Improved-xlm-attempt2
This model is a fine-tuned version of cardiffnlp/twitter-xlm-roberta-base-sentiment on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3637
- Accuracy: 0.87
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 | Accuracy |
|---|---|---|---|---|
| No log | 0.07 | 50 | 0.4087 | 0.86 |
| No log | 0.14 | 100 | 0.3930 | 0.86 |
| No log | 0.21 | 150 | 0.4688 | 0.79 |
| No log | 0.27 | 200 | 0.3834 | 0.82 |
| No log | 0.34 | 250 | 0.4249 | 0.83 |
| No log | 0.41 | 300 | 0.5777 | 0.8 |
| No log | 0.48 | 350 | 0.4752 | 0.82 |
| No log | 0.55 | 400 | 0.3080 | 0.89 |
| No log | 0.62 | 450 | 0.4125 | 0.83 |
| 0.3475 | 0.68 | 500 | 0.3273 | 0.9 |
| 0.3475 | 0.75 | 550 | 0.6456 | 0.77 |
| 0.3475 | 0.82 | 600 | 0.6110 | 0.77 |
| 0.3475 | 0.89 | 650 | 0.3898 | 0.85 |
| 0.3475 | 0.96 | 700 | 0.4062 | 0.87 |
| 0.3475 | 1.03 | 750 | 0.3637 | 0.87 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.7
- Tokenizers 0.14.1