smids_10x_deit_small_adamax_00001_fold1
This model is a fine-tuned version of facebook/deit-small-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.8282
- Accuracy: 0.9065
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: 1e-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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2758 | 1.0 | 751 | 0.3168 | 0.8831 |
| 0.1955 | 2.0 | 1502 | 0.2645 | 0.9032 |
| 0.1342 | 3.0 | 2253 | 0.2464 | 0.9115 |
| 0.0581 | 4.0 | 3004 | 0.2670 | 0.9032 |
| 0.0977 | 5.0 | 3755 | 0.3303 | 0.9115 |
| 0.0404 | 6.0 | 4506 | 0.3924 | 0.9048 |
| 0.0407 | 7.0 | 5257 | 0.4392 | 0.9098 |
| 0.0229 | 8.0 | 6008 | 0.5277 | 0.9132 |
| 0.023 | 9.0 | 6759 | 0.5759 | 0.9115 |
| 0.016 | 10.0 | 7510 | 0.6280 | 0.9032 |
| 0.0002 | 11.0 | 8261 | 0.6513 | 0.9098 |
| 0.0008 | 12.0 | 9012 | 0.6409 | 0.9182 |
| 0.006 | 13.0 | 9763 | 0.6473 | 0.9199 |
| 0.0 | 14.0 | 10514 | 0.7396 | 0.9065 |
| 0.0 | 15.0 | 11265 | 0.7703 | 0.9065 |
| 0.0 | 16.0 | 12016 | 0.7534 | 0.9065 |
| 0.0001 | 17.0 | 12767 | 0.8086 | 0.9032 |
| 0.0 | 18.0 | 13518 | 0.7937 | 0.9032 |
| 0.0 | 19.0 | 14269 | 0.7606 | 0.9165 |
| 0.0 | 20.0 | 15020 | 0.8234 | 0.9065 |
| 0.0001 | 21.0 | 15771 | 0.7617 | 0.9149 |
| 0.0 | 22.0 | 16522 | 0.8024 | 0.9015 |
| 0.0 | 23.0 | 17273 | 0.8089 | 0.9065 |
| 0.0 | 24.0 | 18024 | 0.8495 | 0.9015 |
| 0.0 | 25.0 | 18775 | 0.7997 | 0.9115 |
| 0.0 | 26.0 | 19526 | 0.8566 | 0.9015 |
| 0.0 | 27.0 | 20277 | 0.8140 | 0.9065 |
| 0.0 | 28.0 | 21028 | 0.8138 | 0.9065 |
| 0.0073 | 29.0 | 21779 | 0.7958 | 0.9082 |
| 0.0 | 30.0 | 22530 | 0.8037 | 0.9115 |
| 0.0 | 31.0 | 23281 | 0.8741 | 0.9032 |
| 0.0 | 32.0 | 24032 | 0.8298 | 0.9082 |
| 0.0 | 33.0 | 24783 | 0.8730 | 0.9015 |
| 0.0 | 34.0 | 25534 | 0.8840 | 0.8982 |
| 0.0 | 35.0 | 26285 | 0.8051 | 0.9132 |
| 0.0 | 36.0 | 27036 | 0.8192 | 0.9115 |
| 0.0 | 37.0 | 27787 | 0.8059 | 0.9132 |
| 0.0 | 38.0 | 28538 | 0.8065 | 0.9149 |
| 0.0 | 39.0 | 29289 | 0.8139 | 0.9132 |
| 0.0 | 40.0 | 30040 | 0.8141 | 0.9132 |
| 0.0 | 41.0 | 30791 | 0.8317 | 0.9098 |
| 0.0 | 42.0 | 31542 | 0.8371 | 0.9048 |
| 0.0 | 43.0 | 32293 | 0.8394 | 0.9032 |
| 0.0 | 44.0 | 33044 | 0.8362 | 0.9048 |
| 0.0 | 45.0 | 33795 | 0.8367 | 0.9048 |
| 0.0 | 46.0 | 34546 | 0.8416 | 0.9032 |
| 0.0 | 47.0 | 35297 | 0.8349 | 0.9048 |
| 0.0 | 48.0 | 36048 | 0.8314 | 0.9065 |
| 0.0 | 49.0 | 36799 | 0.8317 | 0.9065 |
| 0.0 | 50.0 | 37550 | 0.8282 | 0.9065 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2