iter,tokens,train_loss,val_loss 100,157286400,5.3923,5.3944 200,314572800,4.4256,4.4123 300,471859200,3.9328,3.9326 400,629145600,3.7044,3.7130 500,786432000,3.5865,3.5860 600,943718400,3.4926,3.4855 700,1101004800,3.4271,3.4207 800,1258291200,3.3782,3.3770 900,1415577600,3.3439,3.3347 1000,1572864000,3.3015,3.3075 1100,1730150400,3.2849,3.2764 1200,1887436800,3.2507,3.2510 1300,2044723200,3.2361,3.2321 1400,2202009600,3.2270,3.2149 1500,2359296000,3.2024,3.2032 1600,2516582400,3.1908,3.1925 1700,2673868800,3.1755,3.1684 1800,2831155200,3.1710,3.1616 1900,2988441600,3.1485,3.1536 2000,3145728000,3.1470,3.1510 2100,3303014400,3.1321,3.1354 2200,3460300800,3.1170,3.1359 2300,3617587200,3.1220,3.1162 2400,3774873600,3.1113,3.1083 2500,3932160000,3.0946,3.1069 2600,4089446400,3.0969,3.0968 2700,4246732800,3.0865,3.0891 2800,4404019200,3.0920,3.0768 2900,4561305600,3.0768,3.0877 3000,4718592000,3.0676,3.0782 3100,4875878400,3.0678,3.0638 3200,5033164800,3.0625,3.0615 3300,5190451200,3.0550,3.0438 3400,5347737600,3.0396,3.0549 3500,5505024000,3.0459,3.0614 3600,5662310400,3.0402,3.0480 3700,5819596800,3.0305,3.0480 3800,5976883200,3.0428,3.0416 3900,6134169600,3.0355,3.0324 4000,6291456000,3.0314,3.0362 4100,6448742400,3.0290,3.0318 4200,6606028800,3.0233,3.0241 4300,6763315200,3.0100,3.0219 4400,6920601600,3.0123,3.0128 4500,7077888000,3.0149,3.0033 4600,7235174400,3.0126,3.0122 4700,7392460800,2.9999,3.0144 4800,7549747200,2.9985,2.9972 4900,7707033600,3.0044,2.9949 5000,7864320000,2.9996,3.0014 5100,8021606400,2.9990,3.0036 5200,8178892800,2.9946,2.9921 5300,8336179200,2.9875,2.9857 5400,8493465600,2.9754,2.9861 5500,8650752000,2.9796,2.9803 5600,8808038400,2.9834,2.9840 5700,8965324800,2.9784,2.9815 5800,9122611200,2.9879,2.9691 5900,9279897600,2.9676,2.9735 6000,9437184000,2.9732,2.9703 6100,9594470400,2.9663,2.9724 6200,9751756800,2.9606,2.9693 6300,9909043200,2.9707,2.9576 6400,10066329600,2.9585,2.9775 6500,10223616000,2.9590,2.9598 6600,10380902400,2.9465,2.9626 6700,10538188800,2.9508,2.9659 6800,10695475200,2.9464,2.9564 6900,10852761600,2.9539,2.9548 7000,11010048000,2.9570,2.9468 7100,11167334400,2.9443,2.9449 7200,11324620800,2.9526,2.9465 7300,11481907200,2.9411,2.9476 7400,11639193600,2.9407,2.9455 7500,11796480000,2.9445,2.9425 7600,11953766400,2.9486,2.9350 7700,12111052800,2.9310,2.9319 7800,12268339200,2.9324,2.9324 7900,12425625600,2.9306,2.9257 8000,12582912000,2.9379,2.9253 8100,12740198400,2.9214,2.9201 8200,12897484800,2.9253,2.9318 8300,13054771200,2.9248,2.9328 8400,13212057600,2.9248,2.9230 8500,13369344000,2.9258,2.9303 8600,13526630400,2.9155,2.9201 8700,13683916800,2.9221,2.9200 8800,13841203200,2.9225,2.9257 8900,13998489600,2.9119,2.9021 9000,14155776000,2.9102,2.9202 9100,14313062400,2.9127,2.9129 9200,14470348800,2.9013,2.9157 9300,14627635200,2.8965,2.9057 9400,14784921600,2.9025,2.9099 9500,14942208000,2.9085,2.9081 9600,15099494400,2.8953,2.9006 9700,15256780800,2.8942,2.8988 9800,15414067200,2.9014,2.9046 9900,15571353600,2.8980,2.8974 10000,15728640000,2.8950,2.9010 10100,15885926400,2.8985,2.9042 10200,16043212800,2.8873,2.8983 10300,16200499200,2.8853,2.8862 10400,16357785600,2.8879,2.9049 10500,16515072000,2.8904,2.8961 10600,16672358400,2.8870,2.8976 10700,16829644800,2.8871,2.8923 10800,16986931200,2.8763,2.8973 10900,17144217600,2.8776,2.8864 11000,17301504000,2.8858,2.8916 11100,17458790400,2.8733,2.8892 11200,17616076800,2.8779,2.8777 11300,17773363200,2.8758,2.8826 11400,17930649600,2.8750,2.8793 11500,18087936000,2.8638,2.8808 11600,18245222400,2.8749,2.8865 11700,18402508800,2.8696,2.8766 11800,18559795200,2.8615,2.8746 11900,18717081600,2.8634,2.8834 12000,18874368000,2.8724,2.8661 12100,19031654400,2.8605,2.8692 12200,19188940800,2.8711,2.8586 12300,19346227200,2.8609,2.8603 12400,19503513600,2.8611,2.8676 12500,19660800000,2.8720,2.8665 12600,19818086400,2.8520,2.8652 12700,19975372800,2.8613,2.8641 12710,19991101440,2.8748,2.8664