{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0013418015922713,
"eval_steps": 500,
"global_step": 11194,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0008945343948474819,
"grad_norm": 5.675168037414551,
"learning_rate": 1.1061797752808989e-06,
"loss": 2.1196,
"step": 10
},
{
"epoch": 0.0017890687896949637,
"grad_norm": 2.9707770347595215,
"learning_rate": 2.2241573033707866e-06,
"loss": 2.0311,
"step": 20
},
{
"epoch": 0.0026836031845424457,
"grad_norm": 1.5259026288986206,
"learning_rate": 3.342134831460675e-06,
"loss": 1.6404,
"step": 30
},
{
"epoch": 0.0035781375793899274,
"grad_norm": 0.9031808376312256,
"learning_rate": 4.4601123595505624e-06,
"loss": 1.4353,
"step": 40
},
{
"epoch": 0.00447267197423741,
"grad_norm": 0.7855185270309448,
"learning_rate": 5.5780898876404495e-06,
"loss": 1.2916,
"step": 50
},
{
"epoch": 0.005367206369084891,
"grad_norm": 0.7476404905319214,
"learning_rate": 6.6960674157303374e-06,
"loss": 1.1757,
"step": 60
},
{
"epoch": 0.006261740763932373,
"grad_norm": 0.7190150022506714,
"learning_rate": 7.814044943820226e-06,
"loss": 1.1344,
"step": 70
},
{
"epoch": 0.007156275158779855,
"grad_norm": 0.6955579519271851,
"learning_rate": 8.932022471910112e-06,
"loss": 1.0784,
"step": 80
},
{
"epoch": 0.008050809553627337,
"grad_norm": 0.613128662109375,
"learning_rate": 1.005e-05,
"loss": 1.0716,
"step": 90
},
{
"epoch": 0.00894534394847482,
"grad_norm": 0.6427867412567139,
"learning_rate": 1.1167977528089888e-05,
"loss": 1.0965,
"step": 100
},
{
"epoch": 0.009839878343322301,
"grad_norm": 0.6494929194450378,
"learning_rate": 1.2285955056179776e-05,
"loss": 1.0301,
"step": 110
},
{
"epoch": 0.010734412738169783,
"grad_norm": 0.656710684299469,
"learning_rate": 1.3403932584269664e-05,
"loss": 1.0766,
"step": 120
},
{
"epoch": 0.011628947133017264,
"grad_norm": 0.6478440165519714,
"learning_rate": 1.4521910112359552e-05,
"loss": 1.0263,
"step": 130
},
{
"epoch": 0.012523481527864746,
"grad_norm": 0.6425960659980774,
"learning_rate": 1.563988764044944e-05,
"loss": 1.0401,
"step": 140
},
{
"epoch": 0.013418015922712228,
"grad_norm": 0.6716069579124451,
"learning_rate": 1.6757865168539328e-05,
"loss": 1.0294,
"step": 150
},
{
"epoch": 0.01431255031755971,
"grad_norm": 0.6451089978218079,
"learning_rate": 1.7875842696629214e-05,
"loss": 1.002,
"step": 160
},
{
"epoch": 0.015207084712407191,
"grad_norm": 0.6245432496070862,
"learning_rate": 1.89938202247191e-05,
"loss": 1.0152,
"step": 170
},
{
"epoch": 0.016101619107254675,
"grad_norm": 0.5898470878601074,
"learning_rate": 2e-05,
"loss": 1.0188,
"step": 180
},
{
"epoch": 0.016996153502102155,
"grad_norm": 0.612930953502655,
"learning_rate": 2e-05,
"loss": 1.0252,
"step": 190
},
{
"epoch": 0.01789068789694964,
"grad_norm": 0.5948618054389954,
"learning_rate": 2e-05,
"loss": 0.9977,
"step": 200
},
{
"epoch": 0.01878522229179712,
"grad_norm": 0.6210647821426392,
"learning_rate": 2e-05,
"loss": 1.0267,
"step": 210
},
{
"epoch": 0.019679756686644602,
"grad_norm": 0.580319344997406,
"learning_rate": 2e-05,
"loss": 1.0047,
"step": 220
},
{
"epoch": 0.020574291081492082,
"grad_norm": 0.5656352639198303,
"learning_rate": 2e-05,
"loss": 0.9926,
"step": 230
},
{
"epoch": 0.021468825476339565,
"grad_norm": 0.6239637136459351,
"learning_rate": 2e-05,
"loss": 1.0122,
"step": 240
},
{
"epoch": 0.022363359871187045,
"grad_norm": 0.5792014002799988,
"learning_rate": 2e-05,
"loss": 1.0079,
"step": 250
},
{
"epoch": 0.02325789426603453,
"grad_norm": 0.5544520616531372,
"learning_rate": 2e-05,
"loss": 1.0014,
"step": 260
},
{
"epoch": 0.024152428660882012,
"grad_norm": 0.5646398663520813,
"learning_rate": 2e-05,
"loss": 1.0073,
"step": 270
},
{
"epoch": 0.025046963055729492,
"grad_norm": 0.5469699501991272,
"learning_rate": 2e-05,
"loss": 0.9744,
"step": 280
},
{
"epoch": 0.025941497450576976,
"grad_norm": 0.5659817457199097,
"learning_rate": 2e-05,
"loss": 1.0111,
"step": 290
},
{
"epoch": 0.026836031845424456,
"grad_norm": 0.5720058679580688,
"learning_rate": 2e-05,
"loss": 0.9685,
"step": 300
},
{
"epoch": 0.02773056624027194,
"grad_norm": 0.5695531964302063,
"learning_rate": 2e-05,
"loss": 0.9996,
"step": 310
},
{
"epoch": 0.02862510063511942,
"grad_norm": 0.5718349814414978,
"learning_rate": 2e-05,
"loss": 1.0562,
"step": 320
},
{
"epoch": 0.029519635029966903,
"grad_norm": 0.5322186946868896,
"learning_rate": 2e-05,
"loss": 0.9927,
"step": 330
},
{
"epoch": 0.030414169424814383,
"grad_norm": 0.5264423489570618,
"learning_rate": 2e-05,
"loss": 0.9787,
"step": 340
},
{
"epoch": 0.031308703819661866,
"grad_norm": 0.5364736318588257,
"learning_rate": 2e-05,
"loss": 0.9557,
"step": 350
},
{
"epoch": 0.03220323821450935,
"grad_norm": 0.5510904788970947,
"learning_rate": 2e-05,
"loss": 0.9946,
"step": 360
},
{
"epoch": 0.033097772609356826,
"grad_norm": 0.5201677083969116,
"learning_rate": 2e-05,
"loss": 0.9811,
"step": 370
},
{
"epoch": 0.03399230700420431,
"grad_norm": 0.5272532105445862,
"learning_rate": 2e-05,
"loss": 0.9672,
"step": 380
},
{
"epoch": 0.03488684139905179,
"grad_norm": 0.5318697690963745,
"learning_rate": 2e-05,
"loss": 0.9779,
"step": 390
},
{
"epoch": 0.03578137579389928,
"grad_norm": 0.5327851176261902,
"learning_rate": 2e-05,
"loss": 0.9924,
"step": 400
},
{
"epoch": 0.03667591018874676,
"grad_norm": 0.5506769418716431,
"learning_rate": 2e-05,
"loss": 0.9944,
"step": 410
},
{
"epoch": 0.03757044458359424,
"grad_norm": 0.5046197772026062,
"learning_rate": 2e-05,
"loss": 0.955,
"step": 420
},
{
"epoch": 0.03846497897844172,
"grad_norm": 0.514418363571167,
"learning_rate": 2e-05,
"loss": 0.9716,
"step": 430
},
{
"epoch": 0.039359513373289204,
"grad_norm": 0.5306272506713867,
"learning_rate": 2e-05,
"loss": 0.9573,
"step": 440
},
{
"epoch": 0.04025404776813669,
"grad_norm": 0.5712807178497314,
"learning_rate": 2e-05,
"loss": 0.9735,
"step": 450
},
{
"epoch": 0.041148582162984164,
"grad_norm": 0.5208743810653687,
"learning_rate": 2e-05,
"loss": 0.9579,
"step": 460
},
{
"epoch": 0.04204311655783165,
"grad_norm": 0.5234618782997131,
"learning_rate": 2e-05,
"loss": 0.972,
"step": 470
},
{
"epoch": 0.04293765095267913,
"grad_norm": 0.5433705449104309,
"learning_rate": 2e-05,
"loss": 0.9576,
"step": 480
},
{
"epoch": 0.043832185347526614,
"grad_norm": 0.4861101806163788,
"learning_rate": 2e-05,
"loss": 0.9465,
"step": 490
},
{
"epoch": 0.04472671974237409,
"grad_norm": 0.5443506240844727,
"learning_rate": 2e-05,
"loss": 0.9752,
"step": 500
},
{
"epoch": 0.045621254137221574,
"grad_norm": 0.516825258731842,
"learning_rate": 2e-05,
"loss": 0.9402,
"step": 510
},
{
"epoch": 0.04651578853206906,
"grad_norm": 0.5197014212608337,
"learning_rate": 2e-05,
"loss": 0.9663,
"step": 520
},
{
"epoch": 0.04741032292691654,
"grad_norm": 0.4976901710033417,
"learning_rate": 2e-05,
"loss": 0.955,
"step": 530
},
{
"epoch": 0.048304857321764025,
"grad_norm": 0.5131090879440308,
"learning_rate": 2e-05,
"loss": 0.9645,
"step": 540
},
{
"epoch": 0.0491993917166115,
"grad_norm": 0.5310055017471313,
"learning_rate": 2e-05,
"loss": 0.9546,
"step": 550
},
{
"epoch": 0.050093926111458985,
"grad_norm": 0.4865564703941345,
"learning_rate": 2e-05,
"loss": 0.9513,
"step": 560
},
{
"epoch": 0.05098846050630647,
"grad_norm": 0.5074427723884583,
"learning_rate": 2e-05,
"loss": 0.941,
"step": 570
},
{
"epoch": 0.05188299490115395,
"grad_norm": 0.5017594695091248,
"learning_rate": 2e-05,
"loss": 0.9416,
"step": 580
},
{
"epoch": 0.05277752929600143,
"grad_norm": 0.5020937919616699,
"learning_rate": 2e-05,
"loss": 0.9775,
"step": 590
},
{
"epoch": 0.05367206369084891,
"grad_norm": 0.5406600832939148,
"learning_rate": 2e-05,
"loss": 0.9408,
"step": 600
},
{
"epoch": 0.054566598085696395,
"grad_norm": 0.529053807258606,
"learning_rate": 2e-05,
"loss": 0.95,
"step": 610
},
{
"epoch": 0.05546113248054388,
"grad_norm": 0.5157285332679749,
"learning_rate": 2e-05,
"loss": 0.9448,
"step": 620
},
{
"epoch": 0.056355666875391355,
"grad_norm": 0.48365968465805054,
"learning_rate": 2e-05,
"loss": 0.9539,
"step": 630
},
{
"epoch": 0.05725020127023884,
"grad_norm": 0.5019218921661377,
"learning_rate": 2e-05,
"loss": 0.9138,
"step": 640
},
{
"epoch": 0.05814473566508632,
"grad_norm": 0.4997801184654236,
"learning_rate": 2e-05,
"loss": 0.9519,
"step": 650
},
{
"epoch": 0.059039270059933806,
"grad_norm": 0.49150338768959045,
"learning_rate": 2e-05,
"loss": 0.9393,
"step": 660
},
{
"epoch": 0.05993380445478129,
"grad_norm": 0.49385330080986023,
"learning_rate": 2e-05,
"loss": 0.9255,
"step": 670
},
{
"epoch": 0.060828338849628766,
"grad_norm": 0.48065996170043945,
"learning_rate": 2e-05,
"loss": 0.9436,
"step": 680
},
{
"epoch": 0.06172287324447625,
"grad_norm": 0.48475712537765503,
"learning_rate": 2e-05,
"loss": 0.962,
"step": 690
},
{
"epoch": 0.06261740763932373,
"grad_norm": 0.48432332277297974,
"learning_rate": 2e-05,
"loss": 0.9409,
"step": 700
},
{
"epoch": 0.06351194203417121,
"grad_norm": 0.5160853862762451,
"learning_rate": 2e-05,
"loss": 0.9439,
"step": 710
},
{
"epoch": 0.0644064764290187,
"grad_norm": 0.5108107924461365,
"learning_rate": 2e-05,
"loss": 0.9427,
"step": 720
},
{
"epoch": 0.06530101082386618,
"grad_norm": 0.5226851105690002,
"learning_rate": 2e-05,
"loss": 0.9465,
"step": 730
},
{
"epoch": 0.06619554521871365,
"grad_norm": 0.5101060271263123,
"learning_rate": 2e-05,
"loss": 0.9428,
"step": 740
},
{
"epoch": 0.06709007961356114,
"grad_norm": 0.5003637671470642,
"learning_rate": 2e-05,
"loss": 0.9553,
"step": 750
},
{
"epoch": 0.06798461400840862,
"grad_norm": 0.4850715100765228,
"learning_rate": 2e-05,
"loss": 0.9295,
"step": 760
},
{
"epoch": 0.06887914840325611,
"grad_norm": 0.4759562313556671,
"learning_rate": 2e-05,
"loss": 0.9413,
"step": 770
},
{
"epoch": 0.06977368279810359,
"grad_norm": 0.4925222396850586,
"learning_rate": 2e-05,
"loss": 0.947,
"step": 780
},
{
"epoch": 0.07066821719295106,
"grad_norm": 0.47600677609443665,
"learning_rate": 2e-05,
"loss": 0.9349,
"step": 790
},
{
"epoch": 0.07156275158779855,
"grad_norm": 0.5029114484786987,
"learning_rate": 2e-05,
"loss": 0.9341,
"step": 800
},
{
"epoch": 0.07245728598264603,
"grad_norm": 0.4818347692489624,
"learning_rate": 2e-05,
"loss": 0.9505,
"step": 810
},
{
"epoch": 0.07335182037749352,
"grad_norm": 0.5230589509010315,
"learning_rate": 2e-05,
"loss": 0.9279,
"step": 820
},
{
"epoch": 0.074246354772341,
"grad_norm": 0.5369635224342346,
"learning_rate": 2e-05,
"loss": 0.9117,
"step": 830
},
{
"epoch": 0.07514088916718847,
"grad_norm": 0.4927598536014557,
"learning_rate": 2e-05,
"loss": 0.9225,
"step": 840
},
{
"epoch": 0.07603542356203596,
"grad_norm": 0.4878654479980469,
"learning_rate": 2e-05,
"loss": 0.9588,
"step": 850
},
{
"epoch": 0.07692995795688344,
"grad_norm": 0.589440643787384,
"learning_rate": 2e-05,
"loss": 0.9388,
"step": 860
},
{
"epoch": 0.07782449235173092,
"grad_norm": 0.48455187678337097,
"learning_rate": 2e-05,
"loss": 0.9194,
"step": 870
},
{
"epoch": 0.07871902674657841,
"grad_norm": 0.49978625774383545,
"learning_rate": 2e-05,
"loss": 0.9324,
"step": 880
},
{
"epoch": 0.07961356114142588,
"grad_norm": 0.5087828040122986,
"learning_rate": 2e-05,
"loss": 0.9421,
"step": 890
},
{
"epoch": 0.08050809553627337,
"grad_norm": 0.49013105034828186,
"learning_rate": 2e-05,
"loss": 0.9463,
"step": 900
},
{
"epoch": 0.08140262993112085,
"grad_norm": 0.46859070658683777,
"learning_rate": 2e-05,
"loss": 0.9414,
"step": 910
},
{
"epoch": 0.08229716432596833,
"grad_norm": 0.48060163855552673,
"learning_rate": 2e-05,
"loss": 0.9308,
"step": 920
},
{
"epoch": 0.08319169872081582,
"grad_norm": 0.4641304314136505,
"learning_rate": 2e-05,
"loss": 0.9334,
"step": 930
},
{
"epoch": 0.0840862331156633,
"grad_norm": 0.4877597689628601,
"learning_rate": 2e-05,
"loss": 0.9328,
"step": 940
},
{
"epoch": 0.08498076751051079,
"grad_norm": 0.4985778033733368,
"learning_rate": 2e-05,
"loss": 0.9366,
"step": 950
},
{
"epoch": 0.08587530190535826,
"grad_norm": 0.46850451827049255,
"learning_rate": 2e-05,
"loss": 0.949,
"step": 960
},
{
"epoch": 0.08676983630020574,
"grad_norm": 0.4797747731208801,
"learning_rate": 2e-05,
"loss": 0.9228,
"step": 970
},
{
"epoch": 0.08766437069505323,
"grad_norm": 0.4770503640174866,
"learning_rate": 2e-05,
"loss": 0.9281,
"step": 980
},
{
"epoch": 0.0885589050899007,
"grad_norm": 0.4758184552192688,
"learning_rate": 2e-05,
"loss": 0.9478,
"step": 990
},
{
"epoch": 0.08945343948474818,
"grad_norm": 0.4701295793056488,
"learning_rate": 2e-05,
"loss": 0.9192,
"step": 1000
},
{
"epoch": 0.09034797387959567,
"grad_norm": 0.49357926845550537,
"learning_rate": 2e-05,
"loss": 0.9252,
"step": 1010
},
{
"epoch": 0.09124250827444315,
"grad_norm": 0.45938366651535034,
"learning_rate": 2e-05,
"loss": 0.931,
"step": 1020
},
{
"epoch": 0.09213704266929064,
"grad_norm": 0.47234824299812317,
"learning_rate": 2e-05,
"loss": 0.9305,
"step": 1030
},
{
"epoch": 0.09303157706413812,
"grad_norm": 0.49671849608421326,
"learning_rate": 2e-05,
"loss": 0.9313,
"step": 1040
},
{
"epoch": 0.09392611145898559,
"grad_norm": 0.49155551195144653,
"learning_rate": 2e-05,
"loss": 0.9429,
"step": 1050
},
{
"epoch": 0.09482064585383308,
"grad_norm": 0.48902663588523865,
"learning_rate": 2e-05,
"loss": 0.9191,
"step": 1060
},
{
"epoch": 0.09571518024868056,
"grad_norm": 0.4676748812198639,
"learning_rate": 2e-05,
"loss": 0.9313,
"step": 1070
},
{
"epoch": 0.09660971464352805,
"grad_norm": 0.4561516344547272,
"learning_rate": 2e-05,
"loss": 0.9209,
"step": 1080
},
{
"epoch": 0.09750424903837553,
"grad_norm": 0.4574839174747467,
"learning_rate": 2e-05,
"loss": 0.9282,
"step": 1090
},
{
"epoch": 0.098398783433223,
"grad_norm": 0.6882016658782959,
"learning_rate": 2e-05,
"loss": 0.9194,
"step": 1100
},
{
"epoch": 0.0992933178280705,
"grad_norm": 0.5273155570030212,
"learning_rate": 2e-05,
"loss": 0.9447,
"step": 1110
},
{
"epoch": 0.10018785222291797,
"grad_norm": 0.4704069495201111,
"learning_rate": 2e-05,
"loss": 0.9131,
"step": 1120
},
{
"epoch": 0.10108238661776545,
"grad_norm": 0.46409177780151367,
"learning_rate": 2e-05,
"loss": 0.9012,
"step": 1130
},
{
"epoch": 0.10197692101261294,
"grad_norm": 0.47346293926239014,
"learning_rate": 2e-05,
"loss": 0.9129,
"step": 1140
},
{
"epoch": 0.10287145540746041,
"grad_norm": 0.4725669026374817,
"learning_rate": 2e-05,
"loss": 0.9222,
"step": 1150
},
{
"epoch": 0.1037659898023079,
"grad_norm": 0.45462873578071594,
"learning_rate": 2e-05,
"loss": 0.9069,
"step": 1160
},
{
"epoch": 0.10466052419715538,
"grad_norm": 0.4361211359500885,
"learning_rate": 2e-05,
"loss": 0.93,
"step": 1170
},
{
"epoch": 0.10555505859200286,
"grad_norm": 0.4952946901321411,
"learning_rate": 2e-05,
"loss": 0.9222,
"step": 1180
},
{
"epoch": 0.10644959298685035,
"grad_norm": 0.48436594009399414,
"learning_rate": 2e-05,
"loss": 0.9311,
"step": 1190
},
{
"epoch": 0.10734412738169782,
"grad_norm": 0.47711387276649475,
"learning_rate": 2e-05,
"loss": 0.9228,
"step": 1200
},
{
"epoch": 0.10823866177654531,
"grad_norm": 0.46835336089134216,
"learning_rate": 2e-05,
"loss": 0.9027,
"step": 1210
},
{
"epoch": 0.10913319617139279,
"grad_norm": 0.5128036737442017,
"learning_rate": 2e-05,
"loss": 0.9198,
"step": 1220
},
{
"epoch": 0.11002773056624027,
"grad_norm": 0.47244781255722046,
"learning_rate": 2e-05,
"loss": 0.9344,
"step": 1230
},
{
"epoch": 0.11092226496108776,
"grad_norm": 0.47003787755966187,
"learning_rate": 2e-05,
"loss": 0.8993,
"step": 1240
},
{
"epoch": 0.11181679935593523,
"grad_norm": 0.4747315049171448,
"learning_rate": 2e-05,
"loss": 0.9155,
"step": 1250
},
{
"epoch": 0.11271133375078271,
"grad_norm": 0.5968290567398071,
"learning_rate": 2e-05,
"loss": 0.9,
"step": 1260
},
{
"epoch": 0.1136058681456302,
"grad_norm": 0.4795837700366974,
"learning_rate": 2e-05,
"loss": 0.8999,
"step": 1270
},
{
"epoch": 0.11450040254047768,
"grad_norm": 0.4849240481853485,
"learning_rate": 2e-05,
"loss": 0.9043,
"step": 1280
},
{
"epoch": 0.11539493693532517,
"grad_norm": 0.45396119356155396,
"learning_rate": 2e-05,
"loss": 0.9236,
"step": 1290
},
{
"epoch": 0.11628947133017264,
"grad_norm": 0.4486008286476135,
"learning_rate": 2e-05,
"loss": 0.883,
"step": 1300
},
{
"epoch": 0.11718400572502012,
"grad_norm": 0.4643603265285492,
"learning_rate": 2e-05,
"loss": 0.9053,
"step": 1310
},
{
"epoch": 0.11807854011986761,
"grad_norm": 0.48251062631607056,
"learning_rate": 2e-05,
"loss": 0.91,
"step": 1320
},
{
"epoch": 0.11897307451471509,
"grad_norm": 0.4961690306663513,
"learning_rate": 2e-05,
"loss": 0.9044,
"step": 1330
},
{
"epoch": 0.11986760890956258,
"grad_norm": 0.4803570806980133,
"learning_rate": 2e-05,
"loss": 0.935,
"step": 1340
},
{
"epoch": 0.12076214330441006,
"grad_norm": 0.46828046441078186,
"learning_rate": 2e-05,
"loss": 0.9122,
"step": 1350
},
{
"epoch": 0.12165667769925753,
"grad_norm": 0.5151194334030151,
"learning_rate": 2e-05,
"loss": 0.9189,
"step": 1360
},
{
"epoch": 0.12255121209410502,
"grad_norm": 0.4741526246070862,
"learning_rate": 2e-05,
"loss": 0.9142,
"step": 1370
},
{
"epoch": 0.1234457464889525,
"grad_norm": 0.4384336471557617,
"learning_rate": 2e-05,
"loss": 0.9204,
"step": 1380
},
{
"epoch": 0.12434028088379999,
"grad_norm": 0.5426257252693176,
"learning_rate": 2e-05,
"loss": 0.9038,
"step": 1390
},
{
"epoch": 0.12523481527864747,
"grad_norm": 0.4690248966217041,
"learning_rate": 2e-05,
"loss": 0.9014,
"step": 1400
},
{
"epoch": 0.12612934967349496,
"grad_norm": 0.44816529750823975,
"learning_rate": 2e-05,
"loss": 0.8798,
"step": 1410
},
