danskbert_ED3

This model is a fine-tuned version of vesteinn/DanskBERT on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4172
• F1-score: 0.9180

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1-score
No log	1.0	69	0.4185	0.8182
No log	2.0	138	0.2883	0.8771
No log	3.0	207	0.6676	0.8605
No log	4.0	276	0.4172	0.9180
No log	5.0	345	0.7406	0.8495
No log	6.0	414	0.6953	0.8668
No log	7.0	483	0.5687	0.9016
0.2011	8.0	552	0.7013	0.8765
0.2011	9.0	621	0.7086	0.8851
0.2011	10.0	690	0.7390	0.8768

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1