loss": 0.3255,
      "step": 1590
    },
    {
      "epoch": 1.5451472718493482,
      "grad_norm": 1.6406483748665126,
      "learning_rate": 5e-06,
      "loss": 0.325,
      "step": 1600
    },
    {
      "epoch": 1.5548044422984066,
      "grad_norm": 1.487355254108548,
      "learning_rate": 5e-06,
      "loss": 0.3195,
      "step": 1610
    },
    {
      "epoch": 1.5644616127474649,
      "grad_norm": 1.5580699551469968,
      "learning_rate": 5e-06,
      "loss": 0.324,
      "step": 1620
    },
    {
      "epoch": 1.5741187831965235,
      "grad_norm": 1.6649624650081492,
      "learning_rate": 5e-06,
      "loss": 0.319,
      "step": 1630
    },
    {
      "epoch": 1.5837759536455818,
      "grad_norm": 1.5071762619332458,
      "learning_rate": 5e-06,
      "loss": 0.319,
      "step": 1640
    },
    {
      "epoch": 1.5934331240946402,
      "grad_norm": 1.4857917379863423,
      "learning_rate": 5e-06,
      "loss": 0.3246,
      "step": 1650
    },
    {
      "epoch": 1.6030902945436987,
      "grad_norm": 1.539444045216992,
      "learning_rate": 5e-06,
      "loss": 0.325,
      "step": 1660
    },
    {
      "epoch": 1.6127474649927571,
      "grad_norm": 1.4202629921913885,
      "learning_rate": 5e-06,
      "loss": 0.3249,
      "step": 1670
    },
    {
      "epoch": 1.6224046354418156,
      "grad_norm": 1.3824989312845557,
      "learning_rate": 5e-06,
      "loss": 0.3174,
      "step": 1680
    },
    {
      "epoch": 1.632061805890874,
      "grad_norm": 1.4180567800715427,
      "learning_rate": 5e-06,
      "loss": 0.32,
      "step": 1690
    },
    {
      "epoch": 1.6417189763399325,
      "grad_norm": 1.5877926258862851,
      "learning_rate": 5e-06,
      "loss": 0.3251,
      "step": 1700
    },
    {
      "epoch": 1.6513761467889907,
      "grad_norm": 1.4625682063733663,
      "learning_rate": 5e-06,
      "loss": 0.3251,
      "step": 1710
    },
    {
      "epoch": 1.6610333172380494,
      "grad_norm": 1.4726154892277907,
      "learning_rate": 5e-06,
      "loss": 0.3217,
      "step": 1720
    },
    {
      "epoch": 1.6706904876871076,
      "grad_norm": 1.4737546342638634,
      "learning_rate": 5e-06,
      "loss": 0.3241,
      "step": 1730
    },
    {
      "epoch": 1.6803476581361663,
      "grad_norm": 1.5913560262828996,
      "learning_rate": 5e-06,
      "loss": 0.3216,
      "step": 1740
    },
    {
      "epoch": 1.6900048285852245,
      "grad_norm": 1.6014273903495235,
      "learning_rate": 5e-06,
      "loss": 0.3228,
      "step": 1750
    },
    {
      "epoch": 1.699661999034283,
      "grad_norm": 1.4444614753017166,
      "learning_rate": 5e-06,
      "loss": 0.3219,
      "step": 1760
    },
    {
      "epoch": 1.7093191694833414,
      "grad_norm": 1.4711587303385112,
      "learning_rate": 5e-06,
      "loss": 0.3204,
      "step": 1770
    },
    {
      "epoch": 1.7189763399323998,
      "grad_norm": 1.4911136718247058,
      "learning_rate": 5e-06,
      "loss": 0.3225,
      "step": 1780
    },
    {
      "epoch": 1.7286335103814583,
      "grad_norm": 1.4836367449856465,
      "learning_rate": 5e-06,
      "loss": 0.3275,
      "step": 1790
    },
    {
      "epoch": 1.7382906808305165,
      "grad_norm": 1.5104260942145018,
      "learning_rate": 5e-06,
      "loss": 0.3261,
      "step": 1800
    },
    {
      "epoch": 1.7479478512795752,
      "grad_norm": 1.4587337741103181,
      "learning_rate": 5e-06,
      "loss": 0.3247,
      "step": 1810
    },
    {
