{"step": 500, "train_loss": 0.1946495920419693, "eval_loss": 0.07109163387212902} {"step": 1000, "train_loss": 0.09101558476686478, "eval_loss": 0.05554991273675114} {"step": 1500, "train_loss": 0.18652863800525665, "eval_loss": 0.06880444183479995} {"step": 2000, "train_loss": 0.33225923776626587, "eval_loss": 0.056894342123996466} {"step": 2500, "train_loss": 0.08416622877120972, "eval_loss": 0.08017167903017253} {"step": 3000, "train_loss": 0.25614333152770996, "eval_loss": 0.05898368632188067} {"step": 3500, "train_loss": 0.061469320207834244, "eval_loss": 0.0491273197112605} {"step": 4000, "train_loss": 0.09703326970338821, "eval_loss": 0.05483939283294603} {"step": 4500, "train_loss": 0.07521650195121765, "eval_loss": 0.061710105335805565} {"step": 5000, "train_loss": 0.17555245757102966, "eval_loss": 0.05175293510546908} {"step": 5500, "train_loss": 0.17540951073169708, "eval_loss": 0.04613059916300699} {"step": 6000, "train_loss": 0.1462906002998352, "eval_loss": 0.05436985206324607} {"step": 6500, "train_loss": 0.04713481292128563, "eval_loss": 0.04921753564849496} {"step": 7000, "train_loss": 0.06472743302583694, "eval_loss": 0.04851211403729394} {"step": 7500, "train_loss": 0.10775092989206314, "eval_loss": 0.045239445520564914} {"step": 8000, "train_loss": 0.20834073424339294, "eval_loss": 0.046097903803456575} {"step": 8500, "train_loss": 0.08387970924377441, "eval_loss": 0.0487001245492138} {"step": 9000, "train_loss": 0.07011547684669495, "eval_loss": 0.03903620288474485} {"step": 9500, "train_loss": 0.047908976674079895, "eval_loss": 0.049733122752513736} {"step": 10000, "train_loss": 0.20336748659610748, "eval_loss": 0.045883785584010184} {"step": 10500, "train_loss": 0.16467736661434174, "eval_loss": 0.03667152998968959} {"step": 11000, "train_loss": 0.35470542311668396, "eval_loss": 0.0474567546043545} {"step": 11500, "train_loss": 0.05843719467520714, "eval_loss": 0.04514552856562659} {"step": 12000, "train_loss": 0.21963396668434143, "eval_loss": 0.04305144364479929} {"step": 12500, "train_loss": 0.11375381052494049, "eval_loss": 0.04996872425545007} {"step": 13000, "train_loss": 0.05538409203290939, "eval_loss": 0.04576564021408558} {"step": 13500, "train_loss": 0.22080650925636292, "eval_loss": 0.04235259955748916} {"step": 14000, "train_loss": 0.057978007942438126, "eval_loss": 0.041589350963477045} {"step": 14500, "train_loss": 0.11194933950901031, "eval_loss": 0.04368015530053526} {"step": 15000, "train_loss": 0.11150765419006348, "eval_loss": 0.04596609401050955} {"step": 15500, "train_loss": 0.13844957947731018, "eval_loss": 0.04991376819089055} {"step": 16000, "train_loss": 0.04531491920351982, "eval_loss": 0.04390412394423038} {"step": 16500, "train_loss": 0.08435271680355072, "eval_loss": 0.0482354701962322} {"step": 17000, "train_loss": 0.0428524985909462, "eval_loss": 0.039364590775221586} {"step": 17500, "train_loss": 0.11203644424676895, "eval_loss": 0.04289573535788804} {"step": 18000, "train_loss": 0.11682510375976562, "eval_loss": 0.04658813652349636} {"step": 18500, "train_loss": 0.1386266052722931, "eval_loss": 0.046255224966444075} {"step": 19000, "train_loss": 0.1526791751384735, "eval_loss": 0.038971403206232935} {"step": 19500, "train_loss": 0.19892887771129608, "eval_loss": 0.0442722924053669} {"step": 20000, "train_loss": 0.19688770174980164, "eval_loss": 0.04827071714680642} {"step": 20500, "train_loss": 