CoolFace
Apppublic

pruthvimv/DecoderonlyTransformer

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes
traininglogs.txt5010 linesDownload Raw Back to root
1Streaming output truncated to the last 5000 lines.2Iteration: 3, Loss: 8.8957433700561523Iteration: 4, Loss: 8.8940343856811524Iteration: 5, Loss: 8.9569206237792975Iteration: 6, Loss: 8.5263452529907236Iteration: 7, Loss: 8.2215013504028327Iteration: 8, Loss: 8.3607473373413098Iteration: 9, Loss: 8.438317298889169Iteration: 10, Loss: 8.2197370529174810Iteration: 11, Loss: 7.85034751892089811Iteration: 12, Loss: 7.37942314147949212Iteration: 13, Loss: 7.56166028976440413Iteration: 14, Loss: 7.15611934661865214Iteration: 15, Loss: 7.28928184509277315Iteration: 16, Loss: 6.91428375244140616Iteration: 17, Loss: 6.93079280853271517Iteration: 18, Loss: 7.08644866943359418Iteration: 19, Loss: 6.92940521240234419Iteration: 20, Loss: 6.60888099670410220Iteration: 21, Loss: 6.562508106231689521Iteration: 22, Loss: 6.39959049224853522Iteration: 23, Loss: 7.23167514801025423Iteration: 24, Loss: 6.80198717117309624Iteration: 25, Loss: 6.55112648010253925Iteration: 26, Loss: 6.58138799667358426Iteration: 27, Loss: 7.1855759620666527Iteration: 28, Loss: 6.63848543167114328Iteration: 29, Loss: 6.84415149688720729Iteration: 30, Loss: 6.4767136573791530Iteration: 31, Loss: 6.93996858596801831Iteration: 32, Loss: 6.38731431961059632Iteration: 33, Loss: 6.48135614395141633Iteration: 34, Loss: 6.41095638275146534Iteration: 35, Loss: 6.33466434478759835Iteration: 36, Loss: 6.77569627761840836Iteration: 37, Loss: 6.03603649139404337Iteration: 38, Loss: 6.68925571441650438Iteration: 39, Loss: 6.85447740554809639Iteration: 40, Loss: 6.176777839660644540Iteration: 41, Loss: 5.88563489913940441Iteration: 42, Loss: 6.18010330200195342Iteration: 43, Loss: 6.58602571487426843Iteration: 44, Loss: 6.75951910018920944Iteration: 45, Loss: 6.26761484146118245Iteration: 46, Loss: 5.86173009872436546Iteration: 47, Loss: 5.931101799011230547Iteration: 48, Loss: 5.75887298583984448Iteration: 49, Loss: 6.30458354949951249Iteration: 50, Loss: 6.09069633483886750Iteration: 51, Loss: 5.70692539215087951Iteration: 52, Loss: 6.62702655792236352Iteration: 53, Loss: 6.41295289993286153Iteration: 54, Loss: 6.01255416870117254Iteration: 55, Loss: 5.89056539535522555Iteration: 56, Loss: 6.00906324386596756Iteration: 57, Loss: 5.80825757980346757Iteration: 58, Loss: 6.44639968872070358Iteration: 59, Loss: 6.5968813896179259Iteration: 60, Loss: 5.69742202758789160Iteration: 61, Loss: 5.666582584381103561Iteration: 62, Loss: 6.57192087173461962Iteration: 63, Loss: 6.248543262481689563Iteration: 64, Loss: 5.76719045639038164Iteration: 65, Loss: 5.98882579803466865Iteration: 66, Loss: 6.82821035385131866Iteration: 67, Loss: 6.671052455902167Iteration: 68, Loss: 6.00752782821655368Iteration: 69, Loss: 6.61491775512695369Iteration: 70, Loss: 5.99197673797607470Iteration: 71, Loss: 5.91367912292480571Iteration: 72, Loss: 5.89387464523315472Iteration: 73, Loss: 5.98923301696777373Iteration: 74, Loss: 5.70804166793823274Iteration: 75, Loss: 6.22814702987670975Iteration: 76, Loss: 6.13558530807495176Iteration: 77, Loss: 5.89401865005493277Iteration: 78, Loss: 5.46430683135986378Iteration: 79, Loss: 6.27013015747070379Iteration: 80, Loss: 6.44797277450561580Iteration: 81, Loss: 5.93414783477783281Iteration: 82, Loss: 6.608502864837646582Iteration: 83, Loss: 6.25254774093627983Iteration: 84, Loss: 6.519276618957519584Iteration: 85, Loss: 6.54817581176757885Iteration: 86, Loss: 5.69352626800537186Iteration: 87, Loss: 6.197644710540771587Iteration: 88, Loss: 6.17635393142700288Iteration: 89, Loss: 6.13732194900512789Iteration: 90, Loss: 6.15821981430053790Iteration: 91, Loss: 6.02569484710693491Iteration: 92, Loss: 6.12086200714111392Iteration: 93, Loss: 7.07084083557128993Iteration: 94, Loss: 6.86803722381591894Iteration: 95, Loss: 6.91814517974853595Iteration: 96, Loss: 6.488998413085937596Iteration: 97, Loss: 6.94689846038818497Iteration: 98, Loss: 6.747998714447021598Iteration: 99, Loss: 6.67830848693847799Iteration: 100, Loss: 6.3235764503479100Iteration: 101, Loss: 6.31793212890625101Iteration: 102, Loss: 5.965436935424805102Iteration: 103, Loss: 6.118473052978516103Iteration: 104, Loss: 6.691493034362793104Iteration: 105, Loss: 6.609532833099365105Iteration: 106, Loss: 6.543168544769287106Iteration: 107, Loss: 6.280616283416748107Iteration: 108, Loss: 6.067577362060547108Iteration: 109, Loss: 6.3025288581848145109Iteration: 110, Loss: 6.34381628036499110Iteration: 111, Loss: 6.1892523765563965111Iteration: 112, Loss: 6.0966796875112Iteration: 113, Loss: 5.819360733032227113Iteration: 114, Loss: 6.153161525726318114Iteration: 115, Loss: 6.803555965423584115Iteration: 116, Loss: 6.13796854019165116Iteration: 117, Loss: 6.348178863525391117Iteration: 118, Loss: 5.611758232116699118Iteration: 119, Loss: 6.010788440704346119Iteration: 120, Loss: 5.407723903656006120Iteration: 121, Loss: 5.719157695770264121Iteration: 122, Loss: 6.108151435852051122Iteration: 123, Loss: 5.821104049682617123Iteration: 124, Loss: 6.263987064361572124Iteration: 125, Loss: 5.888461589813232125Iteration: 126, Loss: 6.182252407073975126Iteration: 127, Loss: 6.188297748565674127Iteration: 128, Loss: 6.057547569274902128Iteration: 129, Loss: 5.656232833862305129Iteration: 130, Loss: 5.977249622344971130Iteration: 131, Loss: 6.145895481109619131Iteration: 132, Loss: 5.892321586608887132Iteration: 133, Loss: 5.942869663238525133Iteration: 134, Loss: 6.106966018676758134Iteration: 135, Loss: 5.72014045715332135Iteration: 136, Loss: 5.406620502471924136Iteration: 137, Loss: 5.6817708015441895137Iteration: 138, Loss: 5.5600714683532715138Iteration: 139, Loss: 5.84980583190918139Iteration: 140, Loss: 5.600287914276123140Iteration: 141, Loss: 5.414928913116455141Iteration: 142, Loss: 5.576510906219482142Iteration: 143, Loss: 5.251941204071045143Iteration: 144, Loss: 5.742587089538574144Iteration: 145, Loss: 5.859933376312256145Iteration: 146, Loss: 5.535821437835693146Iteration: 147, Loss: 5.909081935882568147Iteration: 148, Loss: 6.0841965675354148Iteration: 149, Loss: 5.96501350402832149Iteration: 150, Loss: 5.411850452423096150Iteration: 151, Loss: 5.98453426361084151Iteration: 152, Loss: 5.9200825691223145152Iteration: 153, Loss: 5.8402228355407715153Iteration: 