news-topic-distilbert-multilingual-4class
This model is a fine-tuned version of distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1375
- Accuracy: 0.9167
- Precision: 0.9226
- Recall: 0.9167
- F1: 0.9164
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_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 1.3718 | 1.0 | 7 | 1.3442 | 0.3333 | 0.5682 | 0.3333 | 0.25 |
| 1.2955 | 2.0 | 14 | 1.2759 | 0.75 | 0.7827 | 0.75 | 0.7423 |
| 1.1963 | 3.0 | 21 | 1.1701 | 0.8333 | 0.8571 | 0.8333 | 0.8205 |
| 1.0496 | 4.0 | 28 | 1.0466 | 0.7917 | 0.7887 | 0.7917 | 0.7814 |
| 0.9263 | 5.0 | 35 | 0.9435 | 0.7917 | 0.7887 | 0.7917 | 0.7814 |
| 0.8226 | 6.0 | 42 | 0.8655 | 0.7917 | 0.7887 | 0.7917 | 0.7814 |
| 0.7426 | 7.0 | 49 | 0.8214 | 0.7917 | 0.7887 | 0.7917 | 0.7814 |
| 0.6990 | 8.0 | 56 | 0.8079 | 0.7917 | 0.7887 | 0.7917 | 0.7814 |
Framework versions
- Transformers 5.12.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2