hushem_1x_deit_tiny_rms_lr00001_fold4
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: 0.6971
- Accuracy: 0.7619
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 | 1.1869 | 0.4762 |
| 1.3589 | 2.0 | 12 | 1.4321 | 0.2381 |
| 1.3589 | 3.0 | 18 | 0.8086 | 0.7143 |
| 0.7587 | 4.0 | 24 | 0.7860 | 0.6667 |
| 0.3552 | 5.0 | 30 | 0.6443 | 0.7143 |
| 0.3552 | 6.0 | 36 | 0.6345 | 0.7381 |
| 0.1624 | 7.0 | 42 | 0.6029 | 0.7381 |
| 0.1624 | 8.0 | 48 | 0.6145 | 0.6667 |
| 0.0655 | 9.0 | 54 | 0.6448 | 0.6905 |
| 0.0257 | 10.0 | 60 | 0.6084 | 0.7381 |
| 0.0257 | 11.0 | 66 | 0.5594 | 0.7143 |
| 0.0099 | 12.0 | 72 | 0.6088 | 0.7381 |
| 0.0099 | 13.0 | 78 | 0.6402 | 0.7619 |
| 0.0054 | 14.0 | 84 | 0.6319 | 0.7381 |
| 0.0038 | 15.0 | 90 | 0.6323 | 0.7619 |
| 0.0038 | 16.0 | 96 | 0.6432 | 0.7381 |
| 0.0029 | 17.0 | 102 | 0.6446 | 0.7381 |
| 0.0029 | 18.0 | 108 | 0.6470 | 0.7381 |
| 0.0023 | 19.0 | 114 | 0.6562 | 0.7381 |
| 0.002 | 20.0 | 120 | 0.6656 | 0.7381 |
| 0.002 | 21.0 | 126 | 0.6696 | 0.7381 |
| 0.0017 | 22.0 | 132 | 0.6739 | 0.7381 |
| 0.0017 | 23.0 | 138 | 0.6722 | 0.7619 |
| 0.0015 | 24.0 | 144 | 0.6705 | 0.7619 |
| 0.0014 | 25.0 | 150 | 0.6761 | 0.7619 |
| 0.0014 | 26.0 | 156 | 0.6768 | 0.7619 |
| 0.0012 | 27.0 | 162 | 0.6844 | 0.7619 |
| 0.0012 | 28.0 | 168 | 0.6843 | 0.7619 |
| 0.0012 | 29.0 | 174 | 0.6854 | 0.7619 |
| 0.0011 | 30.0 | 180 | 0.6913 | 0.7619 |
| 0.0011 | 31.0 | 186 | 0.6928 | 0.7619 |
| 0.001 | 32.0 | 192 | 0.6912 | 0.7619 |
| 0.001 | 33.0 | 198 | 0.6912 | 0.7619 |
| 0.001 | 34.0 | 204 | 0.6924 | 0.7619 |
| 0.0009 | 35.0 | 210 | 0.6912 | 0.7619 |
| 0.0009 | 36.0 | 216 | 0.6935 | 0.7619 |
| 0.0009 | 37.0 | 222 | 0.6948 | 0.7619 |
| 0.0009 | 38.0 | 228 | 0.6957 | 0.7619 |
| 0.0009 | 39.0 | 234 | 0.6966 | 0.7619 |
| 0.0009 | 40.0 | 240 | 0.6969 | 0.7619 |
| 0.0009 | 41.0 | 246 | 0.6971 | 0.7619 |
| 0.0009 | 42.0 | 252 | 0.6971 | 0.7619 |
| 0.0009 | 43.0 | 258 | 0.6971 | 0.7619 |
| 0.0008 | 44.0 | 264 | 0.6971 | 0.7619 |
| 0.0009 | 45.0 | 270 | 0.6971 | 0.7619 |
| 0.0009 | 46.0 | 276 | 0.6971 | 0.7619 |
| 0.0008 | 47.0 | 282 | 0.6971 | 0.7619 |
| 0.0008 | 48.0 | 288 | 0.6971 | 0.7619 |
| 0.0009 | 49.0 | 294 | 0.6971 | 0.7619 |
| 0.0009 | 50.0 | 300 | 0.6971 | 0.7619 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1