|
--- |
|
license: mit |
|
base_model: indobenchmark/indobart |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: bdc2024-indobert-filtered-1 |
|
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. --> |
|
|
|
# bdc2024-indobert-filtered-1 |
|
|
|
This model is a fine-tuned version of [indobenchmark/indobart](https://huggingface.co/indobenchmark/indobart) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5705 |
|
- Accuracy: 0.8317 |
|
- Balanced Accuracy: 0.6247 |
|
- Precision: 0.8316 |
|
- Recall: 0.8317 |
|
- F1: 0.8173 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- 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 | Accuracy | Balanced Accuracy | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------------:|:---------:|:------:|:------:| |
|
| No log | 1.0 | 298 | 0.9280 | 0.6998 | 0.3859 | 0.6874 | 0.6998 | 0.6350 | |
|
| 0.886 | 2.0 | 596 | 0.7598 | 0.7648 | 0.4862 | 0.7263 | 0.7648 | 0.7251 | |
|
| 0.886 | 3.0 | 894 | 0.6400 | 0.7992 | 0.5757 | 0.8018 | 0.7992 | 0.7772 | |
|
| 0.5453 | 4.0 | 1192 | 0.5738 | 0.8298 | 0.6337 | 0.8321 | 0.8298 | 0.8184 | |
|
| 0.5453 | 5.0 | 1490 | 0.5705 | 0.8317 | 0.6247 | 0.8316 | 0.8317 | 0.8173 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.1 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.13.3 |
|
|
