nbbert_NC

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: 0.2783
• F1-score: 0.9059

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
No log	1.0	40	0.2996	0.8705
No log	2.0	80	0.2783	0.9059
No log	3.0	120	0.4520	0.8468
No log	4.0	160	0.4208	0.8835
No log	5.0	200	0.4822	0.8769
No log	6.0	240	0.5911	0.8532
No log	7.0	280	0.6615	0.8575
No log	8.0	320	0.6214	0.8704
No log	9.0	360	0.5874	0.8769
No log	10.0	400	0.6864	0.8575

Framework versions

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