| datasets: | |
| - crumb/flan-ul2-tinystories-complex | |
| - crumb/flan-ul2-tinystories | |
| test loss 2.669290 on crumb/flan-ul2-tinystories-complex, initialized from crumb/opentinystories-30m-base, 2 epochs, linear decreasing lr 1e-4. trained with double the batch size (256) |