|
--- |
|
license: mit |
|
base_model: indolem/indobert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: sentiment-pt-pl30-2 |
|
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. --> |
|
|
|
# sentiment-pt-pl30-2 |
|
|
|
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co./indolem/indobert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2988 |
|
- Accuracy: 0.8822 |
|
- Precision: 0.8574 |
|
- Recall: 0.8592 |
|
- F1: 0.8583 |
|
|
|
## 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: 30 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 0.541 | 1.0 | 122 | 0.4985 | 0.7293 | 0.6648 | 0.6310 | 0.6397 | |
|
| 0.4477 | 2.0 | 244 | 0.4465 | 0.7644 | 0.7427 | 0.7883 | 0.7462 | |
|
| 0.347 | 3.0 | 366 | 0.3237 | 0.8647 | 0.8556 | 0.8067 | 0.8255 | |
|
| 0.3005 | 4.0 | 488 | 0.2992 | 0.8922 | 0.8734 | 0.8637 | 0.8683 | |
|
| 0.281 | 5.0 | 610 | 0.2869 | 0.8647 | 0.8398 | 0.8292 | 0.8342 | |
|
| 0.2419 | 6.0 | 732 | 0.2945 | 0.8747 | 0.8443 | 0.8663 | 0.8537 | |
|
| 0.2394 | 7.0 | 854 | 0.2835 | 0.8772 | 0.8504 | 0.8556 | 0.8530 | |
|
| 0.2192 | 8.0 | 976 | 0.2803 | 0.8772 | 0.8535 | 0.8481 | 0.8507 | |
|
| 0.2144 | 9.0 | 1098 | 0.2861 | 0.8747 | 0.8499 | 0.8463 | 0.8481 | |
|
| 0.2056 | 10.0 | 1220 | 0.2724 | 0.8922 | 0.8706 | 0.8687 | 0.8697 | |
|
| 0.1822 | 11.0 | 1342 | 0.2813 | 0.8872 | 0.8606 | 0.8727 | 0.8662 | |
|
| 0.1817 | 12.0 | 1464 | 0.2900 | 0.8872 | 0.8760 | 0.8452 | 0.8584 | |
|
| 0.1621 | 13.0 | 1586 | 0.2926 | 0.8947 | 0.8773 | 0.8655 | 0.8711 | |
|
| 0.1577 | 14.0 | 1708 | 0.2904 | 0.8922 | 0.8683 | 0.8737 | 0.8710 | |
|
| 0.1612 | 15.0 | 1830 | 0.2996 | 0.8847 | 0.8648 | 0.8534 | 0.8588 | |
|
| 0.1496 | 16.0 | 1952 | 0.2970 | 0.8872 | 0.8624 | 0.8677 | 0.8650 | |
|
| 0.149 | 17.0 | 2074 | 0.2948 | 0.8822 | 0.8574 | 0.8592 | 0.8583 | |
|
| 0.1424 | 18.0 | 2196 | 0.2977 | 0.8847 | 0.8609 | 0.8609 | 0.8609 | |
|
| 0.1383 | 19.0 | 2318 | 0.2990 | 0.8847 | 0.8621 | 0.8584 | 0.8602 | |
|
| 0.1407 | 20.0 | 2440 | 0.2988 | 0.8822 | 0.8574 | 0.8592 | 0.8583 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.15.2 |
|
|