Downloads · 30 days
5
1% of all-time downloads
mn-bert-base-demo-named-entity
2rtl3/mn-bert-base-demo-named-entity
mn-bert-base-demo-named-entity is a token classification model from 2rtl3. 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
779
Public
Repo size
7.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin709 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- May 16, 2023
- Updated
- May 16, 2023
- SHA
- a8553e49
Try a prompt
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. -->
mn-bert-base-demo-named-entity
This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1468
- Precision: 0.9092
- Recall: 0.9187
- F1: 0.9139
- Accuracy: 0.9757
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: 32
- 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 |
|---|---|---|---|---|---|---|---|
| 0.172 | 1.0 | 477 | 0.1117 | 0.8614 | 0.8811 | 0.8711 | 0.9662 |
| 0.0846 | 2.0 | 954 | 0.1033 | 0.8748 | 0.8957 | 0.8852 | 0.9698 |
| 0.0562 | 3.0 | 1431 | 0.1005 | 0.8808 | 0.9024 | 0.8915 | 0.9716 |
| 0.0398 | 4.0 | 1908 | 0.1105 | 0.8978 | 0.9073 | 0.9025 | 0.9731 |
| 0.0276 | 5.0 | 2385 | 0.1181 | 0.9031 | 0.9121 | 0.9076 | 0.9740 |
| 0.0204 | 6.0 | 2862 | 0.1309 | 0.9039 | 0.9153 | 0.9096 | 0.9747 |
| 0.0138 | 7.0 | 3339 | 0.1322 | 0.9023 | 0.9132 | 0.9077 | 0.9745 |
| 0.0103 | 8.0 | 3816 | 0.1434 | 0.9071 | 0.9153 | 0.9112 | 0.9748 |
| 0.0071 | 9.0 | 4293 | 0.1458 | 0.9041 | 0.9156 | 0.9098 | 0.9750 |
| 0.0052 | 10.0 | 4770 | 0.1468 | 0.9092 | 0.9187 | 0.9139 | 0.9757 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Languages
- mn
- Created
- May 16, 2023
- Updated
- May 16, 2023