{
"epoch": 0.12702388406834242,
"grad_norm": 0.45386165380477905,
"learning_rate": 2e-05,
"loss": 0.9177,
"step": 1420
},
{
"epoch": 0.1279184184631899,
"grad_norm": 0.47421979904174805,
"learning_rate": 2e-05,
"loss": 0.8928,
"step": 1430
},
{
"epoch": 0.1288129528580374,
"grad_norm": 0.47659310698509216,
"learning_rate": 2e-05,
"loss": 0.9019,
"step": 1440
},
{
"epoch": 0.12970748725288486,
"grad_norm": 0.45950847864151,
"learning_rate": 2e-05,
"loss": 0.9254,
"step": 1450
},
{
"epoch": 0.13060202164773235,
"grad_norm": 0.4390353858470917,
"learning_rate": 2e-05,
"loss": 0.9061,
"step": 1460
},
{
"epoch": 0.13149655604257984,
"grad_norm": 0.5103998780250549,
"learning_rate": 2e-05,
"loss": 0.9362,
"step": 1470
},
{
"epoch": 0.1323910904374273,
"grad_norm": 0.48334017395973206,
"learning_rate": 2e-05,
"loss": 0.9005,
"step": 1480
},
{
"epoch": 0.1332856248322748,
"grad_norm": 0.45984673500061035,
"learning_rate": 2e-05,
"loss": 0.8878,
"step": 1490
},
{
"epoch": 0.1341801592271223,
"grad_norm": 0.4718729555606842,
"learning_rate": 2e-05,
"loss": 0.9176,
"step": 1500
},
{
"epoch": 0.13507469362196978,
"grad_norm": 0.4789274334907532,
"learning_rate": 2e-05,
"loss": 0.9029,
"step": 1510
},
{
"epoch": 0.13596922801681724,
"grad_norm": 0.45665860176086426,
"learning_rate": 2e-05,
"loss": 0.9085,
"step": 1520
},
{
"epoch": 0.13686376241166473,
"grad_norm": 0.4554169774055481,
"learning_rate": 2e-05,
"loss": 0.9031,
"step": 1530
},
{
"epoch": 0.13775829680651222,
"grad_norm": 0.4741033613681793,
"learning_rate": 2e-05,
"loss": 0.9122,
"step": 1540
},
{
"epoch": 0.13865283120135968,
"grad_norm": 0.48835477232933044,
"learning_rate": 2e-05,
"loss": 0.9215,
"step": 1550
},
{
"epoch": 0.13954736559620717,
"grad_norm": 0.4369822144508362,
"learning_rate": 2e-05,
"loss": 0.8953,
"step": 1560
},
{
"epoch": 0.14044189999105466,
"grad_norm": 0.4376717805862427,
"learning_rate": 2e-05,
"loss": 0.9003,
"step": 1570
},
{
"epoch": 0.14133643438590213,
"grad_norm": 0.4347819685935974,
"learning_rate": 2e-05,
"loss": 0.8993,
"step": 1580
},
{
"epoch": 0.14223096878074962,
"grad_norm": 0.4427725076675415,
"learning_rate": 2e-05,
"loss": 0.9025,
"step": 1590
},
{
"epoch": 0.1431255031755971,
"grad_norm": 0.45390942692756653,
"learning_rate": 2e-05,
"loss": 0.9003,
"step": 1600
},
{
"epoch": 0.14402003757044457,
"grad_norm": 0.45958849787712097,
"learning_rate": 2e-05,
"loss": 0.9039,
"step": 1610
},
{
"epoch": 0.14491457196529206,
"grad_norm": 0.45375823974609375,
"learning_rate": 2e-05,
"loss": 0.8962,
"step": 1620
},
{
"epoch": 0.14580910636013955,
"grad_norm": 0.4949476718902588,
"learning_rate": 2e-05,
"loss": 0.8817,
"step": 1630
},
{
"epoch": 0.14670364075498704,
"grad_norm": 0.4698850214481354,
"learning_rate": 2e-05,
"loss": 0.8954,
"step": 1640
},
{
"epoch": 0.1475981751498345,
"grad_norm": 0.4654884338378906,
"learning_rate": 2e-05,
"loss": 0.909,
"step": 1650
},
{
"epoch": 0.148492709544682,
"grad_norm": 0.45599988102912903,
"learning_rate": 2e-05,
"loss": 0.9082,
"step": 1660
},
{
"epoch": 0.14938724393952948,
"grad_norm": 0.4717373847961426,
"learning_rate": 2e-05,
"loss": 0.9158,
"step": 1670
},
{
"epoch": 0.15028177833437695,
"grad_norm": 0.48511821031570435,
"learning_rate": 2e-05,
"loss": 0.9123,
"step": 1680
},
{
"epoch": 0.15117631272922444,
"grad_norm": 0.45996376872062683,
"learning_rate": 2e-05,
"loss": 0.9081,
"step": 1690
},
{
"epoch": 0.15207084712407193,
"grad_norm": 0.46202340722084045,
"learning_rate": 2e-05,
"loss": 0.9267,
"step": 1700
},
{
"epoch": 0.1529653815189194,
"grad_norm": 0.4501361846923828,
"learning_rate": 2e-05,
"loss": 0.9107,
"step": 1710
},
{
"epoch": 0.15385991591376688,
"grad_norm": 0.46675220131874084,
"learning_rate": 2e-05,
"loss": 0.9009,
"step": 1720
},
{
"epoch": 0.15475445030861437,
"grad_norm": 0.4796220064163208,
"learning_rate": 2e-05,
"loss": 0.9012,
"step": 1730
},
{
"epoch": 0.15564898470346183,
"grad_norm": 0.4852994978427887,
"learning_rate": 2e-05,
"loss": 0.9032,
"step": 1740
},
{
"epoch": 0.15654351909830932,
"grad_norm": 0.4488218128681183,
"learning_rate": 2e-05,
"loss": 0.8956,
"step": 1750
},
{
"epoch": 0.15743805349315682,
"grad_norm": 0.4514853060245514,
"learning_rate": 2e-05,
"loss": 0.9065,
"step": 1760
},
{
"epoch": 0.1583325878880043,
"grad_norm": 0.45019781589508057,
"learning_rate": 2e-05,
"loss": 0.8699,
"step": 1770
},
{
"epoch": 0.15922712228285177,
"grad_norm": 0.4355997145175934,
"learning_rate": 2e-05,
"loss": 0.882,
"step": 1780
},
{
"epoch": 0.16012165667769926,
"grad_norm": 0.45496049523353577,
"learning_rate": 2e-05,
"loss": 0.8822,
"step": 1790
},
{
"epoch": 0.16101619107254675,
"grad_norm": 0.4723767936229706,
"learning_rate": 2e-05,
"loss": 0.8843,
"step": 1800
},
{
"epoch": 0.1619107254673942,
"grad_norm": 0.44647493958473206,
"learning_rate": 2e-05,
"loss": 0.9143,
"step": 1810
},
{
"epoch": 0.1628052598622417,
"grad_norm": 0.4418398439884186,
"learning_rate": 2e-05,
"loss": 0.8893,
"step": 1820
},
{
"epoch": 0.1636997942570892,
"grad_norm": 0.45358505845069885,
"learning_rate": 2e-05,
"loss": 0.9136,
"step": 1830
},
{
"epoch": 0.16459432865193666,
"grad_norm": 0.43691468238830566,
"learning_rate": 2e-05,
"loss": 0.9098,
"step": 1840
},
{
"epoch": 0.16548886304678415,
"grad_norm": 0.43452972173690796,
"learning_rate": 2e-05,
"loss": 0.9034,
"step": 1850
},
{
"epoch": 0.16638339744163164,
"grad_norm": 0.4491502046585083,
"learning_rate": 2e-05,
"loss": 0.8972,
"step": 1860
},
{
"epoch": 0.1672779318364791,
"grad_norm": 0.4505089223384857,
"learning_rate": 2e-05,
"loss": 0.8686,
"step": 1870
},
{
"epoch": 0.1681724662313266,
"grad_norm": 0.44601932168006897,
"learning_rate": 2e-05,
"loss": 0.8819,
"step": 1880
},
{
"epoch": 0.16906700062617408,
"grad_norm": 0.4459923803806305,
"learning_rate": 2e-05,
"loss": 0.8992,
"step": 1890
},
{
"epoch": 0.16996153502102157,
"grad_norm": 0.5818774700164795,
"learning_rate": 2e-05,
"loss": 0.8939,
"step": 1900
},
{
"epoch": 0.17085606941586903,
"grad_norm": 0.4722735583782196,
"learning_rate": 2e-05,
"loss": 0.9326,
"step": 1910
},
{
"epoch": 0.17175060381071652,
"grad_norm": 0.4823867976665497,
"learning_rate": 2e-05,
"loss": 0.8946,
"step": 1920
},
{
"epoch": 0.172645138205564,
"grad_norm": 0.44365358352661133,
"learning_rate": 2e-05,
"loss": 0.8925,
"step": 1930
},
{
"epoch": 0.17353967260041148,
"grad_norm": 0.4581582248210907,
"learning_rate": 2e-05,
"loss": 0.8966,
"step": 1940
},
{
"epoch": 0.17443420699525897,
"grad_norm": 0.4919745624065399,
"learning_rate": 2e-05,
"loss": 0.9013,
"step": 1950
},
{
"epoch": 0.17532874139010646,
"grad_norm": 0.44615697860717773,
"learning_rate": 2e-05,
"loss": 0.8969,
"step": 1960
},
{
"epoch": 0.17622327578495392,
"grad_norm": 0.45378655195236206,
"learning_rate": 2e-05,
"loss": 0.874,
"step": 1970
},
{
"epoch": 0.1771178101798014,
"grad_norm": 0.45912545919418335,
"learning_rate": 2e-05,
"loss": 0.8976,
"step": 1980
},
{
"epoch": 0.1780123445746489,
"grad_norm": 0.4544883966445923,
"learning_rate": 2e-05,
"loss": 0.8899,
"step": 1990
},
{
"epoch": 0.17890687896949636,
"grad_norm": 0.4370812475681305,
"learning_rate": 2e-05,
"loss": 0.8977,
"step": 2000
},
{
"epoch": 0.17980141336434385,
"grad_norm": 0.44847485423088074,
"learning_rate": 2e-05,
"loss": 0.8791,
"step": 2010
},
{
"epoch": 0.18069594775919134,
"grad_norm": 0.4509333074092865,
"learning_rate": 2e-05,
"loss": 0.8899,
"step": 2020
},
{
"epoch": 0.18159048215403883,
"grad_norm": 0.44739288091659546,
"learning_rate": 2e-05,
"loss": 0.9084,
"step": 2030
},
{
"epoch": 0.1824850165488863,
"grad_norm": 0.449127733707428,
"learning_rate": 2e-05,
"loss": 0.8859,
"step": 2040
},
{
"epoch": 0.1833795509437338,
"grad_norm": 0.4499713182449341,
"learning_rate": 2e-05,
"loss": 0.8903,
"step": 2050
},
{
"epoch": 0.18427408533858128,
"grad_norm": 0.4185994267463684,
"learning_rate": 2e-05,
"loss": 0.8626,
"step": 2060
},
{
"epoch": 0.18516861973342874,
"grad_norm": 0.4529339075088501,
"learning_rate": 2e-05,
"loss": 0.878,
"step": 2070
},
{
"epoch": 0.18606315412827623,
"grad_norm": 0.4742617905139923,
"learning_rate": 2e-05,
"loss": 0.8982,
"step": 2080
},
{
"epoch": 0.18695768852312372,
"grad_norm": 0.4461440145969391,
"learning_rate": 2e-05,
"loss": 0.8736,
"step": 2090
},
{
"epoch": 0.18785222291797118,
"grad_norm": 0.4527934193611145,
"learning_rate": 2e-05,
"loss": 0.882,
"step": 2100
},
{
"epoch": 0.18874675731281867,
"grad_norm": 0.43730732798576355,
"learning_rate": 2e-05,
"loss": 0.8802,
"step": 2110
},
{
"epoch": 0.18964129170766617,
"grad_norm": 0.44257083535194397,
"learning_rate": 2e-05,
"loss": 0.877,
"step": 2120
},
{
"epoch": 0.19053582610251363,
"grad_norm": 0.4498806595802307,
"learning_rate": 2e-05,
"loss": 0.9177,
"step": 2130
},
{
"epoch": 0.19143036049736112,
"grad_norm": 0.43403714895248413,
"learning_rate": 2e-05,
"loss": 0.8874,
"step": 2140
},
{
"epoch": 0.1923248948922086,
"grad_norm": 0.4649515151977539,
"learning_rate": 2e-05,
"loss": 0.882,
"step": 2150
},
{
"epoch": 0.1932194292870561,
"grad_norm": 0.43300893902778625,
"learning_rate": 2e-05,
"loss": 0.8978,
"step": 2160
},
{
"epoch": 0.19411396368190356,
"grad_norm": 0.4571026861667633,
"learning_rate": 2e-05,
"loss": 0.904,
"step": 2170
},
{
"epoch": 0.19500849807675105,
"grad_norm": 0.4482812285423279,
"learning_rate": 2e-05,
"loss": 0.8768,
"step": 2180
},
{
"epoch": 0.19590303247159854,
"grad_norm": 0.44305941462516785,
"learning_rate": 2e-05,
"loss": 0.892,
"step": 2190
},
{
"epoch": 0.196797566866446,
"grad_norm": 0.4517887532711029,
"learning_rate": 2e-05,
"loss": 0.8776,
"step": 2200
},
{
"epoch": 0.1976921012612935,
"grad_norm": 0.4652104675769806,
"learning_rate": 2e-05,
"loss": 0.8825,
"step": 2210
},
{
"epoch": 0.198586635656141,
"grad_norm": 0.4824739694595337,
"learning_rate": 2e-05,
"loss": 0.898,
"step": 2220
},
{
"epoch": 0.19948117005098845,
"grad_norm": 0.4381744861602783,
"learning_rate": 2e-05,
"loss": 0.8702,
"step": 2230
},
{
"epoch": 0.20037570444583594,
"grad_norm": 0.4330578148365021,
"learning_rate": 2e-05,
"loss": 0.8806,
"step": 2240
},
{
"epoch": 0.20127023884068343,
"grad_norm": 0.44513505697250366,
"learning_rate": 2e-05,
"loss": 0.8892,
"step": 2250
},
{
"epoch": 0.2021647732355309,
"grad_norm": 0.42694783210754395,
"learning_rate": 2e-05,
"loss": 0.8741,
"step": 2260
},
{
"epoch": 0.20305930763037838,
"grad_norm": 0.4454619884490967,
"learning_rate": 2e-05,
"loss": 0.871,
"step": 2270
},
{
"epoch": 0.20395384202522587,
"grad_norm": 0.4577361047267914,
"learning_rate": 2e-05,
"loss": 0.8874,
"step": 2280
},
{
"epoch": 0.20484837642007336,
"grad_norm": 0.4306597113609314,
"learning_rate": 2e-05,
"loss": 0.8895,
"step": 2290
},
{
"epoch": 0.20574291081492083,
"grad_norm": 0.4854651391506195,
"learning_rate": 2e-05,
"loss": 0.8888,
"step": 2300
},
{
"epoch": 0.20663744520976832,
"grad_norm": 0.44619086384773254,
"learning_rate": 2e-05,
"loss": 0.8871,
"step": 2310
},
{
"epoch": 0.2075319796046158,
"grad_norm": 0.47804850339889526,
"learning_rate": 2e-05,
"loss": 0.878,
"step": 2320
},
{
"epoch": 0.20842651399946327,
"grad_norm": 0.4363088607788086,
"learning_rate": 2e-05,
"loss": 0.8831,
"step": 2330
},
{
"epoch": 0.20932104839431076,
"grad_norm": 0.46656882762908936,
"learning_rate": 2e-05,
"loss": 0.8938,
"step": 2340
},
{
"epoch": 0.21021558278915825,
"grad_norm": 0.44763514399528503,
"learning_rate": 2e-05,
"loss": 0.8854,
"step": 2350
},
{
"epoch": 0.2111101171840057,
"grad_norm": 0.433299720287323,
"learning_rate": 2e-05,
"loss": 0.8665,
"step": 2360
},
{
"epoch": 0.2120046515788532,
"grad_norm": 0.4781743288040161,
"learning_rate": 2e-05,
"loss": 0.8985,
"step": 2370
},
{
"epoch": 0.2128991859737007,
"grad_norm": 0.4406478703022003,
"learning_rate": 2e-05,
"loss": 0.8802,
"step": 2380
},
{
"epoch": 0.21379372036854816,
"grad_norm": 0.47858351469039917,
"learning_rate": 2e-05,
"loss": 0.8958,
"step": 2390
},
{
"epoch": 0.21468825476339565,
"grad_norm": 0.45086878538131714,
"learning_rate": 2e-05,
"loss": 0.8771,
"step": 2400
},
{
"epoch": 0.21558278915824314,
"grad_norm": 0.4594736695289612,
"learning_rate": 2e-05,
"loss": 0.8762,
"step": 2410
},
{
"epoch": 0.21647732355309063,
"grad_norm": 0.45185622572898865,
"learning_rate": 2e-05,
"loss": 0.9032,
"step": 2420
},
{
"epoch": 0.2173718579479381,
"grad_norm": 0.4313936233520508,
"learning_rate": 2e-05,
"loss": 0.8611,
"step": 2430
},
{
"epoch": 0.21826639234278558,
"grad_norm": 0.4434468746185303,
"learning_rate": 2e-05,
"loss": 0.8803,
"step": 2440
},
{
"epoch": 0.21916092673763307,
"grad_norm": 0.4205702245235443,
"learning_rate": 2e-05,
"loss": 0.8628,
"step": 2450
},
{
"epoch": 0.22005546113248053,
"grad_norm": 0.44990837574005127,
"learning_rate": 2e-05,
"loss": 0.8886,
"step": 2460
},
{
"epoch": 0.22094999552732802,
"grad_norm": 0.4437563717365265,
"learning_rate": 2e-05,
"loss": 0.877,
"step": 2470
},
{
"epoch": 0.22184452992217552,
"grad_norm": 0.4536307156085968,
"learning_rate": 2e-05,
"loss": 0.8767,
"step": 2480
},
{
"epoch": 0.22273906431702298,
"grad_norm": 0.4591897428035736,
"learning_rate": 2e-05,
"loss": 0.9098,
"step": 2490
},
{
"epoch": 0.22363359871187047,
"grad_norm": 0.4403884708881378,
"learning_rate": 2e-05,
"loss": 0.883,
"step": 2500
},
{
"epoch": 0.22452813310671796,
"grad_norm": 0.4733695089817047,
"learning_rate": 2e-05,
"loss": 0.8779,
"step": 2510
},
{
"epoch": 0.22542266750156542,
"grad_norm": 0.4368247985839844,
"learning_rate": 2e-05,
"loss": 0.8813,
"step": 2520
},
{
"epoch": 0.2263172018964129,
"grad_norm": 0.4843006730079651,
"learning_rate": 2e-05,
"loss": 0.8819,
"step": 2530
},
{
"epoch": 0.2272117362912604,
"grad_norm": 0.4408707022666931,
"learning_rate": 2e-05,
"loss": 0.8836,
"step": 2540
},
{
"epoch": 0.2281062706861079,
"grad_norm": 0.4609002470970154,
"learning_rate": 2e-05,
"loss": 0.8587,
"step": 2550
},
{
"epoch": 0.22900080508095536,
"grad_norm": 0.4641557037830353,
"learning_rate": 2e-05,
"loss": 0.9006,
"step": 2560
},
{
"epoch": 0.22989533947580285,
"grad_norm": 0.4326741099357605,
"learning_rate": 2e-05,
"loss": 0.8911,
"step": 2570
},
{
"epoch": 0.23078987387065034,
"grad_norm": 0.43637990951538086,
"learning_rate": 2e-05,
"loss": 0.8969,
"step": 2580
},
{
"epoch": 0.2316844082654978,
"grad_norm": 0.45137572288513184,
"learning_rate": 2e-05,
"loss": 0.872,
"step": 2590
},
{
"epoch": 0.2325789426603453,
"grad_norm": 0.46193912625312805,
"learning_rate": 2e-05,
"loss": 0.8832,
"step": 2600
},
{
"epoch": 0.23347347705519278,
"grad_norm": 0.4607735276222229,
"learning_rate": 2e-05,
"loss": 0.8835,
"step": 2610
},
{
"epoch": 0.23436801145004024,
"grad_norm": 0.4514963626861572,
"learning_rate": 2e-05,
"loss": 0.8685,
"step": 2620
},
{
"epoch": 0.23526254584488773,
"grad_norm": 0.4118781089782715,
"learning_rate": 2e-05,
"loss": 0.8801,
"step": 2630
},
{
"epoch": 0.23615708023973522,
"grad_norm": 0.44229942560195923,
"learning_rate": 2e-05,
"loss": 0.8809,
"step": 2640
},
{
"epoch": 0.2370516146345827,
"grad_norm": 0.44970157742500305,
"learning_rate": 2e-05,
"loss": 0.8619,
"step": 2650
},
{
"epoch": 0.23794614902943018,
"grad_norm": 0.45758315920829773,
"learning_rate": 2e-05,
"loss": 0.8687,
"step": 2660
},
{
"epoch": 0.23884068342427767,
"grad_norm": 0.42311549186706543,
"learning_rate": 2e-05,
"loss": 0.8548,
"step": 2670
},
{
"epoch": 0.23973521781912516,
"grad_norm": 0.4612109661102295,
"learning_rate": 2e-05,
"loss": 0.8817,
"step": 2680
},
{
"epoch": 0.24062975221397262,
"grad_norm": 0.42606642842292786,
"learning_rate": 2e-05,
"loss": 0.8825,
"step": 2690
},
{
"epoch": 0.2415242866088201,
"grad_norm": 0.42773109674453735,
"learning_rate": 2e-05,
"loss": 0.8766,
"step": 2700
},
{
"epoch": 0.2424188210036676,
"grad_norm": 0.4226321280002594,
"learning_rate": 2e-05,
"loss": 0.867,
"step": 2710
},
{
"epoch": 0.24331335539851506,
"grad_norm": 0.4375416934490204,
"learning_rate": 2e-05,
"loss": 0.873,
"step": 2720
},
{
"epoch": 0.24420788979336255,
"grad_norm": 0.41089096665382385,
"learning_rate": 2e-05,
"loss": 0.8582,
"step": 2730
},
{
"epoch": 0.24510242418821004,
"grad_norm": 0.4491311013698578,
"learning_rate": 2e-05,
"loss": 0.8613,
"step": 2740
},
{
"epoch": 0.2459969585830575,
"grad_norm": 0.4420069754123688,
"learning_rate": 2e-05,
"loss": 0.8594,
"step": 2750
},
{
"epoch": 0.246891492977905,
"grad_norm": 0.4370020627975464,
"learning_rate": 2e-05,
"loss": 0.8719,
"step": 2760
},
{
"epoch": 0.2477860273727525,
"grad_norm": 0.43460679054260254,
"learning_rate": 2e-05,
"loss": 0.8633,
"step": 2770
},
{
"epoch": 0.24868056176759998,
"grad_norm": 0.43074288964271545,
"learning_rate": 2e-05,
"loss": 0.8735,
"step": 2780
},
{
"epoch": 0.24957509616244744,
"grad_norm": 0.440716952085495,
"learning_rate": 2e-05,
"loss": 0.8971,
"step": 2790
},
{
"epoch": 0.25046963055729493,
"grad_norm": 0.4300522804260254,
"learning_rate": 2e-05,
"loss": 0.87,
"step": 2800
},
{
"epoch": 0.2513641649521424,
"grad_norm": 0.42161524295806885,
"learning_rate": 2e-05,
"loss": 0.8625,
"step": 2810
},
{
"epoch": 0.2522586993469899,
"grad_norm": 0.42453935742378235,
"learning_rate": 2e-05,
"loss": 0.8741,
"step": 2820
},
{
"epoch": 0.25315323374183735,
"grad_norm": 0.43741515278816223,
"learning_rate": 2e-05,
"loss": 0.8724,
"step": 2830
},
{
"epoch": 0.25404776813668484,
"grad_norm": 0.46329250931739807,
"learning_rate": 2e-05,
"loss": 0.8742,
"step": 2840
},
{
"epoch": 0.2549423025315323,
"grad_norm": 0.4396478831768036,
"learning_rate": 2e-05,
"loss": 0.8798,
"step": 2850