0.10974899679422379, "eval_loss": 0.04250343190506101} {"step": 21000, "train_loss": 0.11360359191894531, "eval_loss": 0.04189024865627289} {"step": 21500, "train_loss": 0.060086317360401154, "eval_loss": 0.04346604726742953} {"step": 22000, "train_loss": 0.055203378200531006, "eval_loss": 0.048284505086485296} {"step": 22500, "train_loss": 0.10940107703208923, "eval_loss": 0.04722560930531472} {"step": 23000, "train_loss": 0.20880697667598724, "eval_loss": 0.040150139888282865} {"step": 23500, "train_loss": 0.047077011317014694, "eval_loss": 0.04222206474514678} {"step": 24000, "train_loss": 0.055998582392930984, "eval_loss": 0.038588422001339495} {"step": 24500, "train_loss": 0.04707362502813339, "eval_loss": 0.040450805972795933} {"step": 25000, "train_loss": 0.05415862426161766, "eval_loss": 0.04518546140752733} {"step": 25500, "train_loss": 0.04466772451996803, "eval_loss": 0.041960375383496284} {"step": 26000, "train_loss": 0.047442760318517685, "eval_loss": 0.041288824228104204} {"step": 26500, "train_loss": 0.07749441266059875, "eval_loss": 0.040526216849684715} {"step": 27000, "train_loss": 0.049805015325546265, "eval_loss": 0.0405997151392512} {"step": 27500, "train_loss": 0.06138203665614128, "eval_loss": 0.04312202491564676} {"step": 28000, "train_loss": 0.06336996704339981, "eval_loss": 0.041970121557824314} {"step": 28500, "train_loss": 0.13162612915039062, "eval_loss": 0.041932177904527634} {"step": 29000, "train_loss": 0.19776515662670135, "eval_loss": 0.04239444260019809} {"step": 29500, "train_loss": 0.055390965193510056, "eval_loss": 0.04474343446781859} {"step": 30000, "train_loss": 0.20276692509651184, "eval_loss": 0.04023544385563582} {"step": 30500, "train_loss": 0.05050289258360863, "eval_loss": 0.043537743913475424} {"step": 31000, "train_loss": 0.04587681591510773, "eval_loss": 0.042651940311770886} {"step": 31500, "train_loss": 0.04883340001106262, "eval_loss": 0.04098044254351407} {"step": 32000, "train_loss": 0.17418494820594788, "eval_loss": 0.041513879608828574} {"step": 32500, "train_loss": 0.041482873260974884, "eval_loss": 0.03873369318898767} {"step": 33000, "train_loss": 0.046806495636701584, "eval_loss": 0.04372621717629954} {"step": 33500, "train_loss": 0.19478115439414978, "eval_loss": 0.040723936865106225} {"step": 34000, "train_loss": 0.20759014785289764, "eval_loss": 0.0441884258762002} {"step": 34500, "train_loss": 0.05139554291963577, "eval_loss": 0.041649938677437603} {"step": 35000, "train_loss": 0.16587024927139282, "eval_loss": 0.040994381764903665} {"step": 35500, "train_loss": 0.043808627873659134, "eval_loss": 0.03701842238660902} {"step": 36000, "train_loss": 0.037069570273160934, "eval_loss": 0.04319516313262284} {"step": 36500, "train_loss": 0.057296279817819595, "eval_loss": 0.03917533386265859} {"step": 37000, "train_loss": 0.04922749474644661, "eval_loss": 0.04055382666410878} {"step": 37500, "train_loss": 0.0488775335252285, "eval_loss": 0.04566936584888026} {"step": 38000, "train_loss": 0.17206646502017975, "eval_loss": 0.03982914373045787} {"step": 38500, "train_loss": 0.15054038166999817, "eval_loss": 0.041001487581525} {"step": 39000, "train_loss": 0.05246828868985176, "eval_loss": 0.04428976698545739} {"step": 39500, "train_loss": 0.09489425271749496, "eval_loss": 0.04304866446182132} {"step": 40000, "train_loss": 0.16150595247745514, "eval_loss": 0.04063120059436187} {"step": 