|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: BERT_ep9_lr4 |
|
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_lr4 |
|
|
|
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: 0.1801 |
|
- Precision: 0.6659 |
|
- Recall: 0.7266 |
|
- F1: 0.6950 |
|
- Accuracy: 0.9478 |
|
|
|
## 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-08 |
|
- 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 | 0.2732 | 0.6635 | 0.6619 | 0.6627 | 0.9415 | |
|
| 0.2772 | 2.0 | 934 | 0.2436 | 0.6562 | 0.6820 | 0.6688 | 0.9426 | |
|
| 0.2379 | 3.0 | 1401 | 0.2224 | 0.6550 | 0.6980 | 0.6758 | 0.9437 | |
|
| 0.2142 | 4.0 | 1868 | 0.2071 | 0.6597 | 0.7104 | 0.6841 | 0.9450 | |
|
| 0.1968 | 5.0 | 2335 | 0.1960 | 0.6597 | 0.7165 | 0.6869 | 0.9461 | |
|
| 0.1888 | 6.0 | 2802 | 0.1884 | 0.6610 | 0.7195 | 0.6890 | 0.9468 | |
|
| 0.1788 | 7.0 | 3269 | 0.1835 | 0.6641 | 0.7244 | 0.6929 | 0.9474 | |
|
| 0.1768 | 8.0 | 3736 | 0.1808 | 0.6652 | 0.7258 | 0.6942 | 0.9477 | |
|
| 0.1695 | 9.0 | 4203 | 0.1801 | 0.6659 | 0.7266 | 0.6950 | 0.9478 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|