},
{
"epoch": 0.2558368369263798,
"grad_norm": 0.4491777718067169,
"learning_rate": 2e-05,
"loss": 0.8801,
"step": 2860
},
{
"epoch": 0.2567313713212273,
"grad_norm": 0.42968037724494934,
"learning_rate": 2e-05,
"loss": 0.8749,
"step": 2870
},
{
"epoch": 0.2576259057160748,
"grad_norm": 0.43413832783699036,
"learning_rate": 2e-05,
"loss": 0.8765,
"step": 2880
},
{
"epoch": 0.2585204401109223,
"grad_norm": 0.4321322739124298,
"learning_rate": 2e-05,
"loss": 0.8737,
"step": 2890
},
{
"epoch": 0.2594149745057697,
"grad_norm": 0.4269726276397705,
"learning_rate": 2e-05,
"loss": 0.8892,
"step": 2900
},
{
"epoch": 0.2603095089006172,
"grad_norm": 0.4394371211528778,
"learning_rate": 2e-05,
"loss": 0.8775,
"step": 2910
},
{
"epoch": 0.2612040432954647,
"grad_norm": 0.428146630525589,
"learning_rate": 2e-05,
"loss": 0.8638,
"step": 2920
},
{
"epoch": 0.2620985776903122,
"grad_norm": 0.4308774471282959,
"learning_rate": 2e-05,
"loss": 0.8453,
"step": 2930
},
{
"epoch": 0.2629931120851597,
"grad_norm": 0.42960765957832336,
"learning_rate": 2e-05,
"loss": 0.8741,
"step": 2940
},
{
"epoch": 0.2638876464800072,
"grad_norm": 0.43039461970329285,
"learning_rate": 2e-05,
"loss": 0.8811,
"step": 2950
},
{
"epoch": 0.2647821808748546,
"grad_norm": 0.4494170546531677,
"learning_rate": 2e-05,
"loss": 0.8798,
"step": 2960
},
{
"epoch": 0.2656767152697021,
"grad_norm": 0.5378742814064026,
"learning_rate": 2e-05,
"loss": 0.8843,
"step": 2970
},
{
"epoch": 0.2665712496645496,
"grad_norm": 0.44158872961997986,
"learning_rate": 2e-05,
"loss": 0.8864,
"step": 2980
},
{
"epoch": 0.2674657840593971,
"grad_norm": 0.42843884229660034,
"learning_rate": 2e-05,
"loss": 0.8815,
"step": 2990
},
{
"epoch": 0.2683603184542446,
"grad_norm": 0.4513569176197052,
"learning_rate": 2e-05,
"loss": 0.8595,
"step": 3000
},
{
"epoch": 0.26925485284909206,
"grad_norm": 0.44482842087745667,
"learning_rate": 2e-05,
"loss": 0.9163,
"step": 3010
},
{
"epoch": 0.27014938724393955,
"grad_norm": 0.4343452751636505,
"learning_rate": 2e-05,
"loss": 0.8866,
"step": 3020
},
{
"epoch": 0.271043921638787,
"grad_norm": 0.4347887933254242,
"learning_rate": 2e-05,
"loss": 0.8891,
"step": 3030
},
{
"epoch": 0.2719384560336345,
"grad_norm": 0.42345768213272095,
"learning_rate": 2e-05,
"loss": 0.8722,
"step": 3040
},
{
"epoch": 0.27283299042848197,
"grad_norm": 0.4256942868232727,
"learning_rate": 2e-05,
"loss": 0.8741,
"step": 3050
},
{
"epoch": 0.27372752482332946,
"grad_norm": 0.4204983711242676,
"learning_rate": 2e-05,
"loss": 0.8527,
"step": 3060
},
{
"epoch": 0.27462205921817695,
"grad_norm": 0.43554601073265076,
"learning_rate": 2e-05,
"loss": 0.8683,
"step": 3070
},
{
"epoch": 0.27551659361302444,
"grad_norm": 0.429853230714798,
"learning_rate": 2e-05,
"loss": 0.8649,
"step": 3080
},
{
"epoch": 0.2764111280078719,
"grad_norm": 0.4369424879550934,
"learning_rate": 2e-05,
"loss": 0.8713,
"step": 3090
},
{
"epoch": 0.27730566240271937,
"grad_norm": 0.4626963436603546,
"learning_rate": 2e-05,
"loss": 0.8782,
"step": 3100
},
{
"epoch": 0.27820019679756686,
"grad_norm": 0.42847973108291626,
"learning_rate": 2e-05,
"loss": 0.8501,
"step": 3110
},
{
"epoch": 0.27909473119241435,
"grad_norm": 0.6046935319900513,
"learning_rate": 2e-05,
"loss": 0.8682,
"step": 3120
},
{
"epoch": 0.27998926558726184,
"grad_norm": 0.41587957739830017,
"learning_rate": 2e-05,
"loss": 0.8855,
"step": 3130
},
{
"epoch": 0.28088379998210933,
"grad_norm": 0.4413129985332489,
"learning_rate": 2e-05,
"loss": 0.8475,
"step": 3140
},
{
"epoch": 0.2817783343769568,
"grad_norm": 0.443731427192688,
"learning_rate": 2e-05,
"loss": 0.8914,
"step": 3150
},
{
"epoch": 0.28267286877180425,
"grad_norm": 0.4390244781970978,
"learning_rate": 2e-05,
"loss": 0.8715,
"step": 3160
},
{
"epoch": 0.28356740316665174,
"grad_norm": 0.4387482702732086,
"learning_rate": 2e-05,
"loss": 0.8499,
"step": 3170
},
{
"epoch": 0.28446193756149923,
"grad_norm": 0.45408686995506287,
"learning_rate": 2e-05,
"loss": 0.8562,
"step": 3180
},
{
"epoch": 0.2853564719563467,
"grad_norm": 0.447141170501709,
"learning_rate": 2e-05,
"loss": 0.8736,
"step": 3190
},
{
"epoch": 0.2862510063511942,
"grad_norm": 0.43100371956825256,
"learning_rate": 2e-05,
"loss": 0.8773,
"step": 3200
},
{
"epoch": 0.2871455407460417,
"grad_norm": 0.40151116251945496,
"learning_rate": 2e-05,
"loss": 0.8528,
"step": 3210
},
{
"epoch": 0.28804007514088914,
"grad_norm": 0.4174920618534088,
"learning_rate": 2e-05,
"loss": 0.8737,
"step": 3220
},
{
"epoch": 0.28893460953573663,
"grad_norm": 0.4293808937072754,
"learning_rate": 2e-05,
"loss": 0.8511,
"step": 3230
},
{
"epoch": 0.2898291439305841,
"grad_norm": 0.40952080488204956,
"learning_rate": 2e-05,
"loss": 0.8551,
"step": 3240
},
{
"epoch": 0.2907236783254316,
"grad_norm": 0.48760247230529785,
"learning_rate": 2e-05,
"loss": 0.8593,
"step": 3250
},
{
"epoch": 0.2916182127202791,
"grad_norm": 0.4191151559352875,
"learning_rate": 2e-05,
"loss": 0.871,
"step": 3260
},
{
"epoch": 0.2925127471151266,
"grad_norm": 0.4530089795589447,
"learning_rate": 2e-05,
"loss": 0.8466,
"step": 3270
},
{
"epoch": 0.2934072815099741,
"grad_norm": 0.4576856195926666,
"learning_rate": 2e-05,
"loss": 0.8705,
"step": 3280
},
{
"epoch": 0.2943018159048215,
"grad_norm": 0.4397868812084198,
"learning_rate": 2e-05,
"loss": 0.8594,
"step": 3290
},
{
"epoch": 0.295196350299669,
"grad_norm": 0.4292359948158264,
"learning_rate": 2e-05,
"loss": 0.8634,
"step": 3300
},
{
"epoch": 0.2960908846945165,
"grad_norm": 0.4401033818721771,
"learning_rate": 2e-05,
"loss": 0.8606,
"step": 3310
},
{
"epoch": 0.296985419089364,
"grad_norm": 0.4902155101299286,
"learning_rate": 2e-05,
"loss": 0.8452,
"step": 3320
},
{
"epoch": 0.2978799534842115,
"grad_norm": 0.4547151029109955,
"learning_rate": 2e-05,
"loss": 0.8524,
"step": 3330
},
{
"epoch": 0.29877448787905897,
"grad_norm": 0.4428585171699524,
"learning_rate": 2e-05,
"loss": 0.8688,
"step": 3340
},
{
"epoch": 0.2996690222739064,
"grad_norm": 0.4522424638271332,
"learning_rate": 2e-05,
"loss": 0.8582,
"step": 3350
},
{
"epoch": 0.3005635566687539,
"grad_norm": 0.4438844919204712,
"learning_rate": 2e-05,
"loss": 0.848,
"step": 3360
},
{
"epoch": 0.3014580910636014,
"grad_norm": 0.4214642643928528,
"learning_rate": 2e-05,
"loss": 0.8511,
"step": 3370
},
{
"epoch": 0.3023526254584489,
"grad_norm": 0.4343169927597046,
"learning_rate": 2e-05,
"loss": 0.8433,
"step": 3380
},
{
"epoch": 0.30324715985329637,
"grad_norm": 0.4347662925720215,
"learning_rate": 2e-05,
"loss": 0.8697,
"step": 3390
},
{
"epoch": 0.30414169424814386,
"grad_norm": 0.4457205832004547,
"learning_rate": 2e-05,
"loss": 0.8605,
"step": 3400
},
{
"epoch": 0.30503622864299135,
"grad_norm": 0.4358961284160614,
"learning_rate": 2e-05,
"loss": 0.8635,
"step": 3410
},
{
"epoch": 0.3059307630378388,
"grad_norm": 0.42647281289100647,
"learning_rate": 2e-05,
"loss": 0.8744,
"step": 3420
},
{
"epoch": 0.3068252974326863,
"grad_norm": 0.4247570037841797,
"learning_rate": 2e-05,
"loss": 0.8625,
"step": 3430
},
{
"epoch": 0.30771983182753376,
"grad_norm": 0.44041571021080017,
"learning_rate": 2e-05,
"loss": 0.8607,
"step": 3440
},
{
"epoch": 0.30861436622238125,
"grad_norm": 0.4204762876033783,
"learning_rate": 2e-05,
"loss": 0.8755,
"step": 3450
},
{
"epoch": 0.30950890061722874,
"grad_norm": 0.430669367313385,
"learning_rate": 2e-05,
"loss": 0.8491,
"step": 3460
},
{
"epoch": 0.31040343501207623,
"grad_norm": 0.44301435351371765,
"learning_rate": 2e-05,
"loss": 0.8653,
"step": 3470
},
{
"epoch": 0.31129796940692367,
"grad_norm": 0.41568008065223694,
"learning_rate": 2e-05,
"loss": 0.8647,
"step": 3480
},
{
"epoch": 0.31219250380177116,
"grad_norm": 0.47437798976898193,
"learning_rate": 2e-05,
"loss": 0.8691,
"step": 3490
},
{
"epoch": 0.31308703819661865,
"grad_norm": 0.4318526089191437,
"learning_rate": 2e-05,
"loss": 0.8544,
"step": 3500
},
{
"epoch": 0.31398157259146614,
"grad_norm": 0.42749080061912537,
"learning_rate": 2e-05,
"loss": 0.8602,
"step": 3510
},
{
"epoch": 0.31487610698631363,
"grad_norm": 0.4429764151573181,
"learning_rate": 2e-05,
"loss": 0.877,
"step": 3520
},
{
"epoch": 0.3157706413811611,
"grad_norm": 0.44149690866470337,
"learning_rate": 2e-05,
"loss": 0.8792,
"step": 3530
},
{
"epoch": 0.3166651757760086,
"grad_norm": 0.41978949308395386,
"learning_rate": 2e-05,
"loss": 0.8563,
"step": 3540
},
{
"epoch": 0.31755971017085605,
"grad_norm": 0.4202021658420563,
"learning_rate": 2e-05,
"loss": 0.872,
"step": 3550
},
{
"epoch": 0.31845424456570354,
"grad_norm": 0.44597485661506653,
"learning_rate": 2e-05,
"loss": 0.8926,
"step": 3560
},
{
"epoch": 0.319348778960551,
"grad_norm": 0.42776328325271606,
"learning_rate": 2e-05,
"loss": 0.8589,
"step": 3570
},
{
"epoch": 0.3202433133553985,
"grad_norm": 0.43221884965896606,
"learning_rate": 2e-05,
"loss": 0.8673,
"step": 3580
},
{
"epoch": 0.321137847750246,
"grad_norm": 0.7660443186759949,
"learning_rate": 2e-05,
"loss": 0.8769,
"step": 3590
},
{
"epoch": 0.3220323821450935,
"grad_norm": 0.43479782342910767,
"learning_rate": 2e-05,
"loss": 0.8745,
"step": 3600
},
{
"epoch": 0.32292691653994093,
"grad_norm": 0.46180543303489685,
"learning_rate": 2e-05,
"loss": 0.856,
"step": 3610
},
{
"epoch": 0.3238214509347884,
"grad_norm": 0.42978212237358093,
"learning_rate": 2e-05,
"loss": 0.8563,
"step": 3620
},
{
"epoch": 0.3247159853296359,
"grad_norm": 0.42840954661369324,
"learning_rate": 2e-05,
"loss": 0.8543,
"step": 3630
},
{
"epoch": 0.3256105197244834,
"grad_norm": 0.41989150643348694,
"learning_rate": 2e-05,
"loss": 0.8637,
"step": 3640
},
{
"epoch": 0.3265050541193309,
"grad_norm": 0.43360307812690735,
"learning_rate": 2e-05,
"loss": 0.8703,
"step": 3650
},
{
"epoch": 0.3273995885141784,
"grad_norm": 0.45706117153167725,
"learning_rate": 2e-05,
"loss": 0.8643,
"step": 3660
},
{
"epoch": 0.3282941229090259,
"grad_norm": 0.4765286147594452,
"learning_rate": 2e-05,
"loss": 0.8517,
"step": 3670
},
{
"epoch": 0.3291886573038733,
"grad_norm": 0.42985501885414124,
"learning_rate": 2e-05,
"loss": 0.8431,
"step": 3680
},
{
"epoch": 0.3300831916987208,
"grad_norm": 0.4257068336009979,
"learning_rate": 2e-05,
"loss": 0.8579,
"step": 3690
},
{
"epoch": 0.3309777260935683,
"grad_norm": 0.43720927834510803,
"learning_rate": 2e-05,
"loss": 0.8769,
"step": 3700
},
{
"epoch": 0.3318722604884158,
"grad_norm": 0.688318133354187,
"learning_rate": 2e-05,
"loss": 0.8424,
"step": 3710
},
{
"epoch": 0.3327667948832633,
"grad_norm": 0.4148125946521759,
"learning_rate": 2e-05,
"loss": 0.8297,
"step": 3720
},
{
"epoch": 0.33366132927811076,
"grad_norm": 0.45193618535995483,
"learning_rate": 2e-05,
"loss": 0.8659,
"step": 3730
},
{
"epoch": 0.3345558636729582,
"grad_norm": 0.4544907212257385,
"learning_rate": 2e-05,
"loss": 0.849,
"step": 3740
},
{
"epoch": 0.3354503980678057,
"grad_norm": 0.48733794689178467,
"learning_rate": 2e-05,
"loss": 0.8443,
"step": 3750
},
{
"epoch": 0.3363449324626532,
"grad_norm": 0.42958664894104004,
"learning_rate": 2e-05,
"loss": 0.8583,
"step": 3760
},
{
"epoch": 0.33723946685750067,
"grad_norm": 0.43627652525901794,
"learning_rate": 2e-05,
"loss": 0.8742,
"step": 3770
},
{
"epoch": 0.33813400125234816,
"grad_norm": 0.44195058941841125,
"learning_rate": 2e-05,
"loss": 0.8659,
"step": 3780
},
{
"epoch": 0.33902853564719565,
"grad_norm": 0.4201292097568512,
"learning_rate": 2e-05,
"loss": 0.8702,
"step": 3790
},
{
"epoch": 0.33992307004204314,
"grad_norm": 0.42322805523872375,
"learning_rate": 2e-05,
"loss": 0.8645,
"step": 3800
},
{
"epoch": 0.3408176044368906,
"grad_norm": 0.5287156701087952,
"learning_rate": 2e-05,
"loss": 0.8642,
"step": 3810
},
{
"epoch": 0.34171213883173807,
"grad_norm": 0.4101298153400421,
"learning_rate": 2e-05,
"loss": 0.836,
"step": 3820
},
{
"epoch": 0.34260667322658556,
"grad_norm": 0.420767605304718,
"learning_rate": 2e-05,
"loss": 0.8622,
"step": 3830
},
{
"epoch": 0.34350120762143305,
"grad_norm": 0.440177857875824,
"learning_rate": 2e-05,
"loss": 0.8454,
"step": 3840
},
{
"epoch": 0.34439574201628054,
"grad_norm": 0.4709494709968567,
"learning_rate": 2e-05,
"loss": 0.8528,
"step": 3850
},
{
"epoch": 0.345290276411128,
"grad_norm": 0.44540542364120483,
"learning_rate": 2e-05,
"loss": 0.8608,
"step": 3860
},
{
"epoch": 0.34618481080597546,
"grad_norm": 0.4098896384239197,
"learning_rate": 2e-05,
"loss": 0.8567,
"step": 3870
},
{
"epoch": 0.34707934520082295,
"grad_norm": 0.41984960436820984,
"learning_rate": 2e-05,
"loss": 0.8696,
"step": 3880
},
{
"epoch": 0.34797387959567044,
"grad_norm": 0.4696812629699707,
"learning_rate": 2e-05,
"loss": 0.8324,
"step": 3890
},
{
"epoch": 0.34886841399051793,
"grad_norm": 0.42249128222465515,
"learning_rate": 2e-05,
"loss": 0.8539,
"step": 3900
},
{
"epoch": 0.3497629483853654,
"grad_norm": 0.4322523772716522,
"learning_rate": 2e-05,
"loss": 0.8527,
"step": 3910
},
{
"epoch": 0.3506574827802129,
"grad_norm": 0.43218186497688293,
"learning_rate": 2e-05,
"loss": 0.8514,
"step": 3920
},
{
"epoch": 0.3515520171750604,
"grad_norm": 0.4113311171531677,
"learning_rate": 2e-05,
"loss": 0.8527,
"step": 3930
},
{
"epoch": 0.35244655156990784,
"grad_norm": 0.4293188452720642,
"learning_rate": 2e-05,
"loss": 0.8343,
"step": 3940
},
{
"epoch": 0.35334108596475533,
"grad_norm": 0.4172656834125519,
"learning_rate": 2e-05,
"loss": 0.8704,
"step": 3950
},
{
"epoch": 0.3542356203596028,
"grad_norm": 0.4172748327255249,
"learning_rate": 2e-05,
"loss": 0.8503,
"step": 3960
},
{
"epoch": 0.3551301547544503,
"grad_norm": 0.4269205927848816,
"learning_rate": 2e-05,
"loss": 0.8333,
"step": 3970
},
{
"epoch": 0.3560246891492978,
"grad_norm": 0.4614328145980835,
"learning_rate": 2e-05,
"loss": 0.8761,
"step": 3980
},
{
"epoch": 0.3569192235441453,
"grad_norm": 0.45893868803977966,
"learning_rate": 2e-05,
"loss": 0.8497,
"step": 3990
},
{
"epoch": 0.3578137579389927,
"grad_norm": 0.4363267421722412,
"learning_rate": 2e-05,
"loss": 0.8426,
"step": 4000
},
{
"epoch": 0.3587082923338402,
"grad_norm": 0.43977516889572144,
"learning_rate": 2e-05,
"loss": 0.8235,
"step": 4010
},
{
"epoch": 0.3596028267286877,
"grad_norm": 0.42227694392204285,
"learning_rate": 2e-05,
"loss": 0.868,
"step": 4020
},
{
"epoch": 0.3604973611235352,
"grad_norm": 0.42034077644348145,
"learning_rate": 2e-05,
"loss": 0.8641,
"step": 4030
},
{
"epoch": 0.3613918955183827,
"grad_norm": 0.4320007860660553,
"learning_rate": 2e-05,
"loss": 0.8501,
"step": 4040
},
{
"epoch": 0.3622864299132302,
"grad_norm": 0.41753605008125305,
"learning_rate": 2e-05,
"loss": 0.8572,
"step": 4050
},
{
"epoch": 0.36318096430807767,
"grad_norm": 0.44261792302131653,
"learning_rate": 2e-05,
"loss": 0.8716,
"step": 4060
},
{
"epoch": 0.3640754987029251,
"grad_norm": 0.4426165521144867,
"learning_rate": 2e-05,
"loss": 0.877,
"step": 4070
},
{
"epoch": 0.3649700330977726,
"grad_norm": 0.4143220782279968,
"learning_rate": 2e-05,
"loss": 0.8233,
"step": 4080
},
{
"epoch": 0.3658645674926201,
"grad_norm": 0.42633718252182007,
"learning_rate": 2e-05,
"loss": 0.8807,
"step": 4090
},
{
"epoch": 0.3667591018874676,
"grad_norm": 0.4069472849369049,
"learning_rate": 2e-05,
"loss": 0.8432,
"step": 4100
},
{
"epoch": 0.36765363628231507,
"grad_norm": 0.41689738631248474,
"learning_rate": 2e-05,
"loss": 0.8431,
"step": 4110
},
{
"epoch": 0.36854817067716256,
"grad_norm": 0.4277401864528656,
"learning_rate": 2e-05,
"loss": 0.8596,
"step": 4120
},
{
"epoch": 0.36944270507201,
"grad_norm": 0.43761104345321655,
"learning_rate": 2e-05,
"loss": 0.856,
"step": 4130
},
{
"epoch": 0.3703372394668575,
"grad_norm": 0.4598040282726288,
"learning_rate": 2e-05,
"loss": 0.8587,
"step": 4140
},
{
"epoch": 0.371231773861705,
"grad_norm": 0.45169052481651306,
"learning_rate": 2e-05,
"loss": 0.8637,
"step": 4150
},
{
"epoch": 0.37212630825655246,
"grad_norm": 0.4164012670516968,
"learning_rate": 2e-05,
"loss": 0.8858,
"step": 4160
},
{
"epoch": 0.37302084265139995,
"grad_norm": 0.42765775322914124,
"learning_rate": 2e-05,
"loss": 0.8576,
"step": 4170
},
{
"epoch": 0.37391537704624744,
"grad_norm": 0.4144660234451294,
"learning_rate": 2e-05,
"loss": 0.8471,
"step": 4180
},
{
"epoch": 0.37480991144109493,
"grad_norm": 0.4286114275455475,
"learning_rate": 2e-05,
"loss": 0.8514,
"step": 4190
},
{
"epoch": 0.37570444583594237,
"grad_norm": 0.4133700430393219,
"learning_rate": 2e-05,
"loss": 0.8425,
"step": 4200
},
{
"epoch": 0.37659898023078986,
"grad_norm": 0.4405253529548645,
"learning_rate": 2e-05,
"loss": 0.8533,
"step": 4210
},
{
"epoch": 0.37749351462563735,
"grad_norm": 0.48602214455604553,
"learning_rate": 2e-05,
"loss": 0.855,
"step": 4220
},
{
"epoch": 0.37838804902048484,
"grad_norm": 0.7717680931091309,
"learning_rate": 2e-05,
"loss": 0.8478,
"step": 4230
},
{
"epoch": 0.37928258341533233,
"grad_norm": 0.49600282311439514,
"learning_rate": 2e-05,
"loss": 0.8385,
"step": 4240
},
{
"epoch": 0.3801771178101798,
"grad_norm": 0.424430251121521,
"learning_rate": 2e-05,
"loss": 0.8449,
"step": 4250
},
{
"epoch": 0.38107165220502726,
"grad_norm": 0.4365488588809967,
"learning_rate": 2e-05,
"loss": 0.8589,
"step": 4260
},
{
"epoch": 0.38196618659987475,
"grad_norm": 0.45103907585144043,
"learning_rate": 2e-05,
"loss": 0.8562,
"step": 4270
},
{
"epoch": 0.38286072099472224,
"grad_norm": 0.41904696822166443,
"learning_rate": 2e-05,
"loss": 0.8685,
"step": 4280
},
{
"epoch": 0.3837552553895697,
"grad_norm": 0.41022178530693054,
"learning_rate": 2e-05,
"loss": 0.869,
"step": 4290
},
{
"epoch": 0.3846497897844172,
