imbalanced_mamba
This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3386
- Accuracy: 0.9310
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|
| 0.2439 | 0.2 | 420 | 0.3255 | 0.8976 |
| 0.3555 | 0.4 | 840 | 0.2615 | 0.9110 |
| 0.0069 | 0.6 | 1260 | 0.2734 | 0.9233 |
| 1.6392 | 0.8 | 1680 | 0.2935 | 0.9271 |
| 0.0001 | 1.0 | 2100 | 0.2506 | 0.9267 |
| 0.002 | 1.2 | 2520 | 0.3194 | 0.9286 |
| 0.0 | 1.4 | 2940 | 0.3274 | 0.9276 |
| 0.0 | 1.6 | 3360 | 0.3455 | 0.9310 |
| 0.0 | 1.8 | 3780 | 0.3400 | 0.9305 |
| 0.7975 | 2.0 | 4200 | 0.3386 | 0.9310 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
