<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
model_handwritenNumbers-nesanchezo
This model is a fine-tuned version of farleyknight-org-username/vit-base-mnist on the handwriten-Numbers dataset. It achieves the following results on the evaluation set:
- Loss: 0.0807
- Accuracy: 0.9839
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.396 | 0.34 | 500 | 0.1925 | 0.9470 |
0.2672 | 0.67 | 1000 | 0.2655 | 0.9297 |
0.2261 | 1.01 | 1500 | 0.1767 | 0.9548 |
0.1603 | 1.34 | 2000 | 0.1423 | 0.9658 |
0.1308 | 1.68 | 2500 | 0.1378 | 0.9709 |
0.1187 | 2.02 | 3000 | 0.1168 | 0.9737 |
0.0873 | 2.35 | 3500 | 0.0857 | 0.9823 |
0.0686 | 2.69 | 4000 | 0.1188 | 0.9753 |
0.0635 | 3.03 | 4500 | 0.0836 | 0.9804 |
0.034 | 3.36 | 5000 | 0.0807 | 0.9839 |
0.0155 | 3.7 | 5500 | 0.0898 | 0.9823 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3