| global_step,eval_loss,train_loss |
| 1250,0.6965776959955692,0.61790931224823 |
| 2500,0.6794335454255342,0.9763208627700806 |
| 3750,0.6732937547266483,0.6070187091827393 |
| 5000,0.6685135231316089,0.5626436471939087 |
| 6250,0.6684221000373364,0.6495384573936462 |
| 7500,0.6667980900257826,0.6937068700790405 |
| 8750,0.667146667227149,0.5660955309867859 |
| 10000,0.6671847979575396,0.4809238910675049 |
| 11250,0.6658003166913986,0.7043024301528931 |
| 12500,0.6665574563592672,0.42717769742012024 |
| 13750,0.6681778557002545,0.51814866065979 |
| 15000,0.668208908483386,0.5448908805847168 |
| 16250,0.6692276625335216,0.36234185099601746 |
| 17500,0.6706667754203081,0.8254252672195435 |
| 18750,0.6703474833667278,0.530653178691864 |
| 20000,0.6698320330530405,0.6914252042770386 |
|
|
