| Epoch,Training Loss,Validation Loss,Perplexity |
| 1,6.871014557343578,6.88107880102385,973.6761962851759 |
| 2,5.146239291078583,7.61162718282927,2021.5648785535734 |
| 3,3.767260024569425,8.298620523662741,4018.325383934967 |
| 4,2.4471943775471408,8.729707017951055,6183.916069366171 |
| 5,1.447778496886993,9.00603594118302,8152.141571147584 |
| 6,0.8093601042684274,9.11319341818127,9074.22647133121 |
| 7,0.4723491070649127,9.476827714968165,13053.710671387153 |
| 8,0.3648805984243631,9.746890414950498,17100.969126522796 |
| 9,0.22838460195933352,10.033540602807605,22777.77600164143 |
| 10,0.11587010667193147,10.173108484151713,26189.35957459265 |
| 11,0.05089781283377483,10.258553796563161,28525.502667211986 |
| 12,0.0264121715071689,10.382500875801053,32289.612911373773 |
| 13,0.018073340248474415,10.587299010793277,39628.30881033295 |
| 14,0.01582686644901478,10.69601418784448,44179.412890154104 |
| 15,0.013108823649246003,10.872116315723268,52686.59383437666 |
| 16,0.011147769471259205,11.001549854044752,59967.00984334372 |
| 17,0.13079503980962098,10.283178370890267,29236.650955264828 |
| 18,0.3088226785108806,10.50666926616649,36558.509866646324 |
| 19,0.057846921478124244,10.745629251165607,46426.665059916166 |
| 20,0.014262599358828535,10.994005504739258,59516.30006802947 |
| 21,0.009673960170505104,11.06022528860261,63590.876552295435 |
| 22,0.008417614657535988,11.146125610880425,69294.83219387358 |
| 23,0.008406667923631456,11.188230332198078,72274.76621341356 |
| 24,0.009422658827157962,11.411897016316706,90390.73175739887 |
| 25,0.007742026781398664,11.503192459355128,99031.42067870381 |
|
|
