metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: mamba_text_classification
results: []
mamba_text_classification
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2469
- Accuracy: 0.928
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 |
|---|---|---|---|---|
| 0.0078 | 0.1 | 625 | 0.4242 | 0.884 |
| 1.3233 | 0.2 | 1250 | 0.2781 | 0.92 |
| 0.0583 | 0.3 | 1875 | 0.2481 | 0.916 |
| 0.0012 | 0.4 | 2500 | 0.3076 | 0.916 |
| 0.0007 | 0.5 | 3125 | 0.2800 | 0.916 |
| 2.3209 | 0.6 | 3750 | 0.2640 | 0.92 |
| 1.2896 | 0.7 | 4375 | 0.2880 | 0.92 |
| 0.0028 | 0.8 | 5000 | 0.2491 | 0.928 |
| 0.0041 | 0.9 | 5625 | 0.2486 | 0.928 |
| 0.0466 | 1.0 | 6250 | 0.2469 | 0.928 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2