Downloads · 30 days
10
18% of all-time downloads
convbert-finetuned-ner
pnr-svc/convbert-finetuned-ner
convbert-finetuned-ner is a token classification model from pnr-svc. 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
57
Public
Parameters
107M
1.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors428 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- convbert
- Access
- Public
- Created
- Sep 29, 2024
- Updated
- Sep 30, 2024
- SHA
- da19d80d
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. -->
convbert-finetuned-ner
This model is a fine-tuned version of YituTech/conv-bert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1088
- Precision: 0.9589
- Recall: 0.9707
- F1: 0.9648
- Accuracy: 0.9805
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 |
|---|---|---|---|---|---|---|---|
| 0.074 | 1.0 | 5285 | 0.1325 | 0.9499 | 0.9621 | 0.9560 | 0.9744 |
| 0.0658 | 2.0 | 10570 | 0.1142 | 0.9567 | 0.9679 | 0.9623 | 0.9788 |
| 0.0908 | 3.0 | 15855 | 0.1088 | 0.9589 | 0.9707 | 0.9648 | 0.9805 |
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
- convbert
- Created
- Sep 29, 2024
- Updated
- Sep 30, 2024