<!-- 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-prediction
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4297
- Accuracy: 0.9435
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.5255 | 0.99 | 23 | 2.4636 | 0.1962 |
| 2.3262 | 1.98 | 46 | 2.1597 | 0.4274 |
| 2.0029 | 2.97 | 69 | 1.8305 | 0.5403 |
| 1.558 | 4.0 | 93 | 1.5122 | 0.6640 |
| 1.3011 | 4.99 | 116 | 1.2433 | 0.7608 |
| 1.1253 | 5.98 | 139 | 1.0914 | 0.7957 |
| 0.9237 | 6.97 | 162 | 0.9167 | 0.8575 |
| 0.8187 | 8.0 | 186 | 0.8292 | 0.8575 |
| 0.7327 | 8.99 | 209 | 0.7518 | 0.8925 |
| 0.6148 | 9.98 | 232 | 0.7226 | 0.8737 |
| 0.5614 | 10.97 | 255 | 0.6537 | 0.9032 |
| 0.5541 | 12.0 | 279 | 0.5922 | 0.9274 |
| 0.5033 | 12.99 | 302 | 0.5969 | 0.9140 |
| 0.4829 | 13.98 | 325 | 0.5295 | 0.9247 |
| 0.4428 | 14.97 | 348 | 0.4993 | 0.9328 |
| 0.3965 | 16.0 | 372 | 0.4925 | 0.9382 |
| 0.3964 | 16.99 | 395 | 0.4996 | 0.9220 |
| 0.3957 | 17.98 | 418 | 0.4546 | 0.9435 |
| 0.3868 | 18.97 | 441 | 0.4281 | 0.9382 |
| 0.3824 | 19.78 | 460 | 0.4297 | 0.9435 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
