| global_step,eval_loss,train_loss | |
| 10000,2.895169258117676,2.121417284011841 | |
| 20000,2.6220273971557617,1.4240353107452393 | |
| 26645,2.4194741249084473,1.483300805091858 | |
| 30000,2.3234736919403076,1.1640515327453613 | |
| 40000,2.2976105213165283,1.365834355354309 | |
| 50000,2.1453287601470947,1.092398762702942 | |
| 53290,2.223170757293701,1.354332685470581 | |
| 60000,2.1844069957733154,1.3526930809020996 | |
| 70000,2.1598353385925293,1.1366236209869385 | |
| 79935,2.1022424697875977,1.491479754447937 | |
| 80000,2.1339430809020996,1.0291118621826172 | |
| 90000,2.0908524990081787,0.7879655361175537 | |
| 100000,2.147775411605835,0.7697624564170837 | |
| 106580,2.0243842601776123,1.2753760814666748 | |
| 110000,2.075385808944702,1.0065027475357056 | |
| 120000,2.116574764251709,0.6589317321777344 | |
| 130000,2.1382057666778564,1.1009167432785034 | |
| 133225,2.1510250568389893,1.0352411270141602 | |
| 140000,2.1862058639526367,0.8355902433395386 | |