metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ViT_MNIST
results: []
ViT_MNIST
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2367
- Accuracy: 0.9379
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: 5500
- eval_batch_size: 5500
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3795 | 1.0 | 11 | 0.3894 | 0.897 |
| 0.3668 | 2.0 | 22 | 0.3547 | 0.9059 |
| 0.3441 | 3.0 | 33 | 0.3186 | 0.9174 |
| 0.3163 | 4.0 | 44 | 0.2998 | 0.9235 |
| 0.299 | 5.0 | 55 | 0.2860 | 0.9259 |
| 0.2788 | 6.0 | 66 | 0.2770 | 0.9291 |
| 0.2684 | 7.0 | 77 | 0.2553 | 0.9342 |
| 0.2579 | 8.0 | 88 | 0.2545 | 0.9338 |
| 0.2449 | 9.0 | 99 | 0.2403 | 0.9378 |
| 0.2322 | 10.0 | 110 | 0.2367 | 0.9379 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1