roberta-fine-sentiment-hineng-concat
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1126
- Accuracy: 0.8669
- Precision: 0.8667
- Recall: 0.8669
- F1: 0.8668
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.5814 | 1.0 | 4293 | 0.6920 | 0.8249 | 0.8304 | 0.8249 | 0.8257 |
| 0.5169 | 2.0 | 8586 | 0.5919 | 0.8459 | 0.8499 | 0.8459 | 0.8465 |
| 0.4274 | 3.0 | 12879 | 0.7775 | 0.8512 | 0.8513 | 0.8512 | 0.8504 |
| 0.3246 | 4.0 | 17172 | 0.7757 | 0.8522 | 0.8593 | 0.8522 | 0.8528 |
| 0.22 | 5.0 | 21465 | 0.9306 | 0.8574 | 0.8574 | 0.8574 | 0.8574 |
| 0.1226 | 6.0 | 25758 | 0.9663 | 0.8627 | 0.8632 | 0.8627 | 0.8628 |
| 0.085 | 7.0 | 30051 | 1.0266 | 0.8653 | 0.8651 | 0.8653 | 0.8651 |
| 0.0713 | 8.0 | 34344 | 1.1126 | 0.8669 | 0.8667 | 0.8669 | 0.8668 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1