Chekpoint_PAD_end / trainer_state.json
nuresens's picture
Upload 12 files
c7a66a3 verified
Raw
History Blame Contribute Delete
344 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 1000,
"global_step": 18174,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0022009464069549906,
"grad_norm": 1.9078384637832642,
"learning_rate": 6.5934065934065935e-06,
"loss": 1.8816274642944335,
"step": 10
},
{
"epoch": 0.004401892813909981,
"grad_norm": 1.3476145267486572,
"learning_rate": 1.391941391941392e-05,
"loss": 1.7967029571533204,
"step": 20
},
{
"epoch": 0.006602839220864972,
"grad_norm": 1.170466423034668,
"learning_rate": 2.1245421245421246e-05,
"loss": 1.715524673461914,
"step": 30
},
{
"epoch": 0.008803785627819962,
"grad_norm": 1.3609683513641357,
"learning_rate": 2.857142857142857e-05,
"loss": 1.6288368225097656,
"step": 40
},
{
"epoch": 0.011004732034774953,
"grad_norm": 1.151696801185608,
"learning_rate": 3.58974358974359e-05,
"loss": 1.4956942558288575,
"step": 50
},
{
"epoch": 0.013205678441729944,
"grad_norm": 1.6291528940200806,
"learning_rate": 4.322344322344323e-05,
"loss": 1.3890839576721192,
"step": 60
},
{
"epoch": 0.015406624848684934,
"grad_norm": 1.4068406820297241,
"learning_rate": 5.054945054945055e-05,
"loss": 1.3895427703857421,
"step": 70
},
{
"epoch": 0.017607571255639925,
"grad_norm": 1.405369758605957,
"learning_rate": 5.787545787545788e-05,
"loss": 1.3423192977905274,
"step": 80
},
{
"epoch": 0.019808517662594914,
"grad_norm": 1.5128352642059326,
"learning_rate": 6.52014652014652e-05,
"loss": 1.2878559112548829,
"step": 90
},
{
"epoch": 0.022009464069549907,
"grad_norm": 1.572690486907959,
"learning_rate": 7.252747252747253e-05,
"loss": 1.2464408874511719,
"step": 100
},
{
"epoch": 0.024210410476504896,
"grad_norm": 1.610559105873108,
"learning_rate": 7.985347985347986e-05,
"loss": 1.2440325736999511,
"step": 110
},
{
"epoch": 0.02641135688345989,
"grad_norm": 1.573136806488037,
"learning_rate": 8.717948717948718e-05,
"loss": 1.1872939109802245,
"step": 120
},
{
"epoch": 0.02861230329041488,
"grad_norm": 1.6902788877487183,
"learning_rate": 9.450549450549451e-05,
"loss": 1.1642348289489746,
"step": 130
},
{
"epoch": 0.030813249697369868,
"grad_norm": 1.6654378175735474,
"learning_rate": 0.00010183150183150183,
"loss": 1.1244037628173829,
"step": 140
},
{
"epoch": 0.03301419610432486,
"grad_norm": 2.193235397338867,
"learning_rate": 0.00010915750915750915,
"loss": 1.1596935272216797,
"step": 150
},
{
"epoch": 0.03521514251127985,
"grad_norm": 1.470097541809082,
"learning_rate": 0.0001164835164835165,
"loss": 1.1412922859191894,
"step": 160
},
{
"epoch": 0.03741608891823484,
"grad_norm": 1.3646049499511719,
"learning_rate": 0.0001238095238095238,
"loss": 1.1341608047485352,
"step": 170
},
{
"epoch": 0.03961703532518983,
"grad_norm": 1.5164388418197632,
"learning_rate": 0.00013113553113553114,
"loss": 1.141274356842041,
"step": 180
},
{
"epoch": 0.04181798173214482,
"grad_norm": 1.47220778465271,
"learning_rate": 0.00013846153846153847,
"loss": 1.1136648178100585,
"step": 190
},
{
"epoch": 0.044018928139099814,
"grad_norm": 1.4043731689453125,
"learning_rate": 0.00014578754578754578,
"loss": 1.0726648330688477,
"step": 200
},
{
"epoch": 0.04621987454605481,
"grad_norm": 1.2634721994400024,
"learning_rate": 0.0001531135531135531,
"loss": 1.0866886138916017,
"step": 210
},
{
"epoch": 0.04842082095300979,
"grad_norm": 1.4036515951156616,
"learning_rate": 0.00016043956043956044,
"loss": 1.0939341545104981,
"step": 220
},
{
"epoch": 0.050621767359964785,
"grad_norm": 1.2421815395355225,
"learning_rate": 0.00016776556776556777,
"loss": 1.0299765586853027,
"step": 230
},
{
"epoch": 0.05282271376691978,
"grad_norm": 1.2714147567749023,
"learning_rate": 0.0001750915750915751,
"loss": 1.0197788238525392,
"step": 240
},
{
"epoch": 0.055023660173874764,
"grad_norm": 1.3632781505584717,
"learning_rate": 0.0001824175824175824,
"loss": 1.0711404800415039,
"step": 250
},
{
"epoch": 0.05722460658082976,
"grad_norm": 1.2990729808807373,
"learning_rate": 0.00018974358974358974,
"loss": 1.0572866439819335,
"step": 260
},
{
"epoch": 0.05942555298778475,
"grad_norm": 1.1432695388793945,
"learning_rate": 0.0001970695970695971,
"loss": 1.0353819847106933,
"step": 270
},
{
"epoch": 0.061626499394739735,
"grad_norm": 1.357786774635315,
"learning_rate": 0.00019999977137303472,
"loss": 1.0498096466064453,
"step": 280
},
{
"epoch": 0.06382744580169473,
"grad_norm": 1.2086237668991089,
"learning_rate": 0.0001999983742120326,
"loss": 0.9976873397827148,
"step": 290
},
{
"epoch": 0.06602839220864971,
"grad_norm": 1.2265594005584717,
"learning_rate": 0.00019999570692273363,
"loss": 1.0049219131469727,
"step": 300
},
{
"epoch": 0.0682293386156047,
"grad_norm": 1.7034281492233276,
"learning_rate": 0.00019999176953901636,
"loss": 1.0101943016052246,
"step": 310
},
{
"epoch": 0.0704302850225597,
"grad_norm": 1.1741327047348022,
"learning_rate": 0.0001999865621108914,
"loss": 1.0026937484741212,
"step": 320
},
{
"epoch": 0.07263123142951469,
"grad_norm": 1.14133882522583,
"learning_rate": 0.0001999800847045008,
"loss": 1.0280275344848633,
"step": 330
},
{
"epoch": 0.07483217783646968,
"grad_norm": 1.053797960281372,
"learning_rate": 0.0001999723374021174,
"loss": 0.9998103141784668,
"step": 340
},
{
"epoch": 0.07703312424342468,
"grad_norm": 1.3832306861877441,
"learning_rate": 0.00019996332030214337,
"loss": 1.0395806312561036,
"step": 350
},
{
"epoch": 0.07923407065037966,
"grad_norm": 1.145727515220642,
"learning_rate": 0.0001999530335191093,
"loss": 0.9548494338989257,
"step": 360
},
{
"epoch": 0.08143501705733465,
"grad_norm": 1.096012830734253,
"learning_rate": 0.00019994147718367276,
"loss": 0.9871329307556153,
"step": 370
},
{
"epoch": 0.08363596346428964,
"grad_norm": 0.9356358051300049,
"learning_rate": 0.0001999286514426163,
"loss": 0.9341530799865723,
"step": 380
},
{
"epoch": 0.08583690987124463,
"grad_norm": 1.4062135219573975,
"learning_rate": 0.00019991455645884605,
"loss": 0.9540111541748046,
"step": 390
},
{
"epoch": 0.08803785627819963,
"grad_norm": 1.0113333463668823,
"learning_rate": 0.00019989919241138925,
"loss": 0.9937296867370605,
"step": 400
},
{
"epoch": 0.09023880268515462,
"grad_norm": 1.0309836864471436,
"learning_rate": 0.00019988255949539215,
"loss": 0.9602716445922852,
"step": 410
},
{
"epoch": 0.09243974909210961,
"grad_norm": 1.089353084564209,
"learning_rate": 0.00019986465792211757,
"loss": 0.9335391998291016,
"step": 420
},
{
"epoch": 0.09464069549906459,
"grad_norm": 1.054080843925476,
"learning_rate": 0.0001998454879189422,
"loss": 0.9715407371520997,
"step": 430
},
{
"epoch": 0.09684164190601958,
"grad_norm": 1.2168610095977783,
"learning_rate": 0.00019982504972935357,
"loss": 0.9322951316833497,
"step": 440
},
{
"epoch": 0.09904258831297458,
"grad_norm": 0.985170304775238,
"learning_rate": 0.0001998033436129472,
"loss": 0.98055419921875,
"step": 450
},
{
"epoch": 0.10124353471992957,
"grad_norm": 1.1162617206573486,
"learning_rate": 0.00019978036984542307,
"loss": 0.9634963035583496,
"step": 460
},
{
"epoch": 0.10344448112688456,
"grad_norm": 1.0027767419815063,
"learning_rate": 0.00019975612871858222,
"loss": 0.9526361465454102,
"step": 470
},
{
"epoch": 0.10564542753383956,
"grad_norm": 0.9371089935302734,
"learning_rate": 0.0001997306205403231,
"loss": 0.9452459335327148,
"step": 480
},
{
"epoch": 0.10784637394079453,
"grad_norm": 0.9952771067619324,
"learning_rate": 0.00019970384563463753,
"loss": 0.95389404296875,
"step": 490
},
{
"epoch": 0.11004732034774953,
"grad_norm": 0.9913569092750549,
"learning_rate": 0.00019967580434160676,
"loss": 0.9630558013916015,
"step": 500
},
{
"epoch": 0.11224826675470452,
"grad_norm": 0.9107245802879333,
"learning_rate": 0.0001996464970173969,
"loss": 0.9158695220947266,
"step": 510
},
{
"epoch": 0.11444921316165951,
"grad_norm": 0.9648348093032837,
"learning_rate": 0.00019961592403425468,
"loss": 0.9289742469787597,
"step": 520
},
{
"epoch": 0.1166501595686145,
"grad_norm": 0.9094238877296448,
"learning_rate": 0.00019958408578050248,
"loss": 0.9172938346862793,
"step": 530
},
{
"epoch": 0.1188511059755695,
"grad_norm": 0.8862208127975464,
"learning_rate": 0.00019955098266053356,
"loss": 0.9405776023864746,
"step": 540
},
{
"epoch": 0.12105205238252449,
"grad_norm": 0.9264389872550964,
"learning_rate": 0.00019951661509480685,
"loss": 0.9399794578552246,
"step": 550
},
{
"epoch": 0.12325299878947947,
"grad_norm": 1.0130054950714111,
"learning_rate": 0.00019948098351984167,
"loss": 0.8720254898071289,
"step": 560
},
{
"epoch": 0.12545394519643446,
"grad_norm": 0.9762976765632629,
"learning_rate": 0.00019944408838821202,
"loss": 0.8954718589782715,
"step": 570
},
{
"epoch": 0.12765489160338947,
"grad_norm": 1.001057744026184,
"learning_rate": 0.00019940593016854106,
"loss": 0.8816336631774903,
"step": 580
},
{
"epoch": 0.12985583801034445,
"grad_norm": 0.9089824557304382,
"learning_rate": 0.000199366509345495,
"loss": 0.8785006523132324,
"step": 590
},
{
"epoch": 0.13205678441729943,
"grad_norm": 0.9821614027023315,
"learning_rate": 0.00019932582641977705,
"loss": 0.8629944801330567,
"step": 600
},
{
"epoch": 0.13425773082425443,
"grad_norm": 0.8690505027770996,
"learning_rate": 0.0001992838819081209,
"loss": 0.8856033325195313,
"step": 610
},
{
"epoch": 0.1364586772312094,
"grad_norm": 0.9993884563446045,
"learning_rate": 0.00019924067634328438,
"loss": 0.871296501159668,
"step": 620
},
{
"epoch": 0.13865962363816442,
"grad_norm": 0.9565812349319458,
"learning_rate": 0.0001991962102740425,
"loss": 0.8619088172912598,
"step": 630
},
{
"epoch": 0.1408605700451194,
"grad_norm": 1.0189067125320435,
"learning_rate": 0.00019915048426518054,
"loss": 0.927723503112793,
"step": 640
},
{
"epoch": 0.1430615164520744,
"grad_norm": 0.9605172872543335,
"learning_rate": 0.00019910349889748697,
"loss": 0.8939146041870117,
"step": 650
},
{
"epoch": 0.14526246285902938,
"grad_norm": 0.9558774828910828,
"learning_rate": 0.0001990552547677459,
"loss": 0.9257272720336914,
"step": 660
},
{
"epoch": 0.14746340926598436,
"grad_norm": 1.0276355743408203,
"learning_rate": 0.00019900575248872965,
"loss": 0.8982614517211914,
"step": 670
},
{
"epoch": 0.14966435567293937,
"grad_norm": 0.9114047288894653,
"learning_rate": 0.00019895499268919088,
"loss": 0.8813505172729492,
"step": 680
},
{
"epoch": 0.15186530207989435,
"grad_norm": 0.935661256313324,
"learning_rate": 0.0001989029760138547,
"loss": 0.8918737411499024,
"step": 690
},
{
"epoch": 0.15406624848684936,
"grad_norm": 1.042932152748108,
"learning_rate": 0.00019884970312341035,
"loss": 0.9151006698608398,
"step": 700
},
{
"epoch": 0.15626719489380433,
"grad_norm": 1.0090407133102417,
"learning_rate": 0.00019879517469450285,
"loss": 0.8846939086914063,
"step": 710
},
{
"epoch": 0.1584681413007593,
"grad_norm": 0.9468204379081726,
"learning_rate": 0.00019873939141972443,
"loss": 0.9109236717224121,
"step": 720
},
{
"epoch": 0.16066908770771432,
"grad_norm": 2.099306344985962,
"learning_rate": 0.00019868235400760588,
"loss": 0.8627537727355957,
"step": 730
},
{
"epoch": 0.1628700341146693,
"grad_norm": 1.030119776725769,
"learning_rate": 0.0001986240631826072,
"loss": 0.8754992485046387,
"step": 740
},
{
"epoch": 0.1650709805216243,
"grad_norm": 0.8489016890525818,
"learning_rate": 0.00019856451968510875,
"loss": 0.8639801025390625,
"step": 750
},
{
"epoch": 0.16727192692857928,
"grad_norm": 0.8956750631332397,
"learning_rate": 0.00019850372427140158,
"loss": 0.8864573478698731,
"step": 760
},
{
"epoch": 0.1694728733355343,
"grad_norm": 0.9865322113037109,
"learning_rate": 0.00019844167771367803,
"loss": 0.8492755889892578,
"step": 770
},
{
"epoch": 0.17167381974248927,
"grad_norm": 0.9670360088348389,
"learning_rate": 0.0001983783808000218,
"loss": 0.8892242431640625,
"step": 780
},
{
"epoch": 0.17387476614944425,
"grad_norm": 0.8764406442642212,
"learning_rate": 0.00019831383433439797,
"loss": 0.8339031219482422,
"step": 790
},
{
"epoch": 0.17607571255639926,
"grad_norm": 0.9101215600967407,
"learning_rate": 0.00019824803913664276,
"loss": 0.8599502563476562,
"step": 800
},
{
"epoch": 0.17827665896335423,
"grad_norm": 0.9051525592803955,
"learning_rate": 0.00019818099604245325,
"loss": 0.8466466903686524,
"step": 810
},
{
"epoch": 0.18047760537030924,
"grad_norm": 0.990511953830719,
"learning_rate": 0.00019811270590337654,
"loss": 0.8185970306396484,
"step": 820
},
{
"epoch": 0.18267855177726422,
"grad_norm": 0.8963238000869751,
"learning_rate": 0.00019804316958679913,
"loss": 0.8855241775512696,
"step": 830
},
{
"epoch": 0.18487949818421923,
"grad_norm": 0.9547941088676453,
"learning_rate": 0.00019797238797593578,
"loss": 0.8937933921813965,
"step": 840
},
{
"epoch": 0.1870804445911742,
"grad_norm": 1.0186196565628052,
"learning_rate": 0.00019790036196981842,
"loss": 0.8803288459777832,
"step": 850
},
{
"epoch": 0.18928139099812918,
"grad_norm": 0.8781481385231018,
"learning_rate": 0.00019782709248328457,
"loss": 0.8143559455871582,
"step": 860
},
{
"epoch": 0.1914823374050842,
"grad_norm": 1.001970887184143,
"learning_rate": 0.0001977525804469659,
"loss": 0.8750756263732911,
"step": 870
},
{
"epoch": 0.19368328381203917,
"grad_norm": 1.0459098815917969,
"learning_rate": 0.00019767682680727622,
"loss": 0.8288005828857422,
"step": 880
},
{
"epoch": 0.19588423021899418,
"grad_norm": 0.9816129803657532,
"learning_rate": 0.00019759983252639956,
"loss": 0.7945041179656982,
"step": 890
},
{
"epoch": 0.19808517662594916,
"grad_norm": 0.8988497853279114,
"learning_rate": 0.000197521598582278,
"loss": 0.8355922698974609,
"step": 900
},
{
"epoch": 0.20028612303290416,
"grad_norm": 0.892160952091217,
"learning_rate": 0.00019744212596859914,
"loss": 0.854766845703125,
"step": 910
},
{
"epoch": 0.20248706943985914,
"grad_norm": 0.9523811340332031,
"learning_rate": 0.00019736141569478356,
"loss": 0.7782519340515137,
"step": 920
},
{
"epoch": 0.20468801584681412,
"grad_norm": 0.9528471827507019,
"learning_rate": 0.00019727946878597195,
"loss": 0.8091512680053711,
"step": 930
},
{
"epoch": 0.20688896225376913,
"grad_norm": 0.9524006843566895,
"learning_rate": 0.00019719628628301212,
"loss": 0.8312657356262207,
"step": 940
},
{
"epoch": 0.2090899086607241,
"grad_norm": 0.8955079913139343,
"learning_rate": 0.00019711186924244574,
"loss": 0.8257021903991699,
"step": 950
},
{
"epoch": 0.2112908550676791,
"grad_norm": 0.9080793857574463,
"learning_rate": 0.00019702621873649495,
"loss": 0.8441055297851563,
"step": 960
},
{
"epoch": 0.2134918014746341,
"grad_norm": 0.9945964813232422,
"learning_rate": 0.00019693933585304877,
"loss": 0.859739875793457,
"step": 970
},
{
"epoch": 0.21569274788158907,
"grad_norm": 0.9307037591934204,
"learning_rate": 0.00019685122169564925,
"loss": 0.8007944107055665,
"step": 980
},
{
"epoch": 0.21789369428854408,
"grad_norm": 0.8341166377067566,
"learning_rate": 0.00019676187738347736,
"loss": 0.8627373695373535,
"step": 990
},
{
"epoch": 0.22009464069549906,
"grad_norm": 0.9342769980430603,
"learning_rate": 0.000196671304051339,
"loss": 0.8269523620605469,
"step": 1000
},
{
"epoch": 0.22009464069549906,
"eval_loss": 0.8339518904685974,
"eval_runtime": 1054.8035,
"eval_samples_per_second": 8.615,
"eval_steps_per_second": 1.077,
"step": 1000
},
{
"epoch": 0.1111539096461784,
"grad_norm": 1.318543791770935,
"learning_rate": 0.00019965976481479497,
"loss": 0.7344522476196289,
"step": 1010
},
{
"epoch": 0.11225444340505145,
"grad_norm": 1.2357608079910278,
"learning_rate": 0.0001996449179135936,
"loss": 0.7247725486755371,
"step": 1020
},
{
"epoch": 0.11335497716392451,
"grad_norm": 1.403720736503601,
"learning_rate": 0.00019962975453062098,
"loss": 0.7473694324493408,
"step": 1030
},
{
"epoch": 0.11445551092279756,
"grad_norm": 1.3010951280593872,
"learning_rate": 0.00019961427471403752,
"loss": 0.7128599166870118,
"step": 1040
},
{
"epoch": 0.1155560446816706,
"grad_norm": 1.4912559986114502,
"learning_rate": 0.00019959847851300856,
"loss": 0.7000036716461182,
"step": 1050
},
{
"epoch": 0.11665657844054367,
"grad_norm": 1.476868748664856,
"learning_rate": 0.00019958236597770437,
"loss": 0.7557538986206055,
"step": 1060
},
{
"epoch": 0.11775711219941672,
"grad_norm": 1.2181434631347656,
"learning_rate": 0.00019956593715929986,
"loss": 0.7561722755432129,
"step": 1070
},
{
"epoch": 0.11885764595828976,
"grad_norm": 1.2714087963104248,
"learning_rate": 0.00019954919210997453,
"loss": 0.751192283630371,
"step": 1080
},
{
"epoch": 0.11995817971716283,
"grad_norm": 1.3082411289215088,
"learning_rate": 0.0001995321308829123,
"loss": 0.771207618713379,
"step": 1090
},
{
"epoch": 0.12105871347603588,
"grad_norm": 1.2826007604599,
"learning_rate": 0.00019951475353230117,
"loss": 0.7480668544769287,
"step": 1100
},
{
"epoch": 0.12215924723490892,
"grad_norm": 1.3389414548873901,
"learning_rate": 0.00019949706011333337,
"loss": 0.7101992607116699,
"step": 1110
},
{
"epoch": 0.12325978099378199,
"grad_norm": 1.3306312561035156,
"learning_rate": 0.00019947905068220482,
"loss": 0.6952154636383057,
"step": 1120
},
{
"epoch": 0.12436031475265504,
"grad_norm": 1.5364283323287964,
"learning_rate": 0.0001994607252961152,
"loss": 0.7477862358093261,
"step": 1130
},
{
"epoch": 0.12546084851152808,
"grad_norm": 1.5809048414230347,
"learning_rate": 0.0001994420840132677,
"loss": 0.681206226348877,
"step": 1140
},
{
"epoch": 0.12656138227040115,
"grad_norm": 1.5444300174713135,
"learning_rate": 0.0001994231268928688,
"loss": 0.6869724750518799,
"step": 1150
},
{
"epoch": 0.1276619160292742,
"grad_norm": 1.3037437200546265,
"learning_rate": 0.00019940385399512813,
"loss": 0.7233117580413818,
"step": 1160
},
{
"epoch": 0.12876244978814724,
"grad_norm": 1.4460251331329346,
"learning_rate": 0.00019938426538125827,
"loss": 0.7215907573699951,
"step": 1170
},
{
"epoch": 0.1298629835470203,
"grad_norm": 1.340132474899292,
"learning_rate": 0.00019936436111347452,
"loss": 0.6880172252655029,
"step": 1180
},
{
"epoch": 0.13096351730589337,
"grad_norm": 1.358814001083374,
"learning_rate": 0.0001993441412549947,
"loss": 0.6970400333404541,
"step": 1190
},
{
"epoch": 0.1320640510647664,
"grad_norm": 1.3030223846435547,
"learning_rate": 0.00019932360587003906,
"loss": 0.6770397663116455,
"step": 1200
},
{
"epoch": 0.13316458482363946,
"grad_norm": 1.353985071182251,
"learning_rate": 0.0001993027550238299,
"loss": 0.660685396194458,
"step": 1210
},
{
"epoch": 0.13426511858251253,
"grad_norm": 1.331395149230957,
"learning_rate": 0.00019928158878259152,
"loss": 0.7561236381530761,
"step": 1220
},
{
"epoch": 0.13536565234138556,
"grad_norm": 1.6936500072479248,
"learning_rate": 0.00019926010721354995,
"loss": 0.6630916118621826,
"step": 1230
},
{
"epoch": 0.13646618610025862,
"grad_norm": 1.7496025562286377,
"learning_rate": 0.00019923831038493267,
"loss": 0.7098928928375244,
"step": 1240
},
{
"epoch": 0.1375667198591317,
"grad_norm": 1.4740201234817505,
"learning_rate": 0.00019921619836596848,
"loss": 0.7289152622222901,
"step": 1250
},
{
"epoch": 0.13866725361800472,
"grad_norm": 1.6177831888198853,
"learning_rate": 0.0001991937712268873,
"loss": 0.6388457298278809,
"step": 1260
},
{
"epoch": 0.13976778737687778,
"grad_norm": 1.436196208000183,
"learning_rate": 0.0001991710290389198,
"loss": 0.764772367477417,
"step": 1270
},
{
"epoch": 0.14086832113575085,
"grad_norm": 1.770621418952942,
"learning_rate": 0.00019914797187429743,
"loss": 0.7233758449554444,
"step": 1280
},
{
"epoch": 0.14196885489462388,
"grad_norm": 1.5772244930267334,
"learning_rate": 0.00019912459980625183,
"loss": 0.7039950370788575,
"step": 1290
},
{
"epoch": 0.14306938865349694,
"grad_norm": 1.3709217309951782,
"learning_rate": 0.00019910091290901503,
"loss": 0.7573204040527344,
"step": 1300
},
{
"epoch": 0.14416992241237,
"grad_norm": 1.3122904300689697,
"learning_rate": 0.0001990769112578188,
"loss": 0.6998284339904786,
"step": 1310
},
{
"epoch": 0.14527045617124304,
"grad_norm": 1.4337154626846313,
"learning_rate": 0.00019905259492889474,
"loss": 0.7914797306060791,
"step": 1320
},
{
"epoch": 0.1463709899301161,
"grad_norm": 1.5576714277267456,
"learning_rate": 0.0001990279639994738,
"loss": 0.6956133365631103,
"step": 1330
},
{
"epoch": 0.14747152368898916,
"grad_norm": 1.403680443763733,
"learning_rate": 0.00019900301854778617,
"loss": 0.7613757133483887,
"step": 1340
},
{
"epoch": 0.14857205744786223,
"grad_norm": 1.5148899555206299,
"learning_rate": 0.00019897775865306098,
"loss": 0.7047707557678222,
"step": 1350
},
{
"epoch": 0.14967259120673526,
"grad_norm": 1.4134074449539185,
"learning_rate": 0.00019895218439552602,
"loss": 0.710445499420166,
"step": 1360
},
{
"epoch": 0.15077312496560832,
"grad_norm": 1.2723708152770996,
"learning_rate": 0.00019892629585640766,
"loss": 0.7367370128631592,
"step": 1370
},
{
"epoch": 0.1518736587244814,
"grad_norm": 1.4825470447540283,
"learning_rate": 0.00019890009311793031,
"loss": 0.7489582538604737,
"step": 1380
},
{
"epoch": 0.15297419248335442,
"grad_norm": 1.3578537702560425,
"learning_rate": 0.0001988735762633164,
"loss": 0.7605162143707276,
"step": 1390
},
{
"epoch": 0.15407472624222748,
"grad_norm": 1.4326390027999878,
"learning_rate": 0.00019884674537678598,
"loss": 0.7359246253967285,
"step": 1400
},
{
"epoch": 0.15517526000110055,
"grad_norm": 1.54934561252594,
"learning_rate": 0.00019881960054355652,
"loss": 0.7244048118591309,
"step": 1410
},
{
"epoch": 0.15627579375997358,
"grad_norm": 1.4539642333984375,
"learning_rate": 0.00019879214184984257,
"loss": 0.7321300029754638,
"step": 1420
},
{
"epoch": 0.15737632751884664,
"grad_norm": 1.480238914489746,
"learning_rate": 0.00019876436938285558,
"loss": 0.7465243339538574,
"step": 1430
},
{
"epoch": 0.1584768612777197,
"grad_norm": 1.380171775817871,
"learning_rate": 0.00019873628323080359,
"loss": 0.7432620525360107,
"step": 1440
},
{
"epoch": 0.15957739503659274,
"grad_norm": 1.516487717628479,
"learning_rate": 0.00019870788348289083,
"loss": 0.7081382274627686,
"step": 1450
},
{
"epoch": 0.1606779287954658,
"grad_norm": 1.4838062524795532,
"learning_rate": 0.00019867917022931765,
"loss": 0.7314321994781494,
"step": 1460
},
{
"epoch": 0.16177846255433886,
"grad_norm": 1.501446008682251,
"learning_rate": 0.0001986501435612801,
"loss": 0.7468172073364258,
"step": 1470
},
{
"epoch": 0.1628789963132119,
"grad_norm": 1.3697547912597656,
"learning_rate": 0.0001986208035709696,
"loss": 0.6616341590881347,
"step": 1480
},
{
"epoch": 0.16397953007208496,
"grad_norm": 1.4565426111221313,
"learning_rate": 0.00019859115035157285,
"loss": 0.7138534545898437,
"step": 1490
},
{
"epoch": 0.16508006383095802,
"grad_norm": 1.2693283557891846,
"learning_rate": 0.0001985611839972712,
"loss": 0.7095062732696533,
"step": 1500
},
{
"epoch": 0.16618059758983106,
"grad_norm": 1.519113540649414,
"learning_rate": 0.00019853090460324071,
"loss": 0.6623078346252441,
"step": 1510
},
{
"epoch": 0.16728113134870412,
"grad_norm": 1.1893036365509033,
"learning_rate": 0.0001985003122656516,
"loss": 0.785255765914917,
"step": 1520
},
{
"epoch": 0.16838166510757718,
"grad_norm": 1.5294969081878662,
"learning_rate": 0.00019846940708166807,
"loss": 0.7090532302856445,
"step": 1530
},
{
"epoch": 0.16948219886645022,
"grad_norm": 1.3630003929138184,
"learning_rate": 0.00019843818914944795,
"loss": 0.7042516708374024,
"step": 1540
},
{
"epoch": 0.17058273262532328,
"grad_norm": 1.4818453788757324,
"learning_rate": 0.00019840665856814236,
"loss": 0.7102742195129395,
"step": 1550
},
{
"epoch": 0.17168326638419634,
"grad_norm": 1.5661572217941284,
"learning_rate": 0.00019837481543789542,
"loss": 0.7352417469024658,
"step": 1560
},
{
"epoch": 0.17278380014306938,
"grad_norm": 1.5921189785003662,
"learning_rate": 0.00019834265985984394,
"loss": 0.6786233901977539,
"step": 1570
},
{
"epoch": 0.17388433390194244,
"grad_norm": 1.7793580293655396,
"learning_rate": 0.00019831019193611716,
"loss": 0.6913634300231933,
"step": 1580
},
{
"epoch": 0.1749848676608155,
"grad_norm": 1.4666355848312378,
"learning_rate": 0.00019827741176983629,
"loss": 0.6923691749572753,
"step": 1590
},
{
"epoch": 0.17608540141968854,
"grad_norm": 1.2723121643066406,
"learning_rate": 0.0001982443194651142,
"loss": 0.7328421592712402,
"step": 1600
},
{
"epoch": 0.1771859351785616,
"grad_norm": 1.7125496864318848,
"learning_rate": 0.00019821091512705529,
"loss": 0.7273451328277588,
"step": 1610
},
{
"epoch": 0.17828646893743466,
"grad_norm": 1.2607357501983643,
"learning_rate": 0.0001981771988617549,
"loss": 0.6852648258209229,
"step": 1620
},
{
"epoch": 0.1793870026963077,
"grad_norm": 1.4323406219482422,
"learning_rate": 0.0001981431707762991,
"loss": 0.6527719974517823,
"step": 1630
},
{
"epoch": 0.18048753645518076,
"grad_norm": 1.5323034524917603,
"learning_rate": 0.00019810883097876435,
"loss": 0.6863321781158447,
"step": 1640
},
{
"epoch": 0.18158807021405382,
"grad_norm": 1.4771450757980347,
"learning_rate": 0.00019807417957821708,
"loss": 0.713313102722168,
"step": 1650
},
{
"epoch": 0.18268860397292688,
"grad_norm": 1.4179728031158447,
"learning_rate": 0.0001980392166847135,
"loss": 0.7239354133605957,
"step": 1660
},
{
"epoch": 0.18378913773179992,
"grad_norm": 1.54883873462677,
"learning_rate": 0.00019800394240929907,
"loss": 0.7668267726898194,
"step": 1670
},
{
"epoch": 0.18488967149067298,
"grad_norm": 1.4585139751434326,
"learning_rate": 0.0001979683568640083,
"loss": 0.7013049602508545,
"step": 1680
},
{
"epoch": 0.18599020524954604,
"grad_norm": 1.423919439315796,
"learning_rate": 0.0001979324601618642,
"loss": 0.7432220935821533,
"step": 1690
},
{
"epoch": 0.18709073900841908,
"grad_norm": 1.5283218622207642,
"learning_rate": 0.0001978962524168782,
"loss": 0.7024415969848633,
"step": 1700
},
{
"epoch": 0.18819127276729214,
"grad_norm": 1.4342306852340698,
"learning_rate": 0.00019785973374404948,
"loss": 0.6836557388305664,
"step": 1710
},
{
"epoch": 0.1892918065261652,
"grad_norm": 1.3203076124191284,
"learning_rate": 0.0001978229042593649,
"loss": 0.669966173171997,
"step": 1720
},
{
"epoch": 0.19039234028503824,
"grad_norm": 1.6151920557022095,
"learning_rate": 0.0001977857640797984,
"loss": 0.7203169345855713,
"step": 1730
},
{
"epoch": 0.1914928740439113,
"grad_norm": 1.5594950914382935,
"learning_rate": 0.00019774831332331072,
"loss": 0.7175643444061279,
"step": 1740
},
{
"epoch": 0.19259340780278436,
"grad_norm": 1.275919795036316,
"learning_rate": 0.000197710552108849,
"loss": 0.7080940246582031,
"step": 1750
},
{
"epoch": 0.1936939415616574,
"grad_norm": 1.559988021850586,
"learning_rate": 0.00019767248055634656,
"loss": 0.6943031311035156,
"step": 1760
},
{
"epoch": 0.19479447532053046,
"grad_norm": 1.4960150718688965,
"learning_rate": 0.0001976340987867222,
"loss": 0.6438261032104492,
"step": 1770
},
{
"epoch": 0.19589500907940352,
"grad_norm": 1.3384159803390503,
"learning_rate": 0.00019759540692188015,
"loss": 0.6569961547851563,
"step": 1780
},
{
"epoch": 0.19699554283827655,
"grad_norm": 1.6143518686294556,
"learning_rate": 0.00019755640508470942,
"loss": 0.6640120029449463,
"step": 1790
},
{
"epoch": 0.19809607659714962,
"grad_norm": 1.533369779586792,
"learning_rate": 0.00019751709339908352,
"loss": 0.709033203125,
"step": 1800
},
{
"epoch": 0.19919661035602268,
"grad_norm": 1.3830273151397705,
"learning_rate": 0.00019747747198986025,
"loss": 0.7042165279388428,
"step": 1810
},
{
"epoch": 0.20029714411489571,
"grad_norm": 1.5432374477386475,
"learning_rate": 0.00019743754098288087,
"loss": 0.7099340438842774,
"step": 1820
},
{
"epoch": 0.20139767787376878,
"grad_norm": 1.8186261653900146,
"learning_rate": 0.00019739730050497012,
"loss": 0.5920440673828125,
"step": 1830
},
{
"epoch": 0.20249821163264184,
"grad_norm": 1.2721370458602905,
"learning_rate": 0.0001973567506839356,
"loss": 0.6752917766571045,
"step": 1840
},
{
"epoch": 0.20359874539151487,
"grad_norm": 1.5037890672683716,
"learning_rate": 0.00019731589164856742,
"loss": 0.6958805084228515,
"step": 1850
},
{
"epoch": 0.20469927915038794,
"grad_norm": 1.4381048679351807,
"learning_rate": 0.00019727472352863774,
"loss": 0.6831310749053955,
"step": 1860
},
{
"epoch": 0.205799812909261,
"grad_norm": 1.4521901607513428,
"learning_rate": 0.00019723324645490043,
"loss": 0.6515075206756592,
"step": 1870
},
{
"epoch": 0.20690034666813403,
"grad_norm": 1.4317247867584229,
"learning_rate": 0.00019719146055909072,
"loss": 0.7445472240447998,
"step": 1880
},
{
"epoch": 0.2080008804270071,
"grad_norm": 1.3491274118423462,
"learning_rate": 0.00019714936597392454,
"loss": 0.6975584030151367,
"step": 1890
},
{
"epoch": 0.20910141418588016,
"grad_norm": 1.6799184083938599,
"learning_rate": 0.00019710696283309828,
"loss": 0.663750171661377,
"step": 1900
},
{
"epoch": 0.2102019479447532,
"grad_norm": 1.5508129596710205,
"learning_rate": 0.00019706425127128844,
"loss": 0.7214709281921386,
"step": 1910
},
{
"epoch": 0.21130248170362625,
"grad_norm": 1.507115364074707,
"learning_rate": 0.000197021231424151,
"loss": 0.6937719345092773,
"step": 1920
},
{
"epoch": 0.21240301546249932,
"grad_norm": 1.5276693105697632,
"learning_rate": 0.00019697790342832104,
"loss": 0.6974040985107421,
"step": 1930
},
{
"epoch": 0.21350354922137235,
"grad_norm": 1.5013867616653442,
"learning_rate": 0.00019693426742141244,
"loss": 0.7391683101654053,
"step": 1940
},
{
"epoch": 0.21460408298024541,
"grad_norm": 1.6396576166152954,
"learning_rate": 0.00019689032354201736,
"loss": 0.6841801166534424,
"step": 1950
},
{
"epoch": 0.21570461673911848,
"grad_norm": 1.480556845664978,
"learning_rate": 0.00019684607192970574,
"loss": 0.6711002349853515,
"step": 1960
},
{
"epoch": 0.21680515049799154,
"grad_norm": 1.2973003387451172,
"learning_rate": 0.0001968015127250249,
"loss": 0.7282744884490967,
"step": 1970
},
{
"epoch": 0.21790568425686457,
"grad_norm": 1.5058932304382324,
"learning_rate": 0.00019675664606949914,
"loss": 0.7393957138061523,
"step": 1980
},
{
"epoch": 0.21900621801573764,
"grad_norm": 1.6734826564788818,
"learning_rate": 0.00019671147210562927,
"loss": 0.6838624477386475,
"step": 1990
},
{
"epoch": 0.2201067517746107,
"grad_norm": 1.7731140851974487,
"learning_rate": 0.00019666599097689207,
"loss": 0.7038939952850342,
"step": 2000
},
{
"epoch": 0.2201067517746107,
"eval_loss": 0.8496589064598083,
"eval_runtime": 933.6965,
"eval_samples_per_second": 9.732,
"eval_steps_per_second": 2.433,
"step": 2000
},
{
"epoch": 0.22120728553348373,
"grad_norm": 1.6997652053833008,
"learning_rate": 0.00019662020282773995,
"loss": 0.8130602836608887,
"step": 2010
},
{
"epoch": 0.2223078192923568,
"grad_norm": 1.617069125175476,
"learning_rate": 0.00019657410780360047,
"loss": 0.8593770027160644,
"step": 2020
},
{
"epoch": 0.22340835305122986,
"grad_norm": 1.435889482498169,
"learning_rate": 0.0001965277060508758,
"loss": 0.8794844627380372,
"step": 2030
},
{
"epoch": 0.2245088868101029,
"grad_norm": 1.593628168106079,
"learning_rate": 0.00019648099771694236,
"loss": 0.8761175155639649,
"step": 2040
},
{
"epoch": 0.22560942056897595,
"grad_norm": 1.4817216396331787,
"learning_rate": 0.00019643398295015026,
"loss": 0.8747184753417969,
"step": 2050
},
{
"epoch": 0.22670995432784902,
"grad_norm": 1.2658919095993042,
"learning_rate": 0.0001963866618998229,
"loss": 0.8425754547119141,
"step": 2060
},
{
"epoch": 0.22781048808672205,
"grad_norm": 1.549432396888733,
"learning_rate": 0.00019633903471625645,
"loss": 0.8407624244689942,
"step": 2070
},
{
"epoch": 0.22891102184559511,
"grad_norm": 1.2967861890792847,
"learning_rate": 0.00019629110155071938,
"loss": 0.8481991767883301,
"step": 2080
},
{
"epoch": 0.23001155560446818,
"grad_norm": 1.4197816848754883,
"learning_rate": 0.00019624286255545199,
"loss": 0.8669241905212403,
"step": 2090
},
{
"epoch": 0.2311120893633412,
"grad_norm": 1.2624856233596802,
"learning_rate": 0.00019619431788366596,
"loss": 0.8022339820861817,
"step": 2100
},
{
"epoch": 0.23221262312221427,
"grad_norm": 1.6743338108062744,
"learning_rate": 0.0001961454676895438,
"loss": 0.8768888473510742,
"step": 2110
},
{
"epoch": 0.23331315688108734,
"grad_norm": 2.0868279933929443,
"learning_rate": 0.0001960963121282384,
"loss": 0.8667360305786133,
"step": 2120
},
{
"epoch": 0.23441369063996037,
"grad_norm": 1.4186112880706787,
"learning_rate": 0.00019604685135587245,
"loss": 0.8278182029724122,
"step": 2130
},
{
"epoch": 0.23551422439883343,
"grad_norm": 1.2936203479766846,
"learning_rate": 0.00019599708552953815,
"loss": 0.812893009185791,
"step": 2140
},
{
"epoch": 0.2366147581577065,
"grad_norm": 1.2756561040878296,
"learning_rate": 0.0001959470148072965,
"loss": 0.8358366012573242,
"step": 2150
},
{
"epoch": 0.23771529191657953,
"grad_norm": 1.3688085079193115,
"learning_rate": 0.00019589663934817687,
"loss": 0.7904013633728028,
"step": 2160
},
{
"epoch": 0.2388158256754526,
"grad_norm": 1.317444920539856,
"learning_rate": 0.0001958459593121766,
"loss": 0.8964195251464844,
"step": 2170
},
{
"epoch": 0.23991635943432565,
"grad_norm": 1.294002890586853,
"learning_rate": 0.00019579497486026023,
"loss": 0.8562044143676758,
"step": 2180
},
{
"epoch": 0.2410168931931987,
"grad_norm": 1.2761428356170654,
"learning_rate": 0.0001957436861543593,
"loss": 0.8061718940734863,
"step": 2190
},
{
"epoch": 0.24211742695207175,
"grad_norm": 1.4096399545669556,
"learning_rate": 0.0001956920933573716,
"loss": 0.8700193405151367,
"step": 2200
},
{
"epoch": 0.2432179607109448,
"grad_norm": 1.2484604120254517,
"learning_rate": 0.0001956401966331608,
"loss": 0.8373005867004395,
"step": 2210
},
{
"epoch": 0.24431849446981785,
"grad_norm": 1.4023255109786987,
"learning_rate": 0.00019558799614655586,
"loss": 0.7784786224365234,
"step": 2220
},
{
"epoch": 0.2454190282286909,
"grad_norm": 1.3306242227554321,
"learning_rate": 0.00019553549206335048,
"loss": 0.8288736343383789,
"step": 2230
},
{
"epoch": 0.24651956198756397,
"grad_norm": 1.3334354162216187,
"learning_rate": 0.00019548268455030267,
"loss": 0.815639591217041,
"step": 2240
},
{
"epoch": 0.24762009574643704,
"grad_norm": 1.2042546272277832,
"learning_rate": 0.00019542957377513412,
"loss": 0.8448248863220215,
"step": 2250
},
{
"epoch": 0.24872062950531007,
"grad_norm": 1.4218223094940186,
"learning_rate": 0.0001953761599065297,
"loss": 0.8586576461791993,
"step": 2260
},
{
"epoch": 0.24982116326418313,
