single_cls_mamba2-130m_redo
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2062
- Accuracy: 0.969
- Micro Precision: 0.969
- Micro Recall: 0.969
- Micro F1: 0.969
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Micro Precision | Micro Recall | Micro F1 |
|---|
| 0.1705 | 1.0 | 2500 | 0.1675 | 0.963 | 0.963 | 0.963 | 0.963 |
| 0.031 | 2.0 | 5000 | 0.1862 | 0.97 | 0.97 | 0.97 | 0.97 |
| 0.0185 | 3.0 | 7500 | 0.1889 | 0.972 | 0.972 | 0.972 | 0.972 |
| 0.0029 | 4.0 | 10000 | 0.2020 | 0.968 | 0.968 | 0.968 | 0.968 |
| 0.0002 | 5.0 | 12500 | 0.2062 | 0.969 | 0.969 | 0.969 | 0.969 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.1.1+cu118
- Datasets 3.1.0
- Tokenizers 0.20.3
