|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: PlanTL-GOB-ES/bsc-bio-ehr-es |
|
tags: |
|
- token-classification |
|
- generated_from_trainer |
|
datasets: |
|
- Rodrigo1771/combined-train-distemist-dev-85-ner |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: output |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: Rodrigo1771/combined-train-distemist-dev-85-ner |
|
type: Rodrigo1771/combined-train-distemist-dev-85-ner |
|
config: CombinedTrainDisTEMISTDevNER |
|
split: validation |
|
args: CombinedTrainDisTEMISTDevNER |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.3152508603513856 |
|
- name: Recall |
|
type: recall |
|
value: 0.8144595226953674 |
|
- name: F1 |
|
type: f1 |
|
value: 0.45455732567249935 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.8564886649182308 |
|
--- |
|
|
|
<!-- 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/combined-train-distemist-dev-85-ner dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7006 |
|
- Precision: 0.3153 |
|
- Recall: 0.8145 |
|
- F1: 0.4546 |
|
- Accuracy: 0.8565 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.3191 | 1.0 | 541 | 0.4772 | 0.2725 | 0.8074 | 0.4075 | 0.8443 | |
|
| 0.1619 | 2.0 | 1082 | 0.4584 | 0.3041 | 0.7941 | 0.4398 | 0.8553 | |
|
| 0.11 | 3.0 | 1623 | 0.6447 | 0.2976 | 0.8000 | 0.4338 | 0.8435 | |
|
| 0.0764 | 4.0 | 2164 | 0.7413 | 0.2896 | 0.7871 | 0.4234 | 0.8399 | |
|
| 0.0567 | 5.0 | 2705 | 0.7006 | 0.3153 | 0.8145 | 0.4546 | 0.8565 | |
|
| 0.0428 | 6.0 | 3246 | 0.8112 | 0.3071 | 0.8210 | 0.4470 | 0.8504 | |
|
| 0.0332 | 7.0 | 3787 | 0.9046 | 0.3114 | 0.8070 | 0.4494 | 0.8533 | |
|
| 0.0257 | 8.0 | 4328 | 0.9723 | 0.3060 | 0.8109 | 0.4444 | 0.8482 | |
|
| 0.022 | 9.0 | 4869 | 1.0028 | 0.3087 | 0.8077 | 0.4467 | 0.8502 | |
|
| 0.0181 | 10.0 | 5410 | 1.0023 | 0.3116 | 0.8119 | 0.4504 | 0.8533 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
