Downloads · 30 days
4
13% of all-time downloads
bert-ner-custom
nicoheiniger/bert-ner-custom
bert-ner-custom is a token classification model from nicoheiniger. 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
32
Public
Parameters
108M
2.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors431 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Oct 6, 2024
- Updated
- Oct 7, 2024
- SHA
- d11ec1eb
Try a prompt
Base models
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. -->
bert-ner-custom
This model is a fine-tuned version of bert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1914
- Precision: 0.8830
- Recall: 0.9125
- F1: 0.8975
- Accuracy: 0.9712
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 |
|---|---|---|---|---|---|---|---|
| 0.0754 | 1.0 | 1756 | 0.1666 | 0.8592 | 0.8998 | 0.8790 | 0.9678 |
| 0.0349 | 2.0 | 3512 | 0.1794 | 0.8843 | 0.9065 | 0.8953 | 0.9712 |
| 0.0213 | 3.0 | 5268 | 0.1914 | 0.8830 | 0.9125 | 0.8975 | 0.9712 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Oct 6, 2024
- Updated
- Oct 7, 2024