danskbert_NCST

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

• Loss: 0.4281
• F1-score: 0.8075

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• 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
0.4689	1.0	535	0.4281	0.8075
0.4053	2.0	1070	0.5061	0.7802
0.3074	3.0	1605	0.6016	0.7923
0.2363	4.0	2140	1.0487	0.7002
0.1671	5.0	2675	0.9357	0.7901
0.1311	6.0	3210	1.1869	0.7854
0.0909	7.0	3745	1.6172	0.7585
0.0665	8.0	4280	1.4884	0.7743
0.0517	9.0	4815	1.7031	0.7608
0.039	10.0	5350	1.6078	0.7743

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1