| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0003 | 0.0231 | 25 | 0.9931 |
| 0.9798 | 0.0461 | 50 | 0.9937 |
| 0.9877 | 0.0692 | 75 | 1.0048 |
| 1.0181 | 0.0923 | 100 | 1.0190 |
| 1.0461 | 0.1154 | 125 | 1.0339 |
| 1.0125 | 0.1384 | 150 | 1.0409 |
| 1.0167 | 0.1615 | 175 | 1.0377 |
| 1.0352 | 0.1846 | 200 | 1.0491 |
| 1.0443 | 0.2077 | 225 | 1.0417 |
| 1.0312 | 0.2307 | 250 | 1.0430 |
| 1.0313 | 0.2538 | 275 | 1.0441 |
| 1.0368 | 0.2769 | 300 | 1.0404 |
| 1.0333 | 0.3000 | 325 | 1.0383 |
| 1.0125 | 0.3230 | 350 | 1.0330 |
| 1.0251 | 0.3461 | 375 | 1.0293 |
| 1.0086 | 0.3692 | 400 | 1.0259 |
| 1.0057 | 0.3922 | 425 | 1.0222 |
| 1.0172 | 0.4153 | 450 | 1.0186 |
| 1.0135 | 0.4384 | 475 | 1.0159 |
| 1.026 | 0.4615 | 500 | 1.0130 |
| 0.9798 | 0.4845 | 525 | 1.0060 |
| 0.9888 | 0.5076 | 550 | 1.0022 |
| 0.9792 | 0.5307 | 575 | 0.9974 |
| 0.9726 | 0.5538 | 600 | 0.9924 |
| 0.9686 | 0.5768 | 625 | 0.9882 |
| 0.9789 | 0.5999 | 650 | 0.9839 |
| 0.9716 | 0.6230 | 675 | 0.9793 |
| 0.9438 | 0.6461 | 700 | 0.9754 |
| 0.9502 | 0.6691 | 725 | 0.9705 |
| 0.9464 | 0.6922 | 750 | 0.9665 |
| 0.9395 | 0.7153 | 775 | 0.9624 |
| 0.9254 | 0.7383 | 800 | 0.9590 |
| 0.9337 | 0.7614 | 825 | 0.9557 |
| 0.9366 | 0.7845 | 850 | 0.9529 |
| 0.9372 | 0.8076 | 875 | 0.9502 |
| 0.9365 | 0.8306 | 900 | 0.9479 |
| 0.9373 | 0.8537 | 925 | 0.9459 |
| 0.9421 | 0.8768 | 950 | 0.9444 |
| 0.9191 | 0.8999 | 975 | 0.9433 |
| 0.9195 | 0.9229 | 1000 | 0.9425 |
| 0.9318 | 0.9460 | 1025 | 0.9420 |
| 0.9395 | 0.9691 | 1050 | 0.9418 |
| 0.9289 | 0.9922 | 1075 | 0.9418 |