distilbert-base-multilingual-cased-bg-wikipedia
This model is a fine-tuned version of distilbert-base-multilingual-cased on the wikipedia dataset. It achieves the following results on the evaluation set:
- Loss: 1.2419
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: 42
- eval_batch_size: 42
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4974 | 1.0 | 1191 | 1.2832 |
| 1.4301 | 2.0 | 2382 | 1.2626 |
| 1.3846 | 3.0 | 3573 | 1.2203 |
| 1.3635 | 4.0 | 4764 | 1.2335 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3