Downloads · 30 days
10
4% of all-time downloads
betoNer-biobert
Vantwoth/betoNer-biobert
betoNer-biobert is a token classification model from Vantwoth. 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
261
Public
Parameters
109M
4.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors219 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Nov 20, 2024
- Updated
- Nov 20, 2024
- SHA
- fb2a1e9d
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. -->
betoNer-biobert
This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1179
- Precision: 0.9511
- Recall: 0.9644
- F1: 0.9577
- Accuracy: 0.9773
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: 32
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 306 | 0.1159 | 0.9263 | 0.9509 | 0.9384 | 0.9686 |
| 0.3168 | 2.0 | 612 | 0.1014 | 0.9358 | 0.9642 | 0.9498 | 0.9742 |
| 0.3168 | 3.0 | 918 | 0.0959 | 0.9462 | 0.9656 | 0.9558 | 0.9767 |
| 0.0777 | 4.0 | 1224 | 0.1011 | 0.9451 | 0.9661 | 0.9555 | 0.9767 |
| 0.0541 | 5.0 | 1530 | 0.1073 | 0.9512 | 0.9643 | 0.9577 | 0.9772 |
| 0.0541 | 6.0 | 1836 | 0.1083 | 0.9441 | 0.9611 | 0.9525 | 0.9751 |
| 0.0385 | 7.0 | 2142 | 0.1100 | 0.9515 | 0.9632 | 0.9573 | 0.9776 |
| 0.0385 | 8.0 | 2448 | 0.1153 | 0.9477 | 0.9658 | 0.9567 | 0.9770 |
| 0.0325 | 9.0 | 2754 | 0.1161 | 0.9495 | 0.9633 | 0.9564 | 0.9769 |
| 0.0255 | 10.0 | 3060 | 0.1179 | 0.9511 | 0.9644 | 0.9577 | 0.9773 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Created
- Nov 20, 2024
- Updated
- Nov 20, 2024