HylkeBr/robbert_dutch-cola

This model is a fine-tuned version of pdelobelle/robbert-v2-dutch-base on GroNLP/dutch-cola, from where only the acceptable and unacceptable examples were used to fine-tune. The data used for fine-tuning therefore only contains sentences with original mark 'None' and '*'.

Accuracy: 0.8055

The following hyperparameters were used during training:

learning rate: 4e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
num_epochs: 4

Epoch	Training Loss	Step	Validation Loss	Accuracy
1.0	0.5078	1169	0.5111	0.7732
2.0	0.3076	2338	0.6988	0.7700
3.0	0.1901	3507	0.8459	0.8027
4.0	0.1198	4676	1.0620	0.8055