{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.5006709007961356,
"eval_steps": 500,
"global_step": 5597,
"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": 0.4198417365550995,
"learning_rate": 1.9999810479633703e-05,
"loss": 0.8129,
"step": 5090
},
{
"epoch": 0.4562125413722158,
"grad_norm": 0.4091585874557495,
"learning_rate": 1.997707677020786e-05,
"loss": 0.8406,
"step": 5100
},
{
"epoch": 0.4571070757670632,
"grad_norm": 0.4255719780921936,
"learning_rate": 1.9916538196124637e-05,
"loss": 0.8288,
"step": 5110
},
{
"epoch": 0.4580016101619107,
"grad_norm": 0.4284524917602539,
"learning_rate": 1.9818425303863402e-05,
"loss": 0.8433,
"step": 5120
},
{
"epoch": 0.4588961445567582,
"grad_norm": 0.43744298815727234,
"learning_rate": 1.9683111732582887e-05,
"loss": 0.8505,
"step": 5130
},
{
"epoch": 0.4597906789516057,
"grad_norm": 0.43323931097984314,
"learning_rate": 1.951111279120706e-05,
"loss": 0.8592,
"step": 5140
},
{
"epoch": 0.4606852133464532,
"grad_norm": 0.4522682726383209,
"learning_rate": 1.9303083495996028e-05,
"loss": 0.8414,
"step": 5150
},
{
"epoch": 0.46157974774130067,
"grad_norm": 0.459768146276474,
"learning_rate": 1.9059816076075482e-05,
"loss": 0.838,
"step": 5160
},
{
"epoch": 0.46247428213614816,
"grad_norm": 0.4178440272808075,
"learning_rate": 1.8782236956424142e-05,
"loss": 0.8268,
"step": 5170
},
{
"epoch": 0.4633688165309956,
"grad_norm": 0.4157670736312866,
"learning_rate": 1.8471403229808897e-05,
"loss": 0.8271,
"step": 5180
},
{
"epoch": 0.4642633509258431,
"grad_norm": 0.42142942547798157,
"learning_rate": 1.8128498631103333e-05,
"loss": 0.8274,
"step": 5190
},
{
"epoch": 0.4651578853206906,
"grad_norm": 0.4853789508342743,
"learning_rate": 1.7754829029320507e-05,
"loss": 0.8239,
"step": 5200
},
{
"epoch": 0.46605241971553807,
"grad_norm": 0.4462536573410034,
"learning_rate": 1.7351817454527473e-05,
"loss": 0.825,
"step": 5210
},
{
"epoch": 0.46694695411038556,
"grad_norm": 0.41904425621032715,
"learning_rate": 1.6920998678580345e-05,
"loss": 0.8444,
"step": 5220
},
{
"epoch": 0.46784148850523305,
"grad_norm": 0.43547630310058594,
"learning_rate": 1.6464013370317854e-05,
"loss": 0.8282,
"step": 5230
},
{
"epoch": 0.4687360229000805,
"grad_norm": 0.4280226528644562,
"learning_rate": 1.5982601847471915e-05,
"loss": 0.8462,
"step": 5240
},
{
"epoch": 0.469630557294928,
"grad_norm": 0.44293949007987976,
"learning_rate": 1.5478597449089553e-05,
"loss": 0.8138,
"step": 5250
},
{
"epoch": 0.47052509168977547,
"grad_norm": 0.4177446663379669,
"learning_rate": 1.4953919553705725e-05,
"loss": 0.8287,
"step": 5260
},
{
"epoch": 0.47141962608462296,
"grad_norm": 0.44968298077583313,
"learning_rate": 1.441056626985559e-05,
"loss": 0.8305,
"step": 5270
},
{
"epoch": 0.47231416047947045,
"grad_norm": 0.4061439335346222,
"learning_rate": 1.3850606826762668e-05,
"loss": 0.8249,
"step": 5280
},
{
"epoch": 0.47320869487431794,
"grad_norm": 0.4486444294452667,
"learning_rate": 1.3276173694181128e-05,
"loss": 0.8547,
"step": 5290
},
{
"epoch": 0.4741032292691654,
"grad_norm": 0.41771551966667175,
"learning_rate": 1.2689454461401822e-05,
"loss": 0.8173,
"step": 5300
},
{
"epoch": 0.47499776366401286,
"grad_norm": 0.42049357295036316,
"learning_rate": 1.2092683506348939e-05,
"loss": 0.8526,
"step": 5310
},
{
"epoch": 0.47589229805886035,
"grad_norm": 0.3955737352371216,
"learning_rate": 1.14881334864935e-05,
"loss": 0.8224,
"step": 5320
},
{
"epoch": 0.47678683245370784,
"grad_norm": 0.44216734170913696,
"learning_rate": 1.0878106683988481e-05,
"loss": 0.8637,
"step": 5330
},
{
"epoch": 0.47768136684855533,
"grad_norm": 0.44926923513412476,
"learning_rate": 1.026492623798551e-05,
"loss": 0.8406,
"step": 5340
},
{
"epoch": 0.4785759012434028,
"grad_norm": 0.40056657791137695,
"learning_rate": 9.650927297522743e-06,
