|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: PlanTL-GOB-ES/bsc-bio-ehr-es |
|
tags: |
|
- token-classification |
|
- generated_from_trainer |
|
datasets: |
|
- Rodrigo1771/symptemist-75-ner |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: output |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: Rodrigo1771/symptemist-75-ner |
|
type: Rodrigo1771/symptemist-75-ner |
|
config: SympTEMIST NER |
|
split: validation |
|
args: SympTEMIST NER |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.6896 |
|
- name: Recall |
|
type: recall |
|
value: 0.7077175697865353 |
|
- name: F1 |
|
type: f1 |
|
value: 0.6985413290113451 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9496936058263018 |
|
--- |
|
|
|
<!-- 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/symptemist-75-ner dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3089 |
|
- Precision: 0.6896 |
|
- Recall: 0.7077 |
|
- F1: 0.6985 |
|
- Accuracy: 0.9497 |
|
|
|
## 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 | 248 | 0.1649 | 0.5942 | 0.6820 | 0.6351 | 0.9478 | |
|
| No log | 2.0 | 496 | 0.1815 | 0.6558 | 0.6705 | 0.6631 | 0.9476 | |
|
| 0.134 | 3.0 | 744 | 0.2111 | 0.6651 | 0.6979 | 0.6811 | 0.9492 | |
|
| 0.134 | 4.0 | 992 | 0.2523 | 0.6692 | 0.7121 | 0.6900 | 0.9488 | |
|
| 0.026 | 5.0 | 1240 | 0.2771 | 0.6584 | 0.7132 | 0.6847 | 0.9491 | |
|
| 0.026 | 6.0 | 1488 | 0.2968 | 0.6668 | 0.7165 | 0.6908 | 0.9486 | |
|
| 0.0084 | 7.0 | 1736 | 0.3089 | 0.6896 | 0.7077 | 0.6985 | 0.9497 | |
|
| 0.0084 | 8.0 | 1984 | 0.3188 | 0.6825 | 0.7072 | 0.6946 | 0.9499 | |
|
| 0.0042 | 9.0 | 2232 | 0.3296 | 0.6809 | 0.7159 | 0.6980 | 0.9495 | |
|
| 0.0042 | 10.0 | 2480 | 0.3328 | 0.6814 | 0.7165 | 0.6985 | 0.9499 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