"grad_norm": 1.326367735862732,
"learning_rate": 0.00019532244311413704,
"loss": 0.7699498176574707,
"step": 2270
},
{
"epoch": 0.25092169702305617,
"grad_norm": 1.414927363395691,
"learning_rate": 0.00019526842356856568,
"loss": 0.8183151245117187,
"step": 2280
},
{
"epoch": 0.25202223078192926,
"grad_norm": 1.638340950012207,
"learning_rate": 0.00019521410144138693,
"loss": 0.8281731605529785,
"step": 2290
},
{
"epoch": 0.2531227645408023,
"grad_norm": 1.4947667121887207,
"learning_rate": 0.00019515947690513304,
"loss": 0.8409298896789551,
"step": 2300
},
{
"epoch": 0.2542232982996753,
"grad_norm": 1.5608994960784912,
"learning_rate": 0.00019510455013329673,
"loss": 0.8110830307006835,
"step": 2310
},
{
"epoch": 0.2553238320585484,
"grad_norm": 1.3185389041900635,
"learning_rate": 0.00019504932130033067,
"loss": 0.8009634971618652,
"step": 2320
},
{
"epoch": 0.25642436581742145,
"grad_norm": 1.246773600578308,
"learning_rate": 0.00019499379058164694,
"loss": 0.8565659523010254,
"step": 2330
},
{
"epoch": 0.2575248995762945,
"grad_norm": 1.3509032726287842,
"learning_rate": 0.00019493795815361638,
"loss": 0.8486443519592285,
"step": 2340
},
{
"epoch": 0.2586254333351676,
"grad_norm": 1.330709457397461,
"learning_rate": 0.0001948818241935681,
"loss": 0.8198354721069336,
"step": 2350
},
{
"epoch": 0.2597259670940406,
"grad_norm": 1.200380802154541,
"learning_rate": 0.00019482538887978894,
"loss": 0.8310845375061036,
"step": 2360
},
{
"epoch": 0.26082650085291365,
"grad_norm": 1.3873624801635742,
"learning_rate": 0.00019476865239152283,
"loss": 0.8995956420898438,
"step": 2370
},
{
"epoch": 0.26192703461178674,
"grad_norm": 1.5119566917419434,
"learning_rate": 0.00019471161490897029,
"loss": 0.828061580657959,
"step": 2380
},
{
"epoch": 0.26302756837065977,
"grad_norm": 1.461253046989441,
"learning_rate": 0.0001946542766132878,
"loss": 0.8718130111694335,
"step": 2390
},
{
"epoch": 0.2641281021295328,
"grad_norm": 1.5901751518249512,
"learning_rate": 0.00019459663768658722,
"loss": 0.8477680206298828,
"step": 2400
},
{
"epoch": 0.2652286358884059,
"grad_norm": 1.2325890064239502,
"learning_rate": 0.00019453869831193536,
"loss": 0.8439332008361816,
"step": 2410
},
{
"epoch": 0.26632916964727893,
"grad_norm": 1.3299224376678467,
"learning_rate": 0.00019448045867335315,
"loss": 0.8034492492675781,
"step": 2420
},
{
"epoch": 0.26742970340615196,
"grad_norm": 1.4191641807556152,
"learning_rate": 0.00019442191895581524,
"loss": 0.8057695388793945,
"step": 2430
},
{
"epoch": 0.26853023716502505,
"grad_norm": 1.2450047731399536,
"learning_rate": 0.0001943630793452494,
"loss": 0.7739078521728515,
"step": 2440
},
{
"epoch": 0.2696307709238981,
"grad_norm": 1.2834359407424927,
"learning_rate": 0.0001943039400285358,
"loss": 0.8015741348266602,
"step": 2450
},
{
"epoch": 0.2707313046827711,
"grad_norm": 1.4579415321350098,
"learning_rate": 0.0001942445011935066,
"loss": 0.8276127815246582,
"step": 2460
},
{
"epoch": 0.2718318384416442,
"grad_norm": 1.2527804374694824,
"learning_rate": 0.0001941847630289452,
"loss": 0.8028785705566406,
"step": 2470
},
{
"epoch": 0.27293237220051725,
"grad_norm": 1.6216117143630981,
"learning_rate": 0.00019412472572458568,
"loss": 0.8052440643310547,
"step": 2480
},
{
"epoch": 0.2740329059593903,
"grad_norm": 1.3080998659133911,
"learning_rate": 0.00019406438947111232,
"loss": 0.7991613388061524,
"step": 2490
},
{
"epoch": 0.2751334397182634,
"grad_norm": 1.2693983316421509,
"learning_rate": 0.00019400375446015875,
"loss": 0.7874859809875489,
"step": 2500
},
{
"epoch": 0.2762339734771364,
"grad_norm": 1.5021086931228638,
"learning_rate": 0.00019394282088430758,
"loss": 0.857176685333252,
"step": 2510
},
{
"epoch": 0.27733450723600944,
"grad_norm": 1.7014224529266357,
"learning_rate": 0.00019388158893708968,
"loss": 0.8121908187866211,
"step": 2520
},
{
"epoch": 0.27843504099488253,
"grad_norm": 1.2773478031158447,
"learning_rate": 0.00019382005881298355,
"loss": 0.83267240524292,
"step": 2530
},
{
"epoch": 0.27953557475375557,
"grad_norm": 1.2932922840118408,
"learning_rate": 0.00019375823070741472,
"loss": 0.8565213203430175,
"step": 2540
},
{
"epoch": 0.2806361085126286,
"grad_norm": 1.3514758348464966,
"learning_rate": 0.00019369610481675517,
"loss": 0.8068264961242676,
"step": 2550
},
{
"epoch": 0.2817366422715017,
"grad_norm": 1.4034395217895508,
"learning_rate": 0.00019363368133832264,
"loss": 0.7951233863830567,
"step": 2560
},
{
"epoch": 0.2828371760303747,
"grad_norm": 1.402474284172058,
"learning_rate": 0.0001935709604703801,
"loss": 0.8516476631164551,
"step": 2570
},
{
"epoch": 0.28393770978924776,
"grad_norm": 1.2598680257797241,
"learning_rate": 0.000193507942412135,
"loss": 0.8248865127563476,
"step": 2580
},
{
"epoch": 0.28503824354812085,
"grad_norm": 1.4511678218841553,
"learning_rate": 0.00019344462736373865,
"loss": 0.8426539421081543,
"step": 2590
},
{
"epoch": 0.2861387773069939,
"grad_norm": 1.4446839094161987,
"learning_rate": 0.00019338101552628578,
"loss": 0.7813214302062989,
"step": 2600
},
{
"epoch": 0.2872393110658669,
"grad_norm": 1.348212718963623,
"learning_rate": 0.0001933171071018136,
"loss": 0.8185086250305176,
"step": 2610
},
{
"epoch": 0.28833984482474,
"grad_norm": 1.3354694843292236,
"learning_rate": 0.00019325290229330134,
"loss": 0.8290966033935547,
"step": 2620
},
{
"epoch": 0.28944037858361304,
"grad_norm": 1.6722166538238525,
"learning_rate": 0.00019318840130466968,
"loss": 0.8179054260253906,
"step": 2630
},
{
"epoch": 0.2905409123424861,
"grad_norm": 1.2694981098175049,
"learning_rate": 0.00019312360434077985,
"loss": 0.8385242462158203,
"step": 2640
},
{
"epoch": 0.29164144610135917,
"grad_norm": 1.9272838830947876,
"learning_rate": 0.00019305851160743325,
"loss": 0.8141334533691407,
"step": 2650
},
{
"epoch": 0.2927419798602322,
"grad_norm": 1.2957518100738525,
"learning_rate": 0.00019299312331137055,
"loss": 0.835750675201416,
"step": 2660
},
{
"epoch": 0.29384251361910524,
"grad_norm": 1.5437421798706055,
"learning_rate": 0.0001929274396602713,
"loss": 0.7907589912414551,
"step": 2670
},
{
"epoch": 0.29494304737797833,
"grad_norm": 1.487249732017517,
"learning_rate": 0.00019286146086275294,
"loss": 0.7967824935913086,
"step": 2680
},
{
"epoch": 0.29604358113685136,
"grad_norm": 1.3860902786254883,
"learning_rate": 0.00019279518712837052,
"loss": 0.7865518093109131,
"step": 2690
},
{
"epoch": 0.29714411489572445,
"grad_norm": 1.5004669427871704,
"learning_rate": 0.00019272861866761573,
"loss": 0.8506379127502441,
"step": 2700
},
{
"epoch": 0.2982446486545975,
"grad_norm": 1.4427077770233154,
"learning_rate": 0.0001926617556919163,
"loss": 0.8193819999694825,
"step": 2710
},
{
"epoch": 0.2993451824134705,
"grad_norm": 1.2161895036697388,
"learning_rate": 0.00019259459841363552,
"loss": 0.8297209739685059,
"step": 2720
},
{
"epoch": 0.3004457161723436,
"grad_norm": 1.8028621673583984,
"learning_rate": 0.0001925271470460712,
"loss": 0.8238694190979003,
"step": 2730
},
{
"epoch": 0.30154624993121665,
"grad_norm": 1.339763879776001,
"learning_rate": 0.00019245940180345544,
"loss": 0.7622324466705322,
"step": 2740
},
{
"epoch": 0.3026467836900897,
"grad_norm": 1.3132916688919067,
"learning_rate": 0.0001923913629009535,
"loss": 0.7768839359283447,
"step": 2750
},
{
"epoch": 0.3037473174489628,
"grad_norm": 1.3144910335540771,
"learning_rate": 0.0001923230305546635,
"loss": 0.8279050827026367,
"step": 2760
},
{
"epoch": 0.3048478512078358,
"grad_norm": 1.1577019691467285,
"learning_rate": 0.00019225440498161546,
"loss": 0.7885588645935059,
"step": 2770
},
{
"epoch": 0.30594838496670884,
"grad_norm": 1.4336917400360107,
"learning_rate": 0.0001921854863997707,
"loss": 0.7973155021667481,
"step": 2780
},
{
"epoch": 0.30704891872558193,
"grad_norm": 1.363558292388916,
"learning_rate": 0.00019211627502802134,
"loss": 0.7967965602874756,
"step": 2790
},
{
"epoch": 0.30814945248445497,
"grad_norm": 1.5244808197021484,
"learning_rate": 0.0001920467710861892,
"loss": 0.7747397422790527,
"step": 2800
},
{
"epoch": 0.309249986243328,
"grad_norm": 1.5638800859451294,
"learning_rate": 0.00019197697479502547,
"loss": 0.805236530303955,
"step": 2810
},
{
"epoch": 0.3103505200022011,
"grad_norm": 1.3312816619873047,
"learning_rate": 0.00019190688637620986,
"loss": 0.7381678581237793,
"step": 2820
},
{
"epoch": 0.3114510537610741,
"grad_norm": 1.4813461303710938,
"learning_rate": 0.00019183650605234984,
"loss": 0.7765594005584717,
"step": 2830
},
{
"epoch": 0.31255158751994716,
"grad_norm": 1.3135008811950684,
"learning_rate": 0.00019176583404698002,
"loss": 0.8520167350769043,
"step": 2840
},
{
"epoch": 0.31365212127882025,
"grad_norm": 1.4595879316329956,
"learning_rate": 0.00019169487058456148,
"loss": 0.8141855239868164,
"step": 2850
},
{
"epoch": 0.3147526550376933,
"grad_norm": 1.384316325187683,
"learning_rate": 0.00019162361589048095,
"loss": 0.7784629344940186,
"step": 2860
},
{
"epoch": 0.3158531887965663,
"grad_norm": 1.1909021139144897,
"learning_rate": 0.00019155207019105007,
"loss": 0.8151874542236328,
"step": 2870
},
{
"epoch": 0.3169537225554394,
"grad_norm": 1.1605905294418335,
"learning_rate": 0.00019148023371350493,
"loss": 0.8893998146057129,
"step": 2880
},
{
"epoch": 0.31805425631431244,
"grad_norm": 1.6996575593948364,
"learning_rate": 0.00019140810668600493,
"loss": 0.8112521171569824,
"step": 2890
},
{
"epoch": 0.3191547900731855,
"grad_norm": 1.2271260023117065,
"learning_rate": 0.00019133568933763244,
"loss": 0.8266308784484864,
"step": 2900
},
{
"epoch": 0.32025532383205857,
"grad_norm": 1.7019249200820923,
"learning_rate": 0.0001912629818983919,
"loss": 0.7661680698394775,
"step": 2910
},
{
"epoch": 0.3213558575909316,
"grad_norm": 1.2853891849517822,
"learning_rate": 0.00019118998459920902,
"loss": 0.8458981513977051,
"step": 2920
},
{
"epoch": 0.32245639134980464,
"grad_norm": 1.4744017124176025,
"learning_rate": 0.0001911166976719302,
"loss": 0.7988483428955078,
"step": 2930
},
{
"epoch": 0.32355692510867773,
"grad_norm": 1.26249098777771,
"learning_rate": 0.0001910431213493218,
"loss": 0.789542818069458,
"step": 2940
},
{
"epoch": 0.32465745886755076,
"grad_norm": 1.4478040933609009,
"learning_rate": 0.00019096925586506913,
"loss": 0.7970124244689941,
"step": 2950
},
{
"epoch": 0.3257579926264238,
"grad_norm": 1.465301752090454,
"learning_rate": 0.00019089510145377608,
"loss": 0.7939679622650146,
"step": 2960
},
{
"epoch": 0.3268585263852969,
"grad_norm": 1.2790896892547607,
"learning_rate": 0.00019082065835096412,
"loss": 0.8515988349914551,
"step": 2970
},
{
"epoch": 0.3279590601441699,
"grad_norm": 1.3531389236450195,
"learning_rate": 0.00019074592679307165,
"loss": 0.7504467010498047,
"step": 2980
},
{
"epoch": 0.32905959390304296,
"grad_norm": 1.2116661071777344,
"learning_rate": 0.00019067090701745327,
"loss": 0.8174965858459473,
"step": 2990
},
{
"epoch": 0.33016012766191605,
"grad_norm": 1.113641381263733,
"learning_rate": 0.0001905955992623789,
"loss": 0.7890684127807617,
"step": 3000
},
{
"epoch": 0.33016012766191605,
"eval_loss": 0.790532648563385,
"eval_runtime": 930.8796,
"eval_samples_per_second": 9.762,
"eval_steps_per_second": 2.441,
"step": 3000
},
{
"epoch": 0.3312606614207891,
"grad_norm": 1.430518388748169,
"learning_rate": 0.00019052000376703317,
"loss": 0.8236588478088379,
"step": 3010
},
{
"epoch": 0.3323611951796621,
"grad_norm": 1.4252548217773438,
"learning_rate": 0.0001904441207715146,
"loss": 0.847992992401123,
"step": 3020
},
{
"epoch": 0.3334617289385352,
"grad_norm": 1.4208446741104126,
"learning_rate": 0.00019036795051683483,
"loss": 0.8224313735961915,
"step": 3030
},
{
"epoch": 0.33456226269740824,
"grad_norm": 1.3954637050628662,
"learning_rate": 0.00019029149324491785,
"loss": 0.8087237358093262,
"step": 3040
},
{
"epoch": 0.3356627964562813,
"grad_norm": 1.3011157512664795,
"learning_rate": 0.00019021474919859926,
"loss": 0.8049816131591797,
"step": 3050
},
{
"epoch": 0.33676333021515437,
"grad_norm": 1.3143519163131714,
"learning_rate": 0.00019013771862162545,
"loss": 0.7496432781219482,
"step": 3060
},
{
"epoch": 0.3378638639740274,
"grad_norm": 1.403659701347351,
"learning_rate": 0.00019006040175865294,
"loss": 0.7452910423278809,
"step": 3070
},
{
"epoch": 0.33896439773290044,
"grad_norm": 1.1721720695495605,
"learning_rate": 0.00018998279885524744,
"loss": 0.797463321685791,
"step": 3080
},
{
"epoch": 0.3400649314917735,
"grad_norm": 1.8334842920303345,
"learning_rate": 0.00018990491015788313,
"loss": 0.7963507652282715,
"step": 3090
},
{
"epoch": 0.34116546525064656,
"grad_norm": 1.3609745502471924,
"learning_rate": 0.00018982673591394207,
"loss": 0.7899526596069336,
"step": 3100
},
{
"epoch": 0.3422659990095196,
"grad_norm": 1.4191335439682007,
"learning_rate": 0.00018974827637171298,
"loss": 0.8170291900634765,
"step": 3110
},
{
"epoch": 0.3433665327683927,
"grad_norm": 1.546268343925476,
"learning_rate": 0.00018966953178039097,
"loss": 0.7608869552612305,
"step": 3120
},
{
"epoch": 0.3444670665272657,
"grad_norm": 1.2157829999923706,
"learning_rate": 0.00018959050239007627,
"loss": 0.8163496971130371,
"step": 3130
},
{
"epoch": 0.34556760028613875,
"grad_norm": 1.4426497220993042,
"learning_rate": 0.00018951118845177386,
"loss": 0.7838230609893799,
"step": 3140
},
{
"epoch": 0.34666813404501184,
"grad_norm": 1.4075052738189697,
"learning_rate": 0.0001894315902173924,
"loss": 0.780454158782959,
"step": 3150
},
{
"epoch": 0.3477686678038849,
"grad_norm": 1.146291732788086,
"learning_rate": 0.00018935170793974335,
"loss": 0.7559466361999512,
"step": 3160
},
{
"epoch": 0.3488692015627579,
"grad_norm": 1.1670087575912476,
"learning_rate": 0.00018927154187254054,
"loss": 0.7347095489501954,
"step": 3170
},
{
"epoch": 0.349969735321631,
"grad_norm": 1.3034203052520752,
"learning_rate": 0.0001891910922703991,
"loss": 0.7963647365570068,
"step": 3180
},
{
"epoch": 0.35107026908050404,
"grad_norm": 1.2328404188156128,
"learning_rate": 0.0001891103593888345,
"loss": 0.7840650081634521,
"step": 3190
},
{
"epoch": 0.3521708028393771,
"grad_norm": 1.2788565158843994,
"learning_rate": 0.00018902934348426223,
"loss": 0.7421338081359863,
"step": 3200
},
{
"epoch": 0.35327133659825016,
"grad_norm": 1.4272618293762207,
"learning_rate": 0.0001889480448139964,
"loss": 0.7635135173797607,
"step": 3210
},
{
"epoch": 0.3543718703571232,
"grad_norm": 1.2253040075302124,
"learning_rate": 0.0001888664636362495,
"loss": 0.8046904563903808,
"step": 3220
},
{
"epoch": 0.35547240411599623,
"grad_norm": 1.3970891237258911,
"learning_rate": 0.000188784600210131,
"loss": 0.7833479881286621,
"step": 3230
},
{
"epoch": 0.3565729378748693,
"grad_norm": 1.3941155672073364,
"learning_rate": 0.00018870245479564703,
"loss": 0.8373173713684082,
"step": 3240
},
{
"epoch": 0.35767347163374236,
"grad_norm": 1.3662322759628296,
"learning_rate": 0.00018862002765369926,
"loss": 0.8315282821655273,
"step": 3250
},
{
"epoch": 0.3587740053926154,
"grad_norm": 1.5178701877593994,
"learning_rate": 0.00018853731904608414,
"loss": 0.7962240695953369,
"step": 3260
},
{
"epoch": 0.3598745391514885,
"grad_norm": 1.2388792037963867,
"learning_rate": 0.00018845432923549212,
"loss": 0.785247802734375,
"step": 3270
},
{
"epoch": 0.3609750729103615,
"grad_norm": 1.5908961296081543,
"learning_rate": 0.00018837105848550672,
"loss": 0.7622479915618896,
"step": 3280
},
{
"epoch": 0.3620756066692346,
"grad_norm": 1.3947844505310059,
"learning_rate": 0.00018828750706060385,
"loss": 0.8159708976745605,
"step": 3290
},
{
"epoch": 0.36317614042810764,
"grad_norm": 1.5420454740524292,
"learning_rate": 0.00018820367522615078,
"loss": 0.7608321189880372,
"step": 3300
},
{
"epoch": 0.3642766741869807,
"grad_norm": 1.348726749420166,
"learning_rate": 0.00018811956324840546,
"loss": 0.7845717906951905,
"step": 3310
},
{
"epoch": 0.36537720794585377,
"grad_norm": 1.3308541774749756,
"learning_rate": 0.00018803517139451547,
"loss": 0.7821323871612549,
"step": 3320
},
{
"epoch": 0.3664777417047268,
"grad_norm": 1.3453469276428223,
"learning_rate": 0.00018795049993251746,
"loss": 0.7717282772064209,
"step": 3330
},
{
"epoch": 0.36757827546359984,
"grad_norm": 1.2678643465042114,
"learning_rate": 0.00018786554913133608,
"loss": 0.7912368774414062,
"step": 3340
},
{
"epoch": 0.3686788092224729,
"grad_norm": 1.2945518493652344,
"learning_rate": 0.0001877803192607832,
"loss": 0.8306121826171875,
"step": 3350
},
{
"epoch": 0.36977934298134596,
"grad_norm": 1.4001387357711792,
"learning_rate": 0.00018769481059155693,
"loss": 0.7877901554107666,
"step": 3360
},
{
"epoch": 0.370879876740219,
"grad_norm": 1.4055125713348389,
"learning_rate": 0.00018760902339524108,
"loss": 0.7993814945220947,
"step": 3370
},
{
"epoch": 0.3719804104990921,
"grad_norm": 1.5058491230010986,
"learning_rate": 0.0001875229579443039,
"loss": 0.7562387466430665,
"step": 3380
},
{
"epoch": 0.3730809442579651,
"grad_norm": 1.4691188335418701,
"learning_rate": 0.0001874366145120975,
"loss": 0.7943220615386963,
"step": 3390
},
{
"epoch": 0.37418147801683815,
"grad_norm": 1.4147716760635376,
"learning_rate": 0.00018734999337285686,
"loss": 0.7631899356842041,
"step": 3400
},
{
"epoch": 0.37528201177571124,
"grad_norm": 1.7002638578414917,
"learning_rate": 0.000187263094801699,
"loss": 0.7778403759002686,
"step": 3410
},
{
"epoch": 0.3763825455345843,
"grad_norm": 1.263079285621643,
"learning_rate": 0.00018717591907462208,
"loss": 0.7868700981140136,
"step": 3420
},
{
"epoch": 0.3774830792934573,
"grad_norm": 1.6632059812545776,
"learning_rate": 0.0001870884664685045,
"loss": 0.7900818347930908,
"step": 3430
},
{
"epoch": 0.3785836130523304,
"grad_norm": 1.3724589347839355,
"learning_rate": 0.00018700073726110416,
"loss": 0.809692668914795,
"step": 3440
},
{
"epoch": 0.37968414681120344,
"grad_norm": 1.6670794486999512,
"learning_rate": 0.00018691273173105725,
"loss": 0.7572099685668945,
"step": 3450
},
{
"epoch": 0.3807846805700765,
"grad_norm": 1.5179470777511597,
"learning_rate": 0.0001868244501578779,
"loss": 0.7761201858520508,
"step": 3460
},
{
"epoch": 0.38188521432894956,
"grad_norm": 1.4916956424713135,
"learning_rate": 0.00018673589282195669,
"loss": 0.7581660747528076,
"step": 3470
},
{
"epoch": 0.3829857480878226,
"grad_norm": 1.42303466796875,
"learning_rate": 0.00018664706000456026,
"loss": 0.7460827827453613,
"step": 3480
},
{
"epoch": 0.38408628184669563,
"grad_norm": 1.3675720691680908,
"learning_rate": 0.00018655795198783005,
"loss": 0.7278396606445312,
"step": 3490
},
{
"epoch": 0.3851868156055687,
"grad_norm": 1.2975969314575195,
"learning_rate": 0.0001864685690547817,
"loss": 0.7781871318817138,
"step": 3500
},
{
"epoch": 0.38628734936444176,
"grad_norm": 1.6625419855117798,
"learning_rate": 0.00018637891148930383,
"loss": 0.8365812301635742,
"step": 3510
},
{
"epoch": 0.3873878831233148,
"grad_norm": 1.92893385887146,
"learning_rate": 0.00018628897957615755,
"loss": 0.7808390140533448,
"step": 3520
},
{
"epoch": 0.3884884168821879,
"grad_norm": 1.4564015865325928,
"learning_rate": 0.0001861987736009751,
"loss": 0.8045003890991211,
"step": 3530
},
{
"epoch": 0.3895889506410609,
"grad_norm": 1.3779884576797485,
"learning_rate": 0.00018610829385025935,
"loss": 0.8292377471923829,
"step": 3540
},
{
"epoch": 0.39068948439993395,
"grad_norm": 1.7249268293380737,
"learning_rate": 0.00018601754061138256,
"loss": 0.7766525268554687,
"step": 3550
},
{
"epoch": 0.39179001815880704,
"grad_norm": 1.2811200618743896,
"learning_rate": 0.00018592651417258572,
"loss": 0.7709021091461181,
"step": 3560
},
{
"epoch": 0.3928905519176801,
"grad_norm": 1.3547565937042236,
"learning_rate": 0.00018583521482297747,
"loss": 0.7982177734375,
"step": 3570
},
{
"epoch": 0.3939910856765531,
"grad_norm": 1.5291974544525146,
"learning_rate": 0.00018574364285253326,
"loss": 0.8197507858276367,
"step": 3580
},
{
"epoch": 0.3950916194354262,
"grad_norm": 1.5480220317840576,
"learning_rate": 0.0001856517985520944,
"loss": 0.7673719882965088,
"step": 3590
},
{
"epoch": 0.39619215319429923,
"grad_norm": 1.2931580543518066,
"learning_rate": 0.0001855596822133672,
"loss": 0.7790896415710449,
"step": 3600
},
{
"epoch": 0.39729268695317227,
"grad_norm": 1.2749227285385132,
"learning_rate": 0.0001854672941289219,
"loss": 0.8157513618469239,
"step": 3610
},
{
"epoch": 0.39839322071204536,
"grad_norm": 1.3297630548477173,
"learning_rate": 0.00018537463459219187,
"loss": 0.7839149475097656,
"step": 3620
},
{
"epoch": 0.3994937544709184,
"grad_norm": 1.4063315391540527,
"learning_rate": 0.00018528170389747268,
"loss": 0.7640786170959473,
"step": 3630
},
{
"epoch": 0.40059428822979143,
"grad_norm": 1.2009915113449097,
"learning_rate": 0.0001851885023399211,
"loss": 0.8061283111572266,
"step": 3640
},
{
"epoch": 0.4016948219886645,
"grad_norm": 1.2830356359481812,
"learning_rate": 0.00018509503021555407,
"loss": 0.7541686058044433,
"step": 3650
},
{
"epoch": 0.40279535574753755,
"grad_norm": 1.621762752532959,
"learning_rate": 0.0001850012878212481,
"loss": 0.7810799598693847,
"step": 3660
},
{
"epoch": 0.4038958895064106,
"grad_norm": 1.5978320837020874,
"learning_rate": 0.00018490727545473793,
"loss": 0.7868115901947021,
"step": 3670
},
{
"epoch": 0.4049964232652837,
"grad_norm": 1.465620517730713,
"learning_rate": 0.00018481299341461583,
"loss": 0.7783832550048828,
"step": 3680
},
{
"epoch": 0.4060969570241567,
"grad_norm": 1.148144006729126,
"learning_rate": 0.00018471844200033054,
"loss": 0.7679046630859375,
"step": 3690
},
{
"epoch": 0.40719749078302975,
"grad_norm": 1.4279158115386963,
"learning_rate": 0.00018462362151218639,
"loss": 0.7669914245605469,
"step": 3700
},
{
"epoch": 0.40829802454190284,
"grad_norm": 1.4722813367843628,
"learning_rate": 0.0001845285322513423,
"loss": 0.8222566604614258,
"step": 3710
},
{
"epoch": 0.40939855830077587,
"grad_norm": 1.3982079029083252,
"learning_rate": 0.0001844331745198108,
"loss": 0.7618198871612549,
"step": 3720
},
{
"epoch": 0.4104990920596489,
"grad_norm": 1.6215136051177979,
"learning_rate": 0.00018433754862045722,
"loss": 0.7763657093048095,
"step": 3730
},
{
"epoch": 0.411599625818522,
"grad_norm": 1.5549336671829224,
"learning_rate": 0.00018424165485699852,
"loss": 0.7253801822662354,
"step": 3740
},
{
"epoch": 0.41270015957739503,
"grad_norm": 1.2889606952667236,
"learning_rate": 0.00018414549353400238,
"loss": 0.7764887332916259,
"step": 3750
},
{
"epoch": 0.41380069333626807,
"grad_norm": 1.3491219282150269,
"learning_rate": 0.00018404906495688645,
"loss": 0.7364382743835449,
"step": 3760
},
{
"epoch": 0.41490122709514116,
"grad_norm": 1.2835975885391235,
"learning_rate": 0.000183952369431917,
"loss": 0.7898456573486328,
"step": 3770
},
{
"epoch": 0.4160017608540142,
"grad_norm": 1.3867552280426025,
"learning_rate": 0.0001838554072662083,
"loss": 0.817133617401123,
"step": 3780
},
{
"epoch": 0.4171022946128872,
"grad_norm": 1.2192223072052002,
"learning_rate": 0.00018375817876772145,
"loss": 0.7515857219696045,
"step": 3790
},
{
"epoch": 0.4182028283717603,
"grad_norm": 1.2979538440704346,
"learning_rate": 0.0001836606842452634,
"loss": 0.737982702255249,
"step": 3800
},
{
"epoch": 0.41930336213063335,
"grad_norm": 1.2067734003067017,
"learning_rate": 0.00018356292400848611,
"loss": 0.7873512268066406,
"step": 3810
},
{
"epoch": 0.4204038958895064,
"grad_norm": 1.556670069694519,
"learning_rate": 0.00018346489836788542,
"loss": 0.733306884765625,
"step": 3820
},
{
"epoch": 0.4215044296483795,
"grad_norm": 1.4037160873413086,
"learning_rate": 0.00018336660763480005,
"loss": 0.8355989456176758,
"step": 3830
},
{
"epoch": 0.4226049634072525,
"grad_norm": 1.1896283626556396,
"learning_rate": 0.00018326805212141083,
"loss": 0.793169355392456,
"step": 3840
},
{
"epoch": 0.42370549716612554,
"grad_norm": 1.2549667358398438,
"learning_rate": 0.00018316923214073945,
"loss": 0.7088310718536377,
"step": 3850
},
{
"epoch": 0.42480603092499863,
"grad_norm": 1.1542037725448608,
"learning_rate": 0.0001830701480066476,
"loss": 0.7928849697113037,
"step": 3860
},
{
"epoch": 0.42590656468387167,
"grad_norm": 1.327624797821045,
"learning_rate": 0.00018297080003383594,
"loss": 0.7533132553100585,
"step": 3870
},
{
"epoch": 0.4270070984427447,
"grad_norm": 1.4689446687698364,
"learning_rate": 0.00018287118853784314,
"loss": 0.724212646484375,
"step": 3880
},
{
"epoch": 0.4281076322016178,
"grad_norm": 1.35456383228302,
"learning_rate": 0.0001827713138350448,
"loss": 0.795773983001709,
"step": 3890
},
{
"epoch": 0.42920816596049083,
"grad_norm": 1.406788945198059,
"learning_rate": 0.0001826711762426525,
"loss": 0.7669349670410156,
"step": 3900
},
{
"epoch": 0.4303086997193639,
"grad_norm": 1.3539007902145386,
"learning_rate": 0.00018257077607871286,
"loss": 0.7637516975402832,
"step": 3910
},
{
"epoch": 0.43140923347823695,
"grad_norm": 1.0722286701202393,
"learning_rate": 0.0001824701136621063,
"loss": 0.7763535022735596,
"step": 3920
},
{
"epoch": 0.43250976723711,
"grad_norm": 1.1297104358673096,
"learning_rate": 0.00018236918931254629,
"loss": 0.7475133895874023,
"step": 3930
},
{
"epoch": 0.4336103009959831,
"grad_norm": 1.2874252796173096,
"learning_rate": 0.00018226800335057822,
"loss": 0.748918867111206,
"step": 3940
},
{
"epoch": 0.4347108347548561,
"grad_norm": 1.317203402519226,
"learning_rate": 0.00018216655609757832,
"loss": 0.7373288631439209,
"step": 3950
},
{
"epoch": 0.43581136851372915,
"grad_norm": 1.4163801670074463,
"learning_rate": 0.00018206484787575283,
"loss": 0.7076706886291504,
"step": 3960
},
{
"epoch": 0.43691190227260224,
"grad_norm": 1.4905515909194946,
"learning_rate": 0.00018196287900813668,
"loss": 0.7911718845367431,
"step": 3970
},
{
"epoch": 0.43801243603147527,
"grad_norm": 1.3535404205322266,
"learning_rate": 0.00018186064981859279,
"loss": 0.7962939739227295,
"step": 3980
},
{
"epoch": 0.4391129697903483,
"grad_norm": 1.526379108428955,
"learning_rate": 0.0001817581606318108,
"loss": 0.8059768676757812,
"step": 3990
},
{
"epoch": 0.4402135035492214,
"grad_norm": 1.1382709741592407,
"learning_rate": 0.00018165541177330615,
"loss": 0.7581804752349853,
"step": 4000
},
{
"epoch": 0.4402135035492214,
"eval_loss": 0.763033926486969,
"eval_runtime": 935.846,
"eval_samples_per_second": 9.71,
"eval_steps_per_second": 2.428,
"step": 4000
},
{
"epoch": 0.44131403730809443,
"grad_norm": 1.4921393394470215,
"learning_rate": 0.00018155240356941904,
"loss": 0.7233622074127197,
"step": 4010
},
{
"epoch": 0.44241457106696747,
"grad_norm": 1.2846465110778809,
"learning_rate": 0.00018144913634731333,
"loss": 0.7926196575164794,
"step": 4020
},
{
"epoch": 0.44351510482584056,
"grad_norm": 1.5217868089675903,
"learning_rate": 0.00018134561043497556,
"loss": 0.8228995323181152,
"step": 4030
},
{
"epoch": 0.4446156385847136,
"grad_norm": 1.2717784643173218,
"learning_rate": 0.000181241826161214,
"loss": 0.787687349319458,
"step": 4040
},
{
"epoch": 0.4457161723435866,
"grad_norm": 1.4931477308273315,
"learning_rate": 0.00018113778385565733,
"loss": 0.7579782009124756,
"step": 4050
},
{
"epoch": 0.4468167061024597,
"grad_norm": 1.167993187904358,
"learning_rate": 0.00018103348384875383,
"loss": 0.7449905395507812,
"step": 4060
},
{
"epoch": 0.44791723986133275,
"grad_norm": 1.472502589225769,
"learning_rate": 0.00018092892647177035,
"loss": 0.7583009243011475,
"step": 4070
},
{
"epoch": 0.4490177736202058,
"grad_norm": 1.3440701961517334,
"learning_rate": 0.00018082411205679107,
"loss": 0.8116919517517089,
"step": 4080
},
{
"epoch": 0.4501183073790789,
"grad_norm": 1.24441397190094,
"learning_rate": 0.00018071904093671656,
"loss": 0.7991604804992676,
"step": 4090
},
{
"epoch": 0.4512188411379519,
"grad_norm": 1.3697186708450317,
"learning_rate": 0.0001806137134452627,
"loss": 0.7466158866882324,
"step": 4100
},
{
"epoch": 0.45231937489682494,
"grad_norm": 1.1649245023727417,
"learning_rate": 0.00018050812991695975,
"loss": 0.7050142288208008,
"step": 4110
},
{
"epoch": 0.45341990865569803,
"grad_norm": 1.4361720085144043,
"learning_rate": 0.00018040229068715097,
"loss": 0.7678030014038086,
"step": 4120
},
{
"epoch": 0.45452044241457107,
"grad_norm": 1.4761621952056885,
"learning_rate": 0.00018029619609199196,
"loss": 0.7187742710113525,
"step": 4130
},
{
"epoch": 0.4556209761734441,
"grad_norm": 1.1728655099868774,
"learning_rate": 0.00018018984646844919,
"loss": 0.8050548553466796,
"step": 4140
},
{
"epoch": 0.4567215099323172,
"grad_norm": 1.5159052610397339,
"learning_rate": 0.00018008324215429926,
"loss": 0.804990291595459,
"step": 4150
},
{
"epoch": 0.45782204369119023,
"grad_norm": 1.4045536518096924,
"learning_rate": 0.00017997638348812766,
"loss": 0.7503755569458008,
"step": 4160
},
{
"epoch": 0.45892257745006326,
"grad_norm": 1.1234439611434937,
"learning_rate": 0.00017986927080932766,
"loss": 0.7889124393463135,
"step": 4170
},
{
"epoch": 0.46002311120893635,
"grad_norm": 1.2261425256729126,
"learning_rate": 0.00017976190445809944,
"loss": 0.7812236785888672,
"step": 4180
},
{
"epoch": 0.4611236449678094,
"grad_norm": 1.181351900100708,
"learning_rate": 0.0001796542847754487,
"loss": 0.7701861381530761,
"step": 4190
},
{
"epoch": 0.4622241787266824,
"grad_norm": 1.577356219291687,
"learning_rate": 0.00017954641210318588,
"loss": 0.6875332832336426,
"step": 4200
},
{
"epoch": 0.4633247124855555,
"grad_norm": 1.2257264852523804,
"learning_rate": 0.0001794382867839248,
"loss": 0.742178201675415,
"step": 4210
},
{
"epoch": 0.46442524624442855,
"grad_norm": 1.547837734222412,
"learning_rate": 0.0001793299091610819,
"loss": 0.7138393878936767,
"step": 4220
},
{
"epoch": 0.4655257800033016,
"grad_norm": 1.6742470264434814,
"learning_rate": 0.00017922127957887483,
"loss": 0.7569129943847657,
"step": 4230
},
{
"epoch": 0.46662631376217467,
"grad_norm": 1.3880702257156372,
"learning_rate": 0.00017911239838232148,
"loss": 0.7724673271179199,
"step": 4240
},
{
"epoch": 0.4677268475210477,
"grad_norm": 1.5122058391571045,
"learning_rate": 0.00017900326591723892,
"loss": 0.8385299682617188,
"step": 4250
},
{
"epoch": 0.46882738127992074,
"grad_norm": 1.491855502128601,
"learning_rate": 0.00017889388253024234,
"loss": 0.7509782791137696,
"step": 4260
},
{
"epoch": 0.46992791503879383,
"grad_norm": 1.1019190549850464,
"learning_rate": 0.00017878424856874371,
"loss": 0.7592503547668457,
"step": 4270
},
{
"epoch": 0.47102844879766687,
"grad_norm": 1.318244218826294,
"learning_rate": 0.00017867436438095106,
"loss": 0.7721508979797364,
"step": 4280
},
{
"epoch": 0.4721289825565399,
"grad_norm": 1.2803703546524048,
"learning_rate": 0.000178564230315867,
"loss": 0.7693331718444825,
"step": 4290
},
{
"epoch": 0.473229516315413,
"grad_norm": 1.4658492803573608,
"learning_rate": 0.00017845384672328786,
"loss": 0.7309596061706543,
"step": 4300
},
{
"epoch": 0.474330050074286,
"grad_norm": 1.4201295375823975,
"learning_rate": 0.00017834321395380248,
"loss": 0.7964248657226562,
"step": 4310
},
{
"epoch": 0.47543058383315906,
"grad_norm": 1.3890454769134521,
"learning_rate": 0.00017823233235879105,
"loss": 0.7670300960540771,
"step": 4320
},
{
"epoch": 0.47653111759203215,
"grad_norm": 1.4585726261138916,
"learning_rate": 0.00017812120229042416,
"loss": 0.7615702629089356,
"step": 4330
},
{
"epoch": 0.4776316513509052,
"grad_norm": 1.145139217376709,
"learning_rate": 0.00017800982410166145,
"loss": 0.7336215019226074,
"step": 4340
},
{
"epoch": 0.4787321851097782,
"grad_norm": 3.134187936782837,
"learning_rate": 0.00017789819814625072,
"loss": 0.7543439865112305,
"step": 4350
},
{
"epoch": 0.4798327188686513,
"grad_norm": 1.3985061645507812,
"learning_rate": 0.00017778632477872668,
"loss": 0.7479304313659668,
"step": 4360
},
{
"epoch": 0.48093325262752434,
"grad_norm": 1.2374287843704224,
"learning_rate": 0.00017767420435440978,
"loss": 0.7452337741851807,
"step": 4370
},
{
"epoch": 0.4820337863863974,
"grad_norm": 1.2880620956420898,
"learning_rate": 0.00017756183722940518,
"loss": 0.7773733139038086,
"step": 4380
},
{
"epoch": 0.48313432014527047,
"grad_norm": 1.6610068082809448,
"learning_rate": 0.00017744922376060167,
"loss": 0.7617795944213868,
"step": 4390
},
{
"epoch": 0.4842348539041435,
"grad_norm": 1.2445658445358276,
"learning_rate": 0.0001773363643056703,
"loss": 0.7268772125244141,
"step": 4400
},
{
"epoch": 0.48533538766301654,
"grad_norm": 3.3761937618255615,
"learning_rate": 0.0001772232592230635,
"loss": 0.752207899093628,
"step": 4410
},
{
"epoch": 0.4864359214218896,
"grad_norm": 1.310644507408142,
"learning_rate": 0.00017710990887201384,
"loss": 0.7711044788360596,
"step": 4420
},
{
"epoch": 0.48753645518076266,
"grad_norm": 1.2487869262695312,
"learning_rate": 0.00017699631361253282,
"loss": 0.7602442741394043,
"step": 4430
},
{
"epoch": 0.4886369889396357,
"grad_norm": 1.426648497581482,
"learning_rate": 0.00017688247380540981,
"loss": 0.7347400188446045,
"step": 4440
},
{
"epoch": 0.4897375226985088,
"grad_norm": 1.3147786855697632,
"learning_rate": 0.00017676838981221097,
"loss": 0.7086680412292481,
"step": 4450
},
{
"epoch": 0.4908380564573818,
"grad_norm": 1.4242682456970215,
"learning_rate": 0.00017665406199527785,
"loss": 0.7723946571350098,
"step": 4460
},
{
"epoch": 0.49193859021625486,
"grad_norm": 1.2440725564956665,
"learning_rate": 0.0001765394907177266,
"loss": 0.7521542549133301,
"step": 4470
},
{
"epoch": 0.49303912397512795,
"grad_norm": 1.3089182376861572,
"learning_rate": 0.00017642467634344653,
"loss": 0.7493531703948975,
"step": 4480
},
{
"epoch": 0.494139657734001,
"grad_norm": 1.4084196090698242,
"learning_rate": 0.000176309619237099,
"loss": 0.7628543853759766,
"step": 4490
},
{
"epoch": 0.49524019149287407,
"grad_norm": 1.2576475143432617,
"learning_rate": 0.0001761943197641164,
"loss": 0.8009342193603516,
"step": 4500
},
{
"epoch": 0.4963407252517471,
"grad_norm": 1.4927014112472534,
"learning_rate": 0.00017607877829070088,
"loss": 0.764987850189209,
"step": 4510
},
{
"epoch": 0.49744125901062014,
"grad_norm": 1.210005521774292,
"learning_rate": 0.00017596299518382312,
"loss": 0.7543008327484131,
"step": 4520
},
{
"epoch": 0.49854179276949323,
"grad_norm": 1.381812334060669,
"learning_rate": 0.00017584697081122138,
"loss": 0.7667595863342285,
"step": 4530
},
{
"epoch": 0.49964232652836627,
"grad_norm": 1.330445647239685,
"learning_rate": 0.00017573070554140012,
"loss": 0.7743747711181641,
