Downloads · 30 days
6
10% of all-time downloads
bsc-bio-ehr-es-cantemist-ner
Rodrigo1771/bsc-bio-ehr-es-cantemist-ner
bsc-bio-ehr-es-cantemist-ner is a token classification model from Rodrigo1771. Use it when you need labels on individual words, such as names. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
62
Public
Parameters
124M
5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors496 MB · 99%
At a glance
- Task
- Token Classification
- License
- apache-2.0
- Model type
- roberta
- Access
- Public
- Created
- Aug 30, 2024
- Updated
- Aug 30, 2024
- SHA
- efab1c2b
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. -->
output
This model is a fine-tuned version of PlanTL-GOB-ES/bsc-bio-ehr-es on the Rodrigo1771/cantemist-ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.0382
- Precision: 0.8417
- Recall: 0.8625
- F1: 0.8520
- Accuracy: 0.9920
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 454 | 0.0249 | 0.7532 | 0.8247 | 0.7874 | 0.9905 |
| 0.0456 | 2.0 | 908 | 0.0236 | 0.7735 | 0.8365 | 0.8038 | 0.9907 |
| 0.0175 | 3.0 | 1362 | 0.0264 | 0.8018 | 0.8460 | 0.8233 | 0.9908 |
| 0.0106 | 4.0 | 1816 | 0.0289 | 0.8084 | 0.8507 | 0.8290 | 0.9915 |
| 0.0066 | 5.0 | 2270 | 0.0320 | 0.8135 | 0.8523 | 0.8325 | 0.9916 |
| 0.004 | 6.0 | 2724 | 0.0382 | 0.8044 | 0.8582 | 0.8304 | 0.9909 |
| 0.0027 | 7.0 | 3178 | 0.0382 | 0.8417 | 0.8625 | 0.8520 | 0.9920 |
| 0.0017 | 8.0 | 3632 | 0.0433 | 0.8301 | 0.8657 | 0.8475 | 0.9916 |
| 0.001 | 9.0 | 4086 | 0.0442 | 0.8340 | 0.8649 | 0.8492 | 0.9918 |
| 0.0006 | 10.0 | 4540 | 0.0459 | 0.8356 | 0.8649 | 0.8500 | 0.9918 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Task
- Token Classification
- Type
- roberta
- License
- apache-2.0
- Created
- Aug 30, 2024
- Updated
- Aug 30, 2024