| step,training_loss,val_loss | |
| 0,8.2952,8.2952 | |
| 300,2.5408,2.5484 | |
| 600,2.3275,2.3496 | |
| 900,2.2266,2.2587 | |
| 1200,2.1613,2.2052 | |
| 1500,2.1146,2.1682 | |
| 1800,2.0654,2.1304 | |
| 2100,2.035,2.1072 | |
| 2400,2.0061,2.0888 | |
| 2700,1.9786,2.0657 | |
| 3000,1.9517,2.0516 | |
| 3300,1.9313,2.0371 | |
| 3600,1.9106,2.0259 | |
| 3900,1.8977,2.0215 | |
| 4200,1.8809,2.0095 | |
| 4500,1.8713,2.0029 | |
| 4800,1.8517,1.9974 | |
| 5100,1.8438,1.998 | |
| 5400,1.8312,1.9925 | |
| 5700,1.8241,1.9899 | |
| 6000,1.816,1.9861 | |
| 6300,1.8129,1.9872 | |
| 6600,1.806,1.9796 | |
| 6900,1.8111,1.9788 | |
| 7200,1.7882,1.9765 | |
| 7500,1.7808,1.9707 | |
| 7800,1.7798,1.9767 | |
| 8100,1.7731,1.9721 | |
| 8400,1.7705,1.965 | |
| 8700,1.7639,1.9667 | |
| 9000,1.7569,1.9709 | |