"grad_norm": 0.46889710426330566,
"learning_rate": 2e-05,
"loss": 0.8349,
"step": 4300
},
{
"epoch": 0.3855443241792647,
"grad_norm": 0.5098229050636292,
"learning_rate": 2e-05,
"loss": 0.8683,
"step": 4310
},
{
"epoch": 0.3864388585741122,
"grad_norm": 0.4572768807411194,
"learning_rate": 2e-05,
"loss": 0.8684,
"step": 4320
},
{
"epoch": 0.38733339296895963,
"grad_norm": 0.4227602779865265,
"learning_rate": 2e-05,
"loss": 0.8496,
"step": 4330
},
{
"epoch": 0.3882279273638071,
"grad_norm": 0.5929670929908752,
"learning_rate": 2e-05,
"loss": 0.8574,
"step": 4340
},
{
"epoch": 0.3891224617586546,
"grad_norm": 0.4036109745502472,
"learning_rate": 2e-05,
"loss": 0.8279,
"step": 4350
},
{
"epoch": 0.3900169961535021,
"grad_norm": 0.42604905366897583,
"learning_rate": 2e-05,
"loss": 0.8433,
"step": 4360
},
{
"epoch": 0.3909115305483496,
"grad_norm": 0.4268192648887634,
"learning_rate": 2e-05,
"loss": 0.853,
"step": 4370
},
{
"epoch": 0.3918060649431971,
"grad_norm": 0.41308164596557617,
"learning_rate": 2e-05,
"loss": 0.8426,
"step": 4380
},
{
"epoch": 0.3927005993380445,
"grad_norm": 0.4207102358341217,
"learning_rate": 2e-05,
"loss": 0.8525,
"step": 4390
},
{
"epoch": 0.393595133732892,
"grad_norm": 0.44893506169319153,
"learning_rate": 2e-05,
"loss": 0.8575,
"step": 4400
},
{
"epoch": 0.3944896681277395,
"grad_norm": 0.4362022280693054,
"learning_rate": 2e-05,
"loss": 0.8467,
"step": 4410
},
{
"epoch": 0.395384202522587,
"grad_norm": 0.4302770793437958,
"learning_rate": 2e-05,
"loss": 0.8475,
"step": 4420
},
{
"epoch": 0.3962787369174345,
"grad_norm": 0.43263718485832214,
"learning_rate": 2e-05,
"loss": 0.8551,
"step": 4430
},
{
"epoch": 0.397173271312282,
"grad_norm": 0.44275304675102234,
"learning_rate": 2e-05,
"loss": 0.8514,
"step": 4440
},
{
"epoch": 0.39806780570712946,
"grad_norm": 0.42279699444770813,
"learning_rate": 2e-05,
"loss": 0.8621,
"step": 4450
},
{
"epoch": 0.3989623401019769,
"grad_norm": 0.4439516067504883,
"learning_rate": 2e-05,
"loss": 0.8299,
"step": 4460
},
{
"epoch": 0.3998568744968244,
"grad_norm": 0.3999125063419342,
"learning_rate": 2e-05,
"loss": 0.8468,
"step": 4470
},
{
"epoch": 0.4007514088916719,
"grad_norm": 0.41405975818634033,
"learning_rate": 2e-05,
"loss": 0.8492,
"step": 4480
},
{
"epoch": 0.40164594328651937,
"grad_norm": 0.44079893827438354,
"learning_rate": 2e-05,
"loss": 0.858,
"step": 4490
},
{
"epoch": 0.40254047768136686,
"grad_norm": 0.42361101508140564,
"learning_rate": 2e-05,
"loss": 0.8853,
"step": 4500
},
{
"epoch": 0.40343501207621435,
"grad_norm": 0.4321896731853485,
"learning_rate": 2e-05,
"loss": 0.8585,
"step": 4510
},
{
"epoch": 0.4043295464710618,
"grad_norm": 0.43715375661849976,
"learning_rate": 2e-05,
"loss": 0.8481,
"step": 4520
},
{
"epoch": 0.4052240808659093,
"grad_norm": 0.4103354215621948,
"learning_rate": 2e-05,
"loss": 0.8469,
"step": 4530
},
{
"epoch": 0.40611861526075677,
"grad_norm": 0.44220998883247375,
"learning_rate": 2e-05,
"loss": 0.8682,
"step": 4540
},
{
"epoch": 0.40701314965560426,
"grad_norm": 0.5669285655021667,
"learning_rate": 2e-05,
"loss": 0.8519,
"step": 4550
},
{
"epoch": 0.40790768405045175,
"grad_norm": 0.41640788316726685,
"learning_rate": 2e-05,
"loss": 0.8415,
"step": 4560
},
{
"epoch": 0.40880221844529924,
"grad_norm": 0.4092693328857422,
"learning_rate": 2e-05,
"loss": 0.8535,
"step": 4570
},
{
"epoch": 0.4096967528401467,
"grad_norm": 0.4293263256549835,
"learning_rate": 2e-05,
"loss": 0.8357,
"step": 4580
},
{
"epoch": 0.41059128723499416,
"grad_norm": 0.40658220648765564,
"learning_rate": 2e-05,
"loss": 0.8473,
"step": 4590
},
{
"epoch": 0.41148582162984165,
"grad_norm": 0.42512235045433044,
"learning_rate": 2e-05,
"loss": 0.8505,
"step": 4600
},
{
"epoch": 0.41238035602468914,
"grad_norm": 0.42326581478118896,
"learning_rate": 2e-05,
"loss": 0.8359,
"step": 4610
},
{
"epoch": 0.41327489041953663,
"grad_norm": 0.4456283152103424,
"learning_rate": 2e-05,
"loss": 0.8481,
"step": 4620
},
{
"epoch": 0.4141694248143841,
"grad_norm": 0.4178811013698578,
"learning_rate": 2e-05,
"loss": 0.8386,
"step": 4630
},
{
"epoch": 0.4150639592092316,
"grad_norm": 0.4163311719894409,
"learning_rate": 2e-05,
"loss": 0.8612,
"step": 4640
},
{
"epoch": 0.41595849360407905,
"grad_norm": 0.448076069355011,
"learning_rate": 2e-05,
"loss": 0.8478,
"step": 4650
},
{
"epoch": 0.41685302799892654,
"grad_norm": 0.42013415694236755,
"learning_rate": 2e-05,
"loss": 0.8254,
"step": 4660
},
{
"epoch": 0.41774756239377403,
"grad_norm": 0.41915249824523926,
"learning_rate": 2e-05,
"loss": 0.8559,
"step": 4670
},
{
"epoch": 0.4186420967886215,
"grad_norm": 0.4368330240249634,
"learning_rate": 2e-05,
"loss": 0.8372,
"step": 4680
},
{
"epoch": 0.419536631183469,
"grad_norm": 0.4045502543449402,
"learning_rate": 2e-05,
"loss": 0.8419,
"step": 4690
},
{
"epoch": 0.4204311655783165,
"grad_norm": 0.41186532378196716,
"learning_rate": 2e-05,
"loss": 0.8353,
"step": 4700
},
{
"epoch": 0.421325699973164,
"grad_norm": 0.4253060817718506,
"learning_rate": 2e-05,
"loss": 0.8415,
"step": 4710
},
{
"epoch": 0.4222202343680114,
"grad_norm": 0.4444906711578369,
"learning_rate": 2e-05,
"loss": 0.8426,
"step": 4720
},
{
"epoch": 0.4231147687628589,
"grad_norm": 0.44980454444885254,
"learning_rate": 2e-05,
"loss": 0.8444,
"step": 4730
},
{
"epoch": 0.4240093031577064,
"grad_norm": 0.3997156023979187,
"learning_rate": 2e-05,
"loss": 0.8349,
"step": 4740
},
{
"epoch": 0.4249038375525539,
"grad_norm": 0.45415186882019043,
"learning_rate": 2e-05,
"loss": 0.8433,
"step": 4750
},
{
"epoch": 0.4257983719474014,
"grad_norm": 0.44383078813552856,
"learning_rate": 2e-05,
"loss": 0.8424,
"step": 4760
},
{
"epoch": 0.4266929063422489,
"grad_norm": 0.42320993542671204,
"learning_rate": 2e-05,
"loss": 0.845,
"step": 4770
},
{
"epoch": 0.4275874407370963,
"grad_norm": 0.46697622537612915,
"learning_rate": 2e-05,
"loss": 0.8469,
"step": 4780
},
{
"epoch": 0.4284819751319438,
"grad_norm": 0.42103150486946106,
"learning_rate": 2e-05,
"loss": 0.8417,
"step": 4790
},
{
"epoch": 0.4293765095267913,
"grad_norm": 0.4158688485622406,
"learning_rate": 2e-05,
"loss": 0.8558,
"step": 4800
},
{
"epoch": 0.4302710439216388,
"grad_norm": 0.4132760465145111,
"learning_rate": 2e-05,
"loss": 0.8274,
"step": 4810
},
{
"epoch": 0.4311655783164863,
"grad_norm": 0.41097527742385864,
"learning_rate": 2e-05,
"loss": 0.8365,
"step": 4820
},
{
"epoch": 0.43206011271133377,
"grad_norm": 0.45371899008750916,
"learning_rate": 2e-05,
"loss": 0.8492,
"step": 4830
},
{
"epoch": 0.43295464710618126,
"grad_norm": 0.38513296842575073,
"learning_rate": 2e-05,
"loss": 0.8554,
"step": 4840
},
{
"epoch": 0.4338491815010287,
"grad_norm": 0.44337764382362366,
"learning_rate": 2e-05,
"loss": 0.8358,
"step": 4850
},
{
"epoch": 0.4347437158958762,
"grad_norm": 0.4275081753730774,
"learning_rate": 2e-05,
"loss": 0.831,
"step": 4860
},
{
"epoch": 0.43563825029072367,
"grad_norm": 0.6072227358818054,
"learning_rate": 2e-05,
"loss": 0.8444,
"step": 4870
},
{
"epoch": 0.43653278468557116,
"grad_norm": 0.44529175758361816,
"learning_rate": 2e-05,
"loss": 0.8657,
"step": 4880
},
{
"epoch": 0.43742731908041865,
"grad_norm": 0.43206965923309326,
"learning_rate": 2e-05,
"loss": 0.8506,
"step": 4890
},
{
"epoch": 0.43832185347526614,
"grad_norm": 0.4221837818622589,
"learning_rate": 2e-05,
"loss": 0.8444,
"step": 4900
},
{
"epoch": 0.4392163878701136,
"grad_norm": 0.5261819362640381,
"learning_rate": 2e-05,
"loss": 0.8379,
"step": 4910
},
{
"epoch": 0.44011092226496107,
"grad_norm": 0.42317676544189453,
"learning_rate": 2e-05,
"loss": 0.8362,
"step": 4920
},
{
"epoch": 0.44100545665980856,
"grad_norm": 0.4265044331550598,
"learning_rate": 2e-05,
"loss": 0.8299,
"step": 4930
},
{
"epoch": 0.44189999105465605,
"grad_norm": 0.41503632068634033,
"learning_rate": 2e-05,
"loss": 0.836,
"step": 4940
},
{
"epoch": 0.44279452544950354,
"grad_norm": 0.4438629150390625,
"learning_rate": 2e-05,
"loss": 0.8617,
"step": 4950
},
{
"epoch": 0.44368905984435103,
"grad_norm": 0.41733789443969727,
"learning_rate": 2e-05,
"loss": 0.8197,
"step": 4960
},
{
"epoch": 0.4445835942391985,
"grad_norm": 0.4083247780799866,
"learning_rate": 2e-05,
"loss": 0.8521,
"step": 4970
},
{
"epoch": 0.44547812863404596,
"grad_norm": 0.4215552806854248,
"learning_rate": 2e-05,
"loss": 0.8483,
"step": 4980
},
{
"epoch": 0.44637266302889345,
"grad_norm": 0.432403028011322,
"learning_rate": 2e-05,
"loss": 0.8454,
"step": 4990
},
{
"epoch": 0.44726719742374094,
"grad_norm": 0.41806459426879883,
"learning_rate": 2e-05,
"loss": 0.8597,
"step": 5000
},
{
"epoch": 0.4481617318185884,
"grad_norm": 0.3995579183101654,
"learning_rate": 2e-05,
"loss": 0.8533,
"step": 5010
},
{
"epoch": 0.4490562662134359,
"grad_norm": 0.4064474105834961,
"learning_rate": 2e-05,
"loss": 0.85,
"step": 5020
},
{
"epoch": 0.4499508006082834,
"grad_norm": 0.450019508600235,
"learning_rate": 2e-05,
"loss": 0.8465,
"step": 5030
},
{
"epoch": 0.45084533500313084,
"grad_norm": 0.42175576090812683,
"learning_rate": 2e-05,
"loss": 0.8264,
"step": 5040
},
{
"epoch": 0.45173986939797833,
"grad_norm": 0.4329768121242523,
"learning_rate": 2e-05,
"loss": 0.8348,
"step": 5050
},
{
"epoch": 0.4526344037928258,
"grad_norm": 0.4213239252567291,
"learning_rate": 2e-05,
"loss": 0.8428,
"step": 5060
},
{
"epoch": 0.4535289381876733,
"grad_norm": 0.4232270419597626,
"learning_rate": 2e-05,
"loss": 0.8514,
"step": 5070
},
{
"epoch": 0.4544234725825208,
"grad_norm": 0.4631192982196808,
"learning_rate": 2e-05,
"loss": 0.846,
"step": 5080
},
{
"epoch": 0.4553180069773683,
"grad_norm": 0.4208572506904602,
"learning_rate": 2e-05,
"loss": 0.8129,
"step": 5090
},
{
"epoch": 0.4562125413722158,
"grad_norm": 0.40972965955734253,
"learning_rate": 2e-05,
"loss": 0.8406,
"step": 5100
},
{
"epoch": 0.4571070757670632,
"grad_norm": 0.4287187159061432,
"learning_rate": 2e-05,
"loss": 0.8288,
"step": 5110
},
{
"epoch": 0.4580016101619107,
"grad_norm": 0.4280555546283722,
"learning_rate": 2e-05,
"loss": 0.8434,
"step": 5120
},
{
"epoch": 0.4588961445567582,
"grad_norm": 0.4361463189125061,
"learning_rate": 2e-05,
"loss": 0.8507,
"step": 5130
},
{
"epoch": 0.4597906789516057,
"grad_norm": 0.42964521050453186,
"learning_rate": 2e-05,
"loss": 0.8596,
"step": 5140
},
{
"epoch": 0.4606852133464532,
"grad_norm": 0.4830866754055023,
"learning_rate": 2e-05,
"loss": 0.8419,
"step": 5150
},
{
"epoch": 0.46157974774130067,
"grad_norm": 0.41697239875793457,
"learning_rate": 2e-05,
"loss": 0.8386,
"step": 5160
},
{
"epoch": 0.46247428213614816,
"grad_norm": 0.413556307554245,
"learning_rate": 2e-05,
"loss": 0.8276,
"step": 5170
},
{
"epoch": 0.4633688165309956,
"grad_norm": 0.4220239818096161,
"learning_rate": 2e-05,
"loss": 0.8282,
"step": 5180
},
{
"epoch": 0.4642633509258431,
"grad_norm": 0.4359365403652191,
"learning_rate": 2e-05,
"loss": 0.8288,
"step": 5190
},
{
"epoch": 0.4651578853206906,
"grad_norm": 0.44031816720962524,
"learning_rate": 2e-05,
"loss": 0.8258,
"step": 5200
},
{
"epoch": 0.46605241971553807,
"grad_norm": 0.4350534975528717,
"learning_rate": 2e-05,
"loss": 0.8271,
"step": 5210
},
{
"epoch": 0.46694695411038556,
"grad_norm": 0.6063962578773499,
"learning_rate": 2e-05,
"loss": 0.847,
"step": 5220
},
{
"epoch": 0.46784148850523305,
"grad_norm": 0.43683722615242004,
"learning_rate": 2e-05,
"loss": 0.8313,
"step": 5230
},
{
"epoch": 0.4687360229000805,
"grad_norm": 0.4357970952987671,
"learning_rate": 2e-05,
"loss": 0.8498,
"step": 5240
},
{
"epoch": 0.469630557294928,
"grad_norm": 0.43246692419052124,
"learning_rate": 2e-05,
"loss": 0.8177,
"step": 5250
},
{
"epoch": 0.47052509168977547,
"grad_norm": 0.4133908152580261,
"learning_rate": 2e-05,
"loss": 0.8333,
"step": 5260
},
{
"epoch": 0.47141962608462296,
"grad_norm": 0.4512992203235626,
"learning_rate": 2e-05,
"loss": 0.8355,
"step": 5270
},
{
"epoch": 0.47231416047947045,
"grad_norm": 0.41307708621025085,
"learning_rate": 2e-05,
"loss": 0.8308,
"step": 5280
},
{
"epoch": 0.47320869487431794,
"grad_norm": 0.4240661561489105,
"learning_rate": 2e-05,
"loss": 0.8613,
"step": 5290
},
{
"epoch": 0.4741032292691654,
"grad_norm": 0.4320371150970459,
"learning_rate": 2e-05,
"loss": 0.8245,
"step": 5300
},
{
"epoch": 0.47499776366401286,
"grad_norm": 0.4296645522117615,
"learning_rate": 2e-05,
"loss": 0.8602,
"step": 5310
},
{
"epoch": 0.47589229805886035,
"grad_norm": 0.405184805393219,
"learning_rate": 2e-05,
"loss": 0.8311,
"step": 5320
},
{
"epoch": 0.47678683245370784,
"grad_norm": 0.4449639916419983,
"learning_rate": 2e-05,
"loss": 0.8728,
"step": 5330
},
{
"epoch": 0.47768136684855533,
"grad_norm": 0.46990102529525757,
"learning_rate": 2e-05,
"loss": 0.851,
"step": 5340
},
{
"epoch": 0.4785759012434028,
"grad_norm": 0.4048227071762085,
"learning_rate": 2e-05,
"loss": 0.8207,
"step": 5350
},
{
"epoch": 0.4794704356382503,
"grad_norm": 0.4726371169090271,
"learning_rate": 2e-05,
"loss": 0.8509,
"step": 5360
},
{
"epoch": 0.48036497003309775,
"grad_norm": 0.4298088550567627,
"learning_rate": 2e-05,
"loss": 0.8537,
"step": 5370
},
{
"epoch": 0.48125950442794524,
"grad_norm": 0.4202670156955719,
"learning_rate": 2e-05,
"loss": 0.8481,
"step": 5380
},
{
"epoch": 0.48215403882279273,
"grad_norm": 0.4242393970489502,
"learning_rate": 2e-05,
"loss": 0.8517,
"step": 5390
},
{
"epoch": 0.4830485732176402,
"grad_norm": 0.39976486563682556,
"learning_rate": 2e-05,
"loss": 0.8137,
"step": 5400
},
{
"epoch": 0.4839431076124877,
"grad_norm": 0.4355408549308777,
"learning_rate": 2e-05,
"loss": 0.8467,
"step": 5410
},
{
"epoch": 0.4848376420073352,
"grad_norm": 0.42344892024993896,
"learning_rate": 2e-05,
"loss": 0.8063,
"step": 5420
},
{
"epoch": 0.4857321764021827,
"grad_norm": 0.4225989580154419,
"learning_rate": 2e-05,
"loss": 0.8228,
"step": 5430
},
{
"epoch": 0.4866267107970301,
"grad_norm": 0.40819811820983887,
"learning_rate": 2e-05,
"loss": 0.8441,
"step": 5440
},
{
"epoch": 0.4875212451918776,
"grad_norm": 0.4040941894054413,
"learning_rate": 2e-05,
"loss": 0.8287,
"step": 5450
},
{
"epoch": 0.4884157795867251,
"grad_norm": 0.44899114966392517,
"learning_rate": 2e-05,
"loss": 0.8353,
"step": 5460
},
{
"epoch": 0.4893103139815726,
"grad_norm": 0.4067077338695526,
"learning_rate": 2e-05,
"loss": 0.8501,
"step": 5470
},
{
"epoch": 0.4902048483764201,
"grad_norm": 0.42764902114868164,
"learning_rate": 2e-05,
"loss": 0.8414,
"step": 5480
},
{
"epoch": 0.4910993827712676,
"grad_norm": 0.42172637581825256,
"learning_rate": 2e-05,
"loss": 0.8304,
"step": 5490
},
{
"epoch": 0.491993917166115,
"grad_norm": 0.413374125957489,
"learning_rate": 2e-05,
"loss": 0.8426,
"step": 5500
},
{
"epoch": 0.4928884515609625,
"grad_norm": 0.40824776887893677,
"learning_rate": 2e-05,
"loss": 0.8394,
"step": 5510
},
{
"epoch": 0.49378298595581,
"grad_norm": 0.434818297624588,
"learning_rate": 2e-05,
"loss": 0.8583,
"step": 5520
},
{
"epoch": 0.4946775203506575,
"grad_norm": 0.40965044498443604,
"learning_rate": 2e-05,
"loss": 0.8224,
"step": 5530
},
{
"epoch": 0.495572054745505,
"grad_norm": 0.41876915097236633,
"learning_rate": 2e-05,
"loss": 0.8616,
"step": 5540
},
{
"epoch": 0.49646658914035247,
"grad_norm": 0.44509023427963257,
"learning_rate": 2e-05,
"loss": 0.8111,
"step": 5550
},
{
"epoch": 0.49736112353519996,
"grad_norm": 0.45862382650375366,
"learning_rate": 2e-05,
"loss": 0.8263,
"step": 5560
},
{
"epoch": 0.4982556579300474,
"grad_norm": 0.5050536394119263,
"learning_rate": 2e-05,
"loss": 0.8575,
"step": 5570
},
{
"epoch": 0.4991501923248949,
"grad_norm": 0.3999960720539093,
"learning_rate": 2e-05,
"loss": 0.8466,
"step": 5580
},
{
"epoch": 0.5000447267197424,
"grad_norm": 0.4157756268978119,
"learning_rate": 2e-05,
"loss": 0.8429,
"step": 5590
},
{
"epoch": 0.5009392611145899,
"grad_norm": 0.43223127722740173,
"learning_rate": 2e-05,
"loss": 0.8421,
"step": 5600
},
{
"epoch": 0.5018337955094373,
"grad_norm": 0.41067928075790405,
"learning_rate": 2e-05,
"loss": 0.8278,
"step": 5610
},
{
"epoch": 0.5027283299042848,
"grad_norm": 0.4272710680961609,
"learning_rate": 2e-05,
"loss": 0.8433,
"step": 5620
},
{
"epoch": 0.5036228642991323,
"grad_norm": 0.3960169851779938,
"learning_rate": 2e-05,
"loss": 0.8493,
"step": 5630
},
{
"epoch": 0.5045173986939798,
"grad_norm": 0.4120083451271057,
"learning_rate": 2e-05,
"loss": 0.8483,
"step": 5640
},
{
"epoch": 0.5054119330888273,
"grad_norm": 0.3910883367061615,
"learning_rate": 2e-05,
"loss": 0.8486,
"step": 5650
},
{
"epoch": 0.5063064674836747,
"grad_norm": 0.4067328870296478,
"learning_rate": 2e-05,
"loss": 0.8298,
"step": 5660
},
{
"epoch": 0.5072010018785222,
"grad_norm": 0.40505945682525635,
"learning_rate": 2e-05,
"loss": 0.8478,
"step": 5670
},
{
"epoch": 0.5080955362733697,
"grad_norm": 0.40159764885902405,
"learning_rate": 2e-05,
"loss": 0.8247,
"step": 5680
},
{
"epoch": 0.5089900706682172,
"grad_norm": 0.4335174560546875,
"learning_rate": 2e-05,
"loss": 0.8515,
"step": 5690
},
{
"epoch": 0.5098846050630647,
"grad_norm": 0.41705140471458435,
"learning_rate": 2e-05,
"loss": 0.8173,
"step": 5700
},
{
"epoch": 0.5107791394579122,
"grad_norm": 0.4472935199737549,
"learning_rate": 2e-05,
"loss": 0.8474,
"step": 5710
},
{
"epoch": 0.5116736738527596,
"grad_norm": 0.40695905685424805,
"learning_rate": 2e-05,
"loss": 0.8013,
"step": 5720
},
{
"epoch": 0.5125682082476071,
"grad_norm": 0.4252513647079468,
"learning_rate": 2e-05,
"loss": 0.811,
"step": 5730
},
{
"epoch": 0.5134627426424546,
"grad_norm": 0.43663913011550903,
