nbBERT_ND

This model is a fine-tuned version of NbAiLab/nb-bert-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6925
• F1-score: 0.8767

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	223	0.3699	0.8512
No log	2.0	446	0.3821	0.8476
0.3652	3.0	669	0.4355	0.8719
0.3652	4.0	892	0.4200	0.8755
0.2357	5.0	1115	0.5924	0.8719
0.2357	6.0	1338	0.6925	0.8767
0.1243	7.0	1561	0.6726	0.8636
0.1243	8.0	1784	0.7976	0.8588
0.0626	9.0	2007	0.7962	0.8622
0.0626	10.0	2230	0.7938	0.8622

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1