"step": 4540
},
{
"epoch": 0.5007428602872394,
"grad_norm": 1.4331225156784058,
"learning_rate": 0.00017561419974362896,
"loss": 0.7851823329925537,
"step": 4550
},
{
"epoch": 0.5018433940461123,
"grad_norm": 1.4263122081756592,
"learning_rate": 0.00017549745378794138,
"loss": 0.7313291549682617,
"step": 4560
},
{
"epoch": 0.5029439278049854,
"grad_norm": 1.331205129623413,
"learning_rate": 0.00017538046804513376,
"loss": 0.7234756946563721,
"step": 4570
},
{
"epoch": 0.5040444615638585,
"grad_norm": 1.621663212776184,
"learning_rate": 0.0001752632428867639,
"loss": 0.7894155502319335,
"step": 4580
},
{
"epoch": 0.5051449953227315,
"grad_norm": 1.5010970830917358,
"learning_rate": 0.00017514577868515016,
"loss": 0.7276608943939209,
"step": 4590
},
{
"epoch": 0.5062455290816046,
"grad_norm": 1.3064217567443848,
"learning_rate": 0.00017502807581337005,
"loss": 0.7825868606567383,
"step": 4600
},
{
"epoch": 0.5073460628404777,
"grad_norm": 1.4177016019821167,
"learning_rate": 0.00017491013464525907,
"loss": 0.7531017303466797,
"step": 4610
},
{
"epoch": 0.5084465965993507,
"grad_norm": 1.5315032005310059,
"learning_rate": 0.0001747919555554097,
"loss": 0.7451908111572265,
"step": 4620
},
{
"epoch": 0.5095471303582237,
"grad_norm": 1.3292468786239624,
"learning_rate": 0.00017467353891916995,
"loss": 0.7358492374420166,
"step": 4630
},
{
"epoch": 0.5106476641170968,
"grad_norm": 1.224372386932373,
"learning_rate": 0.0001745548851126424,
"loss": 0.7730472564697266,
"step": 4640
},
{
"epoch": 0.5117481978759698,
"grad_norm": 1.2024860382080078,
"learning_rate": 0.00017443599451268286,
"loss": 0.7512335777282715,
"step": 4650
},
{
"epoch": 0.5128487316348429,
"grad_norm": 1.1596184968948364,
"learning_rate": 0.00017431686749689923,
"loss": 0.7704591274261474,
"step": 4660
},
{
"epoch": 0.513949265393716,
"grad_norm": 1.1117010116577148,
"learning_rate": 0.00017419750444365022,
"loss": 0.7481093883514405,
"step": 4670
},
{
"epoch": 0.515049799152589,
"grad_norm": 1.269881248474121,
"learning_rate": 0.0001740779057320444,
"loss": 0.7034889221191406,
"step": 4680
},
{
"epoch": 0.5161503329114621,
"grad_norm": 1.2907774448394775,
"learning_rate": 0.00017395807174193858,
"loss": 0.7934452533721924,
"step": 4690
},
{
"epoch": 0.5172508666703352,
"grad_norm": 1.5453121662139893,
"learning_rate": 0.00017383800285393703,
"loss": 0.7363879680633545,
"step": 4700
},
{
"epoch": 0.5183514004292081,
"grad_norm": 1.2357949018478394,
"learning_rate": 0.00017371769944938997,
"loss": 0.7442324161529541,
"step": 4710
},
{
"epoch": 0.5194519341880812,
"grad_norm": 1.1931536197662354,
"learning_rate": 0.00017359716191039248,
"loss": 0.7587575912475586,
"step": 4720
},
{
"epoch": 0.5205524679469543,
"grad_norm": 1.4029440879821777,
"learning_rate": 0.0001734763906197833,
"loss": 0.7446390151977539,
"step": 4730
},
{
"epoch": 0.5216530017058273,
"grad_norm": 1.2894697189331055,
"learning_rate": 0.0001733553859611436,
"loss": 0.749908447265625,
"step": 4740
},
{
"epoch": 0.5227535354647004,
"grad_norm": 1.2883137464523315,
"learning_rate": 0.00017323414831879572,
"loss": 0.6804169178009033,
"step": 4750
},
{
"epoch": 0.5238540692235735,
"grad_norm": 1.3548226356506348,
"learning_rate": 0.00017311267807780198,
"loss": 0.7411623001098633,
"step": 4760
},
{
"epoch": 0.5249546029824464,
"grad_norm": 1.3655985593795776,
"learning_rate": 0.00017299097562396344,
"loss": 0.7595492839813233,
"step": 4770
},
{
"epoch": 0.5260551367413195,
"grad_norm": 1.2662074565887451,
"learning_rate": 0.00017286904134381875,
"loss": 0.7716023445129394,
"step": 4780
},
{
"epoch": 0.5271556705001926,
"grad_norm": 1.151781439781189,
"learning_rate": 0.00017274687562464277,
"loss": 0.764620018005371,
"step": 4790
},
{
"epoch": 0.5282562042590656,
"grad_norm": 1.2629897594451904,
"learning_rate": 0.00017262447885444554,
"loss": 0.699459457397461,
"step": 4800
},
{
"epoch": 0.5293567380179387,
"grad_norm": 1.3501882553100586,
"learning_rate": 0.00017250185142197086,
"loss": 0.7289613246917724,
"step": 4810
},
{
"epoch": 0.5304572717768118,
"grad_norm": 1.4207645654678345,
"learning_rate": 0.00017237899371669516,
"loss": 0.7605480194091797,
"step": 4820
},
{
"epoch": 0.5315578055356848,
"grad_norm": 1.2983626127243042,
"learning_rate": 0.00017225590612882625,
"loss": 0.7970122814178466,
"step": 4830
},
{
"epoch": 0.5326583392945579,
"grad_norm": 1.3569053411483765,
"learning_rate": 0.00017213258904930206,
"loss": 0.7394134521484375,
"step": 4840
},
{
"epoch": 0.533758873053431,
"grad_norm": 1.1259307861328125,
"learning_rate": 0.0001720090428697894,
"loss": 0.7425519943237304,
"step": 4850
},
{
"epoch": 0.5348594068123039,
"grad_norm": 1.453172206878662,
"learning_rate": 0.0001718852679826827,
"loss": 0.8017748832702637,
"step": 4860
},
{
"epoch": 0.535959940571177,
"grad_norm": 1.2578952312469482,
"learning_rate": 0.00017176126478110287,
"loss": 0.7838920593261719,
"step": 4870
},
{
"epoch": 0.5370604743300501,
"grad_norm": 1.722364068031311,
"learning_rate": 0.00017163703365889588,
"loss": 0.7111594200134277,
"step": 4880
},
{
"epoch": 0.5381610080889231,
"grad_norm": 1.3256832361221313,
"learning_rate": 0.00017151257501063166,
"loss": 0.73086576461792,
"step": 4890
},
{
"epoch": 0.5392615418477962,
"grad_norm": 1.2753175497055054,
"learning_rate": 0.00017138788923160277,
"loss": 0.7703966617584228,
"step": 4900
},
{
"epoch": 0.5403620756066693,
"grad_norm": 1.411819338798523,
"learning_rate": 0.00017126297671782306,
"loss": 0.7726946353912354,
"step": 4910
},
{
"epoch": 0.5414626093655422,
"grad_norm": 1.4981974363327026,
"learning_rate": 0.0001711378378660267,
"loss": 0.7375073909759522,
"step": 4920
},
{
"epoch": 0.5425631431244153,
"grad_norm": 1.4701440334320068,
"learning_rate": 0.00017101247307366654,
"loss": 0.7389264583587647,
"step": 4930
},
{
"epoch": 0.5436636768832884,
"grad_norm": 1.4490705728530884,
"learning_rate": 0.0001708868827389132,
"loss": 0.7916615962982178,
"step": 4940
},
{
"epoch": 0.5447642106421614,
"grad_norm": 1.5919363498687744,
"learning_rate": 0.00017076106726065355,
"loss": 0.7363606929779053,
"step": 4950
},
{
"epoch": 0.5458647444010345,
"grad_norm": 1.5221658945083618,
"learning_rate": 0.00017063502703848954,
"loss": 0.756117582321167,
"step": 4960
},
{
"epoch": 0.5469652781599076,
"grad_norm": 1.3419508934020996,
"learning_rate": 0.00017050876247273698,
"loss": 0.7674195766448975,
"step": 4970
},
{
"epoch": 0.5480658119187806,
"grad_norm": 1.1585789918899536,
"learning_rate": 0.00017038227396442415,
"loss": 0.7340216159820556,
"step": 4980
},
{
"epoch": 0.5491663456776537,
"grad_norm": 1.4809222221374512,
"learning_rate": 0.00017025556191529063,
"loss": 0.7714733600616455,
"step": 4990
},
{
"epoch": 0.5502668794365267,
"grad_norm": 1.363792061805725,
"learning_rate": 0.000170128626727786,
"loss": 0.7531471252441406,
"step": 5000
},
{
"epoch": 0.5502668794365267,
"eval_loss": 0.7419883012771606,
"eval_runtime": 934.9404,
"eval_samples_per_second": 9.719,
"eval_steps_per_second": 2.43,
"step": 5000
},
{
"epoch": 0.5513674131953997,
"grad_norm": 1.3879987001419067,
"learning_rate": 0.00017000146880506852,
"loss": 0.7755624294281006,
"step": 5010
},
{
"epoch": 0.5524679469542728,
"grad_norm": 1.1908470392227173,
"learning_rate": 0.00016987408855100394,
"loss": 0.6974857807159424,
"step": 5020
},
{
"epoch": 0.5535684807131459,
"grad_norm": 1.3515280485153198,
"learning_rate": 0.00016974648637016403,
"loss": 0.7421687126159668,
"step": 5030
},
{
"epoch": 0.5546690144720189,
"grad_norm": 1.3259779214859009,
"learning_rate": 0.00016961866266782555,
"loss": 0.77330641746521,
"step": 5040
},
{
"epoch": 0.555769548230892,
"grad_norm": 1.1782556772232056,
"learning_rate": 0.00016949061784996876,
"loss": 0.7333382129669189,
"step": 5050
},
{
"epoch": 0.5568700819897651,
"grad_norm": 1.1794569492340088,
"learning_rate": 0.0001693623523232762,
"loss": 0.7309277534484864,
"step": 5060
},
{
"epoch": 0.557970615748638,
"grad_norm": 1.4677120447158813,
"learning_rate": 0.00016923386649513148,
"loss": 0.7762013435363769,
"step": 5070
},
{
"epoch": 0.5590711495075111,
"grad_norm": 1.354422926902771,
"learning_rate": 0.00016910516077361782,
"loss": 0.7435779094696044,
"step": 5080
},
{
"epoch": 0.5601716832663842,
"grad_norm": 1.281956672668457,
"learning_rate": 0.0001689762355675169,
"loss": 0.7566828250885009,
"step": 5090
},
{
"epoch": 0.5612722170252572,
"grad_norm": 1.7170436382293701,
"learning_rate": 0.00016884709128630744,
"loss": 0.7960678577423096,
"step": 5100
},
{
"epoch": 0.5623727507841303,
"grad_norm": 1.4090797901153564,
"learning_rate": 0.00016871772834016406,
"loss": 0.7969419479370117,
"step": 5110
},
{
"epoch": 0.5634732845430034,
"grad_norm": 1.6792510747909546,
"learning_rate": 0.0001685881471399558,
"loss": 0.7243700504302979,
"step": 5120
},
{
"epoch": 0.5645738183018764,
"grad_norm": 1.589468002319336,
"learning_rate": 0.0001684583480972449,
"loss": 0.6752159118652343,
"step": 5130
},
{
"epoch": 0.5656743520607495,
"grad_norm": 1.2133830785751343,
"learning_rate": 0.00016832833162428555,
"loss": 0.7530373573303223,
"step": 5140
},
{
"epoch": 0.5667748858196225,
"grad_norm": 1.402968168258667,
"learning_rate": 0.00016819809813402244,
"loss": 0.7213272094726563,
"step": 5150
},
{
"epoch": 0.5678754195784955,
"grad_norm": 1.7174259424209595,
"learning_rate": 0.0001680676480400896,
"loss": 0.7200131416320801,
"step": 5160
},
{
"epoch": 0.5689759533373686,
"grad_norm": 1.206224799156189,
"learning_rate": 0.00016793698175680895,
"loss": 0.7772294521331787,
"step": 5170
},
{
"epoch": 0.5700764870962417,
"grad_norm": 1.2895069122314453,
"learning_rate": 0.0001678060996991891,
"loss": 0.7059802532196044,
"step": 5180
},
{
"epoch": 0.5711770208551147,
"grad_norm": 1.3851865530014038,
"learning_rate": 0.00016767500228292395,
"loss": 0.7481937408447266,
"step": 5190
},
{
"epoch": 0.5722775546139878,
"grad_norm": 1.5495299100875854,
"learning_rate": 0.00016754368992439144,
"loss": 0.7860031604766846,
"step": 5200
},
{
"epoch": 0.5733780883728609,
"grad_norm": 1.0802173614501953,
"learning_rate": 0.0001674121630406521,
"loss": 0.7575831890106202,
"step": 5210
},
{
"epoch": 0.5744786221317338,
"grad_norm": 1.283719778060913,
"learning_rate": 0.00016728042204944792,
"loss": 0.7304069519042968,
"step": 5220
},
{
"epoch": 0.5755791558906069,
"grad_norm": 1.291081428527832,
"learning_rate": 0.00016714846736920081,
"loss": 0.6965278148651123,
"step": 5230
},
{
"epoch": 0.57667968964948,
"grad_norm": 2.7866170406341553,
"learning_rate": 0.00016701629941901148,
"loss": 0.7350920677185059,
"step": 5240
},
{
"epoch": 0.577780223408353,
"grad_norm": 1.5153194665908813,
"learning_rate": 0.00016688391861865794,
"loss": 0.7063103199005127,
"step": 5250
},
{
"epoch": 0.5788807571672261,
"grad_norm": 1.8427544832229614,
"learning_rate": 0.00016675132538859425,
"loss": 0.7724103450775146,
"step": 5260
},
{
"epoch": 0.5799812909260992,
"grad_norm": 1.2077882289886475,
"learning_rate": 0.00016661852014994918,
"loss": 0.7549758434295655,
"step": 5270
},
{
"epoch": 0.5810818246849722,
"grad_norm": 1.4017447233200073,
"learning_rate": 0.0001664855033245248,
"loss": 0.7112679481506348,
"step": 5280
},
{
"epoch": 0.5821823584438452,
"grad_norm": 1.3323004245758057,
"learning_rate": 0.00016635227533479526,
"loss": 0.673241138458252,
"step": 5290
},
{
"epoch": 0.5832828922027183,
"grad_norm": 1.6625175476074219,
"learning_rate": 0.00016621883660390541,
"loss": 0.7120931148529053,
"step": 5300
},
{
"epoch": 0.5843834259615913,
"grad_norm": 1.3365366458892822,
"learning_rate": 0.00016608518755566935,
"loss": 0.726066780090332,
"step": 5310
},
{
"epoch": 0.5854839597204644,
"grad_norm": 2.1613974571228027,
"learning_rate": 0.00016595132861456927,
"loss": 0.7196171760559082,
"step": 5320
},
{
"epoch": 0.5865844934793375,
"grad_norm": 1.333061933517456,
"learning_rate": 0.0001658172602057539,
"loss": 0.7693576812744141,
"step": 5330
},
{
"epoch": 0.5876850272382105,
"grad_norm": 1.3722368478775024,
"learning_rate": 0.0001656829827550373,
"loss": 0.7160601615905762,
"step": 5340
},
{
"epoch": 0.5887855609970836,
"grad_norm": 2.5283138751983643,
"learning_rate": 0.0001655484966888975,
"loss": 0.7215074062347412,
"step": 5350
},
{
"epoch": 0.5898860947559567,
"grad_norm": 1.2876371145248413,
"learning_rate": 0.0001654138024344751,
"loss": 0.7553225040435791,
"step": 5360
},
{
"epoch": 0.5909866285148296,
"grad_norm": 1.3598158359527588,
"learning_rate": 0.00016527890041957184,
"loss": 0.7447906970977783,
"step": 5370
},
{
"epoch": 0.5920871622737027,
"grad_norm": 1.4216128587722778,
"learning_rate": 0.00016514379107264944,
"loss": 0.6964402675628663,
"step": 5380
},
{
"epoch": 0.5931876960325758,
"grad_norm": 1.262564778327942,
"learning_rate": 0.0001650084748228281,
"loss": 0.7048509120941162,
"step": 5390
},
{
"epoch": 0.5942882297914489,
"grad_norm": 1.6969469785690308,
"learning_rate": 0.00016487295209988511,
"loss": 0.7238675117492676,
"step": 5400
},
{
"epoch": 0.5953887635503219,
"grad_norm": 1.38680899143219,
"learning_rate": 0.00016473722333425363,
"loss": 0.755061674118042,
"step": 5410
},
{
"epoch": 0.596489297309195,
"grad_norm": 1.3030256032943726,
"learning_rate": 0.0001646012889570211,
"loss": 0.7230662822723388,
"step": 5420
},
{
"epoch": 0.5975898310680681,
"grad_norm": 2.8049333095550537,
"learning_rate": 0.00016446514939992814,
"loss": 0.7024547576904296,
"step": 5430
},
{
"epoch": 0.598690364826941,
"grad_norm": 1.2925546169281006,
"learning_rate": 0.00016432880509536694,
"loss": 0.7584189414978028,
"step": 5440
},
{
"epoch": 0.5997908985858141,
"grad_norm": 1.4285222291946411,
"learning_rate": 0.00016419225647638008,
"loss": 0.6970412731170654,
"step": 5450
},
{
"epoch": 0.6008914323446872,
"grad_norm": 1.9083236455917358,
"learning_rate": 0.0001640555039766589,
"loss": 0.7205626964569092,
"step": 5460
},
{
"epoch": 0.6019919661035602,
"grad_norm": 1.4175890684127808,
"learning_rate": 0.00016391854803054253,
"loss": 0.6843720436096191,
"step": 5470
},
{
"epoch": 0.6030924998624333,
"grad_norm": 1.6256078481674194,
"learning_rate": 0.00016378138907301604,
"loss": 0.7570401191711426,
"step": 5480
},
{
"epoch": 0.6041930336213064,
"grad_norm": 1.299574851989746,
"learning_rate": 0.0001636440275397094,
"loss": 0.7056687355041504,
"step": 5490
},
{
"epoch": 0.6052935673801794,
"grad_norm": 1.8576395511627197,
"learning_rate": 0.00016350646386689593,
"loss": 0.7708197116851807,
"step": 5500
},
{
"epoch": 0.6063941011390525,
"grad_norm": 1.2749172449111938,
"learning_rate": 0.00016336869849149105,
"loss": 0.7359384059906006,
"step": 5510
},
{
"epoch": 0.6074946348979255,
"grad_norm": 1.502797245979309,
"learning_rate": 0.00016323073185105065,
"loss": 0.7268924713134766,
"step": 5520
},
{
"epoch": 0.6085951686567985,
"grad_norm": 1.2893123626708984,
"learning_rate": 0.00016309256438377004,
"loss": 0.7836434841156006,
"step": 5530
},
{
"epoch": 0.6096957024156716,
"grad_norm": 1.6940971612930298,
"learning_rate": 0.0001629541965284822,
"loss": 0.7172956943511963,
"step": 5540
},
{
"epoch": 0.6107962361745447,
"grad_norm": 1.4099256992340088,
"learning_rate": 0.0001628156287246567,
"loss": 0.7529633522033692,
"step": 5550
},
{
"epoch": 0.6118967699334177,
"grad_norm": 1.2283318042755127,
"learning_rate": 0.00016267686141239812,
"loss": 0.7456967830657959,
"step": 5560
},
{
"epoch": 0.6129973036922908,
"grad_norm": 1.584608554840088,
"learning_rate": 0.00016253789503244465,
"loss": 0.7123336791992188,
"step": 5570
},
{
"epoch": 0.6140978374511639,
"grad_norm": 1.2020970582962036,
"learning_rate": 0.0001623987300261668,
"loss": 0.7346308708190918,
"step": 5580
},
{
"epoch": 0.6151983712100368,
"grad_norm": 1.375866174697876,
"learning_rate": 0.00016225936683556593,
"loss": 0.7147591590881348,
"step": 5590
},
{
"epoch": 0.6162989049689099,
"grad_norm": 3.002707004547119,
"learning_rate": 0.0001621198059032728,
"loss": 0.7241267204284668,
"step": 5600
},
{
"epoch": 0.617399438727783,
"grad_norm": 1.3746256828308105,
"learning_rate": 0.0001619800476725463,
"loss": 0.7762519359588623,
"step": 5610
},
{
"epoch": 0.618499972486656,
"grad_norm": 2.4465384483337402,
"learning_rate": 0.00016184009258727187,
"loss": 0.7804543018341065,
"step": 5620
},
{
"epoch": 0.6196005062455291,
"grad_norm": 1.2646642923355103,
"learning_rate": 0.00016169994109196023,
"loss": 0.744245958328247,
"step": 5630
},
{
"epoch": 0.6207010400044022,
"grad_norm": 1.3681907653808594,
"learning_rate": 0.00016155959363174592,
"loss": 0.7360111713409424,
"step": 5640
},
{
"epoch": 0.6218015737632752,
"grad_norm": 1.1509507894515991,
"learning_rate": 0.00016141905065238587,
"loss": 0.713913106918335,
"step": 5650
},
{
"epoch": 0.6229021075221483,
"grad_norm": 1.4058045148849487,
"learning_rate": 0.00016127831260025799,
"loss": 0.7003890037536621,
"step": 5660
},
{
"epoch": 0.6240026412810213,
"grad_norm": 1.3103810548782349,
"learning_rate": 0.0001611373799223598,
"loss": 0.7160762310028076,
"step": 5670
},
{
"epoch": 0.6251031750398943,
"grad_norm": 1.4053767919540405,
"learning_rate": 0.00016099625306630687,
"loss": 0.7399090766906739,
"step": 5680
},
{
"epoch": 0.6262037087987674,
"grad_norm": 1.4424643516540527,
"learning_rate": 0.00016085493248033163,
"loss": 0.7122686386108399,
"step": 5690
},
{
"epoch": 0.6273042425576405,
"grad_norm": 1.495091438293457,
"learning_rate": 0.0001607134186132817,
"loss": 0.7723418235778808,
"step": 5700
},
{
"epoch": 0.6284047763165135,
"grad_norm": 1.9233251810073853,
"learning_rate": 0.00016057171191461868,
"loss": 0.7351515769958497,
"step": 5710
},
{
"epoch": 0.6295053100753866,
"grad_norm": 1.3022968769073486,
"learning_rate": 0.00016042981283441655,
"loss": 0.7153616428375245,
"step": 5720
},
{
"epoch": 0.6306058438342597,
"grad_norm": 1.5664523839950562,
"learning_rate": 0.00016028772182336034,
"loss": 0.781205701828003,
"step": 5730
},
{
"epoch": 0.6317063775931326,
"grad_norm": 1.485307216644287,
"learning_rate": 0.00016014543933274466,
"loss": 0.7299734115600586,
"step": 5740
},
{
"epoch": 0.6328069113520057,
"grad_norm": 1.2536561489105225,
"learning_rate": 0.00016000296581447225,
"loss": 0.7220814228057861,
"step": 5750
},
{
"epoch": 0.6339074451108788,
"grad_norm": 1.4910413026809692,
"learning_rate": 0.00015986030172105266,
"loss": 0.7590044498443603,
"step": 5760
},
{
"epoch": 0.6350079788697518,
"grad_norm": 1.5727530717849731,
"learning_rate": 0.00015971744750560064,
"loss": 0.6608116149902343,
"step": 5770
},
{
"epoch": 0.6361085126286249,
"grad_norm": 1.3321911096572876,
"learning_rate": 0.00015957440362183485,
"loss": 0.7006593704223633,
"step": 5780
},
{
"epoch": 0.637209046387498,
"grad_norm": 1.6716225147247314,
"learning_rate": 0.00015943117052407625,
"loss": 0.759761381149292,
"step": 5790
},
{
"epoch": 0.638309580146371,
"grad_norm": 1.342505693435669,
"learning_rate": 0.0001592877486672469,
"loss": 0.7411152362823487,
"step": 5800
},
{
"epoch": 0.639410113905244,
"grad_norm": 1.4138150215148926,
"learning_rate": 0.00015914413850686828,
"loss": 0.7032299995422363,
"step": 5810
},
{
"epoch": 0.6405106476641171,
"grad_norm": 1.3087942600250244,
"learning_rate": 0.00015900034049905993,
"loss": 0.6844950199127198,
"step": 5820
},
{
"epoch": 0.6416111814229901,
"grad_norm": 1.1978130340576172,
"learning_rate": 0.0001588563551005381,
"loss": 0.7046521186828614,
"step": 5830
},
{
"epoch": 0.6427117151818632,
"grad_norm": 1.4054518938064575,
"learning_rate": 0.00015871218276861416,
"loss": 0.7417028427124024,
"step": 5840
},
{
"epoch": 0.6438122489407363,
"grad_norm": 1.4107232093811035,
"learning_rate": 0.0001585678239611932,
"loss": 0.7251378536224365,
"step": 5850
},
{
"epoch": 0.6449127826996093,
"grad_norm": 1.2596750259399414,
"learning_rate": 0.00015842327913677252,
"loss": 0.7766359329223633,
"step": 5860
},
{
"epoch": 0.6460133164584824,
"grad_norm": 1.2053841352462769,
"learning_rate": 0.00015827854875444036,
"loss": 0.6772095203399658,
"step": 5870
},
{
"epoch": 0.6471138502173555,
"grad_norm": 1.432888150215149,
"learning_rate": 0.00015813363327387415,
"loss": 0.772012996673584,
"step": 5880
},
{
"epoch": 0.6482143839762284,
"grad_norm": 1.5003931522369385,
"learning_rate": 0.00015798853315533931,
"loss": 0.740192985534668,
"step": 5890
},
{
"epoch": 0.6493149177351015,
"grad_norm": 1.4617244005203247,
"learning_rate": 0.00015784324885968775,
"loss": 0.7542769908905029,
"step": 5900
},
{
"epoch": 0.6504154514939746,
"grad_norm": 1.3754563331604004,
"learning_rate": 0.00015769778084835615,
"loss": 0.7268834114074707,
"step": 5910
},
{
"epoch": 0.6515159852528476,
"grad_norm": 1.3474271297454834,
"learning_rate": 0.00015755212958336488,
"loss": 0.7852190017700196,
"step": 5920
},
{
"epoch": 0.6526165190117207,
"grad_norm": 1.2138652801513672,
"learning_rate": 0.0001574062955273162,
"loss": 0.7471586227416992,
"step": 5930
},
{
"epoch": 0.6537170527705938,
"grad_norm": 1.2696701288223267,
"learning_rate": 0.00015726027914339302,
"loss": 0.667238712310791,
"step": 5940
},
{
"epoch": 0.6548175865294668,
"grad_norm": 1.6794250011444092,
"learning_rate": 0.00015711408089535733,
"loss": 0.7339349269866944,
"step": 5950
},
{
"epoch": 0.6559181202883398,
"grad_norm": 1.243056058883667,
"learning_rate": 0.00015696770124754873,
"loss": 0.8075173377990723,
"step": 5960
},
{
"epoch": 0.6570186540472129,
"grad_norm": 1.385141134262085,
"learning_rate": 0.00015682114066488292,
"loss": 0.7466262817382813,
"step": 5970
},
{
"epoch": 0.6581191878060859,
"grad_norm": 1.2319458723068237,
"learning_rate": 0.00015667439961285028,
"loss": 0.7330340385437012,
"step": 5980
},
{
"epoch": 0.659219721564959,
"grad_norm": 1.4220091104507446,
"learning_rate": 0.00015652747855751447,
"loss": 0.73863205909729,
"step": 5990
},
{
"epoch": 0.6603202553238321,
"grad_norm": 1.4125266075134277,
"learning_rate": 0.00015638037796551074,
"loss": 0.7317982673645019,
"step": 6000
},
{
"epoch": 0.6603202553238321,
"eval_loss": 0.7154231071472168,
"eval_runtime": 936.9703,
"eval_samples_per_second": 9.698,
"eval_steps_per_second": 2.425,
"step": 6000
},
{
"epoch": 0.6614207890827051,
"grad_norm": 1.248883605003357,
"learning_rate": 0.00015623309830404457,
"loss": 0.709596586227417,
"step": 6010
},
{
"epoch": 0.6625213228415782,
"grad_norm": 1.1572697162628174,
"learning_rate": 0.00015608564004089033,
"loss": 0.6387454986572265,
"step": 6020
},
{
"epoch": 0.6636218566004513,
"grad_norm": 1.974361777305603,
"learning_rate": 0.00015593800364438947,
"loss": 0.6919140338897705,
"step": 6030
},
{
"epoch": 0.6647223903593242,
"grad_norm": 1.510246753692627,
"learning_rate": 0.00015579018958344928,
"loss": 0.7729711532592773,
"step": 6040
},
{
"epoch": 0.6658229241181973,
"grad_norm": 1.1816668510437012,
"learning_rate": 0.00015564219832754135,
"loss": 0.7235398292541504,
"step": 6050
},
{
"epoch": 0.6669234578770704,
"grad_norm": 2.0719385147094727,
"learning_rate": 0.00015549403034670003,
"loss": 0.7236655712127685,
"step": 6060
},
{
"epoch": 0.6680239916359434,
"grad_norm": 1.3846322298049927,
"learning_rate": 0.00015534568611152096,
"loss": 0.7563097953796387,
"step": 6070
},
{
"epoch": 0.6691245253948165,
"grad_norm": 1.3005784749984741,
"learning_rate": 0.0001551971660931596,
"loss": 0.6728219509124755,
"step": 6080
},
{
"epoch": 0.6702250591536896,
"grad_norm": 1.6612495183944702,
"learning_rate": 0.0001550484707633297,
"loss": 0.7208469867706299,
"step": 6090
},
{
"epoch": 0.6713255929125626,
"grad_norm": 1.536747932434082,
"learning_rate": 0.00015489960059430184,
"loss": 0.7596847534179687,
"step": 6100
},
{
"epoch": 0.6724261266714356,
"grad_norm": 1.2718262672424316,
"learning_rate": 0.00015475055605890185,
"loss": 0.728467607498169,
"step": 6110
},
{
"epoch": 0.6735266604303087,
"grad_norm": 1.2997578382492065,
"learning_rate": 0.00015460133763050947,
"loss": 0.6834435939788819,
"step": 6120
},
{
"epoch": 0.6746271941891817,
"grad_norm": 1.2644582986831665,
"learning_rate": 0.00015445194578305658,
"loss": 0.6802155017852783,
"step": 6130
},
{
"epoch": 0.6757277279480548,
"grad_norm": 1.3019027709960938,
"learning_rate": 0.00015430238099102601,
"loss": 0.6821646213531494,
"step": 6140
},
{
"epoch": 0.6768282617069279,
"grad_norm": 1.2540215253829956,
"learning_rate": 0.00015415264372944983,
"loss": 0.7386213302612304,
"step": 6150
},
{
"epoch": 0.6779287954658009,
"grad_norm": 1.2781347036361694,
"learning_rate": 0.0001540027344739078,
"loss": 0.76524658203125,
"step": 6160
},
{
"epoch": 0.679029329224674,
"grad_norm": 1.3025370836257935,
"learning_rate": 0.0001538526537005261,
"loss": 0.7432229042053222,
"step": 6170
},
{
"epoch": 0.680129862983547,
"grad_norm": 1.178902506828308,
"learning_rate": 0.0001537024018859756,
"loss": 0.7016994953155518,
"step": 6180
},
{
"epoch": 0.68123039674242,
"grad_norm": 1.3114815950393677,
"learning_rate": 0.0001535519795074703,
"loss": 0.731592321395874,
"step": 6190
},
{
"epoch": 0.6823309305012931,
"grad_norm": 1.7339528799057007,
"learning_rate": 0.0001534013870427662,
"loss": 0.7412378787994385,
"step": 6200
},
{
"epoch": 0.6834314642601662,
"grad_norm": 1.2772549390792847,
"learning_rate": 0.00015325062497015916,
"loss": 0.7278597354888916,
"step": 6210
},
{
"epoch": 0.6845319980190392,
"grad_norm": 1.119942545890808,
"learning_rate": 0.00015309969376848406,
"loss": 0.6550940036773681,
"step": 6220
},
{
"epoch": 0.6856325317779123,
"grad_norm": 1.7672674655914307,
"learning_rate": 0.00015294859391711273,
"loss": 0.6876314640045166,
"step": 6230
},
{
"epoch": 0.6867330655367854,
"grad_norm": 1.5041821002960205,
"learning_rate": 0.00015279732589595276,
"loss": 0.7159430503845214,
"step": 6240
},
{
"epoch": 0.6878335992956583,
"grad_norm": 1.3722065687179565,
"learning_rate": 0.00015264589018544578,
"loss": 0.689654541015625,
"step": 6250
},
{
"epoch": 0.6889341330545314,
"grad_norm": 1.4130030870437622,
"learning_rate": 0.0001524942872665661,
"loss": 0.779707956314087,
"step": 6260
},
{
"epoch": 0.6900346668134045,
"grad_norm": 1.3028900623321533,
"learning_rate": 0.000152342517620819,
"loss": 0.7033322811126709,
"step": 6270
},
{
"epoch": 0.6911352005722775,
"grad_norm": 1.2611339092254639,
"learning_rate": 0.0001521905817302395,
"loss": 0.7246399402618409,
"step": 6280
},
{
"epoch": 0.6922357343311506,
"grad_norm": 1.3958343267440796,
"learning_rate": 0.00015203848007739034,
"loss": 0.7422275543212891,
"step": 6290
},
{
"epoch": 0.6933362680900237,
"grad_norm": 1.3530064821243286,
"learning_rate": 0.00015188621314536098,
"loss": 0.7618152141571045,
"step": 6300
},
{
"epoch": 0.6944368018488967,
"grad_norm": 1.2685966491699219,
"learning_rate": 0.00015173378141776568,
"loss": 0.7283220767974854,
"step": 6310
},
{
"epoch": 0.6955373356077698,
"grad_norm": 1.5027806758880615,
"learning_rate": 0.0001515811853787422,
"loss": 0.6772040843963623,
"step": 6320
},
{
"epoch": 0.6966378693666428,
"grad_norm": 1.2491596937179565,
"learning_rate": 0.0001514284255129501,
"loss": 0.7292652130126953,
"step": 6330
},
{
"epoch": 0.6977384031255158,
"grad_norm": 1.2554333209991455,
"learning_rate": 0.00015127550230556932,
"loss": 0.6931362628936768,
"step": 6340
},
{
"epoch": 0.6988389368843889,
"grad_norm": 1.34043288230896,
"learning_rate": 0.00015112241624229856,
"loss": 0.7329248428344727,
"step": 6350
},
{
"epoch": 0.699939470643262,
"grad_norm": 1.1904277801513672,
"learning_rate": 0.00015096916780935372,
"loss": 0.7226557254791259,
"step": 6360
},
{
"epoch": 0.701040004402135,
"grad_norm": 1.2233314514160156,
"learning_rate": 0.0001508157574934665,
"loss": 0.7005710124969482,
"step": 6370
},
{
"epoch": 0.7021405381610081,
"grad_norm": 1.4783847332000732,
"learning_rate": 0.00015066218578188272,
"loss": 0.7101388454437256,
"step": 6380
},
{
"epoch": 0.7032410719198812,
"grad_norm": 1.2805193662643433,
"learning_rate": 0.00015050845316236076,
"loss": 0.7289349555969238,
"step": 6390
},
{
"epoch": 0.7043416056787541,
"grad_norm": 1.3018475770950317,
"learning_rate": 0.0001503545601231701,
"loss": 0.713924503326416,
"step": 6400
},
{
"epoch": 0.7054421394376272,
"grad_norm": 1.3639897108078003,
"learning_rate": 0.00015020050715308972,
"loss": 0.6581418514251709,
"step": 6410
},
{
"epoch": 0.7065426731965003,
"grad_norm": 1.4128023386001587,
"learning_rate": 0.0001500462947414066,
"loss": 0.7135940074920655,
"step": 6420
},
{
"epoch": 0.7076432069553733,
"grad_norm": 1.2122293710708618,
"learning_rate": 0.00014989192337791404,
"loss": 0.7303122997283935,
"step": 6430
},
{
"epoch": 0.7087437407142464,
"grad_norm": 1.1786285638809204,
"learning_rate": 0.00014973739355291022,
"loss": 0.7025662422180176,
"step": 6440
},
{
"epoch": 0.7098442744731195,
"grad_norm": 1.3302885293960571,
"learning_rate": 0.00014958270575719668,
"loss": 0.7187159538269043,
"step": 6450
},
{
"epoch": 0.7109448082319925,
"grad_norm": 1.4084340333938599,
"learning_rate": 0.00014942786048207656,
"loss": 0.725886344909668,
"step": 6460
},
{
"epoch": 0.7120453419908656,
"grad_norm": 1.2113697528839111,
"learning_rate": 0.0001492728582193532,
"loss": 0.7125999450683593,
"step": 6470
},
{
"epoch": 0.7131458757497386,
"grad_norm": 1.41702401638031,
"learning_rate": 0.0001491176994613287,
"loss": 0.6910535335540772,
"step": 6480
},
{
"epoch": 0.7142464095086116,
"grad_norm": 1.6196422576904297,
"learning_rate": 0.00014896238470080196,
"loss": 0.7285680770874023,
"step": 6490
},
{
"epoch": 0.7153469432674847,
"grad_norm": 1.186160922050476,
"learning_rate": 0.00014880691443106762,
"loss": 0.7270355701446534,
"step": 6500
},
{
"epoch": 0.7164474770263578,
"grad_norm": 1.3876869678497314,
"learning_rate": 0.00014865128914591397,
"loss": 0.6556861877441407,
"step": 6510
},
{
"epoch": 0.7175480107852308,
"grad_norm": 1.2404990196228027,
"learning_rate": 0.00014849550933962186,
"loss": 0.6614561557769776,
"step": 6520
},
{
"epoch": 0.7186485445441039,
"grad_norm": 1.5126335620880127,
"learning_rate": 0.00014833957550696277,
"loss": 0.6966361045837403,
"step": 6530
},
{
"epoch": 0.719749078302977,
"grad_norm": 1.2630326747894287,
"learning_rate": 0.00014818348814319747,
"loss": 0.7556998252868652,
"step": 6540
},
{
"epoch": 0.7208496120618499,
"grad_norm": 1.3583987951278687,
"learning_rate": 0.00014802724774407432,
"loss": 0.707868242263794,
"step": 6550
},
{
"epoch": 0.721950145820723,
"grad_norm": 1.3609402179718018,
"learning_rate": 0.00014787085480582772,
"loss": 0.7230880737304688,
"step": 6560
},
{
"epoch": 0.7230506795795961,
"grad_norm": 1.1819531917572021,
"learning_rate": 0.00014771430982517662,
"loss": 0.6786688804626465,
"step": 6570
},
{
"epoch": 0.7241512133384692,
"grad_norm": 1.2774471044540405,
"learning_rate": 0.00014755761329932274,
"loss": 0.7156373977661132,
"step": 6580
},
{
"epoch": 0.7252517470973422,
"grad_norm": 1.375931739807129,
"learning_rate": 0.0001474007657259493,
"loss": 0.7217991828918457,
"step": 6590
},
{
"epoch": 0.7263522808562153,
"grad_norm": 1.1880601644515991,
"learning_rate": 0.0001472437676032191,
"loss": 0.7250751495361328,
"step": 6600
},
{
"epoch": 0.7274528146150884,
"grad_norm": 2.0583808422088623,
"learning_rate": 0.0001470866194297732,
"loss": 0.6847675800323486,
"step": 6610
},
{
"epoch": 0.7285533483739614,
"grad_norm": 1.3453950881958008,
"learning_rate": 0.0001469293217047292,
"loss": 0.7251123428344727,
"step": 6620
},
{
"epoch": 0.7296538821328344,
"grad_norm": 1.527479887008667,
"learning_rate": 0.00014677187492767964,
"loss": 0.6714204311370849,
"step": 6630
},
{
"epoch": 0.7307544158917075,
"grad_norm": 1.5210182666778564,
"learning_rate": 0.00014661427959869057,
"loss": 0.6623645782470703,
"step": 6640
},
{
"epoch": 0.7318549496505805,
"grad_norm": 1.4670600891113281,
"learning_rate": 0.00014645653621829977,
"loss": 0.6705510139465332,
"step": 6650
},
{
"epoch": 0.7329554834094536,
"grad_norm": 1.5107208490371704,
"learning_rate": 0.00014629864528751526,
"loss": 0.6907163619995117,
"step": 6660
},
{
"epoch": 0.7340560171683267,
"grad_norm": 1.3847161531448364,
"learning_rate": 0.00014614060730781377,
"loss": 0.6747828960418701,
"step": 6670
},
{
"epoch": 0.7351565509271997,
"grad_norm": 1.7698922157287598,
"learning_rate": 0.00014598242278113897,
"loss": 0.7515909194946289,
"step": 6680
},
{
"epoch": 0.7362570846860728,
"grad_norm": 1.2080354690551758,
"learning_rate": 0.0001458240922099,
"loss": 0.7281320571899415,
"step": 6690
},
{
"epoch": 0.7373576184449459,
"grad_norm": 1.295284628868103,
"learning_rate": 0.00014566561609696986,
"loss": 0.699878454208374,
"step": 6700
},
{
"epoch": 0.7384581522038188,
"grad_norm": 1.39139986038208,
"learning_rate": 0.00014550699494568384,
"loss": 0.7556473731994628,
"step": 6710
},
{
"epoch": 0.7395586859626919,
"grad_norm": 1.4971297979354858,
"learning_rate": 0.0001453482292598379,
"loss": 0.6911003112792968,
"step": 6720
},
{
"epoch": 0.740659219721565,
"grad_norm": 1.5792361497879028,
"learning_rate": 0.00014518931954368694,
"loss": 0.7027464389801026,
"step": 6730
},
{
"epoch": 0.741759753480438,
"grad_norm": 1.2973233461380005,
"learning_rate": 0.0001450302663019434,
"loss": 0.7206850528717041,
"step": 6740
},
{
"epoch": 0.7428602872393111,
"grad_norm": 1.3215023279190063,
"learning_rate": 0.0001448710700397756,
"loss": 0.7368278980255127,
"step": 6750
},
{
"epoch": 0.7439608209981842,
"grad_norm": 1.1171671152114868,
"learning_rate": 0.00014471173126280606,
"loss": 0.66349196434021,
"step": 6760
},
{
"epoch": 0.7450613547570571,
"grad_norm": 1.2632873058319092,
"learning_rate": 0.00014455225047710989,
"loss": 0.6891120910644531,
"step": 6770
},
{
"epoch": 0.7461618885159302,
"grad_norm": 1.3787199258804321,
"learning_rate": 0.00014439262818921334,
"loss": 0.6997201442718506,
"step": 6780
},
{
"epoch": 0.7472624222748033,
"grad_norm": 1.269120693206787,
"learning_rate": 0.00014423286490609203,
"loss": 0.7099348068237304,
"step": 6790
},
{
"epoch": 0.7483629560336763,
"grad_norm": 1.2346347570419312,
"learning_rate": 0.00014407296113516934,
"loss": 0.735411548614502,
"step": 6800
},
{
"epoch": 0.7494634897925494,
"grad_norm": 1.6132004261016846,
"learning_rate": 0.000143912917384315,
"loss": 0.7112602233886719,
"step": 6810
},
{
"epoch": 0.7505640235514225,
"grad_norm": 1.3072880506515503,
"learning_rate": 0.00014375273416184322,
"loss": 0.6661246299743653,
"step": 6820
},
{
"epoch": 0.7516645573102955,