154, Loss: 5.389885425567627154Iteration: 155, Loss: 5.74519681930542155Iteration: 156, Loss: 6.013050556182861156Iteration: 157, Loss: 5.992757320404053157Iteration: 158, Loss: 6.308543682098389158Iteration: 159, Loss: 6.182354927062988159Iteration: 160, Loss: 5.6226396560668945160Iteration: 161, Loss: 6.5104522705078125161Iteration: 162, Loss: 6.268352508544922162Iteration: 163, Loss: 6.019026756286621163Iteration: 164, Loss: 6.052421569824219164Iteration: 165, Loss: 6.085065841674805165Iteration: 166, Loss: 5.39570426940918166Iteration: 167, Loss: 5.6573381423950195167Iteration: 168, Loss: 5.6706061363220215168Iteration: 169, Loss: 5.158276081085205169Iteration: 170, Loss: 5.309848308563232170Iteration: 171, Loss: 6.1511712074279785171Iteration: 172, Loss: 4.560102462768555172Iteration: 173, Loss: 5.3311944007873535173Iteration: 174, Loss: 5.3757758140563965174Iteration: 175, Loss: 5.358829498291016175Iteration: 176, Loss: 5.50523042678833176Iteration: 177, Loss: 6.082781791687012177Iteration: 178, Loss: 6.439744472503662178Iteration: 179, Loss: 6.193914413452148179Iteration: 180, Loss: 6.283757209777832180Iteration: 181, Loss: 5.499276638031006181Iteration: 182, Loss: 6.228940010070801182Iteration: 183, Loss: 5.8529181480407715183Iteration: 184, Loss: 6.006184101104736184Iteration: 185, Loss: 5.650347709655762185Iteration: 186, Loss: 5.665425777435303186Iteration: 187, Loss: 6.080619812011719187Iteration: 188, Loss: 6.280272483825684188Iteration: 189, Loss: 6.351895332336426189Iteration: 190, Loss: 6.413197994232178190Iteration: 191, Loss: 6.104734897613525191Iteration: 192, Loss: 6.345442295074463192Iteration: 193, Loss: 6.235412120819092193Iteration: 194, Loss: 6.337061405181885194Iteration: 195, Loss: 5.887033462524414195Iteration: 196, Loss: 6.167230129241943196Iteration: 197, Loss: 6.019498825073242197Iteration: 198, Loss: 6.41754150390625198Iteration: 199, Loss: 6.041718006134033199Iteration: 200, Loss: 6.050971984863281200Iteration: 201, Loss: 5.819769859313965201Iteration: 202, Loss: 6.112922191619873202Iteration: 203, Loss: 6.191938400268555203Iteration: 204, Loss: 6.089895725250244204Iteration: 205, Loss: 6.56103515625205Iteration: 206, Loss: 5.657137393951416206Iteration: 207, Loss: 5.857328414916992207Iteration: 208, Loss: 5.906668663024902208Iteration: 209, Loss: 5.939087390899658209Iteration: 210, Loss: 6.268979549407959210Iteration: 211, Loss: 6.502005577087402211Iteration: 212, Loss: 6.271628379821777212Iteration: 213, Loss: 5.991197109222412213Iteration: 214, Loss: 5.752562046051025214Iteration: 215, Loss: 5.987998962402344215Iteration: 216, Loss: 5.9180779457092285216Iteration: 217, Loss: 5.839540958404541217Iteration: 218, Loss: 5.694380760192871218Iteration: 219, Loss: 5.769063949584961219Iteration: 220, Loss: 6.0850090980529785220Iteration: 221, Loss: 5.935741424560547221Iteration: 222, Loss: 6.08074426651001222Iteration: 223, Loss: 6.21307897567749223Iteration: 224, Loss: 6.262242317199707224Iteration: 225, Loss: 6.267460823059082225Iteration: 226, Loss: 6.168012619018555226Iteration: 227, Loss: 5.478061676025391227Iteration: 228, Loss: 5.890650272369385228Iteration: 229, Loss: 6.129105091094971229Iteration: 230, Loss: 5.797150611877441230Iteration: 231, Loss: 5.9422173500061035231Iteration: 232, Loss: 5.144233703613281232Iteration: 233, Loss: 6.016806602478027233Iteration: 234, Loss: 6.136236190795898234Iteration: 235, Loss: 5.7314958572387695235Iteration: 236, Loss: 5.684961318969727236Iteration: 237, Loss: 5.888591289520264237Iteration: 238, Loss: 5.926122665405273238Iteration: 239, Loss: 5.729434013366699239Iteration: 240, Loss: 5.385494232177734240Iteration: 241, Loss: 5.846940040588379241Iteration: 242, Loss: 5.390106678009033242Iteration: 243, Loss: 4.9919257164001465243Iteration: 244, Loss: 5.86312198638916244Iteration: 245, Loss: 5.932711124420166245Iteration: 246, Loss: 5.415818214416504246Iteration: 247, Loss: 5.896981239318848247Iteration: 248, Loss: 4.972280025482178248Iteration: 249, Loss: 4.876093864440918249Iteration: 250, Loss: 5.348508358001709250Iteration: 251, Loss: 4.844058513641357251Iteration: 252, Loss: 5.630105495452881252Iteration: 253, Loss: 5.355116367340088253Iteration: 254, Loss: 5.327448844909668254Iteration: 255, Loss: 6.161587238311768255Iteration: 256, Loss: 6.217568874359131256Iteration: 257, Loss: 5.728657245635986257Iteration: 258, Loss: 5.797525882720947258Iteration: 259, Loss: 6.218994617462158259Iteration: 260, Loss: 6.15427827835083260Iteration: 261, Loss: 6.395106315612793261Iteration: 262, Loss: 6.419852256774902262Iteration: 263, Loss: 6.075401306152344263Iteration: 264, Loss: 5.982921600341797264Iteration: 265, Loss: 6.230443954467773265Iteration: 266, Loss: 6.458049297332764266Iteration: 267, Loss: 6.359076023101807267Iteration: 268, Loss: 6.025213718414307268Iteration: 269, Loss: 6.255280017852783269Iteration: 270, Loss: 5.995932102203369270Iteration: 271, Loss: 6.060234069824219271Iteration: 272, Loss: 5.82446813583374272Iteration: 273, Loss: 6.90054988861084273Iteration: 274, Loss: 6.233528137207031274Iteration: 275, Loss: 5.831746578216553275Iteration: 276, Loss: 5.663260459899902276Iteration: 277, Loss: 5.309703350067139277Iteration: 278, Loss: 5.594249725341797278Iteration: 279, Loss: 6.141429424285889279Iteration: 280, Loss: 5.708788871765137280Iteration: 281, Loss: 5.49778413772583281Iteration: 282, Loss: 5.713610649108887282Iteration: 283, Loss: 5.136019706726074283Iteration: 284, Loss: 5.288973808288574284Iteration: 285, Loss: 6.851740837097168285Iteration: 286, Loss: 5.973753929138184286Iteration: 287, Loss: 5.616447448730469287Iteration: 288, Loss: 6.721349716186523288Iteration: 289, Loss: 5.531193256378174289Iteration: 290, Loss: 5.291085720062256290Iteration: 291, Loss: 5.645886421203613291Iteration: 292, Loss: 5.383398056030273292Iteration: 293, Loss: 5.875349998474121293Iteration: 294, Loss: 5.266530513763428294Iteration: 295, Loss: 5.799900531768799295Iteration: 296, Loss: 5.566010475158691296Iteration: 297, Loss: 5.9753875732421875297Iteration: 298, Loss: 5.34618616104126298Iteration: 299, Loss: 5.686859607696533299Iteration: 300, Loss: 5.288567543029785300Iteration: 301, Loss: 6.282960891723633301Iteration: 302, Loss: 5.971612930297852302Iteration: 303, Loss: 5.417961120605469303Iteration: 304, Loss: 5.882336139678955304Iteration: 305, Loss: 