"loss": 0.8103,
"step": 5350
},
{
"epoch": 0.4794704356382503,
"grad_norm": 0.4562889039516449,
"learning_rate": 9.038448128676012e-06,
"loss": 0.8398,
"step": 5360
},
{
"epoch": 0.48036497003309775,
"grad_norm": 0.4305453598499298,
"learning_rate": 8.42982120983949e-06,
"loss": 0.8423,
"step": 5370
},
{
"epoch": 0.48125950442794524,
"grad_norm": 0.4203610122203827,
"learning_rate": 7.827364349047303e-06,
"loss": 0.8354,
"step": 5380
},
{
"epoch": 0.48215403882279273,
"grad_norm": 0.4284190237522125,
"learning_rate": 7.233371857163706e-06,
"loss": 0.8382,
"step": 5390
},
{
"epoch": 0.4830485732176402,
"grad_norm": 0.38907209038734436,
"learning_rate": 6.650105810556492e-06,
"loss": 0.8002,
"step": 5400
},
{
"epoch": 0.4839431076124877,
"grad_norm": 0.4654206335544586,
"learning_rate": 6.079787436527681e-06,
"loss": 0.8328,
"step": 5410
},
{
"epoch": 0.4848376420073352,
"grad_norm": 0.4053092896938324,
"learning_rate": 5.524588654307961e-06,
"loss": 0.7919,
"step": 5420
},
{
"epoch": 0.4857321764021827,
"grad_norm": 0.39228886365890503,
"learning_rate": 4.986623803828985e-06,
"loss": 0.8072,
"step": 5430
},
{
"epoch": 0.4866267107970301,
"grad_norm": 0.3962017893791199,
"learning_rate": 4.467941593772423e-06,
"loss": 0.8275,
"step": 5440
},
{
"epoch": 0.4875212451918776,
"grad_norm": 0.39359042048454285,
"learning_rate": 3.9705172995597606e-06,
"loss": 0.8117,
"step": 5450
},
{
"epoch": 0.4884157795867251,
"grad_norm": 0.45149052143096924,
"learning_rate": 3.4962452409948346e-06,
"loss": 0.819,
"step": 5460
},
{
"epoch": 0.4893103139815726,
"grad_norm": 0.3883521258831024,
"learning_rate": 3.046931568206211e-06,
"loss": 0.8322,
"step": 5470
},
{
"epoch": 0.4902048483764201,
"grad_norm": 0.41358286142349243,
"learning_rate": 2.624287383362404e-06,
"loss": 0.823,
"step": 5480
},
{
"epoch": 0.4910993827712676,
"grad_norm": 0.40121743083000183,
"learning_rate": 2.2299222243541845e-06,
"loss": 0.8112,
"step": 5490
},
{
"epoch": 0.491993917166115,
"grad_norm": 0.4031897783279419,
"learning_rate": 1.8653379352598246e-06,
"loss": 0.8239,
"step": 5500
},
{
"epoch": 0.4928884515609625,
"grad_norm": 0.38571080565452576,
"learning_rate": 1.5319229469361075e-06,
"loss": 0.8202,
"step": 5510
},
{
"epoch": 0.49378298595581,
"grad_norm": 0.40710529685020447,
"learning_rate": 1.2309469895160917e-06,
"loss": 0.8385,
"step": 5520
},
{
"epoch": 0.4946775203506575,
"grad_norm": 0.38847389817237854,
"learning_rate": 9.635562569497974e-07,
"loss": 0.804,
"step": 5530
},
{
"epoch": 0.495572054745505,
"grad_norm": 0.38712096214294434,
"learning_rate": 7.307690420024867e-07,
"loss": 0.8424,
"step": 5540
},
{
"epoch": 0.49646658914035247,
"grad_norm": 0.4275812804698944,
"learning_rate": 5.334718583335942e-07,
"loss": 0.7923,
"step": 5550
},
{
"epoch": 0.49736112353519996,
"grad_norm": 0.42604172229766846,
"learning_rate": 3.7241606442442763e-07,
"loss": 0.8072,
"step": 5560
},
{
"epoch": 0.4982556579300474,
"grad_norm": 0.3994891047477722,
"learning_rate": 2.482150022115879e-07,
"loss": 0.8389,
"step": 5570
},
{
"epoch": 0.4991501923248949,
"grad_norm": 0.3870413899421692,
"learning_rate": 1.6134166132293174e-07,
"loss": 0.8272,
"step": 5580
},
{
"epoch": 0.5000447267197424,
"grad_norm": 0.4021168053150177,
"learning_rate": 1.1212687781127357e-07,
"loss": 0.8228,
"step": 5590
},
{
"epoch": 0.5006709007961356,
"step": 5597,
"total_flos": 2.2737574718397743e+19,
"train_loss": 0.027895621365684686,
"train_runtime": 1769.4654,
"train_samples_per_second": 37.957,
"train_steps_per_second": 3.163
}
],
"logging_steps": 10,
"max_steps": 5597,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 2.2737574718397743e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.5006709007961356,
"eval_steps": 500,
"global_step": 5597,
"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,