Downloads · 30 days
5
8% of all-time downloads
bert-finetuned-ner-ime
jujbob/bert-finetuned-ner-ime
bert-finetuned-ner-ime is a token classification model from jujbob. Use it when you need labels on individual words, such as names. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
61
Public
Repo size
6.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin394 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jun 7, 2023
- Updated
- Jun 8, 2023
- SHA
- eacfcd9b
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. -->
bert-finetuned-ner-ime
This model is a fine-tuned version of snunlp/KR-BERT-char16424 on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0076
- Precision: 0.9982
- Recall: 0.9982
- F1: 0.9982
- Accuracy: 0.9980
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 |
|---|---|---|---|---|---|---|---|
| 0.0378 | 1.0 | 1756 | 0.0290 | 0.9934 | 0.9939 | 0.9936 | 0.9920 |
| 0.0214 | 2.0 | 3512 | 0.0138 | 0.9969 | 0.9970 | 0.9970 | 0.9965 |
| 0.0151 | 3.0 | 5268 | 0.0076 | 0.9982 | 0.9982 | 0.9982 | 0.9980 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.11.0
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Created
- Jun 7, 2023
- Updated
- Jun 8, 2023