smids_5x_deit_small_rms_00001_fold4
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: 1.4091
- Accuracy: 0.8733
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 |
|---|---|---|---|---|
| 0.2357 | 1.0 | 375 | 0.3537 | 0.8617 |
| 0.1744 | 2.0 | 750 | 0.3961 | 0.8667 |
| 0.086 | 3.0 | 1125 | 0.5528 | 0.8517 |
| 0.0758 | 4.0 | 1500 | 0.6078 | 0.87 |
| 0.0324 | 5.0 | 1875 | 0.7790 | 0.8683 |
| 0.0181 | 6.0 | 2250 | 0.9636 | 0.855 |
| 0.0003 | 7.0 | 2625 | 0.8894 | 0.8633 |
| 0.0164 | 8.0 | 3000 | 1.0314 | 0.865 |
| 0.0386 | 9.0 | 3375 | 1.0455 | 0.87 |
| 0.0021 | 10.0 | 3750 | 1.0868 | 0.86 |
| 0.0004 | 11.0 | 4125 | 1.1036 | 0.8667 |
| 0.0001 | 12.0 | 4500 | 1.0921 | 0.8683 |
| 0.0451 | 13.0 | 4875 | 1.1416 | 0.865 |
| 0.0313 | 14.0 | 5250 | 1.1480 | 0.875 |
| 0.0 | 15.0 | 5625 | 1.2563 | 0.8617 |
| 0.0294 | 16.0 | 6000 | 1.1827 | 0.8683 |
| 0.0014 | 17.0 | 6375 | 1.1784 | 0.8683 |
| 0.0017 | 18.0 | 6750 | 1.2479 | 0.8633 |
| 0.0 | 19.0 | 7125 | 1.1339 | 0.8783 |
| 0.0 | 20.0 | 7500 | 1.1679 | 0.8783 |
| 0.0 | 21.0 | 7875 | 1.2344 | 0.8683 |
| 0.0027 | 22.0 | 8250 | 1.2529 | 0.8667 |
| 0.0001 | 23.0 | 8625 | 1.2449 | 0.865 |
| 0.0 | 24.0 | 9000 | 1.2744 | 0.865 |
| 0.0177 | 25.0 | 9375 | 1.2614 | 0.8717 |
| 0.0 | 26.0 | 9750 | 1.2469 | 0.8717 |
| 0.0 | 27.0 | 10125 | 1.3072 | 0.8667 |
| 0.0 | 28.0 | 10500 | 1.2917 | 0.8683 |
| 0.0 | 29.0 | 10875 | 1.2871 | 0.8767 |
| 0.0 | 30.0 | 11250 | 1.3156 | 0.8617 |
| 0.0 | 31.0 | 11625 | 1.2509 | 0.8767 |
| 0.0 | 32.0 | 12000 | 1.2613 | 0.8783 |
| 0.0 | 33.0 | 12375 | 1.3454 | 0.8683 |
| 0.0001 | 34.0 | 12750 | 1.2978 | 0.8667 |
| 0.0 | 35.0 | 13125 | 1.2980 | 0.8617 |
| 0.0 | 36.0 | 13500 | 1.2859 | 0.8683 |
| 0.0 | 37.0 | 13875 | 1.3447 | 0.8683 |
| 0.0044 | 38.0 | 14250 | 1.3496 | 0.87 |
| 0.0 | 39.0 | 14625 | 1.3716 | 0.8717 |
| 0.0 | 40.0 | 15000 | 1.3540 | 0.8733 |
| 0.0 | 41.0 | 15375 | 1.3616 | 0.8733 |
| 0.0 | 42.0 | 15750 | 1.3855 | 0.8717 |
| 0.0 | 43.0 | 16125 | 1.3813 | 0.8733 |
| 0.0 | 44.0 | 16500 | 1.4013 | 0.8717 |
| 0.0 | 45.0 | 16875 | 1.3939 | 0.875 |
| 0.0 | 46.0 | 17250 | 1.3982 | 0.875 |
| 0.0 | 47.0 | 17625 | 1.4014 | 0.875 |
| 0.0 | 48.0 | 18000 | 1.4060 | 0.8733 |
| 0.0 | 49.0 | 18375 | 1.4084 | 0.8733 |
| 0.0 | 50.0 | 18750 | 1.4091 | 0.8733 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2