      "epoch": 1.7576050217286334,
      "grad_norm": 1.5339818170022481,
      "learning_rate": 5e-06,
      "loss": 0.3237,
      "step": 1820
    },
    {
      "epoch": 1.767262192177692,
      "grad_norm": 1.4650422841731612,
      "learning_rate": 5e-06,
      "loss": 0.3218,
      "step": 1830
    },
    {
      "epoch": 1.7769193626267503,
      "grad_norm": 1.6273768535871191,
      "learning_rate": 5e-06,
      "loss": 0.3239,
      "step": 1840
    },
    {
      "epoch": 1.7865765330758088,
      "grad_norm": 1.6280662513787525,
      "learning_rate": 5e-06,
      "loss": 0.3267,
      "step": 1850
    },
    {
      "epoch": 1.7962337035248672,
      "grad_norm": 1.469702386246834,
      "learning_rate": 5e-06,
      "loss": 0.322,
      "step": 1860
    },
    {
      "epoch": 1.8058908739739257,
      "grad_norm": 1.6861190386571836,
      "learning_rate": 5e-06,
      "loss": 0.3246,
      "step": 1870
    },
    {
      "epoch": 1.8155480444229841,
      "grad_norm": 1.481497242440989,
      "learning_rate": 5e-06,
      "loss": 0.3226,
      "step": 1880
    },
    {
      "epoch": 1.8252052148720423,
      "grad_norm": 1.6155053021371237,
      "learning_rate": 5e-06,
      "loss": 0.3236,
      "step": 1890
    },
    {
      "epoch": 1.834862385321101,
      "grad_norm": 1.416112013187697,
      "learning_rate": 5e-06,
      "loss": 0.3228,
      "step": 1900
    },
    {
      "epoch": 1.8445195557701592,
      "grad_norm": 1.581676674672017,
      "learning_rate": 5e-06,
      "loss": 0.3241,
      "step": 1910
    },
    {
      "epoch": 1.854176726219218,
      "grad_norm": 1.5569951920933318,
      "learning_rate": 5e-06,
      "loss": 0.3259,
      "step": 1920
    },
    {
      "epoch": 1.8638338966682761,
      "grad_norm": 1.6829953573077656,
      "learning_rate": 5e-06,
      "loss": 0.3239,
      "step": 1930
    },
    {
      "epoch": 1.8734910671173346,
      "grad_norm": 1.4499124168214599,
      "learning_rate": 5e-06,
      "loss": 0.3237,
      "step": 1940
    },
    {
      "epoch": 1.883148237566393,
      "grad_norm": 1.3921897240084418,
      "learning_rate": 5e-06,
      "loss": 0.3202,
      "step": 1950
    },
    {
      "epoch": 1.8928054080154515,
      "grad_norm": 1.7399387456220219,
      "learning_rate": 5e-06,
      "loss": 0.3185,
      "step": 1960
    },
    {
      "epoch": 1.90246257846451,
      "grad_norm": 1.5558707224477395,
      "learning_rate": 5e-06,
      "loss": 0.323,
      "step": 1970
    },
    {
      "epoch": 1.9121197489135682,
      "grad_norm": 1.49802902853701,
      "learning_rate": 5e-06,
      "loss": 0.3234,
      "step": 1980
    },
    {
      "epoch": 1.9217769193626268,
      "grad_norm": 1.4807948737028658,
      "learning_rate": 5e-06,
      "loss": 0.322,
      "step": 1990
    },
    {
      "epoch": 1.931434089811685,
      "grad_norm": 1.3868348286955445,
      "learning_rate": 5e-06,
      "loss": 0.3247,
      "step": 2000
    },
    {
      "epoch": 1.9410912602607437,
      "grad_norm": 1.6163693821676344,
      "learning_rate": 5e-06,
      "loss": 0.3248,
      "step": 2010
    },
    {
      "epoch": 1.950748430709802,
      "grad_norm": 1.552439354775519,
      "learning_rate": 5e-06,
      "loss": 0.3233,
      "step": 2020
    },
    {
      "epoch": 1.9604056011588604,
      "grad_norm": 1.5224507289579325,
      "learning_rate": 5e-06,
      "loss": 0.3311,
      "step": 2030
    },
    {
      "epoch": 1.9700627716079189,
      "grad_norm": 1.3715156278923533,
