Downloads · 30 days
6
2% of all-time downloads
bert-finetuned-ner-ko
harheem/bert-finetuned-ner-ko
bert-finetuned-ner-ko is a token classification model from harheem. 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
315
Public
Parameters
177M
2.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors709 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- May 15, 2024
- Updated
- May 15, 2024
- SHA
- 91107d6e
Try a prompt
Base models
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. -->
bert-finetuned-ner-ko
This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0783
- Precision: 0.9554
- Recall: 0.9583
- F1: 0.9568
- Accuracy: 0.9794
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: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 366 | 0.0930 | 0.9425 | 0.9430 | 0.9428 | 0.9729 |
| 0.1523 | 2.0 | 732 | 0.0754 | 0.9513 | 0.9567 | 0.9540 | 0.9780 |
| 0.054 | 3.0 | 1098 | 0.0783 | 0.9554 | 0.9583 | 0.9568 | 0.9794 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- May 15, 2024
- Updated
- May 15, 2024