5.691854000091553305Iteration: 306, Loss: 5.76567268371582306Iteration: 307, Loss: 5.651424884796143307Iteration: 308, Loss: 5.395307540893555308Iteration: 309, Loss: 5.8922882080078125309Iteration: 310, Loss: 5.3178558349609375310Iteration: 311, Loss: 5.656792163848877311Iteration: 312, Loss: 5.227596759796143312Iteration: 313, Loss: 4.961878776550293313Iteration: 314, Loss: 5.383378028869629314Iteration: 315, Loss: 5.707679748535156315Iteration: 316, Loss: 5.47835111618042316Iteration: 317, Loss: 5.067833423614502317Iteration: 318, Loss: 5.147241115570068318Iteration: 319, Loss: 5.016454219818115319Iteration: 320, Loss: 6.083288669586182320Iteration: 321, Loss: 5.455960750579834321Iteration: 322, Loss: 5.270016670227051322Iteration: 323, Loss: 5.462577819824219323Iteration: 324, Loss: 5.460826873779297324Iteration: 325, Loss: 5.14052152633667325Iteration: 326, Loss: 5.364246368408203326Iteration: 327, Loss: 5.790009498596191327Iteration: 328, Loss: 6.402365207672119328Iteration: 329, Loss: 5.752277851104736329Iteration: 330, Loss: 6.451425552368164330Iteration: 331, Loss: 5.518096923828125331Iteration: 332, Loss: 5.953461170196533332Iteration: 333, Loss: 5.464916229248047333Iteration: 334, Loss: 5.981619358062744334Iteration: 335, Loss: 5.317166805267334335Iteration: 336, Loss: 5.465054035186768336Iteration: 337, Loss: 5.529736518859863337Iteration: 338, Loss: 5.681159496307373338Iteration: 339, Loss: 5.385167598724365339Iteration: 340, Loss: 5.9599609375340Iteration: 341, Loss: 6.153255939483643341Iteration: 342, Loss: 5.866151332855225342Iteration: 343, Loss: 5.7697319984436035343Iteration: 344, Loss: 5.703106880187988344Iteration: 345, Loss: 5.675689697265625345Iteration: 346, Loss: 5.6524786949157715346Iteration: 347, Loss: 5.412796974182129347Iteration: 348, Loss: 5.438567161560059348Iteration: 349, Loss: 5.5347161293029785349Iteration: 350, Loss: 5.507183074951172350Iteration: 351, Loss: 6.065235614776611351Iteration: 352, Loss: 5.911828517913818352Iteration: 353, Loss: 5.538563251495361353Iteration: 354, Loss: 6.215968132019043354Iteration: 355, Loss: 5.531988620758057355Iteration: 356, Loss: 5.973682880401611356Iteration: 357, Loss: 5.90043830871582357Iteration: 358, Loss: 5.866061210632324358Iteration: 359, Loss: 5.661550998687744359Iteration: 360, Loss: 5.687011241912842360Iteration: 361, Loss: 5.792910099029541361Iteration: 362, Loss: 5.308346271514893362Iteration: 363, Loss: 4.932343482971191363Iteration: 364, Loss: 5.2400031089782715364Iteration: 365, Loss: 5.690175533294678365Iteration: 366, Loss: 5.558934211730957366Iteration: 367, Loss: 5.611934661865234367Iteration: 368, Loss: 6.2190141677856445368Iteration: 369, Loss: 5.526708126068115369Iteration: 370, Loss: 5.419858932495117370Iteration: 371, Loss: 5.787680149078369371Iteration: 372, Loss: 5.36270809173584372Iteration: 373, Loss: 5.601659774780273373Iteration: 374, Loss: 5.5439229011535645374Iteration: 375, Loss: 5.057365894317627375Iteration: 376, Loss: 5.222695827484131376Iteration: 377, Loss: 5.173471927642822377Iteration: 378, Loss: 5.269149303436279378Iteration: 379, Loss: 5.083975791931152379Iteration: 380, Loss: 5.916669845581055380Iteration: 381, Loss: 6.056134223937988381Iteration: 382, Loss: 5.712060928344727382Iteration: 383, Loss: 5.967216491699219383Iteration: 384, Loss: 5.713843822479248384Iteration: 385, Loss: 5.511733531951904385Iteration: 386, Loss: 5.608048915863037386Iteration: 387, Loss: 5.3184614181518555387Iteration: 388, Loss: 5.210299491882324388Iteration: 389, Loss: 5.555120944976807389Iteration: 390, Loss: 5.268784999847412390Iteration: 391, Loss: 5.505034923553467391Iteration: 392, Loss: 5.460942268371582392Iteration: 393, Loss: 5.334105014801025393Iteration: 394, Loss: 5.136957168579102394Iteration: 395, Loss: 5.5469183921813965395Iteration: 396, Loss: 5.276756763458252396Iteration: 397, Loss: 5.075644016265869397Iteration: 398, Loss: 5.364024639129639398Iteration: 399, Loss: 5.20625114440918399Iteration: 400, Loss: 5.155729293823242400Iteration: 401, Loss: 5.46332311630249401Iteration: 402, Loss: 5.677847862243652402Iteration: 403, Loss: 5.019672393798828403Iteration: 404, Loss: 4.933140277862549404Iteration: 405, Loss: 5.1611833572387695405Iteration: 406, Loss: 5.421034812927246406Iteration: 407, Loss: 5.386486053466797407Iteration: 408, Loss: 5.968545913696289408Iteration: 409, Loss: 5.45906925201416409Iteration: 410, Loss: 5.102582931518555410Iteration: 411, Loss: 4.761255741119385411Iteration: 412, Loss: 4.858714580535889412Iteration: 413, Loss: 5.326050758361816413Iteration: 414, Loss: 5.575449466705322414Iteration: 415, Loss: 5.85734748840332415Iteration: 416, Loss: 5.841215133666992416Iteration: 417, Loss: 6.898280143737793417Iteration: 418, Loss: 6.352571964263916418Iteration: 419, Loss: 6.399647235870361419Iteration: 420, Loss: 6.204813480377197420Iteration: 421, Loss: 6.458000183105469421Iteration: 422, Loss: 5.9020915031433105422Iteration: 423, Loss: 6.300922870635986423Iteration: 424, Loss: 6.112170696258545424Iteration: 425, Loss: 6.350991725921631425Iteration: 426, Loss: 6.113605976104736426Iteration: 427, Loss: 5.839822769165039427Iteration: 428, Loss: 5.638772964477539428Iteration: 429, Loss: 5.990797996520996429Iteration: 430, Loss: 5.394360065460205430Iteration: 431, Loss: 5.658740043640137431Iteration: 432, Loss: 5.937881946563721432Iteration: 433, Loss: 5.59810733795166433Iteration: 434, Loss: 5.730947017669678434Iteration: 435, Loss: 5.753401279449463435Iteration: 436, Loss: 5.997549533843994436Iteration: 437, Loss: 5.521857261657715437Iteration: 438, Loss: 5.403270244598389438Iteration: 439, Loss: 5.317099571228027439Iteration: 440, Loss: 5.5190911293029785440Iteration: 441, Loss: 5.344241142272949441Iteration: 442, Loss: 5.81777811050415442Iteration: 443, Loss: 5.931428909301758443Iteration: 444, Loss: 5.620940208435059444Iteration: 445, Loss: 5.620310306549072445Iteration: 446, Loss: 5.19871711730957446Iteration: 447, Loss: 6.020562171936035447Iteration: 448, Loss: 5.6974968910217285448Iteration: 449, Loss: 5.535641670227051449Iteration: 450, Loss: 6.346283912658691450Iteration: 451, Loss: 6.551259517669678451Iteration: 452, Loss: 6.019059181213379452Iteration: 453, Loss: 6.105724334716797453Iteration: 454, Loss: 6.248625755310059454Iteration: 455, Loss: 6.463501930236816455Iteration: 456, Loss: 6.3013014793396456Iteration: 