"learning_rate": 2e-05,
"loss": 0.8178,
"step": 5740
},
{
"epoch": 0.514357277037302,
"grad_norm": 0.44863978028297424,
"learning_rate": 2e-05,
"loss": 0.8813,
"step": 5750
},
{
"epoch": 0.5152518114321496,
"grad_norm": 0.4074670374393463,
"learning_rate": 2e-05,
"loss": 0.8271,
"step": 5760
},
{
"epoch": 0.516146345826997,
"grad_norm": 0.40927979350090027,
"learning_rate": 2e-05,
"loss": 0.836,
"step": 5770
},
{
"epoch": 0.5170408802218446,
"grad_norm": 0.4151337146759033,
"learning_rate": 2e-05,
"loss": 0.8417,
"step": 5780
},
{
"epoch": 0.517935414616692,
"grad_norm": 0.4326043128967285,
"learning_rate": 2e-05,
"loss": 0.8077,
"step": 5790
},
{
"epoch": 0.5188299490115394,
"grad_norm": 0.40305671095848083,
"learning_rate": 2e-05,
"loss": 0.8354,
"step": 5800
},
{
"epoch": 0.519724483406387,
"grad_norm": 0.43959853053092957,
"learning_rate": 2e-05,
"loss": 0.8466,
"step": 5810
},
{
"epoch": 0.5206190178012344,
"grad_norm": 0.41634973883628845,
"learning_rate": 2e-05,
"loss": 0.8323,
"step": 5820
},
{
"epoch": 0.521513552196082,
"grad_norm": 0.4298132061958313,
"learning_rate": 2e-05,
"loss": 0.8319,
"step": 5830
},
{
"epoch": 0.5224080865909294,
"grad_norm": 0.4450173079967499,
"learning_rate": 2e-05,
"loss": 0.8375,
"step": 5840
},
{
"epoch": 0.523302620985777,
"grad_norm": 0.4296300709247589,
"learning_rate": 2e-05,
"loss": 0.8542,
"step": 5850
},
{
"epoch": 0.5241971553806244,
"grad_norm": 0.40995725989341736,
"learning_rate": 2e-05,
"loss": 0.8501,
"step": 5860
},
{
"epoch": 0.5250916897754718,
"grad_norm": 0.39617258310317993,
"learning_rate": 2e-05,
"loss": 0.8305,
"step": 5870
},
{
"epoch": 0.5259862241703194,
"grad_norm": 0.5173221826553345,
"learning_rate": 2e-05,
"loss": 0.8028,
"step": 5880
},
{
"epoch": 0.5268807585651668,
"grad_norm": 0.43695807456970215,
"learning_rate": 2e-05,
"loss": 0.8264,
"step": 5890
},
{
"epoch": 0.5277752929600144,
"grad_norm": 0.4001128375530243,
"learning_rate": 2e-05,
"loss": 0.8482,
"step": 5900
},
{
"epoch": 0.5286698273548618,
"grad_norm": 0.4043898582458496,
"learning_rate": 2e-05,
"loss": 0.8421,
"step": 5910
},
{
"epoch": 0.5295643617497092,
"grad_norm": 0.424685537815094,
"learning_rate": 2e-05,
"loss": 0.8099,
"step": 5920
},
{
"epoch": 0.5304588961445568,
"grad_norm": 0.41427651047706604,
"learning_rate": 2e-05,
"loss": 0.8326,
"step": 5930
},
{
"epoch": 0.5313534305394042,
"grad_norm": 0.44595223665237427,
"learning_rate": 2e-05,
"loss": 0.8224,
"step": 5940
},
{
"epoch": 0.5322479649342517,
"grad_norm": 0.41775259375572205,
"learning_rate": 2e-05,
"loss": 0.8671,
"step": 5950
},
{
"epoch": 0.5331424993290992,
"grad_norm": 0.4003002941608429,
"learning_rate": 2e-05,
"loss": 0.8483,
"step": 5960
},
{
"epoch": 0.5340370337239467,
"grad_norm": 0.4185355007648468,
"learning_rate": 2e-05,
"loss": 0.8432,
"step": 5970
},
{
"epoch": 0.5349315681187942,
"grad_norm": 0.44274353981018066,
"learning_rate": 2e-05,
"loss": 0.8343,
"step": 5980
},
{
"epoch": 0.5358261025136416,
"grad_norm": 0.41979002952575684,
"learning_rate": 2e-05,
"loss": 0.839,
"step": 5990
},
{
"epoch": 0.5367206369084891,
"grad_norm": 0.44058290123939514,
"learning_rate": 2e-05,
"loss": 0.8291,
"step": 6000
},
{
"epoch": 0.5376151713033366,
"grad_norm": 0.3949108421802521,
"learning_rate": 2e-05,
"loss": 0.8293,
"step": 6010
},
{
"epoch": 0.5385097056981841,
"grad_norm": 0.4048909842967987,
"learning_rate": 2e-05,
"loss": 0.8159,
"step": 6020
},
{
"epoch": 0.5394042400930316,
"grad_norm": 0.42056983709335327,
"learning_rate": 2e-05,
"loss": 0.8497,
"step": 6030
},
{
"epoch": 0.5402987744878791,
"grad_norm": 0.41351082921028137,
"learning_rate": 2e-05,
"loss": 0.8536,
"step": 6040
},
{
"epoch": 0.5411933088827265,
"grad_norm": 0.41852301359176636,
"learning_rate": 2e-05,
"loss": 0.8262,
"step": 6050
},
{
"epoch": 0.542087843277574,
"grad_norm": 0.4367627799510956,
"learning_rate": 2e-05,
"loss": 0.8249,
"step": 6060
},
{
"epoch": 0.5429823776724215,
"grad_norm": 0.44677454233169556,
"learning_rate": 2e-05,
"loss": 0.8318,
"step": 6070
},
{
"epoch": 0.543876912067269,
"grad_norm": 0.43542051315307617,
"learning_rate": 2e-05,
"loss": 0.8192,
"step": 6080
},
{
"epoch": 0.5447714464621165,
"grad_norm": 0.4212096631526947,
"learning_rate": 2e-05,
"loss": 0.8382,
"step": 6090
},
{
"epoch": 0.5456659808569639,
"grad_norm": 0.43694615364074707,
"learning_rate": 2e-05,
"loss": 0.8463,
"step": 6100
},
{
"epoch": 0.5465605152518115,
"grad_norm": 0.4332883954048157,
"learning_rate": 2e-05,
"loss": 0.8299,
"step": 6110
},
{
"epoch": 0.5474550496466589,
"grad_norm": 0.40514519810676575,
"learning_rate": 2e-05,
"loss": 0.8243,
"step": 6120
},
{
"epoch": 0.5483495840415064,
"grad_norm": 0.6231455206871033,
"learning_rate": 2e-05,
"loss": 0.828,
"step": 6130
},
{
"epoch": 0.5492441184363539,
"grad_norm": 0.4162121117115021,
"learning_rate": 2e-05,
"loss": 0.8507,
"step": 6140
},
{
"epoch": 0.5501386528312013,
"grad_norm": 0.40288665890693665,
"learning_rate": 2e-05,
"loss": 0.828,
"step": 6150
},
{
"epoch": 0.5510331872260489,
"grad_norm": 0.40403953194618225,
"learning_rate": 2e-05,
"loss": 0.795,
"step": 6160
},
{
"epoch": 0.5519277216208963,
"grad_norm": 0.4342193007469177,
"learning_rate": 2e-05,
"loss": 0.8315,
"step": 6170
},
{
"epoch": 0.5528222560157438,
"grad_norm": 0.4117024540901184,
"learning_rate": 2e-05,
"loss": 0.8697,
"step": 6180
},
{
"epoch": 0.5537167904105913,
"grad_norm": 0.42151591181755066,
"learning_rate": 2e-05,
"loss": 0.8296,
"step": 6190
},
{
"epoch": 0.5546113248054387,
"grad_norm": 0.43775543570518494,
"learning_rate": 2e-05,
"loss": 0.8519,
"step": 6200
},
{
"epoch": 0.5555058592002863,
"grad_norm": 0.4081503450870514,
"learning_rate": 2e-05,
"loss": 0.8292,
"step": 6210
},
{
"epoch": 0.5564003935951337,
"grad_norm": 0.4835996627807617,
"learning_rate": 2e-05,
"loss": 0.8535,
"step": 6220
},
{
"epoch": 0.5572949279899813,
"grad_norm": 0.4140726625919342,
"learning_rate": 2e-05,
"loss": 0.8555,
"step": 6230
},
{
"epoch": 0.5581894623848287,
"grad_norm": 0.42983901500701904,
"learning_rate": 2e-05,
"loss": 0.8152,
"step": 6240
},
{
"epoch": 0.5590839967796761,
"grad_norm": 0.42850202322006226,
"learning_rate": 2e-05,
"loss": 0.8208,
"step": 6250
},
{
"epoch": 0.5599785311745237,
"grad_norm": 0.4253295361995697,
"learning_rate": 2e-05,
"loss": 0.8287,
"step": 6260
},
{
"epoch": 0.5608730655693711,
"grad_norm": 0.44828975200653076,
"learning_rate": 2e-05,
"loss": 0.8229,
"step": 6270
},
{
"epoch": 0.5617675999642187,
"grad_norm": 0.4131523370742798,
"learning_rate": 2e-05,
"loss": 0.8393,
"step": 6280
},
{
"epoch": 0.5626621343590661,
"grad_norm": 0.43689417839050293,
"learning_rate": 2e-05,
"loss": 0.8304,
"step": 6290
},
{
"epoch": 0.5635566687539136,
"grad_norm": 0.41511228680610657,
"learning_rate": 2e-05,
"loss": 0.8419,
"step": 6300
},
{
"epoch": 0.5644512031487611,
"grad_norm": 0.42378249764442444,
"learning_rate": 2e-05,
"loss": 0.8168,
"step": 6310
},
{
"epoch": 0.5653457375436085,
"grad_norm": 0.4373960793018341,
"learning_rate": 2e-05,
"loss": 0.8236,
"step": 6320
},
{
"epoch": 0.566240271938456,
"grad_norm": 0.4234122335910797,
"learning_rate": 2e-05,
"loss": 0.8231,
"step": 6330
},
{
"epoch": 0.5671348063333035,
"grad_norm": 0.412605345249176,
"learning_rate": 2e-05,
"loss": 0.8316,
"step": 6340
},
{
"epoch": 0.568029340728151,
"grad_norm": 0.40895146131515503,
"learning_rate": 2e-05,
"loss": 0.8252,
"step": 6350
},
{
"epoch": 0.5689238751229985,
"grad_norm": 0.5273805260658264,
"learning_rate": 2e-05,
"loss": 0.8222,
"step": 6360
},
{
"epoch": 0.569818409517846,
"grad_norm": 0.41901421546936035,
"learning_rate": 2e-05,
"loss": 0.8408,
"step": 6370
},
{
"epoch": 0.5707129439126934,
"grad_norm": 0.4204256534576416,
"learning_rate": 2e-05,
"loss": 0.8351,
"step": 6380
},
{
"epoch": 0.5716074783075409,
"grad_norm": 0.3933697044849396,
"learning_rate": 2e-05,
"loss": 0.8477,
"step": 6390
},
{
"epoch": 0.5725020127023884,
"grad_norm": 0.42342227697372437,
"learning_rate": 2e-05,
"loss": 0.8336,
"step": 6400
},
{
"epoch": 0.5733965470972359,
"grad_norm": 0.4157317578792572,
"learning_rate": 2e-05,
"loss": 0.8285,
"step": 6410
},
{
"epoch": 0.5742910814920834,
"grad_norm": 0.44679099321365356,
"learning_rate": 2e-05,
"loss": 0.804,
"step": 6420
},
{
"epoch": 0.5751856158869308,
"grad_norm": 0.4184143543243408,
"learning_rate": 2e-05,
"loss": 0.848,
"step": 6430
},
{
"epoch": 0.5760801502817783,
"grad_norm": 0.5115336179733276,
"learning_rate": 2e-05,
"loss": 0.8193,
"step": 6440
},
{
"epoch": 0.5769746846766258,
"grad_norm": 0.4901410639286041,
"learning_rate": 2e-05,
"loss": 0.7911,
"step": 6450
},
{
"epoch": 0.5778692190714733,
"grad_norm": 0.41687488555908203,
"learning_rate": 2e-05,
"loss": 0.8215,
"step": 6460
},
{
"epoch": 0.5787637534663208,
"grad_norm": 0.40609365701675415,
"learning_rate": 2e-05,
"loss": 0.8503,
"step": 6470
},
{
"epoch": 0.5796582878611682,
"grad_norm": 0.4130139648914337,
"learning_rate": 2e-05,
"loss": 0.844,
"step": 6480
},
{
"epoch": 0.5805528222560158,
"grad_norm": 0.3894928991794586,
"learning_rate": 2e-05,
"loss": 0.8078,
"step": 6490
},
{
"epoch": 0.5814473566508632,
"grad_norm": 0.4059717357158661,
"learning_rate": 2e-05,
"loss": 0.82,
"step": 6500
},
{
"epoch": 0.5823418910457107,
"grad_norm": 0.39439281821250916,
"learning_rate": 2e-05,
"loss": 0.8223,
"step": 6510
},
{
"epoch": 0.5832364254405582,
"grad_norm": 0.41296902298927307,
"learning_rate": 2e-05,
"loss": 0.8112,
"step": 6520
},
{
"epoch": 0.5841309598354056,
"grad_norm": 0.40260857343673706,
"learning_rate": 2e-05,
"loss": 0.8299,
"step": 6530
},
{
"epoch": 0.5850254942302532,
"grad_norm": 0.4431058466434479,
"learning_rate": 2e-05,
"loss": 0.8239,
"step": 6540
},
{
"epoch": 0.5859200286251006,
"grad_norm": 0.41467252373695374,
"learning_rate": 2e-05,
"loss": 0.838,
"step": 6550
},
{
"epoch": 0.5868145630199482,
"grad_norm": 0.41163110733032227,
"learning_rate": 2e-05,
"loss": 0.829,
"step": 6560
},
{
"epoch": 0.5877090974147956,
"grad_norm": 0.41619303822517395,
"learning_rate": 2e-05,
"loss": 0.8469,
"step": 6570
},
{
"epoch": 0.588603631809643,
"grad_norm": 0.40279582142829895,
"learning_rate": 2e-05,
"loss": 0.8492,
"step": 6580
},
{
"epoch": 0.5894981662044906,
"grad_norm": 0.4173218011856079,
"learning_rate": 2e-05,
"loss": 0.8412,
"step": 6590
},
{
"epoch": 0.590392700599338,
"grad_norm": 0.39412686228752136,
"learning_rate": 2e-05,
"loss": 0.8164,
"step": 6600
},
{
"epoch": 0.5912872349941856,
"grad_norm": 0.4315510094165802,
"learning_rate": 2e-05,
"loss": 0.8236,
"step": 6610
},
{
"epoch": 0.592181769389033,
"grad_norm": 0.4310390055179596,
"learning_rate": 2e-05,
"loss": 0.8564,
"step": 6620
},
{
"epoch": 0.5930763037838805,
"grad_norm": 0.44314512610435486,
"learning_rate": 2e-05,
"loss": 0.8074,
"step": 6630
},
{
"epoch": 0.593970838178728,
"grad_norm": 0.43687209486961365,
"learning_rate": 2e-05,
"loss": 0.8287,
"step": 6640
},
{
"epoch": 0.5948653725735754,
"grad_norm": 0.42191919684410095,
"learning_rate": 2e-05,
"loss": 0.8181,
"step": 6650
},
{
"epoch": 0.595759906968423,
"grad_norm": 0.45914867520332336,
"learning_rate": 2e-05,
"loss": 0.8356,
"step": 6660
},
{
"epoch": 0.5966544413632704,
"grad_norm": 0.4325195848941803,
"learning_rate": 2e-05,
"loss": 0.8165,
"step": 6670
},
{
"epoch": 0.5975489757581179,
"grad_norm": 0.40290647745132446,
"learning_rate": 2e-05,
"loss": 0.7956,
"step": 6680
},
{
"epoch": 0.5984435101529654,
"grad_norm": 0.40643876791000366,
"learning_rate": 2e-05,
"loss": 0.8141,
"step": 6690
},
{
"epoch": 0.5993380445478128,
"grad_norm": 0.417226642370224,
"learning_rate": 2e-05,
"loss": 0.8305,
"step": 6700
},
{
"epoch": 0.6002325789426604,
"grad_norm": 0.4675147533416748,
"learning_rate": 2e-05,
"loss": 0.8406,
"step": 6710
},
{
"epoch": 0.6011271133375078,
"grad_norm": 0.4098436236381531,
"learning_rate": 2e-05,
"loss": 0.7987,
"step": 6720
},
{
"epoch": 0.6020216477323553,
"grad_norm": 0.3960382640361786,
"learning_rate": 2e-05,
"loss": 0.8477,
"step": 6730
},
{
"epoch": 0.6029161821272028,
"grad_norm": 0.40754252672195435,
"learning_rate": 2e-05,
"loss": 0.8302,
"step": 6740
},
{
"epoch": 0.6038107165220503,
"grad_norm": 0.4250786006450653,
"learning_rate": 2e-05,
"loss": 0.832,
"step": 6750
},
{
"epoch": 0.6047052509168978,
"grad_norm": 0.4180477559566498,
"learning_rate": 2e-05,
"loss": 0.8354,
"step": 6760
},
{
"epoch": 0.6055997853117452,
"grad_norm": 0.41738566756248474,
"learning_rate": 2e-05,
"loss": 0.8199,
"step": 6770
},
{
"epoch": 0.6064943197065927,
"grad_norm": 0.43392977118492126,
"learning_rate": 2e-05,
"loss": 0.8356,
"step": 6780
},
{
"epoch": 0.6073888541014402,
"grad_norm": 0.41899681091308594,
"learning_rate": 2e-05,
"loss": 0.8404,
"step": 6790
},
{
"epoch": 0.6082833884962877,
"grad_norm": 0.40851065516471863,
"learning_rate": 2e-05,
"loss": 0.8319,
"step": 6800
},
{
"epoch": 0.6091779228911351,
"grad_norm": 0.41358789801597595,
"learning_rate": 2e-05,
"loss": 0.8086,
"step": 6810
},
{
"epoch": 0.6100724572859827,
"grad_norm": 0.4153432250022888,
"learning_rate": 2e-05,
"loss": 0.8239,
"step": 6820
},
{
"epoch": 0.6109669916808301,
"grad_norm": 0.3868885636329651,
"learning_rate": 2e-05,
"loss": 0.8316,
"step": 6830
},
{
"epoch": 0.6118615260756776,
"grad_norm": 0.45753178000450134,
"learning_rate": 2e-05,
"loss": 0.8321,
"step": 6840
},
{
"epoch": 0.6127560604705251,
"grad_norm": 1.877017855644226,
"learning_rate": 2e-05,
"loss": 0.8251,
"step": 6850
},
{
"epoch": 0.6136505948653725,
"grad_norm": 0.3940776586532593,
"learning_rate": 2e-05,
"loss": 0.8498,
"step": 6860
},
{
"epoch": 0.6145451292602201,
"grad_norm": 0.4279727041721344,
"learning_rate": 2e-05,
"loss": 0.8172,
"step": 6870
},
{
"epoch": 0.6154396636550675,
"grad_norm": 0.43859291076660156,
"learning_rate": 2e-05,
"loss": 0.8389,
"step": 6880
},
{
"epoch": 0.6163341980499151,
"grad_norm": 0.41172870993614197,
"learning_rate": 2e-05,
"loss": 0.8369,
"step": 6890
},
{
"epoch": 0.6172287324447625,
"grad_norm": 0.41583412885665894,
"learning_rate": 2e-05,
"loss": 0.8083,
"step": 6900
},
{
"epoch": 0.6181232668396099,
"grad_norm": 0.41212162375450134,
"learning_rate": 2e-05,
"loss": 0.8307,
"step": 6910
},
{
"epoch": 0.6190178012344575,
"grad_norm": 0.39989569783210754,
"learning_rate": 2e-05,
"loss": 0.8053,
"step": 6920
},
{
"epoch": 0.6199123356293049,
"grad_norm": 0.4336104989051819,
"learning_rate": 2e-05,
"loss": 0.8287,
"step": 6930
},
{
"epoch": 0.6208068700241525,
"grad_norm": 0.44162747263908386,
"learning_rate": 2e-05,
"loss": 0.8336,
"step": 6940
},
{
"epoch": 0.6217014044189999,
"grad_norm": 0.448621928691864,
"learning_rate": 2e-05,
"loss": 0.8206,
"step": 6950
},
{
"epoch": 0.6225959388138473,
"grad_norm": 0.4249946177005768,
"learning_rate": 2e-05,
"loss": 0.825,
"step": 6960
},
{
"epoch": 0.6234904732086949,
"grad_norm": 0.4055660367012024,
"learning_rate": 2e-05,
"loss": 0.7874,
"step": 6970
},
{
"epoch": 0.6243850076035423,
"grad_norm": 0.3934391140937805,
"learning_rate": 2e-05,
"loss": 0.824,
"step": 6980
},
{
"epoch": 0.6252795419983899,
"grad_norm": 0.4052409827709198,
"learning_rate": 2e-05,
"loss": 0.8365,
"step": 6990
},
{
"epoch": 0.6261740763932373,
"grad_norm": 0.41568654775619507,
"learning_rate": 2e-05,
"loss": 0.8479,
"step": 7000
},
{
"epoch": 0.6270686107880848,
"grad_norm": 0.4137478768825531,
"learning_rate": 2e-05,
"loss": 0.8175,
"step": 7010
},
{
"epoch": 0.6279631451829323,
"grad_norm": 0.410024493932724,
"learning_rate": 2e-05,
"loss": 0.838,
"step": 7020
},
{
"epoch": 0.6288576795777797,
"grad_norm": 0.38836365938186646,
"learning_rate": 2e-05,
"loss": 0.8403,
"step": 7030
},
{
"epoch": 0.6297522139726273,
"grad_norm": 0.418420672416687,
"learning_rate": 2e-05,
"loss": 0.8431,
"step": 7040
},
{
"epoch": 0.6306467483674747,
"grad_norm": 0.4103337526321411,
"learning_rate": 2e-05,
"loss": 0.8155,
"step": 7050
},
{
"epoch": 0.6315412827623222,
"grad_norm": 0.4171472489833832,
"learning_rate": 2e-05,
"loss": 0.8413,
"step": 7060
},
{
"epoch": 0.6324358171571697,
"grad_norm": 0.4332127571105957,
"learning_rate": 2e-05,
"loss": 0.8151,
"step": 7070
},
{
"epoch": 0.6333303515520172,
"grad_norm": 0.3930632472038269,
"learning_rate": 2e-05,
"loss": 0.8362,
"step": 7080
},
{
"epoch": 0.6342248859468647,
"grad_norm": 0.40426895022392273,
"learning_rate": 2e-05,
"loss": 0.8247,
"step": 7090
},
{
"epoch": 0.6351194203417121,
"grad_norm": 0.4346529543399811,
"learning_rate": 2e-05,
"loss": 0.8306,
"step": 7100
},
{
"epoch": 0.6360139547365596,
"grad_norm": 0.4234216809272766,
"learning_rate": 2e-05,
"loss": 0.8301,
"step": 7110
},
{
"epoch": 0.6369084891314071,
"grad_norm": 0.41293755173683167,
"learning_rate": 2e-05,
"loss": 0.8006,
"step": 7120
},
{
"epoch": 0.6378030235262546,
"grad_norm": 0.41545289754867554,
"learning_rate": 2e-05,
"loss": 0.8287,
"step": 7130
},
{
"epoch": 0.638697557921102,
"grad_norm": 0.4211075007915497,
"learning_rate": 2e-05,
"loss": 0.8167,
"step": 7140
},
{
"epoch": 0.6395920923159496,
"grad_norm": 0.41593942046165466,
"learning_rate": 2e-05,
"loss": 0.8344,
"step": 7150
},
{
"epoch": 0.640486626710797,
"grad_norm": 0.41257229447364807,
"learning_rate": 2e-05,
"loss": 0.8048,
"step": 7160
},
{
"epoch": 0.6413811611056445,
"grad_norm": 0.449800580739975,
"learning_rate": 2e-05,
"loss": 0.8128,
"step": 7170
},
{
"epoch": 0.642275695500492,
"grad_norm": 0.4342520534992218,
"learning_rate": 2e-05,
"loss": 0.8146,
"step": 7180
},
{
"epoch": 0.6431702298953395,
"grad_norm": 0.4132433235645294,
