ALL_PAD / trainer_state.json
nuresens's picture
Upload 12 files
db8c8bf verified
Raw
History Blame Contribute Delete
152 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.8804270070984428,
"eval_steps": 1000,
"global_step": 8000,
"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
}
],
"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": false
},
"attributes": {}
}
},
"total_flos": 1.9426659175242056e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}