457, Loss: 6.040557384490967457Iteration: 458, Loss: 5.9172844886779785458Iteration: 459, Loss: 6.020273685455322459Iteration: 460, Loss: 5.987469673156738460Iteration: 461, Loss: 6.272679328918457461Iteration: 462, Loss: 5.602950572967529462Iteration: 463, Loss: 6.323299407958984463Iteration: 464, Loss: 6.2629876136779785464Iteration: 465, Loss: 5.838166236877441465Iteration: 466, Loss: 5.609889507293701466Iteration: 467, Loss: 5.937382698059082467Iteration: 468, Loss: 5.1390156745910645468Iteration: 469, Loss: 5.300936698913574469Iteration: 470, Loss: 5.765490531921387470Iteration: 471, Loss: 5.519032955169678471Iteration: 472, Loss: 5.454690933227539472Iteration: 473, Loss: 5.595682621002197473Iteration: 474, Loss: 6.075573444366455474Iteration: 475, Loss: 5.233826160430908475Iteration: 476, Loss: 5.361355781555176476Iteration: 477, Loss: 5.172372817993164477Iteration: 478, Loss: 5.327831745147705478Iteration: 479, Loss: 6.199558734893799479Iteration: 480, Loss: 5.262738227844238480Iteration: 481, Loss: 5.609508514404297481Iteration: 482, Loss: 5.357351303100586482Iteration: 483, Loss: 5.495264530181885483Iteration: 484, Loss: 5.700713157653809484Iteration: 485, Loss: 5.587535858154297485Iteration: 486, Loss: 5.189087390899658486Iteration: 487, Loss: 6.089048862457275487Iteration: 488, Loss: 6.449041366577148488Iteration: 489, Loss: 6.33252477645874489Iteration: 490, Loss: 5.4395952224731445490Iteration: 491, Loss: 5.09760856628418491Iteration: 492, Loss: 5.4576215744018555492Iteration: 493, Loss: 5.091348648071289493Iteration: 494, Loss: 5.34702730178833494Iteration: 495, Loss: 5.761697292327881495Iteration: 496, Loss: 6.168027877807617496Iteration: 497, Loss: 5.793379783630371497Iteration: 498, Loss: 5.708368301391602498Iteration: 499, Loss: 6.035825252532959499Iteration: 500, Loss: 6.24630069732666500Iteration: 501, Loss: 6.03572940826416501Iteration: 502, Loss: 6.073697090148926502Iteration: 503, Loss: 6.154294967651367503Iteration: 504, Loss: 5.9149861335754395504Iteration: 505, Loss: 6.130240440368652505Iteration: 506, Loss: 5.729521751403809506Iteration: 507, Loss: 5.872653007507324507Iteration: 508, Loss: 5.6363606452941895508Iteration: 509, Loss: 5.597302436828613509Iteration: 510, Loss: 5.156281471252441510Iteration: 511, Loss: 5.730008602142334511Iteration: 512, Loss: 5.542484760284424512Iteration: 513, Loss: 5.387118816375732513Iteration: 514, Loss: 5.050543308258057514Iteration: 515, Loss: 4.972561359405518515Iteration: 516, Loss: 5.2657365798950195516Iteration: 517, Loss: 5.605152130126953517Iteration: 518, Loss: 5.571448802947998518Iteration: 519, Loss: 5.271175384521484519Iteration: 520, Loss: 5.632900714874268520Iteration: 521, Loss: 5.197997093200684521Iteration: 522, Loss: 5.052903652191162522Iteration: 523, Loss: 5.114415168762207523Iteration: 524, Loss: 5.477663993835449524Iteration: 525, Loss: 6.001165390014648525Iteration: 526, Loss: 4.957319736480713526Iteration: 527, Loss: 5.41843843460083527Iteration: 528, Loss: 5.470510959625244528Iteration: 529, Loss: 5.2463059425354529Iteration: 530, Loss: 5.940227508544922530Iteration: 531, Loss: 5.994011878967285531Iteration: 532, Loss: 5.596691131591797532Iteration: 533, Loss: 5.554963111877441533Iteration: 534, Loss: 5.028261661529541534Iteration: 535, Loss: 5.339777946472168535Iteration: 536, Loss: 5.0044121742248535536Iteration: 537, Loss: 5.5605854988098145537Iteration: 538, Loss: 5.338362216949463538Iteration: 539, Loss: 5.957266807556152539Iteration: 540, Loss: 5.2715229988098145540Iteration: 541, Loss: 4.77555513381958541Iteration: 542, Loss: 5.781469821929932542Iteration: 543, Loss: 5.052041530609131543Iteration: 544, Loss: 4.827467918395996544Iteration: 545, Loss: 5.353562355041504545Iteration: 546, Loss: 4.916378498077393546Iteration: 547, Loss: 6.425590515136719547Iteration: 548, Loss: 4.9753098487854548Iteration: 549, Loss: 5.188260078430176549Iteration: 550, Loss: 4.658123016357422550Iteration: 551, Loss: 4.799177646636963551Iteration: 552, Loss: 5.809119701385498552Iteration: 553, Loss: 5.261131286621094553Iteration: 554, Loss: 5.191847801208496554Iteration: 555, Loss: 4.917084217071533555Iteration: 556, Loss: 4.915203094482422556Iteration: 557, Loss: 5.2854719161987305557Iteration: 558, Loss: 4.548479080200195558Iteration: 559, Loss: 4.750126838684082559Iteration: 560, Loss: 5.604252815246582560Iteration: 561, Loss: 4.427209377288818561Iteration: 562, Loss: 4.904053211212158562Iteration: 563, Loss: 4.828861236572266563Iteration: 564, Loss: 5.353742599487305564Iteration: 565, Loss: 4.636666774749756565Iteration: 566, Loss: 4.535226345062256566Iteration: 567, Loss: 4.978822708129883567Iteration: 568, Loss: 5.911948204040527568Iteration: 569, Loss: 5.989530086517334569Iteration: 570, Loss: 5.638257026672363570Iteration: 571, Loss: 6.310571670532227571Iteration: 572, Loss: 6.4584832191467285572Iteration: 573, Loss: 5.560121059417725573Iteration: 574, Loss: 5.342097282409668574Iteration: 575, Loss: 6.393880367279053575Iteration: 576, Loss: 5.898612022399902576Iteration: 577, Loss: 6.107451438903809577Iteration: 578, Loss: 5.997403144836426578Iteration: 579, Loss: 5.6743364334106445579Iteration: 580, Loss: 5.532434940338135580Iteration: 581, Loss: 5.320373058319092581Iteration: 582, Loss: 5.906468391418457582Iteration: 583, Loss: 5.993997097015381583Iteration: 584, Loss: 5.862972259521484584Iteration: 585, Loss: 5.788580417633057585Iteration: 586, Loss: 5.359506607055664586Iteration: 587, Loss: 5.4089508056640625587Iteration: 588, Loss: 4.740593433380127588Iteration: 589, Loss: 5.491763591766357589Iteration: 590, Loss: 5.393052577972412590Iteration: 591, Loss: 5.3395304679870605591Iteration: 592, Loss: 5.254554748535156592Iteration: 593, Loss: 5.423133850097656593Iteration: 594, Loss: 5.567538261413574594Iteration: 595, Loss: 4.620695114135742595Iteration: 596, Loss: 4.767985820770264596Iteration: 597, Loss: 5.190037727355957597Iteration: 598, Loss: 5.119837284088135598Iteration: 599, Loss: 5.7588605880737305599Iteration: 600, Loss: 5.214957237243652600Iteration: 601, Loss: 5.485315322875977601Iteration: 602, Loss: 5.963164329528809602Iteration: 603, Loss: 5.1960768699646603Iteration: 604, Loss: 5.318953990936279604Iteration: 605, Loss: 5.8173346519470215605Iteration: 606, Loss: 4.906783580780029606Iteration: 607, Loss: 4.993984699249268607Iteration: 