phobert-vsmec-emotion-recognition
This model is a fine-tuned version of vinai/phobert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0830
- Accuracy: 0.6152
- F1: 0.5827
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: 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.8725 | 1.0 | 347 | 1.8562 | 0.3105 | 0.2389 |
| 1.3068 | 2.0 | 694 | 1.3418 | 0.4913 | 0.4652 |
| 1.2032 | 3.0 | 1041 | 1.1452 | 0.5743 | 0.5450 |
| 0.8067 | 4.0 | 1388 | 1.1615 | 0.5598 | 0.5326 |
| 0.6503 | 5.0 | 1735 | 1.3213 | 0.5860 | 0.5654 |
| 0.439 | 6.0 | 2082 | 1.2085 | 0.6152 | 0.5886 |
| 0.4644 | 7.0 | 2429 | 1.3908 | 0.6283 | 0.5971 |
| 0.2703 | 8.0 | 2776 | 1.6088 | 0.5875 | 0.5588 |
| 0.2721 | 9.0 | 3123 | 1.8229 | 0.6050 | 0.5654 |
| 0.195 | 10.0 | 3470 | 2.0830 | 0.6152 | 0.5827 |
Framework versions
- Transformers 4.57.2
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.22.2