metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: mamba_text_classification_1
results: []
mamba_text_classification_1
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2164
- Accuracy: 0.944
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 |
|---|---|---|---|---|
| 0.1091 | 0.1 | 625 | 0.3236 | 0.9116 |
| 1.8143 | 0.2 | 1250 | 0.2305 | 0.9296 |
| 0.0028 | 0.3 | 1875 | 0.2749 | 0.9284 |
| 0.0052 | 0.4 | 2500 | 0.2432 | 0.936 |
| 0.0007 | 0.5 | 3125 | 0.2512 | 0.9348 |
| 1.6534 | 0.6 | 3750 | 0.2360 | 0.9384 |
| 1.472 | 0.7 | 4375 | 0.2378 | 0.9388 |
| 0.0049 | 0.8 | 5000 | 0.2196 | 0.9416 |
| 0.017 | 0.9 | 5625 | 0.2171 | 0.9436 |
| 0.3069 | 1.0 | 6250 | 0.2164 | 0.944 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1