608, Loss: 5.574909687042236608Iteration: 609, Loss: 4.414271354675293609Iteration: 610, Loss: 5.295023441314697610Iteration: 611, Loss: 5.912129878997803611Iteration: 612, Loss: 5.800784111022949612Iteration: 613, Loss: 5.39879035949707613Iteration: 614, Loss: 5.294640064239502614Iteration: 615, Loss: 5.427684783935547615Iteration: 616, Loss: 5.015369892120361616Iteration: 617, Loss: 4.889204502105713617Iteration: 618, Loss: 4.830273628234863618Iteration: 619, Loss: 5.104650497436523619Iteration: 620, Loss: 4.665687084197998620Iteration: 621, Loss: 4.915043830871582621Iteration: 622, Loss: 5.2374444007873535622Iteration: 623, Loss: 4.646146297454834623Iteration: 624, Loss: 5.114381790161133624Iteration: 625, Loss: 4.923508167266846625Iteration: 626, Loss: 4.7903289794921875626Iteration: 627, Loss: 4.9853196144104627Iteration: 628, Loss: 4.723362445831299628Iteration: 629, Loss: 4.928465843200684629Iteration: 630, Loss: 4.662862300872803630Iteration: 631, Loss: 4.828316688537598631Iteration: 632, Loss: 4.655803680419922632Iteration: 633, Loss: 4.424772262573242633Iteration: 634, Loss: 4.611084461212158634Iteration: 635, Loss: 4.570537567138672635Iteration: 636, Loss: 3.870482921600342636Iteration: 637, Loss: 4.485755443572998637Iteration: 638, Loss: 5.642794132232666638Iteration: 639, Loss: 5.252090930938721639Iteration: 640, Loss: 6.245862007141113640Iteration: 641, Loss: 6.211639404296875641Iteration: 642, Loss: 6.016371726989746642Iteration: 643, Loss: 6.093167304992676643Iteration: 644, Loss: 6.4858245849609375644Iteration: 645, Loss: 6.308721542358398645Iteration: 646, Loss: 6.154480457305908646Iteration: 647, Loss: 6.060593605041504647Iteration: 648, Loss: 5.876302719116211648Iteration: 649, Loss: 6.162001132965088649Iteration: 650, Loss: 5.94292688369751650Iteration: 651, Loss: 5.970715522766113651Iteration: 652, Loss: 5.87782621383667652Iteration: 653, Loss: 5.431954860687256653Iteration: 654, Loss: 5.288069725036621654Iteration: 655, Loss: 5.3027448654174805655Iteration: 656, Loss: 5.632654190063477656Iteration: 657, Loss: 5.543703556060791657Iteration: 658, Loss: 5.658126354217529658Iteration: 659, Loss: 5.444355487823486659Iteration: 660, Loss: 5.141800880432129660Iteration: 661, Loss: 5.8546953201293945661Iteration: 662, Loss: 5.994268417358398662Iteration: 663, Loss: 5.536617755889893663Iteration: 664, Loss: 5.564896106719971664Iteration: 665, Loss: 5.990903377532959665Iteration: 666, Loss: 5.748326778411865666Iteration: 667, Loss: 5.676361560821533667Iteration: 668, Loss: 5.825193881988525668Iteration: 669, Loss: 5.921685218811035669Iteration: 670, Loss: 5.938249111175537670Iteration: 671, Loss: 5.6031694412231445671Iteration: 672, Loss: 5.217106342315674672Iteration: 673, Loss: 5.6260294914245605673Iteration: 674, Loss: 5.3820977210998535674Iteration: 675, Loss: 5.4872307777404785675Iteration: 676, Loss: 5.182299613952637676Iteration: 677, Loss: 5.444328308105469677Iteration: 678, Loss: 5.4629058837890625678Iteration: 679, Loss: 5.479344367980957679Iteration: 680, Loss: 5.032104969024658680Iteration: 681, Loss: 5.218182563781738681Iteration: 682, Loss: 5.0162858963012695682Iteration: 683, Loss: 6.1266326904296875683Iteration: 684, Loss: 5.560999393463135684Iteration: 685, Loss: 5.128485202789307685Iteration: 686, Loss: 5.139979362487793686Iteration: 687, Loss: 5.7211995124816895687Iteration: 688, Loss: 5.340282917022705688Iteration: 689, Loss: 5.70376443862915689Iteration: 690, Loss: 5.124520301818848690Iteration: 691, Loss: 5.73840856552124691Iteration: 692, Loss: 4.978404521942139692Iteration: 693, Loss: 5.3069610595703125693Iteration: 694, Loss: 5.123588562011719694Iteration: 695, Loss: 4.718210220336914695Iteration: 696, Loss: 5.41464376449585696Iteration: 697, Loss: 4.504172325134277697Iteration: 698, Loss: 5.40156364440918698Iteration: 699, Loss: 5.613332271575928699Iteration: 700, Loss: 4.684786319732666700Iteration: 701, Loss: 4.28521728515625701Iteration: 702, Loss: 4.7745771408081055702Iteration: 703, Loss: 5.12887716293335703Iteration: 704, Loss: 5.595335960388184704Iteration: 705, Loss: 4.86565637588501705Iteration: 706, Loss: 4.461732864379883706Iteration: 707, Loss: 4.497946262359619707Iteration: 708, Loss: 4.376232624053955708Iteration: 709, Loss: 5.035597801208496709Iteration: 710, Loss: 4.922641754150391710Iteration: 711, Loss: 4.476902961730957711Iteration: 712, Loss: 5.440768241882324712Iteration: 713, Loss: 5.180270671844482713Iteration: 714, Loss: 4.7786173820495605714Iteration: 715, Loss: 4.597978591918945715Iteration: 716, Loss: 4.658175468444824716Iteration: 717, Loss: 4.517860412597656717Iteration: 718, Loss: 5.217967510223389718Iteration: 719, Loss: 5.406540393829346719Iteration: 720, Loss: 4.441930294036865720Iteration: 721, Loss: 4.480402946472168721Iteration: 722, Loss: 5.629583358764648722Iteration: 723, Loss: 5.191711902618408723Iteration: 724, Loss: 4.494837284088135724Iteration: 725, Loss: 4.733370304107666725Iteration: 726, Loss: 5.74600076675415726Iteration: 727, Loss: 5.59882116317749727Iteration: 728, Loss: 4.959428310394287728Iteration: 729, Loss: 5.492926597595215729Iteration: 730, Loss: 4.849294185638428730Iteration: 731, Loss: 4.717833518981934731Iteration: 732, Loss: 4.7213239669799805732Iteration: 733, Loss: 4.922951698303223733Iteration: 734, Loss: 4.684055805206299734Iteration: 735, Loss: 5.298535346984863735Iteration: 736, Loss: 5.134542942047119736Iteration: 737, Loss: 4.792236804962158737Iteration: 738, Loss: 4.395248889923096738Iteration: 739, Loss: 5.229986190795898739Iteration: 740, Loss: 5.367891311645508740Iteration: 741, Loss: 4.996557235717773741Iteration: 742, Loss: 5.489526748657227742Iteration: 743, Loss: 5.096949577331543743Iteration: 744, Loss: 5.499503135681152744Iteration: 745, Loss: 5.575303554534912745Iteration: 746, Loss: 4.738057613372803746Iteration: 747, Loss: 5.202676296234131747Iteration: 748, Loss: 5.17632532119751748Iteration: 749, Loss: 5.143235206604004749Iteration: 750, Loss: 5.140250205993652750Iteration: 751, Loss: 4.760838985443115751Iteration: 752, Loss: 5.076111793518066752Iteration: 753, Loss: 6.103909969329834753Iteration: 754, Loss: 5.5591721534729754Iteration: 755, Loss: 5.55359411239624755Iteration: 756, Loss: 5.327295780181885756Iteration: 757, Loss: 5.6996893882751465757Iteration: 758, Loss: 5.63177490234375758Iteration: 759, Loss: 