hushem_5x_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: 1.0089
- Accuracy: 0.6889
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 |
|---|---|---|---|---|
| 1.2704 | 1.0 | 27 | 1.2632 | 0.3333 |
| 0.9284 | 2.0 | 54 | 1.1387 | 0.4 |
| 0.673 | 3.0 | 81 | 0.9948 | 0.5111 |
| 0.5262 | 4.0 | 108 | 0.8999 | 0.6222 |
| 0.3091 | 5.0 | 135 | 0.8487 | 0.5778 |
| 0.2356 | 6.0 | 162 | 0.7708 | 0.7333 |
| 0.1849 | 7.0 | 189 | 0.7590 | 0.7111 |
| 0.1256 | 8.0 | 216 | 0.7636 | 0.6889 |
| 0.0704 | 9.0 | 243 | 0.7602 | 0.6444 |
| 0.0451 | 10.0 | 270 | 0.7394 | 0.6667 |
| 0.0288 | 11.0 | 297 | 0.7424 | 0.7111 |
| 0.0167 | 12.0 | 324 | 0.7807 | 0.6667 |
| 0.0111 | 13.0 | 351 | 0.8113 | 0.6667 |
| 0.0073 | 14.0 | 378 | 0.8256 | 0.7111 |
| 0.006 | 15.0 | 405 | 0.8473 | 0.6889 |
| 0.0044 | 16.0 | 432 | 0.8545 | 0.6889 |
| 0.0038 | 17.0 | 459 | 0.8649 | 0.7111 |
| 0.0035 | 18.0 | 486 | 0.8829 | 0.6889 |
| 0.0029 | 19.0 | 513 | 0.8931 | 0.6889 |
| 0.0027 | 20.0 | 540 | 0.8979 | 0.6889 |
| 0.0022 | 21.0 | 567 | 0.9159 | 0.6889 |
| 0.0022 | 22.0 | 594 | 0.9078 | 0.6889 |
| 0.002 | 23.0 | 621 | 0.9310 | 0.6889 |
| 0.0018 | 24.0 | 648 | 0.9346 | 0.6889 |
| 0.0018 | 25.0 | 675 | 0.9373 | 0.6889 |
| 0.0017 | 26.0 | 702 | 0.9476 | 0.6889 |
| 0.0016 | 27.0 | 729 | 0.9510 | 0.6889 |
| 0.0014 | 28.0 | 756 | 0.9558 | 0.6889 |
| 0.0015 | 29.0 | 783 | 0.9590 | 0.6889 |
| 0.0013 | 30.0 | 810 | 0.9714 | 0.6889 |
| 0.0012 | 31.0 | 837 | 0.9702 | 0.6889 |
| 0.0012 | 32.0 | 864 | 0.9742 | 0.6889 |
| 0.0011 | 33.0 | 891 | 0.9800 | 0.6889 |
| 0.0011 | 34.0 | 918 | 0.9820 | 0.6889 |
| 0.0011 | 35.0 | 945 | 0.9877 | 0.6889 |
| 0.0011 | 36.0 | 972 | 0.9898 | 0.6889 |
| 0.001 | 37.0 | 999 | 0.9922 | 0.6889 |
| 0.001 | 38.0 | 1026 | 0.9935 | 0.6889 |
| 0.0009 | 39.0 | 1053 | 0.9969 | 0.6889 |
| 0.0009 | 40.0 | 1080 | 0.9993 | 0.6889 |
| 0.0009 | 41.0 | 1107 | 1.0018 | 0.6889 |
| 0.0009 | 42.0 | 1134 | 1.0033 | 0.6889 |
| 0.0009 | 43.0 | 1161 | 1.0054 | 0.6889 |
| 0.0009 | 44.0 | 1188 | 1.0069 | 0.6889 |
| 0.0009 | 45.0 | 1215 | 1.0080 | 0.6889 |
| 0.0009 | 46.0 | 1242 | 1.0085 | 0.6889 |
| 0.0009 | 47.0 | 1269 | 1.0088 | 0.6889 |
| 0.0009 | 48.0 | 1296 | 1.0089 | 0.6889 |
| 0.0009 | 49.0 | 1323 | 1.0089 | 0.6889 |
| 0.0009 | 50.0 | 1350 | 1.0089 | 0.6889 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0