      "learning_rate": 5e-06,
      "loss": 0.3224,
      "step": 2040
    },
    {
      "epoch": 1.9797199420569773,
      "grad_norm": 1.4690837804253396,
      "learning_rate": 5e-06,
      "loss": 0.3245,
      "step": 2050
    },
    {
      "epoch": 1.9893771125060358,
      "grad_norm": 1.5304270102797093,
      "learning_rate": 5e-06,
      "loss": 0.3283,
      "step": 2060
    },
    {
      "epoch": 1.999034282955094,
      "grad_norm": 1.5064039907716613,
      "learning_rate": 5e-06,
      "loss": 0.326,
      "step": 2070
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.41363242268562317,
      "eval_runtime": 183.9864,
      "eval_samples_per_second": 151.658,
      "eval_steps_per_second": 0.592,
      "step": 2071
    },
    {
      "epoch": 2.0086914534041527,
      "grad_norm": 1.9529357489293813,
      "learning_rate": 5e-06,
      "loss": 0.2222,
      "step": 2080
    },
    {
      "epoch": 2.018348623853211,
      "grad_norm": 1.755518669301023,
      "learning_rate": 5e-06,
      "loss": 0.2019,
      "step": 2090
    },
    {
      "epoch": 2.0280057943022696,
      "grad_norm": 1.740635003243075,
      "learning_rate": 5e-06,
      "loss": 0.203,
      "step": 2100
    },
    {
      "epoch": 2.037662964751328,
      "grad_norm": 1.8237819578036996,
      "learning_rate": 5e-06,
      "loss": 0.1982,
      "step": 2110
    },
    {
      "epoch": 2.0473201352003865,
      "grad_norm": 1.5602633442114324,
      "learning_rate": 5e-06,
      "loss": 0.1992,
      "step": 2120
    },
    {
      "epoch": 2.0569773056494447,
      "grad_norm": 1.816471476491465,
      "learning_rate": 5e-06,
      "loss": 0.2049,
      "step": 2130
    },
    {
      "epoch": 2.066634476098503,
      "grad_norm": 1.7673442658203458,
      "learning_rate": 5e-06,
      "loss": 0.1993,
      "step": 2140
    },
    {
      "epoch": 2.0762916465475616,
      "grad_norm": 1.6973737687900528,
      "learning_rate": 5e-06,
      "loss": 0.1998,
      "step": 2150
    },
    {
      "epoch": 2.08594881699662,
      "grad_norm": 1.5869449008271677,
      "learning_rate": 5e-06,
      "loss": 0.202,
      "step": 2160
    },
    {
      "epoch": 2.0956059874456785,
      "grad_norm": 1.64683922032891,
      "learning_rate": 5e-06,
      "loss": 0.2002,
      "step": 2170
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 1.9386924431067427,
      "learning_rate": 5e-06,
      "loss": 0.2076,
      "step": 2180
    },
    {
      "epoch": 2.1149203283437954,
      "grad_norm": 1.6210647566768155,
      "learning_rate": 5e-06,
      "loss": 0.2028,
      "step": 2190
    },
    {
      "epoch": 2.1245774987928536,
      "grad_norm": 1.6287574889203644,
      "learning_rate": 5e-06,
      "loss": 0.2042,
      "step": 2200
    },
    {
      "epoch": 2.1342346692419123,
      "grad_norm": 1.655477861818872,
      "learning_rate": 5e-06,
      "loss": 0.2013,
      "step": 2210
    },
    {
      "epoch": 2.1438918396909705,
      "grad_norm": 1.5729371185522592,
      "learning_rate": 5e-06,
      "loss": 0.2015,
      "step": 2220
    },
    {
      "epoch": 2.153549010140029,
      "grad_norm": 1.6476425123948135,
      "learning_rate": 5e-06,
      "loss": 0.2012,
      "step": 2230
    },
    {
      "epoch": 2.1632061805890874,
      "grad_norm": 1.8001638906124682,
      "learning_rate": 5e-06,
      "loss": 0.2008,
      "step": 2240
    },
    {
      "epoch": 2.1728633510381457,
      "grad_norm": 1.7044240854710664,