5.337080001831055759Iteration: 760, Loss: 4.912563323974609760Iteration: 761, Loss: 5.056389808654785761Iteration: 762, Loss: 4.7606892585754395762Iteration: 763, Loss: 5.060219764709473763Iteration: 764, Loss: 5.409912586212158764Iteration: 765, Loss: 5.252354621887207765Iteration: 766, Loss: 5.298149108886719766Iteration: 767, Loss: 4.970165729522705767Iteration: 768, Loss: 4.83400821685791768Iteration: 769, Loss: 5.152285575866699769Iteration: 770, Loss: 5.150280952453613770Iteration: 771, Loss: 4.921036720275879771Iteration: 772, Loss: 4.999067306518555772Iteration: 773, Loss: 4.84515380859375773Iteration: 774, Loss: 5.234988212585449774Iteration: 775, Loss: 5.857335090637207775Iteration: 776, Loss: 5.154032230377197776Iteration: 777, Loss: 5.452803134918213777Iteration: 778, Loss: 4.759232044219971778Iteration: 779, Loss: 5.191748142242432779Iteration: 780, Loss: 4.6056742668151855780Iteration: 781, Loss: 4.9111480712890625781Iteration: 782, Loss: 4.988877773284912782Iteration: 783, Loss: 4.9169464111328125783Iteration: 784, Loss: 5.254184246063232784Iteration: 785, Loss: 4.9828996658325195785Iteration: 786, Loss: 5.121694087982178786Iteration: 787, Loss: 5.217060565948486787Iteration: 788, Loss: 5.227149486541748788Iteration: 789, Loss: 4.799383640289307789Iteration: 790, Loss: 5.1415557861328125790Iteration: 791, Loss: 4.936748504638672791Iteration: 792, Loss: 4.731064796447754792Iteration: 793, Loss: 4.985180377960205793Iteration: 794, Loss: 5.219829082489014794Iteration: 795, Loss: 4.57879114151001795Iteration: 796, Loss: 4.413763523101807796Iteration: 797, Loss: 4.886512756347656797Iteration: 798, Loss: 4.720084190368652798Iteration: 799, Loss: 5.0612688064575195799Iteration: 800, Loss: 4.830511569976807800Iteration: 801, Loss: 4.647517204284668801Iteration: 802, Loss: 4.899204254150391802Iteration: 803, Loss: 4.421438217163086803Iteration: 804, Loss: 4.9686784744262695804Iteration: 805, Loss: 5.140814781188965805Iteration: 806, Loss: 4.812811851501465806Iteration: 807, Loss: 5.149649620056152807Iteration: 808, Loss: 5.275010108947754808Iteration: 809, Loss: 5.200407981872559809Iteration: 810, Loss: 4.672547340393066810Iteration: 811, Loss: 5.182009220123291811Iteration: 812, Loss: 5.285711288452148812Iteration: 813, Loss: 5.116220474243164813Iteration: 814, Loss: 4.65631103515625814Iteration: 815, Loss: 4.882637023925781815Iteration: 816, Loss: 5.294802665710449816Iteration: 817, Loss: 4.977978706359863817Iteration: 818, Loss: 5.222915172576904818Iteration: 819, Loss: 5.062192440032959819Iteration: 820, Loss: 4.43284797668457820Iteration: 821, Loss: 5.5927252769470215821Iteration: 822, Loss: 5.403996467590332822Iteration: 823, Loss: 5.297943115234375823Iteration: 824, Loss: 5.414769172668457824Iteration: 825, Loss: 5.410807132720947825Iteration: 826, Loss: 4.4687180519104826Iteration: 827, Loss: 4.803441047668457827Iteration: 828, Loss: 4.649642467498779828Iteration: 829, Loss: 4.195302486419678829Iteration: 830, Loss: 4.472550868988037830Iteration: 831, Loss: 5.449754238128662831Iteration: 832, Loss: 3.6177287101745605832Iteration: 833, Loss: 4.493494510650635833Iteration: 834, Loss: 4.5746660232543945834Iteration: 835, Loss: 4.556402683258057835Iteration: 836, Loss: 4.739713668823242836Iteration: 837, Loss: 5.303156852722168837Iteration: 838, Loss: 5.680971622467041838Iteration: 839, Loss: 5.4112019538879395839Iteration: 840, Loss: 5.409489154815674840Iteration: 841, Loss: 4.713760852813721841Iteration: 842, Loss: 5.415802955627441842Iteration: 843, Loss: 5.178596496582031843Iteration: 844, Loss: 5.316206932067871844Iteration: 845, Loss: 4.944616317749023845Iteration: 846, Loss: 4.957474708557129846Iteration: 847, Loss: 5.426403999328613847Iteration: 848, Loss: 5.421308994293213848Iteration: 849, Loss: 5.601507186889648849Iteration: 850, Loss: 5.543405055999756850Iteration: 851, Loss: 5.369035720825195851Iteration: 852, Loss: 5.579522609710693852Iteration: 853, Loss: 5.561617374420166853Iteration: 854, Loss: 5.46715784072876854Iteration: 855, Loss: 5.134836673736572855Iteration: 856, Loss: 5.312839031219482856Iteration: 857, Loss: 5.297892093658447857Iteration: 858, Loss: 5.7094855308532715858Iteration: 859, Loss: 5.236093044281006859Iteration: 860, Loss: 5.209606170654297860Iteration: 861, Loss: 4.918812274932861861Iteration: 862, Loss: 5.3252482414245605862Iteration: 863, Loss: 5.508021354675293863Iteration: 864, Loss: 5.401193141937256864Iteration: 865, Loss: 5.85665225982666865Iteration: 866, Loss: 5.022864818572998866Iteration: 867, Loss: 5.24431037902832867Iteration: 868, Loss: 5.167258262634277868Iteration: 869, Loss: 5.161757946014404869Iteration: 870, Loss: 5.385096549987793870Iteration: 871, Loss: 5.599978446960449871Iteration: 872, Loss: 5.517195224761963872Iteration: 873, Loss: 5.2667236328125873Iteration: 874, Loss: 5.114016532897949874Iteration: 875, Loss: 5.254546642303467875Iteration: 876, Loss: 5.049236297607422876Iteration: 877, Loss: 4.914315700531006877Iteration: 878, Loss: 4.951077461242676878Iteration: 879, Loss: 5.136532306671143879Iteration: 880, Loss: 5.311972141265869880Iteration: 881, Loss: 5.131547927856445881Iteration: 882, Loss: 5.40075159072876882Iteration: 883, Loss: 5.509274959564209883Iteration: 884, Loss: 5.556529998779297884Iteration: 885, Loss: 5.483212471008301885Iteration: 886, Loss: 5.477928161621094886Iteration: 887, Loss: 4.796082973480225887Iteration: 888, Loss: 5.106568813323975888Iteration: 889, Loss: 5.570615768432617889Iteration: 890, Loss: 5.144264221191406890Iteration: 891, Loss: 5.270713806152344891Iteration: 892, Loss: 4.450285911560059892Iteration: 893, Loss: 5.3470139503479893Iteration: 894, Loss: 5.450132369995117894Iteration: 895, Loss: 5.024446487426758895Iteration: 896, Loss: 4.92164945602417896Iteration: 897, Loss: 5.253388404846191897Iteration: 898, Loss: 5.189298152923584898Iteration: 899, Loss: 5.142160892486572899Iteration: 900, Loss: 4.795007228851318900Iteration: 901, Loss: 5.261613368988037901Iteration: 902, Loss: 4.716215133666992902Iteration: 903, Loss: 4.29185152053833903Iteration: 904, Loss: 5.216892242431641904Iteration: 905, Loss: 5.298376560211182905Iteration: 906, Loss: 4.796523571014404906Iteration: 907, Loss: 5.255432605743408907Iteration: 908, Loss: 4.129613876342773908Iteration: 909, Loss: 4.080851078033447909Iteration: 910, Loss: 