40500, "train_loss": 0.09125489741563797, "eval_loss": 0.04261542187305167} {"step": 41000, "train_loss": 0.04630933701992035, "eval_loss": 0.0392384777078405} {"step": 41500, "train_loss": 0.13537681102752686, "eval_loss": 0.04141834541223943} {"step": 42000, "train_loss": 0.0828075036406517, "eval_loss": 0.04458493954734877} {"step": 42500, "train_loss": 0.051012299954891205, "eval_loss": 0.042966521403286606} {"step": 43000, "train_loss": 0.19184324145317078, "eval_loss": 0.044349907082505524} {"step": 43500, "train_loss": 0.05028413608670235, "eval_loss": 0.04033082153182477} {"step": 44000, "train_loss": 0.05724010989069939, "eval_loss": 0.042173117166385055} {"step": 44500, "train_loss": 0.04310576245188713, "eval_loss": 0.04372378753032535} {"step": 45000, "train_loss": 0.08490516245365143, "eval_loss": 0.042356434802059084} {"step": 45500, "train_loss": 0.07653524726629257, "eval_loss": 0.038796579698100686} {"step": 46000, "train_loss": 0.1549132913351059, "eval_loss": 0.03918709995923564} {"step": 46500, "train_loss": 0.04469612240791321, "eval_loss": 0.04086829553125426} {"step": 47000, "train_loss": 0.05447040870785713, "eval_loss": 0.04171563469571993} {"step": 47500, "train_loss": 0.1761266142129898, "eval_loss": 0.03854676446644589} {"step": 48000, "train_loss": 0.17536315321922302, "eval_loss": 0.03885211067972705} {"step": 48500, "train_loss": 0.08636154979467392, "eval_loss": 0.040809341822750866} {"step": 49000, "train_loss": 0.20343148708343506, "eval_loss": 0.037756266130600125} {"step": 49500, "train_loss": 0.13832034170627594, "eval_loss": 0.04082292487146333} {"step": 50000, "train_loss": 0.1316085010766983, "eval_loss": 0.04258840094553307} {"step": 50500, "train_loss": 0.06307778507471085, "eval_loss": 0.04069256398361176} {"step": 51000, "train_loss": 0.04110788181424141, "eval_loss": 0.043268439010716975} {"step": 51500, "train_loss": 0.054394982755184174, "eval_loss": 0.04125195642700419} {"step": 52000, "train_loss": 0.04094891995191574, "eval_loss": 0.04263281129533425} {"step": 52500, "train_loss": 0.1621224582195282, "eval_loss": 0.039585176040418446} {"step": 53000, "train_loss": 0.08138779550790787, "eval_loss": 0.04212860786356032} {"step": 53500, "train_loss": 0.04134226217865944, "eval_loss": 0.044035256025381386} {"step": 54000, "train_loss": 0.16133247315883636, "eval_loss": 0.03916054964065552} {"step": 54500, "train_loss": 0.20840421319007874, "eval_loss": 0.03971569600980729} {"step": 55000, "train_loss": 0.14440304040908813, "eval_loss": 0.040890168747864664} {"step": 55500, "train_loss": 0.0526202991604805, "eval_loss": 0.040660134865902364} {"step": 56000, "train_loss": 0.13709449768066406, "eval_loss": 0.03786621202016249} {"step": 56500, "train_loss": 0.03918236494064331, "eval_loss": 0.04035887500504032} {"step": 57000, "train_loss": 0.17055237293243408, "eval_loss": 0.042973372736014426} {"step": 57500, "train_loss": 0.048342619091272354, "eval_loss": 0.03971305297454819} {"step": 58000, "train_loss": 0.04882567375898361, "eval_loss": 0.043074010231066495} {"step": 58500, "train_loss": 0.07903209328651428, "eval_loss": 0.04072413616813719} {"step": 59000, "train_loss": 0.04064828157424927, "eval_loss": 0.04001344577409327} {"step": 59500, "train_loss": 0.09160736203193665, "eval_loss": 0.04281495517352596} {"step": 60000, "train_loss": 0.08791781216859818, "eval_loss": 0.03931670117890462} {"step": 