results_final
This model is a fine-tuned version of w11wo/indonesian-roberta-base-sentiment-classifier on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4223
- Accuracy: 0.8881
- F1 Macro: 0.8879
- F1 Weighted: 0.8879
- Precision Macro: 0.8889
- Recall Macro: 0.8881
- Precision Weighted: 0.8889
- Recall Weighted: 0.8881
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: 4e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Weighted | Precision Macro | Recall Macro | Precision Weighted | Recall Weighted |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.366 | 1.7182 | 500 | 0.4078 | 0.8830 | 0.8828 | 0.8828 | 0.8842 | 0.8829 | 0.8841 | 0.8830 |
| 0.2238 | 3.4364 | 1000 | 0.4223 | 0.8881 | 0.8879 | 0.8879 | 0.8889 | 0.8881 | 0.8889 | 0.8881 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1
- Downloads last month
- 3