      "learning_rate": 5e-06,
      "loss": 0.2054,
      "step": 2250
    },
    {
      "epoch": 2.1825205214872043,
      "grad_norm": 1.7542655066679125,
      "learning_rate": 5e-06,
      "loss": 0.2034,
      "step": 2260
    },
    {
      "epoch": 2.1921776919362626,
      "grad_norm": 1.6322702947383616,
      "learning_rate": 5e-06,
      "loss": 0.2057,
      "step": 2270
    },
    {
      "epoch": 2.2018348623853212,
      "grad_norm": 1.6677542060673687,
      "learning_rate": 5e-06,
      "loss": 0.207,
      "step": 2280
    },
    {
      "epoch": 2.2114920328343795,
      "grad_norm": 1.7199005988447569,
      "learning_rate": 5e-06,
      "loss": 0.2078,
      "step": 2290
    },
    {
      "epoch": 2.221149203283438,
      "grad_norm": 1.7417097237727022,
      "learning_rate": 5e-06,
      "loss": 0.2056,
      "step": 2300
    },
    {
      "epoch": 2.2308063737324964,
      "grad_norm": 1.7881569830854456,
      "learning_rate": 5e-06,
      "loss": 0.2018,
      "step": 2310
    },
    {
      "epoch": 2.240463544181555,
      "grad_norm": 1.778258239931456,
      "learning_rate": 5e-06,
      "loss": 0.2085,
      "step": 2320
    },
    {
      "epoch": 2.2501207146306133,
      "grad_norm": 1.7066617550978782,
      "learning_rate": 5e-06,
      "loss": 0.2081,
      "step": 2330
    },
    {
      "epoch": 2.2597778850796715,
      "grad_norm": 1.6359235244009738,
      "learning_rate": 5e-06,
      "loss": 0.2068,
      "step": 2340
    },
    {
      "epoch": 2.26943505552873,
      "grad_norm": 1.9690603812490861,
      "learning_rate": 5e-06,
      "loss": 0.2093,
      "step": 2350
    },
    {
      "epoch": 2.2790922259777884,
      "grad_norm": 1.8155935869005713,
      "learning_rate": 5e-06,
      "loss": 0.2086,
      "step": 2360
    },
    {
      "epoch": 2.288749396426847,
      "grad_norm": 1.7505898538326212,
      "learning_rate": 5e-06,
      "loss": 0.2082,
      "step": 2370
    },
    {
      "epoch": 2.2984065668759053,
      "grad_norm": 1.687851682529015,
      "learning_rate": 5e-06,
      "loss": 0.2094,
      "step": 2380
    },
    {
      "epoch": 2.308063737324964,
      "grad_norm": 2.0069895205569535,
      "learning_rate": 5e-06,
      "loss": 0.2114,
      "step": 2390
    },
    {
      "epoch": 2.317720907774022,
      "grad_norm": 1.8064841179245696,
      "learning_rate": 5e-06,
      "loss": 0.2059,
      "step": 2400
    },
    {
      "epoch": 2.327378078223081,
      "grad_norm": 1.7513896709251378,
      "learning_rate": 5e-06,
      "loss": 0.2073,
      "step": 2410
    },
    {
      "epoch": 2.337035248672139,
      "grad_norm": 1.7915692908106093,
      "learning_rate": 5e-06,
      "loss": 0.2097,
      "step": 2420
    },
    {
      "epoch": 2.3466924191211973,
      "grad_norm": 1.6328915879521833,
      "learning_rate": 5e-06,
      "loss": 0.2126,
      "step": 2430
    },
    {
      "epoch": 2.356349589570256,
      "grad_norm": 1.6676621870989963,
      "learning_rate": 5e-06,
      "loss": 0.2082,
      "step": 2440
    },
    {
      "epoch": 2.366006760019314,
      "grad_norm": 1.71621065929775,
      "learning_rate": 5e-06,
      "loss": 0.2079,
      "step": 2450
    },
    {
      "epoch": 2.375663930468373,
      "grad_norm": 1.6107515870333837,
      "learning_rate": 5e-06,
      "loss": 0.213,
      "step": 2460
    },
    {
      "epoch": 2.385321100917431,
      "grad_norm": 1.723592646527568,
      "learning_rate": 5e-06,
      "loss": 0.2112,
      "step": 2470
