Daniël de Kok
Daniël de Kok
Some values are invalid: * Having more layer groups than layers. * The number of layers is not a multiple of the number of layer groups (e.g. 12 layers, 5...
This allows us to check whether stacking should be replaced by a loop: https://github.com/stickeritis/sticker-transformers/pull/18#discussion_r363758770
The `conllx` dependency is now used throughout `sticker`. Abstract over layers and features using traits, so that the `sticker` create becomes oblivious to the underlying format. `sticker-utils` could then provide...
Once an epoch is done, we start a new line. The batch accuracy/loss that is displayed is then that of the last batch of the epoch. These numbers are confusing...