NusaBERT-Plutchik-Emotion-Classifier
This model is a fine-tuned version of Aardiiiiy/EmoSense-ID-Indonesian-Emotion-Classifier on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8873
- F1: 0.6419
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: 64
- eval_batch_size: 256
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.9680 | 1.0 | 1707 | 0.8993 | 0.6121 |
| 0.8416 | 2.0 | 3414 | 0.8629 | 0.6290 |
| 0.7233 | 3.0 | 5121 | 0.8632 | 0.6383 |
| 0.6380 | 4.0 | 6828 | 0.8709 | 0.6403 |
| 0.5863 | 5.0 | 8535 | 0.8873 | 0.6419 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.13.0+cu132
- Datasets 5.0.0
- Tokenizers 0.22.2