hushem_1x_deit_tiny_sgd_00001_fold5
This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.7419
- Accuracy: 0.2439
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 |
|---|---|---|---|---|
| No log | 1.0 | 6 | 1.7664 | 0.2439 |
| 1.7149 | 2.0 | 12 | 1.7652 | 0.2439 |
| 1.7149 | 3.0 | 18 | 1.7640 | 0.2439 |
| 1.7055 | 4.0 | 24 | 1.7627 | 0.2439 |
| 1.7032 | 5.0 | 30 | 1.7616 | 0.2439 |
| 1.7032 | 6.0 | 36 | 1.7604 | 0.2439 |
| 1.7195 | 7.0 | 42 | 1.7594 | 0.2439 |
| 1.7195 | 8.0 | 48 | 1.7584 | 0.2439 |
| 1.6458 | 9.0 | 54 | 1.7574 | 0.2439 |
| 1.7017 | 10.0 | 60 | 1.7564 | 0.2439 |
| 1.7017 | 11.0 | 66 | 1.7554 | 0.2439 |
| 1.7123 | 12.0 | 72 | 1.7545 | 0.2439 |
| 1.7123 | 13.0 | 78 | 1.7536 | 0.2439 |
| 1.6713 | 14.0 | 84 | 1.7528 | 0.2439 |
| 1.6849 | 15.0 | 90 | 1.7520 | 0.2439 |
| 1.6849 | 16.0 | 96 | 1.7512 | 0.2439 |
| 1.7051 | 17.0 | 102 | 1.7505 | 0.2439 |
| 1.7051 | 18.0 | 108 | 1.7498 | 0.2439 |
| 1.6541 | 19.0 | 114 | 1.7491 | 0.2439 |
| 1.7161 | 20.0 | 120 | 1.7484 | 0.2439 |
| 1.7161 | 21.0 | 126 | 1.7478 | 0.2439 |
| 1.6901 | 22.0 | 132 | 1.7472 | 0.2439 |
| 1.6901 | 23.0 | 138 | 1.7466 | 0.2439 |
| 1.6528 | 24.0 | 144 | 1.7461 | 0.2439 |
| 1.7234 | 25.0 | 150 | 1.7456 | 0.2439 |
| 1.7234 | 26.0 | 156 | 1.7451 | 0.2439 |
| 1.6839 | 27.0 | 162 | 1.7447 | 0.2439 |
| 1.6839 | 28.0 | 168 | 1.7443 | 0.2439 |
| 1.6859 | 29.0 | 174 | 1.7439 | 0.2439 |
| 1.6955 | 30.0 | 180 | 1.7436 | 0.2439 |
| 1.6955 | 31.0 | 186 | 1.7433 | 0.2439 |
| 1.7014 | 32.0 | 192 | 1.7430 | 0.2439 |
| 1.7014 | 33.0 | 198 | 1.7428 | 0.2439 |
| 1.6319 | 34.0 | 204 | 1.7426 | 0.2439 |
| 1.6586 | 35.0 | 210 | 1.7424 | 0.2439 |
| 1.6586 | 36.0 | 216 | 1.7422 | 0.2439 |
| 1.6897 | 37.0 | 222 | 1.7421 | 0.2439 |
| 1.6897 | 38.0 | 228 | 1.7420 | 0.2439 |
| 1.6863 | 39.0 | 234 | 1.7420 | 0.2439 |
| 1.6801 | 40.0 | 240 | 1.7419 | 0.2439 |
| 1.6801 | 41.0 | 246 | 1.7419 | 0.2439 |
| 1.7183 | 42.0 | 252 | 1.7419 | 0.2439 |
| 1.7183 | 43.0 | 258 | 1.7419 | 0.2439 |
| 1.6529 | 44.0 | 264 | 1.7419 | 0.2439 |
| 1.6913 | 45.0 | 270 | 1.7419 | 0.2439 |
| 1.6913 | 46.0 | 276 | 1.7419 | 0.2439 |
| 1.7139 | 47.0 | 282 | 1.7419 | 0.2439 |
| 1.7139 | 48.0 | 288 | 1.7419 | 0.2439 |
| 1.6464 | 49.0 | 294 | 1.7419 | 0.2439 |
| 1.6966 | 50.0 | 300 | 1.7419 | 0.2439 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0