Downloads · 30 days
8
3% of all-time downloads
ner_ANAT_DISO
roscazo/ner_ANAT_DISO
ner_ANAT_DISO is a token classification model from roscazo. 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
319
Public
Repo size
1.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin496 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- roberta
- Access
- Public
- Created
- Jan 5, 2023
- Updated
- Jan 5, 2023
- SHA
- e628d781
Try a prompt
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. -->
ner_ANAT_DISO
This model is a fine-tuned version of PlanTL-GOB-ES/bsc-bio-ehr-es on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0746
- Anat Precision: 0.6512
- Anat Recall: 0.6573
- Anat F1: 0.6542
- Anat Number: 534
- Diso Precision: 0.8727
- Diso Recall: 0.8844
- Diso F1: 0.8785
- Diso Number: 2915
- Overall Precision: 0.8385
- Overall Recall: 0.8492
- Overall F1: 0.8438
- Overall Accuracy: 0.9838
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Anat Precision | Anat Recall | Anat F1 | Anat Number | Diso Precision | Diso Recall | Diso F1 | Diso Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.0625 | 1.0 | 1682 | 0.0591 | 0.5407 | 0.6723 | 0.5993 | 534 | 0.8516 | 0.8624 | 0.8570 | 2915 | 0.7945 | 0.8330 | 0.8133 | 0.9808 |
| 0.0397 | 2.0 | 3364 | 0.0633 | 0.6237 | 0.6798 | 0.6505 | 534 | 0.8576 | 0.8820 | 0.8696 | 2915 | 0.8196 | 0.8507 | 0.8348 | 0.9826 |
| 0.0181 | 3.0 | 5046 | 0.0698 | 0.6452 | 0.6948 | 0.6691 | 534 | 0.8670 | 0.8878 | 0.8773 | 2915 | 0.8312 | 0.8579 | 0.8443 | 0.9833 |
| 0.0121 | 4.0 | 6728 | 0.0746 | 0.6512 | 0.6573 | 0.6542 | 534 | 0.8727 | 0.8844 | 0.8785 | 2915 | 0.8385 | 0.8492 | 0.8438 | 0.9838 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Task
- Token Classification
- Library
- transformers
- Type
- roberta
- License
- apache-2.0
- Created
- Jan 5, 2023
- Updated
- Jan 5, 2023