|
--- |
|
language: |
|
- vi |
|
base_model: vinai/phobert-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: phobert-base_baseline_syllables |
|
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. --> |
|
|
|
# phobert-base_baseline_syllables |
|
|
|
This model is a fine-tuned version of [vinai/phobert-base](https://huggingface.co/vinai/phobert-base) on the covid19_ner dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0881 |
|
- Patient Id: 0.9817 |
|
- Name: 0.9476 |
|
- Gender: 0.9385 |
|
- Age: 0.9684 |
|
- Job: 0.7463 |
|
- Location: 0.9427 |
|
- Organization: 0.8958 |
|
- Date: 0.9883 |
|
- Symptom And Disease: 0.8849 |
|
- Transportation: 0.9943 |
|
- F1 Macro: 0.9288 |
|
- F1 Micro: 0.9448 |
|
|
|
## 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: 2e-05 |
|
- 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: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Patient Id | Name | Gender | Age | Job | Location | Organization | Date | Symptom And Disease | Transportation | F1 Macro | F1 Micro | |
|
|:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:------:|:------:|:------:|:--------:|:------------:|:------:|:-------------------:|:--------------:|:--------:|:--------:| |
|
| 0.3091 | 1.0 | 629 | 0.1389 | 0.9660 | 0.9316 | 0.8391 | 0.9008 | 0.0 | 0.9237 | 0.8249 | 0.9865 | 0.8435 | 0.9444 | 0.8160 | 0.9115 | |
|
| 0.0807 | 2.0 | 1258 | 0.0955 | 0.9809 | 0.9178 | 0.9481 | 0.9707 | 0.4646 | 0.9390 | 0.8704 | 0.9883 | 0.8628 | 0.9831 | 0.8926 | 0.9358 | |
|
| 0.0491 | 3.0 | 1887 | 0.0898 | 0.9828 | 0.9418 | 0.9401 | 0.9671 | 0.6824 | 0.9457 | 0.9007 | 0.9856 | 0.8715 | 0.9886 | 0.9206 | 0.9436 | |
|
| 0.0375 | 4.0 | 2516 | 0.0886 | 0.9817 | 0.9452 | 0.9354 | 0.9644 | 0.7509 | 0.9406 | 0.8887 | 0.9869 | 0.8805 | 0.9943 | 0.9269 | 0.9425 | |
|
| 0.0282 | 5.0 | 3145 | 0.0881 | 0.9817 | 0.9476 | 0.9385 | 0.9684 | 0.7463 | 0.9427 | 0.8958 | 0.9883 | 0.8849 | 0.9943 | 0.9288 | 0.9448 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
