smids_1x_deit_small_rms_00001_fold5
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: 0.9281
- Accuracy: 0.88
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 |
|---|---|---|---|---|
| 0.3852 | 1.0 | 75 | 0.3081 | 0.87 |
| 0.2965 | 2.0 | 150 | 0.3016 | 0.8733 |
| 0.1467 | 3.0 | 225 | 0.3200 | 0.8783 |
| 0.1384 | 4.0 | 300 | 0.3262 | 0.8833 |
| 0.0702 | 5.0 | 375 | 0.3415 | 0.8817 |
| 0.0486 | 6.0 | 450 | 0.4818 | 0.8817 |
| 0.0342 | 7.0 | 525 | 0.4838 | 0.8817 |
| 0.0455 | 8.0 | 600 | 0.6047 | 0.8717 |
| 0.0096 | 9.0 | 675 | 0.5775 | 0.8817 |
| 0.028 | 10.0 | 750 | 0.6719 | 0.875 |
| 0.0419 | 11.0 | 825 | 0.6284 | 0.8833 |
| 0.0004 | 12.0 | 900 | 0.6384 | 0.8817 |
| 0.0259 | 13.0 | 975 | 0.6301 | 0.875 |
| 0.03 | 14.0 | 1050 | 0.6619 | 0.8733 |
| 0.0082 | 15.0 | 1125 | 0.8292 | 0.8667 |
| 0.0001 | 16.0 | 1200 | 0.7120 | 0.88 |
| 0.005 | 17.0 | 1275 | 0.7140 | 0.8867 |
| 0.028 | 18.0 | 1350 | 0.8747 | 0.865 |
| 0.0095 | 19.0 | 1425 | 0.8049 | 0.8767 |
| 0.0001 | 20.0 | 1500 | 0.7748 | 0.8767 |
| 0.0085 | 21.0 | 1575 | 0.7202 | 0.885 |
| 0.0152 | 22.0 | 1650 | 0.8388 | 0.875 |
| 0.0057 | 23.0 | 1725 | 0.8400 | 0.8733 |
| 0.0001 | 24.0 | 1800 | 0.8934 | 0.8717 |
| 0.0082 | 25.0 | 1875 | 0.8430 | 0.8783 |
| 0.0001 | 26.0 | 1950 | 0.8852 | 0.8783 |
| 0.008 | 27.0 | 2025 | 0.8664 | 0.8767 |
| 0.0113 | 28.0 | 2100 | 0.8872 | 0.88 |
| 0.0078 | 29.0 | 2175 | 0.8576 | 0.8817 |
| 0.0049 | 30.0 | 2250 | 0.8872 | 0.88 |
| 0.0 | 31.0 | 2325 | 0.9217 | 0.8733 |
| 0.0 | 32.0 | 2400 | 0.8681 | 0.8833 |
| 0.0081 | 33.0 | 2475 | 0.9201 | 0.8783 |
| 0.0 | 34.0 | 2550 | 0.9023 | 0.8767 |
| 0.0058 | 35.0 | 2625 | 0.9043 | 0.8767 |
| 0.0 | 36.0 | 2700 | 0.9027 | 0.88 |
| 0.0029 | 37.0 | 2775 | 0.9082 | 0.88 |
| 0.0 | 38.0 | 2850 | 0.9260 | 0.8767 |
| 0.0 | 39.0 | 2925 | 0.9311 | 0.8783 |
| 0.0 | 40.0 | 3000 | 0.9195 | 0.8767 |
| 0.0028 | 41.0 | 3075 | 0.9229 | 0.8767 |
| 0.0 | 42.0 | 3150 | 0.9218 | 0.8783 |
| 0.0075 | 43.0 | 3225 | 0.9281 | 0.8767 |
| 0.0 | 44.0 | 3300 | 0.9291 | 0.8767 |
| 0.0025 | 45.0 | 3375 | 0.9268 | 0.8783 |
| 0.0 | 46.0 | 3450 | 0.9285 | 0.88 |
| 0.0049 | 47.0 | 3525 | 0.9282 | 0.88 |
| 0.0048 | 48.0 | 3600 | 0.9283 | 0.88 |
| 0.0 | 49.0 | 3675 | 0.9284 | 0.88 |
| 0.0043 | 50.0 | 3750 | 0.9281 | 0.88 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0