Downloads · 30 days
14
19% of all-time downloads
distilbert-base-multilingual-cased-mapa_fine-ner
dmargutierrez/distilbert-base-multilingual-cased-mapa_fine-ner
distilbert-base-multilingual-cased-mapa_fine-ner is a token classification model from dmargutierrez. 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
72
Public
Parameters
135M
5.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin539 MB · 50%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Mar 20, 2023
- Updated
- Mar 21, 2023
- SHA
- bb683869
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. -->
distilbert-base-multilingual-cased-mapa_fine-ner
This model is a fine-tuned version of distilbert-base-multilingual-cased on the lextreme dataset. It achieves the following results on the evaluation set:
- Loss: 0.0282
- Precision: 0.8763
- Recall: 0.9115
- F1: 0.8936
- Accuracy: 0.9957
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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0244 | 1.0 | 1739 | 0.0202 | 0.8083 | 0.9314 | 0.8655 | 0.9941 |
| 0.0154 | 2.0 | 3478 | 0.0173 | 0.8813 | 0.9006 | 0.8908 | 0.9954 |
| 0.0118 | 3.0 | 5217 | 0.0161 | 0.8885 | 0.9131 | 0.9006 | 0.9960 |
| 0.0084 | 4.0 | 6956 | 0.0194 | 0.8485 | 0.9295 | 0.8871 | 0.9953 |
| 0.0069 | 5.0 | 8695 | 0.0219 | 0.8583 | 0.9198 | 0.8880 | 0.9953 |
| 0.0054 | 6.0 | 10434 | 0.0229 | 0.8622 | 0.9160 | 0.8883 | 0.9954 |
| 0.0032 | 7.0 | 12173 | 0.0248 | 0.8817 | 0.8979 | 0.8898 | 0.9956 |
| 0.0023 | 8.0 | 13912 | 0.0265 | 0.8900 | 0.9023 | 0.8961 | 0.9958 |
| 0.0018 | 9.0 | 15651 | 0.0275 | 0.8657 | 0.9137 | 0.8890 | 0.9954 |
| 0.0016 | 10.0 | 17390 | 0.0282 | 0.8763 | 0.9115 | 0.8936 | 0.9957 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu117
- Datasets 2.9.0
- Tokenizers 0.13.2
- Task
- Token Classification
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Mar 20, 2023
- Updated
- Mar 21, 2023