4.6469011306762695910Iteration: 911, Loss: 3.989063024520874911Iteration: 912, Loss: 4.960813522338867912Iteration: 913, Loss: 4.750061988830566913Iteration: 914, Loss: 4.683300018310547914Iteration: 915, Loss: 5.504064559936523915Iteration: 916, Loss: 5.535990238189697916Iteration: 917, Loss: 5.021008491516113917Iteration: 918, Loss: 5.064034938812256918Iteration: 919, Loss: 5.3962297439575195919Iteration: 920, Loss: 5.20798921585083920Iteration: 921, Loss: 5.415538311004639921Iteration: 922, Loss: 5.775729179382324922Iteration: 923, Loss: 5.234016418457031923Iteration: 924, Loss: 5.222485065460205924Iteration: 925, Loss: 5.488558769226074925Iteration: 926, Loss: 5.768907070159912926Iteration: 927, Loss: 5.264004707336426927Iteration: 928, Loss: 5.1745524406433105928Iteration: 929, Loss: 5.429603576660156929Iteration: 930, Loss: 5.162397384643555930Iteration: 931, Loss: 5.1418609619140625931Iteration: 932, Loss: 4.937302112579346932Iteration: 933, Loss: 6.100217819213867933Iteration: 934, Loss: 5.508360385894775934Iteration: 935, Loss: 5.1105637550354935Iteration: 936, Loss: 4.881490707397461936Iteration: 937, Loss: 4.595038414001465937Iteration: 938, Loss: 4.87841796875938Iteration: 939, Loss: 5.469422817230225939Iteration: 940, Loss: 5.097489833831787940Iteration: 941, Loss: 4.829648017883301941Iteration: 942, Loss: 4.994056701660156942Iteration: 943, Loss: 4.5927886962890625943Iteration: 944, Loss: 4.667985439300537944Iteration: 945, Loss: 6.141078948974609945Iteration: 946, Loss: 5.283452987670898946Iteration: 947, Loss: 4.7512922286987305947Iteration: 948, Loss: 5.801706790924072948Iteration: 949, Loss: 4.768344402313232949Iteration: 950, Loss: 4.505396842956543950Iteration: 951, Loss: 4.960529327392578951Iteration: 952, Loss: 4.8130083084106445952Iteration: 953, Loss: 5.285974025726318953Iteration: 954, Loss: 4.764886856079102954Iteration: 955, Loss: 5.129539489746094955Iteration: 956, Loss: 4.940432071685791956Iteration: 957, Loss: 5.288727283477783957Iteration: 958, Loss: 4.791271686553955958Iteration: 959, Loss: 4.995933532714844959Iteration: 960, Loss: 4.608998775482178960Iteration: 961, Loss: 5.586217403411865961Iteration: 962, Loss: 5.341586589813232962Iteration: 963, Loss: 4.875980854034424963Iteration: 964, Loss: 5.323189735412598964Iteration: 965, Loss: 5.028912544250488965Iteration: 966, Loss: 5.235151290893555966Iteration: 967, Loss: 4.9287028312683105967Iteration: 968, Loss: 4.8131327629089355968Iteration: 969, Loss: 5.35591983795166969Iteration: 970, Loss: 4.763430595397949970Iteration: 971, Loss: 5.014503002166748971Iteration: 972, Loss: 4.70588493347168972Iteration: 973, Loss: 4.380824089050293973Iteration: 974, Loss: 4.681766986846924974Iteration: 975, Loss: 5.098120212554932975Iteration: 976, Loss: 4.928041934967041976Iteration: 977, Loss: 4.54606294631958977Iteration: 978, Loss: 4.56408166885376978Iteration: 979, Loss: 4.511712074279785979Iteration: 980, Loss: 5.500552654266357980Iteration: 981, Loss: 4.912964344024658981Iteration: 982, Loss: 4.695742607116699982Iteration: 983, Loss: 4.920217037200928983Iteration: 984, Loss: 4.797123908996582984Iteration: 985, Loss: 4.51774263381958985Iteration: 986, Loss: 4.8468122482299805986Iteration: 987, Loss: 5.245523929595947987Iteration: 988, Loss: 5.489053249359131988Iteration: 989, Loss: 5.165535926818848989Iteration: 990, Loss: 5.836493015289307990Iteration: 991, Loss: 4.966404438018799991Iteration: 992, Loss: 5.388394832611084992Iteration: 993, Loss: 4.892366409301758993Iteration: 994, Loss: 5.49268102645874994Iteration: 995, Loss: 4.631957530975342995Iteration: 996, Loss: 4.902523994445801996Iteration: 997, Loss: 4.9452738761901855997Iteration: 998, Loss: 5.217776298522949998Iteration: 999, Loss: 4.872873783111572999Iteration: 1000, Loss: 5.3472313880920411000Iteration: 1001, Loss: 5.3573842048645021001Iteration: 1002, Loss: 4.98228454589843751002Iteration: 1003, Loss: 5.0061130523681641003Iteration: 1004, Loss: 4.9365906715393071004Iteration: 1005, Loss: 4.814556598663331005Iteration: 1006, Loss: 4.97431230545043951006Iteration: 1007, Loss: 4.7140517234802251007Iteration: 1008, Loss: 4.8920311927795411008Iteration: 1009, Loss: 4.94383001327514651009Iteration: 1010, Loss: 5.0140666961669921010Iteration: 1011, Loss: 5.4426994323730471011Iteration: 1012, Loss: 5.2380409240722661012Iteration: 1013, Loss: 5.0676565170288091013Iteration: 1014, Loss: 5.6339821815490721014Iteration: 1015, Loss: 4.9120926856994631015Iteration: 1016, Loss: 5.4572811126708981016Iteration: 1017, Loss: 5.358318805694581017Iteration: 1018, Loss: 5.3030490875244141018Iteration: 1019, Loss: 5.1041507720947271019Iteration: 1020, Loss: 5.1413850784301761020Iteration: 1021, Loss: 5.3087463378906251021Iteration: 1022, Loss: 4.7248916625976561022Iteration: 1023, Loss: 4.3402385711669921023Iteration: 1024, Loss: 4.6718716621398931024Iteration: 1025, Loss: 5.0867033004760741025Iteration: 1026, Loss: 5.04799127578735351026Iteration: 1027, Loss: 5.0572414398193361027Iteration: 1028, Loss: 5.7122797966003421028Iteration: 1029, Loss: 5.0661969184875491029Iteration: 1030, Loss: 4.8202395439147951030Iteration: 1031, Loss: 5.2350416183471681031Iteration: 1032, Loss: 4.7955527305603031032Iteration: 1033, Loss: 5.0321011543273931033Iteration: 1034, Loss: 5.0611715316772461034Iteration: 1035, Loss: 4.5179896354675291035Iteration: 1036, Loss: 4.6584305763244631036Iteration: 1037, Loss: 4.4043745994567871037Iteration: 1038, Loss: 4.6285252571105961038Iteration: 1039, Loss: 4.5001969337463381039Iteration: 1040, Loss: 5.3840737342834471040Iteration: 1041, Loss: 5.3923807144165041041Iteration: 1042, Loss: 5.0188221931457521042Iteration: 1043, Loss: 5.43031787872314451043Iteration: 1044, Loss: 5.05241632461547851044Iteration: 1045, Loss: 4.8959155082702641045Iteration: 1046, Loss: 5.0972628593444821046Iteration: 1047, Loss: 4.7369742393493651047Iteration: 1048, Loss: 4.613530635833741048Iteration: 1049, Loss: 4.9719872474670411049Iteration: 1050, Loss: 4.7697815895080571050Iteration: 1051, Loss: 5.0120706558227541051Iteration: 1052, Loss: 4.9636411666870121052Iteration: 1053, Loss: 4.8383827209472661053Iteration: 1054, Loss: 4.6409850120544431054Iteration: 1055, Loss: 4.9936051368713381055Iteration: 1056, Loss: 4.7918772697448731056Iteration: 1057, Loss: 4.6589770317077641057Iteration: 1058, Loss: 4.8924160003662111058Iteration: 