"grad_norm": 1.301348090171814,
"learning_rate": 0.00014359241197651112,
"loss": 0.6509958267211914,
"step": 6830
},
{
"epoch": 0.7527650910691686,
"grad_norm": 1.1231361627578735,
"learning_rate": 0.00014343195133751738,
"loss": 0.6790677547454834,
"step": 6840
},
{
"epoch": 0.7538656248280416,
"grad_norm": 1.1891106367111206,
"learning_rate": 0.00014327135275450022,
"loss": 0.6516884803771973,
"step": 6850
},
{
"epoch": 0.7549661585869146,
"grad_norm": 1.1670225858688354,
"learning_rate": 0.00014311061673753615,
"loss": 0.6912143707275391,
"step": 6860
},
{
"epoch": 0.7560666923457877,
"grad_norm": 1.3946342468261719,
"learning_rate": 0.00014294974379713802,
"loss": 0.6989268302917481,
"step": 6870
},
{
"epoch": 0.7571672261046608,
"grad_norm": 1.179093360900879,
"learning_rate": 0.00014278873444425368,
"loss": 0.7307651996612549,
"step": 6880
},
{
"epoch": 0.7582677598635338,
"grad_norm": 1.292688012123108,
"learning_rate": 0.00014262758919026422,
"loss": 0.6909995079040527,
"step": 6890
},
{
"epoch": 0.7593682936224069,
"grad_norm": 1.2528825998306274,
"learning_rate": 0.00014246630854698232,
"loss": 0.7367213726043701,
"step": 6900
},
{
"epoch": 0.76046882738128,
"grad_norm": 1.1586990356445312,
"learning_rate": 0.00014230489302665073,
"loss": 0.6632703304290771,
"step": 6910
},
{
"epoch": 0.761569361140153,
"grad_norm": 1.6231518983840942,
"learning_rate": 0.00014214334314194055,
"loss": 0.6899041175842285,
"step": 6920
},
{
"epoch": 0.762669894899026,
"grad_norm": 1.302525281906128,
"learning_rate": 0.0001419816594059496,
"loss": 0.7668297767639161,
"step": 6930
},
{
"epoch": 0.7637704286578991,
"grad_norm": 1.283761978149414,
"learning_rate": 0.0001418198423322009,
"loss": 0.7081122398376465,
"step": 6940
},
{
"epoch": 0.7648709624167721,
"grad_norm": 1.1314969062805176,
"learning_rate": 0.0001416578924346409,
"loss": 0.6925370216369628,
"step": 6950
},
{
"epoch": 0.7659714961756452,
"grad_norm": 1.2459073066711426,
"learning_rate": 0.00014149581022763794,
"loss": 0.6523490428924561,
"step": 6960
},
{
"epoch": 0.7670720299345183,
"grad_norm": 1.5697073936462402,
"learning_rate": 0.00014133359622598056,
"loss": 0.6504369735717773,
"step": 6970
},
{
"epoch": 0.7681725636933913,
"grad_norm": 1.4411842823028564,
"learning_rate": 0.00014117125094487596,
"loss": 0.6521959781646729,
"step": 6980
},
{
"epoch": 0.7692730974522644,
"grad_norm": 2.7891016006469727,
"learning_rate": 0.0001410087748999482,
"loss": 0.6588033676147461,
"step": 6990
},
{
"epoch": 0.7703736312111374,
"grad_norm": 1.2571395635604858,
"learning_rate": 0.00014084616860723676,
"loss": 0.7186612606048584,
"step": 7000
},
{
"epoch": 0.7703736312111374,
"eval_loss": 0.6988013386726379,
"eval_runtime": 935.5187,
"eval_samples_per_second": 9.713,
"eval_steps_per_second": 2.429,
"step": 7000
},
{
"epoch": 0.7714741649700104,
"grad_norm": 1.1871322393417358,
"learning_rate": 0.00014068343258319472,
"loss": 0.6798050880432129,
"step": 7010
},
{
"epoch": 0.7725746987288835,
"grad_norm": 1.6656651496887207,
"learning_rate": 0.0001405205673446872,
"loss": 0.7257527351379395,
"step": 7020
},
{
"epoch": 0.7736752324877566,
"grad_norm": 1.366361141204834,
"learning_rate": 0.00014035757340898978,
"loss": 0.6586103916168213,
"step": 7030
},
{
"epoch": 0.7747757662466296,
"grad_norm": 1.5451475381851196,
"learning_rate": 0.00014019445129378677,
"loss": 0.6806992530822754,
"step": 7040
},
{
"epoch": 0.7758763000055027,
"grad_norm": 1.2665611505508423,
"learning_rate": 0.00014003120151716953,
"loss": 0.7109615325927734,
"step": 7050
},
{
"epoch": 0.7769768337643758,
"grad_norm": 1.2748724222183228,
"learning_rate": 0.000139867824597635,
"loss": 0.7034411430358887,
"step": 7060
},
{
"epoch": 0.7780773675232487,
"grad_norm": 1.4949373006820679,
"learning_rate": 0.00013970432105408378,
"loss": 0.6983131885528564,
"step": 7070
},
{
"epoch": 0.7791779012821218,
"grad_norm": 1.5629324913024902,
"learning_rate": 0.00013954069140581884,
"loss": 0.6774309635162353,
"step": 7080
},
{
"epoch": 0.7802784350409949,
"grad_norm": 1.2059013843536377,
"learning_rate": 0.00013937693617254351,
"loss": 0.6928264141082764,
"step": 7090
},
{
"epoch": 0.7813789687998679,
"grad_norm": 1.350574254989624,
"learning_rate": 0.00013921305587436,
"loss": 0.6662729740142822,
"step": 7100
},
{
"epoch": 0.782479502558741,
"grad_norm": 1.2160134315490723,
"learning_rate": 0.00013904905103176787,
"loss": 0.7077804565429687,
"step": 7110
},
{
"epoch": 0.7835800363176141,
"grad_norm": 1.2523444890975952,
"learning_rate": 0.0001388849221656621,
"loss": 0.7563854694366455,
"step": 7120
},
{
"epoch": 0.7846805700764871,
"grad_norm": 1.2325736284255981,
"learning_rate": 0.0001387206697973316,
"loss": 0.6632079601287841,
"step": 7130
},
{
"epoch": 0.7857811038353602,
"grad_norm": 1.342939853668213,
"learning_rate": 0.0001385562944484577,
"loss": 0.6962016105651856,
"step": 7140
},
{
"epoch": 0.7868816375942332,
"grad_norm": 1.6244813203811646,
"learning_rate": 0.00013839179664111204,
"loss": 0.6567019939422607,
"step": 7150
},
{
"epoch": 0.7879821713531062,
"grad_norm": 1.8458601236343384,
"learning_rate": 0.00013822717689775547,
"loss": 0.660393762588501,
"step": 7160
},
{
"epoch": 0.7890827051119793,
"grad_norm": 1.518789529800415,
"learning_rate": 0.00013806243574123597,
"loss": 0.6897108554840088,
"step": 7170
},
{
"epoch": 0.7901832388708524,
"grad_norm": 1.2446949481964111,
"learning_rate": 0.00013789757369478715,
"loss": 0.6905016422271728,
"step": 7180
},
{
"epoch": 0.7912837726297254,
"grad_norm": 1.1706857681274414,
"learning_rate": 0.00013773259128202668,
"loss": 0.6798492908477783,
"step": 7190
},
{
"epoch": 0.7923843063885985,
"grad_norm": 2.5733892917633057,
"learning_rate": 0.0001375674890269544,
"loss": 0.6814803600311279,
"step": 7200
},
{
"epoch": 0.7934848401474716,
"grad_norm": 1.091080904006958,
"learning_rate": 0.00013740226745395084,
"loss": 0.6753903388977051,
"step": 7210
},
{
"epoch": 0.7945853739063445,
"grad_norm": 1.5836533308029175,
"learning_rate": 0.00013723692708777553,
"loss": 0.6552946090698242,
"step": 7220
},
{
"epoch": 0.7956859076652176,
"grad_norm": 1.1512203216552734,
"learning_rate": 0.00013707146845356517,
"loss": 0.6479218482971192,
"step": 7230
},
{
"epoch": 0.7967864414240907,
"grad_norm": 1.2342529296875,
"learning_rate": 0.00013690589207683224,
"loss": 0.6967320442199707,
"step": 7240
},
{
"epoch": 0.7978869751829637,
"grad_norm": 1.3044766187667847,
"learning_rate": 0.00013674019848346309,
"loss": 0.6886932849884033,
"step": 7250
},
{
"epoch": 0.7989875089418368,
"grad_norm": 1.1774944067001343,
"learning_rate": 0.00013657438819971644,
"loss": 0.6783594608306884,
"step": 7260
},
{
"epoch": 0.8000880427007099,
"grad_norm": 1.2176823616027832,
"learning_rate": 0.00013640846175222147,
"loss": 0.7020230770111084,
"step": 7270
},
{
"epoch": 0.8011885764595829,
"grad_norm": 1.2440234422683716,
"learning_rate": 0.00013624241966797657,
"loss": 0.659848976135254,
"step": 7280
},
{
"epoch": 0.802289110218456,
"grad_norm": 1.3187357187271118,
"learning_rate": 0.0001360762624743471,
"loss": 0.6982054710388184,
"step": 7290
},
{
"epoch": 0.803389643977329,
"grad_norm": 1.218770146369934,
"learning_rate": 0.0001359099906990643,
"loss": 0.7144939422607421,
"step": 7300
},
{
"epoch": 0.804490177736202,
"grad_norm": 1.4207760095596313,
"learning_rate": 0.0001357436048702231,
"loss": 0.7038421154022216,
"step": 7310
},
{
"epoch": 0.8055907114950751,
"grad_norm": 1.2784091234207153,
"learning_rate": 0.0001355771055162808,
"loss": 0.7102098941802979,
"step": 7320
},
{
"epoch": 0.8066912452539482,
"grad_norm": 1.3901985883712769,
"learning_rate": 0.00013541049316605528,
"loss": 0.7364766120910644,
"step": 7330
},
{
"epoch": 0.8077917790128212,
"grad_norm": 1.591460108757019,
"learning_rate": 0.00013524376834872322,
"loss": 0.7228377819061279,
"step": 7340
},
{
"epoch": 0.8088923127716943,
"grad_norm": 1.3788084983825684,
"learning_rate": 0.00013507693159381856,
"loss": 0.7458762168884278,
"step": 7350
},
{
"epoch": 0.8099928465305674,
"grad_norm": 1.2996565103530884,
"learning_rate": 0.0001349099834312308,
"loss": 0.762279748916626,
"step": 7360
},
{
"epoch": 0.8110933802894403,
"grad_norm": 1.245705485343933,
"learning_rate": 0.00013474292439120324,
"loss": 0.698921537399292,
"step": 7370
},
{
"epoch": 0.8121939140483134,
"grad_norm": 2.505213737487793,
"learning_rate": 0.00013457575500433125,
"loss": 0.674662446975708,
"step": 7380
},
{
"epoch": 0.8132944478071865,
"grad_norm": 2.3632819652557373,
"learning_rate": 0.0001344084758015609,
"loss": 0.7322216987609863,
"step": 7390
},
{
"epoch": 0.8143949815660595,
"grad_norm": 1.5684608221054077,
"learning_rate": 0.00013424108731418678,
"loss": 0.695711612701416,
"step": 7400
},
{
"epoch": 0.8154955153249326,
"grad_norm": 1.2372469902038574,
"learning_rate": 0.00013407359007385077,
"loss": 0.6515445709228516,
"step": 7410
},
{
"epoch": 0.8165960490838057,
"grad_norm": 1.4333858489990234,
"learning_rate": 0.00013390598461254013,
"loss": 0.7076169013977051,
"step": 7420
},
{
"epoch": 0.8176965828426787,
"grad_norm": 1.4251869916915894,
"learning_rate": 0.00013373827146258567,
"loss": 0.6859198570251465,
"step": 7430
},
{
"epoch": 0.8187971166015517,
"grad_norm": 1.328965425491333,
"learning_rate": 0.0001335704511566605,
"loss": 0.6973493576049805,
"step": 7440
},
{
"epoch": 0.8198976503604248,
"grad_norm": 1.5237798690795898,
"learning_rate": 0.00013340252422777788,
"loss": 0.6448246479034424,
"step": 7450
},
{
"epoch": 0.8209981841192978,
"grad_norm": 1.3510645627975464,
"learning_rate": 0.00013323449120928972,
"loss": 0.7142490863800048,
"step": 7460
},
{
"epoch": 0.8220987178781709,
"grad_norm": 1.3509327173233032,
"learning_rate": 0.00013306635263488504,
"loss": 0.6812589645385743,
"step": 7470
},
{
"epoch": 0.823199251637044,
"grad_norm": 1.3660122156143188,
"learning_rate": 0.0001328981090385879,
"loss": 0.7049969673156739,
"step": 7480
},
{
"epoch": 0.824299785395917,
"grad_norm": 1.6111016273498535,
"learning_rate": 0.00013272976095475604,
"loss": 0.6968174934387207,
"step": 7490
},
{
"epoch": 0.8254003191547901,
"grad_norm": 1.4804449081420898,
"learning_rate": 0.00013256130891807909,
"loss": 0.6459970474243164,
"step": 7500
},
{
"epoch": 0.8265008529136632,
"grad_norm": 1.3297840356826782,
"learning_rate": 0.00013239275346357677,
"loss": 0.6993029594421387,
"step": 7510
},
{
"epoch": 0.8276013866725361,
"grad_norm": 1.4443268775939941,
"learning_rate": 0.00013222409512659731,
"loss": 0.7198901176452637,
"step": 7520
},
{
"epoch": 0.8287019204314092,
"grad_norm": 1.931485891342163,
"learning_rate": 0.00013205533444281565,
"loss": 0.7343377113342285,
"step": 7530
},
{
"epoch": 0.8298024541902823,
"grad_norm": 1.3457489013671875,
"learning_rate": 0.00013188647194823186,
"loss": 0.7027858257293701,
"step": 7540
},
{
"epoch": 0.8309029879491553,
"grad_norm": 1.467539668083191,
"learning_rate": 0.00013171750817916932,
"loss": 0.6650913238525391,
"step": 7550
},
{
"epoch": 0.8320035217080284,
"grad_norm": 1.6861003637313843,
"learning_rate": 0.00013154844367227312,
"loss": 0.7291770935058594,
"step": 7560
},
{
"epoch": 0.8331040554669015,
"grad_norm": 1.1725903749465942,
"learning_rate": 0.00013137927896450825,
"loss": 0.7654675483703614,
"step": 7570
},
{
"epoch": 0.8342045892257745,
"grad_norm": 1.3469438552856445,
"learning_rate": 0.000131210014593158,
"loss": 0.6373929500579834,
"step": 7580
},
{
"epoch": 0.8353051229846475,
"grad_norm": 1.3646994829177856,
"learning_rate": 0.00013104065109582216,
"loss": 0.6589652061462402,
"step": 7590
},
{
"epoch": 0.8364056567435206,
"grad_norm": 1.4819387197494507,
"learning_rate": 0.0001308711890104153,
"loss": 0.7560039520263672,
"step": 7600
},
{
"epoch": 0.8375061905023936,
"grad_norm": 2.5454657077789307,
"learning_rate": 0.00013070162887516526,
"loss": 0.7073025226593017,
"step": 7610
},
{
"epoch": 0.8386067242612667,
"grad_norm": 1.3752559423446655,
"learning_rate": 0.00013053197122861118,
"loss": 0.6591440677642822,
"step": 7620
},
{
"epoch": 0.8397072580201398,
"grad_norm": 1.2405189275741577,
"learning_rate": 0.00013036221660960197,
"loss": 0.6888460636138916,
"step": 7630
},
{
"epoch": 0.8408077917790128,
"grad_norm": 1.35996413230896,
"learning_rate": 0.00013019236555729448,
"loss": 0.7027706146240235,
"step": 7640
},
{
"epoch": 0.8419083255378859,
"grad_norm": 1.7200969457626343,
"learning_rate": 0.00013002241861115186,
"loss": 0.6196746349334716,
"step": 7650
},
{
"epoch": 0.843008859296759,
"grad_norm": 1.377030372619629,
"learning_rate": 0.00012985237631094187,
"loss": 0.627590274810791,
"step": 7660
},
{
"epoch": 0.8441093930556319,
"grad_norm": 1.4566055536270142,
"learning_rate": 0.00012968223919673503,
"loss": 0.6607007026672364,
"step": 7670
},
{
"epoch": 0.845209926814505,
"grad_norm": 1.4451576471328735,
"learning_rate": 0.0001295120078089031,
"loss": 0.7037580013275146,
"step": 7680
},
{
"epoch": 0.8463104605733781,
"grad_norm": 1.415389060974121,
"learning_rate": 0.00012934168268811719,
"loss": 0.7002586364746094,
"step": 7690
},
{
"epoch": 0.8474109943322511,
"grad_norm": 1.4278415441513062,
"learning_rate": 0.0001291712643753462,
"loss": 0.7121758460998535,
"step": 7700
},
{
"epoch": 0.8485115280911242,
"grad_norm": 1.371798038482666,
"learning_rate": 0.00012900075341185487,
"loss": 0.6606307029724121,
"step": 7710
},
{
"epoch": 0.8496120618499973,
"grad_norm": 1.5357285737991333,
"learning_rate": 0.00012883015033920235,
"loss": 0.6908731460571289,
"step": 7720
},
{
"epoch": 0.8507125956088702,
"grad_norm": 1.506842851638794,
"learning_rate": 0.0001286594556992403,
"loss": 0.6720726966857911,
"step": 7730
},
{
"epoch": 0.8518131293677433,
"grad_norm": 1.4170438051223755,
"learning_rate": 0.00012848867003411116,
"loss": 0.6788636207580566,
"step": 7740
},
{
"epoch": 0.8529136631266164,
"grad_norm": 1.1453160047531128,
"learning_rate": 0.0001283177938862465,
"loss": 0.6716455936431884,
"step": 7750
},
{
"epoch": 0.8540141968854894,
"grad_norm": 1.438539981842041,
"learning_rate": 0.0001281468277983653,
"loss": 0.7212297439575195,
"step": 7760
},
{
"epoch": 0.8551147306443625,
"grad_norm": 1.373718500137329,
"learning_rate": 0.00012797577231347216,
"loss": 0.6638013839721679,
"step": 7770
},
{
"epoch": 0.8562152644032356,
"grad_norm": 1.2419517040252686,
"learning_rate": 0.00012780462797485563,
"loss": 0.6845217227935791,
"step": 7780
},
{
"epoch": 0.8573157981621087,
"grad_norm": 1.5489189624786377,
"learning_rate": 0.0001276333953260865,
"loss": 0.6920717239379883,
"step": 7790
},
{
"epoch": 0.8584163319209817,
"grad_norm": 1.2467175722122192,
"learning_rate": 0.00012746207491101596,
"loss": 0.66603102684021,
"step": 7800
},
{
"epoch": 0.8595168656798547,
"grad_norm": 1.4268126487731934,
"learning_rate": 0.000127290667273774,
"loss": 0.6849881649017334,
"step": 7810
},
{
"epoch": 0.8606173994387278,
"grad_norm": 1.495902419090271,
"learning_rate": 0.0001271191729587677,
"loss": 0.6129237174987793,
"step": 7820
},
{
"epoch": 0.8617179331976008,
"grad_norm": 1.6803451776504517,
"learning_rate": 0.0001269475925106793,
"loss": 0.6143646240234375,
"step": 7830
},
{
"epoch": 0.8628184669564739,
"grad_norm": 1.113897442817688,
"learning_rate": 0.00012677592647446472,
"loss": 0.6867623805999756,
"step": 7840
},
{
"epoch": 0.863919000715347,
"grad_norm": 1.457037329673767,
"learning_rate": 0.0001266041753953517,
"loss": 0.6972255229949951,
"step": 7850
},
{
"epoch": 0.86501953447422,
"grad_norm": 1.371835470199585,
"learning_rate": 0.00012643233981883805,
"loss": 0.6636334896087647,
"step": 7860
},
{
"epoch": 0.8661200682330931,
"grad_norm": 1.516221523284912,
"learning_rate": 0.0001262604202906899,
"loss": 0.6858119964599609,
"step": 7870
},
{
"epoch": 0.8672206019919662,
"grad_norm": 1.3317691087722778,
"learning_rate": 0.00012608841735694016,
"loss": 0.6870519161224365,
"step": 7880
},
{
"epoch": 0.8683211357508391,
"grad_norm": 1.4758000373840332,
"learning_rate": 0.00012591633156388654,
"loss": 0.7490305423736572,
"step": 7890
},
{
"epoch": 0.8694216695097122,
"grad_norm": 1.363806962966919,
"learning_rate": 0.00012574416345808995,
"loss": 0.7155299186706543,
"step": 7900
},
{
"epoch": 0.8705222032685853,
"grad_norm": 1.3234132528305054,
"learning_rate": 0.0001255719135863727,
"loss": 0.7069467544555664,
"step": 7910
},
{
"epoch": 0.8716227370274583,
"grad_norm": 1.5334231853485107,
"learning_rate": 0.00012539958249581688,
"loss": 0.6356239795684815,
"step": 7920
},
{
"epoch": 0.8727232707863314,
"grad_norm": 2.0638036727905273,
"learning_rate": 0.0001252271707337624,
"loss": 0.6625099182128906,
"step": 7930
},
{
"epoch": 0.8738238045452045,
"grad_norm": 1.4381542205810547,
"learning_rate": 0.0001250546788478056,
"loss": 0.6540022373199463,
"step": 7940
},
{
"epoch": 0.8749243383040775,
"grad_norm": 1.5481128692626953,
"learning_rate": 0.00012488210738579707,
"loss": 0.7181411266326905,
"step": 7950
},
{
"epoch": 0.8760248720629505,
"grad_norm": 1.4068529605865479,
"learning_rate": 0.00012470945689584028,
"loss": 0.7064788818359375,
"step": 7960
},
{
"epoch": 0.8771254058218236,
"grad_norm": 1.434870958328247,
"learning_rate": 0.00012453672792628968,
"loss": 0.6818098545074462,
"step": 7970
},
{
"epoch": 0.8782259395806966,
"grad_norm": 1.3886451721191406,
"learning_rate": 0.00012436392102574894,
"loss": 0.7107852458953857,
"step": 7980
},
{
"epoch": 0.8793264733395697,
"grad_norm": 1.203020453453064,
"learning_rate": 0.00012419103674306928,
"loss": 0.6583857536315918,
"step": 7990
},
{
"epoch": 0.8804270070984428,
"grad_norm": 1.9182116985321045,
"learning_rate": 0.00012401807562734772,
"loss": 0.659544849395752,
"step": 8000
},
{
"epoch": 0.8804270070984428,
"eval_loss": 0.6778551340103149,
"eval_runtime": 932.9618,
"eval_samples_per_second": 9.74,
"eval_steps_per_second": 2.435,
"step": 8000
},
{
"epoch": 0.8815275408573158,
"grad_norm": 1.1438349485397339,
"learning_rate": 0.00012384503822792522,
"loss": 0.7064003467559814,
"step": 8010
},
{
"epoch": 0.8826280746161889,
"grad_norm": 1.7863585948944092,
"learning_rate": 0.0001236719250943851,
"loss": 0.6962413787841797,
"step": 8020
},
{
"epoch": 0.883728608375062,
"grad_norm": 1.2342000007629395,
"learning_rate": 0.00012349873677655122,
"loss": 0.7125117301940918,
"step": 8030
},
{
"epoch": 0.8848291421339349,
"grad_norm": 1.3097106218338013,
"learning_rate": 0.00012332547382448616,
"loss": 0.6737674713134766,
"step": 8040
},
{
"epoch": 0.885929675892808,
"grad_norm": 1.818900465965271,
"learning_rate": 0.00012315213678848968,
"loss": 0.7128641128540039,
"step": 8050
},
{
"epoch": 0.8870302096516811,
"grad_norm": 1.3802350759506226,
"learning_rate": 0.00012297872621909665,
"loss": 0.676642370223999,
"step": 8060
},
{
"epoch": 0.8881307434105541,
"grad_norm": 1.3735311031341553,
"learning_rate": 0.00012280524266707562,
"loss": 0.7140858173370361,
"step": 8070
},
{
"epoch": 0.8892312771694272,
"grad_norm": 1.2950201034545898,
"learning_rate": 0.000122631686683427,
"loss": 0.6506130695343018,
"step": 8080
},
{
"epoch": 0.8903318109283003,
"grad_norm": 1.5455875396728516,
"learning_rate": 0.00012245805881938102,
"loss": 0.6791904926300049,
"step": 8090
},
{
"epoch": 0.8914323446871733,
"grad_norm": 1.6769343614578247,
"learning_rate": 0.00012228435962639646,
"loss": 0.6474512577056885,
"step": 8100
},
{
"epoch": 0.8925328784460463,
"grad_norm": 1.5164687633514404,
"learning_rate": 0.00012211058965615852,
"loss": 0.6617956161499023,
"step": 8110
},
{
"epoch": 0.8936334122049194,
"grad_norm": 1.212746500968933,
"learning_rate": 0.00012193674946057716,
"loss": 0.6868027210235595,
"step": 8120
},
{
"epoch": 0.8947339459637924,
"grad_norm": 1.5468772649765015,
"learning_rate": 0.00012176283959178549,
"loss": 0.7017358303070068,
"step": 8130
},
{
"epoch": 0.8958344797226655,
"grad_norm": 1.515346884727478,
"learning_rate": 0.00012158886060213783,
"loss": 0.6743238925933838,
"step": 8140
},
{
"epoch": 0.8969350134815386,
"grad_norm": 1.4134080410003662,
"learning_rate": 0.00012141481304420805,
"loss": 0.6742711067199707,
"step": 8150
},
{
"epoch": 0.8980355472404116,
"grad_norm": 1.7870819568634033,
"learning_rate": 0.00012124069747078783,
"loss": 0.662075138092041,
"step": 8160
},
{
"epoch": 0.8991360809992847,
"grad_norm": 1.2318055629730225,
"learning_rate": 0.00012106651443488486,
"loss": 0.6702588558197021,
"step": 8170
},
{
"epoch": 0.9002366147581577,
"grad_norm": 1.790337085723877,
"learning_rate": 0.00012089226448972104,
"loss": 0.6329897403717041,
"step": 8180
},
{
"epoch": 0.9013371485170307,
"grad_norm": 1.4314793348312378,
"learning_rate": 0.00012071794818873088,
"loss": 0.6269967079162597,
"step": 8190
},
{
"epoch": 0.9024376822759038,
"grad_norm": 1.3605494499206543,
"learning_rate": 0.00012054356608555957,
"loss": 0.7243019580841065,
"step": 8200
},
{
"epoch": 0.9035382160347769,
"grad_norm": 1.4494309425354004,
"learning_rate": 0.00012036911873406132,
"loss": 0.6475474834442139,
"step": 8210
},
{
"epoch": 0.9046387497936499,
"grad_norm": 1.5264508724212646,
"learning_rate": 0.00012019460668829759,
"loss": 0.6825450897216797,
"step": 8220
},
{
"epoch": 0.905739283552523,
"grad_norm": 1.9596912860870361,
"learning_rate": 0.00012002003050253522,
"loss": 0.6889598846435547,
"step": 8230
},
{
"epoch": 0.9068398173113961,
"grad_norm": 1.162349820137024,
"learning_rate": 0.00011984539073124497,
"loss": 0.69486083984375,
"step": 8240
},
{
"epoch": 0.907940351070269,
"grad_norm": 1.5693060159683228,
"learning_rate": 0.00011967068792909932,
"loss": 0.6712918758392334,
"step": 8250
},
{
"epoch": 0.9090408848291421,
"grad_norm": 1.401931643486023,
"learning_rate": 0.00011949592265097105,
"loss": 0.6797111988067627,
"step": 8260
},
{
"epoch": 0.9101414185880152,
"grad_norm": 1.3472332954406738,
"learning_rate": 0.00011932109545193144,
"loss": 0.672774076461792,
"step": 8270
},
{
"epoch": 0.9112419523468882,
"grad_norm": 1.4004240036010742,
"learning_rate": 0.00011914620688724829,
"loss": 0.7006333351135254,
"step": 8280
},
{
"epoch": 0.9123424861057613,
"grad_norm": 1.2783311605453491,
"learning_rate": 0.0001189712575123844,
"loss": 0.7153875350952148,
"step": 8290
},
{
"epoch": 0.9134430198646344,
"grad_norm": 1.1996188163757324,
"learning_rate": 0.0001187962478829957,
"loss": 0.689389419555664,
"step": 8300
},
{
"epoch": 0.9145435536235074,
"grad_norm": 1.2539170980453491,
"learning_rate": 0.00011862117855492947,
"loss": 0.6108541011810302,
"step": 8310
},
{
"epoch": 0.9156440873823805,
"grad_norm": 2.2254698276519775,
"learning_rate": 0.0001184460500842226,
"loss": 0.6142482280731201,
"step": 8320
},
{
"epoch": 0.9167446211412535,
"grad_norm": 1.3384058475494385,
"learning_rate": 0.00011827086302709985,
"loss": 0.7159160614013672,
"step": 8330
},
{
"epoch": 0.9178451549001265,
"grad_norm": 1.348150372505188,
"learning_rate": 0.00011809561793997196,
"loss": 0.7021602630615235,
"step": 8340
},
{
"epoch": 0.9189456886589996,
"grad_norm": 1.2070444822311401,
"learning_rate": 0.00011792031537943419,
"loss": 0.6672283172607422,
"step": 8350
},
{
"epoch": 0.9200462224178727,
"grad_norm": 1.4409536123275757,
"learning_rate": 0.00011774495590226411,
"loss": 0.6677028179168701,
"step": 8360
},
{
"epoch": 0.9211467561767457,
"grad_norm": 1.392524003982544,
"learning_rate": 0.00011756954006542016,
"loss": 0.662090253829956,
"step": 8370
},
{
"epoch": 0.9222472899356188,
"grad_norm": 1.2901691198349,
"learning_rate": 0.00011739406842603984,
"loss": 0.7365155696868897,
"step": 8380
},
{
"epoch": 0.9233478236944919,
"grad_norm": 1.2124253511428833,
"learning_rate": 0.00011721854154143779,
"loss": 0.7207441329956055,
"step": 8390
},
{
"epoch": 0.9244483574533648,
"grad_norm": 1.5050990581512451,
"learning_rate": 0.00011704295996910412,
"loss": 0.6663022041320801,
"step": 8400
},
{
"epoch": 0.9255488912122379,
"grad_norm": 1.2585158348083496,
"learning_rate": 0.00011686732426670273,
"loss": 0.6244583606719971,
"step": 8410
},
{
"epoch": 0.926649424971111,
"grad_norm": 1.5437763929367065,
"learning_rate": 0.0001166916349920693,
"loss": 0.7076413631439209,
"step": 8420
},
{
"epoch": 0.927749958729984,
"grad_norm": 1.6555818319320679,
"learning_rate": 0.00011651589270320982,
"loss": 0.6495061397552491,
"step": 8430
},
{
"epoch": 0.9288504924888571,
"grad_norm": 1.3378431797027588,
"learning_rate": 0.00011634009795829854,
"loss": 0.6376430511474609,
"step": 8440
},
{
"epoch": 0.9299510262477302,
"grad_norm": 1.5055992603302002,
"learning_rate": 0.00011616425131567633,
"loss": 0.6544463634490967,
"step": 8450
},
{
"epoch": 0.9310515600066032,
"grad_norm": 1.3278628587722778,
"learning_rate": 0.00011598835333384892,
"loss": 0.6161699771881104,
"step": 8460
},
{
"epoch": 0.9321520937654763,
"grad_norm": 1.372585415840149,
"learning_rate": 0.00011581240457148514,
"loss": 0.6854087352752686,
"step": 8470
},
{
"epoch": 0.9332526275243493,
"grad_norm": 1.1991004943847656,
"learning_rate": 0.00011563640558741497,
"loss": 0.6809545516967773,
"step": 8480
},
{
"epoch": 0.9343531612832223,
"grad_norm": 1.5184593200683594,
"learning_rate": 0.00011546035694062806,
"loss": 0.722816801071167,
"step": 8490
},
{
"epoch": 0.9354536950420954,
"grad_norm": 1.4115090370178223,
"learning_rate": 0.0001152842591902717,
"loss": 0.6591164112091065,
"step": 8500
},
{
"epoch": 0.9365542288009685,
"grad_norm": 1.2823673486709595,
"learning_rate": 0.00011510811289564911,
"loss": 0.6075215339660645,
"step": 8510
},
{
"epoch": 0.9376547625598415,
"grad_norm": 1.4146981239318848,
"learning_rate": 0.00011493191861621779,
"loss": 0.6822831630706787,
"step": 8520
},
{
"epoch": 0.9387552963187146,
"grad_norm": 1.1857773065567017,
"learning_rate": 0.00011475567691158755,
"loss": 0.6445578098297119,
"step": 8530
},
{
"epoch": 0.9398558300775877,
"grad_norm": 1.292283296585083,
"learning_rate": 0.00011457938834151891,
"loss": 0.6735328674316406,
"step": 8540
},
{
"epoch": 0.9409563638364606,
"grad_norm": 1.457037329673767,
"learning_rate": 0.00011440305346592117,
"loss": 0.6686610221862793,
"step": 8550
},
{
"epoch": 0.9420568975953337,
"grad_norm": 1.120066523551941,
"learning_rate": 0.00011422667284485072,
"loss": 0.6486789226531983,
"step": 8560
},
{
"epoch": 0.9431574313542068,
"grad_norm": 1.5501199960708618,
"learning_rate": 0.00011405024703850929,
"loss": 0.7010744094848633,
"step": 8570
},
{
"epoch": 0.9442579651130798,
"grad_norm": 1.3510217666625977,
"learning_rate": 0.00011387377660724203,
"loss": 0.6792937755584717,
"step": 8580
},
{
"epoch": 0.9453584988719529,
"grad_norm": 1.881199836730957,
"learning_rate": 0.0001136972621115359,
"loss": 0.6840526580810546,
"step": 8590
},
{
"epoch": 0.946459032630826,
"grad_norm": 1.2974997758865356,
"learning_rate": 0.0001135207041120178,
"loss": 0.6829899787902832,
"step": 8600
},
{
"epoch": 0.947559566389699,
"grad_norm": 1.389054775238037,
"learning_rate": 0.00011334410316945279,
"loss": 0.6700395107269287,
"step": 8610
},
{
"epoch": 0.948660100148572,
"grad_norm": 1.7065324783325195,
"learning_rate": 0.00011316745984474226,
"loss": 0.6658083438873291,
"step": 8620
},
{
"epoch": 0.9497606339074451,
"grad_norm": 1.3307225704193115,
"learning_rate": 0.00011299077469892236,
"loss": 0.6729567527770997,
"step": 8630
},
{
"epoch": 0.9508611676663181,
"grad_norm": 1.1633726358413696,
"learning_rate": 0.00011281404829316192,
"loss": 0.6986813545227051,
"step": 8640
},
{
"epoch": 0.9519617014251912,
"grad_norm": 1.5887185335159302,
"learning_rate": 0.00011263728118876091,
"loss": 0.6705009460449218,
"step": 8650
},
{
"epoch": 0.9530622351840643,
"grad_norm": 1.6422045230865479,
"learning_rate": 0.00011246047394714851,
"loss": 0.6934192180633545,
"step": 8660
},
{
"epoch": 0.9541627689429373,
"grad_norm": 1.285357117652893,
"learning_rate": 0.00011228362712988139,
"loss": 0.6789482593536377,
"step": 8670
},
{
"epoch": 0.9552633027018104,
"grad_norm": 1.0956073999404907,
"learning_rate": 0.00011210674129864194,
"loss": 0.6241205215454102,
"step": 8680
},
{
"epoch": 0.9563638364606835,
"grad_norm": 1.3815491199493408,
"learning_rate": 0.00011192981701523644,
"loss": 0.6313820838928222,
"step": 8690
},
{
"epoch": 0.9574643702195564,
"grad_norm": 1.1785467863082886,
"learning_rate": 0.00011175285484159327,
"loss": 0.7110901832580566,
"step": 8700
},
{
"epoch": 0.9585649039784295,
"grad_norm": 1.3523856401443481,
"learning_rate": 0.00011157585533976125,
"loss": 0.6473616123199463,
"step": 8710
},
{
"epoch": 0.9596654377373026,
"grad_norm": 1.396385908126831,
"learning_rate": 0.00011139881907190764,
"loss": 0.6724176406860352,
"step": 8720
},
{
"epoch": 0.9607659714961756,
"grad_norm": 1.4832608699798584,
"learning_rate": 0.00011122174660031656,
"loss": 0.6629071235656738,
"step": 8730
},
{
"epoch": 0.9618665052550487,
"grad_norm": 1.3116185665130615,
"learning_rate": 0.00011104463848738708,
"loss": 0.6672964572906495,
"step": 8740
},
{
"epoch": 0.9629670390139218,
"grad_norm": 1.2962026596069336,
"learning_rate": 0.00011086749529563143,
"loss": 0.6599955081939697,
"step": 8750
},
{
"epoch": 0.9640675727727948,
"grad_norm": 1.7756977081298828,
"learning_rate": 0.00011069031758767336,
"loss": 0.6891998767852783,
"step": 8760
},
{
"epoch": 0.9651681065316678,
"grad_norm": 3.2222952842712402,
"learning_rate": 0.00011051310592624616,
"loss": 0.6948216438293457,
"step": 8770
},
{
"epoch": 0.9662686402905409,
"grad_norm": 1.4013516902923584,
"learning_rate": 0.00011033586087419095,
"loss": 0.6780813217163086,
"step": 8780
},
{
"epoch": 0.9673691740494139,
"grad_norm": 1.391592264175415,
"learning_rate": 0.00011015858299445496,
"loss": 0.6651968479156494,
"step": 8790
},
{
"epoch": 0.968469707808287,
"grad_norm": 1.375892996788025,
"learning_rate": 0.00010998127285008968,
"loss": 0.6654308795928955,
"step": 8800
},
{
"epoch": 0.9695702415671601,
"grad_norm": 1.1397273540496826,
"learning_rate": 0.000109803931004249,
"loss": 0.6280717372894287,
"step": 8810
},
{
"epoch": 0.9706707753260331,
"grad_norm": 1.4741898775100708,
"learning_rate": 0.00010962655802018762,
"loss": 0.6391614437103271,
"step": 8820
},
{
"epoch": 0.9717713090849062,
"grad_norm": 1.4808393716812134,
"learning_rate": 0.00010944915446125901,
"loss": 0.6131552219390869,
"step": 8830
},
{
"epoch": 0.9728718428437793,
"grad_norm": 1.4386202096939087,
"learning_rate": 0.00010927172089091385,
"loss": 0.6284717082977295,
"step": 8840
},
{
"epoch": 0.9739723766026522,
"grad_norm": 1.433688759803772,
"learning_rate": 0.00010909425787269807,
"loss": 0.62590012550354,
"step": 8850
},
{
"epoch": 0.9750729103615253,
"grad_norm": 1.2748039960861206,
"learning_rate": 0.00010891676597025113,
"loss": 0.6905404567718506,
"step": 8860
},
{
"epoch": 0.9761734441203984,
"grad_norm": 1.135408639907837,
"learning_rate": 0.00010873924574730435,
"loss": 0.6123764038085937,
"step": 8870
},
{
"epoch": 0.9772739778792714,
"grad_norm": 1.297870397567749,
"learning_rate": 0.00010856169776767882,
"loss": 0.6861724853515625,
"step": 8880
},
{
"epoch": 0.9783745116381445,
"grad_norm": 1.5463156700134277,
"learning_rate": 0.00010838412259528387,
"loss": 0.7149630546569824,
"step": 8890
},
{
"epoch": 0.9794750453970176,
"grad_norm": 1.5263346433639526,
"learning_rate": 0.00010820652079411526,
"loss": 0.690766429901123,
"step": 8900
},
{
"epoch": 0.9805755791558906,
"grad_norm": 1.5566282272338867,
"learning_rate": 0.00010802889292825322,
"loss": 0.6245404243469238,
"step": 8910
},
{
"epoch": 0.9816761129147636,
"grad_norm": 1.388037085533142,
"learning_rate": 0.00010785123956186078,
"loss": 0.6118120670318603,
"step": 8920
},
{
"epoch": 0.9827766466736367,
"grad_norm": 1.256276249885559,
"learning_rate": 0.00010767356125918207,
"loss": 0.6763318538665771,
"step": 8930
},
{
"epoch": 0.9838771804325097,
"grad_norm": 1.463404655456543,
"learning_rate": 0.00010749585858454028,
"loss": 0.7092677116394043,
"step": 8940
},
{
"epoch": 0.9849777141913828,
"grad_norm": 1.1706784963607788,
"learning_rate": 0.00010731813210233607,
"loss": 0.636759901046753,
"step": 8950
},
{
"epoch": 0.9860782479502559,
"grad_norm": 1.3767774105072021,
"learning_rate": 0.00010714038237704574,
"loss": 0.6593461513519288,
"step": 8960
},
{
"epoch": 0.987178781709129,
"grad_norm": 1.4210212230682373,
"learning_rate": 0.00010696260997321939,
"loss": 0.6599185466766357,
"step": 8970
},
{
"epoch": 0.988279315468002,
"grad_norm": 1.31072199344635,
"learning_rate": 0.00010678481545547909,
"loss": 0.6481338024139405,
"step": 8980
},
{
"epoch": 0.989379849226875,
"grad_norm": 1.274679183959961,
"learning_rate": 0.00010660699938851726,
"loss": 0.6515744686126709,
"step": 8990
},
{
"epoch": 0.9904803829857481,
"grad_norm": 1.4656940698623657,
"learning_rate": 0.00010642916233709466,
"loss": 0.6446514129638672,
"step": 9000
},
{
"epoch": 0.9904803829857481,
"eval_loss": 0.6570879817008972,
"eval_runtime": 933.4338,
"eval_samples_per_second": 9.735,
"eval_steps_per_second": 2.434,
"step": 9000
},
{
"epoch": 0.9915809167446211,
"grad_norm": 1.5283229351043701,
"learning_rate": 0.00010625130486603878,
"loss": 0.6613879203796387,
"step": 9010
},
{
"epoch": 0.9926814505034942,
"grad_norm": 1.1899523735046387,
"learning_rate": 0.00010607342754024192,
"loss": 0.6648157596588135,
"step": 9020
},
{
"epoch": 0.9937819842623673,
"grad_norm": 1.220186710357666,
"learning_rate": 0.00010589553092465941,
"loss": 0.6912306785583496,
"step": 9030
},
{
"epoch": 0.9948825180212403,
"grad_norm": 1.266737461090088,
"learning_rate": 0.00010571761558430792,
"loss": 0.6725640773773194,
"step": 9040
},
{
"epoch": 0.9959830517801134,
"grad_norm": 1.5282708406448364,
"learning_rate": 0.00010553968208426355,
"loss": 0.681598424911499,
"step": 9050
},
{
"epoch": 0.9970835855389865,
"grad_norm": 1.5123765468597412,
"learning_rate": 0.00010536173098966005,
"loss": 0.6819860458374023,
"step": 9060
},
{
"epoch": 0.9981841192978594,
"grad_norm": 1.1356281042099,
"learning_rate": 0.00010518376286568712,
"loss": 0.6530678749084473,
"step": 9070
},
{
"epoch": 0.9992846530567325,
"grad_norm": 1.3316847085952759,
"learning_rate": 0.00010500577827758848,
"loss": 0.6698222160339355,
"step": 9080
},
{
"epoch": 1.000330160127662,
"grad_norm": 1.2219398021697998,
"learning_rate": 0.0001048277777906602,
"loss": 0.6112509727478027,
"step": 9090
},
{
"epoch": 1.001430693886535,
"grad_norm": 1.3303433656692505,
"learning_rate": 0.0001046497619702488,