"learning_rate": 2e-05,
"loss": 0.8415,
"step": 7190
},
{
"epoch": 0.644064764290187,
"grad_norm": 0.4973197281360626,
"learning_rate": 2e-05,
"loss": 0.8223,
"step": 7200
},
{
"epoch": 0.6449592986850344,
"grad_norm": 0.4398617148399353,
"learning_rate": 2e-05,
"loss": 0.8289,
"step": 7210
},
{
"epoch": 0.6458538330798819,
"grad_norm": 0.4164842963218689,
"learning_rate": 2e-05,
"loss": 0.822,
"step": 7220
},
{
"epoch": 0.6467483674747294,
"grad_norm": 0.4236685335636139,
"learning_rate": 2e-05,
"loss": 0.8316,
"step": 7230
},
{
"epoch": 0.6476429018695768,
"grad_norm": 0.3826504051685333,
"learning_rate": 2e-05,
"loss": 0.808,
"step": 7240
},
{
"epoch": 0.6485374362644244,
"grad_norm": 0.3991691470146179,
"learning_rate": 2e-05,
"loss": 0.7917,
"step": 7250
},
{
"epoch": 0.6494319706592718,
"grad_norm": 0.424884557723999,
"learning_rate": 2e-05,
"loss": 0.8294,
"step": 7260
},
{
"epoch": 0.6503265050541194,
"grad_norm": 0.40788933634757996,
"learning_rate": 2e-05,
"loss": 0.8373,
"step": 7270
},
{
"epoch": 0.6512210394489668,
"grad_norm": 0.4224216938018799,
"learning_rate": 2e-05,
"loss": 0.8121,
"step": 7280
},
{
"epoch": 0.6521155738438142,
"grad_norm": 0.4418998062610626,
"learning_rate": 2e-05,
"loss": 0.8019,
"step": 7290
},
{
"epoch": 0.6530101082386618,
"grad_norm": 0.38550126552581787,
"learning_rate": 2e-05,
"loss": 0.8127,
"step": 7300
},
{
"epoch": 0.6539046426335092,
"grad_norm": 0.43809986114501953,
"learning_rate": 2e-05,
"loss": 0.8219,
"step": 7310
},
{
"epoch": 0.6547991770283568,
"grad_norm": 0.40225595235824585,
"learning_rate": 2e-05,
"loss": 0.8139,
"step": 7320
},
{
"epoch": 0.6556937114232042,
"grad_norm": 0.4040333330631256,
"learning_rate": 2e-05,
"loss": 0.7946,
"step": 7330
},
{
"epoch": 0.6565882458180518,
"grad_norm": 0.4118202030658722,
"learning_rate": 2e-05,
"loss": 0.8222,
"step": 7340
},
{
"epoch": 0.6574827802128992,
"grad_norm": 0.41328543424606323,
"learning_rate": 2e-05,
"loss": 0.8336,
"step": 7350
},
{
"epoch": 0.6583773146077466,
"grad_norm": 0.42486241459846497,
"learning_rate": 2e-05,
"loss": 0.8187,
"step": 7360
},
{
"epoch": 0.6592718490025942,
"grad_norm": 0.4181831181049347,
"learning_rate": 2e-05,
"loss": 0.8238,
"step": 7370
},
{
"epoch": 0.6601663833974416,
"grad_norm": 0.40414634346961975,
"learning_rate": 2e-05,
"loss": 0.8342,
"step": 7380
},
{
"epoch": 0.6610609177922891,
"grad_norm": 0.39222392439842224,
"learning_rate": 2e-05,
"loss": 0.805,
"step": 7390
},
{
"epoch": 0.6619554521871366,
"grad_norm": 0.40987029671669006,
"learning_rate": 2e-05,
"loss": 0.8117,
"step": 7400
},
{
"epoch": 0.6628499865819841,
"grad_norm": 0.3892180919647217,
"learning_rate": 2e-05,
"loss": 0.8101,
"step": 7410
},
{
"epoch": 0.6637445209768316,
"grad_norm": 0.44778111577033997,
"learning_rate": 2e-05,
"loss": 0.8262,
"step": 7420
},
{
"epoch": 0.664639055371679,
"grad_norm": 0.441082239151001,
"learning_rate": 2e-05,
"loss": 0.8106,
"step": 7430
},
{
"epoch": 0.6655335897665265,
"grad_norm": 0.40722551941871643,
"learning_rate": 2e-05,
"loss": 0.8289,
"step": 7440
},
{
"epoch": 0.666428124161374,
"grad_norm": 0.44159558415412903,
"learning_rate": 2e-05,
"loss": 0.8154,
"step": 7450
},
{
"epoch": 0.6673226585562215,
"grad_norm": 0.4278644919395447,
"learning_rate": 2e-05,
"loss": 0.7992,
"step": 7460
},
{
"epoch": 0.668217192951069,
"grad_norm": 0.42330044507980347,
"learning_rate": 2e-05,
"loss": 0.8146,
"step": 7470
},
{
"epoch": 0.6691117273459164,
"grad_norm": 0.4159793257713318,
"learning_rate": 2e-05,
"loss": 0.8158,
"step": 7480
},
{
"epoch": 0.6700062617407639,
"grad_norm": 0.4060797393321991,
"learning_rate": 2e-05,
"loss": 0.8262,
"step": 7490
},
{
"epoch": 0.6709007961356114,
"grad_norm": 0.40918755531311035,
"learning_rate": 2e-05,
"loss": 0.8091,
"step": 7500
},
{
"epoch": 0.6717953305304589,
"grad_norm": 0.4164888560771942,
"learning_rate": 2e-05,
"loss": 0.7999,
"step": 7510
},
{
"epoch": 0.6726898649253064,
"grad_norm": 0.4159010350704193,
"learning_rate": 2e-05,
"loss": 0.8176,
"step": 7520
},
{
"epoch": 0.6735843993201539,
"grad_norm": 0.39323922991752625,
"learning_rate": 2e-05,
"loss": 0.7912,
"step": 7530
},
{
"epoch": 0.6744789337150013,
"grad_norm": 0.4300224483013153,
"learning_rate": 2e-05,
"loss": 0.8058,
"step": 7540
},
{
"epoch": 0.6753734681098488,
"grad_norm": 0.4318203032016754,
"learning_rate": 2e-05,
"loss": 0.8007,
"step": 7550
},
{
"epoch": 0.6762680025046963,
"grad_norm": 0.394403874874115,
"learning_rate": 2e-05,
"loss": 0.8057,
"step": 7560
},
{
"epoch": 0.6771625368995438,
"grad_norm": 0.44359275698661804,
"learning_rate": 2e-05,
"loss": 0.8537,
"step": 7570
},
{
"epoch": 0.6780570712943913,
"grad_norm": 0.41513705253601074,
"learning_rate": 2e-05,
"loss": 0.8125,
"step": 7580
},
{
"epoch": 0.6789516056892387,
"grad_norm": 0.4087067246437073,
"learning_rate": 2e-05,
"loss": 0.8399,
"step": 7590
},
{
"epoch": 0.6798461400840863,
"grad_norm": 0.38161593675613403,
"learning_rate": 2e-05,
"loss": 0.8151,
"step": 7600
},
{
"epoch": 0.6807406744789337,
"grad_norm": 0.40588846802711487,
"learning_rate": 2e-05,
"loss": 0.8216,
"step": 7610
},
{
"epoch": 0.6816352088737812,
"grad_norm": 0.3970322906970978,
"learning_rate": 2e-05,
"loss": 0.8204,
"step": 7620
},
{
"epoch": 0.6825297432686287,
"grad_norm": 0.4004708230495453,
"learning_rate": 2e-05,
"loss": 0.8084,
"step": 7630
},
{
"epoch": 0.6834242776634761,
"grad_norm": 0.42199960350990295,
"learning_rate": 2e-05,
"loss": 0.8052,
"step": 7640
},
{
"epoch": 0.6843188120583237,
"grad_norm": 0.429627001285553,
"learning_rate": 2e-05,
"loss": 0.8126,
"step": 7650
},
{
"epoch": 0.6852133464531711,
"grad_norm": 0.40379664301872253,
"learning_rate": 2e-05,
"loss": 0.8038,
"step": 7660
},
{
"epoch": 0.6861078808480187,
"grad_norm": 0.40914231538772583,
"learning_rate": 2e-05,
"loss": 0.8041,
"step": 7670
},
{
"epoch": 0.6870024152428661,
"grad_norm": 0.4253308176994324,
"learning_rate": 2e-05,
"loss": 0.8009,
"step": 7680
},
{
"epoch": 0.6878969496377135,
"grad_norm": 0.39738699793815613,
"learning_rate": 2e-05,
"loss": 0.7902,
"step": 7690
},
{
"epoch": 0.6887914840325611,
"grad_norm": 0.40318480134010315,
"learning_rate": 2e-05,
"loss": 0.7896,
"step": 7700
},
{
"epoch": 0.6896860184274085,
"grad_norm": 0.42683500051498413,
"learning_rate": 2e-05,
"loss": 0.8108,
"step": 7710
},
{
"epoch": 0.690580552822256,
"grad_norm": 0.3892528712749481,
"learning_rate": 2e-05,
"loss": 0.8327,
"step": 7720
},
{
"epoch": 0.6914750872171035,
"grad_norm": 0.4224511384963989,
"learning_rate": 2e-05,
"loss": 0.8067,
"step": 7730
},
{
"epoch": 0.6923696216119509,
"grad_norm": 0.6183866858482361,
"learning_rate": 2e-05,
"loss": 0.8237,
"step": 7740
},
{
"epoch": 0.6932641560067985,
"grad_norm": 0.4008243680000305,
"learning_rate": 2e-05,
"loss": 0.8089,
"step": 7750
},
{
"epoch": 0.6941586904016459,
"grad_norm": 0.39835166931152344,
"learning_rate": 2e-05,
"loss": 0.7862,
"step": 7760
},
{
"epoch": 0.6950532247964935,
"grad_norm": 0.4232148230075836,
"learning_rate": 2e-05,
"loss": 0.8191,
"step": 7770
},
{
"epoch": 0.6959477591913409,
"grad_norm": 0.3994593918323517,
"learning_rate": 2e-05,
"loss": 0.7985,
"step": 7780
},
{
"epoch": 0.6968422935861884,
"grad_norm": 0.40056857466697693,
"learning_rate": 2e-05,
"loss": 0.8101,
"step": 7790
},
{
"epoch": 0.6977368279810359,
"grad_norm": 0.46421918272972107,
"learning_rate": 2e-05,
"loss": 0.8071,
"step": 7800
},
{
"epoch": 0.6986313623758833,
"grad_norm": 0.4290282130241394,
"learning_rate": 2e-05,
"loss": 0.8031,
"step": 7810
},
{
"epoch": 0.6995258967707308,
"grad_norm": 0.4016701877117157,
"learning_rate": 2e-05,
"loss": 0.8265,
"step": 7820
},
{
"epoch": 0.7004204311655783,
"grad_norm": 0.40227213501930237,
"learning_rate": 2e-05,
"loss": 0.8142,
"step": 7830
},
{
"epoch": 0.7013149655604258,
"grad_norm": 0.40672552585601807,
"learning_rate": 2e-05,
"loss": 0.8014,
"step": 7840
},
{
"epoch": 0.7022094999552733,
"grad_norm": 0.41232022643089294,
"learning_rate": 2e-05,
"loss": 0.8052,
"step": 7850
},
{
"epoch": 0.7031040343501208,
"grad_norm": 0.4154973328113556,
"learning_rate": 2e-05,
"loss": 0.803,
"step": 7860
},
{
"epoch": 0.7039985687449682,
"grad_norm": 0.4158405363559723,
"learning_rate": 2e-05,
"loss": 0.8228,
"step": 7870
},
{
"epoch": 0.7048931031398157,
"grad_norm": 0.39905792474746704,
"learning_rate": 2e-05,
"loss": 0.8107,
"step": 7880
},
{
"epoch": 0.7057876375346632,
"grad_norm": 0.4117918312549591,
"learning_rate": 2e-05,
"loss": 0.8173,
"step": 7890
},
{
"epoch": 0.7066821719295107,
"grad_norm": 0.4062362313270569,
"learning_rate": 2e-05,
"loss": 0.817,
"step": 7900
},
{
"epoch": 0.7075767063243582,
"grad_norm": 0.4103967845439911,
"learning_rate": 2e-05,
"loss": 0.8027,
"step": 7910
},
{
"epoch": 0.7084712407192056,
"grad_norm": 0.43863022327423096,
"learning_rate": 2e-05,
"loss": 0.8072,
"step": 7920
},
{
"epoch": 0.7093657751140532,
"grad_norm": 0.41436973214149475,
"learning_rate": 2e-05,
"loss": 0.836,
"step": 7930
},
{
"epoch": 0.7102603095089006,
"grad_norm": 0.4197036623954773,
"learning_rate": 2e-05,
"loss": 0.8155,
"step": 7940
},
{
"epoch": 0.7111548439037481,
"grad_norm": 0.4083525538444519,
"learning_rate": 2e-05,
"loss": 0.8353,
"step": 7950
},
{
"epoch": 0.7120493782985956,
"grad_norm": 0.4156051576137543,
"learning_rate": 2e-05,
"loss": 0.8171,
"step": 7960
},
{
"epoch": 0.712943912693443,
"grad_norm": 0.4303976893424988,
"learning_rate": 2e-05,
"loss": 0.8424,
"step": 7970
},
{
"epoch": 0.7138384470882906,
"grad_norm": 0.38429346680641174,
"learning_rate": 2e-05,
"loss": 0.8026,
"step": 7980
},
{
"epoch": 0.714732981483138,
"grad_norm": 0.41261962056159973,
"learning_rate": 2e-05,
"loss": 0.8001,
"step": 7990
},
{
"epoch": 0.7156275158779855,
"grad_norm": 0.4345111548900604,
"learning_rate": 2e-05,
"loss": 0.7872,
"step": 8000
},
{
"epoch": 0.716522050272833,
"grad_norm": 0.4165780246257782,
"learning_rate": 2e-05,
"loss": 0.8063,
"step": 8010
},
{
"epoch": 0.7174165846676804,
"grad_norm": 0.4243733882904053,
"learning_rate": 2e-05,
"loss": 0.8163,
"step": 8020
},
{
"epoch": 0.718311119062528,
"grad_norm": 0.40169522166252136,
"learning_rate": 2e-05,
"loss": 0.7934,
"step": 8030
},
{
"epoch": 0.7192056534573754,
"grad_norm": 0.4156307578086853,
"learning_rate": 2e-05,
"loss": 0.8143,
"step": 8040
},
{
"epoch": 0.720100187852223,
"grad_norm": 0.4062471091747284,
"learning_rate": 2e-05,
"loss": 0.8066,
"step": 8050
},
{
"epoch": 0.7209947222470704,
"grad_norm": 0.4005821645259857,
"learning_rate": 2e-05,
"loss": 0.8089,
"step": 8060
},
{
"epoch": 0.7218892566419178,
"grad_norm": 0.42837730050086975,
"learning_rate": 2e-05,
"loss": 0.8088,
"step": 8070
},
{
"epoch": 0.7227837910367654,
"grad_norm": 0.3871780037879944,
"learning_rate": 2e-05,
"loss": 0.8162,
"step": 8080
},
{
"epoch": 0.7236783254316128,
"grad_norm": 0.41431939601898193,
"learning_rate": 2e-05,
"loss": 0.823,
"step": 8090
},
{
"epoch": 0.7245728598264604,
"grad_norm": 0.3937652111053467,
"learning_rate": 2e-05,
"loss": 0.825,
"step": 8100
},
{
"epoch": 0.7254673942213078,
"grad_norm": 0.42264991998672485,
"learning_rate": 2e-05,
"loss": 0.8149,
"step": 8110
},
{
"epoch": 0.7263619286161553,
"grad_norm": 0.40388330817222595,
"learning_rate": 2e-05,
"loss": 0.7964,
"step": 8120
},
{
"epoch": 0.7272564630110028,
"grad_norm": 0.41297823190689087,
"learning_rate": 2e-05,
"loss": 0.8157,
"step": 8130
},
{
"epoch": 0.7281509974058502,
"grad_norm": 0.403692364692688,
"learning_rate": 2e-05,
"loss": 0.8067,
"step": 8140
},
{
"epoch": 0.7290455318006978,
"grad_norm": 0.41570308804512024,
"learning_rate": 2e-05,
"loss": 0.8094,
"step": 8150
},
{
"epoch": 0.7299400661955452,
"grad_norm": 0.4090012311935425,
"learning_rate": 2e-05,
"loss": 0.806,
"step": 8160
},
{
"epoch": 0.7308346005903927,
"grad_norm": 0.4117349684238434,
"learning_rate": 2e-05,
"loss": 0.8245,
"step": 8170
},
{
"epoch": 0.7317291349852402,
"grad_norm": 0.429177463054657,
"learning_rate": 2e-05,
"loss": 0.8267,
"step": 8180
},
{
"epoch": 0.7326236693800877,
"grad_norm": 0.4083811044692993,
"learning_rate": 2e-05,
"loss": 0.816,
"step": 8190
},
{
"epoch": 0.7335182037749352,
"grad_norm": 0.4355076253414154,
"learning_rate": 2e-05,
"loss": 0.8477,
"step": 8200
},
{
"epoch": 0.7344127381697826,
"grad_norm": 0.3947085440158844,
"learning_rate": 2e-05,
"loss": 0.811,
"step": 8210
},
{
"epoch": 0.7353072725646301,
"grad_norm": 0.4387696385383606,
"learning_rate": 2e-05,
"loss": 0.7965,
"step": 8220
},
{
"epoch": 0.7362018069594776,
"grad_norm": 0.4257657527923584,
"learning_rate": 2e-05,
"loss": 0.8135,
"step": 8230
},
{
"epoch": 0.7370963413543251,
"grad_norm": 0.40082642436027527,
"learning_rate": 2e-05,
"loss": 0.8042,
"step": 8240
},
{
"epoch": 0.7379908757491725,
"grad_norm": 0.41494259238243103,
"learning_rate": 2e-05,
"loss": 0.8112,
"step": 8250
},
{
"epoch": 0.73888541014402,
"grad_norm": 0.4127449095249176,
"learning_rate": 2e-05,
"loss": 0.818,
"step": 8260
},
{
"epoch": 0.7397799445388675,
"grad_norm": 0.3956024944782257,
"learning_rate": 2e-05,
"loss": 0.7886,
"step": 8270
},
{
"epoch": 0.740674478933715,
"grad_norm": 0.43969056010246277,
"learning_rate": 2e-05,
"loss": 0.8157,
"step": 8280
},
{
"epoch": 0.7415690133285625,
"grad_norm": 0.62724369764328,
"learning_rate": 2e-05,
"loss": 0.8201,
"step": 8290
},
{
"epoch": 0.74246354772341,
"grad_norm": 0.4054270088672638,
"learning_rate": 2e-05,
"loss": 0.8261,
"step": 8300
},
{
"epoch": 0.7433580821182575,
"grad_norm": 0.38642802834510803,
"learning_rate": 2e-05,
"loss": 0.8189,
"step": 8310
},
{
"epoch": 0.7442526165131049,
"grad_norm": 0.42306891083717346,
"learning_rate": 2e-05,
"loss": 0.795,
"step": 8320
},
{
"epoch": 0.7451471509079524,
"grad_norm": 0.43081989884376526,
"learning_rate": 2e-05,
"loss": 0.8165,
"step": 8330
},
{
"epoch": 0.7460416853027999,
"grad_norm": 0.4071492850780487,
"learning_rate": 2e-05,
"loss": 0.8138,
"step": 8340
},
{
"epoch": 0.7469362196976473,
"grad_norm": 0.4356868267059326,
"learning_rate": 2e-05,
"loss": 0.8186,
"step": 8350
},
{
"epoch": 0.7478307540924949,
"grad_norm": 0.40252014994621277,
"learning_rate": 2e-05,
"loss": 0.8059,
"step": 8360
},
{
"epoch": 0.7487252884873423,
"grad_norm": 0.3909730017185211,
"learning_rate": 2e-05,
"loss": 0.8473,
"step": 8370
},
{
"epoch": 0.7496198228821899,
"grad_norm": 0.4067108631134033,
"learning_rate": 2e-05,
"loss": 0.8162,
"step": 8380
},
{
"epoch": 0.7505143572770373,
"grad_norm": 0.4101555645465851,
"learning_rate": 2e-05,
"loss": 0.8245,
"step": 8390
},
{
"epoch": 0.7514088916718847,
"grad_norm": 0.42581531405448914,
"learning_rate": 2e-05,
"loss": 0.7902,
"step": 8400
},
{
"epoch": 0.7523034260667323,
"grad_norm": 0.41230538487434387,
"learning_rate": 2e-05,
"loss": 0.808,
"step": 8410
},
{
"epoch": 0.7531979604615797,
"grad_norm": 0.4191984236240387,
"learning_rate": 2e-05,
"loss": 0.8127,
"step": 8420
},
{
"epoch": 0.7540924948564273,
"grad_norm": 0.3885388970375061,
"learning_rate": 2e-05,
"loss": 0.8016,
"step": 8430
},
{
"epoch": 0.7549870292512747,
"grad_norm": 0.38983532786369324,
"learning_rate": 2e-05,
"loss": 0.8218,
"step": 8440
},
{
"epoch": 0.7558815636461222,
"grad_norm": 0.4019433259963989,
"learning_rate": 2e-05,
"loss": 0.8119,
"step": 8450
},
{
"epoch": 0.7567760980409697,
"grad_norm": 0.40456968545913696,
"learning_rate": 2e-05,
"loss": 0.7857,
"step": 8460
},
{
"epoch": 0.7576706324358171,
"grad_norm": 0.40845203399658203,
"learning_rate": 2e-05,
"loss": 0.8103,
"step": 8470
},
{
"epoch": 0.7585651668306647,
"grad_norm": 0.41237568855285645,
"learning_rate": 2e-05,
"loss": 0.8166,
"step": 8480
},
{
"epoch": 0.7594597012255121,
"grad_norm": 0.40178152918815613,
"learning_rate": 2e-05,
"loss": 0.7922,
"step": 8490
},
{
"epoch": 0.7603542356203596,
"grad_norm": 0.4130358397960663,
"learning_rate": 2e-05,
"loss": 0.8458,
"step": 8500
},
{
"epoch": 0.7612487700152071,
"grad_norm": 0.4019741415977478,
"learning_rate": 2e-05,
"loss": 0.7825,
"step": 8510
},
{
"epoch": 0.7621433044100545,
"grad_norm": 0.42670419812202454,
"learning_rate": 2e-05,
"loss": 0.8295,
"step": 8520
},
{
"epoch": 0.7630378388049021,
"grad_norm": 0.38693976402282715,
"learning_rate": 2e-05,
"loss": 0.8029,
"step": 8530
},
{
"epoch": 0.7639323731997495,
"grad_norm": 0.4117787182331085,
"learning_rate": 2e-05,
"loss": 0.8239,
"step": 8540
},
{
"epoch": 0.764826907594597,
"grad_norm": 0.4235455393791199,
"learning_rate": 2e-05,
"loss": 0.8281,
"step": 8550
},
{
"epoch": 0.7657214419894445,
"grad_norm": 0.410953551530838,
"learning_rate": 2e-05,
"loss": 0.8018,
"step": 8560
},
{
"epoch": 0.766615976384292,
"grad_norm": 0.42626288533210754,
"learning_rate": 2e-05,
"loss": 0.778,
"step": 8570
},
{
"epoch": 0.7675105107791395,
"grad_norm": 0.40481773018836975,
"learning_rate": 2e-05,
"loss": 0.8213,
"step": 8580
},
{
"epoch": 0.7684050451739869,
"grad_norm": 0.38530778884887695,
"learning_rate": 2e-05,
"loss": 0.7886,
"step": 8590
},
{
"epoch": 0.7692995795688344,
"grad_norm": 0.4185646176338196,
"learning_rate": 2e-05,
"loss": 0.8214,
"step": 8600
},
{
"epoch": 0.7701941139636819,
"grad_norm": 0.45213767886161804,
"learning_rate": 2e-05,
"loss": 0.8136,
"step": 8610
},
{
"epoch": 0.7710886483585294,
"grad_norm": 0.39413052797317505,
"learning_rate": 2e-05,
"loss": 0.789,
"step": 8620
},
{
"epoch": 0.7719831827533769,
"grad_norm": 0.41384357213974,
"learning_rate": 2e-05,
"loss": 0.8238,
"step": 8630
},
{
"epoch": 0.7728777171482244,
