distilbert-base-multilingual-cased-aoe-hyper
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: 0.4021
- Accuracy: 0.8799
- Recall: 0.8013
- Precision: 0.7246
- F1: 0.7610
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: 6.292247538797816e-06
- train_batch_size: 8
- eval_batch_size: 16
- seed: 16
- 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 |
|---|---|---|---|---|---|---|---|
| 0.2696 | 1.0 | 654 | 0.3423 | 0.8699 | 0.6090 | 0.7983 | 0.6909 |
| 0.4222 | 2.0 | 1308 | 0.3537 | 0.8814 | 0.7596 | 0.7476 | 0.7536 |
| 0.3135 | 3.0 | 1962 | 0.3992 | 0.8699 | 0.8205 | 0.6919 | 0.7507 |
| 0.2558 | 4.0 | 2616 | 0.4021 | 0.8799 | 0.8013 | 0.7246 | 0.7610 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3