"loss": 0.5625757217407227,
"step": 9100
},
{
"epoch": 1.002531227645408,
"grad_norm": 1.4828858375549316,
"learning_rate": 0.0001044717313817495,
"loss": 0.538677453994751,
"step": 9110
},
{
"epoch": 1.0036317614042811,
"grad_norm": 1.430071473121643,
"learning_rate": 0.00010429368659060452,
"loss": 0.5688505172729492,
"step": 9120
},
{
"epoch": 1.004732295163154,
"grad_norm": 1.449544906616211,
"learning_rate": 0.00010411562816230105,
"loss": 0.5810873508453369,
"step": 9130
},
{
"epoch": 1.005832828922027,
"grad_norm": 1.3704406023025513,
"learning_rate": 0.00010393755666236962,
"loss": 0.6056427001953125,
"step": 9140
},
{
"epoch": 1.0069333626809003,
"grad_norm": 1.2655109167099,
"learning_rate": 0.0001037594726563824,
"loss": 0.5762576580047607,
"step": 9150
},
{
"epoch": 1.0080338964397733,
"grad_norm": 1.2094171047210693,
"learning_rate": 0.00010358137670995117,
"loss": 0.5494341373443603,
"step": 9160
},
{
"epoch": 1.0091344301986462,
"grad_norm": 1.2639278173446655,
"learning_rate": 0.00010340326938872557,
"loss": 0.5654037952423095,
"step": 9170
},
{
"epoch": 1.0102349639575194,
"grad_norm": 1.4117326736450195,
"learning_rate": 0.00010322515125839156,
"loss": 0.5302557468414306,
"step": 9180
},
{
"epoch": 1.0113354977163924,
"grad_norm": 1.3134077787399292,
"learning_rate": 0.0001030470228846693,
"loss": 0.565282678604126,
"step": 9190
},
{
"epoch": 1.0124360314752654,
"grad_norm": 1.5069129467010498,
"learning_rate": 0.00010286888483331147,
"loss": 0.5286280632019043,
"step": 9200
},
{
"epoch": 1.0135365652341386,
"grad_norm": 1.1918617486953735,
"learning_rate": 0.00010269073767010155,
"loss": 0.5556656360626221,
"step": 9210
},
{
"epoch": 1.0146370989930116,
"grad_norm": 1.7210688591003418,
"learning_rate": 0.00010251258196085194,
"loss": 0.5592852592468261,
"step": 9220
},
{
"epoch": 1.0157376327518846,
"grad_norm": 1.2481610774993896,
"learning_rate": 0.0001023344182714022,
"loss": 0.5417603492736817,
"step": 9230
},
{
"epoch": 1.0168381665107578,
"grad_norm": 1.478549838066101,
"learning_rate": 0.00010215624716761719,
"loss": 0.5636984825134277,
"step": 9240
},
{
"epoch": 1.0179387002696307,
"grad_norm": 1.3777730464935303,
"learning_rate": 0.00010197806921538531,
"loss": 0.5147793292999268,
"step": 9250
},
{
"epoch": 1.0190392340285037,
"grad_norm": 1.5314768552780151,
"learning_rate": 0.00010179988498061679,
"loss": 0.5494320869445801,
"step": 9260
},
{
"epoch": 1.020139767787377,
"grad_norm": 2.0159618854522705,
"learning_rate": 0.00010162169502924177,
"loss": 0.5387672424316406,
"step": 9270
},
{
"epoch": 1.02124030154625,
"grad_norm": 1.2471246719360352,
"learning_rate": 0.00010144349992720851,
"loss": 0.5366960525512695,
"step": 9280
},
{
"epoch": 1.022340835305123,
"grad_norm": 1.4914518594741821,
"learning_rate": 0.00010126530024048173,
"loss": 0.582341194152832,
"step": 9290
},
{
"epoch": 1.023441369063996,
"grad_norm": 1.282611608505249,
"learning_rate": 0.00010108709653504058,
"loss": 0.5790839195251465,
"step": 9300
},
{
"epoch": 1.024541902822869,
"grad_norm": 1.549333930015564,
"learning_rate": 0.00010090888937687704,
"loss": 0.580591869354248,
"step": 9310
},
{
"epoch": 1.0256424365817423,
"grad_norm": 1.5579323768615723,
"learning_rate": 0.00010073067933199412,
"loss": 0.5911038875579834,
"step": 9320
},
{
"epoch": 1.0267429703406152,
"grad_norm": 1.4953557252883911,
"learning_rate": 0.00010055246696640384,
"loss": 0.5799122810363769,
"step": 9330
},
{
"epoch": 1.0278435040994882,
"grad_norm": 1.2972475290298462,
"learning_rate": 0.00010037425284612578,
"loss": 0.5956815719604492,
"step": 9340
},
{
"epoch": 1.0289440378583614,
"grad_norm": 1.37742018699646,
"learning_rate": 0.00010019603753718494,
"loss": 0.5809694290161133,
"step": 9350
},
{
"epoch": 1.0300445716172344,
"grad_norm": 1.4490617513656616,
"learning_rate": 0.00010001782160561017,
"loss": 0.5942407608032226,
"step": 9360
},
{
"epoch": 1.0311451053761074,
"grad_norm": 1.4518905878067017,
"learning_rate": 9.983960561743229e-05,
"loss": 0.5407237529754638,
"step": 9370
},
{
"epoch": 1.0322456391349806,
"grad_norm": 1.5244001150131226,
"learning_rate": 9.966139013868227e-05,
"loss": 0.5425854206085206,
"step": 9380
},
{
"epoch": 1.0333461728938536,
"grad_norm": 1.5521200895309448,
"learning_rate": 9.948317573538948e-05,
"loss": 0.5721479415893554,
"step": 9390
},
{
"epoch": 1.0344467066527265,
"grad_norm": 1.141882300376892,
"learning_rate": 9.930496297357993e-05,
"loss": 0.5802173614501953,
"step": 9400
},
{
"epoch": 1.0355472404115997,
"grad_norm": 1.535967469215393,
"learning_rate": 9.912675241927428e-05,
"loss": 0.5469345092773438,
"step": 9410
},
{
"epoch": 1.0366477741704727,
"grad_norm": 1.6038310527801514,
"learning_rate": 9.894854463848633e-05,
"loss": 0.5816481113433838,
"step": 9420
},
{
"epoch": 1.0377483079293457,
"grad_norm": 1.359624981880188,
"learning_rate": 9.877034019722096e-05,
"loss": 0.5771404266357422,
"step": 9430
},
{
"epoch": 1.038848841688219,
"grad_norm": 1.7508776187896729,
"learning_rate": 9.859213966147251e-05,
"loss": 0.5596833229064941,
"step": 9440
},
{
"epoch": 1.0399493754470919,
"grad_norm": 1.413081407546997,
"learning_rate": 9.841394359722288e-05,
"loss": 0.5669137001037597,
"step": 9450
},
{
"epoch": 1.0410499092059649,
"grad_norm": 1.5584485530853271,
"learning_rate": 9.823575257043981e-05,
"loss": 0.5704692840576172,
"step": 9460
},
{
"epoch": 1.042150442964838,
"grad_norm": 1.2165954113006592,
"learning_rate": 9.805756714707496e-05,
"loss": 0.5172412872314454,
"step": 9470
},
{
"epoch": 1.043250976723711,
"grad_norm": 1.322078824043274,
"learning_rate": 9.787938789306226e-05,
"loss": 0.5793346405029297,
"step": 9480
},
{
"epoch": 1.044351510482584,
"grad_norm": 1.5404146909713745,
"learning_rate": 9.770121537431611e-05,
"loss": 0.5746114730834961,
"step": 9490
},
{
"epoch": 1.0454520442414572,
"grad_norm": 1.4195271730422974,
"learning_rate": 9.75230501567293e-05,
"loss": 0.5136219501495362,
"step": 9500
},
{
"epoch": 1.0465525780003302,
"grad_norm": 1.4150032997131348,
"learning_rate": 9.73448928061717e-05,
"loss": 0.6030344486236572,
"step": 9510
},
{
"epoch": 1.0476531117592032,
"grad_norm": 1.4359147548675537,
"learning_rate": 9.716674388848794e-05,
"loss": 0.5824178218841553,
"step": 9520
},
{
"epoch": 1.0487536455180764,
"grad_norm": 1.5768718719482422,
"learning_rate": 9.698860396949608e-05,
"loss": 0.5618523597717285,
"step": 9530
},
{
"epoch": 1.0498541792769494,
"grad_norm": 1.2160522937774658,
"learning_rate": 9.681047361498545e-05,
"loss": 0.5521860122680664,
"step": 9540
},
{
"epoch": 1.0509547130358223,
"grad_norm": 1.4238855838775635,
"learning_rate": 9.663235339071511e-05,
"loss": 0.5845486640930175,
"step": 9550
},
{
"epoch": 1.0520552467946955,
"grad_norm": 1.3449312448501587,
"learning_rate": 9.645424386241187e-05,
"loss": 0.5475558757781982,
"step": 9560
},
{
"epoch": 1.0531557805535685,
"grad_norm": 1.2532756328582764,
"learning_rate": 9.627614559576861e-05,
"loss": 0.5722627162933349,
"step": 9570
},
{
"epoch": 1.0542563143124415,
"grad_norm": 1.35926353931427,
"learning_rate": 9.609805915644237e-05,
"loss": 0.6075043201446533,
"step": 9580
},
{
"epoch": 1.0553568480713147,
"grad_norm": 1.5080028772354126,
"learning_rate": 9.591998511005276e-05,
"loss": 0.5763302326202393,
"step": 9590
},
{
"epoch": 1.0564573818301877,
"grad_norm": 1.291339635848999,
"learning_rate": 9.574192402217987e-05,
"loss": 0.5642305850982666,
"step": 9600
},
{
"epoch": 1.0575579155890606,
"grad_norm": 1.3691743612289429,
"learning_rate": 9.556387645836279e-05,
"loss": 0.5661220550537109,
"step": 9610
},
{
"epoch": 1.0586584493479338,
"grad_norm": 1.326614260673523,
"learning_rate": 9.538584298409751e-05,
"loss": 0.5190118789672852,
"step": 9620
},
{
"epoch": 1.0597589831068068,
"grad_norm": 1.41879141330719,
"learning_rate": 9.520782416483543e-05,
"loss": 0.5871242046356201,
"step": 9630
},
{
"epoch": 1.0608595168656798,
"grad_norm": 1.4510483741760254,
"learning_rate": 9.502982056598117e-05,
"loss": 0.5653789520263672,
"step": 9640
},
{
"epoch": 1.061960050624553,
"grad_norm": 1.1974501609802246,
"learning_rate": 9.48518327528913e-05,
"loss": 0.5508618831634522,
"step": 9650
},
{
"epoch": 1.063060584383426,
"grad_norm": 1.3627103567123413,
"learning_rate": 9.467386129087202e-05,
"loss": 0.5760284423828125,
"step": 9660
},
{
"epoch": 1.064161118142299,
"grad_norm": 1.5365513563156128,
"learning_rate": 9.449590674517772e-05,
"loss": 0.5518731117248535,
"step": 9670
},
{
"epoch": 1.0652616519011722,
"grad_norm": 1.1490570306777954,
"learning_rate": 9.431796968100899e-05,
"loss": 0.5980854988098144,
"step": 9680
},
{
"epoch": 1.0663621856600451,
"grad_norm": 1.2105135917663574,
"learning_rate": 9.414005066351096e-05,
"loss": 0.5309963226318359,
"step": 9690
},
{
"epoch": 1.0674627194189181,
"grad_norm": 1.4333903789520264,
"learning_rate": 9.396215025777139e-05,
"loss": 0.6052345752716064,
"step": 9700
},
{
"epoch": 1.0685632531777913,
"grad_norm": 1.425232172012329,
"learning_rate": 9.3784269028819e-05,
"loss": 0.5622373580932617,
"step": 9710
},
{
"epoch": 1.0696637869366643,
"grad_norm": 1.675125241279602,
"learning_rate": 9.360640754162146e-05,
"loss": 0.5412164688110351,
"step": 9720
},
{
"epoch": 1.0707643206955373,
"grad_norm": 1.2521365880966187,
"learning_rate": 9.342856636108394e-05,
"loss": 0.5297177791595459,
"step": 9730
},
{
"epoch": 1.0718648544544105,
"grad_norm": 1.2801131010055542,
"learning_rate": 9.325074605204694e-05,
"loss": 0.5316737174987793,
"step": 9740
},
{
"epoch": 1.0729653882132835,
"grad_norm": 1.4605565071105957,
"learning_rate": 9.307294717928475e-05,
"loss": 0.5497438907623291,
"step": 9750
},
{
"epoch": 1.0740659219721564,
"grad_norm": 1.5081639289855957,
"learning_rate": 9.289517030750353e-05,
"loss": 0.5808797359466553,
"step": 9760
},
{
"epoch": 1.0751664557310296,
"grad_norm": 1.330993890762329,
"learning_rate": 9.271741600133967e-05,
"loss": 0.5543405055999756,
"step": 9770
},
{
"epoch": 1.0762669894899026,
"grad_norm": 1.3712098598480225,
"learning_rate": 9.253968482535775e-05,
"loss": 0.5406375885009765,
"step": 9780
},
{
"epoch": 1.0773675232487756,
"grad_norm": 1.383906364440918,
"learning_rate": 9.236197734404901e-05,
"loss": 0.5470988273620605,
"step": 9790
},
{
"epoch": 1.0784680570076488,
"grad_norm": 1.335876226425171,
"learning_rate": 9.218429412182929e-05,
"loss": 0.5713230609893799,
"step": 9800
},
{
"epoch": 1.0795685907665218,
"grad_norm": 1.1821215152740479,
"learning_rate": 9.200663572303754e-05,
"loss": 0.5229569435119629,
"step": 9810
},
{
"epoch": 1.0806691245253948,
"grad_norm": 1.4670119285583496,
"learning_rate": 9.182900271193374e-05,
"loss": 0.5764679431915283,
"step": 9820
},
{
"epoch": 1.081769658284268,
"grad_norm": 1.2624047994613647,
"learning_rate": 9.165139565269735e-05,
"loss": 0.5724782943725586,
"step": 9830
},
{
"epoch": 1.082870192043141,
"grad_norm": 1.3869458436965942,
"learning_rate": 9.147381510942528e-05,
"loss": 0.5221073150634765,
"step": 9840
},
{
"epoch": 1.083970725802014,
"grad_norm": 1.4844560623168945,
"learning_rate": 9.129626164613033e-05,
"loss": 0.5416149616241455,
"step": 9850
},
{
"epoch": 1.0850712595608871,
"grad_norm": 1.3767277002334595,
"learning_rate": 9.111873582673923e-05,
"loss": 0.6047924995422364,
"step": 9860
},
{
"epoch": 1.08617179331976,
"grad_norm": 1.5383551120758057,
"learning_rate": 9.094123821509096e-05,
"loss": 0.5274580001831055,
"step": 9870
},
{
"epoch": 1.087272327078633,
"grad_norm": 1.2816697359085083,
"learning_rate": 9.076376937493483e-05,
"loss": 0.5252585411071777,
"step": 9880
},
{
"epoch": 1.0883728608375063,
"grad_norm": 1.2027966976165771,
"learning_rate": 9.058632986992885e-05,
"loss": 0.5822482109069824,
"step": 9890
},
{
"epoch": 1.0894733945963793,
"grad_norm": 1.2647066116333008,
"learning_rate": 9.040892026363779e-05,
"loss": 0.5323410511016846,
"step": 9900
},
{
"epoch": 1.0905739283552522,
"grad_norm": 1.3446309566497803,
"learning_rate": 9.023154111953153e-05,
"loss": 0.5853124618530273,
"step": 9910
},
{
"epoch": 1.0916744621141254,
"grad_norm": 1.6669002771377563,
"learning_rate": 9.005419300098316e-05,
"loss": 0.5669122695922851,
"step": 9920
},
{
"epoch": 1.0927749958729984,
"grad_norm": 1.5223747491836548,
"learning_rate": 8.987687647126726e-05,
"loss": 0.5276257514953613,
"step": 9930
},
{
"epoch": 1.0938755296318714,
"grad_norm": 1.502421498298645,
"learning_rate": 8.969959209355796e-05,
"loss": 0.5534720897674561,
"step": 9940
},
{
"epoch": 1.0949760633907446,
"grad_norm": 1.6878782510757446,
"learning_rate": 8.952234043092748e-05,
"loss": 0.5756337165832519,
"step": 9950
},
{
"epoch": 1.0960765971496176,
"grad_norm": 1.4568076133728027,
"learning_rate": 8.934512204634394e-05,
"loss": 0.5389360427856446,
"step": 9960
},
{
"epoch": 1.0971771309084906,
"grad_norm": 1.538132905960083,
"learning_rate": 8.91679375026699e-05,
"loss": 0.5364737987518311,
"step": 9970
},
{
"epoch": 1.0982776646673638,
"grad_norm": 1.3475421667099,
"learning_rate": 8.899078736266034e-05,
"loss": 0.5229525089263916,
"step": 9980
},
{
"epoch": 1.0993781984262367,
"grad_norm": 1.2797374725341797,
"learning_rate": 8.881367218896106e-05,
"loss": 0.549396562576294,
"step": 9990
},
{
"epoch": 1.1004787321851097,
"grad_norm": 1.4405937194824219,
"learning_rate": 8.86365925441067e-05,
"loss": 0.5339887619018555,
"step": 10000
},
{
"epoch": 1.1004787321851097,
"eval_loss": 0.645664393901825,
"eval_runtime": 932.9022,
"eval_samples_per_second": 9.741,
"eval_steps_per_second": 2.435,
"step": 10000
},
{
"epoch": 1.101579265943983,
"grad_norm": 1.3958356380462646,
"learning_rate": 8.84595489905192e-05,
"loss": 0.5660539150238038,
"step": 10010
},
{
"epoch": 1.102679799702856,
"grad_norm": 1.396467924118042,
"learning_rate": 8.828254209050568e-05,
"loss": 0.5679352760314942,
"step": 10020
},
{
"epoch": 1.1037803334617289,
"grad_norm": 1.2196985483169556,
"learning_rate": 8.810557240625706e-05,
"loss": 0.5765405178070069,
"step": 10030
},
{
"epoch": 1.104880867220602,
"grad_norm": 1.4449983835220337,
"learning_rate": 8.792864049984587e-05,
"loss": 0.5600188255310059,
"step": 10040
},
{
"epoch": 1.105981400979475,
"grad_norm": 1.3970757722854614,
"learning_rate": 8.775174693322478e-05,
"loss": 0.547023868560791,
"step": 10050
},
{
"epoch": 1.107081934738348,
"grad_norm": 1.5250433683395386,
"learning_rate": 8.75748922682246e-05,
"loss": 0.5262825012207031,
"step": 10060
},
{
"epoch": 1.1081824684972212,
"grad_norm": 1.4120254516601562,
"learning_rate": 8.739807706655268e-05,
"loss": 0.5640243530273438,
"step": 10070
},
{
"epoch": 1.1092830022560942,
"grad_norm": 1.482752799987793,
"learning_rate": 8.722130188979093e-05,
"loss": 0.5791533470153809,
"step": 10080
},
{
"epoch": 1.1103835360149672,
"grad_norm": 1.3123983144760132,
"learning_rate": 8.704456729939426e-05,
"loss": 0.5320858001708985,
"step": 10090
},
{
"epoch": 1.1114840697738404,
"grad_norm": 1.3366868495941162,
"learning_rate": 8.68678738566885e-05,
"loss": 0.5802273750305176,
"step": 10100
},
{
"epoch": 1.1125846035327134,
"grad_norm": 1.3356527090072632,
"learning_rate": 8.669122212286895e-05,
"loss": 0.5578311443328857,
"step": 10110
},
{
"epoch": 1.1136851372915864,
"grad_norm": 1.6467251777648926,
"learning_rate": 8.651461265899837e-05,
"loss": 0.5911059379577637,
"step": 10120
},
{
"epoch": 1.1147856710504596,
"grad_norm": 1.4272658824920654,
"learning_rate": 8.63380460260053e-05,
"loss": 0.593011999130249,
"step": 10130
},
{
"epoch": 1.1158862048093325,
"grad_norm": 1.2023085355758667,
"learning_rate": 8.616152278468215e-05,
"loss": 0.5002655506134033,
"step": 10140
},
{
"epoch": 1.1169867385682055,
"grad_norm": 1.3153420686721802,
"learning_rate": 8.598504349568371e-05,
"loss": 0.5830286502838135,
"step": 10150
},
{
"epoch": 1.1180872723270787,
"grad_norm": 1.1589187383651733,
"learning_rate": 8.580860871952488e-05,
"loss": 0.538927412033081,
"step": 10160
},
{
"epoch": 1.1191878060859517,
"grad_norm": 1.4752134084701538,
"learning_rate": 8.563221901657951e-05,
"loss": 0.5325389385223389,
"step": 10170
},
{
"epoch": 1.1202883398448247,
"grad_norm": 1.238957405090332,
"learning_rate": 8.545587494707803e-05,
"loss": 0.5546379566192627,
"step": 10180
},
{
"epoch": 1.1213888736036979,
"grad_norm": 1.6187667846679688,
"learning_rate": 8.52795770711061e-05,
"loss": 0.6247538566589356,
"step": 10190
},
{
"epoch": 1.1224894073625709,
"grad_norm": 1.3420737981796265,
"learning_rate": 8.510332594860254e-05,
"loss": 0.544011402130127,
"step": 10200
},
{
"epoch": 1.1235899411214438,
"grad_norm": 1.467471957206726,
"learning_rate": 8.492712213935781e-05,
"loss": 0.5251177787780762,
"step": 10210
},
{
"epoch": 1.124690474880317,
"grad_norm": 1.3805572986602783,
"learning_rate": 8.475096620301197e-05,
"loss": 0.5827580451965332,
"step": 10220
},
{
"epoch": 1.12579100863919,
"grad_norm": 1.3061833381652832,
"learning_rate": 8.457485869905317e-05,
"loss": 0.569155502319336,
"step": 10230
},
{
"epoch": 1.126891542398063,
"grad_norm": 1.6370940208435059,
"learning_rate": 8.439880018681552e-05,
"loss": 0.5413296222686768,
"step": 10240
},
{
"epoch": 1.1279920761569362,
"grad_norm": 2.5416014194488525,
"learning_rate": 8.422279122547782e-05,
"loss": 0.5164606094360351,
"step": 10250
},
{
"epoch": 1.1290926099158092,
"grad_norm": 1.512996792793274,
"learning_rate": 8.404683237406119e-05,
"loss": 0.516339111328125,
"step": 10260
},
{
"epoch": 1.1301931436746822,
"grad_norm": 1.628615140914917,
"learning_rate": 8.387092419142784e-05,
"loss": 0.579530143737793,
"step": 10270
},
{
"epoch": 1.1312936774335554,
"grad_norm": 1.1453278064727783,
"learning_rate": 8.369506723627887e-05,
"loss": 0.5491249084472656,
"step": 10280
},
{
"epoch": 1.1323942111924283,
"grad_norm": 1.5447189807891846,
"learning_rate": 8.351926206715283e-05,
"loss": 0.5202213287353515,
"step": 10290
},
{
"epoch": 1.1334947449513013,
"grad_norm": 1.273950219154358,
"learning_rate": 8.334350924242367e-05,
"loss": 0.5555094718933106,
"step": 10300
},
{
"epoch": 1.1345952787101745,
"grad_norm": 1.4859063625335693,
"learning_rate": 8.31678093202992e-05,
"loss": 0.5437803268432617,
"step": 10310
},
{
"epoch": 1.1356958124690475,
"grad_norm": 1.7420828342437744,
"learning_rate": 8.299216285881905e-05,
"loss": 0.5592195510864257,
"step": 10320
},
{
"epoch": 1.1367963462279205,
"grad_norm": 1.6611294746398926,
"learning_rate": 8.281657041585322e-05,
"loss": 0.5487903594970703,
"step": 10330
},
{
"epoch": 1.1378968799867937,
"grad_norm": 1.4547579288482666,
"learning_rate": 8.264103254910002e-05,
"loss": 0.5715785026550293,
"step": 10340
},
{
"epoch": 1.1389974137456667,
"grad_norm": 1.1584798097610474,
"learning_rate": 8.246554981608454e-05,
"loss": 0.5216844558715821,
"step": 10350
},
{
"epoch": 1.1400979475045396,
"grad_norm": 1.2190358638763428,
"learning_rate": 8.229012277415662e-05,
"loss": 0.5647663593292236,
"step": 10360
},
{
"epoch": 1.1411984812634128,
"grad_norm": 1.188764214515686,
"learning_rate": 8.211475198048937e-05,
"loss": 0.5595799922943115,
"step": 10370
},
{
"epoch": 1.1422990150222858,
"grad_norm": 1.456380009651184,
"learning_rate": 8.193943799207704e-05,
"loss": 0.5215430736541748,
"step": 10380
},
{
"epoch": 1.1433995487811588,
"grad_norm": 1.1335468292236328,
"learning_rate": 8.176418136573378e-05,
"loss": 0.5104115009307861,
"step": 10390
},
{
"epoch": 1.144500082540032,
"grad_norm": 1.3286983966827393,
"learning_rate": 8.158898265809119e-05,
"loss": 0.5777870655059815,
"step": 10400
},
{
"epoch": 1.145600616298905,
"grad_norm": 1.819345474243164,
"learning_rate": 8.141384242559719e-05,
"loss": 0.5760471820831299,
"step": 10410
},
{
"epoch": 1.146701150057778,
"grad_norm": 1.296452522277832,
"learning_rate": 8.123876122451383e-05,
"loss": 0.5638991832733155,
"step": 10420
},
{
"epoch": 1.1478016838166512,
"grad_norm": 1.227638840675354,
"learning_rate": 8.106373961091574e-05,
"loss": 0.5241059780120849,
"step": 10430
},
{
"epoch": 1.1489022175755241,
"grad_norm": 1.5030274391174316,
"learning_rate": 8.088877814068827e-05,
"loss": 0.5832951068878174,
"step": 10440
},
{
"epoch": 1.150002751334397,
"grad_norm": 1.3097337484359741,
"learning_rate": 8.071387736952578e-05,
"loss": 0.5601954460144043,
"step": 10450
},
{
"epoch": 1.1511032850932703,
"grad_norm": 1.6203055381774902,
"learning_rate": 8.053903785292972e-05,
"loss": 0.5755797863006592,
"step": 10460
},
{
"epoch": 1.1522038188521433,
"grad_norm": 1.3375892639160156,
"learning_rate": 8.036426014620721e-05,
"loss": 0.5382943630218506,
"step": 10470
},
{
"epoch": 1.1533043526110163,
"grad_norm": 1.4045087099075317,
"learning_rate": 8.018954480446883e-05,
"loss": 0.5268109321594239,
"step": 10480
},
{
"epoch": 1.1544048863698895,
"grad_norm": 1.2828348875045776,
"learning_rate": 8.001489238262722e-05,
"loss": 0.5480836868286133,
"step": 10490
},
{
"epoch": 1.1555054201287625,
"grad_norm": 1.5711835622787476,
"learning_rate": 7.984030343539517e-05,
"loss": 0.5869584083557129,
"step": 10500
},
{
"epoch": 1.1566059538876354,
"grad_norm": 1.3476799726486206,
"learning_rate": 7.966577851728378e-05,
"loss": 0.5382761478424072,
"step": 10510
},
{
"epoch": 1.1577064876465086,
"grad_norm": 1.5182106494903564,
"learning_rate": 7.949131818260094e-05,
"loss": 0.6074789047241211,
"step": 10520
},
{
"epoch": 1.1588070214053816,
"grad_norm": 1.3571536540985107,
"learning_rate": 7.931692298544923e-05,
"loss": 0.5754176139831543,
"step": 10530
},
{
"epoch": 1.1599075551642546,
"grad_norm": 1.3608640432357788,
"learning_rate": 7.914259347972453e-05,
"loss": 0.553553295135498,
"step": 10540
},
{
"epoch": 1.1610080889231278,
"grad_norm": 1.243920922279358,
"learning_rate": 7.89683302191139e-05,
"loss": 0.5536637783050538,
"step": 10550
},
{
"epoch": 1.1621086226820008,
"grad_norm": 1.2218928337097168,
"learning_rate": 7.87941337570942e-05,
"loss": 0.5542477607727051,
"step": 10560
},
{
"epoch": 1.1632091564408737,
"grad_norm": 1.670407772064209,
"learning_rate": 7.862000464692991e-05,
"loss": 0.5104245185852051,
"step": 10570
},
{
"epoch": 1.164309690199747,
"grad_norm": 1.2716584205627441,
"learning_rate": 7.84459434416718e-05,
"loss": 0.5328535079956055,
"step": 10580
},
{
"epoch": 1.16541022395862,
"grad_norm": 1.3101935386657715,
"learning_rate": 7.827195069415478e-05,
"loss": 0.5197044849395752,
"step": 10590
},
{
"epoch": 1.166510757717493,
"grad_norm": 1.3846157789230347,
"learning_rate": 7.809802695699653e-05,
"loss": 0.5402404308319092,
"step": 10600
},
{
"epoch": 1.167611291476366,
"grad_norm": 1.82635498046875,
"learning_rate": 7.792417278259534e-05,
"loss": 0.5920222282409668,
"step": 10610
},
{
"epoch": 1.168711825235239,
"grad_norm": 1.3558955192565918,
"learning_rate": 7.775038872312878e-05,
"loss": 0.5492220401763916,
"step": 10620
},
{
"epoch": 1.169812358994112,
"grad_norm": 1.4536257982254028,
"learning_rate": 7.757667533055147e-05,
"loss": 0.6132895469665527,
"step": 10630
},
{
"epoch": 1.1709128927529853,
"grad_norm": 1.6311299800872803,
"learning_rate": 7.740303315659385e-05,
"loss": 0.5418387413024902,
"step": 10640
},
{
"epoch": 1.1720134265118582,
"grad_norm": 1.2570173740386963,
"learning_rate": 7.722946275275997e-05,
"loss": 0.5302232265472412,
"step": 10650
},
{
"epoch": 1.1731139602707312,
"grad_norm": 2.6688199043273926,
"learning_rate": 7.705596467032601e-05,
"loss": 0.5420310497283936,
"step": 10660
},
{
"epoch": 1.1742144940296044,
"grad_norm": 2.012589693069458,
"learning_rate": 7.688253946033847e-05,
"loss": 0.4935464859008789,
"step": 10670
},
{
"epoch": 1.1753150277884774,
"grad_norm": 1.4231624603271484,
"learning_rate": 7.670918767361237e-05,
"loss": 0.5156264305114746,
"step": 10680
},
{
"epoch": 1.1764155615473504,
"grad_norm": 1.4600694179534912,
"learning_rate": 7.653590986072948e-05,
"loss": 0.531367826461792,
"step": 10690
},
{
"epoch": 1.1775160953062236,
"grad_norm": 1.6874834299087524,
"learning_rate": 7.636270657203677e-05,
"loss": 0.5385661602020264,
"step": 10700
},
{
"epoch": 1.1786166290650966,
"grad_norm": 1.3517987728118896,
"learning_rate": 7.618957835764431e-05,
"loss": 0.5076663494110107,
"step": 10710
},
{
"epoch": 1.1797171628239695,
"grad_norm": 1.4955812692642212,
"learning_rate": 7.601652576742391e-05,
"loss": 0.5833661079406738,
"step": 10720
},
{
"epoch": 1.1808176965828427,
"grad_norm": 1.3935877084732056,
"learning_rate": 7.584354935100708e-05,
"loss": 0.5592706680297852,
"step": 10730
},
{
"epoch": 1.1819182303417157,
"grad_norm": 1.2664036750793457,
"learning_rate": 7.567064965778346e-05,
"loss": 0.5279371261596679,
"step": 10740
},
{
"epoch": 1.1830187641005887,
"grad_norm": 1.1014900207519531,
"learning_rate": 7.549782723689895e-05,
"loss": 0.5438811779022217,
"step": 10750
},
{
"epoch": 1.184119297859462,
"grad_norm": 1.4666019678115845,
"learning_rate": 7.532508263725408e-05,
"loss": 0.5314435005187989,
"step": 10760
},
{
"epoch": 1.1852198316183349,
"grad_norm": 1.2678279876708984,
"learning_rate": 7.515241640750216e-05,
"loss": 0.5594861030578613,
"step": 10770
},
{
"epoch": 1.1863203653772079,
"grad_norm": 1.5975234508514404,
"learning_rate": 7.497982909604768e-05,
"loss": 0.5591346263885498,
"step": 10780
},
{
"epoch": 1.187420899136081,
"grad_norm": 1.4370521306991577,
"learning_rate": 7.480732125104432e-05,
"loss": 0.5794358730316163,
"step": 10790
},
{
"epoch": 1.188521432894954,
"grad_norm": 1.2756903171539307,
"learning_rate": 7.463489342039356e-05,
"loss": 0.5140445709228516,
"step": 10800
},
{
"epoch": 1.189621966653827,
"grad_norm": 1.5315232276916504,
"learning_rate": 7.446254615174257e-05,
"loss": 0.5834676265716553,
"step": 10810
},
{
"epoch": 1.1907225004127002,
"grad_norm": 1.4891504049301147,
"learning_rate": 7.429027999248278e-05,
"loss": 0.5219389915466308,
"step": 10820
},
{
"epoch": 1.1918230341715732,
"grad_norm": 1.121517300605774,
"learning_rate": 7.411809548974792e-05,
"loss": 0.6150117874145508,
"step": 10830
},
{
"epoch": 1.1929235679304462,
"grad_norm": 1.5480682849884033,
"learning_rate": 7.394599319041247e-05,
"loss": 0.540202283859253,
"step": 10840
},
{
"epoch": 1.1940241016893194,
"grad_norm": 1.4104912281036377,
"learning_rate": 7.377397364108964e-05,
"loss": 0.5523455619812012,
"step": 10850
},
{
"epoch": 1.1951246354481924,
"grad_norm": 1.5009377002716064,
"learning_rate": 7.36020373881301e-05,
"loss": 0.5467785835266114,
"step": 10860
},
{
"epoch": 1.1962251692070653,
"grad_norm": 1.069107174873352,
"learning_rate": 7.343018497761967e-05,
"loss": 0.5234423637390136,
"step": 10870
},
{
"epoch": 1.1973257029659385,
"grad_norm": 1.7287311553955078,
"learning_rate": 7.325841695537807e-05,
"loss": 0.550012731552124,
"step": 10880
},
{
"epoch": 1.1984262367248115,
"grad_norm": 1.5347057580947876,
"learning_rate": 7.30867338669569e-05,
"loss": 0.5385851860046387,
"step": 10890
},
{
"epoch": 1.1995267704836845,
"grad_norm": 1.8157823085784912,
"learning_rate": 7.291513625763811e-05,
"loss": 0.5204545021057129,
"step": 10900
},
{
"epoch": 1.2006273042425577,
"grad_norm": 1.426628589630127,
"learning_rate": 7.2743624672432e-05,
"loss": 0.5078720092773438,
"step": 10910
},
{
"epoch": 1.2017278380014307,
"grad_norm": 1.2783440351486206,
"learning_rate": 7.257219965607582e-05,
"loss": 0.5363798141479492,
"step": 10920
},
{
"epoch": 1.2028283717603037,
"grad_norm": 1.0291374921798706,
"learning_rate": 7.240086175303167e-05,
"loss": 0.5672127723693847,
"step": 10930
},
{
"epoch": 1.2039289055191769,
"grad_norm": 1.4691543579101562,
"learning_rate": 7.222961150748522e-05,
"loss": 0.5512874126434326,
"step": 10940
},
{
"epoch": 1.2050294392780498,
"grad_norm": 1.160654902458191,
"learning_rate": 7.20584494633435e-05,
"loss": 0.5304359912872314,
"step": 10950
},
{
"epoch": 1.2061299730369228,
"grad_norm": 1.8972187042236328,
"learning_rate": 7.188737616423356e-05,
"loss": 0.5836920261383056,
"step": 10960
},
{
"epoch": 1.207230506795796,
"grad_norm": 1.4059360027313232,
"learning_rate": 7.171639215350048e-05,
"loss": 0.5374305725097657,
"step": 10970
},
{
"epoch": 1.208331040554669,
"grad_norm": 1.2987669706344604,
"learning_rate": 7.154549797420585e-05,
"loss": 0.5593585968017578,
"step": 10980
},
{
"epoch": 1.209431574313542,
"grad_norm": 1.3504046201705933,
"learning_rate": 7.137469416912584e-05,
"loss": 0.4856422901153564,
"step": 10990
},
{
"epoch": 1.2105321080724152,
"grad_norm": 1.179612159729004,
"learning_rate": 7.120398128074972e-05,
"loss": 0.5871953010559082,
"step": 11000
},
{
"epoch": 1.2105321080724152,
"eval_loss": 0.6313351392745972,
"eval_runtime": 932.0447,
"eval_samples_per_second": 9.75,
"eval_steps_per_second": 2.438,
"step": 11000
},
{
"epoch": 1.2116326418312882,
"grad_norm": 1.352623701095581,
"learning_rate": 7.103335985127781e-05,
"loss": 0.5402306079864502,
"step": 11010
},
{
"epoch": 1.2127331755901611,
"grad_norm": 1.3804001808166504,
"learning_rate": 7.086283042262017e-05,
"loss": 0.5479353427886963,
"step": 11020
},
{
"epoch": 1.2138337093490343,
"grad_norm": 1.2353771924972534,
"learning_rate": 7.069239353639444e-05,
"loss": 0.5009084224700928,
"step": 11030
},
{
"epoch": 1.2149342431079073,
"grad_norm": 1.2486281394958496,
"learning_rate": 7.052204973392453e-05,
"loss": 0.5391026496887207,
"step": 11040
},
{
"epoch": 1.2160347768667803,
"grad_norm": 1.4168950319290161,
"learning_rate": 7.035179955623854e-05,
"loss": 0.5182691097259522,
"step": 11050
},
{
"epoch": 1.2171353106256535,
"grad_norm": 1.3232142925262451,
"learning_rate": 7.018164354406737e-05,
"loss": 0.5839329719543457,
"step": 11060
},
{
"epoch": 1.2182358443845265,
"grad_norm": 1.8011705875396729,
"learning_rate": 7.001158223784266e-05,
"loss": 0.554843521118164,
"step": 11070
},
{
"epoch": 1.2193363781433995,
"grad_norm": 1.805098056793213,
"learning_rate": 6.984161617769547e-05,
"loss": 0.4783599376678467,
"step": 11080
},
{
"epoch": 1.2204369119022727,
"grad_norm": 1.480394959449768,
"learning_rate": 6.96717459034541e-05,
"loss": 0.5437171459197998,
"step": 11090
},
{
"epoch": 1.2215374456611456,
"grad_norm": 1.3816556930541992,
"learning_rate": 6.950197195464288e-05,
"loss": 0.6335927009582519,
"step": 11100
},
{
"epoch": 1.2226379794200186,
"grad_norm": 1.5177781581878662,
"learning_rate": 6.933229487047997e-05,
"loss": 0.5134160041809082,
"step": 11110
},
{
"epoch": 1.2237385131788918,
"grad_norm": 1.4167152643203735,
"learning_rate": 6.916271518987606e-05,
"loss": 0.5330657005310059,
"step": 11120
},
{
"epoch": 1.2248390469377648,
"grad_norm": 1.5164214372634888,
"learning_rate": 6.899323345143236e-05,
"loss": 0.5688257217407227,
"step": 11130
},
{
"epoch": 1.2259395806966378,
"grad_norm": 1.772307276725769,
"learning_rate": 6.882385019343912e-05,
"loss": 0.5567258358001709,
"step": 11140
},
{
"epoch": 1.227040114455511,
"grad_norm": 1.391466736793518,
"learning_rate": 6.86545659538736e-05,
"loss": 0.5308495044708252,
"step": 11150
},
{
"epoch": 1.228140648214384,
"grad_norm": 1.3482818603515625,
"learning_rate": 6.848538127039888e-05,
"loss": 0.5634209632873535,
"step": 11160
},
{
"epoch": 1.229241181973257,
"grad_norm": 1.2815320491790771,
"learning_rate": 6.831629668036153e-05,
"loss": 0.5400688648223877,
"step": 11170
},
{
"epoch": 1.2303417157321301,
"grad_norm": 1.2190264463424683,
"learning_rate": 6.814731272079041e-05,
"loss": 0.5475270271301269,
"step": 11180
},
{
"epoch": 1.2314422494910031,
"grad_norm": 1.4535679817199707,
"learning_rate": 6.797842992839468e-05,
"loss": 0.5594796180725098,
"step": 11190
},
{
"epoch": 1.232542783249876,
"grad_norm": 1.440649390220642,
"learning_rate": 6.780964883956223e-05,
"loss": 0.5315773010253906,
"step": 11200
},
{
"epoch": 1.2336433170087493,
"grad_norm": 1.3808083534240723,
"learning_rate": 6.764096999035786e-05,
"loss": 0.5375969886779786,
"step": 11210
},
{
"epoch": 1.2347438507676223,
"grad_norm": 1.2516003847122192,
"learning_rate": 6.74723939165218e-05,
"loss": 0.564496660232544,
"step": 11220
},
{
"epoch": 1.2358443845264953,
"grad_norm": 1.2547093629837036,
"learning_rate": 6.730392115346765e-05,
"loss": 0.5357757091522217,
"step": 11230
},
{
"epoch": 1.2369449182853685,
"grad_norm": 1.3246700763702393,
"learning_rate": 6.713555223628102e-05,
"loss": 0.5504026412963867,
"step": 11240
},
{
"epoch": 1.2380454520442414,
"grad_norm": 1.5105892419815063,
"learning_rate": 6.696728769971768e-05,
"loss": 0.49925909042358396,
"step": 11250
},
{
"epoch": 1.2391459858031144,
"grad_norm": 1.5887067317962646,
"learning_rate": 6.679912807820186e-05,
"loss": 0.5856089115142822,
"step": 11260
},
{
"epoch": 1.2402465195619876,
"grad_norm": 1.463101863861084,
"learning_rate": 6.663107390582455e-05,
"loss": 0.546326732635498,
"step": 11270
},
{
"epoch": 1.2413470533208606,
"grad_norm": 1.1963809728622437,
"learning_rate": 6.646312571634188e-05,
"loss": 0.46823701858520506,
"step": 11280
},
{
"epoch": 1.2424475870797336,
"grad_norm": 1.434715747833252,
"learning_rate": 6.629528404317325e-05,
"loss": 0.5244136810302734,
"step": 11290
},
{
"epoch": 1.2435481208386068,
"grad_norm": 1.4906326532363892,
"learning_rate": 6.612754941939995e-05,
"loss": 0.5256683826446533,
"step": 11300
},
{
"epoch": 1.2446486545974798,
"grad_norm": 1.4505363702774048,
"learning_rate": 6.595992237776306e-05,
"loss": 0.5030346870422363,
"step": 11310
},
{
"epoch": 1.2457491883563527,
"grad_norm": 1.7681077718734741,
"learning_rate": 6.579240345066212e-05,
"loss": 0.5191401481628418,
"step": 11320
},
{
"epoch": 1.246849722115226,
"grad_norm": 1.6598243713378906,
"learning_rate": 6.562499317015321e-05,
"loss": 0.5171903133392334,
"step": 11330
},
{
"epoch": 1.247950255874099,
"grad_norm": 1.3658227920532227,
"learning_rate": 6.545769206794738e-05,
"loss": 0.5106462001800537,
"step": 11340
},
{
"epoch": 1.249050789632972,
"grad_norm": 1.4717799425125122,
"learning_rate": 6.529050067540887e-05,
"loss": 0.53608717918396,
"step": 11350
},
{
"epoch": 1.250151323391845,
"grad_norm": 1.272996187210083,
"learning_rate": 6.512341952355356e-05,
"loss": 0.5537538528442383,
"step": 11360
},
{
"epoch": 1.251251857150718,
"grad_norm": 1.7279982566833496,
"learning_rate": 6.495644914304703e-05,
"loss": 0.48906898498535156,
"step": 11370
},
{
"epoch": 1.252352390909591,
"grad_norm": 1.6621391773223877,
"learning_rate": 6.478959006420332e-05,
"loss": 0.5204698085784912,
"step": 11380
},
{
"epoch": 1.2534529246684643,
"grad_norm": 1.3156055212020874,