    },
    {
      "epoch": 2.3949782713664898,
      "grad_norm": 1.810751615032428,
      "learning_rate": 5e-06,
      "loss": 0.214,
      "step": 2480
    },
    {
      "epoch": 2.404635441815548,
      "grad_norm": 1.8583457997365094,
      "learning_rate": 5e-06,
      "loss": 0.2133,
      "step": 2490
    },
    {
      "epoch": 2.4142926122646067,
      "grad_norm": 1.8098882466647033,
      "learning_rate": 5e-06,
      "loss": 0.2118,
      "step": 2500
    },
    {
      "epoch": 2.423949782713665,
      "grad_norm": 1.7310394353267804,
      "learning_rate": 5e-06,
      "loss": 0.2091,
      "step": 2510
    },
    {
      "epoch": 2.433606953162723,
      "grad_norm": 1.9482929822769175,
      "learning_rate": 5e-06,
      "loss": 0.2103,
      "step": 2520
    },
    {
      "epoch": 2.443264123611782,
      "grad_norm": 1.8075435579847086,
      "learning_rate": 5e-06,
      "loss": 0.2111,
      "step": 2530
    },
    {
      "epoch": 2.45292129406084,
      "grad_norm": 1.6649997057492705,
      "learning_rate": 5e-06,
      "loss": 0.2119,
      "step": 2540
    },
    {
      "epoch": 2.4625784645098987,
      "grad_norm": 1.595570416233996,
      "learning_rate": 5e-06,
      "loss": 0.209,
      "step": 2550
    },
    {
      "epoch": 2.472235634958957,
      "grad_norm": 1.707621313978413,
      "learning_rate": 5e-06,
      "loss": 0.2124,
      "step": 2560
    },
    {
      "epoch": 2.4818928054080156,
      "grad_norm": 1.7540598817249424,
      "learning_rate": 5e-06,
      "loss": 0.2134,
      "step": 2570
    },
    {
      "epoch": 2.491549975857074,
      "grad_norm": 1.7644906677930094,
      "learning_rate": 5e-06,
      "loss": 0.212,
      "step": 2580
    },
    {
      "epoch": 2.5012071463061325,
      "grad_norm": 1.7556689404760746,
      "learning_rate": 5e-06,
      "loss": 0.2141,
      "step": 2590
    },
    {
      "epoch": 2.5108643167551907,
      "grad_norm": 1.7473267171283928,
      "learning_rate": 5e-06,
      "loss": 0.2124,
      "step": 2600
    },
    {
      "epoch": 2.520521487204249,
      "grad_norm": 1.9136137702521907,
      "learning_rate": 5e-06,
      "loss": 0.2127,
      "step": 2610
    },
    {
      "epoch": 2.5301786576533076,
      "grad_norm": 1.7481532118907182,
      "learning_rate": 5e-06,
      "loss": 0.2131,
      "step": 2620
    },
    {
      "epoch": 2.539835828102366,
      "grad_norm": 1.832460065168467,
      "learning_rate": 5e-06,
      "loss": 0.2153,
      "step": 2630
    },
    {
      "epoch": 2.5494929985514245,
      "grad_norm": 1.6966236245813655,
      "learning_rate": 5e-06,
      "loss": 0.2131,
      "step": 2640
    },
    {
      "epoch": 2.5591501690004828,
      "grad_norm": 1.7181221486120444,
      "learning_rate": 5e-06,
      "loss": 0.213,
      "step": 2650
    },
    {
      "epoch": 2.5688073394495414,
      "grad_norm": 1.6118010065233517,
      "learning_rate": 5e-06,
      "loss": 0.2148,
      "step": 2660
    },
    {
      "epoch": 2.5784645098985997,
      "grad_norm": 1.7015205827064956,
      "learning_rate": 5e-06,
      "loss": 0.219,
      "step": 2670
    },
    {
      "epoch": 2.5881216803476583,
      "grad_norm": 1.688200340928073,
      "learning_rate": 5e-06,
      "loss": 0.2145,
      "step": 2680
    },
    {
      "epoch": 2.5977788507967166,
      "grad_norm": 1.628479976082271,
      "learning_rate": 5e-06,
      "loss": 0.2173,
      "step": 2690
    },
    {
      "epoch": 2.607436021245775,
