Downloads · 30 days
20
5% of all-time downloads
mongolian-distilbert-base-multilingual-cased-demo
Enkhbold/mongolian-distilbert-base-multilingual-cased-demo
mongolian-distilbert-base-multilingual-cased-demo is a token classification model from Enkhbold. 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
394
Public
Repo size
5.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin539 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- May 22, 2023
- Updated
- May 22, 2023
- SHA
- 14128264
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. -->
mongolian-distilbert-base-multilingual-cased-demo
This model is a fine-tuned version of distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1370
- Precision: 0.8794
- Recall: 0.9055
- F1: 0.8923
- Accuracy: 0.9724
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 |
|---|---|---|---|---|---|---|---|
| 0.2163 | 1.0 | 477 | 0.1387 | 0.7933 | 0.8434 | 0.8176 | 0.9560 |
| 0.1049 | 2.0 | 954 | 0.0989 | 0.8491 | 0.8840 | 0.8662 | 0.9688 |
| 0.0705 | 3.0 | 1431 | 0.0948 | 0.8598 | 0.8955 | 0.8773 | 0.9715 |
| 0.0476 | 4.0 | 1908 | 0.1065 | 0.8577 | 0.8969 | 0.8768 | 0.9701 |
| 0.0336 | 5.0 | 2385 | 0.1142 | 0.8703 | 0.8995 | 0.8847 | 0.9718 |
| 0.0252 | 6.0 | 2862 | 0.1225 | 0.8758 | 0.9023 | 0.8888 | 0.9716 |
| 0.018 | 7.0 | 3339 | 0.1256 | 0.8738 | 0.9022 | 0.8877 | 0.9716 |
| 0.0135 | 8.0 | 3816 | 0.1322 | 0.8807 | 0.9081 | 0.8942 | 0.9731 |
| 0.0103 | 9.0 | 4293 | 0.1367 | 0.8767 | 0.9043 | 0.8903 | 0.9720 |
| 0.0087 | 10.0 | 4770 | 0.1370 | 0.8794 | 0.9055 | 0.8923 | 0.9724 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Token Classification
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Languages
- mn
- Created
- May 22, 2023
- Updated
- May 22, 2023