metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: mamba_text_classification
results: []
datasets:
- stanfordnlp/imdb
mamba_text_classification
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2105
- Accuracy: 0.9392
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 |
|---|---|---|---|---|
| 0.0254 | 0.1 | 625 | 0.2948 | 0.9176 |
| 1.1469 | 0.2 | 1250 | 0.2673 | 0.9204 |
| 0.0081 | 0.3 | 1875 | 0.2720 | 0.926 |
| 0.0011 | 0.4 | 2500 | 0.2633 | 0.9246 |
| 0.0184 | 0.5 | 3125 | 0.2350 | 0.9268 |
| 0.6982 | 0.6 | 3750 | 0.2286 | 0.937 |
| 0.9975 | 0.7 | 4375 | 0.2280 | 0.9378 |
| 0.0044 | 0.8 | 5000 | 0.2215 | 0.938 |
| 0.1517 | 0.9 | 5625 | 0.2111 | 0.9398 |
| 0.3835 | 1.0 | 6250 | 0.2105 | 0.9392 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2