Downloads · 30 days
17
40% of all-time downloads
distilbert-base-uncased-finetuned-ner
grazh/distilbert-base-uncased-finetuned-ner
distilbert-base-uncased-finetuned-ner is a token classification model from grazh. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
43
Public
Parameters
66.4M
1.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors265 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Dec 21, 2025
- Updated
- Dec 21, 2025
- SHA
- 4a68a766
Try a prompt
Base models
Datasets
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. -->
distilbert-base-uncased-finetuned-ner
This model is a fine-tuned version of distilbert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0645
- Precision: 0.9263
- Recall: 0.9361
- F1: 0.9312
- Accuracy: 0.9836
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: 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
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2405 | 1.0 | 878 | 0.0710 | 0.9038 | 0.9208 | 0.9122 | 0.9797 |
| 0.0522 | 2.0 | 1756 | 0.0635 | 0.9198 | 0.9308 | 0.9253 | 0.9823 |
| 0.0307 | 3.0 | 2634 | 0.0645 | 0.9263 | 0.9361 | 0.9312 | 0.9836 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 3.6.0
- Tokenizers 0.22.1
- Task
- Token Classification
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Dec 21, 2025
- Updated
- Dec 21, 2025