"learning_rate": 6.46228428169826e-05,
"loss": 0.5125308513641358,
"step": 11390
},
{
"epoch": 1.2545534584273372,
"grad_norm": 1.330880045890808,
"learning_rate": 6.445620793099017e-05,
"loss": 0.5905975341796875,
"step": 11400
},
{
"epoch": 1.2556539921862102,
"grad_norm": 1.2688566446304321,
"learning_rate": 6.428968593547428e-05,
"loss": 0.538023853302002,
"step": 11410
},
{
"epoch": 1.2567545259450834,
"grad_norm": 1.4353107213974,
"learning_rate": 6.412327735932473e-05,
"loss": 0.5337255001068115,
"step": 11420
},
{
"epoch": 1.2578550597039564,
"grad_norm": 1.5013387203216553,
"learning_rate": 6.395698273107101e-05,
"loss": 0.5099579811096191,
"step": 11430
},
{
"epoch": 1.2589555934628294,
"grad_norm": 1.2426739931106567,
"learning_rate": 6.379080257888075e-05,
"loss": 0.534146785736084,
"step": 11440
},
{
"epoch": 1.2600561272217026,
"grad_norm": 1.6446844339370728,
"learning_rate": 6.362473743055793e-05,
"loss": 0.5322544574737549,
"step": 11450
},
{
"epoch": 1.2611566609805756,
"grad_norm": 1.686376690864563,
"learning_rate": 6.345878781354137e-05,
"loss": 0.49163188934326174,
"step": 11460
},
{
"epoch": 1.2622571947394485,
"grad_norm": 1.1854013204574585,
"learning_rate": 6.329295425490287e-05,
"loss": 0.5487308025360107,
"step": 11470
},
{
"epoch": 1.2633577284983217,
"grad_norm": 1.2076501846313477,
"learning_rate": 6.312723728134565e-05,
"loss": 0.5687746524810791,
"step": 11480
},
{
"epoch": 1.2644582622571947,
"grad_norm": 1.283212661743164,
"learning_rate": 6.296163741920262e-05,
"loss": 0.5073586463928222,
"step": 11490
},
{
"epoch": 1.2655587960160677,
"grad_norm": 1.5739465951919556,
"learning_rate": 6.279615519443478e-05,
"loss": 0.5076786041259765,
"step": 11500
},
{
"epoch": 1.266659329774941,
"grad_norm": 1.2881146669387817,
"learning_rate": 6.263079113262943e-05,
"loss": 0.5398012161254883,
"step": 11510
},
{
"epoch": 1.2677598635338139,
"grad_norm": 1.2973806858062744,
"learning_rate": 6.246554575899865e-05,
"loss": 0.5032637596130372,
"step": 11520
},
{
"epoch": 1.2688603972926868,
"grad_norm": 1.1523220539093018,
"learning_rate": 6.230041959837755e-05,
"loss": 0.5277178287506104,
"step": 11530
},
{
"epoch": 1.26996093105156,
"grad_norm": 1.4288959503173828,
"learning_rate": 6.213541317522248e-05,
"loss": 0.5073719978332519,
"step": 11540
},
{
"epoch": 1.271061464810433,
"grad_norm": 1.527894377708435,
"learning_rate": 6.197052701360972e-05,
"loss": 0.5319782733917237,
"step": 11550
},
{
"epoch": 1.272161998569306,
"grad_norm": 1.3601008653640747,
"learning_rate": 6.180576163723335e-05,
"loss": 0.5333952903747559,
"step": 11560
},
{
"epoch": 1.2732625323281792,
"grad_norm": 1.3930809497833252,
"learning_rate": 6.164111756940399e-05,
"loss": 0.5384100437164306,
"step": 11570
},
{
"epoch": 1.2743630660870522,
"grad_norm": 1.320168137550354,
"learning_rate": 6.147659533304688e-05,
"loss": 0.5310112476348877,
"step": 11580
},
{
"epoch": 1.2754635998459252,
"grad_norm": 1.419121265411377,
"learning_rate": 6.13121954507004e-05,
"loss": 0.5662523746490479,
"step": 11590
},
{
"epoch": 1.2765641336047984,
"grad_norm": 1.4326211214065552,
"learning_rate": 6.11479184445142e-05,
"loss": 0.548285961151123,
"step": 11600
},
{
"epoch": 1.2776646673636713,
"grad_norm": 1.1404590606689453,
"learning_rate": 6.098376483624781e-05,
"loss": 0.5539699077606202,
"step": 11610
},
{
"epoch": 1.2787652011225443,
"grad_norm": 1.2722629308700562,
"learning_rate": 6.0819735147268684e-05,
"loss": 0.5377175331115722,
"step": 11620
},
{
"epoch": 1.2798657348814175,
"grad_norm": 1.4954121112823486,
"learning_rate": 6.065582989855084e-05,
"loss": 0.5826393127441406,
"step": 11630
},
{
"epoch": 1.2809662686402905,
"grad_norm": 1.3951152563095093,
"learning_rate": 6.049204961067294e-05,
"loss": 0.4958986759185791,
"step": 11640
},
{
"epoch": 1.2820668023991635,
"grad_norm": 1.2395576238632202,
"learning_rate": 6.032839480381686e-05,
"loss": 0.5686951160430909,
"step": 11650
},
{
"epoch": 1.2831673361580367,
"grad_norm": 1.4314342737197876,
"learning_rate": 6.016486599776583e-05,
"loss": 0.5331714153289795,
"step": 11660
},
{
"epoch": 1.2842678699169097,
"grad_norm": 1.52439284324646,
"learning_rate": 6.000146371190301e-05,
"loss": 0.5311639785766602,
"step": 11670
},
{
"epoch": 1.2853684036757826,
"grad_norm": 1.2747385501861572,
"learning_rate": 5.983818846520961e-05,
"loss": 0.5257352828979492,
"step": 11680
},
{
"epoch": 1.2864689374346558,
"grad_norm": 1.2864420413970947,
"learning_rate": 5.967504077626347e-05,
"loss": 0.5125638961791992,
"step": 11690
},
{
"epoch": 1.2875694711935288,
"grad_norm": 1.7245609760284424,
"learning_rate": 5.951202116323713e-05,
"loss": 0.5418309211730957,
"step": 11700
},
{
"epoch": 1.2886700049524018,
"grad_norm": 1.4170472621917725,
"learning_rate": 5.934913014389649e-05,
"loss": 0.5558959007263183,
"step": 11710
},
{
"epoch": 1.289770538711275,
"grad_norm": 1.3441578149795532,
"learning_rate": 5.9186368235598974e-05,
"loss": 0.5303954124450684,
"step": 11720
},
{
"epoch": 1.290871072470148,
"grad_norm": 1.413962721824646,
"learning_rate": 5.902373595529195e-05,
"loss": 0.512939167022705,
"step": 11730
},
{
"epoch": 1.291971606229021,
"grad_norm": 1.4360628128051758,
"learning_rate": 5.886123381951103e-05,
"loss": 0.5611459732055664,
"step": 11740
},
{
"epoch": 1.2930721399878942,
"grad_norm": 1.286071538925171,
"learning_rate": 5.869886234437858e-05,
"loss": 0.45622029304504397,
"step": 11750
},
{
"epoch": 1.2941726737467671,
"grad_norm": 1.3270988464355469,
"learning_rate": 5.85366220456018e-05,
"loss": 0.5786046504974365,
"step": 11760
},
{
"epoch": 1.2952732075056401,
"grad_norm": 1.5115126371383667,
"learning_rate": 5.837451343847148e-05,
"loss": 0.5562834739685059,
"step": 11770
},
{
"epoch": 1.2963737412645133,
"grad_norm": 1.062003493309021,
"learning_rate": 5.821253703785991e-05,
"loss": 0.5147458553314209,
"step": 11780
},
{
"epoch": 1.2974742750233863,
"grad_norm": 1.228249430656433,
"learning_rate": 5.805069335821975e-05,
"loss": 0.5717658996582031,
"step": 11790
},
{
"epoch": 1.2985748087822593,
"grad_norm": 1.596361756324768,
"learning_rate": 5.788898291358181e-05,
"loss": 0.5841880321502686,
"step": 11800
},
{
"epoch": 1.2996753425411325,
"grad_norm": 1.5199474096298218,
"learning_rate": 5.7727406217554025e-05,
"loss": 0.555940818786621,
"step": 11810
},
{
"epoch": 1.3007758763000055,
"grad_norm": 1.4114420413970947,
"learning_rate": 5.7565963783319356e-05,
"loss": 0.5127843856811524,
"step": 11820
},
{
"epoch": 1.3018764100588784,
"grad_norm": 1.6298942565917969,
"learning_rate": 5.7404656123634395e-05,
"loss": 0.5329164981842041,
"step": 11830
},
{
"epoch": 1.3029769438177516,
"grad_norm": 1.439675211906433,
"learning_rate": 5.724348375082762e-05,
"loss": 0.5392729759216308,
"step": 11840
},
{
"epoch": 1.3040774775766246,
"grad_norm": 1.2933672666549683,
"learning_rate": 5.708244717679794e-05,
"loss": 0.4998462677001953,
"step": 11850
},
{
"epoch": 1.3051780113354976,
"grad_norm": 1.6806026697158813,
"learning_rate": 5.6921546913012876e-05,
"loss": 0.5419587135314942,
"step": 11860
},
{
"epoch": 1.3062785450943708,
"grad_norm": 1.4215166568756104,
"learning_rate": 5.6760783470506996e-05,
"loss": 0.4861127853393555,
"step": 11870
},
{
"epoch": 1.3073790788532438,
"grad_norm": 1.4881281852722168,
"learning_rate": 5.660015735988037e-05,
"loss": 0.5439533710479736,
"step": 11880
},
{
"epoch": 1.3084796126121168,
"grad_norm": 1.171539306640625,
"learning_rate": 5.643966909129683e-05,
"loss": 0.5540058612823486,
"step": 11890
},
{
"epoch": 1.30958014637099,
"grad_norm": 1.3200775384902954,
"learning_rate": 5.627931917448242e-05,
"loss": 0.5166882991790771,
"step": 11900
},
{
"epoch": 1.310680680129863,
"grad_norm": 1.4884803295135498,
"learning_rate": 5.611910811872383e-05,
"loss": 0.5412510871887207,
"step": 11910
},
{
"epoch": 1.311781213888736,
"grad_norm": 1.2572506666183472,
"learning_rate": 5.595903643286666e-05,
"loss": 0.5392833232879639,
"step": 11920
},
{
"epoch": 1.3128817476476091,
"grad_norm": 1.3699381351470947,
"learning_rate": 5.579910462531386e-05,
"loss": 0.5508726596832275,
"step": 11930
},
{
"epoch": 1.313982281406482,
"grad_norm": 1.1962960958480835,
"learning_rate": 5.563931320402404e-05,
"loss": 0.48737268447875975,
"step": 11940
},
{
"epoch": 1.315082815165355,
"grad_norm": 1.2119905948638916,
"learning_rate": 5.547966267651019e-05,
"loss": 0.49958209991455077,
"step": 11950
},
{
"epoch": 1.3161833489242283,
"grad_norm": 1.4131637811660767,
"learning_rate": 5.5320153549837415e-05,
"loss": 0.5119901180267334,
"step": 11960
},
{
"epoch": 1.3172838826831013,
"grad_norm": 1.5542107820510864,
"learning_rate": 5.516078633062207e-05,
"loss": 0.4940051555633545,
"step": 11970
},
{
"epoch": 1.3183844164419742,
"grad_norm": 2.2184031009674072,
"learning_rate": 5.5001561525029624e-05,
"loss": 0.515054178237915,
"step": 11980
},
{
"epoch": 1.3194849502008474,
"grad_norm": 1.4567434787750244,
"learning_rate": 5.4842479638773226e-05,
"loss": 0.5146004676818847,
"step": 11990
},
{
"epoch": 1.3205854839597204,
"grad_norm": 2.799847364425659,
"learning_rate": 5.468354117711212e-05,
"loss": 0.5162035465240479,
"step": 12000
},
{
"epoch": 1.3205854839597204,
"eval_loss": 0.6135916709899902,
"eval_runtime": 932.9854,
"eval_samples_per_second": 9.74,
"eval_steps_per_second": 2.435,
"step": 12000
},
{
"epoch": 1.3216860177185934,
"grad_norm": 1.5677978992462158,
"learning_rate": 5.452474664485014e-05,
"loss": 0.49845075607299805,
"step": 12010
},
{
"epoch": 1.3227865514774666,
"grad_norm": 1.5483510494232178,
"learning_rate": 5.4366096546333734e-05,
"loss": 0.5526577472686768,
"step": 12020
},
{
"epoch": 1.3238870852363396,
"grad_norm": 1.186592698097229,
"learning_rate": 5.420759138545086e-05,
"loss": 0.494019079208374,
"step": 12030
},
{
"epoch": 1.3249876189952126,
"grad_norm": 1.410312294960022,
"learning_rate": 5.4049231665629006e-05,
"loss": 0.5278650760650635,
"step": 12040
},
{
"epoch": 1.3260881527540858,
"grad_norm": 1.6113433837890625,
"learning_rate": 5.3891017889833776e-05,
"loss": 0.5318747520446777,
"step": 12050
},
{
"epoch": 1.3271886865129587,
"grad_norm": 1.4662244319915771,
"learning_rate": 5.3732950560567155e-05,
"loss": 0.4939723014831543,
"step": 12060
},
{
"epoch": 1.3282892202718317,
"grad_norm": 1.315240740776062,
"learning_rate": 5.357503017986617e-05,
"loss": 0.5257238388061524,
"step": 12070
},
{
"epoch": 1.329389754030705,
"grad_norm": 1.2644096612930298,
"learning_rate": 5.341725724930098e-05,
"loss": 0.5119235515594482,
"step": 12080
},
{
"epoch": 1.330490287789578,
"grad_norm": 1.6229888200759888,
"learning_rate": 5.325963226997347e-05,
"loss": 0.5457443237304688,
"step": 12090
},
{
"epoch": 1.3315908215484509,
"grad_norm": 1.637445092201233,
"learning_rate": 5.3102155742515626e-05,
"loss": 0.49096202850341797,
"step": 12100
},
{
"epoch": 1.332691355307324,
"grad_norm": 1.6066944599151611,
"learning_rate": 5.2944828167087926e-05,
"loss": 0.48032388687133787,
"step": 12110
},
{
"epoch": 1.333791889066197,
"grad_norm": 1.6189576387405396,
"learning_rate": 5.2787650043377736e-05,
"loss": 0.5643033504486084,
"step": 12120
},
{
"epoch": 1.33489242282507,
"grad_norm": 1.4686189889907837,
"learning_rate": 5.263062187059785e-05,
"loss": 0.549506425857544,
"step": 12130
},
{
"epoch": 1.3359929565839432,
"grad_norm": 1.4847965240478516,
"learning_rate": 5.2473744147484705e-05,
"loss": 0.49640259742736814,
"step": 12140
},
{
"epoch": 1.3370934903428162,
"grad_norm": 1.6143943071365356,
"learning_rate": 5.231701737229692e-05,
"loss": 0.4493229389190674,
"step": 12150
},
{
"epoch": 1.3381940241016892,
"grad_norm": 1.4236085414886475,
"learning_rate": 5.216044204281365e-05,
"loss": 0.5239033222198486,
"step": 12160
},
{
"epoch": 1.3392945578605624,
"grad_norm": 1.2380789518356323,
"learning_rate": 5.200401865633322e-05,
"loss": 0.4879602909088135,
"step": 12170
},
{
"epoch": 1.3403950916194354,
"grad_norm": 1.3326728343963623,
"learning_rate": 5.184774770967107e-05,
"loss": 0.5358062744140625,
"step": 12180
},
{
"epoch": 1.3414956253783084,
"grad_norm": 1.3785207271575928,
"learning_rate": 5.169162969915875e-05,
"loss": 0.5260441780090332,
"step": 12190
},
{
"epoch": 1.3425961591371816,
"grad_norm": 1.303104043006897,
"learning_rate": 5.153566512064194e-05,
"loss": 0.5232130527496338,
"step": 12200
},
{
"epoch": 1.3436966928960545,
"grad_norm": 1.6834733486175537,
"learning_rate": 5.1379854469479036e-05,
"loss": 0.528822374343872,
"step": 12210
},
{
"epoch": 1.3447972266549275,
"grad_norm": 1.6714493036270142,
"learning_rate": 5.122419824053948e-05,
"loss": 0.5261149883270264,
"step": 12220
},
{
"epoch": 1.3458977604138007,
"grad_norm": 1.4997385740280151,
"learning_rate": 5.1068696928202444e-05,
"loss": 0.5220358848571778,
"step": 12230
},
{
"epoch": 1.3469982941726737,
"grad_norm": 1.4198510646820068,
"learning_rate": 5.091335102635479e-05,
"loss": 0.5430432796478272,
"step": 12240
},
{
"epoch": 1.3480988279315467,
"grad_norm": 1.3801181316375732,
"learning_rate": 5.075816102839004e-05,
"loss": 0.5042877197265625,
"step": 12250
},
{
"epoch": 1.3491993616904199,
"grad_norm": 1.2426743507385254,
"learning_rate": 5.060312742720639e-05,
"loss": 0.5603894233703614,
"step": 12260
},
{
"epoch": 1.3502998954492929,
"grad_norm": 1.430693507194519,
"learning_rate": 5.044825071520538e-05,
"loss": 0.5188490390777588,
"step": 12270
},
{
"epoch": 1.3514004292081658,
"grad_norm": 1.1664015054702759,
"learning_rate": 5.029353138429018e-05,
"loss": 0.5350808143615723,
"step": 12280
},
{
"epoch": 1.352500962967039,
"grad_norm": 1.3433830738067627,
"learning_rate": 5.013896992586424e-05,
"loss": 0.5293370723724365,
"step": 12290
},
{
"epoch": 1.353601496725912,
"grad_norm": 1.5283178091049194,
"learning_rate": 4.998456683082945e-05,
"loss": 0.5362238883972168,
"step": 12300
},
{
"epoch": 1.354702030484785,
"grad_norm": 1.371490716934204,
"learning_rate": 4.98303225895848e-05,
"loss": 0.5349930763244629,
"step": 12310
},
{
"epoch": 1.3558025642436582,
"grad_norm": 1.4135675430297852,
"learning_rate": 4.9676237692024676e-05,
"loss": 0.5660553932189941,
"step": 12320
},
{
"epoch": 1.3569030980025312,
"grad_norm": 1.3543716669082642,
"learning_rate": 4.952231262753752e-05,
"loss": 0.5383255481719971,
"step": 12330
},
{
"epoch": 1.3580036317614042,
"grad_norm": 1.4029062986373901,
"learning_rate": 4.936854788500391e-05,
"loss": 0.5411499977111817,
"step": 12340
},
{
"epoch": 1.3591041655202774,
"grad_norm": 1.5914642810821533,
"learning_rate": 4.9214943952795446e-05,
"loss": 0.5031930923461914,
"step": 12350
},
{
"epoch": 1.3602046992791503,
"grad_norm": 1.189834713935852,
"learning_rate": 4.906150131877283e-05,
"loss": 0.5469556331634522,
"step": 12360
},
{
"epoch": 1.3613052330380233,
"grad_norm": 1.6527738571166992,
"learning_rate": 4.890822047028454e-05,
"loss": 0.5288655281066894,
"step": 12370
},
{
"epoch": 1.3624057667968965,
"grad_norm": 1.2583094835281372,
"learning_rate": 4.875510189416511e-05,
"loss": 0.5249460697174072,
"step": 12380
},
{
"epoch": 1.3635063005557695,
"grad_norm": 1.339673638343811,
"learning_rate": 4.86021460767339e-05,
"loss": 0.5296471595764161,
"step": 12390
},
{
"epoch": 1.3646068343146425,
"grad_norm": 1.3416361808776855,
"learning_rate": 4.8449353503793014e-05,
"loss": 0.5382433891296386,
"step": 12400
},
{
"epoch": 1.3657073680735157,
"grad_norm": 1.7241756916046143,
"learning_rate": 4.829672466062638e-05,
"loss": 0.5634636878967285,
"step": 12410
},
{
"epoch": 1.3668079018323886,
"grad_norm": 1.4954578876495361,
"learning_rate": 4.814426003199772e-05,
"loss": 0.49434552192687986,
"step": 12420
},
{
"epoch": 1.3679084355912616,
"grad_norm": 1.4081655740737915,
"learning_rate": 4.799196010214926e-05,
"loss": 0.559640645980835,
"step": 12430
},
{
"epoch": 1.3690089693501348,
"grad_norm": 1.3289753198623657,
"learning_rate": 4.783982535480007e-05,
"loss": 0.5251254558563232,
"step": 12440
},
{
"epoch": 1.3701095031090078,
"grad_norm": 1.3901984691619873,
"learning_rate": 4.768785627314476e-05,
"loss": 0.5464468955993652,
"step": 12450
},
{
"epoch": 1.3712100368678808,
"grad_norm": 1.6319056749343872,
"learning_rate": 4.7536053339851464e-05,
"loss": 0.5166916370391845,
"step": 12460
},
{
"epoch": 1.372310570626754,
"grad_norm": 1.2068886756896973,
"learning_rate": 4.738441703706091e-05,
"loss": 0.49025301933288573,
"step": 12470
},
{
"epoch": 1.373411104385627,
"grad_norm": 1.2937670946121216,
"learning_rate": 4.723294784638445e-05,
"loss": 0.538811445236206,
"step": 12480
},
{
"epoch": 1.3745116381445,
"grad_norm": 1.159222960472107,
"learning_rate": 4.7081646248902664e-05,
"loss": 0.533691692352295,
"step": 12490
},
{
"epoch": 1.3756121719033731,
"grad_norm": 1.475082516670227,
"learning_rate": 4.693051272516385e-05,
"loss": 0.5690941333770752,
"step": 12500
},
{
"epoch": 1.3767127056622461,
"grad_norm": 1.3520079851150513,
"learning_rate": 4.6779547755182595e-05,
"loss": 0.5233016014099121,
"step": 12510
},
{
"epoch": 1.377813239421119,
"grad_norm": 1.2905855178833008,
"learning_rate": 4.6628751818437985e-05,
"loss": 0.5325565338134766,
"step": 12520
},
{
"epoch": 1.3789137731799923,
"grad_norm": 1.3417586088180542,
"learning_rate": 4.6478125393872326e-05,
"loss": 0.5162881374359131,
"step": 12530
},
{
"epoch": 1.3800143069388653,
"grad_norm": 1.269593596458435,
"learning_rate": 4.632766895988949e-05,
"loss": 0.5292275905609131,
"step": 12540
},
{
"epoch": 1.3811148406977383,
"grad_norm": 1.2621039152145386,
"learning_rate": 4.617738299435353e-05,
"loss": 0.5439098358154297,
"step": 12550
},
{
"epoch": 1.3822153744566115,
"grad_norm": 2.1502459049224854,
"learning_rate": 4.6027267974587e-05,
"loss": 0.5295673847198487,
"step": 12560
},
{
"epoch": 1.3833159082154844,
"grad_norm": 1.1357793807983398,
"learning_rate": 4.587732437736952e-05,
"loss": 0.5145630836486816,
"step": 12570
},
{
"epoch": 1.3844164419743574,
"grad_norm": 1.447072982788086,
"learning_rate": 4.572755267893628e-05,
"loss": 0.5478739738464355,
"step": 12580
},
{
"epoch": 1.3855169757332306,
"grad_norm": 1.6219820976257324,
"learning_rate": 4.557795335497643e-05,
"loss": 0.5329634666442871,
"step": 12590
},
{
"epoch": 1.3866175094921036,
"grad_norm": 1.6089611053466797,
"learning_rate": 4.5428526880631815e-05,
"loss": 0.5637258052825928,
"step": 12600
},
{
"epoch": 1.3877180432509766,
"grad_norm": 1.7128835916519165,
"learning_rate": 4.527927373049511e-05,
"loss": 0.5293717384338379,
"step": 12610
},
{
"epoch": 1.3888185770098498,
"grad_norm": 1.4186064004898071,
"learning_rate": 4.513019437860858e-05,
"loss": 0.4770808696746826,
"step": 12620
},
{
"epoch": 1.3899191107687228,
"grad_norm": 1.505110740661621,
"learning_rate": 4.4981289298462446e-05,
"loss": 0.5102827072143554,
"step": 12630
},
{
"epoch": 1.391019644527596,
"grad_norm": 2.0490097999572754,
"learning_rate": 4.483255896299357e-05,
"loss": 0.5344661712646485,
"step": 12640
},
{
"epoch": 1.392120178286469,
"grad_norm": 1.282111406326294,
"learning_rate": 4.4684003844583534e-05,
"loss": 0.5514573097229004,
"step": 12650
},
{
"epoch": 1.393220712045342,
"grad_norm": 1.6085493564605713,
"learning_rate": 4.4535624415057684e-05,
"loss": 0.5532805442810058,
"step": 12660
},
{
"epoch": 1.3943212458042151,
"grad_norm": 1.3189293146133423,
"learning_rate": 4.438742114568324e-05,
"loss": 0.46045541763305664,
"step": 12670
},
{
"epoch": 1.395421779563088,
"grad_norm": 1.4094516038894653,
"learning_rate": 4.423939450716791e-05,
"loss": 0.5289006710052491,
"step": 12680
},
{
"epoch": 1.396522313321961,
"grad_norm": 1.194648265838623,
"learning_rate": 4.4091544969658385e-05,
"loss": 0.4610511302947998,
"step": 12690
},
{
"epoch": 1.3976228470808343,
"grad_norm": 1.4054875373840332,
"learning_rate": 4.3943873002739044e-05,
"loss": 0.5385354995727539,
"step": 12700
},
{
"epoch": 1.3987233808397073,
"grad_norm": 1.3765729665756226,
"learning_rate": 4.3796379075429994e-05,
"loss": 0.5162423133850098,
"step": 12710
},
{
"epoch": 1.3998239145985802,
"grad_norm": 1.9108331203460693,
"learning_rate": 4.364906365618613e-05,
"loss": 0.5515697002410889,
"step": 12720
},
{
"epoch": 1.4009244483574534,
"grad_norm": 1.29691481590271,
"learning_rate": 4.350192721289526e-05,
"loss": 0.48247671127319336,
"step": 12730
},
{
"epoch": 1.4020249821163264,
"grad_norm": 1.5985174179077148,
"learning_rate": 4.335497021287675e-05,
"loss": 0.5108057022094726,
"step": 12740
},
{
"epoch": 1.4031255158751994,
"grad_norm": 1.1953842639923096,
"learning_rate": 4.320819312288006e-05,
"loss": 0.5506106376647949,
"step": 12750
},
{
"epoch": 1.4042260496340726,
"grad_norm": 1.3660629987716675,
"learning_rate": 4.306159640908329e-05,
"loss": 0.4917247772216797,
"step": 12760
},
{
"epoch": 1.4053265833929456,
"grad_norm": 1.4527275562286377,
"learning_rate": 4.291518053709156e-05,
"loss": 0.5028563499450683,
"step": 12770
},
{
"epoch": 1.4064271171518186,
"grad_norm": 1.5173895359039307,
"learning_rate": 4.276894597193567e-05,
"loss": 0.531541109085083,
"step": 12780
},
{
"epoch": 1.4075276509106918,
"grad_norm": 1.388485312461853,
"learning_rate": 4.2622893178070546e-05,
"loss": 0.5469501972198486,
"step": 12790
},
{
"epoch": 1.4086281846695647,
"grad_norm": 1.2715303897857666,
"learning_rate": 4.2477022619373795e-05,
"loss": 0.5065861225128174,
"step": 12800
},
{
"epoch": 1.4097287184284377,
"grad_norm": 1.375125527381897,
"learning_rate": 4.2331334759144225e-05,
"loss": 0.5102115631103515,
"step": 12810
},
{
"epoch": 1.410829252187311,
"grad_norm": 1.3314223289489746,
"learning_rate": 4.218583006010044e-05,
"loss": 0.5135067462921142,
"step": 12820
},
{
"epoch": 1.411929785946184,
"grad_norm": 1.2753770351409912,
"learning_rate": 4.204050898437921e-05,
"loss": 0.530963659286499,
"step": 12830
},
{
"epoch": 1.4130303197050569,
"grad_norm": 1.2953945398330688,
"learning_rate": 4.189537199353417e-05,
"loss": 0.5231512546539306,
"step": 12840
},
{
"epoch": 1.41413085346393,
"grad_norm": 1.478853464126587,
"learning_rate": 4.175041954853421e-05,
"loss": 0.5153040885925293,
"step": 12850
},
{
"epoch": 1.415231387222803,
"grad_norm": 1.7187341451644897,
"learning_rate": 4.1605652109762225e-05,
"loss": 0.5362359046936035,
"step": 12860
},
{
"epoch": 1.416331920981676,
"grad_norm": 1.1309502124786377,
"learning_rate": 4.1461070137013305e-05,
"loss": 0.4846354007720947,
"step": 12870
},
{
"epoch": 1.4174324547405492,
"grad_norm": 1.5288585424423218,
"learning_rate": 4.131667408949368e-05,
"loss": 0.536449670791626,
"step": 12880
},
{
"epoch": 1.4185329884994222,
"grad_norm": 1.4492231607437134,
"learning_rate": 4.117246442581896e-05,
"loss": 0.5303133487701416,
"step": 12890
},
{
"epoch": 1.4196335222582952,
"grad_norm": 1.4299237728118896,
"learning_rate": 4.102844160401279e-05,
"loss": 0.49590587615966797,
"step": 12900
},
{
"epoch": 1.4207340560171684,
"grad_norm": 1.2255241870880127,
"learning_rate": 4.0884606081505374e-05,
"loss": 0.4480147838592529,
"step": 12910
},
{
"epoch": 1.4218345897760414,
"grad_norm": 1.3076447248458862,
"learning_rate": 4.074095831513216e-05,
"loss": 0.5100639820098877,
"step": 12920
},
{
"epoch": 1.4229351235349144,
"grad_norm": 1.34635329246521,
"learning_rate": 4.059749876113202e-05,
"loss": 0.5147515773773194,
"step": 12930
},
{
"epoch": 1.4240356572937876,
"grad_norm": 1.398501992225647,
"learning_rate": 4.0454227875146334e-05,
"loss": 0.5074705123901367,
"step": 12940
},
{
"epoch": 1.4251361910526605,
"grad_norm": 1.5088456869125366,
"learning_rate": 4.031114611221703e-05,
"loss": 0.5495419979095459,
"step": 12950
},
{
"epoch": 1.4262367248115335,
"grad_norm": 1.4350841045379639,
"learning_rate": 4.016825392678548e-05,
"loss": 0.5102008819580078,
"step": 12960
},
{
"epoch": 1.4273372585704067,
"grad_norm": 1.5860239267349243,
"learning_rate": 4.002555177269085e-05,
"loss": 0.4671715259552002,
"step": 12970
},
{
"epoch": 1.4284377923292797,
"grad_norm": 1.2882176637649536,
"learning_rate": 3.988304010316888e-05,
"loss": 0.4910801887512207,
"step": 12980
},
{
"epoch": 1.4295383260881527,
"grad_norm": 1.353554368019104,
"learning_rate": 3.97407193708502e-05,
"loss": 0.4905055522918701,
"step": 12990
},
{
"epoch": 1.4306388598470259,
"grad_norm": 1.5040994882583618,
"learning_rate": 3.959859002775904e-05,
"loss": 0.5559825897216797,
"step": 13000
},
{
"epoch": 1.4306388598470259,
"eval_loss": 0.6006145477294922,
"eval_runtime": 933.1966,
"eval_samples_per_second": 9.737,
"eval_steps_per_second": 2.435,
"step": 13000
},
{
"epoch": 1.4317393936058989,
"grad_norm": 1.5252652168273926,
"learning_rate": 3.9456652525311775e-05,
"loss": 0.5047395706176758,
"step": 13010
},
{
"epoch": 1.4328399273647718,
"grad_norm": 1.5694782733917236,
"learning_rate": 3.931490731431544e-05,
"loss": 0.46917476654052737,
"step": 13020
},
{
"epoch": 1.433940461123645,
"grad_norm": 1.298323631286621,
"learning_rate": 3.917335484496634e-05,
"loss": 0.5607198715209961,
"step": 13030
},
{
"epoch": 1.435040994882518,
"grad_norm": 1.151871681213379,
"learning_rate": 3.9031995566848687e-05,
"loss": 0.5415894031524658,
"step": 13040
},
{
"epoch": 1.436141528641391,
"grad_norm": 1.271160364151001,
"learning_rate": 3.889082992893301e-05,
"loss": 0.5198471069335937,
"step": 13050
},
{
"epoch": 1.4372420624002642,
"grad_norm": 1.6260325908660889,
"learning_rate": 3.8749858379574856e-05,
"loss": 0.4984140872955322,
"step": 13060
},
{
"epoch": 1.4383425961591372,
"grad_norm": 1.2122149467468262,
"learning_rate": 3.8609081366513275e-05,
"loss": 0.5378758430480957,
"step": 13070
},
{
"epoch": 1.4394431299180102,
"grad_norm": 1.4511668682098389,
"learning_rate": 3.846849933686962e-05,
"loss": 0.49872121810913084,
"step": 13080
},
{
"epoch": 1.4405436636768834,
"grad_norm": 1.3906524181365967,
"learning_rate": 3.832811273714569e-05,
"loss": 0.509521770477295,
"step": 13090
},
{
"epoch": 1.4416441974357563,
"grad_norm": 1.5202287435531616,
"learning_rate": 3.818792201322283e-05,
"loss": 0.49728941917419434,
"step": 13100
},
{
"epoch": 1.4427447311946293,
"grad_norm": 1.234118938446045,
"learning_rate": 3.804792761036014e-05,
"loss": 0.5287348747253418,
"step": 13110
},
{
"epoch": 1.4438452649535025,
"grad_norm": 1.542027235031128,
"learning_rate": 3.7908129973193175e-05,
"loss": 0.4547781467437744,
"step": 13120
},
{
"epoch": 1.4449457987123755,
"grad_norm": 1.4923428297042847,
"learning_rate": 3.776852954573257e-05,
"loss": 0.4881281852722168,
"step": 13130
},
{
"epoch": 1.4460463324712485,
"grad_norm": 1.5383400917053223,
"learning_rate": 3.762912677136271e-05,
"loss": 0.5386209487915039,
"step": 13140
},
{
"epoch": 1.4471468662301217,
"grad_norm": 1.6984336376190186,
"learning_rate": 3.7489922092839956e-05,
"loss": 0.49674625396728517,
"step": 13150
},
{
"epoch": 1.4482473999889947,
"grad_norm": 1.4773831367492676,
"learning_rate": 3.7350915952291776e-05,
"loss": 0.49255056381225587,
"step": 13160
},
{
"epoch": 1.4493479337478676,
"grad_norm": 1.767876148223877,
"learning_rate": 3.72121087912149e-05,
"loss": 0.4835840702056885,
"step": 13170
},
{
"epoch": 1.4504484675067408,
"grad_norm": 1.4098162651062012,
"learning_rate": 3.707350105047414e-05,
"loss": 0.5085628509521485,
"step": 13180
},
{
"epoch": 1.4515490012656138,
"grad_norm": 1.7641174793243408,
"learning_rate": 3.693509317030084e-05,
"loss": 0.4194155693054199,
"step": 13190
},
{
"epoch": 1.4526495350244868,
"grad_norm": 1.540986180305481,
"learning_rate": 3.6796885590291744e-05,
"loss": 0.5055553913116455,
"step": 13200
},
{
"epoch": 1.45375006878336,
"grad_norm": 1.4886335134506226,
"learning_rate": 3.6658878749407266e-05,
"loss": 0.47327437400817873,
"step": 13210
},
{
"epoch": 1.454850602542233,
"grad_norm": 1.1624953746795654,
"learning_rate": 3.652107308597031e-05,
"loss": 0.5468912601470948,
"step": 13220
},
{
"epoch": 1.4559511363011062,
"grad_norm": 1.251796007156372,
"learning_rate": 3.638346903766479e-05,
"loss": 0.5090361595153808,
"step": 13230
},
{
"epoch": 1.4570516700599792,
"grad_norm": 1.456272006034851,
"learning_rate": 3.624606704153439e-05,
"loss": 0.5223624229431152,
"step": 13240
},
{
"epoch": 1.4581522038188521,
"grad_norm": 1.7384787797927856,
"learning_rate": 3.610886753398084e-05,
"loss": 0.515346908569336,
"step": 13250
},
{
"epoch": 1.4592527375777253,
"grad_norm": 1.4537709951400757,
"learning_rate": 3.597187095076298e-05,
"loss": 0.5127240180969238,
"step": 13260
},
{
"epoch": 1.4603532713365983,
"grad_norm": 1.4933159351348877,
"learning_rate": 3.5835077726994984e-05,
"loss": 0.5056961059570313,
"step": 13270
},
{
"epoch": 1.4614538050954713,
"grad_norm": 1.3322826623916626,
"learning_rate": 3.569848829714519e-05,
"loss": 0.5281732559204102,
"step": 13280
},
{
"epoch": 1.4625543388543445,
"grad_norm": 1.5161052942276,
"learning_rate": 3.556210309503465e-05,
"loss": 0.5495526790618896,
"step": 13290
},
{
"epoch": 1.4636548726132175,
"grad_norm": 1.23734712600708,
"learning_rate": 3.542592255383586e-05,
"loss": 0.5442331790924072,
"step": 13300
},
{
"epoch": 1.4647554063720905,
"grad_norm": 1.366429328918457,
"learning_rate": 3.528994710607112e-05,
"loss": 0.4855631351470947,
"step": 13310
},
{
"epoch": 1.4658559401309637,
"grad_norm": 1.7758201360702515,
"learning_rate": 3.51541771836115e-05,
"loss": 0.5233217239379883,
"step": 13320
},
{
"epoch": 1.4669564738898366,
"grad_norm": 1.7179821729660034,
"learning_rate": 3.501861321767521e-05,
"loss": 0.5118228912353515,
"step": 13330
},
{
"epoch": 1.4680570076487096,
"grad_norm": 1.486463189125061,
"learning_rate": 3.488325563882636e-05,
"loss": 0.5506513118743896,
"step": 13340
},
{
"epoch": 1.4691575414075828,
"grad_norm": 1.2534334659576416,
"learning_rate": 3.47481048769735e-05,
"loss": 0.5199797630310059,
"step": 13350
},
{
"epoch": 1.4702580751664558,
"grad_norm": 1.1043325662612915,
"learning_rate": 3.461316136136843e-05,
"loss": 0.5226203441619873,
"step": 13360
},
{
"epoch": 1.4713586089253288,
"grad_norm": 1.258324146270752,
"learning_rate": 3.447842552060454e-05,
"loss": 0.47593889236450193,
"step": 13370
},
{
"epoch": 1.472459142684202,
"grad_norm": 1.465816617012024,
"learning_rate": 3.434389778261579e-05,
"loss": 0.5070627689361572,
"step": 13380
},
{
"epoch": 1.473559676443075,
"grad_norm": 1.3153942823410034,
"learning_rate": 3.4209578574675105e-05,
"loss": 0.497767972946167,
"step": 13390
},
{
"epoch": 1.474660210201948,
"grad_norm": 1.4301342964172363,
"learning_rate": 3.40754683233931e-05,
"loss": 0.5043089389801025,
"step": 13400
},
{
"epoch": 1.4757607439608211,
"grad_norm": 1.4582939147949219,
"learning_rate": 3.394156745471672e-05,
"loss": 0.537001657485962,
"step": 13410
},
{
"epoch": 1.476861277719694,
"grad_norm": 1.4918025732040405,
"learning_rate": 3.380787639392794e-05,
"loss": 0.47727375030517577,
"step": 13420
},
{
"epoch": 1.477961811478567,
"grad_norm": 1.9263042211532593,
"learning_rate": 3.3674395565642324e-05,
"loss": 0.5241379261016845,
"step": 13430
},
{
"epoch": 1.4790623452374403,
"grad_norm": 1.3534560203552246,
"learning_rate": 3.354112539380771e-05,
"loss": 0.49828281402587893,
"step": 13440
},
{
"epoch": 1.4801628789963133,
"grad_norm": 1.9766839742660522,
"learning_rate": 3.340806630170288e-05,
"loss": 0.5248537063598633,
"step": 13450
},
{
"epoch": 1.4812634127551862,
"grad_norm": 1.2477192878723145,
"learning_rate": 3.327521871193627e-05,
"loss": 0.5167280673980713,
"step": 13460
},
{
"epoch": 1.4823639465140594,
"grad_norm": 1.16605544090271,
"learning_rate": 3.31425830464444e-05,
"loss": 0.5039694786071778,
"step": 13470
},
{
"epoch": 1.4834644802729324,
"grad_norm": 1.327203392982483,
"learning_rate": 3.3010159726490895e-05,
"loss": 0.47118306159973145,
"step": 13480
},
{
"epoch": 1.4845650140318054,
"grad_norm": 1.6757255792617798,
"learning_rate": 3.2877949172664834e-05,
"loss": 0.5024468898773193,
"step": 13490
},
{
"epoch": 1.4856655477906786,
"grad_norm": 1.440145492553711,
"learning_rate": 3.274595180487956e-05,
"loss": 0.5378376483917237,
"step": 13500
},
{
"epoch": 1.4867660815495516,
"grad_norm": 1.4280515909194946,
"learning_rate": 3.261416804237126e-05,
"loss": 0.5332531929016113,
"step": 13510
},
{
"epoch": 1.4878666153084246,
"grad_norm": 1.2752246856689453,
"learning_rate": 3.248259830369788e-05,
"loss": 0.5394261837005615,
"step": 13520
},
{
"epoch": 1.4889671490672978,
"grad_norm": 1.1912692785263062,
"learning_rate": 3.235124300673729e-05,
"loss": 0.5306824684143067,
"step": 13530
},
{
"epoch": 1.4900676828261707,
"grad_norm": 1.5071934461593628,
"learning_rate": 3.222010256868658e-05,
"loss": 0.524613904953003,
"step": 13540
},
{
"epoch": 1.4911682165850437,
"grad_norm": 1.2503234148025513,
"learning_rate": 3.2089177406060264e-05,
"loss": 0.5718852996826171,
"step": 13550
},
{
"epoch": 1.492268750343917,
"grad_norm": 1.454397439956665,
"learning_rate": 3.1958467934689153e-05,
"loss": 0.4814920425415039,
"step": 13560
},
{
"epoch": 1.49336928410279,
"grad_norm": 3.508129119873047,
"learning_rate": 3.182797456971898e-05,
"loss": 0.4959763526916504,
"step": 13570
},
{
"epoch": 1.4944698178616629,
"grad_norm": 1.4555495977401733,
"learning_rate": 3.169769772560918e-05,
"loss": 0.49576363563537595,
"step": 13580
},
{
"epoch": 1.495570351620536,
"grad_norm": 1.3573147058486938,
"learning_rate": 3.156763781613141e-05,
"loss": 0.49452862739562986,
"step": 13590
},
{
"epoch": 1.496670885379409,
"grad_norm": 1.4841245412826538,
"learning_rate": 3.143779525436835e-05,
"loss": 0.5319545269012451,
"step": 13600
},
{
"epoch": 1.497771419138282,
"grad_norm": 1.6145817041397095,
"learning_rate": 3.130817045271245e-05,
"loss": 0.5460486888885498,
"step": 13610
},
{
"epoch": 1.4988719528971552,
"grad_norm": 1.9636765718460083,
"learning_rate": 3.117876382286433e-05,
"loss": 0.5048194408416748,
"step": 13620
},
{
"epoch": 1.4999724866560282,
"grad_norm": 1.4671472311019897,
"learning_rate": 3.104957577583189e-05,
"loss": 0.5170011520385742,
"step": 13630
},
{
"epoch": 1.5010730204149012,
"grad_norm": 1.4642596244812012,
"learning_rate": 3.092060672192868e-05,
"loss": 0.5584310531616211,
"step": 13640
},
{
"epoch": 1.5021735541737744,
"grad_norm": 1.3807435035705566,
"learning_rate": 3.079185707077272e-05,
"loss": 0.45142621994018556,
"step": 13650
},
{
"epoch": 1.5032740879326474,
"grad_norm": 1.5718172788619995,
"learning_rate": 3.0663327231285154e-05,
"loss": 0.5343811988830567,
"step": 13660
},
{
"epoch": 1.5043746216915204,