60500, "train_loss": 0.12772460281848907, "eval_loss": 0.04121816920815036} {"step": 61000, "train_loss": 0.19262759387493134, "eval_loss": 0.04153191053774208} {"step": 61500, "train_loss": 0.08969896286725998, "eval_loss": 0.04095127555774525} {"step": 62000, "train_loss": 0.031086035072803497, "eval_loss": 0.039187201706226915} {"step": 62500, "train_loss": 0.043718308210372925, "eval_loss": 0.03925735712982714} {"step": 63000, "train_loss": 0.04534859210252762, "eval_loss": 0.04070412483997643} {"step": 63500, "train_loss": 0.1968090981245041, "eval_loss": 0.044246201461646706} {"step": 64000, "train_loss": 0.1817813515663147, "eval_loss": 0.04411018156679347} {"step": 64500, "train_loss": 0.04597022011876106, "eval_loss": 0.03919053450226784} {"step": 65000, "train_loss": 0.041364505887031555, "eval_loss": 0.038803645758889616} {"step": 65500, "train_loss": 0.09717413038015366, "eval_loss": 0.04256393760442734} {"step": 66000, "train_loss": 0.04208482801914215, "eval_loss": 0.042166406637988985} {"step": 66500, "train_loss": 0.17965669929981232, "eval_loss": 0.0409254293772392} {"step": 67000, "train_loss": 0.20611540973186493, "eval_loss": 0.03906242083758116} {"step": 67500, "train_loss": 0.053405459970235825, "eval_loss": 0.04074702807702124} {"step": 68000, "train_loss": 0.0782008096575737, "eval_loss": 0.04078496858710423} {"step": 68500, "train_loss": 0.04679597169160843, "eval_loss": 0.040197648922912776} {"step": 69000, "train_loss": 0.04605494439601898, "eval_loss": 0.04257643298478797} {"step": 69500, "train_loss": 0.08730171620845795, "eval_loss": 0.0399825896602124} {"step": 70000, "train_loss": 0.043718356639146805, "eval_loss": 0.043555888114497066} {"step": 70500, "train_loss": 0.18755625188350677, "eval_loss": 0.040985516796354204} {"step": 71000, "train_loss": 0.12897196412086487, "eval_loss": 0.04059841588605195} {"step": 71500, "train_loss": 0.04923213645815849, "eval_loss": 0.04216129949782044} {"step": 72000, "train_loss": 0.09729090332984924, "eval_loss": 0.04031876043882221} {"step": 72500, "train_loss": 0.05081339180469513, "eval_loss": 0.03927382716210559} {"step": 73000, "train_loss": 0.14748086035251617, "eval_loss": 0.04033009504200891} {"step": 73500, "train_loss": 0.045727092772722244, "eval_loss": 0.04043730691773817} {"step": 74000, "train_loss": 0.09891384840011597, "eval_loss": 0.039998164982534945} {"step": 74500, "train_loss": 0.1606588512659073, "eval_loss": 0.04033222090220079} {"step": 75000, "train_loss": 0.050552841275930405, "eval_loss": 0.04058729897951707} {"step": 75500, "train_loss": 0.1960919350385666, "eval_loss": 0.04149536648765206} {"step": 76000, "train_loss": 0.07781004905700684, "eval_loss": 0.04025406972505152} {"step": 76500, "train_loss": 0.03238295391201973, "eval_loss": 0.039860166725702584} {"step": 77000, "train_loss": 0.18552236258983612, "eval_loss": 0.03974387142807245} {"step": 77500, "train_loss": 0.08355175703763962, "eval_loss": 0.040582018438726664} {"step": 78000, "train_loss": 0.04619794338941574, "eval_loss": 0.037818134704139084} {"step": 78500, "train_loss": 0.08171719312667847, "eval_loss": 0.03899433388141915} {"step": 79000, "train_loss": 0.047125402837991714, "eval_loss": 0.04092266905354336} {"step": 79500, "train_loss": 0.049861613661050797, "eval_loss": 0.04075802903389558} {"step": 80000, "train_loss": 0.04751469939947128, "eval_loss": 0.04017745872261003} {"step": 