metadata
license: mit
base_model: indolem/indobert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: ROS-text-classification
results: []
ROS-text-classification
This model is a fine-tuned version of indolem/indobert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8096
- Balanced Accuracy: 0.7524
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: 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Balanced Accuracy |
---|---|---|---|---|
1.4134 | 1.0 | 139 | 1.2061 | 0.5871 |
0.7846 | 2.0 | 278 | 0.9400 | 0.6932 |
0.6999 | 3.0 | 417 | 0.8096 | 0.7524 |
0.3644 | 4.0 | 556 | 0.8431 | 0.7721 |
0.3832 | 5.0 | 695 | 0.9038 | 0.7594 |
0.2631 | 6.0 | 834 | 1.0126 | 0.7800 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1