mamba_text_classification
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2373
- Accuracy: 0.9412
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: 5e-05
- train_batch_size: 4
- 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: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|
| 0.0085 | 0.1 | 625 | 0.3822 | 0.908 |
| 2.2785 | 0.2 | 1250 | 0.3288 | 0.904 |
| 0.0482 | 0.3 | 1875 | 0.2656 | 0.9312 |
| 0.0051 | 0.4 | 2500 | 0.2493 | 0.9356 |
| 0.0016 | 0.5 | 3125 | 0.2741 | 0.936 |
| 2.21 | 0.6 | 3750 | 0.2366 | 0.936 |
| 0.0077 | 0.7 | 4375 | 0.2647 | 0.936 |
| 0.0015 | 0.8 | 5000 | 0.2410 | 0.94 |
| 0.0376 | 0.9 | 5625 | 0.2369 | 0.9412 |
| 0.0133 | 1.0 | 6250 | 0.2373 | 0.9412 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