80500, "train_loss": 0.04099234193563461, "eval_loss": 0.039863166166469455} {"step": 81000, "train_loss": 0.17065687477588654, "eval_loss": 0.040629533817991614} {"step": 81500, "train_loss": 0.040214903652668, "eval_loss": 0.042107936285901815} {"step": 82000, "train_loss": 0.18280252814292908, "eval_loss": 0.03985708538675681} {"step": 82500, "train_loss": 0.04854872077703476, "eval_loss": 0.04058692796388641} {"step": 83000, "train_loss": 0.03489544242620468, "eval_loss": 0.03926278604194522} {"step": 83500, "train_loss": 0.0685657262802124, "eval_loss": 0.04003953828942031} {"step": 84000, "train_loss": 0.10278767347335815, "eval_loss": 0.04109566495753825} {"step": 84500, "train_loss": 0.04680768400430679, "eval_loss": 0.03991425776621327} {"step": 85000, "train_loss": 0.10738731175661087, "eval_loss": 0.03898704325547442} {"step": 85500, "train_loss": 0.049204569309949875, "eval_loss": 0.038518213434144855} {"step": 86000, "train_loss": 0.14056135714054108, "eval_loss": 0.04164271539775655} {"step": 86500, "train_loss": 0.15005086362361908, "eval_loss": 0.03984140686225146} {"step": 87000, "train_loss": 0.043276455253362656, "eval_loss": 0.04022500029532239} {"step": 87500, "train_loss": 0.04013163223862648, "eval_loss": 0.04035594523884356} {"step": 88000, "train_loss": 0.036915093660354614, "eval_loss": 0.03971188882132992} {"step": 88500, "train_loss": 0.10548150539398193, "eval_loss": 0.03917114750947803} {"step": 89000, "train_loss": 0.0603865422308445, "eval_loss": 0.04285005439305678} {"step": 89500, "train_loss": 0.047995951026678085, "eval_loss": 0.03992798662511632} {"step": 90000, "train_loss": 0.09907437115907669, "eval_loss": 0.040398523793555796} {"step": 90500, "train_loss": 0.13143959641456604, "eval_loss": 0.04078399029094726} {"step": 91000, "train_loss": 0.049949534237384796, "eval_loss": 0.038582829060032964} {"step": 91500, "train_loss": 0.043559812009334564, "eval_loss": 0.040055412275251} {"step": 92000, "train_loss": 0.1689513772726059, "eval_loss": 0.04080250719562173} {"step": 92500, "train_loss": 0.07637742906808853, "eval_loss": 0.038471898704301566} {"step": 93000, "train_loss": 0.17724883556365967, "eval_loss": 0.039869183499831706} {"step": 93500, "train_loss": 0.0599936842918396, "eval_loss": 0.041433153906837106} {"step": 94000, "train_loss": 0.044684216380119324, "eval_loss": 0.039357353816740215} {"step": 94500, "train_loss": 0.03585042431950569, "eval_loss": 0.04091822070768103} {"step": 95000, "train_loss": 0.21430467069149017, "eval_loss": 0.0401810392504558} {"step": 95500, "train_loss": 0.17122812569141388, "eval_loss": 0.040508290578145534} {"step": 96000, "train_loss": 0.16569896042346954, "eval_loss": 0.04125184612348676} {"step": 96500, "train_loss": 0.04025258868932724, "eval_loss": 0.041178248124197125} {"step": 97000, "train_loss": 0.03985762968659401, "eval_loss": 0.03745894297026098} {"step": 97500, "train_loss": 0.12152106314897537, "eval_loss": 0.04072054661810398} {"step": 98000, "train_loss": 0.07258746773004532, "eval_loss": 0.04031049052719027} {"step": 98500, "train_loss": 0.07620606571435928, "eval_loss": 0.03911083919228986} {"step": 99000, "train_loss": 0.17625728249549866, "eval_loss": 0.039836780226323754} {"step": 99500, "train_loss": 0.05658499523997307, "eval_loss": 0.04048855829751119} {"step": 100000, "train_loss": 0.047881338745355606, "eval_loss": 0.04135053465142846}