"grad_norm": 0.4355621933937073,
"learning_rate": 2e-05,
"loss": 0.8103,
"step": 8640
},
{
"epoch": 0.7737722515430718,
"grad_norm": 0.40865957736968994,
"learning_rate": 2e-05,
"loss": 0.7966,
"step": 8650
},
{
"epoch": 0.7746667859379193,
"grad_norm": 0.4261012375354767,
"learning_rate": 2e-05,
"loss": 0.8134,
"step": 8660
},
{
"epoch": 0.7755613203327668,
"grad_norm": 0.385575532913208,
"learning_rate": 2e-05,
"loss": 0.7839,
"step": 8670
},
{
"epoch": 0.7764558547276142,
"grad_norm": 0.40317976474761963,
"learning_rate": 2e-05,
"loss": 0.812,
"step": 8680
},
{
"epoch": 0.7773503891224618,
"grad_norm": 0.44876375794410706,
"learning_rate": 2e-05,
"loss": 0.8397,
"step": 8690
},
{
"epoch": 0.7782449235173092,
"grad_norm": 0.43180447816848755,
"learning_rate": 2e-05,
"loss": 0.807,
"step": 8700
},
{
"epoch": 0.7791394579121568,
"grad_norm": 0.40485119819641113,
"learning_rate": 2e-05,
"loss": 0.8182,
"step": 8710
},
{
"epoch": 0.7800339923070042,
"grad_norm": 0.39239615201950073,
"learning_rate": 2e-05,
"loss": 0.7839,
"step": 8720
},
{
"epoch": 0.7809285267018516,
"grad_norm": 0.4359530806541443,
"learning_rate": 2e-05,
"loss": 0.8033,
"step": 8730
},
{
"epoch": 0.7818230610966992,
"grad_norm": 0.4605741798877716,
"learning_rate": 2e-05,
"loss": 0.8012,
"step": 8740
},
{
"epoch": 0.7827175954915466,
"grad_norm": 0.4017501175403595,
"learning_rate": 2e-05,
"loss": 0.8122,
"step": 8750
},
{
"epoch": 0.7836121298863942,
"grad_norm": 0.4082208275794983,
"learning_rate": 2e-05,
"loss": 0.8066,
"step": 8760
},
{
"epoch": 0.7845066642812416,
"grad_norm": 0.4194105267524719,
"learning_rate": 2e-05,
"loss": 0.8049,
"step": 8770
},
{
"epoch": 0.785401198676089,
"grad_norm": 0.43814149498939514,
"learning_rate": 2e-05,
"loss": 0.8185,
"step": 8780
},
{
"epoch": 0.7862957330709366,
"grad_norm": 0.41030582785606384,
"learning_rate": 2e-05,
"loss": 0.8033,
"step": 8790
},
{
"epoch": 0.787190267465784,
"grad_norm": 0.39272475242614746,
"learning_rate": 2e-05,
"loss": 0.8113,
"step": 8800
},
{
"epoch": 0.7880848018606316,
"grad_norm": 0.40445712208747864,
"learning_rate": 2e-05,
"loss": 0.7854,
"step": 8810
},
{
"epoch": 0.788979336255479,
"grad_norm": 0.44358667731285095,
"learning_rate": 2e-05,
"loss": 0.7826,
"step": 8820
},
{
"epoch": 0.7898738706503265,
"grad_norm": 0.39127156138420105,
"learning_rate": 2e-05,
"loss": 0.7995,
"step": 8830
},
{
"epoch": 0.790768405045174,
"grad_norm": 0.3970036804676056,
"learning_rate": 2e-05,
"loss": 0.8177,
"step": 8840
},
{
"epoch": 0.7916629394400214,
"grad_norm": 0.4345267415046692,
"learning_rate": 2e-05,
"loss": 0.8107,
"step": 8850
},
{
"epoch": 0.792557473834869,
"grad_norm": 0.4030192792415619,
"learning_rate": 2e-05,
"loss": 0.811,
"step": 8860
},
{
"epoch": 0.7934520082297164,
"grad_norm": 0.39985257387161255,
"learning_rate": 2e-05,
"loss": 0.8043,
"step": 8870
},
{
"epoch": 0.794346542624564,
"grad_norm": 0.41247808933258057,
"learning_rate": 2e-05,
"loss": 0.8032,
"step": 8880
},
{
"epoch": 0.7952410770194114,
"grad_norm": 0.39995160698890686,
"learning_rate": 2e-05,
"loss": 0.8346,
"step": 8890
},
{
"epoch": 0.7961356114142589,
"grad_norm": 0.468544065952301,
"learning_rate": 2e-05,
"loss": 0.7943,
"step": 8900
},
{
"epoch": 0.7970301458091064,
"grad_norm": 0.42242684960365295,
"learning_rate": 2e-05,
"loss": 0.7974,
"step": 8910
},
{
"epoch": 0.7979246802039538,
"grad_norm": 0.4119330048561096,
"learning_rate": 2e-05,
"loss": 0.7895,
"step": 8920
},
{
"epoch": 0.7988192145988013,
"grad_norm": 0.41047221422195435,
"learning_rate": 2e-05,
"loss": 0.8204,
"step": 8930
},
{
"epoch": 0.7997137489936488,
"grad_norm": 0.4078488349914551,
"learning_rate": 2e-05,
"loss": 0.8102,
"step": 8940
},
{
"epoch": 0.8006082833884963,
"grad_norm": 0.40713298320770264,
"learning_rate": 2e-05,
"loss": 0.8108,
"step": 8950
},
{
"epoch": 0.8015028177833438,
"grad_norm": 0.41238003969192505,
"learning_rate": 2e-05,
"loss": 0.8073,
"step": 8960
},
{
"epoch": 0.8023973521781913,
"grad_norm": 0.4073646068572998,
"learning_rate": 2e-05,
"loss": 0.8082,
"step": 8970
},
{
"epoch": 0.8032918865730387,
"grad_norm": 0.3946633040904999,
"learning_rate": 2e-05,
"loss": 0.8088,
"step": 8980
},
{
"epoch": 0.8041864209678862,
"grad_norm": 0.40976259112358093,
"learning_rate": 2e-05,
"loss": 0.8242,
"step": 8990
},
{
"epoch": 0.8050809553627337,
"grad_norm": 0.3919033408164978,
"learning_rate": 2e-05,
"loss": 0.7878,
"step": 9000
},
{
"epoch": 0.8059754897575812,
"grad_norm": 0.42108699679374695,
"learning_rate": 2e-05,
"loss": 0.7784,
"step": 9010
},
{
"epoch": 0.8068700241524287,
"grad_norm": 0.41512513160705566,
"learning_rate": 2e-05,
"loss": 0.7946,
"step": 9020
},
{
"epoch": 0.8077645585472761,
"grad_norm": 0.41406333446502686,
"learning_rate": 2e-05,
"loss": 0.8026,
"step": 9030
},
{
"epoch": 0.8086590929421236,
"grad_norm": 0.39251622557640076,
"learning_rate": 2e-05,
"loss": 0.7895,
"step": 9040
},
{
"epoch": 0.8095536273369711,
"grad_norm": 0.4009459316730499,
"learning_rate": 2e-05,
"loss": 0.7849,
"step": 9050
},
{
"epoch": 0.8104481617318186,
"grad_norm": 0.4119388163089752,
"learning_rate": 2e-05,
"loss": 0.7957,
"step": 9060
},
{
"epoch": 0.8113426961266661,
"grad_norm": 0.4085330367088318,
"learning_rate": 2e-05,
"loss": 0.7923,
"step": 9070
},
{
"epoch": 0.8122372305215135,
"grad_norm": 0.4566907584667206,
"learning_rate": 2e-05,
"loss": 0.7999,
"step": 9080
},
{
"epoch": 0.8131317649163611,
"grad_norm": 0.3861619830131531,
"learning_rate": 2e-05,
"loss": 0.8103,
"step": 9090
},
{
"epoch": 0.8140262993112085,
"grad_norm": 0.40000587701797485,
"learning_rate": 2e-05,
"loss": 0.8074,
"step": 9100
},
{
"epoch": 0.814920833706056,
"grad_norm": 0.41271087527275085,
"learning_rate": 2e-05,
"loss": 0.7676,
"step": 9110
},
{
"epoch": 0.8158153681009035,
"grad_norm": 0.42897579073905945,
"learning_rate": 2e-05,
"loss": 0.7906,
"step": 9120
},
{
"epoch": 0.8167099024957509,
"grad_norm": 0.40415453910827637,
"learning_rate": 2e-05,
"loss": 0.8119,
"step": 9130
},
{
"epoch": 0.8176044368905985,
"grad_norm": 0.40211018919944763,
"learning_rate": 2e-05,
"loss": 0.7821,
"step": 9140
},
{
"epoch": 0.8184989712854459,
"grad_norm": 0.4081565737724304,
"learning_rate": 2e-05,
"loss": 0.7899,
"step": 9150
},
{
"epoch": 0.8193935056802935,
"grad_norm": 0.3916639983654022,
"learning_rate": 2e-05,
"loss": 0.8131,
"step": 9160
},
{
"epoch": 0.8202880400751409,
"grad_norm": 0.4301687180995941,
"learning_rate": 2e-05,
"loss": 0.7832,
"step": 9170
},
{
"epoch": 0.8211825744699883,
"grad_norm": 0.4468179941177368,
"learning_rate": 2e-05,
"loss": 0.8046,
"step": 9180
},
{
"epoch": 0.8220771088648359,
"grad_norm": 0.4290895164012909,
"learning_rate": 2e-05,
"loss": 0.8342,
"step": 9190
},
{
"epoch": 0.8229716432596833,
"grad_norm": 0.44506120681762695,
"learning_rate": 2e-05,
"loss": 0.8168,
"step": 9200
},
{
"epoch": 0.8238661776545309,
"grad_norm": 0.4138713479042053,
"learning_rate": 2e-05,
"loss": 0.7929,
"step": 9210
},
{
"epoch": 0.8247607120493783,
"grad_norm": 0.4156189262866974,
"learning_rate": 2e-05,
"loss": 0.8314,
"step": 9220
},
{
"epoch": 0.8256552464442258,
"grad_norm": 0.4113473892211914,
"learning_rate": 2e-05,
"loss": 0.7659,
"step": 9230
},
{
"epoch": 0.8265497808390733,
"grad_norm": 0.4080910384654999,
"learning_rate": 2e-05,
"loss": 0.8052,
"step": 9240
},
{
"epoch": 0.8274443152339207,
"grad_norm": 0.41655945777893066,
"learning_rate": 2e-05,
"loss": 0.7997,
"step": 9250
},
{
"epoch": 0.8283388496287682,
"grad_norm": 0.40191036462783813,
"learning_rate": 2e-05,
"loss": 0.8103,
"step": 9260
},
{
"epoch": 0.8292333840236157,
"grad_norm": 0.39463943243026733,
"learning_rate": 2e-05,
"loss": 0.7962,
"step": 9270
},
{
"epoch": 0.8301279184184632,
"grad_norm": 0.40958184003829956,
"learning_rate": 2e-05,
"loss": 0.8171,
"step": 9280
},
{
"epoch": 0.8310224528133107,
"grad_norm": 0.3833797574043274,
"learning_rate": 2e-05,
"loss": 0.8,
"step": 9290
},
{
"epoch": 0.8319169872081581,
"grad_norm": 0.4075131416320801,
"learning_rate": 2e-05,
"loss": 0.7875,
"step": 9300
},
{
"epoch": 0.8328115216030056,
"grad_norm": 0.43667423725128174,
"learning_rate": 2e-05,
"loss": 0.8074,
"step": 9310
},
{
"epoch": 0.8337060559978531,
"grad_norm": 0.4032801389694214,
"learning_rate": 2e-05,
"loss": 0.7967,
"step": 9320
},
{
"epoch": 0.8346005903927006,
"grad_norm": 0.40782514214515686,
"learning_rate": 2e-05,
"loss": 0.8026,
"step": 9330
},
{
"epoch": 0.8354951247875481,
"grad_norm": 0.42317259311676025,
"learning_rate": 2e-05,
"loss": 0.815,
"step": 9340
},
{
"epoch": 0.8363896591823956,
"grad_norm": 0.41793304681777954,
"learning_rate": 2e-05,
"loss": 0.7936,
"step": 9350
},
{
"epoch": 0.837284193577243,
"grad_norm": 0.42689675092697144,
"learning_rate": 2e-05,
"loss": 0.8237,
"step": 9360
},
{
"epoch": 0.8381787279720905,
"grad_norm": 0.41917455196380615,
"learning_rate": 2e-05,
"loss": 0.8163,
"step": 9370
},
{
"epoch": 0.839073262366938,
"grad_norm": 0.4138127863407135,
"learning_rate": 2e-05,
"loss": 0.804,
"step": 9380
},
{
"epoch": 0.8399677967617855,
"grad_norm": 0.4061967730522156,
"learning_rate": 2e-05,
"loss": 0.7989,
"step": 9390
},
{
"epoch": 0.840862331156633,
"grad_norm": 0.41995999217033386,
"learning_rate": 2e-05,
"loss": 0.7901,
"step": 9400
},
{
"epoch": 0.8417568655514804,
"grad_norm": 0.4823813736438751,
"learning_rate": 2e-05,
"loss": 0.8088,
"step": 9410
},
{
"epoch": 0.842651399946328,
"grad_norm": 0.3967750668525696,
"learning_rate": 2e-05,
"loss": 0.7972,
"step": 9420
},
{
"epoch": 0.8435459343411754,
"grad_norm": 0.42522183060646057,
"learning_rate": 2e-05,
"loss": 0.7985,
"step": 9430
},
{
"epoch": 0.8444404687360229,
"grad_norm": 0.4333302080631256,
"learning_rate": 2e-05,
"loss": 0.806,
"step": 9440
},
{
"epoch": 0.8453350031308704,
"grad_norm": 0.43844830989837646,
"learning_rate": 2e-05,
"loss": 0.7953,
"step": 9450
},
{
"epoch": 0.8462295375257178,
"grad_norm": 0.41072431206703186,
"learning_rate": 2e-05,
"loss": 0.7859,
"step": 9460
},
{
"epoch": 0.8471240719205654,
"grad_norm": 0.4005672037601471,
"learning_rate": 2e-05,
"loss": 0.7941,
"step": 9470
},
{
"epoch": 0.8480186063154128,
"grad_norm": 0.4260163903236389,
"learning_rate": 2e-05,
"loss": 0.7918,
"step": 9480
},
{
"epoch": 0.8489131407102604,
"grad_norm": 0.4085536301136017,
"learning_rate": 2e-05,
"loss": 0.7867,
"step": 9490
},
{
"epoch": 0.8498076751051078,
"grad_norm": 0.4217403531074524,
"learning_rate": 2e-05,
"loss": 0.8014,
"step": 9500
},
{
"epoch": 0.8507022094999552,
"grad_norm": 0.4104573726654053,
"learning_rate": 2e-05,
"loss": 0.7892,
"step": 9510
},
{
"epoch": 0.8515967438948028,
"grad_norm": 0.40049198269844055,
"learning_rate": 2e-05,
"loss": 0.8007,
"step": 9520
},
{
"epoch": 0.8524912782896502,
"grad_norm": 0.40141692757606506,
"learning_rate": 2e-05,
"loss": 0.7904,
"step": 9530
},
{
"epoch": 0.8533858126844978,
"grad_norm": 0.4304947853088379,
"learning_rate": 2e-05,
"loss": 0.8156,
"step": 9540
},
{
"epoch": 0.8542803470793452,
"grad_norm": 0.4269062280654907,
"learning_rate": 2e-05,
"loss": 0.8107,
"step": 9550
},
{
"epoch": 0.8551748814741926,
"grad_norm": 0.423477441072464,
"learning_rate": 2e-05,
"loss": 0.8022,
"step": 9560
},
{
"epoch": 0.8560694158690402,
"grad_norm": 0.41677993535995483,
"learning_rate": 2e-05,
"loss": 0.8015,
"step": 9570
},
{
"epoch": 0.8569639502638876,
"grad_norm": 0.4094560146331787,
"learning_rate": 2e-05,
"loss": 0.7921,
"step": 9580
},
{
"epoch": 0.8578584846587352,
"grad_norm": 0.4014447033405304,
"learning_rate": 2e-05,
"loss": 0.7723,
"step": 9590
},
{
"epoch": 0.8587530190535826,
"grad_norm": 0.3942165970802307,
"learning_rate": 2e-05,
"loss": 0.7994,
"step": 9600
},
{
"epoch": 0.8596475534484301,
"grad_norm": 0.44933682680130005,
"learning_rate": 2e-05,
"loss": 0.7849,
"step": 9610
},
{
"epoch": 0.8605420878432776,
"grad_norm": 0.4162166714668274,
"learning_rate": 2e-05,
"loss": 0.7989,
"step": 9620
},
{
"epoch": 0.861436622238125,
"grad_norm": 0.3895867168903351,
"learning_rate": 2e-05,
"loss": 0.7914,
"step": 9630
},
{
"epoch": 0.8623311566329726,
"grad_norm": 0.40665486454963684,
"learning_rate": 2e-05,
"loss": 0.8053,
"step": 9640
},
{
"epoch": 0.86322569102782,
"grad_norm": 0.4157429039478302,
"learning_rate": 2e-05,
"loss": 0.8034,
"step": 9650
},
{
"epoch": 0.8641202254226675,
"grad_norm": 0.4088215231895447,
"learning_rate": 2e-05,
"loss": 0.8113,
"step": 9660
},
{
"epoch": 0.865014759817515,
"grad_norm": 0.3911498486995697,
"learning_rate": 2e-05,
"loss": 0.8017,
"step": 9670
},
{
"epoch": 0.8659092942123625,
"grad_norm": 0.4243428111076355,
"learning_rate": 2e-05,
"loss": 0.8188,
"step": 9680
},
{
"epoch": 0.86680382860721,
"grad_norm": 0.4083731174468994,
"learning_rate": 2e-05,
"loss": 0.8238,
"step": 9690
},
{
"epoch": 0.8676983630020574,
"grad_norm": 0.42192342877388,
"learning_rate": 2e-05,
"loss": 0.8178,
"step": 9700
},
{
"epoch": 0.8685928973969049,
"grad_norm": 0.4085046052932739,
"learning_rate": 2e-05,
"loss": 0.8031,
"step": 9710
},
{
"epoch": 0.8694874317917524,
"grad_norm": 0.4100043475627899,
"learning_rate": 2e-05,
"loss": 0.8009,
"step": 9720
},
{
"epoch": 0.8703819661865999,
"grad_norm": 0.40045925974845886,
"learning_rate": 2e-05,
"loss": 0.8086,
"step": 9730
},
{
"epoch": 0.8712765005814473,
"grad_norm": 0.4051165282726288,
"learning_rate": 2e-05,
"loss": 0.8092,
"step": 9740
},
{
"epoch": 0.8721710349762949,
"grad_norm": 0.44314494729042053,
"learning_rate": 2e-05,
"loss": 0.8086,
"step": 9750
},
{
"epoch": 0.8730655693711423,
"grad_norm": 0.4086655378341675,
"learning_rate": 2e-05,
"loss": 0.8025,
"step": 9760
},
{
"epoch": 0.8739601037659898,
"grad_norm": 0.40157368779182434,
"learning_rate": 2e-05,
"loss": 0.8079,
"step": 9770
},
{
"epoch": 0.8748546381608373,
"grad_norm": 0.4612876772880554,
"learning_rate": 2e-05,
"loss": 0.7964,
"step": 9780
},
{
"epoch": 0.8757491725556847,
"grad_norm": 0.6778886914253235,
"learning_rate": 2e-05,
"loss": 0.7888,
"step": 9790
},
{
"epoch": 0.8766437069505323,
"grad_norm": 0.39757344126701355,
"learning_rate": 2e-05,
"loss": 0.8099,
"step": 9800
},
{
"epoch": 0.8775382413453797,
"grad_norm": 0.40263235569000244,
"learning_rate": 2e-05,
"loss": 0.8215,
"step": 9810
},
{
"epoch": 0.8784327757402272,
"grad_norm": 0.40354594588279724,
"learning_rate": 2e-05,
"loss": 0.7957,
"step": 9820
},
{
"epoch": 0.8793273101350747,
"grad_norm": 0.40376466512680054,
"learning_rate": 2e-05,
"loss": 0.808,
"step": 9830
},
{
"epoch": 0.8802218445299221,
"grad_norm": 0.4262758493423462,
"learning_rate": 2e-05,
"loss": 0.8055,
"step": 9840
},
{
"epoch": 0.8811163789247697,
"grad_norm": 0.40980347990989685,
"learning_rate": 2e-05,
"loss": 0.7961,
"step": 9850
},
{
"epoch": 0.8820109133196171,
"grad_norm": 0.4027796983718872,
"learning_rate": 2e-05,
"loss": 0.7181,
"step": 9860
},
{
"epoch": 0.8829054477144647,
"grad_norm": 0.4226361811161041,
"learning_rate": 2e-05,
"loss": 0.8061,
"step": 9870
},
{
"epoch": 0.8837999821093121,
"grad_norm": 0.41341036558151245,
"learning_rate": 2e-05,
"loss": 0.8066,
"step": 9880
},
{
"epoch": 0.8846945165041595,
"grad_norm": 0.38552162051200867,
"learning_rate": 2e-05,
"loss": 0.7879,
"step": 9890
},
{
"epoch": 0.8855890508990071,
"grad_norm": 0.4181029498577118,
"learning_rate": 2e-05,
"loss": 0.8101,
"step": 9900
},
{
"epoch": 0.8864835852938545,
"grad_norm": 0.4152522683143616,
"learning_rate": 2e-05,
"loss": 0.7946,
"step": 9910
},
{
"epoch": 0.8873781196887021,
"grad_norm": 0.40568605065345764,
"learning_rate": 2e-05,
"loss": 0.7948,
"step": 9920
},
{
"epoch": 0.8882726540835495,
"grad_norm": 0.40510791540145874,
"learning_rate": 2e-05,
"loss": 0.7992,
"step": 9930
},
{
"epoch": 0.889167188478397,
"grad_norm": 0.41713112592697144,
"learning_rate": 2e-05,
"loss": 0.7983,
"step": 9940
},
{
"epoch": 0.8900617228732445,
"grad_norm": 0.44775959849357605,
"learning_rate": 2e-05,
"loss": 0.8094,
"step": 9950
},
{
"epoch": 0.8909562572680919,
"grad_norm": 0.3833668529987335,
"learning_rate": 2e-05,
"loss": 0.8058,
"step": 9960
},
{
"epoch": 0.8918507916629395,
"grad_norm": 0.402144193649292,
"learning_rate": 2e-05,
"loss": 0.8017,
"step": 9970
},
{
"epoch": 0.8927453260577869,
"grad_norm": 0.4162628650665283,
"learning_rate": 2e-05,
"loss": 0.8048,
"step": 9980
},
{
"epoch": 0.8936398604526344,
"grad_norm": 0.48505809903144836,
"learning_rate": 2e-05,
"loss": 0.814,
"step": 9990
},
{
"epoch": 0.8945343948474819,
"grad_norm": 0.3965017795562744,
"learning_rate": 2e-05,
"loss": 0.7811,
"step": 10000
},
{
"epoch": 0.8954289292423294,
"grad_norm": 0.4107840061187744,
"learning_rate": 2e-05,
"loss": 0.7764,
"step": 10010
},
{
"epoch": 0.8963234636371769,
"grad_norm": 0.40887635946273804,
"learning_rate": 2e-05,
"loss": 0.8146,
"step": 10020
},
{
"epoch": 0.8972179980320243,
"grad_norm": 0.6916907429695129,
"learning_rate": 2e-05,
"loss": 0.805,
"step": 10030
},
{
"epoch": 0.8981125324268718,
"grad_norm": 0.4452870488166809,
"learning_rate": 2e-05,
"loss": 0.7951,
"step": 10040
},
{
"epoch": 0.8990070668217193,
"grad_norm": 0.40345507860183716,
"learning_rate": 2e-05,
"loss": 0.8325,
"step": 10050
},
{
"epoch": 0.8999016012165668,
"grad_norm": 0.411654531955719,
"learning_rate": 2e-05,
"loss": 0.8227,
"step": 10060
},
{
"epoch": 0.9007961356114143,
"grad_norm": 0.3914259672164917,
"learning_rate": 2e-05,
"loss": 0.7979,
"step": 10070
},
{
"epoch": 0.9016906700062617,
"grad_norm": 0.4226438105106354,
"learning_rate": 2e-05,
"loss": 0.8181,
"step": 10080
},
{