"grad_norm": 1.4733718633651733,
"learning_rate": 3.053501761168909e-05,
"loss": 0.49410390853881836,
"step": 13670
},
{
"epoch": 1.5054751554503936,
"grad_norm": 1.4786248207092285,
"learning_rate": 3.0406928619508092e-05,
"loss": 0.47629489898681643,
"step": 13680
},
{
"epoch": 1.5065756892092665,
"grad_norm": 1.437113642692566,
"learning_rate": 3.0279060661565028e-05,
"loss": 0.48892903327941895,
"step": 13690
},
{
"epoch": 1.5076762229681395,
"grad_norm": 1.2976839542388916,
"learning_rate": 3.015141414398075e-05,
"loss": 0.5163634777069092,
"step": 13700
},
{
"epoch": 1.5087767567270127,
"grad_norm": 1.6507548093795776,
"learning_rate": 3.0023989472172766e-05,
"loss": 0.5434659957885742,
"step": 13710
},
{
"epoch": 1.5098772904858857,
"grad_norm": 1.31253182888031,
"learning_rate": 2.989678705085398e-05,
"loss": 0.5194432735443115,
"step": 13720
},
{
"epoch": 1.5109778242447587,
"grad_norm": 1.432991862297058,
"learning_rate": 2.976980728403147e-05,
"loss": 0.5175258159637451,
"step": 13730
},
{
"epoch": 1.5120783580036319,
"grad_norm": 2.1796889305114746,
"learning_rate": 2.964305057500508e-05,
"loss": 0.5054359912872315,
"step": 13740
},
{
"epoch": 1.5131788917625049,
"grad_norm": 1.4726945161819458,
"learning_rate": 2.951651732636622e-05,
"loss": 0.4896527290344238,
"step": 13750
},
{
"epoch": 1.5142794255213778,
"grad_norm": 1.432494044303894,
"learning_rate": 2.939020793999653e-05,
"loss": 0.46663222312927244,
"step": 13760
},
{
"epoch": 1.515379959280251,
"grad_norm": 1.4755899906158447,
"learning_rate": 2.9264122817066765e-05,
"loss": 0.47660222053527834,
"step": 13770
},
{
"epoch": 1.516480493039124,
"grad_norm": 1.4614745378494263,
"learning_rate": 2.9138262358035197e-05,
"loss": 0.5349469184875488,
"step": 13780
},
{
"epoch": 1.517581026797997,
"grad_norm": 1.3046956062316895,
"learning_rate": 2.901262696264675e-05,
"loss": 0.4655785083770752,
"step": 13790
},
{
"epoch": 1.5186815605568702,
"grad_norm": 1.69575035572052,
"learning_rate": 2.888721702993139e-05,
"loss": 0.569233751296997,
"step": 13800
},
{
"epoch": 1.5197820943157432,
"grad_norm": 1.6944596767425537,
"learning_rate": 2.8762032958203055e-05,
"loss": 0.5464329242706298,
"step": 13810
},
{
"epoch": 1.5208826280746162,
"grad_norm": 1.676538109779358,
"learning_rate": 2.8637075145058257e-05,
"loss": 0.5451251983642578,
"step": 13820
},
{
"epoch": 1.5219831618334894,
"grad_norm": 1.5484033823013306,
"learning_rate": 2.8512343987375033e-05,
"loss": 0.47975883483886717,
"step": 13830
},
{
"epoch": 1.5230836955923623,
"grad_norm": 1.3609403371810913,
"learning_rate": 2.838783988131134e-05,
"loss": 0.47988286018371584,
"step": 13840
},
{
"epoch": 1.5241842293512353,
"grad_norm": 2.036940574645996,
"learning_rate": 2.826356322230418e-05,
"loss": 0.5064961910247803,
"step": 13850
},
{
"epoch": 1.5252847631101085,
"grad_norm": 1.508659839630127,
"learning_rate": 2.8139514405068058e-05,
"loss": 0.5125546455383301,
"step": 13860
},
{
"epoch": 1.5263852968689815,
"grad_norm": 1.718461036682129,
"learning_rate": 2.801569382359387e-05,
"loss": 0.4710413932800293,
"step": 13870
},
{
"epoch": 1.5274858306278545,
"grad_norm": 1.8719013929367065,
"learning_rate": 2.7892101871147548e-05,
"loss": 0.5405392169952392,
"step": 13880
},
{
"epoch": 1.5285863643867277,
"grad_norm": 1.4192867279052734,
"learning_rate": 2.7768738940269023e-05,
"loss": 0.5199221134185791,
"step": 13890
},
{
"epoch": 1.5296868981456007,
"grad_norm": 1.271347999572754,
"learning_rate": 2.764560542277068e-05,
"loss": 0.5048525333404541,
"step": 13900
},
{
"epoch": 1.5307874319044736,
"grad_norm": 1.4697716236114502,
"learning_rate": 2.7522701709736343e-05,
"loss": 0.47776007652282715,
"step": 13910
},
{
"epoch": 1.5318879656633468,
"grad_norm": 1.1631221771240234,
"learning_rate": 2.740002819151992e-05,
"loss": 0.5136751651763916,
"step": 13920
},
{
"epoch": 1.5329884994222198,
"grad_norm": 1.584194540977478,
"learning_rate": 2.7277585257744242e-05,
"loss": 0.520424747467041,
"step": 13930
},
{
"epoch": 1.5340890331810928,
"grad_norm": 1.674691081047058,
"learning_rate": 2.71553732972997e-05,
"loss": 0.4916074275970459,
"step": 13940
},
{
"epoch": 1.535189566939966,
"grad_norm": 1.3031243085861206,
"learning_rate": 2.7033392698343218e-05,
"loss": 0.561707592010498,
"step": 13950
},
{
"epoch": 1.536290100698839,
"grad_norm": 2.6450769901275635,
"learning_rate": 2.6911643848296787e-05,
"loss": 0.49480366706848145,
"step": 13960
},
{
"epoch": 1.537390634457712,
"grad_norm": 1.9828189611434937,
"learning_rate": 2.6790127133846378e-05,
"loss": 0.5189652442932129,
"step": 13970
},
{
"epoch": 1.5384911682165852,
"grad_norm": 1.3217980861663818,
"learning_rate": 2.6668842940940654e-05,
"loss": 0.5654374122619629,
"step": 13980
},
{
"epoch": 1.5395917019754581,
"grad_norm": 1.5207453966140747,
"learning_rate": 2.6547791654789867e-05,
"loss": 0.49074726104736327,
"step": 13990
},
{
"epoch": 1.5406922357343311,
"grad_norm": 1.3792606592178345,
"learning_rate": 2.642697365986434e-05,
"loss": 0.49360318183898927,
"step": 14000
},
{
"epoch": 1.5406922357343311,
"eval_loss": 0.586557924747467,
"eval_runtime": 931.9289,
"eval_samples_per_second": 9.751,
"eval_steps_per_second": 2.438,
"step": 14000
},
{
"epoch": 1.5417927694932043,
"grad_norm": 1.5167111158370972,
"learning_rate": 2.6306389339893657e-05,
"loss": 0.45190792083740233,
"step": 14010
},
{
"epoch": 1.5428933032520773,
"grad_norm": 1.3391878604888916,
"learning_rate": 2.618603907786509e-05,
"loss": 0.4652193546295166,
"step": 14020
},
{
"epoch": 1.5439938370109503,
"grad_norm": 1.2597346305847168,
"learning_rate": 2.6065923256022563e-05,
"loss": 0.5516125202178955,
"step": 14030
},
{
"epoch": 1.5450943707698235,
"grad_norm": 1.2354804277420044,
"learning_rate": 2.5946042255865367e-05,
"loss": 0.5130207538604736,
"step": 14040
},
{
"epoch": 1.5461949045286965,
"grad_norm": 1.5597954988479614,
"learning_rate": 2.5826396458147073e-05,
"loss": 0.5015468597412109,
"step": 14050
},
{
"epoch": 1.5472954382875694,
"grad_norm": 1.4555859565734863,
"learning_rate": 2.5706986242874055e-05,
"loss": 0.5252137660980225,
"step": 14060
},
{
"epoch": 1.5483959720464426,
"grad_norm": 1.9595062732696533,
"learning_rate": 2.5587811989304646e-05,
"loss": 0.5172215938568115,
"step": 14070
},
{
"epoch": 1.5494965058053156,
"grad_norm": 1.2958043813705444,
"learning_rate": 2.54688740759476e-05,
"loss": 0.5510001659393311,
"step": 14080
},
{
"epoch": 1.5505970395641886,
"grad_norm": 1.2450227737426758,
"learning_rate": 2.5350172880561117e-05,
"loss": 0.4833174705505371,
"step": 14090
},
{
"epoch": 1.5516975733230618,
"grad_norm": 1.5833539962768555,
"learning_rate": 2.5231708780151462e-05,
"loss": 0.5583213329315185,
"step": 14100
},
{
"epoch": 1.5527981070819348,
"grad_norm": 1.1792974472045898,
"learning_rate": 2.5113482150972012e-05,
"loss": 0.47814168930053713,
"step": 14110
},
{
"epoch": 1.5538986408408078,
"grad_norm": 1.307870864868164,
"learning_rate": 2.4995493368521784e-05,
"loss": 0.4371782302856445,
"step": 14120
},
{
"epoch": 1.554999174599681,
"grad_norm": 1.296129822731018,
"learning_rate": 2.4877742807544402e-05,
"loss": 0.5552921772003174,
"step": 14130
},
{
"epoch": 1.556099708358554,
"grad_norm": 1.2839207649230957,
"learning_rate": 2.4760230842026887e-05,
"loss": 0.45152988433837893,
"step": 14140
},
{
"epoch": 1.557200242117427,
"grad_norm": 1.4040298461914062,
"learning_rate": 2.464295784519852e-05,
"loss": 0.44363880157470703,
"step": 14150
},
{
"epoch": 1.5583007758763001,
"grad_norm": 1.6277488470077515,
"learning_rate": 2.4525924189529437e-05,
"loss": 0.5193778514862061,
"step": 14160
},
{
"epoch": 1.559401309635173,
"grad_norm": 1.5271227359771729,
"learning_rate": 2.4409130246729773e-05,
"loss": 0.5011728286743165,
"step": 14170
},
{
"epoch": 1.560501843394046,
"grad_norm": 1.5227077007293701,
"learning_rate": 2.4292576387748223e-05,
"loss": 0.5214500427246094,
"step": 14180
},
{
"epoch": 1.5616023771529193,
"grad_norm": 1.171847939491272,
"learning_rate": 2.417626298277096e-05,
"loss": 0.5235694408416748,
"step": 14190
},
{
"epoch": 1.5627029109117923,
"grad_norm": 1.4584394693374634,
"learning_rate": 2.406019040122044e-05,
"loss": 0.553814697265625,
"step": 14200
},
{
"epoch": 1.5638034446706652,
"grad_norm": 1.4516977071762085,
"learning_rate": 2.3944359011754336e-05,
"loss": 0.4300075054168701,
"step": 14210
},
{
"epoch": 1.5649039784295384,
"grad_norm": 1.4983289241790771,
"learning_rate": 2.382876918226409e-05,
"loss": 0.5188943862915039,
"step": 14220
},
{
"epoch": 1.5660045121884114,
"grad_norm": 1.672825574874878,
"learning_rate": 2.3713421279874126e-05,
"loss": 0.5167557239532471,
"step": 14230
},
{
"epoch": 1.5671050459472844,
"grad_norm": 1.6849709749221802,
"learning_rate": 2.3598315670940352e-05,
"loss": 0.4564533233642578,
"step": 14240
},
{
"epoch": 1.5682055797061576,
"grad_norm": 1.3236452341079712,
"learning_rate": 2.3483452721049182e-05,
"loss": 0.5154578208923339,
"step": 14250
},
{
"epoch": 1.5693061134650306,
"grad_norm": 1.1491893529891968,
"learning_rate": 2.336883279501628e-05,
"loss": 0.5059072971343994,
"step": 14260
},
{
"epoch": 1.5704066472239036,
"grad_norm": 1.3376238346099854,
"learning_rate": 2.325445625688555e-05,
"loss": 0.5027592182159424,
"step": 14270
},
{
"epoch": 1.5715071809827768,
"grad_norm": 1.5275547504425049,
"learning_rate": 2.314032346992768e-05,
"loss": 0.5160568237304688,
"step": 14280
},
{
"epoch": 1.5726077147416497,
"grad_norm": 1.4245470762252808,
"learning_rate": 2.3026434796639396e-05,
"loss": 0.535769271850586,
"step": 14290
},
{
"epoch": 1.5737082485005227,
"grad_norm": 1.4865559339523315,
"learning_rate": 2.291279059874195e-05,
"loss": 0.5234790802001953,
"step": 14300
},
{
"epoch": 1.574808782259396,
"grad_norm": 1.3173142671585083,
"learning_rate": 2.279939123718018e-05,
"loss": 0.5088066101074219,
"step": 14310
},
{
"epoch": 1.575909316018269,
"grad_norm": 1.3520629405975342,
"learning_rate": 2.268623707212124e-05,
"loss": 0.49616203308105467,
"step": 14320
},
{
"epoch": 1.5770098497771419,
"grad_norm": 1.3545994758605957,
"learning_rate": 2.2573328462953636e-05,
"loss": 0.49118871688842775,
"step": 14330
},
{
"epoch": 1.578110383536015,
"grad_norm": 1.534203290939331,
"learning_rate": 2.2460665768285826e-05,
"loss": 0.49422922134399416,
"step": 14340
},
{
"epoch": 1.579210917294888,
"grad_norm": 1.398881196975708,
"learning_rate": 2.2348249345945316e-05,
"loss": 0.507296371459961,
"step": 14350
},
{
"epoch": 1.580311451053761,
"grad_norm": 1.3228986263275146,
"learning_rate": 2.223607955297735e-05,
"loss": 0.5225358009338379,
"step": 14360
},
{
"epoch": 1.5814119848126342,
"grad_norm": 1.4749466180801392,
"learning_rate": 2.2124156745643998e-05,
"loss": 0.5400196552276612,
"step": 14370
},
{
"epoch": 1.5825125185715072,
"grad_norm": 1.4052789211273193,
"learning_rate": 2.201248127942265e-05,
"loss": 0.5146516323089599,
"step": 14380
},
{
"epoch": 1.5836130523303802,
"grad_norm": 1.4668323993682861,
"learning_rate": 2.190105350900533e-05,
"loss": 0.478867769241333,
"step": 14390
},
{
"epoch": 1.5847135860892534,
"grad_norm": 1.3071681261062622,
"learning_rate": 2.1789873788297256e-05,
"loss": 0.5231433391571045,
"step": 14400
},
{
"epoch": 1.5858141198481264,
"grad_norm": 1.437474012374878,
"learning_rate": 2.167894247041583e-05,
"loss": 0.4709481716156006,
"step": 14410
},
{
"epoch": 1.5869146536069993,
"grad_norm": 1.2293906211853027,
"learning_rate": 2.156825990768949e-05,
"loss": 0.45884432792663576,
"step": 14420
},
{
"epoch": 1.5880151873658725,
"grad_norm": 1.4255151748657227,
"learning_rate": 2.145782645165668e-05,
"loss": 0.47333617210388185,
"step": 14430
},
{
"epoch": 1.5891157211247455,
"grad_norm": 1.4081617593765259,
"learning_rate": 2.134764245306452e-05,
"loss": 0.5467502117156983,
"step": 14440
},
{
"epoch": 1.5902162548836185,
"grad_norm": 1.1437593698501587,
"learning_rate": 2.123770826186796e-05,
"loss": 0.5400538444519043,
"step": 14450
},
{
"epoch": 1.5913167886424917,
"grad_norm": 1.2119172811508179,
"learning_rate": 2.112802422722847e-05,
"loss": 0.4829564094543457,
"step": 14460
},
{
"epoch": 1.5924173224013647,
"grad_norm": 1.4367520809173584,
"learning_rate": 2.101859069751301e-05,
"loss": 0.48166666030883787,
"step": 14470
},
{
"epoch": 1.5935178561602377,
"grad_norm": 1.367094874382019,
"learning_rate": 2.09094080202929e-05,
"loss": 0.4969982147216797,
"step": 14480
},
{
"epoch": 1.5946183899191109,
"grad_norm": 1.5659687519073486,
"learning_rate": 2.080047654234282e-05,
"loss": 0.47341599464416506,
"step": 14490
},
{
"epoch": 1.5957189236779838,
"grad_norm": 1.3533883094787598,
"learning_rate": 2.0691796609639424e-05,
"loss": 0.4816636085510254,
"step": 14500
},
{
"epoch": 1.5968194574368568,
"grad_norm": 1.7425504922866821,
"learning_rate": 2.0583368567360662e-05,
"loss": 0.48581724166870116,
"step": 14510
},
{
"epoch": 1.59791999119573,
"grad_norm": 1.588092565536499,
"learning_rate": 2.0475192759884287e-05,
"loss": 0.5044478893280029,
"step": 14520
},
{
"epoch": 1.599020524954603,
"grad_norm": 1.1368178129196167,
"learning_rate": 2.0367269530787016e-05,
"loss": 0.4993897438049316,
"step": 14530
},
{
"epoch": 1.600121058713476,
"grad_norm": 1.3419239521026611,
"learning_rate": 2.0259599222843275e-05,
"loss": 0.4705319881439209,
"step": 14540
},
{
"epoch": 1.6012215924723492,
"grad_norm": 1.4129960536956787,
"learning_rate": 2.0152182178024314e-05,
"loss": 0.5142210483551025,
"step": 14550
},
{
"epoch": 1.6023221262312222,
"grad_norm": 1.6611522436141968,
"learning_rate": 2.004501873749689e-05,
"loss": 0.492765474319458,
"step": 14560
},
{
"epoch": 1.6034226599900951,
"grad_norm": 1.702540397644043,
"learning_rate": 1.9938109241622317e-05,
"loss": 0.4946121692657471,
"step": 14570
},
{
"epoch": 1.6045231937489683,
"grad_norm": 1.3767914772033691,
"learning_rate": 1.9831454029955322e-05,
"loss": 0.5122776508331299,
"step": 14580
},
{
"epoch": 1.6056237275078413,
"grad_norm": 1.5030194520950317,
"learning_rate": 1.9725053441243115e-05,
"loss": 0.4482386589050293,
"step": 14590
},
{
"epoch": 1.6067242612667143,
"grad_norm": 1.1301559209823608,
"learning_rate": 1.961890781342408e-05,
"loss": 0.4801701545715332,
"step": 14600
},
{
"epoch": 1.6078247950255875,
"grad_norm": 1.5897738933563232,
"learning_rate": 1.9513017483626862e-05,
"loss": 0.4930363655090332,
"step": 14610
},
{
"epoch": 1.6089253287844605,
"grad_norm": 1.474489688873291,
"learning_rate": 1.940738278816926e-05,
"loss": 0.4937438011169434,
"step": 14620
},
{
"epoch": 1.6100258625433335,
"grad_norm": 1.2943518161773682,
"learning_rate": 1.9302004062557134e-05,
"loss": 0.49902844429016113,
"step": 14630
},
{
"epoch": 1.6111263963022067,
"grad_norm": 1.439143419265747,
"learning_rate": 1.9196881641483422e-05,
"loss": 0.493579626083374,
"step": 14640
},
{
"epoch": 1.6122269300610796,
"grad_norm": 1.1729177236557007,
"learning_rate": 1.909201585882693e-05,
"loss": 0.4507144451141357,
"step": 14650
},
{
"epoch": 1.6133274638199526,
"grad_norm": 1.2200846672058105,
"learning_rate": 1.8987407047651407e-05,
"loss": 0.49028811454772947,
"step": 14660
},
{
"epoch": 1.6144279975788258,
"grad_norm": 1.785130500793457,
"learning_rate": 1.88830555402044e-05,
"loss": 0.46147780418395995,
"step": 14670
},
{
"epoch": 1.6155285313376988,
"grad_norm": 1.1389403343200684,
"learning_rate": 1.877896166791632e-05,
"loss": 0.4744100570678711,
"step": 14680
},
{
"epoch": 1.6166290650965718,
"grad_norm": 1.4580739736557007,
"learning_rate": 1.8675125761399148e-05,
"loss": 0.4804403781890869,
"step": 14690
},
{
"epoch": 1.617729598855445,
"grad_norm": 1.6603548526763916,
"learning_rate": 1.8571548150445718e-05,
"loss": 0.4724745273590088,
"step": 14700
},
{
"epoch": 1.618830132614318,
"grad_norm": 1.3855637311935425,
"learning_rate": 1.8468229164028374e-05,
"loss": 0.48644042015075684,
"step": 14710
},
{
"epoch": 1.619930666373191,
"grad_norm": 1.2005995512008667,
"learning_rate": 1.836516913029809e-05,
"loss": 0.5345818519592285,
"step": 14720
},
{
"epoch": 1.6210312001320641,
"grad_norm": 1.6608595848083496,
"learning_rate": 1.826236837658334e-05,
"loss": 0.4784832954406738,
"step": 14730
},
{
"epoch": 1.6221317338909371,
"grad_norm": 1.3046231269836426,
"learning_rate": 1.8159827229389203e-05,
"loss": 0.5194854736328125,
"step": 14740
},
{
"epoch": 1.62323226764981,
"grad_norm": 1.331171989440918,
"learning_rate": 1.8057546014396054e-05,
"loss": 0.46275959014892576,
"step": 14750
},
{
"epoch": 1.6243328014086833,
"grad_norm": 1.342647671699524,
"learning_rate": 1.7955525056458865e-05,
"loss": 0.48211326599121096,
"step": 14760
},
{
"epoch": 1.6254333351675563,
"grad_norm": 1.4507157802581787,
"learning_rate": 1.785376467960592e-05,
"loss": 0.5052865028381348,
"step": 14770
},
{
"epoch": 1.6265338689264293,
"grad_norm": 1.2627122402191162,
"learning_rate": 1.77522652070379e-05,
"loss": 0.4653797626495361,
"step": 14780
},
{
"epoch": 1.6276344026853025,
"grad_norm": 1.3553953170776367,
"learning_rate": 1.765102696112677e-05,
"loss": 0.46643242835998533,
"step": 14790
},
{
"epoch": 1.6287349364441754,
"grad_norm": 1.1551592350006104,
"learning_rate": 1.755005026341492e-05,
"loss": 0.45400371551513674,
"step": 14800
},
{
"epoch": 1.6298354702030484,
"grad_norm": 1.27424156665802,
"learning_rate": 1.7449335434613965e-05,
"loss": 0.46638951301574705,
"step": 14810
},
{
"epoch": 1.6309360039619216,
"grad_norm": 1.3628164529800415,
"learning_rate": 1.7348882794603817e-05,
"loss": 0.5398729801177978,
"step": 14820
},
{
"epoch": 1.6320365377207946,
"grad_norm": 1.5087414979934692,
"learning_rate": 1.724869266243163e-05,
"loss": 0.5284961223602295,
"step": 14830
},
{
"epoch": 1.6331370714796676,
"grad_norm": 1.3179941177368164,
"learning_rate": 1.714876535631086e-05,
"loss": 0.5219568729400634,
"step": 14840
},
{
"epoch": 1.6342376052385408,
"grad_norm": 3.281517744064331,
"learning_rate": 1.704910119362011e-05,
"loss": 0.5182487487792968,
"step": 14850
},
{
"epoch": 1.6353381389974138,
"grad_norm": 2.0216126441955566,
"learning_rate": 1.6949700490902344e-05,
"loss": 0.5168362617492676,
"step": 14860
},
{
"epoch": 1.6364386727562867,
"grad_norm": 1.3312880992889404,
"learning_rate": 1.6850563563863653e-05,
"loss": 0.5118043422698975,
"step": 14870
},
{
"epoch": 1.63753920651516,
"grad_norm": 1.6636582612991333,
"learning_rate": 1.6751690727372383e-05,
"loss": 0.4981687545776367,
"step": 14880
},
{
"epoch": 1.638639740274033,
"grad_norm": 1.4290971755981445,
"learning_rate": 1.6653082295458078e-05,
"loss": 0.4633773326873779,
"step": 14890
},
{
"epoch": 1.639740274032906,
"grad_norm": 1.3814940452575684,
"learning_rate": 1.655473858131059e-05,
"loss": 0.5143929958343506,
"step": 14900
},
{
"epoch": 1.640840807791779,
"grad_norm": 2.3319756984710693,
"learning_rate": 1.645665989727887e-05,
"loss": 0.4911513805389404,
"step": 14910
},
{
"epoch": 1.641941341550652,
"grad_norm": 1.4319030046463013,
"learning_rate": 1.6358846554870232e-05,
"loss": 0.49818644523620603,
"step": 14920
},
{
"epoch": 1.643041875309525,
"grad_norm": 1.725895643234253,
"learning_rate": 1.6261298864749174e-05,
"loss": 0.5000430107116699,
"step": 14930
},
{
"epoch": 1.6441424090683983,
"grad_norm": 1.540236473083496,
"learning_rate": 1.6164017136736474e-05,
"loss": 0.5167610168457031,
"step": 14940
},
{
"epoch": 1.6452429428272712,
"grad_norm": 1.1650645732879639,
"learning_rate": 1.606700167980816e-05,
"loss": 0.4852792263031006,
"step": 14950
},
{
"epoch": 1.6463434765861442,
"grad_norm": 1.428930640220642,
"learning_rate": 1.5970252802094655e-05,
"loss": 0.5504137516021729,
"step": 14960
},
{
"epoch": 1.6474440103450174,
"grad_norm": 1.4974743127822876,
"learning_rate": 1.587377081087953e-05,
"loss": 0.4994840145111084,
"step": 14970
},
{
"epoch": 1.6485445441038904,
"grad_norm": 1.3454649448394775,
"learning_rate": 1.5777556012598872e-05,
"loss": 0.5037373542785645,
"step": 14980
},
{
"epoch": 1.6496450778627634,
"grad_norm": 1.2475671768188477,
"learning_rate": 1.5681608712840046e-05,
"loss": 0.4917168617248535,
"step": 14990
},
{
"epoch": 1.6507456116216366,
"grad_norm": 1.809220314025879,
"learning_rate": 1.5585929216340833e-05,
"loss": 0.5278836250305176,
"step": 15000
},
{
"epoch": 1.6507456116216366,
"eval_loss": 0.5768125057220459,
"eval_runtime": 931.6313,
"eval_samples_per_second": 9.754,
"eval_steps_per_second": 2.439,
"step": 15000
},
{
"epoch": 1.6518461453805096,
"grad_norm": 1.5842989683151245,
"learning_rate": 1.5490517826988428e-05,
"loss": 0.5073791980743408,
"step": 15010
},
{
"epoch": 1.6529466791393825,
"grad_norm": 1.6960078477859497,
"learning_rate": 1.5395374847818554e-05,
"loss": 0.5073424339294433,
"step": 15020
},
{
"epoch": 1.6540472128982557,
"grad_norm": 1.3419781923294067,
"learning_rate": 1.5300500581014366e-05,
"loss": 0.4553565502166748,
"step": 15030
},
{
"epoch": 1.6551477466571287,
"grad_norm": 1.3546874523162842,
"learning_rate": 1.5205895327905594e-05,
"loss": 0.5026891708374024,
"step": 15040
},
{
"epoch": 1.6562482804160017,
"grad_norm": 1.3619909286499023,
"learning_rate": 1.5111559388967567e-05,
"loss": 0.4951028347015381,
"step": 15050
},
{
"epoch": 1.657348814174875,
"grad_norm": 1.388611912727356,
"learning_rate": 1.501749306382022e-05,
"loss": 0.4830893039703369,
"step": 15060
},
{
"epoch": 1.6584493479337479,
"grad_norm": 1.2514212131500244,
"learning_rate": 1.4923696651227148e-05,
"loss": 0.48197135925292967,
"step": 15070
},
{
"epoch": 1.6595498816926209,
"grad_norm": 1.7655376195907593,
"learning_rate": 1.4830170449094782e-05,
"loss": 0.47304229736328124,
"step": 15080
},
{
"epoch": 1.660650415451494,
"grad_norm": 1.4693835973739624,
"learning_rate": 1.473691475447122e-05,
"loss": 0.531934118270874,
"step": 15090
},
{
"epoch": 1.661750949210367,
"grad_norm": 1.4505038261413574,
"learning_rate": 1.464392986354547e-05,
"loss": 0.5015509128570557,
"step": 15100
},
{
"epoch": 1.66285148296924,
"grad_norm": 1.4145722389221191,
"learning_rate": 1.455121607164639e-05,
"loss": 0.5127259254455566,
"step": 15110
},
{
"epoch": 1.6639520167281132,
"grad_norm": 1.1756004095077515,
"learning_rate": 1.4458773673241899e-05,
"loss": 0.4785099983215332,
"step": 15120
},
{
"epoch": 1.6650525504869862,
"grad_norm": 1.9841219186782837,
"learning_rate": 1.4366602961937792e-05,
"loss": 0.48294615745544434,
"step": 15130
},
{
"epoch": 1.6661530842458592,
"grad_norm": 1.2202997207641602,
"learning_rate": 1.427470423047711e-05,
"loss": 0.4258007526397705,
"step": 15140
},
{
"epoch": 1.6672536180047324,
"grad_norm": 1.5636476278305054,
"learning_rate": 1.4183077770738984e-05,
"loss": 0.5582244873046875,
"step": 15150
},
{
"epoch": 1.6683541517636054,
"grad_norm": 1.5996443033218384,
"learning_rate": 1.4091723873737782e-05,
"loss": 0.5360244750976563,
"step": 15160
},
{
"epoch": 1.6694546855224783,
"grad_norm": 1.4036110639572144,
"learning_rate": 1.4000642829622201e-05,
"loss": 0.475919246673584,
"step": 15170
},
{
"epoch": 1.6705552192813515,
"grad_norm": 2.1175453662872314,
"learning_rate": 1.390983492767437e-05,
"loss": 0.4716984272003174,
"step": 15180
},
{
"epoch": 1.6716557530402245,
"grad_norm": 1.5125775337219238,
"learning_rate": 1.3819300456308782e-05,
"loss": 0.5062418937683105,
"step": 15190
},
{
"epoch": 1.6727562867990975,
"grad_norm": 1.3970881700515747,
"learning_rate": 1.3729039703071633e-05,
"loss": 0.4574153900146484,
"step": 15200
},
{
"epoch": 1.6738568205579707,
"grad_norm": 1.2937811613082886,
"learning_rate": 1.3639052954639654e-05,
"loss": 0.5153883934020996,
"step": 15210
},
{
"epoch": 1.6749573543168437,
"grad_norm": 1.1903363466262817,
"learning_rate": 1.3549340496819352e-05,
"loss": 0.5300961971282959,
"step": 15220
},
{
"epoch": 1.6760578880757167,
"grad_norm": 1.2180707454681396,
"learning_rate": 1.3459902614546049e-05,
"loss": 0.4628392219543457,
"step": 15230
},
{
"epoch": 1.6771584218345899,
"grad_norm": 1.2995896339416504,
"learning_rate": 1.3370739591883019e-05,
"loss": 0.5026005744934082,
"step": 15240
},
{
"epoch": 1.6782589555934628,
"grad_norm": 1.6798291206359863,
"learning_rate": 1.328185171202052e-05,
"loss": 0.5069782257080078,
"step": 15250
},
{
"epoch": 1.6793594893523358,
"grad_norm": 1.4230648279190063,
"learning_rate": 1.3193239257274947e-05,
"loss": 0.496774959564209,
"step": 15260
},
{
"epoch": 1.680460023111209,
"grad_norm": 1.2680587768554688,
"learning_rate": 1.3104902509087902e-05,
"loss": 0.4989671230316162,
"step": 15270
},
{
"epoch": 1.681560556870082,
"grad_norm": 1.1969767808914185,
"learning_rate": 1.3016841748025366e-05,
"loss": 0.48966221809387206,
"step": 15280
},
{
"epoch": 1.682661090628955,
"grad_norm": 1.284861445426941,
"learning_rate": 1.2929057253776667e-05,
"loss": 0.45687193870544435,
"step": 15290
},
{
"epoch": 1.6837616243878282,
"grad_norm": 1.0533421039581299,
"learning_rate": 1.2841549305153788e-05,
"loss": 0.46650400161743166,
"step": 15300
},
{
"epoch": 1.6848621581467011,
"grad_norm": 1.4541234970092773,
"learning_rate": 1.2754318180090308e-05,
"loss": 0.46855959892272947,
"step": 15310
},
{
"epoch": 1.6859626919055741,
"grad_norm": 1.3567590713500977,
"learning_rate": 1.2667364155640605e-05,
"loss": 0.5405444622039794,
"step": 15320
},
{
"epoch": 1.6870632256644473,
"grad_norm": 1.57472825050354,
"learning_rate": 1.2580687507978939e-05,
"loss": 0.4519017696380615,
"step": 15330
},
{
"epoch": 1.6881637594233203,
"grad_norm": 4.239459991455078,
"learning_rate": 1.2494288512398689e-05,
"loss": 0.5046291828155518,
"step": 15340
},
{
"epoch": 1.6892642931821933,
"grad_norm": 1.2556648254394531,
"learning_rate": 1.2408167443311214e-05,
"loss": 0.4740407466888428,
"step": 15350
},
{
"epoch": 1.6903648269410665,
"grad_norm": 1.581095814704895,
"learning_rate": 1.2322324574245325e-05,
"loss": 0.49892234802246094,
"step": 15360
},
{
"epoch": 1.6914653606999395,
"grad_norm": 1.3345414400100708,
"learning_rate": 1.2236760177846151e-05,
"loss": 0.4784794807434082,
"step": 15370
},
{
"epoch": 1.6925658944588124,
"grad_norm": 1.4904940128326416,
"learning_rate": 1.2151474525874374e-05,
"loss": 0.5195693969726562,
"step": 15380
},
{
"epoch": 1.6936664282176856,
"grad_norm": 1.6829164028167725,
"learning_rate": 1.2066467889205346e-05,
"loss": 0.5046294212341309,
"step": 15390
},
{
"epoch": 1.6947669619765586,
"grad_norm": 1.5731713771820068,
"learning_rate": 1.1981740537828324e-05,
"loss": 0.5192636489868164,
"step": 15400
},
{
"epoch": 1.6958674957354316,
"grad_norm": 1.3151862621307373,
"learning_rate": 1.1897292740845379e-05,
"loss": 0.4913020133972168,
"step": 15410
},
{
"epoch": 1.6969680294943048,
"grad_norm": 1.512939214706421,
"learning_rate": 1.1813124766470828e-05,
"loss": 0.49221248626708985,
"step": 15420
},
{
"epoch": 1.6980685632531778,
"grad_norm": 1.901566743850708,
"learning_rate": 1.1729236882030204e-05,
"loss": 0.4731272220611572,
"step": 15430
},
{
"epoch": 1.6991690970120508,
"grad_norm": 1.6065196990966797,
"learning_rate": 1.1645629353959397e-05,
"loss": 0.5022298336029053,
"step": 15440
},
{
"epoch": 1.700269630770924,
"grad_norm": 1.7327016592025757,
"learning_rate": 1.1562302447803896e-05,
"loss": 0.4893610954284668,
"step": 15450
},
{
"epoch": 1.701370164529797,
"grad_norm": 1.6957242488861084,
"learning_rate": 1.1479256428217955e-05,
"loss": 0.5109964847564697,
"step": 15460
},
{
"epoch": 1.70247069828867,
"grad_norm": 1.4845256805419922,
"learning_rate": 1.1396491558963629e-05,
"loss": 0.5053259372711182,
"step": 15470
},
{
"epoch": 1.7035712320475431,
"grad_norm": 1.2765010595321655,
"learning_rate": 1.1314008102910045e-05,
"loss": 0.5121177673339844,
"step": 15480
},
{
"epoch": 1.704671765806416,
"grad_norm": 1.2795841693878174,
"learning_rate": 1.1231806322032512e-05,
"loss": 0.472731351852417,
"step": 15490
},
{
"epoch": 1.705772299565289,
"grad_norm": 1.382643461227417,
"learning_rate": 1.1149886477411797e-05,
"loss": 0.4737096786499023,
"step": 15500
},
{
"epoch": 1.7068728333241623,
"grad_norm": 1.3392523527145386,
"learning_rate": 1.1068248829233063e-05,
"loss": 0.49882683753967283,
"step": 15510
},
{
"epoch": 1.7079733670830353,
"grad_norm": 1.4851186275482178,
"learning_rate": 1.0986893636785345e-05,
"loss": 0.503405237197876,
"step": 15520
},
{
"epoch": 1.7090739008419082,
"grad_norm": 1.2914671897888184,
"learning_rate": 1.0905821158460461e-05,
"loss": 0.5247926235198974,
"step": 15530
},
{
"epoch": 1.7101744346007814,
"grad_norm": 1.3877924680709839,
"learning_rate": 1.082503165175235e-05,
"loss": 0.5006815433502197,
"step": 15540
},
{
"epoch": 1.7112749683596544,
"grad_norm": 1.3942450284957886,
"learning_rate": 1.0744525373256187e-05,
"loss": 0.4631918430328369,
"step": 15550
},
{
"epoch": 1.7123755021185274,
"grad_norm": 1.1906051635742188,
"learning_rate": 1.066430257866764e-05,
"loss": 0.4653836727142334,
"step": 15560
},
{
"epoch": 1.7134760358774006,
"grad_norm": 1.127695918083191,
"learning_rate": 1.0584363522781893e-05,
"loss": 0.49837164878845214,
"step": 15570
},
{
"epoch": 1.7145765696362736,
"grad_norm": 1.3896594047546387,
"learning_rate": 1.0504708459493085e-05,
"loss": 0.5270628929138184,
"step": 15580
},
{
"epoch": 1.7156771033951466,
"grad_norm": 2.0562868118286133,
"learning_rate": 1.0425337641793265e-05,
"loss": 0.45902328491210936,
"step": 15590
},
{
"epoch": 1.7167776371540198,
"grad_norm": 1.2802178859710693,
"learning_rate": 1.0346251321771727e-05,
"loss": 0.47810897827148435,
"step": 15600
},
{
"epoch": 1.7178781709128927,
"grad_norm": 1.6513473987579346,
"learning_rate": 1.0267449750614167e-05,
"loss": 0.482440185546875,
"step": 15610
},
{
"epoch": 1.7189787046717657,
"grad_norm": 1.267770528793335,
"learning_rate": 1.0188933178601934e-05,
"loss": 0.5080968379974365,
"step": 15620
},
{
"epoch": 1.720079238430639,
"grad_norm": 1.3432246446609497,
"learning_rate": 1.0110701855111127e-05,
"loss": 0.503794813156128,
"step": 15630
},
{
"epoch": 1.721179772189512,
"grad_norm": 1.2334939241409302,
"learning_rate": 1.0032756028611878e-05,
"loss": 0.47652387619018555,
"step": 15640
},
{
"epoch": 1.7222803059483849,
"grad_norm": 1.353100299835205,
"learning_rate": 9.955095946667648e-06,
"loss": 0.5236512184143066,
"step": 15650
},
{
"epoch": 1.723380839707258,
"grad_norm": 1.2821303606033325,
"learning_rate": 9.877721855934174e-06,
"loss": 0.46499147415161135,
"step": 15660
},
{
"epoch": 1.724481373466131,
"grad_norm": 1.4900397062301636,
"learning_rate": 9.800634002159014e-06,
"loss": 0.4873676776885986,
"step": 15670
},
{
"epoch": 1.725581907225004,
"grad_norm": 1.3059898614883423,
"learning_rate": 9.72383263018054e-06,
"loss": 0.44753055572509765,
"step": 15680
},
{
"epoch": 1.7266824409838772,
"grad_norm": 1.3506933450698853,
"learning_rate": 9.647317983927229e-06,
"loss": 0.4810802936553955,
"step": 15690
},
{
"epoch": 1.7277829747427502,
"grad_norm": 1.4350816011428833,
"learning_rate": 9.571090306416896e-06,
"loss": 0.49394817352294923,
"step": 15700
},
{
"epoch": 1.7288835085016232,
"grad_norm": 1.6091362237930298,
"learning_rate": 9.495149839755957e-06,
"loss": 0.49670777320861814,
"step": 15710
},
{
"epoch": 1.7299840422604964,
"grad_norm": 1.3593058586120605,
"learning_rate": 9.419496825138553e-06,
"loss": 0.49642577171325686,
"step": 15720
},
{
"epoch": 1.7310845760193694,
"grad_norm": 1.3399890661239624,
"learning_rate": 9.344131502845887e-06,
"loss": 0.4302056312561035,
"step": 15730
},
{
"epoch": 1.7321851097782424,
"grad_norm": 1.6365526914596558,
"learning_rate": 9.269054112245423e-06,
"loss": 0.46183066368103026,
"step": 15740
},
{
"epoch": 1.7332856435371156,
"grad_norm": 1.5882436037063599,
"learning_rate": 9.194264891790117e-06,
"loss": 0.4774309635162354,
"step": 15750
},
{
"epoch": 1.7343861772959885,
"grad_norm": 1.5163041353225708,
"learning_rate": 9.119764079017646e-06,
"loss": 0.48533201217651367,
"step": 15760
},
{
"epoch": 1.7354867110548615,
"grad_norm": 1.3020312786102295,
"learning_rate": 9.045551910549744e-06,
"loss": 0.503715181350708,
"step": 15770
},
{
"epoch": 1.7365872448137347,
"grad_norm": 1.533768892288208,
"learning_rate": 8.97162862209132e-06,
"loss": 0.4952040195465088,
"step": 15780
},
{
"epoch": 1.7376877785726077,
"grad_norm": 1.2133359909057617,
"learning_rate": 8.897994448429814e-06,
"loss": 0.49822845458984377,
"step": 15790
},
{
"epoch": 1.7387883123314807,
"grad_norm": 1.351006031036377,
"learning_rate": 8.824649623434344e-06,
"loss": 0.49312901496887207,
"step": 15800
},
{
"epoch": 1.7398888460903539,
"grad_norm": 1.1706602573394775,
"learning_rate": 8.75159438005515e-06,
"loss": 0.4812896251678467,
"step": 15810
},
{
"epoch": 1.7409893798492269,
"grad_norm": 1.482608437538147,
"learning_rate": 8.678828950322581e-06,
"loss": 0.4352248191833496,
"step": 15820
},
{
"epoch": 1.7420899136080998,
"grad_norm": 1.3559718132019043,
"learning_rate": 8.606353565346648e-06,
"loss": 0.4912106037139893,
"step": 15830
},
{
"epoch": 1.743190447366973,
"grad_norm": 1.5892529487609863,
"learning_rate": 8.53416845531606e-06,
"loss": 0.534601354598999,
"step": 15840
},
{
"epoch": 1.744290981125846,
"grad_norm": 1.6422041654586792,
"learning_rate": 8.462273849497627e-06,
"loss": 0.5063694953918457,
"step": 15850
},
{
"epoch": 1.745391514884719,
"grad_norm": 1.3670654296875,
"learning_rate": 8.390669976235466e-06,
"loss": 0.44977493286132814,
"step": 15860
},
{
"epoch": 1.7464920486435922,
"grad_norm": 1.6988846063613892,
"learning_rate": 8.31935706295035e-06,
"loss": 0.511663818359375,
"step": 15870
},
{
"epoch": 1.7475925824024652,
"grad_norm": 1.5501463413238525,
"learning_rate": 8.248335336138846e-06,
"loss": 0.47885308265686033,
"step": 15880
},
{
"epoch": 1.7486931161613382,
"grad_norm": 1.479164958000183,
"learning_rate": 8.17760502137278e-06,
"loss": 0.45977344512939455,
"step": 15890
},
{
"epoch": 1.7497936499202114,
"grad_norm": 1.2264204025268555,
"learning_rate": 8.107166343298377e-06,
"loss": 0.47014689445495605,
"step": 15900
},
{
"epoch": 1.7508941836790843,
"grad_norm": 1.8232094049453735,
"learning_rate": 8.037019525635592e-06,
"loss": 0.5137889862060547,
"step": 15910
},
{
"epoch": 1.7519947174379573,
"grad_norm": 1.3626301288604736,
"learning_rate": 7.967164791177395e-06,
"loss": 0.50910964012146,
"step": 15920
},
{
"epoch": 1.7530952511968305,
"grad_norm": 1.3373427391052246,
"learning_rate": 7.897602361789137e-06,
"loss": 0.4888981819152832,
"step": 15930
},
{
"epoch": 1.7541957849557035,
