Downloads · 30 days
14
27% of all-time downloads
nb-bert-norne-ner
thivy/nb-bert-norne-ner
nb-bert-norne-ner is a token classification model from thivy. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as cc-by-4.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
51
Public
Parameters
177M
7.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors709 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- cc-by-4.0
- Model type
- bert
- Access
- Public
- Created
- Dec 22, 2025
- Updated
- Dec 22, 2025
- SHA
- 49440543
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
nb-bert-norne-ner
This model is a fine-tuned version of NbAiLab/nb-bert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0430
- Precision: 0.9277
- Recall: 0.9296
- F1: 0.9287
- Accuracy: 0.9951
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0233 | 1.0 | 3734 | 0.0272 | 0.8978 | 0.9109 | 0.9043 | 0.9939 |
| 0.0165 | 2.0 | 7468 | 0.0214 | 0.9200 | 0.9228 | 0.9214 | 0.9949 |
| 0.0071 | 3.0 | 11202 | 0.0269 | 0.9218 | 0.9222 | 0.9220 | 0.9951 |
| 0.0042 | 4.0 | 14936 | 0.0275 | 0.9237 | 0.9259 | 0.9248 | 0.9951 |
| 0.0025 | 5.0 | 18670 | 0.0331 | 0.9226 | 0.9279 | 0.9253 | 0.9951 |
| 0.0014 | 6.0 | 22404 | 0.0370 | 0.9204 | 0.9276 | 0.9240 | 0.9949 |
| 0.0015 | 7.0 | 26138 | 0.0389 | 0.9225 | 0.9259 | 0.9242 | 0.9951 |
| 0.0 | 8.0 | 29872 | 0.0404 | 0.9263 | 0.9310 | 0.9286 | 0.9953 |
| 0.0003 | 9.0 | 33606 | 0.0426 | 0.9259 | 0.9300 | 0.9279 | 0.9952 |
| 0.0 | 10.0 | 37340 | 0.0430 | 0.9277 | 0.9296 | 0.9287 | 0.9951 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.1
- Datasets 4.4.1
- Tokenizers 0.22.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- cc-by-4.0
- Created
- Dec 22, 2025
- Updated
- Dec 22, 2025