"epoch": 0.9025852044011092,
"grad_norm": 0.40700963139533997,
"learning_rate": 2e-05,
"loss": 0.8008,
"step": 10090
},
{
"epoch": 0.9034797387959567,
"grad_norm": 0.443543940782547,
"learning_rate": 2e-05,
"loss": 0.8009,
"step": 10100
},
{
"epoch": 0.9043742731908042,
"grad_norm": 0.5130864381790161,
"learning_rate": 2e-05,
"loss": 0.7808,
"step": 10110
},
{
"epoch": 0.9052688075856516,
"grad_norm": 0.41374361515045166,
"learning_rate": 2e-05,
"loss": 0.7958,
"step": 10120
},
{
"epoch": 0.9061633419804992,
"grad_norm": 0.4013523757457733,
"learning_rate": 2e-05,
"loss": 0.8286,
"step": 10130
},
{
"epoch": 0.9070578763753466,
"grad_norm": 0.39789554476737976,
"learning_rate": 2e-05,
"loss": 0.7901,
"step": 10140
},
{
"epoch": 0.9079524107701941,
"grad_norm": 0.4110311269760132,
"learning_rate": 2e-05,
"loss": 0.8167,
"step": 10150
},
{
"epoch": 0.9088469451650416,
"grad_norm": 0.3805530369281769,
"learning_rate": 2e-05,
"loss": 0.7877,
"step": 10160
},
{
"epoch": 0.909741479559889,
"grad_norm": 0.4392894208431244,
"learning_rate": 2e-05,
"loss": 0.8098,
"step": 10170
},
{
"epoch": 0.9106360139547366,
"grad_norm": 0.41831013560295105,
"learning_rate": 1.999957358086795e-05,
"loss": 0.7789,
"step": 10180
},
{
"epoch": 0.911530548349584,
"grad_norm": 0.5079995393753052,
"learning_rate": 1.9991993813020483e-05,
"loss": 0.7979,
"step": 10190
},
{
"epoch": 0.9124250827444316,
"grad_norm": 0.42399561405181885,
"learning_rate": 1.9974946373028628e-05,
"loss": 0.79,
"step": 10200
},
{
"epoch": 0.913319617139279,
"grad_norm": 0.4186520278453827,
"learning_rate": 1.994844749501764e-05,
"loss": 0.8101,
"step": 10210
},
{
"epoch": 0.9142141515341264,
"grad_norm": 0.3986724317073822,
"learning_rate": 1.9912522413632988e-05,
"loss": 0.7755,
"step": 10220
},
{
"epoch": 0.915108685928974,
"grad_norm": 0.4643847942352295,
"learning_rate": 1.9867205340009656e-05,
"loss": 0.7972,
"step": 10230
},
{
"epoch": 0.9160032203238214,
"grad_norm": 0.39945170283317566,
"learning_rate": 1.9812539429193164e-05,
"loss": 0.788,
"step": 10240
},
{
"epoch": 0.916897754718669,
"grad_norm": 0.4100631773471832,
"learning_rate": 1.9748576739043423e-05,
"loss": 0.7874,
"step": 10250
},
{
"epoch": 0.9177922891135164,
"grad_norm": 0.45851850509643555,
"learning_rate": 1.967537818066047e-05,
"loss": 0.7902,
"step": 10260
},
{
"epoch": 0.918686823508364,
"grad_norm": 0.3962000608444214,
"learning_rate": 1.959301346037941e-05,
"loss": 0.8049,
"step": 10270
},
{
"epoch": 0.9195813579032114,
"grad_norm": 0.4065761864185333,
"learning_rate": 1.9501561013389646e-05,
"loss": 0.7913,
"step": 10280
},
{
"epoch": 0.9204758922980588,
"grad_norm": 0.430561363697052,
"learning_rate": 1.9401107929041795e-05,
"loss": 0.8102,
"step": 10290
},
{
"epoch": 0.9213704266929064,
"grad_norm": 0.44964852929115295,
"learning_rate": 1.9291749867913225e-05,
"loss": 0.7977,
"step": 10300
},
{
"epoch": 0.9222649610877538,
"grad_norm": 0.43178752064704895,
"learning_rate": 1.91735909707114e-05,
"loss": 0.7988,
"step": 10310
},
{
"epoch": 0.9231594954826013,
"grad_norm": 0.40959179401397705,
"learning_rate": 1.9046743759101545e-05,
"loss": 0.7932,
"step": 10320
},
{
"epoch": 0.9240540298774488,
"grad_norm": 0.4233705997467041,
"learning_rate": 1.8911329028553324e-05,
"loss": 0.7922,
"step": 10330
},
{
"epoch": 0.9249485642722963,
"grad_norm": 0.38121169805526733,
"learning_rate": 1.876747573330835e-05,
"loss": 0.783,
"step": 10340
},
{
"epoch": 0.9258430986671438,
"grad_norm": 0.39084741473197937,
"learning_rate": 1.8615320863578244e-05,
"loss": 0.8046,
"step": 10350
},
{
"epoch": 0.9267376330619912,
"grad_norm": 0.38831624388694763,
"learning_rate": 1.8455009315090036e-05,
"loss": 0.7799,
"step": 10360
},
{
"epoch": 0.9276321674568387,
"grad_norm": 0.40661489963531494,
"learning_rate": 1.8286693751103294e-05,
"loss": 0.7958,
"step": 10370
},
{
"epoch": 0.9285267018516862,
"grad_norm": 0.39345505833625793,
"learning_rate": 1.811053445703024e-05,
"loss": 0.798,
"step": 10380
},
{
"epoch": 0.9294212362465337,
"grad_norm": 0.3949539363384247,
"learning_rate": 1.7926699187797375e-05,
"loss": 0.7945,
"step": 10390
},
{
"epoch": 0.9303157706413812,
"grad_norm": 0.4265754818916321,
"learning_rate": 1.7735363008093995e-05,
"loss": 0.7931,
"step": 10400
},
{
"epoch": 0.9312103050362286,
"grad_norm": 0.5953425168991089,
"learning_rate": 1.7536708125659577e-05,
"loss": 0.8059,
"step": 10410
},
{
"epoch": 0.9321048394310761,
"grad_norm": 0.40443354845046997,
"learning_rate": 1.733092371776905e-05,
"loss": 0.7955,
"step": 10420
},
{
"epoch": 0.9329993738259236,
"grad_norm": 0.4181784391403198,
"learning_rate": 1.7118205751080915e-05,
"loss": 0.7951,
"step": 10430
},
{
"epoch": 0.9338939082207711,
"grad_norm": 0.4302588105201721,
"learning_rate": 1.6898756795019935e-05,
"loss": 0.7944,
"step": 10440
},
{
"epoch": 0.9347884426156186,
"grad_norm": 0.38713979721069336,
"learning_rate": 1.667278582887211e-05,
"loss": 0.7737,
"step": 10450
},
{
"epoch": 0.9356829770104661,
"grad_norm": 0.38739466667175293,
"learning_rate": 1.6440508042775545e-05,
"loss": 0.775,
"step": 10460
},
{
"epoch": 0.9365775114053135,
"grad_norm": 0.40342336893081665,
"learning_rate": 1.6202144632796796e-05,
"loss": 0.8246,
"step": 10470
},
{
"epoch": 0.937472045800161,
"grad_norm": 0.4529002606868744,
"learning_rate": 1.595792259028783e-05,
"loss": 0.7995,
"step": 10480
},
{
"epoch": 0.9383665801950085,
"grad_norm": 0.4084119200706482,
"learning_rate": 1.570807448572419e-05,
"loss": 0.8079,
"step": 10490
},
{
"epoch": 0.939261114589856,
"grad_norm": 0.4093131124973297,
"learning_rate": 1.5452838247230197e-05,
"loss": 0.7701,
"step": 10500
},
{
"epoch": 0.9401556489847035,
"grad_norm": 0.42214351892471313,
"learning_rate": 1.5192456934002106e-05,
"loss": 0.7953,
"step": 10510
},
{
"epoch": 0.9410501833795509,
"grad_norm": 0.4307670295238495,
"learning_rate": 1.492717850484502e-05,
"loss": 0.7853,
"step": 10520
},
{
"epoch": 0.9419447177743985,
"grad_norm": 0.39015600085258484,
"learning_rate": 1.4657255582043904e-05,
"loss": 0.7972,
"step": 10530
},
{
"epoch": 0.9428392521692459,
"grad_norm": 0.3974817395210266,
"learning_rate": 1.4382945210793663e-05,
"loss": 0.7831,
"step": 10540
},
{
"epoch": 0.9437337865640933,
"grad_norm": 0.41717299818992615,
"learning_rate": 1.4104508614417267e-05,
"loss": 0.7929,
"step": 10550
},
{
"epoch": 0.9446283209589409,
"grad_norm": 0.3872585892677307,
"learning_rate": 1.382221094560512e-05,
"loss": 0.7835,
"step": 10560
},
{
"epoch": 0.9455228553537883,
"grad_norm": 0.4160507917404175,
"learning_rate": 1.3536321033912506e-05,
"loss": 0.7916,
"step": 10570
},
{
"epoch": 0.9464173897486359,
"grad_norm": 0.40326473116874695,
"learning_rate": 1.3247111129755609e-05,
"loss": 0.7779,
"step": 10580
},
{
"epoch": 0.9473119241434833,
"grad_norm": 0.39376524090766907,
"learning_rate": 1.2954856645149868e-05,
"loss": 0.7801,
"step": 10590
},
{
"epoch": 0.9482064585383309,
"grad_norm": 0.399444043636322,
"learning_rate": 1.2659835891437553e-05,
"loss": 0.7948,
"step": 10600
},
{
"epoch": 0.9491009929331783,
"grad_norm": 0.39917421340942383,
"learning_rate": 1.236232981425436e-05,
"loss": 0.8013,
"step": 10610
},
{
"epoch": 0.9499955273280257,
"grad_norm": 0.426316499710083,
"learning_rate": 1.2062621725987402e-05,
"loss": 0.7943,
"step": 10620
},
{
"epoch": 0.9508900617228733,
"grad_norm": 0.40278160572052,
"learning_rate": 1.1760997035979318e-05,
"loss": 0.8177,
"step": 10630
},
{
"epoch": 0.9517845961177207,
"grad_norm": 0.3994607925415039,
"learning_rate": 1.1457742978735514e-05,
"loss": 0.7877,
"step": 10640
},
{
"epoch": 0.9526791305125683,
"grad_norm": 0.39965105056762695,
"learning_rate": 1.1153148340393298e-05,
"loss": 0.7714,
"step": 10650
},
{
"epoch": 0.9535736649074157,
"grad_norm": 0.45205795764923096,
"learning_rate": 1.0847503183713424e-05,
"loss": 0.784,
"step": 10660
},
{
"epoch": 0.9544681993022631,
"grad_norm": 0.37542465329170227,
"learning_rate": 1.0541098571855896e-05,
"loss": 0.7742,
"step": 10670
},
{
"epoch": 0.9553627336971107,
"grad_norm": 0.42491087317466736,
"learning_rate": 1.0234226291203123e-05,
"loss": 0.7935,
"step": 10680
},
{
"epoch": 0.9562572680919581,
"grad_norm": 0.39044612646102905,
"learning_rate": 9.927178573494333e-06,
"loss": 0.7707,
"step": 10690
},
{
"epoch": 0.9571518024868056,
"grad_norm": 0.4195990264415741,
"learning_rate": 9.620247817535902e-06,
"loss": 0.7795,
"step": 10700
},
{
"epoch": 0.9580463368816531,
"grad_norm": 0.41163694858551025,
"learning_rate": 9.313726310752581e-06,
"loss": 0.7862,
"step": 10710
},
{
"epoch": 0.9589408712765006,
"grad_norm": 0.38126346468925476,
"learning_rate": 9.00790595084477e-06,
"loss": 0.7727,
"step": 10720
},
{
"epoch": 0.9598354056713481,
"grad_norm": 0.3894900679588318,
"learning_rate": 8.703077967816944e-06,
"loss": 0.7728,
"step": 10730
},
{
"epoch": 0.9607299400661955,
"grad_norm": 0.3957975506782532,
"learning_rate": 8.39953264664192e-06,
"loss": 0.787,
"step": 10740
},
{
"epoch": 0.961624474461043,
"grad_norm": 0.3912501335144043,
"learning_rate": 8.097559050825058e-06,
"loss": 0.7735,
"step": 10750
},
{
"epoch": 0.9625190088558905,
"grad_norm": 0.4231681823730469,
"learning_rate": 7.79744474713166e-06,
"loss": 0.7695,
"step": 10760
},
{
"epoch": 0.963413543250738,
"grad_norm": 0.39351552724838257,
"learning_rate": 7.499475531739696e-06,
"loss": 0.76,
"step": 10770
},
{
"epoch": 0.9643080776455855,
"grad_norm": 0.40175527334213257,
"learning_rate": 7.203935158078662e-06,
"loss": 0.7559,
"step": 10780
},
{
"epoch": 0.965202612040433,
"grad_norm": 0.44672691822052,
"learning_rate": 6.911105066613709e-06,
"loss": 0.7563,
"step": 10790
},
{
"epoch": 0.9660971464352804,
"grad_norm": 0.39074698090553284,
"learning_rate": 6.621264116832394e-06,
"loss": 0.7707,
"step": 10800
},
{
"epoch": 0.9669916808301279,
"grad_norm": 0.40112221240997314,
"learning_rate": 6.334688321689274e-06,
"loss": 0.7832,
"step": 10810
},
{
"epoch": 0.9678862152249754,
"grad_norm": 0.39769646525382996,
"learning_rate": 6.051650584761237e-06,
"loss": 0.7865,
"step": 10820
},
{
"epoch": 0.9687807496198229,
"grad_norm": 0.38688308000564575,
"learning_rate": 5.772420440363841e-06,
"loss": 0.7883,
"step": 10830
},
{
"epoch": 0.9696752840146704,
"grad_norm": 0.40065833926200867,
"learning_rate": 5.497263796876207e-06,
"loss": 0.7612,
"step": 10840
},
{
"epoch": 0.9705698184095178,
"grad_norm": 0.4035244882106781,
"learning_rate": 5.226442683518813e-06,
"loss": 0.7824,
"step": 10850
},
{
"epoch": 0.9714643528043654,
"grad_norm": 0.3741912543773651,
"learning_rate": 4.960215000825432e-06,
"loss": 0.7814,
"step": 10860
},
{
"epoch": 0.9723588871992128,
"grad_norm": 0.3867122232913971,
"learning_rate": 4.698834275046711e-06,
"loss": 0.787,
"step": 10870
},
{
"epoch": 0.9732534215940603,
"grad_norm": 0.42283132672309875,
"learning_rate": 4.442549416719423e-06,
"loss": 0.7474,
"step": 10880
},
{
"epoch": 0.9741479559889078,
"grad_norm": 0.3961840867996216,
"learning_rate": 4.1916044836311565e-06,
"loss": 0.7572,
"step": 10890
},
{
"epoch": 0.9750424903837552,
"grad_norm": 0.3689751923084259,
"learning_rate": 3.94623844840626e-06,
"loss": 0.7537,
"step": 10900
},
{
"epoch": 0.9759370247786028,
"grad_norm": 0.3921884596347809,
"learning_rate": 3.7066849709343467e-06,
"loss": 0.7572,
"step": 10910
},
{
"epoch": 0.9768315591734502,
"grad_norm": 0.3970646262168884,
"learning_rate": 3.473172175858059e-06,
"loss": 0.7886,
"step": 10920
},
{
"epoch": 0.9777260935682976,
"grad_norm": 0.41024208068847656,
"learning_rate": 3.2459224353320046e-06,
"loss": 0.7799,
"step": 10930
},
{
"epoch": 0.9786206279631452,
"grad_norm": 0.4044209420681,
"learning_rate": 3.025152157259735e-06,
"loss": 0.7923,
"step": 10940
},
{
"epoch": 0.9795151623579926,
"grad_norm": 0.41627100110054016,
"learning_rate": 2.811071579210425e-06,
"loss": 0.7568,
"step": 10950
},
{
"epoch": 0.9804096967528402,
"grad_norm": 0.3886393904685974,
"learning_rate": 2.603884568211513e-06,
"loss": 0.7823,
"step": 10960
},
{
"epoch": 0.9813042311476876,
"grad_norm": 0.38916870951652527,
"learning_rate": 2.4037884266079434e-06,
"loss": 0.753,
"step": 10970
},
{
"epoch": 0.9821987655425352,
"grad_norm": 0.366916686296463,
"learning_rate": 2.2109737041728955e-06,
"loss": 0.7599,
"step": 10980
},
{
"epoch": 0.9830932999373826,
"grad_norm": 0.3820417523384094,
"learning_rate": 2.0256240166489454e-06,
"loss": 0.7518,
"step": 10990
},
{
"epoch": 0.98398783433223,
"grad_norm": 0.4016690254211426,
"learning_rate": 1.847915870892413e-06,
"loss": 0.7777,
"step": 11000
},
{
"epoch": 0.9848823687270776,
"grad_norm": 0.42526599764823914,
"learning_rate": 1.6780184967874715e-06,
"loss": 0.7803,
"step": 11010
},
{
"epoch": 0.985776903121925,
"grad_norm": 0.4010556638240814,
"learning_rate": 1.5160936860900294e-06,
"loss": 0.7529,
"step": 11020
},
{
"epoch": 0.9866714375167726,
"grad_norm": 0.38847821950912476,
"learning_rate": 1.3622956383548762e-06,
"loss": 0.7761,
"step": 11030
},
{
"epoch": 0.98756597191162,
"grad_norm": 0.40093299746513367,
"learning_rate": 1.216770814092834e-06,
"loss": 0.7725,
"step": 11040
},
{
"epoch": 0.9884605063064675,
"grad_norm": 0.3731876611709595,
"learning_rate": 1.0796577952977013e-06,
"loss": 0.7465,
"step": 11050
},
{
"epoch": 0.989355040701315,
"grad_norm": 0.39313456416130066,
"learning_rate": 9.510871534758705e-07,
"loss": 0.7767,
"step": 11060
},
{
"epoch": 0.9902495750961624,
"grad_norm": 0.3929767906665802,
"learning_rate": 8.311813253042334e-07,
"loss": 0.7783,
"step": 11070
},
{
"epoch": 0.99114410949101,
"grad_norm": 0.39682626724243164,
"learning_rate": 7.200544960348308e-07,
"loss": 0.7751,
"step": 11080
},
{
"epoch": 0.9920386438858574,
"grad_norm": 0.3871004581451416,
"learning_rate": 6.178124907572545e-07,
"loss": 0.7768,
"step": 11090
},
{
"epoch": 0.9929331782807049,
"grad_norm": 0.3698189854621887,
"learning_rate": 5.245526736223528e-07,
"loss": 0.7771,
"step": 11100
},
{
"epoch": 0.9938277126755524,
"grad_norm": 0.4282488226890564,
"learning_rate": 4.403638551232205e-07,
"loss": 0.7776,
"step": 11110
},
{
"epoch": 0.9947222470703999,
"grad_norm": 0.41703957319259644,
"learning_rate": 3.6532620752175616e-07,
"loss": 0.7948,
"step": 11120
},
{
"epoch": 0.9956167814652473,
"grad_norm": 0.38908591866493225,
"learning_rate": 2.9951118850133247e-07,
"loss": 0.7674,
"step": 11130
},
{
"epoch": 0.9965113158600948,
"grad_norm": 0.3643728792667389,
"learning_rate": 2.429814731182774e-07,
"loss": 0.7677,
"step": 11140
},
{
"epoch": 0.9974058502549423,
"grad_norm": 0.4033120274543762,
"learning_rate": 1.957908941169813e-07,
"loss": 0.7632,
"step": 11150
},
{
"epoch": 0.9983003846497898,
"grad_norm": 0.3840574324131012,
"learning_rate": 1.5798439066545254e-07,
"loss": 0.7607,
"step": 11160
},
{
"epoch": 0.9991949190446373,
"grad_norm": 0.37100493907928467,
"learning_rate": 1.2959796556014471e-07,
"loss": 0.7931,
"step": 11170
},
{
"epoch": 1.0000894534394849,
"grad_norm": 0.3749045729637146,
"learning_rate": 1.1065865094081884e-07,
"loss": 0.7438,
"step": 11180
},
{
"epoch": 1.0009839878343323,
"grad_norm": 0.397793173789978,
"learning_rate": 1.011844825480734e-07,
"loss": 0.6805,
"step": 11190
},
{
"epoch": 1.0013418015922713,
"step": 11194,
"total_flos": 4.547514943786923e+19,
"train_loss": 0.004294461174822288,
"train_runtime": 605.7812,
"train_samples_per_second": 221.743,
"train_steps_per_second": 18.479
}
],
"logging_steps": 10,
"max_steps": 11194,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 159,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.547514943786923e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0013418015922713,
"eval_steps": 500,
"global_step": 11194,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0008945343948474819,
"grad_norm": 5.675168037414551,
"learning_rate": 1.1061797752808989e-06,
"loss": 2.1196,
"step": 10
},
{
"epoch": 0.0017890687896949637,
"grad_norm": 2.9707770347595215,
"learning_rate": 2.2241573033707866e-06,
"loss": 2.0311,
"step": 20
},
{
"epoch": 0.0026836031845424457,
"grad_norm": 1.5259026288986206,
"learning_rate": 3.342134831460675e-06,
"loss": 1.6404,
"step": 30
},
{
"epoch": 0.0035781375793899274,
"grad_norm": 0.9031808376312256,
"learning_rate": 4.4601123595505624e-06,
"loss": 1.4353,
"step": 40
},
{
"epoch": 0.00447267197423741,
"grad_norm": 0.7855185270309448,
"learning_rate": 5.5780898876404495e-06,
"loss": 1.2916,
"step": 50
},
{
"epoch": 0.005367206369084891,
"grad_norm": 0.7476404905319214,
"learning_rate": 6.6960674157303374e-06,
"loss": 1.1757,
"step": 60
},
{
"epoch": 0.006261740763932373,
"grad_norm": 0.7190150022506714,
"learning_rate": 7.814044943820226e-06,
"loss": 1.1344,
"step": 70
},
{
"epoch": 0.007156275158779855,
"grad_norm": 0.6955579519271851,
"learning_rate": 8.932022471910112e-06,
"loss": 1.0784,
"step": 80
},
{
"epoch": 0.008050809553627337,
"grad_norm": 0.613128662109375,
"learning_rate": 1.005e-05,
"loss": 1.0716,
"step": 90
},
{
"epoch": 0.00894534394847482,
"grad_norm": 0.6427867412567139,
"learning_rate": 1.1167977528089888e-05,
"loss": 1.0965,
"step": 100
},
{
"epoch": 0.009839878343322301,
"grad_norm": 0.6494929194450378,
"learning_rate": 1.2285955056179776e-05,
"loss": 1.0301,
"step": 110
},
{
"epoch": 0.010734412738169783,
"grad_norm": 0.656710684299469,
"learning_rate": 1.3403932584269664e-05,
"loss": 1.0766,
"step": 120
},
{
"epoch": 0.011628947133017264,
"grad_norm": 0.6478440165519714,
"learning_rate": 1.4521910112359552e-05,
"loss": 1.0263,