mamba_imbalanced
This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2374
- Accuracy: 0.9367
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: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|
| 0.0526 | 0.1 | 210 | 0.4061 | 0.8257 |
| 1.7356 | 0.2 | 420 | 0.5385 | 0.7952 |
| 0.0 | 0.3 | 630 | 0.3027 | 0.8819 |
| 0.0136 | 0.4 | 840 | 0.2634 | 0.9181 |
| 0.0246 | 0.5 | 1050 | 0.2984 | 0.9243 |
| 0.0012 | 0.6 | 1260 | 0.2351 | 0.9295 |
| 0.0033 | 0.7 | 1470 | 0.2207 | 0.9348 |
| 0.0019 | 0.8 | 1680 | 0.2407 | 0.9381 |
| 0.0002 | 0.9 | 1890 | 0.2384 | 0.9362 |
| 0.0846 | 1.0 | 2100 | 0.2374 | 0.9367 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
