|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: BERT_ep9_lr2 |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# BERT_ep9_lr2 |
|
|
|
This model is a fine-tuned version of [ajtamayoh/NER_EHR_Spanish_model_Mulitlingual_BERT](https://huggingface.co/ajtamayoh/NER_EHR_Spanish_model_Mulitlingual_BERT) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0899 |
|
- Precision: 0.8601 |
|
- Recall: 0.8819 |
|
- F1: 0.8709 |
|
- Accuracy: 0.9780 |
|
|
|
## 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-06 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 9 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 467 | 0.0847 | 0.8136 | 0.8571 | 0.8348 | 0.9722 | |
|
| 0.1137 | 2.0 | 934 | 0.0748 | 0.8367 | 0.8735 | 0.8547 | 0.9755 | |
|
| 0.0747 | 3.0 | 1401 | 0.0747 | 0.8550 | 0.8702 | 0.8625 | 0.9769 | |
|
| 0.0603 | 4.0 | 1868 | 0.0805 | 0.8485 | 0.8765 | 0.8622 | 0.9769 | |
|
| 0.0479 | 5.0 | 2335 | 0.0830 | 0.8607 | 0.8778 | 0.8692 | 0.9776 | |
|
| 0.0433 | 6.0 | 2802 | 0.0853 | 0.8560 | 0.8803 | 0.8680 | 0.9775 | |
|
| 0.0352 | 7.0 | 3269 | 0.0869 | 0.8567 | 0.8852 | 0.8707 | 0.9778 | |
|
| 0.0329 | 8.0 | 3736 | 0.0884 | 0.8583 | 0.8822 | 0.8701 | 0.9779 | |
|
| 0.0305 | 9.0 | 4203 | 0.0899 | 0.8601 | 0.8819 | 0.8709 | 0.9780 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|