1059, Loss: 4.6909689903259281059Iteration: 1060, Loss: 4.67722606658935551060Iteration: 1061, Loss: 4.9958386421203611061Iteration: 1062, Loss: 5.1852402687072751062Iteration: 1063, Loss: 4.4720144271850591063Iteration: 1064, Loss: 4.5176529884338381064Iteration: 1065, Loss: 4.6879057884216311065Iteration: 1066, Loss: 4.9801611900329591066Iteration: 1067, Loss: 4.8936862945556641067Iteration: 1068, Loss: 5.4779739379882811068Iteration: 1069, Loss: 4.8995394706726071069Iteration: 1070, Loss: 4.6107444763183591070Iteration: 1071, Loss: 4.2137598991394041071Iteration: 1072, Loss: 4.3665628433227541072Iteration: 1073, Loss: 4.8434538841247561073Iteration: 1074, Loss: 5.0857453346252441074Iteration: 1075, Loss: 5.3787937164306641075Iteration: 1076, Loss: 5.1476092338562011076Iteration: 1077, Loss: 6.0920925140380861077Iteration: 1078, Loss: 5.4826159477233891078Iteration: 1079, Loss: 5.5679688453674321079Iteration: 1080, Loss: 5.4045906066894531080Iteration: 1081, Loss: 5.6613588333129881081Iteration: 1082, Loss: 5.2973241806030271082Iteration: 1083, Loss: 5.4427142143249511083Iteration: 1084, Loss: 5.3046312332153321084Iteration: 1085, Loss: 5.6415586471557621085Iteration: 1086, Loss: 5.378362178802491086Iteration: 1087, Loss: 5.05881786346435551087Iteration: 1088, Loss: 4.9018726348876951088Iteration: 1089, Loss: 5.41662597656251089Iteration: 1090, Loss: 4.7166318893432621090Iteration: 1091, Loss: 5.0155963897705081091Iteration: 1092, Loss: 5.29206609725952151092Iteration: 1093, Loss: 5.0218124389648441093Iteration: 1094, Loss: 5.1678371429443361094Iteration: 1095, Loss: 5.1735424995422361095Iteration: 1096, Loss: 5.4626960754394531096Iteration: 1097, Loss: 5.0310392379760741097Iteration: 1098, Loss: 4.84565734863281251098Iteration: 1099, Loss: 4.8053293228149411099Iteration: 1100, Loss: 4.9920024871826171100Iteration: 1101, Loss: 4.8078646659851071101Iteration: 1102, Loss: 5.1976642608642581102Iteration: 1103, Loss: 5.4078059196472171103Iteration: 1104, Loss: 5.1364707946777341104Iteration: 1105, Loss: 5.1491227149963381105Iteration: 1106, Loss: 4.665033817291261106Iteration: 1107, Loss: 5.4571285247802731107Iteration: 1108, Loss: 5.22786188125610351108Iteration: 1109, Loss: 4.949815750122071109Iteration: 1110, Loss: 5.72566223144531251110Iteration: 1111, Loss: 5.9019255638122561111Iteration: 1112, Loss: 5.4023170471191411112Iteration: 1113, Loss: 5.56467485427856451113Iteration: 1114, Loss: 5.65595769882202151114Iteration: 1115, Loss: 5.8324165344238281115Iteration: 1116, Loss: 5.53749084472656251116Iteration: 1117, Loss: 5.2138071060180661117Iteration: 1118, Loss: 5.1369624137878421118Iteration: 1119, Loss: 5.3786697387695311119Iteration: 1120, Loss: 5.40202808380126951120Iteration: 1121, Loss: 5.6377315521240231121Iteration: 1122, Loss: 5.0612087249755861122Iteration: 1123, Loss: 5.6911983489990231123Iteration: 1124, Loss: 5.5399737358093261124Iteration: 1125, Loss: 5.1560320854187011125Iteration: 1126, Loss: 4.8710556030273441126Iteration: 1127, Loss: 5.43571233749389651127Iteration: 1128, Loss: 4.7189264297485351128Iteration: 1129, Loss: 4.7450094223022461129Iteration: 1130, Loss: 5.3239493370056151130Iteration: 1131, Loss: 5.0232276916503911131Iteration: 1132, Loss: 4.9427204132080081132Iteration: 1133, Loss: 5.0964312553405761133Iteration: 1134, Loss: 5.5105690956115721134Iteration: 1135, Loss: 4.7089042663574221135Iteration: 1136, Loss: 4.81906938552856451136Iteration: 1137, Loss: 4.699223995208741137Iteration: 1138, Loss: 4.7842984199523931138Iteration: 1139, Loss: 5.62611389160156251139Iteration: 1140, Loss: 4.8107690811157231140Iteration: 1141, Loss: 5.220074176788331141Iteration: 1142, Loss: 4.8090558052062991142Iteration: 1143, Loss: 5.0332717895507811143Iteration: 1144, Loss: 5.26154851913452151144Iteration: 1145, Loss: 5.1491451263427731145Iteration: 1146, Loss: 4.7649369239807131146Iteration: 1147, Loss: 5.5182142257690431147Iteration: 1148, Loss: 5.8166947364807131148Iteration: 1149, Loss: 5.7106094360351561149Iteration: 1150, Loss: 4.9448804855346681150Iteration: 1151, Loss: 4.5931744575500491151Iteration: 1152, Loss: 5.0581459999084471152Iteration: 1153, Loss: 4.6290225982666021153Iteration: 1154, Loss: 4.8963451385498051154Iteration: 1155, Loss: 5.2330589294433591155Iteration: 1156, Loss: 5.4435229301452641156Iteration: 1157, Loss: 5.0447783470153811157Iteration: 1158, Loss: 4.9699673652648931158Iteration: 1159, Loss: 5.1442370414733891159Iteration: 1160, Loss: 5.2561993598937991160Iteration: 1161, Loss: 5.2167992591857911161Iteration: 1162, Loss: 5.3104968070983891162Iteration: 1163, Loss: 5.51008605957031251163Iteration: 1164, Loss: 5.1596193313598631164Iteration: 1165, Loss: 5.3928313255310061165Iteration: 1166, Loss: 5.108544349670411166Iteration: 1167, Loss: 5.0874204635620121167Iteration: 1168, Loss: 4.8905673027038571168Iteration: 1169, Loss: 4.8899674415588381169Iteration: 1170, Loss: 4.4562640190124511170Iteration: 1171, Loss: 4.9448590278625491171Iteration: 1172, Loss: 4.7719125747680661172Iteration: 1173, Loss: 4.7292494773864751173Iteration: 1174, Loss: 4.4811344146728521174Iteration: 1175, Loss: 4.2636256217956541175Iteration: 1176, Loss: 4.6916146278381351176Iteration: 1177, Loss: 5.0543460845947271177Iteration: 1178, Loss: 4.9853415489196781178Iteration: 1179, Loss: 4.5932526588439941179Iteration: 1180, Loss: 5.1726741790771481180Iteration: 1181, Loss: 4.6476516723632811181Iteration: 1182, Loss: 4.568468093872071182Iteration: 1183, Loss: 4.62581110000610351183Iteration: 1184, Loss: 4.9727683067321781184Iteration: 1185, Loss: 5.4683394432067871185Iteration: 1186, Loss: 4.4119248390197751186Iteration: 1187, Loss: 4.895146846771241187Iteration: 1188, Loss: 4.9730138778686521188Iteration: 1189, Loss: 4.65769481658935551189Iteration: 1190, Loss: 5.3681426048278811190Iteration: 1191, Loss: 5.4840135574340821191Iteration: 1192, Loss: 4.9933853149414061192Iteration: 1193, Loss: 4.9915404319763181193Iteration: 1194, Loss: 4.3436622619628911194Iteration: 1195, Loss: 4.8054523468017581195Iteration: 1196, Loss: 4.5099973678588871196Iteration: 1197, Loss: 5.0767564773559571197Iteration: 1198, Loss: 4.9210853576660161198Iteration: 1199, Loss: 5.4447507858276371199Iteration: 1200, Loss: 4.7145404815673831200Iteration: 1201, Loss: 4.250975131988525

Showing the first 1,200 of 5010 lines. Download the file for the rest.