distilbert-base-multilingual-cased-aoe-test-hyperparamter-test-results-unchecked
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: 0.3312
- Accuracy: 0.9072
- Recall: 0.6316
- Precision: 0.7
- F1: 0.6640
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: 1.324640265180116e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 23
- optimizer: Use 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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1 |
|---|---|---|---|---|---|---|---|
| 0.5941 | 1.0 | 915 | 0.3405 | 0.9050 | 0.5414 | 0.7347 | 0.6234 |
| 0.2929 | 2.0 | 1830 | 0.3312 | 0.9072 | 0.6316 | 0.7 | 0.6640 |
| 0.1391 | 3.0 | 2745 | 0.4197 | 0.9072 | 0.6090 | 0.7105 | 0.6559 |
| 0.3502 | 4.0 | 3660 | 0.4577 | 0.9083 | 0.6241 | 0.7094 | 0.664 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3