20231008-9-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: 0.5609
- Loss: 1.8042
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 |
|---|---|---|---|---|
| 3.0492 | 1.82 | 200 | 0.3888 | 2.6521 |
| 2.589 | 3.64 | 400 | 0.4582 | 2.4219 |
| 2.35 | 5.45 | 600 | 0.4440 | 2.5098 |
| 2.2866 | 7.27 | 800 | 0.4607 | 2.2587 |
| 2.1603 | 9.09 | 1000 | 0.5060 | 2.1101 |
| 2.0746 | 10.91 | 1200 | 0.5040 | 2.2520 |
| 1.9926 | 12.73 | 1400 | 0.5512 | 1.8800 |
| 1.9296 | 14.55 | 1600 | 0.5682 | 1.8248 |
| 1.9172 | 16.36 | 1800 | 0.56 | 1.9773 |
| 1.8996 | 18.18 | 2000 | 0.5735 | 1.8932 |
| 1.8936 | 20.0 | 2200 | 0.5609 | 1.8042 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1