|
--- |
|
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-85-ner |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: output |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: Rodrigo1771/cantemist-85-ner |
|
type: Rodrigo1771/cantemist-85-ner |
|
config: CantemistNer |
|
split: validation |
|
args: CantemistNer |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.8399232245681382 |
|
- name: Recall |
|
type: recall |
|
value: 0.8617565970854667 |
|
- name: F1 |
|
type: f1 |
|
value: 0.8506998444790046 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9916544445403043 |
|
--- |
|
|
|
<!-- 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-85-ner dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0496 |
|
- Precision: 0.8399 |
|
- Recall: 0.8618 |
|
- F1: 0.8507 |
|
- Accuracy: 0.9917 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.0542 | 1.0 | 511 | 0.0271 | 0.7485 | 0.7972 | 0.7721 | 0.9895 | |
|
| 0.0184 | 2.0 | 1022 | 0.0277 | 0.7897 | 0.8519 | 0.8196 | 0.9906 | |
|
| 0.0103 | 3.0 | 1533 | 0.0305 | 0.8238 | 0.8488 | 0.8361 | 0.9914 | |
|
| 0.0058 | 4.0 | 2044 | 0.0320 | 0.8197 | 0.8539 | 0.8364 | 0.9913 | |
|
| 0.0041 | 5.0 | 2555 | 0.0374 | 0.8397 | 0.8417 | 0.8407 | 0.9917 | |
|
| 0.0026 | 6.0 | 3066 | 0.0427 | 0.8368 | 0.8503 | 0.8435 | 0.9917 | |
|
| 0.0015 | 7.0 | 3577 | 0.0451 | 0.8207 | 0.8598 | 0.8398 | 0.9912 | |
|
| 0.0013 | 8.0 | 4088 | 0.0448 | 0.8318 | 0.8629 | 0.8471 | 0.9916 | |
|
| 0.0007 | 9.0 | 4599 | 0.0496 | 0.8399 | 0.8618 | 0.8507 | 0.9917 | |
|
| 0.0006 | 10.0 | 5110 | 0.0503 | 0.8399 | 0.8618 | 0.8507 | 0.9916 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
