20231008-5-distilbert-base-multilingual-cased-new
This model is a fine-tuned version of distilbert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.5614
- Loss: 1.9964
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 2.9949 | 1.82 | 200 | 0.3868 | 2.5810 |
| 2.5887 | 3.64 | 400 | 0.4463 | 2.5529 |
| 2.3369 | 5.45 | 600 | 0.4665 | 2.4076 |
| 2.2815 | 7.27 | 800 | 0.5133 | 2.2435 |
| 2.1494 | 9.09 | 1000 | 0.5 | 2.1755 |
| 2.0746 | 10.91 | 1200 | 0.5523 | 1.9893 |
| 1.9617 | 12.73 | 1400 | 0.5648 | 1.8462 |
| 1.9549 | 14.55 | 1600 | 0.5392 | 1.8725 |
| 1.9192 | 16.36 | 1800 | 0.5605 | 2.0018 |
| 1.8967 | 18.18 | 2000 | 0.6077 | 1.7557 |
| 1.899 | 20.0 | 2200 | 0.5614 | 1.9964 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1