modernbert-large-email-importance-classifier
This model is a fine-tuned version of answerdotai/ModernBERT-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9648
- Accuracy: 0.368
- F1 Macro: 0.3267
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- 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: 5
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|---|---|---|---|---|---|
| 1.5192 | 1.0 | 155 | 1.7710 | 0.252 | 0.1952 |
| 1.3485 | 2.0 | 310 | 1.9118 | 0.3 | 0.2403 |
| 1.1313 | 3.0 | 465 | 1.9024 | 0.296 | 0.2535 |
| 1.0355 | 4.0 | 620 | 2.0135 | 0.332 | 0.2880 |
| 0.9768 | 5.0 | 775 | 1.9648 | 0.368 | 0.3267 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.5.1+cu121
- Datasets 4.4.1
- Tokenizers 0.22.1