|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: BERT_ep6_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_ep6_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: 0.1977 |
|
- Precision: 0.6776 |
|
- Recall: 0.7052 |
|
- F1: 0.6911 |
|
- Accuracy: 0.9476 |
|
|
|
## 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: 6 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 467 | 0.2591 | 0.6800 | 0.6636 | 0.6717 | 0.9439 | |
|
| 0.2747 | 2.0 | 934 | 0.2325 | 0.6757 | 0.6824 | 0.6790 | 0.9452 | |
|
| 0.2444 | 3.0 | 1401 | 0.2158 | 0.6761 | 0.6955 | 0.6857 | 0.9465 | |
|
| 0.2184 | 4.0 | 1868 | 0.2052 | 0.6780 | 0.7025 | 0.6900 | 0.9471 | |
|
| 0.2087 | 5.0 | 2335 | 0.1994 | 0.6777 | 0.7049 | 0.6910 | 0.9475 | |
|
| 0.1984 | 6.0 | 2802 | 0.1977 | 0.6776 | 0.7052 | 0.6911 | 0.9476 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.2 |
|
|
