Downloads · 30 days
17
0% of all-time downloads
distilbert-base-multilingual-cased-finetuned-conll2003-ner
gunghio/distilbert-base-multilingual-cased-finetuned-conll2003-ner
distilbert-base-multilingual-cased-finetuned-conll2003-ner is a token classification model from gunghio. Use it when you need labels on individual words, such as names. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
15.8K
Public
Parameters
135M
2.4 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.bin539 MB · 50%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- distilbert
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Apr 25, 2024
- SHA
- 8f22608f
Try a prompt
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. -->
gunghio/distilbert-base-multilingual-cased-finetuned-conll2003-ner
This model was trained from scratch on an conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0388
- Precision: 0.9360
- Recall: 0.9458
- F1: 0.9409
- Accuracy: 0.9902
Model description
It is based on distilbert-base-multilingual-cased
Intended uses & limitations
More information needed
Training and evaluation data
Training dataset: conll2003
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1653 | 1.0 | 878 | 0.0465 | 0.9267 | 0.9300 | 0.9283 | 0.9883 |
| 0.0322 | 2.0 | 1756 | 0.0404 | 0.9360 | 0.9431 | 0.9396 | 0.9897 |
| 0.0185 | 3.0 | 2634 | 0.0388 | 0.9360 | 0.9458 | 0.9409 | 0.9902 |
Framework versions
- Transformers 4.6.1
- Pytorch 1.8.1+cu101
- Datasets 1.6.2
- Tokenizers 0.10.2
- Task
- Token Classification
- Library
- transformers
- Type
- distilbert
- Languages
- en, de, nl, es, multilingual
- Created
- Mar 2, 2022
- Updated
- Apr 25, 2024