      "grad_norm": 1.6284654190992232,
      "learning_rate": 5e-06,
      "loss": 0.2166,
      "step": 2700
    },
    {
      "epoch": 2.6170931916948335,
      "grad_norm": 1.7027701458933544,
      "learning_rate": 5e-06,
      "loss": 0.2154,
      "step": 2710
    },
    {
      "epoch": 2.6267503621438917,
      "grad_norm": 1.6155718880952934,
      "learning_rate": 5e-06,
      "loss": 0.2154,
      "step": 2720
    },
    {
      "epoch": 2.6364075325929504,
      "grad_norm": 1.6351349351929865,
      "learning_rate": 5e-06,
      "loss": 0.2161,
      "step": 2730
    },
    {
      "epoch": 2.6460647030420086,
      "grad_norm": 1.7361275613850788,
      "learning_rate": 5e-06,
      "loss": 0.2183,
      "step": 2740
    },
    {
      "epoch": 2.6557218734910673,
      "grad_norm": 1.9309759687598864,
      "learning_rate": 5e-06,
      "loss": 0.2183,
      "step": 2750
    },
    {
      "epoch": 2.6653790439401255,
      "grad_norm": 1.7778715949832347,
      "learning_rate": 5e-06,
      "loss": 0.2164,
      "step": 2760
    },
    {
      "epoch": 2.675036214389184,
      "grad_norm": 1.689951172416981,
      "learning_rate": 5e-06,
      "loss": 0.2181,
      "step": 2770
    },
    {
      "epoch": 2.6846933848382424,
      "grad_norm": 1.9355370897589272,
      "learning_rate": 5e-06,
      "loss": 0.2205,
      "step": 2780
    },
    {
      "epoch": 2.6943505552873006,
      "grad_norm": 1.8460056442038406,
      "learning_rate": 5e-06,
      "loss": 0.2153,
      "step": 2790
    },
    {
      "epoch": 2.7040077257363593,
      "grad_norm": 1.857187825531335,
      "learning_rate": 5e-06,
      "loss": 0.2194,
      "step": 2800
    },
    {
      "epoch": 2.7136648961854175,
      "grad_norm": 1.7784483414745131,
      "learning_rate": 5e-06,
      "loss": 0.2155,
      "step": 2810
    },
    {
      "epoch": 2.723322066634476,
      "grad_norm": 1.6570596632282855,
      "learning_rate": 5e-06,
      "loss": 0.2204,
      "step": 2820
    },
    {
      "epoch": 2.7329792370835344,
      "grad_norm": 1.8006740077758066,
      "learning_rate": 5e-06,
      "loss": 0.2185,
      "step": 2830
    },
    {
      "epoch": 2.742636407532593,
      "grad_norm": 1.6910488555694076,
      "learning_rate": 5e-06,
      "loss": 0.2215,
      "step": 2840
    },
    {
      "epoch": 2.7522935779816513,
      "grad_norm": 1.6824061864717337,
      "learning_rate": 5e-06,
      "loss": 0.2168,
      "step": 2850
    },
    {
      "epoch": 2.76195074843071,
      "grad_norm": 1.667248411860486,
      "learning_rate": 5e-06,
      "loss": 0.2171,
      "step": 2860
    },
    {
      "epoch": 2.771607918879768,
      "grad_norm": 1.6621742506671506,
      "learning_rate": 5e-06,
      "loss": 0.2172,
      "step": 2870
    },
    {
      "epoch": 2.7812650893288264,
      "grad_norm": 1.951777361512585,
      "learning_rate": 5e-06,
      "loss": 0.2169,
      "step": 2880
    },
    {
      "epoch": 2.790922259777885,
      "grad_norm": 1.6376961183273515,
      "learning_rate": 5e-06,
      "loss": 0.2184,
      "step": 2890
    },
    {
      "epoch": 2.8005794302269438,
      "grad_norm": 1.7499302221356705,
      "learning_rate": 5e-06,
      "loss": 0.2172,
      "step": 2900
    },
    {
      "epoch": 2.810236600676002,
      "grad_norm": 1.6961296830905148,
      "learning_rate": 5e-06,
      "loss": 0.2191,
      "step": 2910
    },
    {
      "epoch": 2.8198937711250602,
      "grad_norm": 1.7673008414488,
      "learning_rate": 5e-06,
