xlm-roberta-large
This model is a fine-tuned version of makhataei/xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 7.1503
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: 1e-06
- train_batch_size: 14
- eval_batch_size: 14
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0416 | 1.0 | 202 | 6.9265 |
| 0.0306 | 2.0 | 404 | 7.2318 |
| 0.0272 | 3.0 | 606 | 7.4132 |
| 0.0776 | 4.0 | 808 | 7.3535 |
| 0.2776 | 5.0 | 1010 | 7.1503 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2