<!-- 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. -->
my_classification
This model is a fine-tuned version of google/vit-base-patch16-224 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3033
- Accuracy: 0.7277
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 5.7973 | 1.0 | 175 | 4.2373 | 0.1537 |
| 3.3114 | 2.0 | 350 | 2.8087 | 0.4224 |
| 1.68 | 3.0 | 525 | 1.9823 | 0.5983 |
| 0.7776 | 4.0 | 700 | 1.6113 | 0.6648 |
| 0.3974 | 5.0 | 875 | 1.4166 | 0.6962 |
| 0.1666 | 6.0 | 1050 | 1.3312 | 0.7119 |
| 0.0657 | 7.0 | 1225 | 1.3033 | 0.7277 |
| 0.0315 | 8.0 | 1400 | 1.3021 | 0.7191 |
| 0.0187 | 9.0 | 1575 | 1.2946 | 0.7198 |
| 0.0146 | 10.0 | 1750 | 1.3018 | 0.7191 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