      "loss": 0.2203,
      "step": 2920
    },
    {
      "epoch": 2.829550941574119,
      "grad_norm": 1.756708895885833,
      "learning_rate": 5e-06,
      "loss": 0.2192,
      "step": 2930
    },
    {
      "epoch": 2.839208112023177,
      "grad_norm": 1.7064534219401073,
      "learning_rate": 5e-06,
      "loss": 0.2194,
      "step": 2940
    },
    {
      "epoch": 2.848865282472236,
      "grad_norm": 1.854536004459549,
      "learning_rate": 5e-06,
      "loss": 0.2207,
      "step": 2950
    },
    {
      "epoch": 2.858522452921294,
      "grad_norm": 1.7590173226380559,
      "learning_rate": 5e-06,
      "loss": 0.2234,
      "step": 2960
    },
    {
      "epoch": 2.8681796233703523,
      "grad_norm": 1.6888816007203014,
      "learning_rate": 5e-06,
      "loss": 0.2206,
      "step": 2970
    },
    {
      "epoch": 2.877836793819411,
      "grad_norm": 1.8848356855139519,
      "learning_rate": 5e-06,
      "loss": 0.2199,
      "step": 2980
    },
    {
      "epoch": 2.8874939642684696,
      "grad_norm": 1.7081747642661718,
      "learning_rate": 5e-06,
      "loss": 0.2181,
      "step": 2990
    },
    {
      "epoch": 2.897151134717528,
      "grad_norm": 1.8139898022279473,
      "learning_rate": 5e-06,
      "loss": 0.221,
      "step": 3000
    },
    {
      "epoch": 2.906808305166586,
      "grad_norm": 1.8123670196961439,
      "learning_rate": 5e-06,
      "loss": 0.2176,
      "step": 3010
    },
    {
      "epoch": 2.9164654756156447,
      "grad_norm": 1.6673754695154868,
      "learning_rate": 5e-06,
      "loss": 0.2232,
      "step": 3020
    },
    {
      "epoch": 2.926122646064703,
      "grad_norm": 1.6571101014785201,
      "learning_rate": 5e-06,
      "loss": 0.2203,
      "step": 3030
    },
    {
      "epoch": 2.9357798165137616,
      "grad_norm": 1.7173214731808049,
      "learning_rate": 5e-06,
      "loss": 0.2215,
      "step": 3040
    },
    {
      "epoch": 2.94543698696282,
      "grad_norm": 1.74112205509197,
      "learning_rate": 5e-06,
      "loss": 0.2193,
      "step": 3050
    },
    {
      "epoch": 2.955094157411878,
      "grad_norm": 1.6720045527666803,
      "learning_rate": 5e-06,
      "loss": 0.2215,
      "step": 3060
    },
    {
      "epoch": 2.9647513278609368,
      "grad_norm": 1.699005956548853,
      "learning_rate": 5e-06,
      "loss": 0.2208,
      "step": 3070
    },
    {
      "epoch": 2.9744084983099954,
      "grad_norm": 1.65145518846451,
      "learning_rate": 5e-06,
      "loss": 0.2229,
      "step": 3080
    },
    {
      "epoch": 2.9840656687590537,
      "grad_norm": 1.7864091472536987,
      "learning_rate": 5e-06,
      "loss": 0.2221,
      "step": 3090
    },
    {
      "epoch": 2.993722839208112,
      "grad_norm": 1.7192522447102805,
      "learning_rate": 5e-06,
      "loss": 0.2213,
      "step": 3100
    },
    {
      "epoch": 2.998551424432641,
      "eval_loss": 0.4467960000038147,
      "eval_runtime": 177.447,
      "eval_samples_per_second": 157.247,
      "eval_steps_per_second": 0.614,
      "step": 3105
    },
    {
      "epoch": 2.998551424432641,
      "step": 3105,
      "total_flos": 5200153128468480.0,
      "train_loss": 0.3273588392085691,
      "train_runtime": 26340.0491,
      "train_samples_per_second": 60.381,
      "train_steps_per_second": 0.118
    }
  ],
  "logging_steps": 10,
  "max_steps": 3105,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5200153128468480.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}