"grad_norm": 1.5660104751586914,
"learning_rate": 7.828332458407706e-06,
"loss": 0.4907257556915283,
"step": 15940
},
{
"epoch": 1.7552963187145765,
"grad_norm": 1.306642770767212,
"learning_rate": 7.759355301040926e-06,
"loss": 0.4595799446105957,
"step": 15950
},
{
"epoch": 1.7563968524734497,
"grad_norm": 1.514398455619812,
"learning_rate": 7.690671108766857e-06,
"loss": 0.5057201862335206,
"step": 15960
},
{
"epoch": 1.7574973862323227,
"grad_norm": 1.4387516975402832,
"learning_rate": 7.6222800997330145e-06,
"loss": 0.4697705268859863,
"step": 15970
},
{
"epoch": 1.7585979199911956,
"grad_norm": 1.4733822345733643,
"learning_rate": 7.554182491155781e-06,
"loss": 0.5505812168121338,
"step": 15980
},
{
"epoch": 1.7596984537500688,
"grad_norm": 1.7628105878829956,
"learning_rate": 7.486378499319691e-06,
"loss": 0.5085331439971924,
"step": 15990
},
{
"epoch": 1.7607989875089418,
"grad_norm": 1.2045661211013794,
"learning_rate": 7.4188683395766675e-06,
"loss": 0.5183740615844726,
"step": 16000
},
{
"epoch": 1.7607989875089418,
"eval_loss": 0.571410059928894,
"eval_runtime": 932.4122,
"eval_samples_per_second": 9.746,
"eval_steps_per_second": 2.437,
"step": 16000
},
{
"epoch": 1.7618995212678148,
"grad_norm": 1.3397146463394165,
"learning_rate": 7.351652226345429e-06,
"loss": 0.498541259765625,
"step": 16010
},
{
"epoch": 1.763000055026688,
"grad_norm": 1.3733508586883545,
"learning_rate": 7.2847303731107486e-06,
"loss": 0.47433271408081057,
"step": 16020
},
{
"epoch": 1.764100588785561,
"grad_norm": 2.1013832092285156,
"learning_rate": 7.2181029924228814e-06,
"loss": 0.4796009063720703,
"step": 16030
},
{
"epoch": 1.765201122544434,
"grad_norm": 1.7820372581481934,
"learning_rate": 7.151770295896665e-06,
"loss": 0.5235174179077149,
"step": 16040
},
{
"epoch": 1.7663016563033072,
"grad_norm": 1.4959107637405396,
"learning_rate": 7.085732494211139e-06,
"loss": 0.5341545581817627,
"step": 16050
},
{
"epoch": 1.7674021900621801,
"grad_norm": 2.441849708557129,
"learning_rate": 7.0199897971086395e-06,
"loss": 0.491743803024292,
"step": 16060
},
{
"epoch": 1.7685027238210531,
"grad_norm": 1.544525384902954,
"learning_rate": 6.9545424133942495e-06,
"loss": 0.5034923553466797,
"step": 16070
},
{
"epoch": 1.7696032575799263,
"grad_norm": 1.5638337135314941,
"learning_rate": 6.889390550935104e-06,
"loss": 0.4558037281036377,
"step": 16080
},
{
"epoch": 1.7707037913387993,
"grad_norm": 1.5608367919921875,
"learning_rate": 6.824534416659767e-06,
"loss": 0.48253445625305175,
"step": 16090
},
{
"epoch": 1.7718043250976723,
"grad_norm": 1.3421342372894287,
"learning_rate": 6.759974216557452e-06,
"loss": 0.4774980068206787,
"step": 16100
},
{
"epoch": 1.7729048588565455,
"grad_norm": 17.058841705322266,
"learning_rate": 6.695710155677581e-06,
"loss": 0.47089519500732424,
"step": 16110
},
{
"epoch": 1.7740053926154185,
"grad_norm": 1.2970026731491089,
"learning_rate": 6.631742438128907e-06,
"loss": 0.4535526752471924,
"step": 16120
},
{
"epoch": 1.7751059263742914,
"grad_norm": 1.2941163778305054,
"learning_rate": 6.568071267079035e-06,
"loss": 0.47034287452697754,
"step": 16130
},
{
"epoch": 1.7762064601331646,
"grad_norm": 1.3525419235229492,
"learning_rate": 6.504696844753633e-06,
"loss": 0.493410587310791,
"step": 16140
},
{
"epoch": 1.7773069938920376,
"grad_norm": 1.5001431703567505,
"learning_rate": 6.441619372435969e-06,
"loss": 0.4770656585693359,
"step": 16150
},
{
"epoch": 1.7784075276509106,
"grad_norm": 1.4837284088134766,
"learning_rate": 6.378839050466101e-06,
"loss": 0.4954259395599365,
"step": 16160
},
{
"epoch": 1.7795080614097838,
"grad_norm": 1.3771638870239258,
"learning_rate": 6.3163560782403154e-06,
"loss": 0.5287114143371582,
"step": 16170
},
{
"epoch": 1.7806085951686568,
"grad_norm": 1.476910948753357,
"learning_rate": 6.254170654210489e-06,
"loss": 0.5077893257141113,
"step": 16180
},
{
"epoch": 1.7817091289275298,
"grad_norm": 1.2749086618423462,
"learning_rate": 6.192282975883501e-06,
"loss": 0.4867675304412842,
"step": 16190
},
{
"epoch": 1.782809662686403,
"grad_norm": 1.3131582736968994,
"learning_rate": 6.130693239820473e-06,
"loss": 0.44357953071594236,
"step": 16200
},
{
"epoch": 1.783910196445276,
"grad_norm": 1.1828453540802002,
"learning_rate": 6.0694016416363295e-06,
"loss": 0.43459081649780273,
"step": 16210
},
{
"epoch": 1.785010730204149,
"grad_norm": 1.3610748052597046,
"learning_rate": 6.008408375999031e-06,
"loss": 0.5149364948272706,
"step": 16220
},
{
"epoch": 1.7861112639630221,
"grad_norm": 1.6660943031311035,
"learning_rate": 5.947713636628993e-06,
"loss": 0.480855655670166,
"step": 16230
},
{
"epoch": 1.787211797721895,
"grad_norm": 1.461757779121399,
"learning_rate": 5.8873176162984935e-06,
"loss": 0.5205021381378174,
"step": 16240
},
{
"epoch": 1.788312331480768,
"grad_norm": 1.26321280002594,
"learning_rate": 5.827220506831099e-06,
"loss": 0.49908056259155276,
"step": 16250
},
{
"epoch": 1.7894128652396413,
"grad_norm": 1.5928549766540527,
"learning_rate": 5.767422499100927e-06,
"loss": 0.4879549503326416,
"step": 16260
},
{
"epoch": 1.7905133989985142,
"grad_norm": 1.4870657920837402,
"learning_rate": 5.707923783032177e-06,
"loss": 0.4822522163391113,
"step": 16270
},
{
"epoch": 1.7916139327573872,
"grad_norm": 1.4528108835220337,
"learning_rate": 5.64872454759845e-06,
"loss": 0.46695284843444823,
"step": 16280
},
{
"epoch": 1.7927144665162604,
"grad_norm": 1.4516433477401733,
"learning_rate": 5.589824980822167e-06,
"loss": 0.48630385398864745,
"step": 16290
},
{
"epoch": 1.7938150002751334,
"grad_norm": 1.4366508722305298,
"learning_rate": 5.531225269773965e-06,
"loss": 0.47826972007751467,
"step": 16300
},
{
"epoch": 1.7949155340340064,
"grad_norm": 3.543513298034668,
"learning_rate": 5.472925600572154e-06,
"loss": 0.478728723526001,
"step": 16310
},
{
"epoch": 1.7960160677928796,
"grad_norm": 1.2810817956924438,
"learning_rate": 5.414926158381983e-06,
"loss": 0.5134160995483399,
"step": 16320
},
{
"epoch": 1.7971166015517526,
"grad_norm": 1.3912413120269775,
"learning_rate": 5.3572271274152875e-06,
"loss": 0.5069539070129394,
"step": 16330
},
{
"epoch": 1.7982171353106255,
"grad_norm": 1.8073666095733643,
"learning_rate": 5.2998286909296646e-06,
"loss": 0.5096320152282715,
"step": 16340
},
{
"epoch": 1.7993176690694987,
"grad_norm": 1.441056251525879,
"learning_rate": 5.242731031228021e-06,
"loss": 0.5048434257507324,
"step": 16350
},
{
"epoch": 1.8004182028283717,
"grad_norm": 1.3597674369812012,
"learning_rate": 5.185934329657982e-06,
"loss": 0.5135327339172363,
"step": 16360
},
{
"epoch": 1.8015187365872447,
"grad_norm": 1.3271512985229492,
"learning_rate": 5.129438766611294e-06,
"loss": 0.4613320350646973,
"step": 16370
},
{
"epoch": 1.802619270346118,
"grad_norm": 1.5799742937088013,
"learning_rate": 5.073244521523268e-06,
"loss": 0.508840274810791,
"step": 16380
},
{
"epoch": 1.8037198041049909,
"grad_norm": 1.9551643133163452,
"learning_rate": 5.017351772872192e-06,
"loss": 0.5128527641296386,
"step": 16390
},
{
"epoch": 1.8048203378638639,
"grad_norm": 1.3026198148727417,
"learning_rate": 4.961760698178741e-06,
"loss": 0.4174784183502197,
"step": 16400
},
{
"epoch": 1.805920871622737,
"grad_norm": 1.7748159170150757,
"learning_rate": 4.906471474005514e-06,
"loss": 0.5316793918609619,
"step": 16410
},
{
"epoch": 1.80702140538161,
"grad_norm": 4.936583042144775,
"learning_rate": 4.8514842759563306e-06,
"loss": 0.47519512176513673,
"step": 16420
},
{
"epoch": 1.808121939140483,
"grad_norm": 1.405379056930542,
"learning_rate": 4.796799278675801e-06,
"loss": 0.48841171264648436,
"step": 16430
},
{
"epoch": 1.8092224728993562,
"grad_norm": 1.3053354024887085,
"learning_rate": 4.742416655848692e-06,
"loss": 0.4694413661956787,
"step": 16440
},
{
"epoch": 1.8103230066582292,
"grad_norm": 1.1684783697128296,
"learning_rate": 4.688336580199415e-06,
"loss": 0.5031184673309326,
"step": 16450
},
{
"epoch": 1.8114235404171022,
"grad_norm": 1.4179846048355103,
"learning_rate": 4.634559223491419e-06,
"loss": 0.4918079853057861,
"step": 16460
},
{
"epoch": 1.8125240741759754,
"grad_norm": 1.4172260761260986,
"learning_rate": 4.581084756526777e-06,
"loss": 0.4953932285308838,
"step": 16470
},
{
"epoch": 1.8136246079348484,
"grad_norm": 1.4033087491989136,
"learning_rate": 4.527913349145441e-06,
"loss": 0.4812478065490723,
"step": 16480
},
{
"epoch": 1.8147251416937213,
"grad_norm": 1.6133384704589844,
"learning_rate": 4.475045170224923e-06,
"loss": 0.5024697780609131,
"step": 16490
},
{
"epoch": 1.8158256754525945,
"grad_norm": 1.6788911819458008,
"learning_rate": 4.4224803876795835e-06,
"loss": 0.4599743366241455,
"step": 16500
},
{
"epoch": 1.8169262092114675,
"grad_norm": 1.5224758386611938,
"learning_rate": 4.370219168460188e-06,
"loss": 0.46500720977783205,
"step": 16510
},
{
"epoch": 1.8180267429703405,
"grad_norm": 1.4024637937545776,
"learning_rate": 4.318261678553359e-06,
"loss": 0.45071611404418943,
"step": 16520
},
{
"epoch": 1.8191272767292137,
"grad_norm": 1.508223533630371,
"learning_rate": 4.266608082981061e-06,
"loss": 0.4437118053436279,
"step": 16530
},
{
"epoch": 1.8202278104880867,
"grad_norm": 1.2013787031173706,
"learning_rate": 4.215258545800027e-06,
"loss": 0.4877159118652344,
"step": 16540
},
{
"epoch": 1.8213283442469597,
"grad_norm": 1.4575247764587402,
"learning_rate": 4.164213230101299e-06,
"loss": 0.4529064178466797,
"step": 16550
},
{
"epoch": 1.8224288780058329,
"grad_norm": 1.7645288705825806,
"learning_rate": 4.113472298009669e-06,
"loss": 0.4811866283416748,
"step": 16560
},
{
"epoch": 1.8235294117647058,
"grad_norm": 1.2957864999771118,
"learning_rate": 4.063035910683177e-06,
"loss": 0.4628279685974121,
"step": 16570
},
{
"epoch": 1.8246299455235788,
"grad_norm": 1.6794031858444214,
"learning_rate": 4.012904228312597e-06,
"loss": 0.5454041481018066,
"step": 16580
},
{
"epoch": 1.825730479282452,
"grad_norm": 1.1122554540634155,
"learning_rate": 3.963077410120952e-06,
"loss": 0.441547155380249,
"step": 16590
},
{
"epoch": 1.826831013041325,
"grad_norm": 1.4875439405441284,
"learning_rate": 3.913555614362973e-06,
"loss": 0.4898341178894043,
"step": 16600
},
{
"epoch": 1.827931546800198,
"grad_norm": 1.4908473491668701,
"learning_rate": 3.8643389983246015e-06,
"loss": 0.4408401966094971,
"step": 16610
},
{
"epoch": 1.8290320805590712,
"grad_norm": 1.4305132627487183,
"learning_rate": 3.815427718322495e-06,
"loss": 0.4727658748626709,
"step": 16620
},
{
"epoch": 1.8301326143179442,
"grad_norm": 1.689435362815857,
"learning_rate": 3.766821929703601e-06,
"loss": 0.4846055030822754,
"step": 16630
},
{
"epoch": 1.8312331480768171,
"grad_norm": 1.223456859588623,
"learning_rate": 3.7185217868444754e-06,
"loss": 0.4678616523742676,
"step": 16640
},
{
"epoch": 1.8323336818356903,
"grad_norm": 1.547015905380249,
"learning_rate": 3.6705274431510285e-06,
"loss": 0.49344382286071775,
"step": 16650
},
{
"epoch": 1.8334342155945633,
"grad_norm": 1.5444703102111816,
"learning_rate": 3.622839051057869e-06,
"loss": 0.4967376232147217,
"step": 16660
},
{
"epoch": 1.8345347493534363,
"grad_norm": 1.434402346611023,
"learning_rate": 3.5754567620278623e-06,
"loss": 0.5205514430999756,
"step": 16670
},
{
"epoch": 1.8356352831123095,
"grad_norm": 1.2810301780700684,
"learning_rate": 3.5283807265517053e-06,
"loss": 0.511384916305542,
"step": 16680
},
{
"epoch": 1.8367358168711825,
"grad_norm": 1.4732449054718018,
"learning_rate": 3.4816110941473745e-06,
"loss": 0.48352503776550293,
"step": 16690
},
{
"epoch": 1.8378363506300555,
"grad_norm": 1.2525042295455933,
"learning_rate": 3.4351480133596793e-06,
"loss": 0.5211921691894531,
"step": 16700
},
{
"epoch": 1.8389368843889287,
"grad_norm": 1.4626001119613647,
"learning_rate": 3.388991631759797e-06,
"loss": 0.485138988494873,
"step": 16710
},
{
"epoch": 1.8400374181478016,
"grad_norm": 1.286407232284546,
"learning_rate": 3.343142095944829e-06,
"loss": 0.4560691833496094,
"step": 16720
},
{
"epoch": 1.8411379519066746,
"grad_norm": 1.4930766820907593,
"learning_rate": 3.2975995515372338e-06,
"loss": 0.5162207126617432,
"step": 16730
},
{
"epoch": 1.8422384856655478,
"grad_norm": 1.2225842475891113,
"learning_rate": 3.2523641431845164e-06,
"loss": 0.49532690048217776,
"step": 16740
},
{
"epoch": 1.8433390194244208,
"grad_norm": 1.545382022857666,
"learning_rate": 3.2074360145586292e-06,
"loss": 0.5100488662719727,
"step": 16750
},
{
"epoch": 1.8444395531832938,
"grad_norm": 1.4129167795181274,
"learning_rate": 3.1628153083556154e-06,
"loss": 0.4331677436828613,
"step": 16760
},
{
"epoch": 1.845540086942167,
"grad_norm": 1.328216791152954,
"learning_rate": 3.1185021662950897e-06,
"loss": 0.507054328918457,
"step": 16770
},
{
"epoch": 1.84664062070104,
"grad_norm": 2.003307342529297,
"learning_rate": 3.0744967291198245e-06,
"loss": 0.48369827270507815,
"step": 16780
},
{
"epoch": 1.847741154459913,
"grad_norm": 1.4729647636413574,
"learning_rate": 3.030799136595275e-06,
"loss": 0.49610328674316406,
"step": 16790
},
{
"epoch": 1.8488416882187861,
"grad_norm": 1.3687442541122437,
"learning_rate": 2.9874095275091773e-06,
"loss": 0.4711920261383057,
"step": 16800
},
{
"epoch": 1.8499422219776591,
"grad_norm": 1.3515735864639282,
"learning_rate": 2.944328039671085e-06,
"loss": 0.49788694381713866,
"step": 16810
},
{
"epoch": 1.851042755736532,
"grad_norm": 1.8043967485427856,
"learning_rate": 2.9015548099118883e-06,
"loss": 0.4700901031494141,
"step": 16820
},
{
"epoch": 1.8521432894954053,
"grad_norm": 1.2496004104614258,
"learning_rate": 2.859089974083451e-06,
"loss": 0.5190350532531738,
"step": 16830
},
{
"epoch": 1.8532438232542783,
"grad_norm": 1.4848257303237915,
"learning_rate": 2.8169336670581746e-06,
"loss": 0.47342667579650877,
"step": 16840
},
{
"epoch": 1.8543443570131513,
"grad_norm": 1.4094747304916382,
"learning_rate": 2.77508602272849e-06,
"loss": 0.4407971858978271,
"step": 16850
},
{
"epoch": 1.8554448907720245,
"grad_norm": 1.4990885257720947,
"learning_rate": 2.7335471740065234e-06,
"loss": 0.4893205165863037,
"step": 16860
},
{
"epoch": 1.8565454245308974,
"grad_norm": 1.47908616065979,
"learning_rate": 2.692317252823606e-06,
"loss": 0.4609483242034912,
"step": 16870
},
{
"epoch": 1.8576459582897704,
"grad_norm": 1.6612927913665771,
"learning_rate": 2.6513963901299234e-06,
"loss": 0.4675410270690918,
"step": 16880
},
{
"epoch": 1.8587464920486436,
"grad_norm": 1.532789945602417,
"learning_rate": 2.6107847158940215e-06,
"loss": 0.4971677303314209,
"step": 16890
},
{
"epoch": 1.8598470258075166,
"grad_norm": 1.4709246158599854,
"learning_rate": 2.5704823591024663e-06,
"loss": 0.4678687572479248,
"step": 16900
},
{
"epoch": 1.8609475595663896,
"grad_norm": 1.3649404048919678,
"learning_rate": 2.5304894477593876e-06,
"loss": 0.4728785514831543,
"step": 16910
},
{
"epoch": 1.8620480933252628,
"grad_norm": 1.7306904792785645,
"learning_rate": 2.490806108886101e-06,
"loss": 0.5300139427185059,
"step": 16920
},
{
"epoch": 1.8631486270841358,
"grad_norm": 1.3341495990753174,
"learning_rate": 2.4514324685206533e-06,
"loss": 0.47535066604614257,
"step": 16930
},
{
"epoch": 1.8642491608430087,
"grad_norm": 1.3063191175460815,
"learning_rate": 2.4123686517175113e-06,
"loss": 0.5029531478881836,
"step": 16940
},
{
"epoch": 1.865349694601882,
"grad_norm": 1.340134859085083,
"learning_rate": 2.3736147825470622e-06,
"loss": 0.47799053192138674,
"step": 16950
},
{
"epoch": 1.866450228360755,
"grad_norm": 1.3002986907958984,
"learning_rate": 2.335170984095314e-06,
"loss": 0.4505612850189209,
"step": 16960
},
{
"epoch": 1.867550762119628,
"grad_norm": 1.389679193496704,
"learning_rate": 2.29703737846344e-06,
"loss": 0.45545973777771,
"step": 16970
},
{
"epoch": 1.868651295878501,
"grad_norm": 1.4512994289398193,
"learning_rate": 2.2592140867673915e-06,
"loss": 0.4941407203674316,
"step": 16980
},
{
"epoch": 1.869751829637374,
"grad_norm": 1.6442269086837769,
"learning_rate": 2.2217012291375628e-06,
"loss": 0.4537534713745117,
"step": 16990
},
{
"epoch": 1.870852363396247,
"grad_norm": 1.2994282245635986,
"learning_rate": 2.1844989247184033e-06,
"loss": 0.49846301078796384,
"step": 17000
},
{
"epoch": 1.870852363396247,
"eval_loss": 0.5682608485221863,
"eval_runtime": 932.9495,
"eval_samples_per_second": 9.74,
"eval_steps_per_second": 2.435,
"step": 17000
},
{
"epoch": 1.8719528971551203,
"grad_norm": 1.1467418670654297,
"learning_rate": 2.1476072916679192e-06,
"loss": 0.4407179832458496,
"step": 17010
},
{
"epoch": 1.8730534309139932,
"grad_norm": 1.1982682943344116,
"learning_rate": 2.111026447157516e-06,
"loss": 0.42673497200012206,
"step": 17020
},
{
"epoch": 1.8741539646728662,
"grad_norm": 1.60700523853302,
"learning_rate": 2.0747565073714116e-06,
"loss": 0.47693214416503904,
"step": 17030
},
{
"epoch": 1.8752544984317394,
"grad_norm": 1.5725548267364502,
"learning_rate": 2.0387975875064246e-06,
"loss": 0.4478909492492676,
"step": 17040
},
{
"epoch": 1.8763550321906124,
"grad_norm": 1.3157997131347656,
"learning_rate": 2.0031498017714866e-06,
"loss": 0.4547413349151611,
"step": 17050
},
{
"epoch": 1.8774555659494854,
"grad_norm": 1.277468204498291,
"learning_rate": 1.967813263387397e-06,
"loss": 0.4340005397796631,
"step": 17060
},
{
"epoch": 1.8785560997083586,
"grad_norm": 1.4535624980926514,
"learning_rate": 1.9327880845863568e-06,
"loss": 0.5111487865447998,
"step": 17070
},
{
"epoch": 1.8796566334672316,
"grad_norm": 1.5918365716934204,
"learning_rate": 1.8980743766116805e-06,
"loss": 0.4864856719970703,
"step": 17080
},
{
"epoch": 1.8807571672261045,
"grad_norm": 1.2914265394210815,
"learning_rate": 1.8636722497174186e-06,
"loss": 0.4729818344116211,
"step": 17090
},
{
"epoch": 1.8818577009849777,
"grad_norm": 1.4036930799484253,
"learning_rate": 1.8295818131680353e-06,
"loss": 0.4701414108276367,
"step": 17100
},
{
"epoch": 1.882958234743851,
"grad_norm": 1.5308575630187988,
"learning_rate": 1.7958031752379644e-06,
"loss": 0.5042922496795654,
"step": 17110
},
{
"epoch": 1.8840587685027237,
"grad_norm": 1.3055890798568726,
"learning_rate": 1.762336443211421e-06,
"loss": 0.4950597286224365,
"step": 17120
},
{
"epoch": 1.885159302261597,
"grad_norm": 1.3631311655044556,
"learning_rate": 1.729181723381923e-06,
"loss": 0.4810330390930176,
"step": 17130
},
{
"epoch": 1.88625983602047,
"grad_norm": 1.5162733793258667,
"learning_rate": 1.6963391210520263e-06,
"loss": 0.4800120830535889,
"step": 17140
},
{
"epoch": 1.8873603697793429,
"grad_norm": 1.5902050733566284,
"learning_rate": 1.6638087405329684e-06,
"loss": 0.48700656890869143,
"step": 17150
},
{
"epoch": 1.888460903538216,
"grad_norm": 1.2508811950683594,
"learning_rate": 1.6315906851443797e-06,
"loss": 0.49460883140563966,
"step": 17160
},
{
"epoch": 1.8895614372970893,
"grad_norm": 1.4485799074172974,
"learning_rate": 1.5996850572138178e-06,
"loss": 0.4614389419555664,
"step": 17170
},
{
"epoch": 1.890661971055962,
"grad_norm": 1.2980258464813232,
"learning_rate": 1.5680919580766452e-06,
"loss": 0.4821598052978516,
"step": 17180
},
{
"epoch": 1.8917625048148352,
"grad_norm": 1.4772777557373047,
"learning_rate": 1.5368114880755623e-06,
"loss": 0.5066043853759765,
"step": 17190
},
{
"epoch": 1.8928630385737084,
"grad_norm": 1.7577104568481445,
"learning_rate": 1.5058437465602982e-06,
"loss": 0.47014532089233396,
"step": 17200
},
{
"epoch": 1.8939635723325812,
"grad_norm": 1.3802697658538818,
"learning_rate": 1.4751888318873751e-06,
"loss": 0.4421832084655762,
"step": 17210
},
{
"epoch": 1.8950641060914544,
"grad_norm": 1.3932445049285889,
"learning_rate": 1.4448468414197447e-06,
"loss": 0.4291090488433838,
"step": 17220
},
{
"epoch": 1.8961646398503276,
"grad_norm": 1.379677414894104,
"learning_rate": 1.4148178715264305e-06,
"loss": 0.48565011024475097,
"step": 17230
},
{
"epoch": 1.8972651736092003,
"grad_norm": 1.3849470615386963,
"learning_rate": 1.3851020175823293e-06,
"loss": 0.46511154174804686,
"step": 17240
},
{
"epoch": 1.8983657073680735,
"grad_norm": 1.4539759159088135,
"learning_rate": 1.3556993739678225e-06,
"loss": 0.503264331817627,
"step": 17250
},
{
"epoch": 1.8994662411269467,
"grad_norm": 1.5131036043167114,
"learning_rate": 1.3266100340685094e-06,
"loss": 0.4900333404541016,
"step": 17260
},
{
"epoch": 1.9005667748858195,
"grad_norm": 1.3216376304626465,
"learning_rate": 1.2978340902749186e-06,
"loss": 0.4727010250091553,
"step": 17270
},
{
"epoch": 1.9016673086446927,
"grad_norm": 1.4103116989135742,
"learning_rate": 1.2693716339821972e-06,
"loss": 0.44039249420166016,
"step": 17280
},
{
"epoch": 1.902767842403566,
"grad_norm": 1.6242998838424683,
"learning_rate": 1.2412227555898216e-06,
"loss": 0.4784849166870117,
"step": 17290
},
{
"epoch": 1.9038683761624386,
"grad_norm": 1.6019479036331177,
"learning_rate": 1.2133875445012987e-06,
"loss": 0.5038319110870362,
"step": 17300
},
{
"epoch": 1.9049689099213118,
"grad_norm": 1.4574084281921387,
"learning_rate": 1.1858660891239326e-06,
"loss": 0.5139556884765625,
"step": 17310
},
{
"epoch": 1.906069443680185,
"grad_norm": 1.3651478290557861,
"learning_rate": 1.1586584768685126e-06,
"loss": 0.46247267723083496,
"step": 17320
},
{
"epoch": 1.9071699774390578,
"grad_norm": 1.471900224685669,
"learning_rate": 1.1317647941489595e-06,
"loss": 0.5233954906463623,
"step": 17330
},
{
"epoch": 1.908270511197931,
"grad_norm": 1.32711660861969,
"learning_rate": 1.1051851263822243e-06,
"loss": 0.41936254501342773,
"step": 17340
},
{
"epoch": 1.9093710449568042,
"grad_norm": 1.2101941108703613,
"learning_rate": 1.0789195579878565e-06,
"loss": 0.4684199333190918,
"step": 17350
},
{
"epoch": 1.910471578715677,
"grad_norm": 1.4281100034713745,
"learning_rate": 1.0529681723877915e-06,
"loss": 0.5159236431121826,
"step": 17360
},
{
"epoch": 1.9115721124745502,
"grad_norm": 1.3076903820037842,
"learning_rate": 1.0273310520061197e-06,
"loss": 0.4783883571624756,
"step": 17370
},
{
"epoch": 1.9126726462334234,
"grad_norm": 1.3305416107177734,
"learning_rate": 1.0020082782687956e-06,
"loss": 0.46505227088928225,
"step": 17380
},
{
"epoch": 1.9137731799922961,
"grad_norm": 1.523998737335205,
"learning_rate": 9.769999316033397e-07,
"loss": 0.4530588150024414,
"step": 17390
},
{
"epoch": 1.9148737137511693,
"grad_norm": 1.498590111732483,
"learning_rate": 9.523060914386706e-07,
"loss": 0.4810521125793457,
"step": 17400
},
{
"epoch": 1.9159742475100425,
"grad_norm": 1.529248833656311,
"learning_rate": 9.279268362047733e-07,
"loss": 0.4706155776977539,
"step": 17410
},
{
"epoch": 1.9170747812689153,
"grad_norm": 1.3469491004943848,
"learning_rate": 9.038622433324873e-07,
"loss": 0.5135562419891357,
"step": 17420
},
{
"epoch": 1.9181753150277885,
"grad_norm": 1.729160189628601,
"learning_rate": 8.801123892532625e-07,
"loss": 0.5041571617126465,
"step": 17430
},
{
"epoch": 1.9192758487866617,
"grad_norm": 1.291731834411621,
"learning_rate": 8.566773493988933e-07,
"loss": 0.4330272674560547,
"step": 17440
},
{
"epoch": 1.9203763825455344,
"grad_norm": 1.4224591255187988,
"learning_rate": 8.335571982013068e-07,
"loss": 0.48047146797180174,
"step": 17450
},
{
"epoch": 1.9214769163044076,
"grad_norm": 2.2447707653045654,
"learning_rate": 8.107520090923193e-07,
"loss": 0.5047957420349121,
"step": 17460
},
{
"epoch": 1.9225774500632808,
"grad_norm": 1.2477126121520996,
"learning_rate": 7.882618545033804e-07,
"loss": 0.44909052848815917,
"step": 17470
},
{
"epoch": 1.9236779838221536,
"grad_norm": 1.3699957132339478,
"learning_rate": 7.660868058653736e-07,
"loss": 0.47534732818603515,
"step": 17480
},
{
"epoch": 1.9247785175810268,
"grad_norm": 1.3152520656585693,
"learning_rate": 7.442269336083496e-07,
"loss": 0.4800139904022217,
"step": 17490
},
{
"epoch": 1.9258790513399,
"grad_norm": 1.39982008934021,
"learning_rate": 7.22682307161382e-07,
"loss": 0.48000526428222656,
"step": 17500
},
{
"epoch": 1.9269795850987728,
"grad_norm": 1.4196877479553223,
"learning_rate": 7.014529949522342e-07,
"loss": 0.5063993453979492,
"step": 17510
},
{
"epoch": 1.928080118857646,
"grad_norm": 1.5006624460220337,
"learning_rate": 6.805390644072485e-07,
"loss": 0.43894391059875487,
"step": 17520
},
{
"epoch": 1.9291806526165192,
"grad_norm": 1.6288270950317383,
"learning_rate": 6.599405819510462e-07,
"loss": 0.46645798683166506,
"step": 17530
},
{
"epoch": 1.930281186375392,
"grad_norm": 1.3500694036483765,
"learning_rate": 6.396576130063836e-07,
"loss": 0.49541325569152833,
"step": 17540
},
{
"epoch": 1.9313817201342651,
"grad_norm": 1.525153398513794,
"learning_rate": 6.196902219939072e-07,
"loss": 0.43886051177978513,
"step": 17550
},
{
"epoch": 1.9324822538931383,
"grad_norm": 1.7500393390655518,
"learning_rate": 6.000384723319541e-07,
"loss": 0.5485270023345947,
"step": 17560
},
{
"epoch": 1.933582787652011,
"grad_norm": 1.453203558921814,
"learning_rate": 5.807024264363637e-07,
"loss": 0.511164379119873,
"step": 17570
},
{
"epoch": 1.9346833214108843,
"grad_norm": 2.376689910888672,
"learning_rate": 5.616821457202436e-07,
"loss": 0.4577455520629883,
"step": 17580
},
{
"epoch": 1.9357838551697575,
"grad_norm": 1.5021432638168335,
"learning_rate": 5.429776905938489e-07,
"loss": 0.5322932720184326,
"step": 17590
},
{
"epoch": 1.9368843889286302,
"grad_norm": 1.3834331035614014,
"learning_rate": 5.245891204642916e-07,
"loss": 0.5016115188598633,
"step": 17600
},
{
"epoch": 1.9379849226875034,
"grad_norm": 1.7016886472702026,
"learning_rate": 5.065164937354428e-07,
"loss": 0.4722607135772705,
"step": 17610
},
{
"epoch": 1.9390854564463766,
"grad_norm": 1.045343279838562,
"learning_rate": 4.887598678076754e-07,
"loss": 0.5081735134124756,
"step": 17620
},
{
"epoch": 1.9401859902052494,
"grad_norm": 1.570024013519287,
"learning_rate": 4.7131929907773265e-07,
"loss": 0.4836297035217285,
"step": 17630
},
{
"epoch": 1.9412865239641226,
"grad_norm": 1.472091555595398,
"learning_rate": 4.5419484293853787e-07,
"loss": 0.48404769897460936,
"step": 17640
},
{
"epoch": 1.9423870577229958,
"grad_norm": 1.5276206731796265,
"learning_rate": 4.373865537789845e-07,
"loss": 0.5093550682067871,
"step": 17650
},
{
"epoch": 1.9434875914818686,
"grad_norm": 1.3952054977416992,
"learning_rate": 4.208944849838026e-07,
"loss": 0.48434224128723147,
"step": 17660
},
{
"epoch": 1.9445881252407418,
"grad_norm": 1.3175244331359863,
"learning_rate": 4.04718688933392e-07,
"loss": 0.4982771396636963,
"step": 17670
},
{
"epoch": 1.945688658999615,
"grad_norm": 1.412063717842102,
"learning_rate": 3.8885921700360097e-07,
"loss": 0.4713120460510254,
"step": 17680
},
{
"epoch": 1.9467891927584877,
"grad_norm": 1.2484747171401978,
"learning_rate": 3.7331611956565873e-07,
"loss": 0.4762276172637939,
"step": 17690
},
{
"epoch": 1.947889726517361,
"grad_norm": 1.2910903692245483,
"learning_rate": 3.5808944598589854e-07,
"loss": 0.427127742767334,
"step": 17700
},
{
"epoch": 1.9489902602762341,
"grad_norm": 1.4708642959594727,
"learning_rate": 3.4317924462570206e-07,
"loss": 0.40667085647583007,
"step": 17710
},
{
"epoch": 1.9500907940351069,
"grad_norm": 1.301836609840393,
"learning_rate": 3.2858556284127704e-07,
"loss": 0.48629393577575686,
"step": 17720
},
{
"epoch": 1.95119132779398,
"grad_norm": 1.5625560283660889,
"learning_rate": 3.1430844698358e-07,
"loss": 0.4781522274017334,
"step": 17730
},
{
"epoch": 1.9522918615528533,
"grad_norm": 1.4539226293563843,
"learning_rate": 3.003479423980604e-07,
"loss": 0.5038555145263672,
"step": 17740
},
{
"epoch": 1.953392395311726,
"grad_norm": 1.582055926322937,
"learning_rate": 2.86704093424639e-07,
"loss": 0.4954071998596191,
"step": 17750
},
{
"epoch": 1.9544929290705992,
"grad_norm": 1.6103061437606812,
"learning_rate": 2.733769433974631e-07,
"loss": 0.4805437088012695,
"step": 17760
},
{
"epoch": 1.9555934628294724,
"grad_norm": 1.2809866666793823,
"learning_rate": 2.603665346448514e-07,
"loss": 0.41643438339233396,
"step": 17770
},
{
"epoch": 1.9566939965883452,
"grad_norm": 1.6181905269622803,
"learning_rate": 2.476729084890939e-07,
"loss": 0.5079646110534668,
"step": 17780
},
{
"epoch": 1.9577945303472184,
"grad_norm": 1.2779567241668701,
"learning_rate": 2.3529610524635204e-07,
"loss": 0.5132848262786865,
"step": 17790
},
{
"epoch": 1.9588950641060916,
"grad_norm": 1.164239525794983,
"learning_rate": 2.2323616422654792e-07,
"loss": 0.48766608238220216,
"step": 17800
},
{
"epoch": 1.9599955978649644,
"grad_norm": 1.2715116739273071,
"learning_rate": 2.114931237331974e-07,
"loss": 0.4858466625213623,
"step": 17810
},
{
"epoch": 1.9610961316238376,
"grad_norm": 2.002347469329834,
"learning_rate": 2.0006702106332155e-07,
"loss": 0.48214139938354494,
"step": 17820
},
{
"epoch": 1.9621966653827108,
"grad_norm": 1.4881888628005981,
"learning_rate": 1.8895789250732432e-07,
"loss": 0.45288238525390623,
"step": 17830
},
{
"epoch": 1.9632971991415835,
"grad_norm": 1.4361538887023926,
"learning_rate": 1.7816577334882623e-07,
"loss": 0.45493340492248535,
"step": 17840
},
{
"epoch": 1.9643977329004567,
"grad_norm": 1.6458100080490112,
"learning_rate": 1.6769069786466418e-07,
"loss": 0.5392881870269776,
"step": 17850
},
{
"epoch": 1.96549826665933,
"grad_norm": 1.2623995542526245,
"learning_rate": 1.5753269932465842e-07,
"loss": 0.4598273754119873,
"step": 17860
},
{
"epoch": 1.9665988004182027,
"grad_norm": 1.3777285814285278,
"learning_rate": 1.4769180999157916e-07,
"loss": 0.4408675193786621,
"step": 17870
},
{
"epoch": 1.9676993341770759,
"grad_norm": 1.3780516386032104,
"learning_rate": 1.3816806112103564e-07,
"loss": 0.471256685256958,
"step": 17880
},
{
"epoch": 1.968799867935949,
"grad_norm": 1.2169220447540283,
"learning_rate": 1.289614829613761e-07,
"loss": 0.5015215396881103,
"step": 17890
},
{
"epoch": 1.9699004016948218,
"grad_norm": 1.317850112915039,
"learning_rate": 1.200721047535436e-07,
"loss": 0.4539444923400879,
"step": 17900
},
{
"epoch": 1.971000935453695,
"grad_norm": 1.5186268091201782,
"learning_rate": 1.1149995473108687e-07,
"loss": 0.48162994384765623,
"step": 17910
},
{
"epoch": 1.9721014692125682,
"grad_norm": 1.4606624841690063,
"learning_rate": 1.0324506011993862e-07,
"loss": 0.5585051536560058,
"step": 17920
},
{
"epoch": 1.973202002971441,
"grad_norm": 1.2997623682022095,
"learning_rate": 9.530744713844853e-08,
"loss": 0.4758197784423828,
"step": 17930
},
{
"epoch": 1.9743025367303142,
"grad_norm": 1.5833791494369507,
"learning_rate": 8.768714099723907e-08,
"loss": 0.5214679718017579,
"step": 17940
},
{
"epoch": 1.9754030704891874,
"grad_norm": 1.3749985694885254,
"learning_rate": 8.038416589911668e-08,
"loss": 0.47807064056396487,
"step": 17950
},
{
"epoch": 1.9765036042480602,
"grad_norm": 1.7009193897247314,
"learning_rate": 7.339854503903842e-08,
"loss": 0.5729294776916504,
"step": 17960
},
{
"epoch": 1.9776041380069334,
"grad_norm": 1.4971975088119507,
"learning_rate": 6.673030060400099e-08,
"loss": 0.5276317119598388,
"step": 17970
},
{
"epoch": 1.9787046717658066,
"grad_norm": 1.1393322944641113,
"learning_rate": 6.037945377297405e-08,
"loss": 0.4593236446380615,
"step": 17980
},
{
"epoch": 1.9798052055246793,
"grad_norm": 1.2766488790512085,
"learning_rate": 5.434602471686701e-08,
"loss": 0.46477689743041994,
"step": 17990
},
{
"epoch": 1.9809057392835525,
"grad_norm": 1.5589616298675537,
"learning_rate": 4.863003259841792e-08,
"loss": 0.467799711227417,
"step": 18000
},
{
"epoch": 1.9809057392835525,
"eval_loss": 0.5677331686019897,
"eval_runtime": 941.1455,
"eval_samples_per_second": 9.655,
"eval_steps_per_second": 2.414,
"step": 18000
},
{
"epoch": 1.9820062730424257,
"grad_norm": 1.496228814125061,
"learning_rate": 4.323149557217132e-08,
"loss": 0.5040238380432129,
"step": 18010
},
{
"epoch": 1.9831068068012985,
"grad_norm": 1.2449252605438232,
"learning_rate": 3.81504307843894e-08,
"loss": 0.4716463565826416,
"step": 18020
},
{
"epoch": 1.9842073405601717,
"grad_norm": 1.3843759298324585,
"learning_rate": 3.338685437301869e-08,
"loss": 0.4571837425231934,
"step": 18030
},
{
"epoch": 1.9853078743190449,
"grad_norm": 1.5251961946487427,
"learning_rate": 2.894078146763457e-08,
"loss": 0.4924781322479248,
"step": 18040
},
{
"epoch": 1.9864084080779176,
"grad_norm": 1.187515139579773,
"learning_rate": 2.4812226189396825e-08,
"loss": 0.4604593276977539,
"step": 18050
},
{
"epoch": 1.9875089418367908,
"grad_norm": 1.8020973205566406,
"learning_rate": 2.100120165097197e-08,
"loss": 0.5087060928344727,
"step": 18060
},
{
"epoch": 1.988609475595664,
"grad_norm": 1.7916630506515503,
"learning_rate": 1.7507719956555422e-08,
"loss": 0.4540903091430664,
"step": 18070
},
{
"epoch": 1.9897100093545368,
"grad_norm": 1.270185947418213,
"learning_rate": 1.4331792201782712e-08,
"loss": 0.4518903732299805,
"step": 18080
},
{
"epoch": 1.99081054311341,
"grad_norm": 1.4558676481246948,
"learning_rate": 1.1473428473673942e-08,
"loss": 0.4700045108795166,
"step": 18090
},
{
"epoch": 1.9919110768722832,
"grad_norm": 1.418771743774414,
"learning_rate": 8.932637850700421e-09,
"loss": 0.47863569259643557,
"step": 18100
},
{
"epoch": 1.993011610631156,
"grad_norm": 1.5367437601089478,
"learning_rate": 6.709428402629225e-09,
"loss": 0.48225626945495603,
"step": 18110
},
{
"epoch": 1.9941121443900292,
"grad_norm": 1.5482364892959595,
"learning_rate": 4.803807190600917e-09,
"loss": 0.44969968795776366,
"step": 18120
},
{
"epoch": 1.9952126781489024,
"grad_norm": 1.7544103860855103,
"learning_rate": 3.2157802670518266e-09,
"loss": 0.5117983341217041,
"step": 18130
},
{
"epoch": 1.996313211907775,
"grad_norm": 1.4483720064163208,
"learning_rate": 1.9453526756918474e-09,
"loss": 0.5166549205780029,
"step": 18140
},
{
"epoch": 1.9974137456666483,
"grad_norm": 1.318522334098816,
"learning_rate": 9.925284515377443e-10,
"loss": 0.4185433864593506,
"step": 18150
},
{
"epoch": 1.9985142794255215,
"grad_norm": 1.5816627740859985,
"learning_rate": 3.573106208354382e-10,
"loss": 0.4965072154998779,
"step": 18160
},
{
"epoch": 1.9996148131843943,
"grad_norm": 1.4003589153289795,
"learning_rate": 3.9701201104414e-11,
"loss": 0.4872720718383789,
"step": 18170
},
{
"epoch": 2.0,
"eval_loss": 0.5677207112312317,
"eval_runtime": 935.5474,
"eval_samples_per_second": 9.713,
"eval_steps_per_second": 2.429,
"step": 18174
}
],
"logging_steps": 10,
"max_steps": 18174,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.0987971993743094e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}