Hal_distilbert-base-multilingual-cased_finetuned
This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0061
- Accuracy: 0.7029
- F1: 0.7029
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.0574 | 1.0 | 350 | 1.0402 | 0.4957 | 0.4957 |
| 0.8715 | 2.0 | 700 | 0.8827 | 0.605 | 0.605 |
| 0.7597 | 3.0 | 1050 | 0.8572 | 0.6457 | 0.6457 |
| 0.6288 | 4.0 | 1400 | 0.7878 | 0.685 | 0.685 |
| 0.562 | 5.0 | 1750 | 0.7963 | 0.6986 | 0.6986 |
| 0.4641 | 6.0 | 2100 | 0.8860 | 0.68 | 0.68 |
| 0.404 | 7.0 | 2450 | 0.9763 | 0.6786 | 0.6786 |
| 0.3175 | 8.0 | 2800 | 1.0061 | 0.7029 | 0.7029 |
| 0.2651 | 9.0 | 3150 | 1.1665 | 0.6886 | 0.6886 |
| 0.2106 | 10.0 | 3500 | 1.2857 | 0.6864 | 0.6864 |
| 0.1346 | 11.0 | 3850 | 1.5759 | 0.6936 | 0.6936 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0