|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: PlanTL-GOB-ES/bsc-bio-ehr-es |
|
tags: |
|
- token-classification |
|
- generated_from_trainer |
|
datasets: |
|
- Rodrigo1771/cantemist-fasttext-75-ner |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: output |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: Rodrigo1771/cantemist-fasttext-75-ner |
|
type: Rodrigo1771/cantemist-fasttext-75-ner |
|
config: CantemistNer |
|
split: validation |
|
args: CantemistNer |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.8462436745815493 |
|
- name: Recall |
|
type: recall |
|
value: 0.8562426152028357 |
|
- name: F1 |
|
type: f1 |
|
value: 0.8512137823022711 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.991867253328732 |
|
--- |
|
|
|
<!-- 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](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) on the Rodrigo1771/cantemist-fasttext-75-ner dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0478 |
|
- Precision: 0.8462 |
|
- Recall: 0.8562 |
|
- F1: 0.8512 |
|
- Accuracy: 0.9919 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.0571 | 0.9992 | 616 | 0.0266 | 0.7767 | 0.8492 | 0.8113 | 0.9906 | |
|
| 0.018 | 2.0 | 1233 | 0.0304 | 0.8075 | 0.8476 | 0.8271 | 0.9914 | |
|
| 0.0101 | 2.9992 | 1849 | 0.0356 | 0.8159 | 0.8468 | 0.8311 | 0.9906 | |
|
| 0.0057 | 4.0 | 2466 | 0.0365 | 0.8239 | 0.8460 | 0.8348 | 0.9910 | |
|
| 0.0027 | 4.9992 | 3082 | 0.0396 | 0.8211 | 0.8480 | 0.8343 | 0.9916 | |
|
| 0.0018 | 6.0 | 3699 | 0.0435 | 0.8306 | 0.8633 | 0.8467 | 0.9915 | |
|
| 0.0013 | 6.9992 | 4315 | 0.0478 | 0.8462 | 0.8562 | 0.8512 | 0.9919 | |
|
| 0.0008 | 8.0 | 4932 | 0.0469 | 0.8347 | 0.8614 | 0.8478 | 0.9915 | |
|
| 0.0004 | 8.9992 | 5548 | 0.0515 | 0.8414 | 0.8610 | 0.8511 | 0.9919 | |
|
| 0.0002 | 9.9919 | 6160 | 0.0520 | 0.8386 | 0.8598 | 0.8491 | 0.9918 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
