metadata
license: mit
base_model: flax-community/indonesian-roberta-base
tags:
- generated_from_trainer
model-index:
- name: topic-classification-tweet-10
results: []
topic-classification-tweet-10
This model is a fine-tuned version of flax-community/indonesian-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0626
- Balanced Accuracy: 0.5160
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: 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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Balanced Accuracy |
|---|---|---|---|---|
| 1.1552 | 1.0 | 504 | 1.1809 | 0.3828 |
| 0.8732 | 2.0 | 1008 | 0.9191 | 0.4076 |
| 0.6933 | 3.0 | 1512 | 0.8095 | 0.4664 |
| 0.5438 | 4.0 | 2016 | 0.9478 | 0.5007 |
| 0.4576 | 5.0 | 2520 | 1.0626 | 0.5160 |
| 0.3853 | 6.0 | 3024 | 1.0753 | 0.4874 |
| 0.2755 | 7.0 | 3528 | 1.1464 | 0.5106 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1