|
--- |
|
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-8-ner |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: output |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: Rodrigo1771/symptemist-8-ner |
|
type: Rodrigo1771/symptemist-8-ner |
|
config: SympTEMIST NER |
|
split: validation |
|
args: SympTEMIST NER |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.6832101372756072 |
|
- name: Recall |
|
type: recall |
|
value: 0.7082649151614668 |
|
- name: F1 |
|
type: f1 |
|
value: 0.6955119591507659 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9498058968847252 |
|
--- |
|
|
|
<!-- 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-8-ner dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3003 |
|
- Precision: 0.6832 |
|
- Recall: 0.7083 |
|
- F1: 0.6955 |
|
- Accuracy: 0.9498 |
|
|
|
## 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 | 0.9976 | 209 | 0.1511 | 0.5818 | 0.6694 | 0.6226 | 0.9457 | |
|
| No log | 2.0 | 419 | 0.1794 | 0.6113 | 0.7017 | 0.6534 | 0.9465 | |
|
| 0.1282 | 2.9976 | 628 | 0.2102 | 0.6572 | 0.6979 | 0.6769 | 0.9470 | |
|
| 0.1282 | 4.0 | 838 | 0.2329 | 0.6605 | 0.6984 | 0.6789 | 0.9489 | |
|
| 0.0255 | 4.9976 | 1047 | 0.2591 | 0.6646 | 0.6973 | 0.6806 | 0.9491 | |
|
| 0.0255 | 6.0 | 1257 | 0.2737 | 0.6599 | 0.6968 | 0.6778 | 0.9491 | |
|
| 0.0255 | 6.9976 | 1466 | 0.2876 | 0.6687 | 0.7094 | 0.6884 | 0.9492 | |
|
| 0.0085 | 8.0 | 1676 | 0.3003 | 0.6832 | 0.7083 | 0.6955 | 0.9498 | |
|
| 0.0085 | 8.9976 | 1885 | 0.3072 | 0.6697 | 0.7170 | 0.6926 | 0.9492 | |
|
| 0.004 | 9.9761 | 2090 | 0.3125 | 0.6711 | 0.7137 | 0.6918 | 0.9492 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
