metadata
license: apache-2.0
tags:
- generated_from_trainer
base_model: indolem/indobertweet-base-uncased
model-index:
- name: indonesia-election-topic-classification
results: []
indonesia-election-topic-classification
This model is a fine-tuned version of indolem/indobertweet-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5418
- Balanced Accuracy: 0.4849
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 |
|---|---|---|---|---|
| No log | 1.0 | 446 | 0.8460 | 0.3867 |
| 0.8653 | 2.0 | 892 | 0.9161 | 0.4401 |
| 0.5112 | 3.0 | 1338 | 1.1297 | 0.4674 |
| 0.3104 | 4.0 | 1784 | 1.3028 | 0.4474 |
| 0.1834 | 5.0 | 2230 | 1.4835 | 0.4815 |
| 0.0876 | 6.0 | 2676 | 1.5418 | 0.4849 |
| 0.048 | 7.0 | 3122 | 1.5620 | 0.4737 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1